mirror of
https://github.com/netbirdio/netbird.git
synced 2026-08-11 18:21:29 +02:00
Compare commits
3 Commits
agent-netw
...
docs/agent
| Author | SHA1 | Date | |
|---|---|---|---|
|
|
aad0e7c322 | ||
|
|
b083240374 | ||
|
|
b27ef7ff76 |
2
.github/workflows/pr-title-check.yml
vendored
2
.github/workflows/pr-title-check.yml
vendored
@@ -16,8 +16,6 @@ jobs:
|
||||
const allowedTags = [
|
||||
'management',
|
||||
'client',
|
||||
'android',
|
||||
'ios',
|
||||
'signal',
|
||||
'proxy',
|
||||
'relay',
|
||||
|
||||
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
|
||||
|
||||
@@ -93,10 +93,7 @@ nfpms:
|
||||
- src: client/ui/build/appicon.png
|
||||
dst: /usr/share/pixmaps/netbird.png
|
||||
dependencies:
|
||||
- netbird (>= 0.75.0)
|
||||
- libgtk-4-1 (>= 4.14)
|
||||
- libwebkitgtk-6.0-4
|
||||
- xdg-utils
|
||||
- netbird
|
||||
|
||||
- maintainer: Netbird <dev@netbird.io>
|
||||
description: Netbird client UI.
|
||||
@@ -117,10 +114,7 @@ nfpms:
|
||||
- src: client/ui/build/appicon.png
|
||||
dst: /usr/share/pixmaps/netbird.png
|
||||
dependencies:
|
||||
- netbird >= 0.75.0
|
||||
- (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
|
||||
- (webkitgtk6.0 or libwebkitgtk-6_0-4)
|
||||
- xdg-utils
|
||||
- netbird
|
||||
|
||||
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
|
||||
319
AGENTS.md
319
AGENTS.md
@@ -1,6 +1,6 @@
|
||||
# NetBird Agent Guidelines
|
||||
|
||||
**NetBird** is an open-source connectivity platform: a WireGuard®-based overlay
|
||||
**NetBird** is an open source connectivity platform: a WireGuard®-based overlay
|
||||
network with a control plane. The **agent** (`client/`) runs on user machines as
|
||||
a privileged daemon and manages the WireGuard interface, routing, firewall, and
|
||||
DNS. **Management** (`management/`) is the control plane and REST/gRPC API,
|
||||
@@ -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.
|
||||
|
||||
@@ -478,7 +478,7 @@ go test -race ./client/internal/dns/...
|
||||
|
||||
## Checklist before submitting a PR
|
||||
|
||||
As a critical network service and open-source project, we must enforce a few
|
||||
As a critical network service and open source project, we must enforce a few
|
||||
things before submitting a pull request. The
|
||||
[pull request template](/.github/pull_request_template.md) mirrors this list —
|
||||
fill it in rather than deleting it.
|
||||
|
||||
@@ -130,7 +130,7 @@ In November 2022, NetBird joined the [StartUpSecure program](https://www.forschu
|
||||

|
||||
|
||||
### Acknowledgements
|
||||
We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
|
||||
We build on open source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
|
||||
|
||||
### Legal
|
||||
This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/.
|
||||
|
||||
@@ -14,7 +14,7 @@ Report security issues one of these two ways:
|
||||
on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
|
||||
- **Email** — `security@netbird.io`.
|
||||
|
||||
If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than
|
||||
If the finding affects NetBird Cloud or our hosted infrastructure rather than the open source code, email us rather than
|
||||
filing a repository report.
|
||||
|
||||
### What to include
|
||||
|
||||
@@ -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
|
||||
@@ -65,12 +57,6 @@ type DnsReadyListener interface {
|
||||
dns.ReadyListener
|
||||
}
|
||||
|
||||
// TunSettings is a snapshot of the settings the TUN device is rebuilt with
|
||||
type TunSettings struct {
|
||||
Routes string
|
||||
SearchDomains string
|
||||
}
|
||||
|
||||
func init() {
|
||||
formatter.SetLogcatFormatter(log.StandardLogger())
|
||||
}
|
||||
@@ -90,8 +76,6 @@ 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 +96,11 @@ 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 +110,6 @@ 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 +162,7 @@ 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 +170,7 @@ 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 +211,7 @@ 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)
|
||||
}
|
||||
|
||||
@@ -267,29 +240,9 @@ func (c *Client) RenewTun(fd int) error {
|
||||
return e.RenewTun(fd)
|
||||
}
|
||||
|
||||
func (c *Client) GetTunSettings() (*TunSettings, error) {
|
||||
cc := c.getConnectClient()
|
||||
if cc == nil {
|
||||
return nil, fmt.Errorf("engine not running")
|
||||
}
|
||||
|
||||
e := cc.Engine()
|
||||
if e == nil {
|
||||
return nil, fmt.Errorf("engine not initialized")
|
||||
}
|
||||
|
||||
routes, searchDomains := e.TunSettings()
|
||||
return &TunSettings{
|
||||
Routes: strings.Join(routes, ";"),
|
||||
SearchDomains: strings.Join(searchDomains, ";"),
|
||||
}, nil
|
||||
}
|
||||
|
||||
// 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 +261,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool, anonym
|
||||
InternalConfig: cfg,
|
||||
StatusRecorder: c.recorder,
|
||||
TempDir: cacheDir,
|
||||
StatePath: platformFiles.StateFilePath(),
|
||||
}
|
||||
|
||||
if cc != nil {
|
||||
@@ -332,7 +284,6 @@ 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"
|
||||
@@ -38,20 +36,12 @@ type Auth struct {
|
||||
}
|
||||
|
||||
// NewAuth instantiate Auth struct and validate the management URL
|
||||
//
|
||||
// The configuration at cfgPath is reused when one is already there, and only created when it is
|
||||
// not. Building a fresh in-memory config unconditionally gives the client a new WireGuard key on
|
||||
// every call: the peer registers under that key, the key is written out, and any peer registered by
|
||||
// an earlier call is orphaned on the server. It also breaks a client that enrols and then runs from
|
||||
// the persisted config, because the identity it registered is not the one it runs with — the
|
||||
// management stream rejects it with "no peer auth method provided".
|
||||
func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
|
||||
inputCfg := profilemanager.ConfigInput{
|
||||
ConfigPath: cfgPath,
|
||||
ManagementURL: mgmURL,
|
||||
}
|
||||
|
||||
cfg, err := profilemanager.UpdateOrCreateConfig(inputCfg)
|
||||
cfg, err := profilemanager.CreateInMemoryConfig(inputCfg)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
@@ -63,14 +53,11 @@ 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 +150,12 @@ 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 +163,17 @@ 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)
|
||||
|
||||
@@ -1,51 +0,0 @@
|
||||
package android
|
||||
|
||||
import (
|
||||
"path/filepath"
|
||||
"testing"
|
||||
)
|
||||
|
||||
// NewAuth must reuse the configuration already at cfgPath rather than building a fresh one.
|
||||
//
|
||||
// Creating a new in-memory config on every call gives the client a new WireGuard private key each
|
||||
// time. The peer registers under that key and the key is written out, so a peer registered by an
|
||||
// earlier call is orphaned on the server — a client that enrols twice leaves two entries and owns
|
||||
// neither. It also breaks enrol-then-run: RunWithoutLogin reloads the configuration from disk, so
|
||||
// the identity that registered is not the identity that runs, and the management stream rejects it
|
||||
// with "no peer auth method provided, please use a setup key or interactive SSO login".
|
||||
func TestNewAuth_ReusesPersistedIdentity(t *testing.T) {
|
||||
cfgPath := filepath.Join(t.TempDir(), "config.json")
|
||||
|
||||
first, err := NewAuth(cfgPath, "https://api.example.com:443")
|
||||
if err != nil {
|
||||
t.Fatalf("first NewAuth: %v", err)
|
||||
}
|
||||
if first.config.PrivateKey == "" {
|
||||
t.Fatal("first NewAuth produced no private key")
|
||||
}
|
||||
|
||||
second, err := NewAuth(cfgPath, "https://api.example.com:443")
|
||||
if err != nil {
|
||||
t.Fatalf("second NewAuth: %v", err)
|
||||
}
|
||||
|
||||
if second.config.PrivateKey != first.config.PrivateKey {
|
||||
t.Errorf("private key changed between calls: a second enrolment would orphan the peer registered by the first")
|
||||
}
|
||||
}
|
||||
|
||||
// A missing configuration is still created, so a first enrolment works unchanged.
|
||||
func TestNewAuth_CreatesConfigWhenAbsent(t *testing.T) {
|
||||
cfgPath := filepath.Join(t.TempDir(), "config.json")
|
||||
|
||||
auth, err := NewAuth(cfgPath, "https://api.example.com:443")
|
||||
if err != nil {
|
||||
t.Fatalf("NewAuth: %v", err)
|
||||
}
|
||||
if auth.config == nil || auth.config.PrivateKey == "" {
|
||||
t.Fatal("NewAuth did not create a usable configuration")
|
||||
}
|
||||
if auth.cfgPath != cfgPath {
|
||||
t.Errorf("cfgPath = %q, want %q", auth.cfgPath, cfgPath)
|
||||
}
|
||||
}
|
||||
@@ -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")
|
||||
}
|
||||
@@ -113,14 +113,11 @@ func (c *ConnectClient) RunOnAndroid(
|
||||
stateFilePath string,
|
||||
cacheDir string,
|
||||
) error {
|
||||
notifier := tunnelnotifier.New(networkChangeListener, nil)
|
||||
defer notifier.Close()
|
||||
|
||||
// in case of non Android os these variables will be nil
|
||||
mobileDependency := MobileDependency{
|
||||
TunAdapter: tunAdapter,
|
||||
IFaceDiscover: iFaceDiscover,
|
||||
NetworkChangeListener: notifier,
|
||||
NetworkChangeListener: networkChangeListener,
|
||||
HostDNSAddresses: dnsAddresses,
|
||||
DnsReadyListener: dnsReadyListener,
