diff --git a/.git-branches.toml b/.git-branches.toml index d1818090f..4c34d7928 100644 --- a/.git-branches.toml +++ b/.git-branches.toml @@ -3,7 +3,7 @@ [branches] main = "main" perennials = [] -perennial-regex = "" +perennial-regex = "^release-" [create] new-branch-type = "feature" diff --git a/.github/workflows/agent-network-e2e.yml b/.github/workflows/agent-network-e2e.yml index 88b98293d..9501c5fba 100644 --- a/.github/workflows/agent-network-e2e.yml +++ b/.github/workflows/agent-network-e2e.yml @@ -12,6 +12,13 @@ on: AWS issues it. Leave empty for the Sonnet 4.6 default. required: false default: "" + test_pattern: + description: >- + Package pattern to run. Defaults to the whole suite; narrow it to one + package (e.g. ./e2e/agentnetwork/...) when a run only needs that + package's answer and not the sixteen minutes the container suite costs. + required: false + default: "./e2e/..." concurrency: group: ${{ github.workflow }}-${{ github.ref }} @@ -77,4 +84,8 @@ jobs: GOOGLE_VERTEX_PROJECT: ${{ secrets.E2E_GOOGLE_VERTEX_PROJECT }} GOOGLE_VERTEX_REGION: ${{ secrets.E2E_GOOGLE_VERTEX_REGION }} GOOGLE_VERTEX_MODEL: ${{ secrets.E2E_GOOGLE_VERTEX_MODEL }} - run: go test -tags e2e -timeout 40m -v ./e2e/... + # Read through an env var rather than interpolated into the run + # script: a dispatch input reaching a shell command directly is a + # script-injection seam, however trusted the dispatcher. + TEST_PATTERN: ${{ inputs.test_pattern || './e2e/...' }} + run: go test -tags e2e -timeout 40m -v "$TEST_PATTERN" diff --git a/.github/workflows/check-license-dependencies.yml b/.github/workflows/check-license-dependencies.yml index 17c9fdc8d..81d293e4f 100644 --- a/.github/workflows/check-license-dependencies.yml +++ b/.github/workflows/check-license-dependencies.yml @@ -2,7 +2,7 @@ name: Check License Dependencies on: push: - branches: [main] + branches: [main, "release-*"] paths: - "go.mod" - "go.sum" diff --git a/.github/workflows/frontend-ui.yml b/.github/workflows/frontend-ui.yml index 552ccef29..014c5c2ae 100644 --- a/.github/workflows/frontend-ui.yml +++ b/.github/workflows/frontend-ui.yml @@ -10,6 +10,7 @@ on: push: branches: - main + - "release-*" paths: - "client/ui/frontend/**" - "client/ui/i18n/**" diff --git a/.github/workflows/golang-test-darwin.yml b/.github/workflows/golang-test-darwin.yml index 420749a0e..c17d8e775 100644 --- a/.github/workflows/golang-test-darwin.yml +++ b/.github/workflows/golang-test-darwin.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: concurrency: diff --git a/.github/workflows/golang-test-freebsd.yml b/.github/workflows/golang-test-freebsd.yml index 9c795e783..65c39147a 100644 --- a/.github/workflows/golang-test-freebsd.yml +++ b/.github/workflows/golang-test-freebsd.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: concurrency: diff --git a/.github/workflows/golang-test-linux.yml b/.github/workflows/golang-test-linux.yml index 0af506bba..004b78b3e 100644 --- a/.github/workflows/golang-test-linux.yml +++ b/.github/workflows/golang-test-linux.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: concurrency: diff --git a/.github/workflows/golang-test-windows.yml b/.github/workflows/golang-test-windows.yml index 50a5ba4d6..fb7b745d2 100644 --- a/.github/workflows/golang-test-windows.yml +++ b/.github/workflows/golang-test-windows.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: env: diff --git a/.github/workflows/install-script-test.yml b/.github/workflows/install-script-test.yml index 1514caedc..61709501c 100644 --- a/.github/workflows/install-script-test.yml +++ b/.github/workflows/install-script-test.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: paths: - "release_files/install.sh" diff --git a/.github/workflows/mobile-build-validation.yml b/.github/workflows/mobile-build-validation.yml deleted file mode 100644 index 44e912c73..000000000 --- a/.github/workflows/mobile-build-validation.yml +++ /dev/null @@ -1,71 +0,0 @@ -name: Mobile - -on: - push: - branches: - - main - pull_request: - -concurrency: - group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }} - cancel-in-progress: true - -jobs: - android_build: - name: "Android / Build" - runs-on: ubuntu-latest - steps: - - name: Checkout repository - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 - with: - persist-credentials: false - - name: Install Go - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0 - with: - go-version-file: "go.mod" - - name: Setup Android SDK - uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1 - with: - cmdline-tools-version: 8512546 - - name: Setup Java - uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520 - with: - java-version: "11" - distribution: "adopt" - - name: NDK Cache - id: ndk-cache - uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0 - with: - path: /usr/local/lib/android/sdk/ndk - key: ndk-cache-23.1.7779620 - - name: Setup NDK - run: /usr/local/lib/android/sdk/cmdline-tools/7.0/bin/sdkmanager --install "ndk;23.1.7779620" - - name: install gomobile - run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20251113184115-a159579294ab - - name: gomobile init - run: gomobile init - - name: build android netbird lib - run: PATH=$PATH:$(go env GOPATH) gomobile bind -o $GITHUB_WORKSPACE/netbird.aar -javapkg=io.netbird.gomobile -ldflags="-checklinkname=0 -X golang.zx2c4.com/wireguard/ipc.socketDirectory=/data/data/io.netbird.client/cache/wireguard -X github.com/netbirdio/netbird/version.version=buildtest" $GITHUB_WORKSPACE/client/android - env: - CGO_ENABLED: 0 - ANDROID_NDK_HOME: /usr/local/lib/android/sdk/ndk/23.1.7779620 - ios_build: - name: "iOS / Build" - runs-on: macos-latest - steps: - - name: Checkout repository - uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 - with: - persist-credentials: false - - name: Install Go - uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0 - with: - go-version-file: "go.mod" - - name: install gomobile - run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20251113184115-a159579294ab - - name: gomobile init - run: gomobile init - - name: build iOS netbird lib - run: PATH=$PATH:$(go env GOPATH) gomobile bind -target=ios -bundleid=io.netbird.framework -ldflags="-X github.com/netbirdio/netbird/version.version=buildtest" -o ./NetBirdSDK.xcframework ./client/ios/NetBirdSDK - env: - CGO_ENABLED: 0 diff --git a/.github/workflows/no-new-replace.yml b/.github/workflows/no-new-replace.yml new file mode 100644 index 000000000..b906ce450 --- /dev/null +++ b/.github/workflows/no-new-replace.yml @@ -0,0 +1,78 @@ +name: No New Replace Directives + +on: + pull_request: + paths: + - "go.mod" + +permissions: + contents: read + +concurrency: + group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }} + cancel-in-progress: true + +jobs: + check-replace-directives: + name: check-replace-directives + runs-on: ubuntu-latest + steps: + - name: Checkout code + uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0 + with: + persist-credentials: false + fetch-depth: 0 + + - name: Install Go + uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0 + with: + go-version-file: go.mod + + - name: Compare replace directives against the base branch + env: + BASE_SHA: ${{ github.event.pull_request.base.sha }} + run: | + set -euo pipefail + + # A replace directive only applies when this module is the main + # module. Anything importing netbird as a library, the embedded + # clients among them, resolves the replaced path upstream instead and + # fails to build against whatever the replacement provides. Requiring + # a fork under its own module path avoids that; a replace does not. + # + # go.mod is parsed rather than diffed so that reordering, comments and + # single-line versus block syntax do not register as changes. + # + # Versions are part of the key because a replace can be scoped to one + # version of a module. Keyed on paths alone, retargeting such a + # directive at a different version would read as unchanged. + list_replaces() { + go mod edit -json "$1" \ + | jq -r ' + def ref: .Path + (if (.Version // "") == "" then "" else " " + .Version end); + (.Replace // [])[] | "\(.Old | ref) => \(.New | ref)" + ' \ + | sort + } + + git show "${BASE_SHA}:go.mod" > /tmp/base-go.mod + list_replaces /tmp/base-go.mod > /tmp/base-replaces + list_replaces go.mod > /tmp/head-replaces + + added=$(comm -13 /tmp/base-replaces /tmp/head-replaces) + if [ -n "$added" ]; then + echo "::error::This PR adds a replace directive to go.mod:" + echo "$added" | sed 's/^/ /' + echo "" + echo "A replace directive applies only to the main module, so it does not" + echo "reach anything that imports netbird as a library. Require the module" + echo "under a path you control instead, as done for github.com/netbirdio/go-nat." + exit 1 + fi + + removed=$(comm -23 /tmp/base-replaces /tmp/head-replaces) + if [ -n "$removed" ]; then + echo "This PR removes replace directives:" + echo "$removed" | sed 's/^/ /' + fi + echo "No new replace directives." diff --git a/.github/workflows/release.yml b/.github/workflows/release.yml index 727bff45a..4d1945451 100644 --- a/.github/workflows/release.yml +++ b/.github/workflows/release.yml @@ -6,6 +6,7 @@ on: - "v*" branches: - main + - "release-*" pull_request: env: @@ -254,15 +255,23 @@ jobs: id: tag_and_push_images if: | (github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository) || - (github.event_name == 'push' && github.ref == 'refs/heads/main') + (github.event_name == 'push' && (github.ref == 'refs/heads/main' || startsWith(github.ref, 'refs/heads/release-'))) run: | set -euo pipefail + # $GITHUB_REF / $GITHUB_EVENT_NAME are read from the runner + # environment rather than substituted into this script with the + # workflow expression syntax: branch names may legally contain + # $(…), and interpolating github.ref would execute it. resolve_tags() { - if [[ "${{ github.event_name }}" == "pull_request" ]]; then + if [[ "$GITHUB_EVENT_NAME" == "pull_request" ]]; then echo "pr-${{ github.event.pull_request.number }}" - else + elif [[ "$GITHUB_REF" == "refs/heads/main" ]]; then echo "main sha-$(git rev-parse --short HEAD)" + else + # Release branches get an immutable sha-* tag only — the floating + # "main" tag must never move from a release branch. + echo "sha-$(git rev-parse --short HEAD)" fi } diff --git a/.github/workflows/sync-tag.yml b/.github/workflows/sync-tag.yml index d99f88b54..088e538d5 100644 --- a/.github/workflows/sync-tag.yml +++ b/.github/workflows/sync-tag.yml @@ -9,21 +9,9 @@ concurrency: group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }} cancel-in-progress: true -# Receiving workflows (cloud sync-tag, mobile bump-netbird) expect the short -# tag form (e.g. v0.30.0), not refs/tags/v0.30.0 — github.ref_name, not github.ref. +# The receiving bump-netbird workflows expect the short tag form +# (e.g. v0.30.0), not refs/tags/v0.30.0 — github.ref_name, not github.ref. jobs: - trigger_sync_tag: - runs-on: ubuntu-latest - steps: - - name: Trigger release tag sync - uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2 - with: - workflow: sync-tag.yml - ref: main - repo: ${{ secrets.UPSTREAM_REPO }} - token: ${{ secrets.NC_GITHUB_TOKEN }} - inputs: '{ "tag": "${{ github.ref_name }}" }' - trigger_android_bump: runs-on: ubuntu-latest if: github.event.created && !github.event.deleted && startsWith(github.ref, 'refs/tags/v') && !contains(github.ref_name, '-') diff --git a/.github/workflows/test-infrastructure-files.yml b/.github/workflows/test-infrastructure-files.yml index 729214d9e..1313379ee 100644 --- a/.github/workflows/test-infrastructure-files.yml +++ b/.github/workflows/test-infrastructure-files.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: paths: - "infrastructure_files/**" diff --git a/.github/workflows/ui-translations.yml b/.github/workflows/ui-translations.yml new file mode 100644 index 000000000..7d3b12f2d --- /dev/null +++ b/.github/workflows/ui-translations.yml @@ -0,0 +1,42 @@ +name: UI Translations + +on: + pull_request: + paths: + - "client/ui/i18n/locales/**" + - "client/ui/i18n/check-translations.mjs" + - ".github/workflows/ui-translations.yml" + push: + branches: + - main + paths: + - "client/ui/i18n/locales/**" + - "client/ui/i18n/check-translations.mjs" + +permissions: + contents: read + +concurrency: + group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }} + cancel-in-progress: true + +jobs: + check-translations: + name: Check translation key parity + runs-on: ubuntu-latest + timeout-minutes: 5 + steps: + - name: Checkout repository + uses: actions/checkout@de0fac2e4500dabe0009e67214ff5f5447ce83dd # v6.0.2 + with: + persist-credentials: false + + - name: Set up Node.js + uses: actions/setup-node@v4 + with: + node-version: "22" + + # English (en) is the source of truth for translation keys; every other + # locale declared in _index.json must carry the exact same key set. + - name: Check translation key parity + run: node client/ui/i18n/check-translations.mjs diff --git a/.github/workflows/wasm-build-validation.yml b/.github/workflows/wasm-build-validation.yml index e8a12cdaf..5f21472e5 100644 --- a/.github/workflows/wasm-build-validation.yml +++ b/.github/workflows/wasm-build-validation.yml @@ -4,6 +4,7 @@ on: push: branches: - main + - "release-*" pull_request: concurrency: diff --git a/.goreleaser.yaml b/.goreleaser.yaml index 8dd05a192..c5d260376 100644 --- a/.goreleaser.yaml +++ b/.goreleaser.yaml @@ -468,6 +468,13 @@ checksum: - glob: ./infrastructure_files/migrate-to-enterprise.sh release: + # The signing pipeline (netbirdio/sign-pipelines, dispatched by + # trigger_signer) marks the release latest once the Windows and macOS + # artifacts are signed. Without this override goreleaser marks it latest + # at publish time, while those artifacts are still unsigned. + make_latest: false + # Mark x.y.z-rc.* and other prerelease tags as prereleases on GitHub. + prerelease: auto extra_files: - glob: ./infrastructure_files/getting-started-with-zitadel.sh - glob: ./release_files/install.sh diff --git a/.goreleaser_ui.yaml b/.goreleaser_ui.yaml index ca5148823..1c5bc41ac 100644 --- a/.goreleaser_ui.yaml +++ b/.goreleaser_ui.yaml @@ -96,6 +96,7 @@ nfpms: - netbird (>= 0.75.0) - libgtk-4-1 (>= 4.14) - libwebkitgtk-6.0-4 + - xdg-utils - maintainer: Netbird description: Netbird client UI. @@ -119,6 +120,7 @@ nfpms: - netbird >= 0.75.0 - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14) - (webkitgtk6.0 or libwebkitgtk-6_0-4) + - xdg-utils rpm: signature: @@ -142,3 +144,11 @@ uploads: target: https://pkgs.wiretrustee.com/yum/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }} username: dev@wiretrustee.com method: PUT + +release: + # Uploads into the release created by the main .goreleaser.yaml run. + # make_latest stays false everywhere: the signing pipeline + # (netbirdio/sign-pipelines) marks the release latest after the Windows + # and macOS artifacts are signed. + make_latest: false + prerelease: auto diff --git a/.goreleaser_ui_darwin.yaml b/.goreleaser_ui_darwin.yaml index 47b991344..8ca0e8da6 100644 --- a/.goreleaser_ui_darwin.yaml +++ b/.goreleaser_ui_darwin.yaml @@ -43,3 +43,11 @@ checksum: name_template: "{{ .ProjectName }}_darwin_checksums.txt" changelog: disable: true + +release: + # Uploads into the release created by the main .goreleaser.yaml run. + # make_latest stays false everywhere: the signing pipeline + # (netbirdio/sign-pipelines) marks the release latest after the Windows + # and macOS artifacts are signed. + make_latest: false + prerelease: auto diff --git a/.goreleaser_ui_gtk3.yaml b/.goreleaser_ui_gtk3.yaml index d0a7de6e2..a9b2ca650 100644 --- a/.goreleaser_ui_gtk3.yaml +++ b/.goreleaser_ui_gtk3.yaml @@ -43,19 +43,17 @@ archives: - netbird-ui-gtk3 nfpms: - # Same package_name as the GTK4 packages -- the two are mutually-exclusive - # alternatives served from separate repo paths (see uploads below); a given - # distro points at exactly one of them. The file names must still differ: - # the Debian pool is shared storage keyed by file name, so a default-named - # gtk3 .deb would overwrite the stable one. + # Mutually-exclusive alternative to the GTK4 netbird-ui package -- both + # ship the same /usr/bin/netbird-ui from the shared stable/yum repos, so + # this one carries its own name and conflicts with the GTK4 package. - maintainer: Netbird description: Netbird client UI. homepage: https://netbird.io/ license: BSD-3-Clause vendor: NetBird id: netbird_ui_deb_gtk3 - package_name: netbird-ui - file_name_template: "{{ .PackageName }}-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}" + package_name: netbird-ui-gtk3 + file_name_template: "{{ .PackageName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}" builds: - netbird-ui-gtk3 formats: @@ -67,10 +65,15 @@ nfpms: dst: /usr/share/applications/org.wails.netbird.desktop - src: client/ui/build/appicon.png dst: /usr/share/pixmaps/netbird.png + conflicts: + - netbird-ui + replaces: + - netbird-ui dependencies: - netbird (>= 0.75.0) - libgtk-3-0 - libwebkit2gtk-4.1-0 + - xdg-utils - maintainer: Netbird description: Netbird client UI. @@ -78,8 +81,8 @@ nfpms: license: BSD-3-Clause vendor: NetBird id: netbird_ui_rpm_gtk3 - package_name: netbird-ui - file_name_template: "{{ .PackageName }}-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}" + package_name: netbird-ui-gtk3 + file_name_template: "{{ .PackageName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}" builds: - netbird-ui-gtk3 formats: @@ -91,10 +94,15 @@ nfpms: dst: /usr/share/applications/org.wails.netbird.desktop - src: client/ui/build/appicon.png dst: /usr/share/pixmaps/netbird.png + # No `replaces` here: nfpm maps it to rpm Obsoletes, which would make + # dnf swap installed GTK4 netbird-ui packages for this one on upgrade. + conflicts: + - netbird-ui dependencies: - netbird >= 0.75.0 - (gtk3 or libgtk-3-0) - (webkit2gtk4.1 or libwebkit2gtk-4_1-0) + - xdg-utils rpm: signature: @@ -109,23 +117,28 @@ changelog: disable: true uploads: - # The gtk3 packages reuse the netbird-ui package name, so they live in - # dedicated repo paths (deb distribution `gtk3`, yum path `yum-gtk3`) that - # legacy distros point their repo config at. - - name: debian-gtk3 + - name: debian skip: "{{ .Env.SKIP_PUBLISH }}" ids: - netbird_ui_deb_gtk3 mode: archive - target: https://pkgs.wiretrustee.com/debian/pool/{{ .ArtifactName }};deb.distribution=gtk3;deb.component=main;deb.architecture={{ if .Arm }}armhf{{ else }}{{ .Arch }}{{ end }};deb.package= + target: https://pkgs.wiretrustee.com/debian/pool/{{ .ArtifactName }};deb.distribution=stable;deb.component=main;deb.architecture={{ if .Arm }}armhf{{ else }}{{ .Arch }}{{ end }};deb.package= username: dev@wiretrustee.com method: PUT - - name: yum-gtk3 + - name: yum skip: "{{ .Env.SKIP_PUBLISH }}" ids: - netbird_ui_rpm_gtk3 mode: archive - target: https://pkgs.wiretrustee.com/yum-gtk3/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }} + target: https://pkgs.wiretrustee.com/yum/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }} username: dev@wiretrustee.com method: PUT + +release: + # Uploads into the release created by the main .goreleaser.yaml run. + # make_latest stays false everywhere: the signing pipeline + # (netbirdio/sign-pipelines) marks the release latest after the Windows + # and macOS artifacts are signed. + make_latest: false + prerelease: auto diff --git a/AGENTS.md b/AGENTS.md index 95b02a91d..5497acb15 100644 --- a/AGENTS.md +++ b/AGENTS.md @@ -1,6 +1,6 @@ # NetBird Agent Guidelines -**NetBird** is an open-source connectivity platform: a WireGuard®-based overlay +**NetBird** is an open source connectivity platform: a WireGuard®-based overlay network with a control plane. The **agent** (`client/`) runs on user machines as a privileged daemon and manages the WireGuard interface, routing, firewall, and DNS. **Management** (`management/`) is the control plane and REST/gRPC API, diff --git a/CONTRIBUTING.md b/CONTRIBUTING.md index db5097a48..9dea37ec8 100644 --- a/CONTRIBUTING.md +++ b/CONTRIBUTING.md @@ -112,6 +112,7 @@ aligns with our security standards and design expectations. - [Test suite](#test-suite) - [Checklist before submitting a PR](#checklist-before-submitting-a-pr) - [When we close a PR](#when-we-close-a-pr) + - [Translations](#translations) - [Other project repositories](#other-project-repositories) - [Contributor License Agreement](#contributor-license-agreement) @@ -478,7 +479,7 @@ go test -race ./client/internal/dns/... ## Checklist before submitting a PR -As a critical network service and open-source project, we must enforce a few +As a critical network service and open source project, we must enforce a few things before submitting a pull request. The [pull request template](/.github/pull_request_template.md) mirrors this list — fill it in rather than deleting it. @@ -612,6 +613,17 @@ A closed PR is not a rejected idea. Take it back to the [discussion](https://github.com/netbirdio/netbird/discussions), settle the approach, and reopen the work from there. +## Translations + +Desktop UI translations are not contributed through pull requests. Translate on +[Crowdin](https://crowdin.com/project/netbird) instead: no ticket needed, just +join the project and pick your language. Crowdin syncs with this repository and +opens the service PRs itself, so hand-edited locale files would conflict with +the next sync. Style, terminology, and review guidance live in +[client/ui/i18n/TRANSLATING.md](client/ui/i18n/TRANSLATING.md). To request a +language the project does not offer yet, ask on the Crowdin project page or in +a [discussion](https://github.com/netbirdio/netbird/discussions). + ## Other project repositories NetBird project is composed of 3 main repositories: diff --git a/README.md b/README.md index 40c6b9ed5..3bcb4a035 100644 --- a/README.md +++ b/README.md @@ -130,7 +130,7 @@ In November 2022, NetBird joined the [StartUpSecure program](https://www.forschu ![CISPA_Logo_BLACK_EN_RZ_RGB (1)](https://user-images.githubusercontent.com/700848/203091324-c6d311a0-22b5-4b05-a288-91cbc6cdcc46.png) ### Acknowledgements -We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing). +We build on open source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing). ### Legal This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/. diff --git a/SECURITY.md b/SECURITY.md index bdf88d670..cbcc975ba 100644 --- a/SECURITY.md +++ b/SECURITY.md @@ -14,7 +14,7 @@ Report security issues one of these two ways: on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place. - **Email** — `security@netbird.io`. -If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than +If the finding affects NetBird Cloud or our hosted infrastructure rather than the open source code, email us rather than filing a repository report. ### What to include diff --git a/agent-network/README.md b/agent-network/README.md index 1997ea299..5211fe8f9 100644 --- a/agent-network/README.md +++ b/agent-network/README.md @@ -40,6 +40,35 @@ You can then use this private endpoint to configure your AI agents, whether that Full step-by-step setup: **https://docs.netbird.io/agent-network/quickstart** +## Client settings that don't follow the endpoint + +Most of an agent's traffic follows the base URL you hand it, but a few +client-side checks call their vendor directly and never reach the proxy. On a +network that blocks direct egress they fail even though inference works, so +they are worth setting once when you roll the endpoint out. + +For Claude Code: + +- **Fast mode** checks availability against `api.anthropic.com` rather than the + configured base URL. Set `CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK=1` when the + agent authenticates with `ANTHROPIC_AUTH_TOKEN` alone (the usual shape when + the proxy injects the real provider key) or when a TLS-inspecting proxy + answers the check itself. Set + `CLAUDE_CODE_SKIP_FAST_MODE_NETWORK_ERRORS=1` when the network refuses the + connection outright. Fast mode is an Anthropic-API feature, so it is + unavailable on a Bedrock- or Vertex-backed endpoint whatever you set. +- **Model discovery** is off by default. Set + `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1` for the picker to list the + models your policies authorise; the proxy filters the response to that set. + The client gives discovery a three-second budget and treats any redirect as + a failure, so the endpoint must serve `/v1/models` directly. +- **The WebFetch domain safety check** also calls `api.anthropic.com` directly + and is unaffected by the variables above. + +Allowing direct egress to `api.anthropic.com` covers the network cases but not +the credential one, where the check reaches Anthropic and is rejected because +the agent presents a proxy-issued key. + ## Architecture Agent Network is built on two existing NetBird capabilities: diff --git a/client/android/client.go b/client/android/client.go index 3eab7af70..234201191 100644 --- a/client/android/client.go +++ b/client/android/client.go @@ -15,6 +15,7 @@ import ( log "github.com/sirupsen/logrus" + nbAnonymize "github.com/netbirdio/netbird/client/anonymize" "github.com/netbirdio/netbird/client/iface/device" "github.com/netbirdio/netbird/client/internal" "github.com/netbirdio/netbird/client/internal/debug" @@ -26,6 +27,8 @@ import ( "github.com/netbirdio/netbird/client/internal/stdnet" "github.com/netbirdio/netbird/client/mdm" "github.com/netbirdio/netbird/client/net" + "github.com/netbirdio/netbird/client/netstate" + "github.com/netbirdio/netbird/client/netsweep" "github.com/netbirdio/netbird/client/system" "github.com/netbirdio/netbird/formatter" "github.com/netbirdio/netbird/route" @@ -33,10 +36,12 @@ import ( types "github.com/netbirdio/netbird/upload-server/types" ) -// ConnectionListener export internal Listener for mobile -type ConnectionListener interface { - peer.Listener -} +// AnonymizeLevelDefault and AnonymizeLevelStrict are the accepted +// anonymizeLevel values for DebugBundle. +const ( + AnonymizeLevelDefault = nbAnonymize.LevelDefaultString + AnonymizeLevelStrict = nbAnonymize.LevelStrictString +) // TunAdapter export internal TunAdapter for mobile type TunAdapter interface { @@ -78,6 +83,13 @@ type Client struct { deviceName string uiVersion string networkChangeListener listener.NetworkChangeListener + // netState outlives engine restarts: it mirrors the OS connectivity, not + // the engine lifecycle. Run and RunWithoutLogin inject it into each new + // ConnectClient, which distributes it to every reconnection loop. + netState *netstate.State + + // sweeper also outlives engine restarts; NotifyNetworkChange sweeps it. + sweeper *netsweep.Sweeper stateMu sync.RWMutex connectClient *internal.ConnectClient @@ -149,6 +161,7 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd execWorkaround(androidSDKVersion) net.SetAndroidProtectSocketFn(tunAdapter.ProtectSocket) + system.SetIFaceDiscover(iFaceDiscover) return &Client{ deviceName: deviceName, uiVersion: uiVersion, @@ -157,6 +170,8 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd recorder: peer.NewRecorder(""), ctxCancelLock: &sync.Mutex{}, networkChangeListener: networkChangeListener, + netState: netstate.New(), + sweeper: netsweep.New(), } } @@ -198,7 +213,8 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid } // todo do not throw error in case of cancelled context ctx = internal.CtxInitState(ctx) - connectClient := internal.NewConnectClient(ctx, cfg, c.recorder) + connectClient := internal.NewConnectClient(ctx, cfg, c.recorder, + internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper)) c.setState(cfg, cacheDir, cfgFile, connectClient) // This path runs the interactive SSO flow, so reaching here means the peer // is authenticated again — release the latch Status() reports from. Clear @@ -240,7 +256,8 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR // todo do not throw error in case of cancelled context ctx = internal.CtxInitState(ctx) - connectClient := internal.NewConnectClient(ctx, cfg, c.recorder) + connectClient := internal.NewConnectClient(ctx, cfg, c.recorder, + internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper)) c.setState(cfg, cacheDir, cfgFile, connectClient) return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir) } @@ -288,9 +305,29 @@ func (c *Client) GetTunSettings() (*TunSettings, error) { }, nil } +// SetNetworkAvailable feeds OS-reported network availability into the client. +// While unavailable, the internal reconnect loops suspend their attempts and +// the connection listener reports NoNetwork instead of Connecting; when +// availability returns, the loops resume immediately with a fresh backoff. +func (c *Client) SetNetworkAvailable(available bool) { + c.netState.Set(available) + c.recorder.SetNetworkAvailable(available) +} + +// NotifyNetworkChange marks the management, signal and relay connections +// stale after the OS switched networks and schedules a sweep that cuts +// whatever has not redialed on the new network by then. The engine and the +// TUN device stay untouched. +func (c *Client) NotifyNetworkChange() { + c.sweeper.MarkNetworkChange() + log.Infof("network change: connections marked stale") +} + // DebugBundle generates a debug bundle, uploads it, and returns the upload key. -// It works both with and without a running engine. -func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (string, error) { +// It works both with and without a running engine. anonymizeLevel is "default" +// or "strict"; strict also anonymizes internal IP ranges, peer names, and +// WireGuard public keys, and implies anonymize. +func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool, anonymizeLevel string) (string, error) { cfg, cacheDir, cc := c.stateSnapshot() // If the engine hasn't been started, load config from disk @@ -310,6 +347,7 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin InternalConfig: cfg, StatusRecorder: c.recorder, TempDir: cacheDir, + StatePath: platformFiles.StateFilePath(), } if cc != nil { @@ -333,6 +371,7 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin deps, debug.BundleConfig{ Anonymize: anonymize, + AnonymizeLevel: nbAnonymize.ParseLevel(anonymizeLevel), IncludeSystemInfo: true, }, ) @@ -525,7 +564,11 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error { // SetConnectionListener set the network connection listener func (c *Client) SetConnectionListener(listener ConnectionListener) { - c.recorder.SetConnectionListener(listener) + if listener == nil { + c.recorder.RemoveConnectionListener() + return + } + c.recorder.SetConnectionListener(connectionListenerAdapter{listener}) } // RemoveConnectionListener remove connection listener diff --git a/client/android/connection_listener.go b/client/android/connection_listener.go new file mode 100644 index 000000000..77c47574b --- /dev/null +++ b/client/android/connection_listener.go @@ -0,0 +1,41 @@ +//go:build android + +package android + +import ( + "github.com/netbirdio/netbird/client/internal/peer" +) + +// Client state values delivered via ConnectionListener.OnStateChanged, +// re-exported as basic constants so gomobile emits them into the generated +// Java bindings. They mirror peer.ClientState*: append-only, never reorder. +const ( + ClientStateDisconnected = int(peer.ClientStateDisconnected) + ClientStateConnected = int(peer.ClientStateConnected) + ClientStateConnecting = int(peer.ClientStateConnecting) + ClientStateDisconnecting = int(peer.ClientStateDisconnecting) + ClientStateNoNetwork = int(peer.ClientStateNoNetwork) +) + +// ConnectionListener export internal Listener for mobile. It mirrors +// peer.Listener with OnStateChanged taking a plain int (one of the +// ClientState* constants), because gomobile cannot bind named types. +type ConnectionListener interface { + OnStateChanged(state int) + OnConnected() + OnDisconnected() + OnConnecting() + OnDisconnecting() + OnAddressChanged(string, string) + OnPeersListChanged(int) +} + +// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to +// peer.Listener, converting the typed state to the int the binding carries. +type connectionListenerAdapter struct { + ConnectionListener +} + +func (a connectionListenerAdapter) OnStateChanged(state peer.ClientState) { + a.ConnectionListener.OnStateChanged(int(state)) +} diff --git a/client/android/login.go b/client/android/login.go index 3f367b97f..24c911eb5 100644 --- a/client/android/login.go +++ b/client/android/login.go @@ -191,39 +191,49 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error { return nil } -// loginHintSetter is implemented by both concrete flows (PKCE and device code) -// but absent from the OAuthFlow interface, hence the assertion below — the same -// way internal/auth wires it in authenticateWithPKCEFlow. -type loginHintSetter interface { - SetLoginHint(hint string) -} - func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, isAndroidTV bool) (*auth.TokenInfo, error) { - oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV) + oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV, profileLoginHint(a.cfgPath)) if err != nil { return nil, fmt.Errorf("failed to get OAuth flow: %v", err) } - // An empty hint is deliberate, not a fallback: a fresh or logged-out profile - // leaves the choice to the IdP, which is how accounts get switched. - if a.cfgPath != "" { - if hint := readProfileEmail(a.cfgPath); hint != "" { - if setter, ok := oAuthFlow.(loginHintSetter); ok { - setter.SetLoginHint(hint) - } - } + return runOAuthFlow(a.ctx, oAuthFlow, urlOpener, nil) +} + +// profileLoginHint returns the stored account email for the profile at cfgPath. +// An empty hint is deliberate, not a fallback: a fresh profile leaves the +// choice to the IdP. Switching accounts is done by switching or removing +// profiles, not by logging out — logout keeps the email. +func profileLoginHint(cfgPath string) string { + if cfgPath == "" { + return "" + } + return readProfileEmail(cfgPath) +} + +// runOAuthFlow drives an already acquired OAuth flow to a token: requests the +// flow info, presents the verification URL through the opener and waits for +// the browser round-trip. Open is called synchronously — it is what marks the +// surface as opened on the client side, and a fast token's OnLoginSuccess is +// a no-op until it has, so the dismissal would be dropped rather than +// delayed. Openers must therefore not block: they post their UI work and +// return. onWaiting, when set, runs after the URL is shown, right before the +// blocking wait. +func runOAuthFlow(ctx context.Context, flow auth.OAuthFlow, urlOpener URLOpener, onWaiting func()) (*auth.TokenInfo, error) { + flowInfo, err := flow.RequestAuthInfo(ctx) + if err != nil { + return nil, fmt.Errorf("request auth info: %w", err) } - flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO()) - if err != nil { - return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err) + urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode) + + if onWaiting != nil { + onWaiting() } - go urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode) - - tokenInfo, err := oAuthFlow.WaitToken(a.ctx, flowInfo) + tokenInfo, err := flow.WaitToken(ctx, flowInfo) if err != nil { - return nil, fmt.Errorf("waiting for browser login failed: %v", err) + return nil, fmt.Errorf("wait for token: %w", err) } return &tokenInfo, nil diff --git a/client/android/profile_manager.go b/client/android/profile_manager.go index 3197124d7..20d585d6a 100644 --- a/client/android/profile_manager.go +++ b/client/android/profile_manager.go @@ -22,7 +22,8 @@ type Profile struct { ID string Name string // Email is the account this profile last logged in with, "" if it never - // completed an SSO login or was logged out. See profile_state.go. + // completed an SSO login. Kept across logouts; cleared when the profile is + // removed. See profile_state.go. Email string IsActive bool } @@ -200,11 +201,9 @@ func (pm *ProfileManager) LogoutProfile(id string) error { return fmt.Errorf("failed to save config: %w", err) } - // Not fatal: a stale hint costs an account switch, not the logout itself. - if err := removeProfileEmail(configPath); err != nil { - log.Warnf("failed to clear stored account email for profile %s: %v", id, err) - } - + // The stored account email is kept on purpose, matching the desktop and CLI + // logout semantics: the next login passes it as the login_hint so the IdP + // preselects the account. Removing the profile is what deletes it. log.Infof("logged out from profile: %s", id) return nil } @@ -224,11 +223,24 @@ func (pm *ProfileManager) RenameProfile(id string, newName string) error { // RemoveProfile deletes a profile func (pm *ProfileManager) RemoveProfile(id string) error { + configPath, err := pm.getProfileConfigPath(id) + if err != nil { + return err + } + // Use ServiceManager (removes profile from profiles/ directory) if err := pm.serviceMgr.RemoveProfile(profilemanager.ID(id), androidUsername); err != nil { return fmt.Errorf("failed to remove profile: %w", err) } + // The account file is this package's, not the ServiceManager's, so it must + // go here. The default profile has a fixed filename, so a recreated one + // would otherwise inherit the deleted profile's email as its login_hint. + // Not fatal: the profile itself is gone. + if err := removeProfileEmail(configPath); err != nil { + log.Warnf("failed to remove stored account email for profile %s: %v", id, err) + } + log.Infof("removed profile: %s", id) return nil } diff --git a/client/android/profile_prefs.go b/client/android/profile_prefs.go new file mode 100644 index 000000000..9c1fd307b --- /dev/null +++ b/client/android/profile_prefs.go @@ -0,0 +1,38 @@ +//go:build android + +package android + +import ( + "fmt" + + "github.com/netbirdio/netbird/client/internal/profilemanager" +) + +type prefsStore interface { + Get(namespace string, v any) (bool, error) + Put(namespace string, v any) error +} + +type profilePrefs struct { + prefs *profilemanager.Prefs +} + +func newProfilePrefs(configDir, profileID string) (*profilePrefs, error) { + if configDir == "" || profileID == "" { + return nil, fmt.Errorf("profile prefs require a config dir and profile ID") + } + pm := NewProfileManager(configDir) + prefs, err := pm.serviceMgr.ProfilePrefs(profilemanager.ID(profileID), androidUsername) + if err != nil { + return nil, fmt.Errorf("resolve profile prefs: %w", err) + } + return &profilePrefs{prefs: prefs}, nil +} + +func (p *profilePrefs) Get(namespace string, v any) (bool, error) { + return p.prefs.Get(namespace, v) +} + +func (p *profilePrefs) Put(namespace string, v any) error { + return p.prefs.Put(namespace, v) +} diff --git a/client/android/profile_state.go b/client/android/profile_state.go index 3f0a09701..0063b587f 100644 --- a/client/android/profile_state.go +++ b/client/android/profile_state.go @@ -90,10 +90,10 @@ func writeProfileEmail(configPath string, email string) error { return nil } -// removeProfileEmail drops the stored account email. Called on logout: while the -// email is on disk it goes out as a login_hint, which would steer the next login -// straight back into the account just logged out of. Mirrors the desktop UI's -// RemoveProfileState call. +// removeProfileEmail drops the stored account email. Called on profile removal, +// not on logout: a logged-out profile keeps its email so the next login passes +// it as the login_hint, matching the desktop and CLI semantics. Mirrors the +// desktop UI's RemoveProfileState call. func removeProfileEmail(configPath string) error { accountPath, err := profileAccountPathFor(configPath) if err != nil { diff --git a/client/android/profile_state_test.go b/client/android/profile_state_test.go index 623e16c3b..82a1c2a87 100644 --- a/client/android/profile_state_test.go +++ b/client/android/profile_state_test.go @@ -127,10 +127,10 @@ func TestWriteThenReadProfileEmail(t *testing.T) { t.Fatalf("remove: %v", err) } if got := readProfileEmail(configPath); got != "" { - t.Errorf("expected no email after logout, got %q", got) + t.Errorf("expected no email after removal, got %q", got) } - // Logout may run on a never-logged-in profile, so a second remove must pass. + // Removal may run on a never-logged-in profile, so a second remove must pass. if err := removeProfileEmail(configPath); err != nil { t.Fatalf("second remove should be a no-op: %v", err) } diff --git a/client/android/ssh_client.go b/client/android/ssh_client.go new file mode 100644 index 000000000..2822b6539 --- /dev/null +++ b/client/android/ssh_client.go @@ -0,0 +1,649 @@ +//go:build android + +package android + +import ( + "context" + "errors" + "fmt" + "io" + "net" + "strconv" + "strings" + "sync" + "time" + + log "github.com/sirupsen/logrus" + gossh "golang.org/x/crypto/ssh" + + "github.com/netbirdio/netbird/client/internal" + "github.com/netbirdio/netbird/client/internal/auth" + "github.com/netbirdio/netbird/client/internal/profilemanager" + nbssh "github.com/netbirdio/netbird/client/ssh" + "github.com/netbirdio/netbird/client/ssh/detection" +) + +const ( + sshDialTimeout = 30 * time.Second + sshDetectionTimeout = 5 * time.Second +) + +// PasswordRequiredMarker tells Java to prompt for a password and retry. It is +// a string because gomobile flattens errors to their message, so a sentinel +// value would not survive the binding. +const PasswordRequiredMarker = "netbird-ssh-password-required" + +// HostKeyUnknownMarker tells Java to show the fingerprint and, on confirmation, +// retry with TrustHostKey set. The presented fingerprint is appended after the +// marker so the prompt can display it and the retry can guard against a key +// that changed between the two connects. Only regular (non-NetBird) servers +// reach this: NetBird peers verify against the registry. +const HostKeyUnknownMarker = "netbird-ssh-hostkey-unknown" + +var ( + errPasswordRequired = errors.New(PasswordRequiredMarker) + errClientClosed = errors.New("ssh client closed") +) + +// errHostKeyUnknown carries the presented fingerprint so Connect can build the +// marker message the Java side parses. +type errHostKeyUnknown struct { + fingerprint string +} + +func (e *errHostKeyUnknown) Error() string { + return HostKeyUnknownMarker + ":" + e.fingerprint +} + +// SSHTerminalListener receives SSH session events. It is implemented in Java. +// +// All callbacks are invoked from goroutines and may run concurrently with each +// other; the implementation must be safe to call from any thread. +type SSHTerminalListener interface { + OnConnected() + OnData(data []byte) + OnClose(reason string) + OnError(message string) +} + +// SSHClient is a NetBird-aware SSH client exposed to Java via gomobile. +// +// It dials through the running NetBird tunnel and runs a standard SSH session +// on top with PTY enabled. Host-key verification uses the NetBird-provided +// peer SSH host keys, identical to the desktop client. +type SSHClient struct { + nb *Client + mu sync.Mutex + listener SSHTerminalListener + urlOpener URLOpener + + sshClient *gossh.Client + session *gossh.Session + stdin io.WriteCloser + closed bool + + // gen identifies the current connection attempt. Connect and Close bump it, + // so an in-flight dial or a reader left over from a previous connection + // finds itself stale and stays silent instead of publishing OnConnected or + // OnClose for a connection the caller already abandoned. + gen uint64 + dialCancel context.CancelFunc + + // knownHostsConfigDir and knownHostsProfile locate the TOFU store for + // regular SSH servers in the profile's preferences. Java supplies them, + // since an overlay IP is a different host under a different profile. Empty + // until set: without them a regular server cannot be verified and Connect + // refuses one. + knownHostsConfigDir string + knownHostsProfile string + // trustHostKey carries the fingerprint the user confirmed on a previous + // attempt, so the retry accepts exactly that key and persists it. + trustHostKey string +} + +// NewSSHClient creates a new SSH client bound to the running NetBird Client. +func NewSSHClient(c *Client) *SSHClient { + return &SSHClient{nb: c} +} + +// SetListener registers the Java listener. Must be called before Connect to +// receive any events. +func (s *SSHClient) SetListener(l SSHTerminalListener) { + s.mu.Lock() + s.listener = l + s.mu.Unlock() +} + +// SetURLOpener registers the Java URL opener used to display the device-code +// authorization page in a Custom Tabs window when the target peer requires +// JWT authentication. Must be set before Connect to be effective. +func (s *SSHClient) SetURLOpener(opener URLOpener) { + s.mu.Lock() + s.urlOpener = opener + s.mu.Unlock() +} + +// SetKnownHostsStore points the TOFU host-key store at a profile's preferences. +// Must be set before connecting to a regular SSH server; without it such a +// server cannot be verified and Connect refuses one. +func (s *SSHClient) SetKnownHostsStore(configDir, profileID string) { + s.mu.Lock() + s.knownHostsConfigDir = configDir + s.knownHostsProfile = profileID + s.mu.Unlock() +} + +// TrustHostKey records the fingerprint the user confirmed for a regular server, +// so the next Connect accepts that exact key and adds it to the known-hosts +// store. Passing a fingerprint that no longer matches makes the connect fail +// rather than trust a key that changed since the prompt. +func (s *SSHClient) TrustHostKey(fingerprint string) { + s.mu.Lock() + s.trustHostKey = fingerprint + s.mu.Unlock() +} + +// Connect dials the SSH server through the NetBird tunnel and performs the +// SSH handshake. It auto-detects the server type via SSH banner inspection +// and selects the appropriate authentication path: +// +// - NetBird-SSH server requiring JWT: launches the OAuth 2.0 device-code +// flow, opens the verification URL through the registered URLOpener, and +// uses the resulting token as the SSH password. Host-key verification +// uses the NetBird peer registry. +// - NetBird-SSH server without JWT: authenticates with the NetBird SSH +// private key. Host-key verification uses the NetBird peer registry. +// - Regular SSH server (e.g. OpenSSH): authenticates with the NetBird key +// first (so a user-installed NetBird public key works), then falls back +// to the supplied password if non-empty. Host-key verification is +// trust-on-first-use against the per-profile known-hosts store. +// +// The password parameter is only consulted for regular SSH servers. +func (s *SSHClient) Connect(host string, port int, user, password string) error { + if port < 1 || port > 65535 { + return fmt.Errorf("invalid port: %d", port) + } + + cfg, cfgPath, cc := s.nb.authSnapshot() + if cc == nil { + return errors.New("netbird client not running") + } + if cfg == nil { + return errors.New("netbird config not loaded") + } + engine := cc.Engine() + if engine == nil { + return errors.New("netbird engine not available") + } + + s.mu.Lock() + s.gen++ + gen := s.gen + s.mu.Unlock() + + serverType := detectServerType(host, port) + log.Debugf("SSH server type: %s", serverType) + + authMethods, hostKeyCallback, err := s.buildAuth(cfg, cfgPath, engine, serverType, password) + if err != nil { + return err + } + + clientConfig := &gossh.ClientConfig{ + User: user, + Auth: authMethods, + HostKeyCallback: hostKeyCallback, + Timeout: sshDialTimeout, + } + err = s.dialAndHandshake(gen, host, port, clientConfig) + + // An unknown host key is a prompt, not a failure: return the marker intact + // (rootCause would unwrap it) so Java can show the fingerprint and retry. + var unknownHost *errHostKeyUnknown + if errors.As(err, &unknownHost) { + return errors.New(unknownHost.Error()) + } + + // A regular server may still accept a password, so let the caller ask for + // one instead of failing. NetBird servers never use a password, so a + // failure there is genuine. + if err != nil && serverType != detection.ServerTypeNetBirdJWT && + serverType != detection.ServerTypeNetBirdNoJWT && isAuthFailure(err) && + passwordCouldHelp(err, password != "") { + return errPasswordRequired + } + if err != nil { + return rootCause(err) + } + return nil +} + +// StartSession requests a PTY and starts an interactive shell. Output from +// the session is forwarded to the listener via OnData. +func (s *SSHClient) StartSession(cols, rows int) error { + err := s.startSession(cols, rows) + if err != nil { + log.Infof("SSH: start session failed: %v", err) + return rootCause(err) + } + return nil +} + +// Write sends data to the SSH session stdin. +func (s *SSHClient) Write(data []byte) error { + s.mu.Lock() + stdin := s.stdin + s.mu.Unlock() + if stdin == nil { + return errors.New("ssh session not started") + } + if _, err := stdin.Write(data); err != nil { + return fmt.Errorf("write stdin: %w", err) + } + return nil +} + +// Resize updates the PTY window size. +func (s *SSHClient) Resize(cols, rows int) error { + s.mu.Lock() + session := s.session + s.mu.Unlock() + if session == nil { + return errors.New("ssh session not started") + } + return session.WindowChange(rows, cols) +} + +// Reset makes a closed client usable for another Connect: Close leaves the +// one-shot guard set, and clearing it lets the same client back a reconnect. +func (s *SSHClient) Reset() { + s.mu.Lock() + defer s.mu.Unlock() + s.closed = false +} + +// Close terminates the SSH session and underlying connection. Safe to call +// multiple times. +func (s *SSHClient) Close() error { + s.mu.Lock() + s.gen++ + if s.dialCancel != nil { + s.dialCancel() + s.dialCancel = nil + } + sshClient := s.sshClient + session := s.session + stdin := s.stdin + s.sshClient = nil + s.session = nil + s.stdin = nil + notify := !s.closed + s.closed = true + listener := s.listener + s.mu.Unlock() + + if stdin != nil { + if err := stdin.Close(); err != nil { + log.Debugf("ssh: stdin close: %v", err) + } + } + if session != nil { + if err := session.Close(); err != nil && !errors.Is(err, io.EOF) { + log.Debugf("ssh: session close: %v", err) + } + } + var firstErr error + if sshClient != nil { + if err := sshClient.Close(); err != nil { + firstErr = err + } + } + if notify && listener != nil { + listener.OnClose("closed by client") + } + return firstErr +} + +func (s *SSHClient) startSession(cols, rows int) error { + log.Debugf("SSH: starting session %dx%d", cols, rows) + s.mu.Lock() + sshClient := s.sshClient + gen := s.gen + s.mu.Unlock() + + if sshClient == nil { + return errors.New("ssh client not connected") + } + + pty, err := nbssh.StartPTYSession(sshClient, cols, rows) + if err != nil { + return err + } + + s.mu.Lock() + if gen != s.gen { + s.mu.Unlock() + closeQuiet(pty.Session, "stale session") + return errClientClosed + } + s.session = pty.Session + s.stdin = pty.Stdin + s.mu.Unlock() + + readerDone := make(chan string, 2) + go func() { readerDone <- s.readLoop(pty.Stdout, "stdout") }() + go func() { readerDone <- s.readLoop(pty.Stderr, "stderr") }() + go func() { + reason := <-readerDone + if second := <-readerDone; reason == "" { + reason = second + } + s.notifyClose(gen, reason) + }() + log.Debug("SSH: session started, shell running") + return nil +} + +func (s *SSHClient) buildAuth(cfg *profilemanager.Config, cfgPath string, engine *internal.Engine, + serverType detection.ServerType, password string) ([]gossh.AuthMethod, gossh.HostKeyCallback, error) { + + switch serverType { + case detection.ServerTypeNetBirdJWT: + token, err := s.requestJWTToken(cfg, cfgPath) + if err != nil { + return nil, nil, fmt.Errorf("jwt: %w", err) + } + auths := []gossh.AuthMethod{gossh.Password(token)} + return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil + + case detection.ServerTypeNetBirdNoJWT: + if cfg.SSHKey == "" { + return nil, nil, errors.New("no NetBird SSH key available") + } + signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey)) + if err != nil { + return nil, nil, fmt.Errorf("parse netbird ssh key: %w", err) + } + auths := []gossh.AuthMethod{gossh.PublicKeys(signer)} + return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil + + case detection.ServerTypeRegular: + var auths []gossh.AuthMethod + if cfg.SSHKey != "" { + if signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey)); err == nil { + auths = append(auths, gossh.PublicKeys(signer)) + } else { + log.Debugf("ssh: parse netbird key for regular auth: %v", err) + } + } + if password != "" { + pw := password + auths = append(auths, gossh.Password(pw)) + auths = append(auths, gossh.KeyboardInteractive(func(_, _ string, questions []string, _ []bool) ([]string, error) { + answers := make([]string, len(questions)) + for i := range questions { + answers[i] = pw + } + return answers, nil + })) + } + if len(auths) == 0 { + // Nothing to offer at all: ask for a password rather than failing, + // so the caller can retry once the user supplies one. + return nil, nil, errPasswordRequired + } + callback, err := s.tofuHostKeyCallback() + if err != nil { + return nil, nil, err + } + return auths, callback, nil + + default: + return nil, nil, fmt.Errorf("unsupported SSH server type: %v", serverType) + } +} + +// tofuHostKeyCallback verifies a regular server's host key against the +// per-profile known-hosts store. An unknown host returns errHostKeyUnknown so +// Java can show the fingerprint and, once confirmed, retry with the key +// trusted; a changed key is rejected outright, as OpenSSH does. When the user +// has confirmed a fingerprint, the callback accepts exactly that key and +// appends it to the store. +func (s *SSHClient) tofuHostKeyCallback() (gossh.HostKeyCallback, error) { + s.mu.Lock() + configDir := s.knownHostsConfigDir + profileID := s.knownHostsProfile + trusted := s.trustHostKey + s.mu.Unlock() + + if configDir == "" || profileID == "" { + return nil, errors.New("no known-hosts store configured for regular SSH") + } + + store, err := openKnownHostsStore(configDir, profileID) + if err != nil { + return nil, fmt.Errorf("load known-hosts store: %w", err) + } + + return func(hostname string, remote net.Addr, key gossh.PublicKey) error { + verdict, err := store.verify(hostname, remote, key) + if err != nil { + return err + } + if verdict == hostKeyMatched { + return nil + } + if verdict == hostKeyChanged { + return fmt.Errorf("SSH host key changed for %s (possible attack)", hostname) + } + + fingerprint := gossh.FingerprintSHA256(key) + if trusted == "" { + return &errHostKeyUnknown{fingerprint: fingerprint} + } + if trusted != fingerprint { + return fmt.Errorf("SSH host key changed since it was confirmed for %s", hostname) + } + if err := store.append(hostname, remote, key); err != nil { + return fmt.Errorf("persist trusted host key: %w", err) + } + // The confirmation is spent: now that the key is stored, a later + // reconnect must verify against the file, not re-accept this fingerprint. + s.mu.Lock() + s.trustHostKey = "" + s.mu.Unlock() + return nil + }, nil +} + +func (s *SSHClient) requestJWTToken(cfg *profilemanager.Config, cfgPath string) (string, error) { + s.mu.Lock() + urlOpener := s.urlOpener + s.mu.Unlock() + if urlOpener == nil { + return "", errors.New("URL opener not configured for JWT auth") + } + + ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute) + defer cancel() + + flow, err := auth.NewOAuthFlow(ctx, cfg, false, true, profileLoginHint(cfgPath)) + if err != nil { + return "", fmt.Errorf("create oauth flow: %w", err) + } + + // The status callback covers the browser round-trip, which would + // otherwise leave the terminal blank. + tokenInfo, err := runOAuthFlow(ctx, flow, urlOpener, func() { + s.notifyStatus("Waiting for browser authentication...") + }) + if err != nil { + return "", err + } + + token := tokenInfo.GetTokenToUse() + if token == "" { + return "", errors.New("empty token returned by IdP") + } + + // Tells the client the browser round-trip is over so it can dismiss the + // surface it opened, the same way the login and session-extend flows do. + // Without it the Custom Tab stays in front of the terminal even though the + // token has already been collected. + urlOpener.OnLoginSuccess() + + return token, nil +} + +func (s *SSHClient) dialAndHandshake(gen uint64, host string, port int, clientConfig *gossh.ClientConfig) error { + addr := net.JoinHostPort(host, strconv.Itoa(port)) + ctx, cancel := context.WithTimeout(context.Background(), sshDialTimeout) + defer cancel() + + s.mu.Lock() + if gen != s.gen { + s.mu.Unlock() + return errClientClosed + } + s.dialCancel = cancel + s.mu.Unlock() + + var dialer net.Dialer + conn, err := dialer.DialContext(ctx, "tcp", addr) + if err != nil { + return fmt.Errorf("dial %s: %w", addr, err) + } + + client, err := nbssh.Handshake(ctx, conn, addr, clientConfig) + if err != nil { + return err + } + + s.mu.Lock() + if gen != s.gen { + s.mu.Unlock() + closeQuiet(client, "stale ssh client") + return errClientClosed + } + s.sshClient = client + listener := s.listener + s.mu.Unlock() + + if listener != nil { + listener.OnConnected() + } + return nil +} + +func (s *SSHClient) readLoop(r io.Reader, name string) string { + buf := make([]byte, 4096) + for { + n, err := r.Read(buf) + if n > 0 { + s.mu.Lock() + listener := s.listener + s.mu.Unlock() + if listener != nil { + chunk := make([]byte, n) + copy(chunk, buf[:n]) + listener.OnData(chunk) + } + } + if err != nil { + // EOF is a normal shell exit, so report it without a reason. + if errors.Is(err, io.EOF) { + return "" + } + log.Debugf("ssh %s read: %v", name, err) + return rootCause(err).Error() + } + } +} + +// notifyStatus writes a progress line to the terminal through the normal +// output path, so long steps are visible while nothing else is arriving. +func (s *SSHClient) notifyStatus(text string) { + s.mu.Lock() + listener := s.listener + s.mu.Unlock() + if listener != nil { + listener.OnData([]byte("\r\n\x1b[33m" + text + "\x1b[0m\r\n")) + } +} + +func (s *SSHClient) notifyClose(gen uint64, reason string) { + s.mu.Lock() + if gen != s.gen || s.closed { + s.mu.Unlock() + return + } + s.closed = true + listener := s.listener + s.mu.Unlock() + if listener != nil { + listener.OnClose(reason) + } +} + +func closeQuiet(c io.Closer, label string) { + if c == nil { + return + } + if err := c.Close(); err != nil && !errors.Is(err, io.EOF) { + log.Debugf("ssh: close %s: %v", label, err) + } +} + +func detectServerType(host string, port int) detection.ServerType { + ctx, cancel := context.WithTimeout(context.Background(), sshDetectionTimeout) + defer cancel() + + dialer := &net.Dialer{} + serverType, err := detection.DetectSSHServerType(ctx, dialer, host, port) + if err != nil { + log.Debugf("ssh: server detection failed: %v (assuming regular SSH)", err) + return detection.ServerTypeRegular + } + return serverType +} + +// rootCause returns the innermost error of a %w chain, so the terminal shows +// "i/o timeout" rather than every layer that added context on the way up. +func rootCause(err error) error { + for { + // A joined error has no single root, so keep it as-is. + if _, ok := err.(interface{ Unwrap() []error }); ok { + return err + } + next := errors.Unwrap(err) + if next == nil { + return err + } + err = next + } +} + +// isAuthFailure distinguishes credential rejection from dial, timeout and +// host-key errors, which retrying with a password would not fix. +func isAuthFailure(err error) bool { + if errors.Is(err, errPasswordRequired) { + return true + } + var partial *gossh.PartialSuccessError + if errors.As(err, &partial) { + return true + } + return strings.Contains(err.Error(), "unable to authenticate") +} + +// passwordCouldHelp reports whether prompting for a password again can change +// the outcome. gossh lists a method under "attempted methods" only when the +// server offered it, so a supplied password that was never attempted means the +// server does not accept passwords and the real error should surface instead. +func passwordCouldHelp(err error, passwordOffered bool) bool { + if !passwordOffered { + return true + } + msg := err.Error() + return strings.Contains(msg, "password") || strings.Contains(msg, "keyboard-interactive") +} diff --git a/client/android/ssh_known_hosts.go b/client/android/ssh_known_hosts.go new file mode 100644 index 000000000..eea90fd32 --- /dev/null +++ b/client/android/ssh_known_hosts.go @@ -0,0 +1,168 @@ +//go:build android + +package android + +import ( + "bytes" + "net" + "strconv" + "strings" + "sync" + + gossh "golang.org/x/crypto/ssh" + "golang.org/x/crypto/ssh/knownhosts" +) + +const knownHostsNamespace = "ssh" + +const ( + hostKeyUnknown hostKeyVerdict = iota + hostKeyMatched + hostKeyChanged +) + +var knownHostsMu sync.Mutex + +type hostKeyVerdict uint8 + +type knownHostsSection struct { + KnownHosts []string `json:"knownHosts"` +} + +type knownHostsStore struct { + prefs prefsStore +} + +// RemoveKnownHost deletes every known-hosts entry for host:port from the +// profile's store, so a host trusted for a session that is being deleted does +// not linger. Java calls this only once no session targets that host, so a +// shared host stays trusted. A missing entry is not an error: the goal state +// is "absent". +func RemoveKnownHost(configDir, profileID, host string, port int) error { + store, err := openKnownHostsStore(configDir, profileID) + if err != nil { + return err + } + return store.removeHost(host, port) +} + +func openKnownHostsStore(configDir, profileID string) (*knownHostsStore, error) { + prefs, err := newProfilePrefs(configDir, profileID) + if err != nil { + return nil, err + } + return &knownHostsStore{prefs: prefs}, nil +} + +func (st *knownHostsStore) verify(hostname string, remote net.Addr, key gossh.PublicKey) (hostKeyVerdict, error) { + lines, err := st.lines() + if err != nil { + return hostKeyUnknown, err + } + targets := knownHostsTargets(hostname, remote) + + verdict := hostKeyUnknown + for _, line := range lines { + pubKey, ok := knownHostsLineKey(line, targets) + if !ok { + continue + } + if pubKey.Type() == key.Type() && bytes.Equal(pubKey.Marshal(), key.Marshal()) { + return hostKeyMatched, nil + } + verdict = hostKeyChanged + } + return verdict, nil +} + +func (st *knownHostsStore) append(hostname string, remote net.Addr, key gossh.PublicKey) error { + line := knownhosts.Line(knownHostsTargets(hostname, remote), key) + + knownHostsMu.Lock() + defer knownHostsMu.Unlock() + + lines, err := st.lines() + if err != nil { + return err + } + return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: append(lines, line)}) +} + +func (st *knownHostsStore) removeHost(host string, port int) error { + target := knownhosts.Normalize(net.JoinHostPort(host, strconv.Itoa(port))) + + knownHostsMu.Lock() + defer knownHostsMu.Unlock() + + lines, err := st.lines() + if err != nil { + return err + } + kept := make([]string, 0, len(lines)) + for _, line := range lines { + if knownHostsLineMatches(line, target) { + continue + } + kept = append(kept, line) + } + if len(kept) == len(lines) { + return nil + } + return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: kept}) +} + +func (st *knownHostsStore) lines() ([]string, error) { + var section knownHostsSection + if _, err := st.prefs.Get(knownHostsNamespace, §ion); err != nil { + return nil, err + } + return section.KnownHosts, nil +} + +func knownHostsTargets(hostname string, remote net.Addr) []string { + targets := []string{knownhosts.Normalize(hostname)} + if remote != nil { + if normalized := knownhosts.Normalize(remote.String()); normalized != targets[0] { + targets = append(targets, normalized) + } + } + return targets +} + +func knownHostsLineKey(line string, targets []string) (gossh.PublicKey, bool) { + trimmed := strings.TrimSpace(line) + if trimmed == "" || strings.HasPrefix(trimmed, "#") { + return nil, false + } + _, hosts, pubKey, _, _, err := gossh.ParseKnownHosts([]byte(trimmed)) + if err != nil { + return nil, false + } + for _, host := range hosts { + for _, target := range targets { + if host == target { + return pubKey, true + } + } + } + return nil, false +} + +// knownHostsLineMatches reports whether a known-hosts line's address list +// contains the normalized target. Comment and blank lines never match. +func knownHostsLineMatches(line, target string) bool { + trimmed := strings.TrimSpace(line) + if trimmed == "" || strings.HasPrefix(trimmed, "#") { + return false + } + fields := strings.Fields(trimmed) + if len(fields) == 0 { + return false + } + for _, addr := range strings.Split(fields[0], ",") { + if addr == target { + return true + } + } + return false +} diff --git a/client/android/ssh_sessions.go b/client/android/ssh_sessions.go new file mode 100644 index 000000000..44b5464e9 --- /dev/null +++ b/client/android/ssh_sessions.go @@ -0,0 +1,104 @@ +//go:build android + +package android + +const ( + sshSessionsNamespace = "ssh-sessions" + maxStoredSSHSessions = 50 +) + +type sshSessionRecord struct { + ID string `json:"id"` + Host string `json:"host"` + Port int `json:"port"` + User string `json:"user"` +} + +type sshSessionsSection struct { + Sessions []sshSessionRecord `json:"sessions"` +} + +// SSHSessionEntry is one stored SSH session, without any credential. +type SSHSessionEntry struct { + ID string + Host string + Port int + User string +} + +// SSHSessionArray wraps stored SSH sessions for gomobile compatibility. +type SSHSessionArray struct { + items []*SSHSessionEntry +} + +// NewSSHSessionArray creates an empty session array to fill via Add. +func NewSSHSessionArray() *SSHSessionArray { + return &SSHSessionArray{} +} + +// Add appends a session entry, oldest first. +func (a *SSHSessionArray) Add(id, host string, port int, user string) { + a.items = append(a.items, &SSHSessionEntry{ID: id, Host: host, Port: port, User: user}) +} + +// Length returns the number of entries. +func (a *SSHSessionArray) Length() int { + return len(a.items) +} + +// Get returns the entry at index i, or nil when out of range. +func (a *SSHSessionArray) Get(i int) *SSHSessionEntry { + if i < 0 || i >= len(a.items) { + return nil + } + return a.items[i] +} + +// SSHSessionStore reads and writes a profile's stored SSH sessions. +type SSHSessionStore struct { + prefs prefsStore +} + +// NewSSHSessionStore opens the session store of the given profile. +func NewSSHSessionStore(configDir, profileID string) (*SSHSessionStore, error) { + prefs, err := newProfilePrefs(configDir, profileID) + if err != nil { + return nil, err + } + return &SSHSessionStore{prefs: prefs}, nil +} + +// Load returns the stored sessions, oldest first. +func (s *SSHSessionStore) Load() (*SSHSessionArray, error) { + var section sshSessionsSection + if _, err := s.prefs.Get(sshSessionsNamespace, §ion); err != nil { + return nil, err + } + + out := NewSSHSessionArray() + for _, record := range section.Sessions { + if record.ID == "" || record.Host == "" { + continue + } + out.Add(record.ID, record.Host, record.Port, record.User) + } + return out, nil +} + +// Save replaces the stored sessions, keeping only the newest entries when the +// list exceeds the storage cap. +func (s *SSHSessionStore) Save(sessions *SSHSessionArray) error { + var items []*SSHSessionEntry + if sessions != nil { + items = sessions.items + } + if len(items) > maxStoredSSHSessions { + items = items[len(items)-maxStoredSSHSessions:] + } + + records := make([]sshSessionRecord, 0, len(items)) + for _, item := range items { + records = append(records, sshSessionRecord{ID: item.ID, Host: item.Host, Port: item.Port, User: item.User}) + } + return s.prefs.Put(sshSessionsNamespace, sshSessionsSection{Sessions: records}) +} diff --git a/client/anonymize/anonymize.go b/client/anonymize/anonymize.go index c140cef89..c5d43ed55 100644 --- a/client/anonymize/anonymize.go +++ b/client/anonymize/anonymize.go @@ -2,6 +2,7 @@ package anonymize import ( "crypto/rand" + "encoding/base64" "fmt" "math/big" "net" @@ -15,13 +16,88 @@ import ( const anonTLD = ".domain" +// Level selects how much the anonymizer redacts. Levels are ordered: a higher +// level redacts strictly more. On the wire (protos, flags) levels travel as +// their string form. +type Level int + +const ( + // LevelDefault anonymizes public IP addresses, IPv6 ULA, domains, and MAC + // addresses. Internal IPv4 ranges (RFC 1918, CGNAT, link-local) are + // preserved so support can reason about the real topology. + LevelDefault Level = iota + // LevelStrict additionally anonymizes internal IP ranges, peer names, and + // WireGuard public keys. + LevelStrict +) + +// LevelDefaultString and LevelStrictString are the wire forms of the levels, +// for boundaries that pass levels as strings (flags, protos, mobile bindings). +const ( + LevelDefaultString = "default" + LevelStrictString = "strict" +) + +// ParseLevel maps s to a Level. Empty means LevelDefault; anything +// unrecognized maps to LevelStrict so an unknown request never yields less +// anonymization than intended. +func ParseLevel(s string) Level { + switch strings.ToLower(s) { + case "", LevelDefaultString: + return LevelDefault + default: + return LevelStrict + } +} + +// String returns the wire form of the level: "default" or "strict". +func (l Level) String() string { + if l >= LevelStrict { + return LevelStrictString + } + return LevelDefaultString +} + +// protectedDomains are NetBird-operated suffixes that stay recognizable in an +// anonymized bundle. At LevelStrict the labels in front of them (the peer +// name) are still replaced, except under netbird.io, which only hosts +// NetBird infrastructure (api, signal, flow), never peer names. +var protectedDomains = []string{"netbird.io", "netbird.selfhosted", "netbird.cloud", "netbird.stage"} + +const infraDomain = "netbird.io" + +var ( + macColonRegex = regexp.MustCompile(`\b[0-9a-fA-F]{2}(?::[0-9a-fA-F]{2}){5}\b`) + macDashRegex = regexp.MustCompile(`\b[0-9a-fA-F]{2}(?:-[0-9a-fA-F]{2}){5}\b`) + wgKeyRegex = regexp.MustCompile(`\b[A-Za-z0-9+/]{43}=`) +) + type Anonymizer struct { ipAnonymizer map[netip.Addr]netip.Addr domainAnonymizer map[string]string - currentAnonIPv4 netip.Addr - currentAnonIPv6 netip.Addr - startAnonIPv4 netip.Addr - startAnonIPv6 netip.Addr + // domainOrder caches the keys of domainAnonymizer sorted longest-first + // for AnonymizeString; it is rebuilt when the map gains entries. + domainOrder []string + labelAnonymizer map[string]string + labelAnonymized map[string]struct{} + labelCounter uint32 + macAnonymizer map[string]string + macCounter uint32 + wgKeyAnonymizer map[string]string + wgKeyAnonymized map[string]struct{} + currentAnonIPv4 netip.Addr + currentAnonIPv6 netip.Addr + startAnonIPv4 netip.Addr + startAnonIPv6 netip.Addr + + // LevelStrict also anonymizes internal ranges (RFC 1918, CGNAT, + // link-local), replacing them from the dedicated internal pools below so + // a reader can still tell an internal address from a public one. + level Level + currentAnonInternalIPv4 netip.Addr + currentAnonInternalIPv6 netip.Addr + startAnonInternalIPv4 netip.Addr + startAnonInternalIPv6 netip.Addr domainKeyRegex *regexp.Regexp } @@ -32,25 +108,50 @@ func DefaultAddresses() (netip.Addr, netip.Addr) { return netip.AddrFrom4([4]byte{198, 51, 100, 0}), netip.MustParseAddr("2001:db8:ffff::") } +// InternalAddresses returns the pool starts used in strict mode for internal +// ranges. Both are reserved ranges that cannot collide with real addressing: +// 198.18.0.0 (RFC 2544 benchmarking), 2001:db8:1:: (RFC 3849 documentation). +func InternalAddresses() (netip.Addr, netip.Addr) { + return netip.AddrFrom4([4]byte{198, 18, 0, 0}), netip.MustParseAddr("2001:db8:1::") +} + func NewAnonymizer(startIPv4, startIPv6 netip.Addr) *Anonymizer { + internalIPv4, internalIPv6 := InternalAddresses() return &Anonymizer{ ipAnonymizer: map[netip.Addr]netip.Addr{}, domainAnonymizer: map[string]string{}, + labelAnonymizer: map[string]string{}, + labelAnonymized: map[string]struct{}{}, + macAnonymizer: map[string]string{}, + wgKeyAnonymizer: map[string]string{}, + wgKeyAnonymized: map[string]struct{}{}, currentAnonIPv4: startIPv4, currentAnonIPv6: startIPv6, startAnonIPv4: startIPv4, startAnonIPv6: startIPv6, + level: LevelDefault, + currentAnonInternalIPv4: internalIPv4, + currentAnonInternalIPv6: internalIPv6, + startAnonInternalIPv4: internalIPv4, + startAnonInternalIPv6: internalIPv6, + domainKeyRegex: regexp.MustCompile(`\bdomain=([^\s,:"]+)`), } } +// SetLevel selects the anonymization level. The zero value of a new +// Anonymizer is LevelDefault. +func (a *Anonymizer) SetLevel(level Level) { + a.level = level +} + func (a *Anonymizer) AnonymizeIP(ip netip.Addr) netip.Addr { + // Normalize 4-in-6 addresses so ::ffff:192.168.1.1 classifies and maps + // like 192.168.1.1. + ip = ip.Unmap() + if ip.IsLoopback() || - ip.IsLinkLocalUnicast() || - ip.IsLinkLocalMulticast() || - ip.IsInterfaceLocalMulticast() || - (ip.Is4() && ip.IsPrivate()) || ip.IsUnspecified() || ip.IsMulticast() || isWellKnown(ip) || @@ -59,18 +160,100 @@ func (a *Anonymizer) AnonymizeIP(ip netip.Addr) netip.Addr { return ip } + if isInternal(ip) && a.level < LevelStrict { + return ip + } + if _, ok := a.ipAnonymizer[ip]; !ok { - if ip.Is4() { - a.ipAnonymizer[ip] = a.currentAnonIPv4 - a.currentAnonIPv4 = a.currentAnonIPv4.Next() - } else { - a.ipAnonymizer[ip] = a.currentAnonIPv6 - a.currentAnonIPv6 = a.currentAnonIPv6.Next() - } + a.ipAnonymizer[ip] = a.nextAnonIP(ip) } return a.ipAnonymizer[ip] } +func (a *Anonymizer) nextAnonIP(ip netip.Addr) netip.Addr { + // At the strict level, internal addresses (including IPv6 ULA, matched + // by IsPrivate) come from the internal pools so they remain recognizable + // as internal without disclosing the real values. + if a.level >= LevelStrict && (isInternal(ip) || ip.IsPrivate()) { + if ip.Is4() { + anon := a.currentAnonInternalIPv4 + a.currentAnonInternalIPv4 = a.currentAnonInternalIPv4.Next() + return anon + } + anon := a.currentAnonInternalIPv6 + a.currentAnonInternalIPv6 = a.currentAnonInternalIPv6.Next() + return anon + } + + if ip.Is4() { + anon := a.currentAnonIPv4 + a.currentAnonIPv4 = a.currentAnonIPv4.Next() + return anon + } + anon := a.currentAnonIPv6 + a.currentAnonIPv6 = a.currentAnonIPv6.Next() + return anon +} + +// AnonymizeMAC replaces a MAC address with a consistent placeholder from the +// locally administered range starting at 02:00:00:00:00:01, at every +// anonymization level. Broadcast, multicast, all-zero, and already assigned +// placeholder addresses are preserved. The colon and dash spellings of the +// same address share one placeholder; the output keeps the input's separator. +func (a *Anonymizer) AnonymizeMAC(mac string) string { + hw, err := net.ParseMAC(mac) + if err != nil || len(hw) != 6 { + return mac + } + + if isWellKnownMAC(hw) || a.isAnonymizedMAC(hw) { + return mac + } + + key := hw.String() + anon, ok := a.macAnonymizer[key] + if !ok { + a.macCounter++ + anon = fmt.Sprintf("02:00:00:%02x:%02x:%02x", byte(a.macCounter>>16), byte(a.macCounter>>8), byte(a.macCounter)) + a.macAnonymizer[key] = anon + } + + if strings.Contains(mac, "-") { + anon = strings.ReplaceAll(anon, ":", "-") + } + return anon +} + +// isAnonymizedMAC reports whether hw is a placeholder this anonymizer already +// handed out, so a second pass over anonymized output leaves it unchanged. +func (a *Anonymizer) isAnonymizedMAC(hw net.HardwareAddr) bool { + if hw[0] != 0x02 || hw[1] != 0 || hw[2] != 0 { + return false + } + value := uint32(hw[3])<<16 | uint32(hw[4])<<8 | uint32(hw[5]) + return value <= a.macCounter +} + +// AnonymizeWGKey replaces a WireGuard public key with a consistent random +// placeholder of the same shape. Keys are only anonymized at LevelStrict; +// placeholders already handed out pass through unchanged. +func (a *Anonymizer) AnonymizeWGKey(key string) string { + if a.level < LevelStrict || !looksLikeWGKey(key) { + return key + } + if _, ok := a.wgKeyAnonymized[key]; ok { + return key + } + + anon, ok := a.wgKeyAnonymizer[key] + if !ok { + anon = generateAnonymousKey() + a.wgKeyAnonymizer[key] = anon + a.wgKeyAnonymized[anon] = struct{}{} + } + return anon +} + func (a *Anonymizer) AnonymizeUDPAddr(addr net.UDPAddr) net.UDPAddr { // Convert IP to netip.Addr ip, ok := netip.AddrFromSlice(addr.IP) @@ -89,12 +272,12 @@ func (a *Anonymizer) AnonymizeUDPAddr(addr net.UDPAddr) net.UDPAddr { // isInAnonymizedRange checks if an IP is within the range of already assigned anonymized IPs func (a *Anonymizer) isInAnonymizedRange(ip netip.Addr) bool { - if ip.Is4() && ip.Compare(a.startAnonIPv4) >= 0 && ip.Compare(a.currentAnonIPv4) <= 0 { - return true - } else if !ip.Is4() && ip.Compare(a.startAnonIPv6) >= 0 && ip.Compare(a.currentAnonIPv6) <= 0 { - return true + if ip.Is4() { + return inPoolRange(ip, a.startAnonIPv4, a.currentAnonIPv4) || + inPoolRange(ip, a.startAnonInternalIPv4, a.currentAnonInternalIPv4) } - return false + return inPoolRange(ip, a.startAnonIPv6, a.currentAnonIPv6) || + inPoolRange(ip, a.startAnonInternalIPv6, a.currentAnonInternalIPv6) } func (a *Anonymizer) AnonymizeIPString(ip string) string { @@ -118,14 +301,23 @@ func (a *Anonymizer) AnonymizeDomain(domain string) string { baseDomain = domain[:len(domain)-1] } - if strings.HasSuffix(baseDomain, "netbird.io") || - strings.HasSuffix(baseDomain, "netbird.selfhosted") || - strings.HasSuffix(baseDomain, "netbird.cloud") || - strings.HasSuffix(baseDomain, "netbird.stage") || - strings.HasSuffix(baseDomain, anonTLD) { + if strings.HasSuffix(baseDomain, anonTLD) { return domain } + // A reverse zone names an address prefix, so it follows the address rules, + // which also keeps its digit labels intact. + if zone, ok := a.anonymizeReverseZone(baseDomain); ok { + return withTrailingDot(zone, hasDot) + } + + if suffix := protectedSuffix(baseDomain); suffix != "" { + if a.level < LevelStrict || baseDomain == suffix || suffix == infraDomain { + return domain + } + return withTrailingDot(a.anonymizePeerName(baseDomain, suffix), hasDot) + } + parts := strings.Split(baseDomain, ".") if len(parts) < 2 { return domain @@ -141,12 +333,53 @@ func (a *Anonymizer) AnonymizeDomain(domain string) string { } result := strings.Replace(baseDomain, baseForLookup, anonymized, 1) - if hasDot { - result += "." + if a.level >= LevelStrict && len(parts) > 2 { + prefix := strings.TrimSuffix(baseDomain, "."+baseForLookup) + result = a.anonymizeLabels(prefix, "host") + "." + anonymized + // The full mapping feeds AnonymizeString so seeded FQDNs are caught + // in log lines as a whole, labels included. + a.domainAnonymizer[baseDomain] = result + } + return withTrailingDot(result, hasDot) +} + +// anonymizePeerName replaces the labels in front of a protected suffix with +// numbered peer placeholders, keeping the suffix, and records the full +// mapping for string replacement in logs. The numbering keeps a peer +// recognizable across the whole bundle without disclosing its name. +func (a *Anonymizer) anonymizePeerName(baseDomain, suffix string) string { + prefix := strings.TrimSuffix(baseDomain, "."+suffix) + result := a.anonymizeLabels(prefix, "peer") + "." + suffix + if result != baseDomain { + a.domainAnonymizer[baseDomain] = result } return result } +// anonymizeLabels replaces each dot-separated label with a consistent +// numbered placeholder ("-"). Wildcard labels and +// placeholders already handed out pass through unchanged. +func (a *Anonymizer) anonymizeLabels(prefix, placeholder string) string { + labels := strings.Split(prefix, ".") + for i, label := range labels { + if label == "*" { + continue + } + if _, ok := a.labelAnonymized[label]; ok { + continue + } + anon, ok := a.labelAnonymizer[label] + if !ok { + a.labelCounter++ + anon = fmt.Sprintf("%s-%d", placeholder, a.labelCounter) + a.labelAnonymizer[label] = anon + a.labelAnonymized[anon] = struct{}{} + } + labels[i] = anon + } + return strings.Join(labels, ".") +} + func (a *Anonymizer) AnonymizeURI(uri string) string { u, err := url.Parse(uri) if err != nil { @@ -178,17 +411,75 @@ func (a *Anonymizer) AnonymizeString(str string) string { ipv4Regex := regexp.MustCompile(`\b(?:[0-9]{1,3}\.){3}[0-9]{1,3}\b`) ipv6Regex := regexp.MustCompile(`\b([0-9a-fA-F:]+:+[0-9a-fA-F]{0,4})(?:%[0-9a-zA-Z]+)?(?:\/[0-9]{1,3})?(?::[0-9]{1,5})?\b`) + // Reverse zones go first and are then held out of the passes below: their + // labels are digits, which the address patterns would otherwise consume. + str, restoreZones := a.replaceReverseZones(str) + str = ipv4Regex.ReplaceAllStringFunc(str, a.AnonymizeIPString) str = ipv6Regex.ReplaceAllStringFunc(str, a.AnonymizeIPString) - for domain, anonDomain := range a.domainAnonymizer { - str = strings.ReplaceAll(str, domain, anonDomain) + for _, domain := range a.sortedDomains() { + str = strings.ReplaceAll(str, domain, a.domainAnonymizer[domain]) } str = a.AnonymizeSchemeURI(str) str = a.AnonymizeDNSLogLine(str) - return str + // MAC handling runs after the IP passes so preserved IPv6 addresses are + // already out of the way; the separator guard skips matches embedded in a + // longer colon- or dash-separated sequence (such as an IPv6 tail). + str = a.anonymizeMACsInString(str, macColonRegex, ':') + str = a.anonymizeMACsInString(str, macDashRegex, '-') + + if a.level >= LevelStrict { + str = wgKeyRegex.ReplaceAllStringFunc(str, a.AnonymizeWGKey) + } + + return restoreZones(str) +} + +// sortedDomains returns the domain mappings longest-first, so a full-FQDN +// mapping (strict level) is applied before the base-domain mapping it +// contains. The order is rebuilt only when domainAnonymizer has grown. +func (a *Anonymizer) sortedDomains() []string { + if len(a.domainOrder) == len(a.domainAnonymizer) { + return a.domainOrder + } + + a.domainOrder = a.domainOrder[:0] + for domain := range a.domainAnonymizer { + a.domainOrder = append(a.domainOrder, domain) + } + slices.SortFunc(a.domainOrder, func(x, y string) int { + if d := len(y) - len(x); d != 0 { + return d + } + return strings.Compare(x, y) + }) + return a.domainOrder +} + +// anonymizeMACsInString replaces MAC addresses matched by re, skipping +// matches that directly adjoin another sep so a six-group run inside a longer +// separated sequence is left alone. +func (a *Anonymizer) anonymizeMACsInString(str string, re *regexp.Regexp, sep byte) string { + matches := re.FindAllStringIndex(str, -1) + if len(matches) == 0 { + return str + } + + var b strings.Builder + last := 0 + for _, m := range matches { + if (m[0] > 0 && str[m[0]-1] == sep) || (m[1] < len(str) && str[m[1]] == sep) { + continue + } + b.WriteString(str[last:m[0]]) + b.WriteString(a.AnonymizeMAC(str[m[0]:m[1]])) + last = m[1] + } + b.WriteString(str[last:]) + return b.String() } // AnonymizeSchemeURI finds and anonymizes URIs with ws, wss, rel, rels, stun, stuns, turn, and turns schemes. @@ -239,10 +530,79 @@ func isWellKnown(addr netip.Addr) bool { "128.0.0.0", "8000::", // 2nd split subnet for default routes } - if slices.Contains(wellKnown, addr.String()) { + return slices.Contains(wellKnown, addr.String()) +} + +// isInternal reports whether ip identifies a host only within the local +// network: IPv4 private (RFC 1918), CGNAT (RFC 6598), and link-local (v4 and +// v6). These are preserved at the default level so support can reason about +// the real topology, and replaced from the internal pools at the strict +// level. IPv6 ULA is deliberately not internal: its random global ID uniquely +// fingerprints the network, so it is anonymized at every level. +func isInternal(ip netip.Addr) bool { + return (ip.Is4() && ip.IsPrivate()) || + ip.IsLinkLocalUnicast() || + isCGNAT(ip) +} + +func inPoolRange(ip, start, current netip.Addr) bool { + return ip.Compare(start) >= 0 && ip.Compare(current) <= 0 +} + +// isWellKnownMAC reports whether hw carries no stable host identity: all-zero +// or a group address (broadcast and multicast). +func isWellKnownMAC(hw net.HardwareAddr) bool { + if hw[0]&1 == 1 { return true } + for _, b := range hw { + if b != 0 { + return false + } + } + return true +} +// looksLikeWGKey reports whether s has the shape of a WireGuard key: +// 44 base64 characters decoding to 32 bytes. +func looksLikeWGKey(s string) bool { + if len(s) != 44 || s[43] != '=' { + return false + } + decoded, err := base64.StdEncoding.DecodeString(s) + return err == nil && len(decoded) == 32 +} + +func generateAnonymousKey() string { + buf := make([]byte, 32) + if _, err := rand.Read(buf); err != nil { + return strings.Repeat("A", 43) + "=" + } + return base64.StdEncoding.EncodeToString(buf) +} + +// protectedSuffix returns the protected NetBird suffix baseDomain ends with, +// or empty. The match is label-anchored so an unrelated domain that merely +// ends in the same characters is not preserved. +func protectedSuffix(baseDomain string) string { + for _, d := range protectedDomains { + if baseDomain == d || strings.HasSuffix(baseDomain, "."+d) { + return d + } + } + return "" +} + +func withTrailingDot(domain string, hasDot bool) string { + if hasDot { + return domain + "." + } + return domain +} + +// isCGNAT reports whether addr is in 100.64.0.0/10 (RFC 6598), the range +// NetBird assigns overlay peer addresses from. +func isCGNAT(addr netip.Addr) bool { cgnatRangeStart := netip.AddrFrom4([4]byte{100, 64, 0, 0}) cgnatRange := netip.PrefixFrom(cgnatRangeStart, 10) diff --git a/client/anonymize/anonymize_test.go b/client/anonymize/anonymize_test.go index 852315fa1..7c3c7bcf8 100644 --- a/client/anonymize/anonymize_test.go +++ b/client/anonymize/anonymize_test.go @@ -1,8 +1,11 @@ package anonymize_test import ( + "bytes" + "encoding/base64" "net/netip" "regexp" + "strings" "testing" "github.com/stretchr/testify/assert" @@ -44,6 +47,301 @@ func TestAnonymizeIP(t *testing.T) { } } +func TestParseLevel(t *testing.T) { + tests := []struct { + input string + expect anonymize.Level + }{ + {"", anonymize.LevelDefault}, + {"default", anonymize.LevelDefault}, + {"DEFAULT", anonymize.LevelDefault}, + {"strict", anonymize.LevelStrict}, + {"STRICT", anonymize.LevelStrict}, + // Unknown values must never yield less anonymization than requested. + {"garbage", anonymize.LevelStrict}, + } + + for _, tc := range tests { + t.Run("input="+tc.input, func(t *testing.T) { + assert.Equal(t, tc.expect, anonymize.ParseLevel(tc.input), "parsed level should match") + }) + } +} + +func TestAnonymizeIP_DefaultLevelInternalRanges(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + + tests := []struct { + name string + ip string + expect string + }{ + {"RFC1918 10/8", "10.1.2.3", "10.1.2.3"}, + {"RFC1918 172.16/12", "172.16.5.5", "172.16.5.5"}, + {"RFC1918 192.168/16", "192.168.1.1", "192.168.1.1"}, + {"CGNAT", "100.64.0.5", "100.64.0.5"}, + {"IPv4 link-local", "169.254.1.1", "169.254.1.1"}, + {"IPv6 link-local", "fe80::1", "fe80::1"}, + // ULA is anonymized even at the default level: its random global ID + // uniquely fingerprints the network, unlike shared RFC 1918 space. + {"IPv6 ULA", "fd12:3456:789a::1", "2001:db8:ffff::"}, + // 4-in-6 addresses classify like their unmapped IPv4 form. + {"4-in-6 RFC1918", "::ffff:192.168.1.1", "192.168.1.1"}, + {"4-in-6 CGNAT", "::ffff:100.64.0.5", "100.64.0.5"}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + result := anonymizer.AnonymizeIP(netip.MustParseAddr(tc.ip)) + assert.Equal(t, tc.expect, result.String(), "default level should preserve internal ranges except ULA") + }) + } +} + +func TestAnonymizeIP_StrictLevel(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + // Order matters: internal pool addresses are assigned sequentially. + tests := []struct { + name string + ip string + expect string + }{ + {"RFC1918 192.168/16", "192.168.1.1", "198.18.0.0"}, + {"Second RFC1918", "192.168.1.2", "198.18.0.1"}, + {"Repeated RFC1918", "192.168.1.1", "198.18.0.0"}, + {"RFC1918 10/8", "10.1.2.3", "198.18.0.2"}, + {"RFC1918 172.16/12", "172.16.5.5", "198.18.0.3"}, + {"CGNAT", "100.64.0.5", "198.18.0.4"}, + {"IPv4 link-local", "169.254.1.1", "198.18.0.5"}, + {"Public IPv4 uses public pool", "1.2.3.4", "198.51.100.0"}, + {"IPv6 link-local", "fe80::1", "2001:db8:1::"}, + {"IPv6 ULA", "fd12:3456:789a::1", "2001:db8:1::1"}, + {"Public IPv6 uses public pool", "2607:f8b0:4005:805::200e", "2001:db8:ffff::"}, + {"Loopback IPv4", "127.0.0.1", "127.0.0.1"}, + {"Loopback IPv6", "::1", "::1"}, + {"Unspecified", "0.0.0.0", "0.0.0.0"}, + {"Multicast", "224.0.0.251", "224.0.0.251"}, + {"Well known resolver", "8.8.8.8", "8.8.8.8"}, + {"Well known split marker", "128.0.0.0", "128.0.0.0"}, + {"In internal pool range", "198.18.0.3", "198.18.0.3"}, + {"In public pool range", "198.51.100.0", "198.51.100.0"}, + {"4-in-6 repeated RFC1918", "::ffff:192.168.1.1", "198.18.0.0"}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + result := anonymizer.AnonymizeIP(netip.MustParseAddr(tc.ip)) + assert.Equal(t, tc.expect, result.String(), "strict level should replace internal ranges from the internal pools") + }) + } +} + +func TestAnonymizeString_StrictInternalIPs(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + input := "route 10.20.30.0/24 via 192.168.1.1 dev eth0 src 100.64.0.7" + firstPass := anonymizer.AnonymizeString(input) + secondPass := anonymizer.AnonymizeString(firstPass) + + assert.NotContains(t, firstPass, "10.20.30.0", "private network address should be anonymized") + assert.NotContains(t, firstPass, "192.168.1.1", "private gateway should be anonymized") + assert.NotContains(t, firstPass, "100.64.0.7", "CGNAT address should be anonymized") + assert.Contains(t, firstPass, "/24", "prefix length should be preserved") + assert.Equal(t, firstPass, secondPass, "second pass should not further anonymize the string") +} + +func TestAnonymizeMAC(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + + first := anonymizer.AnonymizeMAC("aa:bb:cc:dd:ee:0f") + assert.Equal(t, "02:00:00:00:00:01", first, "first MAC should get the first placeholder") + assert.Equal(t, first, anonymizer.AnonymizeMAC("aa:bb:cc:dd:ee:0f"), "repeated MAC should map to the same placeholder") + assert.Equal(t, first, anonymizer.AnonymizeMAC("AA:BB:CC:DD:EE:0F"), "case should not affect the mapping") + assert.Equal(t, "02-00-00-00-00-01", anonymizer.AnonymizeMAC("AA-BB-CC-DD-EE-0F"), "dash form should keep its separator but share the mapping") + + second := anonymizer.AnonymizeMAC("10:22:33:44:55:66") + assert.Equal(t, "02:00:00:00:00:02", second, "second distinct MAC should get the next placeholder") + + tests := []struct { + name string + mac string + }{ + {"Broadcast", "ff:ff:ff:ff:ff:ff"}, + {"IPv4 multicast", "01:00:5e:00:00:fb"}, + {"IPv6 multicast", "33:33:00:00:00:01"}, + {"All zero", "00:00:00:00:00:00"}, + {"Assigned placeholder", "02:00:00:00:00:01"}, + {"Invalid", "not-a-mac"}, + } + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + assert.Equal(t, tc.mac, anonymizer.AnonymizeMAC(tc.mac), "should be preserved") + }) + } +} + +func TestAnonymizeString_MACAddresses(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + + tests := []struct { + name string + input string + expect string + }{ + { + name: "nftables ether rule", + input: "ether saddr aa:bb:cc:dd:ee:ff drop", + expect: "ether saddr 02:00:00:00:00:01 drop", + }, + { + name: "Windows dash form", + input: "Physical Address : AA-BB-CC-DD-EE-FF", + expect: "Physical Address : 02-00-00-00-00-01", + }, + { + name: "IPv6 address tail is not treated as MAC", + input: "addr fe80:0:11:22:33:44:55:66 scope link", + expect: "addr fe80:0:11:22:33:44:55:66 scope link", + }, + { + name: "broadcast MAC preserved", + input: "dst ff:ff:ff:ff:ff:ff type ARP", + expect: "dst ff:ff:ff:ff:ff:ff type ARP", + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + result := anonymizer.AnonymizeString(tc.input) + assert.Equal(t, tc.expect, result, "MAC addresses should be anonymized at every level") + assert.Equal(t, result, anonymizer.AnonymizeString(result), "second pass should not change the result") + }) + } +} + +func TestAnonymizeWGKey(t *testing.T) { + key := base64.StdEncoding.EncodeToString(bytes.Repeat([]byte{0x42}, 32)) + + t.Run("default level preserves keys", func(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + assert.Equal(t, key, anonymizer.AnonymizeWGKey(key), "default level should not touch WireGuard keys") + }) + + t.Run("strict level replaces keys", func(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + anon := anonymizer.AnonymizeWGKey(key) + assert.NotEqual(t, key, anon, "strict level should replace the key") + assert.Regexp(t, `^[A-Za-z0-9+/]{43}=$`, anon, "placeholder should keep the WireGuard key shape") + assert.Equal(t, anon, anonymizer.AnonymizeWGKey(key), "repeated key should map to the same placeholder") + assert.Equal(t, anon, anonymizer.AnonymizeWGKey(anon), "an assigned placeholder should pass through unchanged") + + assert.Equal(t, "not-a-key", anonymizer.AnonymizeWGKey("not-a-key"), "non-key values should be preserved") + }) +} + +func TestAnonymizeString_WGKeys(t *testing.T) { + key := base64.StdEncoding.EncodeToString(bytes.Repeat([]byte{0x42}, 32)) + input := "peer " + key + " handshake completed" + + t.Run("default level preserves keys", func(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + assert.Equal(t, input, anonymizer.AnonymizeString(input), "default level should not touch WireGuard keys in strings") + }) + + t.Run("strict level replaces keys", func(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + firstPass := anonymizer.AnonymizeString(input) + assert.NotContains(t, firstPass, key, "the key should not survive strict anonymization") + assert.Equal(t, anonymizer.AnonymizeWGKey(key), extractKey(t, firstPass), "string replacement should be consistent with AnonymizeWGKey") + assert.Equal(t, firstPass, anonymizer.AnonymizeString(firstPass), "second pass should not change the result") + }) +} + +func extractKey(t *testing.T, logLine string) string { + t.Helper() + fields := strings.Fields(logLine) + require.Len(t, fields, 4, "log line should keep its structure") + return fields[1] +} + +func TestAnonymizeDomain_StrictLevel(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + t.Run("netbird peer name", func(t *testing.T) { + result := anonymizer.AnonymizeDomain("my-laptop.netbird.cloud") + assert.Regexp(t, `^peer-\d+\.netbird\.cloud$`, result, "peer name should be anonymized, suffix kept") + assert.NotContains(t, result, "my-laptop", "the peer name should not survive") + assert.Equal(t, result, anonymizer.AnonymizeDomain("my-laptop.netbird.cloud"), "repeated domain should map consistently") + assert.Equal(t, result, anonymizer.AnonymizeDomain(result), "an anonymized domain should pass through unchanged") + }) + + t.Run("bare netbird domain", func(t *testing.T) { + assert.Equal(t, "netbird.cloud", anonymizer.AnonymizeDomain("netbird.cloud"), "the bare protected suffix should be preserved") + }) + + t.Run("netbird infrastructure preserved", func(t *testing.T) { + assert.Equal(t, "api.netbird.io", anonymizer.AnonymizeDomain("api.netbird.io"), + "netbird.io hosts infrastructure, not peer names, and should stay readable") + }) + + t.Run("leading labels of other domains", func(t *testing.T) { + result := anonymizer.AnonymizeDomain("host1.corp.example.com") + assert.Regexp(t, `^host-\d+\.host-\d+\.anon-[a-zA-Z0-9]+\.domain$`, result, "every label should be anonymized") + for _, label := range []string{"host1", "corp", "example"} { + assert.NotContains(t, result, label, "no original label should survive") + } + assert.Equal(t, result, anonymizer.AnonymizeDomain("host1.corp.example.com"), "repeated domain should map consistently") + }) + + t.Run("same label maps consistently across domains", func(t *testing.T) { + first := anonymizer.AnonymizeDomain("shared.one.com") + second := anonymizer.AnonymizeDomain("shared.two.com") + assert.Equal(t, strings.Split(first, ".")[0], strings.Split(second, ".")[0], "the shared host label should get one placeholder") + }) + + t.Run("wildcard label preserved", func(t *testing.T) { + result := anonymizer.AnonymizeDomain("*.example.com") + assert.Regexp(t, `^\*\.anon-[a-zA-Z0-9]+\.domain$`, result, "the wildcard label should stay a wildcard") + }) +} + +func TestAnonymizeDomain_DefaultLevelKeepsPeerNames(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + + assert.Equal(t, "my-laptop.netbird.cloud", anonymizer.AnonymizeDomain("my-laptop.netbird.cloud"), + "default level should preserve netbird FQDNs including the peer name") + assert.Regexp(t, `^sub\.anon-[a-zA-Z0-9]+\.domain$`, anonymizer.AnonymizeDomain("sub.example.com"), + "default level should keep subdomain labels") +} + +func TestAnonymizeString_StrictPeerNames(t *testing.T) { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(anonymize.LevelStrict) + + // Seed like the bundle generator does from the status: base first, then + // the full FQDN, so replacement must prefer the longer mapping. + anonBase := anonymizer.AnonymizeDomain("example.com") + anonPeer := anonymizer.AnonymizeDomain("peer1.netbird.cloud") + anonHost := anonymizer.AnonymizeDomain("host1.example.com") + + logLine := "connected to peer1.netbird.cloud via host1.example.com endpoint" + firstPass := anonymizer.AnonymizeString(logLine) + assert.NotContains(t, firstPass, "peer1", "the peer name should not survive in logs") + assert.NotContains(t, firstPass, "host1", "the host label should not survive in logs") + assert.Contains(t, firstPass, anonPeer, "the seeded peer mapping should be applied") + assert.Contains(t, firstPass, anonHost, "the seeded host mapping should be applied, not just the base mapping") + assert.NotContains(t, firstPass, "host1."+anonBase, "the base mapping must not preempt the longer FQDN mapping") + assert.Equal(t, firstPass, anonymizer.AnonymizeString(firstPass), "second pass should not change the result") +} + func TestAnonymizeDNSLogLine(t *testing.T) { anonymizer := anonymize.NewAnonymizer(netip.Addr{}, netip.Addr{}) tests := []struct { diff --git a/client/anonymize/reverse_zone.go b/client/anonymize/reverse_zone.go new file mode 100644 index 000000000..b521b71b7 --- /dev/null +++ b/client/anonymize/reverse_zone.go @@ -0,0 +1,174 @@ +package anonymize + +import ( + "encoding/hex" + "net/netip" + "regexp" + "strconv" + "strings" +) + +const ( + reverseZoneSuffixV4 = ".in-addr.arpa" + reverseZoneSuffixV6 = ".ip6.arpa" + + v6Nibbles = 32 + v4Octets = 4 +) + +// reverseZoneRegexes match a reverse zone or a full reverse name in free text. +// They are applied before the address passes of AnonymizeString, whose IPv4 +// pattern would otherwise consume the digit labels of a zone and replace parts +// of it with unrelated addresses. +var reverseZoneRegexes = []*regexp.Regexp{ + regexp.MustCompile(`(?:[0-9]{1,3}\.){1,4}in-addr\.arpa\b`), + regexp.MustCompile(`(?:[0-9a-fA-F]\.){1,32}ip6\.arpa\b`), +} + +// anonymizeReverseZone maps a reverse zone to the zone of the anonymized form +// of the prefix it encodes, so it follows the address rules rather than the +// domain ones: the zone of an address that is preserved is preserved too, and +// the zone of one that is replaced names the replacement. This keeps a reverse +// zone recognizable as such, and consistent with the addresses it belongs to +// elsewhere in the same output. It reports false for anything that is not a +// reverse zone. +func (a *Anonymizer) anonymizeReverseZone(domain string) (string, bool) { + prefix, labelCount, suffix, ok := parseReverseZone(domain) + if !ok { + return "", false + } + + anonymized := a.AnonymizeIP(prefix) + if anonymized == prefix { + return domain, true + } + + return reverseZoneName(anonymized, labelCount) + suffix, true +} + +// replaceReverseZones anonymizes every reverse zone in str and swaps each one +// for a placeholder, returning a function that puts the anonymized zones back. +// The placeholders carry no dots, digits or colons, so no later pass matches +// them. +func (a *Anonymizer) replaceReverseZones(str string) (string, func(string) string) { + var zones []string + + for _, re := range reverseZoneRegexes { + str = re.ReplaceAllStringFunc(str, func(match string) string { + zone, ok := a.anonymizeReverseZone(match) + if !ok { + return match + } + + zones = append(zones, zone) + return reverseZonePlaceholder(len(zones) - 1) + }) + } + + if len(zones) == 0 { + return str, func(s string) string { return s } + } + + return str, func(s string) string { + for i, zone := range zones { + s = strings.ReplaceAll(s, reverseZonePlaceholder(i), zone) + } + return s + } +} + +func reverseZonePlaceholder(index int) string { + return "\x00reversezone" + strconv.Itoa(index) + "\x00" +} + +// parseReverseZone turns a reverse zone into the address of the prefix its +// labels spell backwards, padding the absent low-order part with zeroes, and +// returns the label count and zone suffix so the name can be rebuilt. +func parseReverseZone(domain string) (netip.Addr, int, string, bool) { + lower := strings.ToLower(domain) + + switch { + case strings.HasSuffix(lower, reverseZoneSuffixV4): + labels := strings.Split(strings.TrimSuffix(lower, reverseZoneSuffixV4), ".") + addr, ok := reverseZoneAddrV4(labels) + return addr, len(labels), reverseZoneSuffixV4, ok + case strings.HasSuffix(lower, reverseZoneSuffixV6): + labels := strings.Split(strings.TrimSuffix(lower, reverseZoneSuffixV6), ".") + addr, ok := reverseZoneAddrV6(labels) + return addr, len(labels), reverseZoneSuffixV6, ok + default: + return netip.Addr{}, 0, "", false + } +} + +func reverseZoneAddrV4(labels []string) (netip.Addr, bool) { + if len(labels) == 0 || len(labels) > v4Octets { + return netip.Addr{}, false + } + + var octets [v4Octets]byte + for i, label := range labels { + octet, err := strconv.ParseUint(label, 10, 8) + if err != nil { + return netip.Addr{}, false + } + octets[len(labels)-1-i] = byte(octet) + } + + return netip.AddrFrom4(octets), true +} + +func reverseZoneAddrV6(labels []string) (netip.Addr, bool) { + if len(labels) == 0 || len(labels) > v6Nibbles { + return netip.Addr{}, false + } + + nibbles := make([]byte, 0, v6Nibbles) + for i := len(labels) - 1; i >= 0; i-- { + if len(labels[i]) != 1 || !isHexDigit(labels[i][0]) { + return netip.Addr{}, false + } + nibbles = append(nibbles, labels[i][0]) + } + for len(nibbles) < v6Nibbles { + nibbles = append(nibbles, '0') + } + + var groups []string + for i := 0; i < len(nibbles); i += 4 { + groups = append(groups, string(nibbles[i:i+4])) + } + + addr, err := netip.ParseAddr(strings.Join(groups, ":")) + if err != nil { + return netip.Addr{}, false + } + + return addr, true +} + +// reverseZoneName spells the first labelCount labels of addr backwards, the +// inverse of parseReverseZone, without the zone suffix. +func reverseZoneName(addr netip.Addr, labelCount int) string { + labels := make([]string, 0, labelCount) + + if addr.Is4() { + octets := addr.As4() + for i := labelCount - 1; i >= 0; i-- { + labels = append(labels, strconv.Itoa(int(octets[i]))) + } + return strings.Join(labels, ".") + } + + address := addr.As16() + nibbles := hex.EncodeToString(address[:]) + for i := labelCount - 1; i >= 0; i-- { + labels = append(labels, string(nibbles[i])) + } + + return strings.Join(labels, ".") +} + +func isHexDigit(c byte) bool { + return c >= '0' && c <= '9' || c >= 'a' && c <= 'f' || c >= 'A' && c <= 'F' +} diff --git a/client/anonymize/reverse_zone_test.go b/client/anonymize/reverse_zone_test.go new file mode 100644 index 000000000..8c3b8954a --- /dev/null +++ b/client/anonymize/reverse_zone_test.go @@ -0,0 +1,171 @@ +package anonymize + +import ( + "strings" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +func newLeveledAnonymizer(level Level) *Anonymizer { + a := NewAnonymizer(DefaultAddresses()) + a.SetLevel(level) + return a +} + +// TestAnonymizeDomainReverseZone covers reverse zones going through the address +// rules instead of the domain ones, so a zone stays a zone and an address that +// is preserved keeps the zone that names it. +func TestAnonymizeDomainReverseZone(t *testing.T) { + // 100.64.0.0/10 is the overlay range, which is CGNAT: preserved at the + // default level and replaced from the internal pool at the strict one + const overlayZone = "64.100.in-addr.arpa" + + t.Run("overlay zone preserved at the default level", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + assert.Equal(t, overlayZone, a.AnonymizeDomain(overlayZone), "should keep the zone of a preserved address") + }) + + t.Run("private zone preserved at the default level", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + assert.Equal(t, "168.192.in-addr.arpa", a.AnonymizeDomain("168.192.in-addr.arpa"), "should keep the zone of a private address") + }) + + t.Run("overlay zone replaced at the strict level", func(t *testing.T) { + a := newLeveledAnonymizer(LevelStrict) + + got := a.AnonymizeDomain(overlayZone) + require.True(t, strings.HasSuffix(got, reverseZoneSuffixV4), "should stay a reverse zone, got %q", got) + assert.NotEqual(t, overlayZone, got, "should replace the encoded prefix") + assert.Len(t, strings.Split(strings.TrimSuffix(got, reverseZoneSuffixV4), "."), 2, + "should keep the label count, got %q", got) + }) + + t.Run("public zone replaced at the default level", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + got := a.AnonymizeDomain("113.0.203.in-addr.arpa") + require.True(t, strings.HasSuffix(got, reverseZoneSuffixV4), "should stay a reverse zone, got %q", got) + assert.NotEqual(t, "113.0.203.in-addr.arpa", got, "should replace a public prefix") + }) + + t.Run("zone of an address keeps that address mapping", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + anonymizedAddr := a.AnonymizeIPString("203.0.113.7") + got := a.AnonymizeDomain("7.113.0.203.in-addr.arpa") + + octets := strings.Split(anonymizedAddr, ".") + want := octets[3] + "." + octets[2] + "." + octets[1] + "." + octets[0] + reverseZoneSuffixV4 + assert.Equal(t, want, got, "should name the same replacement as the address itself") + }) + + t.Run("ipv6 nibble labels stay single digits", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + zone := "0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.2.0.0.0" + reverseZoneSuffixV6 + got := a.AnonymizeDomain(zone) + + require.True(t, strings.HasSuffix(got, reverseZoneSuffixV6), "should stay a reverse zone, got %q", got) + labels := strings.Split(strings.TrimSuffix(got, reverseZoneSuffixV6), ".") + assert.Len(t, labels, 28, "should keep every nibble label, got %q", got) + for _, label := range labels { + assert.Len(t, label, 1, "nibble label %q should stay a single digit", label) + } + }) + + t.Run("trailing dot is kept", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + assert.Equal(t, "64.100.in-addr.arpa.", a.AnonymizeDomain("64.100.in-addr.arpa."), "should keep the trailing dot") + }) + + t.Run("a domain that only looks like a zone is anonymized as a domain", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + got := a.AnonymizeDomain("not-a-zone.in-addr.arpa") + assert.NotContains(t, got, "in-addr.arpa", "should fall back to domain anonymization") + }) +} + +// TestAnonymizeStringReverseZone verifies that a zone inside free text, such as +// a DNS log line, is not chewed up by the address passes. The IPv4 pattern +// matches any run of dotted digits, which a reverse zone is made of. +func TestAnonymizeStringReverseZone(t *testing.T) { + t.Run("ipv6 zone survives the address passes", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + zone := "0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.2.0.0.0" + reverseZoneSuffixV6 + got := a.AnonymizeString("question: domain=" + zone + " type=PTR") + + assert.Contains(t, got, "type=PTR", "should keep the rest of the line") + assert.NotContains(t, got, "198.51.100", "should not rewrite nibble labels as an address") + + labels := strings.Split(strings.TrimSuffix(strings.TrimPrefix(got, "question: domain="), reverseZoneSuffixV6+" type=PTR"), ".") + assert.Len(t, labels, 28, "should keep every nibble label, got %q", got) + }) + + t.Run("preserved ipv4 zone is untouched", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + line := "reverse zone 64.100.in-addr.arpa registered" + assert.Equal(t, line, a.AnonymizeString(line), "should keep the zone of a preserved address") + }) + + t.Run("public ipv4 zone is replaced consistently", func(t *testing.T) { + a := newLeveledAnonymizer(LevelDefault) + + got := a.AnonymizeString("zone 113.0.203.in-addr.arpa and address 203.0.113.7") + assert.NotContains(t, got, "113.0.203.in-addr.arpa", "should replace the zone") + assert.NotContains(t, got, "203.0.113.7", "should replace the address") + assert.Contains(t, got, reverseZoneSuffixV4, "should keep the zone suffix") + }) +} + +func TestParseReverseZone(t *testing.T) { + tests := []struct { + name string + zone string + addr string + labels int + }{ + {name: "v4 two labels", zone: "0.100" + reverseZoneSuffixV4, addr: "100.0.0.0", labels: 2}, + {name: "v4 three labels", zone: "1.168.192" + reverseZoneSuffixV4, addr: "192.168.1.0", labels: 3}, + {name: "v4 full address", zone: "7.113.0.203" + reverseZoneSuffixV4, addr: "203.0.113.7", labels: 4}, + { + name: "v6 prefix", + zone: "0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.0.2.0.0.0" + reverseZoneSuffixV6, + addr: "2::", + labels: 28, + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + addr, labels, suffix, ok := parseReverseZone(tc.zone) + require.True(t, ok, "should decode the reverse zone") + assert.Equal(t, tc.addr, addr.String(), "should decode to the encoded prefix") + assert.Equal(t, tc.labels, labels, "should count the labels") + assert.Equal(t, tc.zone, reverseZoneName(addr, labels)+suffix, "should re-encode to the original zone") + }) + } +} + +func TestParseReverseZoneRejectsNonZones(t *testing.T) { + tests := []string{ + "example.com", + "in-addr.arpa", + "x.100" + reverseZoneSuffixV4, + "256" + reverseZoneSuffixV4, + "1.2.3.4.5" + reverseZoneSuffixV4, + "ab" + reverseZoneSuffixV6, + "g" + reverseZoneSuffixV6, + } + + for _, zone := range tests { + t.Run(zone, func(t *testing.T) { + _, _, _, ok := parseReverseZone(zone) + assert.False(t, ok, "should reject %q", zone) + }) + } +} diff --git a/client/cmd/debug.go b/client/cmd/debug.go index 7ddc3afc4..893b1e248 100644 --- a/client/cmd/debug.go +++ b/client/cmd/debug.go @@ -27,8 +27,8 @@ import ( const errCloseConnection = "Failed to close connection: %v" var ( - logFileCount uint32 - systemInfoFlag bool + logFileCount uint32 + systemInfoFlag bool uploadBundleFlag bool uploadBundleURLFlag string uploadBundleInsecureFlag bool @@ -156,6 +156,11 @@ func debugConfigDump(cmd *cobra.Command, _ []string) error { // request. Returns an error if the RPC fails or if the daemon reports // an upload failure reason. func debugBundle(cmd *cobra.Command, _ []string) error { + anonymizeEnabled, anonymizeLevel, err := effectiveAnonymize() + if err != nil { + return err + } + conn, err := getClient(cmd) if err != nil { return err @@ -168,10 +173,11 @@ func debugBundle(cmd *cobra.Command, _ []string) error { client := proto.NewDaemonServiceClient(conn) request := &proto.DebugBundleRequest{ - Anonymize: anonymizeFlag, - SystemInfo: systemInfoFlag, - LogFileCount: logFileCount, - CliVersion: version.NetbirdVersion(), + Anonymize: anonymizeEnabled, + AnonymizeLevel: anonymizeLevel.String(), + SystemInfo: systemInfoFlag, + LogFileCount: logFileCount, + CliVersion: version.NetbirdVersion(), } if uploadBundleFlag { request.UploadURL = uploadBundleURLFlag @@ -229,6 +235,11 @@ func runForDuration(cmd *cobra.Command, args []string) error { return fmt.Errorf("invalid duration format: %v", err) } + anonymizeEnabled, anonymizeLevel, err := effectiveAnonymize() + if err != nil { + return err + } + conn, err := getClient(cmd) if err != nil { return err @@ -368,10 +379,11 @@ func runForDuration(cmd *cobra.Command, args []string) error { cmd.Println("Creating debug bundle...") request := &proto.DebugBundleRequest{ - Anonymize: anonymizeFlag, - SystemInfo: systemInfoFlag, - LogFileCount: logFileCount, - CliVersion: version.NetbirdVersion(), + Anonymize: anonymizeEnabled, + AnonymizeLevel: anonymizeLevel.String(), + SystemInfo: systemInfoFlag, + LogFileCount: logFileCount, + CliVersion: version.NetbirdVersion(), } if uploadBundleFlag { request.UploadURL = uploadBundleURLFlag diff --git a/client/cmd/login.go b/client/cmd/login.go index fb1232325..8171bf901 100644 --- a/client/cmd/login.go +++ b/client/cmd/login.go @@ -5,7 +5,6 @@ import ( "fmt" "os" "os/user" - "runtime" "strings" log "github.com/sirupsen/logrus" @@ -122,7 +121,7 @@ func doDaemonLogin(ctx context.Context, cmd *cobra.Command, providedSetupKey str loginRequest := proto.LoginRequest{ SetupKey: providedSetupKey, ManagementUrl: managementURL, - IsUnixDesktopClient: isUnixRunningDesktop(), + IsUnixDesktopClient: util.HasGraphicalSession(), Hostname: hostName, DnsLabels: dnsLabelsReq, ProfileName: &handle, @@ -190,7 +189,8 @@ func doExtendSession(ctx context.Context, cmd *cobra.Command) error { client := proto.NewDaemonServiceClient(conn) - req := &proto.RequestExtendAuthSessionRequest{} + // the CLI runs in the user's session, the daemon does not: tell it what we can see + req := &proto.RequestExtendAuthSessionRequest{HasGraphicalSession: util.HasGraphicalSession()} // Pre-fill the IdP login hint from the active profile so the user // doesn't have to retype their email. Best-effort: we still proceed // without a hint if the lookup fails. @@ -414,7 +414,7 @@ func foregroundGetTokenInfo(ctx context.Context, cmd *cobra.Command, config *pro hint = profileState.Email } - oAuthFlow, err := auth.NewOAuthFlow(ctx, config, isUnixRunningDesktop(), false, hint) + oAuthFlow, err := auth.NewOAuthFlow(ctx, config, util.HasGraphicalSession(), false, hint) if err != nil { return nil, err } @@ -464,14 +464,6 @@ func openURL(cmd *cobra.Command, verificationURIComplete, userCode string, noBro } } -// isUnixRunningDesktop checks if a Linux OS is running desktop environment -func isUnixRunningDesktop() bool { - if runtime.GOOS != "linux" && runtime.GOOS != "freebsd" { - return false - } - return os.Getenv("DESKTOP_SESSION") != "" || os.Getenv("XDG_CURRENT_DESKTOP") != "" -} - func setEnvAndFlags(cmd *cobra.Command) error { SetFlagsFromEnvVars(rootCmd) diff --git a/client/cmd/root.go b/client/cmd/root.go index ebaae7e3e..ccad78942 100644 --- a/client/cmd/root.go +++ b/client/cmd/root.go @@ -21,6 +21,7 @@ import ( "github.com/spf13/pflag" "google.golang.org/grpc" + "github.com/netbirdio/netbird/client/anonymize" daddr "github.com/netbirdio/netbird/client/internal/daemonaddr" "github.com/netbirdio/netbird/client/internal/profilemanager" ) @@ -69,6 +70,7 @@ var ( autoConnectDisabled bool extraIFaceBlackList []string anonymizeFlag bool + anonymizeLevelFlag string dnsRouteInterval time.Duration // lazyConnEnabled is the parse target for the deprecated --enable-lazy-connection // flag. The flag is inert; the value is no longer read (use NB_LAZY_CONN instead). @@ -156,7 +158,8 @@ func init() { rootCmd.MarkFlagsMutuallyExclusive("setup-key", "setup-key-file") rootCmd.PersistentFlags().StringVar(&preSharedKey, preSharedKeyFlag, "", "Sets WireGuard PreSharedKey property. If set, then only peers that have the same key can communicate.") rootCmd.PersistentFlags().StringVarP(&hostName, "hostname", "n", "", "Sets a custom hostname for the device") - rootCmd.PersistentFlags().BoolVarP(&anonymizeFlag, "anonymize", "A", false, "anonymize IP addresses and non-netbird.io domains in logs and status output") + rootCmd.PersistentFlags().BoolVarP(&anonymizeFlag, "anonymize", "A", false, "anonymize public IP addresses, MAC addresses, and non-netbird.io domains in logs and status output; private, CGNAT, and link-local IP ranges are kept (see --anonymize-level strict)") + rootCmd.PersistentFlags().StringVar(&anonymizeLevelFlag, "anonymize-level", "", "anonymization level: \"default\" or \"strict\"; strict also anonymizes private, CGNAT, and link-local IP ranges, peer names, and WireGuard public keys. Setting this flag implies --anonymize") rootCmd.PersistentFlags().StringVarP(&configPath, "config", "c", profilemanager.DefaultConfigPath, "Overrides the default profile file location") rootCmd.AddCommand(upCmd) @@ -293,6 +296,19 @@ var CLIBackOffSettings = &backoff.ExponentialBackOff{ Clock: backoff.SystemClock, } +// effectiveAnonymize resolves the --anonymize and --anonymize-level flags: +// setting a level implies anonymization, and an invalid level is rejected. +func effectiveAnonymize() (bool, anonymize.Level, error) { + if anonymizeLevelFlag == "" { + return anonymizeFlag, anonymize.LevelDefault, nil + } + level := anonymize.ParseLevel(anonymizeLevelFlag) + if !strings.EqualFold(anonymizeLevelFlag, level.String()) { + return false, anonymize.LevelDefault, fmt.Errorf("invalid anonymize level %q: use %q or %q", anonymizeLevelFlag, anonymize.LevelDefault.String(), anonymize.LevelStrict.String()) + } + return true, level, nil +} + func getSetupKey() (string, error) { if setupKeyPath != "" && setupKey == "" { return getSetupKeyFromFile(setupKeyPath) diff --git a/client/cmd/service_controller.go b/client/cmd/service_controller.go index 9ba3bce25..b187a7b87 100644 --- a/client/cmd/service_controller.go +++ b/client/cmd/service_controller.go @@ -45,8 +45,8 @@ func daemonServerOptions(network string) []grpc.ServerOption { return nil } - creds := ipcauth.NewTransportCredentials() - if creds == nil { + creds := ipcauth.NewTransportCredentials() //nolint:staticcheck + if creds == nil { //nolint:staticcheck // nil only on platforms without a peer-identity primitive log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS) return nil } diff --git a/client/cmd/service_socket.go b/client/cmd/service_socket.go index ed1f001a7..bf3122f7c 100644 --- a/client/cmd/service_socket.go +++ b/client/cmd/service_socket.go @@ -27,8 +27,8 @@ func listenOnAddress(addr string) (*socketListener, error) { } if network == "npipe" { - listener, path, err := listenNamedPipe(address) - if err != nil { + listener, path, err := listenNamedPipe(address) //nolint:staticcheck + if err != nil { //nolint:staticcheck // always errors on non-Windows builds return nil, err } return &socketListener{Listener: listener, network: network, address: path}, nil diff --git a/client/cmd/status.go b/client/cmd/status.go index c4057ed82..f2e5bcc66 100644 --- a/client/cmd/status.go +++ b/client/cmd/status.go @@ -121,8 +121,14 @@ func statusFunc(cmd *cobra.Command, args []string) error { sessionExpiresAt = ts.AsTime().UTC() } + anonymizeEnabled, anonymizeLevel, err := effectiveAnonymize() + if err != nil { + return err + } + var outputInformationHolder = nbstatus.ConvertToStatusOutputOverview(resp.GetFullStatus(), nbstatus.ConvertOptions{ - Anonymize: anonymizeFlag, + Anonymize: anonymizeEnabled, + AnonymizeLevel: anonymizeLevel, DaemonVersion: resp.GetDaemonVersion(), DaemonStatus: nbstatus.ParseDaemonStatus(status), StatusFilter: statusFilter, diff --git a/client/cmd/testutil_test.go b/client/cmd/testutil_test.go index 205327ef5..f40056f83 100644 --- a/client/cmd/testutil_test.go +++ b/client/cmd/testutil_test.go @@ -6,7 +6,7 @@ import ( "testing" "time" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/stretchr/testify/require" "go.opentelemetry.io/otel" "google.golang.org/grpc" diff --git a/client/cmd/up.go b/client/cmd/up.go index cf042e3be..77224a358 100644 --- a/client/cmd/up.go +++ b/client/cmd/up.go @@ -21,9 +21,13 @@ import ( "github.com/netbirdio/netbird/client/internal" "github.com/netbirdio/netbird/client/internal/peer" "github.com/netbirdio/netbird/client/internal/profilemanager" +<<<<<<< HEAD "github.com/netbirdio/netbird/client/mdm" "github.com/netbirdio/netbird/client/proto" +======= +>>>>>>> main nbnet "github.com/netbirdio/netbird/client/net" + "github.com/netbirdio/netbird/client/proto" "github.com/netbirdio/netbird/client/server" "github.com/netbirdio/netbird/client/system" "github.com/netbirdio/netbird/shared/management/domain" @@ -631,7 +635,7 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte NatExternalIPs: natExternalIPs, CleanNATExternalIPs: natExternalIPs != nil && len(natExternalIPs) == 0, CustomDNSAddress: customDNSAddressConverted, - IsUnixDesktopClient: isUnixRunningDesktop(), + IsUnixDesktopClient: util.HasGraphicalSession(), Hostname: hostName, ExtraIFaceBlacklist: extraIFaceBlackList, DnsLabels: dnsLabels, diff --git a/client/embed/embed.go b/client/embed/embed.go index 2bde0fdff..3d884a228 100644 --- a/client/embed/embed.go +++ b/client/embed/embed.go @@ -21,8 +21,12 @@ import ( "github.com/netbirdio/netbird/client/internal/auth" "github.com/netbirdio/netbird/client/internal/peer" "github.com/netbirdio/netbird/client/internal/profilemanager" +<<<<<<< HEAD "github.com/netbirdio/netbird/client/mdm" sshcommon "github.com/netbirdio/netbird/client/ssh" +======= + nbssh "github.com/netbirdio/netbird/client/ssh" +>>>>>>> main "github.com/netbirdio/netbird/client/system" "github.com/netbirdio/netbird/shared/management/domain" mgmProto "github.com/netbirdio/netbird/shared/management/proto" @@ -92,6 +96,13 @@ type Options struct { // when the embedded client must never act as a stepping stone into // the host's local network (e.g. the proxy's overlay peer). BlockLANAccess bool + // LazyConnectionEnabled is a tri-state local override for lazy connections, + // mirroring the NB_LAZY_CONN env var. Nil defers to the management feature + // flag; a set value overrides it in both directions. A short-lived client + // that reaches only a few known peers can set this to false, so its peers + // connect eagerly and the first request does not wait for the connection to + // be established. + LazyConnectionEnabled *bool // WireguardPort is the port for the tunnel interface. Use 0 for a random port. WireguardPort *int // MTU is the MTU for the tunnel interface. @@ -225,6 +236,15 @@ func New(opts Options) (*Client, error) { config.PrivateKey = opts.PrivateKey } + if opts.LazyConnectionEnabled != nil { + // Runtime-only override, read back through lazyconn.ParseState; a set value + // wins over the management feature flag in both directions. + config.LazyConnection = "off" + if *opts.LazyConnectionEnabled { + config.LazyConnection = "on" + } + } + if opts.Performance.PreallocatedBuffersPerPool != nil { wgdevice.SetPreallocatedBuffersPerPool(*opts.Performance.PreallocatedBuffersPerPool) } @@ -526,12 +546,7 @@ func (c *Client) VerifySSHHostKey(peerAddress string, key []byte) error { return err } - storedKey, found := engine.GetPeerSSHKey(peerAddress) - if !found { - return sshcommon.ErrPeerNotFound - } - - return sshcommon.VerifyHostKey(storedKey, key, peerAddress) + return nbssh.PeerKeyLookup(engine.GetPeerSSHKey).VerifySSHHostKey(peerAddress, key) } // SetPerformance retunes a running Client. Only PreallocatedBuffersPerPool diff --git a/client/embed/embed_test.go b/client/embed/embed_test.go index a2f438975..27beb8934 100644 --- a/client/embed/embed_test.go +++ b/client/embed/embed_test.go @@ -6,7 +6,7 @@ import ( "testing" "time" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/stretchr/testify/require" "google.golang.org/grpc" diff --git a/client/firewall/iptables/acl_linux.go b/client/firewall/iptables/acl_linux.go index 4b4cebf9c..89d1ebf7c 100644 --- a/client/firewall/iptables/acl_linux.go +++ b/client/firewall/iptables/acl_linux.go @@ -42,6 +42,7 @@ type aclManager struct { optionalEntries map[string][]entry ipsetStore *ipsetStore v6 bool + ipsetSupported bool stateManager *statemanager.Manager } @@ -60,6 +61,8 @@ func newAclManager(iptablesClient *iptables.IPTables, wgIface iFaceMapper) (*acl func (m *aclManager) init(stateManager *statemanager.Manager) error { m.stateManager = stateManager + m.ipsetSupported = m.probeIPSetSupport() + m.seedInitialEntries() m.seedInitialOptionalEntries() @@ -91,6 +94,12 @@ func (m *aclManager) AddPeerFiltering( if m.v6 && ipsetName != "" { ipsetName += "-v6" } + // When the kernel lacks the required ipset hash module, fall back to + // per-IP iptables rules (pre-0.68 behavior) so ACLs keep working instead + // of silently leaving the chain empty. + if ipsetName != "" && !m.ipsetSupported { + ipsetName = "" + } proto := protoForFamily(protocol, m.v6) specs := filterRuleSpecs(ip, proto, sPort, dPort, action, ipsetName) @@ -498,6 +507,40 @@ func transformIPsetName(ipsetName string, sPort, dPort *firewall.Port, action fi } } +// probeIPSetSupport checks whether the kernel can create the ipset type used for +// ACL rules. On kernels lacking the required ipset hash module, ipset creation +// fails (e.g. "invalid argument"), which would otherwise leave the ACL chain +// empty and silently drop all policy-permitted inbound traffic. When unsupported, +// the manager falls back to per-IP iptables rules. +func (m *aclManager) probeIPSetSupport() bool { + // Use a unique name so concurrent processes don't collide and we only ever + // destroy the set we created ourselves. ipset names are limited to 31 chars, + // so use a short random suffix. + probeName := "nb-probe-" + uuid.New().String()[:8] + + opts := ipset.CreateOptions{ + Replace: true, + } + if m.v6 { + opts.Family = ipset.FamilyIPV6 + } + + if err := ipset.Create(probeName, ipset.TypeHashNet, opts); err != nil { + log.Warnf("ipset is not available (failed to create probe set: %v); "+ + "falling back to per-IP iptables ACL rules. Ensure the kernel provides "+ + "the ipset hash:net module (ip_set_hash_net) for better performance with large rule sets", err) + return false + } + + defer func() { + if err := ipset.Destroy(probeName); err != nil { + log.Debugf("destroy ipset probe set %q: %v", probeName, err) + } + }() + + return true +} + func (m *aclManager) createIPSet(name string) error { opts := ipset.CreateOptions{ Replace: true, diff --git a/client/firewall/iptables/dnat_refcount_linux_test.go b/client/firewall/iptables/dnat_refcount_linux_test.go new file mode 100644 index 000000000..681bc0b99 --- /dev/null +++ b/client/firewall/iptables/dnat_refcount_linux_test.go @@ -0,0 +1,240 @@ +//go:build privileged + +package iptables + +import ( + "net/netip" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + fw "github.com/netbirdio/netbird/client/firewall/manager" + "github.com/netbirdio/netbird/client/iface" + "github.com/netbirdio/netbird/client/iface/wgaddr" +) + +func iptRefcountIfaceV4() *iFaceMock { + return &iFaceMock{ + NameFunc: func() string { return "wt-refcount" }, + AddressFunc: func() wgaddr.Address { + return wgaddr.Address{ + IP: netip.MustParseAddr("10.20.0.1"), + Network: netip.MustParsePrefix("10.20.0.0/24"), + } + }, + } +} + +func iptRefcountIfaceDual() *iFaceMock { + return &iFaceMock{ + NameFunc: func() string { return "wt-refcount" }, + AddressFunc: func() wgaddr.Address { + return wgaddr.Address{ + IP: netip.MustParseAddr("10.20.0.1"), + Network: netip.MustParsePrefix("10.20.0.0/24"), + IPv6: netip.MustParseAddr("fd00::1"), + IPv6Net: netip.MustParsePrefix("fd00::/64"), + } + }, + } +} + +func newIptRefcountManager(t *testing.T, dual bool) *Manager { + t.Helper() + var ifMock *iFaceMock + if dual { + ifMock = iptRefcountIfaceDual() + } else { + ifMock = iptRefcountIfaceV4() + } + m, err := Create(ifMock, iface.DefaultMTU) + require.NoError(t, err, "create manager") + require.NoError(t, m.Init(nil), "init manager") + t.Cleanup(func() { + require.NoError(t, m.Close(nil), "close manager") + }) + return m +} + +func iptDnatV4(port uint16) fw.ForwardRule { + return fw.ForwardRule{ + Protocol: fw.ProtocolTCP, + DestinationPort: fw.Port{Values: []uint16{port}}, + TranslatedAddress: netip.MustParseAddr("10.20.0.2"), + TranslatedPort: fw.Port{Values: []uint16{80}}, + } +} + +func iptDnatV6(port uint16) fw.ForwardRule { + return fw.ForwardRule{ + Protocol: fw.ProtocolTCP, + DestinationPort: fw.Port{Values: []uint16{port}}, + TranslatedAddress: netip.MustParseAddr("fd00::2"), + TranslatedPort: fw.Port{Values: []uint16{80}}, + } +} + +// TestIptablesRouting_RepeatedEnableSingleReference verifies that EnableRouting +// (called on every network-map update) holds at most one reference per family +// and a single DisableRouting drops both back to zero. +func TestIptablesRouting_RepeatedEnableSingleReference(t *testing.T) { + m := newIptRefcountManager(t, true) + state := m.router.ipFwdState + + require.NoError(t, m.EnableRouting(), "first enable") + require.NoError(t, m.EnableRouting(), "second enable") + require.NoError(t, m.EnableRouting(), "third enable") + v4, v6 := state.Counts() + assert.Equal(t, 1, v4, "repeated enable holds a single v4 reference") + assert.Equal(t, 1, v6, "repeated enable holds a single v6 reference") + + require.NoError(t, m.DisableRouting(), "disable") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "single disable releases the v4 reference") + assert.Equal(t, 0, v6, "single disable releases the v6 reference") +} + +// TestIptablesRouting_DisableKeepsDNATReference verifies that an unpaired +// DisableRouting does not release references held by active DNAT rules. +func TestIptablesRouting_DisableKeepsDNATReference(t *testing.T) { + m := newIptRefcountManager(t, true) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(iptDnatV6(9095)) + require.NoError(t, err, "add v6 dnat") + + require.NoError(t, m.DisableRouting(), "unpaired disable") + _, v6 := state.Counts() + assert.Equal(t, 1, v6, "DNAT-held reference survives unpaired DisableRouting") + + require.NoError(t, m.DeleteDNATRule(r1), "delete v6 dnat") + _, v6 = state.Counts() + assert.Equal(t, 0, v6, "delete releases the DNAT reference") +} + +// TestIptablesDNAT_RefcountBalancedV4 covers a Balanced Add/Delete pair on v4. +func TestIptablesDNAT_RefcountBalancedV4(t *testing.T) { + m := newIptRefcountManager(t, false) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(iptDnatV4(7081)) + require.NoError(t, err, "add v4 dnat 1") + v4, v6 := state.Counts() + assert.Equal(t, 1, v4, "v4 refcount after first add") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + r2, err := m.AddDNATRule(iptDnatV4(7082)) + require.NoError(t, err, "add v4 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 2, v4, "v4 refcount after second add") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + require.NoError(t, m.DeleteDNATRule(r1)) + v4, v6 = state.Counts() + assert.Equal(t, 1, v4, "v4 refcount after first delete") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + require.NoError(t, m.DeleteDNATRule(r2)) + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "v4 refcount after second delete") + assert.Equal(t, 0, v6, "v6 refcount unchanged") +} + +// TestIptablesDNAT_RefcountBalancedV6 checks the v6 path increments v6 only and +// decrements back to zero. +func TestIptablesDNAT_RefcountBalancedV6(t *testing.T) { + m := newIptRefcountManager(t, true) + require.NotNil(t, m.router6, "v6 router") + require.Same(t, m.router.ipFwdState, m.router6.ipFwdState, "shared state") + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(iptDnatV6(9081)) + require.NoError(t, err, "add v6 dnat 1") + v4, v6 := state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 1, v6, "v6 refcount after first add") + + r2, err := m.AddDNATRule(iptDnatV6(9082)) + require.NoError(t, err, "add v6 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "v4 refcount unchanged") + assert.Equal(t, 2, v6, "v6 refcount after second add") + + require.NoError(t, m.DeleteDNATRule(r1)) + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "v4 refcount unchanged") + assert.Equal(t, 1, v6, "v6 refcount after first delete") + + require.NoError(t, m.DeleteDNATRule(r2)) + v4, v6 = state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 0, v6, "v6 refcount after second delete") +} + +// TestIptablesDNAT_DuplicateAddNoLeak verifies the duplicate-rule path returns +// without bumping the refcount. +func TestIptablesDNAT_DuplicateAddNoLeak(t *testing.T) { + m := newIptRefcountManager(t, true) + state := m.router.ipFwdState + + rule := iptDnatV4(7083) + r1, err := m.AddDNATRule(rule) + require.NoError(t, err) + v4, _ := state.Counts() + assert.Equal(t, 1, v4) + + _, err = m.AddDNATRule(rule) + require.NoError(t, err, "duplicate add") + v4, _ = state.Counts() + assert.Equal(t, 1, v4, "duplicate add must not increment") + + require.NoError(t, m.DeleteDNATRule(r1)) + v4, _ = state.Counts() + assert.Equal(t, 0, v4, "single delete must drop to zero") +} + +// TestIptablesDNAT_DeleteMissingNoUnderflow verifies Delete on an unknown rule +// neither errors nor releases the refcount. +func TestIptablesDNAT_DeleteMissingNoUnderflow(t *testing.T) { + m := newIptRefcountManager(t, true) + state := m.router.ipFwdState + + phantom := iptDnatV4(7099) + require.NoError(t, m.DeleteDNATRule(&phantom), "delete missing v4") + v4, v6 := state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 0, v6) + + phantom6 := iptDnatV6(9099) + require.NoError(t, m.DeleteDNATRule(&phantom6), "delete missing v6") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 0, v6) + + r1, err := m.AddDNATRule(iptDnatV4(7100)) + require.NoError(t, err) + v4, _ = state.Counts() + assert.Equal(t, 1, v4, "real add still increments after phantom delete") + require.NoError(t, m.DeleteDNATRule(r1)) +} + +// TestIptablesDNAT_DoubleDeleteNoUnderflow verifies a second Delete on the same +// rule is a no-op. +func TestIptablesDNAT_DoubleDeleteNoUnderflow(t *testing.T) { + m := newIptRefcountManager(t, true) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(iptDnatV6(9083)) + require.NoError(t, err) + _, v6 := state.Counts() + assert.Equal(t, 1, v6) + + require.NoError(t, m.DeleteDNATRule(r1), "first delete") + _, v6 = state.Counts() + assert.Equal(t, 0, v6) + + require.NoError(t, m.DeleteDNATRule(r1), "second delete must be no-op") + _, v6 = state.Counts() + assert.Equal(t, 0, v6, "double delete must not underflow") +} diff --git a/client/firewall/iptables/manager_linux.go b/client/firewall/iptables/manager_linux.go index 696537dd8..aa052d933 100644 --- a/client/firewall/iptables/manager_linux.go +++ b/client/firewall/iptables/manager_linux.go @@ -89,7 +89,7 @@ func (m *Manager) createIPv6Components(wgIface iFaceMapper, mtu uint16) error { } // Share the same IP forwarding state with the v4 router, since - // EnableIPForwarding controls both v4 and v6 sysctls. + // Forwarding refcounter is per-family but shared between v4 and v6 routers. m.router6.ipFwdState = m.router.ipFwdState m.aclMgr6, err = newAclManager(ip6Client, wgIface) @@ -402,17 +402,12 @@ func (m *Manager) SetLogLevel(log.Level) { } func (m *Manager) EnableRouting() error { - if err := m.router.ipFwdState.RequestForwarding(); err != nil { - return fmt.Errorf("enable IP forwarding: %w", err) - } - return nil + // v6 only when the overlay actually has v6. + return m.router.ipFwdState.RequestRouting(m.router6 != nil) } func (m *Manager) DisableRouting() error { - if err := m.router.ipFwdState.ReleaseForwarding(); err != nil { - return fmt.Errorf("disable IP forwarding: %w", err) - } - return nil + return m.router.ipFwdState.ReleaseRouting() } // AddDNATRule adds a DNAT rule diff --git a/client/firewall/iptables/manager_linux_test.go b/client/firewall/iptables/manager_linux_test.go index 7b0989f6c..2c3c1a08e 100644 --- a/client/firewall/iptables/manager_linux_test.go +++ b/client/firewall/iptables/manager_linux_test.go @@ -291,3 +291,40 @@ func TestIptablesCreatePerformance(t *testing.T) { }) } } + +// TestIptablesACLIPSetFallback verifies that when the kernel lacks ipset support, +// the ACL manager falls back to per-IP iptables rules (-s ) instead of +// silently leaving the chain empty. See discussion #6125. +func TestIptablesACLIPSetFallback(t *testing.T) { + ipv4Client, err := iptables.NewWithProtocol(iptables.ProtocolIPv4) + require.NoError(t, err) + + // Use Create()/Init() so the router-owned chains (chainRTFWDIN/OUT) are + // created before the ACL manager's createDefaultChains() references them. + manager, err := Create(ifaceMock, iface.DefaultMTU) + require.NoError(t, err) + require.NoError(t, manager.Init(nil)) + + aclMgr := manager.aclMgr + // Simulate a kernel without the ipset hash module. + aclMgr.ipsetSupported = false + + defer func() { + require.NoError(t, manager.Close(nil)) + }() + + ip := netip.MustParseAddr("10.20.0.42") + port := &fw.Port{Values: []uint16{22}} + + rules, err := aclMgr.AddPeerFiltering(nil, ip.AsSlice(), "tcp", nil, port, fw.ActionAccept, "nb0000001") + require.NoError(t, err, "AddPeerFiltering should succeed via fallback") + require.NotEmpty(t, rules) + + rule := rules[0].