mirror of
https://github.com/netbirdio/netbird.git
synced 2026-08-11 18:21:29 +02:00
Compare commits
2 Commits
agent-netw
...
debug-ui-m
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
baac630f43 | ||
|
|
16c119309d |
133
.github/workflows/release.yml
vendored
133
.github/workflows/release.yml
vendored
@@ -475,132 +475,6 @@ jobs:
|
||||
path: dist/
|
||||
retention-days: 3
|
||||
|
||||
release_ui_gtk3:
|
||||
# Legacy GTK3/WebKit2GTK 4.1 UI build for distros without WebKitGTK 6.0
|
||||
# (Ubuntu 22.04, Debian 12, RHEL 9, Fedora <=39). Runs on ubuntu-22.04 so
|
||||
# the binary links against the oldest supported glibc.
|
||||
runs-on: ubuntu-22.04
|
||||
outputs:
|
||||
release_ui_gtk3_artifact_url: ${{ steps.upload_release_ui_gtk3.outputs.artifact-url }}
|
||||
steps:
|
||||
- name: Checkout
|
||||
uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
|
||||
with:
|
||||
fetch-depth: 0 # It is required for GoReleaser to work properly
|
||||
persist-credentials: false
|
||||
|
||||
- name: Parse semver string
|
||||
id: semver_parser
|
||||
uses: netbirdio/shared-actions/actions/parse-semver@be5df6047383da2236e02243cceb857d8567c27e # v0.0.2
|
||||
|
||||
- name: Set snapshot flag
|
||||
if: ${{ !startsWith(github.ref, 'refs/tags/v') }}
|
||||
run: |
|
||||
echo "flags=--snapshot" >> $GITHUB_ENV
|
||||
|
||||
- name: Set build vars
|
||||
if: ${{ startsWith(github.ref, 'refs/tags/v') }}
|
||||
run: |
|
||||
if [[ "x-${{ steps.semver_parser.outputs.prerelease }}" == "x-" && "x-${{ github.repository }}" == "x-netbirdio/netbird" ]]; then
|
||||
echo "x-${{ github.repository }}"
|
||||
echo "x-${{ steps.semver_parser.outputs.prerelease }}"
|
||||
echo "SKIP_PUBLISH=false" >> $GITHUB_ENV
|
||||
else
|
||||
echo "x-${{ github.repository }}"
|
||||
echo "x-${{ steps.semver_parser.outputs.prerelease }}"
|
||||
fi
|
||||
|
||||
- name: Set up Go
|
||||
uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
|
||||
with:
|
||||
go-version-file: "go.mod"
|
||||
cache: false
|
||||
- name: Cache Go modules
|
||||
# Restore-only from the release_ui cache written by trusted runs; the
|
||||
# module cache is identical (same go.sum) and stale build-cache
|
||||
# entries just miss.
|
||||
uses: actions/cache/restore@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
|
||||
with:
|
||||
path: |
|
||||
~/go/pkg/mod
|
||||
~/.cache/go-build
|
||||
key: ${{ runner.os }}-ui-go-releaser-${{ hashFiles('**/go.sum') }}
|
||||
restore-keys: |
|
||||
${{ runner.os }}-ui-go-releaser-
|
||||
|
||||
- name: Install modules
|
||||
run: go mod tidy
|
||||
|
||||
- name: check git status
|
||||
run: git --no-pager diff --exit-code
|
||||
|
||||
- name: Set up Node.js
|
||||
uses: actions/setup-node@49933ea5288caeca8642d1e84afbd3f7d6820020 # v4
|
||||
with:
|
||||
node-version: '22'
|
||||
|
||||
- name: Set up pnpm
|
||||
uses: pnpm/action-setup@a3252b78c470c02df07e9d59298aecedc3ccdd6d # v3.0.0
|
||||
with:
|
||||
version: 11
|
||||
|
||||
- name: Install dependencies
|
||||
run: sudo apt update && sudo apt install -y -q libgtk-3-dev libwebkit2gtk-4.1-dev
|
||||
|
||||
- name: Decode GPG signing key
|
||||
if: github.event_name != 'pull_request' || github.event.pull_request.head.repo.full_name == github.repository
|
||||
env:
|
||||
GPG_RPM_PRIVATE_KEY: ${{ secrets.GPG_RPM_PRIVATE_KEY }}
|
||||
run: |
|
||||
echo "$GPG_RPM_PRIVATE_KEY" | base64 -d > /tmp/gpg-rpm-signing-key.asc
|
||||
echo "GPG_RPM_KEY_FILE=/tmp/gpg-rpm-signing-key.asc" >> $GITHUB_ENV
|
||||
|
||||
- name: Install wails3 CLI
|
||||
# Version derived from go.mod so the binding generator always matches
|
||||
# the wails runtime the binary links against.
|
||||
# -tags gtk3: the CLI links the wails runtime's cgo packages, and the
|
||||
# default tags request gtk4/webkitgtk-6.0 pkg-config entries that do
|
||||
# not exist on ubuntu-22.04.
|
||||
run: |
|
||||
WAILS_VERSION=$(go list -m -f '{{.Version}}' github.com/wailsapp/wails/v3)
|
||||
go install -tags gtk3 github.com/wailsapp/wails/v3/cmd/wails3@$WAILS_VERSION
|
||||
|
||||
- name: Run GoReleaser
|
||||
uses: goreleaser/goreleaser-action@5daf1e915a5f0af01ddbcd89a43b8061ff4f1a89 # v7.2.2
|
||||
with:
|
||||
version: ${{ env.GORELEASER_VER }}
|
||||
args: release --config .goreleaser_ui_gtk3.yaml --clean ${{ env.flags }}
|
||||
env:
|
||||
GITHUB_TOKEN: ${{ secrets.GITHUB_TOKEN }}
|
||||
UPLOAD_DEBIAN_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
|
||||
UPLOAD_YUM_SECRET: ${{ secrets.PKG_UPLOAD_SECRET }}
|
||||
GPG_RPM_KEY_FILE: ${{ env.GPG_RPM_KEY_FILE }}
|
||||
NFPM_NETBIRD_UI_RPM_GTK3_PASSPHRASE: ${{ secrets.GPG_RPM_PASSPHRASE }}
|
||||
SKIP_PUBLISH: ${{ env.SKIP_PUBLISH }}
|
||||
- name: Verify RPM signatures
|
||||
run: |
|
||||
docker run --rm -v $(pwd)/dist:/dist fedora:41 bash -c '
|
||||
dnf install -y -q rpm-sign curl >/dev/null 2>&1
|
||||
curl -sSL https://pkgs.netbird.io/yum/repodata/repomd.xml.key -o /tmp/rpm-pub.key
|
||||
rpm --import /tmp/rpm-pub.key
|
||||
echo "=== Verifying RPM signatures ==="
|
||||
for rpm_file in /dist/*.rpm; do
|
||||
[ -f "$rpm_file" ] || continue
|
||||
echo "--- $(basename $rpm_file) ---"
|
||||
rpm -K "$rpm_file"
|
||||
done
|
||||
'
|
||||
- name: Clean up GPG key
|
||||
if: always()
|
||||
run: rm -f /tmp/gpg-rpm-signing-key.asc
|
||||
- name: upload non tags for debug purposes
|
||||
id: upload_release_ui_gtk3
|
||||
uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a #v7.0.1
|
||||
with:
|
||||
name: release-ui-gtk3
|
||||
path: dist/
|
||||
retention-days: 3
|
||||
|
||||
release_ui_darwin:
|
||||
runs-on: macos-latest
|
||||
outputs:
|
||||
@@ -814,7 +688,7 @@ jobs:
|
||||
comment_release_artifacts:
|
||||
name: Comment release artifacts
|
||||
runs-on: ubuntu-latest
|
||||
needs: [release, release_ui, release_ui_gtk3, release_ui_darwin]
|
||||
needs: [release, release_ui, release_ui_darwin]
|
||||
if: ${{ always() && github.event_name == 'pull_request' && github.event.pull_request.head.repo.full_name == github.repository }}
|
||||
permissions:
|
||||
contents: read
|
||||
@@ -826,14 +700,12 @@ jobs:
|
||||
env:
|
||||
RELEASE_RESULT: ${{ needs.release.result }}
|
||||
RELEASE_UI_RESULT: ${{ needs.release_ui.result }}
|
||||
RELEASE_UI_GTK3_RESULT: ${{ needs.release_ui_gtk3.result }}
|
||||
RELEASE_UI_DARWIN_RESULT: ${{ needs.release_ui_darwin.result }}
|
||||
RELEASE_ARTIFACT_URL: ${{ needs.release.outputs.release_artifact_url }}
|
||||
LINUX_PACKAGES_ARTIFACT_URL: ${{ needs.release.outputs.linux_packages_artifact_url }}
|
||||
WINDOWS_PACKAGES_ARTIFACT_URL: ${{ needs.release.outputs.windows_packages_artifact_url }}
|
||||
MACOS_PACKAGES_ARTIFACT_URL: ${{ needs.release.outputs.macos_packages_artifact_url }}
|
||||
RELEASE_UI_ARTIFACT_URL: ${{ needs.release_ui.outputs.release_ui_artifact_url }}
|
||||
RELEASE_UI_GTK3_ARTIFACT_URL: ${{ needs.release_ui_gtk3.outputs.release_ui_gtk3_artifact_url }}
|
||||
RELEASE_UI_DARWIN_ARTIFACT_URL: ${{ needs.release_ui_darwin.outputs.release_ui_darwin_artifact_url }}
|
||||
GHCR_IMAGES_MARKDOWN: ${{ needs.release.outputs.ghcr_images }}
|
||||
with:
|
||||
@@ -856,7 +728,6 @@ jobs:
|
||||
['Windows packages', process.env.WINDOWS_PACKAGES_ARTIFACT_URL, process.env.RELEASE_RESULT],
|
||||
['macOS packages', process.env.MACOS_PACKAGES_ARTIFACT_URL, process.env.RELEASE_RESULT],
|
||||
['UI artifacts', process.env.RELEASE_UI_ARTIFACT_URL, process.env.RELEASE_UI_RESULT],
|
||||
['UI GTK3 artifacts', process.env.RELEASE_UI_GTK3_ARTIFACT_URL, process.env.RELEASE_UI_GTK3_RESULT],
|
||||
['UI macOS artifacts', process.env.RELEASE_UI_DARWIN_ARTIFACT_URL, process.env.RELEASE_UI_DARWIN_RESULT],
|
||||
];
|
||||
|
||||
@@ -913,7 +784,7 @@ jobs:
|
||||
|
||||
trigger_signer:
|
||||
runs-on: ubuntu-latest
|
||||
needs: [release, release_ui, release_ui_gtk3, release_ui_darwin, test_windows_installer]
|
||||
needs: [release, release_ui, release_ui_darwin, test_windows_installer]
|
||||
if: startsWith(github.ref, 'refs/tags/')
|
||||
steps:
|
||||
- name: Trigger binaries sign pipelines
|
||||
|
||||
@@ -257,15 +257,6 @@ jobs:
|
||||
with:
|
||||
persist-credentials: false
|
||||
|
||||
- name: Verify fresh-install session cookie key hardening
|
||||
run: |
|
||||
grep -Fxq ' SESSION_COOKIE_ENCRYPTION_KEY=$(openssl rand -base64 32)' infrastructure_files/getting-started.sh
|
||||
grep -Fxq ' sessionCookieEncryptionKey: "$SESSION_COOKIE_ENCRYPTION_KEY"' infrastructure_files/getting-started.sh
|
||||
grep -Fxq ' install -m 600 /dev/null config.yaml' infrastructure_files/getting-started.sh
|
||||
grep -Fxq ' openssl rand -base64 32' infrastructure_files/getting-started-enterprise.sh
|
||||
grep -Fxq ' NETBIRD_SESSION_COOKIE_ENCRYPTION_KEY=$(rand_b64_key)' infrastructure_files/getting-started-enterprise.sh
|
||||
grep -Fxq ' sessionCookieEncryptionKey: "${NETBIRD_SESSION_COOKIE_ENCRYPTION_KEY}"' infrastructure_files/getting-started-enterprise.sh
|
||||
|
||||
- name: Verify Dex retirement notice
|
||||
run: |
|
||||
if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
|
||||
|
||||
@@ -96,7 +96,6 @@ nfpms:
|
||||
- netbird (>= 0.75.0)
|
||||
- libgtk-4-1 (>= 4.14)
|
||||
- libwebkitgtk-6.0-4
|
||||
- xdg-utils
|
||||
|
||||
- maintainer: Netbird <dev@netbird.io>
|
||||
description: Netbird client UI.
|
||||
@@ -120,7 +119,6 @@ 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:
|
||||
|
||||
@@ -1,142 +0,0 @@
|
||||
version: 2
|
||||
env:
|
||||
- SKIP_PUBLISH={{ if index .Env "SKIP_PUBLISH" }}{{ .Env.SKIP_PUBLISH }}{{ else }}true{{ end }}
|
||||
project_name: netbird-ui
|
||||
|
||||
before:
|
||||
hooks:
|
||||
# Bindings are gitignored; regenerate before the frontend build so
|
||||
# the @wailsio/runtime Vite plugin can resolve them (vite refuses to
|
||||
# build without them).
|
||||
# -f '-tags gtk3': the generator type-checks client/ui, whose cgo imports
|
||||
# would otherwise resolve gtk4/webkitgtk-6.0 pkg-config entries that do
|
||||
# not exist on ubuntu-22.04.
|
||||
- sh -c 'cd client/ui && wails3 generate bindings -clean=true -ts -f "-tags gtk3"'
|
||||
- sh -c 'cd client/ui/frontend && pnpm install --frozen-lockfile && pnpm build'
|
||||
|
||||
builds:
|
||||
# Legacy GTK3 / WebKit2GTK 4.1 build for distros without WebKitGTK 6.0
|
||||
# (Ubuntu 22.04, Debian 12, RHEL 9, Fedora <=39). The gtk3 tag flips the
|
||||
# Wails Linux backend to the GTK3 stack and swaps our GTK4-only XEmbed
|
||||
# tray host for the pure-Go stub (client/ui/xembed_host_gtk3_linux.go).
|
||||
# Must be built on the oldest supported glibc (ubuntu-22.04 runner).
|
||||
- id: netbird-ui-gtk3
|
||||
dir: client/ui
|
||||
binary: netbird-ui
|
||||
env:
|
||||
- CGO_ENABLED=1
|
||||
goos:
|
||||
- linux
|
||||
goarch:
|
||||
- amd64
|
||||
ldflags:
|
||||
- -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
|
||||
mod_timestamp: "{{ .CommitTimestamp }}"
|
||||
tags:
|
||||
- production
|
||||
- gtk3
|
||||
|
||||
archives:
|
||||
- id: linux-gtk3-arch
|
||||
name_template: "{{ .ProjectName }}-linux-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
|
||||
builds:
|
||||
- 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.
|
||||
- maintainer: Netbird <dev@netbird.io>
|
||||
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 }}"
|
||||
builds:
|
||||
- netbird-ui-gtk3
|
||||
formats:
|
||||
- deb
|
||||
scripts:
|
||||
postinstall: "release_files/ui-post-install.sh"
|
||||
contents:
|
||||
- src: client/ui/build/linux/netbird.desktop
|
||||
dst: /usr/share/applications/org.wails.netbird.desktop
|
||||
- src: client/ui/build/appicon.png
|
||||
dst: /usr/share/pixmaps/netbird.png
|
||||
dependencies:
|
||||
- netbird (>= 0.75.0)
|
||||
- libgtk-3-0
|
||||
- libwebkit2gtk-4.1-0
|
||||
- xdg-utils
|
||||
|
||||
- maintainer: Netbird <dev@netbird.io>
|
||||
description: Netbird client UI.
|
||||
homepage: https://netbird.io/
|
||||
license: BSD-3-Clause
|
||||
vendor: NetBird
|
||||
id: netbird_ui_rpm_gtk3
|
||||
package_name: netbird-ui
|
||||
file_name_template: "{{ .PackageName }}-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
|
||||
builds:
|
||||
- netbird-ui-gtk3
|
||||
formats:
|
||||
- rpm
|
||||
scripts:
|
||||
postinstall: "release_files/ui-post-install.sh"
|
||||
contents:
|
||||
- src: client/ui/build/linux/netbird.desktop
|
||||
dst: /usr/share/applications/org.wails.netbird.desktop
|
||||
- src: client/ui/build/appicon.png
|
||||
dst: /usr/share/pixmaps/netbird.png
|
||||
dependencies:
|
||||
- netbird >= 0.75.0
|
||||
- (gtk3 or libgtk-3-0)
|
||||
- (webkit2gtk4.1 or libwebkit2gtk-4_1-0)
|
||||
- xdg-utils
|
||||
|
||||
rpm:
|
||||
signature:
|
||||
key_file: '{{ if index .Env "GPG_RPM_KEY_FILE" }}{{ .Env.GPG_RPM_KEY_FILE }}{{ end }}'
|
||||
|
||||
# The GTK4 UI job shares project_name, so the default checksum file name would
|
||||
# collide with it on the shared GitHub release.
|
||||
checksum:
|
||||
name_template: "{{ .ProjectName }}_gtk3_checksums.txt"
|
||||
|
||||
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.
|
||||
#
|
||||
# GoReleaser derives the credential env var from the upload name, so these
|
||||
# would look for UPLOAD_DEBIAN-GTK3_SECRET / UPLOAD_YUM-GTK3_SECRET. The
|
||||
# release workflow only exports UPLOAD_DEBIAN_SECRET / UPLOAD_YUM_SECRET, and
|
||||
# a missing secret is a silent skip rather than a failure -- the packages
|
||||
# reached the GitHub release but never the package repositories. Point
|
||||
# `password` at the exported vars so both uploads authenticate.
|
||||
- name: debian-gtk3
|
||||
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=
|
||||
username: dev@wiretrustee.com
|
||||
password: "{{ .Env.UPLOAD_DEBIAN_SECRET }}"
|
||||
method: PUT
|
||||
|
||||
- name: yum-gtk3
|
||||
skip: "{{ .Env.SKIP_PUBLISH }}"
|
||||
ids:
|
||||
- netbird_ui_rpm_gtk3
|
||||
mode: archive
|
||||
target: https://pkgs.wiretrustee.com/yum-gtk3/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }}
|
||||
username: dev@wiretrustee.com
|
||||
password: "{{ .Env.UPLOAD_YUM_SECRET }}"
|
||||
method: PUT
|
||||
317
AGENTS.md
317
AGENTS.md
@@ -14,22 +14,20 @@ in this file, not duplicated there.
|
||||
|
||||
## Contents
|
||||
|
||||
- [STOP and ask the user before](#stop-and-ask-the-user-before)
|
||||
- [Quick reference](#quick-reference)
|
||||
- [Structure](#structure)
|
||||
- [Where to look](#where-to-look)
|
||||
- [Security](#security)
|
||||
- [Agent conventions](#agent-conventions)
|
||||
- [Repo-wide principles](#repo-wide-principles)
|
||||
- [Type safety](#type-safety)
|
||||
- [Concurrency and lifecycle](#concurrency-and-lifecycle)
|
||||
- [Error handling](#error-handling)
|
||||
- [Comments](#comments)
|
||||
- [Testing](#testing)
|
||||
- [Pitfalls](#pitfalls)
|
||||
- [Commits, PRs, releases](#commits-prs-releases)
|
||||
- [After you push: CI and review bots](#after-you-push-ci-and-review-bots)
|
||||
- [Discussion and support](#discussion-and-support)
|
||||
- [NetBird Agent Guidelines](#netbird-agent-guidelines)
|
||||
- [Contents](#contents)
|
||||
- [STOP and ask the user before](#stop-and-ask-the-user-before)
|
||||
- [Quick reference](#quick-reference)
|
||||
- [Structure](#structure)
|
||||
- [Where to look](#where-to-look)
|
||||
- [Repo-wide principles](#repo-wide-principles)
|
||||
- [Error handling](#error-handling)
|
||||
- [Comments](#comments)
|
||||
- [Testing](#testing)
|
||||
- [Pitfalls](#pitfalls)
|
||||
- [Commits, PRs, releases](#commits-prs-releases)
|
||||
- [After you push: CI and review bots](#after-you-push-ci-and-review-bots)
|
||||
- [Discussion and support](#discussion-and-support)
|
||||
|
||||
## STOP and ask the user before
|
||||
|
||||
@@ -159,125 +157,11 @@ netbird/
|
||||
| LLM routing / Agent Network | `proxy/internal/llm/`, `agent-network/` |
|
||||
| End-to-end tests | `e2e/` |
|
||||
|
||||
## Security
|
||||
|
||||
### Never fail open
|
||||
|
||||
When a security check — access control, an IP restriction, an auth decision —
|
||||
hits an error such as an unparseable value, an unavailable lookup, or a state it
|
||||
does not recognize, it must **deny**. Never skip the check or allow the request
|
||||
through because the check itself failed, and make the `default` and unknown cases
|
||||
of a security-related `switch` deny rather than fall through.
|
||||
|
||||
### Daemon RPC input is untrusted
|
||||
|
||||
The agent runs as root (LocalSystem on Windows), so a daemon RPC crosses a
|
||||
privilege boundary: treat every field as untrusted input rather than as something
|
||||
the UI or CLI validated on the way in.
|
||||
|
||||
When you add or change an RPC, ask what the handler does with caller input while
|
||||
running as root. If the answer touches a filesystem path, a URL or host, or a
|
||||
privileged state change, it needs a gate **in the handler** — a check in the client
|
||||
that normally calls it is not a check at all.
|
||||
|
||||
- **A caller-supplied path the daemon opens.** Never `os.Open` it as root.
|
||||
Constrain it, then open it *as the caller* with `ipcauth.OpenOwnedFile`, which
|
||||
opens `O_NOFOLLOW`, requires a regular file, and refuses a file the caller does
|
||||
not own — so a symlink or hardlink aimed at a root-only file is rejected.
|
||||
- **A caller-supplied URL or host the daemon fetches.** Restrict the scheme and
|
||||
allow only known hosts for unprivileged callers. Prefer a lexical host
|
||||
allowlist plus TLS verification over "resolve the host, then reject private
|
||||
IPs": the resolve-then-trust pattern has a DNS-rebinding race (public IP at
|
||||
check time, attacker IP at connect time), while a name allowlist has no IP
|
||||
check to race. Never accept `http://` where `https://` is expected.
|
||||
- **A privileged state change** (SSH root login, management URL, deregistration)
|
||||
gates on the caller identity from `ipcauth.CallerIdentity(ctx)`.
|
||||
|
||||
Caller identity comes from the kernel — `SO_PEERCRED`, `LOCAL_PEERCRED`, or the
|
||||
named-pipe client token — and never from an RPC field. When
|
||||
`ipcauth.CallerIdentity` reports that it could not determine an identity, **deny**;
|
||||
do not fall back to treating the caller as the transport peer.
|
||||
|
||||
## Agent conventions
|
||||
|
||||
### Three networking modes
|
||||
|
||||
Where packets actually flow depends on the mode the agent is running in. The
|
||||
three are not interchangeable, so establish which one a change applies to — and
|
||||
what it should do in the other two — before you write it.
|
||||
|
||||
- **kernel mode** (Linux only): in-kernel WireGuard®. The kernel handles both
|
||||
peer-to-peer and routed traffic, and ACLs are iptables or nftables rules. The
|
||||
client programs kernel facilities but never sees the traffic itself.
|
||||
- **userspace mode** (wireguard-go with a TUN): wireguard-go runs in-process. The
|
||||
kernel handles peer-to-peer traffic once it leaves the TUN, while routed traffic
|
||||
— exit nodes and network routes — goes through the userspace forwarder, which
|
||||
terminates the connection and re-establishes it over OS sockets. Used on
|
||||
platforms without kernel WireGuard® or when the user opts out.
|
||||
- **netstack mode**: wireguard-go in-process with no TUN and no kernel
|
||||
networking. The forwarder does all routing by stitching userspace sockets, and
|
||||
listeners such as the embedded SSH and DNS servers bind on a gVisor netstack.
|
||||
Used where the process cannot create a TUN device, such as the embedded client
|
||||
(`client/embed/`) and the WASM build.
|
||||
|
||||
### The overlay interface is not "WireGuard"
|
||||
|
||||
Do not put "WireGuard" in identifiers or comments unless the code is genuinely
|
||||
coupled to WireGuard® specifically — a wireguard-go call, a handshake field, a
|
||||
kernel WireGuard® netlink attribute. For the interface, the host, peers, or
|
||||
traffic in general, say "the NetBird interface", "the interface", or "the overlay".
|
||||
Most firewall, routing, and DNS code is transport-agnostic, so a WireGuard®
|
||||
reference there is simply inaccurate and rots as the transports change.
|
||||
|
||||
### IPv6 is a soft feature
|
||||
|
||||
The IPv6 overlay is opt-in dual-stack, and capability can change at runtime. Treat
|
||||
it as soft rather than a requirement:
|
||||
|
||||
- Gate local v6 paths on the interface accessor (`wgIface.Address().HasIPv6()`),
|
||||
not on raw state fields, and skip the v6 path when the host has no v6 rather
|
||||
than returning an error.
|
||||
- Treat an empty or unparseable peer v6 address as "no v6 for that peer" and skip
|
||||
it, keeping the v4 path working.
|
||||
- Never let a missing v6 break v4. Fail-closed is for security checks; a
|
||||
capability mismatch skips the v6 work and carries on.
|
||||
|
||||
### Environment variables
|
||||
|
||||
Name the variable in a constant and parse booleans with `strconv.ParseBool` rather
|
||||
than comparing strings inline, so an unexpected value is logged instead of
|
||||
silently meaning false:
|
||||
|
||||
```go
|
||||
const EnvDisableFeature = "NB_DISABLE_FEATURE"
|
||||
|
||||
func isDisabledByEnv() bool {
|
||||
val := os.Getenv(EnvDisableFeature)
|
||||
if val == "" {
|
||||
return false
|
||||
}
|
||||
disabled, err := strconv.ParseBool(val)
|
||||
if err != nil {
|
||||
log.Warnf("failed to parse %s: %v", EnvDisableFeature, err)
|
||||
return false
|
||||
}
|
||||
return disabled
|
||||
}
|
||||
```
|
||||
|
||||
### Validating against protocol specs
|
||||
|
||||
When a change depends on what a protocol actually mandates, read the specification
|
||||
text from the [IETF datatracker](https://datatracker.ietf.org/) rather than a
|
||||
summary, and check that you have the current RFC — the widely cited one for a
|
||||
protocol is often superseded. Cite the section, not just the document, so a
|
||||
reviewer can jump straight to the rule.
|
||||
|
||||
## Repo-wide principles
|
||||
|
||||
1. **Run `go fmt` on every modified Go file.** Formatting is not optional.
|
||||
2. **Zero unaddressed linter warnings.** Fix what `golangci-lint` reports on code
|
||||
you touch, and delete imports, helpers, and parameters your refactor orphaned.
|
||||
2. **Zero unaddressed diagnostics.** Fix IDE and linter warnings on code you
|
||||
touch, and delete imports, helpers, and parameters your refactor orphaned.
|
||||
Exception: unused parameters in shared code may be consumed by builds outside
|
||||
this repository — do not remove them, ask instead.
|
||||
3. **Function comments are mandatory for exported functions**, written as full
|
||||
@@ -291,12 +175,9 @@ reviewer can jump straight to the rule.