|
||||
StateFilePath: stateFilePath,
|
||||
|
||||
@@ -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, ", ")))
|
||||
}
|
||||
|
||||
@@ -1,15 +0,0 @@
|
||||
package dns
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"net"
|
||||
)
|
||||
|
||||
func getInterfaceIndex(interfaceName string) (int, error) {
|
||||
iface, err := net.InterfaceByName(interfaceName)
|
||||
if err != nil {
|
||||
return 0, fmt.Errorf("lookup interface %q: %w", interfaceName, err)
|
||||
}
|
||||
|
||||
return iface.Index, nil
|
||||
}
|
||||
@@ -1,35 +0,0 @@
|
||||
package dns
|
||||
|
||||
import (
|
||||
"net"
|
||||
"testing"
|
||||
)
|
||||
|
||||
func TestGetInterfaceIndexExisting(t *testing.T) {
|
||||
interfaces, err := net.Interfaces()
|
||||
if err != nil {
|
||||
t.Fatalf("list network interfaces: %v", err)
|
||||
}
|
||||
if len(interfaces) == 0 {
|
||||
t.Fatal("expected at least one network interface")
|
||||
}
|
||||
|
||||
iface := interfaces[0]
|
||||
index, err := getInterfaceIndex(iface.Name)
|
||||
if err != nil {
|
||||
t.Fatalf("look up existing interface %q: %v", iface.Name, err)
|
||||
}
|
||||
if index != iface.Index {
|
||||
t.Fatalf("expected interface index %d, got %d", iface.Index, index)
|
||||
}
|
||||
}
|
||||
|
||||
func TestGetInterfaceIndexMissing(t *testing.T) {
|
||||
index, err := getInterfaceIndex("netbird-interface-that-does-not-exist")
|
||||
if index != 0 {
|
||||
t.Fatalf("expected missing interface index to be 0, got %d", index)
|
||||
}
|
||||
if err == nil {
|
||||
t.Fatal("expected missing interface lookup to return an error")
|
||||
}
|
||||
}
|
||||
@@ -51,5 +51,7 @@ func (n *notifier) notify() {
|
||||
return
|
||||
}
|
||||
|
||||
n.listener.OnNetworkChanged("")
|
||||
go func(l listener.NetworkChangeListener) {
|
||||
l.OnNetworkChanged("")
|
||||
}(n.listener)
|
||||
}
|
||||
|
||||
@@ -252,7 +252,7 @@ func NewDefaultServerPermanentUpstream(
|
||||
ds.hostsDNSHolder.set(hostsDnsList)
|
||||
ds.permanent = true
|
||||
ds.currentConfig = dnsConfigToHostDNSConfig(config, ds.service.RuntimeIP(), ds.service.RuntimePort())
|
||||
ds.searchDomainNotifier = newNotifier(ds.searchDomains())
|
||||
ds.searchDomainNotifier = newNotifier(ds.SearchDomains())
|
||||
ds.searchDomainNotifier.setListener(listener)
|
||||
setServerDns(ds)
|
||||
return ds
|
||||
@@ -602,12 +602,6 @@ func (s *DefaultServer) UpdateDNSServer(serial uint64, update nbdns.Config) erro
|
||||
}
|
||||
|
||||
func (s *DefaultServer) SearchDomains() []string {
|
||||
s.mux.Lock()
|
||||
defer s.mux.Unlock()
|
||||
return s.searchDomains()
|
||||
}
|
||||
|
||||
func (s *DefaultServer) searchDomains() []string {
|
||||
var searchDomains []string
|
||||
|
||||
for _, dConf := range s.currentConfig.Domains {
|
||||
@@ -692,7 +686,7 @@ func (s *DefaultServer) applyConfiguration(update nbdns.Config) error {
|
||||
}()
|
||||
|
||||
if s.searchDomainNotifier != nil {
|
||||
s.searchDomainNotifier.onNewSearchDomains(s.searchDomains())
|
||||
s.searchDomainNotifier.onNewSearchDomains(s.SearchDomains())
|
||||
}
|
||||
|
||||
s.updateNSGroupStates(update.NameServerGroups)
|
||||
|
||||
@@ -130,3 +130,8 @@ func GetClientPrivate(iface privateClientIface, upstreamIP netip.Addr, dialTimeo
|
||||
}
|
||||
return client, nil
|
||||
}
|
||||
|
||||
func getInterfaceIndex(interfaceName string) (int, error) {
|
||||
iface, err := net.InterfaceByName(interfaceName)
|
||||
return iface.Index, err
|
||||
}
|
||||
|
||||
@@ -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"
|
||||
@@ -573,7 +572,12 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
|
||||
}
|
||||
e.stateManager.Start()
|
||||
|
||||
dnsServer, err := e.newDnsServer()
|
||||
initialRoutes, dnsConfig, dnsFeatureFlag, err := e.readInitialSettings()
|
||||
if err != nil {
|
||||
return fmt.Errorf("read initial settings: %w", err)
|
||||
}
|
||||
|
||||
dnsServer, err := e.newDnsServer(dnsConfig)
|
||||
if err != nil {
|
||||
return fmt.Errorf("create dns server: %w", err)
|
||||
}
|
||||
@@ -591,8 +595,10 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
|
||||
WGInterface: e.wgInterface,
|
||||
StatusRecorder: e.statusRecorder,
|
||||
RelayManager: e.relayManager,
|
||||
InitialRoutes: initialRoutes,
|
||||
StateManager: e.stateManager,
|
||||
DNSServer: dnsServer,
|
||||
DNSFeatureFlag: dnsFeatureFlag,
|
||||
PeerStore: e.peerStore,
|
||||
DisableClientRoutes: e.config.DisableClientRoutes,
|
||||
DisableServerRoutes: e.config.DisableServerRoutes,
|
||||
@@ -1386,7 +1392,6 @@ 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),
|
||||
}
|
||||
@@ -2097,6 +2102,42 @@ func (e *Engine) close() {
|
||||
}
|
||||
}
|
||||
|
||||
func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, error) {
|
||||
if runtime.GOOS != "android" {
|
||||
// nolint:nilnil
|
||||
return nil, nil, false, nil
|
||||
}
|
||||
|
||||
info := system.GetInfo(e.ctx)
|
||||
info.SetFlags(
|
||||
e.config.RosenpassEnabled,
|
||||
e.config.RosenpassPermissive,
|
||||
&e.config.ServerSSHAllowed,
|
||||
e.config.DisableClientRoutes,
|
||||
e.config.DisableServerRoutes,
|
||||
e.config.DisableDNS,
|
||||
e.config.DisableFirewall,
|
||||
e.config.BlockLANAccess,
|
||||
e.config.BlockInbound,
|
||||
e.config.DisableIPv6,
|
||||
e.config.SyncMessageVersion,
|
||||
e.config.EnableSSHRoot,
|
||||
e.config.EnableSSHSFTP,
|
||||
e.config.EnableSSHLocalPortForwarding,
|
||||
e.config.EnableSSHRemotePortForwarding,
|
||||
e.config.DisableSSHAuth,
|
||||
)
|
||||
|
||||
netMap, err := e.mgmClient.GetNetworkMap(info)
|
||||
if err != nil {
|
||||
return nil, nil, false, err
|
||||
}
|
||||
routes := toRoutes(netMap.GetRoutes())
|
||||
dnsCfg := toDNSConfig(netMap.GetDNSConfig(), e.wgInterface.Address())
|
||||
dnsFeatureFlag := toDNSFeatureFlag(netMap)
|
||||
return routes, &dnsCfg, dnsFeatureFlag, nil
|
||||
}
|
||||
|
||||
func (e *Engine) newWgIface() (*iface.WGIface, error) {
|
||||
transportNet, err := e.newStdNet()
|
||||
if err != nil {
|
||||
@@ -2131,7 +2172,7 @@ func (e *Engine) newWgIface() (*iface.WGIface, error) {
|
||||
func (e *Engine) wgInterfaceCreate() (err error) {
|
||||
switch runtime.GOOS {
|
||||
case "android":
|
||||
err = e.wgInterface.CreateOnAndroid(e.routeManager.CurrentRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
|
||||
err = e.wgInterface.CreateOnAndroid(e.routeManager.InitialRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
|
||||
case "ios":
|
||||
e.mobileDep.NetworkChangeListener.SetInterfaceIP(e.config.WgAddr.String())
|
||||
if e.config.WgAddr.HasIPv6() {
|
||||
@@ -2144,7 +2185,7 @@ func (e *Engine) wgInterfaceCreate() (err error) {
|
||||
return err
|
||||
}
|
||||
|
||||
func (e *Engine) newDnsServer() (dns.Server, error) {
|
||||
func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
|
||||
// due to tests where we are using a mocked version of the DNS server
|
||||
if e.dnsServer != nil {
|
||||
return e.dnsServer, nil
|
||||
@@ -2156,7 +2197,7 @@ func (e *Engine) newDnsServer() (dns.Server, error) {
|
||||
e.ctx,
|
||||
e.wgInterface,
|
||||
e.mobileDep.HostDNSAddresses,
|
||||
nbdns.Config{},
|
||||
*dnsConfig,
|
||||
e.mobileDep.NetworkChangeListener,
|
||||
e.statusRecorder,
|
||||
e.config.DisableDNS,
|
||||
|
||||
@@ -1,20 +0,0 @@
|
||||
package internal
|
||||
|
||||
func (e *Engine) TunSettings() ([]string, []string) {
|
||||
e.syncMsgMux.Lock()
|
||||
routeManager := e.routeManager
|
||||
dnsServer := e.dnsServer
|
||||
e.syncMsgMux.Unlock()
|
||||
|
||||
var routes []string
|
||||
if routeManager != nil {
|
||||
routes = routeManager.CurrentRouteRange()
|
||||
}
|
||||
|
||||
var searchDomains []string
|
||||
if dnsServer != nil {
|
||||
searchDomains = dnsServer.SearchDomains()
|
||||
}
|
||||
|
||||
return routes, searchDomains
|
||||
}
|
||||
@@ -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)
|
||||
}
|
||||
}
|
||||
|
||||
@@ -45,35 +45,12 @@ func (pm *ProfileManager) GetProfileState(id ID) (*ProfileState, error) {
|
||||
return &state, nil
|
||||
}
|
||||
|
||||
// SetProfileState writes the state file of the profile identified by id. Prefer
|
||||
// it over SetActiveProfileState whenever the caller knows which profile the data
|
||||
// belongs to: an SSO login spans seconds of user interaction, and the active
|
||||
// profile can change during it, which would file the account email under
|
||||
// whichever profile happened to be active when the flow returned.
|
||||
func (pm *ProfileManager) SetProfileState(id ID, state *ProfileState) error {
|
||||
func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
|
||||
configDir, err := getConfigDir()
|
||||
if err != nil {
|
||||
return fmt.Errorf("get config directory: %w", err)
|
||||
}
|
||||
|
||||
if id == "" {
|
||||
return fmt.Errorf("empty profile ID")
|
||||
}
|
||||
if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
|
||||
return fmt.Errorf("invalid profile ID: %q", id)
|
||||
}
|
||||
|
||||
stateFile := filepath.Join(configDir, id.String()+".state.json")
|
||||
if err := util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state); err != nil {
|
||||
return fmt.Errorf("write profile state: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// SetActiveProfileState writes the state file of whichever profile is active at
|
||||
// call time. Use SetProfileState when the target profile is known.