(*Rule) + require.Empty(t, rule.ipsetName, "fallback rule must not reference an ipset") + require.Contains(t, strings.Join(rule.specs, " "), "-s 10.20.0.42", "fallback rule must match by source IP") + require.NotContains(t, strings.Join(rule.specs, " "), "--match-set", "fallback rule must not use ipset matching") + + // The rule must actually be present in the ACL chain (not silently dropped). + checkRuleSpecs(t, ipv4Client, rule.chain, true, rule.specs...) +} diff --git a/client/firewall/iptables/router_linux.go b/client/firewall/iptables/router_linux.go index 42d305f5c..01b18570c 100644 --- a/client/firewall/iptables/router_linux.go +++ b/client/firewall/iptables/router_linux.go @@ -102,7 +102,7 @@ func newRouter(iptablesClient *iptables.IPTables, wgIface iFaceMapper, mtu uint1 wgIface: wgIface, mtu: mtu, v6: iptablesClient.Proto() == iptables.ProtocolIPv6, - ipFwdState: ipfwdstate.NewIPForwardingState(), + ipFwdState: ipfwdstate.NewIPForwardingState(wgIface.Name()), } r.ipsetCounter = refcounter.New( @@ -770,10 +770,6 @@ func (r *router) updateState() { } func (r *router) AddDNATRule(rule firewall.ForwardRule) (firewall.Rule, error) { - if err := r.ipFwdState.RequestForwarding(); err != nil { - return nil, err - } - ruleKey := rule.ID() if _, exists := r.rules[ruleKey+dnatSuffix]; exists { return rule, nil @@ -840,18 +836,34 @@ func (r *router) AddDNATRule(rule firewall.ForwardRule) (firewall.Rule, error) { for key, ruleInfo := range rules { if err := r.iptablesClient.Append(ruleInfo.table, ruleInfo.chain, ruleInfo.rule...); err != nil { - if rollbackErr := r.rollbackRules(rules); rollbackErr != nil { - log.Errorf("rollback failed: %v", rollbackErr) - } + r.cleanupFailedDNATAdd(rules) return nil, fmt.Errorf("add rule %s: %w", key, err) } r.rules[key] = ruleInfo.rule } + if err := r.ipFwdState.RequestForwarding(r.v6); err != nil { + r.cleanupFailedDNATAdd(rules) + return nil, fmt.Errorf("enable forwarding: %w", err) + } + r.updateState() return rule, nil } +// cleanupFailedDNATAdd removes the bookkeeping written by a partially applied +// AddDNATRule before rolling back the kernel rules, so no entries remain that +// never got a forwarding refcount. rollbackRules re-adds entries it failed to +// remove from the kernel. +func (r *router) cleanupFailedDNATAdd(rules map[string]ruleInfo) { + for key := range rules { + delete(r.rules, key) + } + if err := r.rollbackRules(rules); err != nil { + log.Errorf("rollback failed: %v", err) + } +} + func (r *router) rollbackRules(rules map[string]ruleInfo) error { var merr *multierror.Error for key, ruleInfo := range rules { @@ -868,32 +880,47 @@ func (r *router) rollbackRules(rules map[string]ruleInfo) error { } func (r *router) DeleteDNATRule(rule firewall.Rule) error { - if err := r.ipFwdState.ReleaseForwarding(); err != nil { - log.Errorf("%v", err) - } - ruleKey := rule.ID() + _, hadDNAT := r.rules[ruleKey+dnatSuffix] + _, hadSNAT := r.rules[ruleKey+snatSuffix] + _, hadFWD := r.rules[ruleKey+fwdSuffix] + if !hadDNAT && !hadSNAT && !hadFWD { + return nil + } + var merr *multierror.Error if dnatRule, exists := r.rules[ruleKey+dnatSuffix]; exists { if err := r.iptablesClient.Delete(tableNat, chainRTRDR, dnatRule...); err != nil { merr = multierror.Append(merr, fmt.Errorf("delete DNAT rule: %w", err)) + } else { + delete(r.rules, ruleKey+dnatSuffix) } - delete(r.rules, ruleKey+dnatSuffix) } if snatRule, exists := r.rules[ruleKey+snatSuffix]; exists { if err := r.iptablesClient.Delete(tableNat, chainRTNAT, snatRule...); err != nil { merr = multierror.Append(merr, fmt.Errorf("delete SNAT rule: %w", err)) + } else { + delete(r.rules, ruleKey+snatSuffix) } - delete(r.rules, ruleKey+snatSuffix) } if fwdRule, exists := r.rules[ruleKey+fwdSuffix]; exists { if err := r.iptablesClient.Delete(tableFilter, chainRTFWDOUT, fwdRule...); err != nil { merr = multierror.Append(merr, fmt.Errorf("delete forward rule: %w", err)) + } else { + delete(r.rules, ruleKey+fwdSuffix) + } + } + + // Release the refcount only once all rules are gone from the kernel. On + // partial failure the failed entries stay in r.rules so a retry can remove + // them and release then. + if merr == nil { + if err := r.ipFwdState.ReleaseForwarding(r.v6); err != nil { + log.Errorf("%v", err) } - delete(r.rules, ruleKey+fwdSuffix) } r.updateState() diff --git a/client/firewall/nftables/dnat_refcount_linux_test.go b/client/firewall/nftables/dnat_refcount_linux_test.go new file mode 100644 index 000000000..86079676f --- /dev/null +++ b/client/firewall/nftables/dnat_refcount_linux_test.go @@ -0,0 +1,249 @@ +//go:build privileged + +package nftables + +import ( + "net/netip" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + fw "github.com/netbirdio/netbird/client/firewall/manager" + "github.com/netbirdio/netbird/client/iface" + "github.com/netbirdio/netbird/client/iface/wgaddr" +) + +func nftRefcountIfaceV4() *iFaceMock { + return &iFaceMock{ + NameFunc: func() string { return "wt-refcount" }, + AddressFunc: func() wgaddr.Address { + return wgaddr.Address{ + IP: netip.MustParseAddr("100.96.0.1"), + Network: netip.MustParsePrefix("100.96.0.0/16"), + } + }, + } +} + +func nftRefcountIfaceDual() *iFaceMock { + return &iFaceMock{ + NameFunc: func() string { return "wt-refcount" }, + AddressFunc: func() wgaddr.Address { + return wgaddr.Address{ + IP: netip.MustParseAddr("100.96.0.1"), + Network: netip.MustParsePrefix("100.96.0.0/16"), + IPv6: netip.MustParseAddr("fd00::1"), + IPv6Net: netip.MustParsePrefix("fd00::/64"), + } + }, + } +} + +func newNftRefcountManager(t *testing.T, dual bool) *Manager { + t.Helper() + if check() != NFTABLES { + t.Skip("nftables not supported on this system") + } + var ifMock *iFaceMock + if dual { + ifMock = nftRefcountIfaceDual() + } else { + ifMock = nftRefcountIfaceV4() + } + m, err := Create(ifMock, iface.DefaultMTU) + require.NoError(t, err, "create manager") + require.NoError(t, m.Init(nil), "init manager") + t.Cleanup(func() { + require.NoError(t, m.Close(nil), "close manager") + }) + return m +} + +func dnatV4(port uint16) fw.ForwardRule { + return fw.ForwardRule{ + Protocol: fw.ProtocolTCP, + DestinationPort: fw.Port{Values: []uint16{port}}, + TranslatedAddress: netip.MustParseAddr("100.96.0.2"), + TranslatedPort: fw.Port{Values: []uint16{80}}, + } +} + +func dnatV6(port uint16) fw.ForwardRule { + return fw.ForwardRule{ + Protocol: fw.ProtocolTCP, + DestinationPort: fw.Port{Values: []uint16{port}}, + TranslatedAddress: netip.MustParseAddr("fd00::2"), + TranslatedPort: fw.Port{Values: []uint16{80}}, + } +} + +// TestNftablesDNAT_RefcountBalancedV4 verifies that Add/Delete pairs leave the +// v4 refcount at zero. +func TestNftablesDNAT_RefcountBalancedV4(t *testing.T) { + m := newNftRefcountManager(t, false) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(dnatV4(8081)) + require.NoError(t, err, "add v4 dnat 1") + v4, v6 := state.Counts() + assert.Equal(t, 1, v4, "v4 refcount after first add") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + r2, err := m.AddDNATRule(dnatV4(8082)) + require.NoError(t, err, "add v4 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 2, v4, "v4 refcount after second add") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + require.NoError(t, m.DeleteDNATRule(r1), "delete v4 dnat 1") + v4, v6 = state.Counts() + assert.Equal(t, 1, v4, "v4 refcount after first delete") + assert.Equal(t, 0, v6, "v6 refcount unchanged") + + require.NoError(t, m.DeleteDNATRule(r2), "delete v4 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "v4 refcount after second delete") + assert.Equal(t, 0, v6, "v6 refcount unchanged") +} + +// TestNftablesDNAT_RefcountBalancedV6 verifies the v6 path increments v6 only +// and decrements back to zero on Delete. +func TestNftablesDNAT_RefcountBalancedV6(t *testing.T) { + m := newNftRefcountManager(t, true) + require.NotNil(t, m.router6, "v6 router") + require.Same(t, m.router.ipFwdState, m.router6.ipFwdState, "shared state") + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(dnatV6(9091)) + require.NoError(t, err, "add v6 dnat 1") + v4, v6 := state.Counts() + assert.Equal(t, 0, v4, "v4 refcount unchanged") + assert.Equal(t, 1, v6, "v6 refcount after first add") + + r2, err := m.AddDNATRule(dnatV6(9092)) + require.NoError(t, err, "add v6 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 2, v6, "v6 refcount after second add") + + require.NoError(t, m.DeleteDNATRule(r1), "delete v6 dnat 1") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "v4 refcount unchanged") + assert.Equal(t, 1, v6, "v6 refcount after first delete") + + require.NoError(t, m.DeleteDNATRule(r2), "delete v6 dnat 2") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 0, v6, "v6 refcount after second delete") +} + +// TestNftablesDNAT_DuplicateAddNoLeak verifies that a duplicate Add (same +// ForwardRule) does not double-increment the refcount. +func TestNftablesDNAT_DuplicateAddNoLeak(t *testing.T) { + m := newNftRefcountManager(t, true) + state := m.router.ipFwdState + + rule := dnatV4(8083) + r1, err := m.AddDNATRule(rule) + require.NoError(t, err, "add v4 dnat") + v4, _ := state.Counts() + assert.Equal(t, 1, v4) + + // duplicate add: same rule ID, must be a no-op for the refcount. + _, err = m.AddDNATRule(rule) + require.NoError(t, err, "duplicate add") + v4, _ = state.Counts() + assert.Equal(t, 1, v4, "duplicate add must not increment") + + require.NoError(t, m.DeleteDNATRule(r1), "delete v4 dnat") + v4, _ = state.Counts() + assert.Equal(t, 0, v4, "single delete must drop to zero") +} + +// TestNftablesDNAT_DeleteMissingNoUnderflow verifies deleting a rule that was +// never added does not underflow the refcount. +func TestNftablesDNAT_DeleteMissingNoUnderflow(t *testing.T) { + m := newNftRefcountManager(t, true) + state := m.router.ipFwdState + + // Construct a Rule reference for something never added. The router stores + // rules by ID(), and DeleteDNATRule looks them up in r.rules; a missing + // entry must be a no-op rather than calling Release. + phantom := dnatV4(8099) + require.NoError(t, m.DeleteDNATRule(&phantom), "delete missing v4 dnat") + v4, v6 := state.Counts() + assert.Equal(t, 0, v4, "v4 refcount unaffected by missing delete") + assert.Equal(t, 0, v6, "v6 refcount unaffected") + + phantom6 := dnatV6(9099) + require.NoError(t, m.DeleteDNATRule(&phantom6), "delete missing v6 dnat") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4) + assert.Equal(t, 0, v6, "v6 refcount unaffected by missing delete") + + // And after a phantom delete, a real add still results in count=1. + r1, err := m.AddDNATRule(dnatV4(8100)) + require.NoError(t, err, "add v4 dnat after phantom delete") + v4, _ = state.Counts() + assert.Equal(t, 1, v4, "real add still increments after phantom delete") + require.NoError(t, m.DeleteDNATRule(r1)) +} + +// TestNftablesRouting_RepeatedEnableSingleReference verifies that EnableRouting +// (called on every network-map update) holds at most one reference per family +// and a single DisableRouting drops both back to zero. +func TestNftablesRouting_RepeatedEnableSingleReference(t *testing.T) { + m := newNftRefcountManager(t, true) + state := m.router.ipFwdState + + require.NoError(t, m.EnableRouting(), "first enable") + require.NoError(t, m.EnableRouting(), "second enable") + require.NoError(t, m.EnableRouting(), "third enable") + v4, v6 := state.Counts() + assert.Equal(t, 1, v4, "repeated enable holds a single v4 reference") + assert.Equal(t, 1, v6, "repeated enable holds a single v6 reference") + + require.NoError(t, m.DisableRouting(), "disable") + v4, v6 = state.Counts() + assert.Equal(t, 0, v4, "single disable releases the v4 reference") + assert.Equal(t, 0, v6, "single disable releases the v6 reference") +} + +// TestNftablesRouting_DisableKeepsDNATReference verifies that an unpaired +// DisableRouting does not release references held by active DNAT rules. +func TestNftablesRouting_DisableKeepsDNATReference(t *testing.T) { + m := newNftRefcountManager(t, true) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(dnatV6(9095)) + require.NoError(t, err, "add v6 dnat") + + require.NoError(t, m.DisableRouting(), "unpaired disable") + _, v6 := state.Counts() + assert.Equal(t, 1, v6, "DNAT-held reference survives unpaired DisableRouting") + + require.NoError(t, m.DeleteDNATRule(r1), "delete v6 dnat") + _, v6 = state.Counts() + assert.Equal(t, 0, v6, "delete releases the DNAT reference") +} + +// TestNftablesDNAT_DoubleDeleteNoUnderflow verifies that deleting the same rule +// twice does not underflow the refcount (the second delete is a no-op). +func TestNftablesDNAT_DoubleDeleteNoUnderflow(t *testing.T) { + m := newNftRefcountManager(t, true) + state := m.router.ipFwdState + + r1, err := m.AddDNATRule(dnatV6(9093)) + require.NoError(t, err) + _, v6 := state.Counts() + assert.Equal(t, 1, v6) + + require.NoError(t, m.DeleteDNATRule(r1), "first delete") + _, v6 = state.Counts() + assert.Equal(t, 0, v6) + + require.NoError(t, m.DeleteDNATRule(r1), "second delete must be no-op") + _, v6 = state.Counts() + assert.Equal(t, 0, v6, "double delete must not underflow") +} diff --git a/client/firewall/nftables/manager_linux.go b/client/firewall/nftables/manager_linux.go index fdc7c2f3c..984b1c3ba 100644 --- a/client/firewall/nftables/manager_linux.go +++ b/client/firewall/nftables/manager_linux.go @@ -105,8 +105,8 @@ func (m *Manager) createIPv6Components(tableName string, wgIface iFaceMapper, mt return fmt.Errorf("create v6 router: %w", err) } - // Share the same IP forwarding state with the v4 router, since - // EnableIPForwarding controls both v4 and v6 sysctls. + // Share the per-family forwarding refcounter with the v4 router so a v4 + // rule and a v6 rule against the same state machine cooperate cleanly. m.router6.ipFwdState = m.router.ipFwdState m.aclManager6, err = newAclManager(workTable6, wgIface, chainNameRoutingFw) @@ -530,17 +530,12 @@ func (m *Manager) SetLogLevel(log.Level) { } func (m *Manager) EnableRouting() error { - if err := m.router.ipFwdState.RequestForwarding(); err != nil { - return fmt.Errorf("enable IP forwarding: %w", err) - } - return nil + // v6 only when the overlay actually has v6. + return m.router.ipFwdState.RequestRouting(m.router6 != nil) } func (m *Manager) DisableRouting() error { - if err := m.router.ipFwdState.ReleaseForwarding(); err != nil { - return fmt.Errorf("disable IP forwarding: %w", err) - } - return nil + return m.router.ipFwdState.ReleaseRouting() } // Flush rule/chain/set operations from the buffer diff --git a/client/firewall/nftables/router_linux.go b/client/firewall/nftables/router_linux.go index dfb94c514..d3e031c5f 100644 --- a/client/firewall/nftables/router_linux.go +++ b/client/firewall/nftables/router_linux.go @@ -93,7 +93,7 @@ func newRouter(workTable *nftables.Table, wgIface iFaceMapper, mtu uint16) (*rou rules: make(map[string]*nftables.Rule), af: familyForAddr(workTable.Family == nftables.TableFamilyIPv4), wgIface: wgIface, - ipFwdState: ipfwdstate.NewIPForwardingState(), + ipFwdState: ipfwdstate.NewIPForwardingState(wgIface.Name()), mtu: mtu, } @@ -1553,10 +1553,6 @@ func (r *router) refreshRulesMap() error { } func (r *router) AddDNATRule(rule firewall.ForwardRule) (firewall.Rule, error) { - if err := r.ipFwdState.RequestForwarding(); err != nil { - return nil, err - } - ruleKey := rule.ID() if _, exists := r.rules[ruleKey+dnatSuffix]; exists { return rule, nil @@ -1567,7 +1563,18 @@ func (r *router) AddDNATRule(rule firewall.ForwardRule) (firewall.Rule, error) { return nil, fmt.Errorf("convert protocol to number: %w", err) } + // Request forwarding before queueing rules: addDnatRedirect/addDnatMasq + // buffer netlink messages on r.conn that the next caller's Flush would + // commit if we returned without flushing them ourselves. + v6 := r.af.tableFamily == nftables.TableFamilyIPv6 + if err := r.ipFwdState.RequestForwarding(v6); err != nil { + return nil, fmt.Errorf("enable forwarding: %w", err) + } + if err := r.addDnatRedirect(rule, protoNum, ruleKey); err != nil { + if rerr := r.ipFwdState.ReleaseForwarding(v6); rerr != nil { + log.Warnf("rollback forwarding refcount: %v", rerr) + } return nil, err } @@ -1579,6 +1586,11 @@ func (r *router) AddDNATRule(rule firewall.ForwardRule) (firewall.Rule, error) { // TODO: find chains with drop policies and add rules there if err := r.conn.Flush(); err != nil { + if rerr := r.ipFwdState.ReleaseForwarding(v6); rerr != nil { + log.Warnf("rollback forwarding refcount: %v", rerr) + } + delete(r.rules, ruleKey+dnatSuffix) + delete(r.rules, ruleKey+snatSuffix) return nil, fmt.Errorf("flush rules: %w", err) } @@ -1781,16 +1793,18 @@ func (r *router) addDnatMasq(rule firewall.ForwardRule, protoNum uint8, ruleKey } func (r *router) DeleteDNATRule(rule firewall.Rule) error { - if err := r.ipFwdState.ReleaseForwarding(); err != nil { - log.Errorf("%v", err) - } - ruleKey := rule.ID() if err := r.refreshRulesMap(); err != nil { return fmt.Errorf(refreshRulesMapError, err) } + _, hadDNAT := r.rules[ruleKey+dnatSuffix] + _, hadSNAT := r.rules[ruleKey+snatSuffix] + if !hadDNAT && !hadSNAT { + return nil + } + var merr *multierror.Error var needsFlush bool @@ -1822,9 +1836,16 @@ func (r *router) DeleteDNATRule(rule firewall.Rule) error { } } + // Release the refcount only once the rules are gone from the kernel. On + // failure (including the refreshRulesMap error above) the rules and their + // map entries remain, keeping forwarding on until a retry removes them. if merr == nil { delete(r.rules, ruleKey+dnatSuffix) delete(r.rules, ruleKey+snatSuffix) + + if err := r.ipFwdState.ReleaseForwarding(r.af.tableFamily == nftables.TableFamilyIPv6); err != nil { + log.Errorf("%v", err) + } } return nberrors.FormatErrorOrNil(merr) diff --git a/client/firewall/uspfilter/filter_filter_test.go b/client/firewall/uspfilter/filter_filter_test.go index a64c83138..5ca8538be 100644 --- a/client/firewall/uspfilter/filter_filter_test.go +++ b/client/firewall/uspfilter/filter_filter_test.go @@ -5,7 +5,7 @@ import ( "net/netip" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/google/gopacket" "github.com/google/gopacket/layers" "github.com/stretchr/testify/require" diff --git a/client/firewall/uspfilter/filter_routeacl_test.go b/client/firewall/uspfilter/filter_routeacl_test.go index 449554d8b..b6397d09b 100644 --- a/client/firewall/uspfilter/filter_routeacl_test.go +++ b/client/firewall/uspfilter/filter_routeacl_test.go @@ -4,7 +4,7 @@ import ( "net/netip" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/google/gopacket/layers" "github.com/stretchr/testify/assert" "github.com/stretchr/testify/require" diff --git a/client/grpc/dialer_generic.go b/client/grpc/dialer_generic.go index 479575996..8a80525e9 100644 --- a/client/grpc/dialer_generic.go +++ b/client/grpc/dialer_generic.go @@ -16,28 +16,47 @@ import ( "google.golang.org/grpc" nbnet "github.com/netbirdio/netbird/client/net" + "github.com/netbirdio/netbird/client/netsweep" ) func WithCustomDialer(_ bool, _ string) grpc.DialOption { + return grpc.WithContextDialer(dialContext) +} + +// WithSweeper dials like WithCustomDialer but registers connections and +// dials with the sweeper. Append it after WithCustomDialer: gRPC applies +// dial options in order, so the later context dialer wins. +func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption { return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) { - if runtime.GOOS == "linux" { - currentUser, err := user.Current() - if err != nil { - return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err) - } + dial := sweeper.StartDial(ctx) + defer dial.Release() - // the custom dialer requires root permissions which are not required for use cases run as non-root - if currentUser.Uid != "0" { - log.Debug("Not running as root, using standard dialer") - dialer := &net.Dialer{} - return dialer.DialContext(ctx, "tcp", addr) - } - } - - conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr) + conn, err := dialContext(dial.Ctx(), addr) if err != nil { - return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err) + return nil, err } - return conn, nil + return dial.WrapConn(conn) }) } + +func dialContext(ctx context.Context, addr string) (net.Conn, error) { + if runtime.GOOS == "linux" { + currentUser, err := user.Current() + if err != nil { + return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err) + } + + // the custom dialer requires root permissions which are not required for use cases run as non-root + if currentUser.Uid != "0" { + log.Debug("Not running as root, using standard dialer") + dialer := &net.Dialer{} + return dialer.DialContext(ctx, "tcp", addr) + } + } + + conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr) + if err != nil { + return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err) + } + return conn, nil +} diff --git a/client/grpc/dialer_js.go b/client/grpc/dialer_js.go index b89ec3c21..8863756d7 100644 --- a/client/grpc/dialer_js.go +++ b/client/grpc/dialer_js.go @@ -3,6 +3,7 @@ package grpc import ( "google.golang.org/grpc" + "github.com/netbirdio/netbird/client/netsweep" "github.com/netbirdio/netbird/util/wsproxy/client" ) @@ -11,3 +12,8 @@ import ( func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption { return client.WithWebSocketDialer(tlsEnabled, component) } + +// WithSweeper is a no-op on WASM/JS: there is no network change signal. +func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption { + return grpc.EmptyDialOption{} +} diff --git a/client/grpc/retry.go b/client/grpc/retry.go new file mode 100644 index 000000000..754ffa341 --- /dev/null +++ b/client/grpc/retry.go @@ -0,0 +1,49 @@ +package grpc + +import ( + "context" + "errors" + "time" + + "github.com/cenkalti/backoff/v4" + + "github.com/netbirdio/netbird/client/netstate" +) + +// Retry mirrors backoff.Retry, but the sleep between attempts also wakes on +// OS network availability transitions: an operation cut down by a network +// change retries the moment the network settles instead of sleeping through +// the recovery. A nil netState never fires, leaving plain backoff.Retry +// behavior. +func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, netState *netstate.State) error { + bo.Reset() + for { + err := operation() + if err == nil { + return nil + } + + var permanent *backoff.PermanentError + if errors.As(err, &permanent) { + return permanent.Err + } + + next := bo.NextBackOff() + if next == backoff.Stop { + if cerr := ctx.Err(); cerr != nil { + return cerr + } + return err + } + + timer := time.NewTimer(next) + select { + case <-timer.C: + case <-netState.Changed(): + timer.Stop() + case <-ctx.Done(): + timer.Stop() + return ctx.Err() + } + } +} diff --git a/client/grpc/retry_test.go b/client/grpc/retry_test.go new file mode 100644 index 000000000..4edca47b6 --- /dev/null +++ b/client/grpc/retry_test.go @@ -0,0 +1,91 @@ +package grpc + +import ( + "context" + "errors" + "testing" + "time" + + "github.com/cenkalti/backoff/v4" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/client/netstate" +) + +func TestRetryWakesOnNetworkChange(t *testing.T) { + ns := netstate.New() + attempts := 0 + operation := func() error { + attempts++ + if attempts == 1 { + return errors.New("cut by network change") + } + return nil + } + + go func() { + time.Sleep(20 * time.Millisecond) + ns.Set(false) + }() + + start := time.Now() + err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Minute), ns) + + require.NoError(t, err) + assert.Equal(t, 2, attempts, "network change must cause one immediate retry") + assert.Less(t, time.Since(start), time.Second, "the transition must cut the minute-long sleep short") +} + +func TestRetryPermanentError(t *testing.T) { + sentinel := errors.New("permission denied") + operation := func() error { + return backoff.Permanent(sentinel) + } + + err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil) + assert.ErrorIs(t, err, sentinel, "permanent errors must stop retries") +} + +func TestRetryNilNetState(t *testing.T) { + attempts := 0 + operation := func() error { + attempts++ + if attempts < 3 { + return errors.New("transient") + } + return nil + } + + err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil) + require.NoError(t, err) + assert.Equal(t, 3, attempts, "nil network state must preserve timed retries") +} + +func TestRetryStops(t *testing.T) { + failure := errors.New("still failing") + operation := func() error { + return failure + } + + err := Retry(context.Background(), operation, &backoff.StopBackOff{}, nil) + assert.ErrorIs(t, err, failure, "stop backoff must return the operation error") +} + +func TestRetryCtxCancelDuringSleep(t *testing.T) { + ctx, cancel := context.WithCancel(context.Background()) + operation := func() error { + return errors.New("failing") + } + + go func() { + time.Sleep(20 * time.Millisecond) + cancel() + }() + + start := time.Now() + err := Retry(ctx, operation, backoff.NewConstantBackOff(time.Minute), netstate.New()) + + assert.ErrorIs(t, err, context.Canceled, "context cancellation must stop the retry loop") + assert.Less(t, time.Since(start), time.Second, "context cancellation must interrupt backoff sleep") +} diff --git a/client/iface/bind/ice_bind.go b/client/iface/bind/ice_bind.go index 156450c61..2d35b9c6f 100644 --- a/client/iface/bind/ice_bind.go +++ b/client/iface/bind/ice_bind.go @@ -22,6 +22,16 @@ import ( nbnet "github.com/netbirdio/netbird/client/net" ) +const ( + // wgMsgTypeHandshakeInitiation is the lowest WireGuard message type. + wgMsgTypeHandshakeInitiation uint32 = 1 + // wgMsgTypeTransport is the highest WireGuard message type. + wgMsgTypeTransport uint32 = 4 + // wgMinMsgSize is the smallest WireGuard message: transport data with an empty + // payload, which is what a keepalive is. + wgMinMsgSize = 32 +) + type receiverCreator struct { iceBind *ICEBind } @@ -216,8 +226,15 @@ func (s *ICEBind) createReceiverFn(pc wgConn.BatchReader, conn *net.UDPConn, rxO for i := 0; i < numMsgs; i++ { msg := &(*msgs)[i] - // todo: handle err - if ok, _ := s.filterOutStunMessages(msg.Buffers, msg.N, msg.Addr); ok { + if ok, err := s.filterOutStunMessages(msg.Buffers, msg.N, msg.Addr); ok { + if err != nil { + log.Debugf("failed to handle STUN packet from %s: %v", msg.Addr, err) + } + // WireGuard reuses sizes and eps across reads and only skips a slot + // whose size is below the minimum message size. Leaving a consumed + // slot untouched makes it process this buffer again under the + // previous packet's length and endpoint. + sizes[i] = 0 continue } sizes[i] = msg.N @@ -271,11 +288,16 @@ func (s *ICEBind) createOrUpdateMux() { func (s *ICEBind) filterOutStunMessages(buffers [][]byte, n int, addr net.Addr) (bool, error) { for i := range buffers { - if !stun.IsMessage(buffers[i]) { + if n > len(buffers[i]) { + continue + } + pkt := buffers[i][:n] + + if isWireGuardMsg(pkt) || !stun.IsMessage(pkt) { continue } - msg, err := s.parseSTUNMessage(buffers[i][:n]) + msg, err := s.parseSTUNMessage(pkt) if err != nil { buffers[i] = []byte{} return true, err @@ -347,18 +369,34 @@ func putMessages(msgs *[]ipv6.Message, msgsPool *sync.Pool) { msgsPool.Put(msgs) } -func isTransportPkg(buffers [][]byte, n int) bool { - // The first buffer should contain at least 4 bytes for type - if len(buffers[0]) < 4 { - return true +// isWireGuardMsg reports whether the packet carries a WireGuard message header: a +// little-endian uint32 message type in the range 1..4, which leaves the three bytes +// after the type byte zero, in a packet long enough to hold any WireGuard message. +// +// A well formed STUN message cannot take that shape. Its length field sits in the two +// bytes the type must leave zero, and for a message of at least wgMinMsgSize bytes that +// field holds at least 12, so the two framings do not overlap. The test has to be this +// tight because stun.IsMessage only looks at the magic cookie, which in a WireGuard +// message overlaps the receiver index: a session whose index happens to equal the cookie +// would otherwise have all of its inbound data misrouted to the STUN handler until the +// next rekey. +func isWireGuardMsg(pkt []byte) bool { + if len(pkt) < wgMinMsgSize { + return false } - // WireGuard packet type is a little-endian uint32 at start - packetType := binary.LittleEndian.Uint32(buffers[0][:4]) - - // Check if packetType matches known WireGuard message types - if packetType == 4 && n > 32 { - return true - } - return false + msgType := binary.LittleEndian.Uint32(pkt[:4]) + return msgType >= wgMsgTypeHandshakeInitiation && msgType <= wgMsgTypeTransport +} + +// isTransportPkg reports whether the packet is WireGuard transport data carrying a +// payload, which is what counts as peer activity. A keepalive holds no payload and is +// exactly wgMinMsgSize bytes. +func isTransportPkg(buffers [][]byte, n int) bool { + if n < 4 || n > len(buffers[0]) { + return false + } + + msgType := binary.LittleEndian.Uint32(buffers[0][:4]) + return msgType == wgMsgTypeTransport && n > wgMinMsgSize } diff --git a/client/iface/bind/stun_filter_test.go b/client/iface/bind/stun_filter_test.go new file mode 100644 index 000000000..0e118e0fd --- /dev/null +++ b/client/iface/bind/stun_filter_test.go @@ -0,0 +1,215 @@ +//go:build !js + +package bind + +import ( + "encoding/binary" + "net" + "testing" + "time" + + "github.com/pion/stun/v3" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + "golang.org/x/net/ipv4" + wgConn "golang.zx2c4.com/wireguard/conn" +) + +// magicCookieBytes is the STUN magic cookie as it appears on the wire. In a +// WireGuard message the same offset holds the receiver (or sender) index, which is +// a random uint32, so a session can draw exactly this value. +var magicCookieBytes = []byte{0x21, 0x12, 0xA4, 0x42} + +const testBufSize = 1500 + +// wgMsg builds a WireGuard message of the given type and size, with the index field +// at bytes 4:8 set to index. +func wgMsg(msgType uint32, size int, index []byte) []byte { + pkt := make([]byte, size) + binary.LittleEndian.PutUint32(pkt[:4], msgType) + copy(pkt[4:8], index) + return pkt +} + +// intoBuffer copies pkt into a full-size receive buffer, the way the kernel read +// does, so tests see the same buffer/length split as the hot path. +func intoBuffer(pkt []byte) [][]byte { + buf := make([]byte, testBufSize) + copy(buf, pkt) + return [][]byte{buf} +} + +func TestFilterOutStunMessages_PassesWireGuardWithCookieShapedIndex(t *testing.T) { + tests := []struct { + name string + msgType uint32 + size int + }{ + {"transport data", wgMsgTypeTransport, 128}, + {"keepalive", wgMsgTypeTransport, wgMinMsgSize}, + {"handshake initiation", wgMsgTypeHandshakeInitiation, 148}, + {"handshake response", 2, 92}, + {"cookie reply", 3, 64}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + pkt := wgMsg(tc.msgType, tc.size, magicCookieBytes) + require.True(t, stun.IsMessage(pkt), "precondition: pion sees this as STUN") + + buffers := intoBuffer(pkt) + bind := &ICEBind{} + + filtered, err := bind.filterOutStunMessages(buffers, tc.size, &net.UDPAddr{}) + assert.NoError(t, err) + assert.False(t, filtered, "WireGuard message must be handed to WireGuard, not the STUN handler") + assert.Len(t, buffers[0], testBufSize, "buffer must be left intact for WireGuard") + }) + } +} + +func TestFilterOutStunMessages_FiltersRealSTUNMessage(t *testing.T) { + msg, err := stun.Build(stun.BindingRequest, stun.TransactionID, stun.Fingerprint) + require.NoError(t, err) + + buffers := intoBuffer(msg.Raw) + bind := &ICEBind{} + + filtered, err := bind.filterOutStunMessages(buffers, len(msg.Raw), &net.UDPAddr{}) + assert.NoError(t, err) + assert.True(t, filtered, "STUN message must be consumed by the STUN handler") + assert.Empty(t, buffers[0], "consumed buffer must be emptied so WireGuard does not see it") +} + +// TestIsWireGuardMsg_DisjointFromSTUN locks the invariant the filter relies on: a +// well formed STUN message long enough to be a WireGuard message always has a +// non-zero length field, so it cannot be mistaken for a WireGuard header. +func TestIsWireGuardMsg_DisjointFromSTUN(t *testing.T) { + types := []stun.MessageType{ + stun.BindingRequest, + stun.BindingSuccess, + stun.BindingError, + {Method: stun.MethodBinding, Class: stun.ClassIndication}, + } + + for _, msgType := range types { + // Long enough that the length guard is not what makes this pass. + msg, err := stun.Build(msgType, stun.TransactionID, + stun.NewUsername("remoteUfrag:localUfrag"), stun.Fingerprint) + require.NoError(t, err) + require.GreaterOrEqual(t, len(msg.Raw), wgMinMsgSize, "precondition: %s", msgType) + assert.False(t, isWireGuardMsg(msg.Raw), + "%s must not look like a WireGuard message", msgType) + } +} + +func TestIsWireGuardMsg(t *testing.T) { + tests := []struct { + name string + pkt []byte + want bool + }{ + {"transport data", wgMsg(wgMsgTypeTransport, 128, nil), true}, + {"handshake initiation", wgMsg(wgMsgTypeHandshakeInitiation, 148, nil), true}, + {"unknown type 5", wgMsg(5, 128, nil), false}, + {"type 0", wgMsg(0, 128, nil), false}, + {"non-zero reserved byte", []byte{0x04, 0x00, 0x01, 0x00}, false}, + {"too short", []byte{0x04, 0x00, 0x00}, false}, + {"empty", nil, false}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + assert.Equal(t, tc.want, isWireGuardMsg(tc.pkt), "wrong classification for %s", tc.name) + }) + } +} + +// TestFilterOutStunMessages_IgnoresBytesBeyondPacket guards against classifying on +// buffer contents left over from an earlier, longer packet. +func TestFilterOutStunMessages_IgnoresBytesBeyondPacket(t *testing.T) { + buf := make([]byte, testBufSize) + copy(buf[4:8], magicCookieBytes) + buffers := [][]byte{buf} + bind := &ICEBind{} + + filtered, err := bind.filterOutStunMessages(buffers, 2, &net.UDPAddr{}) + assert.NoError(t, err) + assert.False(t, filtered, "a 2 byte packet must not be classified from stale buffer bytes") +} + +// TestReceiveFn_ClearsSizeOfConsumedPacket covers the accounting WireGuard relies +// on: sizes is reused across reads, so a slot whose packet was consumed as STUN must +// be reported as empty. Otherwise WireGuard reprocesses the same buffer under the +// previous packet's length, which for a WireGuard-shaped packet means it is handled +// twice. +func TestReceiveFn_ClearsSizeOfConsumedPacket(t *testing.T) { + conn := listenUDP(t, "udp4", "127.0.0.1:0") + defer conn.Close() + + recvFn := receiverCreator{setupICEBind(t)}.CreateReceiverFn( + ipv4.NewPacketConn(conn), conn, false, createMsgPool(), + ) + + msg, err := stun.Build(stun.BindingRequest, stun.TransactionID, stun.Fingerprint) + require.NoError(t, err) + + sender := listenUDP(t, "udp4", "127.0.0.1:0") + defer sender.Close() + _, err = sender.WriteTo(msg.Raw, conn.LocalAddr()) + require.NoError(t, err) + + require.NoError(t, conn.SetReadDeadline(time.Now().Add(3*time.Second))) + + bufs := [][]byte{make([]byte, 1500)} + // A leftover size from an earlier read, which is what makes the missing reset + // observable. + sizes := []int{148} + eps := make([]wgConn.Endpoint, 1) + + n, err := recvFn(bufs, sizes, eps) + require.NoError(t, err) + require.Equal(t, 1, n) + assert.Zero(t, sizes[0], "consumed STUN packet must not leave a size behind for WireGuard") +} + +func TestIsTransportPkg(t *testing.T) { + tests := []struct { + name string + pkt []byte + n int + want bool + }{ + {"transport data with payload", wgMsg(wgMsgTypeTransport, 128, nil), 128, true}, + {"keepalive", wgMsg(wgMsgTypeTransport, wgMinMsgSize, nil), wgMinMsgSize, false}, + {"handshake initiation", wgMsg(wgMsgTypeHandshakeInitiation, 148, nil), 148, false}, + {"stale type bytes beyond packet", wgMsg(wgMsgTypeTransport, 128, nil), 2, false}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + assert.Equal(t, tc.want, isTransportPkg(intoBuffer(tc.pkt), tc.n), + "wrong activity classification for %s", tc.name) + }) + } +} + +// TestFilterOutStunMessages_ConsumesSTUNWithWireGuardShapedType covers the one STUN +// encoding whose leading bytes collide with a WireGuard message type: method 0x080 as a +// request encodes to 0x0200, so the type byte reads as a handshake response and the byte +// after it is zero. Only the length check keeps such a message out of WireGuard's hands. +// pion implements no method in that range, so this is a synthetic worst case rather than +// traffic ICE produces. +func TestFilterOutStunMessages_ConsumesSTUNWithWireGuardShapedType(t *testing.T) { + msg, err := stun.Build(stun.NewType(stun.Method(0x080), stun.ClassRequest), stun.TransactionID) + require.NoError(t, err) + require.Equal(t, []byte{0x02, 0x00, 0x00, 0x00}, msg.Raw[:4], + "precondition: the leading bytes read as a WireGuard message type") + + buffers := intoBuffer(msg.Raw) + bind := &ICEBind{} + + filtered, err := bind.filterOutStunMessages(buffers, len(msg.Raw), &net.UDPAddr{}) + assert.NoError(t, err) + assert.True(t, filtered, "STUN message must be consumed despite its WireGuard-shaped type") +} diff --git a/client/iface/device/device_filter_test.go b/client/iface/device/device_filter_test.go index 0d86c9323..a75ef90f9 100644 --- a/client/iface/device/device_filter_test.go +++ b/client/iface/device/device_filter_test.go @@ -4,7 +4,7 @@ import ( "net" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/google/gopacket" "github.com/google/gopacket/layers" diff --git a/client/iface/mocks/filter.go b/client/iface/mocks/filter.go index 5ae98039c..ff3dd0c8a 100644 --- a/client/iface/mocks/filter.go +++ b/client/iface/mocks/filter.go @@ -8,7 +8,7 @@ import ( "net/netip" reflect "reflect" - gomock "github.com/golang/mock/gomock" + gomock "go.uber.org/mock/gomock" ) // MockPacketFilter is a mock of PacketFilter interface. diff --git a/client/iface/mocks/tun.go b/client/iface/mocks/tun.go index 677c82b0b..519ee6005 100644 --- a/client/iface/mocks/tun.go +++ b/client/iface/mocks/tun.go @@ -8,7 +8,7 @@ import ( os "os" reflect "reflect" - gomock "github.com/golang/mock/gomock" + gomock "go.uber.org/mock/gomock" tun "golang.zx2c4.com/wireguard/tun" ) diff --git a/client/iface/wgproxy/bind/proxy.go b/client/iface/wgproxy/bind/proxy.go index be690ed4f..fcaee15c7 100644 --- a/client/iface/wgproxy/bind/proxy.go +++ b/client/iface/wgproxy/bind/proxy.go @@ -53,15 +53,15 @@ func NewProxyBind(bind Bind, mtu uint16) *ProxyBind { return p } -// AddTurnConn adds a new connection to the bind. +// AddRelayedConn adds a new connection to the bind. // endpoint is the NetBird address of the remote peer. The SetEndpoint return with the address what will be used in the // WireGuard configuration. // // Parameters: // - ctx: Context is used for proxyToLocal to avoid unnecessary error messages // - nbAddr: The NetBird UDP address of the remote peer, it required to generate fake address -// - remoteConn: The established TURN connection to the remote peer -func (p *ProxyBind) AddTurnConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error { +// - remoteConn: The established relayed connection to the remote peer +func (p *ProxyBind) AddRelayedConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error { fakeNetIP, err := fakeAddress(nbAddr) if err != nil { return err diff --git a/client/iface/wgproxy/ebpf/proxy.go b/client/iface/wgproxy/ebpf/proxy.go index 1b1a8ce1c..91c741c0d 100644 --- a/client/iface/wgproxy/ebpf/proxy.go +++ b/client/iface/wgproxy/ebpf/proxy.go @@ -30,9 +30,9 @@ type WGEBPFProxy struct { proxyPort int mtu uint16 - ebpfManager ebpfMgr.Manager - turnConnStore map[uint16]net.Conn - turnConnMutex sync.Mutex + ebpfManager ebpfMgr.Manager + relayedConnStore map[uint16]net.Conn + relayedConnMutex sync.Mutex lastUsedPort uint16 rawConnIPv4 net.PacketConn @@ -50,7 +50,7 @@ func NewWGEBPFProxy(wgPort int, mtu uint16) *WGEBPFProxy { localWGListenPort: wgPort, mtu: mtu, ebpfManager: ebpf.GetEbpfManagerInstance(), - turnConnStore: make(map[uint16]net.Conn), + relayedConnStore: make(map[uint16]net.Conn), } return wgProxy } @@ -110,14 +110,14 @@ func (p *WGEBPFProxy) Listen() error { return nil } -// AddTurnConn add new turn connection for the proxy -func (p *WGEBPFProxy) AddTurnConn(turnConn net.Conn) (*net.UDPAddr, error) { - wgEndpointPort, err := p.storeTurnConn(turnConn) +// AddRelayedConn add new relayed connection for the proxy +func (p *WGEBPFProxy) AddRelayedConn(relayedConn net.Conn) (*net.UDPAddr, error) { + wgEndpointPort, err := p.storeRelayedConn(relayedConn) if err != nil { return nil, err } - log.Infof("turn conn added to wg proxy store: %s, endpoint port: :%d", turnConn.RemoteAddr(), wgEndpointPort) + log.Infof("relayed conn added to wg proxy store: %s, endpoint port: :%d", relayedConn.RemoteAddr(), wgEndpointPort) wgEndpoint := &net.UDPAddr{ IP: net.ParseIP(loopbackAddr), @@ -186,48 +186,48 @@ func (p *WGEBPFProxy) readAndForwardPacket(buf []byte) error { return fmt.Errorf("failed to read UDP packet from WG: %w", err) } - p.turnConnMutex.Lock() - conn, ok := p.turnConnStore[uint16(addr.Port)] - p.turnConnMutex.Unlock() + p.relayedConnMutex.Lock() + conn, ok := p.relayedConnStore[uint16(addr.Port)] + p.relayedConnMutex.Unlock() if !ok { if p.ctx.Err() == nil { - log.Debugf("turn conn not found by port because conn already has been closed: %d", addr.Port) + log.Debugf("relayed conn not found by port because conn already has been closed: %d", addr.Port) } return nil } if _, err := conn.Write(buf[:n]); err != nil { - return fmt.Errorf("failed to forward local WG packet (%d) to remote turn conn: %w", addr.Port, err) + return fmt.Errorf("forward local WG packet (%d) to remote relayed conn: %w", addr.Port, err) } return nil } -func (p *WGEBPFProxy) storeTurnConn(turnConn net.Conn) (uint16, error) { - p.turnConnMutex.Lock() - defer p.turnConnMutex.Unlock() +func (p *WGEBPFProxy) storeRelayedConn(relayedConn net.Conn) (uint16, error) { + p.relayedConnMutex.Lock() + defer p.relayedConnMutex.Unlock() np, err := p.nextFreePort() if err != nil { return np, err } - p.turnConnStore[np] = turnConn + p.relayedConnStore[np] = relayedConn return np, nil } -func (p *WGEBPFProxy) removeTurnConn(turnConnID uint16) { - p.turnConnMutex.Lock() - defer p.turnConnMutex.Unlock() +func (p *WGEBPFProxy) removeRelayedConn(relayedConnID uint16) { + p.relayedConnMutex.Lock() + defer p.relayedConnMutex.Unlock() - _, ok := p.turnConnStore[turnConnID] + _, ok := p.relayedConnStore[relayedConnID] if ok { - log.Debugf("remove turn conn from store by port: %d", turnConnID) + log.Debugf("remove relayed conn from store by port: %d", relayedConnID) } - delete(p.turnConnStore, turnConnID) + delete(p.relayedConnStore, relayedConnID) } func (p *WGEBPFProxy) nextFreePort() (uint16, error) { - if len(p.turnConnStore) == 65535 { - return 0, fmt.Errorf("reached maximum turn connection numbers") + if len(p.relayedConnStore) == 65535 { + return 0, fmt.Errorf("reached maximum relayed connection numbers") } generatePort: if p.lastUsedPort == 65535 { @@ -236,7 +236,7 @@ generatePort: p.lastUsedPort++ } - if _, ok := p.turnConnStore[p.lastUsedPort]; ok { + if _, ok := p.relayedConnStore[p.lastUsedPort]; ok { goto generatePort } return p.lastUsedPort, nil diff --git a/client/iface/wgproxy/ebpf/proxy_test.go b/client/iface/wgproxy/ebpf/proxy_test.go index 3ec4f0eba..228c06c9b 100644 --- a/client/iface/wgproxy/ebpf/proxy_test.go +++ b/client/iface/wgproxy/ebpf/proxy_test.go @@ -9,32 +9,32 @@ import ( func TestWGEBPFProxy_connStore(t *testing.T) { wgProxy := NewWGEBPFProxy(1, 1280) - p, _ := wgProxy.storeTurnConn(nil) + p, _ := wgProxy.storeRelayedConn(nil) if p != 1 { t.Errorf("invalid initial port: %d", wgProxy.lastUsedPort) } numOfConns := 10 for i := 0; i < numOfConns; i++ { - p, _ = wgProxy.storeTurnConn(nil) + p, _ = wgProxy.storeRelayedConn(nil) } if p != uint16(numOfConns)+1 { t.Errorf("invalid last used port: %d, expected: %d", p, numOfConns+1) } - if len(wgProxy.turnConnStore) != numOfConns+1 { - t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), numOfConns+1) + if len(wgProxy.relayedConnStore) != numOfConns+1 { + t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), numOfConns+1) } } func TestWGEBPFProxy_portCalculation_overflow(t *testing.T) { wgProxy := NewWGEBPFProxy(1, 1280) - _, _ = wgProxy.storeTurnConn(nil) + _, _ = wgProxy.storeRelayedConn(nil) wgProxy.lastUsedPort = 65535 - p, _ := wgProxy.storeTurnConn(nil) + p, _ := wgProxy.storeRelayedConn(nil) - if len(wgProxy.turnConnStore) != 2 { - t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), 2) + if len(wgProxy.relayedConnStore) != 2 { + t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), 2) } if p != 2 { @@ -46,11 +46,11 @@ func TestWGEBPFProxy_portCalculation_maxConn(t *testing.T) { wgProxy := NewWGEBPFProxy(1, 1280) for i := 0; i < 65535; i++ { - _, _ = wgProxy.storeTurnConn(nil) + _, _ = wgProxy.storeRelayedConn(nil) } - _, err := wgProxy.storeTurnConn(nil) + _, err := wgProxy.storeRelayedConn(nil) if err == nil { - t.Errorf("invalid turn conn store calculation") + t.Errorf("invalid relayed conn store calculation") } } diff --git a/client/iface/wgproxy/ebpf/wrapper.go b/client/iface/wgproxy/ebpf/wrapper.go index a6156a661..f75e21aa6 100644 --- a/client/iface/wgproxy/ebpf/wrapper.go +++ b/client/iface/wgproxy/ebpf/wrapper.go @@ -121,10 +121,10 @@ func NewProxyWrapper(proxy *WGEBPFProxy) *ProxyWrapper { } } -func (p *ProxyWrapper) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error { - addr, err := p.wgeBPFProxy.AddTurnConn(remoteConn) +func (p *ProxyWrapper) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error { + addr, err := p.wgeBPFProxy.AddRelayedConn(remoteConn) if err != nil { - return fmt.Errorf("add turn conn: %w", err) + return fmt.Errorf("add relayed conn: %w", err) } headers, err := NewPacketHeaders(p.wgeBPFProxy.localWGListenPort, addr) @@ -252,7 +252,7 @@ func (p *ProxyWrapper) CloseConn() error { } func (p *ProxyWrapper) proxyToLocal(ctx context.Context) { - defer p.wgeBPFProxy.removeTurnConn(uint16(p.wgRelayedEndpointAddr.Port)) + defer p.wgeBPFProxy.removeRelayedConn(uint16(p.wgRelayedEndpointAddr.Port)) buf := make([]byte, p.wgeBPFProxy.mtu+bufsize.WGBufferOverhead) for { @@ -273,7 +273,7 @@ func (p *ProxyWrapper) proxyToLocal(ctx context.Context) { if ctx.Err() != nil { return } - log.Errorf("failed to write out turn pkg to local conn: %v", err) + log.Errorf("failed to write out relayed pkg to local conn: %v", err) } } } @@ -286,7 +286,7 @@ func (p *ProxyWrapper) readFromRemote(ctx context.Context, buf []byte) (int, err } p.closeListener.Notify() if !errors.Is(err, io.EOF) { - log.Errorf("failed to read from turn conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err) + log.Errorf("failed to read from relayed conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err) } return 0, err } diff --git a/client/iface/wgproxy/proxy.go b/client/iface/wgproxy/proxy.go index 40346bc15..b0033bffa 100644 --- a/client/iface/wgproxy/proxy.go +++ b/client/iface/wgproxy/proxy.go @@ -7,7 +7,7 @@ import ( // Proxy is a transfer layer between the relayed connection and the WireGuard type Proxy interface { - AddTurnConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error + AddRelayedConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error EndpointAddr() *net.UDPAddr // EndpointAddr returns the address of the WireGuard peer endpoint Work() // Work start or resume the proxy Pause() // Pause to forward the packages from remote connection to WireGuard. The opposite way still works. diff --git a/client/iface/wgproxy/proxy_test.go b/client/iface/wgproxy/proxy_test.go index 1aeab66b7..d86cdbe80 100644 --- a/client/iface/wgproxy/proxy_test.go +++ b/client/iface/wgproxy/proxy_test.go @@ -95,7 +95,7 @@ func TestProxyCloseByRemoteConn(t *testing.T) { t.Run(tt.name, func(t *testing.T) { addr, _ := net.ResolveUDPAddr("udp", "100.108.135.221:51892") relayedConn := newMockConn() - err := tt.proxy.AddTurnConn(ctx, addr, relayedConn) + err := tt.proxy.AddRelayedConn(ctx, addr, relayedConn) if err != nil { t.Errorf("error: %v", err) } @@ -157,7 +157,7 @@ func redirectTraffic(t *testing.T, proxy Proxy, wgPort int, endPointAddr *net.UD _ = relayedServer.Close() }() - if err := proxy.AddTurnConn(context.Background(), endPointAddr, relayedConn); err != nil { + if err := proxy.AddRelayedConn(context.Background(), endPointAddr, relayedConn); err != nil { t.Errorf("error: %v", err) } defer func() { diff --git a/client/iface/wgproxy/redirect_test.go b/client/iface/wgproxy/redirect_test.go index 135970838..f0d59cc64 100644 --- a/client/iface/wgproxy/redirect_test.go +++ b/client/iface/wgproxy/redirect_test.go @@ -119,9 +119,9 @@ func testRedirectAs(t *testing.T, proxy Proxy, wgPort int, nbAddr, p2pEndpoint * } defer relayConn.Close() - // Add TURN connection to proxy - if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil { - t.Fatalf("failed to add TURN connection: %v", err) + // Add relayed connection to proxy + if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil { + t.Fatalf("failed to add relayed connection: %v", err) } defer func() { if err := proxy.CloseConn(); err != nil { @@ -304,8 +304,8 @@ func TestRedirectAs_Multiple_Switches(t *testing.T) { Port: 38746, } - if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil { - t.Fatalf("failed to add TURN connection: %v", err) + if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil { + t.Fatalf("failed to add relayed connection: %v", err) } defer func() { if err := proxy.CloseConn(); err != nil { diff --git a/client/iface/wgproxy/udp/proxy.go b/client/iface/wgproxy/udp/proxy.go index 783843aba..a0895c8c7 100644 --- a/client/iface/wgproxy/udp/proxy.go +++ b/client/iface/wgproxy/udp/proxy.go @@ -51,12 +51,12 @@ func NewWGUDPProxy(wgPort int, mtu uint16) *WGUDPProxy { return p } -// AddTurnConn +// AddRelayedConn dials the local WireGuard port and stores the relayed connection. // The provided Context must be non-nil. If the context expires before // the connection is complete, an error is returned. Once successfully // connected, any expiration of the context will not affect the // connection. -func (p *WGUDPProxy) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error { +func (p *WGUDPProxy) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error { dialer := net.Dialer{} localConn, err := dialer.DialContext(ctx, "udp", fmt.Sprintf(":%d", p.localWGListenPort)) if err != nil { diff --git a/client/installer.nsis b/client/installer.nsis index 71699071b..eb2d7d5bd 100644 --- a/client/installer.nsis +++ b/client/installer.nsis @@ -22,8 +22,6 @@ !define UI_REG_APP_PATH "Software\Microsoft\Windows\CurrentVersion\App Paths\${UI_APP_EXE}" !define UI_UNINSTALL_PATH "Software\Microsoft\Windows\CurrentVersion\Uninstall\${UI_APP_NAME}" -!define AUTOSTART_REG_KEY "Software\Microsoft\Windows\CurrentVersion\Run" - !define NETBIRD_DATA_DIR "$COMMONPROGRAMDATA\Netbird" Unicode True @@ -228,13 +226,6 @@ WriteRegStr ${REG_ROOT} "${UNINSTALL_PATH}" "Publisher" "${COMP_NAME}" WriteRegStr ${REG_ROOT} "${UI_REG_APP_PATH}" "" "$INSTDIR\${UI_APP_EXE}" -; Autostart is owned by the UI's per-user setting (HKCU\...\Run via Wails), -; not the installer. Drop the machine-wide entry older installers wrote so the -; toggle is the single source of truth. HKCU is left untouched -- it may hold -; the user's own toggle state, which must survive upgrades. -DetailPrint "Removing installer-managed autostart registry entry if present..." -DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}" - EnVar::SetHKLM EnVar::AddValueEx "path" "$INSTDIR" @@ -299,15 +290,6 @@ ExecWait '"$INSTDIR\${MAIN_APP_EXE}" service uninstall' DetailPrint "Terminating Netbird UI process..." ExecWait `taskkill /im ${UI_APP_EXE}.exe /f` -; Remove autostart registry entries -DetailPrint "Removing autostart registry entries if they exist..." -; Legacy machine-wide entry written by older installers. -DeleteRegValue HKLM "${AUTOSTART_REG_KEY}" "${APP_NAME}" -; Per-user entry the UI toggle writes via Wails (value name is the lowercase -; app-name slug). Uninstall removes the app, so drop it too. -DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "${APP_NAME}" -DeleteRegValue HKCU "${AUTOSTART_REG_KEY}" "netbird" - ; Handle data deletion based on checkbox DetailPrint "Checking if user requested data deletion..." ${If} $DeleteDataEnabled == "1" diff --git a/client/internal/acl/manager.go b/client/internal/acl/manager.go index d9b179457..cbd9c5ab1 100644 --- a/client/internal/acl/manager.go +++ b/client/internal/acl/manager.go @@ -116,11 +116,11 @@ func (d *DefaultManager) ApplyFiltering(networkMap *mgmProto.NetworkMap, dnsRout // firewall state, so an identical hash means an identical resulting ruleset. func (d *DefaultManager) firewallConfigHash(networkMap *mgmProto.NetworkMap, dnsRouteFeatureFlag bool) (uint64, error) { return hashstructure.Hash(struct { - PeerRules []*mgmProto.FirewallRule - PeerRulesIsEmpty bool - RouteRules []*mgmProto.RouteFirewallRule - RouteRulesIsEmpty bool - DNSRouteFeatureFlag bool + PeerRules []*mgmProto.FirewallRule + PeerRulesIsEmpty bool + RouteRules []*mgmProto.RouteFirewallRule + RouteRulesIsEmpty bool + DNSRouteFeatureFlag bool }{ PeerRules: networkMap.GetFirewallRules(), PeerRulesIsEmpty: networkMap.GetFirewallRulesIsEmpty(), @@ -144,13 +144,13 @@ func (d *DefaultManager) applyPeerACLs(networkMap *mgmProto.NetworkMap) { log.Warn("this peer is connected to a NetBird Management service with an older version. Allowing all traffic from connected peers") rules = append(rules, &mgmProto.FirewallRule{ - PeerIP: "0.0.0.0", + PeerIP: "0.0.0.0", //nolint:staticcheck Direction: mgmProto.RuleDirection_IN, Action: mgmProto.RuleAction_ACCEPT, Protocol: mgmProto.RuleProtocol_ALL, }, &mgmProto.FirewallRule{ - PeerIP: "0.0.0.0", + PeerIP: "0.0.0.0", //nolint:staticcheck Direction: mgmProto.RuleDirection_OUT, Action: mgmProto.RuleAction_ACCEPT, Protocol: mgmProto.RuleProtocol_ALL, @@ -407,7 +407,6 @@ func (d *DefaultManager) getRuleGroupingSelector(rule *mgmProto.FirewallRule) st return fmt.Sprintf("%v:%v:%v:%s:%v", strconv.Itoa(int(rule.Direction)), rule.Action, rule.Protocol, rule.Port, rule.PortInfo) } - // extractRuleIP extracts the peer IP from a firewall rule. // If sourcePrefixes is populated (new management), decode the first entry and use its address. // Otherwise fall back to the deprecated PeerIP string field (old management). diff --git a/client/internal/acl/manager_test.go b/client/internal/acl/manager_test.go index 968654ae9..8f737706e 100644 --- a/client/internal/acl/manager_test.go +++ b/client/internal/acl/manager_test.go @@ -5,9 +5,9 @@ import ( "net/netip" "testing" - "github.com/golang/mock/gomock" "github.com/stretchr/testify/assert" "github.com/stretchr/testify/require" + "go.uber.org/mock/gomock" "github.com/netbirdio/netbird/client/firewall" "github.com/netbirdio/netbird/client/iface" @@ -87,7 +87,7 @@ func TestDefaultManager(t *testing.T) { networkMap.FirewallRules = append( networkMap.FirewallRules, &mgmProto.FirewallRule{ - PeerIP: "10.93.0.3", + PeerIP: "10.93.0.3", //nolint:staticcheck Direction: mgmProto.RuleDirection_IN, Action: mgmProto.RuleAction_DROP, Protocol: mgmProto.RuleProtocol_ICMP, @@ -556,12 +556,12 @@ func TestApplyFilteringSkipsUnchangedConfig(t *testing.T) { func buildNetworkMap(peerRules, routeRules int) *mgmProto.NetworkMap { nm := &mgmProto.NetworkMap{ - FirewallRulesIsEmpty: peerRules == 0, + FirewallRulesIsEmpty: peerRules == 0, RoutesFirewallRulesIsEmpty: routeRules == 0, } for i := range peerRules { nm.FirewallRules = append(nm.FirewallRules, &mgmProto.FirewallRule{ - PeerIP: fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff), + PeerIP: fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff), //nolint:staticcheck Direction: mgmProto.RuleDirection_IN, Action: mgmProto.RuleAction_ACCEPT, Protocol: mgmProto.RuleProtocol_TCP, diff --git a/client/internal/acl/mocks/iface_mapper.go b/client/internal/acl/mocks/iface_mapper.go index 95d5a2c58..f8cca1c2d 100644 --- a/client/internal/acl/mocks/iface_mapper.go +++ b/client/internal/acl/mocks/iface_mapper.go @@ -7,7 +7,7 @@ package mocks import ( reflect "reflect" - gomock "github.com/golang/mock/gomock" + gomock "go.uber.org/mock/gomock" wgdevice "golang.zx2c4.com/wireguard/device" "github.com/netbirdio/netbird/client/iface/device" diff --git a/client/internal/auth/auth.go b/client/internal/auth/auth.go index 153727a6c..b3a9e1158 100644 --- a/client/internal/auth/auth.go +++ b/client/internal/auth/auth.go @@ -138,26 +138,37 @@ func (a *Auth) IsSSOSupported(ctx context.Context) (bool, error) { // GetOAuthFlow returns an OAuth flow (PKCE or Device) using the existing management connection // This avoids creating a new connection to the management server -func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool) (OAuthFlow, error) { +func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool, hint string) (OAuthFlow, error) { var flow OAuthFlow - var err error - err = a.withRetry(ctx, func(client *mgm.GrpcClient) error { + err := a.withRetry(ctx, func(client *mgm.GrpcClient) error { if forceDeviceAuth { - flow, err = a.getDeviceFlow(client) - return err + deviceFlow, err := a.getDeviceFlow(client) + if err != nil { + return err + } + deviceFlow.SetLoginHint(hint) + flow = deviceFlow + return nil } // Try PKCE flow first - flow, err = a.getPKCEFlow(client) + pkceFlow, err := a.getPKCEFlow(client) if err != nil { // If PKCE not supported, try Device flow if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) { - flow, err = a.getDeviceFlow(client) - return err + deviceFlow, err := a.getDeviceFlow(client) + if err != nil { + return err + } + deviceFlow.SetLoginHint(hint) + flow = deviceFlow + return nil } return err } + pkceFlow.SetLoginHint(hint) + flow = pkceFlow return nil }) diff --git a/client/internal/auth/oauth.go b/client/internal/auth/oauth.go index a50a2ce6f..91329c98b 100644 --- a/client/internal/auth/oauth.go +++ b/client/internal/auth/oauth.go @@ -97,9 +97,7 @@ func authenticateWithPKCEFlow(ctx context.Context, config *profilemanager.Config return nil, fmt.Errorf("getting pkce authorization flow info failed with error: %v", err) } - if hint != "" { - pkceFlowInfo.SetLoginHint(hint) - } + pkceFlowInfo.SetLoginHint(hint) return pkceFlowInfo, nil } @@ -127,9 +125,7 @@ func authenticateWithDeviceCodeFlow(ctx context.Context, config *profilemanager. } } - if hint != "" { - deviceFlowInfo.SetLoginHint(hint) - } + deviceFlowInfo.SetLoginHint(hint) return deviceFlowInfo, nil } diff --git a/client/internal/connect.go b/client/internal/connect.go index ceb39419e..e45ecca44 100644 --- a/client/internal/connect.go +++ b/client/internal/connect.go @@ -38,6 +38,8 @@ import ( "github.com/netbirdio/netbird/client/internal/updater" "github.com/netbirdio/netbird/client/internal/updater/installer" nbnet "github.com/netbirdio/netbird/client/net" + "github.com/netbirdio/netbird/client/netstate" + "github.com/netbirdio/netbird/client/netsweep" cProto "github.com/netbirdio/netbird/client/proto" "github.com/netbirdio/netbird/client/ssh" sshconfig "github.com/netbirdio/netbird/client/ssh/config" @@ -70,18 +72,42 @@ type ConnectClient struct { updateManager *updater.Manager persistSyncResponse bool + + // netState gates every reconnection loop on OS-reported network + // availability. Nil (the default) disables gating; mobile platforms + // inject it via WithNetworkState. + netState *netstate.State + + // sweeper cuts the management, signal and relay connections on network + // change; nil disables it. + sweeper *netsweep.Sweeper +} + +// ConnectClientOption configures optional ConnectClient behavior. +type ConnectClientOption func(*ConnectClient) + +// WithNetworkState injects the OS network availability state that gates every +// reconnection loop; without it gating is disabled. +func WithNetworkState(netState *netstate.State) ConnectClientOption { + return func(c *ConnectClient) { c.netState = netState } +} + +// WithSweeper injects the network change sweeper. +func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption { + return func(c *ConnectClient) { c.sweeper = sweeper } } func NewConnectClient( ctx context.Context, config *profilemanager.Config, statusRecorder *peer.Status, + opts ...ConnectClientOption, ) *ConnectClient { // Derive the run context here so Stop owns the cancel that unblocks the run // loop. runCancel is set once at construction, so Stop can call it without // racing the run loop's startup. Callers therefore need not cancel before Stop. runCtx, runCancel := context.WithCancel(ctx) - return &ConnectClient{ + c := &ConnectClient{ ctx: runCtx, runCancel: runCancel, runExited: make(chan struct{}), @@ -89,6 +115,10 @@ func NewConnectClient( statusRecorder: statusRecorder, engineMutex: sync.Mutex{}, } + for _, opt := range opts { + opt(c) + } + return c } func (c *ConnectClient) SetUpdateManager(um *updater.Manager) { @@ -274,6 +304,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan return nil } + // suspend connection attempts while the OS reports no usable network + if waited, err := c.netState.Wait(c.ctx); err != nil { + return nil + } else if waited { + backOff.Reset() + } + state.Set(StatusConnecting) engineCtx, cancel := context.WithCancel(c.ctx) @@ -285,7 +322,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan }() log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host) - mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled) + mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled, + mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper)) if err != nil { // On daemon shutdown / Down() the parent context is cancelled // and the dial fails with "context canceled". Wrapping that @@ -360,7 +398,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan }() // with the global Netbird config in hand connect (just a connection, no stream yet) Signal - signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey) + signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper) if err != nil { log.Error(err) return wrapErr(err) @@ -396,7 +434,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan engineConfig.StateDir = filepath.Dir(path) } - relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU) + relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU, + relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper)) c.statusRecorder.SetRelayMgr(relayManager) if len(relayURLs) > 0 { if token != nil { @@ -424,6 +463,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan UpdateManager: c.updateManager, ClientMetrics: c.clientMetrics, MetricsCtx: c.ctx, + NetState: c.netState, }, mobileDependency) engine.SetSyncResponsePersistence(c.persistSyncResponse) c.engine = engine @@ -480,6 +520,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan // status stream stuck at Connecting. err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx)) if err != nil { + // Once the client context is cancelled backoff.WithContext surfaces the + // bare context error, and any attempt torn down mid-flight reports the + // same. That cancellation is the caller asking us to stop (Stop, Down or + // an engine restart), so exit cleanly instead of handing back a failure + // the caller would have to distinguish from a real one. + if c.ctx.Err() != nil && errors.Is(err, context.Canceled) { + log.Info("exiting client retry loop, context cancelled") + return nil + } + log.Debugf("exiting client retry loop due to unrecoverable error: %s", err) if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) { state.Set(StatusNeedsLogin) @@ -673,7 +723,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 { } // connectToSignal creates Signal Service client and established a connection -func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) { +func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) { var sigTLSEnabled bool if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS { sigTLSEnabled = true @@ -681,7 +731,8 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP sigTLSEnabled = false } - signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled) + signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled, + signal.WithNetworkState(netState), signal.WithSweeper(sweeper)) if err != nil { log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err) return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err) diff --git a/client/internal/debug/debug.go b/client/internal/debug/debug.go index 0f81844f6..1d31c75ca 100644 --- a/client/internal/debug/debug.go +++ b/client/internal/debug/debug.go @@ -34,9 +34,8 @@ import ( "github.com/netbirdio/netbird/shared/netiputil" ) -const readmeContent = `Netbird debug bundle -This debug bundle contains the following files. -If the --anonymize flag is set, the files are anonymized to protect sensitive information. +const readmeContent = `This debug bundle contains the following files. +If anonymization is enabled (--anonymize / --anonymize-level), the files are anonymized to protect sensitive information. status.txt: Anonymized status information of the NetBird client. client.log: Most recent, anonymized client log file of the NetBird client. @@ -52,6 +51,7 @@ nftables.txt: Anonymized nftables rules with packet counters across all families sysctls.txt: Forwarding, reverse-path filter, source-validation, and conntrack accounting sysctl values that the NetBird client may read or modify, if --system-info flag was provided (Linux only). resolv.conf: DNS resolver configuration from /etc/resolv.conf (Unix systems only), if --system-info flag was provided. scutil_dns.txt: DNS configuration from scutil --dns (macOS only), if --system-info flag was provided. +dns_windows.txt: Anonymized NRPT rules and policy table in effect, DNS client policy, and per-interface and per-adapter DNS configuration (Windows only), if --system-info flag was provided. resolved_domains.txt: Anonymized resolved domain IP addresses from the status recorder. config.txt: Anonymized configuration information of the NetBird client. network_map.json: Anonymized sync response containing peer configurations, routes, DNS settings, and firewall rules. @@ -70,21 +70,34 @@ capture.pcap: Packet capture in pcap format. Only present when capture was runni Anonymization Process -The files in this bundle have been anonymized to protect sensitive information. Here's how the anonymization was applied: +The files in this bundle have been anonymized to protect sensitive information. The level applied to this bundle is recorded at the top of this file. Here's how the anonymization was applied: IP Addresses -IPv4 addresses are replaced with addresses starting from 198.51.100.0 -IPv6 addresses are replaced with addresses starting from 100:: +Default level: +- Public IPv4 addresses are replaced with addresses starting from 198.51.100.0 +- Public IPv6 addresses are replaced with addresses starting from 2001:db8:ffff:: +- IPv6 unique local addresses (fc00::/7) are anonymized as well: their random global ID uniquely identifies the network. +- IP addresses from internal IPv4 ranges and well-known addresses are not anonymized (e.g. 8.8.8.8, 100.64.0.0/10, addresses starting with 192.168., 172.16., 10., 169.254., fe80::). + +Strict level (--anonymize-level strict), in addition to the default level: +- Private (RFC 1918), CGNAT (100.64.0.0/10), and link-local (169.254.0.0/16, fe80::/10) addresses are anonymized too. +- Internal IPv4 addresses are replaced with addresses starting from 198.18.0.0 and internal IPv6 addresses with addresses starting from 2001:db8:1::, so internal addresses remain distinguishable from public ones. +- Addresses are mapped in order of first appearance: subnet structure, allocation scheme, and gateway conventions are not preserved. Prefix lengths of networks are preserved. +- Peer names in front of NetBird domains are replaced with numbered placeholders (e.g. peer-1.netbird.cloud), and subdomain labels of other domains with host-N placeholders. +- WireGuard public keys are replaced with consistent placeholder keys. -IP addresses from non public ranges and well known addresses are not anonymized (e.g. 8.8.8.8, 100.64.0.0/10, addresses starting with 192.168., 172.16., 10., etc.). Reoccuring IP addresses are replaced with the same anonymized address. Note: The anonymized IP addresses in the status file do not match those in the log and routes files. However, the anonymized IP addresses are consistent within the status file and across the routes and log files. +MAC Addresses +MAC addresses are replaced at every anonymization level with consistent placeholders counting up from 02:00:00:00:00:01. Broadcast, multicast, and all-zero addresses are kept. At the default level a preserved IPv6 link-local address may still embed a MAC address (EUI-64); the strict level anonymizes those addresses. + Domains All domain names (except for the netbird domains) are replaced with randomly generated strings ending in ".domain". Anonymized domains are consistent across all files in the bundle. Reoccuring domain names are replaced with the same anonymized domain. +At the strict level, the peer name labels in front of netbird domains are anonymized as well. Sync Response The network_map.json file contains the following anonymized information: @@ -225,6 +238,13 @@ scutil_dns.txt (macOS only): - Shows DNS configuration for all network interfaces - Includes search domains, nameservers, and DNS resolver settings - All IP addresses and domain names are anonymized + +dns_windows.txt (Windows only): +- Lists the NRPT rules of both policy stores, the local one and the group policy one, marking the rules the client created +- Follows them with the policy table the resolver has loaded, which differs from the rules while a change has not been picked up yet +- Includes the DNS client group policy, the global TCP/IP and Dnscache parameters, and the DNS values of every interface that has any +- Ends with the resolver configuration in effect per adapter, from GetAdaptersAddresses +- All IP addresses and domain names are anonymized ` const ( @@ -281,6 +301,7 @@ type BundleGenerator struct { cliVersion string anonymize bool + anonymizeLevel anonymize.Level includeSystemInfo bool logFileCount uint32 @@ -288,7 +309,10 @@ type BundleGenerator struct { } type BundleConfig struct { - Anonymize bool + Anonymize bool + // AnonymizeLevel selects how much the anonymizer redacts. + // anonymize.LevelStrict implies Anonymize. + AnonymizeLevel anonymize.Level IncludeSystemInfo bool LogFileCount uint32 } @@ -327,8 +351,11 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen uiLogOpener = openLogFile } + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(cfg.AnonymizeLevel) + return &BundleGenerator{ - anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()), + anonymizer: anonymizer, internalConfig: deps.InternalConfig, statusRecorder: deps.StatusRecorder, @@ -345,7 +372,8 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen daemonVersion: deps.DaemonVersion, cliVersion: deps.CliVersion, - anonymize: cfg.Anonymize, + anonymize: cfg.Anonymize || cfg.AnonymizeLevel >= anonymize.LevelStrict, + anonymizeLevel: cfg.AnonymizeLevel, includeSystemInfo: cfg.IncludeSystemInfo, logFileCount: logFileCount, } @@ -485,7 +513,13 @@ func (g *BundleGenerator) addSystemInfo() { } func (g *BundleGenerator) addReadme() error { - readmeReader := strings.NewReader(readmeContent) + level := "none (anonymization disabled)" + if g.anonymize { + level = g.anonymizeLevel.String() + } + header := fmt.Sprintf("Netbird debug bundle\nAnonymization level applied to this bundle: %s\n", level) + + readmeReader := strings.NewReader(header + readmeContent) if err := g.addFileToZip(readmeReader, "README.txt"); err != nil { return fmt.Errorf("add README file to zip: %w", err) } @@ -507,9 +541,10 @@ func (g *BundleGenerator) addStatus() error { fullStatus := g.statusRecorder.GetFullStatus() protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus) overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{ - Anonymize: g.anonymize, - ProfileName: profName, - DaemonVersion: g.daemonVersion, + Anonymize: g.anonymize, + AnonymizeLevel: g.anonymizeLevel, + ProfileName: profName, + DaemonVersion: g.daemonVersion, }) overview.CliVersion = g.cliVersion statusOutput := overview.FullDetailSummary() @@ -662,7 +697,7 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder) configContent.WriteString("NetBird Client Configuration:\n\n") if key, err := wgtypes.ParseKey(g.internalConfig.PrivateKey); err == nil { - configContent.WriteString(fmt.Sprintf("PublicKey: %s\n", key.PublicKey().String())) + configContent.WriteString(fmt.Sprintf("PublicKey: %s\n", g.anonymizer.AnonymizeWGKey(key.PublicKey().String()))) } configContent.WriteString(fmt.Sprintf("WgIface: %s\n", g.internalConfig.WgIface)) configContent.WriteString(fmt.Sprintf("WgPort: %d\n", g.internalConfig.WgPort)) @@ -952,6 +987,11 @@ func (g *BundleGenerator) addUpdateLogs() error { } baseName := filepath.Base(logFile) + data, err = g.anonymizeBytes(data) + if err != nil { + log.Warnf("skipping update log file %s: %v", baseName, err) + continue + } if err := g.addFileToZip(bytes.NewReader(data), filepath.Join("update-logs", baseName)); err != nil { return fmt.Errorf("add update log file %s to zip: %w", baseName, err) } @@ -979,6 +1019,13 @@ func (g *BundleGenerator) addCorruptedStateFiles() error { } fileName := filepath.Base(match) + // Corrupted state files usually fail structured JSON anonymization, + // so run them through the string anonymizer instead. + data, err = g.anonymizeBytes(data) + if err != nil { + log.Warnf("skipping corrupted state file %s: %v", fileName, err) + continue + } if err := g.addFileToZip(bytes.NewReader(data), "corrupted_states/"+fileName); err != nil { log.Warnf("Failed to add corrupted state file %s to zip: %v", fileName, err) continue @@ -990,6 +1037,27 @@ func (g *BundleGenerator) addCorruptedStateFiles() error { return nil } +// anonymizeBytes runs raw file content through the string anonymizer line by +// line when anonymization is enabled. It errors instead of returning partial +// content, so a caller never adds an unanonymized fallback to the bundle. +func (g *BundleGenerator) anonymizeBytes(data []byte) ([]byte, error) { + if !g.anonymize { + return data, nil + } + + var buf bytes.Buffer + scanner := bufio.NewScanner(bytes.NewReader(data)) + scanner.Buffer(make([]byte, 1024*1024), 1024*1024) + for scanner.Scan() { + buf.WriteString(g.anonymizer.AnonymizeString(scanner.Text())) + buf.WriteByte('\n') + } + if err := scanner.Err(); err != nil { + return nil, fmt.Errorf("anonymize content: %w", err) + } + return buf.Bytes(), nil +} + func (g *BundleGenerator) addMetrics() error { if g.clientMetrics == nil { log.Debugf("skipping metrics in debug bundle: no metrics collector") @@ -1462,6 +1530,7 @@ func anonymizeRemotePeer(peer *mgmProto.RemotePeerConfig, anonymizer *anonymize. } peer.Fqdn = anonymizer.AnonymizeDomain(peer.Fqdn) + peer.WgPubKey = anonymizer.AnonymizeWGKey(peer.WgPubKey) anonymizeSSHConfig(peer.SshConfig) } diff --git a/client/internal/debug/debug_linux.go b/client/internal/debug/debug_linux.go index 40d864eda..a36c0c0e7 100644 --- a/client/internal/debug/debug_linux.go +++ b/client/internal/debug/debug_linux.go @@ -844,6 +844,10 @@ func collectSysctls() string { []string{"net.ipv4.conf.all.src_valid_mark", "net.ipv4.conf.default.src_valid_mark"}, listInterfaceSysctls("ipv4", "src_valid_mark")..., )) + writeSysctlGroup(&builder, "accept_ra", append( + []string{"net.ipv6.conf.all.accept_ra", "net.ipv6.conf.default.accept_ra"}, + listInterfaceSysctls("ipv6", "accept_ra")..., + )) writeSysctlGroup(&builder, "conntrack", []string{ "net.netfilter.nf_conntrack_acct", "net.netfilter.nf_conntrack_tcp_loose", diff --git a/client/internal/debug/debug_nonunix.go b/client/internal/debug/debug_nonunix.go index 18d017050..adc9b9649 100644 --- a/client/internal/debug/debug_nonunix.go +++ b/client/internal/debug/debug_nonunix.go @@ -1,4 +1,4 @@ -//go:build !unix +//go:build !unix && !windows package debug diff --git a/client/internal/debug/debug_windows.go b/client/internal/debug/debug_windows.go new file mode 100644 index 000000000..e88940fd3 --- /dev/null +++ b/client/internal/debug/debug_windows.go @@ -0,0 +1,443 @@ +//go:build windows + +package debug + +import ( + "encoding/hex" + "errors" + "fmt" + "net/netip" + "strings" + "unsafe" + + log "github.com/sirupsen/logrus" + "golang.org/x/sys/windows" + "golang.org/x/sys/windows/registry" + + nbdns "github.com/netbirdio/netbird/client/internal/dns" +) + +const dnsInfoFileName = "dns_windows.txt" + +const ( + gpoDNSClientRoot = `SOFTWARE\Policies\Microsoft\Windows NT\DNSClient` + tcpipParamsPath = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters` + dnscacheParams = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters` +) + +// interfaceDNSValues are the per-interface values that decide how a name is +// resolved and registered. Everything the DNS host manager writes is in here, +// so a bundle shows both what we set and what it replaced. +var interfaceDNSValues = []string{ + "NameServer", + "DhcpNameServer", + "Domain", + "DhcpDomain", + "SearchList", + "RegistrationEnabled", + "DisableDynamicUpdate", + "MaxNumberOfAddressesToRegister", + "EnableDHCP", +} + +// addDNSInfo collects and adds DNS configuration information to the archive +func (g *BundleGenerator) addDNSInfo() error { + if err := g.addFileToZip(strings.NewReader(g.collectDNSInfo()), dnsInfoFileName); err != nil { + return fmt.Errorf("add DNS info to zip: %w", err) + } + + return nil +} + +// collectDNSInfo renders the report. Everything below it reaches the platform +// through COM and through lazily resolved procedures, which panic when a +// procedure is missing rather than returning an error, and a debug bundle is not +// allowed to take the daemon down. The panic is contained here, and whatever was +// collected before it is kept and reported with it. +func (g *BundleGenerator) collectDNSInfo() (content string) { + var sb strings.Builder + + defer func() { + if r := recover(); r != nil { + log.Errorf("collecting Windows DNS configuration panicked: %v", r) + fmt.Fprintf(&sb, "\nerror: collection stopped: %v\n", r) + } + content = sb.String() + }() + + sb.WriteString("Windows DNS configuration\n") + sb.WriteString("=========================\n") + + adapters, adaptersErr := adapterAddresses() + + g.writeNRPTRules(&sb, "NRPT rules, local policy store", nbdns.DNSPolicyConfigRoot) + g.writeNRPTRules(&sb, "NRPT rules, group policy store", nbdns.GPODNSPolicyConfigRoot) + g.writeEffectiveNRPTPolicies(&sb) + g.writeRegistryKey(&sb, "DNS client group policy", gpoDNSClientRoot) + g.writeRegistryKey(&sb, "Global TCP/IP parameters", tcpipParamsPath) + g.writeRegistryKey(&sb, "Dnscache parameters", dnscacheParams) + g.writeInterfaceDNS(&sb, "Per-interface DNS, IPv4", nbdns.InterfaceConfigPath, adapterNames(adapters)) + g.writeInterfaceDNS(&sb, "Per-interface DNS, IPv6", nbdns.InterfaceConfigPathV6, adapterNames(adapters)) + g.writeAdapterDNS(&sb, adapters, adaptersErr) + + return sb.String() +} + +// writeNRPTRules lists every rule in a policy store, ours and any other +// product's, since a foreign rule for the same namespace decides resolution +// just as ours does. Rules the client wrote are marked. +func (g *BundleGenerator) writeNRPTRules(sb *strings.Builder, title, root string) { + writeSection(sb, title, root) + + names, err := subKeyNames(root) + if err != nil { + fmt.Fprintf(sb, "error: %v\n", err) + return + } + + if len(names) == 0 { + sb.WriteString("no rules\n") + return + } + + for _, name := range names { + owner := "" + if strings.HasPrefix(strings.ToLower(name), strings.ToLower(nbdns.NRPTKeyPrefix)) { + owner = " (netbird)" + } + fmt.Fprintf(sb, "%s%s\n", name, owner) + g.writeValues(sb, root+`\`+name, nil, " ") + } +} + +// writeEffectiveNRPTPolicies reports the table the resolver answers from, which +// the registry cannot show: a rule is written before it is loaded, and it keeps +// being enforced after its key is gone until the resolver reloads its policy. +func (g *BundleGenerator) writeEffectiveNRPTPolicies(sb *strings.Builder) { + writeSection(sb, "NRPT policy table in effect", nrptPolicyClass+"."+nrptPolicyMethod+" in "+nrptPolicyNamespace) + + entries, err := effectiveNRPTPolicies() + if err != nil { + fmt.Fprintf(sb, "error: %v\n", err) + return + } + + if len(entries) == 0 { + sb.WriteString("no policies\n") + return + } + + for _, entry := range entries { + fmt.Fprintf(sb, "%s\n", g.anonymizeValue("Namespace", entry.namespace)) + for _, value := range entry.values { + fmt.Fprintf(sb, " %s: %s\n", value.name, g.anonymizeValue(value.name, value.value)) + } + } +} + +// writeInterfaceDNS reports the DNS values of every interface that has any, so +// the netbird interface can be compared against the physical ones. The registry +// keys the values by GUID, so each is named from the adapter list; a GUID with +// no adapter is a leftover key of an interface that no longer exists. +func (g *BundleGenerator) writeInterfaceDNS(sb *strings.Builder, title, root string, names map[string]string) { + writeSection(sb, title, root) + + guids, err := subKeyNames(root) + if err != nil { + fmt.Fprintf(sb, "error: %v\n", err) + return + } + + var reported int + for _, guid := range guids { + var iface strings.Builder + g.writeValues(&iface, root+`\`+guid, interfaceDNSValues, " ") + if iface.Len() == 0 { + continue + } + + name, ok := names[strings.ToLower(guid)] + if !ok { + name = "no adapter with this GUID" + } + + reported++ + fmt.Fprintf(sb, "%s (%s)\n%s", guid, name, iface.String()) + } + + if reported == 0 { + sb.WriteString("no interface holds DNS values\n") + } +} + +// writeRegistryKey reports the values of a single key, without its subkeys. +func (g *BundleGenerator) writeRegistryKey(sb *strings.Builder, title, path string) { + writeSection(sb, title, path) + + var values strings.Builder + g.writeValues(&values, path, nil, "") + if values.Len() == 0 { + sb.WriteString("no values\n") + return + } + + sb.WriteString(values.String()) +} + +// writeValues renders the values of a key. A nil names list reports every +// value, otherwise only those named and present. +func (g *BundleGenerator) writeValues(sb *strings.Builder, path string, names []string, indent string) { + k, err := registry.OpenKey(registry.LOCAL_MACHINE, path, registry.QUERY_VALUE) + switch { + case errors.Is(err, registry.ErrNotExist), errors.Is(err, windows.ERROR_PATH_NOT_FOUND): + // an absent key is the normal state for the GPO store and for + // interfaces without DNS settings + log.Debugf("HKEY_LOCAL_MACHINE\\%s does not exist", path) + return + case err != nil: + fmt.Fprintf(sb, "%serror: open HKEY_LOCAL_MACHINE\\%s: %v\n", indent, path, err) + return + } + defer closeKey(k) + + if names == nil { + names, err = k.ReadValueNames(-1) + if err != nil { + fmt.Fprintf(sb, "%serror: read value names: %v\n", indent, err) + return + } + } + + for _, name := range names { + value, err := readRegistryValue(k, name) + switch { + case errors.Is(err, registry.ErrNotExist): + // the caller asks for a fixed set of values, most of which a + // given interface does not carry + continue + case err != nil: + // report rather than omit: a value that is there but cannot be + // read reads as unset otherwise + fmt.Fprintf(sb, "%s%s: error: %v\n", indent, name, err) + continue + } + + fmt.Fprintf(sb, "%s%s: %s\n", indent, name, g.anonymizeValue(name, value)) + } +} + +// anonymizeValue redacts a registry value according to what its name says it +// holds. Domains and addresses are handled per entry rather than by the string +// pass: the pass only replaces domains something else in the bundle already +// seeded, and its address regex would eat the digit labels of a reverse zone. +func (g *BundleGenerator) anonymizeValue(name, value string) string { + if !g.anonymize || value == "" { + return value + } + + switch { + case holdsDomains(name): + return joinValueEntries(splitValueEntries(value), g.anonymizeDomain) + case holdsAddresses(name): + return joinValueEntries(splitValueEntries(value), g.anonymizer.AnonymizeIPString) + default: + return g.anonymizer.AnonymizeString(value) + } +} + +// holdsDomains reports whether a value name holds domains: the domain list of +// an NRPT rule (Name) or of the policy table (Namespace), a search list, the +// DNS suffix values of the TCP/IP and policy keys, which all end in "Domain" +// (Domain, DhcpDomain, NV Domain, ICSDomain), and a proxy host name. +func holdsDomains(name string) bool { + lower := strings.ToLower(name) + return lower == "name" || lower == "namespace" || lower == "searchlist" || + strings.HasSuffix(lower, "domain") || strings.HasSuffix(lower, "proxyname") +} + +// holdsAddresses reports whether a value name holds DNS server addresses +// (NameServer, DhcpNameServer, GenericDNSServers, NameServers). +func holdsAddresses(name string) bool { + lower := strings.ToLower(name) + return strings.Contains(lower, "nameserver") || strings.Contains(lower, "dnsserver") +} + +// adapterNames maps adapter GUIDs, as the registry keys the interfaces, to the +// names an operator sees. +func adapterNames(adapters []*windows.IpAdapterAddresses) map[string]string { + names := make(map[string]string, len(adapters)) + for _, adapter := range adapters { + guid := windows.BytePtrToString(adapter.AdapterName) + names[strings.ToLower(guid)] = windows.UTF16PtrToString(adapter.FriendlyName) + } + return names +} + +// writeAdapterDNS reports the resolver configuration in effect per adapter, +// which is what the resolver uses for a name no NRPT rule matches. +func (g *BundleGenerator) writeAdapterDNS(sb *strings.Builder, adapters []*windows.IpAdapterAddresses, err error) { + writeSection(sb, "Adapter DNS configuration", "GetAdaptersAddresses") + + if err != nil { + fmt.Fprintf(sb, "error: %v\n", err) + return + } + + for _, adapter := range adapters { + name := windows.UTF16PtrToString(adapter.FriendlyName) + suffix := g.anonymizeDomain(windows.UTF16PtrToString(adapter.DnsSuffix)) + + fmt.Fprintf(sb, "%s (index %d, oper status %d)\n", name, adapter.IfIndex, adapter.OperStatus) + fmt.Fprintf(sb, " DNS suffix: %s\n", suffix) + + var servers []string + for server := adapter.FirstDnsServerAddress; server != nil; server = server.Next { + addr, ok := netip.AddrFromSlice(server.Address.IP()) + if !ok { + continue + } + + addr = addr.Unmap() + if g.anonymize { + addr = g.anonymizer.AnonymizeIP(addr) + } + servers = append(servers, addr.String()) + } + + fmt.Fprintf(sb, " DNS servers: %s\n", strings.Join(servers, ", ")) + } +} + +// anonymizeDomain anonymizes a single domain, keeping the leading dot an NRPT +// match domain carries. +func (g *BundleGenerator) anonymizeDomain(entry string) string { + if !g.anonymize { + return entry + } + + domain, dot := strings.CutPrefix(entry, ".") + if domain == "" { + return entry + } + + anonymized := g.anonymizer.AnonymizeDomain(domain) + if dot { + anonymized = "." + anonymized + } + return anonymized +} + +// splitValueEntries splits a registry value that holds a list. The separator +// differs per value: a REG_MULTI_SZ arrives joined with ", ", a SearchList is +// comma separated and a NameServer may use commas or spaces. +func splitValueEntries(value string) []string { + return strings.FieldsFunc(value, func(r rune) bool { + return r == ',' || r == ';' || r == ' ' || r == '\t' + }) +} + +func joinValueEntries(entries []string, anonymize func(string) string) string { + for i, entry := range entries { + entries[i] = anonymize(entry) + } + return strings.Join(entries, ", ") +} + +func writeSection(sb *strings.Builder, title, source string) { + fmt.Fprintf(sb, "\n%s\n%s\n%s\n", title, strings.Repeat("-", len(title)), source) +} + +func subKeyNames(root string) ([]string, error) { + k, err := registry.OpenKey(registry.LOCAL_MACHINE, root, registry.ENUMERATE_SUB_KEYS) + if err != nil { + return nil, fmt.Errorf("open HKEY_LOCAL_MACHINE\\%s: %w", root, err) + } + defer closeKey(k) + + names, err := k.ReadSubKeyNames(-1) + if err != nil { + return nil, fmt.Errorf("read subkey names: %w", err) + } + + return names, nil +} + +// readRegistryValue renders a value as text regardless of its type, so an +// unexpected type in a policy key still shows up instead of being dropped. +func readRegistryValue(k registry.Key, name string) (string, error) { + _, valueType, err := k.GetValue(name, nil) + if err != nil { + return "", fmt.Errorf("get value %s: %w", name, err) + } + + switch valueType { + case registry.SZ, registry.EXPAND_SZ: + value, _, err := k.GetStringValue(name) + if err != nil { + return "", fmt.Errorf("get string value %s: %w", name, err) + } + return value, nil + case registry.MULTI_SZ: + values, _, err := k.GetStringsValue(name) + if err != nil { + return "", fmt.Errorf("get strings value %s: %w", name, err) + } + return strings.Join(values, ", "), nil + case registry.DWORD, registry.QWORD: + value, _, err := k.GetIntegerValue(name) + if err != nil { + return "", fmt.Errorf("get integer value %s: %w", name, err) + } + return fmt.Sprintf("%d (0x%x)", value, value), nil + case registry.BINARY: + value, _, err := k.GetBinaryValue(name) + if err != nil { + return "", fmt.Errorf("get binary value %s: %w", name, err) + } + return hex.EncodeToString(value), nil + default: + return fmt.Sprintf("", valueType), nil + } +} + +// adapterAddresses returns the adapter list including DNS servers. The call +// reports the size it needs, so grow the buffer and retry until it fits. +func adapterAddresses() (adapters []*windows.IpAdapterAddresses, err error) { + // GetAdaptersAddresses is resolved on first use and panics when it is + // missing, so this reports it as an error and leaves the rest of the + // report intact. + defer func() { + if r := recover(); r != nil { + adapters, err = nil, fmt.Errorf("GetAdaptersAddresses: %v", r) + } + }() + + const flags = windows.GAA_FLAG_SKIP_ANYCAST | windows.GAA_FLAG_SKIP_MULTICAST + + size := uint32(15000) + for range 3 { + buf := make([]byte, size) + first := (*windows.IpAdapterAddresses)(unsafe.Pointer(&buf[0])) + + err := windows.GetAdaptersAddresses(windows.AF_UNSPEC, flags, 0, first, &size) + if errors.Is(err, windows.ERROR_BUFFER_OVERFLOW) { + continue + } + if err != nil { + return nil, fmt.Errorf("GetAdaptersAddresses: %w", err) + } + + for adapter := first; adapter != nil; adapter = adapter.Next { + adapters = append(adapters, adapter) + } + return adapters, nil + } + + return nil, fmt.Errorf("GetAdaptersAddresses: buffer kept growing") +} + +func closeKey(k registry.Key) { + if err := k.Close(); err != nil { + log.Debugf("close registry key: %v", err) + } +} diff --git a/client/internal/debug/debug_windows_test.go b/client/internal/debug/debug_windows_test.go new file mode 100644 index 000000000..47df3f6f9 --- /dev/null +++ b/client/internal/debug/debug_windows_test.go @@ -0,0 +1,146 @@ +//go:build windows + +package debug + +import ( + "strings" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/client/anonymize" +) + +func newDNSValueGenerator(level anonymize.Level) *BundleGenerator { + anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(level) + + return &BundleGenerator{ + anonymize: true, + anonymizeLevel: level, + anonymizer: anonymizer, + } +} + +// TestAnonymizeValueByName covers the value kinds of the DNS registry keys. The +// names decide the treatment, because the string pass alone replaces only +// domains another part of the bundle already seeded. +func TestAnonymizeValueByName(t *testing.T) { + tests := []struct { + name string + valueName string + value string + assert func(t *testing.T, got string) + }{ + { + name: "NRPT match domains keep the leading dot", + valueName: "Name", + value: ".internal.example.com, .corp.example.org", + assert: func(t *testing.T, got string) { + t.Helper() + for _, entry := range strings.Split(got, ", ") { + assert.True(t, strings.HasPrefix(entry, "."), "entry %q should keep its leading dot", entry) + assert.NotContains(t, entry, "example", "entry %q should not keep the original domain", entry) + } + }, + }, + { + name: "any value name ending in Domain is treated as a domain", + valueName: "ICSDomain", + value: "mshome.net", + assert: func(t *testing.T, got string) { + t.Helper() + assert.NotContains(t, got, "mshome", "should anonymize a domain suffix value") + }, + }, + { + name: "search list is a comma separated domain list", + valueName: "SearchList", + value: "corp.example.com,branch.example.com", + assert: func(t *testing.T, got string) { + t.Helper() + assert.NotContains(t, got, "example", "should anonymize every search domain") + assert.Len(t, strings.Split(got, ", "), 2, "should keep both search domains") + }, + }, + { + name: "name servers are anonymized as addresses", + valueName: "DhcpNameServer", + value: "203.0.113.10 8.8.8.8", + assert: func(t *testing.T, got string) { + t.Helper() + assert.NotContains(t, got, "203.0.113.10", "should anonymize a public resolver address") + // well-known resolvers stay readable at every level + assert.Contains(t, got, "8.8.8.8", "should keep a well-known resolver address") + }, + }, + { + name: "opaque values are left to the string pass", + valueName: "DataBasePath", + value: `%SystemRoot%\System32\drivers\etc`, + assert: func(t *testing.T, got string) { + t.Helper() + assert.Equal(t, `%SystemRoot%\System32\drivers\etc`, got, "should not alter a path") + }, + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + g := newDNSValueGenerator(anonymize.LevelDefault) + tc.assert(t, g.anonymizeValue(tc.valueName, tc.value)) + }) + } +} + +// TestParseNRPTPolicyTable parses the MOF text of the policy table out +// parameters, as the provider on a client with one NRPT rule renders it. +func TestParseNRPTPolicyTable(t *testing.T) { + const text = `[abstract] +class __PARAMETERS +{ + [Out, EmbeddedInstance("DnsClientPolicyConfiguration"): ToSubClass, ID(2): DisableOverride ToInstance] DnsClientPolicyConfiguration cmdletOutput[] = { +instance of DnsClientPolicyConfiguration +{ + DirectAccessProxyType = "NoProxy"; + DirectAccessQueryIPsecRequired = FALSE; + NameEncoding = "Utf8WithoutMapping"; + Namespace = ".0.100.in-addr.arpa"; +}, +instance of DnsClientPolicyConfiguration +{ + DirectAccessProxyType = "NoProxy"; + NameEncoding = "Utf8WithoutMapping"; + NameServers = {"100.0.255.254", "100.0.255.253"}; + Namespace = ".nb.internal"; +}}; + [in] boolean Effective; + [out] uint32 ReturnValue = 0; +}; +` + + entries := parseNRPTPolicyTable(text) + require.Len(t, entries, 2, "should parse both embedded instances") + + assert.Equal(t, ".0.100.in-addr.arpa", entries[0].namespace, "should read the namespace of the first instance") + assert.Equal(t, ".nb.internal", entries[1].namespace, "should read the namespace of the second instance") + + assert.Equal(t, []registryValue{ + {name: "DirectAccessProxyType", value: "NoProxy"}, + {name: "DirectAccessQueryIPsecRequired", value: "FALSE"}, + {name: "NameEncoding", value: "Utf8WithoutMapping"}, + }, entries[0].values, "should keep the remaining values in order") + + assert.Contains(t, entries[1].values, registryValue{name: "NameServers", value: "100.0.255.254, 100.0.255.253"}, + "should flatten a MOF array") + + for _, value := range entries[1].values { + assert.NotContains(t, value.name, "ReturnValue", "should not read the class level parameters as values") + } +} + +func TestParseNRPTPolicyTableEmpty(t *testing.T) { + assert.Empty(t, parseNRPTPolicyTable(""), "should parse no entries from empty text") + assert.Empty(t, parseNRPTPolicyTable("class __PARAMETERS\n{\n};\n"), "should parse no entries from a table with no instances") +} diff --git a/client/internal/debug/nrpt_windows.go b/client/internal/debug/nrpt_windows.go new file mode 100644 index 000000000..6b6e0e29a --- /dev/null +++ b/client/internal/debug/nrpt_windows.go @@ -0,0 +1,317 @@ +//go:build windows + +package debug + +import ( + "errors" + "fmt" + "runtime" + "strings" + "time" + + "github.com/go-ole/go-ole" + "github.com/go-ole/go-ole/oleutil" + log "github.com/sirupsen/logrus" +) + +const ( + // The NRPT policy table is reachable through the CIM class that backs + // Get-DnsClientNrptPolicy. Unlike the rules in the registry, the table is + // what the resolver currently has loaded, which is the only way to tell an + // applied rule from one that is merely written, in either direction. + nrptPolicyNamespace = `root\Microsoft\Windows\DNS` + nrptPolicyClass = "PS_DnsClientNrptPolicy" + nrptPolicyMethod = "Get" + + // The class has no instances, so the table comes from the out parameters + // of a static method call, rendered as MOF text: the embedded instances + // arrive as a safe array of objects, which cannot be read back through the + // COM bindings, and the text form carries all of them. + nrptPolicyInstanceKeyword = "instance of DnsClientPolicyConfiguration" + + nrptPolicyTimeout = 15 * time.Second +) + +// COM initialization results that leave the calling thread usable: S_FALSE for +// a thread this process already initialized, RPC_E_CHANGED_MODE for one that +// belongs to another apartment. +const ( + sFalse = 0x00000001 + rpcEChangedMode = 0x80010106 +) + +// nrptQueryInFlight admits one read of the policy table at a time. A provider +// that stops answering keeps its goroutine and the OS thread that goroutine +// pinned, so a later bundle reports that instead of pinning another one. +var nrptQueryInFlight = make(chan struct{}, 1) + +// nrptPolicyEntry is one namespace of the effective policy table, holding the +// values of an embedded DnsClientPolicyConfiguration instance in the order the +// provider reported them. +type nrptPolicyEntry struct { + namespace string + values []registryValue +} + +// registryValue is a name and its rendered value, shared by the registry and +// policy table readers so both anonymize by value name the same way. +type registryValue struct { + name string + value string +} + +// effectiveNRPTPolicies reads the effective NRPT table. The call is bounded +// because a WMI provider can block indefinitely and a debug bundle must not. +func effectiveNRPTPolicies() ([]nrptPolicyEntry, error) { + type result struct { + text string + err error + } + + select { + case nrptQueryInFlight <- struct{}{}: + default: + return nil, errors.New("an earlier read of the policy table has not returned") + } + + done := make(chan result, 1) + go func() { + // the slot is released here rather than by the caller, so a read that + // outlives the timeout holds it until the provider answers + defer func() { <-nrptQueryInFlight }() + + text, err := nrptPolicyTableText() + done <- result{text: text, err: err} + }() + + select { + case res := <-done: + if res.err != nil { + return nil, res.err + } + return parseNRPTPolicyTable(res.text), nil + case <-time.After(nrptPolicyTimeout): + return nil, errors.New("read of the policy table timed out") + } +} + +// nrptPolicyTableText calls the policy table method and returns the MOF text of +// its out parameters. +func nrptPolicyTableText() (text string, err error) { + // COM is per thread, and the collection is short lived, so the thread is + // pinned for the duration rather than initialized for the process. + runtime.LockOSThread() + defer runtime.UnlockOSThread() + + defer func() { + // The COM call chain is dynamically typed, so a provider that answers + // with an unexpected shape must not take the daemon down with it. + if r := recover(); r != nil { + err = fmt.Errorf("read NRPT policy table: %v", r) + } + }() + + owns, err := coInitialize() + if err != nil { + return "", err + } + if owns { + defer ole.CoUninitialize() + } + + locator, err := oleutil.CreateObject("WbemScripting.SWbemLocator") + if err != nil { + return "", fmt.Errorf("create WMI locator: %w", err) + } + defer locator.Release() + + dispatch, err := locator.QueryInterface(ole.IID_IDispatch) + if err != nil { + return "", fmt.Errorf("query WMI locator interface: %w", err) + } + defer dispatch.Release() + + service, err := dispatchCall(dispatch, "ConnectServer", nil, nrptPolicyNamespace) + if err != nil { + return "", fmt.Errorf("connect to %s: %w", nrptPolicyNamespace, err) + } + defer service.Release() + + inParams, err := spawnMethodInParams(service) + if err != nil { + return "", err + } + defer inParams.Release() + + // The effective table is the merge of the local and the group policy + // store, which is what the resolver answers from. + if _, err := oleutil.PutProperty(inParams, "Effective", true); err != nil { + return "", fmt.Errorf("set Effective parameter: %w", err) + } + + outParams, err := dispatchCall(service, "ExecMethod", nrptPolicyClass, nrptPolicyMethod, inParams) + if err != nil { + return "", fmt.Errorf("call %s.