|
||||
7. **Avoid LLM-slop tells:** em dashes, hedging narration, restating the diff in
|
||||
prose, trailing summaries. Defaults, not absolute bans. Applies to code,
|
||||
comments, commit messages, and PR descriptions alike.
|
||||
8. **Concurrency: do a two-pass race analysis after every change** that touches
|
||||
shared state, including reads of existing maps and slices. Guard them with a
|
||||
mutex (or an atomic or channel where that fits better), keep critical
|
||||
sections short, and run `go test -race` on the touched packages. See
|
||||
[Concurrency and lifecycle](#concurrency-and-lifecycle) for the failure modes
|
||||
to check for.
|
||||
8. **Concurrency: do a two-pass race analysis after every change** that adds
|
||||
shared state. Guard maps and slices with a mutex, keep critical sections
|
||||
short, and run `go test -race` on the touched packages.
|
||||
9. **Cross-platform builds must keep working.** The agent targets Linux, macOS,
|
||||
Windows, FreeBSD, Android, and iOS. When you add a platform-specific file,
|
||||
add the counterpart or a build-tagged fallback for the others.
|
||||
@@ -304,93 +185,6 @@ reviewer can jump straight to the rule.
|
||||
11. **Never log secrets** — private keys, setup keys, tokens, PAT values — and
|
||||
keep peer IPs and hostnames out of logs above debug level.
|
||||
|
||||
## Type safety
|
||||
|
||||
**No bare primitives for domain concepts.** A `string` parameter for an account
|
||||
ID next to a `string` parameter for a peer ID is two bugs waiting to happen,
|
||||
because the compiler cannot catch the swap. Declare the type once and use it
|
||||
throughout, converting only at the boundaries where data enters or leaves —
|
||||
protobuf, gRPC, HTTP, an external library.
|
||||
|
||||
```go
|
||||
type ServiceID string
|
||||
type AccountID string
|
||||
|
||||
// Internal: typed all the way through
|
||||
func (r *Router) RemoveRoute(host SNIHost, svcID ServiceID) { ... }
|
||||
|
||||
// Proto boundary: convert once, on the way in and on the way out
|
||||
svcID := ServiceID(mapping.GetId())
|
||||
req.ServiceId = string(svcID)
|
||||
```
|
||||
|
||||
- **IP addresses are `netip.Addr`**, not `string` and not `net.IP`. Parse at the
|
||||
boundary and pass the typed value inward.
|
||||
- **Always `Unmap()`** after parsing an address, after converting from `net.IP`,
|
||||
and after extracting one from `RemoteAddr()`. This normalizes a v4-mapped v6
|
||||
address (`::ffff:10.1.2.3`) to plain v4 so IPv4 rules match it. A stored or
|
||||
compared mapped address silently fails to match those rules.
|
||||
- **Ports are `uint16`** internally; use `int` only where a library forces it and
|
||||
convert immediately.
|
||||
- **Enums are a typed string with constants**, so the valid set is discoverable
|
||||
and a typo fails to compile.
|
||||
- **Map keys follow the same rule**, and must be a real type (`type ServiceID
|
||||
string`) rather than an alias (`type serviceID = string`) — an alias silently
|
||||
accepts bare strings.
|
||||
|
||||
## Concurrency and lifecycle
|
||||
|
||||
Beyond the mutex hygiene in the principles above, check for these failure
|
||||
modes.
|
||||
|
||||
- **Never read a struct field inside a goroutine** when another goroutine may nil
|
||||
or reassign it. Pass the value as a parameter, or capture it into a local before
|
||||
launching. This matters most when `Stop()` nils a field without waiting for the
|
||||
goroutine to finish.
|
||||
|
||||
```go
|
||||
go func(ifaceName string) { // good: passed in, cannot be nilled underneath
|
||||
m.Start(ctx, ifaceName)
|
||||
}(iface.Name())
|
||||
```
|
||||
|
||||
- **Never wait on a channel while holding a lock the sender needs.** Copy what you
|
||||
need out from under the lock, release it, then wait.
|
||||
|
||||
```go
|
||||
func (m *Manager) Stop() {
|
||||
m.mu.Lock()
|
||||
cancel, done := m.cancel, m.done
|
||||
m.mu.Unlock()
|
||||
if cancel != nil {
|
||||
cancel()
|
||||
<-done
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
- **`Stop`/`Close` must be idempotent** — guard on an already-stopped flag or a
|
||||
nil cancel — and must release the state they guarded. Clear maps and caches;
|
||||
a cancelled goroutine holding a live map still pins that memory. Note that a
|
||||
nil map only panics on writes; reads and iteration behave like an empty map,
|
||||
so where post-close use must be rejected, check the stopped flag explicitly.
|
||||
- **Publish coupled state only after every fallible step succeeds.** When several
|
||||
fields form an invariant, build them into locals and assign them to the receiver
|
||||
at the end. Assigning as you go leaves the object half-initialized when a later
|
||||
step fails, so a readiness predicate reports ready while a coupled field is nil.
|
||||
If an earlier step already had an external side effect — a created chain, an
|
||||
opened handle, an inserted rule — roll it back before returning the error.
|
||||
- **Clean up what you own on constructor error paths.** Once a constructor has
|
||||
started something, every later error path must undo it: cancel a goroutine and
|
||||
wait for it to exit, stop a ticker, close a watcher. The object is never
|
||||
returned, so its `Close` will never run.
|
||||
- **A failed `Start` must undo everything it started.** When a component brings up
|
||||
several subsystems in sequence — connection manager, watchers, routing, DNS,
|
||||
flow, persisted state — a failure partway through has to tear down the ones
|
||||
already running, not just close the handle the error came from. Put the
|
||||
already-started guard *before* that teardown path, so a rejected second `Start`
|
||||
cannot dismantle the one that is running.
|
||||
|
||||
## Error handling
|
||||
|
||||
Use single-assignment form when the error is only needed inside the `if`:
|
||||
@@ -454,45 +248,6 @@ Log the errors you choose not to act on:
|
||||
- Close errors may be ignored for read-only operations; log them at debug for
|
||||
writes.
|
||||
|
||||
**Do not log and return the same error.** It gets reported twice, from two places,
|
||||
and the second reader cannot tell whether it happened once or twice. Return it and
|
||||
let the caller decide. The exception is an API handler that has already written a
|
||||
response. Internal helpers return errors rather than logging and swallowing them.
|
||||
|
||||
**Never return a typed nil as an error.** A nil `*MyError` stored in an `error`
|
||||
interface is not nil, so `err != nil` is true and callers take the failure path on
|
||||
success. Return the error only where it is actually set:
|
||||
|
||||
```go
|
||||
if _, err := conn.Write(buf); err != nil { // good
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
```
|
||||
|
||||
**Accumulate with `multierror` when an operation should continue past individual
|
||||
failures** — teardown, cleanup, or setup where partial success is acceptable.
|
||||
`client/errors.FormatErrorOrNil` returns nil for an empty accumulator, so callers
|
||||
still see a plain nil on full success:
|
||||
|
||||
```go
|
||||
func (m *Manager) Cleanup() error {
|
||||
var merr *multierror.Error
|
||||
for _, r := range m.resources {
|
||||
if err := r.Close(); err != nil {
|
||||
merr = multierror.Append(merr, fmt.Errorf("close %s: %w", r.Name, err))
|
||||
}
|
||||
}
|
||||
return nberrors.FormatErrorOrNil(merr)
|
||||
}
|
||||
```
|
||||
|
||||
| Scenario | Approach | Why |
|
||||
| --------------------- | --------------------- | ----------------------------------------- |
|
||||
| Cleanup / teardown | Accumulate | Clean up as much as possible |
|
||||
| Setup with rollback | Abort on first error | Partial state is invalid; undo what stuck |
|
||||
| Setup with partial OK | Accumulate | Degraded operation is still useful |
|
||||
|
||||
## Comments
|
||||
|
||||
Comment the **why**, never the **what**. Default to no comment, and add one only
|
||||
@@ -514,14 +269,10 @@ checksum = updateChecksum(checksum, oldPort, newPort)
|
||||
|
||||
### Length budget
|
||||
|
||||
Neither of these is linter-enforced, so they are conventions the surrounding code
|
||||
mostly follows rather than hard limits:
|
||||
|
||||
- **Around 90 characters per line.** Wrap the comment rather than running well past
|
||||
it.
|
||||
- **Roughly 250 characters per comment**, about three wrapped lines. Doc comments
|
||||
on exported identifiers may exceed it when the API genuinely needs the
|
||||
explanation; inline comments inside a function body rarely should.
|
||||
- **90 characters per line.** Wrap the comment, do not run past it.
|
||||
- **250 characters per comment**, roughly three wrapped lines. Doc comments on
|
||||
exported identifiers may exceed it when the API genuinely needs the
|
||||
explanation; inline comments inside a function body may not.
|
||||
|
||||
The budget is a smell detector, not a rule to game. Do not compress a needed
|
||||
explanation into cryptic shorthand to fit — if a block of code needs more than
|
||||
@@ -578,19 +329,6 @@ up, and the 250-character budget does not apply to them.
|
||||
otherwise.
|
||||
- **Message guidance:** optional for `NoError`/`Error`; always give context for
|
||||
comparison, boolean, and collection assertions.
|
||||
- **Reproduce a bug before fixing it.** Write the test, watch it fail *for the
|
||||
reason you expect* — a test that fails for an unrelated reason proves nothing —
|
||||
then apply the fix and confirm it passes. Add the thin surrounding cases while
|
||||
you are there.
|
||||
- **Use `t.Setenv`** rather than `os.Setenv` so the previous value is restored on
|
||||
cleanup. To test the unset case, call `t.Setenv` first to register the restore,
|
||||
then `os.Unsetenv`.
|
||||
- **Prefer `t.Cleanup` over `defer`** in any test with parallel subtests: the
|
||||
parent function returns, running its `defer`s, while parallel subtests are
|
||||
still suspended. Sequential subtests finish inside `t.Run`, so `defer` is safe
|
||||
there, but `t.Cleanup` works in both cases.
|
||||
- **Explanatory comments in tests are welcome.** Describe the scenario being set
|
||||
up; the comment budget below does not apply to them.
|
||||
|
||||
```go
|
||||
server, err := StartTestServer()
|
||||
@@ -642,8 +380,7 @@ assert.Equal(t, expectedResult, result, "Result should match expected")
|
||||
than replacing it with your own summary: describe the change, link the issue,
|
||||
tick the checklist honestly (including "ran locally" and "single purpose"),
|
||||
and complete the documentation section. Do not tick a box you have not
|
||||
verified, and do not delete rows that do not apply — the docs gate in CI reads
|
||||
that section and fails when it is missing.
|
||||
verified, and do not delete rows that do not apply.
|
||||
|
||||
- **Keep the PR description short.** Under 1000 words on top of the template's
|
||||
own text, and usually far less — a few paragraphs. Reviewers read the diff;
|
||||
@@ -702,12 +439,6 @@ assert.Equal(t, expectedResult, result, "Result should match expected")
|
||||
on their own. Propose that split to the user rather than opening one large PR
|
||||
and hoping.
|
||||
|
||||
Prefer GitHub's stacked pull requests for such a sequence, rather than
|
||||
hand-managing base branches: open each PR against the branch below it instead of
|
||||
`main`, so every PR's diff shows only its own change. Merging a layer retargets
|
||||
the PRs above it, and branch protections and required checks on the base branch
|
||||
still apply to each one.
|
||||
|
||||
- **User-facing changes need a docs PR** in
|
||||
[netbirdio/docs](https://github.com/netbirdio/docs), linked from the PR
|
||||
description.
|
||||
|
||||
@@ -40,35 +40,6 @@ 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:
|
||||
|
||||
@@ -15,7 +15,6 @@ 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"
|
||||
@@ -33,13 +32,6 @@ import (
|
||||
types "github.com/netbirdio/netbird/upload-server/types"
|
||||
)
|
||||
|
||||
// AnonymizeLevelDefault and AnonymizeLevelStrict are the accepted
|
||||
// anonymizeLevel values for DebugBundle.
|
||||
const (
|
||||
AnonymizeLevelDefault = nbAnonymize.LevelDefaultString
|
||||
AnonymizeLevelStrict = nbAnonymize.LevelStrictString
|
||||
)
|
||||
|
||||
// ConnectionListener export internal Listener for mobile
|
||||
type ConnectionListener interface {
|
||||
peer.Listener
|
||||
@@ -90,8 +82,6 @@ type Client struct {
|
||||
connectClient *internal.ConnectClient
|
||||
config *profilemanager.Config
|
||||
cacheDir string
|
||||
// Identifies the running profile for the SSO login hint; see profile_state.go.
|
||||
cfgPath string
|
||||
|
||||
stateChangeMu sync.Mutex
|
||||
stateChangeSubID string
|
||||
@@ -112,12 +102,11 @@ type Client struct {
|
||||
extendCancel context.CancelFunc
|
||||
}
|
||||
|
||||
func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cfgPath string, cc *internal.ConnectClient) {
|
||||
func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
|
||||
c.stateMu.Lock()
|
||||
defer c.stateMu.Unlock()
|
||||
c.config = cfg
|
||||
c.cacheDir = cacheDir
|
||||
c.cfgPath = cfgPath
|
||||
c.connectClient = cc
|
||||
}
|
||||
|
||||
@@ -127,16 +116,6 @@ func (c *Client) stateSnapshot() (*profilemanager.Config, string, *internal.Conn
|
||||
return c.config, c.cacheDir, c.connectClient
|
||||
}
|
||||
|
||||
// authSnapshot returns the config together with the path it was loaded from, in
|
||||
// one lock: the path identifies the profile whose account email backs the login
|
||||
// hint, so reading it separately could pair one profile's config with another's
|
||||
// hint when a profile switch lands in between.
|
||||
func (c *Client) authSnapshot() (*profilemanager.Config, string, *internal.ConnectClient) {
|
||||
c.stateMu.RLock()
|
||||
defer c.stateMu.RUnlock()
|
||||
return c.config, c.cfgPath, c.connectClient
|
||||
}
|
||||
|
||||
func (c *Client) getConnectClient() *internal.ConnectClient {
|
||||
c.stateMu.RLock()
|
||||
defer c.stateMu.RUnlock()
|
||||
@@ -189,7 +168,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
|
||||
defer c.ctxCancel()
|
||||
c.ctxCancelLock.Unlock()
|
||||
|
||||
auth := NewAuthWithConfig(ctx, cfg, cfgFile)
|
||||
auth := NewAuthWithConfig(ctx, cfg)
|
||||
err = auth.login(urlOpener, isAndroidTV)
|
||||
if err != nil {
|
||||
return err
|
||||
@@ -197,7 +176,7 @@ 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)
|
||||
c.setState(cfg, cacheDir, cfgFile, connectClient)
|
||||
c.setState(cfg, cacheDir, connectClient)
|
||||
// This path runs the interactive SSO flow, so reaching here means the peer
|
||||
// is authenticated again — release the latch Status() reports from. Clear
|
||||
// only once the fresh connect client is installed: until then Status()
|
||||
@@ -238,7 +217,7 @@ 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)
|
||||
c.setState(cfg, cacheDir, cfgFile, connectClient)
|
||||
c.setState(cfg, cacheDir, connectClient)
|
||||
return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
|
||||
}
|
||||
|
||||
@@ -286,10 +265,8 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
|
||||
}
|
||||
|
||||
// DebugBundle generates a debug bundle, uploads it, and returns the upload key.
|
||||
// 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) {
|
||||
// It works both with and without a running engine.
|
||||
func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (string, error) {
|
||||
cfg, cacheDir, cc := c.stateSnapshot()
|
||||
|
||||
// If the engine hasn't been started, load config from disk
|
||||
@@ -308,7 +285,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool, anonym
|
||||
InternalConfig: cfg,
|
||||
StatusRecorder: c.recorder,
|
||||
TempDir: cacheDir,
|
||||
StatePath: platformFiles.StateFilePath(),
|
||||
}
|
||||
|
||||
if cc != nil {
|
||||
@@ -332,7 +308,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool, anonym
|
||||
deps,
|
||||
debug.BundleConfig{
|
||||
Anonymize: anonymize,
|
||||
AnonymizeLevel: nbAnonymize.ParseLevel(anonymizeLevel),
|
||||
IncludeSystemInfo: true,
|
||||
},
|
||||
)
|
||||
|
||||
@@ -4,8 +4,6 @@ import (
|
||||
"context"
|
||||
"fmt"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/auth"
|
||||
"github.com/netbirdio/netbird/client/internal/profilemanager"
|
||||
"github.com/netbirdio/netbird/client/system"
|
||||
@@ -63,14 +61,11 @@ func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
|
||||
}, nil
|
||||
}
|
||||
|
||||
// NewAuthWithConfig instantiate Auth based on existing config. cfgPath is the
|
||||
// file the config was loaded from; it identifies the profile whose account email
|
||||
// backs the login_hint.
|
||||
func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config, cfgPath string) *Auth {
|
||||
// NewAuthWithConfig instantiate Auth based on existing config
|
||||
func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config) *Auth {
|
||||
return &Auth{
|
||||
ctx: ctx,
|
||||
config: config,
|
||||
cfgPath: cfgPath,
|
||||
ctx: ctx,
|
||||
config: config,
|
||||
}
|
||||
}
|
||||
|
||||
@@ -163,14 +158,12 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
|
||||
}
|
||||
|
||||
jwtToken := ""
|
||||
email := ""
|
||||
if needsLogin {
|
||||
tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
|
||||
if err != nil {
|
||||
return fmt.Errorf("interactive sso login failed: %v", err)
|
||||
}
|
||||
jwtToken = tokenInfo.GetTokenToUse()
|
||||
email = tokenInfo.Email
|
||||
}
|
||||
|
||||
err, _ = authClient.Login(a.ctx, "", jwtToken)
|
||||
@@ -178,42 +171,17 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
|
||||
return fmt.Errorf("login failed: %v", err)
|
||||
}
|
||||
|
||||
// Stored after Login, not before: a rejected token must not leave a hint
|
||||
// pointing at an account that cannot be used.
|
||||
if email != "" && a.cfgPath != "" {
|
||||
if err := writeProfileEmail(a.cfgPath, email); err != nil {
|
||||
log.Warnf("failed to store profile account email: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
go urlOpener.OnLoginSuccess()
|
||||
|
||||
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)
|
||||
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)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO())
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err)
|
||||
|
||||
@@ -13,17 +13,18 @@ import (
|
||||
)
|
||||
|
||||
const (
|
||||
// Android-specific config filename (different from desktop default.json)
|
||||
defaultConfigFilename = "netbird.cfg"
|
||||
// Subdirectory for non-default profiles (must match Java Preferences.java)
|
||||
profilesSubdir = "profiles"
|
||||
// Android uses a single user context per app (non-empty username required by ServiceManager)
|
||||
androidUsername = "android"
|
||||
)
|
||||
|
||||
// Profile represents a profile for gomobile
|
||||
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.
|
||||
Email string
|
||||
ID string
|
||||
Name string
|
||||
IsActive bool
|
||||
}
|
||||
|
||||
@@ -100,7 +101,6 @@ func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
|
||||
profiles = append(profiles, &Profile{
|
||||
ID: p.ID.String(),
|
||||
Name: p.Name,
|
||||
Email: pm.profileEmail(p.ID.String()),
|
||||
IsActive: p.IsActive,
|
||||
})
|
||||
}
|
||||
@@ -123,22 +123,7 @@ func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
|
||||
if err != nil {
|
||||
return nil, fmt.Errorf("failed to resolve active profile %q: %w", activeState.ID, err)
|
||||
}
|
||||
return &Profile{
|
||||
ID: prof.ID.String(),
|
||||
Name: prof.Name,
|
||||
Email: pm.profileEmail(prof.ID.String()),
|
||||
IsActive: true,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// profileEmail returns the account email recorded for a profile. Display-only, so
|
||||
// an unresolvable path degrades to "" rather than an error.
|
||||
func (pm *ProfileManager) profileEmail(id string) string {
|
||||
configPath, err := pm.getProfileConfigPath(id)
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
return readProfileEmail(configPath)
|
||||
return &Profile{ID: prof.ID.String(), Name: prof.Name, IsActive: true}, nil
|
||||
}
|
||||
|
||||
// SwitchProfile switches to a different profile
|
||||
@@ -200,11 +185,6 @@ 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)
|
||||
}
|
||||
|
||||
log.Infof("logged out from profile: %s", id)
|
||||
return nil
|
||||
}
|
||||
|
||||
@@ -1,108 +0,0 @@
|
||||
package android
|
||||
|
||||
import (
|
||||
"context"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/profilemanager"
|
||||
"github.com/netbirdio/netbird/util"
|
||||
)
|
||||
|
||||
const (
|
||||
// Android-specific config filename (different from desktop default.json)
|
||||
defaultConfigFilename = "netbird.cfg"
|
||||
// Subdirectory for non-default profiles (must match Java Preferences.java)
|
||||
profilesSubdir = "profiles"
|
||||
// profileAccountSuffix names the file holding the profile's account email.
|
||||
// Deliberately not ".state.json", which desktop uses for the same data:
|
||||
// there the email and the engine's state manager live in different
|
||||
// directories, but on Android both resolve under files/, so sharing the name
|
||||
// would have the two overwrite each other — the state manager rewrites the
|
||||
// whole file from its own keys (see statemanager.Manager.PersistState), and
|
||||
// this package's writer does the same in reverse.
|
||||
profileAccountSuffix = ".account.json"
|
||||
)
|
||||
|
||||
// profileAccountPathFor derives the account file path from a profile's config
|
||||
// path: netbird.cfg -> netbird.account.json, <id>.json -> <id>.account.json.
|
||||
//
|
||||
// Deriving from the config path rather than resolving the active profile keeps
|
||||
// the write on the profile the login actually ran for: Auth.login runs in a
|
||||
// goroutine, so the active profile can change under a flow already in flight.
|
||||
func profileAccountPathFor(configPath string) (string, error) {
|
||||
if configPath == "" {
|
||||
return "", fmt.Errorf("empty config path")
|
||||
}
|
||||
|
||||
base := filepath.Base(configPath)
|
||||
stem := strings.TrimSuffix(base, filepath.Ext(base))
|
||||
if stem == "" || stem == "." {
|
||||
return "", fmt.Errorf("config path %q has no filename stem", configPath)
|
||||
}
|
||||
|
||||
return filepath.Join(filepath.Dir(configPath), stem+profileAccountSuffix), nil
|
||||
}
|
||||
|
||||
// readProfileEmail returns the account email stored for the profile whose config
|
||||
// lives at configPath. A missing or unreadable file yields "", which leaves the
|
||||
// account choice to the IdP.
|
||||
func readProfileEmail(configPath string) string {
|
||||
accountPath, err := profileAccountPathFor(configPath)
|
||||
if err != nil {
|
||||
log.Debugf("no profile account path for login hint: %v", err)
|
||||
return ""
|
||||
}
|
||||
|
||||
var state profilemanager.ProfileState
|
||||
if _, err := util.ReadJson(accountPath, &state); err != nil {
|
||||
if !os.IsNotExist(err) {
|
||||
log.Debugf("failed to read profile account for login hint: %v", err)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
return state.Email
|
||||
}
|
||||
|
||||
// writeProfileEmail records the account email for the profile whose config lives
|
||||
// at configPath, so later logins can pass it as an OIDC login_hint. An empty
|
||||
// email is ignored rather than blanking what is already stored.
|
||||
func writeProfileEmail(configPath string, email string) error {
|
||||
if email == "" {
|
||||
return nil
|
||||
}
|
||||
|
||||
accountPath, err := profileAccountPathFor(configPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("resolve profile account path: %w", err)
|
||||
}
|
||||
|
||||
state := profilemanager.ProfileState{Email: email}
|
||||
if err := util.WriteJsonWithRestrictedPermission(context.Background(), accountPath, state); err != nil {
|
||||
return fmt.Errorf("write profile account: %w", err)
|
||||
}
|
||||
|
||||
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.
|
||||
func removeProfileEmail(configPath string) error {
|
||||
accountPath, err := profileAccountPathFor(configPath)
|
||||
if err != nil {
|
||||
return fmt.Errorf("resolve profile account path: %w", err)
|
||||
}
|
||||
|
||||
if err := os.Remove(accountPath); err != nil && !os.IsNotExist(err) {
|
||||
return fmt.Errorf("remove profile account: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
@@ -1,161 +0,0 @@
|
||||
package android
|
||||
|
||||
import (
|
||||
"os"
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestProfileAccountPathFor(t *testing.T) {
|
||||
tests := []struct {
|
||||
name string
|
||||
configPath string
|
||||
want string
|
||||
wantErr bool
|
||||
}{
|
||||
{
|
||||
name: "default profile",
|
||||
configPath: "/data/data/io.netbird.client/files/netbird.cfg",
|
||||
want: filepath.FromSlash("/data/data/io.netbird.client/files/netbird.account.json"),
|
||||
},
|
||||
{
|
||||
name: "id profile",
|
||||
configPath: "/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.json",
|
||||
want: filepath.FromSlash("/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.account.json"),
|
||||
},
|
||||
{
|
||||
name: "legacy name-keyed profile is handled the same way",
|
||||
configPath: "/data/data/io.netbird.client/files/profiles/work.json",
|
||||
want: filepath.FromSlash("/data/data/io.netbird.client/files/profiles/work.account.json"),
|
||||
},
|
||||
{
|
||||
name: "empty path is rejected",
|
||||
configPath: "",
|
||||
wantErr: true,
|
||||
},
|
||||
}
|
||||
|
||||
for _, tt := range tests {
|
||||
t.Run(tt.name, func(t *testing.T) {
|
||||
got, err := profileAccountPathFor(tt.configPath)
|
||||
if tt.wantErr {
|
||||
if err == nil {
|
||||
t.Fatalf("expected an error, got path %q", got)
|
||||
}
|
||||
return
|
||||
}
|
||||
if err != nil {
|
||||
t.Fatalf("unexpected error: %v", err)
|
||||
}
|
||||
if got != tt.want {
|
||||
t.Errorf("got %q, want %q", got, tt.want)
|
||||
}
|
||||
})
|
||||
}
|
||||
}
|
||||
|
||||
func TestProfileAccountPathForDefaultDoesNotCollide(t *testing.T) {
|
||||
root := "/data/data/io.netbird.client/files"
|
||||
|
||||
defaultAccount, err := profileAccountPathFor(filepath.Join(root, defaultConfigFilename))
|
||||
if err != nil {
|
||||
t.Fatalf("default profile: %v", err)
|
||||
}
|
||||
|
||||
idAccount, err := profileAccountPathFor(filepath.Join(root, profilesSubdir, "abc123.json"))
|
||||
if err != nil {
|
||||
t.Fatalf("id profile: %v", err)
|
||||
}
|
||||
|
||||
if defaultAccount == idAccount {
|
||||
t.Fatalf("default and id profile share an account file: %q", defaultAccount)
|
||||
}
|
||||
}
|
||||
|
||||
// The account file must never land on the engine state file: on Android both
|
||||
// resolve under files/, and the state manager rewrites the whole file from its
|
||||
// own keys, so sharing a path would have the two overwrite each other. The
|
||||
// expected names here mirror ProfileManager.GetStateFilePath.