|
||||
func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
|
||||
activeProf, err := pm.GetActiveProfile()
|
||||
if err != nil {
|
||||
if errors.Is(err, ErrNoActiveProfile) {
|
||||
@@ -82,7 +59,18 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
|
||||
return fmt.Errorf("get active profile: %w", err)
|
||||
}
|
||||
|
||||
return pm.SetProfileState(activeProf.ID, state)
|
||||
id := activeProf.ID
|
||||
if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
|
||||
return fmt.Errorf("invalid active profile ID: %q", id)
|
||||
}
|
||||
|
||||
stateFile := filepath.Join(configDir, id.String()+".state.json")
|
||||
err = util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state)
|
||||
if err != nil {
|
||||
return fmt.Errorf("write profile state: %w", err)
|
||||
}
|
||||
|
||||
return nil
|
||||
}
|
||||
|
||||
// RemoveProfileState deletes the per-profile state file (which holds the
|
||||
|
||||
@@ -479,7 +479,7 @@ func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix, logger
|
||||
|
||||
// internalDnatFw checks if the firewall supports internal DNAT
|
||||
func (d *DnsInterceptor) internalDnatFw() (internalDNATer, bool) {
|
||||
if d.firewall == nil || d.fakeIPManager == nil || runtime.GOOS != "android" {
|
||||
if d.firewall == nil || runtime.GOOS != "android" {
|
||||
return nil, false
|
||||
}
|
||||
fw, ok := d.firewall.(internalDNATer)
|
||||
|
||||
@@ -8,13 +8,14 @@ import (
|
||||
"net/netip"
|
||||
"net/url"
|
||||
"runtime"
|
||||
"sort"
|
||||
"slices"
|
||||
"strings"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
"syscall"
|
||||
"time"
|
||||
|
||||
"github.com/google/uuid"
|
||||
"github.com/hashicorp/go-multierror"
|
||||
log "github.com/sirupsen/logrus"
|
||||
"golang.org/x/exp/maps"
|
||||
@@ -61,7 +62,7 @@ type Manager interface {
|
||||
GetActiveClientRoutes() route.HAMap
|
||||
GetClientRoutesWithNetID() map[route.NetID][]*route.Route
|
||||
SetRouteChangeListener(listener listener.NetworkChangeListener)
|
||||
CurrentRouteRange() []string
|
||||
InitialRouteRange() []string
|
||||
SetFirewall(firewall.Manager) error
|
||||
SetDNSForwarderPort(port uint16)
|
||||
ReconcilePeerAllowedIPs(peerKey string) error
|
||||
@@ -75,8 +76,10 @@ type ManagerConfig struct {
|
||||
WGInterface iface.WGIface
|
||||
StatusRecorder *peer.Status
|
||||
RelayManager *relayClient.Manager
|
||||
InitialRoutes []*route.Route
|
||||
StateManager *statemanager.Manager
|
||||
DNSServer dns.Server
|
||||
DNSFeatureFlag bool
|
||||
PeerStore *peerstore.Store
|
||||
DisableClientRoutes bool
|
||||
DisableServerRoutes bool
|
||||
@@ -146,12 +149,45 @@ func NewManager(config ManagerConfig) *DefaultManager {
|
||||
useNoop := netstack.IsEnabled() || config.DisableClientRoutes
|
||||
dm.setupRefCounters(useNoop)
|
||||
|
||||
// don't proceed with client routes if it is disabled
|
||||
if config.DisableClientRoutes {
|
||||
return dm
|
||||
}
|
||||
|
||||
if runtime.GOOS == "android" {
|
||||
dm.setupAndroidRoutes(config)
|
||||
}
|
||||
return dm
|
||||
}
|
||||
func (m *DefaultManager) setupAndroidRoutes(config ManagerConfig) {
|
||||
cr := m.initialClientRoutes(config.InitialRoutes)
|
||||
|
||||
func (m *DefaultManager) enableFakeIPRoutes() {
|
||||
m.fakeIPManager = fakeip.NewManager()
|
||||
m.notifier.NotifyRouteChange()
|
||||
routesForComparison := slices.Clone(cr)
|
||||
|
||||
if config.DNSFeatureFlag {
|
||||
m.fakeIPManager = fakeip.NewManager()
|
||||
|
||||
v4ID := uuid.NewString()
|
||||
fakeIPRoute := &route.Route{
|
||||
ID: route.ID(v4ID),
|
||||
Network: m.fakeIPManager.GetFakeIPBlock(),
|
||||
NetID: route.NetID(v4ID),
|
||||
Peer: m.pubKey,
|
||||
NetworkType: route.IPv4Network,
|
||||
}
|
||||
v6ID := uuid.NewString()
|
||||
fakeIPv6Route := &route.Route{
|
||||
ID: route.ID(v6ID),
|
||||
Network: m.fakeIPManager.GetFakeIPv6Block(),
|
||||
NetID: route.NetID(v6ID),
|
||||
Peer: m.pubKey,
|
||||
NetworkType: route.IPv6Network,
|
||||
}
|
||||
cr = append(cr, fakeIPRoute, fakeIPv6Route)
|
||||
m.notifier.SetFakeIPRoutes([]*route.Route{fakeIPRoute, fakeIPv6Route})
|
||||
}
|
||||
|
||||
m.notifier.SetInitialClientRoutes(cr, routesForComparison)
|
||||
}
|
||||
|
||||
func (m *DefaultManager) setupRefCounters(useNoop bool) {
|
||||
@@ -428,9 +464,6 @@ func (m *DefaultManager) UpdateRoutes(
|
||||
|
||||
var merr *multierror.Error
|
||||
if !m.disableClientRoutes {
|
||||
if runtime.GOOS == "android" && useNewDNSRoute && m.fakeIPManager == nil {
|
||||
m.enableFakeIPRoutes()
|
||||
}
|
||||
|
||||
// Update route selector based on management server's isSelected status
|
||||
m.updateRouteSelectorFromManagement(clientRoutes)
|
||||
@@ -467,32 +500,9 @@ func (m *DefaultManager) SetRouteChangeListener(listener listener.NetworkChangeL
|
||||
m.notifier.SetListener(listener)
|
||||
}
|
||||
|
||||
// CurrentRouteRange returns the current TUN route list. It is used by mobile systems
|
||||
func (m *DefaultManager) CurrentRouteRange() []string {
|
||||
m.mux.Lock()
|
||||
defer m.mux.Unlock()
|
||||
|
||||
if m.disableClientRoutes {
|
||||
return nil
|
||||
}
|
||||
|
||||
filtered := m.routeSelector.FilterSelectedExitNodes(m.clientRoutes)
|
||||
var nets []string
|
||||
for _, routes := range filtered {
|
||||
for _, r := range routes {
|
||||
if r.IsDynamic() {
|
||||
continue
|
||||
}
|
||||
nets = append(nets, r.NetString())
|
||||
}
|
||||
}
|
||||
|
||||
if m.fakeIPManager != nil {
|
||||
nets = append(nets, m.fakeIPManager.GetFakeIPBlock().String(), m.fakeIPManager.GetFakeIPv6Block().String())
|
||||
}
|
||||
|
||||
sort.Strings(nets)
|
||||
return nets
|
||||
// InitialRouteRange return the list of initial routes. It used by mobile systems
|
||||
func (m *DefaultManager) InitialRouteRange() []string {
|
||||
return m.notifier.GetInitialRouteRanges()
|
||||
}
|
||||
|
||||
// GetRouteSelector returns the route selector
|
||||
@@ -690,6 +700,16 @@ func (m *DefaultManager) ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]
|
||||
return newServerRoutesMap, newClientRoutesIDMap
|
||||
}
|
||||
|
||||
func (m *DefaultManager) initialClientRoutes(initialRoutes []*route.Route) []*route.Route {
|
||||
_, crMap := m.ClassifyRoutes(initialRoutes)
|
||||
rs := make([]*route.Route, 0, len(crMap))
|
||||
for _, routes := range crMap {
|
||||
rs = append(rs, routes...)
|
||||
}
|
||||
|
||||
return rs
|
||||
}
|
||||
|
||||
func isRouteSupported(route *route.Route) bool {
|
||||
if netstack.IsEnabled() || !nbnet.CustomRoutingDisabled() || route.IsDynamic() {
|
||||
return true
|
||||
|
||||
@@ -30,8 +30,8 @@ func (m *MockManager) Init() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// CurrentRouteRange mock implementation of CurrentRouteRange from Manager interface
|
||||
func (m *MockManager) CurrentRouteRange() []string {
|
||||
// InitialRouteRange mock implementation of InitialRouteRange from Manager interface
|
||||
func (m *MockManager) InitialRouteRange() []string {
|
||||
return nil
|
||||
}
|
||||
|
||||
|
||||
@@ -6,6 +6,7 @@ import (
|
||||
"net/netip"
|
||||
"slices"
|
||||
"sort"
|
||||
"strings"
|
||||
"sync"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/listener"
|
||||
@@ -13,15 +14,12 @@ import (
|
||||
)
|
||||
|
||||
type Notifier struct {
|
||||
mu sync.Mutex
|
||||
|
||||
// currentRoutes is the last announced route set. It exists only to
|
||||
// suppress noise: without it every network map sync would trigger the
|
||||
// Java side, even when the routes did not change. The actual TUN route
|
||||
// state is owned by the route manager and pulled from there.
|
||||
initialRoutes []*route.Route
|
||||
currentRoutes []*route.Route
|
||||
fakeIPRoutes []*route.Route
|
||||
|
||||
listener listener.NetworkChangeListener
|
||||
listener listener.NetworkChangeListener
|
||||
listenerMux sync.Mutex
|
||||
}
|
||||
|
||||
func NewNotifier() *Notifier {
|
||||
@@ -29,15 +27,20 @@ func NewNotifier() *Notifier {
|
||||
}
|
||||
|
||||
func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
|
||||
n.mu.Lock()
|
||||
defer n.mu.Unlock()
|
||||
n.listenerMux.Lock()
|
||||
defer n.listenerMux.Unlock()
|
||||
n.listener = listener
|
||||
}
|
||||
|
||||
func (n *Notifier) NotifyRouteChange() {
|
||||
n.mu.Lock()
|
||||
defer n.mu.Unlock()
|
||||
n.notifyLocked()
|
||||
// SetInitialClientRoutes stores the initial route sets for TUN configuration.
|
||||
func (n *Notifier) SetInitialClientRoutes(initialRoutes []*route.Route, routesForComparison []*route.Route) {
|
||||
n.initialRoutes = filterStatic(initialRoutes)
|
||||
n.currentRoutes = filterStatic(routesForComparison)
|
||||
}
|
||||
|
||||
// SetFakeIPRoutes stores the fake IP routes to be included in every TUN rebuild.
|
||||
func (n *Notifier) SetFakeIPRoutes(routes []*route.Route) {
|
||||
n.fakeIPRoutes = routes
|
||||
}
|
||||
|
||||
func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
|
||||
@@ -51,32 +54,46 @@ func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
|
||||
}
|
||||
}
|
||||
|
||||
n.mu.Lock()
|
||||
defer n.mu.Unlock()
|
||||
if !hasRouteDiff(n.currentRoutes, newRoutes) {
|
||||
if !n.hasRouteDiff(n.currentRoutes, newRoutes) {
|
||||
return
|
||||
}
|
||||
|
||||
n.currentRoutes = newRoutes
|
||||
n.notifyLocked()
|
||||
n.notify()
|
||||
}
|
||||
|
||||
func (n *Notifier) OnNewPrefixes([]netip.Prefix) {
|
||||
// Not used on Android
|
||||
}
|
||||
|
||||
func (n *Notifier) notifyLocked() {
|
||||
func (n *Notifier) notify() {
|
||||
n.listenerMux.Lock()
|
||||
defer n.listenerMux.Unlock()
|
||||
if n.listener == nil {
|
||||
return
|
||||
}
|
||||
n.listener.OnNetworkChanged("")
|
||||
|
||||
allRoutes := slices.Clone(n.currentRoutes)
|
||||
allRoutes = append(allRoutes, n.fakeIPRoutes...)
|
||||
|
||||
routeStrings := n.routesToStrings(allRoutes)
|
||||
sort.Strings(routeStrings)
|
||||
go func(l listener.NetworkChangeListener) {
|
||||
l.OnNetworkChanged(strings.Join(routeStrings, ","))
|
||||
}(n.listener)
|
||||
}
|
||||
|
||||
func (n *Notifier) Close() {
|
||||
// unused
|
||||
func filterStatic(routes []*route.Route) []*route.Route {
|
||||
out := make([]*route.Route, 0, len(routes))
|
||||
for _, r := range routes {
|
||||
if !r.IsDynamic() {
|
||||
out = append(out, r)
|
||||
}
|
||||
}
|
||||
return out
|
||||
}
|
||||
|
||||
func routesToStrings(routes []*route.Route) []string {
|
||||
func (n *Notifier) routesToStrings(routes []*route.Route) []string {
|
||||
nets := make([]string, 0, len(routes))
|
||||
for _, r := range routes {
|
||||
nets = append(nets, r.NetString())
|
||||
@@ -84,10 +101,25 @@ func routesToStrings(routes []*route.Route) []string {
|
||||
return nets
|
||||
}
|
||||
|
||||
func hasRouteDiff(a []*route.Route, b []*route.Route) bool {
|
||||
as := routesToStrings(a)
|
||||
bs := routesToStrings(b)
|
||||
sort.Strings(as)
|
||||
sort.Strings(bs)
|
||||
return !slices.Equal(as, bs)
|
||||
func (n *Notifier) hasRouteDiff(a []*route.Route, b []*route.Route) bool {
|
||||
slices.SortFunc(a, func(x, y *route.Route) int {
|
||||
return strings.Compare(x.NetString(), y.NetString())
|
||||
})
|
||||
slices.SortFunc(b, func(x, y *route.Route) int {
|
||||
return strings.Compare(x.NetString(), y.NetString())
|
||||
})
|
||||
|
||||
return !slices.EqualFunc(a, b, func(x, y *route.Route) bool {
|
||||
return x.NetString() == y.NetString()
|
||||
})
|
||||
}
|
||||
|
||||
func (n *Notifier) GetInitialRouteRanges() []string {
|
||||
initialStrings := n.routesToStrings(n.initialRoutes)
|
||||
sort.Strings(initialStrings)
|
||||
return initialStrings
|
||||
}
|
||||
|
||||
func (n *Notifier) Close() {
|
||||
// unused
|
||||
}
|
||||
|
||||
@@ -29,7 +29,11 @@ func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
|
||||
n.listener = listener
|
||||
}
|
||||
|
||||
func (n *Notifier) NotifyRouteChange() {
|
||||
func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
|
||||
// iOS doesn't care about initial routes
|
||||
}
|
||||
|
||||
func (n *Notifier) SetFakeIPRoutes([]*route.Route) {
|
||||
// Not used on iOS
|
||||
}
|
||||
|
||||
|
||||
@@ -19,7 +19,11 @@ func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
|
||||
// Not used on non-mobile platforms
|
||||
}
|
||||
|
||||
func (n *Notifier) NotifyRouteChange() {
|
||||
func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
|
||||
// Not used on non-mobile platforms
|
||||
}
|
||||
|
||||
func (n *Notifier) SetFakeIPRoutes([]*route.Route) {
|
||||
// Not used on non-mobile platforms
|
||||
}
|
||||
|
||||
@@ -31,6 +35,10 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
|
||||
// Not used on non-mobile platforms
|
||||
}
|
||||
|
||||
func (n *Notifier) GetInitialRouteRanges() []string {
|
||||
return []string{}
|
||||
}
|
||||
|
||||
func (n *Notifier) Close() {
|
||||
// unused
|
||||
}
|
||||
|
||||
@@ -98,44 +98,47 @@ func (u *Installer) startDaemon(daemonFolder string) error {
|
||||
func (u *Installer) startUIAsUser() error {
|
||||
log.Infof("starting netbird-ui: %s", uiBinary)
|
||||
|
||||
username, err := consoleUser()
|
||||
// Get the current console user
|
||||
cmd := exec.Command("stat", "-f", "%Su", "/dev/console")
|
||||
output, err := cmd.Output()
|
||||
if err != nil {
|
||||
return err
|
||||
return fmt.Errorf("failed to get console user: %w", err)
|
||||
}
|
||||
|
||||
username := strings.TrimSpace(string(output))
|
||||
if username == "" || username == "root" {
|
||||
return fmt.Errorf("no active user session found")
|
||||
}
|
||||
|
||||
log.Infof("starting UI for user: %s", username)
|
||||
|
||||
// Get user's UID
|
||||
userInfo, err := user.Lookup(username)
|
||||
if err != nil {
|
||||
return fmt.Errorf("lookup user %s: %w", username, err)
|
||||
return fmt.Errorf("failed to lookup user %s: %w", username, err)
|
||||
}
|
||||
|
||||
log.Infof("starting UI for user: %s (uid %s)", username, userInfo.Uid)
|
||||
|
||||
launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "sudo", "-u", username, "-H", "open", "-a", uiBinary)
|
||||
// Start the UI process as the console user using launchctl
|
||||
// This ensures the app runs in the user's context with proper GUI access
|
||||
launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "open", "-a", uiBinary)
|
||||
log.Infof("launchCmd: %s", launchCmd.String())
|
||||
// Set the user's home directory for proper macOS app behavior
|
||||
launchCmd.Env = append(os.Environ(), "HOME="+userInfo.HomeDir)
|
||||
log.Infof("set HOME environment variable: %s", userInfo.HomeDir)
|
||||
|
||||
if err := launchCmd.Run(); err != nil {
|
||||
return fmt.Errorf("run UI launch: %w", err)
|
||||
if err := launchCmd.Start(); err != nil {
|
||||
return fmt.Errorf("failed to start UI process: %w", err)
|
||||
}
|
||||
|
||||
// Release the process so it can run independently
|
||||
if err := launchCmd.Process.Release(); err != nil {
|
||||
log.Warnf("failed to release UI process: %v", err)
|
||||
}
|
||||
|
||||
log.Infof("netbird-ui started successfully for user %s", username)
|
||||
return nil
|
||||
}
|
||||
|
||||
func consoleUser() (string, error) {
|
||||
output, err := exec.Command("stat", "-f", "%Su", "/dev/console").Output()
|
||||
if err != nil {
|
||||
return "", fmt.Errorf("get console user: %w", err)
|
||||
}
|
||||
|
||||
username := strings.TrimSpace(string(output))
|
||||
switch username {
|
||||
case "", "root", "loginwindow", "_mbsetupuser":
|
||||
return "", fmt.Errorf("no active GUI user session, console user: %q", username)
|
||||
}
|
||||
|
||||
return username, nil
|
||||
}
|
||||
|
||||
func (u *Installer) installPkgFile(ctx context.Context, path string) error {
|
||||
log.Infof("installing pkg file: %s", path)
|
||||
|
||||
|
||||
@@ -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
|
||||
@@ -166,19 +158,13 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
|
||||
defer c.ctxCancel()
|
||||
c.ctxCancelLock.Unlock()
|
||||
|
||||
// No login pre-flight here. The engine's own loginToManagement (connect.go) performs
|
||||
// the authoritative Login immediately before the first Sync, so a LoginSync() call at
|
||||
// this point only duplicated it — costing two extra Login RPCs (IsLoginRequired +
|
||||
// Login) on every engine start, since IsLoginRequired is itself a full Login RPC.