%s: %w", nrptPolicyClass, nrptPolicyMethod, err) + } + defer outParams.Release() + + textVariant, err := oleutil.CallMethod(outParams, "GetObjectText_") + if err != nil { + return "", fmt.Errorf("render policy table: %w", err) + } + defer func() { + if err := textVariant.Clear(); err != nil { + log.Debugf("clear policy table variant: %v", err) + } + }() + + return textVariant.ToString(), nil +} + +// spawnMethodInParams builds the in parameters instance the method needs. The +// provider rejects the call without one, even when every parameter is optional. +func spawnMethodInParams(service *ole.IDispatch) (*ole.IDispatch, error) { + class, err := dispatchCall(service, "Get", nrptPolicyClass) + if err != nil { + return nil, fmt.Errorf("get class %s: %w", nrptPolicyClass, err) + } + defer class.Release() + + methods, err := dispatchProperty(class, "Methods_") + if err != nil { + return nil, fmt.Errorf("get class methods: %w", err) + } + defer methods.Release() + + method, err := dispatchCall(methods, "Item", nrptPolicyMethod) + if err != nil { + return nil, fmt.Errorf("get method %s: %w", nrptPolicyMethod, err) + } + defer method.Release() + + params, err := dispatchProperty(method, "InParameters") + if err != nil { + return nil, fmt.Errorf("get method parameters: %w", err) + } + defer params.Release() + + inParams, err := dispatchCall(params, "SpawnInstance_") + if err != nil { + return nil, fmt.Errorf("spawn parameter instance: %w", err) + } + + return inParams, nil +} + +// parseNRPTPolicyTable pulls the embedded instances out of the MOF text. Each +// instance is a namespace of the table, with one name and value per line. +func parseNRPTPolicyTable(text string) []nrptPolicyEntry { + var entries []nrptPolicyEntry + var current *nrptPolicyEntry + + for _, line := range strings.Split(text, "\n") { + line = strings.TrimSpace(strings.TrimSuffix(strings.TrimSpace(line), ";")) + + switch { + case strings.HasPrefix(line, nrptPolicyInstanceKeyword): + entries = append(entries, nrptPolicyEntry{}) + current = &entries[len(entries)-1] + continue + case strings.HasPrefix(line, "}"): + // closes an instance, and the array with the last one, so the + // class level parameters that follow are not read as values + current = nil + continue + case current == nil, line == "{": + continue + } + + name, value, ok := strings.Cut(line, " = ") + if !ok { + continue + } + + value = unquoteMOFValue(value) + if name == "Namespace" { + current.namespace = value + continue + } + + current.values = append(current.values, registryValue{name: name, value: value}) + } + + return entries +} + +// unquoteMOFValue renders a MOF scalar or array as plain text: "a" becomes a, +// and {"a", "b"} becomes a, b. +func unquoteMOFValue(value string) string { + value = strings.TrimSpace(value) + + if inner, ok := strings.CutPrefix(value, "{"); ok { + value = strings.TrimSuffix(inner, "}") + + entries := strings.Split(value, ",") + for i, entry := range entries { + entries[i] = strings.Trim(strings.TrimSpace(entry), `"`) + } + return strings.Join(entries, ", ") + } + + return strings.Trim(value, `"`) +} + +// coInitialize prepares the calling thread for COM and reports whether this +// call owns the initialization, which decides whether it may be balanced with +// CoUninitialize. S_FALSE took a reference on a thread this process had already +// initialized and so has to be released, while RPC_E_CHANGED_MODE took none: +// the thread belongs to another apartment, which is usable but is not ours to +// uninitialize. +func coInitialize() (bool, error) { + err := ole.CoInitializeEx(0, ole.COINIT_MULTITHREADED) + if err == nil { + return true, nil + } + + var oleErr *ole.OleError + if errors.As(err, &oleErr) { + switch oleErr.Code() { + case sFalse: + return true, nil + case rpcEChangedMode: + return false, nil + } + } + + return false, fmt.Errorf("initialize COM: %w", err) +} + +// dispatchCall calls a COM method that returns an object. +func dispatchCall(dispatch *ole.IDispatch, method string, params ...any) (*ole.IDispatch, error) { + variant, err := oleutil.CallMethod(dispatch, method, params...) + if err != nil { + return nil, err + } + + object := variant.ToIDispatch() + if object == nil { + return nil, fmt.Errorf("%s returned no object", method) + } + + return object, nil +} + +// dispatchProperty reads a COM property that holds an object. +func dispatchProperty(dispatch *ole.IDispatch, property string) (*ole.IDispatch, error) { + variant, err := oleutil.GetProperty(dispatch, property) + if err != nil { + return nil, err + } + + object := variant.ToIDispatch() + if object == nil { + return nil, fmt.Errorf("property %s holds no object", property) + } + + return object, nil +} diff --git a/client/internal/debug/wgshow.go b/client/internal/debug/wgshow.go index 1e8a8a6cc..ee24902e6 100644 --- a/client/internal/debug/wgshow.go +++ b/client/internal/debug/wgshow.go @@ -35,14 +35,14 @@ func (g *BundleGenerator) toWGShowFormat(s *configurer.Stats) string { var sb strings.Builder sb.WriteString(fmt.Sprintf("interface: %s\n", s.DeviceName)) - sb.WriteString(fmt.Sprintf(" public key: %s\n", s.PublicKey)) + sb.WriteString(fmt.Sprintf(" public key: %s\n", g.anonymizer.AnonymizeWGKey(s.PublicKey))) sb.WriteString(fmt.Sprintf(" listen port: %d\n", s.ListenPort)) if s.FWMark != 0 { sb.WriteString(fmt.Sprintf(" fwmark: %#x\n", s.FWMark)) } for _, peer := range s.Peers { - sb.WriteString(fmt.Sprintf("\npeer: %s\n", peer.PublicKey)) + sb.WriteString(fmt.Sprintf("\npeer: %s\n", g.anonymizer.AnonymizeWGKey(peer.PublicKey))) if peer.Endpoint.IP != nil { if g.anonymize { anonEndpoint := g.anonymizer.AnonymizeUDPAddr(peer.Endpoint) @@ -54,7 +54,11 @@ func (g *BundleGenerator) toWGShowFormat(s *configurer.Stats) string { if len(peer.AllowedIPs) > 0 { var ipStrings []string for _, ipnet := range peer.AllowedIPs { - ipStrings = append(ipStrings, ipnet.String()) + ipStr := ipnet.String() + if g.anonymize { + ipStr = g.anonymizer.AnonymizeIPString(ipStr) + } + ipStrings = append(ipStrings, ipStr) } sb.WriteString(fmt.Sprintf(" allowed ips: %s\n", strings.Join(ipStrings, ", "))) } diff --git a/client/internal/dns/host_darwin.go b/client/internal/dns/host_darwin.go index 0f4eb6bf8..81029752e 100644 --- a/client/internal/dns/host_darwin.go +++ b/client/internal/dns/host_darwin.go @@ -267,18 +267,38 @@ func (s *systemConfigurator) getSystemDNSSettings() (SystemDNSSettings, error) { return SystemDNSSettings{}, fmt.Errorf("sending the command: %w", err) } - var dnsSettings SystemDNSSettings + dnsSettings, serverAddresses, err := parseSystemDNSSettings(b) + if err != nil { + return dnsSettings, err + } + + s.mu.Lock() + s.origNameservers = serverAddresses + s.mu.Unlock() + + return dnsSettings, nil +} + +// parseSystemDNSSettings parses the output of `scutil show State:/Network/Service//DNS`. +// Lines that don't match the expected "index : value" shape are skipped: hosts with unusual +// network services (e.g. orphaned hardware ports) can produce entries without a value. +func parseSystemDNSSettings(out []byte) (SystemDNSSettings, []netip.Addr, error) { + // port is not exposed by scutil, default to 53 + dnsSettings := SystemDNSSettings{ServerPort: DefaultPort} var serverAddresses []netip.Addr inSearchDomainsArray := false inServerAddressesArray := false - scanner := bufio.NewScanner(bytes.NewReader(b)) + scanner := bufio.NewScanner(bytes.NewReader(out)) for scanner.Scan() { line := strings.TrimSpace(scanner.Text()) switch { case strings.HasPrefix(line, "DomainName :"): - domainName := strings.TrimSpace(strings.Split(line, ":")[1]) - dnsSettings.Domains = append(dnsSettings.Domains, domainName) + domainName := strings.TrimSpace(strings.TrimPrefix(line, "DomainName :")) + if domainName != "" { + dnsSettings.Domains = append(dnsSettings.Domains, domainName) + } + continue case line == "SearchDomains : {": inSearchDomainsArray = true continue @@ -288,36 +308,45 @@ func (s *systemConfigurator) getSystemDNSSettings() (SystemDNSSettings, error) { case line == "}": inSearchDomainsArray = false inServerAddressesArray = false + continue + } + + if !inSearchDomainsArray && !inServerAddressesArray { + continue + } + + parts := strings.SplitN(line, " : ", 2) + if len(parts) != 2 { + log.Debugf("skipping unexpected scutil DNS line %q", line) + continue + } + value := strings.TrimSpace(parts[1]) + if value == "" { + continue } if inSearchDomainsArray { - searchDomain := strings.Split(line, " : ")[1] - dnsSettings.Domains = append(dnsSettings.Domains, searchDomain) - } else if inServerAddressesArray { - address := strings.Split(line, " : ")[1] - if ip, err := netip.ParseAddr(address); err == nil && !ip.IsUnspecified() { - ip = ip.Unmap() - serverAddresses = append(serverAddresses, ip) - // Prefer the first IPv4 server as ServerIP since our DNS listener is IPv4. - if !dnsSettings.ServerIP.IsValid() && ip.Is4() { - dnsSettings.ServerIP = ip - } - } + dnsSettings.Domains = append(dnsSettings.Domains, value) + continue + } + + ip, err := netip.ParseAddr(value) + if err != nil || ip.IsUnspecified() { + continue + } + ip = ip.Unmap() + serverAddresses = append(serverAddresses, ip) + // Prefer the first IPv4 server as ServerIP since our DNS listener is IPv4. + if !dnsSettings.ServerIP.IsValid() && ip.Is4() { + dnsSettings.ServerIP = ip } } if err := scanner.Err(); err != nil { - return dnsSettings, err + return dnsSettings, serverAddresses, err } - // default to 53 port - dnsSettings.ServerPort = DefaultPort - - s.mu.Lock() - s.origNameservers = serverAddresses - s.mu.Unlock() - - return dnsSettings, nil + return dnsSettings, serverAddresses, nil } func (s *systemConfigurator) getOriginalNameservers() []netip.Addr { @@ -435,11 +464,15 @@ func (s *systemConfigurator) getPrimaryService() (string, string, error) { router := "" for scanner.Scan() { text := scanner.Text() + parts := strings.SplitN(text, ":", 2) + if len(parts) != 2 { + continue + } if strings.Contains(text, "PrimaryService") { - primaryService = strings.TrimSpace(strings.Split(text, ":")[1]) + primaryService = strings.TrimSpace(parts[1]) } if strings.Contains(text, "Router") { - router = strings.TrimSpace(strings.Split(text, ":")[1]) + router = strings.TrimSpace(parts[1]) } } if err := scanner.Err(); err != nil && err != io.EOF { diff --git a/client/internal/dns/host_darwin_test.go b/client/internal/dns/host_darwin_test.go index 94d020c39..bee691c71 100644 --- a/client/internal/dns/host_darwin_test.go +++ b/client/internal/dns/host_darwin_test.go @@ -328,6 +328,120 @@ func removeTestDNSKey(key string) error { return err } +func TestParseSystemDNSSettings(t *testing.T) { + tests := []struct { + name string + output string + expectedDomains []string + expectedServers []netip.Addr + expectedIP netip.Addr + }{ + { + name: "well_formed", + output: ` { + DomainName : example.com + SearchDomains : { + 0 : example.com + 1 : corp.example.com + } + ServerAddresses : { + 0 : 192.168.1.1 + 1 : fd00::53 + } +} +`, + expectedDomains: []string{"example.com", "example.com", "corp.example.com"}, + expectedServers: []netip.Addr{netip.MustParseAddr("192.168.1.1"), netip.MustParseAddr("fd00::53")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + // entries without a value after the separator used to panic with + // "index out of range [1] with length 1" + name: "malformed_array_entries_skipped", + output: ` { + SearchDomains : { + 0 : + (null) + + 1 : corp.example.com + } + ServerAddresses : { + 0 : + 1 : 192.168.1.1 + } +} +`, + expectedDomains: []string{"corp.example.com"}, + expectedServers: []netip.Addr{netip.MustParseAddr("192.168.1.1")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + name: "domain_name_without_value_skipped", + output: ` { + DomainName : + ServerAddresses : { + 0 : 192.168.1.1 + } +} +`, + expectedServers: []netip.Addr{netip.MustParseAddr("192.168.1.1")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + name: "ipv6_first_prefers_ipv4_server_ip", + output: ` { + ServerAddresses : { + 0 : fd00::53 + 1 : 192.168.1.1 + } +} +`, + expectedServers: []netip.Addr{netip.MustParseAddr("fd00::53"), netip.MustParseAddr("192.168.1.1")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + name: "invalid_and_unspecified_addresses_skipped", + output: ` { + ServerAddresses : { + 0 : (null) + 1 : 0.0.0.0 + 2 : 192.168.1.1 + } +} +`, + expectedServers: []netip.Addr{netip.MustParseAddr("192.168.1.1")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + name: "v4_mapped_address_unmapped", + output: ` { + ServerAddresses : { + 0 : ::ffff:192.168.1.1 + } +} +`, + expectedServers: []netip.Addr{netip.MustParseAddr("192.168.1.1")}, + expectedIP: netip.MustParseAddr("192.168.1.1"), + }, + { + name: "empty_output", + output: "", + }, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + settings, servers, err := parseSystemDNSSettings([]byte(tc.output)) + require.NoError(t, err, "parsing should not fail") + + assert.Equal(t, tc.expectedDomains, settings.Domains, "domains should match") + assert.Equal(t, tc.expectedServers, servers, "server addresses should match") + assert.Equal(t, tc.expectedIP, settings.ServerIP, "server IP should match") + assert.Equal(t, DefaultPort, settings.ServerPort, "server port should default to 53") + }) + } +} + func TestGetOriginalNameservers(t *testing.T) { configurator := &systemConfigurator{ createdKeys: make(map[string]struct{}), diff --git a/client/internal/dns/host_windows.go b/client/internal/dns/host_windows.go index 4f6ece532..53380b2aa 100644 --- a/client/internal/dns/host_windows.go +++ b/client/internal/dns/host_windows.go @@ -31,10 +31,30 @@ var ( dnsFlushResolverCacheFn = dnsapi.NewProc("DnsFlushResolverCache") ) +// Registry locations of the host DNS configuration this package programs, +// exported so a diagnostic reader reports the same locations that are written. const ( - dnsPolicyConfigMatchPath = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig\NetBird-Match` - gpoDnsPolicyRoot = `SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig` - gpoDnsPolicyConfigMatchPath = gpoDnsPolicyRoot + `\NetBird-Match` + // NRPTKeyPrefix starts the name of every NRPT rule key this client creates. + // Older versions used different layouts under the same prefix: a single + // unsuffixed key, then one key per domain, now one key per batch of domains. + NRPTKeyPrefix = "NetBird-Match" + + // DNSPolicyConfigRoot holds the NRPT rules of the local policy store. + DNSPolicyConfigRoot = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig` + + // GPODNSPolicyConfigRoot holds the NRPT rules of the group policy store, + // which takes precedence over the local one when it is present. + GPODNSPolicyConfigRoot = `SOFTWARE\Policies\Microsoft\Windows NT\DNSClient\DnsPolicyConfig` + + // InterfaceConfigPath and InterfaceConfigPathV6 hold the per-interface DNS + // settings, keyed by interface GUID, in separate hives per address family. + InterfaceConfigPath = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces` + InterfaceConfigPathV6 = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces` +) + +const ( + dnsPolicyConfigMatchPath = DNSPolicyConfigRoot + `\` + NRPTKeyPrefix + gpoDnsPolicyConfigMatchPath = GPODNSPolicyConfigRoot + `\` + NRPTKeyPrefix dnsPolicyConfigVersionKey = "Version" dnsPolicyConfigVersionValue = 2 @@ -45,8 +65,6 @@ const ( nrptMaxDomainsPerRule = 50 - interfaceConfigPath = `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces` - interfaceConfigPathV6 = `SYSTEM\CurrentControlSet\Services\Tcpip6\Parameters\Interfaces` interfaceConfigNameServerKey = "NameServer" interfaceConfigDhcpNameSrvKey = "DhcpNameServer" interfaceConfigSearchListKey = "SearchList" @@ -73,7 +91,6 @@ type registryConfigurator struct { guid string routingAll bool gpo bool - nrptEntryCount int origNameservers []netip.Addr } @@ -84,7 +101,7 @@ func newHostManager(wgInterface WGIface) (*registryConfigurator, error) { } var useGPO bool - k, err := registry.OpenKey(registry.LOCAL_MACHINE, gpoDnsPolicyRoot, registry.QUERY_VALUE) + k, err := registry.OpenKey(registry.LOCAL_MACHINE, GPODNSPolicyConfigRoot, registry.QUERY_VALUE) if err != nil { log.Debugf("failed to open GPO DNS policy root: %v", err) } else { @@ -123,7 +140,7 @@ func (r *registryConfigurator) captureOriginalNameservers() ([]netip.Addr, error seen := make(map[netip.Addr]struct{}) var out []netip.Addr var merr *multierror.Error - for _, root := range []string{interfaceConfigPath, interfaceConfigPathV6} { + for _, root := range []string{InterfaceConfigPath, InterfaceConfigPathV6} { addrs, err := r.captureFromTcpipRoot(root) if err != nil { merr = multierror.Append(merr, fmt.Errorf("%s: %w", root, err)) @@ -306,14 +323,9 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager } if len(matchDomains) != 0 { - count, err := r.addDNSMatchPolicy(matchDomains, config.ServerIP) - // Update count even on error to ensure cleanup covers partially created rules - r.nrptEntryCount = count - if err != nil { + if err := r.addDNSMatchPolicy(matchDomains, config.ServerIP); err != nil { return fmt.Errorf("add dns match policy: %w", err) } - } else { - r.nrptEntryCount = 0 } r.updateState(stateManager) @@ -329,9 +341,8 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager func (r *registryConfigurator) updateState(stateManager *statemanager.Manager) { if err := stateManager.UpdateState(&ShutdownState{ - Guid: r.guid, - GPO: r.gpo, - NRPTEntryCount: r.nrptEntryCount, + Guid: r.guid, + GPO: r.gpo, }); err != nil { log.Errorf("failed to update shutdown state: %s", err) } @@ -346,7 +357,7 @@ func (r *registryConfigurator) addDNSSetupForAll(ip netip.Addr) error { return nil } -func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) (int, error) { +func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) error { // if the gpo key is present, we need to put our DNS settings there, otherwise our config might be ignored // see https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-gpnrpt/8cc31cb9-20cb-4140-9e85-3e08703b4745 @@ -363,19 +374,17 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, ruleIndex) if err := r.configureDNSPolicy(localPath, batchDomains, ip); err != nil { - return ruleIndex, fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err) + return fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err) } - // Increment immediately so the caller's cleanup path knows about this rule - ruleIndex++ - if r.gpo { if err := r.configureDNSPolicy(gpoPath, batchDomains, ip); err != nil { - return ruleIndex, fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex-1, err) + return fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex, err) } } - log.Debugf("added NRPT rule %d with %d domains", ruleIndex-1, len(batchDomains)) + log.Debugf("added NRPT rule %d with %d domains", ruleIndex, len(batchDomains)) + ruleIndex++ } if r.gpo { @@ -385,7 +394,7 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr } log.Infof("added %d NRPT rules for %d domains", ruleIndex, len(domains)) - return ruleIndex, nil + return nil } func (r *registryConfigurator) configureDNSPolicy(policyPath string, domains []string, ip netip.Addr) error { @@ -450,7 +459,7 @@ func (r *registryConfigurator) flushDNSCache() { ret, _, err := dnsFlushResolverCacheFn.Call() if ret == 0 { - if err != nil && !errors.Is(err, syscall.Errno(0)) { + if !errors.Is(err, syscall.Errno(0)) { log.Errorf("DnsFlushResolverCache failed: %v", err) return } @@ -496,7 +505,7 @@ func (r *registryConfigurator) deleteInterfaceRegistryKeyProperty(propertyKey st } func (r *registryConfigurator) getInterfaceRegistryKey() (registry.Key, error) { - regKeyPath := interfaceConfigPath + "\\" + r.guid + regKeyPath := InterfaceConfigPath + "\\" + r.guid regKey, err := registry.OpenKey(registry.LOCAL_MACHINE, regKeyPath, registry.SET_VALUE) if err != nil { return regKey, fmt.Errorf("open HKEY_LOCAL_MACHINE\\%s: %w", regKeyPath, err) @@ -518,28 +527,28 @@ func (r *registryConfigurator) restoreHostDNS() error { return nil } +// removeDNSMatchPolicies deletes every NRPT rule this client may have created, +// from the local and the GPO policy store. The rules are found by enumerating +// the registry, the only authoritative record of what was written. Cleanup must +// not depend on a rule count: the in-memory one is scoped to a single +// registryConfigurator and the persisted one is deleted on every clean +// disconnect, and a rule left behind keeps resolving names over an interface +// that is gone, until reboot discards the volatile key. func (r *registryConfigurator) removeDNSMatchPolicies() error { var merr *multierror.Error - // Try to remove the base entries (for backward compatibility) - if err := removeRegistryKeyFromDNSPolicyConfig(dnsPolicyConfigMatchPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove local base entry: %w", err)) - } - - if err := removeRegistryKeyFromDNSPolicyConfig(gpoDnsPolicyConfigMatchPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove GPO base entry: %w", err)) - } - - for i := 0; i < r.nrptEntryCount; i++ { - localPath := fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i) - gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, i) - - if err := removeRegistryKeyFromDNSPolicyConfig(localPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove local entry %d: %w", i, err)) + for _, root := range []string{DNSPolicyConfigRoot, GPODNSPolicyConfigRoot} { + names, err := listNRPTRuleKeys(root) + if err != nil { + merr = multierror.Append(merr, fmt.Errorf("list rule keys under %s: %w", root, err)) + continue } - if err := removeRegistryKeyFromDNSPolicyConfig(gpoPath); err != nil { - merr = multierror.Append(merr, fmt.Errorf("remove GPO entry %d: %w", i, err)) + for _, name := range names { + path := root + `\` + name + if err := removeRegistryKeyFromDNSPolicyConfig(path); err != nil { + merr = multierror.Append(merr, fmt.Errorf("remove entry %s: %w", path, err)) + } } } @@ -554,6 +563,39 @@ func (r *registryConfigurator) restoreUncleanShutdownDNS() error { return r.restoreHostDNS() } +// listNRPTRuleKeys returns the names of our NRPT rule keys under a policy store +// root. An absent root holds nothing to clean up, which is the normal state of +// the GPO store on a machine without DNS Client policy. +func listNRPTRuleKeys(root string) ([]string, error) { + k, err := registry.OpenKey(registry.LOCAL_MACHINE, root, registry.ENUMERATE_SUB_KEYS) + switch { + case errors.Is(err, registry.ErrNotExist), errors.Is(err, syscall.ERROR_PATH_NOT_FOUND): + // the GPO store is absent on a machine without DNS client policy + log.Debugf("HKEY_LOCAL_MACHINE\\%s does not exist", root) + return nil, nil + case err != nil: + // any other failure has to reach the caller: reporting no rules would + // report a successful cleanup while leaving the rules in place + return nil, fmt.Errorf("open HKEY_LOCAL_MACHINE\\%s: %w", root, err) + } + defer closer(k) + + names, err := k.ReadSubKeyNames(-1) + if err != nil { + return nil, fmt.Errorf("read subkey names: %w", err) + } + + var ruleKeys []string + for _, name := range names { + // registry key names are case insensitive + if strings.HasPrefix(strings.ToLower(name), strings.ToLower(NRPTKeyPrefix)) { + ruleKeys = append(ruleKeys, name) + } + } + + return ruleKeys, nil +} + func removeRegistryKeyFromDNSPolicyConfig(regKeyPath string) error { k, err := registry.OpenKey(registry.LOCAL_MACHINE, regKeyPath, registry.QUERY_VALUE) if err != nil { @@ -585,7 +627,7 @@ func refreshGroupPolicy() error { ) if ret == 0 { - if err != nil && !errors.Is(err, syscall.Errno(0)) { + if !errors.Is(err, syscall.Errno(0)) { return fmt.Errorf("RefreshPolicyEx failed: %w", err) } return fmt.Errorf("RefreshPolicyEx failed") diff --git a/client/internal/dns/host_windows_test.go b/client/internal/dns/host_windows_test.go index 3cd2b1bd5..861613c95 100644 --- a/client/internal/dns/host_windows_test.go +++ b/client/internal/dns/host_windows_test.go @@ -25,7 +25,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { // Create a test interface registry key so updateSearchDomains doesn't fail testGUID := "{12345678-1234-1234-1234-123456789ABC}" - interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID + interfacePath := InterfaceConfigPath + `\` + testGUID testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE) require.NoError(t, err, "Should create test interface registry key") testKey.Close() @@ -56,7 +56,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { require.NoError(t, err) // Verify 3 NRPT rules exist - assert.Equal(t, 3, cfg.nrptEntryCount, "Should create 3 NRPT rules for 125 domains") + assert.Equal(t, 3, countNRPTRuleKeys(t), "Should create 3 NRPT rules for 125 domains") for i := 0; i < 3; i++ { exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i)) require.NoError(t, err) @@ -81,7 +81,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) { require.NoError(t, err) // Verify first 2 NRPT rules exist - assert.Equal(t, 2, cfg.nrptEntryCount, "Should create 2 NRPT rules for 75 domains") + assert.Equal(t, 2, countNRPTRuleKeys(t), "Should create 2 NRPT rules for 75 domains") for i := 0; i < 2; i++ { exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i)) require.NoError(t, err) @@ -106,9 +106,65 @@ func registryKeyExists(path string) (bool, error) { return true, nil } +// TestNRPTCleanupWithoutRuleCount verifies that rules written by a previous run +// are removed by a configurator that has no record of how many there are: an +// unclean exit loses the in-memory count and a clean disconnect deletes the +// persisted one, so cleanup cannot depend on either. +func TestNRPTCleanupWithoutRuleCount(t *testing.T) { + if testing.Short() { + t.Skip("skipping registry integration test in short mode") + } + + defer cleanupRegistryKeys(t) + cleanupRegistryKeys(t) + + testIP := netip.MustParseAddr("100.64.0.1") + + // 75 domains produce two indexed rules, as the current layout does + domains := make([]string, 75) + for i := range domains { + domains[i] = fmt.Sprintf(".domain%d.com", i+1) + } + + previousRun := ®istryConfigurator{} + require.NoError(t, previousRun.addDNSMatchPolicy(domains, testIP)) + + // the unsuffixed key an older version would have written + require.NoError(t, previousRun.configureDNSPolicy(dnsPolicyConfigMatchPath, []string{".legacy.example.com"}, testIP)) + + // a policy owned by someone else, which cleanup must not touch + foreignPath := DNSPolicyConfigRoot + `\DnsPolicyConfigTestForeign` + foreignKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, foreignPath, registry.SET_VALUE) + require.NoError(t, err, "Should create foreign policy key") + foreignKey.Close() + defer func() { + _ = registry.DeleteKey(registry.LOCAL_MACHINE, foreignPath) + }() + + require.Equal(t, 3, countNRPTRuleKeys(t), "Should have two indexed rules and the legacy one") + + // a configurator that never applied a DNS config, as one built after a + // restart or from a shutdown state without a count is + freshRun := ®istryConfigurator{} + require.NoError(t, freshRun.removeDNSMatchPolicies()) + + assert.Equal(t, 0, countNRPTRuleKeys(t), "Should remove every rule left by the previous run") + + exists, err := registryKeyExists(foreignPath) + require.NoError(t, err) + assert.True(t, exists, "Should not remove a policy that is not ours") +} + +func countNRPTRuleKeys(t *testing.T) int { + t.Helper() + + names, err := listNRPTRuleKeys(DNSPolicyConfigRoot) + require.NoError(t, err, "Should list NRPT rule keys") + return len(names) +} + func cleanupRegistryKeys(*testing.T) { - // Clean up more entries to account for batching tests with many domains - cfg := ®istryConfigurator{nrptEntryCount: 20} + cfg := ®istryConfigurator{} _ = cfg.removeDNSMatchPolicies() } @@ -125,7 +181,7 @@ func TestNRPTDomainBatching(t *testing.T) { // Create a test interface registry key so updateSearchDomains doesn't fail testGUID := "{12345678-1234-1234-1234-123456789ABC}" - interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID + interfacePath := InterfaceConfigPath + `\` + testGUID testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE) require.NoError(t, err, "Should create test interface registry key") testKey.Close() @@ -193,7 +249,7 @@ func TestNRPTDomainBatching(t *testing.T) { require.NoError(t, err) // Verify that exactly expectedRuleCount rules were created - assert.Equal(t, tc.expectedRuleCount, cfg.nrptEntryCount, + assert.Equal(t, tc.expectedRuleCount, countNRPTRuleKeys(t), "Should create %d NRPT rules for %d domains", tc.expectedRuleCount, tc.domainCount) // Verify all expected rules exist diff --git a/client/internal/dns/response_writer_test.go b/client/internal/dns/response_writer_test.go index 857964406..bc8416029 100644 --- a/client/internal/dns/response_writer_test.go +++ b/client/internal/dns/response_writer_test.go @@ -4,7 +4,7 @@ import ( "net" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/google/gopacket" "github.com/google/gopacket/layers" "github.com/miekg/dns" diff --git a/client/internal/dns/server_privileged_test.go b/client/internal/dns/server_privileged_test.go index a03aea169..a17044cf5 100644 --- a/client/internal/dns/server_privileged_test.go +++ b/client/internal/dns/server_privileged_test.go @@ -9,7 +9,7 @@ import ( "os" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/miekg/dns" "github.com/stretchr/testify/assert" "golang.zx2c4.com/wireguard/wgctrl/wgtypes" diff --git a/client/internal/dns/unclean_shutdown_windows.go b/client/internal/dns/unclean_shutdown_windows.go index 24a9eca50..ab0b2cc63 100644 --- a/client/internal/dns/unclean_shutdown_windows.go +++ b/client/internal/dns/unclean_shutdown_windows.go @@ -5,9 +5,8 @@ import ( ) type ShutdownState struct { - Guid string - GPO bool - NRPTEntryCount int + Guid string + GPO bool } func (s *ShutdownState) Name() string { @@ -16,9 +15,8 @@ func (s *ShutdownState) Name() string { func (s *ShutdownState) Cleanup() error { manager := ®istryConfigurator{ - guid: s.Guid, - gpo: s.GPO, - nrptEntryCount: s.NRPTEntryCount, + guid: s.Guid, + gpo: s.GPO, } if err := manager.restoreUncleanShutdownDNS(); err != nil { diff --git a/client/internal/dnsfwd/manager.go b/client/internal/dnsfwd/manager.go index c4c16cd3f..29ca0d247 100644 --- a/client/internal/dnsfwd/manager.go +++ b/client/internal/dnsfwd/manager.go @@ -101,7 +101,7 @@ func (m *Manager) Start(fwdEntries []*ForwarderEntry) error { m.dnsForwarder = NewDNSForwarder(listenAddress, dnsTTL, m.firewall, m.statusRecorder, m.wgIface) go func() { - if err := m.dnsForwarder.Listen(fwdEntries); err != nil { + if err := m.dnsForwarder.Listen(fwdEntries); err != nil { //nolint:staticcheck // todo handle close error if it is exists log.Errorf("failed to start DNS forwarder, err: %v", err) } diff --git a/client/internal/engine.go b/client/internal/engine.go index f4f47992f..7f3f8185f 100644 --- a/client/internal/engine.go +++ b/client/internal/engine.go @@ -23,6 +23,7 @@ import ( "golang.zx2c4.com/wireguard/tun/netstack" "golang.zx2c4.com/wireguard/wgctrl/wgtypes" + "github.com/netbirdio/netbird/client/anonymize" nberrors "github.com/netbirdio/netbird/client/errors" "github.com/netbirdio/netbird/client/firewall" "github.com/netbirdio/netbird/client/firewall/firewalld" @@ -58,6 +59,7 @@ import ( "github.com/netbirdio/netbird/client/internal/syncstore" "github.com/netbirdio/netbird/client/internal/updater" "github.com/netbirdio/netbird/client/jobexec" + "github.com/netbirdio/netbird/client/netstate" cProto "github.com/netbirdio/netbird/client/proto" "github.com/netbirdio/netbird/client/system" nbdns "github.com/netbirdio/netbird/dns" @@ -180,6 +182,9 @@ type EngineServices struct { UpdateManager *updater.Manager ClientMetrics *metrics.ClientMetrics MetricsCtx context.Context + // NetState gates the reconnection loops on OS-reported network + // availability; nil disables gating. + NetState *netstate.State } // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers. @@ -203,6 +208,10 @@ type Engine struct { config *EngineConfig mobileDep MobileDependency + // netState gates the peer reconnection guards on OS-reported network + // availability; nil disables gating. + netState *netstate.State + // STUNs is a list of STUN servers used by ICE STUNs []*stun.URI // TURNs is a list of STUN servers used by ICE @@ -336,6 +345,7 @@ func NewEngine( syncMsgMux: &sync.Mutex{}, config: config, mobileDep: mobileDep, + netState: services.NetState, STUNs: []*stun.URI{}, TURNs: []*stun.URI{}, networkSerial: 0, @@ -1385,6 +1395,7 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR bundleJobParams := debug.BundleConfig{ Anonymize: params.Anonymize, + AnonymizeLevel: anonymize.ParseLevel(params.AnonymizeLevel), IncludeSystemInfo: true, LogFileCount: uint32(params.LogFileCount), } @@ -1891,7 +1902,8 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV Addr: e.getRosenpassAddr(), PermissiveMode: e.config.RosenpassPermissive, }, - ICEConfig: e.createICEConfig(), + ICEConfig: e.createICEConfig(), + NetworkState: e.netState, } serviceDependencies := peer.ServiceDependencies{ @@ -2560,7 +2572,7 @@ func (e *Engine) SetCapture(pc device.PacketCapture) error { } afc := capture.NewAFPacketCapture(intf.Name(), sess) - if err := afc.Start(); err != nil { + if err := afc.Start(); err != nil { //nolint:staticcheck // always errors on non-Linux builds return fmt.Errorf("start AF_PACKET capture on %s: %w", intf.Name(), err) } e.afpacketCapture = afc diff --git a/client/internal/engine_privileged_test.go b/client/internal/engine_privileged_test.go index f787f741f..032992464 100644 --- a/client/internal/engine_privileged_test.go +++ b/client/internal/engine_privileged_test.go @@ -12,7 +12,7 @@ import ( "testing" "time" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/google/uuid" log "github.com/sirupsen/logrus" "github.com/stretchr/testify/assert" diff --git a/client/internal/metrics/connection_type.go b/client/internal/metrics/connection_type.go index a3406a6b8..d393e5112 100644 --- a/client/internal/metrics/connection_type.go +++ b/client/internal/metrics/connection_type.go @@ -4,11 +4,17 @@ package metrics type ConnectionType string const ( - // ConnectionTypeICE represents a direct peer-to-peer connection using ICE - ConnectionTypeICE ConnectionType = "ice" + // ConnectionTypeICEP2P represents a direct peer-to-peer connection using ICE + ConnectionTypeICEP2P ConnectionType = "ice_p2p" + + // ConnectionTypeICETurn represents an ICE connection through a TURN server + ConnectionTypeICETurn ConnectionType = "ice_turn" // ConnectionTypeRelay represents a relayed connection ConnectionTypeRelay ConnectionType = "relay" + + // ConnectionTypeUnknown represents a connection with no active transport. It is not pushed. + ConnectionTypeUnknown ConnectionType = "unknown" ) // String returns the string representation of the connection type diff --git a/client/internal/metrics/influxdb_test.go b/client/internal/metrics/influxdb_test.go index b964e31a3..6a226fe2f 100644 --- a/client/internal/metrics/influxdb_test.go +++ b/client/internal/metrics/influxdb_test.go @@ -28,7 +28,7 @@ func TestInfluxDBMetrics_RecordAndExport(t *testing.T) { WgHandshakeSuccess: time.Now().Add(-1 * time.Second), } - m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, false, ts) + m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICEP2P, false, ts) var buf bytes.Buffer err := m.Export(&buf) @@ -60,7 +60,7 @@ func TestInfluxDBMetrics_ExportDeterministicFieldOrder(t *testing.T) { // Record multiple times and verify consistent field order for i := 0; i < 10; i++ { - m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, false, ts) + m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICEP2P, false, ts) } var buf bytes.Buffer diff --git a/client/internal/metrics/infra/README.md b/client/internal/metrics/infra/README.md index 7941a30cf..0a69404df 100644 --- a/client/internal/metrics/infra/README.md +++ b/client/internal/metrics/infra/README.md @@ -56,14 +56,33 @@ Measurement: `netbird_peer_connection` Tags: - `deployment_type`: "cloud" | "selfhosted" | "unknown" -- `connection_type`: "ice" | "relay" +- `connection_type`: "ice_p2p" | "ice_turn" | "relay" (see below) - `attempt_type`: "initial" | "reconnection" - `version`: NetBird version string - `os`: Operating system (linux, darwin, windows, android, ios, etc.) - `arch`: CPU architecture (amd64, arm64, etc.) +- `peer_id`: anonymised peer identifier (truncated SHA-256 of the WireGuard public key) +- `connection_pair_id`: deterministic identifier for the peer pair, identical on both sides **Note:** `SignalingReceived` is set when the first offer or answer arrives from the remote peer (in both initial and reconnection paths). It excludes the potentially unbounded wait for the remote peer to come online. +#### `connection_type` values + +Derived from the connection priority (`conntype.ConnPriority`) by `metricsConnType` in `client/internal/peer/conn.go`: + +| Value | Priority | Traffic is | +|-------|----------|------------| +| `ice_p2p` | `ICEP2P` | direct peer-to-peer | +| `ice_turn` | `ICETurn` | relayed, through a TURN server | +| `relay` | `Relay` | relayed, through a NetBird relay | +| `unknown` | `None` or unrecognised | no active transport — **the sample is not pushed** | + +**Direct traffic is `ice_p2p` only.** `ice_turn` is relayed despite being negotiated by ICE, matching `Conn.isRelayed`. + +`None` means no transport is active: not established yet, or reset after a relay drop or a peer-state reset. Such a sample cannot be attributed to a transport, so `recordConnectionMetrics` drops it instead of pushing it — `unknown` therefore never appears in the bucket. Connection counts are counts of connections whose transport was known at sampling time. + +**Samples recorded before 0.77 used a single `ice` value** which covered `ICEP2P`, `ICETurn` *and* `None`, so historical `ice` samples overstate direct connections by an unknown amount and must not be compared with `ice_p2p`. + ### Sync Duration Measurement: `netbird_sync` diff --git a/client/internal/peer/conn.go b/client/internal/peer/conn.go index 09a4e8b02..b84b05671 100644 --- a/client/internal/peer/conn.go +++ b/client/internal/peer/conn.go @@ -26,6 +26,7 @@ import ( "github.com/netbirdio/netbird/client/internal/portforward" "github.com/netbirdio/netbird/client/internal/rosenpass" "github.com/netbirdio/netbird/client/internal/stdnet" + "github.com/netbirdio/netbird/client/netstate" "github.com/netbirdio/netbird/route" relayClient "github.com/netbirdio/netbird/shared/relay/client" ) @@ -93,6 +94,10 @@ type ConnConfig struct { // ICEConfig ICE protocol configuration ICEConfig icemaker.Config + + // NetworkState gates the reconnection guard on OS-reported network + // availability; nil disables gating. + NetworkState *netstate.State } type Conn struct { @@ -254,7 +259,7 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error { conn.handshaker.AddICEListener(conn.workerICE.OnNewOffer) } - conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher) + conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher, conn.config.NetworkState) conn.wg.Add(1) go func() { @@ -307,6 +312,8 @@ func (conn *Conn) Close(signalToRemote bool) { if conn.wgWatcherCancel != nil { conn.wgWatcherCancel() + conn.wgWatcher = nil + conn.wgWatcherCancel = nil } conn.workerRelay.CloseConn() if conn.workerICE != nil { @@ -438,7 +445,7 @@ func (conn *Conn) onICEConnectionIsReady(priority conntype.ConnPriority, iceConn conn.dumpState.NewLocalProxy() wgProxy, err = conn.newProxy(iceConnInfo.RemoteConn) if err != nil { - conn.Log.Errorf("failed to add turn net.Conn to local proxy: %v", err) + conn.Log.Errorf("failed to add relayed net.Conn to local proxy: %v", err) return } ep = wgProxy.EndpointAddr() @@ -876,9 +883,8 @@ func (conn *Conn) newProxy(remoteConn net.Conn) (wgproxy.Proxy, error) { } wgProxy := conn.config.WgConfig.WgInterface.GetProxy() - if err := wgProxy.AddTurnConn(conn.ctx, udpAddr, remoteConn); err != nil { - conn.Log.Errorf("failed to add turn net.Conn to local proxy: %v", err) - return nil, err + if err := wgProxy.AddRelayedConn(conn.ctx, udpAddr, remoteConn); err != nil { + return nil, fmt.Errorf("add relayed conn to proxy: %w", err) } return wgProxy, nil } @@ -959,12 +965,9 @@ func (conn *Conn) recordConnectionMetrics() { priority := conn.currentConnPriority conn.mu.Unlock() - var connType metrics.ConnectionType - switch priority { - case conntype.Relay: - connType = metrics.ConnectionTypeRelay - default: - connType = metrics.ConnectionTypeICE + connType := metricsConnType(priority) + if connType == metrics.ConnectionTypeUnknown { + return } // Record metrics with timestamps - duration calculation happens in metrics package @@ -1065,3 +1068,16 @@ func boolToConnStatus(connected bool) guard.ConnStatus { } return guard.ConnStatusDisconnected } + +func metricsConnType(priority conntype.ConnPriority) metrics.ConnectionType { + switch priority { + case conntype.Relay: + return metrics.ConnectionTypeRelay + case conntype.ICETurn: + return metrics.ConnectionTypeICETurn + case conntype.ICEP2P: + return metrics.ConnectionTypeICEP2P + default: + return metrics.ConnectionTypeUnknown + } +} diff --git a/client/internal/peer/conn_test.go b/client/internal/peer/conn_test.go index 49979ea83..b709d5e40 100644 --- a/client/internal/peer/conn_test.go +++ b/client/internal/peer/conn_test.go @@ -11,6 +11,8 @@ import ( "github.com/stretchr/testify/assert" "github.com/netbirdio/netbird/client/iface" + "github.com/netbirdio/netbird/client/internal/metrics" + "github.com/netbirdio/netbird/client/internal/peer/conntype" "github.com/netbirdio/netbird/client/internal/peer/dispatcher" "github.com/netbirdio/netbird/client/internal/peer/guard" "github.com/netbirdio/netbird/client/internal/peer/ice" @@ -386,3 +388,33 @@ func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) { } assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections") } + +func TestMetricsConnType(t *testing.T) { + tests := []struct { + name string + priority conntype.ConnPriority + expected metrics.ConnectionType + }{ + {"relay", conntype.Relay, metrics.ConnectionTypeRelay}, + {"ice over turn is relayed, not p2p", conntype.ICETurn, metrics.ConnectionTypeICETurn}, + {"direct p2p", conntype.ICEP2P, metrics.ConnectionTypeICEP2P}, + {"unset priority is unknown, not p2p", conntype.None, metrics.ConnectionTypeUnknown}, + {"unrecognised priority is unknown", conntype.ConnPriority(99), metrics.ConnectionTypeUnknown}, + } + + for _, tc := range tests { + t.Run(tc.name, func(t *testing.T) { + assert.Equal(t, tc.expected, metricsConnType(tc.priority)) + }) + } +} + +func TestMetricsConnType_RelayedMatchesIsRelayed(t *testing.T) { + for _, priority := range []conntype.ConnPriority{conntype.None, conntype.Relay, conntype.ICETurn, conntype.ICEP2P} { + conn := &Conn{currentConnPriority: priority} + tag := metricsConnType(priority) + relayedTag := tag == metrics.ConnectionTypeRelay || tag == metrics.ConnectionTypeICETurn + assert.Equal(t, conn.isRelayed(), relayedTag, + "priority %s: isRelayed and the %q metric tag must agree", priority, tag) + } +} diff --git a/client/internal/peer/guard/guard.go b/client/internal/peer/guard/guard.go index 6c2e846a9..68d77d318 100644 --- a/client/internal/peer/guard/guard.go +++ b/client/internal/peer/guard/guard.go @@ -6,6 +6,8 @@ import ( "github.com/cenkalti/backoff/v4" log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/netstate" ) // ConnStatus represents the connection state as seen by the guard. @@ -31,20 +33,26 @@ type connStatusFunc func() ConnStatus // - Relayed connection disconnected // - ICE candidate changes type Guard struct { - log *log.Entry - isConnectedOnAllWay connStatusFunc - timeout time.Duration - srWatcher *SRWatcher + log *log.Entry + isConnectedOnAllWay connStatusFunc + timeout time.Duration + srWatcher *SRWatcher + // netState gates reconnect attempts on OS-reported network availability; + // nil disables gating. + netState *netstate.State relayedConnDisconnected chan struct{} iCEConnDisconnected chan struct{} } -func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard { +// NewGuard creates a reconnection guard for a peer connection. A nil netState +// disables network availability gating. +func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard { return &Guard{ log: log, isConnectedOnAllWay: isConnectedFn, timeout: timeout, srWatcher: srWatcher, + netState: netState, relayedConnDisconnected: make(chan struct{}, 1), iCEConnDisconnected: make(chan struct{}, 1), } @@ -96,9 +104,16 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) { iceState := &iceRetryState{log: g.log} defer iceState.reset() + netChanged := g.netState.Changed() + for { select { case <-tickerChannel: + // skip attempts while the OS reports no usable network; the + // netChanged case below resumes the loop once it returns + if !g.netState.IsOnline() { + continue + } switch g.isConnectedOnAllWay() { case ConnStatusConnected: // all good, nothing to do @@ -135,6 +150,23 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) { tickerChannel = ticker.C iceState.reset() + case <-netChanged: + // Re-arm for the next transition before acting on this one. + netChanged = g.netState.Changed() + if !g.netState.IsOnline() { + continue + } + // Ticks skipped while offline drove the backoff towards its + // maximum without ever attempting, and left the ICE budget + // frozen — possibly in hourly mode. Recover on our own so the + // peer does not depend on a signal or relay event that never + // comes when both stayed up across the outage. + g.log.Debugf("network is back, reset reconnection ticker") + ticker.Stop() + ticker = g.newReconnectTicker(ctx) + tickerChannel = ticker.C + iceState.reset() + case <-ctx.Done(): g.log.Debugf("context is done, stop reconnect loop") return diff --git a/client/internal/peer/guard/guard_leak_test.go b/client/internal/peer/guard/guard_leak_test.go index ded3e4aea..3d82ec591 100644 --- a/client/internal/peer/guard/guard_leak_test.go +++ b/client/internal/peer/guard/guard_leak_test.go @@ -15,7 +15,7 @@ import ( func newTestGuard(status connStatusFunc) *Guard { srw := NewSRWatcher(nil, nil, nil, ice.Config{}) - return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw) + return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw, nil) } // countBackoffTickerGoroutines returns how many goroutines are currently sitting diff --git a/client/internal/peer/guard/guard_netstate_test.go b/client/internal/peer/guard/guard_netstate_test.go new file mode 100644 index 000000000..2ab736428 --- /dev/null +++ b/client/internal/peer/guard/guard_netstate_test.go @@ -0,0 +1,107 @@ +package guard + +import ( + "context" + "sync/atomic" + "testing" + "time" + + log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/internal/peer/ice" + "github.com/netbirdio/netbird/client/netstate" +) + +// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the +// backoff must be able to grow well past the outage, as it does in production +// where the timeout is seconds to minutes. +func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard { + srw := NewSRWatcher(nil, nil, nil, ice.Config{}) + return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState) +} + +// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected +// across a network outage while neither signal nor relay reports an event — +// both stayed up, as on a short airplane mode toggle over Wi-Fi. +// +// Every tick taken while offline is skipped, but it still advances the +// exponential backoff, so by the time the network returns the next tick can be +// tens of seconds away. Without an explicit reaction to the transition the +// peer waits out that interval for a recovery that could start immediately. +func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) { + netState := netstate.New() + + var attempts atomic.Int32 + g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState) + + ctx, cancel := context.WithCancel(context.Background()) + defer cancel() + // Start from the reconnect ticker (800ms initial interval), the state a + // peer is in after it loses its connection. + go g.Start(ctx, func() { attempts.Add(1) }) + g.SetRelayedConnDisconnected() + + // Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped + // while offline, but each one doubles the wait for the next. + netState.Set(false) + time.Sleep(8 * time.Second) + + offlineAttempts := attempts.Load() + if offlineAttempts != 0 { + t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts) + } + + netState.Set(true) + + // The next organic tick is now several seconds out, so anything within + // this window can only come from reacting to the transition itself. + pollCtx, stopPolling := context.WithTimeout(ctx, 2*time.Second) + defer stopPolling() + + select { + case <-pollCtx.Done(): + t.Fatal("peer was not retried within 2s of the network coming back, " + + "with neither a signal nor a relay event to fall back on") + case <-pollUntil(pollCtx, func() bool { return attempts.Load() > 0 }): + } +} + +// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going +// offline must not itself trigger an attempt. +func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) { + netState := netstate.New() + + var attempts atomic.Int32 + g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState) + + ctx, cancel := context.WithCancel(context.Background()) + defer cancel() + go g.Start(ctx, func() { attempts.Add(1) }) + + netState.Set(false) + time.Sleep(5 * time.Second) + + if got := attempts.Load(); got != 0 { + t.Fatalf("callback ran %d times after going offline, want 0", got) + } +} + +// pollUntil closes the returned channel once cond holds. It gives up when ctx +// is done, so the polling goroutine never outlives the test that started it. +func pollUntil(ctx context.Context, cond func() bool) <-chan struct{} { + done := make(chan struct{}) + go func() { + for { + if cond() { + close(done) + return + } + select { + case <-ctx.Done(): + return + case <-time.After(10 * time.Millisecond): + } + } + }() + return done +} diff --git a/client/internal/peer/handshaker.go b/client/internal/peer/handshaker.go index 56e82e6e3..6ecb2a947 100644 --- a/client/internal/peer/handshaker.go +++ b/client/internal/peer/handshaker.go @@ -81,14 +81,19 @@ type Handshaker struct { func NewHandshaker(log *log.Entry, config ConnConfig, signaler *Signaler, ice *WorkerICE, relay *WorkerRelay, metricsStages *MetricsStages) *Handshaker { h := &Handshaker{ - log: log, - config: config, - signaler: signaler, - ice: ice, - relay: relay, - metricsStages: metricsStages, - remoteOffersCh: make(chan OfferAnswer), - remoteAnswerCh: make(chan OfferAnswer), + log: log, + config: config, + signaler: signaler, + ice: ice, + relay: relay, + metricsStages: metricsStages, + // Buffered by one so an offer or answer that arrives between Open launching + // the Listen goroutine and it reaching its receive is held rather than + // dropped. A peer activated by an incoming signal receives the remote's + // message in that window; an unbuffered channel skips it as "receiver not + // ready", and the connection cannot proceed until the remote re-sends. + remoteOffersCh: make(chan OfferAnswer, 1), + remoteAnswerCh: make(chan OfferAnswer, 1), } // assume remote supports ICE until we learn otherwise from received offers h.remoteICESupported.Store(ice != nil) @@ -162,29 +167,38 @@ func (h *Handshaker) SendOffer() error { return h.sendOffer() } -// OnRemoteOffer handles an offer from the remote peer and returns true if the message was accepted, false otherwise -// doesn't block, discards the message if connection wasn't ready +// OnRemoteOffer hands an offer to Listen without blocking, keeping only the most +// recent one if several arrive before Listen reads them. func (h *Handshaker) OnRemoteOffer(offer OfferAnswer) { - select { - case h.remoteOffersCh <- offer: - return - default: - h.log.Warnf("skipping remote offer message because receiver not ready") - // connection might not be ready yet to receive so we ignore the message - return - } + enqueueLatest(h.remoteOffersCh, offer) } -// OnRemoteAnswer handles an offer from the remote peer and returns true if the message was accepted, false otherwise -// doesn't block, discards the message if connection wasn't ready +// OnRemoteAnswer hands an answer to Listen without blocking, keeping only the most +// recent one if several arrive before Listen reads them. func (h *Handshaker) OnRemoteAnswer(answer OfferAnswer) { + enqueueLatest(h.remoteAnswerCh, answer) +} + +// enqueueLatest delivers msg on a one-slot channel without blocking. When the slot +// already holds an unread message the older one is discarded in favor of msg, so a +// message arriving before Listen starts reading is held rather than dropped, and +// the newest wins if several arrive first. Safe because there is a single producer +// (the engine loop): after draining the stale value the send always has room. +func enqueueLatest(ch chan OfferAnswer, msg OfferAnswer) { select { - case h.remoteAnswerCh <- answer: + case ch <- msg: return default: - // connection might not be ready yet to receive so we ignore the message - h.log.Warnf("skipping remote answer message because receiver not ready") - return + } + + select { + case <-ch: + default: + } + + select { + case ch <- msg: + default: } } diff --git a/client/internal/peer/handshaker_test.go b/client/internal/peer/handshaker_test.go new file mode 100644 index 000000000..5e203d78b --- /dev/null +++ b/client/internal/peer/handshaker_test.go @@ -0,0 +1,63 @@ +package peer + +import ( + "testing" + "time" + + log "github.com/sirupsen/logrus" + "github.com/stretchr/testify/assert" +) + +func newTestHandshaker(t *testing.T) *Handshaker { + t.Helper() + // The tests exercise the answer path, whose Listen branch dispatches to the + // relay listener without sending an answer, so no signaler/ICE/relay is needed. + return NewHandshaker(log.WithField("test", t.Name()), ConnConfig{}, nil, nil, nil, nil) +} + +// TestHandshakerHoldsSignalArrivingBeforeListen covers the case where a peer is +// activated by an incoming signal: the remote's offer/answer arrives in the same +// step that opens the connection, before the Listen loop starts reading. The +// message must be held rather than dropped, or the connection cannot proceed until +// the remote re-sends. This is the path taken when an eager peer connects to a +// lazily-managed one. +func TestHandshakerHoldsSignalArrivingBeforeListen(t *testing.T) { + h := newTestHandshaker(t) + + processed := make(chan *OfferAnswer, 4) + h.AddRelayListener(func(o *OfferAnswer) { processed <- o }) + + // Delivered before Listen is reading, as when the peer is woken by the remote's + // signal and the message is delivered right after Open. + h.OnRemoteAnswer(OfferAnswer{WgListenPort: 51820}) + + go h.Listen(t.Context()) + + select { + case <-processed: + case <-time.After(2 * time.Second): + assert.Fail(t, "remote-answer dispatch: signal delivered before Listen was ready was dropped") + } +} + +// TestHandshakerKeepsLatestSignalBeforeListen covers several signals arriving +// before Listen reads: the newest must win (matching the latest-offer contract), +// rather than the first being kept and later ones discarded. +func TestHandshakerKeepsLatestSignalBeforeListen(t *testing.T) { + h := newTestHandshaker(t) + + processed := make(chan *OfferAnswer, 4) + h.AddRelayListener(func(o *OfferAnswer) { processed <- o }) + + h.OnRemoteAnswer(OfferAnswer{WgListenPort: 1111}) + h.OnRemoteAnswer(OfferAnswer{WgListenPort: 2222}) + + go h.Listen(t.Context()) + + select { + case got := <-processed: + assert.Equal(t, 2222, got.WgListenPort, "remote-answer dispatch: the latest queued signal should be processed") + case <-time.After(2 * time.Second): + assert.Fail(t, "remote-answer dispatch: queued signal was dropped") + } +} diff --git a/client/internal/peer/listener.go b/client/internal/peer/listener.go index c601fe534..2bb7fcf32 100644 --- a/client/internal/peer/listener.go +++ b/client/internal/peer/listener.go @@ -1,11 +1,40 @@ package peer +// ClientState identifies the client connection state delivered via +// Listener.OnStateChanged. +type ClientState int + +// Client states. The numeric values cross the gomobile boundary (the mobile +// bindings re-export them as integer constants), so they are a wire format: +// append new states at the end, never reorder or insert. +const ( + ClientStateDisconnected ClientState = iota + ClientStateConnected + ClientStateConnecting + ClientStateDisconnecting + // ClientStateNoNetwork is an overlay state: it is never stored as the + // last notification, only derived from ClientStateConnecting while the + // OS reports no usable network (see notifier.effectiveState). + ClientStateNoNetwork +) + // Listener is a callback type about the NetBird network connection state type Listener interface { + // OnStateChanged reports every client state transition. New states are + // delivered only through this callback; the per-state callbacks below + // are kept for compatibility and will be removed once all consumers + // have migrated. + OnStateChanged(state ClientState) + + // Deprecated: consume OnStateChanged instead. OnConnected() + // Deprecated: consume OnStateChanged instead. OnDisconnected() + // Deprecated: consume OnStateChanged instead. OnConnecting() + // Deprecated: consume OnStateChanged instead. OnDisconnecting() + OnAddressChanged(string, string) OnPeersListChanged(int) } diff --git a/client/internal/peer/notifier.go b/client/internal/peer/notifier.go index 8d1954fe5..1ee1d32ea 100644 --- a/client/internal/peer/notifier.go +++ b/client/internal/peer/notifier.go @@ -4,31 +4,64 @@ import ( "sync" ) -const ( - stateDisconnected = iota - stateConnected - stateConnecting - stateDisconnecting -) - type notifier struct { + // publishLock orders state publication: it is held across computing the + // effective state and handing it to the listener, so a transition cannot + // overtake a newer one and leave the listener on a stale state. + publishLock sync.Mutex serverStateLock sync.Mutex listenersLock sync.Mutex listener Listener currentClientState bool - lastNotification int + lastNotification ClientState lastNumberOfPeers int lastFqdnAddress string lastIPAddress string + networkAvailable bool } func newNotifier() *notifier { - return ¬ifier{} + return ¬ifier{ + networkAvailable: true, + } +} + +// effectiveState maps the computed state to what listeners should see: +// while the OS reports no usable network, "Connecting" would be a lie — +// connection attempts are suspended — so it is reported as NoNetwork. +// Caller must hold serverStateLock. +func (n *notifier) effectiveState(state ClientState) ClientState { + if !n.networkAvailable && state == ClientStateConnecting { + return ClientStateNoNetwork + } + return state +} + +// setNetworkAvailable records the OS network availability and re-notifies +// the listener when the flag flips the effective state (Connecting <-> +// NoNetwork). +func (n *notifier) setNetworkAvailable(available bool) { + n.publishLock.Lock() + defer n.publishLock.Unlock() + + n.serverStateLock.Lock() + if n.networkAvailable == available { + n.serverStateLock.Unlock() + return + } + previous := n.effectiveState(n.lastNotification) + n.networkAvailable = available + current := n.effectiveState(n.lastNotification) + n.serverStateLock.Unlock() + + if previous != current { + n.notify(current) + } } func (n *notifier) setListener(listener Listener) { n.serverStateLock.Lock() - lastNotification := n.lastNotification + lastNotification := n.effectiveState(n.lastNotification) numOfPeers := n.lastNumberOfPeers fqdnAddress := n.lastFqdnAddress address := n.lastIPAddress @@ -52,6 +85,9 @@ func (n *notifier) removeListener() { } func (n *notifier) updateServerStates(mgmState bool, signalState bool) { + n.publishLock.Lock() + defer n.publishLock.Unlock() + n.serverStateLock.Lock() calculatedState := n.calculateState(mgmState, signalState) @@ -61,43 +97,54 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) { } n.lastNotification = calculatedState + effective := n.effectiveState(calculatedState) n.serverStateLock.Unlock() - n.notify(calculatedState) + n.notify(effective) } func (n *notifier) clientStart() { + n.publishLock.Lock() + defer n.publishLock.Unlock() + n.serverStateLock.Lock() n.currentClientState = true - n.lastNotification = stateConnecting + n.lastNotification = ClientStateConnecting + effective := n.effectiveState(ClientStateConnecting) n.serverStateLock.Unlock() - n.notify(stateConnecting) + n.notify(effective) } func (n *notifier) clientStop() { + n.publishLock.Lock() + defer n.publishLock.Unlock() + n.serverStateLock.Lock() n.currentClientState = false - n.lastNotification = stateDisconnected + n.lastNotification = ClientStateDisconnected n.serverStateLock.Unlock() - n.notify(stateDisconnected) + n.notify(ClientStateDisconnected) } func (n *notifier) clientTearDown() { + n.publishLock.Lock() + defer n.publishLock.Unlock() + n.serverStateLock.Lock() n.currentClientState = false - n.lastNotification = stateDisconnecting + n.lastNotification = ClientStateDisconnecting n.serverStateLock.Unlock() - n.notify(stateDisconnecting) + n.notify(ClientStateDisconnecting) } -func (n *notifier) isServerStateChanged(newState int) bool { +func (n *notifier) isServerStateChanged(newState ClientState) bool { return n.lastNotification != newState } -func (n *notifier) notify(state int) { +func (n *notifier) notify(state ClientState) { n.listenersLock.Lock() listener := n.listener n.listenersLock.Unlock() @@ -109,20 +156,20 @@ func (n *notifier) notify(state int) { notifyListener(listener, state) } -func (n *notifier) calculateState(managementConn, signalConn bool) int { +func (n *notifier) calculateState(managementConn, signalConn bool) ClientState { if managementConn && signalConn { - return stateConnected + return ClientStateConnected } if !managementConn && !signalConn && !n.currentClientState { - return stateDisconnected + return ClientStateDisconnected } - if n.lastNotification == stateDisconnecting { - return stateDisconnecting + if n.lastNotification == ClientStateDisconnecting { + return ClientStateDisconnecting } - return stateConnecting + return ClientStateConnecting } func (n *notifier) peerListChanged(numOfPeers int) { @@ -159,15 +206,19 @@ func (n *notifier) localAddressChanged(fqdn, address string) { listener.OnAddressChanged(fqdn, address) } -func notifyListener(l Listener, state int) { +func notifyListener(l Listener, state ClientState) { + // legacy per-state callbacks; NoNetwork is delivered only via + // OnStateChanged below switch state { - case stateDisconnected: + case ClientStateDisconnected: l.OnDisconnected() - case stateConnected: + case ClientStateConnected: l.OnConnected() - case stateConnecting: + case ClientStateConnecting: l.OnConnecting() - case stateDisconnecting: + case ClientStateDisconnecting: l.OnDisconnecting() } + + l.OnStateChanged(state) } diff --git a/client/internal/peer/notifier_concurrent_test.go b/client/internal/peer/notifier_concurrent_test.go new file mode 100644 index 000000000..fcaaaad3b --- /dev/null +++ b/client/internal/peer/notifier_concurrent_test.go @@ -0,0 +1,108 @@ +package peer + +import ( + "sync" + "testing" + "time" +) + +type recordingListener struct { + mu sync.Mutex + states []ClientState + onState func(ClientState) +} + +func (l *recordingListener) OnStateChanged(state ClientState) { + l.mu.Lock() + l.states = append(l.states, state) + hook := l.onState + l.mu.Unlock() + + if hook != nil { + hook(state) + } +} + +func (l *recordingListener) last() (ClientState, bool) { + l.mu.Lock() + defer l.mu.Unlock() + if len(l.states) == 0 { + return 0, false + } + return l.states[len(l.states)-1], true +} + +func (l *recordingListener) snapshot() []ClientState { + l.mu.Lock() + defer l.mu.Unlock() + return append([]ClientState(nil), l.states...) +} + +func (l *recordingListener) OnConnected() {} +func (l *recordingListener) OnDisconnected() {} +func (l *recordingListener) OnConnecting() {} +func (l *recordingListener) OnDisconnecting() {} +func (l *recordingListener) OnAddressChanged(string, string) {} +func (l *recordingListener) OnPeersListChanged(int) {} + +// TestNotifier_ConcurrentAvailabilityFlipOrdersPublication holds the first +// transition inside the listener callback and flips availability again from +// another goroutine while it is parked. The second flip must not publish +// ahead of the one in flight, otherwise the listener ends up on a state the +// notifier already superseded. +func TestNotifier_ConcurrentAvailabilityFlipOrdersPublication(t *testing.T) { + n := newNotifier() + n.currentClientState = true + n.lastNotification = ClientStateConnecting + + entered := make(chan struct{}) + release := make(chan struct{}) + + l := &recordingListener{} + l.onState = func(state ClientState) { + if state != ClientStateNoNetwork { + return + } + l.mu.Lock() + l.onState = nil + l.mu.Unlock() + close(entered) + <-release + } + n.listener = l + + var wg sync.WaitGroup + wg.Add(1) + go func() { + defer wg.Done() + n.setNetworkAvailable(false) + }() + + <-entered + + flipped := make(chan struct{}) + go func() { + defer close(flipped) + n.setNetworkAvailable(true) + }() + + select { + case <-flipped: + t.Fatal("the online transition published while the offline one was " + + "still in flight; publication is not serialized") + case <-time.After(200 * time.Millisecond): + } + + close(release) + <-flipped + wg.Wait() + + got, ok := l.last() + if !ok { + t.Fatal("listener never observed a state") + } + if got != ClientStateConnecting { + t.Fatalf("listener holds %v after the network came back, want Connecting; sequence: %v", + got, l.snapshot()) + } +} diff --git a/client/internal/peer/notifier_test.go b/client/internal/peer/notifier_test.go index 0b7722b0c..a73016b05 100644 --- a/client/internal/peer/notifier_test.go +++ b/client/internal/peer/notifier_test.go @@ -6,29 +6,32 @@ import ( ) type mocListener struct { - lastState int + lastState ClientState wg sync.WaitGroup peersWg sync.WaitGroup peers int } func (l *mocListener) OnConnected() { - l.lastState = stateConnected + l.lastState = ClientStateConnected l.wg.Done() } func (l *mocListener) OnDisconnected() { - l.lastState = stateDisconnected + l.lastState = ClientStateDisconnected l.wg.Done() } func (l *mocListener) OnConnecting() { - l.lastState = stateConnecting + l.lastState = ClientStateConnecting l.wg.Done() } func (l *mocListener) OnDisconnecting() { - l.lastState = stateDisconnecting + l.lastState = ClientStateDisconnecting l.wg.Done() } +func (l *mocListener) OnStateChanged(state ClientState) { + +} func (l *mocListener) OnAddressChanged(host, addr string) { } @@ -57,15 +60,15 @@ func Test_notifier_serverState(t *testing.T) { type scenario struct { name string - expected int + expected ClientState mgmState bool signalState bool } scenarios := []scenario{ - {"connected", stateConnected, true, true}, - {"mgm down", stateConnecting, false, true}, - {"signal down", stateConnecting, true, false}, - {"disconnected", stateDisconnected, false, false}, + {"connected", ClientStateConnected, true, true}, + {"mgm down", ClientStateConnecting, false, true}, + {"signal down", ClientStateConnecting, true, false}, + {"disconnected", ClientStateDisconnected, false, false}, } for _, tt := range scenarios { @@ -85,7 +88,7 @@ func Test_notifier_SetListener(t *testing.T) { listener.setPeersWaiter() n := newNotifier() - n.lastNotification = stateConnecting + n.lastNotification = ClientStateConnecting n.setListener(listener) listener.wait() listener.waitPeers() @@ -99,7 +102,7 @@ func Test_notifier_RemoveListener(t *testing.T) { listener.setWaiter() listener.setPeersWaiter() n := newNotifier() - n.lastNotification = stateConnecting + n.lastNotification = ClientStateConnecting n.setListener(listener) // setListener replays cached state on a goroutine; wait for both the state // and peers callbacks to finish so we don't race on listener.peers. diff --git a/client/internal/peer/status.go b/client/internal/peer/status.go index 423ce9b23..24e3e7fac 100644 --- a/client/internal/peer/status.go +++ b/client/internal/peer/status.go @@ -1211,6 +1211,12 @@ func (d *Status) ClientTeardown() { d.notifyStateChange() } +// SetNetworkAvailable records the OS-reported network availability; while +// unavailable, listeners see NoNetwork instead of Connecting. +func (d *Status) SetNetworkAvailable(available bool) { + d.notifier.setNetworkAvailable(available) +} + // SetConnectionListener set a listener to the notifier func (d *Status) SetConnectionListener(listener Listener) { d.notifier.setListener(listener) diff --git a/client/internal/peer/worker_ice.go b/client/internal/peer/worker_ice.go index b1aa3e0f9..83cac13f5 100644 --- a/client/internal/peer/worker_ice.go +++ b/client/internal/peer/worker_ice.go @@ -255,8 +255,8 @@ func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent return } - w.log.Debugf("turn agent dial") - remoteConn, err := w.turnAgentDial(ctx, agent, remoteOfferAnswer) + w.log.Debugf("agent dial") + remoteConn, err := w.agentDial(ctx, agent, remoteOfferAnswer) if err != nil { w.log.Debugf("failed to dial the remote peer: %s", err) w.closeAgent(agent, w.agentDialerCancel) @@ -389,6 +389,17 @@ func (w *WorkerICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) { return } + // A forwarded candidate only makes sense for an IPv4 mapping, which + // translates a port on the gateway's address. An IPv6 pinhole translates + // nothing: it unblocks the address ICE already gathers as a host candidate, + // so there is no second address to advertise. Injecting one here would also + // paste an IPv6 address onto whichever server-reflexive candidate arrived + // first, which is usually IPv4. + if mapping.ExternalIP != nil && mapping.ExternalIP.To4() == nil { + w.log.Debugf("skipping port-forwarded candidate: %s mapping is IPv6-only", mapping.NATType) + return + } + w.muxAgent.Lock() if w.portForwardAttempted { w.muxAgent.Unlock() @@ -517,8 +528,8 @@ func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dia w.logSuccessfulPaths(agent) return case ice.ConnectionStateFailed, ice.ConnectionStateDisconnected, ice.ConnectionStateClosed: - // ice.ConnectionStateClosed happens when we recreate the agent. For the P2P to TURN switch important to - // notify the conn.onICEStateDisconnected changes to update the current used priority + // ice.ConnectionStateClosed happens when we recreate the agent. The P2P to relay switch requires + // notifying conn.onICEStateDisconnected so it can update the currently used priority. sessionChanged := w.closeAgent(agent, dialerCancel) @@ -532,7 +543,7 @@ func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dia } } -func (w *WorkerICE) turnAgentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) (*ice.Conn, error) { +func (w *WorkerICE) agentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) (*ice.Conn, error) { if isController(w.config) { return agent.Dial(ctx, remoteOfferAnswer.IceCredentials.UFrag, remoteOfferAnswer.IceCredentials.Pwd) } else { diff --git a/client/internal/portforward/manager.go b/client/internal/portforward/manager.go index b0680160c..7d5a4cb9e 100644 --- a/client/internal/portforward/manager.go +++ b/client/internal/portforward/manager.go @@ -10,10 +10,8 @@ import ( "sync" "time" - "github.com/libp2p/go-nat" + "github.com/netbirdio/go-nat" log "github.com/sirupsen/logrus" - - "github.com/netbirdio/netbird/client/internal/portforward/pcp" ) const ( @@ -168,6 +166,11 @@ func (m *Manager) setup(ctx context.Context) (nat.NAT, *Mapping, error) { if err != nil { return nil, nil, fmt.Errorf("create port mapping: %w", err) } + + // Only meaningful once a mapping has been attempted: that is what opens the + // pinhole and records its outcome. + logIPv6Pinhole(gateway) + return gateway, mapping, nil } @@ -265,7 +268,9 @@ func (m *Manager) checkHealthAndRecreate(ctx context.Context, gateway nat.NAT) b return false } - pcpNAT, ok := gateway.(*pcp.NAT) + // Assert on the interface, not on a concrete type: a dual-stack gateway is + // a wrapper around the IPv4 NAT, so a type assertion misses it. + checker, ok := gateway.(nat.HealthChecker) if !ok { return false } @@ -273,7 +278,7 @@ func (m *Manager) checkHealthAndRecreate(ctx context.Context, gateway nat.NAT) b ctx, cancel := context.WithTimeout(ctx, 10*time.Second) defer cancel() - epoch, serverRestarted, err := pcpNAT.CheckServerHealth(ctx) + epoch, serverRestarted, err := checker.CheckServerHealth(ctx) if err != nil { log.Debugf("PCP health check failed: %v", err) return false @@ -340,3 +345,18 @@ func (m *Manager) startTearDown(ctx context.Context) { func isPermanentLeaseRequired(err error) bool { return err != nil && upnpErrPermanentLeaseOnly.MatchString(err.Error()) } + +// logIPv6Pinhole reports the outcome of the IPv6 pinhole. Pinholes are best +// effort and never fail a mapping on their own, so this is the only way to see +// whether one was actually opened. +func logIPv6Pinhole(gateway nat.NAT) { + reporter, ok := gateway.(nat.IPv6PinholeReporter) + if !ok { + return + } + if err := reporter.IPv6PinholeError(); err != nil { + log.Warnf("IPv6 pinhole: %v", err) + return + } + log.Infof("IPv6 pinhole open") +} diff --git a/client/internal/portforward/pcp/client.go b/client/internal/portforward/pcp/client.go deleted file mode 100644 index f6d243ef9..000000000 --- a/client/internal/portforward/pcp/client.go +++ /dev/null @@ -1,408 +0,0 @@ -package pcp - -import ( - "context" - "crypto/rand" - "errors" - "fmt" - "net" - "net/netip" - "sync" - "time" - - log "github.com/sirupsen/logrus" -) - -const ( - defaultTimeout = 3 * time.Second - responseBufferSize = 128 - - // RFC 6887 Section 8.1.1 retry timing - initialRetryDelay = 3 * time.Second - maxRetryDelay = 1024 * time.Second - maxRetries = 4 // 3s + 6s + 12s + 24s = 45s total worst case -) - -// Client is a PCP protocol client. -// All methods are safe for concurrent use. -type Client struct { - gateway netip.Addr - timeout time.Duration - - mu sync.Mutex - // localIP caches the resolved local IP address. - localIP netip.Addr - // lastEpoch is the last observed server epoch value. - lastEpoch uint32 - // epochTime tracks when lastEpoch was received for state loss detection. - epochTime time.Time - // externalIP caches the external IP from the last successful MAP response. - externalIP netip.Addr - // epochStateLost is set when epoch indicates server restart. - epochStateLost bool -} - -// NewClient creates a new PCP client for the gateway at the given IP. -func NewClient(gateway net.IP) *Client { - addr, ok := netip.AddrFromSlice(gateway) - if !ok { - log.Debugf("invalid gateway IP: %v", gateway) - } - return &Client{ - gateway: addr.Unmap(), - timeout: defaultTimeout, - } -} - -// NewClientWithTimeout creates a new PCP client with a custom timeout. -func NewClientWithTimeout(gateway net.IP, timeout time.Duration) *Client { - addr, ok := netip.AddrFromSlice(gateway) - if !ok { - log.Debugf("invalid gateway IP: %v", gateway) - } - return &Client{ - gateway: addr.Unmap(), - timeout: timeout, - } -} - -// SetLocalIP sets the local IP address to use in PCP requests. -func (c *Client) SetLocalIP(ip net.IP) { - addr, ok := netip.AddrFromSlice(ip) - if !ok { - log.Debugf("invalid local IP: %v", ip) - } - c.mu.Lock() - c.localIP = addr.Unmap() - c.mu.Unlock() -} - -// Gateway returns the gateway IP address. -func (c *Client) Gateway() net.IP { - return c.gateway.AsSlice() -} - -// Announce sends a PCP ANNOUNCE request to discover PCP support. -// Returns the server's epoch time on success. -func (c *Client) Announce(ctx context.Context) (epoch uint32, err error) { - localIP, err := c.getLocalIP() - if err != nil { - return 0, fmt.Errorf("get local IP: %w", err) - } - - req := buildAnnounceRequest(localIP) - resp, err := c.sendRequest(ctx, req) - if err != nil { - return 0, fmt.Errorf("send announce: %w", err) - } - - parsed, err := parseResponse(resp) - if err != nil { - return 0, fmt.Errorf("parse announce response: %w", err) - } - - if parsed.ResultCode != ResultSuccess { - return 0, fmt.Errorf("PCP ANNOUNCE failed: %s", ResultCodeString(parsed.ResultCode)) - } - - c.mu.Lock() - if c.updateEpochLocked(parsed.Epoch) { - log.Warnf("PCP server epoch indicates state loss - mappings may need refresh") - } - c.mu.Unlock() - return parsed.Epoch, nil -} - -// AddPortMapping requests a port mapping from the PCP server. -func (c *Client) AddPortMapping(ctx context.Context, protocol string, internalPort int, lifetime time.Duration) (*MapResponse, error) { - return c.addPortMappingWithHint(ctx, protocol, internalPort, internalPort, netip.Addr{}, lifetime) -} - -// AddPortMappingWithHint requests a port mapping with suggested external port and IP. -// Use lifetime <= 0 to delete a mapping. -func (c *Client) AddPortMappingWithHint(ctx context.Context, protocol string, internalPort, suggestedExtPort int, suggestedExtIP net.IP, lifetime time.Duration) (*MapResponse, error) { - var extIP netip.Addr - if suggestedExtIP != nil { - var ok bool - extIP, ok = netip.AddrFromSlice(suggestedExtIP) - if !ok { - log.Debugf("invalid suggested external IP: %v", suggestedExtIP) - } - extIP = extIP.Unmap() - } - return c.addPortMappingWithHint(ctx, protocol, internalPort, suggestedExtPort, extIP, lifetime) -} - -func (c *Client) addPortMappingWithHint(ctx context.Context, protocol string, internalPort, suggestedExtPort int, suggestedExtIP netip.Addr, lifetime time.Duration) (*MapResponse, error) { - localIP, err := c.getLocalIP() - if err != nil { - return nil, fmt.Errorf("get local IP: %w", err) - } - - proto, err := protocolNumber(protocol) - if err != nil { - return nil, fmt.Errorf("parse protocol: %w", err) - } - - var nonce [12]byte - if _, err := rand.Read(nonce[:]); err != nil { - return nil, fmt.Errorf("generate nonce: %w", err) - } - - // Convert lifetime to seconds. Lifetime 0 means delete, so only apply - // default for positive durations that round to 0 seconds. - var lifetimeSec uint32 - if lifetime > 0 { - lifetimeSec = uint32(lifetime.Seconds()) - if lifetimeSec == 0 { - lifetimeSec = DefaultLifetime - } - } - - req := buildMapRequest(localIP, nonce, proto, uint16(internalPort), uint16(suggestedExtPort), suggestedExtIP, lifetimeSec) - - resp, err := c.sendRequest(ctx, req) - if err != nil { - return nil, fmt.Errorf("send map request: %w", err) - } - - mapResp, err := parseMapResponse(resp) - if err != nil { - return nil, fmt.Errorf("parse map response: %w", err) - } - - if mapResp.Nonce != nonce { - return nil, fmt.Errorf("nonce mismatch in response") - } - - if mapResp.Protocol != proto { - return nil, fmt.Errorf("protocol mismatch: requested %d, got %d", proto, mapResp.Protocol) - } - if mapResp.InternalPort != uint16(internalPort) { - return nil, fmt.Errorf("internal port mismatch: requested %d, got %d", internalPort, mapResp.InternalPort) - } - - if mapResp.ResultCode != ResultSuccess { - return nil, &Error{ - Code: mapResp.ResultCode, - Message: ResultCodeString(mapResp.ResultCode), - } - } - - c.mu.Lock() - if c.updateEpochLocked(mapResp.Epoch) { - log.Warnf("PCP server epoch indicates state loss - mappings may need refresh") - } - c.cacheExternalIPLocked(mapResp.ExternalIP) - c.mu.Unlock() - return mapResp, nil -} - -// DeletePortMapping removes a port mapping by requesting zero lifetime. -func (c *Client) DeletePortMapping(ctx context.Context, protocol string, internalPort int) error { - if _, err := c.addPortMappingWithHint(ctx, protocol, internalPort, 0, netip.Addr{}, 0); err != nil { - var pcpErr *Error - if errors.As(err, &pcpErr) && pcpErr.Code == ResultNotAuthorized { - return nil - } - return fmt.Errorf("delete mapping: %w", err) - } - return nil -} - -// GetExternalAddress returns the external IP address. -// First checks for a cached value from previous MAP responses. -// If not cached, creates a short-lived mapping to discover the external IP. -func (c *Client) GetExternalAddress(ctx context.Context) (net.IP, error) { - c.mu.Lock() - if c.externalIP.IsValid() { - ip := c.externalIP.AsSlice() - c.mu.Unlock() - return ip, nil - } - c.mu.Unlock() - - // Use an ephemeral port in the dynamic range (49152-65535). - // Port 0 is not valid with UDP/TCP protocols per RFC 6887. - ephemeralPort := 49152 + int(uint16(time.Now().UnixNano()))%(65535-49152) - - // Use minimal lifetime (1 second) for discovery. - resp, err := c.AddPortMapping(ctx, "udp", ephemeralPort, time.Second) - if err != nil { - return nil, fmt.Errorf("create temporary mapping: %w", err) - } - - if err := c.DeletePortMapping(ctx, "udp", ephemeralPort); err != nil { - log.Debugf("cleanup temporary PCP mapping: %v", err) - } - - return resp.ExternalIP.AsSlice(), nil -} - -// LastEpoch returns the last observed server epoch value. -// A decrease in epoch indicates the server may have restarted and mappings may be lost. -func (c *Client) LastEpoch() uint32 { - c.mu.Lock() - defer c.mu.Unlock() - return c.lastEpoch -} - -// EpochStateLost returns true if epoch state loss was detected and clears the flag. -func (c *Client) EpochStateLost() bool { - c.mu.Lock() - defer c.mu.Unlock() - lost := c.epochStateLost - c.epochStateLost = false - return lost -} - -// updateEpoch updates the epoch tracking and detects potential state loss. -// Returns true if state loss was detected (server likely restarted). -// Caller must hold c.mu. -func (c *Client) updateEpochLocked(newEpoch uint32) bool { - now := time.Now() - stateLost := false - - // RFC 6887 Section 8.5: Detect invalid epoch indicating server state loss. - // client_delta = time since last response - // server_delta = epoch change since last response - // Invalid if: client_delta+2 < server_delta - server_delta/16 - // OR: server_delta+2 < client_delta - client_delta/16 - // The +2 handles quantization, /16 (6.25%) handles clock drift. - if !c.epochTime.IsZero() && c.lastEpoch > 0 { - clientDelta := uint32(now.Sub(c.epochTime).Seconds()) - serverDelta := newEpoch - c.lastEpoch - - // Check for epoch going backwards or jumping unexpectedly. - // Subtraction is safe: serverDelta/16 is always <= serverDelta. - if clientDelta+2 < serverDelta-(serverDelta/16) || - serverDelta+2 < clientDelta-(clientDelta/16) { - stateLost = true - c.epochStateLost = true - } - } - - c.lastEpoch = newEpoch - c.epochTime = now - return stateLost -} - -// cacheExternalIP stores the external IP from a successful MAP response. -// Caller must hold c.mu. -func (c *Client) cacheExternalIPLocked(ip netip.Addr) { - if ip.IsValid() && !ip.IsUnspecified() { - c.externalIP = ip - } -} - -// sendRequest sends a PCP request with retries per RFC 6887 Section 8.1.1. -func (c *Client) sendRequest(ctx context.Context, req []byte) ([]byte, error) { - addr := &net.UDPAddr{IP: c.gateway.AsSlice(), Port: Port} - - var lastErr error - delay := initialRetryDelay - - for range maxRetries { - resp, err := c.sendOnce(ctx, addr, req) - if err == nil { - return resp, nil - } - lastErr = err - - if ctx.Err() != nil { - return nil, ctx.Err() - } - - // RFC 6887 Section 8.1.1: RT = (1 + RAND) * MIN(2 * RTprev, MRT) - // RAND is random between -0.1 and +0.1 - select { - case <-ctx.Done(): - return nil, ctx.Err() - case <-time.After(retryDelayWithJitter(delay)): - } - delay = min(delay*2, maxRetryDelay) - } - - return nil, fmt.Errorf("PCP request failed after %d retries: %w", maxRetries, lastErr) -} - -// retryDelayWithJitter applies RFC 6887 jitter: multiply by (1 + RAND) where RAND is [-0.1, +0.1]. -func retryDelayWithJitter(d time.Duration) time.Duration { - var b [1]byte - _, _ = rand.Read(b[:]) - // Convert byte to range [-0.1, +0.1]: (b/255 * 0.2) - 0.1 - jitter := (float64(b[0])/255.0)*0.2 - 0.1 - return time.Duration(float64(d) * (1 + jitter)) -} - -func (c *Client) sendOnce(ctx context.Context, addr *net.UDPAddr, req []byte) ([]byte, error) { - // Use ListenUDP instead of DialUDP to validate response source address per RFC 6887 §8.3. - conn, err := net.ListenUDP("udp", nil) - if err != nil { - return nil, fmt.Errorf("listen: %w", err) - } - defer func() { - if err := conn.Close(); err != nil { - log.Debugf("close UDP connection: %v", err) - } - }() - - timeout := c.timeout - if deadline, ok := ctx.Deadline(); ok { - if remaining := time.Until(deadline); remaining < timeout { - timeout = remaining - } - } - - if err := conn.SetDeadline(time.Now().Add(timeout)); err != nil { - return nil, fmt.Errorf("set deadline: %w", err) - } - - if _, err := conn.WriteToUDP(req, addr); err != nil { - return nil, fmt.Errorf("write: %w", err) - } - - resp := make([]byte, responseBufferSize) - n, from, err := conn.ReadFromUDP(resp) - if err != nil { - return nil, fmt.Errorf("read: %w", err) - } - - // RFC 6887 §8.3: Validate response came from expected PCP server. - if !from.IP.Equal(addr.IP) { - return nil, fmt.Errorf("response from unexpected source %s (expected %s)", from.IP, addr.IP) - } - - return resp[:n], nil -} - -func (c *Client) getLocalIP() (netip.Addr, error) { - c.mu.Lock() - defer c.mu.Unlock() - - if !c.localIP.IsValid() { - return netip.Addr{}, fmt.Errorf("local IP not set for gateway %s", c.gateway) - } - return c.localIP, nil -} - -func protocolNumber(protocol string) (uint8, error) { - switch protocol { - case "udp", "UDP": - return ProtoUDP, nil - case "tcp", "TCP": - return ProtoTCP, nil - default: - return 0, fmt.Errorf("unsupported protocol: %s", protocol) - } -} - -// Error represents a PCP error response. -type Error struct { - Code uint8 - Message string -} - -func (e *Error) Error() string { - return fmt.Sprintf("PCP error: %s (%d)", e.Message, e.Code) -} diff --git a/client/internal/portforward/pcp/client_test.go b/client/internal/portforward/pcp/client_test.go deleted file mode 100644 index 79f44a426..000000000 --- a/client/internal/portforward/pcp/client_test.go +++ /dev/null @@ -1,187 +0,0 @@ -package pcp - -import ( - "context" - "net" - "net/netip" - "testing" - "time" - - "github.com/stretchr/testify/assert" - "github.com/stretchr/testify/require" -) - -func TestAddrConversion(t *testing.T) { - tests := []struct { - name string - addr netip.Addr - }{ - {"IPv4", netip.MustParseAddr("192.168.1.100")}, - {"IPv4 loopback", netip.MustParseAddr("127.0.0.1")}, - {"IPv6", netip.MustParseAddr("2001:db8::1")}, - {"IPv6 loopback", netip.MustParseAddr("::1")}, - } - - for _, tt := range tests { - t.Run(tt.name, func(t *testing.T) { - b16 := addrTo16(tt.addr) - - recovered := addrFrom16(b16) - assert.Equal(t, tt.addr, recovered, "address should round-trip") - }) - } -} - -func TestBuildAnnounceRequest(t *testing.T) { - clientIP := netip.MustParseAddr("192.168.1.100") - req := buildAnnounceRequest(clientIP) - - require.Len(t, req, headerSize) - assert.Equal(t, byte(Version), req[0], "version") - assert.Equal(t, byte(OpAnnounce), req[1], "opcode") - - // Check client IP is properly encoded as IPv4-mapped IPv6 - assert.Equal(t, byte(0xff), req[18], "IPv4-mapped prefix byte 10") - assert.Equal(t, byte(0xff), req[19], "IPv4-mapped prefix byte 11") - assert.Equal(t, byte(192), req[20], "IP octet 1") - assert.Equal(t, byte(168), req[21], "IP octet 2") - assert.Equal(t, byte(1), req[22], "IP octet 3") - assert.Equal(t, byte(100), req[23], "IP octet 4") -} - -func TestBuildMapRequest(t *testing.T) { - clientIP := netip.MustParseAddr("192.168.1.100") - nonce := [12]byte{1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12} - req := buildMapRequest(clientIP, nonce, ProtoUDP, 51820, 51820, netip.Addr{}, 3600) - - require.Len(t, req, mapRequestSize) - assert.Equal(t, byte(Version), req[0], "version") - assert.Equal(t, byte(OpMap), req[1], "opcode") - - // Lifetime at bytes 4-7 - assert.Equal(t, uint32(3600), (uint32(req[4])<<24)|(uint32(req[5])<<16)|(uint32(req[6])<<8)|uint32(req[7]), "lifetime") - - // Nonce at bytes 24-35 - assert.Equal(t, nonce[:], req[24:36], "nonce") - - // Protocol at byte 36 - assert.Equal(t, byte(ProtoUDP), req[36], "protocol") - - // Internal port at bytes 40-41 - assert.Equal(t, uint16(51820), (uint16(req[40])<<8)|uint16(req[41]), "internal port") - - // External port at bytes 42-43 - assert.Equal(t, uint16(51820), (uint16(req[42])<<8)|uint16(req[43]), "external port") -} - -func TestParseResponse(t *testing.T) { - // Construct a valid ANNOUNCE response - resp := make([]byte, headerSize) - resp[0] = Version - resp[1] = OpAnnounce | OpReply - // Result code = 0 (success) - // Lifetime = 0 - // Epoch = 12345 - resp[8] = 0 - resp[9] = 0 - resp[10] = 0x30 - resp[11] = 0x39 - - parsed, err := parseResponse(resp) - require.NoError(t, err) - assert.Equal(t, uint8(Version), parsed.Version) - assert.Equal(t, uint8(OpAnnounce|OpReply), parsed.Opcode) - assert.Equal(t, uint8(ResultSuccess), parsed.ResultCode) - assert.Equal(t, uint32(12345), parsed.Epoch) -} - -func TestParseResponseErrors(t *testing.T) { - t.Run("too short", func(t *testing.T) { - _, err := parseResponse([]byte{1, 2, 3}) - assert.Error(t, err) - }) - - t.Run("wrong version", func(t *testing.T) { - resp := make([]byte, headerSize) - resp[0] = 1 // Wrong version - resp[1] = OpReply - _, err := parseResponse(resp) - assert.Error(t, err) - }) - - t.Run("missing reply bit", func(t *testing.T) { - resp := make([]byte, headerSize) - resp[0] = Version - resp[1] = OpAnnounce // Missing OpReply bit - _, err := parseResponse(resp) - assert.Error(t, err) - }) -} - -func TestResultCodeString(t *testing.T) { - assert.Equal(t, "SUCCESS", ResultCodeString(ResultSuccess)) - assert.Equal(t, "NOT_AUTHORIZED", ResultCodeString(ResultNotAuthorized)) - assert.Equal(t, "ADDRESS_MISMATCH", ResultCodeString(ResultAddressMismatch)) - assert.Contains(t, ResultCodeString(255), "UNKNOWN") -} - -func TestProtocolNumber(t *testing.T) { - proto, err := protocolNumber("udp") - require.NoError(t, err) - assert.Equal(t, uint8(ProtoUDP), proto) - - proto, err = protocolNumber("tcp") - require.NoError(t, err) - assert.Equal(t, uint8(ProtoTCP), proto) - - proto, err = protocolNumber("UDP") - require.NoError(t, err) - assert.Equal(t, uint8(ProtoUDP), proto) - - _, err = protocolNumber("icmp") - assert.Error(t, err) -} - -func TestClientCreation(t *testing.T) { - gateway := netip.MustParseAddr("192.168.1.1").AsSlice() - - client := NewClient(gateway) - assert.Equal(t, net.IP(gateway), client.Gateway()) - assert.Equal(t, defaultTimeout, client.timeout) - - clientWithTimeout := NewClientWithTimeout(gateway, 5*time.Second) - assert.Equal(t, 5*time.Second, clientWithTimeout.timeout) -} - -func TestNATType(t *testing.T) { - n := NewNAT(netip.MustParseAddr("192.168.1.1").AsSlice(), netip.MustParseAddr("192.168.1.100").AsSlice()) - assert.Equal(t, "PCP", n.Type()) -} - -// Integration test - skipped unless PCP_TEST_GATEWAY env is set -func TestClientIntegration(t *testing.T) { - t.Skip("Integration test - run manually with PCP_TEST_GATEWAY=") - - gateway := netip.MustParseAddr("10.0.1.1").AsSlice() // Change to your test gateway - localIP := netip.MustParseAddr("10.0.1.100").AsSlice() // Change to your local IP - - client := NewClient(gateway) - client.SetLocalIP(localIP) - ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second) - defer cancel() - - // Test ANNOUNCE - epoch, err := client.Announce(ctx) - require.NoError(t, err) - t.Logf("Server epoch: %d", epoch) - - // Test MAP - resp, err := client.AddPortMapping(ctx, "udp", 51820, 1*time.Hour) - require.NoError(t, err) - t.Logf("Mapping: internal=%d external=%d externalIP=%s", - resp.InternalPort, resp.ExternalPort, resp.ExternalIP) - - // Cleanup - err = client.DeletePortMapping(ctx, "udp", 51820) - require.NoError(t, err) -} diff --git a/client/internal/portforward/pcp/nat.go b/client/internal/portforward/pcp/nat.go deleted file mode 100644 index 0e635b6c8..000000000 --- a/client/internal/portforward/pcp/nat.go +++ /dev/null @@ -1,222 +0,0 @@ -package pcp - -import ( - "context" - "fmt" - "net" - "net/netip" - "runtime" - "sync" - "time" - - log "github.com/sirupsen/logrus" - - "github.com/libp2p/go-nat" - "github.com/libp2p/go-netroute" -) - -var _ nat.NAT = (*NAT)(nil) - -// NAT implements the go-nat NAT interface using PCP. -// Supports dual-stack (IPv4 and IPv6) when available. -// All methods are safe for concurrent use. -// -// TODO: IPv6 pinholes use the local IPv6 address. If the address changes -// (e.g., due to SLAAC rotation or network change), the pinhole becomes stale -// and needs to be recreated with the new address. -type NAT struct { - client *Client - - mu sync.RWMutex - // client6 is the IPv6 PCP client, nil if IPv6 is unavailable. - client6 *Client - // localIP6 caches the local IPv6 address used for PCP requests. - localIP6 netip.Addr -} - -// NewNAT creates a new NAT instance backed by PCP. -func NewNAT(gateway, localIP net.IP) *NAT { - client := NewClient(gateway) - client.SetLocalIP(localIP) - return &NAT{ - client: client, - } -} - -// Type returns "PCP" as the NAT type. -func (n *NAT) Type() string { - return "PCP" -} - -// GetDeviceAddress returns the gateway IP address. -func (n *NAT) GetDeviceAddress() (net.IP, error) { - return n.client.Gateway(), nil -} - -// GetExternalAddress returns the external IP address. -func (n *NAT) GetExternalAddress() (net.IP, error) { - ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second) - defer cancel() - return n.client.GetExternalAddress(ctx) -} - -// GetInternalAddress returns the local IP address used to communicate with the gateway. -func (n *NAT) GetInternalAddress() (net.IP, error) { - addr, err := n.client.getLocalIP() - if err != nil { - return nil, err - } - return addr.AsSlice(), nil -} - -// AddPortMapping creates a port mapping on both IPv4 and IPv6 (if available). -func (n *NAT) AddPortMapping(ctx context.Context, protocol string, internalPort int, _ string, timeout time.Duration) (int, error) { - resp, err := n.client.AddPortMapping(ctx, protocol, internalPort, timeout) - if err != nil { - return 0, fmt.Errorf("add mapping: %w", err) - } - - n.mu.RLock() - client6 := n.client6 - localIP6 := n.localIP6 - n.mu.RUnlock() - - if client6 == nil { - return int(resp.ExternalPort), nil - } - - if _, err := client6.AddPortMapping(ctx, protocol, internalPort, timeout); err != nil { - log.Warnf("IPv6 PCP mapping failed (continuing with IPv4): %v", err) - return int(resp.ExternalPort), nil - } - - log.Infof("created IPv6 PCP pinhole: %s:%d", localIP6, internalPort) - return int(resp.ExternalPort), nil -} - -// DeletePortMapping removes a port mapping from both IPv4 and IPv6. -func (n *NAT) DeletePortMapping(ctx context.Context, protocol string, internalPort int) error { - err := n.client.DeletePortMapping(ctx, protocol, internalPort) - - n.mu.RLock() - client6 := n.client6 - n.mu.RUnlock() - - if client6 != nil { - if err6 := client6.DeletePortMapping(ctx, protocol, internalPort); err6 != nil { - log.Warnf("IPv6 PCP delete mapping failed: %v", err6) - } - } - - if err != nil { - return fmt.Errorf("delete mapping: %w", err) - } - return nil -} - -// CheckServerHealth sends an ANNOUNCE to verify the server is still responsive. -// Returns the current epoch and whether the server may have restarted (epoch state loss detected). -func (n *NAT) CheckServerHealth(ctx context.Context) (epoch uint32, serverRestarted bool, err error) { - epoch, err = n.client.Announce(ctx) - if err != nil { - return 0, false, fmt.Errorf("announce: %w", err) - } - return epoch, n.client.EpochStateLost(), nil -} - -// DiscoverPCP attempts to discover a PCP-capable gateway. -// Returns a NAT interface if PCP is supported, or an error otherwise. -// Discovers both IPv4 and IPv6 gateways when available. -func DiscoverPCP(ctx context.Context) (nat.NAT, error) { - gateway, localIP, err := getDefaultGateway() - if err != nil { - return nil, fmt.Errorf("get default gateway: %w", err) - } - - client := NewClient(gateway) - client.SetLocalIP(localIP) - if _, err := client.Announce(ctx); err != nil { - return nil, fmt.Errorf("PCP announce: %w", err) - } - - result := &NAT{client: client} - discoverIPv6(ctx, result) - - return result, nil -} - -func discoverIPv6(ctx context.Context, result *NAT) { - gateway6, localIP6, err := getDefaultGateway6() - if err != nil { - log.Debugf("IPv6 gateway discovery failed: %v", err) - return - } - - client6 := NewClient(gateway6) - client6.SetLocalIP(localIP6) - if _, err := client6.Announce(ctx); err != nil { - log.Debugf("PCP IPv6 announce failed: %v", err) - return - } - - addr, ok := netip.AddrFromSlice(localIP6) - if !ok { - log.Debugf("invalid IPv6 local IP: %v", localIP6) - return - } - result.mu.Lock() - result.client6 = client6 - result.localIP6 = addr - result.mu.Unlock() - log.Debugf("PCP IPv6 gateway discovered: %s (local: %s)", gateway6, localIP6) -} - -// getDefaultGateway returns the default IPv4 gateway and local IP using the system routing table. -func getDefaultGateway() (gateway net.IP, localIP net.IP, err error) { - router, err := netroute.New() - if err != nil { - return nil, nil, err - } - - dst := net.IPv4zero - if runtime.GOOS == "linux" || runtime.GOOS == "android" { - // go-netroute v0.4.0 rejects unspecified destinations client-side on Linux/Android. - // TODO: on android/ios, use platform APIs (ConnectivityManager.getLinkProperties / - // NWPathMonitor) when netlink-based lookup is restricted or unavailable. - dst = net.IPv4(0, 0, 0, 1) - } - _, gateway, localIP, err = router.Route(dst) - if err != nil { - return nil, nil, err - } - - if gateway == nil { - return nil, nil, nat.ErrNoNATFound - } - - return gateway, localIP, nil -} - -// getDefaultGateway6 returns the default IPv6 gateway IP address using the system routing table. -func getDefaultGateway6() (gateway net.IP, localIP net.IP, err error) { - router, err := netroute.New() - if err != nil { - return nil, nil, err - } - - dst := net.IPv6zero - if runtime.GOOS == "linux" || runtime.GOOS == "android" { - // ::2 - dst = net.IP{0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 2} - } - _, gateway, localIP, err = router.Route(dst) - if err != nil { - return nil, nil, err - } - - if gateway == nil { - return nil, nil, nat.ErrNoNATFound - } - - return gateway, localIP, nil -} diff --git a/client/internal/portforward/pcp/protocol.go b/client/internal/portforward/pcp/protocol.go deleted file mode 100644 index d81c50c8c..000000000 --- a/client/internal/portforward/pcp/protocol.go +++ /dev/null @@ -1,225 +0,0 @@ -// Package pcp implements the Port Control Protocol (RFC 6887). -// -// # Implemented Features -// -// - ANNOUNCE opcode: Discovers PCP server support -// - MAP opcode: Creates/deletes port mappings (IPv4 NAT) and firewall pinholes (IPv6) -// - Dual-stack: Simultaneous IPv4 and IPv6 support via separate clients -// - Nonce validation: Prevents response spoofing -// - Epoch tracking: Detects server restarts per Section 8.5 -// - RFC-compliant retry timing: 3s initial, exponential backoff to 1024s max (Section 8.1.1) -// -// # Not Implemented -// -// - PEER opcode: For outbound peer connections (not needed for inbound NAT traversal) -// - THIRD_PARTY option: For managing mappings on behalf of other devices -// - PREFER_FAILURE option: Requires exact external port or fail (IPv4 NAT only, not needed for IPv6 pinholing) -// - FILTER option: To restrict remote peer addresses -// -// These optional features are omitted because the primary use case is simple -// port forwarding for WireGuard, which only requires MAP with default behavior. -package pcp - -import ( - "encoding/binary" - "fmt" - "net/netip" -) - -const ( - // Version is the PCP protocol version (RFC 6887). - Version = 2 - - // Port is the standard PCP server port. - Port = 5351 - - // DefaultLifetime is the default requested mapping lifetime in seconds. - DefaultLifetime = 7200 // 2 hours - - // Header sizes - headerSize = 24 - mapPayloadSize = 36 - mapRequestSize = headerSize + mapPayloadSize // 60 bytes -) - -// Opcodes -const ( - OpAnnounce = 0 - OpMap = 1 - OpPeer = 2 - OpReply = 0x80 // OR'd with opcode in responses -) - -// Protocol numbers for MAP requests -const ( - ProtoUDP = 17 - ProtoTCP = 6 -) - -// Result codes (RFC 6887 Section 7.4) -const ( - ResultSuccess = 0 - ResultUnsuppVersion = 1 - ResultNotAuthorized = 2 - ResultMalformedRequest = 3 - ResultUnsuppOpcode = 4 - ResultUnsuppOption = 5 - ResultMalformedOption = 6 - ResultNetworkFailure = 7 - ResultNoResources = 8 - ResultUnsuppProtocol = 9 - ResultUserExQuota = 10 - ResultCannotProvideExt = 11 - ResultAddressMismatch = 12 - ResultExcessiveRemotePeers = 13 -) - -// ResultCodeString returns a human-readable string for a result code. -func ResultCodeString(code uint8) string { - switch code { - case ResultSuccess: - return "SUCCESS" - case ResultUnsuppVersion: - return "UNSUPP_VERSION" - case ResultNotAuthorized: - return "NOT_AUTHORIZED" - case ResultMalformedRequest: - return "MALFORMED_REQUEST" - case ResultUnsuppOpcode: - return "UNSUPP_OPCODE" - case ResultUnsuppOption: - return "UNSUPP_OPTION" - case ResultMalformedOption: - return "MALFORMED_OPTION" - case ResultNetworkFailure: - return "NETWORK_FAILURE" - case ResultNoResources: - return "NO_RESOURCES" - case ResultUnsuppProtocol: - return "UNSUPP_PROTOCOL" - case ResultUserExQuota: - return "USER_EX_QUOTA" - case ResultCannotProvideExt: - return "CANNOT_PROVIDE_EXTERNAL" - case ResultAddressMismatch: - return "ADDRESS_MISMATCH" - case ResultExcessiveRemotePeers: - return "EXCESSIVE_REMOTE_PEERS" - default: - return fmt.Sprintf("UNKNOWN(%d)", code) - } -} - -// Response represents a parsed PCP response header. -type Response struct { - Version uint8 - Opcode uint8 - ResultCode uint8 - Lifetime uint32 - Epoch uint32 -} - -// MapResponse contains the full response to a MAP request. -type MapResponse struct { - Response - Nonce [12]byte - Protocol uint8 - InternalPort uint16 - ExternalPort uint16 - ExternalIP netip.Addr -} - -// addrTo16 converts an address to its 16-byte IPv4-mapped IPv6 representation. -func addrTo16(addr netip.Addr) [16]byte { - if addr.Is4() { - return netip.AddrFrom4(addr.As4()).As16() - } - return addr.As16() -} - -// addrFrom16 extracts an address from a 16-byte representation, unmapping IPv4. -func addrFrom16(b [16]byte) netip.Addr { - return netip.AddrFrom16(b).Unmap() -} - -// buildAnnounceRequest creates a PCP ANNOUNCE request packet. -func buildAnnounceRequest(clientIP netip.Addr) []byte { - req := make([]byte, headerSize) - req[0] = Version - req[1] = OpAnnounce - mapped := addrTo16(clientIP) - copy(req[8:24], mapped[:]) - return req -} - -// buildMapRequest creates a PCP MAP request packet. -func buildMapRequest(clientIP netip.Addr, nonce [12]byte, protocol uint8, internalPort, suggestedExtPort uint16, suggestedExtIP netip.Addr, lifetime uint32) []byte { - req := make([]byte, mapRequestSize) - - // Header - req[0] = Version - req[1] = OpMap - binary.BigEndian.PutUint32(req[4:8], lifetime) - mapped := addrTo16(clientIP) - copy(req[8:24], mapped[:]) - - // MAP payload - copy(req[24:36], nonce[:]) - req[36] = protocol - binary.BigEndian.PutUint16(req[40:42], internalPort) - binary.BigEndian.PutUint16(req[42:44], suggestedExtPort) - if suggestedExtIP.IsValid() { - extMapped := addrTo16(suggestedExtIP) - copy(req[44:60], extMapped[:]) - } - - return req -} - -// parseResponse parses the common PCP response header. -func parseResponse(data []byte) (*Response, error) { - if len(data) < headerSize { - return nil, fmt.Errorf("response too short: %d bytes", len(data)) - } - - resp := &Response{ - Version: data[0], - Opcode: data[1], - ResultCode: data[3], // Byte 2 is reserved, byte 3 is result code (RFC 6887 §7.2) - Lifetime: binary.BigEndian.Uint32(data[4:8]), - Epoch: binary.BigEndian.Uint32(data[8:12]), - } - - if resp.Version != Version { - return nil, fmt.Errorf("unsupported PCP version: %d", resp.Version) - } - - if resp.Opcode&OpReply == 0 { - return nil, fmt.Errorf("response missing reply bit: opcode=0x%02x", resp.Opcode) - } - - return resp, nil -} - -// parseMapResponse parses a complete MAP response. -func parseMapResponse(data []byte) (*MapResponse, error) { - if len(data) < mapRequestSize { - return nil, fmt.Errorf("MAP response too short: %d bytes", len(data)) - } - - resp, err := parseResponse(data) - if err != nil { - return nil, fmt.Errorf("parse header: %w", err) - } - - mapResp := &MapResponse{ - Response: *resp, - Protocol: data[36], - InternalPort: binary.BigEndian.Uint16(data[40:42]), - ExternalPort: binary.BigEndian.Uint16(data[42:44]), - ExternalIP: addrFrom16([16]byte(data[44:60])), - } - copy(mapResp.Nonce[:], data[24:36]) - - return mapResp, nil -} diff --git a/client/internal/portforward/pinhole_test.go b/client/internal/portforward/pinhole_test.go new file mode 100644 index 000000000..46b07a9e7 --- /dev/null +++ b/client/internal/portforward/pinhole_test.go @@ -0,0 +1,116 @@ +//go:build !js + +package portforward + +import ( + "context" + "errors" + "strings" + "testing" + + "github.com/netbirdio/go-nat" + log "github.com/sirupsen/logrus" + "github.com/sirupsen/logrus/hooks/test" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// mockPinholeNAT is a gateway that also reports an IPv6 pinhole outcome, the +// shape a dual-stack gateway has. +type mockPinholeNAT struct { + *mockNAT + pinholeErr error +} + +func (m *mockPinholeNAT) IPv6PinholeError() error { + return m.pinholeErr +} + +func TestSetupLogsPinholeOutcome(t *testing.T) { + pinholeErr := errors.New("pcp ipv6: NOT_AUTHORIZED") + + tests := []struct { + name string + pinholeErr error + mappingErr error + wantLevel log.Level + wantText string + }{ + { + name: "an open pinhole is reported", + wantLevel: log.InfoLevel, + wantText: "IPv6 pinhole open", + }, + { + name: "a failed pinhole is reported without failing the mapping", + // The IPv4 mapping is what the caller asked for, so the pinhole + // failure surfaces only in the log. + pinholeErr: pinholeErr, + wantLevel: log.WarnLevel, + wantText: pinholeErr.Error(), + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + gateway := &mockPinholeNAT{mockNAT: newMockNAT(), pinholeErr: tt.pinholeErr} + hook := stubGatewayDiscovery(t, gateway) + + m := NewManager() + m.wgPort = 51820 + + _, mapping, err := m.setup(context.Background()) + + require.NoError(t, err) + require.NotNil(t, mapping) + + entry := findEntry(hook, tt.wantText) + require.NotNil(t, entry, "no log entry mentioning %q", tt.wantText) + assert.Equal(t, tt.wantLevel, entry.Level) + }) + } + + t.Run("a failed mapping reports no pinhole outcome", func(t *testing.T) { + // Nothing opened the pinhole, so whatever it currently reports says + // nothing about this attempt. + gateway := &mockPinholeNAT{mockNAT: newMockNAT()} + gateway.addMappingErr = errors.New("gateway refused") + hook := stubGatewayDiscovery(t, gateway) + + m := NewManager() + m.wgPort = 51820 + + _, _, err := m.setup(context.Background()) + + require.Error(t, err) + assert.Nil(t, findEntry(hook, "IPv6 pinhole")) + }) +} + +// stubGatewayDiscovery makes discovery return gateway and captures log output. +func stubGatewayDiscovery(t *testing.T, gateway nat.NAT) *test.Hook { + t.Helper() + + orig := discoverGateway + discoverGateway = func(context.Context) (nat.NAT, error) { return gateway, nil } + t.Cleanup(func() { discoverGateway = orig }) + + hook := test.NewGlobal() + origLevel := log.GetLevel() + log.SetLevel(log.DebugLevel) + t.Cleanup(func() { + hook.Reset() + log.SetLevel(origLevel) + }) + + return hook +} + +func findEntry(hook *test.Hook, substr string) *log.Entry { + for _, entry := range hook.AllEntries() { + if strings.Contains(entry.Message, substr) { + return entry + } + } + return nil +} diff --git a/client/internal/portforward/state.go b/client/internal/portforward/state.go index b1315cdc0..a21368e58 100644 --- a/client/internal/portforward/state.go +++ b/client/internal/portforward/state.go @@ -4,27 +4,94 @@ package portforward import ( "context" + "errors" "fmt" + "time" - "github.com/libp2p/go-nat" + "github.com/netbirdio/go-nat" + "github.com/netbirdio/go-nat/pcp" log "github.com/sirupsen/logrus" - - "github.com/netbirdio/netbird/client/internal/portforward/pcp" ) // discoverGateway is the function used for NAT gateway discovery. // It can be replaced in tests to avoid real network operations. -// Tries PCP first, then falls back to NAT-PMP/UPnP. var discoverGateway = defaultDiscoverGateway -func defaultDiscoverGateway(ctx context.Context) (nat.NAT, error) { - pcpGateway, err := pcp.DiscoverPCP(ctx) - if err == nil { - return pcpGateway, nil - } - log.Debugf("PCP discovery failed: %v, trying NAT-PMP/UPnP", err) +// pinholeDiscoveryTimeout is the slice of the discovery budget held back for +// the IPv6 pinhole probe. +// +// Sizing it is coarser than it looks: PCP retransmits on a 3s socket timeout +// and a 3s first backoff, so a second attempt needs about 9s. Anything from +// roughly 1s to 8s therefore buys exactly one attempt, and this only sets how +// long that attempt waits. A PCP server sits on the local link and answers in +// milliseconds, so 3s is margin rather than need, and the rest is left to +// gateway discovery, whose multicast SSDP search alone takes 5s. A probe lost +// to a dropped packet is retried by the next discovery round. +// +// It is a variable so tests can shorten it. +var pinholeDiscoveryTimeout = 3 * time.Second - return nat.DiscoverGateway(ctx) +// Discovery entry points, as variables so tests can drive the fallback without +// touching the network. +var ( + discoverNATGateway = nat.DiscoverGateway + + discoverPCPPinhole = func(ctx context.Context) (nat.NAT, error) { + pinhole, err := pcp.DiscoverPCP(ctx) + if err != nil { + return nil, err + } + return pinhole, nil + } +) + +// defaultDiscoverGateway finds a gateway that can make the WireGuard port +// reachable. DiscoverGateway prefers PCP for IPv4, races UPnP and NAT-PMP +// behind it, and attaches an IPv6 pinhole independently of which IPv4 protocol +// wins. +// +// It reports no gateway on a network offering only IPv6, having no IPv4 mapping +// to attach a pinhole to. Such a network still needs one: there is no +// translation to traverse, but the router drops inbound IPv6 until something +// opens it. Fall back to PCP alone, which yields a gateway holding just the +// pinhole. +func defaultDiscoverGateway(ctx context.Context) (nat.NAT, error) { + gatewayCtx, cancel := reserveForPinhole(ctx) + defer cancel() + + gateway, err := discoverNATGateway(gatewayCtx) + if err == nil { + return gateway, nil + } + if !errors.Is(err, nat.ErrNoNATFound) { + return nil, err + } + + pinhole, pinholeErr := discoverPCPPinhole(ctx) + if pinholeErr != nil { + log.Debugf("no IPv6 pinhole after %v: %v", err, pinholeErr) + return nil, err + } + + log.Infof("no IPv4 gateway, continuing with an IPv6 pinhole only") + return pinhole, nil +} + +// reserveForPinhole shortens ctx so that a pinhole probe still has time to run +// afterwards. Finding nothing takes gateway discovery everything it is given, +// so on the unshortened context the probe would start already expired. A budget +// too small to divide is left to gateway discovery, which is the likelier win. +func reserveForPinhole(ctx context.Context) (context.Context, context.CancelFunc) { + deadline, ok := ctx.Deadline() + if !ok { + return context.WithCancel(ctx) + } + + remaining := time.Until(deadline) + if remaining <= pinholeDiscoveryTimeout { + return context.WithCancel(ctx) + } + return context.WithTimeout(ctx, remaining-pinholeDiscoveryTimeout) } // State is persisted only for crash recovery cleanup diff --git a/client/internal/portforward/state_test.go b/client/internal/portforward/state_test.go new file mode 100644 index 000000000..8a584eecb --- /dev/null +++ b/client/internal/portforward/state_test.go @@ -0,0 +1,140 @@ +//go:build !js + +package portforward + +import ( + "context" + "errors" + "testing" + "time" + + "github.com/netbirdio/go-nat" + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// stubDiscovery replaces both discovery entry points for the duration of a +// test. gatewayDelay simulates gateway discovery spending everything it is +// given before reporting that it found nothing. +func stubDiscovery(t *testing.T, gateway nat.NAT, gatewayErr error, gatewayDelay time.Duration, pinhole nat.NAT, pinholeErr error) { + t.Helper() + + origGateway, origPinhole := discoverNATGateway, discoverPCPPinhole + discoverNATGateway = func(ctx context.Context) (nat.NAT, error) { + if gatewayDelay > 0 { + select { + case <-time.After(gatewayDelay): + case <-ctx.Done(): + } + } + return gateway, gatewayErr + } + discoverPCPPinhole = func(ctx context.Context) (nat.NAT, error) { + if err := ctx.Err(); err != nil { + return nil, err + } + return pinhole, pinholeErr + } + + t.Cleanup(func() { discoverNATGateway, discoverPCPPinhole = origGateway, origPinhole }) +} + +func TestDefaultDiscoverGateway(t *testing.T) { + ipv4Gateway := &mockNAT{natType: "PCP+PCPv6"} + ipv6Pinhole := &mockNAT{natType: "PCP"} + otherErr := errors.New("routing table unavailable") + + t.Run("an IPv4 gateway is used as is", func(t *testing.T) { + stubDiscovery(t, ipv4Gateway, nil, 0, ipv6Pinhole, nil) + + got, err := defaultDiscoverGateway(context.Background()) + + require.NoError(t, err) + assert.Same(t, ipv4Gateway, got) + }) + + t.Run("no IPv4 gateway still opens an IPv6 pinhole", func(t *testing.T) { + stubDiscovery(t, nil, nat.ErrNoNATFound, 0, ipv6Pinhole, nil) + + got, err := defaultDiscoverGateway(context.Background()) + + require.NoError(t, err) + assert.Same(t, ipv6Pinhole, got) + }) + + t.Run("no gateway and no pinhole reports the original failure", func(t *testing.T) { + stubDiscovery(t, nil, nat.ErrNoNATFound, 0, nil, errors.New("no IPv6 route")) + + got, err := defaultDiscoverGateway(context.Background()) + + assert.Nil(t, got) + assert.ErrorIs(t, err, nat.ErrNoNATFound, "the pinhole failure must not mask why no gateway was found") + }) + + t.Run("a failure other than no-gateway is reported as is", func(t *testing.T) { + stubDiscovery(t, nil, otherErr, 0, ipv6Pinhole, nil) + + got, err := defaultDiscoverGateway(context.Background()) + + assert.Nil(t, got) + assert.ErrorIs(t, err, otherErr) + }) + + t.Run("the pinhole survives gateway discovery using its whole budget", func(t *testing.T) { + // On one shared context the probe would start already expired, which is + // how this failed against a real gateway. + reserve := 50 * time.Millisecond + origReserve := pinholeDiscoveryTimeout + pinholeDiscoveryTimeout = reserve + t.Cleanup(func() { pinholeDiscoveryTimeout = origReserve }) + + budget := 4 * reserve + ctx, cancel := context.WithTimeout(context.Background(), budget) + defer cancel() + + stubDiscovery(t, nil, nat.ErrNoNATFound, budget, ipv6Pinhole, nil) + + got, err := defaultDiscoverGateway(ctx) + + require.NoError(t, err) + assert.Same(t, ipv6Pinhole, got) + }) +} + +func TestReserveForPinhole(t *testing.T) { + origReserve := pinholeDiscoveryTimeout + pinholeDiscoveryTimeout = time.Second + t.Cleanup(func() { pinholeDiscoveryTimeout = origReserve }) + + t.Run("a budget is divided", func(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second) + defer cancel() + + gatewayCtx, cancelGateway := reserveForPinhole(ctx) + defer cancelGateway() + + deadline, ok := gatewayCtx.Deadline() + require.True(t, ok) + assert.InDelta(t, 9*time.Second, time.Until(deadline), float64(500*time.Millisecond)) + }) + + t.Run("a budget too small to divide is left whole", func(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 500*time.Millisecond) + defer cancel() + + gatewayCtx, cancelGateway := reserveForPinhole(ctx) + defer cancelGateway() + + deadline, ok := gatewayCtx.Deadline() + require.True(t, ok) + assert.InDelta(t, 500*time.Millisecond, time.Until(deadline), float64(100*time.Millisecond)) + }) + + t.Run("no deadline stays unbounded", func(t *testing.T) { + gatewayCtx, cancelGateway := reserveForPinhole(context.Background()) + defer cancelGateway() + + _, ok := gatewayCtx.Deadline() + assert.False(t, ok) + }) +} diff --git a/client/internal/profilemanager/prefs.go b/client/internal/profilemanager/prefs.go new file mode 100644 index 000000000..5613b0be3 --- /dev/null +++ b/client/internal/profilemanager/prefs.go @@ -0,0 +1,130 @@ +package profilemanager + +import ( + "context" + "encoding/json" + "fmt" + "os" + "path/filepath" + "sync" + + "github.com/netbirdio/netbird/util" +) + +const prefsFileSuffix = ".prefs.json" + +var prefsMu sync.Mutex + +// Prefs is a namespaced per-profile preference store backed by a single JSON +// file next to the profile config; it is deleted together with the profile. +type Prefs struct { + path string +} + +// ProfilePrefs returns the preference store of the profile identified by id. +func (s *ServiceManager) ProfilePrefs(id ID, username string) (*Prefs, error) { + if !IsValidProfileFilenameStem(id) { + return nil, fmt.Errorf("invalid profile ID: %q", id) + } + if id == defaultProfileName { + return &Prefs{path: filepath.Join(filepath.Dir(DefaultConfigPath), id.String()+prefsFileSuffix)}, nil + } + configDir, err := s.getConfigDir(username) + if err != nil { + return nil, fmt.Errorf("get config directory for user %s: %w", username, err) + } + return &Prefs{path: filepath.Join(configDir, id.String()+prefsFileSuffix)}, nil +} + +// Get unmarshals the namespace section into v and reports whether it exists. +func (p *Prefs) Get(namespace string, v any) (bool, error) { + if namespace == "" { + return false, fmt.Errorf("empty prefs namespace") + } + + prefsMu.Lock() + defer prefsMu.Unlock() + + sections, err := readPrefsFile(p.path) + if err != nil { + return false, err + } + raw, ok := sections[namespace] + if !ok { + return false, nil + } + if err := json.Unmarshal(raw, v); err != nil { + return false, fmt.Errorf("decode prefs namespace %q: %w", namespace, err) + } + return true, nil +} + +// Put stores v as the namespace section, replacing any previous value. +func (p *Prefs) Put(namespace string, v any) error { + if namespace == "" { + return fmt.Errorf("empty prefs namespace") + } + raw, err := json.Marshal(v) + if err != nil { + return fmt.Errorf("encode prefs namespace %q: %w", namespace, err) + } + + prefsMu.Lock() + defer prefsMu.Unlock() + + sections, err := readPrefsFile(p.path) + if err != nil { + return err + } + sections[namespace] = raw + return writePrefsFile(p.path, sections) +} + +// Remove deletes the namespace section; a missing one is not an error. +func (p *Prefs) Remove(namespace string) error { + if namespace == "" { + return fmt.Errorf("empty prefs namespace") + } + + prefsMu.Lock() + defer prefsMu.Unlock() + + sections, err := readPrefsFile(p.path) + if err != nil { + return err + } + if _, ok := sections[namespace]; !ok { + return nil + } + delete(sections, namespace) + return writePrefsFile(p.path, sections) +} + +func removePrefsFile(path string) error { + prefsMu.Lock() + defer prefsMu.Unlock() + return os.Remove(path) +} + +func readPrefsFile(path string) (map[string]json.RawMessage, error) { + data, err := os.ReadFile(path) + if os.IsNotExist(err) { + return map[string]json.RawMessage{}, nil + } + if err != nil { + return nil, fmt.Errorf("read prefs: %w", err) + } + + sections := map[string]json.RawMessage{} + if err := json.Unmarshal(data, §ions); err != nil { + return nil, fmt.Errorf("decode prefs: %w", err) + } + return sections, nil +} + +func writePrefsFile(path string, sections map[string]json.RawMessage) error { + if err := util.WriteJsonWithRestrictedPermission(context.Background(), path, sections); err != nil { + return fmt.Errorf("write prefs: %w", err) + } + return nil +} diff --git a/client/internal/profilemanager/prefs_test.go b/client/internal/profilemanager/prefs_test.go new file mode 100644 index 000000000..692ade70f --- /dev/null +++ b/client/internal/profilemanager/prefs_test.go @@ -0,0 +1,138 @@ +package profilemanager + +import ( + "errors" + "os" + "path/filepath" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +type testPrefsSection struct { + Mode uint8 `json:"mode"` + Dest string `json:"dest"` +} + +func TestProfilePrefs_RoundTrip(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + created, err := sm.AddProfile("work", username) + require.NoError(t, err) + + prefs, err := sm.ProfilePrefs(created.ID, username) + require.NoError(t, err) + + require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 2, Dest: "/tmp/x"})) + require.NoError(t, prefs.Put("other", map[string]int{"n": 1})) + + var got testPrefsSection + found, err := prefs.Get("filedrop", &got) + require.NoError(t, err) + assert.True(t, found) + assert.Equal(t, testPrefsSection{Mode: 2, Dest: "/tmp/x"}, got) + + var other map[string]int + found, err = prefs.Get("other", &other) + require.NoError(t, err) + assert.True(t, found) + assert.Equal(t, map[string]int{"n": 1}, other) + }) +} + +func TestProfilePrefs_GetMissingNamespace(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + created, err := sm.AddProfile("work", username) + require.NoError(t, err) + + prefs, err := sm.ProfilePrefs(created.ID, username) + require.NoError(t, err) + + var got testPrefsSection + found, err := prefs.Get("filedrop", &got) + require.NoError(t, err) + assert.False(t, found) + }) +} + +func TestProfilePrefs_RemoveNamespace(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + created, err := sm.AddProfile("work", username) + require.NoError(t, err) + + prefs, err := sm.ProfilePrefs(created.ID, username) + require.NoError(t, err) + + require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 1})) + require.NoError(t, prefs.Put("other", map[string]int{"n": 1})) + require.NoError(t, prefs.Remove("filedrop")) + require.NoError(t, prefs.Remove("missing")) + + var got testPrefsSection + found, err := prefs.Get("filedrop", &got) + require.NoError(t, err) + assert.False(t, found) + + var other map[string]int + found, err = prefs.Get("other", &other) + require.NoError(t, err) + assert.True(t, found) + assert.Equal(t, map[string]int{"n": 1}, other) + }) +} + +func TestProfilePrefs_RejectsInvalidID(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + _, err := sm.ProfilePrefs("../escape", username) + assert.Error(t, err) + }) +} + +func TestProfilePrefs_RejectsEmptyNamespace(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + created, err := sm.AddProfile("work", username) + require.NoError(t, err) + + prefs, err := sm.ProfilePrefs(created.ID, username) + require.NoError(t, err) + + _, err = prefs.Get("", &testPrefsSection{}) + assert.Error(t, err) + assert.Error(t, prefs.Put("", testPrefsSection{})) + assert.Error(t, prefs.Remove("")) + }) +} + +func TestProfilePrefs_DefaultProfile(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + prefs, err := sm.ProfilePrefs(defaultProfileName, username) + require.NoError(t, err) + + require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 1})) + + expected := filepath.Join(filepath.Dir(DefaultConfigPath), "default"+prefsFileSuffix) + _, err = os.Stat(expected) + require.NoError(t, err) + }) +} + +func TestRemoveProfile_DeletesPrefsFile(t *testing.T) { + withTestSM(t, func(sm *ServiceManager, username string) { + created, err := sm.AddProfile("work", username) + require.NoError(t, err) + + prefs, err := sm.ProfilePrefs(created.ID, username) + require.NoError(t, err) + require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 2})) + + configDir, err := sm.getConfigDir(username) + require.NoError(t, err) + prefsPath := filepath.Join(configDir, created.ID.String()+prefsFileSuffix) + _, err = os.Stat(prefsPath) + require.NoError(t, err) + + require.NoError(t, sm.RemoveProfile(created.ID, username)) + _, err = os.Stat(prefsPath) + assert.True(t, errors.Is(err, os.ErrNotExist), "prefs file should be removed") + }) +} diff --git a/client/internal/profilemanager/service.go b/client/internal/profilemanager/service.go index 696a60310..ec287f01a 100644 --- a/client/internal/profilemanager/service.go +++ b/client/internal/profilemanager/service.go @@ -420,6 +420,11 @@ func (s *ServiceManager) RemoveProfile(id ID, username string) error { log.Warnf("failed to remove profile state file %s: %v", stateFile, err) } + prefsFile := filepath.Join(filepath.Dir(target.Path), id.String()+prefsFileSuffix) + if err := removePrefsFile(prefsFile); err != nil && !os.IsNotExist(err) { + log.Warnf("failed to remove profile prefs file %s: %v", prefsFile, err) + } + return nil } diff --git a/client/internal/profilemanager/state.go b/client/internal/profilemanager/state.go index fcd1c384c..ddb5dd056 100644 --- a/client/internal/profilemanager/state.go +++ b/client/internal/profilemanager/state.go @@ -87,9 +87,10 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error { // RemoveProfileState deletes the per-profile state file (which holds the // account email used for the SSO login hint and the UI display). Called after -// a successful logout so a logged-out profile no longer shows a stale account -// email. The state file only stores the email, so deleting it is equivalent to -// clearing it; the next SSO login recreates it. A missing file is not an error. +// profile removal; logout keeps the file so the next login can pass the email +// as the login_hint. The state file only stores the email, so deleting it is +// equivalent to clearing it; the next SSO login recreates it. A missing file +// is not an error. func (pm *ProfileManager) RemoveProfileState(profileName string) error { configDir, err := getConfigDir() if err != nil { diff --git a/client/internal/routemanager/ipfwdstate/ipfwdstate.go b/client/internal/routemanager/ipfwdstate/ipfwdstate.go index 2be1c2ae7..3d571e16b 100644 --- a/client/internal/routemanager/ipfwdstate/ipfwdstate.go +++ b/client/internal/routemanager/ipfwdstate/ipfwdstate.go @@ -2,54 +2,183 @@ package ipfwdstate import ( "fmt" + "sync" log "github.com/sirupsen/logrus" "github.com/netbirdio/netbird/client/internal/routemanager/systemops" ) -// IPForwardingState is a struct that keeps track of the IP forwarding state. -// todo: read initial state of the IP forwarding from the system and reset the state based on it. -// todo: separate v4/v6 forwarding state, since the sysctls are independent -// (net.ipv4.ip_forward vs net.ipv6.conf.all.forwarding). Currently the nftables -// manager shares one instance between both routers, which works only because -// EnableIPForwarding enables both sysctls in a single call. +// IPForwardingState tracks v4 and v6 IP-forwarding sysctl enables with +// independent refcounts so a v4-only routing setup doesn't flip v6 sysctls. type IPForwardingState struct { - enabledCounter int + mu sync.Mutex + + v4Count int + v6Count int + + // routingV4/routingV6 track whether the routing path currently holds a + // reference, so repeated EnableRouting calls (one per network-map update) + // hold at most one reference per family and an unpaired DisableRouting + // can't release references held by DNAT rules. + routingV4 bool + routingV6 bool + + wgIfaceName string + v6Saved map[string]int } -func NewIPForwardingState() *IPForwardingState { - return &IPForwardingState{} +// NewIPForwardingState returns a state tracker for the IP-forwarding sysctls. +// wgIfaceName is excluded from the per-interface accept_ra handling. +func NewIPForwardingState(wgIfaceName string) *IPForwardingState { + return &IPForwardingState{wgIfaceName: wgIfaceName} } -func (f *IPForwardingState) RequestForwarding() error { - if f.enabledCounter != 0 { - f.enabledCounter++ +// Counts returns the current v4 and v6 refcounts. Intended for diagnostics +// and tests. +func (f *IPForwardingState) Counts() (v4, v6 int) { + f.mu.Lock() + defer f.mu.Unlock() + return f.v4Count, f.v6Count +} + +// RequestRouting takes the forwarding references for the routing path. It is +// idempotent: while routing already holds a reference, further calls don't +// increment the refcounts, and a v4-only request releases a previously held v6 +// reference. A v6 sysctl failure is logged and not returned so it can't take +// down v4 routing (the sysctl may be unwritable, e.g. read-only /proc/sys or +// IPv6 disabled on the kernel command line); v6 is retried on the next call. +func (f *IPForwardingState) RequestRouting(v6 bool) error { + f.mu.Lock() + defer f.mu.Unlock() + + if !f.routingV4 { + if err := f.requestV4(); err != nil { + return err + } + f.routingV4 = true + } + + if !v6 { + if !f.routingV6 { + return nil + } + f.routingV6 = false + return f.releaseV6() + } + + if f.routingV6 { return nil } - - if err := systemops.EnableIPForwarding(); err != nil { - return fmt.Errorf("failed to enable IP forwarding with sysctl: %w", err) + if err := f.requestV6(); err != nil { + log.Warnf("enable IPv6 forwarding for routing: %v", err) + return nil } - f.enabledCounter = 1 - log.Info("IP forwarding enabled") - + f.routingV6 = true return nil } -func (f *IPForwardingState) ReleaseForwarding() error { - if f.enabledCounter == 0 { - return nil +// ReleaseRouting releases the references RequestRouting holds. Calls without a +// held reference are no-ops. +func (f *IPForwardingState) ReleaseRouting() error { + f.mu.Lock() + defer f.mu.Unlock() + + if f.routingV4 { + f.routingV4 = false + f.releaseV4() } - - if f.enabledCounter > 1 { - f.enabledCounter-- - return nil + if f.routingV6 { + f.routingV6 = false + return f.releaseV6() } - - // if failed to disable IP forwarding we anyway decrement the counter - f.enabledCounter = 0 - - // todo call systemops.DisableIPForwarding() + return nil +} + +// RequestForwarding enables the family's forwarding sysctl on first request. +func (f *IPForwardingState) RequestForwarding(v6 bool) error { + f.mu.Lock() + defer f.mu.Unlock() + + if v6 { + return f.requestV6() + } + return f.requestV4() +} + +// ReleaseForwarding decrements the family counter. The last v6 release restores +// what enable captured. v4 stays on: net.ipv4.ip_forward is co-owned by other +// tooling (docker, k8s, libvirt). +func (f *IPForwardingState) ReleaseForwarding(v6 bool) error { + f.mu.Lock() + defer f.mu.Unlock() + + if v6 { + return f.releaseV6() + } + f.releaseV4() + return nil +} + +func (f *IPForwardingState) requestV4() error { + if f.v4Count == 0 { + if err := systemops.EnableV4IPForwarding(); err != nil { + return fmt.Errorf("enable IPv4 forwarding: %w", err) + } + log.Info("IPv4 forwarding enabled") + } + f.v4Count++ + return nil +} + +func (f *IPForwardingState) releaseV4() { + if f.v4Count > 0 { + f.v4Count-- + } +} + +func (f *IPForwardingState) requestV6() error { + if f.v6Count == 0 { + saved, err := systemops.EnableV6IPForwarding(f.wgIfaceName) + if err != nil { + if rerr := systemops.DisableV6IPForwarding(saved); rerr != nil { + log.Warnf("rollback partial v6 sysctls: %v", rerr) + } + return fmt.Errorf("enable IPv6 forwarding: %w", err) + } + // A failed restore on a previous release keeps its saved values; those + // are the true originals, so keep them over what this enable captured. + if f.v6Saved == nil { + f.v6Saved = saved + } else { + for k, v := range saved { + if _, ok := f.v6Saved[k]; !ok { + f.v6Saved[k] = v + } + } + } + log.Info("IPv6 forwarding enabled") + } + f.v6Count++ + return nil +} + +func (f *IPForwardingState) releaseV6() error { + if f.v6Count == 0 { + return nil + } + f.v6Count-- + if f.v6Count > 0 { + return nil + } + + // Keep the saved values on failure so a later release or enable/release + // cycle can still restore them; re-restoring an already-restored key is a + // no-op since the sysctl already holds the desired value. + if err := systemops.DisableV6IPForwarding(f.v6Saved); err != nil { + return fmt.Errorf("disable IPv6 forwarding: %w", err) + } + f.v6Saved = nil + log.Info("IPv6 forwarding disabled") return nil } diff --git a/client/internal/routemanager/ipfwdstate/ipfwdstate_privileged_linux_test.go b/client/internal/routemanager/ipfwdstate/ipfwdstate_privileged_linux_test.go new file mode 100644 index 000000000..b4615ff02 --- /dev/null +++ b/client/internal/routemanager/ipfwdstate/ipfwdstate_privileged_linux_test.go @@ -0,0 +1,39 @@ +//go:build privileged + +package ipfwdstate + +import ( + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// TestRequestRoutingV6ToV4Transition verifies that a v4-only routing request +// releases a previously held routing-owned v6 reference without touching +// references held by DNAT rules. +func TestRequestRoutingV6ToV4Transition(t *testing.T) { + f := NewIPForwardingState("wt-fwd-test") + + require.NoError(t, f.RequestRouting(true), "request routing with v6") + v4, v6 := f.Counts() + assert.Equal(t, 1, v4, "v4 reference held") + assert.Equal(t, 1, v6, "v6 reference held") + + require.NoError(t, f.RequestRouting(false), "request routing v4-only") + v4, v6 = f.Counts() + assert.Equal(t, 1, v4, "v4 reference kept") + assert.Equal(t, 0, v6, "routing-owned v6 reference released") + + // A DNAT-held reference survives a v4-only routing request. + require.NoError(t, f.RequestForwarding(true), "dnat v6 reference") + require.NoError(t, f.RequestRouting(false), "repeat v4-only request") + _, v6 = f.Counts() + assert.Equal(t, 1, v6, "dnat-held v6 reference survives") + require.NoError(t, f.ReleaseForwarding(true), "release dnat v6 reference") + + require.NoError(t, f.ReleaseRouting(), "release routing") + v4, v6 = f.Counts() + assert.Equal(t, 0, v4, "all v4 references released") + assert.Equal(t, 0, v6, "all v6 references released") +} diff --git a/client/internal/routemanager/sysctl/sysctl_linux.go b/client/internal/routemanager/sysctl/sysctl_linux.go index 46b7c9fb7..bb131c691 100644 --- a/client/internal/routemanager/sysctl/sysctl_linux.go +++ b/client/internal/routemanager/sysctl/sysctl_linux.go @@ -58,11 +58,7 @@ func Setup(wgIface iface) (map[string]int, error) { continue } - // Escape '%' and '.' so they survive the dot-to-slash conversion in Set() - safeName := strings.ReplaceAll(intf.Name, "%", percentEscape) - safeName = strings.ReplaceAll(safeName, ".", dotEscape) - - i := fmt.Sprintf(rpFilterInterfacePath, safeName) + i := fmt.Sprintf(rpFilterInterfacePath, EscapeInterfaceName(intf.Name)) oldVal, err := Set(i, 2, true) if err != nil { result = multierror.Append(result, err) @@ -74,6 +70,13 @@ func Setup(wgIface iface) (map[string]int, error) { return keys, nberrors.FormatErrorOrNil(result) } +// EscapeInterfaceName escapes '%' and '.' in an interface name (e.g. VLANs +// like eth0.100) so the name survives the dot-to-slash conversion in Set. +func EscapeInterfaceName(name string) string { + safe := strings.ReplaceAll(name, "%", percentEscape) + return strings.ReplaceAll(safe, ".", dotEscape) +} + // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) { path := strings.ReplaceAll(key, ".", "/") diff --git a/client/internal/routemanager/systemops/routeselection_windows_test.go b/client/internal/routemanager/systemops/routeselection_windows_test.go new file mode 100644 index 000000000..108338dd9 --- /dev/null +++ b/client/internal/routemanager/systemops/routeselection_windows_test.go @@ -0,0 +1,82 @@ +//go:build windows + +package systemops + +import ( + "math" + "testing" + + "github.com/stretchr/testify/assert" +) + +func TestSortRouteCandidates(t *testing.T) { + tests := []struct { + name string + candidates []candidateRoute + wantOrder []uint32 + }{ + { + name: "longest prefix wins over metrics", + candidates: []candidateRoute{ + {interfaceIndex: 1, prefixLength: 0, routeMetric: 0, interfaceMetric: 5}, + {interfaceIndex: 2, prefixLength: 24, routeMetric: 100, interfaceMetric: 50}, + }, + wantOrder: []uint32{2, 1}, + }, + { + // Windows ranks equal-length prefixes by route metric + interface metric, + // so a higher route metric on a low metric interface can still win. + name: "combined metric beats route metric alone", + candidates: []candidateRoute{ + {interfaceIndex: 8, prefixLength: 0, routeMetric: 0, interfaceMetric: 100}, + {interfaceIndex: 5, prefixLength: 0, routeMetric: 10, interfaceMetric: 5}, + }, + wantOrder: []uint32{5, 8}, + }, + { + name: "lower combined metric wins", + candidates: []candidateRoute{ + {interfaceIndex: 5, prefixLength: 0, routeMetric: 300, interfaceMetric: 5}, + {interfaceIndex: 8, prefixLength: 0, routeMetric: 0, interfaceMetric: 100}, + }, + wantOrder: []uint32{8, 5}, + }, + { + name: "equal combined metric falls back to route metric", + candidates: []candidateRoute{ + {interfaceIndex: 1, prefixLength: 0, routeMetric: 20, interfaceMetric: 10}, + {interfaceIndex: 2, prefixLength: 0, routeMetric: 5, interfaceMetric: 25}, + }, + wantOrder: []uint32{2, 1}, + }, + { + // The metrics are uint32 on the Windows side, so the sum must not wrap. + name: "combined metric beyond the uint32 range", + candidates: []candidateRoute{ + {interfaceIndex: 1, prefixLength: 0, routeMetric: math.MaxUint32, interfaceMetric: 5}, + {interfaceIndex: 2, prefixLength: 0, routeMetric: math.MaxUint32 - 10, interfaceMetric: 5}, + }, + wantOrder: []uint32{2, 1}, + }, + { + name: "unknown interface metric ranks on route metric only", + candidates: []candidateRoute{ + {interfaceIndex: 1, prefixLength: 0, routeMetric: 30, interfaceMetric: -1}, + {interfaceIndex: 2, prefixLength: 0, routeMetric: 5, interfaceMetric: 10}, + }, + wantOrder: []uint32{2, 1}, + }, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + sortRouteCandidates(tt.candidates) + + got := make([]uint32, 0, len(tt.candidates)) + for _, c := range tt.candidates { + got = append(got, c.interfaceIndex) + } + assert.Equal(t, tt.wantOrder, got) + }) + } +} diff --git a/client/internal/routemanager/systemops/systemops_android.go b/client/internal/routemanager/systemops/systemops_android.go index 7cb8dae93..97b4ed8ec 100644 --- a/client/internal/routemanager/systemops/systemops_android.go +++ b/client/internal/routemanager/systemops/systemops_android.go @@ -32,8 +32,17 @@ func (r *SysOps) removeFromRouteTable(netip.Prefix, Nexthop) error { return nil } -func EnableIPForwarding() error { - log.Infof("Enable IP forwarding is not implemented on %s", runtime.GOOS) +func EnableV4IPForwarding() error { + log.Infof("Enable IPv4 forwarding is not implemented on %s", runtime.GOOS) + return nil +} + +func EnableV6IPForwarding(string) (map[string]int, error) { + log.Infof("Enable IPv6 forwarding is not implemented on %s", runtime.GOOS) + return map[string]int{}, nil +} + +func DisableV6IPForwarding(map[string]int) error { return nil } diff --git a/client/internal/routemanager/systemops/systemops_ios.go b/client/internal/routemanager/systemops/systemops_ios.go index 99a363371..0cccd4962 100644 --- a/client/internal/routemanager/systemops/systemops_ios.go +++ b/client/internal/routemanager/systemops/systemops_ios.go @@ -58,8 +58,17 @@ func (r *SysOps) removeFromRouteTable(netip.Prefix, Nexthop) error { return nil } -func EnableIPForwarding() error { - log.Infof("Enable IP forwarding is not implemented on %s", runtime.GOOS) +func EnableV4IPForwarding() error { + log.Infof("Enable IPv4 forwarding is not implemented on %s", runtime.GOOS) + return nil +} + +func EnableV6IPForwarding(string) (map[string]int, error) { + log.Infof("Enable IPv6 forwarding is not implemented on %s", runtime.GOOS) + return map[string]int{}, nil +} + +func DisableV6IPForwarding(map[string]int) error { return nil } diff --git a/client/internal/routemanager/systemops/systemops_linux.go b/client/internal/routemanager/systemops/systemops_linux.go index 8c6b7d9a9..7d608d886 100644 --- a/client/internal/routemanager/systemops/systemops_linux.go +++ b/client/internal/routemanager/systemops/systemops_linux.go @@ -763,13 +763,10 @@ func flushRoutes(tableID, family int) error { return nberrors.FormatErrorOrNil(result) } -func EnableIPForwarding() error { +func EnableV4IPForwarding() error { if _, err := sysctl.Set(ipv4ForwardingPath, 1, false); err != nil { return err } - if _, err := sysctl.Set(ipv6ForwardingPath, 1, false); err != nil { - log.Warnf("failed to enable IPv6 forwarding: %v", err) - } return nil } diff --git a/client/internal/routemanager/systemops/systemops_nonlinux.go b/client/internal/routemanager/systemops/systemops_nonlinux.go index 016a62ebd..837ac0cd2 100644 --- a/client/internal/routemanager/systemops/systemops_nonlinux.go +++ b/client/internal/routemanager/systemops/systemops_nonlinux.go @@ -43,8 +43,17 @@ func (r *SysOps) RemoveVPNRoute(prefix netip.Prefix, intf *net.Interface) error return r.genericRemoveVPNRoute(prefix, intf) } -func EnableIPForwarding() error { - log.Infof("Enable IP forwarding is not implemented on %s", runtime.GOOS) +func EnableV4IPForwarding() error { + log.Infof("Enable IPv4 forwarding is not implemented on %s", runtime.GOOS) + return nil +} + +func EnableV6IPForwarding(string) (map[string]int, error) { + log.Infof("Enable IPv6 forwarding is not implemented on %s", runtime.GOOS) + return map[string]int{}, nil +} + +func DisableV6IPForwarding(map[string]int) error { return nil } diff --git a/client/internal/routemanager/systemops/systemops_windows.go b/client/internal/routemanager/systemops/systemops_windows.go index 7bce6af80..47d556cf6 100644 --- a/client/internal/routemanager/systemops/systemops_windows.go +++ b/client/internal/routemanager/systemops/systemops_windows.go @@ -882,26 +882,40 @@ func getInterfaceMetric(interfaceIndex uint32, family int16) int { return int(ipInterfaceRow.Metric) } -// sortRouteCandidates sorts route candidates by priority: prefix length -> route metric -> interface metric +// sortRouteCandidates sorts route candidates by priority: prefix length -> combined metric -> route metric. +// Windows prefers the longest matching prefix and, among prefixes of the same length, the lowest metric, see +// https://learn.microsoft.com/en-us/windows-hardware/customize/desktop/unattend/microsoft-windows-tcpip-interfaces-interface-routes-route-metric func sortRouteCandidates(candidates []candidateRoute) { sort.Slice(candidates, func(i, j int) bool { if candidates[i].prefixLength != candidates[j].prefixLength { return candidates[i].prefixLength > candidates[j].prefixLength } - if candidates[i].routeMetric != candidates[j].routeMetric { - return candidates[i].routeMetric < candidates[j].routeMetric + mi, mj := combinedMetric(candidates[i]), combinedMetric(candidates[j]) + if mi != mj { + return mi < mj } - return candidates[i].interfaceMetric < candidates[j].interfaceMetric + return candidates[i].routeMetric < candidates[j].routeMetric }) } +// combinedMetric returns the effective metric Windows uses to rank routes with an equal prefix length: +// the sum of the route metric and the metric of the interface the route is on, see +// https://learn.microsoft.com/en-us/windows-server/networking/technologies/network-subsystem/net-sub-interface-metric +// An unknown interface metric contributes nothing. +func combinedMetric(candidate candidateRoute) uint64 { + if candidate.interfaceMetric < 0 { + return uint64(candidate.routeMetric) + } + return uint64(candidate.routeMetric) + uint64(candidate.interfaceMetric) +} + // GetBestInterface finds the best interface for reaching a destination, // excluding the VPN interface to avoid routing loops. // // Route selection priority: // 1. Longest prefix match (most specific route) -// 2. Lowest route metric -// 3. Lowest interface metric +// 2. Lowest combined metric (route metric + interface metric) +// 3. Lowest route metric. func GetBestInterface(dest netip.Addr, vpnIntf string) (*net.Interface, error) { var skipInterfaceIndex int if vpnIntf != "" { @@ -925,7 +939,6 @@ func GetBestInterface(dest netip.Addr, vpnIntf string) (*net.Interface, error) { return nil, fmt.Errorf("no route to %s", dest) } - // Sort routes: prefix length -> route metric -> interface metric sortRouteCandidates(candidates) for _, candidate := range candidates { diff --git a/client/internal/routemanager/systemops/v6forwarding_linux.go b/client/internal/routemanager/systemops/v6forwarding_linux.go new file mode 100644 index 000000000..c1e0d4588 --- /dev/null +++ b/client/internal/routemanager/systemops/v6forwarding_linux.go @@ -0,0 +1,92 @@ +//go:build !android + +package systemops + +import ( + "fmt" + "net" + "os" + + "github.com/hashicorp/go-multierror" + log "github.com/sirupsen/logrus" + + nberrors "github.com/netbirdio/netbird/client/errors" + "github.com/netbirdio/netbird/client/internal/routemanager/sysctl" +) + +const ( + // 1 (default) accepts RAs only while forwarding is off; 2 keeps RA + // acceptance on regardless, so RA-installed host defaults survive our + // v6 forwarding flip. + acceptRAInterfacePath = "net.ipv6.conf.