|
||||
func TestProfileAccountPathAvoidsEngineStateFile(t *testing.T) {
|
||||
root := "/data/data/io.netbird.client/files"
|
||||
|
||||
cases := []struct {
|
||||
configPath string
|
||||
engineState string
|
||||
}{
|
||||
{
|
||||
configPath: filepath.Join(root, defaultConfigFilename),
|
||||
engineState: filepath.Join(root, "state.json"),
|
||||
},
|
||||
{
|
||||
configPath: filepath.Join(root, profilesSubdir, "abc123.json"),
|
||||
engineState: filepath.Join(root, profilesSubdir, "abc123.state.json"),
|
||||
},
|
||||
}
|
||||
|
||||
for _, c := range cases {
|
||||
account, err := profileAccountPathFor(c.configPath)
|
||||
if err != nil {
|
||||
t.Fatalf("%s: %v", c.configPath, err)
|
||||
}
|
||||
if account == c.engineState {
|
||||
t.Errorf("account file collides with the engine state file: %q", account)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func TestWriteThenReadProfileEmail(t *testing.T) {
|
||||
configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
|
||||
if err := ensureDirFor(t, configPath); err != nil {
|
||||
t.Fatalf("prepare dir: %v", err)
|
||||
}
|
||||
|
||||
if got := readProfileEmail(configPath); got != "" {
|
||||
t.Errorf("expected no email before a login, got %q", got)
|
||||
}
|
||||
|
||||
const email = "user@example.com"
|
||||
if err := writeProfileEmail(configPath, email); err != nil {
|
||||
t.Fatalf("write: %v", err)
|
||||
}
|
||||
|
||||
if got := readProfileEmail(configPath); got != email {
|
||||
t.Errorf("got %q, want %q", got, email)
|
||||
}
|
||||
|
||||
if err := removeProfileEmail(configPath); err != nil {
|
||||
t.Fatalf("remove: %v", err)
|
||||
}
|
||||
if got := readProfileEmail(configPath); got != "" {
|
||||
t.Errorf("expected no email after logout, got %q", got)
|
||||
}
|
||||
|
||||
// Logout 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)
|
||||
}
|
||||
}
|
||||
|
||||
func TestWriteProfileEmailIgnoresEmpty(t *testing.T) {
|
||||
configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
|
||||
if err := ensureDirFor(t, configPath); err != nil {
|
||||
t.Fatalf("prepare dir: %v", err)
|
||||
}
|
||||
|
||||
const email = "user@example.com"
|
||||
if err := writeProfileEmail(configPath, email); err != nil {
|
||||
t.Fatalf("write: %v", err)
|
||||
}
|
||||
if err := writeProfileEmail(configPath, ""); err != nil {
|
||||
t.Fatalf("write empty: %v", err)
|
||||
}
|
||||
|
||||
if got := readProfileEmail(configPath); got != email {
|
||||
t.Errorf("empty write clobbered the stored email: got %q, want %q", got, email)
|
||||
}
|
||||
}
|
||||
|
||||
func ensureDirFor(t *testing.T, path string) error {
|
||||
t.Helper()
|
||||
return os.MkdirAll(filepath.Dir(path), 0o700)
|
||||
}
|
||||
@@ -278,7 +278,7 @@ func (c *Client) endExtend() {
|
||||
}
|
||||
|
||||
func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
|
||||
cfg, cfgPath, cc := c.authSnapshot()
|
||||
cfg, _, cc := c.stateSnapshot()
|
||||
if cfg == nil || cc == nil {
|
||||
return fmt.Errorf("engine is not running")
|
||||
}
|
||||
@@ -293,10 +293,7 @@ func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isA
|
||||
}
|
||||
defer authClient.Close()
|
||||
|
||||
// Passing the config path makes the flow pick up the login_hint: an extend
|
||||
// renews the session of the account already signed in, so it must not stop to
|
||||
// offer a choice.
|
||||
a := NewAuthWithConfig(ctx, cfg, cfgPath)
|
||||
a := &Auth{ctx: ctx, config: cfg}
|
||||
tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
|
||||
if err != nil {
|
||||
return fmt.Errorf("interactive sso login failed: %v", err)
|
||||
|
||||
@@ -2,7 +2,6 @@ package anonymize
|
||||
|
||||
import (
|
||||
"crypto/rand"
|
||||
"encoding/base64"
|
||||
"fmt"
|
||||
"math/big"
|
||||
"net"
|
||||
@@ -16,88 +15,13 @@ 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
|
||||
// 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
|
||||
currentAnonIPv4 netip.Addr
|
||||
currentAnonIPv6 netip.Addr
|
||||
startAnonIPv4 netip.Addr
|
||||
startAnonIPv6 netip.Addr
|
||||
|
||||
domainKeyRegex *regexp.Regexp
|
||||
}
|
||||
@@ -108,50 +32,25 @@ 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) ||
|
||||
@@ -160,100 +59,18 @@ 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 {
|
||||
a.ipAnonymizer[ip] = a.nextAnonIP(ip)
|
||||
if ip.Is4() {
|
||||
a.ipAnonymizer[ip] = a.currentAnonIPv4
|
||||
a.currentAnonIPv4 = a.currentAnonIPv4.Next()
|
||||
} else {
|
||||
a.ipAnonymizer[ip] = a.currentAnonIPv6
|
||||
a.currentAnonIPv6 = a.currentAnonIPv6.Next()
|
||||
}
|
||||
}
|
||||
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)
|
||||
@@ -272,12 +89,12 @@ 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() {
|
||||
return inPoolRange(ip, a.startAnonIPv4, a.currentAnonIPv4) ||
|
||||
inPoolRange(ip, a.startAnonInternalIPv4, a.currentAnonInternalIPv4)
|
||||
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
|
||||
}
|
||||
return inPoolRange(ip, a.startAnonIPv6, a.currentAnonIPv6) ||
|
||||
inPoolRange(ip, a.startAnonInternalIPv6, a.currentAnonInternalIPv6)
|
||||
return false
|
||||
}
|
||||
|
||||
func (a *Anonymizer) AnonymizeIPString(ip string) string {
|
||||
@@ -301,17 +118,14 @@ func (a *Anonymizer) AnonymizeDomain(domain string) string {
|
||||
baseDomain = domain[:len(domain)-1]
|
||||
}
|
||||
|
||||
if strings.HasSuffix(baseDomain, anonTLD) {
|
||||
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) {
|
||||
return domain
|
||||
}
|
||||
|
||||
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
|
||||
@@ -327,53 +141,12 @@ func (a *Anonymizer) AnonymizeDomain(domain string) string {
|
||||
}
|
||||
|
||||
result := strings.Replace(baseDomain, baseForLookup, anonymized, 1)
|
||||
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
|
||||
if hasDot {
|
||||
result += "."
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
// anonymizeLabels replaces each dot-separated label with a consistent
|
||||
// numbered placeholder ("<placeholder>-<n>"). 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 {
|
||||
@@ -408,70 +181,16 @@ func (a *Anonymizer) AnonymizeString(str string) string {
|
||||
str = ipv4Regex.ReplaceAllStringFunc(str, a.AnonymizeIPString)
|
||||
str = ipv6Regex.ReplaceAllStringFunc(str, a.AnonymizeIPString)
|
||||
|
||||
for _, domain := range a.sortedDomains() {
|
||||
str = strings.ReplaceAll(str, domain, a.domainAnonymizer[domain])
|
||||
for domain, anonDomain := range a.domainAnonymizer {
|
||||
str = strings.ReplaceAll(str, domain, anonDomain)
|
||||
}
|
||||
|
||||
str = a.AnonymizeSchemeURI(str)
|
||||
str = a.AnonymizeDNSLogLine(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 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.
|
||||
func (a *Anonymizer) AnonymizeSchemeURI(text string) string {
|
||||
re := regexp.MustCompile(`(?i)\b(wss?://|rels?://|stuns?:|turns?:|https?://)\S+\b`)
|
||||
@@ -520,79 +239,10 @@ func isWellKnown(addr netip.Addr) bool {
|
||||
"128.0.0.0", "8000::", // 2nd split subnet for default routes
|
||||
}
|
||||
|
||||
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 {
|
||||
if slices.Contains(wellKnown, addr.String()) {
|
||||
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)
|
||||
|
||||
|
||||
@@ -1,11 +1,8 @@
|
||||
package anonymize_test
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/base64"
|
||||
"net/netip"
|
||||
"regexp"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -47,301 +44,6 @@ 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 {
|
||||
|
||||
@@ -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
|
||||
@@ -156,11 +156,6 @@ 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
|
||||
@@ -173,11 +168,10 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
|
||||
|
||||
client := proto.NewDaemonServiceClient(conn)
|
||||
request := &proto.DebugBundleRequest{
|
||||
Anonymize: anonymizeEnabled,
|
||||
AnonymizeLevel: anonymizeLevel.String(),
|
||||
SystemInfo: systemInfoFlag,
|
||||
LogFileCount: logFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
Anonymize: anonymizeFlag,
|
||||
SystemInfo: systemInfoFlag,
|
||||
LogFileCount: logFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
}
|
||||
if uploadBundleFlag {
|
||||
request.UploadURL = uploadBundleURLFlag
|
||||
@@ -235,11 +229,6 @@ 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
|
||||
@@ -379,11 +368,10 @@ func runForDuration(cmd *cobra.Command, args []string) error {
|
||||
cmd.Println("Creating debug bundle...")
|
||||
|
||||
request := &proto.DebugBundleRequest{
|
||||
Anonymize: anonymizeEnabled,
|
||||
AnonymizeLevel: anonymizeLevel.String(),
|
||||
SystemInfo: systemInfoFlag,
|
||||
LogFileCount: logFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
Anonymize: anonymizeFlag,
|
||||
SystemInfo: systemInfoFlag,
|
||||
LogFileCount: logFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
}
|
||||
if uploadBundleFlag {
|
||||
request.UploadURL = uploadBundleURLFlag
|
||||
|
||||
@@ -21,7 +21,6 @@ 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"
|
||||
)
|
||||
@@ -70,7 +69,6 @@ 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).
|
||||
@@ -158,8 +156,7 @@ 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 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().BoolVarP(&anonymizeFlag, "anonymize", "A", false, "anonymize IP addresses and non-netbird.io domains in logs and status output")
|
||||
rootCmd.PersistentFlags().StringVarP(&configPath, "config", "c", profilemanager.DefaultConfigPath, "Overrides the default profile file location")
|
||||
|
||||
rootCmd.AddCommand(upCmd)
|
||||
@@ -296,19 +293,6 @@ 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)
|
||||
|
||||
@@ -121,14 +121,8 @@ 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: anonymizeEnabled,
|
||||
AnonymizeLevel: anonymizeLevel,
|
||||
Anonymize: anonymizeFlag,
|
||||
DaemonVersion: resp.GetDaemonVersion(),
|
||||
DaemonStatus: nbstatus.ParseDaemonStatus(status),
|
||||
StatusFilter: statusFilter,
|
||||
|
||||
@@ -2,8 +2,8 @@
|
||||
// its wg interface into firewalld's "trusted" zone. This is required because
|
||||
// firewalld's nftables chains are created with NFT_CHAIN_OWNER on recent
|
||||
// versions, which returns EPERM to any other process that tries to insert
|
||||
// rules into them. Trusting the interface makes firewalld itself add the
|
||||
// accept rules to its own chains instead.
|
||||
// rules into them. The workaround mirrors what Tailscale does: let firewalld
|
||||
// itself add the accept rules to its own chains by trusting the interface.
|
||||
package firewalld
|
||||
|
||||
// TrustedZone is the firewalld zone name used for interfaces whose traffic
|
||||
|
||||
@@ -22,16 +22,6 @@ 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
|
||||
}
|
||||
@@ -226,15 +216,8 @@ func (s *ICEBind) createReceiverFn(pc wgConn.BatchReader, conn *net.UDPConn, rxO
|
||||
for i := 0; i < numMsgs; i++ {
|
||||
msg := &(*msgs)[i]
|
||||
|
||||
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
|
||||
// todo: handle err
|
||||
if ok, _ := s.filterOutStunMessages(msg.Buffers, msg.N, msg.Addr); ok {
|
||||
continue
|
||||
}
|
||||
sizes[i] = msg.N
|
||||
@@ -288,16 +271,11 @@ func (s *ICEBind) createOrUpdateMux() {
|
||||
|
||||
func (s *ICEBind) filterOutStunMessages(buffers [][]byte, n int, addr net.Addr) (bool, error) {
|
||||
for i := range buffers {
|
||||
if n > len(buffers[i]) {
|
||||
continue
|
||||
}
|
||||
pkt := buffers[i][:n]
|
||||
|
||||
if isWireGuardMsg(pkt) || !stun.IsMessage(pkt) {
|
||||
if !stun.IsMessage(buffers[i]) {
|
||||
continue
|
||||
}
|
||||
|
||||
msg, err := s.parseSTUNMessage(pkt)
|
||||
msg, err := s.parseSTUNMessage(buffers[i][:n])
|
||||
if err != nil {
|
||||
buffers[i] = []byte{}
|
||||
return true, err
|
||||
@@ -369,34 +347,18 @@ func putMessages(msgs *[]ipv6.Message, msgsPool *sync.Pool) {
|
||||
msgsPool.Put(msgs)
|
||||
}
|
||||
|
||||
// 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
|
||||
}
|
||||
|
||||
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
|
||||
// The first buffer should contain at least 4 bytes for type
|
||||
if len(buffers[0]) < 4 {
|
||||
return true
|
||||
}
|
||||
|
||||
msgType := binary.LittleEndian.Uint32(buffers[0][:4])
|
||||
return msgType == wgMsgTypeTransport && n > wgMinMsgSize
|
||||
// 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
|
||||
}
|
||||
|
||||
@@ -1,215 +0,0 @@
|
||||
//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")
|
||||
}
|
||||
@@ -34,8 +34,9 @@ import (
|
||||
"github.com/netbirdio/netbird/shared/netiputil"
|
||||
)
|
||||
|
||||
const readmeContent = `This debug bundle contains the following files.
|
||||
If anonymization is enabled (--anonymize / --anonymize-level), the files are anonymized to protect sensitive information.
|
||||
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.
|
||||
|
||||
status.txt: Anonymized status information of the NetBird client.
|
||||
client.log: Most recent, anonymized client log file of the NetBird client.
|
||||
@@ -69,34 +70,21 @@ 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. The level applied to this bundle is recorded at the top of this file. Here's how the anonymization was applied:
|
||||
The files in this bundle have been anonymized to protect sensitive information. Here's how the anonymization was applied:
|
||||
|
||||
IP Addresses
|
||||
|
||||
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.
|
||||
IPv4 addresses are replaced with addresses starting from 198.51.100.0
|
||||
IPv6 addresses are replaced with addresses starting from 100::
|
||||
|
||||
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:
|
||||
@@ -293,7 +281,6 @@ type BundleGenerator struct {
|
||||
cliVersion string
|
||||
|
||||
anonymize bool
|
||||
anonymizeLevel anonymize.Level
|
||||
includeSystemInfo bool
|
||||
logFileCount uint32
|
||||
|
||||
@@ -301,10 +288,7 @@ type BundleGenerator struct {
|
||||
}
|
||||
|
||||
type BundleConfig struct {
|
||||
Anonymize bool
|
||||
// AnonymizeLevel selects how much the anonymizer redacts.
|
||||
// anonymize.LevelStrict implies Anonymize.
|
||||
AnonymizeLevel anonymize.Level
|
||||
Anonymize bool
|
||||
IncludeSystemInfo bool
|
||||
LogFileCount uint32
|
||||
}
|
||||
@@ -343,11 +327,8 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
|
||||
uiLogOpener = openLogFile
|
||||
}
|
||||
|
||||
anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses())
|
||||
anonymizer.SetLevel(cfg.AnonymizeLevel)
|
||||
|
||||
return &BundleGenerator{
|
||||
anonymizer: anonymizer,
|
||||
anonymizer: anonymize.NewAnonymizer(anonymize.DefaultAddresses()),
|
||||
|
||||
internalConfig: deps.InternalConfig,
|
||||
statusRecorder: deps.StatusRecorder,
|
||||
@@ -364,8 +345,7 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
|
||||
daemonVersion: deps.DaemonVersion,
|
||||
cliVersion: deps.CliVersion,
|
||||
|
||||
anonymize: cfg.Anonymize || cfg.AnonymizeLevel >= anonymize.LevelStrict,
|
||||
anonymizeLevel: cfg.AnonymizeLevel,
|
||||
anonymize: cfg.Anonymize,
|
||||
includeSystemInfo: cfg.IncludeSystemInfo,
|
||||
logFileCount: logFileCount,
|
||||
}
|
||||
@@ -505,13 +485,7 @@ func (g *BundleGenerator) addSystemInfo() {
|
||||
}
|
||||
|
||||
func (g *BundleGenerator) addReadme() error {
|
||||
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)
|
||||
readmeReader := strings.NewReader(readmeContent)
|
||||
if err := g.addFileToZip(readmeReader, "README.txt"); err != nil {
|
||||
return fmt.Errorf("add README file to zip: %w", err)
|
||||
}
|
||||
@@ -533,10 +507,9 @@ func (g *BundleGenerator) addStatus() error {
|
||||
fullStatus := g.statusRecorder.GetFullStatus()
|
||||
protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
|
||||
overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
|
||||
Anonymize: g.anonymize,
|
||||
AnonymizeLevel: g.anonymizeLevel,
|
||||
ProfileName: profName,
|
||||
DaemonVersion: g.daemonVersion,
|
||||
Anonymize: g.anonymize,
|
||||
ProfileName: profName,
|
||||
DaemonVersion: g.daemonVersion,
|
||||
})
|
||||
overview.CliVersion = g.cliVersion
|
||||
statusOutput := overview.FullDetailSummary()
|
||||
@@ -689,7 +662,7 @@ 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", g.anonymizer.AnonymizeWGKey(key.PublicKey().String())))
|
||||
configContent.WriteString(fmt.Sprintf("PublicKey: %s\n", key.PublicKey().String()))
|
||||
}
|
||||
configContent.WriteString(fmt.Sprintf("WgIface: %s\n", g.internalConfig.WgIface))
|
||||
configContent.WriteString(fmt.Sprintf("WgPort: %d\n", g.internalConfig.WgPort))
|
||||
@@ -979,11 +952,6 @@ 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)
|
||||
}
|
||||
@@ -1011,13 +979,6 @@ 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
|
||||
@@ -1029,27 +990,6 @@ 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")
|
||||
@@ -1522,7 +1462,6 @@ func anonymizeRemotePeer(peer *mgmProto.RemotePeerConfig, anonymizer *anonymize.
|
||||
}
|
||||
|
||||
peer.Fqdn = anonymizer.AnonymizeDomain(peer.Fqdn)
|
||||
peer.WgPubKey = anonymizer.AnonymizeWGKey(peer.WgPubKey)
|
||||
|
||||
anonymizeSSHConfig(peer.SshConfig)
|
||||
}
|
||||
|
||||
@@ -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", g.anonymizer.AnonymizeWGKey(s.PublicKey)))
|
||||
sb.WriteString(fmt.Sprintf(" public key: %s\n", 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", g.anonymizer.AnonymizeWGKey(peer.PublicKey)))
|
||||
sb.WriteString(fmt.Sprintf("\npeer: %s\n", peer.PublicKey))
|
||||
if peer.Endpoint.IP != nil {
|
||||
if g.anonymize {
|
||||
anonEndpoint := g.anonymizer.AnonymizeUDPAddr(peer.Endpoint)
|
||||
@@ -54,11 +54,7 @@ func (g *BundleGenerator) toWGShowFormat(s *configurer.Stats) string {
|
||||
if len(peer.AllowedIPs) > 0 {
|
||||
var ipStrings []string
|
||||
for _, ipnet := range peer.AllowedIPs {
|
||||
ipStr := ipnet.String()
|
||||
if g.anonymize {
|
||||
ipStr = g.anonymizer.AnonymizeIPString(ipStr)
|
||||
}
|
||||
ipStrings = append(ipStrings, ipStr)
|
||||
ipStrings = append(ipStrings, ipnet.String())
|
||||
}
|
||||
sb.WriteString(fmt.Sprintf(" allowed ips: %s\n", strings.Join(ipStrings, ", ")))
|
||||
}
|
||||
|
||||
@@ -23,7 +23,6 @@ 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"
|
||||
@@ -1386,7 +1385,6 @@ 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),
|
||||
}
|
||||
|
||||
@@ -4,17 +4,11 @@ package metrics
|
||||
type ConnectionType string
|
||||
|
||||
const (
|
||||
// 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"
|
||||
// ConnectionTypeICE represents a direct peer-to-peer connection using ICE
|
||||
ConnectionTypeICE ConnectionType = "ice"
|
||||
|
||||
// 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
|
||||
|
||||
@@ -28,7 +28,7 @@ func TestInfluxDBMetrics_RecordAndExport(t *testing.T) {
|
||||
WgHandshakeSuccess: time.Now().Add(-1 * time.Second),
|
||||
}
|
||||
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICEP2P, false, ts)
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, 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", ConnectionTypeICEP2P, false, ts)
|
||||
m.RecordConnectionStages(context.Background(), agentInfo, "pair123", ConnectionTypeICE, false, ts)
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
|
||||
@@ -56,33 +56,14 @@ Measurement: `netbird_peer_connection`
|
||||
|
||||
Tags:
|
||||
- `deployment_type`: "cloud" | "selfhosted" | "unknown"
|
||||
- `connection_type`: "ice_p2p" | "ice_turn" | "relay" (see below)
|
||||
- `connection_type`: "ice" | "relay"
|
||||
- `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`
|
||||
|
||||
@@ -307,8 +307,6 @@ 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 {
|
||||
@@ -961,9 +959,12 @@ func (conn *Conn) recordConnectionMetrics() {
|
||||
priority := conn.currentConnPriority
|
||||
conn.mu.Unlock()
|
||||
|
||||
connType := metricsConnType(priority)
|
||||
if connType == metrics.ConnectionTypeUnknown {
|
||||
return
|
||||
var connType metrics.ConnectionType
|
||||
switch priority {
|
||||
case conntype.Relay:
|
||||
connType = metrics.ConnectionTypeRelay
|
||||
default:
|
||||
connType = metrics.ConnectionTypeICE
|
||||
}
|
||||
|
||||
// Record metrics with timestamps - duration calculation happens in metrics package
|
||||
@@ -1064,16 +1065,3 @@ 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
|
||||
}
|
||||
}
|
||||
|
||||
@@ -11,8 +11,6 @@ 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"
|
||||
@@ -388,33 +386,3 @@ 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)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -14,7 +14,6 @@ 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"
|
||||
@@ -29,13 +28,6 @@ import (
|
||||
types "github.com/netbirdio/netbird/upload-server/types"
|
||||
)
|
||||
|
||||
// AnonymizeLevelDefault and AnonymizeLevelStrict are the accepted
|
||||
// anonymizeLevel values for DebugBundle.
|
||||
const (
|
||||
AnonymizeLevelDefault = nbAnonymize.LevelDefaultString
|
||||
AnonymizeLevelStrict = nbAnonymize.LevelStrictString
|
||||
)
|
||||
|
||||
// ConnectionListener export internal Listener for mobile
|
||||
type ConnectionListener interface {
|
||||
peer.Listener
|
||||
@@ -208,10 +200,8 @@ 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). 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) {
|
||||
// config from disk (or the preloaded tvOS config).
|
||||
func (c *Client) DebugBundle(anonymize bool) (string, error) {
|
||||
cfg, cc := c.stateSnapshot()
|
||||
|
||||
// If the engine hasn't been started, load config so we can reach management.
|
||||
@@ -261,7 +251,6 @@ func (c *Client) DebugBundle(anonymize bool, anonymizeLevel string) (string, err
|
||||
deps,
|
||||
debug.BundleConfig{
|
||||
Anonymize: anonymize,
|
||||
AnonymizeLevel: nbAnonymize.ParseLevel(anonymizeLevel),
|
||||
IncludeSystemInfo: true,
|
||||
},
|
||||
)
|
||||
|
||||
@@ -2781,11 +2781,6 @@ 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
|
||||
}
|
||||
@@ -2862,13 +2857,6 @@ 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"`
|
||||
@@ -7265,7 +7253,7 @@ 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\"\x84\x02\n" +
|
||||
"\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xdc\x01\n" +
|
||||
"\x12DebugBundleRequest\x12\x1c\n" +
|
||||
"\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x1e\n" +
|
||||
"\n" +
|
||||
@@ -7276,8 +7264,7 @@ const file_daemon_proto_rawDesc = "" +
|
||||
"\n" +
|
||||
"cliVersion\x18\x06 \x01(\tR\n" +
|
||||
"cliVersion\x12&\n" +
|
||||
"\x0euploadInsecure\x18\a \x01(\bR\x0euploadInsecure\x12&\n" +
|
||||
"\x0eanonymizeLevel\x18\b \x01(\tR\x0eanonymizeLevel\"}\n" +
|
||||
"\x0euploadInsecure\x18\a \x01(\bR\x0euploadInsecure\"}\n" +
|
||||
"\x13DebugBundleResponse\x12\x12\n" +
|
||||
"\x04path\x18\x01 \x01(\tR\x04path\x12 \n" +
|
||||
"\vuploadedKey\x18\x02 \x01(\tR\vuploadedKey\x120\n" +
|
||||
|
||||
@@ -540,11 +540,6 @@ 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 {
|
||||
|
||||
@@ -16,7 +16,6 @@ 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"
|
||||
@@ -123,7 +122,6 @@ 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(),
|
||||
},
|
||||
|
||||
@@ -8,6 +8,8 @@ import (
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
"google.golang.org/grpc/codes"
|
||||
gstatus "google.golang.org/grpc/status"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal"
|
||||
"github.com/netbirdio/netbird/client/proto"
|
||||
@@ -25,9 +27,9 @@ func TestLogin_ManagementUnreachableIsReturnedInsteadOfDemandingSSO(t *testing.T
|
||||
|
||||
unreachable := errors.New("create connection: dial context: context deadline exceeded")
|
||||
attempts := 0
|
||||
s.isLoginRequiredFn = func(context.Context) (bool, error) {
|
||||
s.loginAttemptFn = func(context.Context, string, string) (internal.StatusType, error) {
|
||||
attempts++
|
||||
return false, unreachable
|
||||
return internal.StatusLoginFailed, unreachable
|
||||
}
|
||||
|
||||
resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
|
||||
@@ -53,12 +55,15 @@ func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
|
||||
s.rootCtx = internal.CtxInitState(context.Background())
|
||||
breakProfilePrivateKey(t, cfgPath)
|
||||
|
||||
s.isLoginRequiredFn = func(context.Context) (bool, error) {
|
||||
return true, nil
|
||||
refused := gstatus.Error(codes.PermissionDenied, "peer is not registered")
|
||||
s.loginAttemptFn = func(context.Context, string, string) (internal.StatusType, error) {
|
||||
return internal.StatusNeedsLogin, refused
|
||||
}
|
||||
|
||||
_, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
|
||||
require.Error(t, err)
|
||||
require.NotErrorIs(t, err, refused,
|
||||
"the refusal was handed back to the caller instead of starting the SSO flow")
|
||||
|
||||
status, stateErr := internal.CtxGetState(s.rootCtx).Status()
|
||||
require.NoError(t, stateErr)
|
||||
@@ -66,32 +71,6 @@ func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
|
||||
"the SSO flow setup was never reached with the broken key")
|
||||
}
|
||||
|
||||
func TestLogin_SetupKeyStillRunsWhenPeerNeedsLogin(t *testing.T) {
|
||||
s, _, _, username, _ := setupServerWithProfile(t)
|
||||
s.rootCtx = internal.CtxInitState(context.Background())
|
||||
|
||||
s.isLoginRequiredFn = func(context.Context) (bool, error) {
|
||||
return true, nil
|
||||
}
|
||||
|
||||
var keysTried []string
|
||||
s.loginAttemptFn = func(_ context.Context, setupKey, _ string) (internal.StatusType, error) {
|
||||
keysTried = append(keysTried, setupKey)
|
||||
return "", nil
|
||||
}
|
||||
|
||||
setupKey := "A2C8E32F-AEB2-4B45-8FD3-8A0C1B2D3E4F"
|
||||
resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username, SetupKey: setupKey})
|
||||
require.NoError(t, err, "the probe's outcome leaked out as the login result")
|
||||
require.NotNil(t, resp)
|
||||
require.Equal(t, []string{setupKey}, keysTried, "the setup key never reached the login attempt")
|
||||
require.Nil(t, s.oauthAuthFlow.flow, "a setup-key login started an SSO flow")
|
||||
|
||||
status, err := internal.CtxGetState(s.rootCtx).Status()
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, internal.StatusIdle, status)
|
||||
}
|
||||
|
||||
// breakProfilePrivateKey replaces the profile's private key with an unparseable
|
||||
// one, which makes any attempt to build a Management client fail on the spot.