|
||||
//
|
||||
// Auth failures still reach the caller through the engine path: loginToManagement
|
||||
// returns PermissionDenied, which marks the shared status recorder
|
||||
// (MarkManagementDisconnected) and fires ClientStop → onDisconnected, where
|
||||
// IsLoginRequiredCached() reports login-required. The error is also returned out of Run().
|
||||
//
|
||||
// A pre-flight was also actively harmful when the server is unreachable: its 2-minute
|
||||
// backoff blocked the start and then reported "login required" for what was really a
|
||||
// timeout. The engine instead keeps retrying and recovers when the server returns.
|
||||
auth := NewAuthWithConfig(ctx, cfg)
|
||||
err = auth.LoginSync()
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
log.Infof("Auth successful")
|
||||
// todo do not throw error in case of cancelled context
|
||||
ctx = internal.CtxInitState(ctx)
|
||||
c.onHostDnsFn = func([]string) {}
|
||||
@@ -208,10 +194,8 @@ 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 +245,6 @@ func (c *Client) DebugBundle(anonymize bool, anonymizeLevel string) (string, err
|
||||
deps,
|
||||
debug.BundleConfig{
|
||||
Anonymize: anonymize,
|
||||
AnonymizeLevel: nbAnonymize.ParseLevel(anonymizeLevel),
|
||||
IncludeSystemInfo: true,
|
||||
},
|
||||
)
|
||||
|
||||
@@ -222,36 +222,17 @@ func (a *Auth) Login(resultListener ErrListener, urlOpener URLOpener, forceDevic
|
||||
// LoginWithDeviceName performs interactive login with device authentication support
|
||||
// The deviceName parameter allows specifying a custom device name (required for tvOS)
|
||||
func (a *Auth) LoginWithDeviceName(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string) {
|
||||
a.startLogin(resultListener, urlOpener, forceDeviceAuth, deviceName, false)
|
||||
}
|
||||
|
||||
// LoginInteractive performs the same interactive login as LoginWithDeviceName but skips the
|
||||
// IsLoginRequired() pre-flight and goes straight to the browser / device-code flow.
|
||||
//
|
||||
// IsLoginRequired() is itself a full Login RPC against the management server, so when the
|
||||
// caller has ALREADY established that login is required it is a pure duplicate. On iOS the
|
||||
// main app decides to show the browser based on its own isLoginRequired() check and then
|
||||
// calls straight into this method, so re-asking the server would add another Login RPC to
|
||||
// every interactive login.
|
||||
//
|
||||
// Use LoginWithDeviceName when the auth state is unknown and a silent (browser-less) login
|
||||
// must still be possible; use this when the browser is going to be shown regardless.
|
||||
func (a *Auth) LoginInteractive(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string) {
|
||||
a.startLogin(resultListener, urlOpener, forceDeviceAuth, deviceName, true)
|
||||
}
|
||||
|
||||
func (a *Auth) startLogin(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string, skipLoginCheck bool) {
|
||||
if resultListener == nil {
|
||||
log.Errorf("startLogin: resultListener is nil")
|
||||
log.Errorf("LoginWithDeviceName: resultListener is nil")
|
||||
return
|
||||
}
|
||||
if urlOpener == nil {
|
||||
log.Errorf("startLogin: urlOpener is nil")
|
||||
log.Errorf("LoginWithDeviceName: urlOpener is nil")
|
||||
resultListener.OnError(fmt.Errorf("urlOpener is nil"))
|
||||
return
|
||||
}
|
||||
go func() {
|
||||
err := a.login(urlOpener, forceDeviceAuth, deviceName, skipLoginCheck)
|
||||
err := a.login(urlOpener, forceDeviceAuth, deviceName)
|
||||
if err != nil {
|
||||
resultListener.OnError(err)
|
||||
} else {
|
||||
@@ -260,7 +241,7 @@ func (a *Auth) startLogin(resultListener ErrListener, urlOpener URLOpener, force
|
||||
}()
|
||||
}
|
||||
|
||||
func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName string, skipLoginCheck bool) error {
|
||||
func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName string) error {
|
||||
// Create context with device name if provided
|
||||
ctx := a.ctx
|
||||
if deviceName != "" {
|
||||
@@ -274,13 +255,10 @@ func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName strin
|
||||
}
|
||||
defer authClient.Close()
|
||||
|
||||
// check if we need to generate JWT token (skipped when the caller already knows)
|
||||
needsLogin := true
|
||||
if !skipLoginCheck {
|
||||
needsLogin, err = authClient.IsLoginRequired(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to check login requirement: %v", err)
|
||||
}
|
||||
// check if we need to generate JWT token
|
||||
needsLogin, err := authClient.IsLoginRequired(ctx)
|
||||
if err != nil {
|
||||
return fmt.Errorf("failed to check login requirement: %v", err)
|
||||
}
|
||||
|
||||
jwtToken := ""
|
||||
|
||||
@@ -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(),
|
||||
},
|
||||
|
||||
@@ -1,110 +0,0 @@
|
||||
package server
|
||||
|
||||
import (
|
||||
"context"
|
||||
"encoding/json"
|
||||
"errors"
|
||||
"os"
|
||||
"testing"
|
||||
|
||||
"github.com/stretchr/testify/require"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal"
|
||||
"github.com/netbirdio/netbird/client/proto"
|
||||
)
|
||||
|
||||
// A login that never reached Management is not a decision about the peer's
|
||||
// credentials, so it must come back as a retryable error rather than an SSO
|
||||
// prompt: the user cannot finish a browser login while Management is down, and
|
||||
// the CLI's own backoff resolves the outage on its own once the daemon reports
|
||||
// the failure. Reproduces `netbird down; netbird up` printing a device-code URL
|
||||
// because Management happened to be restarting when the daemon dialed it.
|
||||
func TestLogin_ManagementUnreachableIsReturnedInsteadOfDemandingSSO(t *testing.T) {
|
||||
s, _, _, username, _ := setupServerWithProfile(t)
|
||||
s.rootCtx = internal.CtxInitState(context.Background())
|
||||
|
||||
unreachable := errors.New("create connection: dial context: context deadline exceeded")
|
||||
attempts := 0
|
||||
s.isLoginRequiredFn = func(context.Context) (bool, error) {
|
||||
attempts++
|
||||
return false, unreachable
|
||||
}
|
||||
|
||||
resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
|
||||
require.Error(t, err)
|
||||
require.ErrorIs(t, err, unreachable, "the transport failure was replaced by something else")
|
||||
require.Nil(t, resp, "a failed login must not answer with a login response")
|
||||
require.Equal(t, 1, attempts)
|
||||
require.Nil(t, s.oauthAuthFlow.flow, "the daemon started an SSO flow for a peer whose login was never decided")
|
||||
|
||||
status, err := internal.CtxGetState(s.rootCtx).Status()
|
||||
require.NoError(t, err)
|
||||
require.Equal(t, internal.StatusLoginFailed, status,
|
||||
"a peer that could not reach Management is not waiting on a login")
|
||||
}
|
||||
|
||||
// The counterpart: Management refusing the peer's credentials is a decision, and
|
||||
// the SSO flow still has to start for it. The profile carries an unusable
|
||||
// private key so the flow setup fails immediately instead of dialing, which is
|
||||
// enough to show the branch was entered — the refusal itself is never what comes
|
||||
// back out.
|
||||
func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
|
||||
s, _, _, username, cfgPath := setupServerWithProfile(t)
|
||||
s.rootCtx = internal.CtxInitState(context.Background())
|
||||
breakProfilePrivateKey(t, cfgPath)
|
||||
|
||||
s.isLoginRequiredFn = func(context.Context) (bool, error) {
|
||||
return true, nil
|
||||
}
|
||||
|
||||
_, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
|
||||
require.Error(t, err)
|
||||
|
||||
status, stateErr := internal.CtxGetState(s.rootCtx).Status()
|
||||
require.NoError(t, stateErr)
|
||||
require.Equal(t, internal.StatusLoginFailed, status,
|
||||
"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) {
|
||||
t.Helper()
|
||||
|
||||
raw, err := os.ReadFile(cfgPath)
|
||||
require.NoError(t, err)
|
||||
|
||||
var cfg map[string]any
|
||||
require.NoError(t, json.Unmarshal(raw, &cfg))
|
||||
cfg["PrivateKey"] = "not-a-key"
|
||||
|
||||
patched, err := json.Marshal(cfg)
|
||||
require.NoError(t, err)
|
||||
require.NoError(t, os.WriteFile(cfgPath, patched, 0o600))
|
||||
}
|
||||
@@ -135,13 +135,6 @@ type Server struct {
|
||||
updateManager *updater.Manager
|
||||
|
||||
jwtCache *jwtCache
|
||||
|
||||
// loginAttemptFn stands in for the Management login round trip. Tests set
|
||||
// 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 {
|
||||
@@ -377,34 +370,7 @@ func (s *Server) connectionGoroutineRunning() bool {
|
||||
}
|
||||
}
|
||||
|
||||
// attemptLogin runs a login round trip against Management, or the stand-in a
|
||||
// test installed in place of it.