%s.accept_ra" + acceptRADefaultPath = "net.ipv6.conf.default.accept_ra" + acceptRAProcPathFormat = "/proc/sys/net/ipv6/conf/%s/accept_ra" +) + +// EnableV6IPForwarding bumps accept_ra=2 on host v6 interfaces before flipping +// forwarding=1, so RA-installed host defaults survive. Returns the prior values +// of sysctls we actually changed; entries already at the target are omitted. +func EnableV6IPForwarding(wgIfaceName string) (map[string]int, error) { + saved := map[string]int{} + bumpAcceptRA(saved, wgIfaceName) + + oldVal, err := sysctl.Set(ipv6ForwardingPath, 1, false) + if err != nil { + return saved, err + } + if oldVal != 1 { + saved[ipv6ForwardingPath] = oldVal + } + return saved, nil +} + +// DisableV6IPForwarding restores what EnableV6IPForwarding captured. +func DisableV6IPForwarding(saved map[string]int) error { + var result *multierror.Error + for key, value := range saved { + if _, err := sysctl.Set(key, value, false); err != nil { + result = multierror.Append(result, fmt.Errorf("restore %s: %w", key, err)) + } + } + return nberrors.FormatErrorOrNil(result) +} + +func bumpAcceptRA(saved map[string]int, wgIfaceName string) { + // Also bump conf.default so interfaces created while forwarding is on + // (hotplug, new Wi-Fi/dock) inherit accept_ra=2 and keep accepting RAs. + bumpAcceptRAKey(saved, acceptRADefaultPath) + + interfaces, err := net.Interfaces() + if err != nil { + log.Warnf("list interfaces for accept_ra: %v", err) + return + } + for _, intf := range interfaces { + if intf.Name == "lo" || intf.Name == wgIfaceName { + continue + } + bumpAcceptRAForInterface(saved, intf.Name) + } +} + +func bumpAcceptRAForInterface(saved map[string]int, name string) { + // Build procfs path from name, not the dotted key: VLAN names like eth0.100. + if _, err := os.Stat(fmt.Sprintf(acceptRAProcPathFormat, name)); err != nil { + return + } + bumpAcceptRAKey(saved, fmt.Sprintf(acceptRAInterfacePath, sysctl.EscapeInterfaceName(name))) +} + +func bumpAcceptRAKey(saved map[string]int, key string) { + // onlyIfOne=true: leave admin overrides (0, 2) alone. + oldVal, err := sysctl.Set(key, 2, true) + if err != nil { + log.Warnf("bump %s: %v", key, err) + return + } + // With onlyIfOne, a write only happened when the old value was 1; values + // left untouched (0, 2) must not be recorded for restore. + if oldVal == 1 { + saved[key] = oldVal + } +} diff --git a/client/internal/routemanager/systemops/v6route_linux_test.go b/client/internal/routemanager/systemops/v6route_linux_test.go index 449d4cbd2..d8c0012d1 100644 --- a/client/internal/routemanager/systemops/v6route_linux_test.go +++ b/client/internal/routemanager/systemops/v6route_linux_test.go @@ -5,6 +5,7 @@ package systemops import ( "errors" "net" + "net/netip" "syscall" "testing" @@ -29,6 +30,7 @@ func ensureIPv6DefaultRoute(t *testing.T) { } if err := netlink.RouteAdd(route); err != nil { if errors.Is(err, syscall.EEXIST) { + requireUsableIPv6Nexthop(t) return } t.Skipf("install IPv6 fallback default route: %v", err) @@ -38,4 +40,36 @@ func ensureIPv6DefaultRoute(t *testing.T) { t.Logf("delete IPv6 fallback default route: %v", err) } }) + + requireUsableIPv6Nexthop(t) +} + +// requireUsableIPv6Nexthop skips the test unless the resolved IPv6 default +// nexthop can actually carry a route. Installing the default route succeeding +// does not imply the kernel accepts it as a nexthop for a concrete prefix. +func requireUsableIPv6Nexthop(t *testing.T) { + t.Helper() + + nexthop, err := GetNextHop(netip.IPv6Unspecified()) + if err != nil { + t.Skipf("resolve IPv6 default nexthop: %v", err) + } + + probe := &netlink.Route{ + Scope: netlink.SCOPE_UNIVERSE, + Table: syscall.RT_TABLE_MAIN, + Family: netlink.FAMILY_V6, + Dst: &net.IPNet{IP: net.ParseIP("100::64"), Mask: net.CIDRMask(128, 128)}, + } + require.NoError(t, addNextHop(nexthop, probe), "build IPv6 probe route") + + switch err := netlink.RouteAdd(probe); { + case err == nil: + if err := netlink.RouteDel(probe); err != nil && !errors.Is(err, syscall.ESRCH) { + t.Logf("delete IPv6 probe route: %v", err) + } + case errors.Is(err, syscall.EEXIST): + default: + t.Skipf("IPv6 nexthop %s unusable for route installation: %v", nexthop, err) + } } diff --git a/client/internal/sleep/service.go b/client/internal/sleep/service.go index 196a33f52..93691c4c7 100644 --- a/client/internal/sleep/service.go +++ b/client/internal/sleep/service.go @@ -18,8 +18,8 @@ type Service struct { } func New() (*Service, error) { - d, err := NewDetector() - if err != nil { + d, err := NewDetector() //nolint:staticcheck + if err != nil { //nolint:staticcheck // always errors on platforms without a sleep detector return nil, err } diff --git a/client/internal/updater/installer/doc.go b/client/internal/updater/installer/doc.go index 0a60454bb..11b0512ac 100644 --- a/client/internal/updater/installer/doc.go +++ b/client/internal/updater/installer/doc.go @@ -37,23 +37,32 @@ // Updater Process (Setup): // // 1. Receives parameters from service via command-line arguments -// 2. Runs installer with appropriate silent/quiet flags: +// 2. Terminates the UI so the installer does not have to replace a locked image +// file, which would otherwise leave the install needing a reboot +// 3. Runs installer with appropriate silent/quiet flags: // - Windows EXE: installer.exe /S -// - Windows MSI: msiexec.exe /i installer.msi /quiet /qn /l*v msi.log +// - Windows MSI: msiexec.exe /i installer.msi /qn /norestart REBOOT=ReallySuppress /l*v msi.log // - macOS PKG: installer -pkg installer.pkg -target / // - macOS Homebrew: brew upgrade netbirdio/tap/netbird -// 3. Installer terminates daemon and UI processes -// 4. Installer replaces binaries with new version -// 5. Updater waits for installer to complete -// 6. Updater restarts daemon: +// 4. Installer terminates the daemon +// 5. Installer replaces binaries with new version +// 6. Updater waits for installer to complete. On Windows, MSI exit codes 3010 +// (ERROR_SUCCESS_REBOOT_REQUIRED) and 1641 (ERROR_SUCCESS_REBOOT_INITIATED) +// are a pending-reboot outcome, not a failure: the install succeeded, but +// some files are only replaced on the next restart (the reboot itself is +// suppressed via /norestart and REBOOT=ReallySuppress), and the flow +// continues as on success +// 7. Updater restarts daemon: // - Windows: netbird.exe service start // - macOS/Linux: netbird service start -// 7. Updater restarts UI: -// - Windows: Launches netbird-ui.exe as active console user using CreateProcessAsUser +// 8. Updater restarts UI: +// - Windows: Launches netbird-ui.exe using CreateProcessAsUser in every +// session it was terminated in, falling back to the active console session // - macOS: Uses launchctl asuser to launch NetBird.app for console user // - Linux: Not implemented (UI typically auto-starts) -// 8. Updater writes result.json with success/error status -// 9. Updater process exits +// 9. Updater writes result.json with success/error status (a pending reboot is +// recorded as success) +// 10. Updater process exits // // # Result Communication // diff --git a/client/internal/updater/installer/installer_common.go b/client/internal/updater/installer/installer_common.go index 8e44bee82..17566f7de 100644 --- a/client/internal/updater/installer/installer_common.go +++ b/client/internal/updater/installer/installer_common.go @@ -42,6 +42,9 @@ func NewWithDir(tempDir string) *Installer { // This will run by the original service process func (u *Installer) RunInstallation(ctx context.Context, targetVersion string) (err error) { resultHandler := NewResultHandler(u.tempDir) + if err := resultHandler.ClearStaleResult(); err != nil { + log.Warnf("clear stale installer result: %v", err) + } defer func() { if err != nil { diff --git a/client/internal/updater/installer/installer_run_windows.go b/client/internal/updater/installer/installer_run_windows.go index 70c7e32cf..b2ecf3299 100644 --- a/client/internal/updater/installer/installer_run_windows.go +++ b/client/internal/updater/installer/installer_run_windows.go @@ -2,6 +2,7 @@ package installer import ( "context" + "errors" "fmt" "os" "os/exec" @@ -22,6 +23,12 @@ const ( msiLogFile = "msi.log" + // ERROR_SUCCESS_REBOOT_REQUIRED and ERROR_SUCCESS_REBOOT_INITIATED + msiRebootRequired = 3010 + msiRebootInitiated = 1641 + + processExitWait = 10 * time.Second + msiDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.msi" exeDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.exe" ) @@ -38,6 +45,8 @@ var ( func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string, daemonFolder string) (resultErr error) { resultHandler := NewResultHandler(u.tempDir) + var uiSessions []uint32 + // Always ensure daemon and UI are restarted after setup defer func() { log.Infof("starting daemon back") @@ -46,7 +55,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string } log.Infof("starting UI back") - if err := u.startUIAsUser(daemonFolder); err != nil { + if err := u.startUI(daemonFolder, uiSessions); err != nil { log.Errorf("failed to start UI: %v", err) } @@ -75,6 +84,14 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string return } + // The UI holds an open handle on its own image. Left running, Restart Manager + // cannot shut it down (msiexec runs as LocalSystem here, the UI as the + // interactive user), so the MSI falls back to replacing the file on reboot and + // marks the install as restart-required. The deferred close-application action + // in the package runs too late to prevent that, it happens after + // InstallValidate has already registered the file as in use. + uiSessions = killUI() + var cmd *exec.Cmd switch installerType { case TypeExe: @@ -84,7 +101,9 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string installerDir := filepath.Dir(installerFile) logPath := filepath.Join(installerDir, msiLogFile) log.Infof("run msi installer: %s", installerFile) - cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/quiet", "/qn", "/l*v", logPath) + // REBOOT=ReallySuppress: a silent install has no way to ask, so without it + // msiexec reboots the machine on its own if it decides one is needed. + cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/qn", "/norestart", "REBOOT=ReallySuppress", "/l*v", logPath) } cmd.Dir = filepath.Dir(installerFile) @@ -95,9 +114,13 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string } log.Infof("installer started with PID %d", cmd.Process.Pid) - if resultErr = cmd.Wait(); resultErr != nil { - log.Errorf("installer process finished with error: %v", resultErr) - return + if err := cmd.Wait(); err != nil { + if !isRebootPending(err) { + resultErr = err + log.Errorf("installer process finished with error: %v", err) + return + } + log.Warnf("installer completed but reported a pending reboot, some files will be replaced on the next restart") } return nil @@ -117,16 +140,142 @@ func (u *Installer) startDaemon(daemonFolder string) error { return nil } -func (u *Installer) startUIAsUser(daemonFolder string) error { +func (u *Installer) startUI(daemonFolder string, sessionIDs []uint32) error { uiPath := filepath.Join(daemonFolder, uiName) log.Infof("starting netbird-ui: %s", uiPath) - // Get the active console session ID - sessionID := windows.WTSGetActiveConsoleSessionId() - if sessionID == 0xFFFFFFFF { - return fmt.Errorf("no active user session found") + if len(sessionIDs) == 0 { + sessionID := windows.WTSGetActiveConsoleSessionId() + if sessionID == 0xFFFFFFFF { + return fmt.Errorf("no active user session found") + } + sessionIDs = []uint32{sessionID} } + var errs []error + for _, sessionID := range sessionIDs { + if err := startUIInSession(uiPath, sessionID); err != nil { + errs = append(errs, fmt.Errorf("session %d: %w", sessionID, err)) + continue + } + log.Infof("netbird-ui started successfully in session %d", sessionID) + } + return errors.Join(errs...) +} + +// isRebootPending reports whether the installer exit code means it succeeded but +// left work for the next restart. The reboot itself is suppressed, so this is not +// a failure. +func isRebootPending(err error) bool { + var exitErr *exec.ExitError + if !errors.As(err, &exitErr) { + return false + } + + switch exitErr.ExitCode() { + case msiRebootRequired, msiRebootInitiated: + return true + default: + return false + } +} + +// killUI terminates any running netbird-ui process and returns the IDs of the +// interactive sessions the terminated processes belonged to. Setup starts the +// UI again in those sessions once the installer is done. +func killUI() []uint32 { + pids, err := processIDsByName(uiName) + if err != nil { + log.Warnf("failed to look up %s processes: %v", uiName, err) + return nil + } + + sessions := make(map[uint32]struct{}) + for _, pid := range pids { + var sessionID uint32 + if err := windows.ProcessIdToSessionId(pid, &sessionID); err != nil { + log.Warnf("failed to look up session of %s (PID %d): %v", uiName, pid, err) + } + + if err := terminateProcess(pid); err != nil { + log.Warnf("failed to terminate %s (PID %d): %v", uiName, pid, err) + continue + } + log.Infof("terminated %s (PID %d) in session %d", uiName, pid, sessionID) + + if sessionID != 0 { + sessions[sessionID] = struct{}{} + } + } + + sessionIDs := make([]uint32, 0, len(sessions)) + for sessionID := range sessions { + sessionIDs = append(sessionIDs, sessionID) + } + return sessionIDs +} + +func processIDsByName(name string) ([]uint32, error) { + snapshot, err := windows.CreateToolhelp32Snapshot(windows.TH32CS_SNAPPROCESS, 0) + if err != nil { + return nil, fmt.Errorf("create process snapshot: %w", err) + } + defer func() { + if err := windows.CloseHandle(snapshot); err != nil { + log.Warnf("failed to close process snapshot: %v", err) + } + }() + + var entry windows.ProcessEntry32 + entry.Size = uint32(unsafe.Sizeof(entry)) + + var pids []uint32 + for err = windows.Process32First(snapshot, &entry); err == nil; err = windows.Process32Next(snapshot, &entry) { + if strings.EqualFold(windows.UTF16ToString(entry.ExeFile[:]), name) { + pids = append(pids, entry.ProcessID) + } + } + if !errors.Is(err, windows.ERROR_NO_MORE_FILES) { + return nil, fmt.Errorf("enumerate processes: %w", err) + } + + return pids, nil +} + +func terminateProcess(pid uint32) error { + handle, err := windows.OpenProcess(windows.PROCESS_TERMINATE|windows.SYNCHRONIZE, false, pid) + if err != nil { + // The process may have exited between enumeration and now. + if errors.Is(err, windows.ERROR_INVALID_PARAMETER) { + return nil + } + return fmt.Errorf("open process: %w", err) + } + defer func() { + if err := windows.CloseHandle(handle); err != nil { + log.Warnf("failed to close process handle: %v", err) + } + }() + + if err := windows.TerminateProcess(handle, 0); err != nil { + return fmt.Errorf("terminate process: %w", err) + } + + // Wait for the handle to signal so the image file is released before the + // installer tries to overwrite it. A timeout is reported through the returned + // event, not through err, which stays nil unless the wait itself failed. + event, err := windows.WaitForSingleObject(handle, uint32(processExitWait.Milliseconds())) + if err != nil { + return fmt.Errorf("wait for process exit: %w", err) + } + if event != windows.WAIT_OBJECT_0 { + return fmt.Errorf("wait for process exit: unexpected wait result %#x", event) + } + + return nil +} + +func startUIInSession(uiPath string, sessionID uint32) error { // Get the user token for that session var userToken windows.Token err := windows.WTSQueryUserToken(sessionID, &userToken) @@ -158,6 +307,16 @@ func (u *Installer) startUIAsUser(daemonFolder string) error { } }() + var env *uint16 + if err := windows.CreateEnvironmentBlock(&env, primaryToken, false); err != nil { + return fmt.Errorf("create environment block: %w", err) + } + defer func() { + if err := windows.DestroyEnvironmentBlock(env); err != nil { + log.Warnf("failed to destroy environment block: %v", err) + } + }() + // Prepare startup info var si windows.StartupInfo si.Cb = uint32(unsafe.Sizeof(si)) @@ -180,7 +339,7 @@ func (u *Installer) startUIAsUser(daemonFolder string) error { nil, false, creationFlags, - nil, + env, nil, &si, &pi, @@ -197,7 +356,6 @@ func (u *Installer) startUIAsUser(daemonFolder string) error { log.Warnf("failed to close thread handle: %v", err) } - log.Infof("netbird-ui started successfully in session %d", sessionID) return nil } diff --git a/client/internal/updater/installer/installer_run_windows_test.go b/client/internal/updater/installer/installer_run_windows_test.go new file mode 100644 index 000000000..6a4540610 --- /dev/null +++ b/client/internal/updater/installer/installer_run_windows_test.go @@ -0,0 +1,108 @@ +package installer + +import ( + "errors" + "os/exec" + "slices" + "strconv" + "testing" +) + +// exitErrorWithCode returns a real *exec.ExitError carrying the given exit code. +func exitErrorWithCode(t *testing.T, code int) error { + t.Helper() + + err := exec.Command("cmd.exe", "/c", "exit "+strconv.Itoa(code)).Run() + if err == nil { + t.Fatalf("expected a non-zero exit for code %d", code) + } + return err +} + +func TestIsRebootPending(t *testing.T) { + tests := []struct { + name string + code int + want bool + }{ + {name: "reboot required", code: msiRebootRequired, want: true}, + {name: "reboot initiated", code: msiRebootInitiated, want: true}, + {name: "generic failure", code: 1603, want: false}, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + if got := isRebootPending(exitErrorWithCode(t, tt.code)); got != tt.want { + t.Errorf("isRebootPending(exit %d) = %v, want %v", tt.code, got, tt.want) + } + }) + } +} + +// TestProcessIDsByNameAndTerminate spawns a long-running system process, finds it +// by name and terminates it, covering the path the updater uses to release the UI +// image file before the installer replaces it. +func TestProcessIDsByNameAndTerminate(t *testing.T) { + cmd := exec.Command("ping.exe", "-n", "60", "127.0.0.1") + if err := cmd.Start(); err != nil { + t.Fatalf("start ping: %v", err) + } + + pid := uint32(cmd.Process.Pid) + killed := false + t.Cleanup(func() { + if !killed { + _ = cmd.Process.Kill() + } + _ = cmd.Wait() + }) + + // Name matching must be case-insensitive: the snapshot reports PING.EXE. + pids, err := processIDsByName("ping.exe") + if err != nil { + t.Fatalf("processIDsByName: %v", err) + } + + if !slices.Contains(pids, pid) { + t.Fatalf("PID %d not among the ping.exe processes found: %v", pid, pids) + } + + if err := terminateProcess(pid); err != nil { + t.Fatalf("terminateProcess: %v", err) + } + killed = true + + // terminateProcess only returns once the handle has signalled, so the process + // is already gone and Wait must not block. It exits with the code passed to + // TerminateProcess, which is 0, so Wait reports no error. + if err := cmd.Wait(); err != nil { + t.Fatalf("wait for terminated ping: %v", err) + } + if !cmd.ProcessState.Exited() { + t.Error("process did not exit after terminateProcess") + } + + remaining, err := processIDsByName("ping.exe") + if err != nil { + t.Fatalf("processIDsByName after terminate: %v", err) + } + if slices.Contains(remaining, pid) { + t.Errorf("PID %d still listed after terminateProcess", pid) + } +} + +func TestProcessIDsByNameNoMatch(t *testing.T) { + pids, err := processIDsByName("netbird-nonexistent-process.exe") + if err != nil { + t.Fatalf("processIDsByName: %v", err) + } + if len(pids) != 0 { + t.Errorf("expected no matches, got %v", pids) + } +} + +func TestIsRebootPendingNonExitError(t *testing.T) { + if isRebootPending(errors.New("start installer: file not found")) { + t.Error("a non-exit error must not be treated as a pending reboot") + } +} diff --git a/client/internal/updater/installer/result.go b/client/internal/updater/installer/result.go index 526c3eb53..55a0d8ac8 100644 --- a/client/internal/updater/installer/result.go +++ b/client/internal/updater/installer/result.go @@ -54,6 +54,12 @@ func (rh *ResultHandler) GetErrorResultReason() string { return "" } +// ClearStaleResult removes a result file left over from a previous installation +// attempt so result watchers cannot read an outdated outcome for the current attempt. +func (rh *ResultHandler) ClearStaleResult() error { + return rh.cleanup() +} + func (rh *ResultHandler) WriteSuccess() error { result := Result{ Success: true, diff --git a/client/internal/updater/manager.go b/client/internal/updater/manager.go index 7fc300739..1b69368d0 100644 --- a/client/internal/updater/manager.go +++ b/client/internal/updater/manager.go @@ -435,7 +435,7 @@ func (m *Manager) install(ctx context.Context, pendingVersion *v.Version) error } inst := installer.New() - if err := inst.RunInstallation(ctx, pendingVersion.String()); err != nil { + if err := inst.RunInstallation(ctx, pendingVersion.String()); err != nil { //nolint:staticcheck // always errors on platforms without an installer log.Errorf("error triggering update: %v", err) m.statusRecorder.PublishEvent( cProto.SystemEvent_ERROR, diff --git a/client/ios/NetBirdSDK/client.go b/client/ios/NetBirdSDK/client.go index bb79db672..8c58dea04 100644 --- a/client/ios/NetBirdSDK/client.go +++ b/client/ios/NetBirdSDK/client.go @@ -14,6 +14,7 @@ import ( log "github.com/sirupsen/logrus" + nbAnonymize "github.com/netbirdio/netbird/client/anonymize" "github.com/netbirdio/netbird/client/internal" "github.com/netbirdio/netbird/client/internal/auth" "github.com/netbirdio/netbird/client/internal/debug" @@ -21,7 +22,12 @@ import ( "github.com/netbirdio/netbird/client/internal/listener" "github.com/netbirdio/netbird/client/internal/peer" "github.com/netbirdio/netbird/client/internal/profilemanager" +<<<<<<< HEAD "github.com/netbirdio/netbird/client/mdm" +======= + "github.com/netbirdio/netbird/client/netstate" + "github.com/netbirdio/netbird/client/netsweep" +>>>>>>> main "github.com/netbirdio/netbird/client/system" "github.com/netbirdio/netbird/formatter" "github.com/netbirdio/netbird/route" @@ -29,10 +35,12 @@ import ( types "github.com/netbirdio/netbird/upload-server/types" ) -// ConnectionListener export internal Listener for mobile -type ConnectionListener interface { - peer.Listener -} +// AnonymizeLevelDefault and AnonymizeLevelStrict are the accepted +// anonymizeLevel values for DebugBundle. +const ( + AnonymizeLevelDefault = nbAnonymize.LevelDefaultString + AnonymizeLevelStrict = nbAnonymize.LevelStrictString +) // RouteListener export internal RouteListener for mobile type NetworkChangeListener interface { @@ -80,6 +88,12 @@ type Client struct { onHostDnsFn func([]string) dnsManager dns.IosDnsManager loginComplete bool + // netState outlives engine restarts: it mirrors the OS connectivity, not + // the engine lifecycle. Run injects it into each new ConnectClient, which + // distributes it to every reconnection loop. + netState *netstate.State + // sweeper also outlives engine restarts; NotifyNetworkChange sweeps it. + sweeper *netsweep.Sweeper // preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked) preloadedConfig *profilemanager.Config @@ -109,6 +123,8 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV ctxCancelLock: &sync.Mutex{}, networkChangeListener: networkChangeListener, dnsManager: dnsManager, + netState: netstate.New(), + sweeper: netsweep.New(), } } @@ -185,7 +201,8 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error { c.onHostDnsFn = func([]string) {} cfg.WgIface = interfaceName - connectClient := internal.NewConnectClient(ctx, cfg, c.recorder) + connectClient := internal.NewConnectClient(ctx, cfg, c.recorder, + internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper)) c.setState(cfg, connectClient) // Persist the latest sync response so DebugBundle can include the network // map. On iOS this is backed by disk to keep it out of the constrained @@ -194,6 +211,25 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error { return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath) } +// SetNetworkAvailable feeds OS-reported network availability into the client +// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops +// suspend their attempts and the connection listener reports NoNetwork +// instead of Connecting; when availability returns, the loops resume +// immediately with a fresh backoff. +func (c *Client) SetNetworkAvailable(available bool) { + c.netState.Set(available) + c.recorder.SetNetworkAvailable(available) +} + +// NotifyNetworkChange marks the management, signal and relay connections +// stale after the OS switched networks and schedules a sweep that cuts +// whatever has not redialed on the new network by then. The engine and the +// TUN device stay untouched. +func (c *Client) NotifyNetworkChange() { + c.sweeper.MarkNetworkChange() + log.Infof("network change: connections marked stale") +} + // Stop the internal client and free the resources func (c *Client) Stop() { c.ctxCancelLock.Lock() @@ -209,8 +245,10 @@ func (c *Client) Stop() { // DebugBundle generates a debug bundle, uploads it and returns the upload key. // It works with or without a running engine: when the engine is up it reuses // the live config, sync response and client metrics; otherwise it loads the -// config from disk (or the preloaded tvOS config). -func (c *Client) DebugBundle(anonymize bool) (string, error) { +// config from disk (or the preloaded tvOS config). anonymizeLevel is "default" +// or "strict"; strict also anonymizes internal IP ranges, peer names, and +// WireGuard public keys, and implies anonymize. +func (c *Client) DebugBundle(anonymize bool, anonymizeLevel string) (string, error) { cfg, cc := c.stateSnapshot() // If the engine hasn't been started, load config so we can reach management. @@ -261,6 +299,7 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) { deps, debug.BundleConfig{ Anonymize: anonymize, + AnonymizeLevel: nbAnonymize.ParseLevel(anonymizeLevel), IncludeSystemInfo: true, }, ) @@ -330,7 +369,11 @@ func (c *Client) GetStatusDetails() *StatusDetails { // SetConnectionListener set the network connection listener func (c *Client) SetConnectionListener(listener ConnectionListener) { - c.recorder.SetConnectionListener(listener) + if listener == nil { + c.recorder.RemoveConnectionListener() + return + } + c.recorder.SetConnectionListener(connectionListenerAdapter{listener}) } // RemoveConnectionListener remove connection listener diff --git a/client/ios/NetBirdSDK/connection_listener.go b/client/ios/NetBirdSDK/connection_listener.go new file mode 100644 index 000000000..d792537ba --- /dev/null +++ b/client/ios/NetBirdSDK/connection_listener.go @@ -0,0 +1,43 @@ +//go:build ios + +package NetBirdSDK + +import ( + "github.com/netbirdio/netbird/client/internal/peer" +) + +// Client state values, re-exported as basic constants so gomobile emits them +// into the generated bindings. They mirror peer.ClientState*: append-only, +// never reorder. +const ( + ClientStateDisconnected = int(peer.ClientStateDisconnected) + ClientStateConnected = int(peer.ClientStateConnected) + ClientStateConnecting = int(peer.ClientStateConnecting) + ClientStateDisconnecting = int(peer.ClientStateDisconnecting) + ClientStateNoNetwork = int(peer.ClientStateNoNetwork) +) + +// ConnectionListener export internal Listener for mobile. +// +// It intentionally lacks OnStateChanged for now: adding a method to a gomobile +// interface breaks every Swift implementation, so the iOS app keeps building +// against the legacy per-state callbacks. A follow-up will extend it together +// with the app. +type ConnectionListener interface { + OnConnected() + OnDisconnected() + OnConnecting() + OnDisconnecting() + OnAddressChanged(string, string) + OnPeersListChanged(int) +} + +// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to +// peer.Listener. +type connectionListenerAdapter struct { + ConnectionListener +} + +// OnStateChanged is dropped on iOS until the app adopts the state callback; +// the legacy per-state callbacks continue to fire. +func (a connectionListenerAdapter) OnStateChanged(peer.ClientState) {} diff --git a/client/ios/NetBirdSDK/login.go b/client/ios/NetBirdSDK/login.go index 6cba0c411..42a575359 100644 --- a/client/ios/NetBirdSDK/login.go +++ b/client/ios/NetBirdSDK/login.go @@ -323,7 +323,7 @@ func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName strin const authInfoRequestTimeout = 30 * time.Second func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, forceDeviceAuth bool) (*auth.TokenInfo, error) { - oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, forceDeviceAuth) + oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, forceDeviceAuth, "") if err != nil { return nil, fmt.Errorf("failed to get OAuth flow: %v", err) } diff --git a/client/netstate/netstate.go b/client/netstate/netstate.go new file mode 100644 index 000000000..0d7a1268b --- /dev/null +++ b/client/netstate/netstate.go @@ -0,0 +1,110 @@ +// Package netstate tracks OS-reported network availability for the client. +// +// A State instance is owned by the platform integration (e.g. the Android or +// iOS bindings, fed from ConnectivityManager callbacks or NWPathMonitor) and +// is injected into the connection retry loops (management, signal, relay, +// peer guards and the top-level connect loop), which consult it to avoid +// burning CPU and battery on reconnect attempts while the device has no +// network at all (e.g. airplane mode), and to reset their backoff as soon as +// the network returns. +// +// Consumers hold a *State that may be nil — every non-mobile platform leaves +// it unset. The read methods are safe on a nil receiver: they report online +// and never block, so consumers behave as if this package did not exist. +package netstate + +import ( + "context" + "sync" + + log "github.com/sirupsen/logrus" +) + +// State holds the OS-reported network availability. The zero value is not +// usable; create instances with New. +type State struct { + mu sync.Mutex + online bool + changed chan struct{} +} + +// New creates a State that starts online. Platforms without network tracking +// pass a nil *State instead: the read methods treat nil as always online and +// never block, so consumers need no nil guards. +func New() *State { + return &State{ + online: true, + changed: make(chan struct{}), + } +} + +// Set records whether the OS reports any usable network. Transitions wake up +// all Wait callers immediately. Unlike the read methods, Set is not nil-safe: +// it is only for the platform owner that created the State with New. +func (s *State) Set(online bool) { + s.mu.Lock() + defer s.mu.Unlock() + if s.online == online { + return + } + s.online = online + close(s.changed) + s.changed = make(chan struct{}) + log.Infof("OS network availability changed: online=%t", online) +} + +// IsOnline reports whether the OS reports at least one usable network. On a +// nil receiver — no State injected — it reports online. +func (s *State) IsOnline() bool { + if s == nil { + return true + } + s.mu.Lock() + defer s.mu.Unlock() + return s.online +} + +// Changed returns a channel closed on the next availability transition, for +// callers that already own a select loop and cannot block in Wait. Re-read it +// after every fire: each transition installs a fresh channel. On a nil +// receiver — no State injected — it returns nil, which blocks forever in a +// select, so the caller simply never observes a transition. +func (s *State) Changed() <-chan struct{} { + if s == nil { + return nil + } + s.mu.Lock() + defer s.mu.Unlock() + return s.changed +} + +// Wait blocks while the network is offline. It reports whether it had to +// wait, so callers can reset their backoff after an outage. It returns early +// with the context error when ctx is done. On a nil receiver — no State +// injected — it returns immediately. +func (s *State) Wait(ctx context.Context) (bool, error) { + if s == nil { + return false, nil + } + waited := false + for { + s.mu.Lock() + if s.online { + s.mu.Unlock() + return waited, nil + } + ch := s.changed + s.mu.Unlock() + + if !waited { + waited = true + log.Debugf("network is offline, pausing connection attempts") + } + + select { + case <-ctx.Done(): + return waited, ctx.Err() + case <-ch: + } + } +} diff --git a/client/netstate/netstate_test.go b/client/netstate/netstate_test.go new file mode 100644 index 000000000..ea7015761 --- /dev/null +++ b/client/netstate/netstate_test.go @@ -0,0 +1,170 @@ +package netstate + +import ( + "context" + "sync" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +func TestNewStateIsOnline(t *testing.T) { + assert.True(t, New().IsOnline(), "a fresh State should start online") +} + +func TestSetTogglesOnlineState(t *testing.T) { + s := New() + + s.Set(false) + assert.False(t, s.IsOnline(), "state should be offline after Set(false)") + + s.Set(true) + assert.True(t, s.IsOnline(), "state should be online after Set(true)") +} + +func TestWaitReturnsImmediatelyWhenOnline(t *testing.T) { + s := New() + + ctx, cancel := context.WithTimeout(context.Background(), time.Second) + defer cancel() + + waited, err := s.Wait(ctx) + require.NoError(t, err) + assert.False(t, waited, "Wait should not block when the network is online") +} + +func TestWaitBlocksUntilOnline(t *testing.T) { + s := New() + s.Set(false) + + ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second) + defer cancel() + + result := make(chan bool, 1) + go func() { + waited, err := s.Wait(ctx) + if err != nil { + result <- false + return + } + result <- waited + }() + + // Verify Wait is actually blocking while offline + select { + case <-result: + t.Fatal("Wait should block while the network is offline") + case <-time.After(100 * time.Millisecond): + } + + s.Set(true) + + select { + case waited := <-result: + assert.True(t, waited, "Wait should report that it had to wait for the network") + case <-time.After(2 * time.Second): + t.Fatal("Wait should return promptly after the network becomes available") + } +} + +func TestWaitReturnsOnContextCancel(t *testing.T) { + s := New() + s.Set(false) + + ctx, cancel := context.WithCancel(context.Background()) + + result := make(chan error, 1) + go func() { + _, err := s.Wait(ctx) + result <- err + }() + + cancel() + + select { + case err := <-result: + assert.ErrorIs(t, err, context.Canceled) + case <-time.After(2 * time.Second): + t.Fatal("Wait should return promptly after context cancellation") + } +} + +func TestWaitWakesAllWaiters(t *testing.T) { + s := New() + s.Set(false) + + ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second) + defer cancel() + + const waiters = 10 + var wg sync.WaitGroup + results := make(chan bool, waiters) + for i := 0; i < waiters; i++ { + wg.Add(1) + go func() { + defer wg.Done() + waited, err := s.Wait(ctx) + if err != nil { + results <- false + return + } + results <- waited + }() + } + + time.Sleep(100 * time.Millisecond) + s.Set(true) + wg.Wait() + + close(results) + count := 0 + for waited := range results { + assert.True(t, waited, "every waiter should report that it waited") + count++ + } + assert.Equal(t, waiters, count, "all waiters should have returned") +} + +func TestNilStateReadsAreNoops(t *testing.T) { + var s *State + + assert.True(t, s.IsOnline(), "nil State should report online") + + waited, err := s.Wait(context.Background()) + require.NoError(t, err) + assert.False(t, waited, "nil State's Wait should not block") +} + +func TestConcurrentSetAndWait(t *testing.T) { + s := New() + + ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second) + defer cancel() + + var wg sync.WaitGroup + for i := 0; i < 4; i++ { + wg.Add(1) + go func() { + defer wg.Done() + for j := 0; j < 100; j++ { + s.Set(j%2 == 0) + s.IsOnline() + } + }() + } + for i := 0; i < 4; i++ { + wg.Add(1) + go func() { + defer wg.Done() + for j := 0; j < 100; j++ { + if _, err := s.Wait(ctx); err != nil { + return + } + } + }() + } + + wg.Wait() +} diff --git a/client/netsweep/netsweep.go b/client/netsweep/netsweep.go new file mode 100644 index 000000000..46bc0a709 --- /dev/null +++ b/client/netsweep/netsweep.go @@ -0,0 +1,267 @@ +// Package netsweep cuts network-bound activity when the OS switches networks: +// a sweep closes the registered connections and aborts the in-flight dials, so +// their owners redial immediately instead of waiting for the old sockets to +// time out. +// +// A nil *Sweeper disables everything: all methods are nil-safe no-ops. +package netsweep + +import ( + "context" + "errors" + "net" + "sync" + "time" + + "github.com/cenkalti/backoff/v4" + log "github.com/sirupsen/logrus" + + "github.com/netbirdio/netbird/client/netstate" +) + +// DefaultSweepDelay absorbs network flapping while the OS settles on a +// default network before the stale registrations are cut. +const DefaultSweepDelay = 500 * time.Millisecond + +const recentMarkWindow = 3 * time.Second + +// Config customizes a Sweeper. The zero value applies the defaults. +type Config struct { + // SweepDelay overrides DefaultSweepDelay when positive. + SweepDelay time.Duration +} + +// ErrSwept reports that a dial finished after a network change swept its +// registration. The connection is already closed; the caller must treat it +// as a failed dial and redial on the new network. +var ErrSwept = errors.New("netsweep: connection swept by network change") + +// sweepID identifies one registration in a sweeper. Connections and dials +// draw from the same counter, so an id is unique across both registries. +type sweepID uint64 + +type connEntry struct { + conn net.Conn + gen uint64 +} + +// Dial tracks one dial from start to connection registration. It hands the +// dialed connection to the sweeper atomically, so a sweep can never fall +// between the dial finishing and the connection being registered. +type Dial struct { + sweeper *Sweeper + ctx context.Context + cancel context.CancelFunc + id sweepID + done bool // set by a sweep, WrapConn or Release; guarded by sweeper.mu + gen uint64 +} + +// Ctx returns the dial's context. A sweep cancels it, so a dial started on the +// old network aborts instead of waiting out its handshake timeout. +func (d *Dial) Ctx() context.Context { + return d.ctx +} + +// Release ends the dial's registration and cancels its context. It is +// idempotent and safe after WrapConn, so callers can defer it. +func (d *Dial) Release() { + s := d.sweeper + if s == nil { + return + } + + s.mu.Lock() + d.done = true + delete(s.dials, d.id) + s.mu.Unlock() + + d.cancel() +} + +// sweptConn deregisters itself from the sweeper when closed. +type sweptConn struct { + net.Conn + sweeper *Sweeper + id sweepID +} + +func (c *sweptConn) Close() error { + c.sweeper.deregister(c.id) + return c.Conn.Close() +} + +// Sweeper registers live connections and in-flight dials so the +// network-change sweep can cut everything registered before the change. +type Sweeper struct { + mu sync.Mutex + conns map[sweepID]connEntry + dials map[sweepID]*Dial + nextID sweepID + gen uint64 + timer *time.Timer + sweepDelay time.Duration + lastMark time.Time +} + +// New creates an empty sweeper with the default configuration. +func New() *Sweeper { + return NewWithConfig(Config{}) +} + +// NewWithConfig creates an empty sweeper customized by cfg. +func NewWithConfig(cfg Config) *Sweeper { + delay := cfg.SweepDelay + if delay <= 0 { + delay = DefaultSweepDelay + } + return &Sweeper{ + conns: make(map[sweepID]connEntry), + dials: make(map[sweepID]*Dial), + sweepDelay: delay, + } +} + +// StartDial registers an in-flight dial. Dial with Ctx, hand the result to +// WrapConn, and Release the dial when the attempt is over, typically deferred. +func (s *Sweeper) StartDial(ctx context.Context) *Dial { + if s == nil { + return &Dial{ctx: ctx} + } + + ctx, cancel := context.WithCancel(ctx) + d := &Dial{sweeper: s, ctx: ctx, cancel: cancel} + + s.mu.Lock() + d.id = s.nextID + s.nextID++ + d.gen = s.gen + s.dials[d.id] = d + s.mu.Unlock() + + return d +} + +// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial, +// the connection belongs to the old network: it is closed and ErrSwept is +// returned. Otherwise conn is registered against the next sweep and returned +// wrapped, deregistering itself on Close. Call it once, before Release. +func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) { + s := d.sweeper + if s == nil { + return conn, nil + } + + s.mu.Lock() + if d.done { + s.mu.Unlock() + if err := conn.Close(); err != nil { + log.Debugf("swept dial close error: %v", err) + } + return nil, ErrSwept + } + d.done = true + delete(s.dials, d.id) + id := s.nextID + s.nextID++ + // The conn inherits the dial's generation: the socket was bound to the + // network that was default when the dial started, not when it finished. + s.conns[id] = connEntry{conn: conn, gen: d.gen} + s.mu.Unlock() + + return &sweptConn{Conn: conn, sweeper: s, id: id}, nil +} + +// MarkNetworkChange records that the OS switched networks: everything +// registered so far becomes stale, and a sweep is (re)scheduled after the +// configured delay to cut whatever is still stale by then. Owners that +// redialed in the meantime hold fresh-generation registrations and survive, +// so no cancellation is needed around the sweep. +func (s *Sweeper) MarkNetworkChange() { + if s == nil { + return + } + + s.mu.Lock() + s.gen++ + cutoff := s.gen + s.lastMark = time.Now() + if s.timer != nil { + s.timer.Stop() + } + s.timer = time.AfterFunc(s.sweepDelay, func() { + n := s.sweep(cutoff) + log.Infof("network change sweep: closed %d stale connections", n) + }) + s.mu.Unlock() +} + +// QuickRetryBackoff wraps bo so that after each Reset the first retry comes +// quickly when the disconnect followed a recent network change and the +// network is online. Any other failure keeps bo's spread, so the clients of +// a restarted server still scatter their reconnects. A nil sweeper returns +// bo unchanged. +func (s *Sweeper) QuickRetryBackoff(ctx context.Context, bo backoff.BackOff, netState *netstate.State) backoff.BackOff { + if s == nil { + return bo + } + return backoff.WithContext(newQuickRetryBackoff(bo, s, netState), ctx) +} + +func (s *Sweeper) markedRecently() bool { + if s == nil { + return false + } + s.mu.Lock() + defer s.mu.Unlock() + return !s.lastMark.IsZero() && time.Since(s.lastMark) < recentMarkWindow +} + +// sweep closes the registered connections and aborts the in-flight dials +// older than cutoff, and returns how many connections it closed. A dial +// whose connection was not yet handed to WrapConn is marked, so the late +// WrapConn closes it instead of registering it. +func (s *Sweeper) sweep(cutoff uint64) int { + if s == nil { + return 0 + } + + s.mu.Lock() + var conns []net.Conn + for id, e := range s.conns { + if e.gen < cutoff { + delete(s.conns, id) + conns = append(conns, e.conn) + } + } + var dials []*Dial + for id, d := range s.dials { + if d.gen < cutoff { + d.done = true + delete(s.dials, id) + dials = append(dials, d) + } + } + s.mu.Unlock() + + if len(dials) > 0 { + log.Debugf("aborting %d in-flight dials", len(dials)) + for _, d := range dials { + d.cancel() + } + } + + for _, conn := range conns { + log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr()) + if err := conn.Close(); err != nil { + log.Debugf("swept connection close error: %v", err) + } + } + return len(conns) +} + +func (s *Sweeper) deregister(id sweepID) { + s.mu.Lock() + delete(s.conns, id) + s.mu.Unlock() +} diff --git a/client/netsweep/netsweep_test.go b/client/netsweep/netsweep_test.go new file mode 100644 index 000000000..88d660c2d --- /dev/null +++ b/client/netsweep/netsweep_test.go @@ -0,0 +1,241 @@ +package netsweep + +import ( + "context" + "math" + "net" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +func TestSweepClosesRegisteredConns(t *testing.T) { + sweeper := New() + + c1 := wrap(t, sweeper, connPair(t)) + c2 := wrap(t, sweeper, connPair(t)) + + assert.Equal(t, 2, sweeper.sweepAll(), "both live connections should be closed") + + // The wrappers must report closed now. + buf := make([]byte, 1) + _, err := c1.Read(buf) + assert.Error(t, err, "first connection should be unusable after the sweep") + _, err = c2.Read(buf) + assert.Error(t, err, "second connection should be unusable after the sweep") + + assert.Equal(t, 0, sweeper.sweepAll(), "second sweep should find nothing") +} + +func TestCloseDeregisters(t *testing.T) { + sweeper := New() + + conn := wrap(t, sweeper, connPair(t)) + require.NoError(t, conn.Close()) + + assert.Equal(t, 0, sweeper.sweepAll(), "closed connection must leave the registry") +} + +func TestCloseIsIdempotent(t *testing.T) { + sweeper := New() + + conn := wrap(t, sweeper, connPair(t)) + require.NoError(t, conn.Close()) + assert.Error(t, conn.Close(), "double close surfaces the underlying error but must not panic") +} + +func TestSweepOnlyAffectsOlderConns(t *testing.T) { + sweeper := New() + + _ = wrap(t, sweeper, connPair(t)) + assert.Equal(t, 1, sweeper.sweepAll()) + + // A connection dialed after the sweep must survive until the next one. + _ = wrap(t, sweeper, connPair(t)) + assert.Equal(t, 1, sweeper.sweepAll(), "post-sweep connection belongs to the next sweep") +} + +func TestSweepAbortsInFlightDials(t *testing.T) { + sweeper := New() + + dial := sweeper.StartDial(context.Background()) + defer dial.Release() + + sweeper.sweepAll() + + assert.ErrorIs(t, dial.Ctx().Err(), context.Canceled, "sweep must cancel the in-flight dial context") +} + +func TestReleasedDialIsNotAborted(t *testing.T) { + sweeper := New() + + // Simulate a dial that finished before the sweep. + released := sweeper.StartDial(context.Background()) + released.Release() + + // A dial still in flight during the sweep. + pending := sweeper.StartDial(context.Background()) + defer pending.Release() + + sweeper.sweepAll() + assert.ErrorIs(t, pending.Ctx().Err(), context.Canceled, "pending dial must be aborted") +} + +func TestSweepBetweenDialAndHandoffClosesConn(t *testing.T) { + sweeper := New() + + dial := sweeper.StartDial(context.Background()) + defer dial.Release() + + // The dial succeeds on the old network, then the sweep lands before the + // connection is handed over. + conn := connPair(t) + assert.Equal(t, 0, sweeper.sweepAll(), "the connection is not registered yet") + + wrapped, err := dial.WrapConn(conn) + require.ErrorIs(t, err, ErrSwept) + require.Nil(t, wrapped) + + buf := make([]byte, 1) + _, err = conn.Read(buf) + assert.Error(t, err, "the old-network connection must be closed, not leaked") + + assert.Equal(t, 0, sweeper.sweepAll(), "nothing may leak into the next sweep") +} + +func TestMarkNetworkChangeSparesFreshConns(t *testing.T) { + sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond}) + + stale := wrap(t, sweeper, connPair(t)) + sweeper.MarkNetworkChange() + _ = wrap(t, sweeper, connPair(t)) + + _ = stale.SetReadDeadline(time.Now().Add(time.Second)) + buf := make([]byte, 1) + _, err := stale.Read(buf) + require.ErrorIs(t, err, net.ErrClosed, "stale connection must be closed by the delayed sweep") + + assert.Equal(t, 1, sweeper.sweepAll(), "the fresh connection must survive the stale sweep") +} + +func TestMarkNetworkChangeAbortsStaleDials(t *testing.T) { + sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond}) + + stale := sweeper.StartDial(context.Background()) + defer stale.Release() + sweeper.MarkNetworkChange() + fresh := sweeper.StartDial(context.Background()) + defer fresh.Release() + + assert.Eventually(t, func() bool { + return stale.Ctx().Err() != nil + }, time.Second, 5*time.Millisecond, "stale dial must be aborted by the delayed sweep") + assert.NoError(t, fresh.Ctx().Err(), "post-mark dial must not be aborted") +} + +func TestConnInheritsDialGeneration(t *testing.T) { + sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond}) + + // The dial starts before the network change but completes after it: the + // socket is bound to the old network, so the sweep must still cut it. + dial := sweeper.StartDial(context.Background()) + defer dial.Release() + sweeper.MarkNetworkChange() + + wrapped, err := dial.WrapConn(connPair(t)) + require.NoError(t, err) + + _ = wrapped.SetReadDeadline(time.Now().Add(time.Second)) + buf := make([]byte, 1) + _, err = wrapped.Read(buf) + require.ErrorIs(t, err, net.ErrClosed, "old-generation connection must be swept") +} + +func TestRepeatedMarksCoalesce(t *testing.T) { + sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond}) + + first := wrap(t, sweeper, connPair(t)) + sweeper.MarkNetworkChange() + second := wrap(t, sweeper, connPair(t)) + sweeper.MarkNetworkChange() + _ = wrap(t, sweeper, connPair(t)) + + buf := make([]byte, 1) + for _, conn := range []net.Conn{first, second} { + _ = conn.SetReadDeadline(time.Now().Add(time.Second)) + _, err := conn.Read(buf) + require.ErrorIs(t, err, net.ErrClosed, "every pre-mark connection must be swept by the rescheduled sweep") + } + assert.Equal(t, 1, sweeper.sweepAll(), "only the newest-generation connection may remain") +} + +func TestNilSweeperIsNoop(t *testing.T) { + var sweeper *Sweeper + + conn := connPair(t) + dial := sweeper.StartDial(context.Background()) + defer dial.Release() + + wrapped, err := dial.WrapConn(conn) + require.NoError(t, err) + assert.Equal(t, conn, wrapped, "nil sweeper must return the conn unchanged") + assert.NoError(t, dial.Ctx().Err(), "nil sweeper must not cancel the dial context") + assert.Equal(t, 0, sweeper.sweepAll(), "nil sweeper closes nothing") +} + +// wrap registers conn with the sweeper through a completed dial. +func wrap(t *testing.T, sweeper *Sweeper, conn net.Conn) net.Conn { + t.Helper() + + dial := sweeper.StartDial(context.Background()) + defer dial.Release() + + wrapped, err := dial.WrapConn(conn) + require.NoError(t, err) + return wrapped +} + +// connPair dials a loopback TCP connection and keeps the accepted peer open +// until the test ends: a peer that closed early would make the connection +// unreadable on its own, so a read error after the sweep would prove nothing. +func connPair(t *testing.T) net.Conn { + t.Helper() + + l, err := net.Listen("tcp", "127.0.0.1:0") + require.NoError(t, err) + t.Cleanup(func() { + if err := l.Close(); err != nil { + t.Logf("listener close error: %v", err) + } + }) + + accepted := make(chan net.Conn, 1) + go func() { + conn, err := l.Accept() + if err != nil { + close(accepted) + return + } + accepted <- conn + }() + + conn, err := net.Dial("tcp", l.Addr().String()) + require.NoError(t, err) + + peer, ok := <-accepted + require.True(t, ok, "listener must accept the dialed connection") + t.Cleanup(func() { + if err := peer.Close(); err != nil { + t.Logf("peer close error: %v", err) + } + }) + + return conn +} + +// sweepAll cuts every registration regardless of generation. +func (s *Sweeper) sweepAll() int { + return s.sweep(math.MaxUint64) +} diff --git a/client/netsweep/quick_retry.go b/client/netsweep/quick_retry.go new file mode 100644 index 000000000..524a5c50c --- /dev/null +++ b/client/netsweep/quick_retry.go @@ -0,0 +1,39 @@ +package netsweep + +import ( + "time" + + "github.com/cenkalti/backoff/v4" + + "github.com/netbirdio/netbird/client/netstate" +) + +const quickRetryDelay = 200 * time.Millisecond + +type quickRetryBackoff struct { + backoff.BackOff + sweeper *Sweeper + netState *netstate.State + used bool +} + +func newQuickRetryBackoff(bo backoff.BackOff, sweeper *Sweeper, netState *netstate.State) *quickRetryBackoff { + return &quickRetryBackoff{ + BackOff: bo, + sweeper: sweeper, + netState: netState, + } +} + +func (b *quickRetryBackoff) NextBackOff() time.Duration { + if !b.used && b.sweeper.markedRecently() && b.netState.IsOnline() { + b.used = true + return quickRetryDelay + } + return b.BackOff.NextBackOff() +} + +func (b *quickRetryBackoff) Reset() { + b.used = false + b.BackOff.Reset() +} diff --git a/client/netsweep/quick_retry_test.go b/client/netsweep/quick_retry_test.go new file mode 100644 index 000000000..5505862c5 --- /dev/null +++ b/client/netsweep/quick_retry_test.go @@ -0,0 +1,58 @@ +package netsweep + +import ( + "context" + "testing" + "time" + + "github.com/cenkalti/backoff/v4" + "github.com/stretchr/testify/assert" +) + +func TestQuickRetryAfterRecentMark(t *testing.T) { + sweeper := New() + sweeper.MarkNetworkChange() + + slow := backoff.NewConstantBackOff(5 * time.Second) + bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil) + + assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "first retry after a mark must be quick") + assert.Equal(t, 5*time.Second, bo.NextBackOff(), "second retry must fall back to the wrapped backoff") + + bo.Reset() + assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "reset must re-arm the quick retry") +} + +func TestQuickRetryWithoutMarkKeepsSpread(t *testing.T) { + sweeper := New() + + slow := backoff.NewConstantBackOff(5 * time.Second) + bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil) + + assert.Equal(t, 5*time.Second, bo.NextBackOff(), "without a mark the wrapped backoff decides") + + sweeper.mu.Lock() + sweeper.lastMark = time.Now().Add(-recentMarkWindow) + sweeper.mu.Unlock() + assert.Equal(t, 5*time.Second, bo.NextBackOff(), "a stale mark must not trigger the quick retry") +} + +func TestQuickRetryNilSweeperPassthrough(t *testing.T) { + var sweeper *Sweeper + + slow := backoff.NewConstantBackOff(5 * time.Second) + bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil) + + assert.Equal(t, backoff.BackOff(slow), bo, "nil sweeper must return the backoff unchanged") +} + +func TestQuickRetryHonorsContext(t *testing.T) { + sweeper := New() + sweeper.MarkNetworkChange() + + ctx, cancel := context.WithCancel(context.Background()) + cancel() + bo := sweeper.QuickRetryBackoff(ctx, backoff.NewConstantBackOff(time.Millisecond), nil) + + assert.Equal(t, backoff.Stop, bo.NextBackOff(), "cancelled context must stop the retry loop") +} diff --git a/client/proto/daemon.pb.go b/client/proto/daemon.pb.go index d4deeb8ec..b438a310a 100644 --- a/client/proto/daemon.pb.go +++ b/client/proto/daemon.pb.go @@ -2781,6 +2781,11 @@ type DebugBundleRequest struct { // untrusted TLS certificate. Restricted to privileged callers; for // self-hosted upload servers. UploadInsecure bool `protobuf:"varint,7,opt,name=uploadInsecure,proto3" json:"uploadInsecure,omitempty"` + // anonymizeLevel selects how much the anonymizer redacts: "default" + // (or empty) keeps internal IP ranges, "strict" also anonymizes them. + // Unknown values are treated as "strict". Only meaningful with anonymize; + // "strict" implies it. + AnonymizeLevel string `protobuf:"bytes,8,opt,name=anonymizeLevel,proto3" json:"anonymizeLevel,omitempty"` unknownFields protoimpl.UnknownFields sizeCache protoimpl.SizeCache } @@ -2857,6 +2862,13 @@ func (x *DebugBundleRequest) GetUploadInsecure() bool { return false } +func (x *DebugBundleRequest) GetAnonymizeLevel() string { + if x != nil { + return x.AnonymizeLevel + } + return "" +} + type DebugBundleResponse struct { state protoimpl.MessageState `protogen:"open.v1"` Path string `protobuf:"bytes,1,opt,name=path,proto3" json:"path,omitempty"` @@ -5616,9 +5628,13 @@ func (x *GetPeerSSHHostKeyResponse) GetFound() bool { type RequestJWTAuthRequest struct { state protoimpl.MessageState `protogen:"open.v1"` // hint for OIDC login_hint parameter (typically email address) - Hint *string `protobuf:"bytes,1,opt,name=hint,proto3,oneof" json:"hint,omitempty"` - unknownFields protoimpl.UnknownFields - sizeCache protoimpl.SizeCache + Hint *string `protobuf:"bytes,1,opt,name=hint,proto3,oneof" json:"hint,omitempty"` + // hasGraphicalSession tells the daemon that the caller has a graphical session, + // which decides whether PKCE or the device code flow is preferred. The daemon + // cannot detect this itself: it does not inherit the session environment. + HasGraphicalSession bool `protobuf:"varint,2,opt,name=hasGraphicalSession,proto3" json:"hasGraphicalSession,omitempty"` + unknownFields protoimpl.UnknownFields + sizeCache protoimpl.SizeCache } func (x *RequestJWTAuthRequest) Reset() { @@ -5658,6 +5674,13 @@ func (x *RequestJWTAuthRequest) GetHint() string { return "" } +func (x *RequestJWTAuthRequest) GetHasGraphicalSession() bool { + if x != nil { + return x.HasGraphicalSession + } + return false +} + // RequestJWTAuthResponse contains authentication flow information type RequestJWTAuthResponse struct { state protoimpl.MessageState `protogen:"open.v1"` @@ -5882,9 +5905,13 @@ type RequestExtendAuthSessionRequest struct { state protoimpl.MessageState `protogen:"open.v1"` // Optional OIDC login_hint (typically the user's email) to pre-fill the // IdP login form. - Hint *string `protobuf:"bytes,1,opt,name=hint,proto3,oneof" json:"hint,omitempty"` - unknownFields protoimpl.UnknownFields - sizeCache protoimpl.SizeCache + Hint *string `protobuf:"bytes,1,opt,name=hint,proto3,oneof" json:"hint,omitempty"` + // hasGraphicalSession tells the daemon that the caller has a graphical session, + // which decides whether PKCE or the device code flow is preferred. The daemon + // cannot detect this itself: it does not inherit the session environment. + HasGraphicalSession bool `protobuf:"varint,2,opt,name=hasGraphicalSession,proto3" json:"hasGraphicalSession,omitempty"` + unknownFields protoimpl.UnknownFields + sizeCache protoimpl.SizeCache } func (x *RequestExtendAuthSessionRequest) Reset() { @@ -5924,6 +5951,13 @@ func (x *RequestExtendAuthSessionRequest) GetHint() string { return "" } +func (x *RequestExtendAuthSessionRequest) GetHasGraphicalSession() bool { + if x != nil { + return x.HasGraphicalSession + } + return false +} + // RequestExtendAuthSessionResponse carries the verification URI the UI // should open in a browser. The daemon retains the flow state and resolves // it via WaitExtendAuthSession. @@ -7253,7 +7287,7 @@ const file_daemon_proto_rawDesc = "" + "\x12translatedHostname\x18\x04 \x01(\tR\x12translatedHostname\x128\n" + "\x0etranslatedPort\x18\x05 \x01(\v2\x10.daemon.PortInfoR\x0etranslatedPort\"G\n" + "\x17ForwardingRulesResponse\x12,\n" + - "\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xdc\x01\n" + + "\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\x84\x02\n" + "\x12DebugBundleRequest\x12\x1c\n" + "\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x1e\n" + "\n" + @@ -7264,7 +7298,8 @@ const file_daemon_proto_rawDesc = "" + "\n" + "cliVersion\x18\x06 \x01(\tR\n" + "cliVersion\x12&\n" + - "\x0euploadInsecure\x18\a \x01(\bR\x0euploadInsecure\"}\n" + + "\x0euploadInsecure\x18\a \x01(\bR\x0euploadInsecure\x12&\n" + + "\x0eanonymizeLevel\x18\b \x01(\tR\x0eanonymizeLevel\"}\n" + "\x13DebugBundleResponse\x12\x12\n" + "\x04path\x18\x01 \x01(\tR\x04path\x12 \n" + "\vuploadedKey\x18\x02 \x01(\tR\vuploadedKey\x120\n" + @@ -7490,9 +7525,10 @@ const file_daemon_proto_rawDesc = "" + "sshHostKey\x12\x16\n" + "\x06peerIP\x18\x02 \x01(\tR\x06peerIP\x12\x1a\n" + "\bpeerFQDN\x18\x03 \x01(\tR\bpeerFQDN\x12\x14\n" + - "\x05found\x18\x04 \x01(\bR\x05found\"9\n" + + "\x05found\x18\x04 \x01(\bR\x05found\"k\n" + "\x15RequestJWTAuthRequest\x12\x17\n" + - "\x04hint\x18\x01 \x01(\tH\x00R\x04hint\x88\x01\x01B\a\n" + + "\x04hint\x18\x01 \x01(\tH\x00R\x04hint\x88\x01\x01\x120\n" + + "\x13hasGraphicalSession\x18\x02 \x01(\bR\x13hasGraphicalSessionB\a\n" + "\x05_hint\"\x9a\x02\n" + "\x16RequestJWTAuthResponse\x12(\n" + "\x0fverificationURI\x18\x01 \x01(\tR\x0fverificationURI\x128\n" + @@ -7512,9 +7548,10 @@ const file_daemon_proto_rawDesc = "" + "\x14WaitJWTTokenResponse\x12\x14\n" + "\x05token\x18\x01 \x01(\tR\x05token\x12\x1c\n" + "\ttokenType\x18\x02 \x01(\tR\ttokenType\x12\x1c\n" + - "\texpiresIn\x18\x03 \x01(\x03R\texpiresIn\"C\n" + + "\texpiresIn\x18\x03 \x01(\x03R\texpiresIn\"u\n" + "\x1fRequestExtendAuthSessionRequest\x12\x17\n" + - "\x04hint\x18\x01 \x01(\tH\x00R\x04hint\x88\x01\x01B\a\n" + + "\x04hint\x18\x01 \x01(\tH\x00R\x04hint\x88\x01\x01\x120\n" + + "\x13hasGraphicalSession\x18\x02 \x01(\bR\x13hasGraphicalSessionB\a\n" + "\x05_hint\"\xe0\x01\n" + " RequestExtendAuthSessionResponse\x12(\n" + "\x0fverificationURI\x18\x01 \x01(\tR\x0fverificationURI\x128\n" + diff --git a/client/proto/daemon.proto b/client/proto/daemon.proto index 3c31156ec..a3e3f4500 100644 --- a/client/proto/daemon.proto +++ b/client/proto/daemon.proto @@ -540,6 +540,11 @@ message DebugBundleRequest { // untrusted TLS certificate. Restricted to privileged callers; for // self-hosted upload servers. bool uploadInsecure = 7; + // anonymizeLevel selects how much the anonymizer redacts: "default" + // (or empty) keeps internal IP ranges, "strict" also anonymizes them. + // Unknown values are treated as "strict". Only meaningful with anonymize; + // "strict" implies it. + string anonymizeLevel = 8; } message DebugBundleResponse { @@ -889,6 +894,10 @@ message GetPeerSSHHostKeyResponse { message RequestJWTAuthRequest { // hint for OIDC login_hint parameter (typically email address) optional string hint = 1; + // hasGraphicalSession tells the daemon that the caller has a graphical session, + // which decides whether PKCE or the device code flow is preferred. The daemon + // cannot detect this itself: it does not inherit the session environment. + bool hasGraphicalSession = 2; } // RequestJWTAuthResponse contains authentication flow information @@ -932,6 +941,10 @@ message RequestExtendAuthSessionRequest { // Optional OIDC login_hint (typically the user's email) to pre-fill the // IdP login form. optional string hint = 1; + // hasGraphicalSession tells the daemon that the caller has a graphical session, + // which decides whether PKCE or the device code flow is preferred. The daemon + // cannot detect this itself: it does not inherit the session environment. + bool hasGraphicalSession = 2; } // RequestExtendAuthSessionResponse carries the verification URI the UI diff --git a/client/server/debug.go b/client/server/debug.go index 60a401b0e..8f4a506b4 100644 --- a/client/server/debug.go +++ b/client/server/debug.go @@ -16,6 +16,7 @@ import ( "google.golang.org/grpc/codes" gstatus "google.golang.org/grpc/status" + "github.com/netbirdio/netbird/client/anonymize" "github.com/netbirdio/netbird/client/internal/debug" "github.com/netbirdio/netbird/client/internal/ipcauth" "github.com/netbirdio/netbird/client/proto" @@ -122,6 +123,7 @@ func (s *Server) generateDebugBundle(req *proto.DebugBundleRequest, uiOpener deb }, debug.BundleConfig{ Anonymize: req.GetAnonymize(), + AnonymizeLevel: anonymize.ParseLevel(req.GetAnonymizeLevel()), IncludeSystemInfo: req.GetSystemInfo(), LogFileCount: req.GetLogFileCount(), }, diff --git a/client/server/panic_windows.go b/client/server/panic_windows.go index 8592f12ad..4bed6662f 100644 --- a/client/server/panic_windows.go +++ b/client/server/panic_windows.go @@ -3,6 +3,7 @@ package server import ( + "errors" "fmt" "os" "path" @@ -69,7 +70,7 @@ func setStdHandle(f *os.File) error { handle := f.Fd() r0, _, e1 := setStdHandleFn.Call(stdErrorHandle, handle) if r0 == 0 { - if e1 != nil { + if !errors.Is(e1, syscall.Errno(0)) { return e1 } return syscall.EINVAL diff --git a/client/server/server.go b/client/server/server.go index a25ea88fc..d640b8521 100644 --- a/client/server/server.go +++ b/client/server/server.go @@ -1747,8 +1747,8 @@ func (s *Server) RequestJWTAuth( hint = profilemanager.GetLoginHint() } - isDesktop := isUnixRunningDesktop() - oAuthFlow, err := auth.NewOAuthFlow(ctx, config, isDesktop, false, hint) + // the daemon has no graphical session of its own, only the caller can answer this + oAuthFlow, err := auth.NewOAuthFlow(ctx, config, msg.GetHasGraphicalSession(), false, hint) if err != nil { return nil, gstatus.Errorf(codes.Internal, "failed to create OAuth flow: %v", err) } @@ -1851,8 +1851,8 @@ func (s *Server) RequestExtendAuthSession( hint = profilemanager.GetLoginHint() } - isDesktop := isUnixRunningDesktop() - oAuthFlow, err := auth.NewOAuthFlow(ctx, config, isDesktop, false, hint) + // the daemon has no graphical session of its own, only the caller can answer this + oAuthFlow, err := auth.NewOAuthFlow(ctx, config, msg.GetHasGraphicalSession(), false, hint) if err != nil { return nil, gstatus.Errorf(codes.Internal, "failed to create OAuth flow: %v", err) } @@ -2024,13 +2024,6 @@ func (s *Server) ExposeService(req *proto.ExposeServiceRequest, srv proto.Daemon return nil } -func isUnixRunningDesktop() bool { - if runtime.GOOS != "linux" && runtime.GOOS != "freebsd" { - return false - } - return os.Getenv("DESKTOP_SESSION") != "" || os.Getenv("XDG_CURRENT_DESKTOP") != "" -} - func (s *Server) runProbes(ctx context.Context, waitForProbeResult bool) { if s.connectClient == nil { return diff --git a/client/server/server_privileged_test.go b/client/server/server_privileged_test.go index 8b6f78f04..0366ccb31 100644 --- a/client/server/server_privileged_test.go +++ b/client/server/server_privileged_test.go @@ -10,7 +10,7 @@ import ( "testing" "time" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/stretchr/testify/require" "go.opentelemetry.io/otel" diff --git a/client/ssh/client/client.go b/client/ssh/client/client.go index 4180849cd..31143a4f4 100644 --- a/client/ssh/client/client.go +++ b/client/ssh/client/client.go @@ -313,21 +313,23 @@ func Dial(ctx context.Context, addr, user string, opts DialOptions) (*Client, er // dialSSH establishes an SSH connection without JWT authentication func dialSSH(ctx context.Context, network, addr string, config *ssh.ClientConfig) (*Client, error) { + if config.Timeout > 0 { + var cancel context.CancelFunc + ctx, cancel = context.WithTimeout(ctx, config.Timeout) + defer cancel() + } + dialer := &net.Dialer{} conn, err := dialer.DialContext(ctx, network, addr) if err != nil { return nil, fmt.Errorf("dial %s: %w", addr, err) } - clientConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config) + client, err := nbssh.Handshake(ctx, conn, addr, config) if err != nil { - if closeErr := conn.Close(); closeErr != nil { - log.Debugf("connection close after handshake failure: %v", closeErr) - } - return nil, fmt.Errorf("ssh handshake: %w", err) + return nil, err } - client := ssh.NewClient(clientConn, chans, reqs) return &Client{ client: client, }, nil diff --git a/client/ssh/client/terminal_unix.go b/client/ssh/client/terminal_unix.go index aaa3418f9..a963dc8be 100644 --- a/client/ssh/client/terminal_unix.go +++ b/client/ssh/client/terminal_unix.go @@ -12,6 +12,8 @@ import ( log "github.com/sirupsen/logrus" "golang.org/x/crypto/ssh" "golang.org/x/term" + + nbssh "github.com/netbirdio/netbird/client/ssh" ) func (c *Client) setupTerminalMode(ctx context.Context, session *ssh.Session) error { @@ -82,37 +84,7 @@ func (c *Client) setupTerminal(session *ssh.Session, fd int) error { return fmt.Errorf("get terminal size: %w", err) } - modes := ssh.TerminalModes{ - ssh.ECHO: 1, - ssh.TTY_OP_ISPEED: 14400, - ssh.TTY_OP_OSPEED: 14400, - // Ctrl+C - ssh.VINTR: 3, - // Ctrl+\ - ssh.VQUIT: 28, - // Backspace - ssh.VERASE: 127, - // Ctrl+U - ssh.VKILL: 21, - // Ctrl+D - ssh.VEOF: 4, - ssh.VEOL: 0, - ssh.VEOL2: 0, - // Ctrl+Q - ssh.VSTART: 17, - // Ctrl+S - ssh.VSTOP: 19, - // Ctrl+Z - ssh.VSUSP: 26, - // Ctrl+O - ssh.VDISCARD: 15, - // Ctrl+R - ssh.VREPRINT: 18, - // Ctrl+W - ssh.VWERASE: 23, - // Ctrl+V - ssh.VLNEXT: 22, - } + modes := nbssh.DefaultTerminalModes terminal := os.Getenv("TERM") if terminal == "" { diff --git a/client/ssh/client/terminal_windows.go b/client/ssh/client/terminal_windows.go index 462438317..c6156fc26 100644 --- a/client/ssh/client/terminal_windows.go +++ b/client/ssh/client/terminal_windows.go @@ -10,6 +10,8 @@ import ( log "github.com/sirupsen/logrus" "golang.org/x/crypto/ssh" + + nbssh "github.com/netbirdio/netbird/client/ssh" ) const ( @@ -80,28 +82,14 @@ func (c *Client) setupTerminalMode(_ context.Context, session *ssh.Session) erro w, h := c.getWindowsConsoleSize() modes := ssh.TerminalModes{ - ssh.ECHO: 1, - ssh.TTY_OP_ISPEED: 14400, - ssh.TTY_OP_OSPEED: 14400, - ssh.ICRNL: 1, - ssh.OPOST: 1, - ssh.ONLCR: 1, - ssh.ISIG: 1, - ssh.ICANON: 1, - ssh.VINTR: 3, // Ctrl+C - ssh.VQUIT: 28, // Ctrl+\ - ssh.VERASE: 127, // Backspace - ssh.VKILL: 21, // Ctrl+U - ssh.VEOF: 4, // Ctrl+D - ssh.VEOL: 0, - ssh.VEOL2: 0, - ssh.VSTART: 17, // Ctrl+Q - ssh.VSTOP: 19, // Ctrl+S - ssh.VSUSP: 26, // Ctrl+Z - ssh.VDISCARD: 15, // Ctrl+O - ssh.VWERASE: 23, // Ctrl+W - ssh.VLNEXT: 22, // Ctrl+V - ssh.VREPRINT: 18, // Ctrl+R + ssh.ICRNL: 1, + ssh.OPOST: 1, + ssh.ONLCR: 1, + ssh.ISIG: 1, + ssh.ICANON: 1, + } + for mode, value := range nbssh.DefaultTerminalModes { + modes[mode] = value } if err := session.RequestPty("xterm-256color", h, w, modes); err != nil { diff --git a/client/ssh/common.go b/client/ssh/common.go index 92e647b7d..4ebf8842a 100644 --- a/client/ssh/common.go +++ b/client/ssh/common.go @@ -13,6 +13,7 @@ import ( "golang.org/x/crypto/ssh" "github.com/netbirdio/netbird/client/proto" + "github.com/netbirdio/netbird/util" ) const ( @@ -34,6 +35,19 @@ type HostKeyVerifier interface { VerifySSHHostKey(peerAddress string, key []byte) error } +// PeerKeyLookup returns the stored SSH host key for a peer address. +type PeerKeyLookup func(peerAddress string) ([]byte, bool) + +// VerifySSHHostKey implements HostKeyVerifier by looking up the stored key +// and comparing it against the presented key. +func (l PeerKeyLookup) VerifySSHHostKey(peerAddress string, presentedKey []byte) error { + storedKey, found := l(peerAddress) + if !found { + return ErrPeerNotFound + } + return VerifyHostKey(storedKey, presentedKey, peerAddress) +} + // DaemonHostKeyVerifier implements HostKeyVerifier using the NetBird daemon type DaemonHostKeyVerifier struct { client proto.DaemonServiceClient @@ -92,7 +106,8 @@ func printAuthInstructions(stderr io.Writer, authResponse *proto.RequestJWTAuthR // RequestJWTToken requests or retrieves a JWT token for SSH authentication func RequestJWTToken(ctx context.Context, client proto.DaemonServiceClient, stdout, stderr io.Writer, useCache bool, hint string, openBrowser func(string) error) (string, error) { - req := &proto.RequestJWTAuthRequest{} + // the ssh client runs in the user's session, the daemon does not: tell it what we can see + req := &proto.RequestJWTAuthRequest{HasGraphicalSession: util.HasGraphicalSession()} if hint != "" { req.Hint = &hint } @@ -193,4 +208,3 @@ func buildAddressList(hostname string, remote net.Addr) []string { } return addresses } - diff --git a/client/ssh/handshake.go b/client/ssh/handshake.go new file mode 100644 index 000000000..e78a806be --- /dev/null +++ b/client/ssh/handshake.go @@ -0,0 +1,45 @@ +package ssh + +import ( + "context" + "fmt" + "io" + "net" + "time" + + log "github.com/sirupsen/logrus" + "golang.org/x/crypto/ssh" +) + +// Handshake runs the SSH client handshake on an already dialed conn and +// returns the resulting client. Dialing bounds only the TCP establishment; +// without a deadline on the socket a peer that accepts and then goes silent +// blocks the handshake forever, so the context deadline is applied to conn +// for the duration of the handshake. conn is closed on any error. +func Handshake(ctx context.Context, conn net.Conn, addr string, config *ssh.ClientConfig) (*ssh.Client, error) { + if deadline, ok := ctx.Deadline(); ok { + if err := conn.SetDeadline(deadline); err != nil { + closeHandshake(conn, "conn after deadline error") + return nil, fmt.Errorf("set handshake deadline: %w", err) + } + } + + sshConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config) + if err != nil { + closeHandshake(conn, "conn after handshake error") + return nil, fmt.Errorf("ssh handshake: %w", err) + } + + if err := conn.SetDeadline(time.Time{}); err != nil { + closeHandshake(sshConn, "ssh conn after deadline clear error") + return nil, fmt.Errorf("clear handshake deadline: %w", err) + } + + return ssh.NewClient(sshConn, chans, reqs), nil +} + +func closeHandshake(c io.Closer, label string) { + if err := c.Close(); err != nil { + log.Debugf("ssh: close %s: %v", label, err) + } +} diff --git a/client/ssh/proxy/proxy.go b/client/ssh/proxy/proxy.go index 721810edb..070515b57 100644 --- a/client/ssh/proxy/proxy.go +++ b/client/ssh/proxy/proxy.go @@ -610,13 +610,10 @@ func (p *SSHProxy) dialBackend(ctx context.Context, addr, user, jwtToken string) return nil, fmt.Errorf("connect to server: %w", err) } - clientConn, chans, reqs, err := cryptossh.NewClientConn(conn, addr, config) - if err != nil { - _ = conn.Close() - return nil, fmt.Errorf("SSH handshake: %w", err) - } + handshakeCtx, cancel := context.WithTimeout(ctx, sshHandshakeTimeout) + defer cancel() - return cryptossh.NewClient(clientConn, chans, reqs), nil + return nbssh.Handshake(handshakeCtx, conn, addr, config) } func (p *SSHProxy) verifyHostKey(hostname string, remote net.Addr, key cryptossh.PublicKey) error { diff --git a/client/ssh/server/command_execution.go b/client/ssh/server/command_execution.go index b0a85fe4b..c8b3240d0 100644 --- a/client/ssh/server/command_execution.go +++ b/client/ssh/server/command_execution.go @@ -75,8 +75,8 @@ func (s *Server) createCommand(logger *log.Entry, privilegeResult PrivilegeCheck } // Try su first for system integration (PAM/audit) when privileged - cmd, err := s.createSuCommand(logger, session, localUser, hasPty) - if err != nil || privilegeResult.UsedFallback { + cmd, err := s.createSuCommand(logger, session, localUser, hasPty) //nolint:staticcheck + if err != nil || privilegeResult.UsedFallback { //nolint:staticcheck // always errors on platforms without su logger.Debugf("su command failed, falling back to executor: %v", err) cmd, cleanup, err := s.createExecutorCommand(logger, session, localUser, hasPty) if err != nil { diff --git a/client/ssh/server/command_execution_windows.go b/client/ssh/server/command_execution_windows.go index e1ba777f6..feb8daa26 100644 --- a/client/ssh/server/command_execution_windows.go +++ b/client/ssh/server/command_execution_windows.go @@ -243,7 +243,7 @@ func (s *Server) setUserEnvironmentVariables(envMap map[string]string, userProfi // prepareCommandEnv prepares environment variables for command execution on Windows func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, session ssh.Session) []string { - username, domain := s.parseUsername(localUser.Username) + username, domain := parseUsername(localUser.Username) userEnv, err := s.getUserEnvironment(logger, username, domain) if err != nil { log.Debugf("failed to get user environment for %s\\%s, using fallback: %v", domain, username, err) @@ -383,7 +383,7 @@ func (s *Server) executeCommandWithPty(logger *log.Entry, session ssh.Session, _ return false } - username, domain := s.parseUsername(localUser.Username) + username, domain := parseUsername(localUser.Username) shell := getUserShell(localUser.Uid) req := PtyExecutionRequest{ diff --git a/client/ssh/server/port_forwarding.go b/client/ssh/server/port_forwarding.go index a47fdb48a..81d3b9173 100644 --- a/client/ssh/server/port_forwarding.go +++ b/client/ssh/server/port_forwarding.go @@ -133,7 +133,12 @@ func (s *Server) checkPrivilegedPortAccess(forwardType string, port uint32, resu return nil } - if result.User != nil && isPrivilegedUsername(result.User.Username) { + // Only uid 0 may bind below the threshold, which is the kernel's own rule and + // is asked directly rather than through isPrivilegedOrUnknown: that helper + // reports an account it cannot evaluate as privileged, which is safe for a + // refusal and unsafe for a grant such as this one. Windows has returned + // above, so Uid here is a Unix uid and never a SID. + if result.User != nil && result.User.Uid == "0" { return nil } diff --git a/client/ssh/server/privileges_other.go b/client/ssh/server/privileges_other.go new file mode 100644 index 000000000..89440dea8 --- /dev/null +++ b/client/ssh/server/privileges_other.go @@ -0,0 +1,16 @@ +//go:build !windows + +package server + +// isProcessElevated is only meaningful on Windows; other platforms use the +// effective UID check in isCurrentProcessPrivileged. +func isProcessElevated() bool { + return false +} + +// isWindowsAccountPrivilegedOrUnknown is only reachable on Windows. Report +// privileged on other platforms so a caller refusing privileged accounts fails +// closed. +func isWindowsAccountPrivilegedOrUnknown(string) bool { + return true +} diff --git a/client/ssh/server/privileges_windows.go b/client/ssh/server/privileges_windows.go new file mode 100644 index 000000000..41ea00fd7 --- /dev/null +++ b/client/ssh/server/privileges_windows.go @@ -0,0 +1,228 @@ +//go:build windows + +package server + +import ( + "fmt" + "strings" + "unsafe" + + log "github.com/sirupsen/logrus" + "golang.org/x/sys/windows" +) + +var ( + netapi32 = windows.NewLazySystemDLL("netapi32.dll") + procNetUserGetLocalGroups = netapi32.NewProc("NetUserGetLocalGroups") +) + +const ( + // lgIncludeIndirect makes NetUserGetLocalGroups also return local groups + // the user belongs to through a global group. + lgIncludeIndirect = 0x1 + maxPreferredLength = 0xFFFFFFFF +) + +// localGroupUsersInfo0 mirrors LOCALGROUP_USERS_INFO_0. +type localGroupUsersInfo0 struct { + name *uint16 +} + +// isProcessElevated reports whether the current process token is elevated +// (TokenElevation): true for elevated administrators, the built-in +// Administrator, administrators with UAC disabled, and SYSTEM; false for +// standard users and administrators running with a UAC-filtered token. +func isProcessElevated() bool { + return windows.GetCurrentProcessToken().IsElevated() +} + +// isWindowsAccountPrivilegedOrUnknown reports whether the account is privileged +// on this machine: a well-known service account, a built-in Administrator +// (RID 500), or a member of the local Administrators group, directly or through +// nested groups. +// +// An account whose privilege cannot be determined counts as privileged, which +// is why the name says "or unknown". That is fail-closed for a caller that +// refuses privileged accounts, and fail-open for a caller that grants something +// to them, so only the former may use this. +func isWindowsAccountPrivilegedOrUnknown(username string) bool { + sid, _, _, err := windows.LookupSID("", username) + if err != nil { + log.Warnf("privilege check: SID lookup for %q failed, treating as privileged: %v", username, err) + return true + } + + if isPrivilegedUserSID(sid) { + return true + } + + member, err := isLocalAdminsMember(username) + if err != nil { + log.Warnf("privilege check: cannot determine Administrators membership for %q, treating as privileged: %v", username, err) + return true + } + return member +} + +// isPrivilegedUserSID reports whether the SID itself identifies a privileged +// principal, without consulting group membership. +func isPrivilegedUserSID(sid *windows.SID) bool { + wellKnown := []windows.WELL_KNOWN_SID_TYPE{ + windows.WinLocalSystemSid, + windows.WinLocalServiceSid, + windows.WinNetworkServiceSid, + windows.WinBuiltinAdministratorsSid, + } + for _, sidType := range wellKnown { + if sid.IsWellKnown(sidType) { + return true + } + } + return isBuiltinAdministratorSID(sid) +} + +// isBuiltinAdministratorSID reports whether the SID is a machine or domain +// built-in Administrator account (S-1-5-21-...-500). RID 500 is reserved for +// that account; it can be renamed but cannot be removed from the +// Administrators group. +func isBuiltinAdministratorSID(sid *windows.SID) bool { + if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY { + return false + } + count := sid.SubAuthorityCount() + if count < 2 || sid.SubAuthority(0) != 21 { + return false + } + return sid.SubAuthority(uint32(count-1)) == 500 +} + +// isLocalAdminsMember reports whether the account is a member of the local +// Administrators group. +// +// Local accounts are checked against the local SAM, which is authoritative for +// them and, unlike a token, cannot under-report: UAC filters the tokens of +// local administrators, and a filtered token carries Administrators as +// deny-only, which a membership check on the token would read as "not a +// member". Domain accounts are exempt from that filtering, so for them an S4U +// token is preferred because its group list is LSA's transitive expansion and +// therefore covers nested and universal groups plus the machine's own local +// groups. NetUserGetLocalGroups expands only one global-group hop but needs no +// logon, so it serves as the fallback when no token can be obtained. +func isLocalAdminsMember(username string) (bool, error) { + adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid) + if err != nil { + return false, fmt.Errorf("create Administrators SID: %w", err) + } + + account, domain := parseUsername(username) + if NewPrivilegeDropper().isLocalUser(domain) { + return localGroupsContainSID(account, adminSid) + } + + member, s4uErr := s4uTokenIsMember(account, domain, adminSid) + if s4uErr == nil { + return member, nil + } + log.Debugf("privilege check: S4U membership check for %q failed, falling back to local group enumeration: %v", username, s4uErr) + + member, err = localGroupsContainSID(buildUserCpn(account, domain), adminSid) + if err != nil { + return false, fmt.Errorf("S4U check: %w; local group enumeration: %w", s4uErr, err) + } + return member, nil +} + +// s4uTokenIsMember obtains an S4U token for the account and checks whether the +// given SID is enabled in it. +func s4uTokenIsMember(account, domain string, sid *windows.SID) (bool, error) { + token, err := generateS4UUserToken(log.NewEntry(log.StandardLogger()), account, domain) + if err != nil { + return false, err + } + defer func() { + if err := windows.CloseHandle(token); err != nil { + log.Debugf("close S4U token: %v", err) + } + }() + return windows.Token(token).IsMember(sid) +} + +// localGroupsContainSID reports whether the wanted group is among the local +// groups the account belongs to, directly or through a global group. +// +// The wanted SID is resolved to its group name once and compared against the +// enumerated names. Well-known SIDs resolve from a static table, so that lookup +// needs no domain controller, and it keeps the comparison correct for a renamed +// or localized group because both sides then carry the new name. Resolving each +// enumerated name back to a SID instead would add a lookup per group that can +// block until it times out while a domain controller is unreachable, and cannot +// change the outcome: the names enumerated here are local groups of this +// machine, whose names are unique, so a name match identifies the group. +// +// A failure to resolve the wanted SID is returned rather than reported as +// "not a member", so a privilege check built on this fails closed. +func localGroupsContainSID(username string, want *windows.SID) (bool, error) { + wantName, _, _, err := want.LookupAccount("") + if err != nil { + return false, fmt.Errorf("resolve group SID %s to a name: %w", want, err) + } + + groups, err := netUserGetLocalGroups(username) + if err != nil { + return false, err + } + + for _, group := range groups { + if strings.EqualFold(group, wantName) { + return true, nil + } + } + return false, nil +} + +// netUserGetLocalGroups returns the names of the local groups the account is a +// member of, including indirect membership through global groups. +func netUserGetLocalGroups(username string) ([]string, error) { + name16, err := windows.UTF16PtrFromString(username) + if err != nil { + return nil, fmt.Errorf("convert username: %w", err) + } + + var buf *byte + var entriesRead, totalEntries uint32 + status, _, _ := procNetUserGetLocalGroups.Call( + 0, // local server + uintptr(unsafe.Pointer(name16)), + 0, // level 0: LOCALGROUP_USERS_INFO_0 + lgIncludeIndirect, + uintptr(unsafe.Pointer(&buf)), + maxPreferredLength, + uintptr(unsafe.Pointer(&entriesRead)), + uintptr(unsafe.Pointer(&totalEntries)), + ) + if status != 0 { + return nil, fmt.Errorf("NetUserGetLocalGroups for %q: status %d", username, status) + } + if buf == nil { + return nil, nil + } + defer func() { + if err := windows.NetApiBufferFree(buf); err != nil { + log.Debugf("free NetApi buffer: %v", err) + } + }() + + // MAX_PREFERRED_LENGTH makes the API allocate as much as it needs, so a + // short read is not expected. Report it rather than silently returning a + // subset of the account's groups. + if entriesRead != totalEntries { + return nil, fmt.Errorf("NetUserGetLocalGroups for %q returned %d of %d groups", username, entriesRead, totalEntries) + } + + entries := unsafe.Slice((*localGroupUsersInfo0)(unsafe.Pointer(buf)), entriesRead) + groups := make([]string, 0, entriesRead) + for _, entry := range entries { + groups = append(groups, windows.UTF16PtrToString(entry.name)) + } + return groups, nil +} diff --git a/client/ssh/server/privileges_windows_test.go b/client/ssh/server/privileges_windows_test.go new file mode 100644 index 000000000..983fccdf7 --- /dev/null +++ b/client/ssh/server/privileges_windows_test.go @@ -0,0 +1,293 @@ +//go:build windows + +package server + +import ( + "os/user" + "testing" + "unsafe" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + "golang.org/x/sys/windows" +) + +// filterNormalAccount limits NetUserEnum to normal user accounts. +const filterNormalAccount = 0x2 + +// TOKEN_ELEVATION_TYPE values. +const ( + tokenElevationTypeDefault = 1 + tokenElevationTypeFull = 2 + tokenElevationTypeLimited = 3 +) + +// tokenElevationType reads TokenElevationType from a token. +func tokenElevationType(token windows.Token) (uint32, error) { + var elevationType, returnedLen uint32 + err := windows.GetTokenInformation(token, windows.TokenElevationType, + (*byte)(unsafe.Pointer(&elevationType)), uint32(unsafe.Sizeof(elevationType)), &returnedLen) + if err != nil { + return 0, err + } + return elevationType, nil +} + +// userInfo0 mirrors USER_INFO_0. +type userInfo0 struct { + name *uint16 +} + +func mustParseSID(t *testing.T, s string) *windows.SID { + t.Helper() + sid, err := windows.StringToSid(s) + require.NoError(t, err, "parse SID %s", s) + return sid +} + +// localAccountNames returns the names of the local user accounts. +func localAccountNames(t *testing.T) []string { + t.Helper() + + var buf *byte + var entriesRead, totalEntries, resume uint32 + err := windows.NetUserEnum(nil, 0, filterNormalAccount, &buf, maxPreferredLength, + &entriesRead, &totalEntries, &resume) + require.NoError(t, err, "enumerate local users") + t.Cleanup(func() { + require.NoError(t, windows.NetApiBufferFree(buf), "free NetApi buffer") + }) + + entries := unsafe.Slice((*userInfo0)(unsafe.Pointer(buf)), entriesRead) + names := make([]string, 0, entriesRead) + for _, entry := range entries { + names = append(names, windows.UTF16PtrToString(entry.name)) + } + return names +} + +// localAccountNameByRID returns the name of the local account carrying the +// given RID. Accounts such as Administrator and Guest can be renamed and are +// localized, so tests must not name them literally. +func localAccountNameByRID(t *testing.T, rid uint32) string { + t.Helper() + + for _, name := range localAccountNames(t) { + sid, _, _, err := windows.LookupSID("", name) + if err != nil { + continue + } + if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY { + continue + } + count := sid.SubAuthorityCount() + if count < 2 || sid.SubAuthority(0) != 21 { + continue + } + if sid.SubAuthority(uint32(count-1)) == rid { + return name + } + } + + t.Fatalf("no local account with RID %d", rid) + return "" +} + +// wellKnownAccountName resolves a well-known SID to the qualified account name +// the local system uses for it, which is localized. +func wellKnownAccountName(t *testing.T, sidType windows.WELL_KNOWN_SID_TYPE) string { + t.Helper() + + sid, err := windows.CreateWellKnownSid(sidType) + require.NoError(t, err, "create well-known SID") + name, domain, _, err := sid.LookupAccount("") + require.NoError(t, err, "resolve %s to an account name", sid) + if domain == "" { + return name + } + return domain + `\` + name +} + +func TestIsBuiltinAdministratorSID(t *testing.T) { + tests := []struct { + name string + sid string + want bool + }{ + {"machine_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true}, + {"domain_administrator", "S-1-5-21-3390233681-4087452608-412898826-500", true}, + {"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false}, + {"guest_account", "S-1-5-21-1111111111-2222222222-3333333333-501", false}, + {"domain_admins_group", "S-1-5-21-1111111111-2222222222-3333333333-512", false}, + {"system", "S-1-5-18", false}, + {"administrators_group", "S-1-5-32-544", false}, + {"non_nt_authority", "S-1-1-0", false}, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + result := isBuiltinAdministratorSID(mustParseSID(t, tt.sid)) + assert.Equal(t, tt.want, result, "RID 500 detection for %s", tt.sid) + }) + } +} + +func TestIsPrivilegedUserSID(t *testing.T) { + tests := []struct { + name string + sid string + want bool + }{ + {"local_system", "S-1-5-18", true}, + {"local_service", "S-1-5-19", true}, + {"network_service", "S-1-5-20", true}, + {"administrators_group", "S-1-5-32-544", true}, + {"builtin_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true}, + {"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false}, + {"users_group", "S-1-5-32-545", false}, + {"everyone", "S-1-1-0", false}, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + result := isPrivilegedUserSID(mustParseSID(t, tt.sid)) + assert.Equal(t, tt.want, result, "SID privilege classification for %s", tt.sid) + }) + } +} + +func TestIsWindowsAccountPrivilegedOrUnknown(t *testing.T) { + tests := []struct { + name string + username string + want bool + }{ + {"system", wellKnownAccountName(t, windows.WinLocalSystemSid), true}, + {"local_service", wellKnownAccountName(t, windows.WinLocalServiceSid), true}, + {"network_service", wellKnownAccountName(t, windows.WinNetworkServiceSid), true}, + {"administrators_group", wellKnownAccountName(t, windows.WinBuiltinAdministratorsSid), true}, + // The built-in Administrator (RID 500) and Guest (RID 501) accounts + // exist on every Windows installation, though they may be disabled. + {"builtin_administrator", localAccountNameByRID(t, 500), true}, + {"guest", localAccountNameByRID(t, 501), false}, + // Unresolvable accounts fail closed. + {"nonexistent_user", "netbird-no-such-user", true}, + {"empty_username", "", true}, + } + + for _, tt := range tests { + t.Run(tt.name, func(t *testing.T) { + result := isWindowsAccountPrivilegedOrUnknown(tt.username) + assert.Equal(t, tt.want, result, "account privilege classification for %q", tt.username) + }) + } +} + +func TestIsProcessElevated(t *testing.T) { + elevated := isProcessElevated() + + // TokenElevationType is a second, independent view of the same token: + // Full means elevated and Limited means a filtered administrator, while + // Default covers both a standard user and an administrator with no linked + // token (UAC off, the built-in Administrator, SYSTEM), so it implies nothing. + elevationType, err := tokenElevationType(windows.GetCurrentProcessToken()) + require.NoError(t, err, "read token elevation type") + + adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid) + require.NoError(t, err, "create Administrators SID") + + // Token(0) makes CheckTokenMembership evaluate the caller's own token. It + // counts only enabled SIDs, so a filtered administrator reports false here. + member, err := windows.Token(0).IsMember(adminSid) + require.NoError(t, err, "check own Administrators membership") + + t.Logf("elevated=%v elevationType=%d memberOfAdministrators=%v", elevated, elevationType, member) + + switch elevationType { + case tokenElevationTypeFull: + assert.True(t, elevated, "a token of elevation type Full must report elevated") + case tokenElevationTypeLimited: + assert.False(t, elevated, "a filtered administrator token must not report elevated") + } + + // Administrators enabled in the token means the token wields administrative + // rights, which is what elevation reports. + if member { + assert.True(t, elevated, "token with enabled Administrators membership must report elevated") + } +} + +// TestS4UMembershipAgreesWithLocalGroups exercises the S4U token path used +// for domain accounts. S4U logons need the TCB privilege, so the test runs +// only as SYSTEM (which is how CI executes the suite). For local accounts the +// token's Administrators membership must agree with the SAM enumeration. +func TestS4UMembershipAgreesWithLocalGroups(t *testing.T) { + system, err := windows.CreateWellKnownSid(windows.WinLocalSystemSid) + require.NoError(t, err, "create SYSTEM SID") + current, err := user.Current() + require.NoError(t, err, "get current user") + if current.Uid != system.String() { + t.Skipf("S4U logon requires SYSTEM (running as %s)", current.Username) + } + + adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid) + require.NoError(t, err, "create Administrators SID") + + checked := 0 + for _, name := range localAccountNames(t) { + viaToken, err := s4uTokenIsMember(name, ".", adminSid) + if err != nil { + // Disabled or logon-restricted accounts cannot get an S4U logon. + t.Logf("skipping %s: %v", name, err) + continue + } + viaSAM, err := localGroupsContainSID(name, adminSid) + require.NoError(t, err, "enumerate local groups for %s", name) + + assert.Equal(t, viaSAM, viaToken, "S4U token and SAM enumeration must agree on Administrators membership for %s", name) + checked++ + } + // Ineligible accounts are skipped, so without this the test could report + // success while comparing nothing at all. + require.Positive(t, checked, "no local account completed an S4U logon, so nothing was compared") + t.Logf("checked %d local accounts via S4U", checked) +} + +// TestLocalGroupsContainSID_Administrator checks the positive case against the +// built-in Administrator, a member of Administrators on every installation. +func TestLocalGroupsContainSID_Administrator(t *testing.T) { + adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid) + require.NoError(t, err, "create Administrators SID") + + administrator := localAccountNameByRID(t, 500) + member, err := localGroupsContainSID(administrator, adminSid) + require.NoError(t, err, "enumerate local groups for %s", administrator) + assert.True(t, member, "%s is a member of the Administrators group", administrator) +} + +// TestLocalGroupsContainSID_UnresolvableGroupFailsClosed covers a wanted SID +// that resolves to no group: the error must surface rather than being reported +// as "not a member", so the privilege check treats the account as privileged. +func TestLocalGroupsContainSID_UnresolvableGroupFailsClosed(t *testing.T) { + unknown := mustParseSID(t, "S-1-5-21-1111111111-2222222222-3333333333-4444") + + _, err := localGroupsContainSID(localAccountNameByRID(t, 500), unknown) + require.Error(t, err, "must report an error when the wanted group cannot be identified") +} + +func TestLocalGroupsContainSID_Guest(t *testing.T) { + guestsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinGuestsSid) + require.NoError(t, err, "create Guests SID") + adminsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid) + require.NoError(t, err, "create Administrators SID") + + guest := localAccountNameByRID(t, 501) + + inGuests, err := localGroupsContainSID(guest, guestsSid) + require.NoError(t, err, "enumerate local groups for %s", guest) + assert.True(t, inGuests, "%s is a member of the Guests group", guest) + + inAdmins, err := localGroupsContainSID(guest, adminsSid) + require.NoError(t, err, "enumerate local groups for %s", guest) + assert.False(t, inAdmins, "%s is not a member of the Administrators group", guest) +} diff --git a/client/ssh/server/server_config_test.go b/client/ssh/server/server_config_test.go index f70e29963..983bd7a43 100644 --- a/client/ssh/server/server_config_test.go +++ b/client/ssh/server/server_config_test.go @@ -239,6 +239,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType string port uint32 username string + uid string expectError bool errorMsg string skipOnWindows bool @@ -248,6 +249,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType: "remote", port: 80, username: "testuser", + uid: "1000", expectError: true, errorMsg: "cannot bind to privileged port", skipOnWindows: true, @@ -257,6 +259,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType: "tcpip-forward", port: 443, username: "testuser", + uid: "1000", expectError: true, errorMsg: "cannot bind to privileged port", skipOnWindows: true, @@ -266,6 +269,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType: "remote", port: 8080, username: "testuser", + uid: "1000", expectError: false, }, { @@ -273,6 +277,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType: "remote", port: 0, username: "testuser", + uid: "1000", expectError: false, }, { @@ -280,13 +285,35 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { forwardType: "remote", port: 22, username: "root", + uid: "0", expectError: false, }, + { + // Only uid 0 is privileged, whatever the account is called. + name: "uid 0 under another name may bind a privileged port", + forwardType: "remote", + port: 22, + username: "toor", + uid: "0", + expectError: false, + skipOnWindows: true, + }, + { + name: "account named root without uid 0 may not", + forwardType: "remote", + port: 22, + username: "root", + uid: "1000", + expectError: true, + errorMsg: "cannot bind to privileged port", + skipOnWindows: true, + }, { name: "local forward privileged port allowed for non-root", forwardType: "local", port: 80, username: "testuser", + uid: "1000", expectError: false, }, } @@ -299,7 +326,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) { result := PrivilegeCheckResult{ Allowed: true, - User: &user.User{Username: tt.username}, + User: &user.User{Username: tt.username, Uid: tt.uid}, } err := server.checkPrivilegedPortAccess(tt.forwardType, tt.port, result) @@ -420,6 +447,13 @@ func TestServer_PortConflictHandling(t *testing.T) { func TestServer_IsPrivilegedUser(t *testing.T) { + // Windows classification depends on account SIDs and group membership, and + // the accounts involved carry localized, renameable names. It is covered by + // TestIsWindowsAccountPrivileged, which resolves them from well-known SIDs. + if runtime.GOOS == "windows" { + t.Skip("covered by TestIsWindowsAccountPrivileged") + } + tests := []struct { username string expected bool @@ -440,44 +474,16 @@ func TestServer_IsPrivilegedUser(t *testing.T) { expected: false, description: "empty username should not be privileged", }, - } - - // Add Windows-specific tests - if runtime.GOOS == "windows" { - tests = append(tests, []struct { - username string - expected bool - description string - }{ - { - username: "Administrator", - expected: true, - description: "Administrator should be considered privileged on Windows", - }, - { - username: "administrator", - expected: true, - description: "administrator should be considered privileged on Windows (case insensitive)", - }, - }...) - } else { - // On non-Windows systems, Administrator should not be privileged - tests = append(tests, []struct { - username string - expected bool - description string - }{ - { - username: "Administrator", - expected: false, - description: "Administrator should not be privileged on non-Windows systems", - }, - }...) + { + username: "Administrator", + expected: false, + description: "Administrator should not be privileged on non-Windows systems", + }, } for _, tt := range tests { t.Run(tt.description, func(t *testing.T) { - result := isPrivilegedUsername(tt.username) + result := isPrivilegedOrUnknown(tt.username) assert.Equal(t, tt.expected, result, tt.description) }) } diff --git a/client/ssh/server/sftp_windows.go b/client/ssh/server/sftp_windows.go index dc532b9e7..25cd17298 100644 --- a/client/ssh/server/sftp_windows.go +++ b/client/ssh/server/sftp_windows.go @@ -17,7 +17,7 @@ import ( // createSftpCommand creates a Windows SFTP command with user switching. // The caller must close the returned token handle after starting the process. func (s *Server) createSftpCommand(targetUser *user.User, sess ssh.Session) (*exec.Cmd, windows.Token, error) { - username, domain := s.parseUsername(targetUser.Username) + username, domain := parseUsername(targetUser.Username) netbirdPath, err := os.Executable() if err != nil { diff --git a/client/ssh/server/user_utils.go b/client/ssh/server/user_utils.go index bc2aa2d7d..6c8142b30 100644 --- a/client/ssh/server/user_utils.go +++ b/client/ssh/server/user_utils.go @@ -16,11 +16,6 @@ var ( ErrPrivilegedUserSwitch = errors.New("cannot switch to privileged user - current user lacks required privileges") ) -// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.) -func isPlatformUnix() bool { - return getCurrentOS() != "windows" -} - // Dependency injection variables for testing - allows mocking dynamic runtime checks var ( getCurrentUser = currentUserWithGetent @@ -29,6 +24,9 @@ var ( getIsProcessPrivileged = isCurrentProcessPrivileged getEuid = os.Geteuid + + getProcessElevated = isProcessElevated + getWindowsAccountPrivilegedOrUnknown = isWindowsAccountPrivilegedOrUnknown ) const ( @@ -65,6 +63,13 @@ type PrivilegeCheckResult struct { RequiresUserSwitching bool } +// privilegeCheckContext holds all context needed for privilege checking +type privilegeCheckContext struct { + currentUser *user.User + currentUserPrivileged bool + allowRoot bool +} + // CheckPrivileges performs comprehensive privilege checking for all SSH features. // This is the single source of truth for privilege decisions across the SSH server. func (s *Server) CheckPrivileges(req PrivilegeCheckRequest) PrivilegeCheckResult { @@ -75,7 +80,7 @@ func (s *Server) CheckPrivileges(req PrivilegeCheckRequest) PrivilegeCheckResult // Handle empty username case - but still check root access controls if req.RequestedUsername == "" { - if isPrivilegedUsername(context.currentUser.Username) && !context.allowRoot { + if isPrivilegedOrUnknown(context.currentUser.Username) && !context.allowRoot { return PrivilegeCheckResult{ Allowed: false, Error: &PrivilegedUserError{Username: context.currentUser.Username}, @@ -135,7 +140,7 @@ func (s *Server) checkUserRequest(ctx *privilegeCheckContext, req PrivilegeCheck needsUserSwitching := !isSameResolvedUser(resolvedUser, ctx.currentUser) - if isPrivilegedUsername(resolvedUser.Username) && !ctx.allowRoot { + if isPrivilegedOrUnknown(resolvedUser.Username) && !ctx.allowRoot { return PrivilegeCheckResult{ Allowed: false, Error: &PrivilegedUserError{Username: resolvedUser.Username}, @@ -175,6 +180,42 @@ func (s *Server) resolveRequestedUser(requestedUsername string) (*user.User, err return u, nil } +// SetAllowRootLogin configures root login access +func (s *Server) SetAllowRootLogin(allow bool) { + s.mu.Lock() + defer s.mu.Unlock() + s.allowRootLogin = allow +} + +// userNameLookup performs user lookup with root login permission check +func (s *Server) userNameLookup(username string) (*user.User, error) { + result, err := s.userPrivilegeCheck(username) + if err != nil { + return nil, err + } + return result.User, nil +} + +// userPrivilegeCheck performs user lookup with full privilege check result +func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) { + result := s.CheckPrivileges(PrivilegeCheckRequest{ + RequestedUsername: username, + FeatureSupportsUserSwitch: true, + FeatureName: FeatureSSHLogin, + }) + + if !result.Allowed { + return result, result.Error + } + + return result, nil +} + +// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.) +func isPlatformUnix() bool { + return getCurrentOS() != "windows" +} + // isSameResolvedUser compares two resolved user identities func isSameResolvedUser(user1, user2 *user.User) bool { if user1 == nil || user2 == nil { @@ -183,13 +224,6 @@ func isSameResolvedUser(user1, user2 *user.User) bool { return user1.Uid == user2.Uid } -// privilegeCheckContext holds all context needed for privilege checking -type privilegeCheckContext struct { - currentUser *user.User - currentUserPrivileged bool - allowRoot bool -} - // isSameUser checks if two usernames refer to the same user // SECURITY: This function must be conservative - it should only return true // when we're certain both usernames refer to the exact same user identity @@ -253,159 +287,30 @@ func isWindowsSameUser(requestedUsername, currentUsername string) bool { return strings.EqualFold(reqDomain, curDomain) } -// SetAllowRootLogin configures root login access -func (s *Server) SetAllowRootLogin(allow bool) { - s.mu.Lock() - defer s.mu.Unlock() - s.allowRootLogin = allow -} - -// userNameLookup performs user lookup with root login permission check -func (s *Server) userNameLookup(username string) (*user.User, error) { - result := s.CheckPrivileges(PrivilegeCheckRequest{ - RequestedUsername: username, - FeatureSupportsUserSwitch: true, - FeatureName: FeatureSSHLogin, - }) - - if !result.Allowed { - return nil, result.Error - } - - return result.User, nil -} - -// userPrivilegeCheck performs user lookup with full privilege check result -func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) { - result := s.CheckPrivileges(PrivilegeCheckRequest{ - RequestedUsername: username, - FeatureSupportsUserSwitch: true, - FeatureName: FeatureSSHLogin, - }) - - if !result.Allowed { - return result, result.Error - } - - return result, nil -} - -// isPrivilegedUsername checks if the given username represents a privileged user across platforms. -// On Unix: root -// On Windows: Administrator, SYSTEM (case-insensitive) -// Handles domain-qualified usernames like "DOMAIN\Administrator" or "user@domain.com" -func isPrivilegedUsername(username string) bool { +// isPrivilegedOrUnknown reports whether the given username represents a +// privileged user, or on Windows an account whose privilege could not be +// determined. +// On Unix: root. +// On Windows: well-known service accounts, built-in Administrator accounts, +// and members of the local Administrators group; handles domain-qualified +// usernames like "DOMAIN\user" or "user@domain.com". An account that cannot be +// resolved or evaluated is reported as privileged. +// +// Use this to refuse privileged accounts, never to grant them anything: the +// undetermined case is safe for a refusal and unsafe for a grant. +func isPrivilegedOrUnknown(username string) bool { if getCurrentOS() != "windows" { return username == "root" } - - bareUsername := username - // Handle Windows domain format: DOMAIN\username - if idx := strings.LastIndex(username, `\`); idx != -1 { - bareUsername = username[idx+1:] - } - // Handle email-style format: username@domain.com - if idx := strings.Index(bareUsername, "@"); idx != -1 { - bareUsername = bareUsername[:idx] - } - - return isWindowsPrivilegedUser(bareUsername) -} - -// isWindowsPrivilegedUser checks if a bare username (domain already stripped) represents a Windows privileged account -func isWindowsPrivilegedUser(bareUsername string) bool { - // common privileged usernames (case insensitive) - privilegedNames := []string{ - "administrator", - "admin", - "root", - "system", - "localsystem", - "networkservice", - "localservice", - } - - usernameLower := strings.ToLower(bareUsername) - for _, privilegedName := range privilegedNames { - if usernameLower == privilegedName { - return true - } - } - - // computer accounts (ending with $) are not privileged by themselves - // They only gain privileges through group membership or specific SIDs - - if targetUser, err := lookupUser(bareUsername); err == nil { - return isWindowsPrivilegedSID(targetUser.Uid) - } - - return false -} - -// isWindowsPrivilegedSID checks if a Windows SID represents a privileged account -func isWindowsPrivilegedSID(sid string) bool { - privilegedSIDs := []string{ - "S-1-5-18", // Local System (SYSTEM) - "S-1-5-19", // Local Service (NT AUTHORITY\LOCAL SERVICE) - "S-1-5-20", // Network Service (NT AUTHORITY\NETWORK SERVICE) - "S-1-5-32-544", // Administrators group (BUILTIN\Administrators) - "S-1-5-500", // Built-in Administrator account (local machine RID 500) - } - - for _, privilegedSID := range privilegedSIDs { - if sid == privilegedSID { - return true - } - } - - // Check for domain administrator accounts (RID 500 in any domain) - // Format: S-1-5-21-domain-domain-domain-500 - // This is reliable as RID 500 is reserved for the domain Administrator account - if strings.HasPrefix(sid, "S-1-5-21-") && strings.HasSuffix(sid, "-500") { - return true - } - - // Check for other well-known privileged RIDs in domain contexts - // RID 512 = Domain Admins group, RID 516 = Domain Controllers group - if strings.HasPrefix(sid, "S-1-5-21-") { - if strings.HasSuffix(sid, "-512") || // Domain Admins group - strings.HasSuffix(sid, "-516") || // Domain Controllers group - strings.HasSuffix(sid, "-519") { // Enterprise Admins group - return true - } - } - - return false + return getWindowsAccountPrivilegedOrUnknown(username) } // isCurrentProcessPrivileged checks if the current process is running with elevated privileges. // On Unix systems, this means running as root (UID 0). -// On Windows, this means running as Administrator or SYSTEM. +// On Windows, this means the process token is elevated (administrators, SYSTEM). func isCurrentProcessPrivileged() bool { if getCurrentOS() == "windows" { - return isWindowsElevated() + return getProcessElevated() } return getEuid() == 0 } - -// isWindowsElevated checks if the current process is running with elevated privileges on Windows -func isWindowsElevated() bool { - currentUser, err := getCurrentUser() - if err != nil { - log.Errorf("failed to get current user for privilege check, assuming non-privileged: %v", err) - return false - } - - if isWindowsPrivilegedSID(currentUser.Uid) { - log.Debugf("Windows user switching supported: running as privileged SID %s", currentUser.Uid) - return true - } - - if isPrivilegedUsername(currentUser.Username) { - log.Debugf("Windows user switching supported: running as privileged username %s", currentUser.Username) - return true - } - - log.Debugf("Windows user switching not supported: not running as privileged user (current: %s)", currentUser.Uid) - return false -} diff --git a/client/ssh/server/user_utils_test.go b/client/ssh/server/user_utils_test.go index 637dc10d0..2fa9b68ee 100644 --- a/client/ssh/server/user_utils_test.go +++ b/client/ssh/server/user_utils_test.go @@ -4,6 +4,7 @@ import ( "errors" "os/user" "runtime" + "strings" "testing" "github.com/stretchr/testify/assert" @@ -27,8 +28,8 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri originalLookupUser := lookupUser originalGetCurrentOS := getCurrentOS originalGetEuid := getEuid - - // Reset caches to ensure clean test state + originalGetProcessElevated := getProcessElevated + originalGetWindowsAccountPrivilegedOrUnknown := getWindowsAccountPrivilegedOrUnknown // Set test values - inject platform dependencies getCurrentUser = func() (*user.User, error) { @@ -53,16 +54,31 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri return euid } - // Mock privilege detection based on the test user - getIsProcessPrivileged = func() bool { + // Simulate the Windows token elevation check based on the fixture user: + // the built-in Administrator (RID 500) and SYSTEM run elevated. + getProcessElevated = func() bool { if currentUser == nil { return false } - // Check both username and SID for Windows systems - if os == "windows" && isWindowsPrivilegedSID(currentUser.Uid) { + return currentUser.Uid == "S-1-5-18" || strings.HasSuffix(currentUser.Uid, "-500") + } + + // Simulate the Windows account classifier for the fixture accounts. + // "root" does not exist on Windows; the real classifier fails closed on + // unresolvable accounts, so it counts as privileged here too. + getWindowsAccountPrivilegedOrUnknown = func(username string) bool { + bare := username + if idx := strings.LastIndex(bare, `\`); idx != -1 { + bare = bare[idx+1:] + } + if idx := strings.Index(bare, "@"); idx != -1 { + bare = bare[:idx] + } + switch strings.ToLower(bare) { + case "administrator", "system", "root": return true } - return isPrivilegedUsername(currentUser.Username) + return false } // Return cleanup function @@ -71,10 +87,8 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri lookupUser = originalLookupUser getCurrentOS = originalGetCurrentOS getEuid = originalGetEuid - - getIsProcessPrivileged = isCurrentProcessPrivileged - - // Reset caches after test + getProcessElevated = originalGetProcessElevated + getWindowsAccountPrivilegedOrUnknown = originalGetWindowsAccountPrivilegedOrUnknown } } @@ -421,6 +435,9 @@ func TestUsedFallback_MeansNoPrivilegeDropping(t *testing.T) { } func TestPrivilegedUsernameDetection(t *testing.T) { + // Windows classification is syscall-backed (SID resolution, group + // membership) and is covered by privileges_windows_test.go; here only the + // Unix logic and the platform dispatch are exercised. tests := []struct { name string username string @@ -432,25 +449,9 @@ func TestPrivilegedUsernameDetection(t *testing.T) { {"unix_regular_user", "alice", "linux", false}, {"unix_root_capital", "Root", "linux", false}, // Case-sensitive - // Windows tests + // Windows dispatch to the (mocked) account classifier {"windows_administrator", "Administrator", "windows", true}, - {"windows_system", "SYSTEM", "windows", true}, - {"windows_admin", "admin", "windows", true}, - {"windows_admin_lowercase", "administrator", "windows", true}, // Case-insensitive - {"windows_domain_admin", "DOMAIN\\Administrator", "windows", true}, - {"windows_email_admin", "admin@domain.com", "windows", true}, {"windows_regular_user", "alice", "windows", false}, - {"windows_domain_user", "DOMAIN\\alice", "windows", false}, - {"windows_localsystem", "localsystem", "windows", true}, - {"windows_networkservice", "networkservice", "windows", true}, - {"windows_localservice", "localservice", "windows", true}, - - // Computer accounts (these depend on current user context in real implementation) - {"windows_computer_account", "WIN2K19-C2$", "windows", false}, // Computer account by itself not privileged - {"windows_domain_computer", "DOMAIN\\COMPUTER$", "windows", false}, // Domain computer account - - // Cross-platform - {"root_on_windows", "root", "windows", true}, // Root should be privileged everywhere } for _, tt := range tests { @@ -459,50 +460,8 @@ func TestPrivilegedUsernameDetection(t *testing.T) { cleanup := setupTestDependencies(nil, nil, tt.platform, 1000, nil, nil) defer cleanup() - result := isPrivilegedUsername(tt.username) - assert.Equal(t, tt.privileged, result) - }) - } -} - -func TestWindowsPrivilegedSIDDetection(t *testing.T) { - tests := []struct { - name string - sid string - privileged bool - description string - }{ - // Well-known system accounts - {"system_account", "S-1-5-18", true, "Local System (SYSTEM)"}, - {"local_service", "S-1-5-19", true, "Local Service"}, - {"network_service", "S-1-5-20", true, "Network Service"}, - {"administrators_group", "S-1-5-32-544", true, "Administrators group"}, - {"builtin_administrator", "S-1-5-500", true, "Built-in Administrator"}, - - // Domain accounts - {"domain_administrator", "S-1-5-21-1234567890-1234567890-1234567890-500", true, "Domain Administrator (RID 500)"}, - {"domain_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-512", true, "Domain Admins group"}, - {"domain_controllers_group", "S-1-5-21-1234567890-1234567890-1234567890-516", true, "Domain Controllers group"}, - {"enterprise_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-519", true, "Enterprise Admins group"}, - - // Regular users - {"regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1001", false, "Regular domain user"}, - {"another_regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1234", false, "Another regular user"}, - {"local_user", "S-1-5-21-1234567890-1234567890-1234567890-1000", false, "Local regular user"}, - - // Groups that are not privileged - {"domain_users", "S-1-5-21-1234567890-1234567890-1234567890-513", false, "Domain Users group"}, - {"power_users", "S-1-5-32-547", false, "Power Users group"}, - - // Invalid SIDs - {"malformed_sid", "S-1-5-invalid", false, "Malformed SID"}, - {"empty_sid", "", false, "Empty SID"}, - } - - for _, tt := range tests { - t.Run(tt.name, func(t *testing.T) { - result := isWindowsPrivilegedSID(tt.sid) - assert.Equal(t, tt.privileged, result, "Failed for %s: %s", tt.description, tt.sid) + result := isPrivilegedOrUnknown(tt.username) + assert.Equal(t, tt.privileged, result, "privilege classification for %s on %s", tt.username, tt.platform) }) } } diff --git a/client/ssh/server/userswitching_windows.go b/client/ssh/server/userswitching_windows.go index 260e1301e..9e8cd5b30 100644 --- a/client/ssh/server/userswitching_windows.go +++ b/client/ssh/server/userswitching_windows.go @@ -91,7 +91,7 @@ func validateUsernameFormat(username string) error { func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, localUser *user.User, hasPty bool) (*exec.Cmd, func(), error) { logger.Debugf("creating Windows executor command for user %s (Pty: %v)", localUser.Username, hasPty) - username, _ := s.parseUsername(localUser.Username) + username, _ := parseUsername(localUser.Username) if err := validateUsername(username); err != nil { return nil, nil, fmt.Errorf("invalid username %q: %w", username, err) } @@ -102,7 +102,7 @@ func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, l // createUserSwitchCommand creates a command with Windows user switching. // Returns the command and a cleanup function that must be called after starting the process. func (s *Server) createUserSwitchCommand(logger *log.Entry, session ssh.Session, localUser *user.User) (*exec.Cmd, func(), error) { - username, domain := s.parseUsername(localUser.Username) + username, domain := parseUsername(localUser.Username) shell := getUserShell(localUser.Uid) @@ -138,7 +138,7 @@ func (s *Server) createUserSwitchCommand(logger *log.Entry, session ssh.Session, } // parseUsername extracts username and domain from a Windows username -func (s *Server) parseUsername(fullUsername string) (username, domain string) { +func parseUsername(fullUsername string) (username, domain string) { // Handle DOMAIN\username format if idx := strings.LastIndex(fullUsername, `\`); idx != -1 { domain = fullUsername[:idx] diff --git a/client/ssh/session.go b/client/ssh/session.go new file mode 100644 index 000000000..999b6f251 --- /dev/null +++ b/client/ssh/session.go @@ -0,0 +1,84 @@ +package ssh + +import ( + "fmt" + "io" + + log "github.com/sirupsen/logrus" + "golang.org/x/crypto/ssh" +) + +// DefaultTerminalModes are the PTY modes used by the interactive terminal clients. +var DefaultTerminalModes = ssh.TerminalModes{ + ssh.ECHO: 1, + ssh.TTY_OP_ISPEED: 14400, + ssh.TTY_OP_OSPEED: 14400, + ssh.VINTR: 3, // Ctrl+C + ssh.VQUIT: 28, // Ctrl+\ + ssh.VERASE: 127, // Backspace + ssh.VKILL: 21, // Ctrl+U + ssh.VEOF: 4, // Ctrl+D + ssh.VEOL: 0, + ssh.VEOL2: 0, + ssh.VSTART: 17, // Ctrl+Q + ssh.VSTOP: 19, // Ctrl+S + ssh.VSUSP: 26, // Ctrl+Z + ssh.VDISCARD: 15, // Ctrl+O + ssh.VREPRINT: 18, // Ctrl+R + ssh.VWERASE: 23, // Ctrl+W + ssh.VLNEXT: 22, // Ctrl+V +} + +// PTYSession is an interactive shell session with a PTY and its I/O pipes. +type PTYSession struct { + Session *ssh.Session + Stdin io.WriteCloser + Stdout io.Reader + Stderr io.Reader +} + +// StartPTYSession opens a session on the client, requests an xterm-256color PTY +// with the default terminal modes, wires up the I/O pipes and starts a shell. +// The session is closed on any error. +func StartPTYSession(client *ssh.Client, cols, rows int) (*PTYSession, error) { + session, err := client.NewSession() + if err != nil { + return nil, fmt.Errorf("new session: %w", err) + } + + pty, err := setupPTYSession(session, cols, rows) + if err != nil { + if closeErr := session.Close(); closeErr != nil { + log.Debugf("ssh: session close after setup error: %v", closeErr) + } + return nil, err + } + return pty, nil +} + +// setupPTYSession requests the PTY, opens the pipes and starts the shell on an +// already created session. +func setupPTYSession(session *ssh.Session, cols, rows int) (*PTYSession, error) { + if err := session.RequestPty("xterm-256color", rows, cols, DefaultTerminalModes); err != nil { + return nil, fmt.Errorf("request pty: %w", err) + } + + stdin, err := session.StdinPipe() + if err != nil { + return nil, fmt.Errorf("stdin pipe: %w", err) + } + stdout, err := session.StdoutPipe() + if err != nil { + return nil, fmt.Errorf("stdout pipe: %w", err) + } + stderr, err := session.StderrPipe() + if err != nil { + return nil, fmt.Errorf("stderr pipe: %w", err) + } + + if err := session.Shell(); err != nil { + return nil, fmt.Errorf("start shell: %w", err) + } + + return &PTYSession{Session: session, Stdin: stdin, Stdout: stdout, Stderr: stderr}, nil +} diff --git a/client/status/status.go b/client/status/status.go index e8276d0fa..1c204cdb1 100644 --- a/client/status/status.go +++ b/client/status/status.go @@ -46,7 +46,10 @@ func ParseDaemonStatus(s string) DaemonStatus { // ConvertOptions holds parameters for ConvertToStatusOutputOverview. type ConvertOptions struct { - Anonymize bool + Anonymize bool + // AnonymizeLevel selects how much the anonymizer redacts. Only + // meaningful when Anonymize is set. + AnonymizeLevel anonymize.Level DaemonVersion string DaemonStatus DaemonStatus StatusFilter string @@ -217,6 +220,7 @@ func ConvertToStatusOutputOverview(pbFullStatus *proto.FullStatus, opts ConvertO if opts.Anonymize { anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses()) + anonymizer.SetLevel(opts.AnonymizeLevel) anonymizeOverview(anonymizer, &overview) } @@ -976,6 +980,7 @@ func timeAgo(t time.Time) string { func anonymizePeerDetail(a *anonymize.Anonymizer, peer *PeerStateDetailOutput) { peer.FQDN = a.AnonymizeDomain(peer.FQDN) + peer.PubKey = a.AnonymizeWGKey(peer.PubKey) if localIP, port, err := net.SplitHostPort(peer.IceCandidateEndpoint.Local); err == nil { peer.IceCandidateEndpoint.Local = fmt.Sprintf("%s:%s", a.AnonymizeIPString(localIP), port) } @@ -1007,6 +1012,7 @@ func anonymizeOverview(a *anonymize.Anonymizer, overview *OutputOverview) { overview.SignalState.URL = a.AnonymizeURI(overview.SignalState.URL) overview.SignalState.Error = a.AnonymizeString(overview.SignalState.Error) + overview.PubKey = a.AnonymizeWGKey(overview.PubKey) overview.IP = a.AnonymizeIPString(overview.IP) overview.IPv6 = a.AnonymizeIPString(overview.IPv6) for i, detail := range overview.Relays.Details { diff --git a/client/system/info_android.go b/client/system/info_android.go index 3c71573bb..d4f479386 100644 --- a/client/system/info_android.go +++ b/client/system/info_android.go @@ -30,6 +30,11 @@ func GetInfo(ctx context.Context) *Info { kernelVersion = osInfo[2] } + addrs, err := networkAddresses() + if err != nil { + log.Warnf("discover network addresses: %s", err) + } + gio := &Info{ GoOS: runtime.GOOS, Kernel: kernel, @@ -41,6 +46,7 @@ func GetInfo(ctx context.Context) *Info { NetbirdVersion: version.NetbirdVersion(), UIVersion: extractUIVersion(ctx), KernelVersion: kernelVersion, + NetworkAddresses: addrs, SystemSerialNumber: serial(), SystemProductName: productModel(), SystemManufacturer: productManufacturer(), diff --git a/client/system/info_js.go b/client/system/info_js.go index f32532881..3323fb542 100644 --- a/client/system/info_js.go +++ b/client/system/info_js.go @@ -15,7 +15,7 @@ func UpdateStaticInfoAsync() { } // GetInfo retrieves system information for WASM environment -func GetInfo(_ context.Context) *Info { +func GetInfo(ctx context.Context) *Info { info := &Info{ GoOS: runtime.GOOS, Kernel: runtime.GOARCH, @@ -30,6 +30,13 @@ func GetInfo(_ context.Context) *Info { collectBrowserInfo(info) collectLocationInfo(info) collectSystemInfo(info) + + // A caller-provided device name wins, as on the other platforms. A peer + // registered over an API keeps reporting the name it was registered with, + // so its meta does not change on the first sync. + if name := extractDeviceName(ctx, info.Hostname); name != "" { + info.Hostname = name + } return info } diff --git a/client/system/info_js_test.go b/client/system/info_js_test.go new file mode 100644 index 000000000..e2a33ada0 --- /dev/null +++ b/client/system/info_js_test.go @@ -0,0 +1,27 @@ +//go:build js + +package system + +import ( + "context" + "testing" +) + +// TestGetInfoHonorsDeviceName covers a caller-provided device name reaching the +// reported hostname, so a peer registered over an API keeps reporting the name +// it was registered with instead of renaming itself on its first sync. +func TestGetInfoHonorsDeviceName(t *testing.T) { + ctx := context.WithValue(context.Background(), DeviceNameCtxKey, "session-name") + if got := GetInfo(ctx).Hostname; got != "session-name" { + t.Errorf("hostname should carry the caller's device name, got %q", got) + } +} + +// TestGetInfoWithoutDeviceNameKeepsFallback covers the embed layer's habit of +// always setting the context value: an empty name must not blank the hostname. +func TestGetInfoWithoutDeviceNameKeepsFallback(t *testing.T) { + ctx := context.WithValue(context.Background(), DeviceNameCtxKey, "") + if got := GetInfo(ctx).Hostname; got == "" { + t.Error("an empty device name must not blank the hostname") + } +} diff --git a/client/system/network_addr.go b/client/system/network_addr.go index 44260a938..505a6f0ea 100644 --- a/client/system/network_addr.go +++ b/client/system/network_addr.go @@ -1,4 +1,4 @@ -//go:build !ios +//go:build !ios && !android package system diff --git a/client/system/network_addr_android.go b/client/system/network_addr_android.go new file mode 100644 index 000000000..99a71e105 --- /dev/null +++ b/client/system/network_addr_android.go @@ -0,0 +1,89 @@ +package system + +import ( + "net/netip" + "strings" +) + +var iFaceDiscover IFaceDiscover + +type IFaceDiscover interface { + IFaces() (string, error) +} + +// SetIFaceDiscover configures the Android interface discovery provider. +func SetIFaceDiscover(discover IFaceDiscover) { + iFaceDiscover = discover +} + +func networkAddresses() ([]NetworkAddress, error) { + if iFaceDiscover == nil { + return nil, nil + } + ifaces, err := iFaceDiscover.IFaces() + if err != nil { + return nil, err + } + + var netAddresses []NetworkAddress + for _, line := range strings.Split(ifaces, "\n") { + addresses, ok := interfaceAddresses(line) + if !ok { + continue + } + for _, address := range addresses { + netAddr, ok := toNetworkAddress(address) + if !ok { + continue + } + if isDuplicated(netAddresses, netAddr) { + continue + } + netAddresses = append(netAddresses, netAddr) + } + } + return netAddresses, nil +} + +func interfaceAddresses(line string) ([]string, bool) { + parts := strings.Split(line, "|") + if len(parts) != 2 { + return nil, false + } + flags := strings.Fields(parts[0]) + if len(flags) != 8 { + return nil, false + } + up, loopback := flags[3], flags[5] + if up != "true" || loopback == "true" { + return nil, false + } + return strings.Fields(parts[1]), true +} + +func toNetworkAddress(address string) (NetworkAddress, bool) { + prefix, err := netip.ParsePrefix(address) + if err != nil { + return NetworkAddress{}, false + } + if prefix.Addr().Is4In6() { + if prefix.Bits() < 96 { + return NetworkAddress{}, false + } + prefix = netip.PrefixFrom(prefix.Addr().Unmap(), prefix.Bits()-96) + } + ip := prefix.Addr() + if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsMulticast() { + return NetworkAddress{}, false + } + return NetworkAddress{NetIP: prefix}, true +} + +func isDuplicated(addresses []NetworkAddress, addr NetworkAddress) bool { + for _, duplicated := range addresses { + if duplicated.NetIP == addr.NetIP { + return true + } + } + return false +} diff --git a/client/system/network_addr_test.go b/client/system/network_addr_test.go index a5f9c4279..b0be40f0a 100644 --- a/client/system/network_addr_test.go +++ b/client/system/network_addr_test.go @@ -1,4 +1,4 @@ -//go:build !ios +//go:build !ios && !android package system diff --git a/client/system/process_test.go b/client/system/process_test.go index 9d0a6b935..de1cfc1db 100644 --- a/client/system/process_test.go +++ b/client/system/process_test.go @@ -1,3 +1,5 @@ +//go:build windows || (linux && !android) || (darwin && !ios) || freebsd + package system import ( diff --git a/client/ui/authsession/service.go b/client/ui/authsession/service.go index 28efe7cfd..9c094c2a1 100644 --- a/client/ui/authsession/service.go +++ b/client/ui/authsession/service.go @@ -6,9 +6,11 @@ import ( "context" "time" + log "github.com/sirupsen/logrus" "google.golang.org/grpc/codes" gstatus "google.golang.org/grpc/status" + "github.com/netbirdio/netbird/client/internal/profilemanager" "github.com/netbirdio/netbird/client/proto" ) @@ -58,10 +60,21 @@ func (s *Session) RequestExtend(ctx context.Context, p ExtendStartParams) (Exten return ExtendStartResult{}, err } - req := &proto.RequestExtendAuthSessionRequest{} - if p.Hint != "" { - h := p.Hint - req.Hint = &h + // a request from the UI implies a graphical session, which the daemon cannot detect itself + req := &proto.RequestExtendAuthSessionRequest{HasGraphicalSession: true} + hint := p.Hint + if hint == "" { + pm := profilemanager.NewProfileManager() + if active, perr := pm.GetActiveProfile(); perr != nil { + log.Debugf("failed to get active profile for login hint: %v", perr) + } else if state, serr := pm.GetProfileState(active.ID); serr != nil { + log.Debugf("failed to get profile state for login hint: %v", serr) + } else { + hint = state.Email + } + } + if hint != "" { + req.Hint = &hint } resp, err := cli.RequestExtendAuthSession(ctx, req) diff --git a/client/ui/frontend/package.json b/client/ui/frontend/package.json index 3131b36cd..dcef99ad3 100644 --- a/client/ui/frontend/package.json +++ b/client/ui/frontend/package.json @@ -15,7 +15,8 @@ "lint": "eslint \"src/**/*.{ts,tsx}\"", "lint:fix": "eslint \"src/**/*.{ts,tsx}\" --fix", "check": "pnpm lint && pnpm typecheck && pnpm format:check", - "check:fix": "pnpm lint:fix && pnpm format && pnpm typecheck" + "check:fix": "pnpm lint:fix && pnpm format && pnpm typecheck", + "i18n:check": "node ../i18n/check-translations.mjs" }, "dependencies": { "@radix-ui/react-dialog": "^1.1.15", diff --git a/client/ui/frontend/src/components/ReadySignal.tsx b/client/ui/frontend/src/components/ReadySignal.tsx new file mode 100644 index 000000000..0d040cabc --- /dev/null +++ b/client/ui/frontend/src/components/ReadySignal.tsx @@ -0,0 +1,18 @@ +import { useEffect, useRef } from "react"; +import { Events } from "@wailsio/runtime"; +import { useStatus } from "@/contexts/StatusContext.tsx"; + +const EVENT_WINDOW_PAINTED = "netbird:window-painted"; + +export const ReadySignal = () => { + const { isReady } = useStatus(); + const sent = useRef(false); + + useEffect(() => { + if (!isReady || sent.current) return; + sent.current = true; + void Events.Emit(EVENT_WINDOW_PAINTED); + }, [isReady]); + + return null; +}; diff --git a/client/ui/frontend/src/contexts/DebugBundleContext.tsx b/client/ui/frontend/src/contexts/DebugBundleContext.tsx index a0a131fbf..5f2ed9041 100644 --- a/client/ui/frontend/src/contexts/DebugBundleContext.tsx +++ b/client/ui/frontend/src/contexts/DebugBundleContext.tsx @@ -71,10 +71,12 @@ type BundleOptions = { hasWindow: boolean; totalSec: number; uploadUrl: string; - anonymize: boolean; + anonymizeLevel: AnonymizeLevel; systemInfo: boolean; }; +export type AnonymizeLevel = "none" | "default" | "strict"; + const startCaptureBestEffort = async (totalSec: number, pcap: CaptureState) => { try { // Mirror the CLI's safety margin: window + 30s, server caps at 10m. @@ -187,7 +189,10 @@ const runBundleFlow = async ( if (opts.uploadUrl) setStage({ kind: "uploading" }); const result = await DebugSvc.Bundle({ - anonymize: opts.anonymize, + anonymize: opts.anonymizeLevel !== "none", + // The daemon only knows "default" and "strict"; "none" is expressed + // through the anonymize flag being off. + anonymizeLevel: opts.anonymizeLevel === "strict" ? "strict" : "default", systemInfo: opts.systemInfo, uploadUrl: opts.uploadUrl, logFileCount, @@ -198,7 +203,7 @@ const runBundleFlow = async ( }; const useDebugBundle = () => { - const [anonymize, setAnonymize] = useState(false); + const [anonymizeLevel, setAnonymizeLevel] = useState("none"); const [systemInfo, setSystemInfo] = useState(true); const [upload, setUpload] = useState(true); const [trace, setTrace] = useState(true); @@ -240,7 +245,7 @@ const useDebugBundle = () => { hasWindow: capture && totalSec > 0, totalSec, uploadUrl: upload ? NETBIRD_UPLOAD_URL : "", - anonymize, + anonymizeLevel, systemInfo, }; @@ -272,8 +277,8 @@ const useDebugBundle = () => { }; return { - anonymize, - setAnonymize, + anonymizeLevel, + setAnonymizeLevel, systemInfo, setSystemInfo, upload, diff --git a/client/ui/frontend/src/layouts/AppLayout.tsx b/client/ui/frontend/src/layouts/AppLayout.tsx index 1588d9d08..0c2837b53 100644 --- a/client/ui/frontend/src/layouts/AppLayout.tsx +++ b/client/ui/frontend/src/layouts/AppLayout.tsx @@ -5,6 +5,7 @@ import { DebugBundleProvider } from "@/contexts/DebugBundleContext.tsx"; import { ProfileProvider } from "@/contexts/ProfileContext.tsx"; import { DialogProvider } from "@/contexts/DialogContext.tsx"; import { RestrictionsProvider } from "@/contexts/RestrictionsContext.tsx"; +import { ReadySignal } from "@/components/ReadySignal.tsx"; export const AppLayout = () => { return ( @@ -16,6 +17,7 @@ export const AppLayout = () => { + diff --git a/client/ui/frontend/src/modules/settings/SettingsTroubleshooting.tsx b/client/ui/frontend/src/modules/settings/SettingsTroubleshooting.tsx index 991937719..8b1774ed6 100644 --- a/client/ui/frontend/src/modules/settings/SettingsTroubleshooting.tsx +++ b/client/ui/frontend/src/modules/settings/SettingsTroubleshooting.tsx @@ -1,6 +1,6 @@ import { useId, type ReactNode } from "react"; import { Trans, useTranslation } from "react-i18next"; -import { CircleCheckBig, FolderOpen, Loader2 } from "lucide-react"; +import { ChevronDown, CircleCheckBig, FolderOpen, Info, Loader2 } from "lucide-react"; import { Browser } from "@wailsio/runtime"; import { Debug as DebugSvc } from "@bindings/services"; import type { DebugBundleResult } from "@bindings/services/models.js"; @@ -8,13 +8,22 @@ import { Button } from "@/components/buttons/Button"; import { DialogActions } from "@/components/dialog/DialogActions"; import { DialogDescription } from "@/components/dialog/DialogDescription"; import { DialogHeading } from "@/components/dialog/DialogHeading"; +import { + DropdownMenu, + DropdownMenuContent, + DropdownMenuRadioGroup, + DropdownMenuRadioItem, + DropdownMenuTrigger, +} from "@/components/DropdownMenu"; import FancyToggleSwitch from "@/components/switches/FancyToggleSwitch"; import HelpText from "@/components/typography/HelpText.tsx"; import { Input } from "@/components/inputs/Input"; import { Label } from "@/components/typography/Label"; import { SquareIcon } from "@/components/SquareIcon"; +import { Tooltip } from "@/components/Tooltip"; +import { cn } from "@/lib/cn"; import { formatRemaining } from "@/lib/formatters"; -import type { DebugStage } from "@/contexts/DebugBundleContext"; +import type { AnonymizeLevel, DebugStage } from "@/contexts/DebugBundleContext"; import { useDebugBundleContext } from "@/contexts/DebugBundleContext"; import { SectionGroup, SettingsBottomBar } from "@/modules/settings/SettingsSection.tsx"; @@ -24,8 +33,8 @@ export function SettingsTroubleshooting() { const { t } = useTranslation(); const durationId = useId(); const { - anonymize, - setAnonymize, + anonymizeLevel, + setAnonymizeLevel, systemInfo, setSystemInfo, upload, @@ -55,12 +64,71 @@ export function SettingsTroubleshooting() { return ( - +
+
+
+ } + > + + + + + + {t("settings.troubleshooting.anonymize.help")} + +
+
+ + + + + + setAnonymizeLevel(v as AnonymizeLevel)} + > + + {t("settings.troubleshooting.anonymize.none")} + + + {t("settings.troubleshooting.anonymize.default")} + + + {t("settings.troubleshooting.anonymize.strict")} + + + + +
+ .** Join the project, pick your language, and translate in the editor. Each string carries a context note (the `description` from the source file) telling you what it is and where it shows up, and the project's glossary, style guide, and QA checks mirror this document. -> 💡 **The one habit that matters most:** read each key's `description` before translating it. Labels are terse and ambiguous on their own; the `description` tells you what the string is, where it shows up, what to keep verbatim, and what it actually means. +> 💡 **The one habit that matters most:** read each string's context before translating it. Labels are terse and ambiguous on their own; the context tells you what the string is, where it shows up, what to keep verbatim, and what it actually means. + +--- + +## How contributions flow + +```text +i18n/locales/en/common.json ──sync──▶ Crowdin ──service PR──▶ i18n/locales//common.json +``` + +- `i18n/locales/en/common.json` is the source of truth. New and changed strings sync to Crowdin automatically (see `crowdin.yml` in the repository root). +- Crowdin opens and updates a service pull request with the translated bundles, keeping the source's file shape and key order. Keys nobody has translated yet are left out of the export; the app falls back to English for them at runtime. Maintainers review and merge that PR. +- Don't hand-edit `i18n/locales//common.json` in your own PRs: the next sync would conflict with or overwrite your changes. Translate on Crowdin instead. +- Missing your language? Request it on the Crowdin project page or in a [GitHub discussion](https://github.com/netbirdio/netbird/discussions). When a language first ships, a maintainer adds its row to `i18n/locales/_index.json` with `code`, `displayName` (the native name), and `englishName`, which puts it in the app's language picker. + +**Prefer translating with an AI agent?** That still works: drive it with *"Read `i18n/TRANSLATING.md` and translate the UI to Russian"* as before, but deliver the result to Crowdin instead of a pull request. Download your language's file from the Crowdin editor, let the agent translate it, and upload it back (the editor's offline translation flow). Crowdin runs its QA checks on upload, and the next service PR carries the strings into the repo. --- @@ -30,25 +45,6 @@ A **business zero-trust VPN** — an encrypted **overlay mesh** between a compan --- -## The files - -``` -i18n/locales/_index.json shipped-language list -i18n/locales/en/common.json source of truth — message + description -i18n/locales//common.json a target — message only -``` - -Chrome-extension JSON, each key → `{ "message", "description" }`. You translate the **`message`**. - -| ✅ Do | ❌ Don't | -|---|---| -| Keep **every key** from `en`, in the same order | Translate, rename, reorder, drop, or add keys (they're identifiers; the set grows over time) | -| Put **only `message`** in target bundles | Copy `description` into a target bundle | -| Give every key a non-empty `message` | Leave keys missing or empty | -| Save valid UTF-8 JSON, no BOM | Add trailing commas or break the JSON | - ---- - ## Hard rules — get these exactly right These are the usual ways a translation *breaks the app*, not just reads oddly. @@ -58,7 +54,7 @@ These are the usual ways a translation *breaks the app*, not just reads oddly. | Copy `{placeholders}` verbatim — `{version}`, `{count}`, `{name}`… | Translate the word inside the braces (`{verbleibend}` breaks it) | | Reposition a placeholder so the sentence flows | Drop or duplicate a placeholder | | Preserve every `\n`, leading/trailing space, and trailing `...` | Trim "invisible" spaces or the `...` (they're load-bearing) | -| Keep `®` in WireGuard® and quotes around `{name}` | Strip punctuation the description flags | +| Keep `®` in WireGuard® and quotes around `{name}` | Strip punctuation the context flags | **Plurals:** the app has only a *one / other* split — the singular key fires only when `count == 1`; the `{count}` key covers everything else (0, 2, 5, 100…). Languages with more than two forms (ru, pl, uk) can't be fully correct here — use the form that fits the widest range (Russian genitive plural: `минут` / `часов` / `дней`). Don't invent extra keys or cram multiple forms into one string. When no single form fits every value — a unit label after a number field, say — reach for a number-agnostic form (an abbreviation, or wording that reads the same for 1 and 100) instead of forcing a plural the *one / other* split can't supply. @@ -78,13 +74,15 @@ When a brand sits beside a common noun, keep its exact spelling but join them th > **Use the word that language's IT users actually say.** Translate when a natural, common term exists; keep the English term *only* when the literal translation would be awkward or no one in that field really uses it. -Apply each term **consistently** — same English term → same translation everywhere — and keep a term once you've settled it. Whether a term stays English or takes a native word is **language-dependent**: a technical loanword (e.g. *Daemon*, *Handshake*) often stays, an everyday word (e.g. *Latency*, *Public key*) usually localizes, and some (*Exit Node*, *Peer*) go either way depending on the language. Decide per term with the rule above — a foreign origin alone is no reason to keep English. **Your main reference is the existing bundles:** match how a term was already rendered for your language rather than re-deciding it. +Apply each term **consistently** — same English term → same translation everywhere — and keep a term once you've settled it. Whether a term stays English or takes a native word is **language-dependent**: a technical loanword (e.g. *Daemon*, *Handshake*) often stays, an everyday word (e.g. *Latency*, *Public key*) usually localizes, and some (*Exit Node*, *Peer*) go either way depending on the language. Decide per term with the rule above — a foreign origin alone is no reason to keep English. **Your main reference is the existing translation:** match how a term was already rendered for your language rather than re-deciding it. Two checks before you commit a term: - **Prefer established localized wording.** If a widely used tool in this space (for example WireGuard) ships your language, its wording for a shared term such as *handshake* is what users already expect — look at the translated app, not just English docs. For generic UI verbs and formal address, follow your OS vendor's style guide (Microsoft / Apple / Google). - **Watch for false friends.** A literal translation can collide with a *different* established term in your field — confirm your word doesn't already mean something else in this domain before using it. +These tiers are mirrored in the Crowdin project glossary, so the editor highlights them inline. When you settle a new Tier C term for your language, add its translation to the glossary entry so it sticks for everyone who comes after you. + --- ## Style @@ -98,7 +96,7 @@ Two checks before you commit a term: Where it reads naturally, aim to keep each string **roughly the same length** as the English — the UI is tight and over-long strings can wrap or truncate. It's a soft preference, not a rule: if your language simply needs more words, use them. -A few habits that keep a bundle reading like one product rather than a word-for-word port: +A few habits that keep a translation reading like one product rather than a word-for-word port: - **Translate meaning, not words.** Render what a string *does*. An idiom or an awkward source phrase should become natural in your language, not a literal calque. - **Keep one voice within a family.** Sibling strings — the connection states, every settings *help* caption, every "… Failed" title — should share a grammatical form. If one member sounds wrong in that form, re-voice the whole family rather than leave one odd sibling. @@ -107,27 +105,26 @@ A few habits that keep a bundle reading like one product rather than a word-for- --- -## Procedure +## Reviewing a language -**New language** — read `en/common.json` *with* descriptions → settle your Tier C terms → write `i18n/locales//common.json` (same keys and order as `en`, `message` only, placeholders & brands preserved) → add a row to `_index.json` (`{"code","displayName"` = native name`,"englishName"}`) → run the QA list. Use the locale-code style the existing entries use (e.g. `fr`, `pt`, `zh-CN`). +**On Crowdin:** proofread in the editor — context, glossary highlights, and QA flags sit inline next to each string. -**Review (de / hu / …)** — read source and target side by side; for each key check glossary conformance (e.g. de `Exit-Node` → `Exit Node`, hu `Kilépő csomópont` → `Exit Node`), placeholder/`\n` integrity, consistency, tone, and that the meaning matches the English `description`. Fix in place, then report what you changed (especially term standardizations) so a native speaker can sanity-check. +**In the repo** — e.g. driving an AI agent with *"Read `i18n/TRANSLATING.md` and review the existing German translation"* — read source and target side by side; for each key check glossary conformance (e.g. de `Exit-Node` → `Exit Node`, hu `Kilépő csomópont` → `Exit Node`), placeholder/`\n` integrity, consistency, tone, and that the meaning matches the English `description`. Report what you found, and apply the fixes **on Crowdin** — direct edits to the locale files are overwritten by the next sync. --- ## QA before you finish -- [ ] Valid JSON · **every `en` key** present, same order · **no `description`** fields - [ ] Every `{placeholder}`, `\n`, and intentional space preserved · `...` / `… Failed` / `{name}` quotes kept -- [ ] Tier A/B left intact · Tier C applied consistently (and matching the existing bundle for your language) +- [ ] Tier A/B left intact · Tier C applied consistently (and matching the existing translation for your language) - [ ] Buttons & tray short · locale punctuation and capitalization applied -- [ ] New language added to `_index.json` +- [ ] Crowdin QA flags resolved (variables, glossary terms, punctuation) - [ ] **Tested in the running app** ↓ --- ## Test it in the app -A bundle can pass every check above and still read wrong on screen. **Run the app, switch to your language, and click through the real surfaces** — tray menu, main window, every Settings tab, the dialogs. Watch for text overflow or truncation, labels that are technically right but wrong *for what the control does*, leaked placeholders, and terms that drift between screens. +A translation can pass every check above and still read wrong on screen. **Run the app, switch to your language, and click through the real surfaces** — tray menu, main window, every Settings tab, the dialogs. Watch for text overflow or truncation, labels that are technically right but wrong *for what the control does*, leaked placeholders, and terms that drift between screens. How to run the app and switch language: see the project README. Can't run it (e.g. a headless agent)? Say so in your summary — don't silently skip this step. diff --git a/client/ui/i18n/check-translations.mjs b/client/ui/i18n/check-translations.mjs new file mode 100644 index 000000000..bd076e0e0 --- /dev/null +++ b/client/ui/i18n/check-translations.mjs @@ -0,0 +1,104 @@ +#!/usr/bin/env node +// Validates that every shipped translation bundle carries exactly the same set +// of keys as the English source of truth. English (en) defines the keys; every +// other locale declared in _index.json must match it 1:1: +// +// - no missing keys — a missing key silently falls back to English at runtime +// (see i18n bundle fallback), so the gap never surfaces to users or CI +// without this check; +// - no orphaned keys — keys left behind after an English key is renamed or +// removed are dead weight and a sign the locale is drifting. +// +// Pure Node, no dependencies, so it runs without installing the frontend +// toolchain. +// +// Local: node client/ui/i18n/check-translations.mjs (or: pnpm i18n:check) +// CI: .github/workflows/ui-translations.yml + +import { readdirSync, readFileSync } from "node:fs"; +import { dirname, join } from "node:path"; +import { fileURLToPath } from "node:url"; + +const SOURCE = "en"; +const localesDir = join(dirname(fileURLToPath(import.meta.url)), "locales"); +const isCI = Boolean(process.env.GITHUB_ACTIONS); + +function readJSON(path) { + return JSON.parse(readFileSync(path, "utf8")); +} + +function keysOf(langCode) { + return Object.keys(readJSON(join(localesDir, langCode, "common.json"))); +} + +// Emit a GitHub Actions annotation so failures render inline on the PR diff. +function annotate(file, message) { + if (isCI) console.log(`::error file=${file}::${message}`); +} + +const index = readJSON(join(localesDir, "_index.json")); +const declared = index.languages.map((l) => l.code); + +if (!declared.includes(SOURCE)) { + console.error(`FATAL: source language "${SOURCE}" is not declared in _index.json`); + process.exit(1); +} + +const sourceKeys = keysOf(SOURCE); +const sourceSet = new Set(sourceKeys); +console.log(`Source of truth: ${SOURCE}/common.json — ${sourceKeys.length} keys\n`); + +let failed = false; + +for (const code of declared) { + if (code === SOURCE) continue; + const file = `client/ui/i18n/locales/${code}/common.json`; + + let keys; + try { + keys = keysOf(code); + } catch (e) { + failed = true; + const msg = `bundle is declared in _index.json but common.json is missing or invalid (${e.message})`; + console.error(`✗ ${code}: ${msg}`); + annotate("client/ui/i18n/locales/_index.json", `${code}: ${msg}`); + continue; + } + + const set = new Set(keys); + const missing = sourceKeys.filter((k) => !set.has(k)); + const extra = keys.filter((k) => !sourceSet.has(k)); + + if (missing.length === 0 && extra.length === 0) { + console.log(`✓ ${code}: ${keys.length} keys`); + continue; + } + + failed = true; + console.error(`✗ ${code}: ${keys.length} keys (expected ${sourceKeys.length})`); + if (missing.length) { + console.error(` missing ${missing.length}: ${missing.join(", ")}`); + annotate(file, `Missing ${missing.length} key(s) present in ${SOURCE}: ${missing.join(", ")}`); + } + if (extra.length) { + console.error(` extra ${extra.length}: ${extra.join(", ")}`); + annotate(file, `Has ${extra.length} key(s) not present in ${SOURCE}: ${extra.join(", ")}`); + } +} + +// Locale directories present on disk but not declared in _index.json are never +// loaded by the app — surface them so dead translation files don't rot silently. +const onDisk = readdirSync(localesDir, { withFileTypes: true }) + .filter((e) => e.isDirectory()) + .map((e) => e.name); +const undeclared = onDisk.filter((d) => !declared.includes(d)); +if (undeclared.length) { + console.warn(`\n⚠ locale directories not declared in _index.json (not shipped): ${undeclared.join(", ")}`); +} + +console.log(); +if (failed) { + console.error("Translation check FAILED — every locale must match the English key set."); + process.exit(1); +} +console.log("Translation check passed — all locales match the English key set."); diff --git a/client/ui/i18n/locales/de/common.json b/client/ui/i18n/locales/de/common.json index d02589591..1208a37fe 100644 --- a/client/ui/i18n/locales/de/common.json +++ b/client/ui/i18n/locales/de/common.json @@ -764,7 +764,19 @@ "message": "Sensible Informationen anonymisieren" }, "settings.troubleshooting.anonymize.help": { - "message": "Versteckt öffentliche IP-Adressen und nicht-NetBird-Domains in Logs." + "message": "Verbirgt IP-Adressen, Domains und andere sensible Werte." + }, + "settings.troubleshooting.anonymize.info": { + "message": "Der Standardmodus lässt interne IPv4-Adressen und Peer-Namen für den Support lesbar. Der strikte Modus anonymisiert zusätzlich private (RFC 1918), CGNAT- und Link-Local-IP-Adressen, Peer-Namen und öffentliche WireGuard-Schlüssel. Wiederkehrende Werte erhalten denselben Platzhalter, sodass Peers unterscheidbar bleiben. Verwenden Sie den strikten Modus, wenn Sie das Debug-Paket außerhalb Ihrer Organisation weitergeben." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Keine" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Standard" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Strikt" }, "settings.troubleshooting.systemInfo.label": { "message": "Systeminformationen einschließen" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "Vorgang fehlgeschlagen." + }, + "settings.ssh.privilege.hint": { + "message": "Erfordert {actor}. Führen Sie stattdessen dies aus:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Sie können dies deaktivieren, aber zum erneuten Aktivieren sind {actor} erforderlich:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Sie können dies aktivieren, aber zum erneuten Deaktivieren sind {actor} erforderlich:" } } diff --git a/client/ui/i18n/locales/en/common.json b/client/ui/i18n/locales/en/common.json index 9769e772f..694444497 100644 --- a/client/ui/i18n/locales/en/common.json +++ b/client/ui/i18n/locales/en/common.json @@ -1013,11 +1013,27 @@ }, "settings.troubleshooting.anonymize.label": { "message": "Anonymize Sensitive Information", - "description": "Toggle label: anonymize sensitive information in the bundle." + "description": "Label for the anonymization level dropdown (None, Default, Strict)." }, "settings.troubleshooting.anonymize.help": { - "message": "Hides public IP addresses and non-NetBird domains from logs.", - "description": "Helper text for anonymizing logs (hides public IPs and non-NetBird domains)." + "message": "Hides IP addresses, domains, and other sensitive values.", + "description": "Helper text under the anonymization dropdown. The level details live in the info tooltip." + }, + "settings.troubleshooting.anonymize.info": { + "message": "Default keeps internal IPv4 addresses and peer names readable for support. Strict additionally anonymizes private (RFC 1918), CGNAT, and link-local IP addresses, peer names, and WireGuard public keys. Recurring values map to the same placeholder, so peers stay distinguishable. Use Strict when sharing the bundle outside your organization.", + "description": "Info tooltip explaining the anonymization levels. 'RFC 1918', 'CGNAT', 'link-local', and 'WireGuard' are technical terms — keep them." + }, + "settings.troubleshooting.anonymize.none": { + "message": "None", + "description": "Dropdown option: no anonymization." + }, + "settings.troubleshooting.anonymize.default": { + "message": "Default", + "description": "Dropdown option: default anonymization level." + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Strict", + "description": "Dropdown option: strict anonymization level." }, "settings.troubleshooting.systemInfo.label": { "message": "Include System Information", diff --git a/client/ui/i18n/locales/es/common.json b/client/ui/i18n/locales/es/common.json index 3420b612b..6dc4ffd0b 100644 --- a/client/ui/i18n/locales/es/common.json +++ b/client/ui/i18n/locales/es/common.json @@ -764,7 +764,19 @@ "message": "Anonimizar información sensible" }, "settings.troubleshooting.anonymize.help": { - "message": "Oculta las direcciones IP públicas y los dominios ajenos a NetBird de los registros." + "message": "Oculta direcciones IP, dominios y otros valores sensibles." + }, + "settings.troubleshooting.anonymize.info": { + "message": "El modo predeterminado mantiene legibles las direcciones IPv4 internas y los nombres de los peers para el soporte. El modo estricto anonimiza además las direcciones IP privadas (RFC 1918), CGNAT y de enlace local, los nombres de los peers y las claves públicas de WireGuard. Los valores recurrentes se asignan al mismo marcador de posición, por lo que los peers siguen siendo distinguibles. Use el modo estricto cuando comparta el paquete de diagnóstico fuera de su organización." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Ninguno" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Predeterminado" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Estricto" }, "settings.troubleshooting.systemInfo.label": { "message": "Incluir información del sistema" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "La operación falló." + }, + "settings.ssh.privilege.hint": { + "message": "Requiere {actor}. Ejecute esto en su lugar:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Puede desactivarlo, pero volver a activarlo requiere {actor}:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Puede activarlo, pero volver a desactivarlo requiere {actor}:" } } diff --git a/client/ui/i18n/locales/fr/common.json b/client/ui/i18n/locales/fr/common.json index a83f85c12..d3e54440c 100644 --- a/client/ui/i18n/locales/fr/common.json +++ b/client/ui/i18n/locales/fr/common.json @@ -764,7 +764,19 @@ "message": "Anonymiser les informations sensibles" }, "settings.troubleshooting.anonymize.help": { - "message": "Masque les adresses IP publiques et les domaines non-NetBird dans les journaux." + "message": "Masque les adresses IP, les domaines et d'autres valeurs sensibles." + }, + "settings.troubleshooting.anonymize.info": { + "message": "Le mode par défaut garde les adresses IPv4 internes et les noms des pairs lisibles pour le support. Le mode strict anonymise en plus les adresses IP privées (RFC 1918), CGNAT et de lien local, les noms des pairs et les clés publiques WireGuard. Les valeurs récurrentes reçoivent le même espace réservé, les pairs restent donc distinguables. Utilisez le mode strict lorsque vous partagez le lot de diagnostic en dehors de votre organisation." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Aucune" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Par défaut" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Strict" }, "settings.troubleshooting.systemInfo.label": { "message": "Inclure les informations système" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "L’opération a échoué." + }, + "settings.ssh.privilege.hint": { + "message": "Nécessite {actor}. Exécutez plutôt ceci :" + }, + "settings.ssh.privilege.oneWay": { + "message": "Vous pouvez le désactiver, mais le réactiver nécessite {actor} :" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Vous pouvez l’activer, mais le désactiver de nouveau nécessite {actor} :" } } diff --git a/client/ui/i18n/locales/hu/common.json b/client/ui/i18n/locales/hu/common.json index b291f7a01..19aede17f 100644 --- a/client/ui/i18n/locales/hu/common.json +++ b/client/ui/i18n/locales/hu/common.json @@ -764,7 +764,19 @@ "message": "Érzékeny információk anonimizálása" }, "settings.troubleshooting.anonymize.help": { - "message": "Elrejti a nyilvános IP-címeket és a nem-NetBird tartományokat a naplókban." + "message": "Elrejti az IP-címeket, a tartományokat és más érzékeny értékeket." + }, + "settings.troubleshooting.anonymize.info": { + "message": "Az Alapértelmezett szint a belső IPv4-címeket és a peer-neveket olvashatóan hagyja a támogatás számára. A Szigorú ezen felül anonimizálja a privát (RFC 1918), CGNAT és link-local IP-címeket, a peer-neveket és a WireGuard nyilvános kulcsokat. Az ismétlődő értékek ugyanazt a helyettesítőt kapják, így a peerek megkülönböztethetők maradnak. Használja a Szigorú szintet, ha a hibakeresési csomagot a szervezetén kívül osztja meg." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Nincs" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Alapértelmezett" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Szigorú" }, "settings.troubleshooting.systemInfo.label": { "message": "Rendszerinformációk beillesztése" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "A művelet meghiúsult." + }, + "settings.ssh.privilege.hint": { + "message": "{actor} szükséges hozzá. Futtassa inkább ezt:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Kikapcsolhatja, de a visszakapcsolásához {actor} szükséges:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Bekapcsolhatja, de az ismételt kikapcsolásához {actor} szükséges:" } } diff --git a/client/ui/i18n/locales/it/common.json b/client/ui/i18n/locales/it/common.json index a68a8b32b..dab9e0cb4 100644 --- a/client/ui/i18n/locales/it/common.json +++ b/client/ui/i18n/locales/it/common.json @@ -764,7 +764,19 @@ "message": "Anonimizza informazioni sensibili" }, "settings.troubleshooting.anonymize.help": { - "message": "Nasconde gli indirizzi IP pubblici e i domini non NetBird dai log." + "message": "Nasconde indirizzi IP, domini e altri valori sensibili." + }, + "settings.troubleshooting.anonymize.info": { + "message": "La modalità predefinita mantiene leggibili gli indirizzi IPv4 interni e i nomi dei peer per il supporto. La modalità rigorosa anonimizza inoltre gli indirizzi IP privati (RFC 1918), CGNAT e link-local, i nomi dei peer e le chiavi pubbliche WireGuard. I valori ricorrenti vengono associati allo stesso segnaposto, quindi i peer restano distinguibili. Usa la modalità rigorosa quando condividi il pacchetto di debug al di fuori della tua organizzazione." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Nessuna" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Predefinito" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Rigoroso" }, "settings.troubleshooting.systemInfo.label": { "message": "Includi informazioni di sistema" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "Operazione non riuscita." + }, + "settings.ssh.privilege.hint": { + "message": "Richiede {actor}. Esegua invece questo:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Può disabilitarlo, ma riabilitarlo richiede {actor}:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Può abilitarlo, ma disabilitarlo di nuovo richiede {actor}:" } } diff --git a/client/ui/i18n/locales/ja/common.json b/client/ui/i18n/locales/ja/common.json index 10cf7598d..246c232a8 100644 --- a/client/ui/i18n/locales/ja/common.json +++ b/client/ui/i18n/locales/ja/common.json @@ -764,7 +764,19 @@ "message": "機密情報を匿名化" }, "settings.troubleshooting.anonymize.help": { - "message": "ログからパブリック IP アドレスと NetBird 以外のドメインを隠します。" + "message": "IP アドレス、ドメイン、その他の機密性の高い値を隠します。" + }, + "settings.troubleshooting.anonymize.info": { + "message": "「デフォルト」では、サポートのために内部 IPv4 アドレスとピア名は読める状態のまま残ります。「厳格」では、さらにプライベート (RFC 1918)、CGNAT、リンクローカルの IP アドレス、ピア名、WireGuard 公開鍵も匿名化されます。繰り返し現れる値は同じプレースホルダーに置き換えられるため、ピアは区別できます。デバッグバンドルを組織外に共有する場合は「厳格」を使用してください。" + }, + "settings.troubleshooting.anonymize.none": { + "message": "なし" + }, + "settings.troubleshooting.anonymize.default": { + "message": "デフォルト" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "厳格" }, "settings.troubleshooting.systemInfo.label": { "message": "システム情報を含める" @@ -1312,6 +1324,9 @@ "daemon.outdated.description": { "message": "このアプリを使用するには NetBird サービスを更新してください。" }, + "daemon.outdated.download": { + "message": "最新版をダウンロード" + }, "error.jwt_clock_skew": { "message": "サインインに失敗しました: このデバイスの時計がサーバーと同期していません。システムの時計を同期してからもう一度お試しください。" }, @@ -1335,5 +1350,14 @@ }, "error.unknown": { "message": "操作に失敗しました。" + }, + "settings.ssh.privilege.hint": { + "message": "{actor}が必要です。代わりに次のコマンドを実行してください:" + }, + "settings.ssh.privilege.oneWay": { + "message": "無効にはできますが、再度有効にするには{actor}が必要です:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "有効にはできますが、再度無効にするには{actor}が必要です:" } } diff --git a/client/ui/i18n/locales/pt/common.json b/client/ui/i18n/locales/pt/common.json index ef1bfd372..418e93717 100644 --- a/client/ui/i18n/locales/pt/common.json +++ b/client/ui/i18n/locales/pt/common.json @@ -764,7 +764,19 @@ "message": "Anonimizar informações sensíveis" }, "settings.troubleshooting.anonymize.help": { - "message": "Oculta endereços IP públicos e domínios que não são do NetBird nos logs." + "message": "Oculta endereços IP, domínios e outros valores sensíveis." + }, + "settings.troubleshooting.anonymize.info": { + "message": "O modo padrão mantém os endereços IPv4 internos e os nomes dos peers legíveis para o suporte. O modo estrito anonimiza também os endereços IP privados (RFC 1918), CGNAT e link-local, os nomes dos peers e as chaves públicas do WireGuard. Valores recorrentes recebem o mesmo marcador, então os peers continuam distinguíveis. Use o modo estrito ao compartilhar o pacote de depuração fora da sua organização." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Nenhum" + }, + "settings.troubleshooting.anonymize.default": { + "message": "Padrão" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Estrito" }, "settings.troubleshooting.systemInfo.label": { "message": "Incluir informações do sistema" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "A operação falhou." + }, + "settings.ssh.privilege.hint": { + "message": "Requer {actor}. Execute isto em vez disso:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Você pode desativar isto, mas ativar novamente requer {actor}:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Você pode ativar isto, mas desativar novamente requer {actor}:" } } diff --git a/client/ui/i18n/locales/ru/common.json b/client/ui/i18n/locales/ru/common.json index a876387f4..958b5a21c 100644 --- a/client/ui/i18n/locales/ru/common.json +++ b/client/ui/i18n/locales/ru/common.json @@ -764,7 +764,19 @@ "message": "Анонимизировать конфиденциальную информацию" }, "settings.troubleshooting.anonymize.help": { - "message": "Скрывает публичные IP-адреса и сторонние (не относящиеся к NetBird) домены в журналах." + "message": "Скрывает IP-адреса, домены и другие конфиденциальные значения." + }, + "settings.troubleshooting.anonymize.info": { + "message": "Режим «По умолчанию» оставляет внутренние IPv4-адреса и имена пиров читаемыми для поддержки. Режим «Строгий» дополнительно анонимизирует частные (RFC 1918), CGNAT и link-local IP-адреса, имена пиров и публичные ключи WireGuard. Повторяющиеся значения заменяются одним и тем же заполнителем, поэтому пиры остаются различимыми. Используйте режим «Строгий», когда передаёте отладочный пакет за пределы вашей организации." + }, + "settings.troubleshooting.anonymize.none": { + "message": "Нет" + }, + "settings.troubleshooting.anonymize.default": { + "message": "По умолчанию" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "Строгий" }, "settings.troubleshooting.systemInfo.label": { "message": "Включить сведения о системе" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "Не удалось выполнить операцию." + }, + "settings.ssh.privilege.hint": { + "message": "Требуются {actor}. Выполните вместо этого:" + }, + "settings.ssh.privilege.oneWay": { + "message": "Отключить можно, но чтобы включить снова, нужны {actor}:" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "Включить можно, но чтобы отключить снова, нужны {actor}:" } } diff --git a/client/ui/i18n/locales/zh-CN/common.json b/client/ui/i18n/locales/zh-CN/common.json index 542b2b045..90ae5e003 100644 --- a/client/ui/i18n/locales/zh-CN/common.json +++ b/client/ui/i18n/locales/zh-CN/common.json @@ -764,7 +764,19 @@ "message": "匿名化敏感信息" }, "settings.troubleshooting.anonymize.help": { - "message": "从日志中隐藏公共 IP 地址和非 NetBird 域名。" + "message": "隐藏 IP 地址、域名和其他敏感值。" + }, + "settings.troubleshooting.anonymize.info": { + "message": "默认级别保留内部 IPv4 地址和对等节点名称，便于支持人员阅读。严格级别还会匿名化私有 (RFC 1918)、CGNAT 和链路本地 IP 地址、对等节点名称以及 WireGuard 公钥。相同的值会映射到相同的占位符，因此对等节点仍可区分。向组织外部分享调试包时请使用严格级别。" + }, + "settings.troubleshooting.anonymize.none": { + "message": "无" + }, + "settings.troubleshooting.anonymize.default": { + "message": "默认" + }, + "settings.troubleshooting.anonymize.strict": { + "message": "严格" }, "settings.troubleshooting.systemInfo.label": { "message": "包含系统信息" @@ -1338,5 +1350,14 @@ }, "error.unknown": { "message": "操作失败。" + }, + "settings.ssh.privilege.hint": { + "message": "需要{actor}。请改为运行：" + }, + "settings.ssh.privilege.oneWay": { + "message": "您可以关闭此项，但重新开启需要{actor}：" + }, + "settings.ssh.privilege.oneWayInverted": { + "message": "您可以开启此项，但再次关闭需要{actor}：" } } diff --git a/client/ui/main.go b/client/ui/main.go index 5f740f5ec..e20bfe074 100644 --- a/client/ui/main.go +++ b/client/ui/main.go @@ -139,13 +139,11 @@ func main() { prefStore: prefStore, }) - window := newMainWindow(app, prefStore) - - // Settings is created eagerly (hidden) so the first gear click paints - // instantly and React keeps per-tab state across reopens. The other - // auxiliary windows stay lazy + destroy-on-close so Wails's macOS - // dock-reopen handler can't resurrect them. - windowManager := services.NewWindowManager(app, window, bundle, prefStore, iconWindow) + windowManager := services.NewWindowManager(app, nil, bundle, prefStore, iconWindow) + windowManager.SetMainFactory(func(startURL string) *application.WebviewWindow { + return newMainWindow(app, prefStore, windowManager, startURL) + }) + registerDockReopenHook(app, windowManager) // Minimal WMs (XEmbed-tray path) neither center small windows nor restore // position across hide -> show, dropping them top-left. Gate Go-side // re-centering on that environment; nil leaves placement to the WM on full @@ -168,7 +166,7 @@ func main() { // RegisterStatusNotifierItem hits a watcher we control. startStatusNotifierWatcher() - tray = NewTray(app, window, TrayServices{ + tray = NewTray(app, nil, TrayServices{ Connection: connection, Settings: settings, Profiles: profiles, @@ -279,10 +277,12 @@ func newApplication(onSecondInstance func()) *application.App { ActivationPolicy: application.ActivationPolicyAccessory, }, Linux: application.LinuxOptions{ - ProgramName: "netbird", + ProgramName: "netbird", + DisableQuitOnLastWindowClosed: true, }, Windows: application.WindowsOptions{ - WndProcInterceptor: endSessionInterceptor(), + WndProcInterceptor: endSessionInterceptor(), + DisableQuitOnLastWindowClosed: true, }, SingleInstance: &application.SingleInstanceOptions{ UniqueID: "io.netbird.ui", @@ -338,9 +338,7 @@ func registerServices(app *application.App, conn *Conn, s registeredServices) { app.RegisterService(application.NewService(s.compat)) } -// newMainWindow creates the hidden main window, sized to the user's last view -// mode, and installs the hide-on-close and macOS dock-reopen hooks. -func newMainWindow(app *application.App, prefStore *preferences.Store) *application.WebviewWindow { +func newMainWindow(app *application.App, prefStore *preferences.Store, wm *services.WindowManager, startURL string) *application.WebviewWindow { // Width matches the last view mode so Advanced-mode users don't see the // window pop from 380px to 900px on launch. Height is mode-agnostic. initialWidth := 380 @@ -357,7 +355,7 @@ func newMainWindow(app *application.App, prefStore *preferences.Store) *applicat InitialPosition: application.WindowCentered, Hidden: true, BackgroundColour: services.WindowBackgroundColour, - URL: "/", + URL: startURL, DisableResize: true, MinimiseButtonState: application.ButtonHidden, MaximiseButtonState: application.ButtonHidden, @@ -368,29 +366,25 @@ func newMainWindow(app *application.App, prefStore *preferences.Store) *applicat }, }) - // Hide instead of quit on close; "really quit" is reached via tray -> Quit. - window.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) { + window.RegisterHook(events.Common.WindowClosing, func(_ *application.WindowEvent) { if services.ShuttingDown() { return } - e.Cancel() - window.Hide() + wm.ForgetMain() }) - // On macOS, Wails' default applicationShouldHandleReopen handler Show()s - // every hidden window on dock-icon click, resurrecting hide-on-close - // surfaces like Settings. Cancel it in a hook (hooks run before listeners) - // and show only the main window. No-op elsewhere — the event never fires. - if runtime.GOOS == "darwin" { - app.Event.RegisterApplicationEventHook(events.Mac.ApplicationShouldHandleReopen, func(e *application.ApplicationEvent) { - e.Cancel() - if e.Context().HasVisibleWindows() { - return - } - window.Show() - window.Focus() - }) - } - return window } + +func registerDockReopenHook(app *application.App, wm *services.WindowManager) { + if runtime.GOOS != "darwin" { + return + } + app.Event.RegisterApplicationEventHook(events.Mac.ApplicationShouldHandleReopen, func(e *application.ApplicationEvent) { + if e.Context().HasVisibleWindows() { + return + } + e.Cancel() + wm.ShowMain() + }) +} diff --git a/client/ui/services/connection.go b/client/ui/services/connection.go index 1069f8754..f78ce4c0f 100644 --- a/client/ui/services/connection.go +++ b/client/ui/services/connection.go @@ -108,10 +108,11 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err } req := &proto.LoginRequest{ - ManagementUrl: p.ManagementURL, - SetupKey: p.SetupKey, - Hostname: p.Hostname, - IsUnixDesktopClient: runtime.GOOS == "linux", + ManagementUrl: p.ManagementURL, + SetupKey: p.SetupKey, + Hostname: p.Hostname, + // a login driven by the UI always has a graphical session available + IsUnixDesktopClient: true, } if profileName != "" { req.ProfileName = ptrStr(profileName) @@ -122,8 +123,16 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err if p.PreSharedKey != "" { req.OptionalPreSharedKey = ptrStr(p.PreSharedKey) } - if p.Hint != "" { - req.Hint = ptrStr(p.Hint) + hint := p.Hint + if hint == "" && profileID != "" { + if state, serr := profilemanager.NewProfileManager().GetProfileState(profilemanager.ID(profileID)); serr == nil { + hint = state.Email + } else { + log.Debugf("failed to get profile state for login hint: %v", serr) + } + } + if hint != "" { + req.Hint = ptrStr(hint) } resp, err := cli.Login(ctx, req) @@ -227,16 +236,6 @@ func (s *Connection) Logout(ctx context.Context, p LogoutParams) error { return s.classifyDaemonError(err) } - // The daemon runs as root and can't reach the user-owned per-profile state - // file holding the account email (see Profiles.List), so clear the stale - // email here; the next SSO login recreates it. - if p.ProfileName != "" { - if err := profilemanager.NewProfileManager().RemoveProfileState(p.ProfileName); err != nil { - // Non-fatal: the logout itself succeeded. - log.Warnf("failed to remove profile state for %s: %v", p.ProfileName, err) - } - } - return nil } @@ -260,7 +259,7 @@ func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string, // Persist the account email the same way the CLI does after its own // WaitSSOLogin: the daemon returns it but cannot store it, since it runs as - // root and the per-profile state file is user-owned (see Logout below). + // root and the per-profile state file is user-owned (see Profiles.List). // Without this the profile has no email, so Profiles.List shows no account // and later logins and session extends go out without a login_hint — // leaving the IdP to guess which account was meant. diff --git a/client/ui/services/debug.go b/client/ui/services/debug.go index 034086747..d1f6555a8 100644 --- a/client/ui/services/debug.go +++ b/client/ui/services/debug.go @@ -15,10 +15,13 @@ import ( ) type DebugBundleParams struct { - Anonymize bool `json:"anonymize"` - SystemInfo bool `json:"systemInfo"` - UploadURL string `json:"uploadUrl"` - LogFileCount uint32 `json:"logFileCount"` + Anonymize bool `json:"anonymize"` + // AnonymizeLevel is "default" or "strict"; strict also anonymizes + // private IP ranges, peer names, and WireGuard public keys. + AnonymizeLevel string `json:"anonymizeLevel"` + SystemInfo bool `json:"systemInfo"` + UploadURL string `json:"uploadUrl"` + LogFileCount uint32 `json:"logFileCount"` } // DebugBundleResult: Path is set for local-only bundles, UploadedKey on upload @@ -48,11 +51,12 @@ func (s *Debug) Bundle(ctx context.Context, p DebugBundleParams) (DebugBundleRes return DebugBundleResult{}, err } resp, err := cli.DebugBundle(ctx, &proto.DebugBundleRequest{ - Anonymize: p.Anonymize, - SystemInfo: p.SystemInfo, - UploadURL: p.UploadURL, - LogFileCount: p.LogFileCount, - CliVersion: version.NetbirdVersion(), + Anonymize: p.Anonymize, + AnonymizeLevel: p.AnonymizeLevel, + SystemInfo: p.SystemInfo, + UploadURL: p.UploadURL, + LogFileCount: p.LogFileCount, + CliVersion: version.NetbirdVersion(), }) if err != nil { return DebugBundleResult{}, err diff --git a/client/ui/services/profile.go b/client/ui/services/profile.go index 5a9a0e68d..e76ab3db6 100644 --- a/client/ui/services/profile.go +++ b/client/ui/services/profile.go @@ -162,8 +162,9 @@ func (s *Profiles) Remove(ctx context.Context, p ProfileRef) error { } // The daemon deletes what it owns but runs as root, so it leaves the - // user-owned state file holding the account email behind (same split as - // Connection.Logout). Legacy profiles are keyed by name rather than by a + // user-owned state file holding the account email behind. Logout keeps the + // email on purpose so later logins can pass it as the login_hint; profile + // removal is what deletes it. Legacy profiles are keyed by name rather than by a // generated ID, so a recreated profile of the same name would inherit the // deleted one's email and offer it as the login_hint. // diff --git a/client/ui/services/windowmanager.go b/client/ui/services/windowmanager.go index 5f7aaa7bd..4930ce22b 100644 --- a/client/ui/services/windowmanager.go +++ b/client/ui/services/windowmanager.go @@ -8,6 +8,7 @@ import ( "sync" "time" + log "github.com/sirupsen/logrus" "github.com/wailsapp/wails/v3/pkg/application" "github.com/wailsapp/wails/v3/pkg/events" @@ -29,6 +30,12 @@ const EventBrowserLoginCancel = "browser-login:cancel" // EventSettingsOpen tells the mounted settings window which tab to show. const EventSettingsOpen = "netbird:settings:open" +const EventWindowPainted = "netbird:window-painted" + +const paintedFallback = 2 * time.Second + +const headlessTeardownDelay = 2 * time.Second + var WindowBackgroundColour = application.NewRGB(24, 26, 29) // bg-nb-gray-950 // WindowHeight is shared by the main and Settings windows. @@ -94,9 +101,6 @@ func DialogWindowOptions(name, title, url string, linuxIcon []byte) application. } } -// WindowManager owns the auxiliary windows (main is created in main.go). Settings is created -// eagerly and hidden on close to keep React state; the rest are created on open, destroyed on -// close, so the macOS dock-reopen handler finds no hidden window to resurrect. type WindowManager struct { app *application.App mainWindow *application.WebviewWindow @@ -112,15 +116,35 @@ type WindowManager struct { // hiddenForLogin holds windows hidden while the BrowserLogin popup is open, restored on close. hiddenForLogin []application.Window mu sync.Mutex + createMu sync.Mutex + newMain func(startURL string) *application.WebviewWindow + ready map[uint]bool + showPending map[uint]bool + pendingTab map[uint]string + pendingEmits map[uint][]string + fallbackTimers map[uint]*time.Timer + headlessMain bool + headlessTimer *time.Timer // recenterOnShow is set only on the minimal-WM/XEmbed path, where the WM neither centers nor // restores position; nil on full desktops so re-centering can't fight a user-moved window. recenterOnShow func() bool } -// NewWindowManager wires the manager to the main app; translator/prefs may be nil (tests). The -// Settings window is created here (hidden) so the first OpenSettings is instant. func NewWindowManager(app *application.App, mainWindow *application.WebviewWindow, translator ErrorTranslator, prefs LanguagePreference, linuxIcon []byte) *WindowManager { - s := &WindowManager{app: app, mainWindow: mainWindow, translator: translator, prefs: prefs, linuxIcon: linuxIcon} + s := &WindowManager{ + app: app, + mainWindow: mainWindow, + translator: translator, + prefs: prefs, + linuxIcon: linuxIcon, + ready: map[uint]bool{}, + showPending: map[uint]bool{}, + pendingTab: map[uint]string{}, + pendingEmits: map[uint][]string{}, + fallbackTimers: map[uint]*time.Timer{}, + } + s.watchPainted() + s.watchTriggerLogin() // Re-title live windows on language flip. Wired internally so the binding generator // doesn't try to expose the interface param. if sub, ok := prefs.(LanguageSubscriber); ok && sub != nil { @@ -136,7 +160,11 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo } }() } - s.settings = app.Window.NewWithOptions(application.WebviewWindowOptions{ + return s +} + +func (s *WindowManager) newSettingsWindow() *application.WebviewWindow { + w := s.app.Window.NewWithOptions(application.WebviewWindowOptions{ Name: "settings", Title: s.title("window.title.settings"), Width: 900, @@ -150,18 +178,15 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo URL: "/#/settings", Mac: AppleMacOSAppearanceOptions(), Windows: MicrosoftWindowsAppearanceOptions(), - Linux: LinuxAppearanceOptions(linuxIcon), + Linux: LinuxAppearanceOptions(s.linuxIcon), }) - // Hide (not destroy) on close to keep React state; reset to General for a flash-free reopen. - s.settings.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) { - if ShuttingDown() { - return - } - e.Cancel() - s.app.Event.Emit(EventSettingsOpen, "general") - s.settings.Hide() + w.RegisterHook(events.Common.WindowClosing, func(_ *application.WindowEvent) { + s.mu.Lock() + s.settings = nil + s.forgetWindowLocked(w) + s.mu.Unlock() }) - return s + return w } // OpenSettings shows the settings window on tab (empty → General), switching tab via @@ -171,11 +196,20 @@ func (s *WindowManager) OpenSettings(tab string) { if target == "" { target = "general" } - s.app.Event.Emit(EventSettingsOpen, target) - s.settings.Show() - s.settings.Focus() - // Re-center (minimal-WM only; see centerWhenReady). - s.centerWhenReady(s.settings) + + w, _ := s.ensureWindow(&s.settings, s.newSettingsWindow) + + s.mu.Lock() + ready := s.ready[w.ID()] + if !ready { + s.pendingTab[w.ID()] = target + } + s.mu.Unlock() + + if ready { + s.app.Event.Emit(EventSettingsOpen, target) + } + s.showWhenReady(w) } // OpenBrowserLogin shows the SSO popup, creating it on first use. @@ -440,13 +474,295 @@ func (s *WindowManager) OpenMain() { // ShowMain brings the main window forward (re-centering on minimal WMs). The single entry // point every surface (tray, SIGUSR1, welcome) should use so centering applies uniformly. func (s *WindowManager) ShowMain() { - if s.mainWindow == nil { + s.showWhenReady(s.MainWindow()) +} + +// ShowMainAndEmit brings the main window forward and emits event once its frontend is ready. +func (s *WindowManager) ShowMainAndEmit(event string) { + w := s.MainWindow() + if w == nil { return } - s.mainWindow.Show() - s.mainWindow.Focus() - // Re-center (minimal-WM only; see centerWhenReady). - s.centerWhenReady(s.mainWindow) + + id := w.ID() + s.mu.Lock() + ready := s.ready[id] + if !ready { + s.pendingEmits[id] = append(s.pendingEmits[id], event) + } + s.mu.Unlock() + + s.showWhenReady(w) + if ready { + s.app.Event.Emit(event) + } +} + +func (s *WindowManager) MainWindow() *application.WebviewWindow { + w, _ := s.ensureMain("/") + return w +} + +func (s *WindowManager) ensureMain(startURL string) (*application.WebviewWindow, bool) { + s.mu.Lock() + factory := s.newMain + s.mu.Unlock() + if factory == nil { + return s.ensureWindow(&s.mainWindow, nil) + } + return s.ensureWindow(&s.mainWindow, func() *application.WebviewWindow { + return factory(startURL) + }) +} + +func (s *WindowManager) ensureWindow(slot **application.WebviewWindow, factory func() *application.WebviewWindow) (*application.WebviewWindow, bool) { + s.createMu.Lock() + defer s.createMu.Unlock() + + s.mu.Lock() + w := *slot + s.mu.Unlock() + if w != nil || factory == nil { + return w, false + } + + w = factory() + s.armReady(w) + + s.mu.Lock() + *slot = w + s.mu.Unlock() + return w, true +} + +func (s *WindowManager) armReady(w *application.WebviewWindow) { + if w == nil { + return + } + w.RegisterHook(events.Common.WindowRuntimeReady, func(_ *application.WindowEvent) { + timer := time.AfterFunc(paintedFallback, func() { + log.Warnf("window %q never reported a first render, showing it anyway", w.Name()) + s.markReady(w) + }) + s.mu.Lock() + s.fallbackTimers[w.ID()] = timer + s.mu.Unlock() + }) +} + +func (s *WindowManager) watchPainted() { + s.app.Event.On(EventWindowPainted, func(e *application.CustomEvent) { + if w := s.windowByName(e.Sender); w != nil { + s.markReady(w) + } + }) +} + +func (s *WindowManager) watchTriggerLogin() { + s.app.Event.On(EventTriggerLogin, func(_ *application.CustomEvent) { + s.mu.Lock() + if s.headlessTimer != nil { + s.headlessTimer.Stop() + s.headlessTimer = nil + } + w := s.mainWindow + ready := w != nil && s.ready[w.ID()] + s.mu.Unlock() + if ready { + return + } + + w, created := s.ensureMain("/") + if w == nil { + return + } + + s.mu.Lock() + if created { + s.headlessMain = true + } + pending := !s.ready[w.ID()] + if pending { + s.pendingEmits[w.ID()] = append(s.pendingEmits[w.ID()], EventTriggerLogin) + } + s.mu.Unlock() + + if !pending { + s.app.Event.Emit(EventTriggerLogin) + } + }) + + s.app.Event.On(EventBrowserLoginCancel, func(_ *application.CustomEvent) { + s.scheduleHeadlessTeardown() + }) + + s.app.Event.On(EventStatusSnapshot, func(e *application.CustomEvent) { + st, ok := e.Data.(Status) + if !ok { + return + } + switch st.Status { + case StatusConnected, StatusLoginFailed, StatusDaemonUnavailable: + s.scheduleHeadlessTeardown() + } + }) +} + +func (s *WindowManager) scheduleHeadlessTeardown() { + s.mu.Lock() + defer s.mu.Unlock() + if !s.headlessMain || s.mainWindow == nil { + return + } + if s.headlessTimer != nil { + s.headlessTimer.Stop() + } + s.headlessTimer = time.AfterFunc(headlessTeardownDelay, s.closeHeadlessMain) +} + +func (s *WindowManager) closeHeadlessMain() { + s.mu.Lock() + w := s.mainWindow + headless := s.headlessMain + s.headlessTimer = nil + s.mu.Unlock() + if !headless || w == nil { + return + } + w.Close() +} + +func (s *WindowManager) forgetWindowLocked(w *application.WebviewWindow) { + if w == nil { + return + } + + id := w.ID() + if timer := s.fallbackTimers[id]; timer != nil { + timer.Stop() + } + delete(s.fallbackTimers, id) + delete(s.ready, id) + delete(s.showPending, id) + delete(s.pendingTab, id) + delete(s.pendingEmits, id) + + kept := s.hiddenForLogin[:0] + for _, hidden := range s.hiddenForLogin { + if hidden != application.Window(w) { + kept = append(kept, hidden) + } + } + s.hiddenForLogin = kept +} + +func (s *WindowManager) windowByName(name string) *application.WebviewWindow { + s.mu.Lock() + defer s.mu.Unlock() + switch name { + case "main": + return s.mainWindow + case "settings": + return s.settings + default: + return nil + } +} + +func (s *WindowManager) markReady(w *application.WebviewWindow) { + id := w.ID() + s.mu.Lock() + already := s.ready[id] + s.ready[id] = true + wanted := s.showPending[id] + tab, hasTab := s.pendingTab[id] + emits := s.pendingEmits[id] + if timer := s.fallbackTimers[id]; timer != nil { + timer.Stop() + delete(s.fallbackTimers, id) + } + delete(s.showPending, id) + delete(s.pendingTab, id) + delete(s.pendingEmits, id) + s.mu.Unlock() + + if already { + return + } + + if hasTab { + s.app.Event.Emit(EventSettingsOpen, tab) + } + + if wanted { + s.showNow(w) + } + + for _, event := range emits { + s.app.Event.Emit(event) + } +} + +func (s *WindowManager) showWhenReady(w *application.WebviewWindow) { + if w == nil { + return + } + + id := w.ID() + s.mu.Lock() + ready := s.ready[id] + if !ready { + s.showPending[id] = true + } + s.mu.Unlock() + + if ready { + s.showNow(w) + } +} + +func (s *WindowManager) showNow(w *application.WebviewWindow) { + s.mu.Lock() + if w == s.mainWindow { + s.headlessMain = false + if s.headlessTimer != nil { + s.headlessTimer.Stop() + s.headlessTimer = nil + } + } + s.mu.Unlock() + w.Show() + w.Focus() + s.centerWhenReady(w) +} + +func (s *WindowManager) ShowMainAt(url string) { + w, created := s.ensureMain(url) + if w == nil { + return + } + if !created { + w.SetURL(url) + } + s.showWhenReady(w) +} + +func (s *WindowManager) SetMainFactory(f func(startURL string) *application.WebviewWindow) { + s.mu.Lock() + defer s.mu.Unlock() + s.newMain = f +} + +func (s *WindowManager) ForgetMain() { + s.mu.Lock() + defer s.mu.Unlock() + s.forgetWindowLocked(s.mainWindow) + s.mainWindow = nil + s.headlessMain = false + if s.headlessTimer != nil { + s.headlessTimer.Stop() + s.headlessTimer = nil + } } // SetRecenterOnShow installs the recenterOnShow predicate (see the field). diff --git a/client/ui/tray.go b/client/ui/tray.go index 148dd50b3..c392a0b62 100644 --- a/client/ui/tray.go +++ b/client/ui/tray.go @@ -174,7 +174,7 @@ func NewTray(app *application.App, window *application.WebviewWindow, svc TraySe // in the right locale — no English flash then re-paint. loc: svc.Localizer, } - t.updater = newTrayUpdater(app, window, svc.Update, svc.Notifier, t.loc, func() { t.applyIcon() }, func() { t.relayoutMenu() }) + t.updater = newTrayUpdater(app, t.showMainAt, svc.Update, svc.Notifier, t.loc, func() { t.applyIcon() }, func() { t.relayoutMenu() }) t.tray = app.SystemTray.New() // Seed panel-theme detection before the first paint so the initial icon // matches the panel's light/dark scheme (Linux only). @@ -241,9 +241,6 @@ func (t *Tray) ShowWindow() { w.Focus() return } - if t.window == nil { - return - } // Route through WindowManager so the main window is centered on first // show — minimal WMs (fluxbox, the XEmbed tray path) otherwise drop it in // the top-left corner. @@ -251,8 +248,49 @@ func (t *Tray) ShowWindow() { t.svc.WindowManager.ShowMain() return } - t.window.Show() - t.window.Focus() + if w := t.mainWindow(); w != nil { + w.Show() + w.Focus() + } +} + +func (t *Tray) mainWindow() *application.WebviewWindow { + if t.svc.WindowManager == nil { + return t.window + } + return t.svc.WindowManager.MainWindow() +} + +func (t *Tray) showMainAt(url string) { + if t.svc.WindowManager != nil { + t.svc.WindowManager.ShowMainAt(url) + return + } + if w := t.mainWindow(); w != nil { + w.SetURL(url) + w.Show() + w.Focus() + } +} + +func (t *Tray) showMain() { + if t.svc.WindowManager != nil { + t.svc.WindowManager.ShowMain() + return + } + if w := t.mainWindow(); w != nil { + w.Show() + w.Focus() + } +} + +func (t *Tray) showMainAndEmit(event string) { + if t.svc.WindowManager != nil { + t.svc.WindowManager.ShowMainAndEmit(event) + return + } + t.showMain() + t.app.Event.Emit(event) } // applyLanguage re-renders every translated surface in the Localizer's current @@ -479,7 +517,8 @@ func (t *Tray) handleConnect(upItem *application.MenuItem) { // NeedsLogin/SessionExpired/LoginFailed won't honor a plain Up RPC — they // need the Login → WaitSSOLogin → Up sequence. Emit EventTriggerLogin so // the React startLogin() (which owns the BrowserLogin popup) drives it; - // the hidden main webview is alive and subscribed, so only the popup shows. + // the WindowManager materialises a hidden main webview when none is live, + // so only the popup shows. t.statusMu.Lock() needsLogin := strings.EqualFold(t.lastStatus, services.StatusNeedsLogin) || strings.EqualFold(t.lastStatus, services.StatusSessionExpired) || diff --git a/client/ui/tray_session.go b/client/ui/tray_session.go index f25419894..6e5d07740 100644 --- a/client/ui/tray_session.go +++ b/client/ui/tray_session.go @@ -30,10 +30,7 @@ const ( // handleSessionExpired notifies and brings the window forward so the user can reconnect. func (t *Tray) handleSessionExpired() { t.notify(t.loc.T("notify.sessionExpired.title"), t.loc.T("notify.sessionExpired.body"), notifyIDSessionExpired) - if t.window != nil { - t.window.Show() - t.window.Focus() - } + t.showMain() } // applySessionExpiry refreshes the cached SSO deadline and reports whether it changed. @@ -307,7 +304,7 @@ func (t *Tray) openSessionExtendFlow() { } seconds := int(time.Until(deadline).Seconds()) if seconds <= 0 { - t.app.Event.Emit(services.EventTriggerLogin) + t.showMainAndEmit(services.EventTriggerLogin) return } if t.svc.WindowManager == nil { diff --git a/client/ui/tray_update.go b/client/ui/tray_update.go index 27037eccb..3ce1f9600 100644 --- a/client/ui/tray_update.go +++ b/client/ui/tray_update.go @@ -4,6 +4,7 @@ package main import ( "context" + neturl "net/url" "sync" "time" @@ -19,7 +20,7 @@ import ( // trayUpdater owns the tray UI that reacts to auto-update. Composed inside Tray. type trayUpdater struct { app *application.App - window *application.WebviewWindow + showMainAt func(url string) update *services.Update notifier *Notifier loc *Localizer @@ -36,10 +37,10 @@ type trayUpdater struct { progressWindowOpen bool } -func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater { +func newTrayUpdater(app *application.App, showMainAt func(url string), update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater { u := &trayUpdater{ app: app, - window: window, + showMainAt: showMainAt, update: update, notifier: notifier, loc: loc, @@ -185,14 +186,12 @@ func (u *trayUpdater) sendUpdateNotification(st updater.State) { // openProgressWindow points the main window at the /update progress page and // brings it forward. func (u *trayUpdater) openProgressWindow(version string) { - if u.window == nil { + if u.showMainAt == nil { return } url := "/#/update" if version != "" { - url += "?version=" + version + url += "?version=" + neturl.QueryEscape(version) } - u.window.SetURL(url) - u.window.Show() - u.window.Focus() + u.showMainAt(url) } diff --git a/client/wasm/cmd/main.go b/client/wasm/cmd/main.go index 4683f4033..260a528f0 100644 --- a/client/wasm/cmd/main.go +++ b/client/wasm/cmd/main.go @@ -56,8 +56,7 @@ func startClient(ctx context.Context, nbClient *netbird.Client) error { // parseClientOptions extracts NetBird options from JavaScript object func parseClientOptions(jsOptions js.Value) (netbird.Options, error) { options := netbird.Options{ - DeviceName: "dashboard-client", - LogLevel: defaultLogLevel, + LogLevel: defaultLogLevel, } if jwtToken := jsOptions.Get("jwtToken"); !jwtToken.IsNull() && !jwtToken.IsUndefined() { @@ -87,13 +86,41 @@ func parseClientOptions(jsOptions js.Value) (netbird.Options, error) { options.DeviceName = deviceName.String() } - if disableIPv6 := jsOptions.Get("disableIPv6"); !disableIPv6.IsNull() && !disableIPv6.IsUndefined() { - options.DisableIPv6 = disableIPv6.Bool() + disableIPv6, err := boolOption(jsOptions, "disableIPv6") + if err != nil { + return options, err + } + if disableIPv6 != nil { + options.DisableIPv6 = *disableIPv6 } + // The caller decides whether this client uses lazy connections; left unset it + // defers to the management feature flag. A short-lived, interactive caller + // turns it off so its sessions reach the few peers their grant covers eagerly, + // instead of the first request waiting for the connection to be established. + lazyConnectionEnabled, err := boolOption(jsOptions, "lazyConnectionEnabled") + if err != nil { + return options, err + } + options.LazyConnectionEnabled = lazyConnectionEnabled + return options, nil } +// boolOption reads a boolean option, returning nil when the caller left it out. +// js.Value.Bool panics on any other type, so a wrong type is reported instead. +func boolOption(jsOptions js.Value, name string) (*bool, error) { + v := jsOptions.Get(name) + if v.IsNull() || v.IsUndefined() { + return nil, nil + } + if v.Type() != js.TypeBoolean { + return nil, fmt.Errorf("option %s must be a boolean, got %s", name, v.Type()) + } + b := v.Bool() + return &b, nil +} + // createStartMethod creates the start method for the client func createStartMethod(client *netbird.Client) js.Func { return js.FuncOf(func(this js.Value, args []js.Value) any { diff --git a/client/wasm/cmd/main_test.go b/client/wasm/cmd/main_test.go new file mode 100644 index 000000000..3ec5a8f6a --- /dev/null +++ b/client/wasm/cmd/main_test.go @@ -0,0 +1,64 @@ +//go:build js + +package main + +import ( + "syscall/js" + "testing" +) + +// TestParseClientOptionsBooleans covers the boolean options against the value +// kinds a JS caller can pass: js.Value.Bool panics on anything but a boolean, +// so a wrong type has to be rejected before it reaches the client. +func TestParseClientOptionsBooleans(t *testing.T) { + t.Run("unset leaves the lazy override empty", func(t *testing.T) { + options, err := parseClientOptions(js.Global().Get("Object").New()) + if err != nil { + t.Fatalf("parse options: %v", err) + } + if options.LazyConnectionEnabled != nil { + t.Errorf("lazy override should stay unset, got %v", *options.LazyConnectionEnabled) + } + if options.DisableIPv6 { + t.Error("disableIPv6 should default to false") + } + }) + + t.Run("null defers to the management flag", func(t *testing.T) { + jsOptions := js.Global().Get("Object").New() + jsOptions.Set("lazyConnectionEnabled", js.Null()) + options, err := parseClientOptions(jsOptions) + if err != nil { + t.Fatalf("parse options: %v", err) + } + if options.LazyConnectionEnabled != nil { + t.Errorf("lazy override should stay unset, got %v", *options.LazyConnectionEnabled) + } + }) + + t.Run("booleans are carried through", func(t *testing.T) { + jsOptions := js.Global().Get("Object").New() + jsOptions.Set("lazyConnectionEnabled", false) + jsOptions.Set("disableIPv6", true) + options, err := parseClientOptions(jsOptions) + if err != nil { + t.Fatalf("parse options: %v", err) + } + if options.LazyConnectionEnabled == nil || *options.LazyConnectionEnabled { + t.Errorf("lazy override should be false, got %v", options.LazyConnectionEnabled) + } + if !options.DisableIPv6 { + t.Error("disableIPv6 should be true") + } + }) + + t.Run("a non-boolean is rejected", func(t *testing.T) { + for _, value := range []any{"true", 1, js.Global().Get("Object").New()} { + jsOptions := js.Global().Get("Object").New() + jsOptions.Set("lazyConnectionEnabled", value) + if _, err := parseClientOptions(jsOptions); err == nil { + t.Errorf("value %v should be rejected", value) + } + } + }) +} diff --git a/client/wasm/internal/ssh/client.go b/client/wasm/internal/ssh/client.go index 9cfe65266..28ae95ec0 100644 --- a/client/wasm/internal/ssh/client.go +++ b/client/wasm/internal/ssh/client.go @@ -80,13 +80,12 @@ func (c *Client) Connect(host string, port int, username, jwtToken string, ipVer return fmt.Errorf("dial %s: %w", addr, err) } - sshConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config) + sshClient, err := nbssh.Handshake(ctx, conn, addr, config) if err != nil { - closeWithLog(conn, "connection after handshake error") - return fmt.Errorf("SSH handshake: %w", err) + return err } - c.sshClient = ssh.NewClient(sshConn, chans, reqs) + c.sshClient = sshClient logrus.Infof("SSH: Connected to %s", addr) return nil @@ -119,57 +118,26 @@ func (c *Client) getAuthMethods(jwtToken string) ([]ssh.AuthMethod, error) { return []ssh.AuthMethod{ssh.PublicKeys(signer)}, nil } -// StartSession starts an SSH session with PTY +// StartSession starts an SSH session with PTY. It holds the client lock for +// the whole startup so Close cannot tear the client down mid-setup and the +// new session cannot be installed into an already closed client. func (c *Client) StartSession(cols, rows int) error { + c.mu.Lock() + defer c.mu.Unlock() + if c.sshClient == nil { return fmt.Errorf("SSH client not connected") } - session, err := c.sshClient.NewSession() + pty, err := nbssh.StartPTYSession(c.sshClient, cols, rows) if err != nil { - return fmt.Errorf("create session: %w", err) + return err } - c.mu.Lock() - defer c.mu.Unlock() - c.session = session - - modes := ssh.TerminalModes{ - ssh.ECHO: 1, - ssh.TTY_OP_ISPEED: 14400, - ssh.TTY_OP_OSPEED: 14400, - ssh.VINTR: 3, - ssh.VQUIT: 28, - ssh.VERASE: 127, - } - - if err := session.RequestPty("xterm-256color", rows, cols, modes); err != nil { - closeWithLog(session, "session after PTY error") - return fmt.Errorf("PTY request: %w", err) - } - - c.stdin, err = session.StdinPipe() - if err != nil { - closeWithLog(session, "session after stdin error") - return fmt.Errorf("get stdin: %w", err) - } - - c.stdout, err = session.StdoutPipe() - if err != nil { - closeWithLog(session, "session after stdout error") - return fmt.Errorf("get stdout: %w", err) - } - - c.stderr, err = session.StderrPipe() - if err != nil { - closeWithLog(session, "session after stderr error") - return fmt.Errorf("get stderr: %w", err) - } - - if err := session.Shell(); err != nil { - closeWithLog(session, "session after shell error") - return fmt.Errorf("start shell: %w", err) - } + c.session = pty.Session + c.stdin = pty.Stdin + c.stdout = pty.Stdout + c.stderr = pty.Stderr logrus.Info("SSH: Session started with PTY") return nil diff --git a/crowdin.yml b/crowdin.yml new file mode 100644 index 000000000..efdbceb8d --- /dev/null +++ b/crowdin.yml @@ -0,0 +1,11 @@ +skip_untranslated_strings: true +skip_untranslated_files: true +import_eq_suggestions: true + +files: + - source: /client/ui/i18n/locales/en/common.json + translation: /client/ui/i18n/locales/%two_letters_code%/common.json + type: chrome + languages_mapping: + two_letters_code: + zh-CN: zh-CN diff --git a/docs/agent-networks/01-end-to-end-flows.md b/docs/agent-networks/01-end-to-end-flows.md index b8891001b..0de6b4c33 100644 --- a/docs/agent-networks/01-end-to-end-flows.md +++ b/docs/agent-networks/01-end-to-end-flows.md @@ -115,7 +115,7 @@ sequenceDiagram Resp->>Resp: parse usage tokens, completion Note over Resp: capture_completion gates raw
completion capture Resp->>Cost: tokens - Cost->>Cost: lookup pricing.yaml + compute cost + Cost->>Cost: lookup rates from config-delivered
pricing table + compute cost Cost->>Rec: tokens + cost Rec->>MgmtGrpc: RecordLLMUsage(provider, model, prompt_t, completion_t, cost, groups, user) Rec-->>Log: emit access-log entry
(if EnableLogCollection) diff --git a/docs/agent-networks/modules/21-management-agentnetwork.md b/docs/agent-networks/modules/21-management-agentnetwork.md index cc74206e9..f91c369f7 100644 --- a/docs/agent-networks/modules/21-management-agentnetwork.md +++ b/docs/agent-networks/modules/21-management-agentnetwork.md @@ -15,6 +15,10 @@ Inside the package: `manager.go` is the CRUD + permissions-gated facade; `synthe | ---- | ---- | | `agentnetwork/manager.go` | Manager interface + CRUD + permission gates + bootstrap-settings + reconcile trigger | | `agentnetwork/synthesizer.go` | Settings/policy → wire-format synthesis; sole writer of the proxy middleware chain | +| `agentnetwork/synthesizer_pricing.go` | `buildCostMeterConfigJSON` — default table + per-provider prices → `cost_meter` config | +| `agentnetwork/pricing/defaults.go` | Default pricing table derived from the catalog + supplementals; `DefaultTable`, `LookupDefault`, wire `Entry` | +| `agentnetwork/pricing/override.go` | `LoadFile`/`StartReloader` for `AgentNetwork.PricingDefaultsFile` (mtime poll, merge over compiled-in base) | +| `agentnetwork/pricing/{exampleyaml,gen}.go` | Generates `defaults_llm_pricing.example.yaml` from the compiled-in table (golden-tested) | | `agentnetwork/policyselect.go` | Per-request policy attribution + account-budget ceiling (min-wins) | | `agentnetwork/reconcile.go` | Per-account synth diff vs in-memory cache → Create/Update/Delete | | `agentnetwork/catalog/catalog.go` | Static provider catalogue (auth headers, identity-injection shapes) | @@ -48,6 +52,8 @@ flowchart TD I --> J[indexProviderGroups: providerID -> sorted source groups] J --> K[buildRouterConfigJSON drops orphan providers] J --> L[buildIdentityInjectConfigJSON per catalog entry] + J --> K2[buildCostMeterConfigJSON: default table + per-provider prices] + K2 --> P H --> M[mergeGuardrails: union allowlist, OR redact] M --> N[applyAccountCollectionControls account toggle = SOLE capture control] N --> O[marshalGuardrailConfig] @@ -60,6 +66,84 @@ flowchart TD R --> T[accountManager.UpdateAccountPeers — fans synth ACLs into network map] ``` +### LLM pricing (management is the sole authority) + +**The proxy carries no price list.** Management synthesizes the entire pricing +table and ships it inside `cost_meter`'s `ConfigJSON`, so a price change reaches +the proxies as an ordinary mapping push — the chain rebuild installs a fresh +table and there is nothing to reload on the proxy side. + +```mermaid +flowchart TD + A[catalog.All — PricingSurfaces x Models] --> B[buildDefaultTable + supplementalDefaults] + B --> C{AgentNetwork.PricingDefaultsFile} + C -- absent --> D[compiled-in table serves] + C -- loaded --> E[LoadFile: merge file entries WHOLE over compiled base] + E --> F[mergedTable atomic.Pointer] + D --> G[DefaultTable] + F --> G + G --> H[buildCostMeterConfigJSON — pricing.defaults] + I[types.Provider.Models operator prices] --> J[normalizePricingModelID
bedrock ARN/region/version, vertex @version] + J --> K[materializeEntry: default entry as base,
operator input/output verbatim,
cache pointers only when non-nil] + K --> L[pricing.providers keyed by provider record ID] + H --> M[cost_meter ConfigJSON] + L --> M + G --> N[GET /catalog — applyDefaultPricing prefills dashboard rows] + O[StartReloader: mtime poll every ReloadInterval 1m] --> E +``` + +**Two tiers, resolved per request on the proxy** (`synthesizer_pricing.go:22-35`): + +- `pricing.defaults` — surface (`openai`/`anthropic`/`bedrock`) → normalized model + id → rates. The **full** default table ships to every account: it is small + (~10 KB) and it is what keeps gateway-style providers (which enumerate no + models, so they claim every model) priced. +- `pricing.providers` — provider **record** id → normalized model id → rates, + matched against the `llm.resolved_provider_id` the router stamps. Entries are + **fully materialized here**, at synth time: `materializeEntry` starts from the + default entry for that model so cache rates the operator didn't state are + inherited, overlays operator `input`/`output` verbatim (**including an explicit + 0**, which prices a self-hosted or internal endpoint as free rather than + silently reverting to list price), and overlays cache-rate **pointers only when + non-nil** — `nil` means "inherit the default", an explicit `0` means "no + discount, bill this bucket at the input rate". The proxy therefore does two map + lookups and no merging. + +Same orphan rule as the router: a provider no enabled policy authorises is +unreachable, so its prices aren't shipped. Model ids are normalized with the +**same** functions the request parser uses (`NormalizeBedrockModel` / +`NormalizeVertexModel`), which is what makes the per-record lookup key compare +equal to the `llm.model` the proxy meters. Post-normalization duplicates resolve +first-occurrence-wins, matching the routing dedup order. + +**`AgentNetwork.PricingDefaultsFile`** (`config.go:190-207`) lets an operator +replace default rates without a rebuild. Schema is `surface → model → rates` +(`input_per_1k`, `output_per_1k`, and optional `cached_input_per_1k` / +`cache_read_per_1k` / `cache_creation_per_1k`). Semantics: + +- A **relative** path resolves against ``, so a bare filename lands + alongside the store. Empty config probes `/defaults_llm_pricing.yaml`. +- An **explicitly configured** path is *required to load*: a typo or malformed + file fails startup, because the operator believes those rates are live. The + conventional probe is optional — an absent file just serves compiled-in + defaults, and the path stays watched in case it appears later. +- File entries **replace** the compiled-in entry for the same (surface, model) + **whole** — they are not field-merged, so an entry must repeat the cache rates + it wants to keep. Everything the file doesn't mention keeps built-in rates. +- Unknown YAML fields are rejected (`KnownFields(true)`) and every rate must be + finite and non-negative — the same constraints the HTTP API enforces on + operator per-provider prices. +- Reload is an mtime poll (`ReloadInterval`, 1 min) and is **lenient at runtime**: + a parse error keeps the previous table, a deleted file reverts to compiled-in + defaults. A mid-edit save can never take pricing down. + +The live table feeds **both** consumers, which is what keeps them consistent: the +synthesizer (what proxies actually bill with) and `GET /api/agent-network/catalog` +via `applyDefaultPricing` (what the dashboard's model-row prices prefill with). +`defaults_llm_pricing.example.yaml` is generated from the compiled-in table +(`go generate ./management/internals/modules/agentnetwork/pricing`) and +golden-tested, so operators start from a file matching the built-in rates exactly. + ### Budget rule resolution (min-wins, group+user bound) ```mermaid @@ -124,7 +208,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest | on_request | 3 | `llm_identity_inject` | `{"providers":[{provider_id, header_pair?, json_metadata?, extra_headers?}]}` | **true** | | on_request | 4 | `llm_guardrail` | `{"provider_allowlists"?: {providerID: []model}, "prompt_capture":{enabled,redact_pii}}` | – | | on_response | 5 | `llm_limit_record` | `{}` (runs LAST at runtime) | – | - | on_response | 6 | `cost_meter` | `{}` | – | + | on_response | 6 | `cost_meter` | `{"pricing":{"defaults":{surface:{model:rates}},"providers"?:{providerRecordID:{model:rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}` | – | | on_response | 7 | `llm_response_parser` | `{"capture_completion": , "redact_pii"?: true}` | – | - **Synthesized service shape** (`synthesizer.go:739`): `Mode=HTTP`, `Private=true`, `Domain=.`, `AccessGroups=unionSourceGroups(enabledPolicies)`, one `TargetTypeCluster` target with `Host=noop.invalid:443` (router rewrites per request), `Options.{DirectUpstream,AgentNetwork}=true`, `DisableAccessLog=!settings.EnableLogCollection`, `CaptureMax{Req,Resp}Bytes=1<<20`, `CaptureContentTypes=["application/json","text/event-stream"]`. @@ -139,6 +223,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest - **Orphan providers (no enabled policy authorises them) NEVER reach the router** (`synthesizer.go:351-357`); skipped from `identity_inject` for symmetry. - **Provider creation refuses empty `api_key`** (`manager.go:175`); **deletion refuses while any policy still references it** (`manager.go:265-273`). - **Session keypair stability across provider edits** (`manager.go:226-228`) — server-managed, copied through every `UpdateProvider`, never API-surfaced. +- **Management is the sole pricing authority.** The proxy has no embedded price list, so an account whose `cost_meter` config carries no `pricing` block bills **nothing** (`cost.skipped=unknown_model`, $0) rather than falling back to stale built-ins. The top-level `pricing` wrapper is also the feature-detection signal in both directions: an old proxy ignores it as an unknown field, and a new proxy reads its absence as "old management". +- **Per-provider prices are materialized at synth time, not merged on the proxy** (`synthesizer_pricing.go:114-131`). A per-record entry is always complete, so the proxy's lookup is per-record-then-defaults with no field-level fallback between tiers. +- **An explicit operator price of `0` prices the model as free** — it must not be treated as "unset" and reverted to list price (`synthesizer_pricing.go:49-54`). Only *cache*-rate fields distinguish unset from zero, via `*float64`. +- **Pricing model ids are normalized with the same functions the request parser uses** (`normalizePricingModelID`). If the two ever diverge, per-record prices silently stop matching and every request falls through to surface defaults. +- **The default table's coverage is structural, not curated.** It is derived from the catalog via each provider's `PricingSurfaces`; `TestDefaultTable_CoversEveryCatalogModel` fails on an unpriced catalog model and `TestDefaultTable_NoConflictingContributions` fails if two providers contribute the same (surface, model) at different rates. +- **A pricing-defaults file failure is fatal only at startup, and only for an explicitly configured path.** Runtime reload failures keep the previous table; a deleted file reverts to compiled-in defaults (`pricing/override.go:62-81, 113-148`). ## Things to scrutinize @@ -176,10 +266,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest - **Capture-pointer semantics (restated):** non-agent-network callers see no field → legacy nil-default emit, identical to pre-PR. Agent-network targets always carry an explicit `capture_*` value. - **`TestSynthesizeServices_HappyPath` was updated:** request-parser config moved from `{}` to `{"capture_prompt":false}` (`synthesizer_test.go:174`). External snapshot tests against synth output need updating. - **`MergedGuardrails` retains zeroed `TokenLimits`/`Budget`/`Retention`** even though `Policy.Limits` carries the real values now; `llm_limit_check` is the authoritative enforcement. Comment at `synthesizer.go:940-948` calls this out. +- **`cost_meter`'s `pricing` block is version-skew-safe in both directions.** A proxy predating config-delivered pricing ignores the field as unknown JSON (it previously priced from its own embedded table, so it keeps billing — at its own rates, which is the skew to be aware of during a rolling upgrade). A current proxy paired with old management sees no `pricing` block, logs one warning at chain-build time, and records `cost.skipped=unknown_model` — token counting and cap enforcement are unaffected, only the USD annotation goes to $0. ### Performance - **`SynthesizeServices` runs on every controller tick / mutation reconcile.** Cost: 4 store reads + optional per-provider keypair backfill. Sort + index + merge are O(N log N) / O(P × G); dominant cost is JSON marshalling. No nested loops escape these dimensions. +- **The full default pricing table is marshalled into every account's `cost_meter` config on every synth** (~10 KB serialized). This is a deliberate trade: it keeps gateway-style providers priced for every catalog model, and it is the largest single contributor to the synth JSON. `DefaultTable()` itself is a pointer load (or a `sync.Once`-built map) — the cost is the marshal, not the build. - **`reconcile.diffMappings` is O(N + M)** with N=M=1 per account today — effectively constant. - **`SynthesizeServicesForCluster`** (`synthesizer.go:71`) walks every account on a cluster; per-account failures are **swallowed** (`synthesizer.go:91-93`) so a single misconfigured account doesn't drop the cluster. Runs per proxy reconnect. @@ -188,6 +280,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest - **Activity codes:** `AgentNetwork{Provider,Policy,Guardrail,BudgetRule}{Created,Updated,Deleted}`; `AgentNetworkSettingsUpdated` with `log_collection/prompt_collection/redact_pii` payload (`manager.go:567-571`). **No activity code for `SelectPolicyForRequest` denies** — surfaced via proxy access log only (likely intentional given volume). - **Deny codes** namespaced: `llm_policy.{token,budget}_cap_exceeded`, `llm_account.{token,budget}_cap_exceeded` (`policyselect.go:18-26`). - **Reconcile failures are logged at warn and swallowed** (`reconcile.go:42-44`). Persistent synth failures (e.g. unknown catalog id) silently keep the proxy out of sync — consider a manager-level synth-health surface if this becomes a support burden. +- **Pricing-file lifecycle logs at info** (load, reload, revert-to-built-ins) and **at warn** for a runtime reload failure; the mtime check itself is `Debugf`. There is no metric on reload failures, so an operator who breaks the file mid-flight keeps billing at the previous table with only a log line to show it (`pricing/override.go:113-148`). ## Test coverage @@ -198,6 +291,9 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest | `synthesizer_guardrail_realstore_test.go` | `PromptCaptureAccountIsSoleControl`; `PromptCaptureFlowsWhenAccountOptsIn`; `AccountRedactWithoutGuardrailRedact`; `NoGuardrail_CaptureOff`. | | `synthesizer_log_collection_realstore_test.go` | `LogCollection{Off_SuppressesAccessLog,On_PermitsAccessLog}` — verifies `DisableAccessLog` propagation through `ToProtoMapping`. | | `synthesizer_parser_redact_realstore_test.go` | **Capture-pointer regression suite:** `ParserConfigsCarryRedactPii`; `ParserConfigsSuppressCaptureWhenLogCollectionOnly` (log=on/prompt=off ⇒ both capture flags false); `ParserConfigsOmitRedactPiiWhenOff`. | +| `synthesizer_pricing_test.go` | `BuildCostMeterConfig_{BedrockModelNormalization,CacheRateNilVsZero,OrphanAndGatewayProviders}` — the per-record tier's three load-bearing rules: keys normalized like the parser's, `nil` cache pointer inherits vs explicit `0` bills at input rate, and orphan / gateway (empty `Models`) providers ship no per-record entry. | +| `pricing/defaults_test.go` | `DefaultTable_{CoversEveryCatalogModel,NoConflictingContributions,AllRatesFiniteNonNegative,PinnedRates}`; `LookupDefault_SurfaceOrder`. Catalog-derived coverage + rate sanity are structural, not curated. | +| `pricing/override_test.go` | `LoadFile_{MergesOverCompiledDefaults,MissingPath,RejectsInvalid}`; `Reload_LifeCycle` (mtime detect, parse error keeps previous, delete reverts to built-ins); `ExampleYAML_InSyncWithBuiltins` golden. | | `policyselect_test.go` | Mock-store: `NoApplicablePolicies`; `AllowWithLowestGroupAttribution`; `LargerPoolWinsAcrossUsageLevels`; `StaysOnLargerPoolAfterPartialDrain`; `FallsThroughToSmallerPoolWhenLargerExhausted`; `TiebreakBy{LargerGroupPool,CreatedAt}`; `DeniesWhenAllExhausted`; `UncappedPolicyAlwaysWinsAgainstCapped`; `DisabledPolicyIgnored`; `StoreErrorPropagates`; `RejectsEmptyAccount`; `SharesGroupCounterAcrossPolicies`; `AntiFallThroughOnLowestGroup`; `BudgetOnlyExhaustionDenies`; `BudgetTighterThanTokenWins`. | | `policyselect_realstore_test.go` | Real-sqlite regression guard: `NoApplicablePolicies`; `AllowAndLowestGroupAttribution`; `LargerPoolWins_FallsThroughWhenExhausted`; `BudgetCapDenies`; `GroupCounterSharedAcrossPolicies`; `DisabledPolicyIgnored`. | | `policyselect_account_realstore_test.go` | Account budget rules: `AccountCeilingBindsEvenWithUncappedPolicy` (min-wins); `AccountGroupCeiling`; `AccountTargetUsersBindsOnlyThatUser`; `AccountRuleRecordsToOwnWindow`. | diff --git a/docs/agent-networks/modules/31-proxy-middleware-builtin.md b/docs/agent-networks/modules/31-proxy-middleware-builtin.md index efe1bc4ce..ad56feb77 100644 --- a/docs/agent-networks/modules/31-proxy-middleware-builtin.md +++ b/docs/agent-networks/modules/31-proxy-middleware-builtin.md @@ -5,7 +5,7 @@ LLM request. The two highest-blast-radius areas are the **capture-pointer semantics** and the **limit_check ⇒ limit_record** record-once invariant. Sibling module: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — the SDK -adapters + pricing catalog this chain delegates to. +adapters + pricing table and cost formula this chain delegates to. --- @@ -34,7 +34,7 @@ rewrites. | `llm_identity_inject` | OnRequest | `llm.{resolved_provider_id,authorising_groups}`, `Input.{UserEmail,UserID,UserGroups,UserGroupNames}` | none | header strip/inject + optional body rewrite | | `llm_guardrail` | OnRequest | `llm.{model,request_prompt_raw}` | `llm_policy.{decision,reason}`, `llm.request_prompt` | none (model allowlist deny) | | `llm_response_parser` | OnResponse | `llm.provider`, `Input.{RespHeaders,RespBody,Status}` | `llm.{input,output,total,cached_input,cache_creation}_tokens`, `llm.response_completion` | none | -| `cost_meter` | OnResponse | `llm.{provider,model}`, token buckets | `cost.usd_total` or `cost.skipped` | pricing lookup | +| `cost_meter` | OnResponse | `llm.{provider,model,resolved_provider_id}`, token buckets | `cost.usd_{input,cached_input,cache_creation,output,total,cache}` or `cost.skipped` | none (in-memory pricing lookup) | | `llm_limit_record` | OnResponse | `llm.{attribution_group_id,attribution_window_seconds,input_tokens,output_tokens}`, `cost.usd_total` | none | gRPC `RecordLLMUsage` | [all_test.go:26–40](../../../proxy/internal/middleware/builtin/all_test.go) @@ -44,7 +44,7 @@ locks the ID set; adding or removing one is a conscious extension. | File | LOC | Notes | |---|---:|---| -| `builtin.go` | 86 | Registry + `FactoryContext` (ctx, data dir, meter, logger, mgmt client) | +| `builtin.go` | 90 | Registry + `FactoryContext` (ctx, meter, logger, mgmt client) | | `all_test.go` | 41 | Locks the 8-ID registry surface | | `agentnetwork_chain_integration_test.go` | 319 | Live sqlite + real gRPC bufconn; gate→recorder wire path | | `llm_request_parser/*` | 162 / 66 / 356 | Provider detection, body parse, prompt extraction with capture-pointer gating | @@ -53,7 +53,7 @@ locks the ID set; adding or removing one is a conscious extension. | `llm_identity_inject/*` | 440 / 108 / 666 | HeaderPair (LiteLLM) + JSONMetadata (Portkey) + ExtraHeaders | | `llm_guardrail/*` | 176 / 82 / 75 / 219 / 217 | Model allowlist + optional prompt capture with PII redaction | | `llm_response_parser/*` | 258 / 222 / 43 / 433 / 169 / 111 | Buffered + SSE accumulation; AWS event-stream accumulator (`streaming_bedrock.go`) for Bedrock; capture-pointer gates completion emit | -| `cost_meter/*` | 181 / 84 / 439 | Token → USD via `proxy/internal/llm/pricing` | +| `cost_meter/*` | 236 / 98 / 586 | Token → USD via `proxy/internal/llm/pricing`; both pricing tiers arrive in the middleware config | | `llm_limit_record/*` | 144 / 35 / 191 | Post-flight `RecordLLMUsage` (5s, debug-on-error) | ## Per-middleware @@ -168,12 +168,46 @@ token schema. ### cost_meter -Reads `llm.provider` + `llm.model` + token buckets, looks up per-1k rate via -`pricing.Loader`, emits `cost.usd_total` or a closed-set `cost.skipped` -reason (`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`, -`unknown_model`). Loader's hot-reload goroutine is bound to proxy-lifetime -context via `startReloader`. **Key invariant:** provider-shape switch lives -in `pricing.Table.Cost` (sibling doc) — `cost_meter` stays provider-agnostic. +Reads `llm.provider` + `llm.model` + token buckets, looks up the per-1k rates, +and emits the full `cost.usd_*` breakdown (four per-bucket values plus the +`_total` and `_cache` aggregates) or a closed-set `cost.skipped` reason +(`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`, +`unknown_model`). + +**Management owns pricing.** The proxy carries no embedded price list: the whole +table arrives in this middleware's `ConfigJSON` as +`{pricing: {defaults, providers}}`, synthesized by management from the catalog +plus the operator's stored per-provider prices +([factory.go:13–34](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)). +Both tiers are validated by `pricing.NewTable` / `pricing.NewEntries` at +construction, so a non-finite or negative rate fails the chain build. A price +change is an ordinary mapping push — the chain rebuild yields a fresh instance +over a fresh immutable table, so there is no data dir, no pricing file, no +reload goroutine, and nothing to invalidate. + +**Two-tier lookup** +([middleware.go:165–183](../../../proxy/internal/middleware/builtin/cost_meter/middleware.go)): + +1. **Per-provider-record** — the operator's stored price for the route that + actually served the request, keyed by the `llm.resolved_provider_id` that + `llm_router` stamped on the allow path, then by normalized model id. Entries + arrive fully materialized (management folds default cache rates in at synth + time), so there is no merging here. Absent metadata — no router in the chain + — skips this tier. +2. **Surface defaults** — the catalog-derived table keyed by `llm.provider` + (`openai`/`anthropic`/`bedrock`). This is also what prices gateway-style + providers, which enumerate no models and therefore get no per-record entry. + +**Backward compatibility:** a config with no `pricing` block means management +predates config-delivered pricing. The factory logs one warning at build time +and the instance records `cost.skipped=unknown_model` ($0) for every request +rather than falling back to a stale built-in price list +([factory.go:55–60](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)). + +**Key invariant:** the provider-shape switch lives in `pricing.EntryCosts` +(sibling doc) and is selected by the **surface**, not by which tier the entry +came from — `cost_meter` stays provider-agnostic, and a per-record override on +an Anthropic route still bills its cache buckets additively. ### llm_limit_record @@ -246,12 +280,14 @@ no mocks. Tests: `TestChain_AllowPath_StampsAttributionAndRecordsCounter` | `llm_identity_inject` | `{providers: [{provider_id, header_pair?|json_metadata?, extra_headers?}]}` | | `llm_guardrail` | `{provider_allowlists: {providerID: []string}, prompt_capture: {enabled, redact_pii}}` — allowlist keyed by resolved provider id; a provider absent from the map is unrestricted (fail-closed backstop; authoritative per-policy/group check is management's `CheckLLMPolicyLimits`) | | `llm_response_parser` | `{redact_pii?, capture_completion?: *bool}` | -| `cost_meter` | `{pricing_path?}` (basename inside data-dir; defaults `pricing.yaml`) | +| `cost_meter` | `{pricing: {defaults: {surface: {model: rates}}, providers: {providerRecordID: {model: rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}`. A missing `pricing` key means "management predates config-delivered pricing": every request records `cost.skipped=unknown_model` | | `llm_limit_record` | `{}` — same pattern as `llm_limit_check` | All factories accept empty / null / `{}` / whitespace as zero-value config; only structurally invalid JSON is rejected so misconfig surfaces at chain -build time. +build time. `cost_meter` adds a semantic check on top of that: a `pricing` +block carrying a negative or non-finite rate fails the build too, rather than +mispricing live traffic. ## Invariants @@ -320,10 +356,11 @@ non-object `metadata` field — header path still attributes, but body-level tag-budget enforcement doesn't run for that request. -**Concurrency.** `cost_meter` shares a `pricing.Loader` via -`atomic.Pointer[Table]`; readers always see a consistent table. Every -middleware is a stateless value receiver. Integration test uses real bufconn -gRPC — race detector is the meaningful bar. +**Concurrency.** `cost_meter`'s two pricing tables are built once from the +middleware config and never mutated, so the lookup path needs no lock or atomic +swap — a price change replaces the whole instance. Every middleware is +otherwise a stateless value receiver. Integration test uses real bufconn gRPC — +race detector is the meaningful bar. **Perf.