|
||||
func breakProfilePrivateKey(t *testing.T, cfgPath string) {
|
||||
|
||||
@@ -140,8 +140,6 @@ type Server struct {
|
||||
// it to drive the login outcomes that need a server on the other end;
|
||||
// production leaves it nil, and every login goes through loginAttempt.
|
||||
loginAttemptFn func(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error)
|
||||
|
||||
isLoginRequiredFn func(ctx context.Context) (bool, error)
|
||||
}
|
||||
|
||||
type oauthAuthFlow struct {
|
||||
@@ -386,21 +384,6 @@ func (s *Server) attemptLogin(ctx context.Context, setupKey, jwtToken string) (i
|
||||
return s.loginAttempt(ctx, setupKey, jwtToken)
|
||||
}
|
||||
|
||||
func (s *Server) isLoginRequired(ctx context.Context) (bool, error) {
|
||||
if s.isLoginRequiredFn != nil {
|
||||
return s.isLoginRequiredFn(ctx)
|
||||
}
|
||||
|
||||
authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
|
||||
if err != nil {
|
||||
log.Errorf("failed to create auth client: %v", err)
|
||||
return false, err
|
||||
}
|
||||
defer authClient.Close()
|
||||
|
||||
return authClient.IsLoginRequired(ctx)
|
||||
}
|
||||
|
||||
// loginAttempt attempts to login using the provided information. It returns
|
||||
// StatusNeedsLogin when Management refused the peer's credentials and
|
||||
// StatusLoginFailed for every other failure, so callers can tell an
|
||||
@@ -657,22 +640,22 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
|
||||
s.config = config
|
||||
s.mutex.Unlock()
|
||||
|
||||
// A probe that errors leaves the login undecided: Management unreachable, a
|
||||
loginStatus, err := s.attemptLogin(ctx, "", "")
|
||||
if err == nil {
|
||||
state.Set(internal.StatusIdle)
|
||||
return &proto.LoginResponse{}, nil
|
||||
}
|
||||
|
||||
// Only an authentication refusal means the peer has to (re-)authenticate.
|
||||
// Any other failure leaves the login undecided: Management unreachable, a
|
||||
// restart mid-request, an internal error. Those are returned for the caller
|
||||
// to retry, because turning them into an SSO prompt asks the user to solve
|
||||
// something that is not theirs to solve, and a browser login cannot succeed
|
||||
// while Management is unreachable anyway. Only Management refusing the
|
||||
// peer's key is a decision, and IsLoginRequired reports that as
|
||||
// needsLogin=true rather than an error.
|
||||
needsLogin, err := s.isLoginRequired(ctx)
|
||||
if err != nil {
|
||||
state.Set(internal.StatusLoginFailed)
|
||||
// while Management is unreachable anyway.
|
||||
if loginStatus != internal.StatusNeedsLogin {
|
||||
state.Set(loginStatus)
|
||||
return nil, err
|
||||
}
|
||||
if !needsLogin {
|
||||
state.Set(internal.StatusIdle)
|
||||
return &proto.LoginResponse{}, nil
|
||||
}
|
||||
|
||||
if msg.SetupKey == "" {
|
||||
hint := ""
|
||||
@@ -1815,9 +1798,6 @@ func (s *Server) RequestExtendAuthSession(
|
||||
if connectClient == nil {
|
||||
return nil, gstatus.Errorf(codes.FailedPrecondition, "client is not running")
|
||||
}
|
||||
if connectClient.Engine() == nil {
|
||||
return nil, gstatus.Errorf(codes.FailedPrecondition, "session can no longer be extended, log in again to reconnect")
|
||||
}
|
||||
|
||||
hint := ""
|
||||
if msg.Hint != nil {
|
||||
|
||||
@@ -46,10 +46,7 @@ func ParseDaemonStatus(s string) DaemonStatus {
|
||||
|
||||
// ConvertOptions holds parameters for ConvertToStatusOutputOverview.
|
||||
type ConvertOptions struct {
|
||||
Anonymize bool
|
||||
// AnonymizeLevel selects how much the anonymizer redacts. Only
|
||||
// meaningful when Anonymize is set.
|
||||
AnonymizeLevel anonymize.Level
|
||||
Anonymize bool
|
||||
DaemonVersion string
|
||||
DaemonStatus DaemonStatus
|
||||
StatusFilter string
|
||||
@@ -220,7 +217,6 @@ func ConvertToStatusOutputOverview(pbFullStatus *proto.FullStatus, opts ConvertO
|
||||
|
||||
if opts.Anonymize {
|
||||
anonymizer := anonymize.NewAnonymizer(anonymize.DefaultAddresses())
|
||||
anonymizer.SetLevel(opts.AnonymizeLevel)
|
||||
anonymizeOverview(anonymizer, &overview)
|
||||
}
|
||||
|
||||
@@ -980,7 +976,6 @@ 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)
|
||||
}
|
||||
@@ -1012,7 +1007,6 @@ 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 {
|
||||
|
||||
@@ -71,12 +71,10 @@ type BundleOptions = {
|
||||
hasWindow: boolean;
|
||||
totalSec: number;
|
||||
uploadUrl: string;
|
||||
anonymizeLevel: AnonymizeLevel;
|
||||
anonymize: boolean;
|
||||
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.
|
||||
@@ -189,10 +187,7 @@ const runBundleFlow = async (
|
||||
|
||||
if (opts.uploadUrl) setStage({ kind: "uploading" });
|
||||
const result = await DebugSvc.Bundle({
|
||||
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",
|
||||
anonymize: opts.anonymize,
|
||||
systemInfo: opts.systemInfo,
|
||||
uploadUrl: opts.uploadUrl,
|
||||
logFileCount,
|
||||
@@ -203,7 +198,7 @@ const runBundleFlow = async (
|
||||
};
|
||||
|
||||
const useDebugBundle = () => {
|
||||
const [anonymizeLevel, setAnonymizeLevel] = useState<AnonymizeLevel>("none");
|
||||
const [anonymize, setAnonymize] = useState(false);
|
||||
const [systemInfo, setSystemInfo] = useState(true);
|
||||
const [upload, setUpload] = useState(true);
|
||||
const [trace, setTrace] = useState(true);
|
||||
@@ -245,7 +240,7 @@ const useDebugBundle = () => {
|
||||
hasWindow: capture && totalSec > 0,
|
||||
totalSec,
|
||||
uploadUrl: upload ? NETBIRD_UPLOAD_URL : "",
|
||||
anonymizeLevel,
|
||||
anonymize,
|
||||
systemInfo,
|
||||
};
|
||||
|
||||
@@ -277,8 +272,8 @@ const useDebugBundle = () => {
|
||||
};
|
||||
|
||||
return {
|
||||
anonymizeLevel,
|
||||
setAnonymizeLevel,
|
||||
anonymize,
|
||||
setAnonymize,
|
||||
systemInfo,
|
||||
setSystemInfo,
|
||||
upload,
|
||||
|
||||
@@ -1,35 +0,0 @@
|
||||
import { useCallback, useEffect, useState } from "react";
|
||||
import { Preferences } from "@bindings/services";
|
||||
|
||||
export const useKeepConnectedOnQuit = () => {
|
||||
const [keepConnected, setKeepConnected] = useState<boolean | null>(null);
|
||||
|
||||
useEffect(() => {
|
||||
let cancelled = false;
|
||||
Preferences.Get()
|
||||
.then((prefs) => {
|
||||
if (cancelled) return;
|
||||
setKeepConnected(prefs?.keepConnectedOnQuit ?? false);
|
||||
})
|
||||
.catch((err: unknown) => {
|
||||
if (cancelled) return;
|
||||
console.warn("[useKeepConnectedOnQuit] load preferences failed", err);
|
||||
setKeepConnected(false);
|
||||
});
|
||||
return () => {
|
||||
cancelled = true;
|
||||
};
|
||||
}, []);
|
||||
|
||||
const setKeepConnectedOnQuit = useCallback(async (keep: boolean) => {
|
||||
setKeepConnected(keep);
|
||||
try {
|
||||
await Preferences.SetKeepConnectedOnQuit(keep);
|
||||
} catch (err: unknown) {
|
||||
setKeepConnected(!keep);
|
||||
console.error("[useKeepConnectedOnQuit] SetKeepConnectedOnQuit failed", err);
|
||||
}
|
||||
}, []);
|
||||
|
||||
return { keepConnected, setKeepConnectedOnQuit };
|
||||
};
|
||||
@@ -11,7 +11,7 @@ import { DialogHeading } from "@/components/dialog/DialogHeading";
|
||||
import { SquareIcon } from "@/components/SquareIcon";
|
||||
import { Connection, Profiles as ProfilesSvc, Session, WindowManager } from "@bindings/services";
|
||||
import { useAutoSizeWindow } from "@/hooks/useAutoSizeWindow";
|
||||
import { EVENT_BROWSER_LOGIN_CANCEL, EVENT_TRIGGER_LOGIN } from "@/lib/connection";
|
||||
import { EVENT_BROWSER_LOGIN_CANCEL } from "@/lib/connection";
|
||||
import { errorDialog, formatErrorMessage } from "@/lib/errors.ts";
|
||||
import { formatRemaining } from "@/lib/formatters";
|
||||
|
||||
@@ -131,21 +131,6 @@ export default function SessionExpirationDialog() {
|
||||
}
|
||||
}, [busy, t]);
|
||||
|
||||
const authenticate = useCallback(async () => {
|
||||
if (busy) return;
|
||||
setBusy(true);
|
||||
try {
|
||||
await Events.Emit(EVENT_TRIGGER_LOGIN);
|
||||
await WindowManager.CloseSessionExpiration();
|
||||
} catch (e) {
|
||||
setBusy(false);
|
||||
await errorDialog({
|
||||
Title: t("connect.error.loginTitle"),
|
||||
Message: formatErrorMessage(e),
|
||||
});
|
||||
}
|
||||
}, [busy, t]);
|
||||
|
||||
const logout = useCallback(async () => {
|
||||
if (busy) return;
|
||||
setBusy(true);
|
||||
@@ -200,7 +185,7 @@ export default function SessionExpirationDialog() {
|
||||
variant={"primary"}
|
||||
size={"md"}
|
||||
className={"w-full"}
|
||||
onClick={expired ? authenticate : stay}
|
||||
onClick={stay}
|
||||
disabled={busy}
|
||||
>
|
||||
{expired ? t("sessionExpiration.authenticate") : t("sessionExpiration.stay")}
|
||||
|
||||
@@ -11,7 +11,6 @@ import { ManagementServerSwitch } from "@/components/ManagementServerSwitch.tsx"
|
||||
import { ManagementMode, useManagementUrl } from "@/hooks/useManagementUrl.ts";
|
||||
import { LanguagePicker } from "@/components/LanguagePicker.tsx";
|
||||
import { useRestrictions } from "@/contexts/RestrictionsContext.tsx";
|
||||
import { useKeepConnectedOnQuit } from "@/hooks/useKeepConnectedOnQuit.ts";
|
||||
|
||||
export function SettingsGeneral() {
|
||||
const { t } = useTranslation();
|
||||
@@ -20,7 +19,6 @@ export function SettingsGeneral() {
|
||||
const { mode, setMode, setUrl, displayUrl, showError, canSave, save, checking, unreachable } =
|
||||
useManagementUrl();
|
||||
const { mdm, features } = useRestrictions();
|
||||
const { keepConnected, setKeepConnectedOnQuit } = useKeepConnectedOnQuit();
|
||||
|
||||
const inputRef = useRef<HTMLInputElement>(null);
|
||||
const managementUrlId = useId();
|
||||
@@ -59,15 +57,6 @@ export function SettingsGeneral() {
|
||||
helpText={t("settings.general.autostart.help")}
|
||||
/>
|
||||
)}
|
||||
<FancyToggleSwitch
|
||||
value={keepConnected ?? false}
|
||||
onChange={(v) => {
|
||||
void setKeepConnectedOnQuit(v);
|
||||
}}
|
||||
loading={keepConnected === null}
|
||||
label={t("settings.general.keepConnectedOnQuit.label")}
|
||||
helpText={t("settings.general.keepConnectedOnQuit.help")}
|
||||
/>
|
||||
</SectionGroup>
|
||||
|
||||
{!mdm.managementURL && !features.disableUpdateSettings && (
|
||||
|
||||
@@ -1,6 +1,6 @@
|
||||
import { useId, type ReactNode } from "react";
|
||||
import { Trans, useTranslation } from "react-i18next";
|
||||
import { ChevronDown, CircleCheckBig, FolderOpen, Info, Loader2 } from "lucide-react";
|
||||
import { CircleCheckBig, FolderOpen, Loader2 } from "lucide-react";
|
||||
import { Browser } from "@wailsio/runtime";
|
||||
import { Debug as DebugSvc } from "@bindings/services";
|
||||
import type { DebugBundleResult } from "@bindings/services/models.js";
|
||||
@@ -8,22 +8,13 @@ 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 { AnonymizeLevel, DebugStage } from "@/contexts/DebugBundleContext";
|
||||
import type { DebugStage } from "@/contexts/DebugBundleContext";
|
||||
import { useDebugBundleContext } from "@/contexts/DebugBundleContext";
|
||||
import { SectionGroup, SettingsBottomBar } from "@/modules/settings/SettingsSection.tsx";
|
||||
|
||||
@@ -33,8 +24,8 @@ export function SettingsTroubleshooting() {
|
||||
const { t } = useTranslation();
|
||||
const durationId = useId();
|
||||
const {
|
||||
anonymizeLevel,
|
||||
setAnonymizeLevel,
|
||||
anonymize,
|
||||
setAnonymize,
|
||||
systemInfo,
|
||||
setSystemInfo,
|
||||
upload,
|
||||
@@ -64,71 +55,12 @@ export function SettingsTroubleshooting() {
|
||||
|
||||
return (
|
||||
<SectionGroup title={t("settings.troubleshooting.section.title")}>
|
||||
<div className={"flex items-center justify-between gap-6"}>
|
||||
<div className={"max-w-md flex-1"}>
|
||||
<Label as={"div"}>
|
||||
<span className={"inline-flex items-center gap-1.5"}>
|
||||
{t("settings.troubleshooting.anonymize.label")}
|
||||
<Tooltip
|
||||
content={
|
||||
<div className={"max-w-xs whitespace-normal leading-relaxed"}>
|
||||
{t("settings.troubleshooting.anonymize.info")}
|
||||
</div>
|
||||
}
|
||||
>
|
||||
<Info
|
||||
size={14}
|
||||
aria-label={t("settings.troubleshooting.anonymize.label")}
|
||||
className={"shrink-0 cursor-default text-nb-gray-400"}
|
||||
/>
|
||||
</Tooltip>
|
||||
</span>
|
||||
</Label>
|
||||
<HelpText margin={false}>
|
||||
{t("settings.troubleshooting.anonymize.help")}
|
||||
</HelpText>
|
||||
</div>
|
||||
<div className={"shrink-0"}>
|
||||
<DropdownMenu>
|
||||
<DropdownMenuTrigger asChild>
|
||||
<button
|
||||
type={"button"}
|
||||
aria-label={t("settings.troubleshooting.anonymize.label")}
|
||||
className={cn(
|
||||
"inline-flex h-[40px] min-w-[160px] items-center justify-between gap-2 px-3",
|
||||
"rounded-md border bg-white dark:bg-nb-gray-900",
|
||||
"border-neutral-200 dark:border-nb-gray-700",
|
||||
"cursor-default text-xs font-semibold text-nb-gray-100 outline-none",
|
||||
"hover:border-nb-gray-600 data-[state=open]:border-nb-gray-600",
|
||||
)}
|
||||
>
|
||||
{t(`settings.troubleshooting.anonymize.${anonymizeLevel}`)}
|
||||
<ChevronDown
|
||||
size={16}
|
||||
aria-hidden={"true"}
|
||||
className={"shrink-0 text-nb-gray-200"}
|
||||
/>
|
||||
</button>
|
||||
</DropdownMenuTrigger>
|
||||
<DropdownMenuContent align={"end"} className={"min-w-[160px]"}>
|
||||
<DropdownMenuRadioGroup
|
||||
value={anonymizeLevel}
|
||||
onValueChange={(v) => setAnonymizeLevel(v as AnonymizeLevel)}
|
||||
>
|
||||
<DropdownMenuRadioItem value={"none"}>
|
||||
{t("settings.troubleshooting.anonymize.none")}
|
||||
</DropdownMenuRadioItem>
|
||||
<DropdownMenuRadioItem value={"default"}>
|
||||
{t("settings.troubleshooting.anonymize.default")}
|
||||
</DropdownMenuRadioItem>
|
||||
<DropdownMenuRadioItem value={"strict"}>
|
||||
{t("settings.troubleshooting.anonymize.strict")}
|
||||
</DropdownMenuRadioItem>
|
||||
</DropdownMenuRadioGroup>
|
||||
</DropdownMenuContent>
|
||||
</DropdownMenu>
|
||||
</div>
|
||||
</div>
|
||||
<FancyToggleSwitch
|
||||
value={anonymize}
|
||||
onChange={setAnonymize}
|
||||
label={t("settings.troubleshooting.anonymize.label")}
|
||||
helpText={t("settings.troubleshooting.anonymize.help")}
|
||||
/>
|
||||
<FancyToggleSwitch
|
||||
value={systemInfo}
|
||||
onChange={setSystemInfo}
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Ändern des Autostarts fehlgeschlagen"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Nach dem Beenden verbunden bleiben",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "Die Verbindung bleibt im Hintergrund bestehen, nachdem Sie NetBird schließen. Sie endet erst, wenn Sie sie selbst trennen.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Anzeigesprache"
|
||||
},
|
||||
|
||||
@@ -735,14 +735,6 @@
|
||||
"message": "Autostart Change Failed",
|
||||
"description": "Error-dialog title when changing the autostart setting fails."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Stay Connected After Quitting",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "The connection stays up in the background after you close NetBird. It only stops when you disconnect it yourself.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Display Language",
|
||||
"description": "Label for the display-language picker."
|
||||
@@ -1013,27 +1005,11 @@
|
||||
},
|
||||
"settings.troubleshooting.anonymize.label": {
|
||||
"message": "Anonymize Sensitive Information",
|
||||
"description": "Label for the anonymization level dropdown (None, Default, Strict)."
|
||||
"description": "Toggle label: anonymize sensitive information in the bundle."
|
||||
},
|
||||
"settings.troubleshooting.anonymize.help": {
|
||||
"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."
|
||||
"message": "Hides public IP addresses and non-NetBird domains from logs.",
|
||||
"description": "Helper text for anonymizing logs (hides public IPs and non-NetBird domains)."
|
||||
},
|
||||
"settings.troubleshooting.systemInfo.label": {
|
||||
"message": "Include System Information",
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Error al cambiar el inicio automático"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Permanecer conectado al salir",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "La conexión sigue activa en segundo plano después de cerrar NetBird. Solo se detiene cuando la desconectas tú.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Idioma de la interfaz"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Échec de la modification du démarrage automatique"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Rester connecté après la fermeture",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "La connexion reste active en arrière-plan après la fermeture de NetBird. Elle ne s'arrête que si vous la coupez vous-même.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Langue d’affichage"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Az automatikus indítás módosítása sikertelen"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Kapcsolat megtartása kilépéskor",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "A kapcsolat a háttérben megmarad, miután bezárod a NetBirdöt. Csak akkor szakad meg, ha te magad bontod.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Megjelenítési nyelv"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Modifica avvio automatico non riuscita"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Resta connesso dopo la chiusura",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "La connessione resta attiva in background dopo la chiusura di NetBird. Si interrompe solo quando la disconnetti tu.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Lingua dell'interfaccia"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "自動起動の変更に失敗しました"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "終了後も接続を維持",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "NetBird を閉じたあとも接続はバックグラウンドで維持されます。自分で切断したときにだけ停止します。",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "表示言語"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Falha ao alterar o início automático"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Permanecer conectado ao sair",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "A conexão continua ativa em segundo plano depois de fechar o NetBird. Ela só para quando você mesmo a desconecta.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Idioma de exibição"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "Не удалось изменить автозапуск"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "Оставаться подключённым после выхода",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "Соединение остаётся активным в фоне после закрытия NetBird. Оно прервётся, только когда вы отключите его сами.",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "Язык интерфейса"
|
||||
},
|
||||
|
||||
@@ -551,14 +551,6 @@
|
||||
"settings.general.autostart.errorTitle": {
|
||||
"message": "更改自启动设置失败"
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.label": {
|
||||
"message": "退出后保持连接",
|
||||
"description": "Toggle label: keep the VPN connection up after quitting the UI."
|
||||
},
|
||||
"settings.general.keepConnectedOnQuit.help": {
|
||||
"message": "关闭 NetBird 后,连接会在后台保持。只有你自己断开时才会停止。",
|
||||
"description": "Helper text for the stay-connected-after-quitting toggle."
|
||||
},
|
||||
"settings.general.language.label": {
|
||||
"message": "显示语言"
|
||||
},
|
||||
|
||||
@@ -95,6 +95,10 @@ func main() {
|
||||
}
|
||||
})
|
||||
|
||||
// Debug patch, not for release: dumps heap/goroutine profiles and the
|
||||
// process tree to /tmp/nbgui for the memory consumption investigation.
|
||||
startMemProfiler(app)
|
||||
|
||||
profiles := services.NewProfiles(conn)
|
||||
// updater.Holder owns the typed update State; DaemonFeed feeds it and the
|
||||
// Update service is a thin Wails-bound facade over it plus the install RPCs.
|
||||
@@ -180,7 +184,6 @@ func main() {
|
||||
WindowManager: windowManager,
|
||||
Session: authSession,
|
||||
Localizer: localizer,
|
||||
Preferences: prefStore,
|
||||
})
|
||||
listenForShowSignal(context.Background(), tray)
|
||||
|
||||
|
||||
319
client/ui/memprof.go
Normal file
319
client/ui/memprof.go
Normal file
@@ -0,0 +1,319 @@
|
||||
//go:build !android && !ios && !freebsd && !js
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"fmt"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"runtime"
|
||||
"runtime/pprof"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
|
||||
"github.com/shirou/gopsutil/v4/process"
|
||||
log "github.com/sirupsen/logrus"
|
||||
"github.com/wailsapp/wails/v3/pkg/application"
|
||||
"github.com/wailsapp/wails/v3/pkg/events"
|
||||
)
|
||||
|
||||
// memProfOffsets are the snapshot times measured from application startup.
|
||||
var memProfOffsets = []time.Duration{0, 2 * time.Minute, 5 * time.Minute}
|
||||
|
||||
// memProfMaxDepth bounds the child walk so a cycle in the reported parent links
|
||||
// cannot spin forever.
|
||||
const memProfMaxDepth = 4
|
||||
|
||||
type memProfileSpec struct {
|
||||
profile string
|
||||
file string
|
||||
debug int
|
||||
}
|
||||
|
||||
var memProfileSpecs = []memProfileSpec{
|
||||
{profile: "heap", file: "heap.pprof", debug: 0},
|
||||
{profile: "heap", file: "heap.txt", debug: 1},
|
||||
{profile: "goroutine", file: "goroutine.txt", debug: 1},
|
||||
{profile: "threadcreate", file: "threadcreate.txt", debug: 1},
|
||||
}
|
||||
|
||||
var memProfStart = time.Now()
|
||||
|
||||
// startMemProfiler dumps a profile snapshot at every memProfOffsets mark, each
|
||||
// into its own timestamped directory under memProfBaseDir. The first runs once
|
||||
// the application is up so the window inventory sees the eagerly created
|
||||
// windows. Every failure is logged and never stops the GUI.
|
||||
func startMemProfiler(app *application.App) {
|
||||
log.Infof("memory profiler enabled, writing to %s (snapshots at %v after startup)", memProfBaseDir(), memProfOffsets)
|
||||
|
||||
app.Event.OnApplicationEvent(events.Common.ApplicationStarted, func(*application.ApplicationEvent) {
|
||||
go func() {
|
||||
started := time.Now()
|
||||
for _, offset := range memProfOffsets {
|
||||
if wait := time.Until(started.Add(offset)); wait > 0 {
|
||||
time.Sleep(wait)
|
||||
}
|
||||
writeMemProfile(app)
|
||||
}
|
||||
}()
|
||||
})
|
||||
}
|
||||
|
||||
// memProfBaseDir returns the directory holding the snapshot directories.
|
||||
func memProfBaseDir() string {
|
||||
if runtime.GOOS == "windows" {
|
||||
return filepath.Join(os.TempDir(), "nbgui")
|
||||
}
|
||||
return "/tmp/nbgui"
|
||||
}
|
||||
|
||||
// writeMemProfile creates a <timestamp>-<pid> directory and fills it with the
|
||||
// runtime profiles, the memory statistics summary and the process tree.
|
||||
func writeMemProfile(app *application.App) {
|
||||
name := fmt.Sprintf("%s-%d", time.Now().Format("20060102-150405"), os.Getpid())
|
||||
dir := filepath.Join(memProfBaseDir(), name)
|
||||
if err := os.MkdirAll(dir, 0o755); err != nil {
|
||||
log.Warnf("create memory profile dir %s: %v", dir, err)
|
||||
return
|
||||
}
|
||||
|
||||
// The heap profile reports live objects as of the last collection, so force
|
||||
// one to keep inuse_space from counting garbage that is already unreachable.
|
||||
runtime.GC()
|
||||
|
||||
if err := writeMemStats(filepath.Join(dir, "memstats.txt"), app); err != nil {
|
||||
log.Warnf("write memory statistics: %v", err)
|
||||
}
|
||||
|
||||
if err := writeProcTree(filepath.Join(dir, "proctree.txt")); err != nil {
|
||||
log.Warnf("write process tree: %v", err)
|
||||
}
|
||||
|
||||
for _, spec := range memProfileSpecs {
|
||||
if err := writeMemProfileFile(spec, filepath.Join(dir, spec.file)); err != nil {
|
||||
log.Warnf("write %s profile: %v", spec.profile, err)
|
||||
}
|
||||
}
|
||||
|
||||
log.Infof("memory profile written to %s", dir)
|
||||
}
|
||||
|
||||
// writeMemProfileFile writes a single runtime profile to path.