|
||||
func (s *Server) attemptLogin(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
|
||||
if s.loginAttemptFn != nil {
|
||||
return s.loginAttemptFn(ctx, setupKey, jwtToken)
|
||||
}
|
||||
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
|
||||
// authentication decision apart from a login that never got made.
|
||||
// loginAttempt attempts to login using the provided information. it returns a status in case something fails
|
||||
func (s *Server) loginAttempt(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
|
||||
authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
|
||||
if err != nil {
|
||||
@@ -657,19 +623,7 @@ 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
|
||||
// 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)
|
||||
return nil, err
|
||||
}
|
||||
if !needsLogin {
|
||||
if _, err := s.loginAttempt(ctx, "", ""); err == nil {
|
||||
state.Set(internal.StatusIdle)
|
||||
return &proto.LoginResponse{}, nil
|
||||
}
|
||||
@@ -730,7 +684,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
|
||||
// which returns NeedsLogin and parks on the browser leg.
|
||||
state.Set(internal.StatusConnecting)
|
||||
|
||||
if loginStatus, err := s.attemptLogin(ctx, msg.SetupKey, ""); err != nil {
|
||||
if loginStatus, err := s.loginAttempt(ctx, msg.SetupKey, ""); err != nil {
|
||||
state.Set(loginStatus)
|
||||
return nil, err
|
||||
}
|
||||
@@ -885,7 +839,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
|
||||
s.oauthAuthFlow.expiresAt = time.Now()
|
||||
s.mutex.Unlock()
|
||||
|
||||
if loginStatus, err := s.attemptLogin(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
|
||||
if loginStatus, err := s.loginAttempt(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
|
||||
state.Set(loginStatus)
|
||||
return nil, err
|
||||
}
|
||||
@@ -1815,9 +1769,6 @@ 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 {
|
||||
|
||||
@@ -26,17 +26,17 @@ contents:
|
||||
|
||||
# Default dependencies for the GTK4 + WebKitGTK 6.0 stack (Ubuntu 24.04+ / Debian 13+)
|
||||
depends:
|
||||
- libgtk-4-1 (>= 4.14)
|
||||
- libgtk-4-1
|
||||
- libwebkitgtk-6.0-4
|
||||
- xdg-utils
|
||||
|
||||
# Distribution-specific overrides for different package formats
|
||||
overrides:
|
||||
# RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux / openSUSE
|
||||
# RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux
|
||||
rpm:
|
||||
depends:
|
||||
- (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
|
||||
- (webkitgtk6.0 or libwebkitgtk-6_0-4)
|
||||
- gtk4
|
||||
- webkitgtk6.0
|
||||
- xdg-utils
|
||||
|
||||
# Arch Linux packages
|
||||
|
||||
@@ -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 };
|
||||
};
|
||||
@@ -43,12 +43,7 @@ function buildSsoCancelPromise(state: SsoState, signal?: AbortSignal): Promise<v
|
||||
}
|
||||
|
||||
async function runSsoLogin(
|
||||
result: {
|
||||
verificationUri: string;
|
||||
verificationUriComplete: string;
|
||||
userCode: string;
|
||||
profileId: string;
|
||||
},
|
||||
result: { verificationUri: string; verificationUriComplete: string; userCode: string },
|
||||
state: SsoState,
|
||||
signal?: AbortSignal,
|
||||
): Promise<void> {
|
||||
@@ -61,7 +56,7 @@ async function runSsoLogin(
|
||||
// suspended, so a frontend-driven Up (a promise continuation) would not
|
||||
// fire until the user woke the window (e.g. hovering the tray icon).
|
||||
const waitPromise = Connection.WaitSSOLoginAndUp(
|
||||
{ userCode: result.userCode, hostname: "", profileId: result.profileId },
|
||||
{ userCode: result.userCode, hostname: "" },
|
||||
{ profileName: "", username: "" },
|
||||
);
|
||||
|
||||
|
||||
@@ -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"
|
||||
},
|
||||
|
||||
@@ -14,6 +14,7 @@ import (
|
||||
"github.com/sirupsen/logrus"
|
||||
"github.com/wailsapp/wails/v3/pkg/application"
|
||||
"github.com/wailsapp/wails/v3/pkg/events"
|
||||
"github.com/wailsapp/wails/v3/pkg/services/notifications"
|
||||
|
||||
"github.com/netbirdio/netbird/client/ui/authsession"
|
||||
"github.com/netbirdio/netbird/client/ui/i18n"
|
||||
@@ -62,7 +63,7 @@ type registeredServices struct {
|
||||
profiles *services.Profiles
|
||||
update *services.Update
|
||||
daemonFeed *services.DaemonFeed
|
||||
notifier *Notifier
|
||||
notifier *notifications.NotificationService
|
||||
compat *services.Compat
|
||||
profileSwitcher *services.ProfileSwitcher
|
||||
bundle *i18n.Bundle
|
||||
@@ -101,7 +102,7 @@ func main() {
|
||||
updaterHolder := updater.NewHolder(app.Event)
|
||||
update := services.NewUpdate(conn, updaterHolder)
|
||||
daemonFeed := services.NewDaemonFeed(conn, app.Event, updaterHolder, debugLog)
|
||||
notifier := newNotifier()
|
||||
notifier := notifications.New()
|
||||
compat := services.NewCompat(conn)
|
||||
// macOS shows no toast until permission is requested. Run it after
|
||||
// ApplicationStarted so the notifier's Startup has initialised the
|
||||
@@ -180,7 +181,6 @@ func main() {
|
||||
WindowManager: windowManager,
|
||||
Session: authSession,
|
||||
Localizer: localizer,
|
||||
Preferences: prefStore,
|
||||
})
|
||||
listenForShowSignal(context.Background(), tray)
|
||||
|
||||
@@ -210,7 +210,7 @@ func main() {
|
||||
// requestNotificationAuthorization prompts for macOS notification permission.
|
||||
// The request blocks until the user responds (up to 3 minutes), so callers run
|
||||
// it in a goroutine. No-op on Linux/Windows.
|
||||
func requestNotificationAuthorization(notifier *Notifier) {
|
||||
func requestNotificationAuthorization(notifier *notifications.NotificationService) {
|
||||
authorized, err := notifier.CheckNotificationAuthorization()
|
||||
if err != nil {
|
||||
logrus.Debugf("check notification authorization: %v", err)
|
||||
|
||||
@@ -1,101 +0,0 @@
|
||||
//go:build !android && !ios && !freebsd && !js
|
||||
|
||||
package main
|
||||
|
||||
import (
|
||||
"context"
|
||||
"errors"
|
||||
"sync/atomic"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
"github.com/wailsapp/wails/v3/pkg/application"
|
||||
"github.com/wailsapp/wails/v3/pkg/services/notifications"
|
||||
)
|
||||
|
||||
var errNotificationsUnavailable = errors.New("notifications unavailable")
|
||||
|
||||
// Notifier wraps the Wails notification service so an unavailable backend
|
||||
// disables notifications instead of aborting the app. Startup fails for
|
||||
// environment reasons (a bare unbundled binary on macOS has no bundle
|
||||
// identifier, a headless Linux session has no D-Bus session bus), and Wails
|
||||
// treats a service startup error as fatal. After a failed startup every call
|
||||
// is a no-op: on macOS, touching UNUserNotificationCenter without a bundle
|
||||
// identifier raises an Objective-C exception that recover() cannot catch.
|
||||
type Notifier struct {
|
||||
inner *notifications.NotificationService
|
||||
available atomic.Bool
|
||||
}
|
||||
|
||||
func newNotifier() *Notifier {
|
||||
return &Notifier{inner: notifications.New()}
|
||||
}
|
||||
|
||||
// ServiceName implements the Wails service-name hook for startup logs.
|
||||
func (n *Notifier) ServiceName() string {
|
||||
return n.inner.ServiceName()
|
||||
}
|
||||
|
||||
// ServiceStartup starts the platform notifier, downgrading failure to a
|
||||
// warning so the app keeps running without notifications.
|
||||
func (n *Notifier) ServiceStartup(ctx context.Context, options application.ServiceOptions) error {
|
||||
if err := n.inner.ServiceStartup(ctx, options); err != nil {
|
||||
log.Warnf("notifications disabled: %v", err)
|
||||
return nil
|
||||
}
|
||||
n.available.Store(true)
|
||||
return nil
|
||||
}
|
||||
|
||||
func (n *Notifier) ServiceShutdown() error {
|
||||
if !n.available.Load() {
|
||||
return nil
|
||||
}
|
||||
return n.inner.ServiceShutdown()
|
||||
}
|
||||
|
||||
func (n *Notifier) CheckNotificationAuthorization() (bool, error) {
|
||||
if !n.available.Load() {
|
||||
return false, errNotificationsUnavailable
|
||||
}
|
||||
return n.inner.CheckNotificationAuthorization()
|
||||
}
|
||||
|
||||
func (n *Notifier) RequestNotificationAuthorization() (bool, error) {
|
||||
if !n.available.Load() {
|
||||
return false, errNotificationsUnavailable
|
||||
}
|
||||
return n.inner.RequestNotificationAuthorization()
|
||||
}
|
||||
|
||||
// SendNotification delivers a notification, silently dropping it when the
|
||||
// backend never started (notifications are best-effort everywhere).
|
||||
func (n *Notifier) SendNotification(options notifications.NotificationOptions) error {
|
||||
if !n.available.Load() {
|
||||
log.Debugf("notifications disabled, dropping %q", options.ID)
|
||||
return nil
|
||||
}
|
||||
return n.inner.SendNotification(options)
|
||||
}
|
||||
|
||||
func (n *Notifier) SendNotificationWithActions(options notifications.NotificationOptions) error {
|
||||
if !n.available.Load() {
|
||||
log.Debugf("notifications disabled, dropping %q", options.ID)
|
||||
return nil
|
||||
}
|
||||
return n.inner.SendNotificationWithActions(options)
|
||||
}
|
||||
|
||||
func (n *Notifier) RegisterNotificationCategory(category notifications.NotificationCategory) error {
|
||||
if !n.available.Load() {
|
||||
return nil
|
||||
}
|
||||
return n.inner.RegisterNotificationCategory(category)
|
||||
}
|
||||
|
||||
// OnNotificationResponse registers the response callback. Pure Go state, so
|
||||
// it is safe (and simply inert) when the backend never started.
|
||||
//
|
||||
//wails:ignore
|
||||
func (n *Notifier) OnNotificationResponse(callback func(result notifications.NotificationResult)) {
|
||||
n.inner.OnNotificationResponse(callback)
|
||||
}
|
||||
@@ -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 == "" {
|
||||
@@ -270,7 +246,6 @@ func (s *Store) ExistedAtLoad() bool {
|
||||
func (s *Store) load() error {
|
||||
if _, err := os.Stat(s.path); err != nil {
|
||||
if errors.Is(err, os.ErrNotExist) {
|
||||
log.Infof("no ui preferences file at %s; using defaults", s.path)
|
||||
return nil
|
||||
}
|
||||
return fmt.Errorf("stat preferences: %w", err)
|
||||
|
||||
@@ -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)
|
||||
|
||||
|
||||
@@ -33,21 +33,12 @@ type LoginResult struct {
|
||||
UserCode string `json:"userCode"`
|
||||
VerificationURI string `json:"verificationUri"`
|
||||
VerificationURIComplete string `json:"verificationUriComplete"`
|
||||
// ProfileID is the ID of the profile this login ran against, or "" when the
|
||||
// caller named the profile itself and no ID was resolved. Pass it back in
|
||||
// WaitSSOParams so the account email lands on this profile even if the
|
||||
// active one changes during SSO.
|
||||
ProfileID string `json:"profileId"`
|
||||
}
|
||||
|
||||
// WaitSSOParams are the inputs to waitSSOLogin.
|
||||
type WaitSSOParams struct {
|
||||
UserCode string `json:"userCode"`
|
||||
Hostname string `json:"hostname"`
|
||||
// ProfileID is the profile the login was started for, used to file the
|
||||
// account email against it rather than against whichever profile is active
|
||||
// when the flow returns. Optional: empty falls back to the active profile.
|
||||
ProfileID string `json:"profileId"`
|
||||
}
|
||||
|
||||
// UpParams selects the profile to bring up.
|
||||
@@ -86,16 +77,11 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
|
||||
// Fall back to the daemon's active profile and the current OS user.