** Hot path is `lookupKV` linear scan over <10 KVs; `cost_meter.Cost` is O(1); SSE accumulation is single-pass. No map allocation per call. @@ -349,13 +386,13 @@ counter accuracy. | `llm_guardrail/redact_test.go` | 15 | Email, SSN, phone (E.164 + NA), bearer, IPv4; fixture-driven | | `llm_response_parser/middleware_test.go` | 18 | Buffered OAI+Anthro, capture-pointer, redact, truncation | | `llm_response_parser/streaming_test.go` | 7 | OAI usage frame, Anthro message_delta, truncated body best-effort | -| `cost_meter/middleware_test.go` | 17 | Each skip reason, provider-shape, pricing loader integration | +| `cost_meter/middleware_test.go` | 22 | Each skip reason, provider-shape formulas, config-delivered defaults, per-record-beats-defaults + miss-falls-back, per-record uses surface formula, nil-pricing skips everything, invalid-rate rejection | | `llm_limit_record/middleware_test.go` | 7 | Skip-on-no-signal, skip-on-missing-attribution, RPC failure swallowed | ## Cross-references - Sibling: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — SDK adapters - + SSE framer + pricing loader. + + SSE framer + pricing table and cost formula. - Path-routed providers (Vertex AI + Bedrock), `keyfile::` credential, GCP token minting, `/bedrock` prefix: [50-path-routed-providers.md](./50-path-routed-providers.md). diff --git a/docs/agent-networks/modules/32-proxy-llm-parsers.md b/docs/agent-networks/modules/32-proxy-llm-parsers.md index 0376bc988..52faeaac1 100644 --- a/docs/agent-networks/modules/32-proxy-llm-parsers.md +++ b/docs/agent-networks/modules/32-proxy-llm-parsers.md @@ -9,7 +9,7 @@ pricing table's per-provider cost formula is the highest-leverage place a small bug would silently mis-bill operators. Sibling module: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md) -— the 8 middlewares that consume this package's parsers + pricing loader. +— the 8 middlewares that consume this package's parsers + pricing table. --- @@ -24,8 +24,9 @@ proxy-framework dependencies: - `openai.go` / `anthropic.go` / `bedrock.go` — per-provider `Parser` impls. - `sse.go` — SSE scanner (`Scanner`, `Event`, `NewScanner`). - `errors.go` — sentinels callers branch on with `errors.Is`. -- `pricing/` — embedded-default + hot-reload override table with - symlink-safe Unix loader (build-tagged stub elsewhere). +- `pricing/` — immutable pricing table + the per-surface cost formula. The + rates themselves come from management inside `cost_meter`'s middleware + config; this package holds no price list and reads no files. - `fixtures/` — captured request/response/stream bodies the tests replay. The package carries zero proxy-framework dependencies so the same parsers can @@ -47,12 +48,9 @@ be reused later by a WASM adapter | `sse_test.go` | 175 | 12 tests; fixture replay + multiline + size limits | | `parser_test.go` | 53 | `Parsers()`, `DetectParser`, provider enum values | | `errors.go` | 31 | 6 sentinels: `Err{Unknown,Unsupported}Provider/Model`, `Err{NotLLM,Malformed}Response`, `ErrStreamingUnsupported`, `ErrMalformedRequest` | -| `pricing/pricing.go` | 421 | `Loader`, `Table`, `Entry`; embedded defaults + atomic swap + mtime reload | -| `pricing/pricing_unix.go` | 69 | `O_NOFOLLOW` + fstat-from-FD + 1 MiB cap | -| `pricing/pricing_other.go` | 21 | Stub returning "not supported on this platform" | -| `pricing/pricing_test.go` | 432 | 21 tests — symlink rejection, reload race, path traversal, oversize | -| `pricing/defaults_pricing.yaml` | 85 | go:embed source of truth | -| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream + pricing starter | +| `pricing/pricing.go` | 234 | `Table`, `Entry`, `EntryJSON`, `Costs`; `NewTable`/`NewEntries` validation + `EntryCosts` formula. No I/O, no reload, no embedded rates | +| `pricing/pricing_test.go` | 177 | 10 tests — provider-shape formulas, cached clamp, rate fallback, nil-safety, rate validation | +| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream | ## Request body → parser dispatch @@ -188,9 +186,11 @@ response leg, covering both Bedrock body shapes: `totalTokens`). `firstNonZero` folds the two naming conventions into one `Usage`; when Converse omits `totalTokens` the parser sums the buckets. -`ProviderName()` returns `"bedrock"` — its own `defaults_pricing.yaml` block, -keyed by the **normalised** model id (region prefix + version suffix stripped by -the request parser). `ParseResponse` returns `ErrStreamingUnsupported` for an +`ProviderName()` returns `"bedrock"` — its own pricing surface in the table +management ships, keyed by the **normalised** model id (region prefix + version +suffix stripped by the request parser; management normalises its keys the same +way at synth time so the two compare equal). `ParseResponse` returns +`ErrStreamingUnsupported` for an AWS binary event-stream content-type (`application/vnd.amazon.eventstream`, `isAWSEventStream`) so the caller routes to the streaming accumulator instead. @@ -205,11 +205,34 @@ response body. Streaming accumulators live in the middleware package ([llm_response_parser/streaming.go](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go)) but use `llm.NewScanner` so the framing contract stays here. -### Pricing catalog +### Pricing table -`Table.Cost` -([pricing.go:129–174](../../../proxy/internal/llm/pricing/pricing.go)) -is the cost formula — most security-relevant math in this module: +**Management is the sole pricing authority.** The proxy carries no embedded +price list and reads no pricing file: the whole table arrives inside +`cost_meter`'s `ConfigJSON` on the ordinary mapping push, and a price change +is just another push — the chain rebuild constructs a fresh `Table`, so there +is nothing to reload +([pricing.go:1–7](../../../proxy/internal/llm/pricing/pricing.go)). The +management side of the contract (catalog defaults, the operator's stored +per-provider prices, and `AgentNetwork.PricingDefaultsFile`) is covered in the +management-side module guide; `cost_meter`'s wire shape is in +[31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md). + +`EntryJSON` +([pricing.go:36–45](../../../proxy/internal/llm/pricing/pricing.go)) is the +management→proxy contract — five USD-per-1k rates under `input_per_1k`, +`output_per_1k`, `cached_input_per_1k`, `cache_read_per_1k`, +`cache_creation_per_1k`. Management's `pricing.Entry` marshals the identical +names, and `EntryJSON`/`Entry` are field-identical so `NewEntries` converts by +direct struct conversion rather than field-by-field copying (a new rate can't +be silently dropped in transit). + +`EntryCosts` +([pricing.go:183–234](../../../proxy/internal/llm/pricing/pricing.go)) +is the cost formula — most security-relevant math in this module. The +**surface** (the `llm.provider` value the request parser stamped) selects the +formula, never the tier the entry came from: a per-provider-record override on +an Anthropic route still bills its cache buckets additively. | Provider | Formula | |---|---| @@ -218,7 +241,7 @@ is the cost formula — most security-relevant math in this module: | default | `inTokens × InputPer1K + outTokens × OutputPer1K` | `bedrock` shares the Anthropic additive-cache formula -([pricing.go:172-174](../../../proxy/internal/llm/pricing/pricing.go)): +([pricing.go:214–229](../../../proxy/internal/llm/pricing/pricing.go)): Anthropic-on-Bedrock reports the same additive cache buckets, while non-Anthropic Bedrock models (Nova, Llama) simply report zero in those buckets so cost reduces to `input + output`. @@ -226,15 +249,12 @@ to `input + output`. Each per-bucket rate falls back to `InputPer1K` when zero — operators opt in to discounts by setting the field. -`Loader` -([pricing.go:212–268](../../../proxy/internal/llm/pricing/pricing.go)) -overlays an optional `pricing.yaml` from data-dir on top of the go:embed -defaults. Atomic pointer swap means readers never observe a partial update. -The mtime-poll reloader (30s default cadence) keeps the previous table on -parse failure so cost annotation never goes blank during a botched edit. - -`defaults_pricing.yaml` is the source of truth for built-in pricing. -Operator overrides only carry the entries they want to change. +`Costs` +([pricing.go:143–163](../../../proxy/internal/llm/pricing/pricing.go)) is the +per-request split. The four per-bucket fields are the base; `TotalUSD` and +`CacheUSD` are **derived** in `newCosts` so the aggregates can never drift from +the breakdown. `InputUSD` is always the non-cached input bucket on both +provider shapes, so input and cached-input never double-count. ## Public contracts @@ -264,29 +284,38 @@ Order matters: `DetectFromURL` ties resolve by registration order. `ProviderBedrock = 3`. Numeric values are persisted in nothing today but treat them as wire-stable — new providers must take fresh numbers. -**`Pricing` lookup** -([pricing.go:129](../../../proxy/internal/llm/pricing/pricing.go)): +**`Pricing` construction + lookup** +([pricing.go:60–130](../../../proxy/internal/llm/pricing/pricing.go)): ```go +func NewEntries(raw map[string]map[string]EntryJSON) (map[string]map[string]Entry, error) +func NewTable(raw map[string]map[string]EntryJSON) (*Table, error) + +func (t *Table) Lookup(provider, model string) (Entry, bool) func (t *Table) Cost(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (float64, bool) +func (t *Table) Costs(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (Costs, bool) +func EntryCosts(entry Entry, surface string, inTokens, outTokens, cachedInput, cacheCreation int64) Costs ``` -Nil-safe: `t.Cost` on a nil receiver returns `(0, false)` -([pricing.go:130–132](../../../proxy/internal/llm/pricing/pricing.go)). -`ok=false` means provider or model is absent from the loaded table; the caller -emits `cost.skipped=unknown_model`. +`NewTable` is the surface-keyed defaults table; `NewEntries` returns the raw +two-level map `cost_meter` uses for the per-provider-record tier (it looks up an +`Entry` directly and calls `EntryCosts`, so it needs no `Table` wrapper). Both +reject any non-finite or negative rate, so a corrupt config fails the chain +build rather than mispricing silently. Nil input yields an empty, +never-matching table. + +Nil-safe: `t.Cost`/`t.Lookup` on a nil receiver returns `ok=false` +([pricing.go:96–99](../../../proxy/internal/llm/pricing/pricing.go)). +`ok=false` means the surface or model is absent from the table management sent; +the caller emits `cost.skipped=unknown_model`. ## Invariants -1. **Cross-platform pricing build.** `pricing_unix.go` carries the only - functional `loadPricing` (uses `syscall.O_NOFOLLOW` and `f.Stat()` on an - open descriptor — both Unix-only). `pricing_other.go` is a build-tag - fallback that returns `"not supported on this platform"` - ([pricing_other.go:14–16](../../../proxy/internal/llm/pricing/pricing_other.go)). - The proxy is Linux-only in production today; a Windows port needs an - equivalent path-as-handle implementation. Reviewers building on Windows - should expect this surface to return an error at startup if an override - file is configured. +1. **The pricing package is pure and platform-independent.** No file I/O, no + `//go:embed`, no goroutines, no build tags — the rates arrive as config, so + there is nothing platform-specific left to port. Anything reintroducing a + read-from-disk path here re-splits pricing authority between management and + the proxy, which is exactly what this design removed. 2. **SSE scanner handles partial chunks.** A buffered prefix that doesn't end in `\n\n` still yields its accumulated event before `io.EOF` @@ -298,38 +327,45 @@ emits `cost.skipped=unknown_model`. usage rather than aborting ([streaming.go:68–73, 144–150](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go)). -3. **`defaults_pricing.yaml` is the source of truth.** Compiled into the - binary via `//go:embed` - ([pricing.go:29–30](../../../proxy/internal/llm/pricing/pricing.go)). - `DefaultTable()` parses once and panics on parse failure - ([pricing.go:42–49](../../../proxy/internal/llm/pricing/pricing.go)) - — by design: a broken embedded YAML must not ship to production. +3. **Management is the only source of rates.** `Table` has no constructor that + invents prices: the only way in is `NewTable`/`NewEntries` over the wire map + management sent. A missing or empty `pricing` block therefore means *no + prices at all* (`cost_meter` records `cost.skipped=unknown_model`, $0) — + never a stale built-in fallback that would silently bill list price. -4. **Loader path validation.** `resolveMiddlewareDataPath` - ([pricing.go:370–394](../../../proxy/internal/llm/pricing/pricing.go)) - rejects absolute paths, traversal segments, and basenames that fail - `basenameRegex = ^[a-zA-Z0-9._-]+$`. The resolved path must remain - inside `baseDir` even after `filepath.Clean`. Tests: - `TestNewLoader_PathValidation`, `TestNewLoader_PathValidation_Extended`, - `TestNewLoader_SymlinkOutsideBaseDirRejected`, `TestNewLoader_SymlinkRejected`. +4. **Tables are immutable once built.** `Table.entries` is written only in + `NewEntries` and never mutated afterwards, and `cost_meter`'s `perRecord` + map is likewise build-time-only + ([pricing.go:47–52](../../../proxy/internal/llm/pricing/pricing.go)). This + is what makes the no-reload design safe: a price change arrives as a mapping + push that builds a new middleware instance over a new table, so concurrent + readers can't observe a half-updated price list and no atomic swap or lock + is needed on the hot path. -5. **Unix loader symlink safety.** `O_NOFOLLOW` on open, `f.Stat()` on the - open descriptor (never re-stat by path), `info.Mode().IsRegular()` check, - `io.LimitReader(f, maxPricingBytes+1)` with a final size assertion - ([pricing_unix.go:25–57](../../../proxy/internal/llm/pricing/pricing_unix.go)). - A mid-read symlink swap is detected because the fstat is on the original - fd. Test: `TestNewLoader_RejectsOversizedFile_FixesM4`. +5. **Rate validation happens at chain-build time, not per request.** + `NewEntries` rejects negative, NaN, and ±Inf rates field by field + ([pricing.go:60–83](../../../proxy/internal/llm/pricing/pricing.go)), naming + the offending surface/model/field in the error. Management enforces the same + constraints at its API boundary and in its YAML parser, so this is + defense-in-depth — but it means a corrupt push fails loudly at build instead + of producing negative costs on live traffic. Test: + `TestNewTable_ValidatesRates`. -6. **`yaml.NewDecoder(...).KnownFields(true)`** - ([pricing.go:397–398](../../../proxy/internal/llm/pricing/pricing.go)) - rejects YAML files that carry fields not in the schema. A typo in an - operator override file fails loud instead of silently zeroing rates. +6. **New rates must be added to `Entry`, `EntryJSON`, *and* management's + `pricing.Entry` together.** `NewEntries` converts by direct struct + conversion `Entry(e)` + ([pricing.go:76–78](../../../proxy/internal/llm/pricing/pricing.go)), which + only compiles while the two structs stay field-identical — so the proxy half + is compiler-enforced. The management half is not: a rate added there but not + here unmarshals into nothing and prices that bucket at `InputPer1K`. ## Things to scrutinise -**Correctness.** Verify OpenAI cached-prompt clamp at -[pricing.go:147–149](../../../proxy/internal/llm/pricing/pricing.go) -short-circuits before subtraction. `Anthropic.TotalTokens` sums all four +**Correctness.** Verify the OpenAI cached-prompt clamp at +[pricing.go:203–206](../../../proxy/internal/llm/pricing/pricing.go) +short-circuits before subtraction. Negative token counts are clamped to zero up +front ([pricing.go:186–197](../../../proxy/internal/llm/pricing/pricing.go)) so +no formula can yield a negative cost. `Anthropic.TotalTokens` sums all four buckets (in + out + cache_read + cache_creation) — downstream dashboards need to know this differs from `input + output`. `OpenAIParser.ExtractPrompt` falls through `messages → input → prompt`; a @@ -338,22 +374,27 @@ noting). **Security.** `Scanner.maxLine = 1 MiB`; a 2 MiB single-line `data:` event errors from `Scanner.Next` and both accumulators stop with partial usage. -Pricing file 1 MiB cap is orders of magnitude larger than realistic. Confirm -new schema additions are mirrored in both `pricingFile` and `Entry`; -`KnownFields(true)` will reject silently-typo'd operator overrides -otherwise. +Pricing is no longer file-backed, so the loader's path-traversal / symlink / +oversize surface is gone entirely — the config channel (an authenticated +mapping push from management) is now the only way rates enter the proxy, and +`NewEntries` is the validation boundary on it. A new rate added to management's +`pricing.Entry` but not to `EntryJSON` here is the remaining silent-mispricing +path (see invariant 6). -**Concurrency.** `Loader.table` is `atomic.Pointer[Table]`; readers never -block or see a torn table. `Loader.Reload` is one goroutine, cancelled via -context (`TestLoader_ReloadBackgroundLoopCancellation`). `DefaultTable()` -uses `sync.Once`. Per-call `Scanner` instances mean no shared state across -concurrent response-parser calls. +**Concurrency.** Nothing in this package is shared mutable state: tables are +built once and never written again, so `cost_meter`'s hot path is lock-free by +construction rather than by atomic swap. Per-call `Scanner` instances mean no +shared state across concurrent response-parser calls. -**Perf.** `Table.Cost` is two map lookups + multiplications, O(1). -`Scanner.Next` is one `ReadString('\n')` per line. Pricing reload poll 30s. +**Perf.** `Table.Cost` is two map lookups + multiplications, O(1); the +per-provider-record tier adds at most one more lookup. `Scanner.Next` is one +`ReadString('\n')` per line. No background goroutines and no per-request +allocation of pricing state. -**Observability.** Reload failures count via `metric.Int64Counter` keyed -`plugin`; warning log rate-limited at 5 min so a broken file doesn't flood. +**Observability.** A config carrying no `pricing` block logs one warning at +chain-build time (`cost_meter` factory) and then records +`cost.skipped=unknown_model` per request, so an old-management deployment is +visible in both logs and the access log rather than quietly reporting $0. Parser errors return sentinels — middleware uses `errors.Is` to map to the right `cost.skipped` reason. @@ -365,7 +406,7 @@ right `cost.skipped` reason. | `openai_test.go` | 11 | Chat Completions + Responses API + legacy `prompt`; cached-tokens subset for both naming conventions; fixture replays | | `anthropic_test.go` | 7 | Messages + legacy `/v1/complete`; streaming REJECTED on `ParseResponse` (must use scanner); fixture replays | | `sse_test.go` | 12 | Fixture replay both providers; multiline `data:`; CRLF; comment skip; trailing-event-without-blank-line; oversize rejection | -| `pricing/pricing_test.go` | 21 | Provider-shape switch; cached-rate fallback; cached-clamp; symlink rejection (target outside basedir + symlink to file); path validation matrix; oversize rejection; reload-keeps-previous-on-parse-error; mtime change detection; goroutine cancellation | +| `pricing/pricing_test.go` | 10 | Provider-shape switch (surface selects the formula); cached-rate + cache-read/creation fallback to `InputPer1K`; cached-clamp; negative-token clamp; nil-receiver safety; rate validation (negative / NaN / Inf rejected); nil + empty table | **Fixtures** ([proxy/internal/llm/fixtures/](../../../proxy/internal/llm/fixtures/)): `openai_chat_completion.json` (chat.completions with usage), @@ -373,14 +414,15 @@ right `cost.skipped` reason. `openai_stream.txt` (3 deltas + usage + `[DONE]`), `anthropic_messages.json` (Messages API non-streaming), `anthropic_stream.txt` (full 7-event sequence: message_start → -content_block_{start,delta×2,stop} → message_delta (usage) → message_stop), -`pricing.yaml` (realistic-pricing starter for operator overrides). +content_block_{start,delta×2,stop} → message_delta (usage) → message_stop). +No pricing fixture: the table is config-delivered, so pricing tests construct +it in-process from a wire-shape map. ## Cross-references - Sibling: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md) — the chain that calls `llm.Parsers()`, `llm.ParserByName`, - `llm.NewScanner`, `pricing.NewLoader`. + `llm.NewScanner`, `pricing.NewTable` / `pricing.NewEntries`. - Path-routed providers (Vertex AI + Bedrock), credential syntax, and the Bedrock AWS event-stream accumulator: [50-path-routed-providers.md](./50-path-routed-providers.md). diff --git a/docs/agent-networks/modules/33-proxy-runtime.md b/docs/agent-networks/modules/33-proxy-runtime.md index f553473f8..54046b614 100644 --- a/docs/agent-networks/modules/33-proxy-runtime.md +++ b/docs/agent-networks/modules/33-proxy-runtime.md @@ -1,7 +1,7 @@ # proxy/runtime — translate + serve + log > **Risk level:** High — every config push from management is translated here, and the chain runs on every HTTP request to a synth target. -> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareDataDir`, `MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path. +> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path. Middleware config is entirely wire-delivered — no proxy-side data dir is involved, including for LLM pricing, which management ships inside `cost_meter`'s config. ## Module boundary @@ -114,8 +114,7 @@ At **request time** the access-log middleware stamps `CapturedData`; the auth ch ## Public contracts touched -- `proxy.Server.MiddlewareDataDir` (string) — base dir for file-backed middleware config (server.go:238-241). -- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:248-250). +- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:249-253). There is no `MiddlewareDataDir`: no built-in middleware reads config from disk, so `builtin.FactoryContext` carries only the proxy-lifetime context, meter, logger, and management client. - `proxy/internal/proxy.WithMiddlewareManager(*middleware.Manager) Option` — new option on `NewReverseProxy`; nil keeps the fast path (reverseproxy.go:48-56). - `proxy/internal/proxy.PathTarget` adds `Middlewares`, `CaptureConfig`, `AgentNetwork`, `DisableAccessLog` (servicemapping.go:27-51), all zero-default. - `proxy/internal/proxy.CapturedData` adds `agentNetwork`, `suppressAccessLog`, `userGroupNames` behind `sync.RWMutex`; slices deep-copied (context.go:47-66, 183-258). diff --git a/docs/agent-networks/modules/50-path-routed-providers.md b/docs/agent-networks/modules/50-path-routed-providers.md index b7cda3a97..08c976c5f 100644 --- a/docs/agent-networks/modules/50-path-routed-providers.md +++ b/docs/agent-networks/modules/50-path-routed-providers.md @@ -87,9 +87,9 @@ strips the `@version` suffix from the model, and maps the publisher to a parser surface via `vertexPublisherVendor`: - `anthropic` → `llm.provider="anthropic"` → metered through the Anthropic - parser, priced under the **`anthropic`** block in `defaults_pricing.yaml` - (the parser emits the standard Anthropic provider label, so Vertex Claude - reuses first-party Anthropic prices). + parser, priced under the **`anthropic`** surface of the pricing table + management ships (the parser emits the standard Anthropic provider label, so + Vertex Claude reuses first-party Anthropic prices). - `openai` → `llm.provider="openai"` (reserved; not in the catalog lineup today). - anything else (notably `google` / Gemini) → empty vendor → **no parser**. @@ -104,8 +104,9 @@ is omitted from the catalog. > Caveat: cross-region inference profiles in `eu` / `apac` carry a ~10% price > premium that the base per-token rates do **not** model — cost annotations for -> those regions read low. Operators who need exact regional billing override -> the affected entries in `pricing.yaml`. +> those regions read low. Operators who need exact regional billing set the +> affected models' prices on the provider record, or replace the default entries +> via management's `AgentNetwork.PricingDefaultsFile`. ## AWS Bedrock (`bedrock_api`) @@ -211,15 +212,19 @@ so a model-listing call can't be rewritten onto an upstream that would 404 it. ## Catalog ↔ pricing cross-check Catalog prices and context windows are cross-checked against LiteLLM's -`model_prices_and_context_window.json`. The proxy's embedded -`defaults_pricing.yaml` covers **every metered first-party model** the catalog -enumerates — guarded by -`TestDefaultTable_FirstPartyModelCoverage` -([pricing/defaults_coverage_test.go](../../../proxy/internal/llm/pricing/defaults_coverage_test.go)), -which fails if a catalog model has no embedded price. Bedrock entries are keyed -by the **normalised** id the request parser emits (region prefix + version -suffix stripped). Vertex Claude carries no Bedrock-style prefix, so it prices -straight off the `anthropic` block. +`model_prices_and_context_window.json`. The **catalog is the source of default +prices**: management's `pricing.DefaultTable` folds every catalog provider's +models into the surfaces that provider declares (`PricingSurfaces`), so coverage +is structural rather than maintained in a parallel file +([pricing/defaults.go](../../../management/internals/modules/agentnetwork/pricing/defaults.go)). +`TestDefaultTable_CoversEveryCatalogModel` fails if a catalog model ends up +unpriced, and `TestDefaultTable_NoConflictingContributions` fails if two +providers contribute the same (surface, model) at different rates. Bedrock +entries are keyed by the **normalised** id the request parser emits (region +prefix + version suffix stripped) — management applies the same normalisation to +per-provider prices at synth time, so the two keys compare equal. Vertex Claude +carries no Bedrock-style prefix, so it prices straight off the `anthropic` +surface. ## Things to scrutinise @@ -232,16 +237,17 @@ operator-misconfigured Vertex provider and unmetered Gemini traffic; verify publishers). **Correctness.** `normalizeBedrockModel` is the join between the wire id and the -pricing key — a model that normalises to something not in `defaults_pricing.yaml` -meters at `cost.skipped=unknown_model` rather than failing the request. The +pricing key — a model that normalises to something absent from the shipped +pricing table meters at `cost.skipped=unknown_model` rather than failing the +request. The `/bedrock` prefix strip must run on both the parser side (so the model is extracted) and the router side (so the upstream path is native); a regression in either silently breaks the other. **Metering caveats.** eu/apac cross-region Bedrock + Vertex profiles carry a -~10% premium not modelled by base pricing — flagged in both the catalog comment -and `defaults_pricing.yaml`. Operators needing exact regional billing override -the relevant entries. +~10% premium not modelled by base pricing — flagged in the catalog comment. +Operators needing exact regional billing set per-provider prices on the model +rows (or replace the default entries via `AgentNetwork.PricingDefaultsFile`). ## Cross-references diff --git a/e2e/agentnetwork/chat_test.go b/e2e/agentnetwork/chat_test.go index ed94623fe..792f67c89 100644 --- a/e2e/agentnetwork/chat_test.go +++ b/e2e/agentnetwork/chat_test.go @@ -438,14 +438,10 @@ func TestProvidersMatrix(t *testing.T) { // Create every provider, all enabled, each with a unique model string so the // proxy's connect-time snapshot carries them all and model→provider routing // is unambiguous (provider toggles after connect don't reconcile to the - // proxy, so we enable everything up front). The first create bootstraps the - // cluster. + // proxy, so we enable everything up front). ids := make([]string, 0, len(matrix)) - for i, pc := range matrix { + for _, pc := range matrix { req := providerRequest(pc) - if i == 0 { - req.BootstrapCluster = ptr(harness.AgentNetworkCluster) - } prov, perr := srv.CreateProvider(ctx, req) require.NoError(t, perr, "create provider %s", pc.name) ids = append(ids, prov.Id) diff --git a/e2e/agentnetwork/custom_pricing_test.go b/e2e/agentnetwork/custom_pricing_test.go index 33788a16a..90e198d3d 100644 --- a/e2e/agentnetwork/custom_pricing_test.go +++ b/e2e/agentnetwork/custom_pricing_test.go @@ -23,9 +23,10 @@ import ( // model the client asks for. The proxy prices off the REQUEST model, not the // upstream response model, so a made-up model id billed at operator rates lets // these tests assert exact costs without a real vendor key. +// Sourced from the harness so the counts can't drift from the mock's config. const ( - vllmPromptTokens = 11 - vllmCompletionTokens = 2 + vllmPromptTokens = harness.VLLMChatInputTokens + vllmCompletionTokens = harness.VLLMChatOutputTokens ) // pricedEnv is a connected single-provider agent-network deployment pointed at @@ -82,13 +83,12 @@ func provisionPricedProvider(t *testing.T, ctx context.Context, name string, mod // need NOT be in the catalog — the operator names it and prices it here. dummyKey := "sk-price-e2e" prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: name, - ProviderId: "openai_api", - UpstreamUrl: vllm.URL, - ApiKey: &dummyKey, - Enabled: ptr(true), - BootstrapCluster: ptr(harness.AgentNetworkCluster), - Models: &models, + Name: name, + ProviderId: "openai_api", + UpstreamUrl: vllm.URL, + ApiKey: &dummyKey, + Enabled: ptr(true), + Models: &models, }) require.NoError(t, err, "create provider") t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) @@ -163,30 +163,90 @@ func chatOnce(t *testing.T, ctx context.Context, env pricedEnv, model, sessionID break } } - time.Sleep(5 * time.Second) + if !waitBeforeRetry(ctx, 5*time.Second) { + break + } } require.Equal(t, 200, code, "chat for %s must return 200; body: %s\n=== proxy logs ===\n%s", model, body, env.proxy.Logs(context.Background())) return body } -// findAccessLogBySession polls the access-log page for the row carrying sessionID. -func findAccessLogBySession(t *testing.T, ctx context.Context, sessionID string) api.AgentNetworkAccessLog { - t.Helper() - var row api.AgentNetworkAccessLog - require.Eventually(t, func() bool { - logs, lerr := srv.ListAccessLogs(ctx) - if lerr != nil { - return false - } - for _, r := range logs.Data { - if r.SessionId != nil && *r.SessionId == sessionID { - row = r - return true +// accessLogIngestWindow is how long a single request's access-log row is given +// to appear before the caller gives up on it. +// accessLogIngestWindow bounds how long a row may take to appear after its +// request returned. The proxy streams each entry to management with a 10s send +// timeout of its own, so a request whose send hits one full timeout and is +// retried has not yet missed anything real — 30s left barely three send +// attempts of headroom and lost the race on a loaded runner. +const accessLogIngestWindow = 60 * time.Second + +// accessLogPollInterval is how long the lookup waits between pages. Ingest is +// asynchronous, so the row lands somewhere inside the window rather than on +// any particular poll. +const accessLogPollInterval = 2 * time.Second + +// lookupAccessLogBySession polls the access-log page for the row carrying +// sessionID and reports whether it arrived within the window. It never fails +// the test: callers that can recover — by firing a fresh request under a new +// session — need to see the miss rather than die on it. +func lookupAccessLogBySession(ctx context.Context, sessionID string, within time.Duration) (api.AgentNetworkAccessLog, bool) { + deadline := time.Now().Add(within) + for { + // Each poll is bounded by what is left of the window rather than by the + // caller's context: a single stalled request would otherwise hold the + // loop open long past the ingest window it is meant to enforce, and the + // caller would read the delay as a missing row. + if logs, lerr := listAccessLogsBy(ctx, deadline); lerr == nil { + for _, r := range logs.Data { + if r.SessionId != nil && *r.SessionId == sessionID { + return r, true + } } } - return false - }, 30*time.Second, 2*time.Second, "session id %q must be recorded in an access-log row", sessionID) + // The wait is bounded by the window as well, so the answer arrives when + // the caller's budget runs out rather than a poll interval later: a + // full interval slept past the deadline reports "no row" up to two + // seconds late, which reads as a slower lookup than the one asked for. + wait := time.Until(deadline) + if wait > accessLogPollInterval { + wait = accessLogPollInterval + } + if wait <= 0 { + return api.AgentNetworkAccessLog{}, false + } + timer := time.NewTimer(wait) + select { + case <-ctx.Done(): + timer.Stop() + return api.AgentNetworkAccessLog{}, false + case <-timer.C: + } + // Checked after the wait rather than before the request: a poll issued + // past the deadline carries no budget and would fail on arrival. + if !time.Now().Before(deadline) { + return api.AgentNetworkAccessLog{}, false + } + } +} + +// listAccessLogsBy fetches one access-log page under a context that expires at +// deadline, so no single call can outlive the window its caller is polling +// within. The parent's cancellation still applies: the child inherits it. +func listAccessLogsBy(ctx context.Context, deadline time.Time) (api.AgentNetworkAccessLogsResponse, error) { + reqCtx, cancel := context.WithDeadline(ctx, deadline) + defer cancel() + return srv.ListAccessLogs(reqCtx) +} + +// findAccessLogBySession polls the access-log page for the row carrying +// sessionID, failing the test if it never lands. Use it for a request whose row +// must exist; where a missing row is a recoverable race, use +// lookupAccessLogBySession and retry. +func findAccessLogBySession(t *testing.T, ctx context.Context, sessionID string) api.AgentNetworkAccessLog { + t.Helper() + row, ok := lookupAccessLogBySession(ctx, sessionID, accessLogIngestWindow) + require.True(t, ok, "session id %q must be recorded in an access-log row", sessionID) return row } @@ -320,6 +380,11 @@ func TestPriceChangeUpdatesRecordedCost(t *testing.T) { outRateA = 0.020 inRateB = 0.050 // 5x / 4x the original, so a repriced row is unmistakable outRateB = 0.080 + // Per-attempt ingest wait, shorter than the default so a request that + // produces no row costs one retry rather than most of the budget, and an + // overall deadline long enough to hold several attempts. + repriceIngestWindow = 20 * time.Second + repriceDeadline = 180 * time.Second ) env := provisionPricedProvider(t, ctx, "reprice", []api.AgentNetworkProviderModel{ @@ -354,27 +419,61 @@ func TestPriceChangeUpdatesRecordedCost(t *testing.T) { // reading its cost, so an un-ingested row is never mistaken for "still rate A". // The expected new input cost is unmistakably higher than rate A, so a // lingering old-rate row can't satisfy the check. + // + // Every way an iteration can come up short — the request failing, its row not + // landing, or the row still carrying rate A — is a symptom of the same + // in-flight rebuild, so each one retries under a fresh session rather than + // ending the test. Only the outer deadline is fatal. wantInputB := float64(vllmPromptTokens) / 1000 * inRateB var repriced api.AgentNetworkAccessLog var lastSession string - deadline := time.Now().Add(90 * time.Second) + // The cost last read, kept separately: repriced is the zero value on every + // path that gives up, so reporting its cost would say "$0.000000" whether + // the rows were still at rate A or no row was ever read. + var lastCost float64 + var sawRow bool + deadline := time.Now().Add(repriceDeadline) + // Everything inside the loop runs under the deadline rather than the + // test's own context. An attempt started just before it would otherwise + // run well past it: the chat container is capped at 90s of its own and the + // row lookup at another 20s, so the loop could report a repricing failure + // nearly two minutes after the window it was given had closed. + repriceCtx, cancelReprice := context.WithDeadline(ctx, deadline) + defer cancelReprice() for time.Now().Before(deadline) { lastSession = fmt.Sprintf("e2e-session-reprice-b-%d", time.Now().UnixNano()) - code, _, cerr := env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireChat, customModel, "Reply with exactly: pong", lastSession) + code, _, cerr := env.client.Chat(repriceCtx, env.endpoint, env.proxyIP, harness.WireChat, customModel, "Reply with exactly: pong", lastSession) if cerr != nil || code != 200 { - time.Sleep(5 * time.Second) + if !waitBeforeRetry(repriceCtx, 5*time.Second) { + break + } + continue + } + row, ok := lookupAccessLogBySession(repriceCtx, lastSession, repriceIngestWindow) + if !ok { + // No row for this request. The proxy now publishes a rebuilt chain + // before the route that reaches it, so a request can no longer be + // served unattributed mid-update; this retry covers the ingest + // window alone. Fire another one under a fresh session. + t.Logf("no access-log row for session %q within %s; retrying under a fresh session", lastSession, repriceIngestWindow) continue } - row := findAccessLogBySession(t, ctx, lastSession) if inDelta(row.InputCostUsd, wantInputB, 1e-6) { repriced = row break } // Still priced at the old rate — the push hasn't landed yet; retry. - time.Sleep(5 * time.Second) + lastCost, sawRow = row.InputCostUsd, true + if !waitBeforeRetry(repriceCtx, 5*time.Second) { + break + } } - require.NotEmpty(t, repriced.Id, "a request after the price change must be priced at the new rate B; last input_cost_usd=$%.6f, wanted $%.6f\n=== proxy logs ===\n%s", - repriced.InputCostUsd, wantInputB, env.proxy.Logs(context.Background())) + lastSeen := "no row was ever read" + if sawRow { + lastSeen = fmt.Sprintf("last input_cost_usd=$%.6f", lastCost) + } + require.NotEmpty(t, repriced.Id, "a request after the price change must be priced at the new rate B; %s, wanted $%.6f\n=== proxy logs ===\n%s", + lastSeen, wantInputB, env.proxy.Logs(context.Background())) assertOpenAICostAtRates(t, repriced, inRateB, outRateB) verifyUsageRowForSession(t, lastSession, inRateB, outRateB) @@ -631,3 +730,47 @@ func inDelta(a, b, tol float64) bool { } return d <= tol } + +// TestCustomDatedModelKeepsItsOwnPrice covers the review fix that anchored the +// release-date fallback to Claude ids. Pricing looks every model up through +// that helper, so while it matched a bare trailing date any operator id ending +// in eight digits inherited the rate of its undated sibling — a silent +// mis-bill on models NetBird knows nothing about. +func TestCustomDatedModelKeepsItsOwnPrice(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute) + defer cancel() + + const ( + baseModel = "internal-llm" + datedModel = "internal-llm-20250101" + baseIn = 0.010 + baseOut = 0.020 + // An order of magnitude apart, so a row billed at the wrong entry is + // unmistakable rather than a rounding argument. + datedIn = 0.100 + datedOut = 0.200 + ) + + env := provisionPricedProvider(t, ctx, "customdated", []api.AgentNetworkProviderModel{ + {Id: baseModel, InputPer1k: baseIn, OutputPer1k: baseOut}, + {Id: datedModel, InputPer1k: datedIn, OutputPer1k: datedOut}, + }) + + t.Run("the undated id bills at its own rate", func(t *testing.T) { + session := fmt.Sprintf("e2e-session-customdated-base-%d", time.Now().UnixNano()) + chatOnce(t, ctx, env, baseModel, session) + assertOpenAICostAtRates(t, findAccessLogBySession(t, ctx, session), baseIn, baseOut) + }) + + t.Run("the dated id keeps its own rate", func(t *testing.T) { + session := fmt.Sprintf("e2e-session-customdated-dated-%d", time.Now().UnixNano()) + chatOnce(t, ctx, env, datedModel, session) + row := findAccessLogBySession(t, ctx, session) + assertOpenAICostAtRates(t, row, datedIn, datedOut) + + // Spelled out because it is the regression: inheriting the sibling's + // rate would bill this request at a tenth of its price. + assert.Greater(t, row.InputCostUsd, float64(vllmPromptTokens)/1000*baseIn*2, + "a custom dated id must not inherit the undated entry's rate") + }) +} diff --git a/e2e/agentnetwork/discovery_live_test.go b/e2e/agentnetwork/discovery_live_test.go new file mode 100644 index 000000000..22c9f31c2 --- /dev/null +++ b/e2e/agentnetwork/discovery_live_test.go @@ -0,0 +1,447 @@ +//go:build e2e + +package agentnetwork + +import ( + "context" + "encoding/json" + "os" + "sort" + "strconv" + "strings" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/e2e/harness" + sharedllm "github.com/netbirdio/netbird/shared/llm" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// TestLiveModelDiscovery drives model discovery against the REAL vendor +// endpoints — OpenAI, Anthropic, Bedrock and Vertex — rather than the mock. +// +// The mock upstream proves the filter's mechanics: it advertises ids we chose, +// so a listing narrowing to the ones we authorised is arithmetic we already +// controlled both sides of. What it cannot prove is that the filter survives +// contact with a real catalogue — ids we never enumerated, dated builds whose +// suffix the vendor picks, surfaces that answer a listing request with +// something other than a listing. That is what this covers, and it is the part +// a QA engineer would otherwise have to walk through by hand. +// +// One proxy serves every case. Each provider gets its own group, policy and +// client, because a model-less request matches exactly ONE route +// (matchModelless): with two providers authorised for the same caller, the +// listing would go to whichever won the tiebreak and the other would go +// untested. Group-scoping the caller makes each provider the only candidate +// for its own client. +func TestLiveModelDiscovery(t *testing.T) { + cases := liveDiscoveryCases() + if len(cases) == 0 { + t.Skip("no provider keys set; source ~/.llm-keys to run live model discovery") + } + + ctx, cancel := context.WithTimeout(context.Background(), 30*time.Minute) + defer cancel() + + t.Logf("[discovery] live matrix: %s", strings.Join(caseNames(cases), ", ")) + + // Provision every provider, group and policy before the proxy starts: the + // proxy takes a configuration snapshot at connect time and does not + // reconcile provider changes made afterwards. + keys := make(map[string]string, len(cases)) + for i := range cases { + keys[cases[i].name] = provisionLiveDiscovery(t, ctx, &cases[i]) + } + + endpoint, firstIP, firstClient, px := connectClient(t, ctx, "disc-live", keys[cases[0].name]) + clients := map[string]*harness.Client{cases[0].name: firstClient} + ips := map[string]string{cases[0].name: firstIP} + for _, tc := range cases[1:] { + cl := joinClient(t, ctx, px, endpoint, keys[tc.name]) + ip, err := cl.ResolveProxyIP(ctx, endpoint) + require.NoError(t, err, "resolve endpoint from the %s client", tc.name) + clients[tc.name] = cl + ips[tc.name] = ip + } + + for _, tc := range cases { + t.Run(tc.name, func(t *testing.T) { + runLiveDiscoveryCase(t, ctx, tc, clients[tc.name], endpoint, ips[tc.name]) + }) + } +} + +// discoveryOutcome is what a discovery request must produce end to end. The +// three are genuinely different contracts, not degrees of success: only the +// first puts a bounded listing in front of the caller. +type discoveryOutcome int + +const ( + // outcomeFiltered: the proxy routes the request and bounds the response to + // what the caller may use. + outcomeFiltered discoveryOutcome = iota + // outcomeDenied: no provider of this shape can serve the surface, so the + // proxy refuses rather than rewriting the request onto an upstream that + // would 404 it. The caller gets a NetBird error, not a vendor one. + outcomeDenied + // outcomeUpstreamNoListing: the proxy routes the request to the configured + // upstream, and the vendor does not implement the endpoint there. Proxy + // side correct, product side a dead end — see the Bedrock case. + outcomeUpstreamNoListing +) + +// liveDiscoveryCase is one provider's discovery surface and what the proxy +// must make of it. +type liveDiscoveryCase struct { + name string + catalogID string + upstream string + apiKey string + + // path is the discovery endpoint the client calls. Not every surface uses + // /v1/models: Bedrock lists inference profiles instead. + path string + // headers the vendor requires on a bare GET (Anthropic versions its API + // through a header, and rejects a request without one). + headers []string + + // models the provider record enumerates. Empty models a gateway record, + // which enumerates nothing and claims everything. + models []string + // allowlist, when non-empty, is a guardrail narrowing the policy below the + // provider's own enumeration — the second of the two bounds discovery + // applies, and the only one a provider record alone cannot demonstrate. + allowlist []string + + // outcome is what this surface must produce end to end. + outcome discoveryOutcome + + // permitted is every id allowed to survive filtering, in the form the + // provider record registers it. A surviving id counts as permitted when it + // matches one of these outright or after Anthropic date-normalisation. + permitted []string + // wantHidden are ids the upstream is known to advertise and the bound must + // remove. Only set where we enumerate the model ourselves, so the + // expectation cannot rot when a vendor changes its catalogue. + wantHidden []string +} + +// liveDiscoveryCases builds the matrix from whichever provider credentials are +// present, mirroring availableProviders' env-var gating so a partial key set +// still yields partial coverage. +func liveDiscoveryCases() []liveDiscoveryCase { + var cases []liveDiscoveryCase + + // OpenAI enumerates TWO real models and the policy permits one. That is + // the only case here where both bounds are observable at once: the + // upstream advertises dozens of ids, the provider record cuts them to two, + // and the guardrail cuts those to one. + if k := os.Getenv("OPENAI_TOKEN"); k != "" { + cases = append(cases, liveDiscoveryCase{ + name: "openai", catalogID: "openai_api", upstream: "https://api.openai.com", apiKey: k, + path: "/v1/models", + models: []string{"gpt-4o-mini", "gpt-4o"}, + allowlist: []string{"gpt-4o-mini"}, + outcome: outcomeFiltered, + permitted: []string{"gpt-4o-mini"}, + wantHidden: []string{"gpt-4o"}, + }) + } + + // Anthropic is the surface Claude Code actually calls. Its listing returns + // DATED build ids (claude-haiku-4-5-20251001) while the provider record + // registers the undated id, so this is the case that proves the filter's + // date-normalisation against ids the vendor chose rather than ids we wrote. + if k := os.Getenv("ANTHROPIC_TOKEN"); k != "" { + cases = append(cases, liveDiscoveryCase{ + name: "anthropic", catalogID: "anthropic_api", upstream: "https://api.anthropic.com", apiKey: k, + path: "/v1/models", + headers: []string{"anthropic-version: 2023-06-01"}, + models: []string{"claude-haiku-4-5"}, + outcome: outcomeFiltered, + permitted: []string{"claude-haiku-4-5"}, + }) + } + + // Bedrock lists inference profiles, not models: matchModelless routes + // /inference-profiles to a Bedrock route and refuses /v1/models for one. + // + // The listing is served by the CONTROL PLANE (bedrock.), not the + // runtime host a provider record must point at for InvokeModel — the + // runtime host answers . The router now sends + // the listing, and only the listing, to the control plane, so this case + // asserts a real filtered listing rather than the 404 it used to get. + // + // The mock upstream cannot show any of this: it answers + // /inference-profiles on the same listener as everything else, so a + // mock-based test passes whichever host the request went to. + if k := os.Getenv("AWS_BEARER_TOKEN_BEDROCK"); k != "" { + region := os.Getenv("AWS_REGION") + if region == "" { + region = "eu-central-1" + } + model := os.Getenv("AWS_BEDROCK_MODEL") + if model == "" { + model = "global.anthropic.claude-sonnet-4-6" + } + cases = append(cases, liveDiscoveryCase{ + name: "bedrock", catalogID: "bedrock_api", + upstream: "https://bedrock-runtime." + region + ".amazonaws.com", apiKey: k, + path: "/inference-profiles", + // Registered verbatim, as an operator would copy it from AWS: the + // region prefix is what makes the id invocable, and the listing + // returns ids in exactly this form. + models: []string{model}, + outcome: outcomeFiltered, + permitted: []string{model}, + }) + } + + // Vertex carries the model in the rawPredict path and serves no listing + // endpoint at all, so the proxy must refuse discovery rather than rewrite + // it onto an upstream that would 404. + if sa := os.Getenv("GOOGLE_VERTEX_SA_BASE64"); sa != "" { + if project := os.Getenv("GOOGLE_VERTEX_PROJECT"); project != "" { + region := os.Getenv("GOOGLE_VERTEX_REGION") + if region == "" { + region = "global" + } + host := "aiplatform.googleapis.com" + if region != "global" { + host = region + "-aiplatform.googleapis.com" + } + cases = append(cases, liveDiscoveryCase{ + name: "vertex", catalogID: "vertex_ai_api", upstream: "https://" + host, + apiKey: "keyfile::" + sa, + path: "/v1/models", + outcome: outcomeDenied, + }) + } + } + + return cases +} + +// provisionLiveDiscovery creates the group, provider, optional guardrail and +// policy for one case, and returns the setup key a client joins that group +// with. Scoping each provider to its own group is what keeps it the only +// candidate for its own client's model-less request. +func provisionLiveDiscovery(t *testing.T, ctx context.Context, tc *liveDiscoveryCase) string { + t.Helper() + + grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-live-" + tc.name}) + require.NoError(t, err, "create group for %s", tc.name) + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) }) + + ephemeral := false + sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: "e2e-disc-live-" + tc.name, + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{grp.Id}, + Ephemeral: &ephemeral, + }) + require.NoError(t, err, "mint setup key for %s", tc.name) + require.NotEmpty(t, sk.Key, "setup key plaintext for %s", tc.name) + + req := api.AgentNetworkProviderRequest{ + Name: "e2e-disc-live-" + tc.name, + ProviderId: tc.catalogID, + UpstreamUrl: tc.upstream, + ApiKey: &tc.apiKey, + Enabled: ptr(true), + } + if len(tc.models) > 0 { + models := make([]api.AgentNetworkProviderModel, 0, len(tc.models)) + for _, id := range tc.models { + models = append(models, api.AgentNetworkProviderModel{Id: id, InputPer1k: 0.001, OutputPer1k: 0.002}) + } + req.Models = &models + } + prov, err := srv.CreateProvider(ctx, req) + require.NoError(t, err, "create provider %s", tc.name) + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) + + polReq := api.AgentNetworkPolicyRequest{ + Name: "e2e-disc-live-" + tc.name, + Enabled: ptr(true), + SourceGroups: []string{grp.Id}, + DestinationProviderIds: []string{prov.Id}, + } + if len(tc.allowlist) > 0 { + var gr api.AgentNetworkGuardrailRequest + gr.Name = "e2e-disc-live-" + tc.name + gr.Checks.ModelAllowlist.Enabled = true + gr.Checks.ModelAllowlist.Models = tc.allowlist + g, gerr := srv.CreateGuardrail(ctx, gr) + require.NoError(t, gerr, "create guardrail for %s", tc.name) + t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) }) + polReq.GuardrailIds = &[]string{g.Id} + } + pol, err := srv.CreatePolicy(ctx, polReq) + require.NoError(t, err, "create policy for %s", tc.name) + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) }) + + return sk.Key +} + +// runLiveDiscoveryCase issues the discovery request and reports everything the +// vendor said before asserting on any of it. The log is the point on the first +// run: a live catalogue is the one input we do not control, so a failure has to +// arrive with the response that caused it rather than just a count. +func runLiveDiscoveryCase(t *testing.T, ctx context.Context, tc liveDiscoveryCase, cl *harness.Client, endpoint, proxyIP string) { + t.Helper() + + // A single request is enough for the two non-listing outcomes, and retrying + // them would burn the retry window waiting for a status that is never + // coming. + if tc.outcome != outcomeFiltered { + code, body, err := cl.Get(ctx, endpoint, proxyIP, tc.path, tc.headers) + require.NoError(t, err, "request must reach the proxy") + t.Logf("[discovery] %s GET %s -> %d; body: %s", tc.name, tc.path, code, truncate(body, 2000)) + assert.NotEqual(t, 200, code, + "%s serves no bounded listing, so a 200 here would mean the caller was handed a picker nothing narrows; body: %s", + tc.name, truncate(body, 2000)) + + // Which side refused is the whole distinction between these two + // outcomes, and a NetBird error is the thing that tells them apart: the + // middleware chain stamps its own name on anything it generates. + if tc.outcome == outcomeDenied { + assert.True(t, isProxyError(body), + "%s serves no listing endpoint at all, so the proxy must refuse the request itself rather than forward it to an upstream that would answer for us; body: %s", + tc.name, truncate(body, 2000)) + return + } + assert.False(t, isProxyError(body), + "%s discovery must be routed to the configured upstream and refused by the vendor, not blocked by the proxy; body: %s", + tc.name, truncate(body, 2000)) + return + } + + code, body := callUntil(t, func() (int, string, error) { + return cl.Get(ctx, endpoint, proxyIP, tc.path, tc.headers) + }, 200) + // Status only, not the body. A Bedrock listing embeds inference-profile + // ARNs carrying the 12-digit AWS account id, and these job logs are + // readable by anyone who can see the run. The ids line below is the finding + // anyway. The failure paths below are the same log: a listing that fails to + // arrive is an AWS refusal naming the resource it refused, and that name is + // an ARN carrying the same account id. + t.Logf("[discovery] %s GET %s -> %d", tc.name, tc.path, code) + require.Equal(t, 200, code, "%s discovery must be served; response was %s", tc.name, bodyShape(body)) + + ids, ok := listingIDs(body) + require.Truef(t, ok, + "%s answered discovery with something other than a {\"data\":[{\"id\":…}]} listing, which the filter forwards untouched — the caller would get an unbounded picker; response was %s", + tc.name, bodyShape(body)) + sort.Strings(ids) + t.Logf("[discovery] %s: %d ids after filtering: %s", tc.name, len(ids), strings.Join(ids, ", ")) + + require.NotEmpty(t, ids, "%s filtered the listing down to nothing; the caller would see an empty picker", tc.name) + + permitted := make(map[string]struct{}, len(tc.permitted)*2) + for _, id := range tc.permitted { + permitted[id] = struct{}{} + permitted[sharedllm.NormalizeAnthropicModel(id)] = struct{}{} + } + for _, id := range ids { + _, direct := permitted[id] + _, dated := permitted[sharedllm.NormalizeAnthropicModel(id)] + // Bedrock ids carry a region prefix and version suffix the record may + // not repeat; the proxy's filter tries the same forms. + _, bedrock := permitted[sharedllm.NormalizeBedrockModel(id)] + assert.Truef(t, direct || dated || bedrock, + "%s offered %q, which no policy on this route permits — every entry the picker shows must be a request the guardrail would allow", tc.name, id) + } + for _, hidden := range tc.wantHidden { + assert.NotContainsf(t, ids, hidden, + "%s offered %q, which the provider enumerates but the policy does not permit", tc.name, hidden) + } +} + +// isProxyError reports whether a response body was generated by the middleware +// chain rather than forwarded from a vendor. Every chain-generated error names +// the middleware that raised it, which no upstream's error body does — so this +// separates "the proxy refused" from "the proxy routed it and the vendor +// refused", the two failures that otherwise look alike from the client side. +func isProxyError(body string) bool { + return strings.Contains(body, `"middleware":`) +} + +// listingIDs pulls the model ids out of a listing response. ok is false when +// the body is neither envelope the proxy's filter recognises — the two must +// stay in step, or this test reports "not a listing" for a response the proxy +// filtered perfectly well. +func listingIDs(body string) ([]string, bool) { + var doc struct { + // OpenAI's shape, which Anthropic adopted. + Data []struct { + ID string `json:"id"` + } `json:"data"` + // Bedrock returns inference-profile summaries under a key of its own, + // with the id under a field of its own. + Summaries []struct { + ID string `json:"inferenceProfileId"` + } `json:"inferenceProfileSummaries"` + } + if err := json.Unmarshal([]byte(body), &doc); err != nil { + return nil, false + } + switch { + case doc.Data != nil: + ids := make([]string, 0, len(doc.Data)) + for _, entry := range doc.Data { + ids = append(ids, entry.ID) + } + return ids, true + case doc.Summaries != nil: + ids := make([]string, 0, len(doc.Summaries)) + for _, entry := range doc.Summaries { + ids = append(ids, entry.ID) + } + return ids, true + } + return nil, false +} + +func caseNames(cases []liveDiscoveryCase) []string { + names := make([]string, 0, len(cases)) + for _, c := range cases { + names = append(names, c.name) + } + return names +} + +// bodyShape describes a response without quoting any of it: its size and the +// top-level keys it arrived under. That is what a discovery failure is +// diagnosed from — which envelope the vendor answered with — and it is all +// that may go in a message rendered into a public job log, because the values +// underneath can carry an ARN and its account id. +func bodyShape(body string) string { + var doc map[string]json.RawMessage + if err := json.Unmarshal([]byte(body), &doc); err != nil { + return strconv.Itoa(len(body)) + " bytes, not a JSON object" + } + keys := make([]string, 0, len(doc)) + for key := range doc { + keys = append(keys, key) + } + sort.Strings(keys) + if len(keys) == 0 { + return strconv.Itoa(len(body)) + " bytes, an empty JSON object" + } + return strconv.Itoa(len(body)) + " bytes, keyed by: " + strings.Join(keys, ", ") +} + +// truncate bounds a logged response body. A live catalogue can run to tens of +// kilobytes, and the useful part is the front. +func truncate(s string, limit int) string { + if len(s) <= limit { + return s + } + return s[:limit] + "… (" + strconv.Itoa(len(s)-limit) + " more bytes)" +} diff --git a/e2e/agentnetwork/discovery_multipolicy_test.go b/e2e/agentnetwork/discovery_multipolicy_test.go new file mode 100644 index 000000000..447c1314c --- /dev/null +++ b/e2e/agentnetwork/discovery_multipolicy_test.go @@ -0,0 +1,170 @@ +//go:build e2e + +package agentnetwork + +import ( + "context" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/e2e/harness" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// TestDiscoveryBoundToCallersPolicies covers a model listing on a provider two +// teams reach under different allowlists. +// +// Bounding the listing by the provider's enumerated models alone is not enough +// once more than one policy is in play: the caller would be offered every model +// any team may use, and each one outside their own policy is a request the +// guardrail refuses a moment later — the empty-or-wrong picker this endpoint +// exists to avoid, just moved one level up. +// +// The client joins the main group only. Both models are enumerated by the same +// provider and both are advertised by the upstream, so a listing that leaked +// the other team's model would visibly contain it. +func TestDiscoveryBoundToCallersPolicies(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute) + defer cancel() + + vllm, err := harness.StartVLLM(ctx, srv) + require.NoError(t, err, "start mock upstream") + t.Cleanup(func() { _ = vllm.Terminate(context.Background()) }) + + grpMain, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-mp-main"}) + require.NoError(t, err, "create main group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpMain.Id) }) + + grpOther, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-disc-mp-other"}) + require.NoError(t, err, "create other group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpOther.Id) }) + + ephemeral := false + mkKey := func(name, groupID string) string { + sk, kerr := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: name, + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{groupID}, + Ephemeral: &ephemeral, + }) + require.NoError(t, kerr, "mint setup key %s", name) + require.NotEmpty(t, sk.Key, "setup key plaintext") + return sk.Key + } + // One client per group. The second is what makes the first assertion mean + // something: without a client that DOES see the other team's model, its + // absence from the main client's listing could equally be a policy that + // never propagated. + keyMain := mkKey("e2e-disc-mp-main-client", grpMain.Id) + keyOther := mkKey("e2e-disc-mp-other-client", grpOther.Id) + + // One provider enumerating both models the upstream advertises, so the + // listing is narrowed by policy rather than by what the provider serves. + staticKey := "static-e2e-token" + prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ + Name: "e2e-disc-mp", + ProviderId: "openai_api", + UpstreamUrl: vllm.URL, + ApiKey: &staticKey, + Enabled: ptr(true), + Models: &[]api.AgentNetworkProviderModel{ + {Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.001}, + {Id: harness.VLLMUnlistedModel, InputPer1k: 0.001, OutputPer1k: 0.001}, + }, + }) + require.NoError(t, err, "create provider") + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) + + mkGuardrail := func(name, model string) api.AgentNetworkGuardrail { + var gr api.AgentNetworkGuardrailRequest + gr.Name = name + gr.Checks.ModelAllowlist.Enabled = true + gr.Checks.ModelAllowlist.Models = []string{model} + g, gerr := srv.CreateGuardrail(ctx, gr) + require.NoError(t, gerr, "create guardrail %s", name) + t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) }) + return g + } + gMain := mkGuardrail("e2e-disc-mp-main", harness.VLLMModel) + gOther := mkGuardrail("e2e-disc-mp-other", harness.VLLMUnlistedModel) + + enabled := true + polMain, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-disc-mp-main", + Enabled: &enabled, + SourceGroups: []string{grpMain.Id}, + DestinationProviderIds: []string{prov.Id}, + GuardrailIds: &[]string{gMain.Id}, + }) + require.NoError(t, err, "create main policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMain.Id) }) + + // The other team's policy, on the same provider, permitting the model the + // client must never be offered. + polOther, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-disc-mp-other", + Enabled: &enabled, + SourceGroups: []string{grpOther.Id}, + DestinationProviderIds: []string{prov.Id}, + GuardrailIds: &[]string{gOther.Id}, + }) + require.NoError(t, err, "create other policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polOther.Id) }) + + endpoint, proxyIP, clMain, px := connectClient(t, ctx, "disc-mp", keyMain) + clOther := joinClient(t, ctx, px, endpoint, keyOther) + + listing := func(t *testing.T, cl *harness.Client, ip string) string { + t.Helper() + code, body := callUntil(t, func() (int, string, error) { + return cl.Get(ctx, endpoint, ip, "/v1/models?limit=1000", nil) + }, 200) + require.Equal(t, 200, code, "discovery must be served; body: %s", body) + return body + } + + otherIP, err := clOther.ResolveProxyIP(ctx, endpoint) + require.NoError(t, err, "resolve endpoint from the other client") + + // The other team's client first: seeing its own model proves polOther is + // live, so the main client's listing is narrowed by policy scoping rather + // than by the other policy having failed to apply at all. + otherBody := listing(t, clOther, otherIP) + assert.Contains(t, otherBody, harness.VLLMUnlistedModel, + "the other group's policy must be in force, or this test proves nothing") + assert.NotContains(t, otherBody, harness.VLLMModel, + "and it must not be offered the main group's model either — isolation runs both ways") + + mainBody := listing(t, clMain, proxyIP) + assert.Contains(t, mainBody, harness.VLLMModel, + "the model the caller's own policy permits must reach the picker") + assert.NotContains(t, mainBody, harness.VLLMUnlistedModel, + "a model only another group's policy permits must not be offered to this caller") +} + +// joinClient starts a second tunnel client against an already-running proxy, so +// a test can drive the same endpoint as two different group memberships without +// paying for a second proxy. +func joinClient(t *testing.T, ctx context.Context, px *harness.Proxy, endpoint, setupKey string) *harness.Client { + t.Helper() + + cl, err := harness.StartClient(ctx, srv, setupKey) + require.NoError(t, err, "start second client") + t.Cleanup(func() { _ = cl.Terminate(context.Background()) }) + + require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "second client must connect to management") + _, err = cl.ResolveProxyIP(ctx, endpoint) + require.NoError(t, err, "second client could not resolve the endpoint") + // Guarded rather than passed straight to require: px.Logs pulls the whole + // proxy container log, which is only worth fetching when the wait failed. + if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil { + require.NoError(t, err, "second client did not see the proxy peer\n=== proxy logs ===\n%s", + px.Logs(context.Background())) + } + return cl +} diff --git a/e2e/agentnetwork/gateway_protocol_test.go b/e2e/agentnetwork/gateway_protocol_test.go new file mode 100644 index 000000000..c21a4fc53 --- /dev/null +++ b/e2e/agentnetwork/gateway_protocol_test.go @@ -0,0 +1,455 @@ +//go:build e2e + +package agentnetwork + +import ( + "context" + "fmt" + "strings" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/e2e/harness" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// Models each catalog surface is registered with in the matrix below. They +// differ per provider so the router's choice is unambiguous: a request that +// lands on the wrong provider record fails the surface assertion instead of +// passing by coincidence. +const ( + matrixAnthropicModel = "claude-sonnet-5" + matrixBedrockModel = "anthropic.claude-sonnet-5" + // matrixBedrockPathModel is what a Bedrock SDK client puts in the URL: a + // cross-region inference profile with a release date and version suffix. + // The proxy must normalise it back to matrixBedrockModel to route and price. + matrixBedrockPathModel = "us.anthropic.claude-sonnet-5-20250101-v1:0" + // matrixVertexModel differs from the Anthropic record's model on purpose: + // a shared id would leave two routes claiming it and make which one serves + // /v1/messages depend on declaration order. + matrixVertexModel = "claude-haiku-4-5" + matrixVertexProject = "e2e-project" + matrixVertexRegion = "us-east5" +) + +// gatewayEnv is a connected client plus a set of provider records, all pointed +// at one mock upstream, so several wire shapes can be driven over a single +// tunnel. +type gatewayEnv struct { + endpoint string + proxyIP string + client *harness.Client + proxy *harness.Proxy + vllm *harness.VLLM + // providerIDs maps the catalog id to the created provider record id. + providerIDs map[string]string +} + +// provisionGatewayMatrix brings up one mock upstream and one provider record +// per catalog surface, all authorised for the same group by a single policy. +// Sharing one proxy and client keeps the wire-shape cases to one tunnel setup; +// each case still creates its own session id so its access-log row is findable. +func provisionGatewayMatrix(t *testing.T, ctx context.Context) gatewayEnv { + t.Helper() + + vllm, err := harness.StartVLLM(ctx, srv) + require.NoError(t, err, "start mock upstream") + t.Cleanup(func() { _ = vllm.Terminate(context.Background()) }) + + grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-gw-matrix"}) + require.NoError(t, err, "create group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) }) + + ephemeral := false + sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: "e2e-gw-matrix-client", + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{grp.Id}, + Ephemeral: &ephemeral, + }) + require.NoError(t, err, "mint setup key") + require.NotEmpty(t, sk.Key, "setup key plaintext") + + // The mock ignores auth, so a dummy credential satisfies each catalog + // entry's auth template. Vertex is the exception: its api_key is a GCP + // service-account keyfile the proxy mints an OAuth token from, and a dummy + // one cannot mint. That is deliberate — the Vertex case below asserts on + // routing, which happens before the token mint. + dummyKey := "sk-gw-e2e" + dummyKeyfile := "keyfile::" + "e2e-not-a-real-service-account-key" + + specs := []struct { + name string + catalogID string + apiKey string + models []api.AgentNetworkProviderModel + }{ + { + name: "openai", catalogID: "openai_api", apiKey: dummyKey, + models: []api.AgentNetworkProviderModel{{Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.002}}, + }, + { + name: "anthropic", catalogID: "anthropic_api", apiKey: dummyKey, + models: []api.AgentNetworkProviderModel{{Id: matrixAnthropicModel, InputPer1k: 0.003, OutputPer1k: 0.015}}, + }, + { + name: "bedrock", catalogID: "bedrock_api", apiKey: dummyKey, + models: []api.AgentNetworkProviderModel{{Id: matrixBedrockModel, InputPer1k: 0.003, OutputPer1k: 0.015}}, + }, + { + name: "vertex", catalogID: "vertex_ai_api", apiKey: dummyKeyfile, + models: []api.AgentNetworkProviderModel{{Id: matrixVertexModel, InputPer1k: 0.001, OutputPer1k: 0.005}}, + }, + } + + providerIDs := make(map[string]string, len(specs)) + ids := make([]string, 0, len(specs)) + for _, spec := range specs { + key := spec.apiKey + models := spec.models + prov, perr := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ + Name: "e2e-gw-" + spec.name, + ProviderId: spec.catalogID, + UpstreamUrl: vllm.URL, + ApiKey: &key, + Enabled: ptr(true), + Models: &models, + }) + require.NoError(t, perr, "create %s provider", spec.name) + id := prov.Id + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), id) }) + providerIDs[spec.catalogID] = id + ids = append(ids, id) + } + + // Uncapped token limit: never blocks the handful of tokens driven here, but + // switches on usage metering so consumption and cost land in the row. + enabled := true + pol, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-gw-matrix", + Enabled: &enabled, + SourceGroups: []string{grp.Id}, + DestinationProviderIds: ids, + Limits: &api.AgentNetworkPolicyLimits{ + TokenLimit: api.AgentNetworkPolicyTokenLimit{ + Enabled: true, + GroupCap: 10_000_000, + UserCap: 10_000_000, + WindowSeconds: 60, + }, + }, + }) + require.NoError(t, err, "create policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) }) + + endpoint, proxyIP, cl, px := connectClient(t, ctx, "gw-matrix", sk.Key) + return gatewayEnv{ + endpoint: endpoint, + proxyIP: proxyIP, + client: cl, + proxy: px, + vllm: vllm, + providerIDs: providerIDs, + } +} + +// connectClient starts a proxy and a tunnel client for the shared account and +// waits until the client can reach the proxy peer, returning the endpoint and +// the proxy's tunnel IP to pin requests to. +func connectClient(t *testing.T, ctx context.Context, name, setupKey string) (string, string, *harness.Client, *harness.Proxy) { + t.Helper() + + settings, err := srv.GetSettings(ctx) + require.NoError(t, err, "read settings") + require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned") + + proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-"+name+"-proxy") + require.NoError(t, err, "mint proxy token") + px, err := harness.StartProxy(ctx, srv, proxyToken) + require.NoError(t, err, "start proxy") + t.Cleanup(func() { _ = px.Terminate(context.Background()) }) + + cl, err := harness.StartClient(ctx, srv, setupKey) + require.NoError(t, err, "start client") + t.Cleanup(func() { _ = cl.Terminate(context.Background()) }) + + require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management") + // The probe resolves the endpoint and its first packet wakes the lazy proxy + // peer, so WaitProxyPeer then observes it connected. + proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint) + require.NoError(t, err, "resolve endpoint to proxy IP") + if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil { + t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background())) + } + return settings.Endpoint, proxyIP, cl, px +} + +// callUntil retries an HTTP call through the tunnel until it returns one of the +// wanted statuses or the deadline passes, absorbing the DNS and tunnel jitter +// the first call through a fresh tunnel can hit. The last status and body are +// returned either way so the caller can assert with real detail. +func callUntil(t *testing.T, call func() (int, string, error), want ...int) (int, string) { + t.Helper() + wanted := make(map[int]struct{}, len(want)) + for _, w := range want { + wanted[w] = struct{}{} + } + + var code int + var body string + deadline := time.Now().Add(90 * time.Second) + for time.Now().Before(deadline) { + c, b, err := call() + if err == nil { + code, body = c, b + if _, ok := wanted[code]; ok { + return code, body + } + } + time.Sleep(5 * time.Second) + } + return code, body +} + +// TestGatewayProtocolProviderMatrix drives one request per wire shape over a +// single tunnel, with a provider record per catalog surface behind it. It is +// the regression net for the routing and parser-selection changes: each case +// asserts the surface the request was metered under and the token counts that +// surface's own usage block carries, so a request parsed by the wrong provider's +// parser meters zero and fails rather than passing on a coincidence. +func TestGatewayProtocolProviderMatrix(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute) + defer cancel() + + env := provisionGatewayMatrix(t, ctx) + diag := func() string { + return fmt.Sprintf("\n=== upstream logs ===\n%s\n=== proxy logs ===\n%s", + env.vllm.Logs(context.Background()), env.proxy.Logs(context.Background())) + } + + t.Run("openai chat completions", func(t *testing.T) { + session := "e2e-gw-openai" + code, body := callUntil(t, func() (int, string, error) { + return env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireChat, harness.VLLMModel, "ping", session) + }, 200) + require.Equal(t, 200, code, "openai chat must succeed; body: %s%s", body, diag()) + require.Contains(t, body, "chat.completion", "body must be an OpenAI completion; got: %s", body) + + row := findAccessLogBySession(t, ctx, session) + require.NotNil(t, row.Provider) + assert.Equal(t, "openai", *row.Provider, "the OpenAI chat path must meter under the openai surface") + assert.Equal(t, int64(harness.VLLMChatInputTokens), row.InputTokens, "OpenAI usage block must be read") + assert.Equal(t, int64(harness.VLLMChatOutputTokens), row.OutputTokens) + }) + + t.Run("anthropic messages", func(t *testing.T) { + session := "e2e-gw-anthropic" + code, body := callUntil(t, func() (int, string, error) { + return env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireMessages, matrixAnthropicModel, "ping", session) + }, 200) + require.Equal(t, 200, code, "anthropic messages must succeed; body: %s%s", body, diag()) + + row := findAccessLogBySession(t, ctx, session) + require.NotNil(t, row.Provider) + assert.Equal(t, "anthropic", *row.Provider, "the /v1/messages path must meter under the anthropic surface") + // These counts only appear if the Anthropic parser read the response: + // its usage fields are named differently from the OpenAI block. + assert.Equal(t, int64(harness.VLLMMessagesInputTokens), row.InputTokens, + "Anthropic input_tokens must be read; zero here means the wrong parser ran") + assert.Equal(t, int64(harness.VLLMMessagesOutputTokens), row.OutputTokens) + assert.Positive(t, row.CachedInputTokens, "the Anthropic cache-read bucket must be recorded") + assert.Positive(t, row.CostUsd, "a metered request must carry a cost") + require.NotNil(t, row.ResolvedProviderId) + assert.Equal(t, env.providerIDs["anthropic_api"], *row.ResolvedProviderId, + "a vendor-tagged request must not cross to another provider's record") + }) + + t.Run("bedrock invoke normalises the path model", func(t *testing.T) { + session := "e2e-gw-bedrock" + code, body := callUntil(t, func() (int, string, error) { + return env.client.Bedrock(ctx, env.endpoint, env.proxyIP, matrixBedrockPathModel, "ping", session) + }, 200) + require.Equal(t, 200, code, "bedrock invoke must succeed; body: %s%s", body, diag()) + + row := findAccessLogBySession(t, ctx, session) + require.NotNil(t, row.Provider) + assert.Equal(t, "bedrock", *row.Provider, "a native Bedrock path must meter under the bedrock surface") + require.NotNil(t, row.Model) + assert.Equal(t, matrixBedrockModel, *row.Model, + "the inference-profile prefix, release date and version suffix must be normalised away") + assert.Equal(t, int64(harness.VLLMMessagesInputTokens), row.InputTokens) + }) + + t.Run("anthropic token counting", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return env.client.PostJSON(ctx, env.endpoint, env.proxyIP, "/v1/messages/count_tokens", + fmt.Sprintf(`{"model":%q,"messages":[{"role":"user","content":"ping"}]}`, matrixAnthropicModel), + []string{"anthropic-version: 2023-06-01"}) + }, 200) + assert.Equal(t, 200, code, "token counting must route rather than deny; body: %s%s", body, diag()) + }) + + t.Run("bedrock token counting", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return env.client.PostJSON(ctx, env.endpoint, env.proxyIP, + "/model/"+matrixBedrockPathModel+"/count-tokens", + `{"input":{"converse":{"messages":[{"role":"user","content":[{"text":"ping"}]}]}}}`, nil) + }, 200) + assert.Equal(t, 200, code, + "the Bedrock count-tokens action must route; denying it pushes counting onto the billable inference path; body: %s%s", + body, diag()) + }) + + t.Run("vertex token counting reaches its provider", func(t *testing.T) { + // The dummy service-account key cannot mint an OAuth token, so the + // request stops at the upstream credential. Both outcomes render as + // 403, so the deny code is what distinguishes them: upstream_auth_failed + // means the path resolved to the Vertex route and only the credential + // failed, while model_not_routable would mean the method segment was + // swallowed into the model id and no route ever claimed it. + path := fmt.Sprintf("/v1/projects/%s/locations/%s/publishers/anthropic/models/%s/count-tokens:rawPredict", + matrixVertexProject, matrixVertexRegion, matrixVertexModel) + _, body := callUntil(t, func() (int, string, error) { + return env.client.PostJSON(ctx, env.endpoint, env.proxyIP, path, + `{"anthropic_version":"vertex-2023-10-16","messages":[{"role":"user","content":"ping"}]}`, nil) + }, 403) + assert.NotContains(t, body, "model_not_routable", + "the count-tokens method segment must not be parsed as part of the model id; body: %s%s", body, diag()) + assert.Contains(t, body, "llm_policy.upstream_auth_failed", + "the request must reach the Vertex route and fail only at the credential; body: %s%s", body, diag()) + }) + + t.Run("connection warming probe", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return env.client.Get(ctx, env.endpoint, env.proxyIP, "/api/hello", nil) + }, 200) + assert.NotEqual(t, 403, code, + "the warm-up probe carries no model and must not be refused as unroutable; body: %s%s", body, diag()) + }) + + t.Run("unknown model denies in the caller's error shape", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireMessages, + "claude-not-a-real-model-9", "ping", "e2e-gw-unknown") + }, 403) + require.Equal(t, 403, code, "a model no provider claims must still be refused; body: %s%s", body, diag()) + + // The NetBird fields stay where they were for existing consumers. + assert.Contains(t, body, "llm_policy.model_not_routable", "the deny code must be preserved") + // And the vendor's own envelope rides alongside, so the client can show + // the reason instead of an unexplained API error. + assert.Contains(t, body, `"type":"error"`, "an Anthropic caller must get the Anthropic error envelope") + assert.Contains(t, body, "permission_error", "403 must map to the vendor's permission error type") + }) +} + +// TestModelDiscoveryWithModelAllowlist covers gateway model discovery on an +// account that restricts models, which is the configuration that broke: the +// listing carries no model, and the per-model allowlist fails closed on an +// undetermined one, so discovery denied for exactly the accounts using the +// feature. It also asserts the allowlist still refuses a model outside it, so +// the exemption cannot be read as a way around the gate. +func TestModelDiscoveryWithModelAllowlist(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute) + defer cancel() + + vllm, err := harness.StartVLLM(ctx, srv) + require.NoError(t, err, "start mock upstream") + t.Cleanup(func() { _ = vllm.Terminate(context.Background()) }) + + grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-gw-discovery"}) + require.NoError(t, err, "create group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) }) + + ephemeral := false + sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: "e2e-gw-discovery-client", + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{grp.Id}, + Ephemeral: &ephemeral, + }) + require.NoError(t, err, "mint setup key") + require.NotEmpty(t, sk.Key, "setup key plaintext") + + // One provider enumerating a single model, while the upstream's own listing + // advertises two. The proxy must serve the shorter list. + dummyKey := "sk-discovery-e2e" + prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ + Name: "e2e-gw-discovery", + ProviderId: "openai_api", + UpstreamUrl: vllm.URL, + ApiKey: &dummyKey, + Enabled: ptr(true), + Models: &[]api.AgentNetworkProviderModel{ + {Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.002}, + }, + }) + require.NoError(t, err, "create provider") + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) + + // The model allowlist is what makes this a regression test: without a + // guardrail enabled, discovery was never gated in the first place. + var gr api.AgentNetworkGuardrailRequest + gr.Name = "e2e-gw-discovery-allowlist" + gr.Checks.ModelAllowlist.Enabled = true + gr.Checks.ModelAllowlist.Models = []string{harness.VLLMModel} + guard, err := srv.CreateGuardrail(ctx, gr) + require.NoError(t, err, "create guardrail") + t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), guard.Id) }) + + enabled := true + pol, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-gw-discovery", + Enabled: &enabled, + SourceGroups: []string{grp.Id}, + DestinationProviderIds: []string{prov.Id}, + GuardrailIds: &[]string{guard.Id}, + }) + require.NoError(t, err, "create policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) }) + + endpoint, proxyIP, cl, px := connectClient(t, ctx, "gw-discovery", sk.Key) + diag := func() string { + return fmt.Sprintf("\n=== upstream logs ===\n%s\n=== proxy logs ===\n%s", + vllm.Logs(context.Background()), px.Logs(context.Background())) + } + + t.Run("listing is served and bounded by policy", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return cl.Get(ctx, endpoint, proxyIP, "/v1/models?limit=1000", nil) + }, 200) + require.Equal(t, 200, code, + "discovery must not be refused because the request carries no model; body: %s%s", body, diag()) + + assert.Contains(t, body, harness.VLLMModel, "the authorised model must reach the picker") + assert.NotContains(t, body, harness.VLLMUnlistedModel, + "a model the policy does not authorise must not be offered; body: %s", body) + }) + + t.Run("allowlist still refuses a model outside it", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return cl.Chat(ctx, endpoint, proxyIP, harness.WireChat, + harness.VLLMUnlistedModel, "ping", "e2e-gw-discovery-blocked") + }, 403) + require.Equal(t, 403, code, + "exempting model-less endpoints must not exempt inference; body: %s%s", body, diag()) + assert.True(t, + strings.Contains(body, "llm_policy.model_blocked") || strings.Contains(body, "llm_policy.model_not_routable"), + "the refusal must name a model policy code; body: %s", body) + }) + + t.Run("allowlisted model still routes", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return cl.Chat(ctx, endpoint, proxyIP, harness.WireChat, + harness.VLLMModel, "ping", "e2e-gw-discovery-allowed") + }, 200) + require.Equal(t, 200, code, "the allowlisted model must still be served; body: %s%s", body, diag()) + }) +} diff --git a/e2e/agentnetwork/gateway_review_test.go b/e2e/agentnetwork/gateway_review_test.go new file mode 100644 index 000000000..556bc4a53 --- /dev/null +++ b/e2e/agentnetwork/gateway_review_test.go @@ -0,0 +1,242 @@ +//go:build e2e + +package agentnetwork + +import ( + "context" + "fmt" + "strings" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/e2e/harness" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// The cases in this file cover behaviour that arrived from code review, after +// the gateway-protocol end-to-end tests were written. Each had unit coverage +// only; none needed a new harness capability, which is why they belong here +// rather than on a manual checklist. + +// TestNonInferenceEndpointsAreAuthorised covers the two review findings on the +// endpoints that carry no body: the per-model lookup must be authorised +// against the same allowlist that bounds the listing beside it, and only a read +// method may claim the non-inference exemption that skips the token pre-flight. +func TestNonInferenceEndpointsAreAuthorised(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute) + defer cancel() + + env := provisionDiscoveryProvider(t, ctx) + + t.Run("lookup of an authorised model succeeds", func(t *testing.T) { + code, body := callUntil(t, func() (int, string, error) { + return env.client.Get(ctx, env.endpoint, env.proxyIP, "/v1/models/"+harness.VLLMModel, nil) + }, 200) + assert.Equal(t, 200, code, "an allowlisted model must remain reachable; body: %s", body) + }) + + t.Run("lookup of an unauthorised model is refused", func(t *testing.T) { + code, body, err := env.client.Get(ctx, env.endpoint, env.proxyIP, "/v1/models/"+harness.VLLMUnlistedModel, nil) + require.NoError(t, err, "request must reach the proxy") + assert.Equal(t, 403, code, + "a model the policy does not authorise must not be confirmed by the detail lookup; body: %s", body) + }) + + // A write must not claim the exemption that lets the listing skip the token + // pre-flight. The body names no model on purpose: that is what a request + // probing for the exemption looks like, and it is the case the method gate + // exists to refuse. (A POST that does name a model is a different thing — + // it routes and meters as the inference request it is.) + for _, path := range []string{"/v1/models", "/v1/models/" + harness.VLLMModel, "/api/hello"} { + t.Run("write to "+path+" is refused", func(t *testing.T) { + code, body, err := env.client.PostJSON(ctx, env.endpoint, env.proxyIP, path, + `{"messages":[{"role":"user","content":"hi"}]}`, nil) + require.NoError(t, err, "request must reach the proxy") + assert.NotEqual(t, 200, code, + "a write to a non-inference path must not be served unmetered; body: %s", body) + }) + } + + // A request carrying the sub-agent attribution headers must still be served + // and metered normally. Asserting the ids themselves is not possible yet: + // the parser lifts them onto the request's metadata, but nothing persists + // them, so they have no queryable surface to check against. + t.Run("sub-agent headers do not disturb the request", func(t *testing.T) { + sessionID := fmt.Sprintf("e2e-session-agentid-%d", time.Now().UnixNano()) + code, body, err := env.client.PostJSON(ctx, env.endpoint, env.proxyIP, "/v1/chat/completions", + fmt.Sprintf(`{"model":%q,"messages":[{"role":"user","content":"Reply with exactly: pong"}]}`, harness.VLLMModel), + []string{ + "x-session-id: " + sessionID, + "x-claude-code-agent-id: agent-child-7", + "x-claude-code-parent-agent-id: agent-root-1", + }) + require.NoError(t, err, "request must reach the proxy") + require.Equal(t, 200, code, "the request must succeed; body: %s", body) + + row := findAccessLogBySession(t, ctx, sessionID) + assert.Positive(t, row.InputTokens, "the request must still be metered normally") + }) +} + +// TestDatedModelIdRouting covers both halves of the dated-id rule that review +// tightened: a dated id still reaches an undated registration, but a route +// pinned to one dated build must never serve a different one. +func TestDatedModelIdRouting(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute) + defer cancel() + + const ( + undated = "claude-sonnet-9" + datedA = "claude-sonnet-9-20250101" + datedB = "claude-sonnet-9-20250202" + ) + + t.Run("a dated id reaches its undated registration", func(t *testing.T) { + env := provisionModelProvider(t, ctx, "dated-undated", "anthropic_api", undated) + + sessionID := fmt.Sprintf("e2e-session-dated-%d", time.Now().UnixNano()) + code, body := callUntil(t, func() (int, string, error) { + return env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireMessages, datedA, "Reply with exactly: pong", sessionID) + }, 200) + require.Equal(t, 200, code, "a pinned release of a registered family must route; body: %s", body) + + row := findAccessLogBySession(t, ctx, sessionID) + assert.Positive(t, row.InputTokens, "the dated request must price at the registered rate, not zero") + }) + + t.Run("a route pinned to one dated build refuses another", func(t *testing.T) { + env := provisionModelProvider(t, ctx, "dated-pinned", "anthropic_api", datedA) + + code, body := callUntil(t, func() (int, string, error) { + return env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireMessages, datedA, "Reply with exactly: pong", "") + }, 200) + require.Equal(t, 200, code, "the exact dated id must still route; body: %s", body) + + code, body, err := env.client.Chat(ctx, env.endpoint, env.proxyIP, harness.WireMessages, datedB, "Reply with exactly: pong", "") + require.NoError(t, err, "request must reach the proxy") + assert.Equal(t, 403, code, + "a provider pinned to one dated build must not serve another; body: %s", body) + }) +} + +// TestBedrockInferenceProfilesReachTheUpstream covers the startup lookup a +// Bedrock client makes. The proxy forwards it to the configured upstream rather +// than denying it, so what comes back is the upstream's answer — never a +// NetBird policy rejection. +func TestBedrockInferenceProfilesReachTheUpstream(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute) + defer cancel() + + env := provisionModelProvider(t, ctx, "infprofiles", "bedrock_api", "anthropic.claude-sonnet-5") + + code, body := callUntil(t, func() (int, string, error) { + return env.client.Get(ctx, env.endpoint, env.proxyIP, "/inference-profiles", nil) + }, 200) + + assert.Equal(t, 200, code, "the lookup must reach the upstream; body: %s", body) + assert.NotContains(t, body, "llm_policy.", + "the proxy must not answer a control-plane lookup with a policy denial") + assert.Contains(t, body, "inferenceProfileSummaries", + "the upstream's own answer must come back untouched") +} + +// provisionDiscoveryProvider brings up one mock-backed provider enumerating a +// single model, with an allowlist guardrail in effect, plus a connected client. +func provisionDiscoveryProvider(t *testing.T, ctx context.Context) pricedEnv { + t.Helper() + env := provisionModelProvider(t, ctx, "noninference", "openai_api", harness.VLLMModel) + + var gr api.AgentNetworkGuardrailRequest + gr.Name = "e2e-noninference-allowlist-" + fmt.Sprint(time.Now().UnixNano()) + gr.Checks.ModelAllowlist.Enabled = true + gr.Checks.ModelAllowlist.Models = []string{harness.VLLMModel} + guard, err := srv.CreateGuardrail(ctx, gr) + require.NoError(t, err, "create guardrail") + t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), guard.Id) }) + + enabled := true + _, err = srv.UpdatePolicy(ctx, env.policyID, api.AgentNetworkPolicyRequest{ + Name: "e2e-noninference", + Enabled: &enabled, + SourceGroups: []string{env.groupID}, + DestinationProviderIds: []string{env.providerID}, + GuardrailIds: &[]string{guard.Id}, + }) + require.NoError(t, err, "attach guardrail to policy") + return env +} + +// provisionModelProvider brings up the mock, one provider under the given +// catalog id enumerating exactly one model, an authorising policy, and a +// connected proxy + client. +func provisionModelProvider(t *testing.T, ctx context.Context, name, catalogID, model string) pricedEnv { + t.Helper() + + vllm, err := harness.StartVLLM(ctx, srv) + require.NoError(t, err, "start mock upstream") + t.Cleanup(func() { _ = vllm.Terminate(context.Background()) }) + + suffix := strings.ToLower(name) + grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-gwr-" + suffix}) + require.NoError(t, err, "create group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) }) + + ephemeral := false + sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: "e2e-gwr-" + suffix + "-client", + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{grp.Id}, + Ephemeral: &ephemeral, + }) + require.NoError(t, err, "mint setup key") + require.NotEmpty(t, sk.Key, "setup key plaintext") + + dummyKey := "sk-gwr-e2e" + prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ + Name: "e2e-gwr-" + suffix, + ProviderId: catalogID, + UpstreamUrl: vllm.URL, + ApiKey: &dummyKey, + Enabled: ptr(true), + Models: &[]api.AgentNetworkProviderModel{ + {Id: model, InputPer1k: 0.001, OutputPer1k: 0.002}, + }, + }) + require.NoError(t, err, "create provider") + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) + + enabled := true + pol, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-gwr-" + suffix, + Enabled: &enabled, + SourceGroups: []string{grp.Id}, + DestinationProviderIds: []string{prov.Id}, + Limits: &api.AgentNetworkPolicyLimits{ + TokenLimit: api.AgentNetworkPolicyTokenLimit{ + Enabled: true, + GroupCap: 10_000_000, + UserCap: 10_000_000, + WindowSeconds: 60, + }, + }, + }) + require.NoError(t, err, "create policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) }) + + endpoint, proxyIP, cl, px := connectClient(t, ctx, "gwr-"+suffix, sk.Key) + return pricedEnv{ + providerID: prov.Id, + groupID: grp.Id, + policyID: pol.Id, + upstream: vllm.URL, + endpoint: endpoint, + proxyIP: proxyIP, + client: cl, + proxy: px, + } +} diff --git a/e2e/agentnetwork/guardrail_block_test.go b/e2e/agentnetwork/guardrail_block_test.go index c4b22ae25..302b5107e 100644 --- a/e2e/agentnetwork/guardrail_block_test.go +++ b/e2e/agentnetwork/guardrail_block_test.go @@ -113,15 +113,14 @@ func runPathRoutedGuardrailCase(t *testing.T, tc pathRoutedGuardrailCase) { // Catch-all provider (no models) so the router forwards any model; a static // bearer key means the router injects a static auth header instead of minting - // a GCP token. Bootstraps the cluster if it isn't already. + // a GCP token. staticKey := "static-e2e-token" prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: tc.name, - ProviderId: tc.catalogID, - UpstreamUrl: vllm.URL, - ApiKey: &staticKey, - Enabled: ptr(true), - BootstrapCluster: ptr(harness.AgentNetworkCluster), + Name: tc.name, + ProviderId: tc.catalogID, + UpstreamUrl: vllm.URL, + ApiKey: &staticKey, + Enabled: ptr(true), }) require.NoError(t, err, "create %s provider", tc.name) t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) diff --git a/e2e/agentnetwork/guardrail_groupswitch_test.go b/e2e/agentnetwork/guardrail_groupswitch_test.go index 5f2dce52e..7108bb587 100644 --- a/e2e/agentnetwork/guardrail_groupswitch_test.go +++ b/e2e/agentnetwork/guardrail_groupswitch_test.go @@ -73,7 +73,6 @@ func TestGuardrailGroupSwitchTakesEffectAfterTTL(t *testing.T) { {Id: modelA, InputPer1k: 0.001, OutputPer1k: 0.001}, {Id: modelB, InputPer1k: 0.001, OutputPer1k: 0.001}, }, - BootstrapCluster: ptr(harness.AgentNetworkCluster), }) require.NoError(t, err, "create provider") t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) diff --git a/e2e/agentnetwork/guardrail_multipolicy_test.go b/e2e/agentnetwork/guardrail_multipolicy_test.go index 1d664fb58..2bb56b3bc 100644 --- a/e2e/agentnetwork/guardrail_multipolicy_test.go +++ b/e2e/agentnetwork/guardrail_multipolicy_test.go @@ -61,15 +61,14 @@ func TestGuardrailMultiPolicyModelAllowlist(t *testing.T) { } // pRestricted declares the two guardrailed models so routing is deterministic - // (model -> provider). Created first, so it carries the bootstrap cluster. + // (model -> provider). pRestricted, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: "restricted", - ProviderId: "openai_api", - UpstreamUrl: vllm.URL, - ApiKey: &staticKey, - Enabled: ptr(true), - Models: models(modelSelected, modelOther), - BootstrapCluster: ptr(harness.AgentNetworkCluster), + Name: "restricted", + ProviderId: "openai_api", + UpstreamUrl: vllm.URL, + ApiKey: &staticKey, + Enabled: ptr(true), + Models: models(modelSelected, modelOther), }) require.NoError(t, err, "create restricted provider") t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), pRestricted.Id) }) diff --git a/e2e/agentnetwork/guardrail_pergroup_providers_test.go b/e2e/agentnetwork/guardrail_pergroup_providers_test.go index eddae65c3..0e98330c4 100644 --- a/e2e/agentnetwork/guardrail_pergroup_providers_test.go +++ b/e2e/agentnetwork/guardrail_pergroup_providers_test.go @@ -115,7 +115,7 @@ func TestGuardrailPerGroupAllowlist_AllProviders(t *testing.T) { staticKey := "static-e2e-token" enabled := true - for i, c := range cases { + for _, c := range cases { req := api.AgentNetworkProviderRequest{ Name: "e2e-pergroup-" + c.name, ProviderId: c.catalogID, @@ -124,9 +124,6 @@ func TestGuardrailPerGroupAllowlist_AllProviders(t *testing.T) { Enabled: ptr(true), Models: c.models, } - if i == 0 { - req.BootstrapCluster = ptr(harness.AgentNetworkCluster) - } prov, perr := srv.CreateProvider(ctx, req) require.NoError(t, perr, "create provider %s", c.name) c.providerID = prov.Id @@ -283,13 +280,12 @@ func TestGuardrailMultiGroupUser(t *testing.T) { // P1 — union scenario: two restricting policies, one per group. p1, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: "e2e-mg-union", - ProviderId: "openai_api", - UpstreamUrl: vllm.URL, - ApiKey: &staticKey, - Enabled: ptr(true), - Models: priced(unionA, unionB, unionC), - BootstrapCluster: ptr(harness.AgentNetworkCluster), + Name: "e2e-mg-union", + ProviderId: "openai_api", + UpstreamUrl: vllm.URL, + ApiKey: &staticKey, + Enabled: ptr(true), + Models: priced(unionA, unionB, unionC), }) require.NoError(t, err, "create union provider") t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), p1.Id) }) diff --git a/e2e/agentnetwork/guardrail_test.go b/e2e/agentnetwork/guardrail_test.go index 6a2487a88..ddc95d62d 100644 --- a/e2e/agentnetwork/guardrail_test.go +++ b/e2e/agentnetwork/guardrail_test.go @@ -115,14 +115,11 @@ func TestModelAllowlistEnforced(t *testing.T) { }) require.NoError(t, err, "mint setup key") - // Providers with their configured (allowed) models; the first bootstraps the cluster. + // Providers with their configured (allowed) models ids := make([]string, 0, len(providers)) allowed := make([]string, 0, len(providers)) - for i, pc := range providers { + for _, pc := range providers { req := providerRequest(pc) - if i == 0 { - req.BootstrapCluster = ptr(harness.AgentNetworkCluster) - } prov, perr := srv.CreateProvider(ctx, req) require.NoError(t, perr, "create provider %s", pc.name) id := prov.Id diff --git a/e2e/agentnetwork/main_test.go b/e2e/agentnetwork/main_test.go index 17c5e00be..687af1d4d 100644 --- a/e2e/agentnetwork/main_test.go +++ b/e2e/agentnetwork/main_test.go @@ -14,6 +14,7 @@ import ( "time" "github.com/netbirdio/netbird/e2e/harness" + "github.com/netbirdio/netbird/shared/management/http/api" ) // srv is the shared combined server for the package, ready (PAT-authenticated) @@ -42,5 +43,30 @@ func run(m *testing.M) int { return 1 } + // Bootstrap the account's agent-network endpoint once for the package: + // providers no longer have settings side effects, and every data-plane + // test expects the shared account pinned to the combined proxy cluster. + cluster := harness.AgentNetworkCluster + if _, err := srv.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ProxyAddress: &cluster}); err != nil { + fmt.Fprintf(os.Stderr, "e2e: bootstrap agent-network endpoint: %v\n", err) + return 1 + } + return m.Run() } + +// waitBeforeRetry pauses between attempts of a polling loop and reports +// whether the caller should keep going. A cancelled context ends the loop +// where a plain sleep would keep retrying against it: every call fails +// instantly once ctx is done, so the loop would spend its whole remaining +// window sleeping between failures nobody is waiting for any more. +func waitBeforeRetry(ctx context.Context, d time.Duration) bool { + timer := time.NewTimer(d) + defer timer.Stop() + select { + case <-ctx.Done(): + return false + case <-timer.C: + return true + } +} diff --git a/e2e/agentnetwork/management_test.go b/e2e/agentnetwork/management_test.go index 6962f9796..9e3176d68 100644 --- a/e2e/agentnetwork/management_test.go +++ b/e2e/agentnetwork/management_test.go @@ -21,11 +21,10 @@ func ptr[T any](v T) *T { return &v } func newProvider(t *testing.T, ctx context.Context, name string) api.AgentNetworkProvider { t.Helper() prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: name, - ProviderId: "openai_api", - UpstreamUrl: "https://api.openai.com", - ApiKey: ptr("sk-dummy-e2e-key"), - BootstrapCluster: ptr("eu.proxy.netbird.test"), + Name: name, + ProviderId: "openai_api", + UpstreamUrl: "https://api.openai.com", + ApiKey: ptr("sk-dummy-e2e-key"), }) require.NoError(t, err, "create provider %q", name) t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) @@ -57,17 +56,11 @@ func TestProviderLifecycle(t *testing.T) { }} } - for i, pc := range cases { - i, pc := i, pc + for _, pc := range cases { + pc := pc t.Run(pc.name, func(t *testing.T) { req := providerRequest(pc) req.Name = "lc-" + pc.name - // Bootstrap the cluster on the first create in case the matrix has - // not run (e.g. no provider keys → settings not yet bootstrapped). - if i == 0 { - req.BootstrapCluster = ptr(harness.AgentNetworkCluster) - } - prov, err := srv.CreateProvider(ctx, req) require.NoError(t, err, "create %s provider", pc.name) t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) @@ -137,45 +130,65 @@ func TestProviderValidation(t *testing.T) { requireClientError(t, err) } -// TestSettingsRoundTrip flips the collection toggles and confirms cluster / -// subdomain stay immutable, then restores the original state. +// TestSettingsRoundTrip flips the collection toggles and confirms the +// endpoint and proxy address stay immutable, then restores the original +// state. A second bootstrap attempt must be rejected as a conflict. func TestSettingsRoundTrip(t *testing.T) { ctx := context.Background() - // Settings are bootstrapped on first provider create. - newProvider(t, ctx, "Settings Bootstrap") - + // The package's TestMain bootstrapped the shared account's endpoint. before, err := srv.GetSettings(ctx) require.NoError(t, err, "get settings") - require.NotEmpty(t, before.Cluster, "settings must carry an assigned cluster") + require.NotEmpty(t, before.Endpoint, "settings must carry the bootstrapped endpoint") + require.NotEmpty(t, before.ProxyAddress, "settings must carry the bootstrapped proxy address") + + require.NotNil(t, before.AccessLogRetentionDays, "bootstrapped settings must carry a retention") + beforeRetention := *before.AccessLogRetentionDays flipped, err := srv.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ + Endpoint: before.Endpoint, + ProxyAddress: before.ProxyAddress, EnableLogCollection: !before.EnableLogCollection, EnablePromptCollection: !before.EnablePromptCollection, RedactPii: !before.RedactPii, + AccessLogRetentionDays: beforeRetention, }) require.NoError(t, err, "update settings") assert.Equal(t, !before.EnableLogCollection, flipped.EnableLogCollection, "log collection toggle must flip") assert.Equal(t, !before.EnablePromptCollection, flipped.EnablePromptCollection, "prompt collection toggle must flip") - assert.Equal(t, before.Cluster, flipped.Cluster, "cluster must be immutable across updates") - assert.Equal(t, before.Subdomain, flipped.Subdomain, "subdomain must be immutable across updates") + require.NotNil(t, flipped.AccessLogRetentionDays) + assert.Equal(t, beforeRetention, *flipped.AccessLogRetentionDays, + "retention sent unchanged must round-trip, not reset to the zero value") + assert.Equal(t, before.Endpoint, flipped.Endpoint, "endpoint must be immutable across updates") + assert.Equal(t, before.ProxyAddress, flipped.ProxyAddress, "proxy address must be immutable across updates") - // A cluster different from the pinned one must be rejected; echoing the - // pinned one back is valid. + // The account is already bootstrapped: a second bootstrap is a conflict, + // whatever shape it asks for. + _, err = srv.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ + Endpoint: ptr("attacker.cluster.invalid"), + }) + requireClientError(t, err) + + // The identity fields ride along on the PUT as a required echo: a request + // carrying a different endpoint is rejected without applying anything. _, err = srv.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ - Cluster: ptr("attacker.cluster.invalid"), + Endpoint: "other.cluster.invalid", + ProxyAddress: before.ProxyAddress, EnableLogCollection: before.EnableLogCollection, EnablePromptCollection: before.EnablePromptCollection, RedactPii: before.RedactPii, + AccessLogRetentionDays: beforeRetention, }) requireClientError(t, err) // Restore the original toggles. _, err = srv.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ - Cluster: ptr(before.Cluster), + Endpoint: before.Endpoint, + ProxyAddress: before.ProxyAddress, EnableLogCollection: before.EnableLogCollection, EnablePromptCollection: before.EnablePromptCollection, RedactPii: before.RedactPii, + AccessLogRetentionDays: beforeRetention, }) require.NoError(t, err, "restore settings") } diff --git a/e2e/agentnetwork/settings_bootstrap_test.go b/e2e/agentnetwork/settings_bootstrap_test.go index ea56f7064..806ce82f4 100644 --- a/e2e/agentnetwork/settings_bootstrap_test.go +++ b/e2e/agentnetwork/settings_bootstrap_test.go @@ -4,6 +4,7 @@ package agentnetwork import ( "context" + "strings" "testing" "github.com/stretchr/testify/assert" @@ -14,7 +15,8 @@ import ( ) // harnessStartFresh boots a dedicated combined server with its own fresh -// account and registers its teardown on t. +// account and registers its teardown on t. Unlike the shared srv, the fresh +// account has NOT had its agent-network endpoint bootstrapped. func harnessStartFresh(ctx context.Context, t *testing.T) (*harness.Combined, error) { t.Helper() fresh, err := harness.StartCombined(ctx) @@ -28,16 +30,16 @@ func harnessStartFresh(ctx context.Context, t *testing.T) (*harness.Combined, er return fresh, nil } -// TestSettingsBootstrapViaPut covers the settings-first bootstrap path on an +// TestSettingsBootstrapViaPost covers the explicit bootstrap contract on an // account that has never been bootstrapped: the GET reads as the defaults -// with an empty cluster/subdomain/endpoint, a PUT without a cluster has -// nothing to pin and fails, and a PUT carrying a cluster creates the row and -// pins it immutably. The shared srv cannot provide that starting state (any -// provider-creating test bootstraps it, and test order is deliberately not -// relied on), so this boots a dedicated combined server — the image is -// already built and cached by TestMain's StartCombined, so the extra cost is -// one container start. -func TestSettingsBootstrapViaPut(t *testing.T) { +// with an empty endpoint/proxy_address, a PUT has no row to update and fails, +// and a POST creates the row and assigns the immutable endpoint — labeled +// beneath a proxy address here, with the toggle overrides from the same +// request applied. The shared srv cannot provide that starting state +// (TestMain bootstraps it), so this boots a dedicated combined server — the +// image is already built and cached by TestMain's StartCombined, so the extra +// cost is one container start. +func TestSettingsBootstrapViaPost(t *testing.T) { ctx := context.Background() fresh, err := harnessStartFresh(ctx, t) @@ -47,32 +49,35 @@ func TestSettingsBootstrapViaPut(t *testing.T) { // as an error and not as a null body. before, err := fresh.GetSettings(ctx) require.NoError(t, err, "get settings on a fresh account must succeed") - assert.Empty(t, before.Cluster, "cluster must be empty before bootstrap") - assert.Empty(t, before.Subdomain, "subdomain must be empty before bootstrap") - assert.Empty(t, before.Endpoint, "endpoint must be empty before bootstrap, not a bare dot") + assert.Empty(t, before.Endpoint, "endpoint must be empty before bootstrap") + assert.Empty(t, before.ProxyAddress, "proxy address must be empty before bootstrap") + assert.False(t, before.Dedicated, "an unbootstrapped account has no serving shape") assert.True(t, before.EnableLogCollection, "defaults must show log collection on, matching bootstrap") assert.False(t, before.EnablePromptCollection, "defaults must show prompt collection off") - // A PUT without a cluster has nothing to pin the account to. + // A PUT has no row to update yet — bootstrap is the explicit POST. _, err = fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ - EnableLogCollection: true, + EnableLogCollection: true, + AccessLogRetentionDays: 30, }) requireClientError(t, err) - // A PUT carrying a cluster bootstraps the account and applies the - // mutable fields from the same request. Every toggle is set away from - // its bootstrap default so each assertion can actually fail. + // A POST with a proxy address bootstraps a labeled endpoint and applies + // the toggles from the same request. Every toggle is set away from its + // bootstrap default so each assertion can actually fail. const cluster = "e2e.bootstrap.netbird.selfhosted" - bootstrapped, err := fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ - Cluster: ptr(cluster), - EnableLogCollection: false, - EnablePromptCollection: true, - RedactPii: true, + bootstrapped, err := fresh.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ + ProxyAddress: ptr(cluster), + EnableLogCollection: ptr(false), + EnablePromptCollection: ptr(true), + RedactPii: ptr(true), }) - require.NoError(t, err, "bootstrap settings via PUT must succeed") - assert.Equal(t, cluster, bootstrapped.Cluster, "cluster must be pinned from the request") - require.NotEmpty(t, bootstrapped.Subdomain, "subdomain must be assigned at bootstrap") - assert.Equal(t, bootstrapped.Subdomain+"."+cluster, bootstrapped.Endpoint, "endpoint must combine subdomain and cluster") + require.NoError(t, err, "bootstrap settings via POST must succeed") + assert.Equal(t, cluster, bootstrapped.ProxyAddress, "proxy address must be pinned from the request") + require.NotEmpty(t, bootstrapped.Endpoint, "endpoint must be assigned at bootstrap") + assert.True(t, strings.HasSuffix(bootstrapped.Endpoint, "."+cluster), + "labeled endpoint must hang one label beneath the proxy address: %s", bootstrapped.Endpoint) + assert.False(t, bootstrapped.Dedicated, "a labeled pin is not dedicated") assert.False(t, bootstrapped.EnableLogCollection, "log collection from the bootstrap request must override the default") assert.True(t, bootstrapped.EnablePromptCollection, "prompt collection from the bootstrap request must apply") assert.True(t, bootstrapped.RedactPii, "redact toggle from the bootstrap request must apply") @@ -85,30 +90,90 @@ func TestSettingsBootstrapViaPut(t *testing.T) { assert.Equal(t, bootstrapped.EnablePromptCollection, after.EnablePromptCollection, "prompt collection must persist") assert.Equal(t, bootstrapped.RedactPii, after.RedactPii, "redact toggle must persist") - // Once bootstrapped, later updates may omit the cluster entirely. + // Once bootstrapped, PUT updates the toggles. The identity fields ride + // along as a required echo of the assigned values; a matching echo is + // accepted and never written. persisted, err := fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ + Endpoint: bootstrapped.Endpoint, + ProxyAddress: bootstrapped.ProxyAddress, EnableLogCollection: true, EnablePromptCollection: false, RedactPii: true, + AccessLogRetentionDays: 21, }) - require.NoError(t, err, "post-bootstrap update without cluster must succeed") - assert.Equal(t, cluster, persisted.Cluster, "omitted cluster must keep the pinned value") + require.NoError(t, err, "post-bootstrap update must succeed") + require.NotNil(t, persisted.AccessLogRetentionDays) + assert.Equal(t, 21, *persisted.AccessLogRetentionDays, "retention from the update must apply") + assert.Equal(t, bootstrapped.Endpoint, persisted.Endpoint, "endpoint must survive updates untouched") + assert.Equal(t, cluster, persisted.ProxyAddress, "proxy address must survive updates untouched") assert.True(t, persisted.EnableLogCollection, "post-bootstrap toggle must apply") assert.False(t, persisted.EnablePromptCollection, "post-bootstrap toggle must apply") - // The cluster is immutable: a different value is rejected rather than - // silently ignored, and the rejected update must not disturb anything. + // The endpoint is immutable: a PUT carrying a different endpoint is + // rejected, and a second bootstrap is rejected as a conflict. Neither + // rejected write may disturb anything. _, err = fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{ - Cluster: ptr("other.cluster.invalid"), - EnableLogCollection: false, + Endpoint: "other.cluster.invalid", + ProxyAddress: persisted.ProxyAddress, + EnableLogCollection: persisted.EnableLogCollection, + EnablePromptCollection: persisted.EnablePromptCollection, + RedactPii: persisted.RedactPii, + AccessLogRetentionDays: 21, + }) + requireClientError(t, err) + + _, err = fresh.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ + Endpoint: ptr("other.cluster.invalid"), }) requireClientError(t, err) final, err := fresh.GetSettings(ctx) - require.NoError(t, err, "get settings after the rejected cluster change must succeed") - assert.Equal(t, persisted.Cluster, final.Cluster, "rejected update must not change the cluster") - assert.Equal(t, persisted.Endpoint, final.Endpoint, "rejected update must not change the endpoint") - assert.Equal(t, persisted.EnableLogCollection, final.EnableLogCollection, "rejected update must not apply its toggles") - assert.Equal(t, persisted.EnablePromptCollection, final.EnablePromptCollection, "rejected update must not apply its toggles") - assert.Equal(t, persisted.RedactPii, final.RedactPii, "rejected update must not apply its toggles") + require.NoError(t, err, "get settings after the rejected bootstrap must succeed") + assert.Equal(t, persisted.Endpoint, final.Endpoint, "rejected bootstrap must not change the endpoint") + assert.Equal(t, persisted.ProxyAddress, final.ProxyAddress, "rejected bootstrap must not change the proxy address") + assert.Equal(t, persisted.EnableLogCollection, final.EnableLogCollection, "rejected bootstrap must not apply its toggles") + assert.Equal(t, persisted.EnablePromptCollection, final.EnablePromptCollection, "rejected bootstrap must not apply its toggles") + assert.Equal(t, persisted.RedactPii, final.RedactPii, "rejected bootstrap must not apply its toggles") +} + +// TestSettingsBootstrapSelfAddressed covers the dedicated shape end to end: +// a POST carrying an endpoint claims the hostname verbatim, the proxy address +// equals it, and the pin reads as dedicated — the address-first flow a +// self-hosted operator uses before deploying the proxy that will declare it. +// The tail covers the recovery path the guarded DELETE exists for: with no +// providers and no proxy at the address, the claim can be released and a +// fresh bootstrap succeeds — the fix for a typo'd immutable endpoint. +func TestSettingsBootstrapSelfAddressed(t *testing.T) { + ctx := context.Background() + + fresh, err := harnessStartFresh(ctx, t) + require.NoError(t, err, "start dedicated combined server") + + created, err := fresh.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ + Endpoint: ptr("gw.e2e.netbird.selfhosted"), + }) + require.NoError(t, err, "self-addressed bootstrap must succeed") + assert.Equal(t, "gw.e2e.netbird.selfhosted", created.Endpoint, "endpoint must be claimed verbatim") + assert.Equal(t, created.Endpoint, created.ProxyAddress, "self-addressed: proxy address is the endpoint") + assert.True(t, created.Dedicated, "a self-addressed pin is dedicated") + + // No providers exist and no proxy declares the address, so both delete + // guards are clear: the delete releases the claim and the account reads + // as unbootstrapped defaults again. + require.NoError(t, fresh.DeleteSettings(ctx), "guarded delete with both guards clear must succeed") + + after, err := fresh.GetSettings(ctx) + require.NoError(t, err, "get settings after delete must succeed") + assert.Empty(t, after.Endpoint, "a deleted account must read as unbootstrapped") + + // A second delete has nothing to remove. + requireClientError(t, fresh.DeleteSettings(ctx)) + + // Re-creating is a fresh bootstrap — the released hostname is free to be + // claimed again, or a different one chosen. + recreated, err := fresh.