|
||||
func writeMemProfileFile(spec memProfileSpec, path string) error {
|
||||
p := pprof.Lookup(spec.profile)
|
||||
if p == nil {
|
||||
return fmt.Errorf("unknown profile %q", spec.profile)
|
||||
}
|
||||
|
||||
f, err := os.Create(path)
|
||||
if err != nil {
|
||||
return fmt.Errorf("create %s: %w", path, err)
|
||||
}
|
||||
defer func() {
|
||||
if err := f.Close(); err != nil {
|
||||
log.Debugf("close %s: %v", path, err)
|
||||
}
|
||||
}()
|
||||
|
||||
if err := p.WriteTo(f, spec.debug); err != nil {
|
||||
return fmt.Errorf("write %s: %w", path, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// writeMemStats dumps the runtime memory statistics next to the process
|
||||
// resident set size. A resident set much larger than Sys means the memory sits
|
||||
// outside the Go heap (webview, GTK, other cgo allocations), where the pprof
|
||||
// profiles cannot see it.
|
||||
func writeMemStats(path string, app *application.App) error {
|
||||
var m runtime.MemStats
|
||||
runtime.ReadMemStats(&m)
|
||||
|
||||
var b strings.Builder
|
||||
fmt.Fprintf(&b, "time: %s\n", time.Now().Format(time.RFC3339))
|
||||
fmt.Fprintf(&b, "uptime: %s\n", time.Since(memProfStart).Round(time.Second))
|
||||
fmt.Fprintf(&b, "pid: %d\n", os.Getpid())
|
||||
fmt.Fprintf(&b, "\n")
|
||||
|
||||
rss, vms := processMemory()
|
||||
fmt.Fprintf(&b, "process_rss: %s\n", rss)
|
||||
fmt.Fprintf(&b, "process_vms: %s\n", vms)
|
||||
fmt.Fprintf(&b, "\n")
|
||||
|
||||
fmt.Fprintf(&b, "sys: %s\n", formatMemBytes(m.Sys))
|
||||
fmt.Fprintf(&b, "heap_alloc: %s\n", formatMemBytes(m.HeapAlloc))
|
||||
fmt.Fprintf(&b, "heap_sys: %s\n", formatMemBytes(m.HeapSys))
|
||||
fmt.Fprintf(&b, "heap_inuse: %s\n", formatMemBytes(m.HeapInuse))
|
||||
fmt.Fprintf(&b, "heap_idle: %s\n", formatMemBytes(m.HeapIdle))
|
||||
fmt.Fprintf(&b, "heap_released: %s\n", formatMemBytes(m.HeapReleased))
|
||||
fmt.Fprintf(&b, "heap_objects: %d\n", m.HeapObjects)
|
||||
fmt.Fprintf(&b, "stack_inuse: %s\n", formatMemBytes(m.StackInuse))
|
||||
fmt.Fprintf(&b, "stack_sys: %s\n", formatMemBytes(m.StackSys))
|
||||
fmt.Fprintf(&b, "mspan_sys: %s\n", formatMemBytes(m.MSpanSys))
|
||||
fmt.Fprintf(&b, "mcache_sys: %s\n", formatMemBytes(m.MCacheSys))
|
||||
fmt.Fprintf(&b, "gc_sys: %s\n", formatMemBytes(m.GCSys))
|
||||
fmt.Fprintf(&b, "other_sys: %s\n", formatMemBytes(m.OtherSys))
|
||||
fmt.Fprintf(&b, "next_gc: %s\n", formatMemBytes(m.NextGC))
|
||||
fmt.Fprintf(&b, "num_gc: %d\n", m.NumGC)
|
||||
fmt.Fprintf(&b, "\n")
|
||||
|
||||
fmt.Fprintf(&b, "goroutines: %d\n", runtime.NumGoroutine())
|
||||
fmt.Fprintf(&b, "cgo_calls: %d\n", runtime.NumCgoCall())
|
||||
fmt.Fprintf(&b, "gomaxprocs: %d\n", runtime.GOMAXPROCS(0))
|
||||
fmt.Fprintf(&b, "\n")
|
||||
|
||||
writeWindowInventory(&b, app)
|
||||
|
||||
if err := os.WriteFile(path, []byte(b.String()), 0o644); err != nil {
|
||||
return fmt.Errorf("write %s: %w", path, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// writeWindowInventory lists the live Wails windows. A window that exists holds
|
||||
// a webview process even while hidden, so this tells apart a leaked window (the
|
||||
// count grows) from windows whose content grew (the count stays put).
|
||||
func writeWindowInventory(b *strings.Builder, app *application.App) {
|
||||
windows := app.Window.GetAll()
|
||||
fmt.Fprintf(b, "windows: %d\n", len(windows))
|
||||
for _, w := range windows {
|
||||
visible := "unknown"
|
||||
if ww, ok := w.(*application.WebviewWindow); ok {
|
||||
visible = strconv.FormatBool(ww.IsVisible())
|
||||
}
|
||||
fmt.Fprintf(b, " id=%-3d name=%-20q visible=%-7s minimised=%-5t focused=%t\n",
|
||||
w.ID(), w.Name(), visible, w.IsMinimised(), w.IsFocused())
|
||||
}
|
||||
}
|
||||
|
||||
// writeProcTree dumps this process and its descendants with their memory
|
||||
// footprint. The webview runs in child processes whose memory the Go runtime
|
||||
// profiles cannot see, so this is what attributes a footprint to a component.
|
||||
func writeProcTree(path string) error {
|
||||
self, err := process.NewProcess(int32(os.Getpid()))
|
||||
if err != nil {
|
||||
return fmt.Errorf("open own process: %w", err)
|
||||
}
|
||||
|
||||
var b strings.Builder
|
||||
fmt.Fprintf(&b, "time: %s\n", time.Now().Format(time.RFC3339))
|
||||
fmt.Fprintf(&b, "uptime: %s\n\n", time.Since(memProfStart).Round(time.Second))
|
||||
fmt.Fprintf(&b, "%-8s %-8s %-28s %12s %12s %12s %12s\n", "PID", "PPID", "NAME", "RSS", "VMS", "PSS", "PRIV_DIRTY")
|
||||
|
||||
var totalRSS, totalPSS, totalPrivate uint64
|
||||
walkProcTree(&b, self, 0, &totalRSS, &totalPSS, &totalPrivate)
|
||||
|
||||
fmt.Fprintf(&b, "\n%-8s %-8s %-28s %12s %12s %12s %12s\n", "", "", "TOTAL",
|
||||
formatKB(totalRSS), "", formatKB(totalPSS), formatKB(totalPrivate))
|
||||
fmt.Fprintf(&b, "\nPSS and PRIV_DIRTY come from /proc/<pid>/smaps_rollup and are Linux only.\n")
|
||||
|
||||
if err := os.WriteFile(path, []byte(b.String()), 0o644); err != nil {
|
||||
return fmt.Errorf("write %s: %w", path, err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// walkProcTree appends one line per process, depth-first, accumulating totals.
|
||||
func walkProcTree(b *strings.Builder, p *process.Process, depth int, totalRSS, totalPSS, totalPrivate *uint64) {
|
||||
name, err := p.Name()
|
||||
if err != nil {
|
||||
name = "unknown"
|
||||
}
|
||||
|
||||
var rss, vms uint64
|
||||
if info, err := p.MemoryInfo(); err == nil {
|
||||
rss, vms = info.RSS, info.VMS
|
||||
}
|
||||
|
||||
pss, private := smapsRollup(p.Pid)
|
||||
*totalRSS += rss
|
||||
*totalPSS += pss
|
||||
*totalPrivate += private
|
||||
|
||||
ppid, err := p.Ppid()
|
||||
if err != nil {
|
||||
ppid = -1
|
||||
}
|
||||
|
||||
fmt.Fprintf(b, "%-8d %-8d %-28s %12s %12s %12s %12s\n", p.Pid, ppid,
|
||||
strings.Repeat(" ", depth)+name, formatKB(rss), formatKB(vms), formatKB(pss), formatKB(private))
|
||||
|
||||
if depth >= memProfMaxDepth {
|
||||
return
|
||||
}
|
||||
|
||||
children, err := p.Children()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
for _, child := range children {
|
||||
walkProcTree(b, child, depth+1, totalRSS, totalPSS, totalPrivate)
|
||||
}
|
||||
}
|
||||
|
||||
// smapsRollup returns the proportional set size and private dirty bytes of pid,
|
||||
// both zero on platforms without /proc.
|
||||
func smapsRollup(pid int32) (uint64, uint64) {
|
||||
f, err := os.Open(fmt.Sprintf("/proc/%d/smaps_rollup", pid))
|
||||
if err != nil {
|
||||
return 0, 0
|
||||
}
|
||||
defer func() {
|
||||
if err := f.Close(); err != nil {
|
||||
log.Debugf("close smaps_rollup for %d: %v", pid, err)
|
||||
}
|
||||
}()
|
||||
|
||||
var pss, private uint64
|
||||
scanner := bufio.NewScanner(f)
|
||||
for scanner.Scan() {
|
||||
fields := strings.Fields(scanner.Text())
|
||||
if len(fields) < 2 {
|
||||
continue
|
||||
}
|
||||
kb, err := strconv.ParseUint(fields[1], 10, 64)
|
||||
if err != nil {
|
||||
continue
|
||||
}
|
||||
switch fields[0] {
|
||||
case "Pss:":
|
||||
pss = kb * 1024
|
||||
case "Private_Dirty:":
|
||||
private = kb * 1024
|
||||
}
|
||||
}
|
||||
return pss, private
|
||||
}
|
||||
|
||||
// processMemory returns the formatted resident and virtual size of this process.
|
||||
func processMemory() (string, string) {
|
||||
p, err := process.NewProcess(int32(os.Getpid()))
|
||||
if err != nil {
|
||||
unavailable := fmt.Sprintf("unavailable (%v)", err)
|
||||
return unavailable, unavailable
|
||||
}
|
||||
|
||||
info, err := p.MemoryInfo()
|
||||
if err != nil {
|
||||
unavailable := fmt.Sprintf("unavailable (%v)", err)
|
||||
return unavailable, unavailable
|
||||
}
|
||||
|
||||
return formatMemBytes(info.RSS), formatMemBytes(info.VMS)
|
||||
}
|
||||
|
||||
// formatMemBytes renders a byte count as megabytes with the raw value kept.
|
||||
func formatMemBytes(n uint64) string {
|
||||
return fmt.Sprintf("%8.1f MB (%d bytes)", float64(n)/(1024*1024), n)
|
||||
}
|
||||
|
||||
// formatKB renders a byte count as megabytes for the process tree columns, and
|
||||
// a dash when the platform did not report the value.
|
||||
func formatKB(n uint64) string {
|
||||
if n == 0 {
|
||||
return "-"
|
||||
}
|
||||
return fmt.Sprintf("%.1f MB", float64(n)/(1024*1024))
|
||||
}
|
||||
@@ -58,10 +58,6 @@ type UIPreferences struct {
|
||||
// decision has run for this OS user. It only ever transitions to true
|
||||
// and is never reset, so the default-on flow runs at most once, ever.
|
||||
AutostartInitialized bool `json:"autostartInitialized"`
|
||||
// KeepConnectedOnQuit leaves the daemon connected when the GUI quits.
|
||||
// Its false zero value preserves the historical disconnect-on-quit
|
||||
// behaviour for preference files written before the field existed.
|
||||
KeepConnectedOnQuit bool `json:"keepConnectedOnQuit"`
|
||||
}
|
||||
|
||||
// LanguageValidator rejects SetLanguage inputs with no shipped bundle.
|
||||
@@ -187,26 +183,6 @@ func (s *Store) SetAutostartInitialized(done bool) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// SetKeepConnectedOnQuit persists the disconnect-on-quit opt-out. No-op if unchanged.
|
||||
func (s *Store) SetKeepConnectedOnQuit(keep bool) error {
|
||||
s.mu.Lock()
|
||||
if s.current.KeepConnectedOnQuit == keep {
|
||||
s.mu.Unlock()
|
||||
return nil
|
||||
}
|
||||
next := s.current
|
||||
next.KeepConnectedOnQuit = keep
|
||||
if err := s.persistLocked(next); err != nil {
|
||||
s.mu.Unlock()
|
||||
return fmt.Errorf("persist preferences: %w", err)
|
||||
}
|
||||
s.current = next
|
||||
s.mu.Unlock()
|
||||
|
||||
s.broadcast(next)
|
||||
return nil
|
||||
}
|
||||
|
||||
// SetLanguage validates, persists, and broadcasts. No-op if unchanged.
|
||||
func (s *Store) SetLanguage(lang i18n.LanguageCode) error {
|
||||
if lang == "" {
|
||||
|
||||
@@ -238,42 +238,6 @@ func TestStore_SetAutostartInitializedPersistsAcrossReload(t *testing.T) {
|
||||
assert.True(t, reloaded.Get().AutostartInitialized, "marker must survive a reload from disk")
|
||||
}
|
||||
|
||||
func TestStore_SetKeepConnectedOnQuitPersistsAcrossReload(t *testing.T) {
|
||||
withTempConfigDir(t)
|
||||
emitter := &recordingEmitter{}
|
||||
s, err := NewStore(nil, emitter)
|
||||
require.NoError(t, err)
|
||||
|
||||
assert.False(t, s.Get().KeepConnectedOnQuit, "quitting must disconnect by default")
|
||||
|
||||
require.NoError(t, s.SetKeepConnectedOnQuit(true))
|
||||
assert.True(t, s.Get().KeepConnectedOnQuit, "Get should reflect the persisted opt-out")
|
||||
require.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "first write should broadcast")
|
||||
|
||||
require.NoError(t, s.SetKeepConnectedOnQuit(true))
|
||||
assert.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "idempotent write should not broadcast again")
|
||||
|
||||
reloaded, err := NewStore(nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.True(t, reloaded.Get().KeepConnectedOnQuit, "opt-out must survive a reload from disk")
|
||||
}
|
||||
|
||||
func TestStore_KeepConnectedOnQuitDefaultsFalseForPreExistingFile(t *testing.T) {
|
||||
withTempConfigDir(t)
|
||||
|
||||
// A preferences file written before the field existed must keep the
|
||||
// historical disconnect-on-quit behaviour rather than silently opting out.
|
||||
path, err := preferencesPath()
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, os.MkdirAll(filepath.Dir(path), 0o755))
|
||||
require.NoError(t, os.WriteFile(path, []byte(`{"language":"en","viewMode":"default"}`), 0o600))
|
||||
|
||||
s, err := NewStore(nil, nil)
|
||||
require.NoError(t, err)
|
||||
assert.False(t, s.Get().KeepConnectedOnQuit, "a file predating the field must not opt out of disconnect-on-quit")
|
||||
assert.True(t, s.ExistedAtLoad(), "the pre-existing file must be seen on disk")
|
||||
}
|
||||
|
||||
func TestStore_ExistedAtLoad(t *testing.T) {
|
||||
withTempConfigDir(t)
|
||||
|
||||
|
||||
@@ -49,11 +49,5 @@ func getCursorPosition(app *application.App) (application.Point, bool) {
|
||||
if app == nil || app.Screen == nil {
|
||||
return p, true
|
||||
}
|
||||
// The wails GTK3 backend caches screens from the active window; a tray app
|
||||
// has none at startup, so the cache is empty and PhysicalToDipPoint would
|
||||
// dereference a nil nearest screen. Raw pixels are correct there anyway.
|
||||
if app.Screen.ScreenNearestPhysicalPoint(p) == nil {
|
||||
return p, true
|
||||
}
|
||||
return app.Screen.PhysicalToDipPoint(p), true
|
||||
}
|
||||
|
||||
@@ -15,13 +15,10 @@ import (
|
||||
)
|
||||
|
||||
type DebugBundleParams struct {
|
||||
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"`
|
||||
Anonymize bool `json:"anonymize"`
|
||||
SystemInfo bool `json:"systemInfo"`
|
||||
UploadURL string `json:"uploadUrl"`
|
||||
LogFileCount uint32 `json:"logFileCount"`
|
||||
}
|
||||
|
||||
// DebugBundleResult: Path is set for local-only bundles, UploadedKey on upload
|
||||
@@ -51,12 +48,11 @@ func (s *Debug) Bundle(ctx context.Context, p DebugBundleParams) (DebugBundleRes
|
||||
return DebugBundleResult{}, err
|
||||
}
|
||||
resp, err := cli.DebugBundle(ctx, &proto.DebugBundleRequest{
|
||||
Anonymize: p.Anonymize,
|
||||
AnonymizeLevel: p.AnonymizeLevel,
|
||||
SystemInfo: p.SystemInfo,
|
||||
UploadURL: p.UploadURL,
|
||||
LogFileCount: p.LogFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
Anonymize: p.Anonymize,
|
||||
SystemInfo: p.SystemInfo,
|
||||
UploadURL: p.UploadURL,
|
||||
LogFileCount: p.LogFileCount,
|
||||
CliVersion: version.NetbirdVersion(),
|
||||
})
|
||||
if err != nil {
|
||||
return DebugBundleResult{}, err
|
||||
|
||||
@@ -34,7 +34,3 @@ func (s *Preferences) SetViewMode(_ context.Context, mode preferences.ViewMode)
|
||||
func (s *Preferences) SetOnboardingCompleted(_ context.Context, done bool) error {
|
||||
return s.store.SetOnboardingCompleted(done)
|
||||
}
|
||||
|
||||
func (s *Preferences) SetKeepConnectedOnQuit(_ context.Context, keep bool) error {
|
||||
return s.store.SetKeepConnectedOnQuit(keep)
|
||||
}
|
||||
|
||||
@@ -16,7 +16,6 @@ import (
|
||||
|
||||
"github.com/netbirdio/netbird/client/ui/authsession"
|
||||
"github.com/netbirdio/netbird/client/ui/i18n"
|
||||
"github.com/netbirdio/netbird/client/ui/preferences"
|
||||
"github.com/netbirdio/netbird/client/ui/services"
|
||||
"github.com/netbirdio/netbird/version"
|
||||
)
|
||||
@@ -51,9 +50,8 @@ type TrayServices struct {
|
||||
WindowManager *services.WindowManager
|
||||
// Session is bound to authsession directly because the services wrapper
|
||||
// only re-exposes the React subset.
|
||||
Session *authsession.Session
|
||||
Localizer *Localizer
|
||||
Preferences *preferences.Store
|
||||
Session *authsession.Session
|
||||
Localizer *Localizer
|
||||
}
|
||||
|
||||
type Tray struct {
|
||||
@@ -463,12 +461,10 @@ func (t *Tray) handleQuit() {
|
||||
t.profileMu.Unlock()
|
||||
t.svc.DaemonFeed.CancelProfileSwitch()
|
||||
|
||||
if t.svc.Preferences == nil || !t.svc.Preferences.Get().KeepConnectedOnQuit {
|
||||
ctx, cancel := context.WithTimeout(context.Background(), quitDownTimeout)
|
||||
defer cancel()
|
||||
if err := t.svc.Connection.Down(ctx); err != nil {
|
||||
log.Errorf("disconnect on quit: %v", err)
|
||||
}
|
||||
ctx, cancel := context.WithTimeout(context.Background(), quitDownTimeout)
|
||||
defer cancel()
|
||||
if err := t.svc.Connection.Down(ctx); err != nil {
|
||||
log.Errorf("disconnect on quit: %v", err)
|
||||
}
|
||||
t.app.Quit()
|
||||
}
|
||||
|
||||
@@ -4,26 +4,17 @@ package main
|
||||
|
||||
// bindTrayClick wires the tray icon's left-click handler on Linux.
|
||||
//
|
||||
// Expected behaviour per tray host:
|
||||
//
|
||||
// Host Left click Right click
|
||||
// KDE Plasma, Waybar main window (Activate) menu (host-rendered)
|
||||
// GNOME Shell + AppIndicator menu only menu only
|
||||
// Minimal WMs via XEmbed host main window (Activate) XEmbed GTK popup
|
||||
//
|
||||
// OnClick fires only on org.kde.StatusNotifierItem.Activate — a real left
|
||||
// click. KDE/Waybar send it over D-Bus; the in-process XEmbed host
|
||||
// (xembed_host_linux.go) maps a Button1 press to the same Activate call.
|
||||
//
|
||||
// GNOME Shell + AppIndicator never sends Activate: it renders the dbusmenu
|
||||
// on ANY click and only reports the menu opening via dbusmenu
|
||||
// Event("opened"). Upstream Wails treated that event as a click, so on GNOME
|
||||
// both buttons raised the main window on top of the menu, and on KDE/Waybar
|
||||
// a right click raised it over the freshly opened menu. The netbirdio/wails
|
||||
// fork (go.mod replace) drops that heuristic: a menu open never fires
|
||||
// OnClick. On GNOME the main window is reached via the "Open NetBird" menu
|
||||
// entry; left-click-opens-window is not achievable there anyway, since the
|
||||
// host always opens the menu itself.
|
||||
// Both Linux click paths converge on Wails' linuxSystemTray.Activate, which
|
||||
// fires the registered clickHandler:
|
||||
// - Real SNI hosts (KDE Plasma, Waybar, GNOME Shell + AppIndicator) invoke
|
||||
// org.kde.StatusNotifierItem.Activate over D-Bus on left-click.
|
||||
// - The in-process StatusNotifierWatcher + XEmbed host used on minimal WMs
|
||||
// (Fluxbox, i3, dwm, OpenBox) maps a Button1 press to that same Activate
|
||||
// call itself (xembed_host_linux.go), so it routes through the same hook.
|
||||
// Registering OnClick here therefore covers both paths with one handler — no
|
||||
// changes to the watcher or XEmbed C code are needed. Left-click now opens the
|
||||
// main window; right-click still opens the menu via Wails' default
|
||||
// SecondaryActivate→OpenMenu handler (and the XEmbed GTK popup on minimal WMs).
|
||||
//
|
||||
// We do NOT register OnDoubleClick: Wails' Linux SNI backend never fires it
|
||||
// (unlike Windows). And we deliberately skip AttachWindow — it plus Wails3's
|
||||
|
||||
@@ -27,10 +27,11 @@ const (
|
||||
finalWarningCountdownSeconds = 120
|
||||
)
|
||||
|
||||
// handleSessionExpired notifies and brings the window forward so the user can reconnect.
|
||||
// handleSessionExpired notifies and brings the window forward so the frontend's /login route drives renewal.
|
||||
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.SetURL("/#/login")
|
||||
t.window.Show()
|
||||
t.window.Focus()
|
||||
}
|
||||
@@ -307,7 +308,11 @@ func (t *Tray) openSessionExtendFlow() {
|
||||
}
|
||||
seconds := int(time.Until(deadline).Seconds())
|
||||
if seconds <= 0 {
|
||||
t.app.Event.Emit(services.EventTriggerLogin)
|
||||
if t.window != nil {
|
||||
t.window.SetURL("/#/login")
|
||||
t.window.Show()
|
||||
t.window.Focus()
|
||||
}
|
||||
return
|
||||
}
|
||||
if t.svc.WindowManager == nil {
|
||||
|
||||
@@ -1,40 +0,0 @@
|
||||
//go:build linux && gtk3 && !(linux && 386)
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"errors"
|
||||
|
||||
"github.com/godbus/dbus/v5"
|
||||
)
|
||||
|
||||
// The legacy GTK3 / WebKit2GTK 4.1 build (-tags gtk3) drops the in-process
|
||||
// XEmbed StatusNotifierWatcher entirely. The real implementation
|
||||
// (xembed_host_linux.go + xembed_tray_linux.c) links GTK4 and uses GTK4-only
|
||||
// popup-menu APIs that have no drop-in GTK3 equivalent, so rather than port the
|
||||
// C layer we stub the host out on gtk3 builds. The tray still works on every
|
||||
// desktop that ships its own StatusNotifierWatcher (KDE, GNOME+AppIndicator,
|
||||
// Cinnamon/xapp, XFCE, …); only the minimal-WM fallback (Fluxbox/OpenBox/i3/
|
||||
// dwm/vanilla GNOME) is unavailable on gtk3 packages. See LINUX-TRAY.md.
|
||||
|
||||
// xembedHost is a placeholder so the package compiles on gtk3 builds; the real
|
||||
// type (with X11/GTK4 state) lives in xembed_host_linux.go. It is never
|
||||
// instantiated here because xembedTrayAvailable always reports false.
|
||||
type xembedHost struct{}
|
||||
|
||||
// run satisfies the call in tray_watcher_linux.go; unreachable on gtk3 because
|
||||
// newXembedHost never returns a non-nil host.
|
||||
func (*xembedHost) run() {}
|
||||
|
||||
// xembedTrayAvailable always reports false on gtk3 builds, so the watcher probe
|
||||
// loop in startStatusNotifierWatcher exits immediately and newXembedHost is
|
||||
// never reached. recenter_linux.go's predicate becomes a harmless no-op too.
|
||||
func xembedTrayAvailable() bool {
|
||||
return false
|
||||
}
|
||||
|
||||
// newXembedHost exists only to satisfy the reference in tray_watcher_linux.go;
|
||||
// it is unreachable because xembedTrayAvailable returns false on gtk3.
|
||||
func newXembedHost(conn *dbus.Conn, busName string, objPath dbus.ObjectPath) (*xembedHost, error) {
|
||||
return nil, errors.New("xembed host unsupported on gtk3 build")
|
||||
}
|
||||
@@ -1,4 +1,4 @@
|
||||
//go:build linux && !gtk3 && !(linux && 386)
|
||||
//go:build linux && !(linux && 386)
|
||||
|
||||
package main
|
||||
|
||||
|
||||
@@ -1,5 +1,3 @@
|
||||
//go:build linux && !gtk3 && !(linux && 386)
|
||||
|
||||
#include "xembed_tray_linux.h"
|
||||
|
||||
#include <X11/Xatom.h>
|
||||
|
||||
@@ -438,10 +438,14 @@ 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).
|
||||
// proxy, so we enable everything up front). The first create bootstraps the
|
||||
// cluster.
|
||||
ids := make([]string, 0, len(matrix))
|
||||
for _, pc := range matrix {
|
||||
for i, 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)
|
||||
|
||||
@@ -23,10 +23,9 @@ 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 = harness.VLLMChatInputTokens
|
||||
vllmCompletionTokens = harness.VLLMChatOutputTokens
|
||||
vllmPromptTokens = 11
|
||||
vllmCompletionTokens = 2
|
||||
)
|
||||
|
||||
// pricedEnv is a connected single-provider agent-network deployment pointed at
|
||||
@@ -83,12 +82,13 @@ 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),
|
||||
Models: &models,
|
||||
Name: name,
|
||||
ProviderId: "openai_api",
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &dummyKey,
|
||||
Enabled: ptr(true),
|
||||
BootstrapCluster: ptr(harness.AgentNetworkCluster),
|
||||
Models: &models,
|
||||
})
|
||||
require.NoError(t, err, "create provider")
|
||||
t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
|
||||
|
||||
@@ -1,455 +0,0 @@
|
||||
//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())
|
||||
})
|
||||
}
|
||||
@@ -113,14 +113,15 @@ 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.