|
||||
profileName := p.ProfileName
|
||||
username := p.Username
|
||||
// Only set when the daemon told us the ID. A caller-supplied ProfileName is
|
||||
// a handle — a display name or an ID prefix resolve too — and the state file
|
||||
// is named after the ID, so passing a handle on would name the wrong file.
|
||||
profileID := ""
|
||||
if profileName == "" {
|
||||
if active, aerr := cli.GetActiveProfile(ctx, &proto.GetActiveProfileRequest{}); aerr == nil {
|
||||
// Address the active profile by ID (the daemon resolves it as a
|
||||
// handle); names can collide, the ID cannot.
|
||||
profileName = active.GetId()
|
||||
profileID = profileName
|
||||
if username == "" {
|
||||
username = active.GetUsername()
|
||||
}
|
||||
@@ -136,7 +122,6 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
|
||||
UserCode: resp.GetUserCode(),
|
||||
VerificationURI: resp.GetVerificationURI(),
|
||||
VerificationURIComplete: resp.GetVerificationURIComplete(),
|
||||
ProfileID: profileID,
|
||||
}, nil
|
||||
}
|
||||
|
||||
@@ -257,31 +242,6 @@ func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
|
||||
return "", s.classifyDaemonError(err)
|
||||
}
|
||||
log.Infof("SSO login completed, daemon reported success")
|
||||
|
||||
// Persist the account email the same way the CLI does after its own
|
||||
// WaitSSOLogin: the daemon returns it but cannot store it, since it runs as
|
||||
// root and the per-profile state file is user-owned (see Logout below).
|
||||
// Without this the profile has no email, so Profiles.List shows no account
|
||||
// and later logins and session extends go out without a login_hint —
|
||||
// leaving the IdP to guess which account was meant.
|
||||
if email := resp.GetEmail(); email != "" {
|
||||
state := &profilemanager.ProfileState{Email: email}
|
||||
pm := profilemanager.NewProfileManager()
|
||||
|
||||
// Against the profile the login was started for: SSO spans seconds of
|
||||
// user interaction, and a profile switch in that window would otherwise
|
||||
// file the email under the wrong profile.
|
||||
if p.ProfileID != "" {
|
||||
err = pm.SetProfileState(profilemanager.ID(p.ProfileID), state)
|
||||
} else {
|
||||
err = pm.SetActiveProfileState(state)
|
||||
}
|
||||
if err != nil {
|
||||
// Non-fatal: the login itself succeeded.
|
||||
log.Warnf("failed to store account email: %v", err)
|
||||
}
|
||||
}
|
||||
|
||||
return resp.GetEmail(), nil
|
||||
}
|
||||
|
||||
|
||||
@@ -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)
|
||||
}
|
||||
|
||||
@@ -6,8 +6,6 @@ import (
|
||||
"context"
|
||||
"os/user"
|
||||
|
||||
log "github.com/sirupsen/logrus"
|
||||
|
||||
"github.com/netbirdio/netbird/client/internal/profilemanager"
|
||||
"github.com/netbirdio/netbird/client/proto"
|
||||
)
|
||||
@@ -153,31 +151,11 @@ func (s *Profiles) Remove(ctx context.Context, p ProfileRef) error {
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
resp, err := cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
|
||||
_, err = cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
|
||||
ProfileName: p.ProfileName,
|
||||
Username: p.Username,
|
||||
})
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// The daemon deletes what it owns but runs as root, so it leaves the
|
||||
// user-owned state file holding the account email behind (same split as
|
||||
// Connection.Logout). Legacy profiles are keyed by name rather than by a
|
||||
// generated ID, so a recreated profile of the same name would inherit the
|
||||
// deleted one's email and offer it as the login_hint.
|
||||
//
|
||||
// Keyed on the ID the daemon resolved, not on the request handle: that may
|
||||
// have been a display name or an ID prefix, which would name a different
|
||||
// file (or none).
|
||||
if id := resp.GetId(); id != "" {
|
||||
if err := profilemanager.NewProfileManager().RemoveProfileState(id); err != nil {
|
||||
// Non-fatal: the profile itself is gone.
|
||||
log.Warnf("failed to remove profile state for %s: %v", id, err)
|
||||
}
|
||||
}
|
||||
|
||||
return nil
|
||||
return err
|
||||
}
|
||||
|
||||
// Rename changes a profile's display name. The on-disk ID is unaffected, so
|
||||
|
||||
@@ -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"
|
||||
)
|
||||
@@ -45,15 +44,14 @@ type TrayServices struct {
|
||||
Profiles *services.Profiles
|
||||
Networks *services.Networks
|
||||
DaemonFeed *services.DaemonFeed
|
||||
Notifier *Notifier
|
||||
Notifier *notifications.NotificationService
|
||||
Update *services.Update
|
||||
ProfileSwitcher *services.ProfileSwitcher
|
||||
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
|
||||
|
||||
@@ -44,7 +44,7 @@ func safeSendNotification(send sendFn, what string, opts notifications.Notificat
|
||||
// notifyIfDaemonOutdated probes the daemon once and fires an OS toast when it
|
||||
// is reachable but too old for this UI. A probe error means the daemon isn't
|
||||
// reachable (not outdated), so it is left to the normal connection flow.
|
||||
func notifyIfDaemonOutdated(compat *services.Compat, notifier *Notifier, loc *Localizer) {
|
||||
func notifyIfDaemonOutdated(compat *services.Compat, notifier *notifications.NotificationService, loc *Localizer) {
|
||||
ready, err := compat.DaemonReady(context.Background())
|
||||
if err != nil {
|
||||
log.Debugf("daemon compatibility probe: %v", err)
|
||||
|
||||
@@ -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 {
|
||||
|
||||
@@ -21,7 +21,7 @@ type trayUpdater struct {
|
||||
app *application.App
|
||||
window *application.WebviewWindow
|
||||
update *services.Update
|
||||
notifier *Notifier
|
||||
notifier *notifications.NotificationService
|
||||
loc *Localizer
|
||||
onIconChange func()
|
||||
// onMenuChange drives a full tray relayout: the update row lives in the
|
||||
@@ -36,7 +36,7 @@ type trayUpdater struct {
|
||||
progressWindowOpen bool
|
||||
}
|
||||
|
||||
func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
|
||||
func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *notifications.NotificationService, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
|
||||
u := &trayUpdater{
|
||||
app: app,
|
||||
window: window,
|
||||
|
||||
@@ -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>
|
||||
|
||||
@@ -115,7 +115,7 @@ sequenceDiagram
|
||||
Resp->>Resp: parse usage tokens, completion
|
||||
Note over Resp: capture_completion gates raw<br/>completion capture
|
||||
Resp->>Cost: tokens
|
||||
Cost->>Cost: lookup pricing.yaml + compute cost
|
||||
Cost->>Cost: lookup rates from config-delivered<br/>pricing table + compute cost
|
||||
Cost->>Rec: tokens + cost
|
||||
Rec->>MgmtGrpc: RecordLLMUsage(provider, model, prompt_t, completion_t, cost, groups, user)
|
||||
Rec-->>Log: emit access-log entry<br/>(if EnableLogCollection)
|
||||
|
||||
@@ -15,6 +15,10 @@ Inside the package: `manager.go` is the CRUD + permissions-gated facade; `synthe
|
||||
| ---- | ---- |
|
||||
| `agentnetwork/manager.go` | Manager interface + CRUD + permission gates + bootstrap-settings + reconcile trigger |
|
||||
| `agentnetwork/synthesizer.go` | Settings/policy → wire-format synthesis; sole writer of the proxy middleware chain |
|
||||
| `agentnetwork/synthesizer_pricing.go` | `buildCostMeterConfigJSON` — default table + per-provider prices → `cost_meter` config |
|
||||
| `agentnetwork/pricing/defaults.go` | Default pricing table derived from the catalog + supplementals; `DefaultTable`, `LookupDefault`, wire `Entry` |
|
||||
| `agentnetwork/pricing/override.go` | `LoadFile`/`StartReloader` for `AgentNetwork.PricingDefaultsFile` (mtime poll, merge over compiled-in base) |
|
||||
| `agentnetwork/pricing/{exampleyaml,gen}.go` | Generates `defaults_llm_pricing.example.yaml` from the compiled-in table (golden-tested) |
|
||||
| `agentnetwork/policyselect.go` | Per-request policy attribution + account-budget ceiling (min-wins) |
|
||||
| `agentnetwork/reconcile.go` | Per-account synth diff vs in-memory cache → Create/Update/Delete |
|
||||
| `agentnetwork/catalog/catalog.go` | Static provider catalogue (auth headers, identity-injection shapes) |
|
||||
@@ -48,6 +52,8 @@ flowchart TD
|
||||
I --> J[indexProviderGroups: providerID -> sorted source groups]
|
||||
J --> K[buildRouterConfigJSON drops orphan providers]
|
||||
J --> L[buildIdentityInjectConfigJSON per catalog entry]
|
||||
J --> K2[buildCostMeterConfigJSON: default table + per-provider prices]
|
||||
K2 --> P
|
||||
H --> M[mergeGuardrails: union allowlist, OR redact]
|
||||
M --> N[applyAccountCollectionControls account toggle = SOLE capture control]
|
||||
N --> O[marshalGuardrailConfig]
|
||||
@@ -60,6 +66,84 @@ flowchart TD
|
||||
R --> T[accountManager.UpdateAccountPeers — fans synth ACLs into network map]
|
||||
```
|
||||
|
||||
### LLM pricing (management is the sole authority)
|
||||
|
||||
**The proxy carries no price list.** Management synthesizes the entire pricing
|
||||
table and ships it inside `cost_meter`'s `ConfigJSON`, so a price change reaches
|
||||
the proxies as an ordinary mapping push — the chain rebuild installs a fresh
|
||||
table and there is nothing to reload on the proxy side.
|
||||
|
||||
```mermaid
|
||||
flowchart TD
|
||||
A[catalog.All — PricingSurfaces x Models] --> B[buildDefaultTable + supplementalDefaults]
|
||||
B --> C{AgentNetwork.PricingDefaultsFile}
|
||||
C -- absent --> D[compiled-in table serves]
|
||||
C -- loaded --> E[LoadFile: merge file entries WHOLE over compiled base]
|
||||
E --> F[mergedTable atomic.Pointer]
|
||||
D --> G[DefaultTable]
|
||||
F --> G
|
||||
G --> H[buildCostMeterConfigJSON — pricing.defaults]
|
||||
I[types.Provider.Models operator prices] --> J[normalizePricingModelID<br/>bedrock ARN/region/version, vertex @version]
|
||||
J --> K[materializeEntry: default entry as base,<br/>operator input/output verbatim,<br/>cache pointers only when non-nil]
|
||||
K --> L[pricing.providers keyed by provider record ID]
|
||||
H --> M[cost_meter ConfigJSON]
|
||||
L --> M
|
||||
G --> N[GET /catalog — applyDefaultPricing prefills dashboard rows]
|
||||
O[StartReloader: mtime poll every ReloadInterval 1m] --> E
|
||||
```
|
||||
|
||||
**Two tiers, resolved per request on the proxy** (`synthesizer_pricing.go:22-35`):
|
||||
|
||||
- `pricing.defaults` — surface (`openai`/`anthropic`/`bedrock`) → normalized model
|
||||
id → rates. The **full** default table ships to every account: it is small
|
||||
(~10 KB) and it is what keeps gateway-style providers (which enumerate no
|
||||
models, so they claim every model) priced.
|
||||
- `pricing.providers` — provider **record** id → normalized model id → rates,
|
||||
matched against the `llm.resolved_provider_id` the router stamps. Entries are
|
||||
**fully materialized here**, at synth time: `materializeEntry` starts from the
|
||||
default entry for that model so cache rates the operator didn't state are
|
||||
inherited, overlays operator `input`/`output` verbatim (**including an explicit
|
||||
0**, which prices a self-hosted or internal endpoint as free rather than
|
||||
silently reverting to list price), and overlays cache-rate **pointers only when
|
||||
non-nil** — `nil` means "inherit the default", an explicit `0` means "no
|
||||
discount, bill this bucket at the input rate". The proxy therefore does two map
|
||||
lookups and no merging.