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{ + Endpoint: ptr("gw2.e2e.netbird.selfhosted"), + }) + require.NoError(t, err, "bootstrap after delete must succeed") + assert.Equal(t, "gw2.e2e.netbird.selfhosted", recreated.Endpoint, "the fresh bootstrap claims the new hostname") } diff --git a/e2e/agentnetwork/skiptls_test.go b/e2e/agentnetwork/skiptls_test.go index 1f57605e3..85af8c604 100644 --- a/e2e/agentnetwork/skiptls_test.go +++ b/e2e/agentnetwork/skiptls_test.go @@ -66,9 +66,7 @@ func TestProviderSkipTLSVerification(t *testing.T) { } } - // First create bootstraps the account cluster. insecureReq := newReq("skip-tls", insecureModel, true) - insecureReq.BootstrapCluster = ptr(harness.AgentNetworkCluster) insecureProv, err := srv.CreateProvider(ctx, insecureReq) require.NoError(t, err, "create skip-tls provider") t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), insecureProv.Id) }) diff --git a/e2e/agentnetwork/streaming_test.go b/e2e/agentnetwork/streaming_test.go new file mode 100644 index 000000000..a5fa8df3f --- /dev/null +++ b/e2e/agentnetwork/streaming_test.go @@ -0,0 +1,209 @@ +//go:build e2e + +package agentnetwork + +import ( + "context" + "fmt" + "testing" + "time" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/e2e/harness" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// streamedModel is priced high enough that a mis-metered request is obvious in +// the recorded cost, and named so it cannot collide with another test's route. +const streamedModel = "e2e-streamed-model" + +const ( + streamInRate = 0.010 + streamOutRate = 0.020 + // The cache-read bucket is priced separately from input, so a run that + // folded the two together fails the per-bucket assertions below. + streamCacheReadRate = 0.001 +) + +// TestStreamingResponseMetersInputTokens is the end-to-end guard for the +// metering bug this endpoint's gateway-protocol work fixed. +// +// On a streamed answer the input-token count exists only in the opening +// message_start event; every later frame reports output. A response read with +// the wrong vendor's parser — the shape a gateway record produces when it names +// one API surface and serves another — never looks at that event, so input +// metered as zero and the bulk of the bill silently vanished. Nothing in the +// suite sent stream: true before this test, so the whole branch went unrun. +// +// The provider points at the mock's streaming listener, which answers every +// request as SSE with token counts that differ from the buffered surface. That +// difference is the point: passing these assertions is only possible if the +// stream accumulator ran. +func TestStreamingResponseMetersInputTokens(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute) + defer cancel() + + env := provisionStreamingProvider(t, ctx, "anthropic_api") + + sessionID := fmt.Sprintf("e2e-session-stream-%d", time.Now().UnixNano()) + code, body := chatStreamUntil(t, ctx, env, harness.WireMessages, streamedModel, sessionID) + require.Equal(t, 200, code, "streamed chat must succeed; body: %s", body) + assert.Contains(t, body, "message_start", + "the client must receive the event stream itself, not a buffered rewrite of it") + + row := findAccessLogBySession(t, ctx, sessionID) + + assert.Equal(t, harness.VLLMStreamInputTokens, int(row.InputTokens), + "input tokens live in message_start; zero here is the bug this test exists for") + assert.Equal(t, harness.VLLMStreamOutputTokens, int(row.OutputTokens), + "output tokens ride message_delta and supersede the message_start seed") + assert.Equal(t, harness.VLLMStreamCacheReadTokens, int(row.CachedInputTokens), + "the Anthropic cache bucket rides message_start too, and only its own parser reads it") + + // The Anthropic surface bills cache reads additively, so the input bucket + // prices the full input count rather than a remainder. + wantInput := float64(harness.VLLMStreamInputTokens) / 1000 * streamInRate + wantOutput := float64(harness.VLLMStreamOutputTokens) / 1000 * streamOutRate + wantCacheRead := float64(harness.VLLMStreamCacheReadTokens) / 1000 * streamCacheReadRate + assert.InDelta(t, wantInput, row.InputCostUsd, 1e-6, "input cost must price the streamed input tokens") + assert.InDelta(t, wantOutput, row.OutputCostUsd, 1e-6, "output cost must price the streamed output tokens") + // The total, not merely a positive number: input and output alone are + // positive, so a cache bucket parsed and then never billed would pass any + // weaker assertion. The gap is 7e-6, well outside the delta. + assert.InDelta(t, wantInput+wantOutput+wantCacheRead, row.CostUsd, 1e-6, + "the recorded cost must be every bucket the surface bills, cache reads included") +} + +// TestStreamingOnGatewayTypedProvider drives the same streamed Anthropic call +// through a provider record whose catalog id names the OpenAI surface — the +// exact misconfiguration that hid the bug, since gateway records commonly pin +// one parser while the upstream serves another shape entirely. +// +// The router must choose the parser from the request path rather than the +// record's provider id, or the Anthropic usage block goes unread and input +// meters at zero all over again. +func TestStreamingOnGatewayTypedProvider(t *testing.T) { + ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute) + defer cancel() + + env := provisionStreamingProvider(t, ctx, "openai_api") + + sessionID := fmt.Sprintf("e2e-session-stream-gw-%d", time.Now().UnixNano()) + code, body := chatStreamUntil(t, ctx, env, harness.WireMessages, streamedModel, sessionID) + require.Equal(t, 200, code, "streamed chat through a gateway record must succeed; body: %s", body) + + row := findAccessLogBySession(t, ctx, sessionID) + + assert.Equal(t, harness.VLLMStreamInputTokens, int(row.InputTokens), + "a record typed openai_api must still read the Anthropic usage block it is actually serving") + assert.Equal(t, harness.VLLMStreamOutputTokens, int(row.OutputTokens), + "output tokens must survive the surface mismatch too") + assert.InDelta(t, float64(harness.VLLMStreamInputTokens)/1000*streamInRate, row.InputCostUsd, 1e-6, + "the request must be priced on the surface it spoke, not the one the record names") +} + +// provisionStreamingProvider brings up the mock, one provider pointed at its +// streaming listener under the given catalog id, a policy authorising it, and a +// connected proxy + client. +func provisionStreamingProvider(t *testing.T, ctx context.Context, catalogID string) pricedEnv { + t.Helper() + + vllm, err := harness.StartVLLM(ctx, srv) + require.NoError(t, err, "start mock upstream") + t.Cleanup(func() { _ = vllm.Terminate(context.Background()) }) + + name := "stream-" + catalogID + grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-" + name}) + require.NoError(t, err, "create group") + t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) }) + + ephemeral := false + sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{ + Name: "e2e-" + name + "-client", + Type: "reusable", + ExpiresIn: 86400, + UsageLimit: 0, + AutoGroups: []string{grp.Id}, + Ephemeral: &ephemeral, + }) + require.NoError(t, err, "mint setup key") + // Deleting the group does not delete the key it auto-joins, so the key + // needs a cleanup of its own. + t.Cleanup(func() { _ = srv.API().SetupKeys.Delete(context.Background(), sk.Id) }) + require.NotEmpty(t, sk.Key, "setup key plaintext") + + dummyKey := "sk-stream-e2e" + cacheRead := streamCacheReadRate + prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ + Name: name, + ProviderId: catalogID, + UpstreamUrl: vllm.StreamURL, + ApiKey: &dummyKey, + Enabled: ptr(true), + Models: &[]api.AgentNetworkProviderModel{{ + Id: streamedModel, + InputPer1k: streamInRate, + OutputPer1k: streamOutRate, + CacheReadPer1k: &cacheRead, + }}, + }) + require.NoError(t, err, "create provider") + t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) }) + + enabled := true + pol, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{ + Name: "e2e-" + name, + Enabled: &enabled, + SourceGroups: []string{grp.Id}, + DestinationProviderIds: []string{prov.Id}, + Limits: &api.AgentNetworkPolicyLimits{ + TokenLimit: api.AgentNetworkPolicyTokenLimit{ + Enabled: true, + GroupCap: 10_000_000, + UserCap: 10_000_000, + WindowSeconds: 60, + }, + }, + }) + require.NoError(t, err, "create policy") + t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) }) + + endpoint, proxyIP, cl, px := connectClient(t, ctx, name, sk.Key) + return pricedEnv{ + providerID: prov.Id, + groupID: grp.Id, + policyID: pol.Id, + upstream: vllm.StreamURL, + endpoint: endpoint, + proxyIP: proxyIP, + client: cl, + proxy: px, + } +} + +// chatStreamUntil drives one streamed chat, retrying to absorb the tunnel and +// DNS jitter a first call through a fresh peer can hit. +func chatStreamUntil(t *testing.T, ctx context.Context, env pricedEnv, kind, model, sessionID string) (int, string) { + t.Helper() + var code int + var body string + deadline := time.Now().Add(90 * time.Second) + for time.Now().Before(deadline) { + c, b, cerr := env.client.ChatStream(ctx, env.endpoint, env.proxyIP, kind, model, "Reply with exactly: pong", sessionID) + if cerr == nil { + code, body = c, b + if code == 200 { + break + } + } + if !waitBeforeRetry(ctx, 5*time.Second) { + break + } + } + if code != 200 { + t.Logf("=== proxy logs ===\n%s", env.proxy.Logs(context.Background())) + } + return code, body +} diff --git a/e2e/agentnetwork/vllm_test.go b/e2e/agentnetwork/vllm_test.go index cd598f1ed..6f5117b2f 100644 --- a/e2e/agentnetwork/vllm_test.go +++ b/e2e/agentnetwork/vllm_test.go @@ -57,12 +57,11 @@ func TestVLLMProvider(t *testing.T) { // is enumerated so the router dispatches this model string to this provider. dummyKey := "sk-vllm-e2e" prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{ - Name: "vllm", - ProviderId: "vllm", - UpstreamUrl: vllm.URL, - ApiKey: &dummyKey, - Enabled: ptr(true), - BootstrapCluster: ptr(harness.AgentNetworkCluster), + Name: "vllm", + ProviderId: "vllm", + UpstreamUrl: vllm.URL, + ApiKey: &dummyKey, + Enabled: ptr(true), Models: &[]api.AgentNetworkProviderModel{ {Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.002}, }, diff --git a/e2e/harness/Dockerfile.client b/e2e/harness/Dockerfile.client index 114577d60..74a3ec245 100644 --- a/e2e/harness/Dockerfile.client +++ b/e2e/harness/Dockerfile.client @@ -20,5 +20,9 @@ ENV NETBIRD_BIN="/usr/local/bin/netbird" \ NB_ENABLE_CAPTURE="false" \ NB_ENTRYPOINT_SERVICE_TIMEOUT="30" ENTRYPOINT [ "/usr/local/bin/netbird-entrypoint.sh" ] -COPY client/netbird-entrypoint.sh /usr/local/bin/netbird-entrypoint.sh +# --chmod because the build context is not always a git checkout. A suite in +# another module builds from this module's extracted copy in the module cache, +# where every file is 0444 — the cache drops the executable bit git records — and +# a bare COPY then produces an entrypoint the runtime cannot exec. +COPY --chmod=0755 client/netbird-entrypoint.sh /usr/local/bin/netbird-entrypoint.sh COPY --from=builder /out/netbird /usr/local/bin/netbird diff --git a/e2e/harness/agentnetwork.go b/e2e/harness/agentnetwork.go index 078e697af..e85475dff 100644 --- a/e2e/harness/agentnetwork.go +++ b/e2e/harness/agentnetwork.go @@ -126,17 +126,33 @@ func (c *Combined) DeleteGuardrail(ctx context.Context, id string) error { return anDelete(ctx, c, "/api/agent-network/guardrails/"+id) } -// GetSettings returns the account's agent-network settings row. It exists only -// after the first provider create bootstraps it. +// CreateSettings bootstraps the account's agent-network settings row, +// assigning the immutable endpoint. Exactly one of req.ProxyAddress (labeled +// endpoint beneath that cluster) and req.Endpoint (self-addressed dedicated +// endpoint) must be set; a second bootstrap returns a conflict. +func (c *Combined) CreateSettings(ctx context.Context, req api.AgentNetworkSettingsCreateRequest) (api.AgentNetworkSettings, error) { + return anRequest[api.AgentNetworkSettings](ctx, c, http.MethodPost, "/api/agent-network/settings", req) +} + +// GetSettings returns the account's agent-network settings row. Before the +// CreateSettings bootstrap it reads as the defaults with an empty endpoint. func (c *Combined) GetSettings(ctx context.Context) (api.AgentNetworkSettings, error) { return anRequest[api.AgentNetworkSettings](ctx, c, http.MethodGet, "/api/agent-network/settings", nil) } -// UpdateSettings applies the mutable collection toggles. +// UpdateSettings applies the mutable collection toggles. The request must +// echo the assigned endpoint and proxy address unchanged — the server rejects +// a PUT that tries to change them. func (c *Combined) UpdateSettings(ctx context.Context, req api.AgentNetworkSettingsRequest) (api.AgentNetworkSettings, error) { return anRequest[api.AgentNetworkSettings](ctx, c, http.MethodPut, "/api/agent-network/settings", req) } +// DeleteSettings removes the account's settings row, releasing the endpoint. +// Refused while providers exist or a proxy is actively serving the endpoint. +func (c *Combined) DeleteSettings(ctx context.Context) error { + return anDelete(ctx, c, "/api/agent-network/settings") +} + // ListConsumption returns the account's consumption rows (possibly empty). func (c *Combined) ListConsumption(ctx context.Context) ([]api.AgentNetworkConsumption, error) { return anRequest[[]api.AgentNetworkConsumption](ctx, c, http.MethodGet, "/api/agent-network/consumption", nil) diff --git a/e2e/harness/client.go b/e2e/harness/client.go index f53d0ea64..73931027d 100644 --- a/e2e/harness/client.go +++ b/e2e/harness/client.go @@ -7,6 +7,7 @@ import ( "errors" "fmt" "io" + "net/http" "os/exec" "strconv" "strings" @@ -32,12 +33,36 @@ type Client struct { container testcontainers.Container } +// clientOptions is what the ClientOption values assemble. +type clientOptions struct { + name string +} + +// ClientOption adjusts how StartClient runs the agent. +type ClientOption func(*clientOptions) + +// WithClientName names the agent, which sets both its network alias and its +// container hostname. The hostname matters beyond addressing: the agent reports +// it to management at registration, so it is the name the peer appears under in +// the API. +// +// Required to run more than one agent against the same server — the default name +// is shared, and two containers cannot hold the same alias on one network. +func WithClientName(name string) ClientOption { + return func(o *clientOptions) { o.name = name } +} + // StartClient builds the client image and runs it on the combined server's // network, joining via the given setup key. The image entrypoint brings the // daemon up automatically; callers wait for connectivity with WaitConnected / // WaitProxyPeer. -func StartClient(ctx context.Context, c *Combined, setupKey string) (*Client, error) { - root, err := repoRoot() +func StartClient(ctx context.Context, c *Combined, setupKey string, opts ...ClientOption) (*Client, error) { + o := clientOptions{name: clientAlias} + for _, opt := range opts { + opt(&o) + } + + root, err := repoRoot(ctx) if err != nil { return nil, err } @@ -47,9 +72,13 @@ func StartClient(ctx context.Context, c *Combined, setupKey string) (*Client, er } req := testcontainers.ContainerRequest{ - Image: clientImage, + Image: clientImage, + // The agent reports the container's hostname to management, so this is + // the name the peer is addressable by in the API as well as on the + // network. The entrypoint takes no hostname flag of its own. + Hostname: o.name, Networks: []string{c.network.Name}, - NetworkAliases: map[string][]string{c.network.Name: {clientAlias}}, + NetworkAliases: map[string][]string{c.network.Name: {o.name}}, Env: map[string]string{ "NB_MANAGEMENT_URL": combinedExposedURL, "NB_SETUP_KEY": setupKey, @@ -171,12 +200,18 @@ func (cl *Client) pollStatus(ctx context.Context, timeout time.Duration, want st const ( // curlExitCouldNotResolve is curl's exit code for a DNS resolution failure, distinct from connection-level failures. curlExitCouldNotResolve = 6 - // dnsProbeRetryWindow bounds DNS-failure retries: the synthesized zone lands a beat after management connects, so early NXDOMAIN is propagation; a zone still absent after this window is a real failure. - dnsProbeRetryWindow = 30 * time.Second - dnsProbeRetryInterval = 2 * time.Second + // curlExitCouldNotConnect is curl's exit code for a connection that never + // established. The probe exists to WAKE the lazy proxy peer, so the first + // attempt legitimately arrives before WireGuard has brought the tunnel up + // and fails here — which is propagation, exactly like an early NXDOMAIN, + // and belongs inside the retry window rather than failing the test outright. + curlExitCouldNotConnect = 7 + // endpointProbeRetryWindow bounds retries of the transient failures above: the synthesized zone and the tunnel both land a beat after management connects. Still failing after this window is a real failure. + endpointProbeRetryWindow = 30 * time.Second + endpointProbeRetryInterval = 2 * time.Second ) -// ResolveProxyIP GETs https:/// from the client's netns: any HTTP status proves DNS + tunnel and wakes the lazy proxy peer; only DNS failures retry, within dnsProbeRetryWindow. Returns the connected IP for --resolve pinning. +// ResolveProxyIP GETs https:/// from the client's netns: any HTTP status proves DNS + tunnel and wakes the lazy proxy peer; DNS and connect failures retry, within endpointProbeRetryWindow. Returns the connected IP for --resolve pinning. func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string, error) { args := []string{ "run", "--rm", @@ -187,7 +222,7 @@ func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string, "-w", "%{remote_ip}", "https://" + endpoint + "/", } - deadline := time.Now().Add(dnsProbeRetryWindow) + deadline := time.Now().Add(endpointProbeRetryWindow) for { cmd := exec.CommandContext(ctx, "docker", args...) var stdout, stderr strings.Builder @@ -203,21 +238,29 @@ func (cl *Client) ResolveProxyIP(ctx context.Context, endpoint string) (string, } var exitErr *exec.ExitError - if !errors.As(err, &exitErr) || exitErr.ExitCode() != curlExitCouldNotResolve { + if !errors.As(err, &exitErr) || !isTransientProbeExit(exitErr.ExitCode()) { return "", fmt.Errorf("no HTTP response from %s: %w (%s)", endpoint, err, strings.TrimSpace(stderr.String())) } - dnsErr := fmt.Errorf("DNS resolution failed for %s: %s", endpoint, strings.TrimSpace(stderr.String())) - if time.Until(deadline) < dnsProbeRetryInterval { - return "", dnsErr + probeErr := fmt.Errorf("endpoint %s not reachable yet: %s", endpoint, strings.TrimSpace(stderr.String())) + if time.Until(deadline) < endpointProbeRetryInterval { + return "", probeErr } select { case <-ctx.Done(): - return "", fmt.Errorf("%w (%w)", dnsErr, ctx.Err()) - case <-time.After(dnsProbeRetryInterval): + return "", fmt.Errorf("%w (%w)", probeErr, ctx.Err()) + case <-time.After(endpointProbeRetryInterval): } } } +// isTransientProbeExit reports whether a curl exit code describes a state the +// endpoint is expected to pass THROUGH on its way up, rather than a settled +// failure. Anything else — TLS refusal, a protocol error, a bad argument — +// would still be failing after the retry window, so it fails immediately. +func isTransientProbeExit(code int) bool { + return code == curlExitCouldNotResolve || code == curlExitCouldNotConnect +} + // Wire shapes for Chat. const ( // WireChat is the OpenAI-compatible /v1/chat/completions shape. @@ -264,6 +307,27 @@ func (cl *Client) ChatPrefixed(ctx context.Context, endpoint, proxyIP, pathPrefi return cl.post(ctx, endpoint, proxyIP, pathPrefix+path, body, withSessionID(headers, sessionID)) } +// ChatStream is Chat with "stream": true in the request body, so the proxy's +// request parser marks the call as streaming and its response parser takes the +// SSE accumulator rather than the buffered-body path. Pair it with a provider +// pointed at VLLM.StreamURL, which answers every request as an event stream. +func (cl *Client) ChatStream(ctx context.Context, endpoint, proxyIP, kind, model, prompt, sessionID string) (int, string, error) { + var path, body string + var headers []string + switch kind { + case WireMessages: + path = "/v1/messages" + headers = []string{"anthropic-version: 2023-06-01"} + body = fmt.Sprintf(`{"model":%q,"max_tokens":2048,"stream":true,"messages":[{"role":"user","content":%q}]}`, model, prompt) + default: + path = "/v1/chat/completions" + // include_usage is what makes a real OpenAI stream emit its final usage + // frame; without it the last chunk carries no tokens at all. + body = fmt.Sprintf(`{"model":%q,"stream":true,"stream_options":{"include_usage":true},"messages":[{"role":"user","content":%q}]}`, model, prompt) + } + return cl.post(ctx, endpoint, proxyIP, path, body, withSessionID(headers, sessionID)) +} + // Vertex issues an Anthropic-on-Vertex rawPredict POST over the tunnel. Unlike // Chat, the model is carried in the request path (project/region/model), so the // proxy routes by path and mints the service-account OAuth token; the body uses @@ -294,10 +358,29 @@ func withSessionID(headers []string, sessionID string) []string { return append(headers, "x-session-id: "+sessionID) } -// post runs curl in a throwaway container sharing the client's network -// namespace so the request traverses the WireGuard tunnel, pinning the endpoint -// to the proxy IP. It returns the HTTP status and response body. +// Get issues a GET to the agent-network endpoint over the client's tunnel. +// Model discovery and the connection-warming probe are read-only endpoints +// that carry no body, so they can't go through the chat helpers. +func (cl *Client) Get(ctx context.Context, endpoint, proxyIP, path string, extraHeaders []string) (int, string, error) { + return cl.do(ctx, http.MethodGet, endpoint, proxyIP, path, "", extraHeaders) +} + +// PostJSON issues an arbitrary JSON POST over the client's tunnel, for wire +// shapes the typed helpers don't cover (token counting, say). +func (cl *Client) PostJSON(ctx context.Context, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) { + return cl.do(ctx, http.MethodPost, endpoint, proxyIP, path, body, extraHeaders) +} + +// post issues a JSON POST. Retained as the shorthand the chat helpers use. func (cl *Client) post(ctx context.Context, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) { + return cl.do(ctx, http.MethodPost, endpoint, proxyIP, path, body, extraHeaders) +} + +// do runs curl in a throwaway container sharing the client's network +// namespace so the request traverses the WireGuard tunnel, pinning the endpoint +// to the proxy IP. It returns the HTTP status and response body. An empty body +// sends no payload, which is what a GET needs. +func (cl *Client) do(ctx context.Context, method, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) { url := "https://" + endpoint + path args := []string{ "run", "--rm", @@ -306,13 +389,15 @@ func (cl *Client) post(ctx context.Context, endpoint, proxyIP, path, body string "-sk", "--connect-timeout", "5", "--max-time", "90", "--resolve", endpoint + ":443:" + proxyIP, "-o", "/dev/stderr", "-w", "%{http_code}", - "-X", "POST", url, + "-X", method, url, "-H", "Content-Type: application/json", } for _, h := range extraHeaders { args = append(args, "-H", h) } - args = append(args, "--data", body) + if body != "" { + args = append(args, "--data", body) + } cmd := exec.CommandContext(ctx, "docker", args...) // -w writes the status code to stdout; -o /dev/stderr writes the body to // stderr so we can capture both separately. diff --git a/e2e/harness/combined.go b/e2e/harness/combined.go index b2f0d89d2..e03f9f256 100644 --- a/e2e/harness/combined.go +++ b/e2e/harness/combined.go @@ -61,11 +61,68 @@ type Combined struct { workDir string } +// combinedOptions is what the CombinedOption values assemble. +type combinedOptions struct { + geolocation bool + env map[string]string +} + +// CombinedOption adjusts how StartCombined boots the server. The defaults suit a +// suite that only drives the API; the options exist for the ones that need more +// of the product than that. +type CombinedOption func(*combinedOptions) + +// WithGeolocation leaves the GeoLite database download enabled. It is off by +// default because the download adds startup latency that most suites get nothing +// for. A suite asserting on location-based posture checks needs it: management +// evaluates those rules against the database, and without it the rule fails +// instead of passing without having been checked. +func WithGeolocation() CombinedOption { + return func(o *combinedOptions) { o.geolocation = true } +} + +// WithServerEnv adds environment variables to the combined container, overriding +// the defaults on a key collision. For settings this harness does not model +// directly, so a suite needing one does not have to fork the harness to get it. +func WithServerEnv(env map[string]string) CombinedOption { + return func(o *combinedOptions) { + if o.env == nil { + o.env = map[string]string{} + } + for k, v := range env { + o.env[k] = v + } + } +} + +// combinedEnv is the combined container's environment: setup-PAT enabled so the +// caller can mint an admin token through /api/setup, geolocation off unless the +// suite asked for it, and whatever the suite added on top. +func combinedEnv(o combinedOptions) map[string]string { + env := map[string]string{ + "NB_SETUP_PAT_ENABLED": "true", + } + if !o.geolocation { + // Skip the GeoLite DB download — it blocks startup and agent-network + // ingest doesn't use geolocation. + env["NB_DISABLE_GEOLOCATION"] = "true" + } + for k, v := range o.env { + env[k] = v + } + return env +} + // StartCombined builds the combined server from its multistage Dockerfile and // boots it with setup-PAT enabled on a fresh shared network, returning once the // API is serving. The caller still owns minting the admin PAT via Bootstrap. -func StartCombined(ctx context.Context) (*Combined, error) { - root, err := repoRoot() +func StartCombined(ctx context.Context, opts ...CombinedOption) (*Combined, error) { + var o combinedOptions + for _, opt := range opts { + opt(&o) + } + + root, err := repoRoot(ctx) if err != nil { return nil, err } @@ -88,7 +145,7 @@ func StartCombined(ctx context.Context) (*Combined, error) { return nil, fmt.Errorf("create work dir: %w", err) } - cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, containerIssuer) + cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, !o.geolocation, containerIssuer) if err := os.WriteFile(filepath.Join(workDir, "config.yaml"), []byte(cfg), 0o644); err != nil { //nolint:gosec // non-secret config, bind-mounted and read by the container _ = net.Remove(ctx) return nil, fmt.Errorf("write combined config: %w", err) @@ -112,13 +169,8 @@ func StartCombined(ctx context.Context) (*Combined, error) { ExposedPorts: []string{combinedHTTPPort}, Networks: []string{net.Name}, NetworkAliases: map[string][]string{net.Name: {combinedAlias}}, - Env: map[string]string{ - "NB_SETUP_PAT_ENABLED": "true", - // Skip the GeoLite DB download — it blocks startup and agent-network - // ingest doesn't use geolocation. - "NB_DISABLE_GEOLOCATION": "true", - }, - Cmd: []string{"--config", "/nb/config.yaml"}, + Env: combinedEnv(o), + Cmd: []string{"--config", "/nb/config.yaml"}, HostConfigModifier: func(hc *container.HostConfig) { hc.Binds = append(hc.Binds, workDir+":/nb") }, diff --git a/e2e/harness/config.go b/e2e/harness/config.go index 71b3656c5..f0952b18c 100644 --- a/e2e/harness/config.go +++ b/e2e/harness/config.go @@ -15,6 +15,11 @@ package harness // server is required to load it — a broken path or malformed file fails startup // rather than silently falling back to the compiled-in rates, and TestMain then // fails with the container logs. +// +// disableGeoliteUpdate is a parameter rather than a fixed true because a suite +// that exercises geolocation needs the database: management can only evaluate a +// location rule with GeoLite loaded, and a rule it cannot evaluate fails rather +// than passing vacuously. See WithGeolocation. const combinedConfigYAML = `server: listenAddress: ":8080" exposedAddress: "%s" @@ -25,7 +30,7 @@ const combinedConfigYAML = `server: authSecret: "e2e-relay-secret" dataDir: "/nb/data" disableAnonymousMetrics: true - disableGeoliteUpdate: true + disableGeoliteUpdate: %t auth: issuer: "%s" store: diff --git a/e2e/harness/options_test.go b/e2e/harness/options_test.go new file mode 100644 index 000000000..8a5557a83 --- /dev/null +++ b/e2e/harness/options_test.go @@ -0,0 +1,161 @@ +//go:build e2e + +package harness + +import ( + "context" + "fmt" + "os" + "os/exec" + "path/filepath" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// The options exist so a suite can ask for a deployment this harness would not +// otherwise give it. What they configure is a container environment and a config +// file, both assembled before anything is started, so they are checkable without +// Docker — which is the point: a wiring mistake here would otherwise only show up +// as a puzzling failure minutes into a container run. + +func TestCombinedEnvGeolocation(t *testing.T) { + var off combinedOptions + assert.Equal(t, "true", combinedEnv(off)["NB_DISABLE_GEOLOCATION"], + "geolocation should be off by default") + + var on combinedOptions + WithGeolocation()(&on) + assert.NotContains(t, combinedEnv(on), "NB_DISABLE_GEOLOCATION", + "WithGeolocation must leave NB_DISABLE_GEOLOCATION unset, so the server downloads the database") + assert.Equal(t, "true", combinedEnv(on)["NB_SETUP_PAT_ENABLED"], + "the setup PAT must stay enabled whatever else is configured; Bootstrap depends on it") +} + +// The config file carries the same decision as the environment variable, and the +// server needs both to agree: disableGeoliteUpdate suppresses the download even +// when geolocation itself is enabled. +func TestCombinedConfigGeolocation(t *testing.T) { + for _, tc := range []struct { + name string + opts []CombinedOption + want string + }{ + {name: "default", want: "disableGeoliteUpdate: true"}, + {name: "with geolocation", opts: []CombinedOption{WithGeolocation()}, want: "disableGeoliteUpdate: false"}, + } { + t.Run(tc.name, func(t *testing.T) { + var o combinedOptions + for _, opt := range tc.opts { + opt(&o) + } + cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, !o.geolocation, containerIssuer) + assert.Contains(t, cfg, tc.want, "geolocation not rendered as expected") + // The issuer is the last verb; a mis-ordered argument list would put + // the boolean here instead and the server would fail to start. + assert.Contains(t, cfg, `issuer: "`+containerIssuer+`"`, "issuer not rendered") + }) + } +} + +func TestWithServerEnvOverrides(t *testing.T) { + var o combinedOptions + WithServerEnv(map[string]string{"NB_LOG_LEVEL": "debug"})(&o) + WithServerEnv(map[string]string{"NB_SETUP_PAT_ENABLED": "false"})(&o) + + env := combinedEnv(o) + assert.Equal(t, "debug", env["NB_LOG_LEVEL"], "added variable missing") + assert.Equal(t, "false", env["NB_SETUP_PAT_ENABLED"], "a suite must be able to override a default") +} + +// Two agents on one network cannot share an alias, so the name has to reach both +// the alias and the hostname. The hostname is the one management records, so it is +// also what the peer is addressable by through the API. +func TestWithClientName(t *testing.T) { + o := clientOptions{name: clientAlias} + require.Equal(t, "client", o.name, "unexpected default client name") + + WithClientName("peer2")(&o) + assert.Equal(t, "peer2", o.name, "WithClientName did not take") +} + +// repoRoot has to recognise this module rather than merely finding a go.mod, or a +// suite in another module gets its own root and a build context without the +// component Dockerfiles in it. +func TestIsModule(t *testing.T) { + dir := t.TempDir() + + other := filepath.Join(dir, "go.mod") + require.NoError(t, os.WriteFile(other, []byte("module example.com/other\n\ngo 1.25\n"), 0o600)) + assert.False(t, isModule(other, modulePath), "another module's go.mod must not be taken for this repo") + + ours := filepath.Join(dir, "ours.mod") + require.NoError(t, os.WriteFile(ours, []byte("// a comment\n\nmodule "+modulePath+"\n\ngo 1.25\n"), 0o600)) + assert.True(t, isModule(ours, modulePath), "this repo's go.mod was not recognised") + + assert.False(t, isModule(filepath.Join(dir, "absent.mod"), modulePath), + "a missing go.mod must not report a match") +} + +// Running from inside the repo, repoRoot finds it by walking up — the module +// lookup is only the fallback, and this asserts the walk still wins so an in-repo +// run never depends on the module cache. +func TestRepoRootFindsThisRepo(t *testing.T) { + root, err := repoRoot(context.Background()) + require.NoError(t, err) + assert.True(t, isModule(filepath.Join(root, "go.mod"), modulePath), + "repoRoot returned %s, which is not this module", root) + + for _, f := range []string{combinedDockerfile, clientDockerfile} { + _, err := os.Stat(filepath.Join(root, f)) + assert.NoError(t, err, "%s is not present under the reported root %s", f, root) + } +} + +// A caller that vendors its dependencies puts the go command in automatic vendor +// mode, where `go list -m -f {{.Dir}}` succeeds and reports an EMPTY directory: +// vendor/ holds packages, not module source. Without -mod=readonly the lookup +// would come back empty and the harness would report a missing module for a +// dependency that is present. +func TestModuleDirResolvesUnderVendorMode(t *testing.T) { + if _, err := exec.LookPath("go"); err != nil { + t.Skip("no go tool on PATH") + } + ctx := context.Background() + + base := t.TempDir() + dep := filepath.Join(base, "dep") + main := filepath.Join(base, "main") + require.NoError(t, os.MkdirAll(dep, 0o750)) + require.NoError(t, os.MkdirAll(main, 0o750)) + + // A local replacement rather than a real dependency, so this needs no network. + require.NoError(t, os.WriteFile(filepath.Join(dep, "go.mod"), + []byte("module example.com/dep\n\ngo 1.25\n"), 0o600)) + require.NoError(t, os.WriteFile(filepath.Join(dep, "dep.go"), + []byte("package dep\n"), 0o600)) + require.NoError(t, os.WriteFile(filepath.Join(main, "go.mod"), + []byte("module example.com/main\n\ngo 1.25\n\nrequire example.com/dep v0.0.0\n\nreplace example.com/dep v0.0.0 => ../dep\n"), 0o600)) + require.NoError(t, os.WriteFile(filepath.Join(main, "main.go"), + []byte("package main\n\nimport _ \"example.com/dep\"\n\nfunc main() {}\n"), 0o600)) + + t.Chdir(main) + vendor := exec.CommandContext(ctx, "go", "mod", "vendor") + out, err := vendor.CombinedOutput() + require.NoError(t, err, "go mod vendor: %s", out) + + dir, err := moduleDir(ctx, "example.com/dep") + require.NoError(t, err, "the module must still resolve with a vendor directory present") + assert.Equal(t, dep, dir, "resolved the wrong directory") +} + +// A cancelled context has to stop the lookup rather than leaving the caller +// waiting on a subprocess it has already given up on. +func TestModuleDirHonoursContext(t *testing.T) { + ctx, cancel := context.WithCancel(context.Background()) + cancel() + + _, err := moduleDir(ctx, modulePath) + assert.ErrorIs(t, err, context.Canceled, "a cancelled context must stop the lookup") +} diff --git a/e2e/harness/paths.go b/e2e/harness/paths.go index d7df6bbfa..569c32efc 100644 --- a/e2e/harness/paths.go +++ b/e2e/harness/paths.go @@ -3,27 +3,82 @@ package harness import ( + "context" "fmt" "os" + "os/exec" "path/filepath" + "strings" ) -// repoRoot walks up from the working directory to the module root (the -// directory holding go.mod), so the Docker build context is correct no matter -// which package the test runs from. -func repoRoot() (string, error) { +// modulePath is this module, used both to recognise the repo when walking up +// from the working directory and to locate it when the suite lives elsewhere. +const modulePath = "github.com/netbirdio/netbird" + +// repoRoot returns the directory the component Dockerfiles are built from. +// +// Walking up from the working directory finds it for any test inside this repo, +// no matter which package it runs from. A suite in another module gets a +// different answer that way — its own module root, where combined/Dockerfile +// does not exist — so the ancestor has to be this module and not merely some +// module. When it is not, the build context is the extracted module directory of +// whichever version that suite depends on, which is the right one: the server it +// tests against is then built from the same revision as the client library it +// was compiled with. +func repoRoot(ctx context.Context) (string, error) { dir, err := os.Getwd() if err != nil { return "", err } for { - if _, statErr := os.Stat(filepath.Join(dir, "go.mod")); statErr == nil { + if isModule(filepath.Join(dir, "go.mod"), modulePath) { return dir, nil } parent := filepath.Dir(dir) if parent == dir { - return "", fmt.Errorf("go.mod not found above %s", dir) + break } dir = parent } + return moduleDir(ctx, modulePath) +} + +// isModule reports whether the go.mod at path declares the given module. +func isModule(path, want string) bool { + b, err := os.ReadFile(path) + if err != nil { + return false + } + for _, line := range strings.Split(string(b), "\n") { + if rest, ok := strings.CutPrefix(strings.TrimSpace(line), "module "); ok { + return strings.TrimSpace(rest) == want + } + } + return false +} + +// moduleDir asks the go tool where a module's source is, which for a dependent +// module is its extracted copy in the module cache. The cache is read-only, and +// a Docker build context is only ever read. +// +// -mod=readonly is required rather than cosmetic. A caller that vendors its +// dependencies puts the go command in automatic vendor mode, where this lookup +// succeeds with an EMPTY directory — vendor/ holds packages, not module source, +// so there is nothing to report. Asking in readonly mode resolves against the +// module graph instead, which answers for both a cached module and a local +// replacement, and neither writes to go.mod. +func moduleDir(ctx context.Context, module string) (string, error) { + cmd := exec.CommandContext(ctx, "go", "list", "-mod=readonly", "-m", "-f", "{{.Dir}}", module) + out, err := cmd.Output() + if err != nil { + return "", fmt.Errorf("locate %s: %w", module, err) + } + dir := strings.TrimSpace(string(out)) + if dir == "" { + return "", fmt.Errorf("locate %s: the go tool reported no directory; run `go mod download %s`", module, module) + } + if _, err := os.Stat(dir); err != nil { + return "", fmt.Errorf("locate %s: %w", module, err) + } + return dir, nil } diff --git a/e2e/harness/proxy.go b/e2e/harness/proxy.go index 85f3518d4..3d709b439 100644 --- a/e2e/harness/proxy.go +++ b/e2e/harness/proxy.go @@ -43,7 +43,7 @@ type Proxy struct { // or override any NB_PROXY_* var (e.g. NB_PROXY_TUNNEL_CACHE_TTL for tests that // need a short authorization-cache window). func StartProxy(ctx context.Context, c *Combined, proxyToken string, envOverrides ...map[string]string) (*Proxy, error) { - root, err := repoRoot() + root, err := repoRoot(ctx) if err != nil { return nil, err } diff --git a/e2e/harness/vllm.go b/e2e/harness/vllm.go index 2f3d306cc..cf9316325 100644 --- a/e2e/harness/vllm.go +++ b/e2e/harness/vllm.go @@ -18,18 +18,63 @@ const ( vllmImage = "nginx:alpine" vllmAlias = "vllm" vllmPort = "8000/tcp" + // vllmStreamPort serves the same wire shapes as an SSE stream. See the + // nginx config for why streaming lives on its own listener. + vllmStreamPort = "8001/tcp" // VLLMModel is the served model id the mock advertises and echoes back. It // matches a real small model commonly served by vLLM so the provider's // enumerated model and the client's request line up. VLLMModel = "Qwen/Qwen2.5-0.5B-Instruct" + // VLLMUnlistedModel is a second id the mock's model listing advertises but + // no test provider enumerates, so a filtered listing is observably shorter + // than the upstream's own. + VLLMUnlistedModel = "Qwen/Qwen2.5-7B-Instruct" +) + +// Token counts the mock reports per wire shape. Tests assert on these rather +// than on "> 0" so a response parsed with the wrong provider's parser (which +// would read a different field, or none) fails loudly instead of passing on +// a coincidental non-zero. +const ( + // VLLMChatInputTokens / VLLMChatOutputTokens ride the OpenAI usage block. + VLLMChatInputTokens = 11 + VLLMChatOutputTokens = 2 + // VLLMMessagesInputTokens / VLLMMessagesOutputTokens ride the Anthropic + // usage block, whose field names the OpenAI parser cannot read. + VLLMMessagesInputTokens = 17 + VLLMMessagesOutputTokens = 3 +) + +// Token counts the streaming surface reports. They differ from the +// non-streaming ones on purpose: a test that asserts these numbers proves the +// SSE accumulator ran, rather than a buffered JSON body having been parsed. +// +// Input and cache-read arrive on message_start; output arrives on +// message_delta and supersedes the seed value message_start carries. Any +// parser that cannot read message_start reports zero input tokens — which is +// exactly the bug these counts exist to catch. +const ( + VLLMStreamInputTokens = 29 + VLLMStreamOutputTokens = 5 + VLLMStreamCacheReadTokens = 7 ) // vllmNginxConf emulates a vLLM OpenAI-compatible server over plain HTTP (vLLM's -// default: no TLS, port 8000). It answers /v1/models with a one-model list and -// any chat/completions path with a canned OpenAI-shaped chat completion carrying -// a non-zero usage block, so the proxy's OpenAI parser records real token -// consumption. Running actual vLLM in CI is infeasible (GPU + multi-GB model +// default: no TLS, port 8000), and additionally answers the wire shapes the +// other catalog surfaces speak so one mock can stand in for every provider the +// proxy routes to. Running actual vLLM in CI is infeasible (GPU + multi-GB model // download), so this stands in for the wire contract the proxy depends on. +// +// Each shape answers with its own vendor's usage block, so a response parsed +// under the wrong surface meters zero rather than passing by accident: +// +// - /v1/chat/completions (and any unmatched path): OpenAI chat completion. +// - /v1/messages: Anthropic Messages, snake_case usage plus a cache bucket. +// - /model/{id}/invoke: Bedrock InvokeModel, which carries the Anthropic body. +// - the token-counting endpoints: a count, with no usage block at all. +// +// The model listing advertises two models so a policy that authorises one +// produces an observably shorter list than the upstream's own. const vllmNginxConf = `pid /tmp/nginx.pid; events {} http { @@ -37,13 +82,75 @@ http { listen 8000; location = /v1/models { default_type application/json; - return 200 '{"object":"list","data":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","object":"model","owned_by":"vllm"}]}'; + return 200 '{"object":"list","data":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","object":"model","owned_by":"vllm"},{"id":"Qwen/Qwen2.5-7B-Instruct","object":"model","owned_by":"vllm"}]}'; + } + location = /v1/messages { + default_type application/json; + return 200 '{"id":"msg_e2e","type":"message","role":"assistant","model":"claude-sonnet-5","content":[{"type":"text","text":"pong"}],"stop_reason":"end_turn","usage":{"input_tokens":17,"output_tokens":3,"cache_read_input_tokens":5}}'; + } + location = /v1/messages/count_tokens { + default_type application/json; + return 200 '{"input_tokens":7}'; + } + location ~ ^/model/.+/invoke$ { + default_type application/json; + return 200 '{"id":"msg_e2e_bedrock","type":"message","role":"assistant","content":[{"type":"text","text":"pong"}],"stop_reason":"end_turn","usage":{"input_tokens":17,"output_tokens":3,"cache_read_input_tokens":5}}'; + } + location ~ ^/model/.+/count-tokens$ { + default_type application/json; + return 200 '{"inputTokens":9}'; + } + location = /api/hello { + return 200; + } + location = /inference-profiles { + default_type application/json; + return 200 '{"inferenceProfileSummaries":[{"inferenceProfileId":"us.anthropic.claude-sonnet-5","status":"ACTIVE"}]}'; } location / { default_type application/json; return 200 '{"id":"chatcmpl-e2e-vllm","object":"chat.completion","created":1700000000,"model":"Qwen/Qwen2.5-0.5B-Instruct","choices":[{"index":0,"message":{"role":"assistant","content":"pong"},"finish_reason":"stop"}],"usage":{"prompt_tokens":11,"completion_tokens":2,"total_tokens":13}}'; } } + + # The streaming surface, on its own port so the response content type is a + # property of the listener rather than of a per-request branch: nginx sets + # Content-Type from default_type, which cannot be varied inside an "if", and + # a second Content-Type via add_header would leave the proxy reading the + # wrong one. A provider record pointed at this port streams every answer. + # + # Input and cache-read tokens ride message_start, output rides message_delta + # — the split that makes a stream different from a buffered body, and the + # reason a parser that ignores message_start meters input as zero. + server { + listen 8001; + location = /v1/messages { + default_type text/event-stream; + return 200 'event: message_start +data: {"type":"message_start","message":{"id":"msg_e2e_stream","type":"message","role":"assistant","model":"claude-sonnet-5","content":[],"usage":{"input_tokens":29,"output_tokens":1,"cache_read_input_tokens":7}}} + +event: content_block_delta +data: {"type":"content_block_delta","index":0,"delta":{"type":"text_delta","text":"pong"}} + +event: message_delta +data: {"type":"message_delta","delta":{"stop_reason":"end_turn"},"usage":{"output_tokens":5}} + +event: message_stop +data: {"type":"message_stop"} + +'; + } + location / { + default_type text/event-stream; + return 200 'data: {"choices":[{"delta":{"content":"pong"}}]} + +data: {"choices":[],"usage":{"prompt_tokens":29,"completion_tokens":5,"total_tokens":34}} + +data: [DONE] + +'; + } + } } ` @@ -55,6 +162,10 @@ type VLLM struct { workDir string // URL is the upstream URL the vllm provider points at (http://:8000). URL string + // StreamURL is the same mock's streaming listener. A provider pointed here + // answers every request as SSE, so the proxy's streaming accumulator runs + // instead of its buffered-body parser. + StreamURL string } // StartVLLM runs the mock vLLM server on the shared network over plain HTTP. @@ -73,14 +184,17 @@ func StartVLLM(ctx context.Context, c *Combined) (*VLLM, error) { req := testcontainers.ContainerRequest{ Image: vllmImage, - ExposedPorts: []string{vllmPort}, + ExposedPorts: []string{vllmPort, vllmStreamPort}, Networks: []string{c.network.Name}, NetworkAliases: map[string][]string{c.network.Name: {vllmAlias}}, Cmd: []string{"nginx", "-c", "/conf/nginx.conf", "-g", "daemon off;"}, HostConfigModifier: func(hc *container.HostConfig) { hc.Binds = append(hc.Binds, workDir+":/conf:ro") }, - WaitingFor: wait.ForListeningPort(vllmPort).WithStartupTimeout(60 * time.Second), + WaitingFor: wait.ForAll( + wait.ForListeningPort(vllmPort), + wait.ForListeningPort(vllmStreamPort), + ).WithStartupTimeout(60 * time.Second), } ctr, err := testcontainers.GenericContainer(ctx, testcontainers.GenericContainerRequest{ @@ -92,7 +206,12 @@ func StartVLLM(ctx context.Context, c *Combined) (*VLLM, error) { return nil, fmt.Errorf("start vllm container: %w", err) } - return &VLLM{container: ctr, workDir: workDir, URL: "http://" + vllmAlias + ":8000"}, nil + return &VLLM{ + container: ctr, + workDir: workDir, + URL: "http://" + vllmAlias + ":8000", + StreamURL: "http://" + vllmAlias + ":8001", + }, nil } // Logs returns the vLLM container logs, for diagnostics on failure. diff --git a/flow/client/client.go b/flow/client/client.go index 3f31c2464..fc07db833 100644 --- a/flow/client/client.go +++ b/flow/client/client.go @@ -146,11 +146,14 @@ func (c *GRPCClient) Receive(ctx context.Context, interval time.Duration, msgHan streamStart := time.Now() - if err := c.receive(stream, msgHandler); err != nil { + // receive always returns a non-nil error once the stream breaks; + // handleRetryableError decides between reconnecting and exiting + // permanently on local context cancellation + err = c.receive(stream, msgHandler) + if !isContextDone(err) { log.Errorf("receive failed: %v", err) - return c.handleRetryableError(err, streamStart, backOff) } - return nil + return c.handleRetryableError(err, streamStart, backOff) } if err := backoff.Retry(operation, backOff); err != nil { diff --git a/funding.json b/funding.json index 6b509a992..34ee9fe46 100644 --- a/funding.json +++ b/funding.json @@ -6,7 +6,7 @@ "name": "NetBird GmbH", "email": "hello@netbird.io", "phone": "", - "description": "NetBird GmbH is a Berlin-based software company specializing in the development of open-source network security solutions. Network security is utterly complex and expensive, accessible only to companies with multi-million dollar IT budgets. In contrast, there are millions of companies left behind. Our mission is to create an advanced network and cybersecurity platform that is both easy-to-use and affordable for teams of all sizes and budgets. By leveraging the open-source strategy and technological advancements, NetBird aims to set the industry standard for connecting and securing IT infrastructure.", + "description": "NetBird GmbH is a Berlin-based software company specializing in the development of open source network security solutions. Network security is utterly complex and expensive, accessible only to companies with multi-million dollar IT budgets. In contrast, there are millions of companies left behind. Our mission is to create an advanced network and cybersecurity platform that is both easy-to-use and affordable for teams of all sizes and budgets. By leveraging the open source strategy and technological advancements, NetBird aims to set the industry standard for connecting and securing IT infrastructure.", "webpageUrl": { "url": "https://github.com/netbirdio" } @@ -15,7 +15,7 @@ { "guid": "netbird", "name": "NetBird", - "description": "NetBird is a configuration-free peer-to-peer private network and a centralized access control system combined in a single open-source platform. It makes it easy to create secure WireGuard-based private networks for your organization or home.", + "description": "NetBird is a configuration-free peer-to-peer private network and a centralized access control system combined in a single open source platform. It makes it easy to create secure WireGuard-based private networks for your organization or home.", "webpageUrl": { "url": "https://github.com/netbirdio/netbird" }, @@ -59,7 +59,7 @@ "guid": "support-yearly", "status": "active", "name": "Support Open Source Development and Maintenance - Yearly", - "description": "This will help us partially cover the yearly cost of maintaining the open-source NetBird project.", + "description": "This will help us partially cover the yearly cost of maintaining the open source NetBird project.", "amount": 100000, "currency": "USD", "frequency": "yearly", @@ -72,7 +72,7 @@ "guid": "support-one-time-year", "status": "active", "name": "Support Open Source Development and Maintenance - One Year", - "description": "This will help us partially cover the yearly cost of maintaining the open-source NetBird project.", + "description": "This will help us partially cover the yearly cost of maintaining the open source NetBird project.", "amount": 100000, "currency": "USD", "frequency": "one-time", @@ -85,7 +85,7 @@ "guid": "support-one-time-monthly", "status": "active", "name": "Support Open Source Development and Maintenance - Monthly", - "description": "This will help us partially cover the monthly cost of maintaining the open-source NetBird project.", + "description": "This will help us partially cover the monthly cost of maintaining the open source NetBird project.", "amount": 10000, "currency": "USD", "frequency": "monthly", @@ -98,7 +98,7 @@ "guid": "support-monthly", "status": "active", "name": "Support Open Source Development and Maintenance - One Month", - "description": "This will help us partially cover the monthly cost of maintaining the open-source NetBird project.", + "description": "This will help us partially cover the monthly cost of maintaining the open source NetBird project.", "amount": 10000, "currency": "USD", "frequency": "monthly", diff --git a/go.mod b/go.mod index f8a1a84b0..efec8c94d 100644 --- a/go.mod +++ b/go.mod @@ -19,7 +19,7 @@ require ( github.com/spf13/cobra v1.10.2 github.com/spf13/pflag v1.0.10 github.com/vishvananda/netlink v1.3.1 - golang.org/x/crypto v0.54.0 + golang.org/x/crypto v0.55.0 golang.org/x/sys v0.47.0 golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173 golang.zx2c4.com/wireguard/wgctrl v0.0.0-20241231184526-a9ab2273dd10 @@ -57,11 +57,11 @@ require ( github.com/fsnotify/fsnotify v1.9.0 github.com/gliderlabs/ssh v0.3.8 github.com/go-jose/go-jose/v4 v4.1.4 + github.com/go-ole/go-ole v1.3.0 github.com/gobwas/ws v1.4.0 github.com/goccy/go-yaml v1.18.0 github.com/godbus/dbus/v5 v5.2.2 github.com/golang-jwt/jwt/v5 v5.3.1 - github.com/golang/mock v1.6.0 github.com/google/go-cmp v0.7.0 github.com/google/gopacket v1.1.19 github.com/google/nftables v0.3.0 @@ -73,7 +73,6 @@ require ( github.com/hashicorp/go-version v1.7.0 github.com/jackc/pgx/v5 v5.5.5 github.com/libdns/route53 v1.5.0 - github.com/libp2p/go-nat v0.2.0 github.com/libp2p/go-netroute v0.4.0 github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81 github.com/mdlayher/socket v0.5.1 @@ -81,6 +80,7 @@ require ( github.com/miekg/dns v1.1.72 github.com/mitchellh/hashstructure/v2 v2.0.2 github.com/moby/moby/api v1.54.1 + github.com/netbirdio/go-nat v0.0.0-20260821095157-6b2c8c5c74e8 github.com/netbirdio/management-integrations/integrations v0.0.0-20260416123949-2355d972be42 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45 github.com/oapi-codegen/runtime v1.1.2 @@ -99,7 +99,7 @@ require ( github.com/pires/go-proxyproto v0.11.0 github.com/pkg/sftp v1.13.9 github.com/prometheus/client_golang v1.23.2 - github.com/quic-go/quic-go v0.55.0 + github.com/quic-go/quic-go v0.59.1 github.com/redis/go-redis/v9 v9.7.3 github.com/rs/xid v1.3.0 github.com/shirou/gopsutil/v4 v4.25.8 @@ -126,9 +126,9 @@ require ( go.uber.org/zap v1.27.0 goauthentik.io/api/v3 v3.2023051.3 golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f - golang.org/x/mobile v0.0.0-20251113184115-a159579294ab - golang.org/x/mod v0.37.0 - golang.org/x/net v0.56.0 + golang.org/x/mobile v0.0.0-20260816165457-f98cc9b3c733 + golang.org/x/mod v0.39.0 + golang.org/x/net v0.58.0 golang.org/x/oauth2 v0.36.0 golang.org/x/sync v0.22.0 golang.org/x/term v0.45.0 @@ -199,7 +199,6 @@ require ( github.com/go-ldap/ldap/v3 v3.4.13 // indirect github.com/go-logr/logr v1.4.3 // indirect github.com/go-logr/stdr v1.2.2 // indirect - github.com/go-ole/go-ole v1.3.0 // indirect github.com/go-openapi/analysis v0.23.0 // indirect github.com/go-openapi/errors v0.22.2 // indirect github.com/go-openapi/jsonpointer v0.21.1 // indirect @@ -217,6 +216,7 @@ require ( github.com/gobwas/pool v0.2.1 // indirect github.com/gogo/protobuf v1.3.2 // indirect github.com/golang-jwt/jwt/v4 v4.5.2 // indirect + github.com/golang/mock v1.6.0 // indirect github.com/google/btree v1.1.3 // indirect github.com/google/go-querystring v1.1.0 // indirect github.com/google/go-tpm v0.9.8 // indirect @@ -239,7 +239,6 @@ require ( github.com/jackc/pgservicefile v0.0.0-20221227161230-091c0ba34f0a // indirect github.com/jackc/puddle/v2 v2.2.1 // indirect github.com/jackpal/go-nat-pmp v1.0.2 // indirect - github.com/jchv/go-winloader v0.0.0-20250406163304-c1995be93bd1 // indirect github.com/jinzhu/inflection v1.0.0 // indirect github.com/jinzhu/now v1.1.5 // indirect github.com/jmespath/go-jmespath v0.4.0 // indirect @@ -314,8 +313,8 @@ require ( go.opentelemetry.io/otel/trace v1.43.0 // indirect go.uber.org/multierr v1.11.0 // indirect go.yaml.in/yaml/v2 v2.4.3 // indirect - golang.org/x/text v0.40.0 // indirect - golang.org/x/tools v0.47.0 // indirect + golang.org/x/text v0.41.0 // indirect + golang.org/x/tools v0.49.0 // indirect golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 // indirect google.golang.org/genproto/googleapis/api v0.0.0-20260319201613-d00831a3d3e7 // indirect gopkg.in/square/go-jose.v2 v2.6.0 // indirect @@ -340,4 +339,6 @@ replace github.com/dexidp/dex/api/v2 => github.com/netbirdio/dex/api/v2 v2.0.0-2 replace github.com/mailru/easyjson => github.com/netbirdio/easyjson v0.9.0 -replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701 +replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260825085513-5f07a01f7a78 + +tool go.uber.org/mock/mockgen diff --git a/go.sum b/go.sum index f6b32e32a..da68b6458 100644 --- a/go.sum +++ b/go.sum @@ -349,8 +349,6 @@ github.com/jackc/puddle/v2 v2.2.1 h1:RhxXJtFG022u4ibrCSMSiu5aOq1i77R3OHKNJj77OAk github.com/jackc/puddle/v2 v2.2.1/go.mod h1:vriiEXHvEE654aYKXXjOvZM39qJ0q+azkZFrfEOc3H4= github.com/jackpal/go-nat-pmp v1.0.2 h1:KzKSgb7qkJvOUTqYl9/Hg/me3pWgBmERKrTGD7BdWus= github.com/jackpal/go-nat-pmp v1.0.2/go.mod h1:QPH045xvCAeXUZOxsnwmrtiCoxIr9eob+4orBN1SBKc= -github.com/jchv/go-winloader v0.0.0-20250406163304-c1995be93bd1 h1:njuLRcjAuMKr7kI3D85AXWkw6/+v9PwtV6M6o11sWHQ= -github.com/jchv/go-winloader v0.0.0-20250406163304-c1995be93bd1/go.mod h1:alcuEEnZsY1WQsagKhZDsoPCRoOijYqhZvPwLG0kzVs= github.com/jcmturner/aescts/v2 v2.0.0 h1:9YKLH6ey7H4eDBXW8khjYslgyqG2xZikXP0EQFKrle8= github.com/jcmturner/aescts/v2 v2.0.0/go.mod h1:AiaICIRyfYg35RUkr8yESTqvSy7csK90qZ5xfvvsoNs= github.com/jcmturner/dnsutils/v2 v2.0.0 h1:lltnkeZGL0wILNvrNiVCR6Ro5PGU/SeBvVO/8c/iPbo= @@ -409,8 +407,6 @@ github.com/libdns/libdns v0.2.2 h1:O6ws7bAfRPaBsgAYt8MDe2HcNBGC29hkZ9MX2eUSX3s= github.com/libdns/libdns v0.2.2/go.mod h1:4Bj9+5CQiNMVGf87wjX4CY3HQJypUHRuLvlsfsZqLWQ= github.com/libdns/route53 v1.5.0 h1:2SKdpPFl/qgWsXQvsLNJJAoX7rSxlk7zgoL4jnWdXVA= github.com/libdns/route53 v1.5.0/go.mod h1:joT4hKmaTNKHEwb7GmZ65eoDz1whTu7KKYPS8ZqIh6Q= -github.com/libp2p/go-nat v0.2.0 h1:Tyz+bUFAYqGyJ/ppPPymMGbIgNRH+WqC5QrT5fKrrGk= -github.com/libp2p/go-nat v0.2.0/go.mod h1:3MJr+GRpRkyT65EpVPBstXLvOlAPzUVlG6Pwg9ohLJk= github.com/libp2p/go-netroute v0.4.0 h1:sZZx9hyANYUx9PZyqcgE/E1GUG3iEtTZHUEvdtXT7/Q= github.com/libp2p/go-netroute v0.4.0/go.mod h1:Nkd5ShYgSMS5MUKy/MU2T57xFoOKvvLR92Lic48LEyA= github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81 h1:J56rFEfUTFT9j9CiRXhi1r8lUJ4W5idG3CiaBZGojNU= @@ -482,6 +478,8 @@ github.com/netbirdio/dex/api/v2 v2.0.0-20260512110716-8d70ad8647c1 h1:neE7z+FPUk github.com/netbirdio/dex/api/v2 v2.0.0-20260512110716-8d70ad8647c1/go.mod h1:awuTyT29CYALpEyET0S307EgNlPWrc7fFKRAyhsO45M= github.com/netbirdio/easyjson v0.9.0 h1:6Nw2lghSVuy8RSkAYDhDv1thBVEmfVbKZnV7T7Z6Aus= github.com/netbirdio/easyjson v0.9.0/go.mod h1:1+xMtQp2MRNVL/V1bOzuP3aP8VNwRW55fQUto+XFtTU= +github.com/netbirdio/go-nat v0.0.0-20260821095157-6b2c8c5c74e8 h1:pBxXEsxcsO3qVUND//5j1kelYlO57x5IrRviNF0+0iA= +github.com/netbirdio/go-nat v0.0.0-20260821095157-6b2c8c5c74e8/go.mod h1:mFViabv4PpnoDw9w7W21a7xux6APA4q7KQZRsv4BCl8= github.com/netbirdio/ice/v4 v4.0.0-20250908184934-6202be846b51 h1:Ov4qdafATOgGMB1wbSuh+0aAHcwz9hdvB6VZjh1mVMI= github.com/netbirdio/ice/v4 v4.0.0-20250908184934-6202be846b51/go.mod h1:ZSIbPdBn5hePO8CpF1PekH2SfpTxg1PDhEwtbqZS7R8= github.com/netbirdio/management-integrations/integrations v0.0.0-20260416123949-2355d972be42 h1:F3zS5fT9xzD1OFLfcdAE+3FfyiwjGukF1hvj0jErgs8= @@ -490,8 +488,8 @@ github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502 h1:3tHlFmhTdX9ax github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502/go.mod h1:CIMRFEJVL+0DS1a3Nx06NaMn4Dz63Ng6O7dl0qH0zVM= github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45 h1:ujgviVYmx243Ksy7NdSwrdGPSRNE3pb8kEDSpH0QuAQ= github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45/go.mod h1:5/sjFmLb8O96B5737VCqhHyGRzNFIaN/Bu7ZodXc3qQ= -github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701 h1:QL9nupfRom0L9jcY7N9l/Bc6QK2PtC6pHzC+ftpTqpw= -github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701/go.mod h1:BzATbK71VFikMMMCo434wAi0QcaI03P+xeaWgDvQvjw= +github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260825085513-5f07a01f7a78 h1:B/jRv24jnFeoA+VccxoCx6K94PUgsqR9wnshpeu9M+8= +github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260825085513-5f07a01f7a78/go.mod h1:/6QR46/nhGCSADHbS++XtDb9dkTnenTHlGskTPRo9S0= github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a h1:3CWK+yTvRKOcC0Q8VCTGy4l60TEb27CQVS7LkMxwjmw= github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw= github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A= @@ -582,8 +580,8 @@ github.com/prometheus/otlptranslator v1.0.0 h1:s0LJW/iN9dkIH+EnhiD3BlkkP5QVIUVEo github.com/prometheus/otlptranslator v1.0.0/go.mod h1:vRYWnXvI6aWGpsdY/mOT/cbeVRBlPWtBNDb7kGR3uKM= github.com/prometheus/procfs v0.19.2 h1:zUMhqEW66Ex7OXIiDkll3tl9a1ZdilUOd/F6ZXw4Vws= github.com/prometheus/procfs v0.19.2/go.mod h1:M0aotyiemPhBCM0z5w87kL22CxfcH05ZpYlu+b4J7mw= -github.com/quic-go/quic-go v0.55.0 h1:zccPQIqYCXDt5NmcEabyYvOnomjs8Tlwl7tISjJh9Mk= -github.com/quic-go/quic-go v0.55.0/go.mod h1:DR51ilwU1uE164KuWXhinFcKWGlEjzys2l8zUl5Ss1U= +github.com/quic-go/quic-go v0.59.1 h1:0Gmua0HW1Tv7ANR7hUYwRyD0MG5OJfgvYSZasGZzBic= +github.com/quic-go/quic-go v0.59.1/go.mod h1:upnsH4Ju1YkqpLXC305eW3yDZ4NfnNbmQRCMWS58IKU= github.com/redis/go-redis/v9 v9.7.3 h1:YpPyAayJV+XErNsatSElgRZZVCwXX9QzkKYNvO7x0wM= github.com/redis/go-redis/v9 v9.7.3/go.mod h1:bGUrSggJ9X9GUmZpZNEOQKaANxSGgOEBRltRTZHSvrA= github.com/rogpeppe/go-internal v1.14.1 h1:UQB4HGPB6osV0SQTLymcB4TgvyWu6ZyliaW0tI/otEQ= @@ -730,13 +728,13 @@ golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1m golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU= golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8= golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk= -golang.org/x/crypto v0.54.0 h1:YLIA59K4fiNzHzjnZt2tUJQjQtUWfWbeHBqKtk3eScw= -golang.org/x/crypto v0.54.0/go.mod h1:KWL8ny2AZdGR2cWmzeHrp2azQPGogOv+HeQaVEXC2dk= +golang.org/x/crypto v0.55.0 h1:+KWHjbgOaAQ66dh/YlkZKHlz9ZUlq61AFirAR9ntP8M= +golang.org/x/crypto v0.55.0/go.mod h1:uq0V9dE/fzQuJtbnL+2EhWOE63vo164FY8xqEnV9xis= golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM= golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80= golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY= -golang.org/x/mobile v0.0.0-20251113184115-a159579294ab h1:Iqyc+2zr7aGyLuEadIm0KRJP0Wwt+fhlXLa51Fxf1+Q= -golang.org/x/mobile v0.0.0-20251113184115-a159579294ab/go.mod h1:Eq3Nh/5pFSWug2ohiudJ1iyU59SO78QFuh4qTTN++I0= +golang.org/x/mobile v0.0.0-20260816165457-f98cc9b3c733 h1:XKMObIaAElmkdO+4SQh1iCfzwciZHJi1OblnX9BED9k= +golang.org/x/mobile v0.0.0-20260816165457-f98cc9b3c733/go.mod h1:jMwjxoDSx9jqhNaZqPnr6nnKzb7cs+Dy1Czk7wdX+R8= golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg= golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA= golang.org/x/mod v0.3.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA= @@ -746,8 +744,8 @@ golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs= golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c= -golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ= -golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0= +golang.org/x/mod v0.39.0 h1:UF5zwQdCRRUpHfyPwr7d4UrGiVeldIsogtzWVnczL74= +golang.org/x/mod v0.39.0/go.mod h1:bvIbwjQ0HUFFf5AKukeeYQG4ZBUG9yxQbR9aEweIwYY= golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4= golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg= golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks= @@ -766,8 +764,8 @@ golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk= golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY= golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44= golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM= -golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o= -golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec= +golang.org/x/net v0.58.0 h1:ynWG7rqYi4ccpTEuPZ2QGWHktVEM9DMCj9yzDE0Q7To= +golang.org/x/net v0.58.0/go.mod h1:YwCddHnFlT7eLQqVprV19OnhLGtc5xOKgE0RyqgfWAU= golang.org/x/oauth2 v0.8.0/go.mod h1:yr7u4HXZRm1R1kBWqr/xKNqewf0plRYoB7sla+BCIXE= golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs= golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q= @@ -793,7 +791,6 @@ golang.org/x/sys v0.0.0-20190916202348-b4ddaad3f8a3/go.mod h1:h1NjWce9XRLGQEsW7w golang.org/x/sys v0.0.0-20191005200804-aed5e4c7ecf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= -golang.org/x/sys v0.0.0-20200810151505-1b9f1253b3ed/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200930185726-fdedc70b468f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20201015000850-e3ed0017c211/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20201119102817-f84b799fce68/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= @@ -846,8 +843,8 @@ golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE= golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU= golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ= -golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs= -golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY= +golang.org/x/text v0.41.0 h1:vz/seA0lnX87Othu2f/0L24RcgrXD9/YFTSuGjj3rH8= +golang.org/x/text v0.41.0/go.mod h1:jvf1O8ajNzZqhSrQBPbutR/EB83Cc0CFrezNQIwbb5M= golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U= golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno= golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ= @@ -861,8 +858,8 @@ golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU= golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58= golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk= -golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q= -golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA= +golang.org/x/tools v0.49.0 h1:3NI7VXzL9+1WZD52Dx2ttoPwD5DWrFGpl9mFZDlmisI= +golang.org/x/tools v0.49.0/go.mod h1:SJNXV9DBKT0UbdttsQjbfJlAE/q+y36++zo3uL3N0Oo= golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0= diff --git a/infrastructure_files/getting-started.sh b/infrastructure_files/getting-started.sh index 4f2c1d82e..0fc5b23c5 100755 --- a/infrastructure_files/getting-started.sh +++ b/infrastructure_files/getting-started.sh @@ -111,6 +111,59 @@ check_nb_domain() { return 0 } +# Non-interactive configuration +# ------------------------------ +# Every prompt below can be pre-answered with an environment variable, so the +# script runs unattended (cloud-init, CI, Terraform, curl | bash). resolve() +# is the single place that decides env var vs prompt vs default; the read_* +# helpers stay pure prompts. +# +# Supported env vars: +# NETBIRD_DOMAIN domain/FQDN (required) +# NETBIRD_LETSENCRYPT_EMAIL ACME email (required for built-in Traefik) +# NETBIRD_AGENT_NETWORK true enables the agent-network preset +# NETBIRD_REVERSE_PROXY_TYPE 0-5 (default 0 = built-in Traefik) +# NETBIRD_ENABLE_PROXY true/false (default false) +# NETBIRD_ENABLE_CROWDSEC true/false (default false) +# NETBIRD_TRAEFIK_EXTERNAL_NETWORK external-Traefik network (type 1) +# NETBIRD_TRAEFIK_ENTRYPOINT external-Traefik entrypoint (type 1, default websecure) +# NETBIRD_TRAEFIK_CERTRESOLVER external-Traefik cert resolver (type 1) +# NETBIRD_BIND_LOCALHOST_ONLY true/false (default true, types 2-5) +# NETBIRD_EXTERNAL_PROXY_NETWORK docker network to join (types 2-4) +# NETBIRD_NON_INTERACTIVE true forces unattended mode even with a TTY + +# tty_available succeeds only when we may prompt: never when the operator has +# set NETBIRD_NON_INTERACTIVE=true, otherwise only when /dev/tty can actually +# be opened. A PTY can be attached in automation (CI runners, some +# provisioners), so the env override is the authoritative signal and the +# /dev/tty probe is the fallback. /dev/tty is a world-rw device node even with +# no terminal, so a permission test ([ -r ]) is not enough - we must open it. +tty_available() { + [[ "${NETBIRD_NON_INTERACTIVE:-}" == "true" ]] && return 1 + { true < /dev/tty; } 2>/dev/null +} + +# resolve ENV_VAR_NAME DEFAULT PROMPT_FN [prompt args...] +# env var set and non-empty -> its value +# interactive -> PROMPT_FN "$@" (prompt behavior unchanged) +# otherwise -> DEFAULT, or abort when DEFAULT is "required" +resolve() { + local env_name="$1" default="$2" prompt_fn="$3" + shift 3 + local env_value="${!env_name:-}" + if [[ -n "$env_value" ]]; then + echo "$env_value" + elif tty_available; then + "$prompt_fn" "$@" + elif [[ "$default" == "required" ]]; then + echo "$env_name is required for a non-interactive install." > /dev/stderr + exit 1 + else + echo "$default" + fi + return 0 +} + read_nb_domain() { READ_NETBIRD_DOMAIN="" echo -n "Enter the domain you want to use for NetBird (e.g. netbird.my-domain.com): " > /dev/stderr @@ -383,7 +436,14 @@ initialize_default_values() { } configure_domain() { + # Domain is validated (not a free-form value), so it keeps its own guard + # rather than going through resolve(): a valid NETBIRD_DOMAIN is used as-is, + # otherwise we prompt, or abort when there is no terminal to prompt on. if ! check_nb_domain "$NETBIRD_DOMAIN"; then + if ! tty_available; then + echo "NETBIRD_DOMAIN is required for a non-interactive install." > /dev/stderr + exit 1 + fi NETBIRD_DOMAIN=$(read_nb_domain) fi @@ -411,11 +471,7 @@ apply_agent_network_preset() { ENABLE_PROXY="true" ENABLE_CROWDSEC="false" - if [[ -n "${NETBIRD_LETSENCRYPT_EMAIL}" ]]; then - TRAEFIK_ACME_EMAIL="${NETBIRD_LETSENCRYPT_EMAIL}" - else - TRAEFIK_ACME_EMAIL=$(read_traefik_acme_email) - fi + TRAEFIK_ACME_EMAIL=$(resolve NETBIRD_LETSENCRYPT_EMAIL required read_traefik_acme_email) echo "" > /dev/stderr echo "Agent-network preset enabled (NETBIRD_AGENT_NETWORK=true):" > /dev/stderr @@ -437,35 +493,35 @@ configure_reverse_proxy() { return 0 fi - # Prompt for reverse proxy type - REVERSE_PROXY_TYPE=$(read_reverse_proxy_type) + # Reverse proxy type (env NETBIRD_REVERSE_PROXY_TYPE, else prompt, else 0) + REVERSE_PROXY_TYPE=$(resolve NETBIRD_REVERSE_PROXY_TYPE 0 read_reverse_proxy_type) # Handle built-in Traefik prompts (option 0) if [[ "$REVERSE_PROXY_TYPE" == "0" ]]; then - TRAEFIK_ACME_EMAIL=$(read_traefik_acme_email) - ENABLE_PROXY=$(read_enable_proxy) + TRAEFIK_ACME_EMAIL=$(resolve NETBIRD_LETSENCRYPT_EMAIL required read_traefik_acme_email) + ENABLE_PROXY=$(resolve NETBIRD_ENABLE_PROXY false read_enable_proxy) if [[ "$ENABLE_PROXY" == "true" ]]; then - ENABLE_CROWDSEC=$(read_enable_crowdsec) + ENABLE_CROWDSEC=$(resolve NETBIRD_ENABLE_CROWDSEC false read_enable_crowdsec) fi fi # Handle external Traefik-specific prompts (option 1) if [[ "$REVERSE_PROXY_TYPE" == "1" ]]; then - TRAEFIK_EXTERNAL_NETWORK=$(read_traefik_network) - TRAEFIK_ENTRYPOINT=$(read_traefik_entrypoint) - TRAEFIK_CERTRESOLVER=$(read_traefik_certresolver) + TRAEFIK_EXTERNAL_NETWORK=$(resolve NETBIRD_TRAEFIK_EXTERNAL_NETWORK "" read_traefik_network) + TRAEFIK_ENTRYPOINT=$(resolve NETBIRD_TRAEFIK_ENTRYPOINT websecure read_traefik_entrypoint) + TRAEFIK_CERTRESOLVER=$(resolve NETBIRD_TRAEFIK_CERTRESOLVER "" read_traefik_certresolver) fi # Handle port binding for external proxy options (2-5) if [[ "$REVERSE_PROXY_TYPE" -ge 2 ]]; then - BIND_LOCALHOST_ONLY=$(read_port_binding_preference) + BIND_LOCALHOST_ONLY=$(resolve NETBIRD_BIND_LOCALHOST_ONLY true read_port_binding_preference) fi # Handle Docker network prompts for external proxies (options 2-4) case "$REVERSE_PROXY_TYPE" in - 2) EXTERNAL_PROXY_NETWORK=$(read_proxy_docker_network "Nginx") ;; - 3) EXTERNAL_PROXY_NETWORK=$(read_proxy_docker_network "Nginx Proxy Manager") ;; - 4) EXTERNAL_PROXY_NETWORK=$(read_proxy_docker_network "Caddy") ;; + 2) EXTERNAL_PROXY_NETWORK=$(resolve NETBIRD_EXTERNAL_PROXY_NETWORK "" read_proxy_docker_network "Nginx") ;; + 3) EXTERNAL_PROXY_NETWORK=$(resolve NETBIRD_EXTERNAL_PROXY_NETWORK "" read_proxy_docker_network "Nginx Proxy Manager") ;; + 4) EXTERNAL_PROXY_NETWORK=$(resolve NETBIRD_EXTERNAL_PROXY_NETWORK "" read_proxy_docker_network "Caddy") ;; *) ;; # No network prompt for other options esac return 0 @@ -643,8 +699,13 @@ start_services_and_show_instructions() { print_post_setup_instructions echo "" - echo -n "Press Enter when your reverse proxy is configured (or Ctrl+C to exit)... " - read -r < /dev/tty + if tty_available; then + echo -n "Press Enter when your reverse proxy is configured (or Ctrl+C to exit)... " + read -r < /dev/tty + else + echo "Non-interactive mode: starting NetBird containers now. Finish configuring" + echo "your reverse proxy using the instructions above so it can reach them." + fi echo -e "$MSG_STARTING_SERVICES" $DOCKER_COMPOSE_COMMAND up -d diff --git a/infrastructure_files/migrate-to-enterprise.sh b/infrastructure_files/migrate-to-enterprise.sh index 8e1fcf521..744ba5375 100755 --- a/infrastructure_files/migrate-to-enterprise.sh +++ b/infrastructure_files/migrate-to-enterprise.sh @@ -15,6 +15,12 @@ set -o pipefail # 2. Postgres migration — add Postgres, migrate SQLite data via migrate-store. # 3. Traffic flow — add NATS + flow-enricher + flow-receiver. # +# Step 2 is skipped when the deployment already runs on Postgres +# (server.store.engine: postgres in config.yaml). Nothing is provisioned or +# migrated in that case and the store config is left exactly as the operator +# wrote it — the enterprise image reads the same Postgres the community image +# did. Such a deployment gets the image swap, and can still opt into step 3. +# # If any step fails once the stack has been touched, the script rolls itself # back automatically: generated files are removed, the Postgres volume this run # created is dropped, and the original deployment is started again. @@ -38,6 +44,18 @@ ENV_BACKUP="" PG_VOLUME_NAME="" BACKUP_DIR="" +# Store state. STORE_ENGINE is what the deployment runs on today; when it is +# already postgres, MIGRATE_POSTGRES stays "no" and nothing is provisioned. +# POSTGRES_SERVICE is empty when Postgres lives outside this compose project. +STORE_ENGINE="" +EXISTING_POSTGRES="no" +POSTGRES_DSN="" +POSTGRES_SERVICE="" +POSTGRES_DEPENDS_CONDITION="service_healthy" +# Whether this run needs to generate config.yaml.enterprise at all. A pure +# image swap does not. +ENTERPRISE_CONFIG="no" + NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA" check_docker_compose() { @@ -173,11 +191,11 @@ EOF # --------------------------------------------------------------------------- detect_combined_service() { - yq eval '.services | to_entries | map(select(.value.image | test("^netbirdio/netbird-server"))) | .[0].key // ""' "$COMPOSE_FILE" + yq eval '.services | to_entries | map(select(.value.image | test("^(ghcr\\.io/)?netbirdio/netbird-server([:@]|$)"))) | .[0].key // ""' "$COMPOSE_FILE" } detect_dashboard_service() { - yq eval '.services | to_entries | map(select(.value.image | test("^netbirdio/dashboard"))) | .[0].key // ""' "$COMPOSE_FILE" + yq eval '.services | to_entries | map(select(.value.image | test("^(ghcr\\.io/)?netbirdio/dashboard([:@]|$)"))) | .[0].key // ""' "$COMPOSE_FILE" } detect_config_yaml_host_path() { @@ -192,6 +210,85 @@ detect_exposed_address() { yq eval '.server.exposedAddress // ""' "$CONFIG_YAML_HOST" } +# The engine is a config.yaml-only setting — there is no env override for it +# (combined/cmd/root.go reads it from YAML and derives the env vars), so +# config.yaml is authoritative. Absent means the sqlite default. +detect_store_engine() { + local engine + engine=$(yq eval '.server.store.engine // ""' "$CONFIG_YAML_HOST") + if [[ -z "$engine" ]] || [[ "$engine" == "null" ]]; then + engine="sqlite" + fi + echo "$engine" | tr '[:upper:]' '[:lower:]' +} + +detect_store_dsn() { + yq eval '.server.store.dsn // ""' "$CONFIG_YAML_HOST" +} + +# config.yaml is where a combined deployment carries its DSN; this only covers +# hand-rolled installs that keep it in the environment instead. +detect_store_dsn_from_compose() { + # `compose config` re-escapes a literal $ as $$ on the way out, so undo that + # to get the value the container actually receives. + $DOCKER_COMPOSE_COMMAND config 2>/dev/null | yq eval " + .services[\"$COMBINED_SERVICE\"].environment.NB_STORE_ENGINE_POSTGRES_DSN // + .services[\"$COMBINED_SERVICE\"].environment.NETBIRD_STORE_ENGINE_POSTGRES_DSN // \"\" + " - 2>/dev/null | sed 's/\$\$/$/g' +} + +# Reads either DSN form: "host=db ..." or "postgres://user:pass@db:5432/name". +dsn_host() { + local dsn="$1" + case "$dsn" in + *://*) printf '%s' "$dsn" | sed -n 's,^[a-zA-Z+]*://\([^/?]*\).*,\1,p' | sed -e 's,.*@,,' -e 's,:.*,,' ;; + *) printf '%s' "$dsn" | sed -n 's/.*[[:space:]]*host=\([^[:space:]]*\).*/\1/p' ;; + esac +} + +# flow-enricher is its own container, so a loopback host or a socket path would +# reach the enricher rather than Postgres. Only flag hosts we can positively +# identify — an unparseable DSN must not leave the operator with no way forward. +dsn_host_reachable() { + local dsn="$1" + case "$(dsn_host "$dsn")" in + localhost | 127.* | ::1 | 0.0.0.0 | /*) return 1 ;; + *) return 0 ;; + esac +} + +# Names the compose service running this deployment's Postgres, for depends_on. +# Empty means external — the DSN host matched no service. A DSN with no readable +# host falls back to matching on image. +detect_postgres_service() { + local host + host=$(dsn_host "$POSTGRES_DSN") + if [[ -n "$host" ]]; then + if [[ "$(host="$host" yq eval '.services | has(env(host))' "$COMPOSE_FILE" 2>/dev/null)" == "true" ]]; then + echo "$host" + fi + return + fi + yq eval '.services | to_entries | map(select(.value.image // "" | test("(^|/)(postgres|postgis|pgvector|timescaledb)(:|@|$)"))) | .[0].key // ""' "$COMPOSE_FILE" +} + +# depends_on: service_healthy is only legal if the service defines a healthcheck. +detect_postgres_depends_condition() { + local tag + tag=$(yq eval ".services[\"$POSTGRES_SERVICE\"].healthcheck | tag" "$COMPOSE_FILE" 2>/dev/null) + if [[ "$tag" == "!!map" ]]; then + echo "service_healthy" + else + echo "service_started" + fi +} + +env_value() { + local value="$1" + value=$(printf '%s' "$value" | sed -e 's/\\/\\\\/g' -e 's/"/\\"/g' -e 's/\$/$$/g') + printf '"%s"' "$value" +} + detect_compose_network() { local tag tag=$(yq eval ".services[\"$COMBINED_SERVICE\"].networks | tag" "$COMPOSE_FILE" 2>/dev/null) @@ -221,9 +318,6 @@ render_override() { # Remove this file (and config.yaml.enterprise if present) to revert. services: - ${DASHBOARD_SERVICE}: - image: \${NETBIRD_DASHBOARD_IMAGE:-ghcr.io/netbirdio/dashboard-cloud:latest} - ${COMBINED_SERVICE}: image: \${NETBIRD_SERVER_IMAGE:-ghcr.io/netbirdio/netbird-server-cloud:latest} environment: @@ -231,16 +325,30 @@ services: NETBIRD_LICENSE_SERVER_BASE_URL: \${NETBIRD_LICENSE_SERVER_BASE_URL} EOF + # An existing Postgres is already wired up by the operator's own compose file, + # so only a Postgres this run creates needs a depends_on. if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then cat < "$ENTERPRISE_CONFIG_FILE" - yq eval " - .server.store.engine = \"postgres\" | - .server.store.dsn = \"$pg_dsn\" | - .server.activityStore.engine = \"postgres\" | - .server.activityStore.dsn = \"$pg_dsn\" | - .server.authStore.engine = \"postgres\" | - .server.authStore.dsn = \"$pg_dsn\" - " "$CONFIG_YAML_HOST" > "$ENTERPRISE_CONFIG_FILE" + if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then + # Fresh Postgres: point every store section at it. migrate-store carries the + # SQLite contents across. + POSTGRES_DSN="$POSTGRES_DSN" yq eval -i ' + .server.store.engine = "postgres" | + .server.store.dsn = strenv(POSTGRES_DSN) | + .server.activityStore.engine = "postgres" | + .server.activityStore.dsn = strenv(POSTGRES_DSN) | + .server.authStore.engine = "postgres" | + .server.authStore.dsn = strenv(POSTGRES_DSN) + ' "$ENTERPRISE_CONFIG_FILE" + fi + # Otherwise the store config is the operator's and stays untouched. + # activityStore and authStore do not inherit from server.store — each falls + # back to its own SQLite file under dataDir — so repointing them at Postgres + # here would silently strand the existing audit log and the embedded IdP's + # users, with no migrate-store run to carry them over. if [[ "$ENABLE_FLOW" == "yes" ]]; then - local flow_addr="${NETBIRD_DOMAIN}" - yq eval -i " + NETBIRD_DOMAIN="$NETBIRD_DOMAIN" yq eval -i ' .server.trafficFlow.enabled = true | - .server.trafficFlow.address = \"$flow_addr\" | - .server.trafficFlow.interval = \"60s\" - " "$ENTERPRISE_CONFIG_FILE" + .server.trafficFlow.address = strenv(NETBIRD_DOMAIN) | + .server.trafficFlow.interval = "60s" + ' "$ENTERPRISE_CONFIG_FILE" fi } @@ -633,6 +761,91 @@ on_exit() { # Main # --------------------------------------------------------------------------- +# Already on Postgres: there is nothing to provision and nothing to migrate. +# The enterprise image reads the very same store config the community image +# did, so step 2 collapses to a no-op and the run is a plain image swap. +configure_existing_postgres() { + EXISTING_POSTGRES="yes" + MIGRATE_POSTGRES="no" + + # DSN first — detect_postgres_service prefers the host it names. + POSTGRES_DSN=$(detect_store_dsn) + if [[ -z "$POSTGRES_DSN" ]] || [[ "$POSTGRES_DSN" == "null" ]]; then + POSTGRES_DSN=$(detect_store_dsn_from_compose) + fi + if [[ "$POSTGRES_DSN" == "null" ]]; then + POSTGRES_DSN="" + fi + + POSTGRES_SERVICE=$(detect_postgres_service) + if [[ -n "$POSTGRES_SERVICE" ]]; then + POSTGRES_DEPENDS_CONDITION=$(detect_postgres_depends_condition) + fi + + echo "Step 2: Postgres migration not needed — this deployment already runs on" + echo " Postgres. Its store configuration is reused as-is and left" + echo " untouched; no database is created and no data is moved." + if [[ -n "$POSTGRES_SERVICE" ]]; then + echo " Postgres service: $POSTGRES_SERVICE (in $COMPOSE_FILE)" + else + echo " Postgres service: managed outside $COMPOSE_FILE" + fi +} + +configure_sqlite_store() { + MIGRATE_POSTGRES=$(read_yes_no "Step 2: Migrate storage from SQLite to Postgres? (recommended)" "n") + [[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0 + + # The override would otherwise merge into a service of the same name and + # quietly rewrite its image and credentials. + local existing + existing=$(yq eval '.services | has("postgres")' "$COMPOSE_FILE") + if [[ "$existing" == "true" ]]; then + echo "" > /dev/stderr + echo "$COMPOSE_FILE already defines a service named 'postgres', but config.yaml" > /dev/stderr + echo "still has server.store.engine: sqlite. This script would add its own" > /dev/stderr + echo "'postgres' service and Compose would merge the two." > /dev/stderr + echo "" > /dev/stderr + echo "Point server.store.engine at that Postgres yourself, or rename the service," > /dev/stderr + echo "then re-run." > /dev/stderr + exit 1 + fi + + echo "" + echo " ⚠ Data will be migrated from SQLite to Postgres. The SQLite store" + echo " will be backed up automatically. To fully revert later, restore" + echo " that backup and delete docker-compose.override.yml +" + echo " config.yaml.enterprise." + local confirm + confirm=$(read_yes_no " Continue?" "y") + if [[ "$confirm" != "yes" ]]; then + MIGRATE_POSTGRES="no" + echo " Skipping Postgres migration." + return 0 + fi + + POSTGRES_PASSWORD=$(rand_password) + POSTGRES_SERVICE="postgres" + POSTGRES_DEPENDS_CONDITION="service_healthy" + POSTGRES_DSN="host=postgres user=netbird password=${POSTGRES_PASSWORD} dbname=netbird port=5432 sslmode=disable" +} + +# mysql, or something this script has never seen. Swapping the images is still +# valid; touching the store is not. +configure_unsupported_store() { + MIGRATE_POSTGRES="no" + echo " ⚠ server.store.engine is '$STORE_ENGINE'. This script only migrates" + echo " SQLite to Postgres, and traffic flow requires Postgres, so both are" + echo " unavailable here. The store configuration will be left untouched." + echo "" + local proceed + proceed=$(read_yes_no "Step 2 skipped. Continue with the image swap only?" "n") + if [[ "$proceed" != "yes" ]]; then + echo "Aborted." + exit 0 + fi +} + init_migration() { DOCKER_COMPOSE_COMMAND=$(check_docker_compose) check_yq @@ -661,12 +874,12 @@ init_migration() { COMPOSE_NETWORK=$(detect_compose_network) if [[ -z "$COMBINED_SERVICE" ]]; then - echo "Could not find a service running netbirdio/netbird-server* in $COMPOSE_FILE." > /dev/stderr + echo "Could not find a service running netbirdio/netbird-server or ghcr.io/netbirdio/netbird-server in $COMPOSE_FILE." > /dev/stderr echo "This script targets the community combined-server deployment." > /dev/stderr exit 1 fi if [[ -z "$DASHBOARD_SERVICE" ]]; then - echo "Could not find a service running netbirdio/dashboard* in $COMPOSE_FILE." > /dev/stderr + echo "Could not find a service running netbirdio/dashboard or ghcr.io/netbirdio/dashboard in $COMPOSE_FILE." > /dev/stderr exit 1 fi if [[ -z "$CONFIG_YAML_HOST" ]]; then @@ -682,12 +895,15 @@ init_migration() { exit 1 fi + STORE_ENGINE=$(detect_store_engine) + echo "Detected existing deployment:" echo " Combined service: $COMBINED_SERVICE" echo " Dashboard: $DASHBOARD_SERVICE" echo " config.yaml: $CONFIG_YAML_HOST" echo " Data volume: $DATA_VOLUME" echo " Network: $COMPOSE_NETWORK" + echo " Store engine: $STORE_ENGINE" echo "" require_eula_acceptance @@ -706,28 +922,17 @@ init_migration() { echo "Step 1: Image swap (community → Enterprise). License key required." NB_LICENSE_KEY=$(read_secret " License key") - # Step 2 — optional + # Step 2 — what this does depends on what the deployment already stores in. echo "" - MIGRATE_POSTGRES=$(read_yes_no "Step 2: Migrate storage from SQLite to Postgres? (recommended)" "n") - if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then - echo "" - echo " ⚠ Data will be migrated from SQLite to Postgres. The SQLite store" - echo " will be backed up automatically. To fully revert later, restore" - echo " that backup and delete docker-compose.override.yml +" - echo " config.yaml.enterprise." - local confirm - confirm=$(read_yes_no " Continue?" "y") - if [[ "$confirm" != "yes" ]]; then - MIGRATE_POSTGRES="no" - echo " Skipping Postgres migration." - else - POSTGRES_PASSWORD=$(rand_password) - fi - fi + case "$STORE_ENGINE" in + postgres) configure_existing_postgres ;; + sqlite) configure_sqlite_store ;; + *) configure_unsupported_store ;; + esac # Step 3 — optional, only if Postgres is on (flow requires Postgres) echo "" - if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then + if [[ "$MIGRATE_POSTGRES" == "yes" ]] || [[ "$EXISTING_POSTGRES" == "yes" ]]; then ENABLE_FLOW=$(read_yes_no "Step 3: Enable traffic flow? (requires Postgres)" "n") if [[ "$ENABLE_FLOW" == "yes" ]]; then # Auth secret MUST match server.authSecret from config.yaml @@ -751,12 +956,46 @@ init_migration() { echo "Could not read server.store.encryptionKey from $CONFIG_YAML_HOST." > /dev/stderr exit 1 fi + + # flow-enricher talks to Postgres directly, so this is the one place an + # existing deployment's DSN is actually needed — and the one place a host + # that only works from inside the server container shows up. + while :; do + local dsn_problem="" + if [[ -z "$POSTGRES_DSN" ]]; then + dsn_problem="No DSN could be read from $CONFIG_YAML_HOST or from the $COMBINED_SERVICE environment." + elif ! dsn_host_reachable "$POSTGRES_DSN"; then + dsn_problem="Its host '$(dsn_host "$POSTGRES_DSN")' only resolves inside the server container." + fi + [[ -n "$dsn_problem" ]] || break + + echo "" + echo " The flow enricher reaches Postgres from a container of its own." + echo " $dsn_problem" + echo " Enter a DSN reachable from other containers, or press Ctrl-C to abort." + POSTGRES_DSN=$(read_required " Postgres DSN (host=… user=… password=… dbname=… port=5432 sslmode=disable)") + done + + # Only where the operator owns Postgres: a DSN entered above may name a + # different host. The sqlite path creates its own service, nothing to find. + if [[ "$EXISTING_POSTGRES" == "yes" ]]; then + POSTGRES_SERVICE=$(detect_postgres_service) + if [[ -n "$POSTGRES_SERVICE" ]]; then + POSTGRES_DEPENDS_CONDITION=$(detect_postgres_depends_condition) + fi + fi fi else ENABLE_FLOW="no" echo "Step 3 (traffic flow) skipped — requires Postgres." fi + # config.yaml.enterprise only exists to hold changes; without any there is + # nothing to generate and the server keeps running on its own config.yaml. + if [[ "$MIGRATE_POSTGRES" == "yes" ]] || [[ "$ENABLE_FLOW" == "yes" ]]; then + ENTERPRISE_CONFIG="yes" + fi + check_data_directory check_stale_postgres_volume } @@ -774,7 +1013,7 @@ apply_changes() { sed -i.bak '/NETBIRD_LICENSE_SERVER_BASE_URL/d' "$OVERRIDE_FILE" && rm -f "$OVERRIDE_FILE.bak" fi - if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then + if [[ "$ENTERPRISE_CONFIG" == "yes" ]]; then echo "Writing $ENTERPRISE_CONFIG_FILE ..." install -m 600 /dev/null "$ENTERPRISE_CONFIG_FILE" render_enterprise_config @@ -810,6 +1049,9 @@ apply_changes() { echo "POSTGRES_PASSWORD=${POSTGRES_PASSWORD}" fi if [[ "$ENABLE_FLOW" == "yes" ]]; then + # Own variable name rather than NB_STORE_ENGINE_POSTGRES_DSN so that a + # deployment already setting that one keeps its own value. + echo "NB_ENTERPRISE_POSTGRES_DSN=$(env_value "$POSTGRES_DSN")" echo "NB_FLOW_AUTH_SECRET=${NB_FLOW_AUTH_SECRET}" echo "NETBIRD_ENCRYPTION_KEY=${NETBIRD_ENCRYPTION_KEY}" fi @@ -871,14 +1113,19 @@ print_summary() { echo " Summary" echo "──────────────────────────────────────────────────────────────────────" echo " Images: swapped to enterprise" - [[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " Storage: Postgres (data migrated from SQLite)" - [[ "$MIGRATE_POSTGRES" != "yes" ]] && echo " Storage: SQLite (unchanged)" + if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then + echo " Storage: Postgres (data migrated from SQLite)" + elif [[ "$EXISTING_POSTGRES" == "yes" ]]; then + echo " Storage: Postgres (pre-existing, configuration unchanged)" + else + echo " Storage: $STORE_ENGINE (unchanged)" + fi [[ "$ENABLE_FLOW" == "yes" ]] && echo " Traffic flow: enabled" [[ "$ENABLE_FLOW" != "yes" ]] && echo " Traffic flow: disabled" echo "" echo " Generated files (next to your docker-compose.yml):" echo " $OVERRIDE_FILE" - [[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " $ENTERPRISE_CONFIG_FILE" + [[ "$ENTERPRISE_CONFIG" == "yes" ]] && echo " $ENTERPRISE_CONFIG_FILE" echo " .env (license key + secrets, mode 600)" [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]] && echo " $ENV_BACKUP (.env as it was before this run)" [[ "$MIGRATE_POSTGRES" == "yes" ]] && echo " backups/sqlite-pre-enterprise-*/ (SQLite backup)" @@ -902,7 +1149,11 @@ print_summary() { else echo " $DOCKER_COMPOSE_COMMAND down" fi - echo " rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE" + if [[ "$ENTERPRISE_CONFIG" == "yes" ]]; then + echo " rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE" + else + echo " rm -f $OVERRIDE_FILE" + fi if [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]]; then echo " mv $ENV_BACKUP .env # restores .env as it was before this run" elif [[ "$ENV_EXISTED" == "no" ]]; then diff --git a/infrastructure_files/observability/grafana/dashboards/management-enterprise.json b/infrastructure_files/observability/grafana/dashboards/management-enterprise.json new file mode 100644 index 000000000..481050a02 --- /dev/null +++ b/infrastructure_files/observability/grafana/dashboards/management-enterprise.json @@ -0,0 +1,8857 @@ +{ + "annotations": [ + { + "kind": "AnnotationQuery", + "spec": { + "builtIn": true, + "enable": true, + "hide": true, + "iconColor": "rgba(0, 211, 255, 1)", + "name": "Annotations & Alerts", + "query": { + "datasource": { + "name": "-- Grafana --" + }, + "group": "grafana", + "kind": "DataQuery", + "spec": {}, + "version": "v0" + } + } + }, + { + "kind": "AnnotationQuery", + "spec": { + "enable": true, + "hide": false, + "iconColor": "red", + "name": "Deployments", + "query": { + "datasource": { + "name": "grafana" + }, + "group": "datasource", + "kind": "DataQuery", + "spec": { + "expr": "", + "interval": "", + "refId": "Anno", + "tags": [], + "type": "tags" + }, + "version": "v0" + } + } + } + ], + "cursorSync": "Crosshair", + "editable": true, + "elements": { + "panel-1": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "exemplar": false, + "expr": "histogram_quantile(0.99, sum by(le) (rate(management_grpc_updatechannel_queue_length_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "format": "table", + "fullMetaSearch": false, + "includeNullMetadata": false, + "instant": false, + "legendFormat": "Connected grpc streams", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p99 of the update-channel queue length: how many network map updates are waiting to be delivered to a peer. The channel buffer is 100 messages - approaching it means updates start getting dropped and peers fall behind.", + "id": 1, + "links": [], + "title": "UpdateChannel Queue length max", + "vizConfig": { + "group": "stat", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 2, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "blue", + "value": 0 + }, + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 50 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-10": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_http_request_duration_ms_total_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\", type=\"read\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "HTTP read duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of read API requests (GET/OPTIONS), from the total request duration histogram tagged type=read.", + "id": 10, + "links": [], + "title": "Read HTTP API Requests p95 Duration (GET/OPTIONS)", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "orange", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-11": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_updatechannel_close_one_duration_micro_microseconds_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "CloseOne", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "sum(rate(management_updatechannel_send_duration_micro_count{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "Send", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum(rate(management_updatechannel_create_duration_micro_count{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "Create", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "C" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_updatechannel_get_all_duration_micro_count{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])*60", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GetAll", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "D" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_updatechannel_haschannel_duration_micro_count{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])*60", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "HasChannel", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "E" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_updatechannel_close_multiple_channels_count{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])*60", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "CloseMultiple", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "F" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate per minute of update-channel operations: close one, send update, create, get all connected peers, has-channel and close multiple. Together they show how much channel churn an instance is handling.", + "id": 11, + "links": [], + "title": "Update Channel operations", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 69, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "reqpm" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-12": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": true, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_updatechannel_create_duration_micro_microseconds_count{job=~\"$job\", instance=~\"$instance\", closed=\"true\"}[$__rate_interval])", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": true, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_updatechannel_create_duration_micro_microseconds_count{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "__expr__" + }, + "group": "__expr__", + "kind": "DataQuery", + "spec": { + "expression": "100-$A/$B*100", + "type": "math" + }, + "version": "v0" + }, + "refId": "C" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Tracks how often a new peer update channel replaces a channel that was still open (closed=true), i.e. peers reconnecting before management noticed the previous stream was gone. The plotted expression is 100 - recreated/total, so the line drops as recreations rise.", + "id": 12, + "links": [], + "title": "Percentage of Recreated channels", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "axisSoftMax": 100, + "axisSoftMin": 0, + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "percent" + }, + "overrides": [ + { + "matcher": { + "id": "byFrameRefID", + "options": "C" + }, + "properties": [ + { + "id": "displayName", + "value": "Recreation" + } + ] + } + ] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-13": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_close_one_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "CloseOne", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_send_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "Send", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_create_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "Create", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "C" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_get_all_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GetAll", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "D" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_haschannel_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "CloseMultiple", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "E" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_updatechannel_close_multiple_channels_bucket{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "HasChannel", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "F" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of each update-channel operation, in microseconds. These are in-memory operations behind a lock, so growth here means lock contention rather than I/O.", + "id": 13, + "links": [], + "title": "Update Channel methods p95 Duration", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "µs" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-14": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "exemplar": false, + "expr": "sum(management_grpc_connected_streams_ratio{job=~\"$job\", instance=~\"$instance\"})", + "format": "time_series", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "Connected grpc streams", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Total number of peers currently holding an open gRPC Sync stream across all management instances (management.grpc.connected.streams). A sudden drop means peers were disconnected and will come back as a Login/Sync reconnect storm.", + "id": 14, + "links": [], + "title": "Connected peers", + "vizConfig": { + "group": "stat", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "decimals": 2, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "blue", + "value": 0 + }, + { + "color": "red", + "value": 0 + }, + { + "color": "#EAB839", + "value": 8000 + }, + { + "color": "green", + "value": 11000 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "options": { + "colorMode": "background", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": true, + "textMode": "auto", + "wideLayout": true + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-15": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "management_grpc_connected_streams_ratio{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "expr": "sum by(instance) (management_grpc_connected_streams_ratio{job=~\"$job\", instance=~\"$instance\"})", + "instant": false, + "legendFormat": "Total", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Open peer Sync streams over time, in total per instance (A) and as raw series (B). Steps down mark instance restarts or LB rebalancing; the ramp back up is the reconnect wave.", + "id": 15, + "links": [], + "title": "Connected peers historical", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-16": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_grpc_sync_request_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Sync duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of the Sync gRPC request - the time management needs to authenticate the peer, build its first network map and open the update channel. Primary latency SLI for peer connects.", + "id": 16, + "links": [], + "title": "gRPC Sync Request p95 Duration", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-17": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_grpc_login_request_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Login duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of the Login gRPC request (peer authentication plus initial configuration and relay credentials). Rises when the IdP, the store or account locking is slow.", + "id": 17, + "links": [], + "title": "gRPC Login Request p95 Duration", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-18": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_account_get_peer_network_map_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the time taken to build the network map returned to a single peer, in milliseconds.", + "id": 18, + "links": [], + "title": "GetPeerNetworkMap Latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-19": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "exemplar": false, + "expr": "sum by(le) (increase(management_account_network_map_object_count_objects_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "interval": "", + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the number of objects (peers, routes, firewall rules, DNS entries and so on) in the network maps sent to clients. Large maps make both calculation and serialization more expensive.", + "id": 19, + "links": [], + "title": "NetworkMap Objects", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 0, + "reverse": false, + "unit": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-2": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(environment) (rate(management_grpc_login_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "login", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(environment) (rate(management_grpc_sync_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "sync", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(environment) (rate(management_grpc_key_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "get key", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "C" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of the three peer-facing gRPC calls: Login (authenticate, return initial config and relay credentials), Sync (open the update channel and receive network map updates) and GetServerKey (fetch the server WireGuard public key). Elevated Login/Sync rates usually mean peers are reconnecting in a loop.", + "id": 2, + "links": [], + "title": "gRPC Requests", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 51, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "reqps" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": true, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "text": {}, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-20": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_updatechannel_tosyncresponse_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the time taken to convert a calculated network map into the gRPC SyncResponse sent to the peer, in microseconds.", + "id": 20, + "links": [], + "title": "To Sync Response", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "µs" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-23": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "sum by(le) (increase(management_grpc_sync_request_duration_p95_by_account_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of per-account p95 Sync durations - each sample is one account's p95, flushed every 60s. Shows whether slow Syncs are spread across the fleet or concentrated in a few accounts.", + "id": 23, + "links": [], + "title": "GRPC Sync Latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.6, + "fill": "dark-red", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Purples", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-24": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_grpc_login_request_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of Login gRPC request durations across all peers. The right tail is what a peer experiences on startup; samples beyond 7s are what the high-latency counters in the Debugging row track.", + "id": 24, + "links": [], + "title": "GRPC Login Latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Purples", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-25": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_grpc_login_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "expr": "sum by(environment) (rate(management_grpc_login_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "instant": false, + "legendFormat": "Total", + "range": true + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of Login requests, per instance (A) and in total (B). Login is the most expensive peer call (IdP plus store writes); a sustained high rate means clients are restarting or failing to hold their Sync stream.", + "id": 25, + "links": [], + "title": "gRPC Login Request rate", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "reqps" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-26": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_grpc_sync_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "expr": "sum by(environment) (rate(management_grpc_sync_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "instant": false, + "legendFormat": "Total", + "range": true + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of Sync requests, per instance (A) and in total (B). Every Sync opens or re-opens a peer update channel, so a spike here is a reconnect storm and predicts CPU spent on network map calculation.", + "id": 26, + "links": [], + "title": "gRPC Sync Request rate", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "reqps" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-27": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_grpc_updatechannel_queue_length_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of update-channel queue lengths across all peers. Mass moving to the right shows a growing backlog of undelivered network map updates.", + "id": 27, + "links": [], + "title": "Update Channel heat map", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Greens", + "steps": 73 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-29": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(endpoint) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", method=\"GET\", code=~\"^2.+\"}[$__rate_interval])*60) > 10", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{endpoint}} > 10", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", host=\"$host\", method=\"GET\", code=~\"^2.+\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "Total", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Successful (2xx) GET requests per minute broken down by endpoint, limited to endpoints above 10 rpm. Shows which read endpoints dashboard and API clients hit hardest.", + "id": 29, + "links": [], + "title": "HTTP Read request counter", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 0, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-30": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(endpoint) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", method!~\"(GET|OPTIONS)\", code=~\"^2.+\"}[$__rate_interval])*60) > 1", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{endpoint}} > 1", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": true, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", host=\"$host\", method!~\"(GET|OPTIONS)\", code=~\"^2.+\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "Total", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Successful (2xx) non-GET/OPTIONS requests per minute by endpoint, limited to endpoints above 1 rpm. Writes take account locks and fan out network map updates, so read this together with the Network Map row.", + "id": 30, + "links": [], + "title": "HTTP Write request counter", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 0, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "reqpm" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-31": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_store_persistence_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of how long it takes to save or delete an account in the store (management.store.persistence.duration.ms). Widening buckets point at database write pressure.", + "id": 31, + "links": [], + "title": "Store Persistence latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.6, + "fill": "dark-red", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Reds", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-32": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_store_transaction_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of store transaction execution time. Nearly every API and gRPC call runs through a transaction, so this is the first place to look when latency rises everywhere at once.", + "id": 32, + "links": [], + "title": "Store Transaction latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.6, + "fill": "dark-red", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Reds", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-33": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_account_peer_meta_update_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{endpoint}} > 10", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate per minute of peers reporting changed metadata (OS, version, hostname, addresses). Each change persists the peer and can trigger an account peers update.", + "id": 33, + "links": [], + "title": "Peer meta updates counter", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 0, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "reqpm" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-34": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_grpc_sync_request_blocked_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Sync request rate", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of Sync requests rejected because the peer is blocked (login expired, peer disabled or account restricted). A rising line means clients retrying without valid access.", + "id": 34, + "links": [], + "title": "gRPC Sync Request Blocked rate", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 0 + } + ] + }, + "unit": "reqps" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-35": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_grpc_login_request_blocked_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Login request rate", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of Login requests rejected because the peer is blocked. Persistent volume here is usually expired peer logins retrying in a loop.", + "id": 35, + "links": [], + "title": "gRPC Login Request Blocked rate", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 0 + } + ] + }, + "unit": "reqps" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-36": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_account_update_account_peers_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the time taken by an account peers update: preparing the data and pushing a fresh network map to every peer in the account, in milliseconds. Scales with account size.", + "id": 36, + "links": [], + "title": "UpdateAccountPeers Latency", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-37": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_updatechannel_calc_networkmap_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the time taken to calculate one peer's network map, in milliseconds. This is the dominant CPU cost when many peers reconnect at once.", + "id": 37, + "links": [], + "title": "Network Map Calculation", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-39": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_updatechannel_calc_posturechecks_duration_micro_microseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of the time taken to evaluate a peer's posture checks while building its network map, in microseconds.", + "id": 39, + "links": [], + "title": "Posture Check Calculation", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Oranges", + "steps": 64 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "µs" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-45": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "exemplar": false, + "expr": "sort_desc(\n topk(\n 10,\n sum by (account_id) (\n increase(management_grpc_login_request_high_latency_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])\n )\n )\n)", + "format": "table", + "instant": true, + "legendFormat": "__auto", + "range": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [ + { + "group": "organize", + "kind": "Transformation", + "spec": { + "options": { + "excludeByName": { + "Time": true + }, + "includeByName": {}, + "indexByName": {}, + "renameByName": { + "Time": "" + } + } + } + } + ] + } + }, + "description": "Top 10 accounts by number of Login requests that exceeded the 7s high-latency threshold.", + "id": 45, + "links": [], + "title": "High Login Latency Ranking (login count per account)", + "vizConfig": { + "group": "table", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "filterable": false, + "footer": { + "reducers": [] + }, + "inspect": false, + "tooltip": { + "placement": "auto" + }, + "wrapHeaderText": false + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "cellHeight": "sm", + "showHeader": true, + "sortBy": [ + { + "desc": false, + "displayName": "Time" + } + ] + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-46": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "exemplar": false, + "expr": "sort_desc(\n topk(\n 10,\n sum by (account_id) (\n increase(management_grpc_sync_request_high_latency_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])\n )\n )\n)", + "format": "table", + "instant": true, + "legendFormat": "__auto", + "range": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [ + { + "group": "organize", + "kind": "Transformation", + "spec": { + "options": { + "excludeByName": { + "Time": true + }, + "includeByName": {}, + "indexByName": {}, + "renameByName": { + "Time": "" + } + } + } + } + ] + } + }, + "description": "Top 10 accounts by number of Sync requests that exceeded the 7s high-latency threshold. Use it to find which tenant is behind a latency spike.", + "id": 46, + "links": [], + "title": "High Sync Latency Ranking (sync count per account)", + "vizConfig": { + "group": "table", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "filterable": false, + "footer": { + "reducers": [] + }, + "inspect": false, + "tooltip": { + "placement": "auto" + }, + "wrapHeaderText": false + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "cellHeight": "sm", + "showHeader": true, + "sortBy": [ + { + "desc": false, + "displayName": "Time" + } + ] + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-47": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "expr": "count(\n sum by (account_id) (\n increase(management_grpc_sync_request_high_latency_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])\n ) > 1\n)", + "legendFormat": "__auto", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Number of distinct accounts with more than one slow (>7s) Sync in the interval - tells you whether a latency spike is fleet-wide or limited to a few tenants.", + "id": 47, + "links": [], + "title": "Accounts with high Sync latency", + "vizConfig": { + "group": "gauge", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "barShape": "flat", + "barWidthFactor": 0.5, + "effects": { + "barGlow": false, + "centerGlow": false, + "gradient": false + }, + "endpointMarker": "point", + "minVizHeight": 75, + "minVizWidth": 75, + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "segmentCount": 1, + "segmentSpacing": 0.3, + "shape": "gauge", + "showThresholdLabels": false, + "showThresholdMarkers": true, + "sizing": "auto", + "sparkline": false, + "textMode": "auto" + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-48": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "expr": "count(\n sum by (account_id) (\n increase(management_grpc_login_request_high_latency_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])\n ) > 1\n)", + "legendFormat": "__auto", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Number of distinct accounts with more than one slow (>7s) Login in the interval.", + "id": 48, + "links": [], + "title": "Accounts with high Login latency", + "vizConfig": { + "group": "gauge", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "barShape": "flat", + "barWidthFactor": 0.5, + "effects": { + "barGlow": false, + "centerGlow": false, + "gradient": false + }, + "endpointMarker": "point", + "minVizHeight": 75, + "minVizWidth": 75, + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "segmentCount": 1, + "segmentSpacing": 0.3, + "shape": "gauge", + "showThresholdLabels": false, + "showThresholdMarkers": true, + "sizing": "auto", + "sparkline": false, + "textMode": "auto" + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-50": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${logs_datasource}" + }, + "group": "loki", + "kind": "DataQuery", + "spec": { + "direction": "backward", + "editorMode": "code", + "expr": "sort_desc(\ntopk(\n 20,\n sum by (peerID) (\n count_over_time(\n {job=\"$log_job\"} |= \"Sync took\" | regexp `peerID:\\s(?P[^,\\]]+)` [$__range]\n )\n )\n)\n)", + "queryType": "instant" + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [ + { + "group": "organize", + "kind": "Transformation", + "spec": { + "options": { + "excludeByName": { + "Time": true + }, + "includeByName": {}, + "indexByName": {}, + "renameByName": { + "Value #A": "number of times ", + "peerID": "peerPubKey" + } + } + } + } + ] + } + }, + "description": "Top 20 peers by number of Sync log lines in the selected range, parsed out of the management logs to find individual peers stuck in a reconnect loop. Pick the log stream with the `log stream` variable; the query matches the `Sync took` debug line, so management must run at debug level for this panel to have data.", + "id": 50, + "links": [], + "title": "Highest Syncs by peer key", + "vizConfig": { + "group": "table", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "align": "auto", + "cellOptions": { + "type": "auto" + }, + "filterable": false, + "footer": { + "reducers": [] + }, + "inspect": false, + "tooltip": { + "placement": "auto" + }, + "wrapHeaderText": false + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [ + { + "matcher": { + "id": "byName", + "options": "labels" + }, + "properties": [ + { + "id": "custom.width", + "value": 180 + } + ] + }, + { + "matcher": { + "id": "byName", + "options": "peerPubKey" + }, + "properties": [ + { + "id": "custom.width", + "value": 455 + } + ] + } + ] + }, + "options": { + "cellHeight": "sm", + "showHeader": true, + "sortBy": [ + { + "desc": true, + "displayName": "number of times " + } + ] + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-52": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "expr": "wsproxy_active_connections{job=~\"$job\", instance=~\"$instance\"}", + "legendFormat": "{{__name__}}", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Currently open WebSocket proxy connections. The wsproxy fronts gRPC for browser-based clients, so this is the number of connected web clients.", + "id": 52, + "links": [], + "title": "Proxy Active Connections", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-53": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "expr": "delta(wsproxy_bytes_transferred_total{job=~\"$job\", instance=~\"$instance\"}[$__interval])", + "legendFormat": "{{direction}}", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Bytes transferred through the WebSocket proxy per interval, split by direction.", + "id": 53, + "links": [], + "title": "Proxy Traffic by Direction", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "decbytes" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-54": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "expr": "increase(wsproxy_errors_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])", + "legendFormat": "{{error_type}}", + "range": true + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "WebSocket proxy errors grouped by error type - dial failures, read/write errors and protocol issues on browser client connections.", + "id": 54, + "links": [], + "title": "Errors by Type", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [], + "displayMode": "list", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "none", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 0 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-65": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "exemplar": false, + "expr": "management_grpc_connected_streams_ratio{job=~\"$job\", instance=~\"$instance\"}", + "instant": true, + "legendFormat": "{{host}}", + "range": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Open peer Sync streams per management instance. Use it to confirm the load balancer spreads streams evenly - a skewed instance carries proportionally more update-channel and network map work.", + "id": 65, + "links": [], + "title": "Connected Peers per Server", + "vizConfig": { + "group": "gauge", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "barShape": "flat", + "barWidthFactor": 0.5, + "effects": { + "barGlow": false, + "centerGlow": false, + "gradient": false + }, + "endpointMarker": "point", + "minVizHeight": 75, + "minVizWidth": 75, + "orientation": "auto", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "segmentCount": 1, + "segmentSpacing": 0.3, + "shape": "gauge", + "showThresholdLabels": false, + "showThresholdMarkers": true, + "sizing": "auto", + "sparkline": false, + "textMode": "auto" + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-66": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(host) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", method=\"GET\", code=~\"^2.+\"}[$__rate_interval]) * 60)", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Successful GET requests per minute grouped by management instance - read load distribution across the fleet.", + "id": 66, + "links": [], + "title": "HTTP Read request counter", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 0, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Mean", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-67": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(host) (rate(management_http_response_counter_total{job=~\"$job\", instance=~\"$instance\", method!~\"(GET|OPTIONS)\", code=~\"^2.