|
||||
// a GCP token. Bootstraps the cluster if it isn't already.
|
||||
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),
|
||||
Name: tc.name,
|
||||
ProviderId: tc.catalogID,
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &staticKey,
|
||||
Enabled: ptr(true),
|
||||
BootstrapCluster: ptr(harness.AgentNetworkCluster),
|
||||
})
|
||||
require.NoError(t, err, "create %s provider", tc.name)
|
||||
t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
|
||||
|
||||
@@ -73,6 +73,7 @@ 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) })
|
||||
|
||||
@@ -61,14 +61,15 @@ func TestGuardrailMultiPolicyModelAllowlist(t *testing.T) {
|
||||
}
|
||||
|
||||
// pRestricted declares the two guardrailed models so routing is deterministic
|
||||
// (model -> provider).
|
||||
// (model -> provider). Created first, so it carries the bootstrap cluster.
|
||||
pRestricted, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
|
||||
Name: "restricted",
|
||||
ProviderId: "openai_api",
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &staticKey,
|
||||
Enabled: ptr(true),
|
||||
Models: models(modelSelected, modelOther),
|
||||
Name: "restricted",
|
||||
ProviderId: "openai_api",
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &staticKey,
|
||||
Enabled: ptr(true),
|
||||
Models: models(modelSelected, modelOther),
|
||||
BootstrapCluster: ptr(harness.AgentNetworkCluster),
|
||||
})
|
||||
require.NoError(t, err, "create restricted provider")
|
||||
t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), pRestricted.Id) })
|
||||
|
||||
@@ -115,7 +115,7 @@ func TestGuardrailPerGroupAllowlist_AllProviders(t *testing.T) {
|
||||
staticKey := "static-e2e-token"
|
||||
enabled := true
|
||||
|
||||
for _, c := range cases {
|
||||
for i, c := range cases {
|
||||
req := api.AgentNetworkProviderRequest{
|
||||
Name: "e2e-pergroup-" + c.name,
|
||||
ProviderId: c.catalogID,
|
||||
@@ -124,6 +124,9 @@ 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
|
||||
@@ -280,12 +283,13 @@ 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),
|
||||
Name: "e2e-mg-union",
|
||||
ProviderId: "openai_api",
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &staticKey,
|
||||
Enabled: ptr(true),
|
||||
Models: priced(unionA, unionB, unionC),
|
||||
BootstrapCluster: ptr(harness.AgentNetworkCluster),
|
||||
})
|
||||
require.NoError(t, err, "create union provider")
|
||||
t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), p1.Id) })
|
||||
|
||||
@@ -115,11 +115,14 @@ func TestModelAllowlistEnforced(t *testing.T) {
|
||||
})
|
||||
require.NoError(t, err, "mint setup key")
|
||||
|
||||
// Providers with their configured (allowed) models
|
||||
// Providers with their configured (allowed) models; the first bootstraps the cluster.
|
||||
ids := make([]string, 0, len(providers))
|
||||
allowed := make([]string, 0, len(providers))
|
||||
for _, pc := range providers {
|
||||
for i, 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
|
||||
|
||||
@@ -14,7 +14,6 @@ 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)
|
||||
@@ -43,14 +42,5 @@ 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()
|
||||
}
|
||||
|
||||
@@ -21,10 +21,11 @@ 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"),
|
||||
Name: name,
|
||||
ProviderId: "openai_api",
|
||||
UpstreamUrl: "https://api.openai.com",
|
||||
ApiKey: ptr("sk-dummy-e2e-key"),
|
||||
BootstrapCluster: ptr("eu.proxy.netbird.test"),
|
||||
})
|
||||
require.NoError(t, err, "create provider %q", name)
|
||||
t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
|
||||
@@ -56,11 +57,17 @@ func TestProviderLifecycle(t *testing.T) {
|
||||
}}
|
||||
}
|
||||
|
||||
for _, pc := range cases {
|
||||
pc := pc
|
||||
for i, pc := range cases {
|
||||
i, pc := i, 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) })
|
||||
@@ -130,65 +137,34 @@ func TestProviderValidation(t *testing.T) {
|
||||
requireClientError(t, err)
|
||||
}
|
||||
|
||||
// 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.
|
||||
// TestSettingsRoundTrip flips the collection toggles and confirms cluster /
|
||||
// subdomain stay immutable, then restores the original state.
|
||||
func TestSettingsRoundTrip(t *testing.T) {
|
||||
ctx := context.Background()
|
||||
|
||||
// The package's TestMain bootstrapped the shared account's endpoint.
|
||||
// Settings are bootstrapped on first provider create.
|
||||
newProvider(t, ctx, "Settings Bootstrap")
|
||||
|
||||
before, err := srv.GetSettings(ctx)
|
||||
require.NoError(t, err, "get settings")
|
||||
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
|
||||
require.NotEmpty(t, before.Cluster, "settings must carry an assigned cluster")
|
||||
|
||||
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")
|
||||
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")
|
||||
|
||||
// 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{
|
||||
Endpoint: "other.cluster.invalid",
|
||||
ProxyAddress: before.ProxyAddress,
|
||||
EnableLogCollection: before.EnableLogCollection,
|
||||
EnablePromptCollection: before.EnablePromptCollection,
|
||||
RedactPii: before.RedactPii,
|
||||
AccessLogRetentionDays: beforeRetention,
|
||||
})
|
||||
requireClientError(t, err)
|
||||
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")
|
||||
|
||||
// Restore the original toggles.
|
||||
_, 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, "restore settings")
|
||||
}
|
||||
|
||||
@@ -1,179 +0,0 @@
|
||||
//go:build e2e
|
||||
|
||||
package agentnetwork
|
||||
|
||||
import (
|
||||
"context"
|
||||
"strings"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/netbirdio/netbird/e2e/harness"
|
||||
"github.com/netbirdio/netbird/shared/management/http/api"
|
||||
)
|
||||
|
||||
// harnessStartFresh boots a dedicated combined server with its own fresh
|
||||
// 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)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
t.Cleanup(func() { _ = fresh.Terminate(context.Background()) })
|
||||
if _, err := fresh.Bootstrap(ctx); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return fresh, nil
|
||||
}
|
||||
|
||||
// TestSettingsBootstrapViaPost covers the explicit bootstrap contract on an
|
||||
// account that has never been bootstrapped: the GET reads as the defaults
|
||||
// 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)
|
||||
require.NoError(t, err, "start dedicated combined server")
|
||||
|
||||
// Before agent-network bootstrap the settings read as the defaults, not
|
||||
// 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.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 has no row to update yet — bootstrap is the explicit POST.
|
||||
_, err = fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
|
||||
EnableLogCollection: true,
|
||||
AccessLogRetentionDays: 30,
|
||||
})
|
||||
requireClientError(t, err)
|
||||
|
||||
// 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.CreateSettings(ctx, api.AgentNetworkSettingsCreateRequest{
|
||||
ProxyAddress: ptr(cluster),
|
||||
EnableLogCollection: ptr(false),
|
||||
EnablePromptCollection: ptr(true),
|
||||
RedactPii: ptr(true),
|
||||
})
|
||||
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")
|
||||
|
||||
// The row is persisted: an independent read agrees on every field.
|
||||
after, err := fresh.GetSettings(ctx)
|
||||
require.NoError(t, err, "get settings after bootstrap must succeed")
|
||||
assert.Equal(t, bootstrapped.Endpoint, after.Endpoint, "bootstrap must persist across reads")
|
||||
assert.Equal(t, bootstrapped.EnableLogCollection, after.EnableLogCollection, "log collection must persist")
|
||||
assert.Equal(t, bootstrapped.EnablePromptCollection, after.EnablePromptCollection, "prompt collection must persist")
|
||||
assert.Equal(t, bootstrapped.RedactPii, after.RedactPii, "redact toggle must persist")
|
||||
|
||||
// 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 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 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{
|
||||
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 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")
|
||||
}
|
||||
@@ -66,7 +66,9 @@ 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) })
|
||||
|
||||
@@ -57,11 +57,12 @@ 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),
|
||||
Name: "vllm",
|
||||
ProviderId: "vllm",
|
||||
UpstreamUrl: vllm.URL,
|
||||
ApiKey: &dummyKey,
|
||||
Enabled: ptr(true),
|
||||
BootstrapCluster: ptr(harness.AgentNetworkCluster),
|
||||
Models: &[]api.AgentNetworkProviderModel{
|
||||
{Id: harness.VLLMModel, InputPer1k: 0.001, OutputPer1k: 0.002},
|
||||
},
|
||||
|
||||
@@ -126,33 +126,17 @@ func (c *Combined) DeleteGuardrail(ctx context.Context, id string) error {
|
||||
return anDelete(ctx, c, "/api/agent-network/guardrails/"+id)
|
||||
}
|
||||
|
||||
// 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.
|
||||
// GetSettings returns the account's agent-network settings row. It exists only
|
||||
// after the first provider create bootstraps it.
|
||||
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. The request must
|
||||
// echo the assigned endpoint and proxy address unchanged — the server rejects
|
||||
// a PUT that tries to change them.
|
||||
// UpdateSettings applies the mutable collection toggles.
|
||||
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)
|
||||
|
||||
@@ -7,7 +7,6 @@ import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"os/exec"
|
||||
"strconv"
|
||||
"strings"
|
||||
@@ -295,29 +294,10 @@ func withSessionID(headers []string, sessionID string) []string {
|
||||
return append(headers, "x-session-id: "+sessionID)
|
||||
}
|
||||
|
||||
// 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
|
||||
// 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. 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) {
|
||||
// to the proxy IP. It returns the HTTP status and response body.
|
||||
func (cl *Client) post(ctx context.Context, endpoint, proxyIP, path, body string, extraHeaders []string) (int, string, error) {
|
||||
url := "https://" + endpoint + path
|
||||
args := []string{
|
||||
"run", "--rm",
|
||||
@@ -326,15 +306,13 @@ func (cl *Client) do(ctx context.Context, method, endpoint, proxyIP, path, body
|
||||
"-sk", "--connect-timeout", "5", "--max-time", "90",
|
||||
"--resolve", endpoint + ":443:" + proxyIP,
|
||||
"-o", "/dev/stderr", "-w", "%{http_code}",
|
||||
"-X", method, url,
|
||||
"-X", "POST", url,
|
||||
"-H", "Content-Type: application/json",
|
||||
}
|
||||
for _, h := range extraHeaders {
|
||||
args = append(args, "-H", h)
|
||||
}
|
||||
if body != "" {
|
||||
args = append(args, "--data", 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.
|
||||
|
||||
@@ -22,42 +22,14 @@ const (
|
||||
// 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
|
||||
)
|
||||
|
||||
// vllmNginxConf emulates a vLLM OpenAI-compatible server over plain HTTP (vLLM's
|
||||
// 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
|
||||
// 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
|
||||
// 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 {
|
||||
@@ -65,26 +37,7 @@ 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"},{"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;
|
||||
return 200 '{"object":"list","data":[{"id":"Qwen/Qwen2.5-0.5B-Instruct","object":"model","owned_by":"vllm"}]}';
|
||||
}
|
||||
location / {
|
||||
default_type application/json;
|
||||
|
||||
7
go.mod
7
go.mod
@@ -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 v0.59.1
|
||||
github.com/quic-go/quic-go v0.55.0
|
||||
github.com/redis/go-redis/v9 v9.7.3
|
||||
github.com/rs/xid v1.3.0
|
||||
github.com/shirou/gopsutil/v4 v4.25.8
|
||||
@@ -114,7 +114,7 @@ require (
|
||||
github.com/ti-mo/conntrack v0.5.1
|
||||
github.com/ti-mo/netfilter v0.5.2
|
||||
github.com/vmihailenco/msgpack/v5 v5.4.1
|
||||
github.com/wailsapp/wails/v3 v3.0.0-beta.3
|
||||
github.com/wailsapp/wails/v3 v3.0.0-alpha2.117
|
||||
github.com/yusufpapurcu/wmi v1.2.4
|
||||
github.com/zcalusic/sysinfo v1.1.3
|
||||
go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.67.0
|
||||
@@ -239,6 +239,7 @@ 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
|
||||
@@ -338,5 +339,3 @@ replace github.com/dexidp/dex => github.com/netbirdio/dex v0.244.1-0.20260716205
|
||||
replace github.com/dexidp/dex/api/v2 => github.com/netbirdio/dex/api/v2 v2.0.0-20260512110716-8d70ad8647c1
|
||||
|
||||
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.3.0.20260810103952-24e716aea4db
|
||||
|
||||
11
go.sum
11
go.sum
@@ -349,6 +349,8 @@ 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=
|
||||
@@ -488,8 +490,6 @@ 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.3.0.20260810103952-24e716aea4db h1:gBOE2r4AW1soSmpYJC5/n9/1L8UQ8+HLjed8CY/TzZY=
|
||||
github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260810103952-24e716aea4db/go.mod h1:bsdahLwBQxXjlmdPPeQyrTcDJfcqAr/ymFj0RXhwtWI=
|
||||
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=
|
||||
@@ -580,8 +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 v0.59.1 h1:0Gmua0HW1Tv7ANR7hUYwRyD0MG5OJfgvYSZasGZzBic=
|
||||
github.com/quic-go/quic-go v0.59.1/go.mod h1:upnsH4Ju1YkqpLXC305eW3yDZ4NfnNbmQRCMWS58IKU=
|
||||
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/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=
|
||||
@@ -660,6 +660,8 @@ github.com/vmihailenco/msgpack/v5 v5.4.1 h1:cQriyiUvjTwOHg8QZaPihLWeRAAVoCpE00IU
|
||||
github.com/vmihailenco/msgpack/v5 v5.4.1/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
|
||||
github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
|
||||
github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
|
||||
github.com/wailsapp/wails/v3 v3.0.0-alpha2.117 h1:udyjqPG3AIgkod5QDR/WblCkpV8R86BFPSrsWxSyt5Y=
|
||||
github.com/wailsapp/wails/v3 v3.0.0-alpha2.117/go.mod h1:74WH2FScMsgucZvHHvv7eOefDXCm/CjuIxqhhZgPhKg=
|
||||
github.com/wlynxg/anet v0.0.5 h1:J3VJGi1gvo0JwZ/P1/Yc/8p63SoW98B5dHkYDmpgvvU=
|
||||
github.com/wlynxg/anet v0.0.5/go.mod h1:eay5PRQr7fIVAMbTbchTnO9gG65Hg/uYGdc7mguHxoA=
|
||||
github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=
|
||||
@@ -791,6 +793,7 @@ 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=
|
||||
|
||||
@@ -11,10 +11,6 @@ SED_STRIP_PADDING='s/=//g'
|
||||
|
||||
NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA"
|
||||
|
||||
# Static IP for Traefik inside the compose bridge network. The management
|
||||
# server trusts X-Forwarded-* headers from this address only.
|
||||
TRAEFIK_IP="172.30.0.10"
|
||||
|
||||
check_docker_compose() {
|
||||
if command -v docker-compose &> /dev/null; then
|
||||
echo "docker-compose"
|
||||
@@ -84,7 +80,7 @@ read_nb_domain() {
|
||||
if ! check_domain_resolves "$value"; then
|
||||
echo "" > /dev/stderr
|
||||
echo "Warning: '$value' does not resolve via DNS from this host." > /dev/stderr
|
||||
echo "Traefik will not be able to issue TLS certificates until it does." > /dev/stderr
|
||||
echo "Caddy will not be able to issue TLS certificates until it does." > /dev/stderr
|
||||
local confirm=""
|
||||
echo -n "Continue anyway? [y/N]: " > /dev/stderr
|
||||
read -r confirm < /dev/tty
|
||||
@@ -96,23 +92,6 @@ read_nb_domain() {
|
||||
echo "$value"
|
||||
}
|
||||
|
||||
read_letsencrypt_email() {
|
||||
if [[ -n "${NETBIRD_LETSENCRYPT_EMAIL:-}" ]]; then
|
||||
echo "$NETBIRD_LETSENCRYPT_EMAIL"
|
||||
return
|
||||
fi
|
||||
local value=""
|
||||
echo "Enter your email for Let's Encrypt certificate notifications." > /dev/stderr
|
||||
echo -n "Email address: " > /dev/stderr
|
||||
read -r value < /dev/tty
|
||||
if [[ -z "$value" ]]; then
|
||||
echo "Email is required for Let's Encrypt." > /dev/stderr
|
||||
read_letsencrypt_email
|
||||
return
|
||||
fi
|
||||
echo "$value"
|
||||
}
|
||||
|
||||
read_required() {
|
||||
local prompt="$1"
|
||||
local value=""
|
||||
@@ -225,11 +204,11 @@ init_environment() {
|
||||
check_openssl
|
||||
DOCKER_COMPOSE_COMMAND=$(check_docker_compose)
|
||||
|
||||
if [[ -f .env ]] || [[ -f docker-compose.yml ]] || [[ -f config.yaml ]]; then
|
||||
if [[ -f .env ]] || [[ -f docker-compose.yml ]] || [[ -f config.yaml ]] || [[ -f Caddyfile ]]; then
|
||||
echo "Generated files already exist in $(pwd)."
|
||||
echo "If you want to reinitialize the environment, please remove them first:"
|
||||
echo " $DOCKER_COMPOSE_COMMAND down --volumes # removes all containers and volumes"
|
||||
echo " rm -f .env docker-compose.yml config.yaml"
|
||||
echo " rm -f .env docker-compose.yml Caddyfile config.yaml"
|
||||
echo "Be aware this will remove all data from the database."
|
||||
exit 1
|
||||
fi
|
||||
@@ -251,9 +230,6 @@ init_environment() {
|
||||
echo ""
|
||||
NETBIRD_DOMAIN=$(read_nb_domain)
|
||||
|
||||
echo ""
|
||||
NETBIRD_LETSENCRYPT_EMAIL=$(read_letsencrypt_email)
|
||||
|
||||
echo ""
|
||||
|
||||
NETBIRD_LICENSE_KEY=$(read_secret "Enter license key (input hidden)")
|
||||
@@ -262,7 +238,6 @@ init_environment() {
|
||||
POSTGRES_DB="netbird"
|
||||
POSTGRES_PASSWORD=$(rand_secret)
|
||||
NETBIRD_ENCRYPTION_KEY=$(rand_b64_key)
|
||||
NETBIRD_SESSION_COOKIE_ENCRYPTION_KEY=$(rand_b64_key)
|
||||
NETBIRD_RELAY_AUTH_SECRET=$(rand_secret)
|
||||
|
||||
POSTGRES_DSN="host=postgres user=${POSTGRES_USER} password=${POSTGRES_PASSWORD} dbname=${POSTGRES_DB} port=5432 sslmode=disable TimeZone=UTC"
|
||||
@@ -272,7 +247,6 @@ init_environment() {
|
||||
echo "Selected:"
|
||||
echo " Traffic flow: ${NETBIRD_TRAFFIC_FLOW}"
|
||||
echo " Domain: ${NETBIRD_DOMAIN}"
|
||||
echo " ACME email: ${NETBIRD_LETSENCRYPT_EMAIL}"
|
||||
echo ""
|
||||
echo "Rendering files into $(pwd) ..."
|
||||
install -m 600 /dev/null .env
|
||||
@@ -282,6 +256,7 @@ init_environment() {
|
||||
if [[ -z "${NETBIRD_LICENSE_SERVER_BASE_URL:-}" ]]; then
|
||||
sed -i.bak '/NETBIRD_LICENSE_SERVER_BASE_URL/d' docker-compose.yml && rm -f docker-compose.yml.bak
|
||||
fi
|
||||
render_caddyfile > Caddyfile
|
||||
install -m 600 /dev/null config.yaml
|
||||
render_config_yaml >> config.yaml
|
||||
|
||||
@@ -308,7 +283,7 @@ init_environment() {
|
||||
echo "All configuration and secrets are stored (mode 600) in $(pwd)/.env"
|
||||
echo ""
|
||||
echo "Tail logs:"
|
||||
echo " cd $(pwd) && $DOCKER_COMPOSE_COMMAND logs -f netbird-server traefik"
|
||||
echo " cd $(pwd) && $DOCKER_COMPOSE_COMMAND logs -f netbird-server caddy"
|
||||
}
|
||||
|
||||
# ------------------------------------------------------------------
|
||||
@@ -331,11 +306,6 @@ NETBIRD_TRAFFIC_FLOW_ENABLED=${NETBIRD_TRAFFIC_FLOW}
|
||||
# Domain
|
||||
NETBIRD_DOMAIN=${NETBIRD_DOMAIN}
|
||||
|
||||
# Reverse proxy (Traefik)
|
||||
NETBIRD_LETSENCRYPT_EMAIL=${NETBIRD_LETSENCRYPT_EMAIL}
|
||||
NETBIRD_TRAEFIK_TAG=${NETBIRD_TRAEFIK_TAG:-v3.6}
|
||||
NETBIRD_TRAEFIK_IP=${TRAEFIK_IP}
|
||||
|
||||
# Image tags. Default to "latest"
|
||||
NETBIRD_DASHBOARD_TAG=${NETBIRD_DASHBOARD_TAG:-latest}
|
||||
NETBIRD_SERVER_TAG=${NETBIRD_SERVER_TAG:-latest}
|
||||
@@ -408,78 +378,26 @@ EOF
|
||||
|
||||
render_compose_common() {
|
||||
cat <<'EOF'
|
||||
# Reverse proxy with automatic TLS via Let's Encrypt. Routes are declared as
|
||||
# labels on the services below and picked up through the Docker provider.
|
||||
traefik:
|
||||
caddy:
|
||||
<<: *default
|
||||
image: traefik:${NETBIRD_TRAEFIK_TAG}
|
||||
container_name: netbird-traefik
|
||||
networks:
|
||||
netbird:
|
||||
ipv4_address: ${NETBIRD_TRAEFIK_IP}
|
||||
command:
|
||||
# Logging
|
||||
- "--log.level=INFO"
|
||||
- "--accesslog=true"
|
||||
# Docker provider
|
||||
- "--providers.docker=true"
|
||||
- "--providers.docker.exposedbydefault=false"
|
||||
- "--providers.docker.network=netbird"
|
||||
# Entrypoints
|
||||
- "--entrypoints.web.address=:80"
|
||||
- "--entrypoints.websecure.address=:443"
|
||||
- "--entrypoints.websecure.allowACMEByPass=true"
|
||||
# readTimeout bounds the whole request, and gRPC streams / relay WebSockets
|
||||
# never end one; idleTimeout would close the keep-alive connection they
|
||||
# are reused over. Entrypoint-wide is the only scope Traefik offers here.
|
||||
# writeTimeout is left alone: it already defaults to 0.
|
||||
- "--entrypoints.websecure.transport.respondingTimeouts.readTimeout=0"
|
||||
- "--entrypoints.websecure.transport.respondingTimeouts.idleTimeout=0"
|
||||
# HTTP to HTTPS redirect
|
||||
- "--entrypoints.web.http.redirections.entrypoint.to=websecure"
|
||||
- "--entrypoints.web.http.redirections.entrypoint.scheme=https"
|
||||
# Let's Encrypt ACME
|
||||
- "--certificatesresolvers.letsencrypt.acme.email=${NETBIRD_LETSENCRYPT_EMAIL}"
|
||||
- "--certificatesresolvers.letsencrypt.acme.storage=/letsencrypt/acme.json"
|
||||
- "--certificatesresolvers.letsencrypt.acme.tlschallenge=true"
|
||||
image: caddy:2
|
||||
container_name: netbird-caddy
|
||||
networks: [netbird]
|
||||
environment:
|
||||
- CADDY_SECURE_DOMAIN=${NETBIRD_DOMAIN}
|
||||
ports:
|
||||
- '443:443'
|
||||
- '443:443/udp'
|
||||
- '80:80'
|
||||
volumes:
|
||||
- /var/run/docker.sock:/var/run/docker.sock:ro
|
||||
- netbird_traefik_letsencrypt:/letsencrypt
|
||||
labels:
|
||||
- traefik.enable=true
|
||||
# Shared security headers, referenced by every NetBird router below. A
|
||||
# label-declared middleware only exists while its container runs, so this
|
||||
# lives on Traefik itself: declaring it on an app container would drop
|
||||
# every router referencing it whenever that container restarts.
|
||||
- traefik.http.middlewares.nb-security.headers.stsSeconds=3600
|
||||
- traefik.http.middlewares.nb-security.headers.stsIncludeSubdomains=true
|
||||
- traefik.http.middlewares.nb-security.headers.contentTypeNosniff=true
|
||||
- traefik.http.middlewares.nb-security.headers.browserXssFilter=true
|
||||
- traefik.http.middlewares.nb-security.headers.referrerPolicy=strict-origin-when-cross-origin
|
||||
- traefik.http.middlewares.nb-security.headers.customResponseHeaders.X-Frame-Options=SAMEORIGIN