|
||||
|
||||
Same orphan rule as the router: a provider no enabled policy authorises is
|
||||
unreachable, so its prices aren't shipped. Model ids are normalized with the
|
||||
**same** functions the request parser uses (`NormalizeBedrockModel` /
|
||||
`NormalizeVertexModel`), which is what makes the per-record lookup key compare
|
||||
equal to the `llm.model` the proxy meters. Post-normalization duplicates resolve
|
||||
first-occurrence-wins, matching the routing dedup order.
|
||||
|
||||
**`AgentNetwork.PricingDefaultsFile`** (`config.go:190-207`) lets an operator
|
||||
replace default rates without a rebuild. Schema is `surface → model → rates`
|
||||
(`input_per_1k`, `output_per_1k`, and optional `cached_input_per_1k` /
|
||||
`cache_read_per_1k` / `cache_creation_per_1k`). Semantics:
|
||||
|
||||
- A **relative** path resolves against `<Datadir>`, so a bare filename lands
|
||||
alongside the store. Empty config probes `<Datadir>/defaults_llm_pricing.yaml`.
|
||||
- An **explicitly configured** path is *required to load*: a typo or malformed
|
||||
file fails startup, because the operator believes those rates are live. The
|
||||
conventional probe is optional — an absent file just serves compiled-in
|
||||
defaults, and the path stays watched in case it appears later.
|
||||
- File entries **replace** the compiled-in entry for the same (surface, model)
|
||||
**whole** — they are not field-merged, so an entry must repeat the cache rates
|
||||
it wants to keep. Everything the file doesn't mention keeps built-in rates.
|
||||
- Unknown YAML fields are rejected (`KnownFields(true)`) and every rate must be
|
||||
finite and non-negative — the same constraints the HTTP API enforces on
|
||||
operator per-provider prices.
|
||||
- Reload is an mtime poll (`ReloadInterval`, 1 min) and is **lenient at runtime**:
|
||||
a parse error keeps the previous table, a deleted file reverts to compiled-in
|
||||
defaults. A mid-edit save can never take pricing down.
|
||||
|
||||
The live table feeds **both** consumers, which is what keeps them consistent: the
|
||||
synthesizer (what proxies actually bill with) and `GET /api/agent-network/catalog`
|
||||
via `applyDefaultPricing` (what the dashboard's model-row prices prefill with).
|
||||
`defaults_llm_pricing.example.yaml` is generated from the compiled-in table
|
||||
(`go generate ./management/internals/modules/agentnetwork/pricing`) and
|
||||
golden-tested, so operators start from a file matching the built-in rates exactly.
|
||||
|
||||
### Budget rule resolution (min-wins, group+user bound)
|
||||
|
||||
```mermaid
|
||||
@@ -124,7 +208,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
|
||||
| on_request | 3 | `llm_identity_inject` | `{"providers":[{provider_id, header_pair?, json_metadata?, extra_headers?}]}` | **true** |
|
||||
| on_request | 4 | `llm_guardrail` | `{"provider_allowlists"?: {providerID: []model}, "prompt_capture":{enabled,redact_pii}}` | – |
|
||||
| on_response | 5 | `llm_limit_record` | `{}` (runs LAST at runtime) | – |
|
||||
| on_response | 6 | `cost_meter` | `{}` | – |
|
||||
| on_response | 6 | `cost_meter` | `{"pricing":{"defaults":{surface:{model:rates}},"providers"?:{providerRecordID:{model:rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}` | – |
|
||||
| on_response | 7 | `llm_response_parser` | `{"capture_completion": <bool>, "redact_pii"?: true}` | – |
|
||||
- **Synthesized service shape** (`synthesizer.go:739`): `Mode=HTTP`, `Private=true`, `Domain=<subdomain>.<cluster>`, `AccessGroups=unionSourceGroups(enabledPolicies)`, one `TargetTypeCluster` target with `Host=noop.invalid:443` (router rewrites per request), `Options.{DirectUpstream,AgentNetwork}=true`, `DisableAccessLog=!settings.EnableLogCollection`, `CaptureMax{Req,Resp}Bytes=1<<20`, `CaptureContentTypes=["application/json","text/event-stream"]`.
|
||||
|
||||
@@ -139,6 +223,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
|
||||
- **Orphan providers (no enabled policy authorises them) NEVER reach the router** (`synthesizer.go:351-357`); skipped from `identity_inject` for symmetry.
|
||||
- **Provider creation refuses empty `api_key`** (`manager.go:175`); **deletion refuses while any policy still references it** (`manager.go:265-273`).
|
||||
- **Session keypair stability across provider edits** (`manager.go:226-228`) — server-managed, copied through every `UpdateProvider`, never API-surfaced.
|
||||
- **Management is the sole pricing authority.** The proxy has no embedded price list, so an account whose `cost_meter` config carries no `pricing` block bills **nothing** (`cost.skipped=unknown_model`, $0) rather than falling back to stale built-ins. The top-level `pricing` wrapper is also the feature-detection signal in both directions: an old proxy ignores it as an unknown field, and a new proxy reads its absence as "old management".
|
||||
- **Per-provider prices are materialized at synth time, not merged on the proxy** (`synthesizer_pricing.go:114-131`). A per-record entry is always complete, so the proxy's lookup is per-record-then-defaults with no field-level fallback between tiers.
|
||||
- **An explicit operator price of `0` prices the model as free** — it must not be treated as "unset" and reverted to list price (`synthesizer_pricing.go:49-54`). Only *cache*-rate fields distinguish unset from zero, via `*float64`.
|
||||
- **Pricing model ids are normalized with the same functions the request parser uses** (`normalizePricingModelID`). If the two ever diverge, per-record prices silently stop matching and every request falls through to surface defaults.
|
||||
- **The default table's coverage is structural, not curated.** It is derived from the catalog via each provider's `PricingSurfaces`; `TestDefaultTable_CoversEveryCatalogModel` fails on an unpriced catalog model and `TestDefaultTable_NoConflictingContributions` fails if two providers contribute the same (surface, model) at different rates.
|
||||
- **A pricing-defaults file failure is fatal only at startup, and only for an explicitly configured path.** Runtime reload failures keep the previous table; a deleted file reverts to compiled-in defaults (`pricing/override.go:62-81, 113-148`).
|
||||
|
||||
## Things to scrutinize
|
||||
|
||||
@@ -176,10 +266,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
|
||||
- **Capture-pointer semantics (restated):** non-agent-network callers see no field → legacy nil-default emit, identical to pre-PR. Agent-network targets always carry an explicit `capture_*` value.
|
||||
- **`TestSynthesizeServices_HappyPath` was updated:** request-parser config moved from `{}` to `{"capture_prompt":false}` (`synthesizer_test.go:174`). External snapshot tests against synth output need updating.
|
||||
- **`MergedGuardrails` retains zeroed `TokenLimits`/`Budget`/`Retention`** even though `Policy.Limits` carries the real values now; `llm_limit_check` is the authoritative enforcement. Comment at `synthesizer.go:940-948` calls this out.
|
||||
- **`cost_meter`'s `pricing` block is version-skew-safe in both directions.** A proxy predating config-delivered pricing ignores the field as unknown JSON (it previously priced from its own embedded table, so it keeps billing — at its own rates, which is the skew to be aware of during a rolling upgrade). A current proxy paired with old management sees no `pricing` block, logs one warning at chain-build time, and records `cost.skipped=unknown_model` — token counting and cap enforcement are unaffected, only the USD annotation goes to $0.
|
||||
|
||||
### Performance
|
||||
|
||||
- **`SynthesizeServices` runs on every controller tick / mutation reconcile.** Cost: 4 store reads + optional per-provider keypair backfill. Sort + index + merge are O(N log N) / O(P × G); dominant cost is JSON marshalling. No nested loops escape these dimensions.
|
||||
- **The full default pricing table is marshalled into every account's `cost_meter` config on every synth** (~10 KB serialized). This is a deliberate trade: it keeps gateway-style providers priced for every catalog model, and it is the largest single contributor to the synth JSON. `DefaultTable()` itself is a pointer load (or a `sync.Once`-built map) — the cost is the marshal, not the build.
|
||||
- **`reconcile.diffMappings` is O(N + M)** with N=M=1 per account today — effectively constant.
|
||||
- **`SynthesizeServicesForCluster`** (`synthesizer.go:71`) walks every account on a cluster; per-account failures are **swallowed** (`synthesizer.go:91-93`) so a single misconfigured account doesn't drop the cluster. Runs per proxy reconnect.
|
||||
|
||||
@@ -188,6 +280,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
|
||||
- **Activity codes:** `AgentNetwork{Provider,Policy,Guardrail,BudgetRule}{Created,Updated,Deleted}`; `AgentNetworkSettingsUpdated` with `log_collection/prompt_collection/redact_pii` payload (`manager.go:567-571`). **No activity code for `SelectPolicyForRequest` denies** — surfaced via proxy access log only (likely intentional given volume).
|
||||
- **Deny codes** namespaced: `llm_policy.{token,budget}_cap_exceeded`, `llm_account.{token,budget}_cap_exceeded` (`policyselect.go:18-26`).
|
||||
- **Reconcile failures are logged at warn and swallowed** (`reconcile.go:42-44`). Persistent synth failures (e.g. unknown catalog id) silently keep the proxy out of sync — consider a manager-level synth-health surface if this becomes a support burden.
|
||||
- **Pricing-file lifecycle logs at info** (load, reload, revert-to-built-ins) and **at warn** for a runtime reload failure; the mtime check itself is `Debugf`. There is no metric on reload failures, so an operator who breaks the file mid-flight keeps billing at the previous table with only a log line to show it (`pricing/override.go:113-148`).
|
||||
|
||||
## Test coverage
|
||||
|
||||
@@ -198,6 +291,9 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
|
||||
| `synthesizer_guardrail_realstore_test.go` | `PromptCaptureAccountIsSoleControl`; `PromptCaptureFlowsWhenAccountOptsIn`; `AccountRedactWithoutGuardrailRedact`; `NoGuardrail_CaptureOff`. |
|
||||
| `synthesizer_log_collection_realstore_test.go` | `LogCollection{Off_SuppressesAccessLog,On_PermitsAccessLog}` — verifies `DisableAccessLog` propagation through `ToProtoMapping`. |
|
||||
| `synthesizer_parser_redact_realstore_test.go` | **Capture-pointer regression suite:** `ParserConfigsCarryRedactPii`; `ParserConfigsSuppressCaptureWhenLogCollectionOnly` (log=on/prompt=off ⇒ both capture flags false); `ParserConfigsOmitRedactPiiWhenOff`. |
|
||||
| `synthesizer_pricing_test.go` | `BuildCostMeterConfig_{BedrockModelNormalization,CacheRateNilVsZero,OrphanAndGatewayProviders}` — the per-record tier's three load-bearing rules: keys normalized like the parser's, `nil` cache pointer inherits vs explicit `0` bills at input rate, and orphan / gateway (empty `Models`) providers ship no per-record entry. |
|
||||
| `pricing/defaults_test.go` | `DefaultTable_{CoversEveryCatalogModel,NoConflictingContributions,AllRatesFiniteNonNegative,PinnedRates}`; `LookupDefault_SurfaceOrder`. Catalog-derived coverage + rate sanity are structural, not curated. |
|
||||
| `pricing/override_test.go` | `LoadFile_{MergesOverCompiledDefaults,MissingPath,RejectsInvalid}`; `Reload_LifeCycle` (mtime detect, parse error keeps previous, delete reverts to built-ins); `ExampleYAML_InSyncWithBuiltins` golden. |
|
||||
| `policyselect_test.go` | Mock-store: `NoApplicablePolicies`; `AllowWithLowestGroupAttribution`; `LargerPoolWinsAcrossUsageLevels`; `StaysOnLargerPoolAfterPartialDrain`; `FallsThroughToSmallerPoolWhenLargerExhausted`; `TiebreakBy{LargerGroupPool,CreatedAt}`; `DeniesWhenAllExhausted`; `UncappedPolicyAlwaysWinsAgainstCapped`; `DisabledPolicyIgnored`; `StoreErrorPropagates`; `RejectsEmptyAccount`; `SharesGroupCounterAcrossPolicies`; `AntiFallThroughOnLowestGroup`; `BudgetOnlyExhaustionDenies`; `BudgetTighterThanTokenWins`. |
|
||||
| `policyselect_realstore_test.go` | Real-sqlite regression guard: `NoApplicablePolicies`; `AllowAndLowestGroupAttribution`; `LargerPoolWins_FallsThroughWhenExhausted`; `BudgetCapDenies`; `GroupCounterSharedAcrossPolicies`; `DisabledPolicyIgnored`. |
|
||||
| `policyselect_account_realstore_test.go` | Account budget rules: `AccountCeilingBindsEvenWithUncappedPolicy` (min-wins); `AccountGroupCeiling`; `AccountTargetUsersBindsOnlyThatUser`; `AccountRuleRecordsToOwnWindow`. |
|
||||
|
||||
@@ -5,7 +5,7 @@ LLM request. The two highest-blast-radius areas are the **capture-pointer
|
||||
semantics** and the **limit_check ⇒ limit_record** record-once invariant.