+\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Successful write requests per minute grouped by management instance - write load distribution across the fleet.", + "id": 67, + "links": [], + "title": "HTTP Write request counter", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 0, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "fieldMinMax": false, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "reqpm" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true, + "sortBy": "Last *", + "sortDesc": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-7": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_http_request_duration_ms_total_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\", type=\"write\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "HTTP write duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of write API requests (PUT/POST/DELETE), tagged type=write. Writes acquire account locks and trigger peer updates, so they are normally slower than reads.", + "id": 7, + "links": [], + "title": "Write HTTP API Requests p95 Duration (PUT/POST/DELETE)", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-74": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(le) (increase(management_pat_usage_distribution_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Distribution of personal access token usage counts, sampled once per minute per token. Mass in the high buckets means a single PAT is hammering the API.", + "id": 74, + "links": [], + "title": "PAT usage counter", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Purples", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-76": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "gnatsd_connz_subscriptions{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": true, + "legendFormat": "{{host}}", + "range": false, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Current subscriptions held by each client connected to NATS (connz). Signal instances subscribe per connected peer, so this tracks how peers are spread across signal nodes.", + "id": 76, + "links": [], + "title": "Subscriptions per node", + "vizConfig": { + "group": "stat", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-77": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "gnatsd_connz_subscriptions{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Subscriptions per connected NATS client over time. Steps mark signal instances restarting and re-subscribing their peers.", + "id": 77, + "links": [], + "title": "Subscriptions per node", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-78": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "gnatsd_connz_num_connections{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Number of client connections on each NATS node - effectively how many signal instances are attached to that node.", + "id": 78, + "links": [], + "title": "Signal nodes connected per NATs", + "vizConfig": { + "group": "stat", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "colorMode": "value", + "graphMode": "area", + "justifyMode": "auto", + "orientation": "auto", + "percentChangeColorMode": "standard", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "showPercentChange": false, + "textMode": "auto", + "wideLayout": true + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-79": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "sum by(environment) (rate(gnatsd_connz_out_msgs{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of messages NATS delivers out to its clients: the peer signalling throughput flowing through the cluster.", + "id": 79, + "links": [], + "title": "Messages per Second", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "mps" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-8": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_http_request_duration_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "HTTP request duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 duration of incoming REST API requests by endpoint and method (management.http.request.duration.ms). Covers dashboard and API clients only - peer traffic is on the gRPC panels.", + "id": 8, + "links": [], + "title": "HTTP API Requests p95 Duration", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": true, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-80": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "sum by(environment) (rate(gnatsd_connz_out_bytes{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Rate of bytes NATS delivers out to its clients - signalling bandwidth, useful next to the message rate to spot unusually large payloads.", + "id": 80, + "links": [], + "title": "Data per Second", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-81": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "sum by(environment) (increase(gnatsd_varz_slow_consumers{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval]))", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Increase of the NATS slow-consumer counter. Anything above zero means a signal node could not read fast enough and NATS dropped its connection, so peers lose signalling until it reconnects.", + "id": 81, + "links": [], + "title": "Slow consumers detected", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 80, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "decimals": 0, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "none" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [], + "displayMode": "list", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "orientation": "auto", + "showValue": "auto", + "stacking": "none", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-82": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "expr": "gnatsd_varz_subscriptions{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{host}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Total subscriptions registered on each NATS server (varz). Grows roughly with the number of connected peers.", + "id": 82, + "links": [], + "title": "Total number of NATS subscriptions", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-83": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "process_resident_memory_bytes{job=~\"$job\", instance=~\"$instance\"}", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "{{instance}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Resident memory of the scraped processes. process_resident_memory_bytes is exposed by every Go/Prometheus process, so narrow the job and instance variables to the NATS nodes to read this panel as NATS memory.", + "id": 83, + "links": [], + "title": "NATS memory consumption", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "auto", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "bytes" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "max", + "min" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-84": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "idelta(management_grpc_sync_request_duration_p95_by_account_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[2m])", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Per-account Sync p95 samples as a heatmap (2m deltas). Use it to spot a handful of large or slow accounts pulling the overall Sync latency up.", + "id": 84, + "links": [], + "title": "GRPC Sync Latency By Account", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.6, + "fill": "dark-red", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Purples", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-85": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "idelta(management_grpc_login_request_duration_p95_by_account_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[2m])", + "format": "heatmap", + "fullMetaSearch": false, + "includeNullMetadata": true, + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Per-account Login p95 samples as a heatmap (2m deltas). Highlights accounts whose logins are much slower than the fleet average.", + "id": 85, + "links": [], + "title": "GRPC Login Latency By Account", + "vizConfig": { + "group": "heatmap", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "scaleDistribution": { + "type": "linear" + } + } + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "calculate": false, + "cellGap": 1, + "color": { + "exponent": 0.5, + "fill": "dark-orange", + "mode": "scheme", + "reverse": false, + "scale": "exponential", + "scheme": "Purples", + "steps": 128 + }, + "exemplars": { + "color": "rgba(255,0,255,0.7)" + }, + "filterValues": { + "le": 1e-09 + }, + "legend": { + "placement": "bottom", + "show": true + }, + "rowsFrame": { + "layout": "auto" + }, + "tooltip": { + "mode": "single", + "showColorScale": false, + "yHistogram": false + }, + "yAxis": { + "axisPlacement": "left", + "axisWidth": 60, + "decimals": 1, + "reverse": false, + "unit": "ms" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-86": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_grpc_sync_request_duration_p95_by_account_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Sync duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 of the per-account Sync p95 distribution - the latency seen by the worst-served accounts rather than by the average request. Diverges from the global p95 when only a few accounts are hurting.", + "id": 86, + "links": [], + "title": "gRPC Sync Request p95 Duration (by Account)", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 500 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-87": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "histogram_quantile(0.95, sum by(le) (rate(management_grpc_login_request_duration_p95_by_account_ms_milliseconds_bucket{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])))", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "GRPC Login duration", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "p95 of the per-account Login p95 distribution - login latency for the worst-served accounts rather than the average request.", + "id": 87, + "links": [], + "title": "gRPC Login Request p95 Duration (by Account)", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "thresholds" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 32, + "gradientMode": "hue", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineWidth": 1, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "line" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 200 + } + ] + }, + "unit": "ms" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-88": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(environment) (increase(management_account_update_account_peers_counter_total{job=~\"$job\", instance=~\"$instance\"}[2m])) / 2", + "format": "time_series", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "interval": "", + "legendFormat": "{{environment}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Account peers updates triggered per minute (2m increase halved). Each trigger recalculates and pushes network maps to every peer in the account.", + "id": 88, + "links": [], + "title": "NetworkMap Triggers Total", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "continuous-BlYlRd", + "seriesBy": "last" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 19, + "gradientMode": "scheme", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "smooth", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "cpm" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-89": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "exemplar": false, + "expr": "sum by(resource) (increase(management_account_update_account_peers_counter_total{job=~\"$job\", instance=~\"$instance\"}[2m]))", + "format": "time_series", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "interval": "", + "legendFormat": "__auto", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Account peers updates over 2m intervals, grouped by the resource that triggered them - the time series behind the pie chart above.", + "id": 89, + "links": [], + "title": "NetworkMap Triggers By Source", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic", + "seriesBy": "max" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.9, + "drawStyle": "line", + "fillOpacity": 50, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 1, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "always", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "normal" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "cpm" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-9": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "sum by(environment) (rate(management_idp_authenticate_request_counter_total{job=~\"$job\", instance=~\"$instance\"}[$__rate_interval])*60)", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "authenticate (mgtm->auth0)", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_idp_update_user_meta_counter_total{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$interval])*60", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "update user meta", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "B" + } + }, + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "expr": "rate(management_idp_get_account_counter_total{job=~\"$job\", instance=~\"$instance\", host=\"$host\"}[$__rate_interval])*60", + "fullMetaSearch": false, + "includeNullMetadata": false, + "legendFormat": "get account", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "C" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Requests per minute that management sends to the configured identity provider: authenticate (service token refresh), user metadata updates and account lookups. IdP throttling shows up here before it shows up as Login latency.", + "id": 9, + "links": [], + "title": "IdP Requests", + "vizConfig": { + "group": "barchart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "fillOpacity": 69, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "lineWidth": 1, + "scaleDistribution": { + "type": "linear" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + } + ] + }, + "unit": "short" + }, + "overrides": [] + }, + "options": { + "barRadius": 0, + "barWidth": 0.97, + "fullHighlight": false, + "groupWidth": 0.7, + "legend": { + "calcs": [ + "lastNotNull", + "min", + "mean", + "max" + ], + "displayMode": "table", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "orientation": "auto", + "showValue": "never", + "stacking": "normal", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + }, + "xTickLabelRotation": 0, + "xTickLabelSpacing": 100 + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-90": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "code", + "exemplar": false, + "expr": "sum by(resource) (increase(management_account_update_account_peers_counter_total{job=~\"$job\", instance=~\"$instance\"}[1h]))", + "instant": true, + "legendFormat": "__auto", + "range": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Account peers updates over the last hour, grouped by the resource that triggered them (policy, group, peer, route, user, network, ...). Shows which kind of configuration change generates the most fan-out work.", + "id": 90, + "links": [], + "title": "NetworkMap Triggers by source in last hour", + "vizConfig": { + "group": "piechart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "fixedColor": "#73BF69", + "mode": "palette-classic" + }, + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + } + } + }, + "overrides": [] + }, + "options": { + "displayLabels": [ + "percent" + ], + "legend": { + "displayMode": "list", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "pieType": "donut", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "sort": "desc", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-91": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(resource) (increase(management_network_map_counter_total{job=~\"$job\", instance=~\"$instance\"}[1h]))", + "instant": true, + "legendFormat": "__auto", + "range": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Network maps computed in the last hour, grouped by the resource whose change triggered the computation.", + "id": 91, + "links": [], + "title": "NetworkMaps by source in last hour", + "vizConfig": { + "group": "piechart", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "fixedColor": "#73BF69", + "mode": "palette-classic" + }, + "custom": { + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + } + } + }, + "overrides": [] + }, + "options": { + "displayLabels": [ + "percent" + ], + "legend": { + "displayMode": "list", + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "pieType": "donut", + "reduceOptions": { + "calcs": [ + "lastNotNull" + ], + "fields": "", + "values": false + }, + "sort": "desc", + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-92": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "builder", + "exemplar": false, + "expr": "sum by(environment) (increase(management_network_map_counter_total{job=~\"$job\", instance=~\"$instance\"}[2m])) / 2", + "format": "time_series", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "interval": "", + "legendFormat": "{{environment}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Network maps computed per minute (2m increase halved). One account peers update fans out into one map per peer, so this - not the trigger count - is the real CPU driver.", + "id": 92, + "links": [], + "title": "NetworkMaps Total", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "continuous-BlYlRd", + "seriesBy": "last" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.6, + "drawStyle": "line", + "fillOpacity": 19, + "gradientMode": "scheme", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "smooth", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 2, + "pointSize": 5, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "never", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "cpm" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + }, + "panel-93": { + "kind": "Panel", + "spec": { + "data": { + "kind": "QueryGroup", + "spec": { + "queries": [ + { + "kind": "PanelQuery", + "spec": { + "hidden": false, + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "disableTextWrap": false, + "editorMode": "code", + "exemplar": false, + "expr": "sum by(resource) (increase(management_network_map_counter_total{job=~\"$job\", instance=~\"$instance\"}[2m])) / 2", + "format": "time_series", + "fullMetaSearch": false, + "includeNullMetadata": true, + "instant": false, + "interval": "", + "legendFormat": "{{resource}}", + "range": true, + "useBackend": false + }, + "version": "v0" + }, + "refId": "A" + } + } + ], + "queryOptions": {}, + "transformations": [] + } + }, + "description": "Network maps computed per minute, grouped by the resource that triggered the computation.", + "id": 93, + "links": [], + "title": "NetworkMaps Total By Source", + "vizConfig": { + "group": "timeseries", + "kind": "VizConfig", + "spec": { + "fieldConfig": { + "defaults": { + "color": { + "mode": "palette-classic", + "seriesBy": "max" + }, + "custom": { + "axisBorderShow": false, + "axisCenteredZero": false, + "axisColorMode": "text", + "axisLabel": "", + "axisPlacement": "auto", + "barAlignment": 0, + "barWidthFactor": 0.9, + "drawStyle": "line", + "fillOpacity": 0, + "gradientMode": "none", + "hideFrom": { + "legend": false, + "tooltip": false, + "viz": false + }, + "insertNulls": false, + "lineInterpolation": "linear", + "lineStyle": { + "fill": "solid" + }, + "lineWidth": 1, + "pointSize": 1, + "scaleDistribution": { + "type": "linear" + }, + "showPoints": "always", + "showValues": false, + "spanNulls": false, + "stacking": { + "group": "A", + "mode": "none" + }, + "thresholdsStyle": { + "mode": "off" + } + }, + "thresholds": { + "mode": "absolute", + "steps": [ + { + "color": "green", + "value": 0 + }, + { + "color": "red", + "value": 80 + } + ] + }, + "unit": "cpm" + }, + "overrides": [] + }, + "options": { + "annotations": { + "clustering": -1, + "multiLane": false + }, + "legend": { + "calcs": [], + "displayMode": "list", + "enableFacetedFilter": false, + "overflow": "ellipsis", + "placement": "bottom", + "showLegend": true + }, + "tooltip": { + "hideZeros": false, + "mode": "single", + "sort": "none" + } + } + }, + "version": "13.2.0-30616302309" + } + } + } + }, + "layout": { + "kind": "RowsLayout", + "spec": { + "rows": [ + { + "kind": "RowsLayoutRow", + "spec": { + "collapse": false, + "layout": { + "kind": "GridLayout", + "spec": { + "items": [ + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-14" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-65" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-15" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-2" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-23" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 16 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-24" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 16 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-16" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 24 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-17" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 24 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-84" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 32 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-85" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 32 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-86" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 40 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-87" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 40 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-26" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 48 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-25" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 48 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-34" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 56 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-35" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 56 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-31" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 64 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-32" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 64 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-9" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 72 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-8" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 72 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-29" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 80 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-30" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 80 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-66" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 88 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-67" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 88 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-10" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 96 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-7" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 96 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-33" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 104 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-74" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 104 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-11" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 112 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-13" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 112 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-12" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 120 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-1" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 120 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-27" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 128 + } + } + ] + } + }, + "title": "General" + } + }, + { + "kind": "RowsLayoutRow", + "spec": { + "collapse": true, + "layout": { + "kind": "GridLayout", + "spec": { + "items": [ + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-76" + }, + "height": 8, + "width": 24, + "x": 0, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-77" + }, + "height": 8, + "width": 24, + "x": 0, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-78" + }, + "height": 8, + "width": 24, + "x": 0, + "y": 16 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-79" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 24 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-80" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 24 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-81" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 32 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-82" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 32 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-83" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 40 + } + } + ] + } + }, + "title": "NATS" + } + }, + { + "kind": "RowsLayoutRow", + "spec": { + "collapse": true, + "layout": { + "kind": "GridLayout", + "spec": { + "items": [ + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-46" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-45" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-47" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-48" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-50" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 16 + } + } + ] + } + }, + "title": "Debugging" + } + }, + { + "kind": "RowsLayoutRow", + "spec": { + "collapse": true, + "layout": { + "kind": "GridLayout", + "spec": { + "items": [ + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-37" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-20" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 8 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-39" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 16 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-36" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 24 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-18" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 32 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-19" + }, + "height": 8, + "width": 23, + "x": 0, + "y": 40 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-90" + }, + "height": 19, + "width": 6, + "x": 0, + "y": 48 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-88" + }, + "height": 10, + "width": 17, + "x": 6, + "y": 48 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-89" + }, + "height": 9, + "width": 17, + "x": 6, + "y": 58 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-91" + }, + "height": 19, + "width": 6, + "x": 0, + "y": 67 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-92" + }, + "height": 10, + "width": 17, + "x": 6, + "y": 67 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-93" + }, + "height": 9, + "width": 17, + "x": 6, + "y": 77 + } + } + ] + } + }, + "title": "Network Map" + } + }, + { + "kind": "RowsLayoutRow", + "spec": { + "collapse": true, + "layout": { + "kind": "GridLayout", + "spec": { + "items": [ + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-52" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-53" + }, + "height": 8, + "width": 12, + "x": 12, + "y": 0 + } + }, + { + "kind": "GridLayoutItem", + "spec": { + "element": { + "kind": "ElementReference", + "name": "panel-54" + }, + "height": 8, + "width": 12, + "x": 0, + "y": 8 + } + } + ] + } + }, + "title": "Browser Client" + } + } + ] + } + }, + "links": [], + "liveNow": false, + "preload": false, + "tags": [], + "timeSettings": { + "autoRefresh": "auto", + "autoRefreshIntervals": [ + "5s", + "10s", + "30s", + "1m", + "5m", + "15m", + "30m", + "1h", + "2h", + "1d" + ], + "fiscalYearStartMonth": 0, + "from": "now-1h", + "hideTimepicker": false, + "timezone": "browser", + "to": "now" + }, + "title": "Management generic", + "variables": [ + { + "kind": "DatasourceVariable", + "spec": { + "allowCustomValue": true, + "current": { + "text": "", + "value": "" + }, + "description": "Prometheus data source scraping the management metrics.", + "hide": "dontHide", + "includeAll": false, + "label": "Data source", + "multi": false, + "name": "datasource", + "options": [], + "pluginId": "prometheus", + "refresh": "onDashboardLoad", + "regex": "", + "skipUrlSync": false + } + }, + { + "kind": "DatasourceVariable", + "spec": { + "allowCustomValue": true, + "current": { + "text": "", + "value": "" + }, + "description": "Loki data source holding the management logs.", + "hide": "dontHide", + "includeAll": false, + "label": "Logs data source", + "multi": false, + "name": "logs_datasource", + "options": [], + "pluginId": "loki", + "refresh": "onDashboardLoad", + "regex": "", + "skipUrlSync": false + } + }, + { + "kind": "QueryVariable", + "spec": { + "allValue": ".*", + "allowCustomValue": true, + "current": { + "text": "All", + "value": [ + "$__all" + ] + }, + "definition": "label_values(job)", + "description": "Prometheus scrape job(s) exposing the management metrics.", + "hide": "dontHide", + "includeAll": true, + "label": "job", + "multi": true, + "name": "job", + "options": [], + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "qryType": 1, + "query": "label_values(job)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "version": "v0" + }, + "refresh": "onDashboardLoad", + "regex": "", + "regexApplyTo": "value", + "skipUrlSync": false, + "sort": "alphabeticalAsc" + } + }, + { + "kind": "QueryVariable", + "spec": { + "allValue": ".*", + "allowCustomValue": true, + "current": { + "text": "All", + "value": [ + "$__all" + ] + }, + "definition": "label_values(up{job=~\"$job\"},instance)", + "description": "Instance(s) of the selected job(s). Depends on the job variable.", + "hide": "dontHide", + "includeAll": true, + "label": "instance", + "multi": true, + "name": "instance", + "options": [], + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "qryType": 1, + "query": "label_values(up{job=~\"$job\"},instance)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "version": "v0" + }, + "refresh": "onDashboardLoad", + "regex": "", + "regexApplyTo": "value", + "skipUrlSync": false, + "sort": "alphabeticalAsc" + } + }, + { + "kind": "QueryVariable", + "spec": { + "allowCustomValue": true, + "current": { + "text": "", + "value": "" + }, + "definition": "label_values(job)", + "description": "Loki stream carrying the management logs (adjust the label if your setup does not use `job`).", + "hide": "dontHide", + "includeAll": false, + "label": "log stream", + "multi": false, + "name": "log_job", + "options": [], + "query": { + "datasource": { + "name": "${logs_datasource}" + }, + "group": "loki", + "kind": "DataQuery", + "spec": { + "label": "job", + "refId": "LokiVariableQueryEditor-VariableQuery", + "type": 1 + }, + "version": "v0" + }, + "refresh": "onDashboardLoad", + "regex": "", + "regexApplyTo": "value", + "skipUrlSync": false, + "sort": "alphabeticalAsc" + } + }, + { + "kind": "CustomVariable", + "spec": { + "allValue": "5m", + "allowCustomValue": true, + "current": { + "text": "60s", + "value": "60s" + }, + "hide": "dontHide", + "includeAll": false, + "label": "interval", + "multi": false, + "name": "interval", + "options": [], + "query": "5m,60s", + "skipUrlSync": false, + "valuesFormat": "csv" + } + }, + { + "kind": "QueryVariable", + "spec": { + "allowCustomValue": true, + "current": { + "text": "All", + "value": "$__all" + }, + "definition": "label_values(management_store_query_count_total,method)", + "hide": "hideVariable", + "includeAll": true, + "multi": true, + "name": "method", + "options": [], + "query": { + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "qryType": 1, + "query": "label_values(management_store_query_count_total,method)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "version": "v0" + }, + "refresh": "onDashboardLoad", + "regex": "", + "regexApplyTo": "value", + "skipUrlSync": false, + "sort": "disabled" + } + }, + { + "kind": "QueryVariable", + "spec": { + "allowCustomValue": true, + "current": { + "text": "All", + "value": [ + "$__all" + ] + }, + "definition": "label_values(aws_rds_cpuutilization_average,dimension_DBClusterIdentifier)", + "hide": "hideVariable", + "includeAll": true, + "multi": true, + "name": "dimension_DBClusterIdentifier", + "options": [], + "query": { + "datasource": { + "name": "${datasource}" + }, + "group": "prometheus", + "kind": "DataQuery", + "spec": { + "qryType": 1, + "query": "label_values(aws_rds_cpuutilization_average,dimension_DBClusterIdentifier)", + "refId": "PrometheusVariableQueryEditor-VariableQuery" + }, + "version": "v0" + }, + "refresh": "onDashboardLoad", + "regex": "", + "regexApplyTo": "value", + "skipUrlSync": false, + "sort": "disabled" + } + } + ] +} diff --git a/management/internals/controllers/network_map/controller/controller.go b/management/internals/controllers/network_map/controller/controller.go index 5785004db..30de974a1 100644 --- a/management/internals/controllers/network_map/controller/controller.go +++ b/management/internals/controllers/network_map/controller/controller.go @@ -176,6 +176,7 @@ func (c *Controller) sendUpdateAccountPeers(ctx context.Context, accountID strin semaphore := make(chan struct{}, 10) c.injectAllProxyPolicies(ctx, account) + account.PrecomputePostureValidation(ctx) dnsCache := &cache.DNSConfigCache{} dnsDomain := c.GetDNSDomain(account.Settings) peersCustomZone := account.GetPeersCustomZone(ctx, dnsDomain) @@ -357,6 +358,7 @@ func (c *Controller) sendUpdateForAffectedPeers(ctx context.Context, accountID s // network map that omitted the synth DNS zone, and the agent kept // resolving against the stale or absent record. c.injectAllProxyPolicies(ctx, account) + account.PrecomputePostureValidation(ctx) dnsCache := &cache.DNSConfigCache{} dnsDomain := c.GetDNSDomain(account.Settings) peersCustomZone := account.GetPeersCustomZone(ctx, dnsDomain) @@ -649,6 +651,11 @@ func (c *Controller) GetValidatedPeerWithComponents(ctx context.Context, isRequi return nil, nil, nil, nil, 0, err } + // it's possible that the peer gets deleted between the call to "sendInitialSync()" and here, bail out in this case + if _, ok := account.Peers[peer.ID]; !ok { + return nil, nil, nil, nil, 0, fmt.Errorf("peer '%s' no longer exists", peer.ID) + } + c.injectAllProxyPolicies(ctx, account) approvedPeersMap, err := c.integratedPeerValidator.GetValidatedPeers(ctx, account.Id, maps.Values(account.Groups), maps.Values(account.Peers), account.Settings.Extra) @@ -1022,7 +1029,7 @@ func (c *Controller) OnPeersDeleted(ctx context.Context, accountID string, peerI FirewallRules: []*proto.FirewallRule{}, FirewallRulesIsEmpty: true, DNSConfig: &proto.DNSConfig{ - ForwarderPort: dnsFwdPort, + ForwarderPort: dnsFwdPort, //nolint:staticcheck }, }, }, diff --git a/management/internals/controllers/network_map/controller/controller_test.go b/management/internals/controllers/network_map/controller/controller_test.go index 90e7b6e18..dfbbb2915 100644 --- a/management/internals/controllers/network_map/controller/controller_test.go +++ b/management/internals/controllers/network_map/controller/controller_test.go @@ -1,10 +1,15 @@ package controller import ( + "context" "testing" "github.com/netbirdio/netbird/management/internals/controllers/network_map" + "github.com/netbirdio/netbird/management/server/account" nbpeer "github.com/netbirdio/netbird/management/server/peer" + "github.com/netbirdio/netbird/management/server/types" + "github.com/stretchr/testify/assert" + "go.uber.org/mock/gomock" ) func TestComputeForwarderPort(t *testing.T) { @@ -107,3 +112,22 @@ func TestComputeForwarderPort(t *testing.T) { t.Errorf("Expected %d for peers with unknown version, got %d", network_map.OldForwarderPort, result) } } + +func TestGetValidatedPeerWithComponents_DeletedPeer(t *testing.T) { + ctrl := gomock.NewController(t) + mockrequestBuffer := account.NewMockRequestBuffer(ctrl) + + c := Controller{ + requestBuffer: mockrequestBuffer, + } + + mockrequestBuffer.EXPECT().GetAccountWithBackpressure(gomock.Any(), gomock.Any()).Return(&types.Account{}, nil) + peer, components, netmap, posturechecks, dnsforwardPort, err := c.GetValidatedPeerWithComponents(context.TODO(), false, "test-account-id", &nbpeer.Peer{ID: "test-peer-id"}) + + assert.Nil(t, peer) + assert.Nil(t, components) + assert.Nil(t, netmap) + assert.Nil(t, posturechecks) + assert.Equal(t, int64(0), dnsforwardPort) + assert.NotNil(t, err) +} diff --git a/management/internals/controllers/network_map/controller/repository.go b/management/internals/controllers/network_map/controller/repository.go index c0fcefc7d..bd8ed4e80 100644 --- a/management/internals/controllers/network_map/controller/repository.go +++ b/management/internals/controllers/network_map/controller/repository.go @@ -3,14 +3,16 @@ package controller import ( "context" + "github.com/netbirdio/netbird/management/internals/modules/agentnetwork" "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service" "github.com/netbirdio/netbird/management/internals/modules/zones" - "github.com/netbirdio/netbird/management/internals/modules/agentnetwork" "github.com/netbirdio/netbird/management/server/peer" "github.com/netbirdio/netbird/management/server/store" "github.com/netbirdio/netbird/management/server/types" ) +//go:generate go tool mockgen -source=./repository.go -package=controller -destination=repository_mock.go + type Repository interface { GetAccountNetwork(ctx context.Context, accountID string) (*types.Network, error) GetAccountPeers(ctx context.Context, accountID string) ([]*peer.Peer, error) diff --git a/management/internals/controllers/network_map/controller/repository_mock.go b/management/internals/controllers/network_map/controller/repository_mock.go new file mode 100644 index 000000000..5246eef4b --- /dev/null +++ b/management/internals/controllers/network_map/controller/repository_mock.go @@ -0,0 +1,150 @@ +// Code generated by MockGen. DO NOT EDIT. +// Source: ./repository.go +// +// Generated by this command: +// +// mockgen -source=./repository.go -package=controller -destination=repository_mock.go +// + +// Package controller is a generated GoMock package. +package controller + +import ( + context "context" + reflect "reflect" + + service "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service" + zones "github.com/netbirdio/netbird/management/internals/modules/zones" + peer "github.com/netbirdio/netbird/management/server/peer" + types "github.com/netbirdio/netbird/management/server/types" + gomock "go.uber.org/mock/gomock" +) + +// MockRepository is a mock of Repository interface. +type MockRepository struct { + ctrl *gomock.Controller + recorder *MockRepositoryMockRecorder + isgomock struct{} +} + +// MockRepositoryMockRecorder is the mock recorder for MockRepository. +type MockRepositoryMockRecorder struct { + mock *MockRepository +} + +// NewMockRepository creates a new mock instance. +func NewMockRepository(ctrl *gomock.Controller) *MockRepository { + mock := &MockRepository{ctrl: ctrl} + mock.recorder = &MockRepositoryMockRecorder{mock} + return mock +} + +// EXPECT returns an object that allows the caller to indicate expected use. +func (m *MockRepository) EXPECT() *MockRepositoryMockRecorder { + return m.recorder +} + +// GetAccountByPeerID mocks base method. +func (m *MockRepository) GetAccountByPeerID(ctx context.Context, peerID string) (*types.Account, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetAccountByPeerID", ctx, peerID) + ret0, _ := ret[0].(*types.Account) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetAccountByPeerID indicates an expected call of GetAccountByPeerID. +func (mr *MockRepositoryMockRecorder) GetAccountByPeerID(ctx, peerID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountByPeerID", reflect.TypeOf((*MockRepository)(nil).GetAccountByPeerID), ctx, peerID) +} + +// GetAccountNetwork mocks base method. +func (m *MockRepository) GetAccountNetwork(ctx context.Context, accountID string) (*types.Network, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetAccountNetwork", ctx, accountID) + ret0, _ := ret[0].(*types.Network) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetAccountNetwork indicates an expected call of GetAccountNetwork. +func (mr *MockRepositoryMockRecorder) GetAccountNetwork(ctx, accountID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountNetwork", reflect.TypeOf((*MockRepository)(nil).GetAccountNetwork), ctx, accountID) +} + +// GetAccountPeers mocks base method. +func (m *MockRepository) GetAccountPeers(ctx context.Context, accountID string) ([]*peer.Peer, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetAccountPeers", ctx, accountID) + ret0, _ := ret[0].([]*peer.Peer) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetAccountPeers indicates an expected call of GetAccountPeers. +func (mr *MockRepositoryMockRecorder) GetAccountPeers(ctx, accountID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountPeers", reflect.TypeOf((*MockRepository)(nil).GetAccountPeers), ctx, accountID) +} + +// GetAccountZones mocks base method. +func (m *MockRepository) GetAccountZones(ctx context.Context, accountID string) ([]*zones.Zone, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetAccountZones", ctx, accountID) + ret0, _ := ret[0].([]*zones.Zone) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetAccountZones indicates an expected call of GetAccountZones. +func (mr *MockRepositoryMockRecorder) GetAccountZones(ctx, accountID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountZones", reflect.TypeOf((*MockRepository)(nil).GetAccountZones), ctx, accountID) +} + +// GetPeerByID mocks base method. +func (m *MockRepository) GetPeerByID(ctx context.Context, accountID, peerID string) (*peer.Peer, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetPeerByID", ctx, accountID, peerID) + ret0, _ := ret[0].(*peer.Peer) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetPeerByID indicates an expected call of GetPeerByID. +func (mr *MockRepositoryMockRecorder) GetPeerByID(ctx, accountID, peerID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerByID", reflect.TypeOf((*MockRepository)(nil).GetPeerByID), ctx, accountID, peerID) +} + +// GetPeersByIDs mocks base method. +func (m *MockRepository) GetPeersByIDs(ctx context.Context, accountID string, peerIDs []string) (map[string]*peer.Peer, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "GetPeersByIDs", ctx, accountID, peerIDs) + ret0, _ := ret[0].(map[string]*peer.Peer) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// GetPeersByIDs indicates an expected call of GetPeersByIDs. +func (mr *MockRepositoryMockRecorder) GetPeersByIDs(ctx, accountID, peerIDs any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeersByIDs", reflect.TypeOf((*MockRepository)(nil).GetPeersByIDs), ctx, accountID, peerIDs) +} + +// SynthesizeAgentNetworkServices mocks base method. +func (m *MockRepository) SynthesizeAgentNetworkServices(ctx context.Context, accountID string) ([]*service.Service, error) { + m.ctrl.T.Helper() + ret := m.ctrl.Call(m, "SynthesizeAgentNetworkServices", ctx, accountID) + ret0, _ := ret[0].([]*service.Service) + ret1, _ := ret[1].(error) + return ret0, ret1 +} + +// SynthesizeAgentNetworkServices indicates an expected call of SynthesizeAgentNetworkServices. +func (mr *MockRepositoryMockRecorder) SynthesizeAgentNetworkServices(ctx, accountID any) *gomock.Call { + mr.mock.ctrl.T.Helper() + return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SynthesizeAgentNetworkServices", reflect.TypeOf((*MockRepository)(nil).SynthesizeAgentNetworkServices), ctx, accountID) +} diff --git a/management/internals/controllers/network_map/interface.go b/management/internals/controllers/network_map/interface.go index e6e464566..b535321d1 100644 --- a/management/internals/controllers/network_map/interface.go +++ b/management/internals/controllers/network_map/interface.go @@ -1,6 +1,6 @@ package network_map -//go:generate go run go.uber.org/mock/mockgen -package network_map -destination=interface_mock.go -source=./interface.go -build_flags=-mod=mod +//go:generate go tool mockgen -package network_map -destination=interface_mock.go -source=./interface.go -build_flags=-mod=mod import ( "context" diff --git a/management/internals/modules/agentnetwork/catalog/catalog.go b/management/internals/modules/agentnetwork/catalog/catalog.go index 2c4efd0b4..3c7b995e5 100644 --- a/management/internals/modules/agentnetwork/catalog/catalog.go +++ b/management/internals/modules/agentnetwork/catalog/catalog.go @@ -113,8 +113,61 @@ type Provider struct { // upstream provider + credentials on Portkey's hosted side). ExtraHeaders []ExtraHeader Models []Model + // Discovery, when non-nil, describes how to ask this vendor which + // models the operator's own credential can actually reach, so the + // provider form can offer a live list instead of only the hand-curated + // Models above. Nil for entries with no listing endpoint (gateways + // vary too much) — those keep free-text entry. + Discovery *Discovery } +// ListingShape names the response envelope a vendor returns its model +// listing in. Every vendor invented its own, and none of them can be +// guessed from the request, so the catalog states it. +type ListingShape string + +const ( + // ShapeOpenAIData is {"data":[{"id":…}]} — OpenAI, and Anthropic, which + // adopted the same envelope. + ShapeOpenAIData ListingShape = "openai_data" + // ShapeBedrockInferenceProfiles is + // {"inferenceProfileSummaries":[{"inferenceProfileId":…}]}. The ids carry + // the region prefix that makes them invocable, which is exactly what an + // operator cannot reconstruct by hand. + ShapeBedrockInferenceProfiles ListingShape = "bedrock_inference_profiles" + // ShapeVertexPublisherModels is {"publisherModels":[{"name":…}]}, where + // name is a resource path and the invocable id is its last segment joined + // to a separate versionId field. + ShapeVertexPublisherModels ListingShape = "vertex_publisher_models" +) + +// Discovery describes one vendor's model-listing endpoint. +// +// Host is deliberately separate from the provider record's upstream URL: +// Bedrock serves listings from the control plane (bedrock.) while +// inference must go to the runtime host (bedrock-runtime.), so the +// two cannot be the same value. Empty Host means "use the record's own +// upstream", which is right for every vendor that serves both from one host. +// +// The regionPlaceholder in Host is substituted from the provider record's +// region. Deriving the discovery host from the catalog rather than accepting +// one from the caller is also what keeps this from being an open proxy: the +// only hosts management will dial are the ones written here. +type Discovery struct { + Host string + Path string + Query string + Shape ListingShape + // Headers are static headers the vendor requires beyond the credential + // (Anthropic versions its API through one and rejects a request without + // it). The auth header itself comes from AuthHeaderName/Template. + Headers map[string]string +} + +// RegionPlaceholder is replaced in Discovery.Host by the provider record's +// configured region. +const RegionPlaceholder = "" + // ExtraHeader names a single optional per-provider routing/config // header. Catalog declares N of these per provider type; the operator // fills any subset on the provider record (see Provider.ExtraValues). @@ -245,8 +298,12 @@ var providers = []Provider{ AuthHeaderTemplate: "Bearer ${API_KEY}", DefaultContentType: "application/json", BrandColor: "#10A37F", - ParserID: "openai", - PricingSurfaces: []string{"openai"}, + Discovery: &Discovery{ + Path: "/v1/models", + Shape: ShapeOpenAIData, + }, + ParserID: "openai", + PricingSurfaces: []string{"openai"}, // Pricing + context windows cross-checked against LiteLLM's // model_prices_and_context_window.json. Notable corrections from // earlier values: o4-mini repriced from $4/$16 to $1.10/$4.40 @@ -284,8 +341,18 @@ var providers = []Provider{ AuthHeaderTemplate: "${API_KEY}", DefaultContentType: "application/json", BrandColor: "#D97757", - ParserID: "anthropic", - PricingSurfaces: []string{"anthropic"}, + Discovery: &Discovery{ + Path: "/v1/models", + // The default page is short and a picker wants the whole + // catalogue in one call. + Query: "limit=1000", + Shape: ShapeOpenAIData, + // Anthropic versions its API through a header and refuses a + // request that omits it, listing included. + Headers: map[string]string{"anthropic-version": "2023-06-01"}, + }, + ParserID: "anthropic", + PricingSurfaces: []string{"anthropic"}, // Per Anthropic's current model lineup. Pricing in USD per 1k // tokens. Context windows: 4.6+ family is 1M; Haiku 4.5 stays at // 200K. claude-3-7-sonnet and claude-3-5-haiku retired @@ -296,6 +363,8 @@ var providers = []Provider{ // account to be on >= 30-day data retention or all requests // 400. Models: []Model{ + {ID: "claude-opus-5", Label: "Claude Opus 5", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, + {ID: "claude-sonnet-5", Label: "Claude Sonnet 5", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000}, {ID: "claude-fable-5", Label: "Claude Fable 5", InputPer1k: 0.010, OutputPer1k: 0.050, CacheReadPer1k: 0.001, CacheCreationPer1k: 0.0125, ContextWindow: 1000000}, {ID: "claude-opus-4-8", Label: "Claude Opus 4.8", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, {ID: "claude-opus-4-7", Label: "Claude Opus 4.7", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, @@ -343,6 +412,22 @@ var providers = []Provider{ AuthHeaderTemplate: "Bearer ${API_KEY}", DefaultContentType: "application/json", BrandColor: "#FF9900", + // Listings come from the CONTROL PLANE, not the runtime host in + // DefaultHost above: ListInferenceProfiles is not an operation + // bedrock-runtime implements, and answers + // there. Inference has to go to the runtime host, so the two hosts + // genuinely differ and Discovery.Host carries the difference. + // + // Inference profiles rather than foundation models because the profile + // id is the invocable one: it carries the region prefix (eu., us., + // global.) that AWS requires and that cannot be derived from the + // configured region — an eu-central-1 account legitimately holds + // global.* profiles. + Discovery: &Discovery{ + Host: "bedrock." + RegionPlaceholder + ".amazonaws.com", + Path: "/inference-profiles", + Shape: ShapeBedrockInferenceProfiles, + }, // ParserID stays empty (path-style dispatch via IsBedrockPathStyle); // the request parser meters these under the "bedrock" surface. PricingSurfaces: []string{"bedrock"}, @@ -355,6 +440,8 @@ var providers = []Provider{ // Llama 3.3 70B entry kept unchanged — LiteLLM tracks only // per-region Llama 3 entries; standalone 3.3 not yet listed. Models: []Model{ + {ID: "anthropic.claude-opus-5", Label: "Claude Opus 5 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, + {ID: "anthropic.claude-sonnet-5", Label: "Claude Sonnet 5 (Bedrock)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000}, {ID: "anthropic.claude-opus-4-8", Label: "Claude Opus 4.8 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, {ID: "anthropic.claude-opus-4-7", Label: "Claude Opus 4.7 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, {ID: "anthropic.claude-opus-4-6", Label: "Claude Opus 4.6 (Bedrock)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, @@ -391,6 +478,15 @@ var providers = []Provider{ AuthHeaderTemplate: "Bearer ${API_KEY}", DefaultContentType: "application/json", BrandColor: "#4285F4", + // Only the v1beta1 publisher listing answers: the v1 form and the + // project-scoped form under BOTH versions return 404. That means the + // list is publisher-global — it cannot say which models this project + // has enabled — so it is offered as a suggestion beside the catalog + // rather than replacing it. See the discovery e2e for the probes. + Discovery: &Discovery{ + Path: "/v1beta1/publishers/anthropic/models", + Shape: ShapeVertexPublisherModels, + }, // ParserID stays empty (path-style dispatch via IsVertexPathStyle); // Anthropic-on-Vertex requests are metered under the "anthropic" // surface with the bare, unversioned model id. @@ -406,6 +502,8 @@ var providers = []Provider{ // exists — the router denies unmeterable publishers rather than forward // them uncounted. Models: []Model{ + {ID: "claude-opus-5", Label: "Claude Opus 5 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, + {ID: "claude-sonnet-5", Label: "Claude Sonnet 5 (Vertex)", InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003, CacheCreationPer1k: 0.00375, ContextWindow: 1000000}, {ID: "claude-fable-5", Label: "Claude Fable 5 (Vertex)", InputPer1k: 0.010, OutputPer1k: 0.050, CacheReadPer1k: 0.001, CacheCreationPer1k: 0.0125, ContextWindow: 1000000}, {ID: "claude-opus-4-8", Label: "Claude Opus 4.8 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, {ID: "claude-opus-4-7", Label: "Claude Opus 4.7 (Vertex)", InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625, ContextWindow: 1000000}, diff --git a/management/internals/modules/agentnetwork/catalog/catalog_test.go b/management/internals/modules/agentnetwork/catalog/catalog_test.go new file mode 100644 index 000000000..e4e887e6f --- /dev/null +++ b/management/internals/modules/agentnetwork/catalog/catalog_test.go @@ -0,0 +1,36 @@ +package catalog + +import ( + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" +) + +// TestClaudeLineupSelectable pins the models Claude Code resolves to by +// default. A model absent from the lineup can't be ticked on a provider +// record, so llm_router denies it as not-routable and the operator has no +// way to authorise the client's own default. +func TestClaudeLineupSelectable(t *testing.T) { + for providerID, wanted := range map[string][]string{ + "anthropic_api": {"claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"}, + "bedrock_api": {"anthropic.claude-opus-5", "anthropic.claude-sonnet-5", "anthropic.claude-haiku-4-5"}, + "vertex_ai_api": {"claude-opus-5", "claude-sonnet-5", "claude-haiku-4-5"}, + } { + provider, ok := Lookup(providerID) + require.True(t, ok, "catalog must define %s", providerID) + + selectable := make(map[string]Model, len(provider.Models)) + for _, m := range provider.Models { + selectable[m.ID] = m + } + for _, id := range wanted { + model, found := selectable[id] + require.True(t, found, "%s must offer %s", providerID, id) + assert.NotEmpty(t, model.Label, "%s/%s needs a label for the picker", providerID, id) + assert.Positive(t, model.InputPer1k, "%s/%s needs an input rate", providerID, id) + assert.Positive(t, model.OutputPer1k, "%s/%s needs an output rate", providerID, id) + assert.Positive(t, model.ContextWindow, "%s/%s needs a context window", providerID, id) + } + } +} diff --git a/management/internals/modules/agentnetwork/handlers/budget_handler_test.go b/management/internals/modules/agentnetwork/handlers/budget_handler_test.go index 4038761c5..3a7709461 100644 --- a/management/internals/modules/agentnetwork/handlers/budget_handler_test.go +++ b/management/internals/modules/agentnetwork/handlers/budget_handler_test.go @@ -102,8 +102,8 @@ func TestSettingsHandler_GetExposesCollectionToggles(t *testing.T) { require.NoError(t, f.store.SaveAgentNetworkSettings(context.Background(), &agentNetworkTypes.Settings{ AccountID: testAccountID, - Cluster: "eu.proxy.netbird.io", - Subdomain: "violet", + Domain: "violet.eu.proxy.netbird.io", + ProxyAddress: "eu.proxy.netbird.io", EnableLogCollection: true, EnablePromptCollection: true, RedactPii: false, diff --git a/management/internals/modules/agentnetwork/handlers/handlers_test.go b/management/internals/modules/agentnetwork/handlers/handlers_test.go index 9d855c05d..6d1be3562 100644 --- a/management/internals/modules/agentnetwork/handlers/handlers_test.go +++ b/management/internals/modules/agentnetwork/handlers/handlers_test.go @@ -10,7 +10,7 @@ import ( "strings" "testing" - "github.com/golang/mock/gomock" + "go.uber.org/mock/gomock" "github.com/gorilla/mux" "github.com/stretchr/testify/assert" "github.com/stretchr/testify/require" diff --git a/management/internals/modules/agentnetwork/handlers/model_discovery_handler_test.go b/management/internals/modules/agentnetwork/handlers/model_discovery_handler_test.go new file mode 100644 index 000000000..389c2ae50 --- /dev/null +++ b/management/internals/modules/agentnetwork/handlers/model_discovery_handler_test.go @@ -0,0 +1,178 @@ +package handlers + +import ( + "context" + "encoding/json" + "fmt" + "net/http" + "net/http/httptest" + "strings" + "testing" + + "github.com/stretchr/testify/assert" + "github.com/stretchr/testify/require" + + "github.com/netbirdio/netbird/management/internals/modules/agentnetwork" + "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/modeldiscovery" + nbcontext "github.com/netbirdio/netbird/management/server/context" + "github.com/netbirdio/netbird/shared/auth" + "github.com/netbirdio/netbird/shared/management/http/api" +) + +// discoveryManagerStub records what the handler asked for and returns a canned +// answer. The Manager interface is embedded rather than implemented: only the +// one method is reachable from this handler, and a call to any other should +// fail loudly rather than silently return a zero value. +type discoveryManagerStub struct { + agentnetwork.Manager + + gotReq modeldiscovery.Request + gotRecordID string + models []modeldiscovery.Model + err error +} + +func (s *discoveryManagerStub) DiscoverProviderModels( + _ context.Context, _, _ string, req modeldiscovery.Request, recordID string, +) ([]modeldiscovery.Model, error) { + s.gotReq = req + s.gotRecordID = recordID + return s.models, s.err +} + +// postDiscovery drives the handler with an authenticated request. +func postDiscovery(t *testing.T, stub *discoveryManagerStub, body string) *httptest.ResponseRecorder { + t.Helper() + h := &handler{manager: stub} + + req := httptest.NewRequest(http.MethodPost, "/agent-network/catalog/providers/models", strings.NewReader(body)) + req = req.WithContext(nbcontext.SetUserAuthInContext(req.Context(), auth.UserAuth{ + AccountId: "acc-1", + UserId: "user-1", + })) + + rec := httptest.NewRecorder() + h.discoverProviderModels(rec, req) + return rec +} + +func TestDiscoverModelsReturnsTheVendorList(t *testing.T) { + stub := &discoveryManagerStub{models: []modeldiscovery.Model{ + {ID: "eu.anthropic.claude-haiku-4-5-20251001-v1:0", Label: "EU Claude Haiku 4.5", PricingKnown: true}, + {ID: "global.cohere.embed-v4:0", Label: "Global Cohere Embed v4"}, + // A vendor that supplies no display name at all. Bedrock does for + // every profile, but the OpenAI listing carries none. + {ID: "gpt-4o-mini", PricingKnown: true}, + }} + + rec := postDiscovery(t, stub, `{ + "catalog_provider_id":"bedrock_api", + "upstream_url":"https://bedrock-runtime.eu-central-1.amazonaws.com", + "api_key":"aws-bearer" + }`) + require.Equal(t, http.StatusOK, rec.Code, "body: %s", rec.Body.String()) + + var out api.AgentNetworkModelDiscoveryResponse + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &out)) + require.Len(t, out.Models, 3) + + assert.Equal(t, "eu.anthropic.claude-haiku-4-5-20251001-v1:0", out.Models[0].Id) + assert.True(t, out.Models[0].PricingKnown) + // An unpriced model must say so rather than arriving indistinguishable + // from a priced one: registering it silently would meter at zero. + assert.False(t, out.Models[1].PricingKnown) + + require.NotNil(t, out.Models[0].Label, "the vendor supplied a display name") + assert.Equal(t, "EU Claude Haiku 4.5", *out.Models[0].Label) + // A vendor that supplies no name must omit the key rather than send an + // empty string: the dashboard falls back to the id on absence, and would + // render a blank row for "". + assert.Nil(t, out.Models[2].Label, "an absent label must not serialize") + assert.NotContains(t, rec.Body.String(), `"label":""`) + + assert.Equal(t, "bedrock_api", stub.gotReq.CatalogID) + assert.Equal(t, "aws-bearer", stub.gotReq.APIKey) + // The upstream is what the region is read back out of for Bedrock, so + // losing it here would break discovery for every regional provider. + assert.Equal(t, "https://bedrock-runtime.eu-central-1.amazonaws.com", stub.gotReq.UpstreamURL) + assert.Empty(t, stub.gotRecordID) +} + +func TestDiscoverModelsUsesAStoredRecordWithoutAKey(t *testing.T) { + stub := &discoveryManagerStub{} + + rec := postDiscovery(t, stub, `{"catalog_provider_id":"openai_api","provider_id":"prov-42"}`) + require.Equal(t, http.StatusOK, rec.Code, "body: %s", rec.Body.String()) + + // The dashboard refreshes a saved provider's list without ever holding + // the credential, so the record id has to reach the manager. + assert.Equal(t, "prov-42", stub.gotRecordID) + assert.Empty(t, stub.gotReq.APIKey) +} + +// TestDiscoverModelsRefusesMixedCredentials covers the case where a caller +// names a saved provider AND supplies a key. Accepting it would run an +// arbitrary credential under the identity of a record the caller may only be +// permitted to read. +func TestDiscoverModelsRefusesMixedCredentials(t *testing.T) { + stub := &discoveryManagerStub{} + + rec := postDiscovery(t, stub, `{ + "catalog_provider_id":"openai_api", + "provider_id":"prov-42", + "api_key":"sk-attacker" + }`) + assert.Equal(t, http.StatusBadRequest, rec.Code) + assert.Empty(t, stub.gotRecordID, "the request must be refused before it reaches the manager") +} + +// TestDiscoverModelsReportsNoDiscoveryDistinctly matters because the caller +// falls back to the catalog's own model list on this outcome. Collapsing it +// into a generic 500 would turn "this provider has no listing endpoint" into +// "something went wrong", and the form would show an error instead of a list. +func TestDiscoverModelsReportsNoDiscoveryDistinctly(t *testing.T) { + stub := &discoveryManagerStub{err: modeldiscovery.ErrNoDiscovery} + + rec := postDiscovery(t, stub, `{"catalog_provider_id":"litellm_proxy","upstream_url":"https://gw.example.com","api_key":"sk"}`) + assert.Equal(t, http.StatusUnprocessableEntity, rec.Code) +} + +// TestDiscoverModelsTrimsTheCatalogID pins that the id the emptiness check +// accepts is the id the manager receives. A padded value that clears the check +// but reaches the catalog untrimmed misses the lookup, and the operator is told +// their provider does not exist. +func TestDiscoverModelsTrimsTheCatalogID(t *testing.T) { + stub := &discoveryManagerStub{} + + rec := postDiscovery(t, stub, `{"catalog_provider_id":" openai_api ","api_key":"sk"}`) + require.Equal(t, http.StatusOK, rec.Code, "body: %s", rec.Body.String()) + assert.Equal(t, "openai_api", stub.gotReq.CatalogID) +} + +// TestDiscoverModelsReportsCallerInputAsBadRequest covers the other half of the +// error mapping. These failures are all reachable from a well-formed request +// with a bad field value, so answering 500 both misinforms the operator and +// puts their typo into the server's error rate. +func TestDiscoverModelsReportsCallerInputAsBadRequest(t *testing.T) { + stub := &discoveryManagerStub{ + err: fmt.Errorf("%w: unknown catalog provider %q", modeldiscovery.ErrInvalidRequest, "nope"), + } + + rec := postDiscovery(t, stub, `{"catalog_provider_id":"nope","api_key":"sk"}`) + assert.Equal(t, http.StatusBadRequest, rec.Code) + assert.Contains(t, rec.Body.String(), "unknown catalog provider") +} + +func TestDiscoverModelsRejectsMalformedRequests(t *testing.T) { + for name, body := range map[string]string{ + "not json": `{`, + "no catalog provider": `{"api_key":"sk"}`, + "blank catalog provider": `{"catalog_provider_id":" ","api_key":"sk"}`, + } { + t.Run(name, func(t *testing.T) { + stub := &discoveryManagerStub{} + rec := postDiscovery(t, stub, body) + assert.Equal(t, http.StatusBadRequest, rec.Code) + }) + } +} diff --git a/management/internals/modules/agentnetwork/handlers/providers_handler.go b/management/internals/modules/agentnetwork/handlers/providers_handler.go index c05363101..645d1da61 100644 --- a/management/internals/modules/agentnetwork/handlers/providers_handler.go +++ b/management/internals/modules/agentnetwork/handlers/providers_handler.go @@ -7,6 +7,7 @@ package handlers import ( "encoding/json" + "errors" "math" "net/http" "net/url" @@ -16,6 +17,7 @@ import ( "github.com/netbirdio/netbird/management/internals/modules/agentnetwork" "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/catalog" + "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/modeldiscovery" "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/pricing" "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types" nbcontext "github.com/netbirdio/netbird/management/server/context" @@ -32,6 +34,7 @@ type handler struct { func RegisterEndpoints(manager agentnetwork.Manager, router *mux.Router) { h := &handler{manager: manager} router.HandleFunc("/agent-network/catalog/providers", h.getCatalogProviders).Methods("GET", "OPTIONS") + router.HandleFunc("/agent-network/catalog/providers/models", h.discoverProviderModels).Methods("POST", "OPTIONS") router.HandleFunc("/agent-network/providers", h.getAllProviders).Methods("GET", "OPTIONS") router.HandleFunc("/agent-network/providers", h.createProvider).Methods("POST", "OPTIONS") router.HandleFunc("/agent-network/providers/{providerId}", h.getProvider).Methods("GET", "OPTIONS") @@ -61,6 +64,98 @@ func (h *handler) getCatalogProviders(w http.ResponseWriter, r *http.Request) { util.WriteJSONObject(r.Context(), w, out) } +// discoverProviderModels asks the vendor which models the operator's own +// credential can reach, so the provider form can offer a live list rather than +// only the static catalog. +func (h *handler) discoverProviderModels(w http.ResponseWriter, r *http.Request) { + userAuth, err := nbcontext.GetUserAuthFromContext(r.Context()) + if err != nil { + util.WriteError(r.Context(), err, w) + return + } + + var body api.AgentNetworkModelDiscoveryRequest + if err := json.NewDecoder(r.Body).Decode(&body); err != nil { + util.WriteErrorResponse("invalid json", http.StatusBadRequest, w) + return + } + // Trimmed once and carried, not trimmed for the emptiness test and then + // discarded: a padded " openai_api " would clear the check here and miss + // the catalog lookup, reporting the provider as unknown. + catalogID := strings.TrimSpace(body.CatalogProviderId) + if catalogID == "" { + util.WriteErrorResponse("catalog_provider_id is required", http.StatusBadRequest, w) + return + } + + recordID := strValue(body.ProviderId) + req := modeldiscovery.Request{ + CatalogID: catalogID, + UpstreamURL: strValue(body.UpstreamUrl), + APIKey: strValue(body.ApiKey), + } + // One source of credential or the other, never a mix: taking a key from + // the request while addressing a saved record would let a caller run an + // arbitrary credential against a provider they can only read. + if recordID != "" && req.APIKey != "" { + util.WriteErrorResponse("provide either provider_id or api_key, not both", http.StatusBadRequest, w) + return + } + + models, err := h.manager.DiscoverProviderModels(r.Context(), userAuth.AccountId, userAuth.UserId, req, recordID) + if err != nil { + // A provider with no listing endpoint is a fact about the catalog + // entry, not a failure: the caller falls back to the catalog's own + // models, so it must be able to tell the two apart. + if errors.Is(err, modeldiscovery.ErrNoDiscovery) { + util.WriteErrorResponse(err.Error(), http.StatusUnprocessableEntity, w) + return + } + // An unknown provider, an unusable upstream, a missing region or a + // missing key are all things the caller sent, reachable from a + // well-formed request. Reporting them as 500 tells the operator the + // server broke and buries genuine faults in the error rate. + if errors.Is(err, modeldiscovery.ErrInvalidRequest) { + util.WriteErrorResponse(err.Error(), http.StatusBadRequest, w) + return + } + util.WriteError(r.Context(), err, w) + return + } + + out := api.AgentNetworkModelDiscoveryResponse{Models: make([]api.AgentNetworkDiscoveredModel, 0, len(models))} + for _, m := range models { + entry := api.AgentNetworkDiscoveredModel{ + Id: m.ID, + PricingKnown: m.PricingKnown, + // Sent even when zero: the form prefills every discovered model as + // an editable row, and an unpriced one is shown at zero and flagged + // rather than left out. + InputPer1k: m.InputPer1k, + OutputPer1k: m.OutputPer1k, + // Cache rates stay absent when unset, matching the catalog + // response — a zero would read as "free", not "not applicable". + CachedInputPer1k: positiveRatePtr(m.CachedInputPer1k), + CacheReadPer1k: positiveRatePtr(m.CacheReadPer1k), + CacheCreationPer1k: positiveRatePtr(m.CacheCreationPer1k), + } + if m.Label != "" { + label := m.Label + entry.Label = &label + } + out.Models = append(out.Models, entry) + } + util.WriteJSONObject(r.Context(), w, out) +} + +// strValue reads an optional string field, treating absent as empty. +func strValue(v *string) string { + if v == nil { + return "" + } + return strings.TrimSpace(*v) +} + // applyDefaultPricing overwrites the catalog response's model rates with // the LIVE default pricing table, which may differ from the compiled-in // catalog rates when the operator provides a defaults_llm_pricing.yaml. @@ -155,12 +250,7 @@ func (h *handler) createProvider(w http.ResponseWriter, r *http.Request) { provider := types.NewProvider(userAuth.AccountId) provider.FromAPIRequest(&req) - bootstrapCluster := "" - if req.BootstrapCluster != nil { - bootstrapCluster = *req.BootstrapCluster - } - - created, err := h.manager.CreateProvider(r.Context(), userAuth.UserId, provider, bootstrapCluster) + created, err := h.manager.CreateProvider(r.Context(), userAuth.UserId, provider) if err != nil { util.WriteError(r.Context(), err, w) return diff --git a/management/internals/modules/agentnetwork/handlers/settings_handler.go b/management/internals/modules/agentnetwork/handlers/settings_handler.go index 171750838..0a365f9ce 100644 --- a/management/internals/modules/agentnetwork/handlers/settings_handler.go +++ b/management/internals/modules/agentnetwork/handlers/settings_handler.go @@ -12,13 +12,55 @@ import ( "github.com/netbirdio/netbird/shared/management/http/util" ) -// addSettingsEndpoints registers the Agent Network settings routes. The -// settings row is bootstrapped server-side on first provider create or on the -// first PUT carrying a cluster; GET reads it and PUT applies a partial update -// of the mutable collection toggles (cluster/subdomain stay immutable). +// addSettingsEndpoints registers the Agent Network settings routes. POST +// bootstraps the settings row, assigning the account's immutable endpoint; +// GET reads it (defaults with an empty endpoint before bootstrap); PUT +// carries every field, replacing the mutable collection toggles and rejecting +// any change to the identity fields; DELETE removes the row — guarded so it +// stays a bootstrap-repair operation — releasing the endpoint for a fresh +// bootstrap. func (h *handler) addSettingsEndpoints(router *mux.Router) { router.HandleFunc("/agent-network/settings", h.getSettings).Methods("GET", "OPTIONS") + router.HandleFunc("/agent-network/settings", h.createSettings).Methods("POST", "OPTIONS") router.HandleFunc("/agent-network/settings", h.updateSettings).Methods("PUT", "OPTIONS") + router.HandleFunc("/agent-network/settings", h.deleteSettings).Methods("DELETE", "OPTIONS") +} + +// createSettings bootstraps the account's settings row. Exactly one of +// proxy_address (labeled endpoint; the server allocates the label) and +// endpoint (self-addressed, claimed verbatim) must be provided; optional +// collection toggles ride along with defaults for omitted fields. +func (h *handler) createSettings(w http.ResponseWriter, r *http.Request) { + userAuth, err := nbcontext.GetUserAuthFromContext(r.Context()) + if err != nil { + util.WriteError(r.Context(), err, w) + return + } + + var req api.AgentNetworkSettingsCreateRequest + if err := json.NewDecoder(r.Body).Decode(&req); err != nil { + util.WriteErrorResponse("couldn't parse JSON request", http.StatusBadRequest, w) + return + } + + settings := types.DefaultSettings(userAuth.AccountId) + settings.FromAPICreateRequest(&req) + + proxyAddress := "" + if req.ProxyAddress != nil { + proxyAddress = *req.ProxyAddress + } + endpoint := "" + if req.Endpoint != nil { + endpoint = *req.Endpoint + } + + created, err := h.manager.CreateSettings(r.Context(), userAuth.UserId, settings, proxyAddress, endpoint) + if err != nil { + util.WriteError(r.Context(), err, w) + return + } + util.WriteJSONObject(r.Context(), w, created.ToAPIResponse()) } // updateSettings replaces the mutable settings fields on the account's row. @@ -48,6 +90,24 @@ func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) { util.WriteJSONObject(r.Context(), w, updated.ToAPIResponse()) } +// deleteSettings removes the account's settings row, releasing the endpoint. +// The manager refuses (412) while providers exist or a proxy is actively +// serving the endpoint; a later POST bootstraps fresh, allocating a new +// endpoint. +func (h *handler) deleteSettings(w http.ResponseWriter, r *http.Request) { + userAuth, err := nbcontext.GetUserAuthFromContext(r.Context()) + if err != nil { + util.WriteError(r.Context(), err, w) + return + } + + if err := h.manager.DeleteSettings(r.Context(), userAuth.AccountId, userAuth.UserId); err != nil { + util.WriteError(r.Context(), err, w) + return + } + util.WriteJSONObject(r.Context(), w, util.EmptyObject{}) +} + // getSettings returns the account's agent-network settings. Accounts that // haven't been bootstrapped yet read as the defaults with an empty cluster, // subdomain and endpoint; the manager synthesises that view. diff --git a/management/internals/modules/agentnetwork/handlers/settings_handler_test.go b/management/internals/modules/agentnetwork/handlers/settings_handler_test.go index 636ec5b26..400208e1c 100644 --- a/management/internals/modules/agentnetwork/handlers/settings_handler_test.go +++ b/management/internals/modules/agentnetwork/handlers/settings_handler_test.go @@ -1,20 +1,25 @@ package handlers import ( + "context" "encoding/json" + "fmt" "net/http" + "strings" "testing" + "time" "github.com/stretchr/testify/assert" "github.com/stretchr/testify/require" + rpproxy "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy" "github.com/netbirdio/netbird/shared/management/http/api" ) // TestSettingsHandler_GetUnbootstrappedReturnsDefaults pins the settings-read // convention shared with the account and DNS settings endpoints: settings // always read as a JSON object. Before bootstrap that object carries the -// defaults with an empty cluster/subdomain/endpoint (the "not bootstrapped" +// defaults with an empty endpoint/proxy_address (the "not bootstrapped" // signal) and no timestamps — never a 404 and never the legacy null body. func TestSettingsHandler_GetUnbootstrappedReturnsDefaults(t *testing.T) { f := newAgentNetworkHandlerFixture(t) @@ -27,9 +32,9 @@ func TestSettingsHandler_GetUnbootstrappedReturnsDefaults(t *testing.T) { var got api.AgentNetworkSettings require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) - assert.Empty(t, got.Cluster, "cluster must be empty until bootstrapped") - assert.Empty(t, got.Subdomain, "subdomain must be empty until bootstrapped") - assert.Empty(t, got.Endpoint, "endpoint must be empty until bootstrapped, not a bare dot") + assert.Empty(t, got.Endpoint, "endpoint must be empty until bootstrapped") + assert.Empty(t, got.ProxyAddress, "proxy address must be empty until bootstrapped") + assert.False(t, got.Dedicated, "an unbootstrapped account has no serving shape") assert.True(t, got.EnableLogCollection, "defaults must show log collection on, matching bootstrap") assert.False(t, got.EnablePromptCollection, "defaults must show prompt collection off") assert.False(t, got.RedactPii, "defaults must show redaction off") @@ -39,62 +44,149 @@ func TestSettingsHandler_GetUnbootstrappedReturnsDefaults(t *testing.T) { assert.Nil(t, got.UpdatedAt, "no timestamps before a row exists") } -// TestSettingsHandler_PutBootstrapsWithCluster covers the settings-first -// bootstrap path: a PUT carrying a cluster on an unbootstrapped account -// creates the row (cluster pinned, subdomain assigned) and applies the -// mutable fields from the same request. -func TestSettingsHandler_PutBootstrapsWithCluster(t *testing.T) { +// TestSettingsHandler_PostBootstrapsLabeled covers the labeled bootstrap +// shape: a POST carrying a proxy_address allocates a label beneath it, so the +// endpoint hangs one label under the shared cluster's address and the pin is +// not dedicated. Toggles riding along apply; omitted ones keep defaults. +func TestSettingsHandler_PostBootstrapsLabeled(t *testing.T) { f := newAgentNetworkHandlerFixture(t) - rec := f.do(t, http.MethodPut, "/agent-network/settings", - `{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": false, "access_log_retention_days": 30}`) - require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String()) + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "enable_prompt_collection": true, "access_log_retention_days": 14}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) var got api.AgentNetworkSettings require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) - assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be pinned from the request") - assert.NotEmpty(t, got.Subdomain, "subdomain must be assigned at bootstrap") - assert.Equal(t, got.Subdomain+".eu.proxy.netbird.io", got.Endpoint, "endpoint must combine subdomain and cluster") - assert.True(t, got.EnableLogCollection, "toggle from the bootstrap request must apply") + assert.Equal(t, "eu.proxy.netbird.io", got.ProxyAddress, "proxy address must be pinned from the request") + require.NotEmpty(t, got.Endpoint, "endpoint must be allocated at bootstrap") + assert.True(t, strings.HasSuffix(got.Endpoint, ".eu.proxy.netbird.io"), + "labeled endpoint must hang off the proxy address: %s", got.Endpoint) + label := strings.TrimSuffix(got.Endpoint, ".eu.proxy.netbird.io") + assert.NotContains(t, label, ".", "the allocated label must be a single DNS label: %s", label) + assert.False(t, got.Dedicated, "a labeled pin is not dedicated") + assert.True(t, got.EnableLogCollection, "omitted toggle must keep its default") assert.True(t, got.EnablePromptCollection, "toggle from the bootstrap request must apply") require.NotNil(t, got.AccessLogRetentionDays) - assert.Equal(t, 30, *got.AccessLogRetentionDays, "retention from the bootstrap request must apply") + assert.Equal(t, 14, *got.AccessLogRetentionDays, "retention from the bootstrap request must apply") + assert.NotNil(t, got.CreatedAt, "a persisted row carries timestamps") // The row is now readable via GET. rec = f.do(t, http.MethodGet, "/agent-network/settings", "") require.Equal(t, http.StatusOK, rec.Code, "GET after bootstrap must succeed") + var read api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &read)) + assert.Equal(t, got.Endpoint, read.Endpoint, "GET must return the bootstrapped endpoint") } -// TestSettingsHandler_PutWithoutClusterOnUnbootstrapped pins that a PUT -// without a cluster cannot conjure a settings row out of nothing — there is -// no cluster to pin — and surfaces as 404 like the GET. -func TestSettingsHandler_PutWithoutClusterOnUnbootstrapped(t *testing.T) { +// TestSettingsHandler_PostBootstrapsSelfAddressed covers the dedicated shape: +// a POST carrying an endpoint claims the hostname verbatim, the proxy address +// equals it, and the pin reads as dedicated. The claim is legitimate before +// any proxy declares the address (address-first). +func TestSettingsHandler_PostBootstrapsSelfAddressed(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"endpoint": "Brave-Otter.Gateway.Example.com"}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + + var got api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) + assert.Equal(t, "brave-otter.gateway.example.com", got.Endpoint, + "endpoint must be claimed verbatim, lowercased") + assert.Equal(t, got.Endpoint, got.ProxyAddress, "self-addressed: the proxy address is the endpoint") + assert.True(t, got.Dedicated, "a self-addressed pin is dedicated") + assert.True(t, got.EnableLogCollection, "omitted toggles must keep their defaults") +} + +// TestSettingsHandler_PostRequiresExactlyOneIdentityField pins the request +// contract: proxy_address and endpoint are mutually exclusive and one is +// required — both or neither is a validation error, not a guess. +func TestSettingsHandler_PostRequiresExactlyOneIdentityField(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", `{}`) + assert.Equal(t, http.StatusUnprocessableEntity, rec.Code, + "empty POST must be rejected: got %d body=%s", rec.Code, rec.Body.String()) + + rec = f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "endpoint": "brave-otter.gateway.example.com"}`) + assert.Equal(t, http.StatusUnprocessableEntity, rec.Code, + "POST with both identity fields must be rejected: got %d body=%s", rec.Code, rec.Body.String()) +} + +// TestSettingsHandler_PostRejectsMalformedHostnames pins per-write input +// validation: shapes canonicalization cannot repair — trailing dots, embedded +// whitespace, empty labels — are rejected with a validation error instead of +// landing in an immutable column. +func TestSettingsHandler_PostRejectsMalformedHostnames(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + for name, body := range map[string]string{ + "trailing dot": `{"endpoint": "gateway.example.com."}`, + "leading dot": `{"endpoint": ".gateway.example.com"}`, + "inner whitespace": `{"endpoint": "gate way.example.com"}`, + "empty label": `{"proxy_address": "eu..proxy.netbird.io"}`, + } { + rec := f.do(t, http.MethodPost, "/agent-network/settings", body) + assert.Equal(t, http.StatusUnprocessableEntity, rec.Code, + "%s must be rejected: got %d body=%s", name, rec.Code, rec.Body.String()) + } +} + +// TestSettingsHandler_PostConflictsOnSecondBootstrap pins that bootstrap is a +// one-time create: a second POST returns 409 and leaves the row untouched. +func TestSettingsHandler_PostConflictsOnSecondBootstrap(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", `{"proxy_address": "eu.proxy.netbird.io"}`) + require.Equal(t, http.StatusOK, rec.Code, "first bootstrap must succeed: %s", rec.Body.String()) + var first api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &first)) + + rec = f.do(t, http.MethodPost, "/agent-network/settings", `{"proxy_address": "us.proxy.netbird.io"}`) + assert.Equal(t, http.StatusConflict, rec.Code, + "second bootstrap must 409: got %d body=%s", rec.Code, rec.Body.String()) + + rec = f.do(t, http.MethodGet, "/agent-network/settings", "") + require.Equal(t, http.StatusOK, rec.Code) + var got api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) + assert.Equal(t, first.Endpoint, got.Endpoint, "the original endpoint must survive the rejected bootstrap") + assert.Equal(t, first.ProxyAddress, got.ProxyAddress, "the original proxy address must survive") +} + +// TestSettingsHandler_PutBeforeBootstrapIs404 pins that a PUT cannot conjure a +// settings row out of nothing — bootstrap is the explicit POST — and the +// error points the caller there. +func TestSettingsHandler_PutBeforeBootstrapIs404(t *testing.T) { f := newAgentNetworkHandlerFixture(t) rec := f.do(t, http.MethodPut, "/agent-network/settings", `{"enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false}`) assert.Equal(t, http.StatusNotFound, rec.Code, - "cluster-less PUT on an unbootstrapped account must 404: got %d body=%s", rec.Code, rec.Body.String()) - assert.Contains(t, rec.Body.String(), "cluster", - "the error must point the caller at the bootstrap paths: %s", rec.Body.String()) + "PUT on an unbootstrapped account must 404: got %d body=%s", rec.Code, rec.Body.String()) + assert.Contains(t, rec.Body.String(), "/api/agent-network/settings", + "the error must point the caller at the bootstrap POST: %s", rec.Body.String()) } // TestSettingsHandler_PutReplacesMutableFields pins the update contract shared -// with the other PUT endpoints: the request replaces every mutable field, so a -// toggle absent from the JSON lands as its zero value rather than being -// preserved. Cluster and subdomain survive untouched. +// with the other PUT endpoints: the request carries every field, replacing the +// mutable ones. The identity fields ride along as a required echo of the +// assigned values — compared, never written — so the endpoint and proxy +// address survive every accepted update. func TestSettingsHandler_PutReplacesMutableFields(t *testing.T) { f := newAgentNetworkHandlerFixture(t) - rec := f.do(t, http.MethodPut, "/agent-network/settings", - `{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": true, "access_log_retention_days": 14}`) - require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String()) + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "enable_prompt_collection": true, "redact_pii": true, "access_log_retention_days": 14}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) var before api.AgentNetworkSettings require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before)) - rec = f.do(t, http.MethodPut, "/agent-network/settings", - `{"enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`) + rec = f.do(t, http.MethodPut, "/agent-network/settings", fmt.Sprintf( + `{"endpoint": %q, "proxy_address": %q, "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false, "access_log_retention_days": 7}`, + before.Endpoint, before.ProxyAddress)) require.Equal(t, http.StatusOK, rec.Code, "update PUT must succeed: %s", rec.Body.String()) var got api.AgentNetworkSettings @@ -103,35 +195,201 @@ func TestSettingsHandler_PutReplacesMutableFields(t *testing.T) { assert.False(t, got.EnablePromptCollection, "sent toggle must apply") assert.False(t, got.RedactPii, "sent toggle must apply") require.NotNil(t, got.AccessLogRetentionDays) - assert.Equal(t, 0, *got.AccessLogRetentionDays, - "retention absent from the request must land as the zero value — PUT replaces all mutable fields") - assert.Equal(t, before.Cluster, got.Cluster, "cluster must survive updates untouched") - assert.Equal(t, before.Subdomain, got.Subdomain, "subdomain must survive updates untouched") + assert.Equal(t, 7, *got.AccessLogRetentionDays, "sent retention must apply") + assert.Equal(t, before.Endpoint, got.Endpoint, "endpoint must survive updates untouched") + assert.Equal(t, before.ProxyAddress, got.ProxyAddress, "proxy address must survive updates untouched") } -// TestSettingsHandler_PutRejectsClusterChange pins cluster immutability: once -// assigned, a differing cluster is rejected as a validation error instead of -// being silently ignored, so callers never observe a value other than the one -// they sent. Echoing the assigned cluster back stays valid, which lets -// declarative clients send their full desired state idempotently. -func TestSettingsHandler_PutRejectsClusterChange(t *testing.T) { +// TestSettingsHandler_PutRejectsChangedIdentity pins the immutability contract: +// the PUT carries the identity fields like every other field, but they are an +// echo — a request carrying a different endpoint or proxy address is rejected +// as a validation error and the row is left untouched. The comparison is +// lenient about casing (the stored values are normalized lowercase), so a +// client replaying a GET response with different casing is not rejected. +func TestSettingsHandler_PutRejectsChangedIdentity(t *testing.T) { f := newAgentNetworkHandlerFixture(t) - rec := f.do(t, http.MethodPut, "/agent-network/settings", - `{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`) - require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String()) + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "enable_prompt_collection": true}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + var before api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before)) - rec = f.do(t, http.MethodPut, "/agent-network/settings", - `{"cluster": "us.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`) - assert.Equal(t, http.StatusUnprocessableEntity, rec.Code, - "cluster change must be rejected as a validation error: got %d body=%s", rec.Code, rec.Body.String()) + for name, body := range map[string]string{ + "changed endpoint": fmt.Sprintf( + `{"endpoint": "other.gateway.example.com", "proxy_address": %q, "enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false, "access_log_retention_days": 30}`, + before.ProxyAddress), + "changed proxy_address": fmt.Sprintf( + `{"endpoint": %q, "proxy_address": "us.proxy.netbird.io", "enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false, "access_log_retention_days": 30}`, + before.Endpoint), + "omitted identity": `{"enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false, "access_log_retention_days": 30}`, + } { + rec = f.do(t, http.MethodPut, "/agent-network/settings", body) + assert.Equal(t, http.StatusUnprocessableEntity, rec.Code, + "%s must be rejected: got %d body=%s", name, rec.Code, rec.Body.String()) + } - rec = f.do(t, http.MethodPut, "/agent-network/settings", - `{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": true}`) - require.Equal(t, http.StatusOK, rec.Code, "echoing the assigned cluster must stay valid: %s", rec.Body.String()) + // The rejected updates must not have applied anything — toggles included. + rec = f.do(t, http.MethodGet, "/agent-network/settings", "") + require.Equal(t, http.StatusOK, rec.Code) + var got api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) + assert.Equal(t, before.Endpoint, got.Endpoint, "rejected PUT must not change the endpoint") + assert.Equal(t, before.ProxyAddress, got.ProxyAddress, "rejected PUT must not change the proxy address") + assert.True(t, got.EnablePromptCollection, "rejected PUT must not apply its toggles") + + // An uppercased echo of the assigned values still names the same host and + // must be accepted. + rec = f.do(t, http.MethodPut, "/agent-network/settings", fmt.Sprintf( + `{"endpoint": %q, "proxy_address": %q, "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": false, "access_log_retention_days": 30}`, + strings.ToUpper(before.Endpoint), strings.ToUpper(before.ProxyAddress))) + assert.Equal(t, http.StatusOK, rec.Code, + "an uppercased identity echo must be accepted: got %d body=%s", rec.Code, rec.Body.String()) +} + +// TestSettingsHandler_PutOmittedRetentionLandsAsZero documents a residual the +// required-ness of access_log_retention_days does not remove. Marking the field +// required changes the generated client type from *int to int, so a generated +// client cannot omit it — but nothing validates OpenAPI required-ness at +// runtime, so a hand-rolled body without the field still decodes as 0, which +// the API documents as "keep indefinitely". +// +// That is the same latitude the three booleans already have, so it is left +// consistent rather than special-cased. This test exists to make the gap +// explicit: if request validation is ever added, this expectation is what +// changes. +func TestSettingsHandler_PutOmittedRetentionLandsAsZero(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "access_log_retention_days": 14}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + var before api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before)) + + rec = f.do(t, http.MethodPut, "/agent-network/settings", fmt.Sprintf( + `{"endpoint": %q, "proxy_address": %q, "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`, + before.Endpoint, before.ProxyAddress)) + require.Equal(t, http.StatusOK, rec.Code, "update PUT must succeed: %s", rec.Body.String()) var got api.AgentNetworkSettings require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) - assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be unchanged") - assert.True(t, got.RedactPii, "toggle sent alongside the echoed cluster must apply") + require.NotNil(t, got.AccessLogRetentionDays) + assert.Equal(t, 0, *got.AccessLogRetentionDays, + "a non-conforming body that omits retention still replaces it with the zero value") +} + +// TestSettingsHandler_DeleteBeforeBootstrapIs404 pins that DELETE on an +// account with no settings row is a 404, mirroring the PUT. +func TestSettingsHandler_DeleteBeforeBootstrapIs404(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodDelete, "/agent-network/settings", "") + assert.Equal(t, http.StatusNotFound, rec.Code, + "DELETE on an unbootstrapped account must 404: got %d body=%s", rec.Code, rec.Body.String()) +} + +// TestSettingsHandler_DeleteBlockedByProviders pins the first delete guard: +// while any provider exists for the account, the delete is refused with 412 +// and the row survives. Providers route through the endpoint — the guard +// keeps DELETE a bootstrap-repair operation rather than a way to abandon a +// configured gateway. +func TestSettingsHandler_DeleteBlockedByProviders(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", `{"proxy_address": "eu.proxy.netbird.io"}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + var before api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before)) + + f.seedProvider(t, "prov-guard") + + rec = f.do(t, http.MethodDelete, "/agent-network/settings", "") + assert.Equal(t, http.StatusPreconditionFailed, rec.Code, + "delete with a provider present must be refused: got %d body=%s", rec.Code, rec.Body.String()) + + rec = f.do(t, http.MethodGet, "/agent-network/settings", "") + require.Equal(t, http.StatusOK, rec.Code) + var got api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got)) + assert.Equal(t, before.Endpoint, got.Endpoint, "the refused delete must leave the row intact") +} + +// TestSettingsHandler_DeleteBlockedByActiveProxy pins the second delete +// guard: while a proxy is actively serving the endpoint — an active proxy +// row declaring the endpoint hostname as its cluster address, the dedicated +// shape — the delete is refused with 412. A proxy that has disconnected no +// longer blocks: the guard is about a live serving path, not history. +// +// The proxy declares its address with mixed casing on purpose: Connect +// stores the declared address verbatim while the settings row is normalized +// lowercase, and hostnames are case-insensitive, so the guard must match +// across the casing difference rather than be sidestepped by it. +func TestSettingsHandler_DeleteBlockedByActiveProxy(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + const endpoint = "gw.dedicated.example.com" + rec := f.do(t, http.MethodPost, "/agent-network/settings", fmt.Sprintf(`{"endpoint": %q}`, endpoint)) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + + now := time.Now() + accountID := testAccountID + proxyRow := &rpproxy.Proxy{ + ID: "proxy-guard", + SessionID: "sess-1", + ClusterAddress: "GW.Dedicated.Example.Com", + AccountID: &accountID, + LastSeen: now, + ConnectedAt: &now, + Status: rpproxy.StatusConnected, + } + require.NoError(t, f.store.SaveProxy(context.Background(), proxyRow)) + + rec = f.do(t, http.MethodDelete, "/agent-network/settings", "") + assert.Equal(t, http.StatusPreconditionFailed, rec.Code, + "delete with an active proxy at the endpoint must be refused: got %d body=%s", rec.Code, rec.Body.String()) + + // Once the proxy disconnects it no longer serves the endpoint, so the + // delete goes through. + require.NoError(t, f.store.DisconnectProxy(context.Background(), proxyRow.ID, proxyRow.SessionID)) + rec = f.do(t, http.MethodDelete, "/agent-network/settings", "") + assert.Equal(t, http.StatusOK, rec.Code, + "delete after the proxy disconnected must succeed: got %d body=%s", rec.Code, rec.Body.String()) +} + +// TestSettingsHandler_DeleteReleasesEndpointForFreshBootstrap pins the +// full-reset semantic that gives replace-on-change clients (e.g. Terraform's +// RequiresReplace) a real path: with both guards clear the delete succeeds, +// the account reads as the defaults again, and a fresh bootstrap draws a +// fresh label. The released hostname is not reserved — a fresh draw may even +// legitimately re-pick it — so the assertions check the new row's shape, not +// that the label differs. +func TestSettingsHandler_DeleteReleasesEndpointForFreshBootstrap(t *testing.T) { + f := newAgentNetworkHandlerFixture(t) + + rec := f.do(t, http.MethodPost, "/agent-network/settings", + `{"proxy_address": "eu.proxy.netbird.io", "enable_prompt_collection": true}`) + require.Equal(t, http.StatusOK, rec.Code, "bootstrap POST must succeed: %s", rec.Body.String()) + + rec = f.do(t, http.MethodDelete, "/agent-network/settings", "") + require.Equal(t, http.StatusOK, rec.Code, + "delete with both guards clear must succeed: got %d body=%s", rec.Code, rec.Body.String()) + + rec = f.do(t, http.MethodGet, "/agent-network/settings", "") + require.Equal(t, http.StatusOK, rec.Code) + var after api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &after)) + assert.Empty(t, after.Endpoint, "a deleted account must read as unbootstrapped defaults") + assert.False(t, after.EnablePromptCollection, "the deleted row's toggles must not linger") + + rec = f.do(t, http.MethodPost, "/agent-network/settings", `{"proxy_address": "eu.proxy.netbird.io"}`) + require.Equal(t, http.StatusOK, rec.Code, "re-bootstrap after delete must succeed: %s", rec.Body.String()) + var second api.AgentNetworkSettings + require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &second)) + require.NotEmpty(t, second.Endpoint, "the fresh bootstrap must allocate an endpoint") + assert.True(t, strings.HasSuffix(second.Endpoint, ".eu.proxy.netbird.io"), + "the fresh endpoint must hang beneath the requested proxy address: %s", second.Endpoint) + assert.False(t, second.EnablePromptCollection, + "the fresh row must carry bootstrap defaults, not the deleted row's toggles") + assert.NotNil(t, second.CreatedAt, "the fresh row is persisted and carries timestamps") } diff --git a/management/internals/modules/agentnetwork/labelgen/adjectives.go b/management/internals/modules/agentnetwork/labelgen/adjectives.go new file mode 100644 index 000000000..5058c2f1c --- /dev/null +++ b/management/internals/modules/agentnetwork/labelgen/adjectives.go @@ -0,0 +1,37 @@ +package labelgen + +// adjectives is the descriptor half of a generated label. It pairs with the +// noun pool in words.go to form `-` labels, and is kept +// separate because words.go is almost entirely nouns — drawing both halves +// from it produced unreadable pairs like "millet-hammock". Entries are +// lowercase ASCII, 4-12 chars, free of hyphens and digits, screened for +// offensive/brand/region-specific terms, and disjoint from the noun pool +// (enforced by TestAdjectives_AreDisjointFromNouns). +var adjectives = []string{ + "able", "active", "adept", "agile", "airy", "alert", "amiable", "ample", + "ancient", "ardent", "artful", "astute", "balmy", "blithe", "bold", "bonny", + "brave", "breezy", "brisk", "bubbly", "buoyant", "bushy", "candid", "canny", + "cheery", "chilly", "chipper", "chunky", "civil", "classic", "clever", "comely", + "compact", "cordial", "cosmic", "courtly", "crafty", "creamy", "crisp", "cuddly", + "curious", "dainty", "dapper", "daring", "dashing", "deft", "dewy", "diligent", + "downy", "dreamy", "dulcet", "durable", "dusky", "eager", "earnest", "earthy", + "easy", "elated", "elegant", "epic", "fabled", "faithful", "fancy", "fearless", + "feisty", "fervent", "fleet", "fluffy", "fond", "frisky", "frosty", "gallant", + "genial", "genteel", "gentle", "giddy", "gilded", "glad", "glassy", "gleaming", + "glossy", "graceful", "grand", "grainy", "hale", "hardy", "hearty", "hefty", + "honest", "hopeful", "humble", "hushed", "immense", "jaunty", "jolly", "jovial", + "joyful", "jubilant", "keen", "kindly", "kindred", "lanky", "leafy", "limber", + "lively", "lofty", "loyal", "lucent", "lucid", "luminous", "lush", "maroon", + "mellow", "merry", "mighty", "mindful", "mirthful", "misty", "modest", "muted", + "nifty", "nimble", "noble", "patient", "peaceful", "pearly", "peppy", "perky", + "petite", "placid", "playful", "pleasant", "plucky", "plush", "polite", "posh", + "prancing", "pristine", "prompt", "proud", "prudent", "quaint", "quick", "quirky", + "radiant", "ready", "regal", "restful", "robust", "rosy", "ruddy", "rugged", + "sandy", "satin", "saucy", "savvy", "sedate", "serene", "shady", "shiny", + "silken", "silky", "sincere", "sleek", "slender", "smart", "smooth", "snappy", + "snug", "soaring", "sparkly", "spiffy", "spirited", "sprightly", "spry", "stalwart", + "stately", "steady", "sterling", "stoic", "stormy", "stout", "sturdy", "sunlit", + "supple", "svelte", "tawny", "tender", "tidy", "timeless", "trusty", "upbeat", + "urbane", "valiant", "vast", "vernal", "vibrant", "vintage", "whimsy", "willing", + "windy", "winsome", "wintry", "witty", "worthy", "zesty", "zippy", +} diff --git a/management/internals/modules/agentnetwork/labelgen/labelgen.go b/management/internals/modules/agentnetwork/labelgen/labelgen.go index b45ff4ea8..549767096 100644 --- a/management/internals/modules/agentnetwork/labelgen/labelgen.go +++ b/management/internals/modules/agentnetwork/labelgen/labelgen.go @@ -64,3 +64,20 @@ func PickUnique(rng *rand.Rand, taken map[string]struct{}, fallbackSuffix string w := pool[rng.Intn(len(pool))] return fmt.Sprintf("%s-%s", w, fallbackSuffix) } + +// PickTuple returns an adjective-noun label such as "brave-otter". It is still +// a single DNS label. +// +// Unlike PickUnique it takes no `taken` set and has no fallback suffix. The +// noun pool holds 857 entries, which is ample per cluster but a hard ceiling +// once labels must be unique across one shared zone; pairing an adjective with +// a noun spans len(adjectives) * 857 instead. Uniqueness is enforced by a +// database constraint and retried by the caller, rather than guessed from a +// pre-read set that a concurrent allocation can invalidate. +func PickTuple(rng *rand.Rand) string { + nouns := uniqueWords() + if len(nouns) == 0 || len(adjectives) == 0 { + return "" + } + return adjectives[rng.Intn(len(adjectives))] + "-" + nouns[rng.Intn(len(nouns))] +} diff --git a/management/internals/modules/agentnetwork/labelgen/labelgen_test.go b/management/internals/modules/agentnetwork/labelgen/labelgen_test.go index f03a3501d..7e12fc133 100644 --- a/management/internals/modules/agentnetwork/labelgen/labelgen_test.go +++ b/management/internals/modules/agentnetwork/labelgen/labelgen_test.go @@ -99,3 +99,82 @@ func TestUniqueWords_DropsDuplicates(t *testing.T) { } assert.GreaterOrEqual(t, len(pool), 500, "Pool must contain at least 500 unique words") } + +// TestPickTuple_ShapeAndPoolMembership locks the wire-visible shape: an +// adjective and a noun, each from its own pool, joined by a single hyphen so +// the result stays one DNS label. +func TestPickTuple_ShapeAndPoolMembership(t *testing.T) { + nouns := uniqueWords() + inNouns := make(map[string]struct{}, len(nouns)) + for _, w := range nouns { + inNouns[w] = struct{}{} + } + inAdjectives := make(map[string]struct{}, len(adjectives)) + for _, a := range adjectives { + inAdjectives[a] = struct{}{} + } + + rng := rand.New(rand.NewSource(7)) + for i := 0; i < 200; i++ { + got := PickTuple(rng) + + parts := strings.Split(got, "-") + require.Len(t, parts, 2, "PickTuple must produce exactly two hyphen-joined words; got %q", got) + + _, adjOK := inAdjectives[parts[0]] + assert.True(t, adjOK, "First half must be an adjective; %q not in adjectives (from %q)", parts[0], got) + _, nounOK := inNouns[parts[1]] + assert.True(t, nounOK, "Second half must be a noun; %q not in words (from %q)", parts[1], got) + + assert.LessOrEqual(t, len(got), 63, "Label must fit a DNS label; got %q (%d chars)", got, len(got)) + } +} + +// TestAdjectives_AreDisjointFromNouns keeps the namespace a clean product and +// prevents nonsense like "azure-azure": a handful of the noun pool's entries +// are adjectival, and any overlap would let the same word land on both sides. +func TestAdjectives_AreDisjointFromNouns(t *testing.T) { + nouns := make(map[string]struct{}, len(uniqueWords())) + for _, w := range uniqueWords() { + nouns[w] = struct{}{} + } + for _, a := range adjectives { + _, clash := nouns[a] + assert.False(t, clash, "Adjective %q also appears in the noun pool; remove it from one list", a) + } +} + +// TestAdjectives_AreDNSSafeAndDeduplicated mirrors the curation contract stated +// in words.go: lowercase ASCII, 4-12 chars, no digits or hyphens, no repeats. +func TestAdjectives_AreDNSSafeAndDeduplicated(t *testing.T) { + seen := make(map[string]struct{}, len(adjectives)) + for _, a := range adjectives { + _, dup := seen[a] + assert.False(t, dup, "Duplicate adjective %q", a) + seen[a] = struct{}{} + + assert.Regexp(t, `^[a-z]{4,12}$`, a, "Adjective %q must be 4-12 lowercase ASCII letters", a) + } + assert.Greater(t, len(adjectives), 150, "Adjective pool too small to give a useful namespace") +} + +// TestPickTuple_DeterministicWithSeededRng documents that generation is a pure +// function of the rng, which is what makes allocation retries reproducible in tests. +func TestPickTuple_DeterministicWithSeededRng(t *testing.T) { + a := PickTuple(rand.New(rand.NewSource(42))) + b := PickTuple(rand.New(rand.NewSource(42))) + assert.Equal(t, a, b, "Same seed must yield the same tuple") +} + +// TestPickTuple_SpansALargeNamespace guards the reason we moved to tuples: a +// single-word pool caps the GLOBAL namespace at 857. Drawing many tuples must +// yield overwhelmingly distinct values. +func TestPickTuple_SpansALargeNamespace(t *testing.T) { + rng := rand.New(rand.NewSource(11)) + seen := make(map[string]struct{}, 2000) + for i := 0; i < 2000; i++ { + seen[PickTuple(rng)] = struct{}{} + } + assert.Greater(t, len(seen), 1900, + "2000 draws should be nearly all distinct across a ~200k namespace; got %d unique", len(seen)) +} diff --git a/management/internals/modules/agentnetwork/manager.go b/management/internals/modules/agentnetwork/manager.go index ba2c06826..41789195e 100644 --- a/management/internals/modules/agentnetwork/manager.go +++ b/management/internals/modules/agentnetwork/manager.go @@ -13,6 +13,7 @@ import ( log "github.com/sirupsen/logrus" "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/labelgen" + "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/modeldiscovery" "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types" "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy" "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/sessionkey" @@ -22,7 +23,6 @@ import ( "github.com/netbirdio/netbird/management/server/permissions/modules" "github.com/netbirdio/netbird/management/server/permissions/operations" "github.com/netbirdio/netbird/management/server/store" - "github.com/netbirdio/netbird/shared/management/proto" "github.com/netbirdio/netbird/shared/management/status" ) @@ -48,9 +48,10 @@ func ensureSessionKeys(p *types.Provider) error { type Manager interface { GetAllProviders(ctx context.Context, accountID, userID string) ([]*types.Provider, error) GetProvider(ctx context.Context, accountID, userID, providerID string) (*types.Provider, error) - CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) + CreateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) DeleteProvider(ctx context.Context, accountID, userID, providerID string) error + DiscoverProviderModels(ctx context.Context, accountID, userID string, req modeldiscovery.Request, recordID string) ([]modeldiscovery.Model, error) GetAllPolicies(ctx context.Context, accountID, userID string) ([]*types.Policy, error) GetPolicy(ctx context.Context, accountID, userID, policyID string) (*types.Policy, error) @@ -71,7 +72,9 @@ type Manager interface { DeleteBudgetRule(ctx context.Context, accountID, userID, ruleID string) error GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error) + CreateSettings(ctx context.Context, userID string, settings *types.Settings, proxyAddress, endpoint string) (*types.Settings, error) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) + DeleteSettings(ctx context.Context, accountID, userID string) error ListConsumption(ctx context.Context, accountID, userID string) ([]*types.Consumption, error) ListAccessLogs(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLog, int64, error) @@ -122,12 +125,20 @@ type managerImpl struct { permissionsManager permissions.Manager proxyController proxy.Controller + // modelDiscovery queries vendors for the models a credential can reach. + // A field rather than a package call so tests can drive it without + // reaching the network. + // + // One instance serves every request for the process's lifetime, so its + // fields must stay read-only after construction: lazy initialisation + // inside Fetch or httpClient would race across request goroutines. + modelDiscovery *modeldiscovery.Client + // reconcileCache holds the last set of synthesised proxy mappings - // per account so reconcile can emit precise Create/Update/Delete - // updates instead of a full re-push on every mutation. Keyed by - // accountID, then by synthesised service ID. + // per account, each paired with the proxy that served it, so a change + // of serving proxy can be diffed without re-deriving it. reconcileMu sync.Mutex - reconcileCache map[string]map[string]*proto.ProxyMapping + reconcileCache map[string]map[string]syntheticMapping // labelRngMu guards labelRng. PickUnique consumes math/rand.Source // state; concurrent provider creates would otherwise race. @@ -151,7 +162,8 @@ func NewManager( accountManager: accountManager, permissionsManager: permissionsManager, proxyController: proxyController, - reconcileCache: make(map[string]map[string]*proto.ProxyMapping), + modelDiscovery: &modeldiscovery.Client{}, + reconcileCache: make(map[string]map[string]syntheticMapping), labelRng: rand.New(rand.NewSource(time.Now().UnixNano())), } } @@ -170,18 +182,45 @@ func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, provid return m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, providerID) } -// CreateProvider persists a new provider for the account. bootstrapCluster -// is used only when the per-account agent-network Settings row hasn't -// been created yet; otherwise it is ignored (the cluster is pinned on -// Settings and every provider in the account routes through it). -func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) { - if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil { +// DiscoverProviderModels asks the vendor which models a credential can reach. +// +// recordID, when set, names an existing provider whose stored credential and +// upstream are used instead of the ones in req — so the dashboard can refresh +// the list without ever holding the key. +// +// Gated on Create rather than Read: this spends the operator's credential +// against a third party, which is not something a read-only role should be +// able to make the server do. That one check also covers reading the stored +// record — Create is strictly stronger than Read here, and the lookup is +// scoped to accountID, so another account's record is never reachable. +func (m *managerImpl) DiscoverProviderModels(ctx context.Context, accountID, userID string, req modeldiscovery.Request, recordID string) ([]modeldiscovery.Model, error) { + if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil { return nil, err } - if strings.TrimSpace(bootstrapCluster) != "" { - if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil { + + if recordID != "" { + record, err := m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, recordID) + if err != nil { return nil, err } + // The catalog id comes from the stored record too: letting the caller + // name a different one would run a provider's credential against + // whichever vendor endpoint they picked. + req.CatalogID = record.ProviderID + req.UpstreamURL = record.UpstreamURL + req.APIKey = record.APIKey + } + + return m.modelDiscovery.Fetch(ctx, req) +} + +// CreateProvider persists a new provider for the account. Providers have no +// settings side effects: the account's endpoint is bootstrapped separately and +// explicitly via CreateSettings, and every provider in the account routes +// through it. +func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) { + if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil { + return nil, err } // An empty api_key would silently produce a synthesised service @@ -206,16 +245,6 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide return nil, fmt.Errorf("save agent network provider: %w", err) } - if strings.TrimSpace(bootstrapCluster) != "" { - if _, err := m.bootstrapSettingsIfNeeded(ctx, m.store, provider.AccountID, bootstrapCluster); err != nil { - // The provider create has already succeeded; logging the - // bootstrap miss matches the plan's PoC behaviour. The synth - // path treats a missing settings row as a no-op, and the next - // provider create retries the bootstrap. - log.WithContext(ctx).Debugf("agent-network bootstrap settings for account %s on cluster %s: %v", provider.AccountID, bootstrapCluster, err) - } - } - m.accountManager.StoreEvent(ctx, userID, provider.ID, provider.AccountID, activity.AgentNetworkProviderCreated, provider.EventMeta()) m.reconcile(ctx, provider.AccountID) @@ -560,52 +589,44 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r } // UpdateSettings replaces the mutable account-level settings — the collection -// toggles and retention — on the account's row. When the account has no -// settings row yet, a non-empty settings.Cluster bootstraps one (same path as -// first provider create); without it the update fails with NotFound. On an -// existing row the cluster and subdomain are immutable: a differing -// settings.Cluster is rejected rather than silently ignored so callers never -// observe a value other than what they sent. Because the collection toggles -// change the synthesised service config (prompt-capture gating, access-log -// emission), a reconcile is triggered so the proxy and peer network maps -// converge on the new state. +// toggles and retention — on the account's row. The identity fields (Domain, +// ProxyAddress) are assigned at bootstrap (CreateSettings) and immutable: the +// request carries them, matching the PUT convention of every other endpoint, +// but they are only compared against the stored row — a request carrying +// different values is rejected, and the stored values are never overwritten. +// When the account has no settings row yet the update fails with NotFound. +// Because the collection toggles change the synthesised service config +// (prompt-capture gating, access-log emission), a reconcile is triggered so +// the proxy and peer network maps converge on the new state. func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) { if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Update); err != nil { return nil, err } - requestedCluster := strings.TrimSpace(settings.Cluster) - // The row lock from LockingStrengthUpdate only holds for the duration of - // the surrounding transaction, so the read, the cluster-immutability - // check, and the save must share one — otherwise concurrent PUTs could - // interleave between them. + // the surrounding transaction, so the read and the save must share one — + // otherwise concurrent PUTs could interleave between them. var updated *types.Settings err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error { existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID) switch { case err == nil: - if requestedCluster != "" && requestedCluster != existing.Cluster { - return status.Errorf(status.InvalidArgument, "cluster is immutable once assigned (current: %s)", existing.Cluster) - } case isNotFound(err): - if requestedCluster == "" { - return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; pass cluster to bootstrap them, or create a provider with bootstrap_cluster set") - } - // Bootstrapping pins the cluster and subdomain — a settings - // create on top of the update the caller already passed, matching - // the gate on the provider-create bootstrap path. - if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil { - return err - } - existing, err = m.bootstrapSettingsIfNeeded(ctx, tx, settings.AccountID, requestedCluster) - if err != nil { - return err - } + return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; POST /api/agent-network/settings to bootstrap them") default: return fmt.Errorf("get agent network settings: %w", err) } + // The identity echo is compared leniently (trimmed, case-insensitive): + // the stored values are normalized lowercase, and a client replaying a + // GET response must never be rejected over casing it didn't choose. + if !hostnamesEquivalent(settings.Domain, existing.Domain) { + return status.Errorf(status.InvalidArgument, "endpoint is immutable: it must match the assigned endpoint %q; delete the settings to release it and bootstrap again", existing.Domain) + } + if !hostnamesEquivalent(settings.ProxyAddress, existing.ProxyAddress) { + return status.Errorf(status.InvalidArgument, "proxy_address is immutable: it must match the assigned proxy address %q; delete the settings to release it and bootstrap again", existing.ProxyAddress) + } + existing.EnableLogCollection = settings.EnableLogCollection existing.EnablePromptCollection = settings.EnablePromptCollection existing.RedactPii = settings.RedactPii @@ -632,6 +653,83 @@ func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, setting return updated, nil } +// hostnamesEquivalent reports whether a caller-supplied hostname names the +// same host as a stored (normalized, lowercase) one: equal after trimming and +// case folding. No structural validation — an arbitrary mismatch and a +// malformed value are both simply "not the assigned value". +func hostnamesEquivalent(supplied, stored string) bool { + return strings.EqualFold(strings.TrimSpace(supplied), stored) +} + +// DeleteSettings removes the account's settings row, releasing the endpoint. +// Two guards make this a bootstrap-repair operation rather than a way to tear +// down a serving gateway, both re-checked under the row lock: +// +// - No Agent Network providers may exist for the account. Providers route +// through the endpoint; delete them first. +// - No proxy may be actively serving the endpoint — that is, no active proxy +// declares the endpoint hostname as its cluster address. This is the +// dedicated (self-addressed) shape's guard: the proxy at the address IS +// this account's gateway. A labeled endpoint hangs beneath a shared +// cluster's address, and with the account's providers already gone the +// shared proxy serves nothing of the account's, so the parent cluster +// being up does not block the delete. +// +// Bootstrapping again after a delete allocates fresh — the released hostname +// is not reserved. That full-reset semantic is what gives clients that model +// immutability as replace-on-change (e.g. Terraform's RequiresReplace) a real +// path: tear down providers, delete, re-create. +func (m *managerImpl) DeleteSettings(ctx context.Context, accountID, userID string) error { + if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Delete); err != nil { + return err + } + + var deleted *types.Settings + err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error { + existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, accountID) + switch { + case err == nil: + case isNotFound(err): + return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; there is nothing to delete") + default: + return fmt.Errorf("get agent network settings: %w", err) + } + + providers, err := tx.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, accountID) + if err != nil { + return fmt.Errorf("get agent network providers: %w", err) + } + if len(providers) > 0 { + return status.Errorf(status.PreconditionFailed, "agent network settings cannot be deleted while %d provider(s) exist; delete the providers first", len(providers)) + } + + serving, err := tx.HasActiveProxyAtClusterAddress(ctx, existing.Domain) + if err != nil { + return fmt.Errorf("check for a proxy serving the endpoint: %w", err) + } + if serving { + return status.Errorf(status.PreconditionFailed, "agent network settings cannot be deleted while a proxy is actively serving the endpoint %q", existing.Domain) + } + + if err := tx.DeleteAgentNetworkSettings(ctx, accountID); err != nil { + return fmt.Errorf("delete agent network settings: %w", err) + } + deleted = existing + return nil + }) + if err != nil { + return err + } + + m.accountManager.StoreEvent(ctx, userID, accountID, accountID, activity.AgentNetworkSettingsDeleted, map[string]any{ + "endpoint": deleted.Domain, + "proxy_address": deleted.ProxyAddress, + }) + m.reconcile(ctx, accountID) + + return nil +} + // isNotFound reports whether err is a status.NotFound error. func isNotFound(err error) bool { var sErr *status.Error @@ -678,74 +776,162 @@ func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string) } } -// requireSettingsBootstrapPermission gates the one-time settings bootstrap a -// first provider create performs. Pinning the account's cluster and subdomain -// is a settings write, so it needs the settings permission on top of the -// provider one. No-op once the settings row exists. -func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, accountID, userID string) error { - _, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID) - if err == nil { - return nil - } - if !isNotFound(err) { - return fmt.Errorf("get agent network settings: %w", err) - } - return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create) -} +// maxDomainAllocationAttempts bounds the label search when bootstrapping a +// labeled endpoint. Package-level (rather than function-local) so tests can +// assert on the exhaustion path without duplicating the literal. +const maxDomainAllocationAttempts = 10 -// bootstrapSettingsIfNeeded creates the per-account agent-network -// settings row when missing. The cluster comes from the create-time -// hint the dashboard sends (auto-picked from the active cluster list); -// the subdomain is picked from the curated wordlist avoiding -// collisions on the same cluster. Idempotent: if a row already exists -// it is returned untouched and the hint is ignored. st is the store to -// operate on — pass the transaction store when calling from within one. -func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.Store, accountID, providerCluster string) (*types.Settings, error) { - if accountID == "" { - return nil, fmt.Errorf("bootstrap settings: account id is required") +// CreateSettings bootstraps the per-account settings row, assigning the +// account's immutable endpoint. Exactly one of proxyAddress and endpoint must +// be non-empty: proxyAddress allocates a labeled endpoint one label beneath +// the given cluster address; endpoint claims the given hostname verbatim as a +// self-addressed (dedicated) endpoint — a legitimate claim before any proxy +// declares the address (address-first). settings carries the account ID and +// the initial collection toggles; its identity fields are assigned here. +func (m *managerImpl) CreateSettings(ctx context.Context, userID string, settings *types.Settings, proxyAddress, endpoint string) (*types.Settings, error) { + if settings == nil || settings.AccountID == "" { + return nil, status.Errorf(status.InvalidArgument, "account id is required") } - if strings.TrimSpace(providerCluster) == "" { - return nil, fmt.Errorf("bootstrap settings: provider cluster is required") + if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil { + return nil, err } - existing, err := st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID) - if err == nil { - return existing, nil + hasProxyAddress := strings.TrimSpace(proxyAddress) != "" + hasEndpoint := strings.TrimSpace(endpoint) != "" + if hasProxyAddress == hasEndpoint { + return nil, status.Errorf(status.InvalidArgument, "exactly one of proxy_address and endpoint is required") } - if !isNotFound(err) { + + // Fail fast on an existing row for a clean 409; the insert below stays + // the authority against concurrent bootstraps (the primary key wins). + if _, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, settings.AccountID); err == nil { + return nil, status.Errorf(status.AlreadyExists, "agent network settings already bootstrapped for account %s", settings.AccountID) + } else if !isNotFound(err) { return nil, fmt.Errorf("get agent network settings: %w", err) } - siblings, err := st.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster) - if err != nil { - return nil, fmt.Errorf("list agent network settings on cluster: %w", err) - } - taken := make(map[string]struct{}, len(siblings)) - for _, s := range siblings { - taken[s.Subdomain] = struct{}{} - } - - suffix := accountID - if len(suffix) > 4 { - suffix = suffix[:4] - } - - m.labelRngMu.Lock() - subdomain := labelgen.PickUnique(m.labelRng, taken, suffix) - m.labelRngMu.Unlock() - now := time.Now().UTC() - settings := types.DefaultSettings(accountID) - settings.Cluster = providerCluster - settings.Subdomain = subdomain settings.CreatedAt = now settings.UpdatedAt = now - if err := st.SaveAgentNetworkSettings(ctx, settings); err != nil { - return nil, fmt.Errorf("save agent network settings: %w", err) + + var err error + if hasEndpoint { + err = m.bootstrapSelfAddressed(ctx, settings, endpoint) + } else { + err = m.bootstrapLabeled(ctx, settings, proxyAddress) } + if err != nil { + return nil, err + } + + m.accountManager.StoreEvent(ctx, userID, settings.AccountID, settings.AccountID, activity.AgentNetworkSettingsUpdated, map[string]any{ + "bootstrapped": true, + "endpoint": settings.Domain, + "dedicated": settings.Dedicated(), + }) + m.reconcile(ctx, settings.AccountID) + return settings, nil } +// bootstrapSelfAddressed claims the given hostname as the account's endpoint, +// served only by a proxy declaring exactly that address (Domain == +// ProxyAddress). The domain unique index is the arbiter of availability. +func (m *managerImpl) bootstrapSelfAddressed(ctx context.Context, settings *types.Settings, endpoint string) error { + hostname, err := types.NormalizeHostname(endpoint) + if err != nil { + return status.Errorf(status.InvalidArgument, "invalid endpoint: %s", err) + } + + settings.Domain = hostname + settings.ProxyAddress = hostname + if err := m.store.CreateAgentNetworkSettings(ctx, settings); err != nil { + if isUniqueConstraintError(err) { + // The violation is either the account primary key (a concurrent + // bootstrap for the same account won) or the domain index + // (another account holds the hostname). Distinguish by re-read. + if _, getErr := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, settings.AccountID); getErr == nil { + return status.Errorf(status.AlreadyExists, "agent network settings already bootstrapped for account %s", settings.AccountID) + } + return status.Errorf(status.AlreadyExists, "endpoint %s is already taken", hostname) + } + return fmt.Errorf("create agent network settings: %w", err) + } + return nil +} + +// bootstrapLabeled allocates a labeled endpoint one label beneath the given +// cluster address: Domain =