|
||||
# Empty value strips the header. Only the dashboard's nginx sets one; the
|
||||
# server emits none. Do not quote it — "" would send a literal Server: "".
|
||||
- traefik.http.middlewares.nb-security.headers.customResponseHeaders.Server=
|
||||
- netbird_caddy_data:/data
|
||||
- ./Caddyfile:/etc/caddy/Caddyfile
|
||||
|
||||
dashboard:
|
||||
<<: *default
|
||||
image: ghcr.io/netbirdio/dashboard-cloud:${NETBIRD_DASHBOARD_TAG}
|
||||
container_name: netbird-dashboard
|
||||
networks: [netbird]
|
||||
labels:
|
||||
- traefik.enable=true
|
||||
# Dashboard catch-all: lowest priority so every route below wins
|
||||
- traefik.http.routers.netbird-dashboard.rule=Host(`${NETBIRD_DOMAIN}`)
|
||||
- traefik.http.routers.netbird-dashboard.entrypoints=websecure
|
||||
- traefik.http.routers.netbird-dashboard.tls=true
|
||||
- traefik.http.routers.netbird-dashboard.tls.certresolver=letsencrypt
|
||||
- traefik.http.routers.netbird-dashboard.middlewares=nb-security@docker
|
||||
- traefik.http.routers.netbird-dashboard.service=dashboard
|
||||
- traefik.http.routers.netbird-dashboard.priority=1
|
||||
- traefik.http.services.dashboard.loadbalancer.server.port=80
|
||||
environment:
|
||||
- NETBIRD_MGMT_API_ENDPOINT=https://${NETBIRD_DOMAIN}
|
||||
- NETBIRD_MGMT_GRPC_API_ENDPOINT=https://${NETBIRD_DOMAIN}
|
||||
@@ -517,28 +435,6 @@ render_compose_server() {
|
||||
- netbird_data:/var/lib/netbird
|
||||
- ./config.yaml:/etc/netbird/config.yaml
|
||||
command: ["--config", "/etc/netbird/config.yaml"]
|
||||
labels:
|
||||
- traefik.enable=true
|
||||
# Signal + Management gRPC (needs an h2c backend for HTTP/2 cleartext)
|
||||
- traefik.http.routers.netbird-grpc.rule=Host(`${NETBIRD_DOMAIN}`) && (PathPrefix(`/signalexchange.SignalExchange/`) || PathPrefix(`/management.ManagementService/`) || PathPrefix(`/management.ProxyService/`))
|
||||
- traefik.http.routers.netbird-grpc.entrypoints=websecure
|
||||
- traefik.http.routers.netbird-grpc.tls=true
|
||||
- traefik.http.routers.netbird-grpc.tls.certresolver=letsencrypt
|
||||
- traefik.http.routers.netbird-grpc.middlewares=nb-security@docker
|
||||
- traefik.http.routers.netbird-grpc.service=netbird-server-h2c
|
||||
- traefik.http.routers.netbird-grpc.priority=100
|
||||
# Relay WebSocket, management API, and the embedded IdP
|
||||
- traefik.http.routers.netbird-backend.rule=Host(`${NETBIRD_DOMAIN}`) && (PathPrefix(`/relay`) || PathPrefix(`/ws-proxy/`) || PathPrefix(`/api`) || PathPrefix(`/oauth2`))
|
||||
- traefik.http.routers.netbird-backend.entrypoints=websecure
|
||||
- traefik.http.routers.netbird-backend.tls=true
|
||||
- traefik.http.routers.netbird-backend.tls.certresolver=letsencrypt
|
||||
- traefik.http.routers.netbird-backend.middlewares=nb-security@docker
|
||||
- traefik.http.routers.netbird-backend.service=netbird-server
|
||||
- traefik.http.routers.netbird-backend.priority=100
|
||||
# Services
|
||||
- traefik.http.services.netbird-server.loadbalancer.server.port=80
|
||||
- traefik.http.services.netbird-server-h2c.loadbalancer.server.port=80
|
||||
- traefik.http.services.netbird-server-h2c.loadbalancer.server.scheme=h2c
|
||||
environment:
|
||||
- NB_LICENSE_KEY=${NETBIRD_LICENSE_KEY}
|
||||
- NETBIRD_LICENSE_SERVER_BASE_URL=${NETBIRD_LICENSE_SERVER_BASE_URL}
|
||||
@@ -601,18 +497,6 @@ render_compose_flow() {
|
||||
- NB_FLOW_NATS_ENDPOINTS=nats://nats:4222
|
||||
- NB_FLOW_NATS_STREAM=traffic-events
|
||||
- NB_FLOW_AUTH_SECRET=${NETBIRD_RELAY_AUTH_SECRET}
|
||||
labels:
|
||||
- traefik.enable=true
|
||||
# Flow receiver gRPC (h2c backend)
|
||||
- traefik.http.routers.netbird-flow.rule=Host(`${NETBIRD_DOMAIN}`) && PathPrefix(`/flow.FlowService/`)
|
||||
- traefik.http.routers.netbird-flow.entrypoints=websecure
|
||||
- traefik.http.routers.netbird-flow.tls=true
|
||||
- traefik.http.routers.netbird-flow.tls.certresolver=letsencrypt
|
||||
- traefik.http.routers.netbird-flow.middlewares=nb-security@docker
|
||||
- traefik.http.routers.netbird-flow.service=netbird-flow-h2c
|
||||
- traefik.http.routers.netbird-flow.priority=100
|
||||
- traefik.http.services.netbird-flow-h2c.loadbalancer.server.port=80
|
||||
- traefik.http.services.netbird-flow-h2c.loadbalancer.server.scheme=h2c
|
||||
|
||||
EOF
|
||||
}
|
||||
@@ -652,16 +536,61 @@ EOF
|
||||
fi
|
||||
cat <<'EOF'
|
||||
netbird_postgres:
|
||||
netbird_traefik_letsencrypt:
|
||||
netbird_caddy_data:
|
||||
|
||||
networks:
|
||||
netbird:
|
||||
name: netbird
|
||||
driver: bridge
|
||||
ipam:
|
||||
config:
|
||||
- subnet: 172.30.0.0/24
|
||||
gateway: 172.30.0.1
|
||||
EOF
|
||||
}
|
||||
|
||||
render_caddyfile() {
|
||||
cat <<'EOF'
|
||||
{
|
||||
servers :80,:443 {
|
||||
protocols h1 h2c h2 h3
|
||||
}
|
||||
}
|
||||
|
||||
(security_headers) {
|
||||
header * {
|
||||
Strict-Transport-Security "max-age=3600; includeSubDomains; preload"
|
||||
X-Content-Type-Options "nosniff"
|
||||
X-Frame-Options "SAMEORIGIN"
|
||||
X-XSS-Protection "1; mode=block"
|
||||
-Server
|
||||
Referrer-Policy strict-origin-when-cross-origin
|
||||
}
|
||||
}
|
||||
|
||||
:80 {
|
||||
redir https://{$CADDY_SECURE_DOMAIN}{uri} permanent
|
||||
}
|
||||
|
||||
{$CADDY_SECURE_DOMAIN}:443 {
|
||||
import security_headers
|
||||
# Signal (gRPC over h2c)
|
||||
reverse_proxy /signalexchange.SignalExchange/* h2c://netbird-server:80
|
||||
# Management (gRPC over h2c + HTTP)
|
||||
reverse_proxy /management.ManagementService/* h2c://netbird-server:80
|
||||
reverse_proxy /api/* netbird-server:80
|
||||
reverse_proxy /ws-proxy/* netbird-server:80
|
||||
# Embedded IdP (OAuth2 endpoints served by netbird server)
|
||||
reverse_proxy /oauth2/* netbird-server:80
|
||||
# Relay (WebSocket multiplexed on the same port)
|
||||
reverse_proxy /relay* netbird-server:80
|
||||
EOF
|
||||
|
||||
if [[ "$NETBIRD_TRAFFIC_FLOW" == "yes" ]]; then
|
||||
cat <<'EOF'
|
||||
# Flow receiver (gRPC over h2c)
|
||||
reverse_proxy /flow.FlowService/* h2c://receiver:80
|
||||
EOF
|
||||
fi
|
||||
|
||||
cat <<'EOF'
|
||||
# Dashboard
|
||||
reverse_proxy /* dashboard:80
|
||||
}
|
||||
EOF
|
||||
}
|
||||
|
||||
@@ -680,7 +609,7 @@ server:
|
||||
logLevel: "info"
|
||||
logFile: "console"
|
||||
|
||||
# TLS is terminated by Traefik in front; leave this block empty.
|
||||
# TLS is terminated by Caddy in front; leave this block empty.
|
||||
tls:
|
||||
certFile: ""
|
||||
keyFile: ""
|
||||
@@ -697,23 +626,12 @@ server:
|
||||
issuer: "https://${NETBIRD_DOMAIN}/oauth2"
|
||||
localAuthDisabled: false
|
||||
signKeyRefreshEnabled: false
|
||||
sessionCookieEncryptionKey: "${NETBIRD_SESSION_COOKIE_ENCRYPTION_KEY}"
|
||||
dashboardRedirectURIs:
|
||||
- "https://${NETBIRD_DOMAIN}/nb-auth"
|
||||
- "https://${NETBIRD_DOMAIN}/nb-silent-auth"
|
||||
cliRedirectURIs:
|
||||
- "http://localhost:53000/"
|
||||
|
||||
# Trust X-Forwarded-* only from the Traefik container's static address. Both
|
||||
# keys must stay in step with the ipv4_address pinned in docker-compose.yml:
|
||||
# trustedPeers decides whether forwarded headers are read at all, and leaving
|
||||
# it unset falls back to 0.0.0.0/0.
|
||||
reverseProxy:
|
||||
trustedPeers:
|
||||
- "${TRAEFIK_IP}/32"
|
||||
trustedHTTPProxies:
|
||||
- "${TRAEFIK_IP}/32"
|
||||
|
||||
store:
|
||||
engine: "postgres"
|
||||
dsn: "${POSTGRES_DSN}"
|
||||
|
||||
@@ -348,7 +348,6 @@ initialize_default_values() {
|
||||
NETBIRD_RELAY_AUTH_SECRET=$(openssl rand -base64 32 | sed "$SED_STRIP_PADDING")
|
||||
# Note: DataStoreEncryptionKey must keep base64 padding (=) for Go's base64.StdEncoding
|
||||
DATASTORE_ENCRYPTION_KEY=$(openssl rand -base64 32)
|
||||
SESSION_COOKIE_ENCRYPTION_KEY=$(openssl rand -base64 32)
|
||||
NETBIRD_STUN_PORT=3478
|
||||
|
||||
# Docker images
|
||||
@@ -528,8 +527,7 @@ generate_configuration_files() {
|
||||
|
||||
# Common files for all configurations
|
||||
render_dashboard_env > dashboard.env
|
||||
install -m 600 /dev/null config.yaml
|
||||
render_combined_yaml >> config.yaml
|
||||
render_combined_yaml > config.yaml
|
||||
return 0
|
||||
}
|
||||
|
||||
@@ -913,7 +911,6 @@ server:
|
||||
auth:
|
||||
issuer: "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/oauth2"
|
||||
signKeyRefreshEnabled: true
|
||||
sessionCookieEncryptionKey: "$SESSION_COOKIE_ENCRYPTION_KEY"
|
||||
dashboardRedirectURIs:
|
||||
- "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/nb-auth"
|
||||
- "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/nb-silent-auth"
|
||||
|
||||
@@ -15,11 +15,7 @@ set -o pipefail
|
||||
# 2. Postgres migration — add Postgres, migrate SQLite data via migrate-store.
|
||||
# 3. Traffic flow — add NATS + flow-enricher + flow-receiver.
|
||||
#
|
||||
# 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.
|
||||
#
|
||||
# To revert a successful migration:
|
||||
# To revert:
|
||||
# docker compose down
|
||||
# rm -f docker-compose.override.yml config.yaml.enterprise
|
||||
# # If Postgres migration was done, also restore the SQLite backup printed
|
||||
@@ -29,15 +25,6 @@ set -o pipefail
|
||||
OVERRIDE_FILE="docker-compose.override.yml"
|
||||
ENTERPRISE_CONFIG_FILE="config.yaml.enterprise"
|
||||
|
||||
# Rollback bookkeeping. ROLLBACK_STATE flips to "armed" the moment the script
|
||||
# starts mutating the deployment, and back to "disarmed" once the migration has
|
||||
# completed successfully.
|
||||
ROLLBACK_STATE="disarmed"
|
||||
ENV_EXISTED="unknown"
|
||||
ENV_BACKUP=""
|
||||
PG_VOLUME_NAME=""
|
||||
BACKUP_DIR=""
|
||||
|
||||
NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA"
|
||||
|
||||
check_docker_compose() {
|
||||
@@ -173,11 +160,11 @@ EOF
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
detect_combined_service() {
|
||||
yq eval '.services | to_entries | map(select(.value.image | test("^(ghcr\\.io/)?netbirdio/netbird-server([:@]|$)"))) | .[0].key // ""' "$COMPOSE_FILE"
|
||||
yq eval '.services | to_entries | map(select(.value.image | test("^netbirdio/netbird-server"))) | .[0].key // ""' "$COMPOSE_FILE"
|
||||
}
|
||||
|
||||
detect_dashboard_service() {
|
||||
yq eval '.services | to_entries | map(select(.value.image | test("^(ghcr\\.io/)?netbirdio/dashboard([:@]|$)"))) | .[0].key // ""' "$COMPOSE_FILE"
|
||||
yq eval '.services | to_entries | map(select(.value.image | test("^netbirdio/dashboard"))) | .[0].key // ""' "$COMPOSE_FILE"
|
||||
}
|
||||
|
||||
detect_config_yaml_host_path() {
|
||||
@@ -374,77 +361,7 @@ render_enterprise_config() {
|
||||
# Execution steps
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
combined_container_id() {
|
||||
$DOCKER_COMPOSE_COMMAND ps -aq "$COMBINED_SERVICE" 2>/dev/null | head -1
|
||||
}
|
||||
|
||||
container_data_mount() {
|
||||
local container="$1"
|
||||
[[ -n "$container" ]] || return 0
|
||||
docker inspect "$container" --format \
|
||||
'{{range .Mounts}}{{if eq .Destination "/var/lib/netbird"}}{{if .Name}}{{.Name}}{{else}}{{.Source}}{{end}}{{end}}{{end}}' 2>/dev/null
|
||||
}
|
||||
|
||||
# The name comes from the container, so `-v` cannot invent an empty volume here.
|
||||
# 0 = empty, 1 = holds data, 2 = could not determine. A failed listing must not
|
||||
# be reported as empty: that would abort a healthy migration over a pull error
|
||||
# or an unreadable bind mount.
|
||||
data_dir_state() {
|
||||
local src="$1" out
|
||||
if [[ "$src" == /* ]]; then
|
||||
[[ -d "$src" ]] || return 2
|
||||
out=$(ls -A "$src" 2>/dev/null) || return 2
|
||||
else
|
||||
docker volume inspect "$src" &> /dev/null || return 0
|
||||
out=$(docker run --rm -v "${src}:/d:ro" busybox sh -c 'ls -A /d' 2>/dev/null) || return 2
|
||||
fi
|
||||
[[ -z "$out" ]] && return 0
|
||||
return 1
|
||||
}
|
||||
|
||||
check_data_directory() {
|
||||
[[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0
|
||||
|
||||
local container
|
||||
container=$(combined_container_id)
|
||||
if [[ -z "$container" ]]; then
|
||||
echo "" > /dev/stderr
|
||||
echo "No container found for service '$COMBINED_SERVICE'." > /dev/stderr
|
||||
echo "The migration backs up the store by copying it out of that container," > /dev/stderr
|
||||
echo "so it has to exist. Start the deployment and re-run:" > /dev/stderr
|
||||
echo " $DOCKER_COMPOSE_COMMAND up -d" > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
|
||||
local src
|
||||
src=$(container_data_mount "$container")
|
||||
if [[ -z "$src" ]]; then
|
||||
echo "" > /dev/stderr
|
||||
echo "The '$COMBINED_SERVICE' container has nothing mounted at /var/lib/netbird." > /dev/stderr
|
||||
echo "Cannot locate the NetBird store to back it up." > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
|
||||
local state=0
|
||||
data_dir_state "$src" || state=$?
|
||||
if [[ $state -eq 0 ]]; then
|
||||
echo "" > /dev/stderr
|
||||
echo "The NetBird data directory is empty:" > /dev/stderr
|
||||
echo " $src" > /dev/stderr
|
||||
echo "There is nothing to migrate. Check that you are running this from the" > /dev/stderr
|
||||
echo "deployment directory of the NetBird install you mean to migrate." > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
if [[ $state -eq 2 ]]; then
|
||||
echo " ⚠ Could not read $src to confirm it holds data — continuing." > /dev/stderr
|
||||
echo " The backup step still fails loudly if it turns out to be empty." > /dev/stderr
|
||||
fi
|
||||
|
||||
echo " Data directory: $src"
|
||||
}
|
||||
|
||||
# Only for the Postgres volume, which has no container to read it off yet.
|
||||
resolve_compose_volume() {
|
||||
resolve_data_volume() {
|
||||
local short="$1"
|
||||
local actual
|
||||
# Resolve project-prefixed volume name from Docker Compose config first.
|
||||
@@ -474,21 +391,18 @@ resolve_compose_volume() {
|
||||
backup_sqlite() {
|
||||
BACKUP_DIR="$(pwd)/backups/sqlite-pre-enterprise-$(date +%Y%m%d-%H%M%S)"
|
||||
mkdir -p "$BACKUP_DIR"
|
||||
|
||||
local container
|
||||
container=$(combined_container_id)
|
||||
if [[ -z "$container" ]]; then
|
||||
echo " ⚠ No container found for '$COMBINED_SERVICE' — cannot back up the store." > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
|
||||
echo "Backing up the NetBird store to $BACKUP_DIR ..."
|
||||
docker cp "${container}:/var/lib/netbird/." "$BACKUP_DIR/"
|
||||
|
||||
local data_volume_actual
|
||||
data_volume_actual=$(resolve_data_volume "$DATA_VOLUME")
|
||||
echo "Backing up SQLite store from volume '$data_volume_actual' to $BACKUP_DIR ..."
|
||||
docker run --rm \
|
||||
-v "${data_volume_actual}:/var/lib/netbird:ro" \
|
||||
-v "${BACKUP_DIR}:/backup" \
|
||||
busybox \
|
||||
sh -c 'cp -a /var/lib/netbird/. /backup/ 2>/dev/null || true'
|
||||
local copied
|
||||
copied=$(find "$BACKUP_DIR" -mindepth 1 | head -1)
|
||||
if [[ -z "$copied" ]]; then
|
||||
echo " ⚠ Backup directory is empty — /var/lib/netbird held no data. Aborting." > /dev/stderr
|
||||
echo " ⚠ Backup directory is empty — the volume '$data_volume_actual' didn't contain data. Aborting." > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
echo " done"
|
||||
@@ -500,135 +414,6 @@ run_migrate_store() {
|
||||
echo " done"
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Rollback — a failed run must not leave the operator with a stopped stack and
|
||||
# half-written artifacts.
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
# Resolve the name Compose would give the Postgres volume before the override
|
||||
# exists, so a leftover volume can be spotted up front.
|
||||
compose_project_name() {
|
||||
local container project
|
||||
container=$($DOCKER_COMPOSE_COMMAND ps -aq 2>/dev/null | head -1)
|
||||
if [[ -n "$container" ]]; then
|
||||
project=$(docker inspect "$container" \
|
||||
--format '{{index .Config.Labels "com.docker.compose.project"}}' 2>/dev/null)
|
||||
if [[ -n "$project" ]]; then
|
||||
echo "$project"
|
||||
return 0
|
||||
fi
|
||||
fi
|
||||
project=$($DOCKER_COMPOSE_COMMAND config 2>/dev/null | yq eval '.name // ""' - 2>/dev/null)
|
||||
if [[ -n "$project" ]] && [[ "$project" != "null" ]]; then
|
||||
echo "$project"
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
postgres_volume_name() {
|
||||
local project
|
||||
project=$(compose_project_name)
|
||||
if [[ -n "$project" ]]; then
|
||||
echo "${project}_netbird_postgres"
|
||||
fi
|
||||
return 0
|
||||
}
|
||||
|
||||
# Postgres skips initdb when its data directory is non-empty, so a volume left
|
||||
# behind by an interrupted run would keep the old password and old contents,
|
||||
# and migrate-store would fail against it.
|
||||
check_stale_postgres_volume() {
|
||||
[[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0
|
||||
|
||||
PG_VOLUME_NAME=$(postgres_volume_name)
|
||||
if [[ -z "$PG_VOLUME_NAME" ]]; then
|
||||
echo ""
|
||||
echo " ⚠ Could not determine the Compose project name, so a Postgres volume"
|
||||
echo " left over from an earlier attempt cannot be checked for. If a"
|
||||
echo " previous run failed, remove it before continuing:"
|
||||
echo " docker volume ls | grep netbird_postgres"
|
||||
return 0
|
||||
fi
|
||||
docker volume inspect "$PG_VOLUME_NAME" &> /dev/null || return 0
|
||||
|
||||
echo ""
|
||||
echo " ⚠ A Postgres volume from an earlier attempt already exists:"
|
||||
echo " $PG_VOLUME_NAME"
|
||||
echo " Postgres does not re-initialise a non-empty data directory, so the"
|
||||
echo " migration would run against stale credentials and stale data."
|
||||
local remove
|
||||
remove=$(read_yes_no " Remove it and continue?" "y")
|
||||
if [[ "$remove" != "yes" ]]; then
|
||||
echo "" > /dev/stderr
|
||||
echo "Aborted. Remove it manually with: docker volume rm $PG_VOLUME_NAME" > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
docker volume rm "$PG_VOLUME_NAME" > /dev/null
|
||||
echo " Removed."
|
||||
}
|
||||
|
||||
# Undo whatever this run changed and start the previous deployment again.
|
||||
rollback() {
|
||||
ROLLBACK_STATE="done"
|
||||
|
||||
echo ""
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
echo " Migration failed — restoring the previous deployment"
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
|
||||
# Resolve while the override is still present; without it Compose no longer
|
||||
# knows about the Postgres volume.
|
||||
local pg_volume="$PG_VOLUME_NAME"
|
||||
if [[ -z "$pg_volume" ]] && [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
|
||||
pg_volume=$(postgres_volume_name)
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "Stopping services ..."
|
||||
$DOCKER_COMPOSE_COMMAND down || true
|
||||
|
||||
echo "Removing generated files ..."
|
||||
rm -f "$OVERRIDE_FILE" "$ENTERPRISE_CONFIG_FILE"
|
||||
|
||||
# Restore .env to exactly what it was, or remove it if this run created it.
|
||||
if [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]]; then
|
||||
mv -f "$ENV_BACKUP" .env || echo " ⚠ Could not restore .env from $ENV_BACKUP." > /dev/stderr
|
||||
elif [[ "$ENV_EXISTED" == "no" ]]; then
|
||||
rm -f .env || true
|
||||
fi
|
||||
|
||||
# Only ever the volume this run created — never the NetBird data volume.
|
||||
if [[ -n "$pg_volume" ]] && [[ "$pg_volume" != "null" ]]; then
|
||||
echo "Removing Postgres volume $pg_volume ..."
|
||||
docker volume rm "$pg_volume" &> /dev/null || true
|
||||
fi
|
||||
|
||||
echo "Starting the previous deployment ..."
|
||||
if ! $DOCKER_COMPOSE_COMMAND up -d; then
|
||||
echo ""
|
||||
echo " ⚠ Could not start the previous deployment automatically." > /dev/stderr
|
||||
echo " Run: $DOCKER_COMPOSE_COMMAND up -d" > /dev/stderr
|
||||
fi
|
||||
|
||||
echo ""
|
||||
echo "Rolled back. Your docker-compose.yml, config.yaml and the NetBird data"
|
||||
echo "volume were never modified."
|
||||
if [[ -n "$BACKUP_DIR" ]] && [[ -d "$BACKUP_DIR" ]]; then
|
||||
echo "The SQLite backup taken during this run is kept at:"
|
||||
echo " $BACKUP_DIR"
|
||||
fi
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
}
|
||||
|
||||
on_exit() {
|
||||
local code=$?
|
||||
trap - EXIT
|
||||
if [[ $code -ne 0 ]] && [[ "$ROLLBACK_STATE" == "armed" ]]; then
|
||||
rollback
|
||||
fi
|
||||
exit $code
|
||||
}
|
||||
|
||||
# ---------------------------------------------------------------------------
|
||||
# Main
|
||||
# ---------------------------------------------------------------------------
|
||||
@@ -661,12 +446,12 @@ init_migration() {
|
||||
COMPOSE_NETWORK=$(detect_compose_network)
|
||||
|
||||
if [[ -z "$COMBINED_SERVICE" ]]; then
|
||||
echo "Could not find a service running netbirdio/netbird-server or ghcr.io/netbirdio/netbird-server in $COMPOSE_FILE." > /dev/stderr
|
||||
echo "Could not find a service running 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 or ghcr.io/netbirdio/dashboard in $COMPOSE_FILE." > /dev/stderr
|
||||
echo "Could not find a service running netbirdio/dashboard* in $COMPOSE_FILE." > /dev/stderr
|
||||
exit 1
|
||||
fi
|
||||
if [[ -z "$CONFIG_YAML_HOST" ]]; then
|
||||
@@ -756,15 +541,9 @@ init_migration() {
|
||||
ENABLE_FLOW="no"
|
||||
echo "Step 3 (traffic flow) skipped — requires Postgres."
|
||||
fi
|
||||
|
||||
check_data_directory
|
||||
check_stale_postgres_volume
|
||||
}
|
||||
|
||||
apply_changes() {
|
||||
# From here on a failure must roll the deployment back.
|
||||
ROLLBACK_STATE="armed"
|
||||
|
||||
echo ""
|
||||
echo "Writing $OVERRIDE_FILE ..."
|
||||
install -m 644 /dev/null "$OVERRIDE_FILE"
|
||||
@@ -785,14 +564,6 @@ apply_changes() {
|
||||
# picks it up automatically.
|
||||
echo "Writing .env additions (mode 600) ..."
|
||||
local ENV_FILE=".env"
|
||||
# Snapshot the operator's .env so a rollback can restore it byte for byte.
|
||||
if [[ -f "$ENV_FILE" ]]; then
|
||||
ENV_EXISTED="yes"
|
||||
ENV_BACKUP="${ENV_FILE}.pre-enterprise-$(date +%Y%m%d-%H%M%S)"
|
||||
cp -p "$ENV_FILE" "$ENV_BACKUP"
|
||||
else
|
||||
ENV_EXISTED="no"
|
||||
fi
|
||||
touch "$ENV_FILE"
|
||||
chmod 600 "$ENV_FILE"
|
||||
{
|
||||
@@ -821,16 +592,11 @@ apply_changes() {
|
||||
|
||||
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
|
||||
echo ""
|
||||
# Stop, but keep the containers: the backup reads the store out of one.
|
||||
echo "Stopping services so the store is quiescent ..."
|
||||
$DOCKER_COMPOSE_COMMAND stop
|
||||
echo "Stopping existing services (volumes preserved) ..."
|
||||
$DOCKER_COMPOSE_COMMAND down
|
||||
|
||||
backup_sqlite
|
||||
|
||||
echo ""
|
||||
echo "Removing stopped containers (volumes preserved) ..."
|
||||
$DOCKER_COMPOSE_COMMAND down
|
||||
|
||||
echo ""
|
||||
echo "Starting Postgres ..."
|
||||
$DOCKER_COMPOSE_COMMAND up -d postgres
|
||||
@@ -860,9 +626,6 @@ apply_changes() {
|
||||
|
||||
echo ""
|
||||
echo "Migration complete."
|
||||
|
||||
# Nothing left to undo.
|
||||
ROLLBACK_STATE="disarmed"
|
||||
}
|
||||
|
||||
print_summary() {
|
||||
@@ -880,7 +643,6 @@ print_summary() {
|
||||
echo " $OVERRIDE_FILE"
|
||||
[[ "$MIGRATE_POSTGRES" == "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)"
|
||||
echo ""
|
||||
echo " Tail logs:"
|
||||
@@ -889,27 +651,19 @@ print_summary() {
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
echo " To revert"
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
echo " $DOCKER_COMPOSE_COMMAND down"
|
||||
if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
|
||||
# Resolve the project-prefixed volume name now, before the override is gone.
|
||||
local pg_volume
|
||||
pg_volume=$(resolve_compose_volume "netbird_postgres")
|
||||
echo " # Stop, but keep the containers so the store can be copied back in:"
|
||||
echo " $DOCKER_COMPOSE_COMMAND stop"
|
||||
echo " # Restore SQLite from the backup created during this run:"
|
||||
echo " docker cp ${BACKUP_DIR}/. \$($DOCKER_COMPOSE_COMMAND ps -aq $COMBINED_SERVICE):/var/lib/netbird/"
|
||||
echo " $DOCKER_COMPOSE_COMMAND down"
|
||||
# Resolve project-prefixed volume names now (before override is removed).
|
||||
local pg_volume data_volume_actual
|
||||
pg_volume=$(resolve_data_volume "netbird_postgres")
|
||||
data_volume_actual=$(resolve_data_volume "$DATA_VOLUME")
|
||||
echo " # Remove the Postgres volume FIRST, before deleting the override file:"
|
||||
echo " docker volume rm $pg_volume"
|
||||
else
|
||||
echo " $DOCKER_COMPOSE_COMMAND down"
|
||||
echo " # Restore SQLite from the backup created during this run:"
|
||||
echo " docker run --rm -v ${data_volume_actual}:/var/lib/netbird -v ${BACKUP_DIR}:/backup busybox sh -c 'cp -a /backup/. /var/lib/netbird/'"
|
||||
fi
|
||||
echo " rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE"
|
||||
if [[ "$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
|
||||
echo " rm -f .env # created by this run"
|
||||
else
|
||||
echo " # Remove migrate-to-enterprise.sh additions from .env (search for the timestamp marker)"
|
||||
fi
|
||||
echo " # Remove migrate-to-enterprise.sh additions from .env (search for the timestamp marker)"
|
||||
echo " $DOCKER_COMPOSE_COMMAND up -d"
|
||||
echo "──────────────────────────────────────────────────────────────────────"
|
||||
}
|
||||
@@ -918,10 +672,6 @@ print_summary() {
|
||||
# Run
|
||||
# ---------------------------------------------------------------------------
|
||||
|
||||
trap on_exit EXIT
|
||||
# Turn signals into a normal exit so the EXIT trap can roll back.
|
||||
trap 'exit 130' INT TERM
|
||||
|
||||
init_migration
|
||||
apply_changes
|
||||
print_summary
|
||||
|
||||
File diff suppressed because it is too large
Load Diff
@@ -176,7 +176,6 @@ 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)
|
||||
@@ -358,7 +357,6 @@ 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)
|
||||
|
||||
@@ -296,8 +296,6 @@ 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},
|
||||
@@ -357,8 +355,6 @@ 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},
|
||||
@@ -410,8 +406,6 @@ 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},
|
||||
|
||||
@@ -1,36 +0,0 @@
|
||||
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)
|
||||
}
|
||||
}
|
||||
}
|
||||
@@ -102,8 +102,8 @@ func TestSettingsHandler_GetExposesCollectionToggles(t *testing.T) {
|
||||
|
||||
require.NoError(t, f.store.SaveAgentNetworkSettings(context.Background(), &agentNetworkTypes.Settings{
|
||||
AccountID: testAccountID,
|
||||
Domain: "violet.eu.proxy.netbird.io",
|
||||
ProxyAddress: "eu.proxy.netbird.io",
|
||||
Cluster: "eu.proxy.netbird.io",
|
||||
Subdomain: "violet",
|
||||
EnableLogCollection: true,
|
||||
EnablePromptCollection: true,
|
||||
RedactPii: false,
|
||||
|
||||
@@ -17,7 +17,6 @@ import (
|
||||
|
||||
"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
|
||||
agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
|
||||
"github.com/netbirdio/netbird/management/server/account"
|
||||
nbcontext "github.com/netbirdio/netbird/management/server/context"
|
||||
"github.com/netbirdio/netbird/management/server/permissions"
|
||||
"github.com/netbirdio/netbird/management/server/store"
|
||||
@@ -62,23 +61,10 @@ func newAgentNetworkHandlerFixture(t *testing.T) *agentNetworkHandlerFixture {
|
||||
Return(true, context.Background(), nil).
|
||||
AnyTimes()
|
||||
|
||||
// Swallow activity events so the mutation paths (create/update/delete)
|
||||
// are exercisable through the HTTP layer.
|
||||
accounts := account.NewMockManager(ctrl)
|
||||
accounts.EXPECT().
|
||||
StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).
|
||||
AnyTimes()
|
||||
accounts.EXPECT().
|
||||
UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).
|
||||
AnyTimes()
|
||||
|
||||
manager := agentnetwork.NewManager(st, perms, accounts, nil)
|
||||
manager := agentnetwork.NewManager(st, perms, nil, nil)
|
||||
h := &handler{manager: manager}
|
||||
|
||||
router := mux.NewRouter()
|
||||
router.HandleFunc("/agent-network/providers", h.createProvider).Methods("POST")
|
||||
router.HandleFunc("/agent-network/providers/{providerId}", h.getProvider).Methods("GET")
|
||||
router.HandleFunc("/agent-network/providers/{providerId}", h.updateProvider).Methods("PUT")
|
||||
h.addPolicyEndpoints(router)
|
||||
h.addConsumptionEndpoints(router)
|
||||
h.addBudgetRuleEndpoints(router)
|
||||
|
||||
@@ -155,7 +155,12 @@ func (h *handler) createProvider(w http.ResponseWriter, r *http.Request) {
|
||||
provider := types.NewProvider(userAuth.AccountId)
|
||||
provider.FromAPIRequest(&req)
|
||||
|
||||
created, err := h.manager.CreateProvider(r.Context(), userAuth.UserId, provider)
|
||||
bootstrapCluster := ""
|
||||
if req.BootstrapCluster != nil {
|
||||
bootstrapCluster = *req.BootstrapCluster
|
||||
}
|
||||
|
||||
created, err := h.manager.CreateProvider(r.Context(), userAuth.UserId, provider, bootstrapCluster)
|
||||
if err != nil {
|
||||
util.WriteError(r.Context(), err, w)
|
||||
return
|
||||
|
||||
@@ -1,9 +1,7 @@
|
||||
package handlers
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"math"
|
||||
nethttp "net/http"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/assert"
|
||||
@@ -53,50 +51,3 @@ func TestValidate_ModelRates(t *testing.T) {
|
||||
assert.Error(t, validate(base(m), true), "case %q must be rejected", name)
|
||||
}
|
||||
}
|
||||
|
||||
// TestProviderHandler_UpdateReplacesFullState pins the update contract shared
|
||||
// with the other PUT endpoints: the request replaces the provider's mutable
|
||||
// state, so optional fields absent from the JSON land as their zero values.
|
||||
// The two exceptions are server-side: the api_key (a secret — omitted means
|
||||
// "not rotated") and the session keypair, both preserved by the manager. The
|
||||
// identity headers stay on the wire as explicit empty strings so a cleared
|
||||
// value round-trips.
|
||||
func TestProviderHandler_UpdateReplacesFullState(t *testing.T) {
|
||||
f := newAgentNetworkHandlerFixture(t)
|
||||
|
||||
create := `{
|
||||
"provider_id": "openai_api",
|
||||
"name": "openai",
|
||||
"upstream_url": "https://api.openai.com",
|
||||
"api_key": "sk-test",
|
||||
"enabled": true,
|
||||
"metadata_disabled": true,
|
||||
"skip_tls_verification": true,
|
||||
"extra_values": {"x-portkey-config": "pc-prod-3f2a"},
|
||||
"identity_header_user_id": "x-bf-dim-netbird_user_id",
|
||||
"models": [{"id": "gpt-4o", "input_per_1k": 0.0025, "output_per_1k": 0.01}]
|
||||
}`
|
||||
rec := f.do(t, nethttp.MethodPost, "/agent-network/providers", create)
|
||||
require.Equal(t, nethttp.StatusOK, rec.Code, "create must succeed: %s", rec.Body.String())
|
||||
|
||||
var created api.AgentNetworkProvider
|
||||
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &created))
|
||||
|
||||
// Minimal update: only the required fields, no api_key. Everything
|
||||
// optional must land as its zero value.
|
||||
update := `{"provider_id": "openai_api", "name": "openai-renamed", "upstream_url": "https://api.openai.com", "enabled": true}`
|
||||
rec = f.do(t, nethttp.MethodPut, "/agent-network/providers/"+created.Id, update)
|
||||
require.Equal(t, nethttp.StatusOK, rec.Code, "update without api_key must succeed (key is preserved): %s", rec.Body.String())
|
||||
|
||||
var updated api.AgentNetworkProvider
|
||||
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &updated))
|
||||
assert.Equal(t, "openai-renamed", updated.Name, "sent field must apply")
|
||||
assert.True(t, updated.Enabled, "sent field must apply")
|
||||
assert.False(t, updated.MetadataDisabled, "omitted metadata_disabled must land as false — PUT replaces the full state")
|
||||
assert.False(t, updated.SkipTlsVerification, "omitted skip_tls_verification must land as false")
|
||||
assert.Nil(t, updated.ExtraValues, "omitted extra_values must be cleared")
|
||||
assert.Equal(t, "", updated.IdentityHeaderUserId, "omitted identity header must be cleared yet stay on the wire")
|
||||
assert.Empty(t, updated.Models, "omitted models must be cleared")
|
||||
assert.Contains(t, rec.Body.String(), `"identity_header_user_id":""`,
|
||||
"cleared identity header must round-trip as an explicit empty string")
|
||||
}
|
||||
|
||||
@@ -2,6 +2,7 @@ package handlers
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"net/http"
|
||||
|
||||
"github.com/gorilla/mux"
|
||||
@@ -10,62 +11,19 @@ import (
|
||||
nbcontext "github.com/netbirdio/netbird/management/server/context"
|
||||
"github.com/netbirdio/netbird/shared/management/http/api"
|
||||
"github.com/netbirdio/netbird/shared/management/http/util"
|
||||
"github.com/netbirdio/netbird/shared/management/status"
|
||||
)
|
||||
|
||||
// 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.
|
||||
// addSettingsEndpoints registers the Agent Network settings routes. The
|
||||
// settings row is bootstrapped server-side on first provider create; GET reads
|
||||
// it and PUT updates the mutable collection toggles (cluster/subdomain stay
|
||||
// immutable).
|
||||
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.
|
||||
// A request carrying a cluster bootstraps the row when the account doesn't
|
||||
// have one yet.
|
||||
// updateSettings applies the collection toggles to the account's settings row.
|
||||
func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) {
|
||||
userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
|
||||
if err != nil {
|
||||
@@ -90,27 +48,11 @@ 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.
|
||||
// getSettings returns the account's agent-network settings. The settings
|
||||
// row is bootstrapped on first provider create, so freshly-onboarded
|
||||
// accounts have nothing to read. Rather than 404-ing in that case (which
|
||||
// the dashboard would have to special-case), return a JSON null with 200
|
||||
// so consumers can branch on the body alone.
|
||||
func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
|
||||
userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
|
||||
if err != nil {
|
||||
@@ -120,6 +62,11 @@ func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
|
||||
|
||||
settings, err := h.manager.GetSettings(r.Context(), userAuth.AccountId, userAuth.UserId)
|
||||
if err != nil {
|
||||
var sErr *status.Error
|
||||
if errors.As(err, &sErr) && sErr.Type() == status.NotFound {
|
||||
util.WriteJSONObject(r.Context(), w, nil)
|
||||
return
|
||||
}
|
||||
util.WriteError(r.Context(), err, w)
|
||||
return
|
||||
}
|
||||
|
||||
@@ -1,395 +0,0 @@
|
||||
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 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)
|
||||
|
||||
rec := f.do(t, http.MethodGet, "/agent-network/settings", "")
|
||||
require.Equal(t, http.StatusOK, rec.Code,
|
||||
"unbootstrapped account must read as 200 with defaults: got %d body=%s", rec.Code, rec.Body.String())
|
||||
require.NotEqual(t, "null", trimSpace(rec.Body.String()),
|
||||
"the legacy 200+null shape must not come back")
|
||||
|
||||
var got api.AgentNetworkSettings
|
||||
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
|
||||
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")
|
||||
require.NotNil(t, got.AccessLogRetentionDays)
|
||||
assert.Equal(t, 30, *got.AccessLogRetentionDays, "defaults must show the bootstrap retention")
|
||||
assert.Nil(t, got.CreatedAt, "no timestamps before a row exists")
|
||||
assert.Nil(t, got.UpdatedAt, "no timestamps before a row exists")
|
||||
}
|
||||
|
||||
// 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.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.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, 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_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,
|
||||
"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 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.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", 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
|
||||
require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
|
||||
assert.True(t, got.EnableLogCollection, "sent toggle must apply")
|
||||
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, 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_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.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))
|
||||
|
||||
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())
|
||||
}
|
||||
|
||||
// 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))
|
||||
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")
|
||||
}
|
||||
@@ -1,37 +0,0 @@
|
||||
package labelgen
|
||||
|
||||
// adjectives is the descriptor half of a generated label. It pairs with the
|
||||
// noun pool in words.go to form `<adjective>-<noun>` 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",
|
||||
}
|
||||
@@ -64,20 +64,3 @@ 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))]
|
||||
}
|
||||
|
||||
@@ -99,82 +99,3 @@ 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))
|
||||
}
|
||||
|
||||
@@ -22,6 +22,7 @@ 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"
|
||||
)
|
||||
|
||||
@@ -47,7 +48,7 @@ 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) (*types.Provider, error)
|
||||
CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error)
|
||||
UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error)
|
||||
DeleteProvider(ctx context.Context, accountID, userID, providerID string) error
|
||||
|
||||
@@ -70,9 +71,7 @@ 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)
|
||||
@@ -124,10 +123,11 @@ type managerImpl struct {
|
||||
proxyController proxy.Controller
|
||||
|
||||
// reconcileCache holds the last set of synthesised proxy mappings
|
||||
// per account, each paired with the proxy that served it, so a change
|
||||
// of serving proxy can be diffed without re-deriving it.
|
||||
// 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.
|
||||
reconcileMu sync.Mutex
|
||||
reconcileCache map[string]map[string]syntheticMapping
|
||||
reconcileCache map[string]map[string]*proto.ProxyMapping
|
||||
|
||||
// labelRngMu guards labelRng. PickUnique consumes math/rand.Source
|
||||
// state; concurrent provider creates would otherwise race.
|
||||
@@ -151,7 +151,7 @@ func NewManager(
|
||||
accountManager: accountManager,
|
||||
permissionsManager: permissionsManager,
|
||||
proxyController: proxyController,
|
||||
reconcileCache: make(map[string]map[string]syntheticMapping),
|
||||
reconcileCache: make(map[string]map[string]*proto.ProxyMapping),
|
||||
labelRng: rand.New(rand.NewSource(time.Now().UnixNano())),
|
||||
}
|
||||
}
|
||||
@@ -170,14 +170,19 @@ 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. 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) {
|
||||
// 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 {
|
||||
return nil, err
|
||||
}
|
||||
if strings.TrimSpace(bootstrapCluster) != "" {
|
||||
if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
|
||||
// An empty api_key would silently produce a synthesised service
|
||||
// that 401s on every upstream request. Surface the misconfiguration
|
||||
@@ -201,6 +206,16 @@ 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, 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)
|
||||
|
||||
@@ -544,152 +559,40 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r
|
||||
return nil
|
||||
}
|
||||
|
||||
// UpdateSettings replaces the mutable account-level settings — the collection
|
||||
// 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.
|
||||
// UpdateSettings applies the mutable account-level settings — the collection
|
||||
// toggles — onto the existing row. Cluster and Subdomain are immutable and are
|
||||
// preserved from the persisted row regardless of the input. 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
|
||||
}
|
||||
|
||||
// The row lock from LockingStrengthUpdate only holds for the duration of
|
||||
// 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:
|
||||
case isNotFound(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
|
||||
existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
|
||||
existing.UpdatedAt = time.Now().UTC()
|
||||
|
||||
if err := tx.SaveAgentNetworkSettings(ctx, existing); err != nil {
|
||||
return fmt.Errorf("save agent network settings: %w", err)
|
||||
}
|
||||
updated = existing
|
||||
return nil
|
||||
})
|
||||
existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
return nil, fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
|
||||
existing.EnableLogCollection = settings.EnableLogCollection
|
||||
existing.EnablePromptCollection = settings.EnablePromptCollection
|
||||
existing.RedactPii = settings.RedactPii
|
||||
existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
|
||||
existing.UpdatedAt = time.Now().UTC()
|
||||
|
||||
if err := m.store.SaveAgentNetworkSettings(ctx, existing); err != nil {
|
||||
return nil, fmt.Errorf("save agent network settings: %w", err)
|
||||
}
|
||||
|
||||
m.accountManager.StoreEvent(ctx, userID, settings.AccountID, settings.AccountID, activity.AgentNetworkSettingsUpdated, map[string]any{
|
||||
"log_collection": updated.EnableLogCollection,
|
||||
"prompt_collection": updated.EnablePromptCollection,
|
||||
"redact_pii": updated.RedactPii,
|
||||
"log_collection": existing.EnableLogCollection,
|
||||
"prompt_collection": existing.EnablePromptCollection,
|
||||
"redact_pii": existing.RedactPii,
|
||||
})
|
||||
m.reconcile(ctx, settings.AccountID)
|
||||
|
||||
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
|
||||
return errors.As(err, &sErr) && sErr.Type() == status.NotFound
|
||||
return existing, nil
|
||||
}
|
||||
|
||||
// validateProviderRefs ensures every destination provider id refers to a
|
||||
@@ -713,181 +616,91 @@ func (m *managerImpl) validateProviderRefs(ctx context.Context, accountID string
|
||||
return nil
|
||||
}
|
||||
|
||||
// GetSettings returns the agent-network settings row for the account. When no
|
||||
// row has been bootstrapped yet, the defaults are returned (without
|
||||
// persisting) with cluster and subdomain empty — settings always read as an
|
||||
// object, like the account and DNS settings endpoints.
|
||||
// GetSettings returns the agent-network settings row for the account.
|
||||
// Returns the underlying status.NotFound when no row has been
|
||||
// bootstrapped yet (i.e. the account has no providers).
|
||||
func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error) {
|
||||
if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Read); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
settings, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
|
||||
switch {
|
||||
case err == nil:
|
||||
return settings, nil
|
||||
case isNotFound(err):
|
||||
return types.DefaultSettings(accountID), nil
|
||||
default:
|
||||
return nil, err
|
||||
}
|
||||
return m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
|
||||
}
|
||||
|
||||
// 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
|
||||
|
||||
// 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")
|
||||
// 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.
|
||||
// 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 err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil {
|
||||
return nil, err
|
||||
var sErr *status.Error
|
||||
if !errors.As(err, &sErr) || sErr.Type() != status.NotFound {
|
||||
return fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create)
|
||||
}
|
||||
|
||||
func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID, providerCluster string) (*types.Settings, error) {
|
||||
if accountID == "" {
|
||||
return nil, fmt.Errorf("bootstrap settings: account id is required")
|
||||
}
|
||||
if strings.TrimSpace(providerCluster) == "" {
|
||||
return nil, fmt.Errorf("bootstrap settings: provider cluster is required")
|
||||
}
|
||||
|
||||
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")
|
||||
existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
|
||||
if err == nil {
|
||||
return existing, nil
|
||||
}
|
||||
|
||||
// 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) {
|
||||
var sErr *status.Error
|
||||
if !errors.As(err, &sErr) || sErr.Type() != status.NotFound {
|
||||
return nil, fmt.Errorf("get agent network settings: %w", err)
|
||||
}
|
||||
|
||||
siblings, err := m.store.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.CreatedAt = now
|
||||
settings.UpdatedAt = now
|
||||
|
||||
var err error
|
||||
if hasEndpoint {
|
||||
err = m.bootstrapSelfAddressed(ctx, settings, endpoint)
|
||||
} else {
|
||||
err = m.bootstrapLabeled(ctx, settings, proxyAddress)
|
||||
settings := &types.Settings{
|
||||
AccountID: accountID,
|
||||
Cluster: providerCluster,
|
||||
Subdomain: subdomain,
|
||||
// Logs on by default; usage is collected regardless. Retention bounds
|
||||
// how long full log rows are kept.
|
||||
EnableLogCollection: true,
|
||||
AccessLogRetentionDays: types.DefaultAccessLogRetentionDays,
|
||||
CreatedAt: now,
|
||||
UpdatedAt: now,
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
if err := m.store.SaveAgentNetworkSettings(ctx, settings); err != nil {
|
||||
return nil, fmt.Errorf("save agent network settings: %w", 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 = <label>.<proxyAddress>, served by whichever proxy
|
||||
// declares the parent. Labels are adjective-noun tuples; a candidate is
|
||||
// checked by read and the domain unique index stays the authority, so a
|
||||
// concurrent allocation of the same tuple surfaces as a unique violation and
|
||||
// another tuple is drawn.
|
||||
func (m *managerImpl) bootstrapLabeled(ctx context.Context, settings *types.Settings, proxyAddress string) error {
|
||||
parent, err := types.NormalizeHostname(proxyAddress)
|
||||
if err != nil {
|
||||
return status.Errorf(status.InvalidArgument, "invalid proxy_address: %s", err)
|
||||
}
|
||||
|
||||
for attempt := 1; attempt <= maxDomainAllocationAttempts; attempt++ {
|
||||
m.labelRngMu.Lock()
|
||||
label := labelgen.PickTuple(m.labelRng)
|
||||
m.labelRngMu.Unlock()
|
||||
if label == "" {
|
||||
// Only reachable if either word pool were emptied. An empty label
|
||||
// would produce a broken endpoint like ".example.com", so fail
|
||||
// loudly rather than looping or inserting.
|
||||
return fmt.Errorf("allocate agent network endpoint for account %s: label generator returned an empty label", settings.AccountID)
|
||||
}
|
||||
|
||||
candidate, err := types.NormalizeHostname(label + "." + parent)
|
||||
if err != nil {
|
||||
return status.Errorf(status.InvalidArgument, "proxy_address leaves no room for a label: %s", err)
|
||||
}
|
||||
|
||||
_, err = m.store.GetAgentNetworkSettingsByDomain(ctx, store.LockingStrengthNone, candidate)
|
||||
if err == nil {
|
||||
log.WithContext(ctx).Tracef("agent-network endpoint %q taken, retrying (attempt %d/%d)", candidate, attempt, maxDomainAllocationAttempts)
|
||||
continue
|
||||
}
|
||||
if !isNotFound(err) {
|
||||
return fmt.Errorf("check agent network endpoint availability: %w", err)
|
||||
}
|
||||
|
||||
settings.Domain = candidate
|
||||
settings.ProxyAddress = parent
|
||||
if err := m.store.CreateAgentNetworkSettings(ctx, settings); err != nil {
|
||||
if isUniqueConstraintError(err) {
|
||||
// A concurrent bootstrap for the same account may have won on
|
||||
// the primary key — return the conflict. A lost race on the
|
||||
// domain index just means the tuple was taken between the
|
||||
// read and the insert: draw another.
|
||||
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)
|
||||
}
|
||||
log.WithContext(ctx).Tracef("agent-network endpoint %q lost an allocation race, retrying (attempt %d/%d)", candidate, attempt, maxDomainAllocationAttempts)
|
||||
continue
|
||||
}
|
||||
return fmt.Errorf("create agent network settings: %w", err)
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
return fmt.Errorf("allocate agent network endpoint for account %s: %d attempts exhausted", settings.AccountID, maxDomainAllocationAttempts)
|
||||
}
|
||||
|
||||
// isUniqueConstraintError reports whether err is a database unique-constraint
|
||||
// violation, matched on the driver message because CreateAgentNetworkSettings
|
||||
// deliberately returns the driver error unwrapped.
|
||||
func isUniqueConstraintError(err error) bool {
|
||||
if err == nil {
|
||||
return false
|
||||
}
|
||||
msg := err.Error()
|
||||
return strings.Contains(msg, "(SQLSTATE 23505)") || // postgres
|
||||
strings.Contains(msg, "Error 1062 (23000)") || // mysql
|
||||
strings.Contains(msg, "UNIQUE constraint failed") // sqlite
|
||||
}
|
||||
|
||||
// ListConsumption returns every consumption row recorded for the
|
||||
// account, ordered window-newest-first. Backs the dashboard's basic
|
||||
// counter view; permission gate is the same Read role that gates
|
||||
@@ -1021,7 +834,7 @@ func (*mockManager) GetProvider(_ context.Context, _, _, _ string) (*types.Provi
|
||||
return &types.Provider{}, nil
|
||||
}
|
||||
|
||||
func (*mockManager) CreateProvider(_ context.Context, _ string, p *types.Provider) (*types.Provider, error) {
|
||||
func (*mockManager) CreateProvider(_ context.Context, _ string, p *types.Provider, _ string) (*types.Provider, error) {
|
||||
return p, nil
|
||||
}
|
||||
|
||||
@@ -1085,27 +898,14 @@ func (*mockManager) UpdateBudgetRule(_ context.Context, _ string, r *types.Accou
|
||||
|
||||
func (*mockManager) DeleteBudgetRule(_ context.Context, _, _, _ string) error { return nil }
|
||||
|
||||
func (*mockManager) GetSettings(_ context.Context, accountID, _ string) (*types.Settings, error) {
|
||||
return types.DefaultSettings(accountID), nil
|
||||
}
|
||||
|
||||
func (*mockManager) CreateSettings(_ context.Context, _ string, s *types.Settings, proxyAddress, endpoint string) (*types.Settings, error) {
|
||||
if endpoint != "" {
|
||||
s.Domain = endpoint
|
||||
s.ProxyAddress = endpoint
|
||||
} else {
|
||||
s.Domain = "mock." + proxyAddress
|
||||
s.ProxyAddress = proxyAddress
|
||||
}
|
||||
return s, nil
|
||||
func (*mockManager) GetSettings(_ context.Context, _, _ string) (*types.Settings, error) {
|
||||
return nil, status.Errorf(status.NotFound, "agent network settings not found")
|
||||
}
|
||||
|
||||
func (*mockManager) UpdateSettings(_ context.Context, _ string, s *types.Settings) (*types.Settings, error) {
|
||||
return s, nil
|
||||
}
|
||||
|
||||
func (*mockManager) DeleteSettings(_ context.Context, _, _ string) error { return nil }
|
||||
|
||||
func (*mockManager) ListConsumption(_ context.Context, _, _ string) ([]*types.Consumption, error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
@@ -47,11 +47,17 @@ var supplementalDefaults = map[string]map[string]Entry{
|
||||
"gpt-5-nano": {InputPer1k: 0.00005, OutputPer1k: 0.0004, CachedInputPer1k: 0.000005},
|
||||
},
|
||||
"anthropic": {
|
||||
// claude-opus-5 is not yet in the catalog lineup but gateway /
|
||||
// grandfathered traffic uses it; priced so it isn't skipped.
|
||||
"claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
|
||||
// "kimi-k3[1m]" is the 1M-context alias some Claude Code guides
|
||||
// configure against Moonshot's Anthropic-compatible endpoint;
|
||||
// priced identically to kimi-k3 so those requests aren't skipped.
|
||||
"kimi-k3[1m]": {InputPer1k: 0.003, OutputPer1k: 0.015, CacheReadPer1k: 0.0003},
|
||||
},
|
||||
"bedrock": {
|
||||
"anthropic.claude-opus-5": {InputPer1k: 0.005, OutputPer1k: 0.025, CacheReadPer1k: 0.0005, CacheCreationPer1k: 0.00625},
|
||||
},
|
||||
}
|
||||
|
||||
var (
|
||||
|
||||
@@ -82,11 +82,6 @@ anthropic:
|
||||
output_per_1k: 0.015
|
||||
cache_read_per_1k: 0.0003
|
||||
cache_creation_per_1k: 0.00375
|
||||
claude-sonnet-5:
|
||||
input_per_1k: 0.003
|
||||
output_per_1k: 0.015
|
||||
cache_read_per_1k: 0.0003
|
||||
cache_creation_per_1k: 0.00375
|
||||
kimi-k3:
|
||||
input_per_1k: 0.003
|
||||
output_per_1k: 0.015
|
||||
@@ -150,11 +145,6 @@ bedrock:
|
||||
output_per_1k: 0.015
|
||||
cache_read_per_1k: 0.0003
|
||||
cache_creation_per_1k: 0.00375
|
||||
anthropic.claude-sonnet-5:
|
||||
input_per_1k: 0.003
|
||||
output_per_1k: 0.015
|
||||
cache_read_per_1k: 0.0003
|
||||
cache_creation_per_1k: 0.00375
|
||||
meta.llama3-3-70b-instruct:
|
||||
input_per_1k: 0.00072
|
||||
output_per_1k: 0.00072
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user