|
||||
|
||||
Sibling module: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — the SDK
|
||||
adapters + pricing catalog this chain delegates to.
|
||||
adapters + pricing table and cost formula this chain delegates to.
|
||||
|
||||
---
|
||||
|
||||
@@ -34,7 +34,7 @@ rewrites.
|
||||
| `llm_identity_inject` | OnRequest | `llm.{resolved_provider_id,authorising_groups}`, `Input.{UserEmail,UserID,UserGroups,UserGroupNames}` | none | header strip/inject + optional body rewrite |
|
||||
| `llm_guardrail` | OnRequest | `llm.{model,request_prompt_raw}` | `llm_policy.{decision,reason}`, `llm.request_prompt` | none (model allowlist deny) |
|
||||
| `llm_response_parser` | OnResponse | `llm.provider`, `Input.{RespHeaders,RespBody,Status}` | `llm.{input,output,total,cached_input,cache_creation}_tokens`, `llm.response_completion` | none |
|
||||
| `cost_meter` | OnResponse | `llm.{provider,model}`, token buckets | `cost.usd_total` or `cost.skipped` | pricing lookup |
|
||||
| `cost_meter` | OnResponse | `llm.{provider,model,resolved_provider_id}`, token buckets | `cost.usd_{input,cached_input,cache_creation,output,total,cache}` or `cost.skipped` | none (in-memory pricing lookup) |
|
||||
| `llm_limit_record` | OnResponse | `llm.{attribution_group_id,attribution_window_seconds,input_tokens,output_tokens}`, `cost.usd_total` | none | gRPC `RecordLLMUsage` |
|
||||
|
||||
[all_test.go:26–40](../../../proxy/internal/middleware/builtin/all_test.go)
|
||||
@@ -44,7 +44,7 @@ locks the ID set; adding or removing one is a conscious extension.
|
||||
|
||||
| File | LOC | Notes |
|
||||
|---|---:|---|
|
||||
| `builtin.go` | 86 | Registry + `FactoryContext` (ctx, data dir, meter, logger, mgmt client) |
|
||||
| `builtin.go` | 90 | Registry + `FactoryContext` (ctx, meter, logger, mgmt client) |
|
||||
| `all_test.go` | 41 | Locks the 8-ID registry surface |
|
||||
| `agentnetwork_chain_integration_test.go` | 319 | Live sqlite + real gRPC bufconn; gate→recorder wire path |
|
||||
| `llm_request_parser/*` | 162 / 66 / 356 | Provider detection, body parse, prompt extraction with capture-pointer gating |
|
||||
@@ -53,7 +53,7 @@ locks the ID set; adding or removing one is a conscious extension.
|
||||
| `llm_identity_inject/*` | 440 / 108 / 666 | HeaderPair (LiteLLM) + JSONMetadata (Portkey) + ExtraHeaders |
|
||||
| `llm_guardrail/*` | 176 / 82 / 75 / 219 / 217 | Model allowlist + optional prompt capture with PII redaction |
|
||||
| `llm_response_parser/*` | 258 / 222 / 43 / 433 / 169 / 111 | Buffered + SSE accumulation; AWS event-stream accumulator (`streaming_bedrock.go`) for Bedrock; capture-pointer gates completion emit |
|
||||
| `cost_meter/*` | 181 / 84 / 439 | Token → USD via `proxy/internal/llm/pricing` |
|
||||
| `cost_meter/*` | 236 / 98 / 586 | Token → USD via `proxy/internal/llm/pricing`; both pricing tiers arrive in the middleware config |
|
||||
| `llm_limit_record/*` | 144 / 35 / 191 | Post-flight `RecordLLMUsage` (5s, debug-on-error) |
|
||||
|
||||
## Per-middleware
|
||||
@@ -168,12 +168,46 @@ token schema.
|
||||
|
||||
### cost_meter
|
||||
|
||||
Reads `llm.provider` + `llm.model` + token buckets, looks up per-1k rate via
|
||||
`pricing.Loader`, emits `cost.usd_total` or a closed-set `cost.skipped`
|
||||
reason (`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`,
|
||||
`unknown_model`). Loader's hot-reload goroutine is bound to proxy-lifetime
|
||||
context via `startReloader`. **Key invariant:** provider-shape switch lives
|
||||
in `pricing.Table.Cost` (sibling doc) — `cost_meter` stays provider-agnostic.
|
||||
Reads `llm.provider` + `llm.model` + token buckets, looks up the per-1k rates,
|
||||
and emits the full `cost.usd_*` breakdown (four per-bucket values plus the
|
||||
`_total` and `_cache` aggregates) or a closed-set `cost.skipped` reason
|
||||
(`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`,
|
||||
`unknown_model`).
|
||||
|
||||
**Management owns pricing.** The proxy carries no embedded price list: the whole
|
||||
table arrives in this middleware's `ConfigJSON` as
|
||||
`{pricing: {defaults, providers}}`, synthesized by management from the catalog
|
||||
plus the operator's stored per-provider prices
|
||||
([factory.go:13–34](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)).
|
||||
Both tiers are validated by `pricing.NewTable` / `pricing.NewEntries` at
|
||||
construction, so a non-finite or negative rate fails the chain build. A price
|
||||
change is an ordinary mapping push — the chain rebuild yields a fresh instance
|
||||
over a fresh immutable table, so there is no data dir, no pricing file, no
|
||||
reload goroutine, and nothing to invalidate.
|
||||
|
||||
**Two-tier lookup**
|
||||
([middleware.go:165–183](../../../proxy/internal/middleware/builtin/cost_meter/middleware.go)):
|
||||
|
||||
1. **Per-provider-record** — the operator's stored price for the route that
|
||||
actually served the request, keyed by the `llm.resolved_provider_id` that
|
||||
`llm_router` stamped on the allow path, then by normalized model id. Entries
|
||||
arrive fully materialized (management folds default cache rates in at synth
|
||||
time), so there is no merging here. Absent metadata — no router in the chain
|
||||
— skips this tier.
|
||||
2. **Surface defaults** — the catalog-derived table keyed by `llm.provider`
|
||||
(`openai`/`anthropic`/`bedrock`). This is also what prices gateway-style
|
||||
providers, which enumerate no models and therefore get no per-record entry.
|
||||
|
||||
**Backward compatibility:** a config with no `pricing` block means management
|
||||
predates config-delivered pricing. The factory logs one warning at build time
|
||||
and the instance records `cost.skipped=unknown_model` ($0) for every request
|
||||
rather than falling back to a stale built-in price list
|
||||
([factory.go:55–60](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)).
|
||||
|
||||
**Key invariant:** the provider-shape switch lives in `pricing.EntryCosts`
|
||||
(sibling doc) and is selected by the **surface**, not by which tier the entry
|
||||
came from — `cost_meter` stays provider-agnostic, and a per-record override on
|
||||
an Anthropic route still bills its cache buckets additively.
|
||||
|
||||
### llm_limit_record
|
||||
|
||||
@@ -246,12 +280,14 @@ no mocks. Tests: `TestChain_AllowPath_StampsAttributionAndRecordsCounter`
|
||||
| `llm_identity_inject` | `{providers: [{provider_id, header_pair?|json_metadata?, extra_headers?}]}` |
|
||||
| `llm_guardrail` | `{provider_allowlists: {providerID: []string}, prompt_capture: {enabled, redact_pii}}` — allowlist keyed by resolved provider id; a provider absent from the map is unrestricted (fail-closed backstop; authoritative per-policy/group check is management's `CheckLLMPolicyLimits`) |
|
||||
| `llm_response_parser` | `{redact_pii?, capture_completion?: *bool}` |
|
||||
| `cost_meter` | `{pricing_path?}` (basename inside data-dir; defaults `pricing.yaml`) |
|
||||
| `cost_meter` | `{pricing: {defaults: {surface: {model: rates}}, providers: {providerRecordID: {model: rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}`. A missing `pricing` key means "management predates config-delivered pricing": every request records `cost.skipped=unknown_model` |
|
||||
| `llm_limit_record` | `{}` — same pattern as `llm_limit_check` |
|
||||
|
||||
All factories accept empty / null / `{}` / whitespace as zero-value config;
|
||||
only structurally invalid JSON is rejected so misconfig surfaces at chain
|
||||
build time.
|
||||
build time. `cost_meter` adds a semantic check on top of that: a `pricing`
|
||||
block carrying a negative or non-finite rate fails the build too, rather than
|
||||
mispricing live traffic.
|
||||
|
||||
## Invariants
|
||||
|
||||
@@ -320,10 +356,11 @@ non-object `metadata` field
|
||||
— header path still attributes, but body-level tag-budget enforcement
|
||||
doesn't run for that request.
|
||||
|
||||
**Concurrency.** `cost_meter` shares a `pricing.Loader` via
|
||||
`atomic.Pointer[Table]`; readers always see a consistent table. Every
|
||||
middleware is a stateless value receiver. Integration test uses real bufconn
|
||||
gRPC — race detector is the meaningful bar.
|
||||
**Concurrency.** `cost_meter`'s two pricing tables are built once from the
|
||||
middleware config and never mutated, so the lookup path needs no lock or atomic
|
||||
swap — a price change replaces the whole instance. Every middleware is
|
||||
otherwise a stateless value receiver. Integration test uses real bufconn gRPC —
|
||||
race detector is the meaningful bar.
|
||||
|
||||
**Perf.** Hot path is `lookupKV` linear scan over <10 KVs; `cost_meter.Cost`
|
||||
is O(1); SSE accumulation is single-pass. No map allocation per call.
|
||||
@@ -349,13 +386,13 @@ counter accuracy.
|
||||
| `llm_guardrail/redact_test.go` | 15 | Email, SSN, phone (E.164 + NA), bearer, IPv4; fixture-driven |
|
||||
| `llm_response_parser/middleware_test.go` | 18 | Buffered OAI+Anthro, capture-pointer, redact, truncation |
|
||||
| `llm_response_parser/streaming_test.go` | 7 | OAI usage frame, Anthro message_delta, truncated body best-effort |
|
||||
| `cost_meter/middleware_test.go` | 17 | Each skip reason, provider-shape, pricing loader integration |
|
||||
| `cost_meter/middleware_test.go` | 22 | Each skip reason, provider-shape formulas, config-delivered defaults, per-record-beats-defaults + miss-falls-back, per-record uses surface formula, nil-pricing skips everything, invalid-rate rejection |
|
||||
| `llm_limit_record/middleware_test.go` | 7 | Skip-on-no-signal, skip-on-missing-attribution, RPC failure swallowed |
|
||||
|
||||
## Cross-references
|
||||
|
||||
- Sibling: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — SDK adapters
|
||||
+ SSE framer + pricing loader.
|
||||
+ SSE framer + pricing table and cost formula.
|
||||
- Path-routed providers (Vertex AI + Bedrock), `keyfile::` credential, GCP
|
||||
token minting, `/bedrock` prefix:
|
||||
[50-path-routed-providers.md](./50-path-routed-providers.md).
|
||||
|
||||
@@ -9,7 +9,7 @@ pricing table's per-provider cost formula is the highest-leverage place a
|
||||
small bug would silently mis-bill operators.
|
||||
|
||||
Sibling module: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md)
|
||||
— the 8 middlewares that consume this package's parsers + pricing loader.
|
||||
— the 8 middlewares that consume this package's parsers + pricing table.
|
||||
|
||||
---
|
||||
|
||||
@@ -24,8 +24,9 @@ proxy-framework dependencies:
|
||||
- `openai.go` / `anthropic.go` / `bedrock.go` — per-provider `Parser` impls.
|
||||
- `sse.go` — SSE scanner (`Scanner`, `Event`, `NewScanner`).
|
||||
- `errors.go` — sentinels callers branch on with `errors.Is`.
|
||||
- `pricing/` — embedded-default + hot-reload override table with
|
||||
symlink-safe Unix loader (build-tagged stub elsewhere).
|
||||
- `pricing/` — immutable pricing table + the per-surface cost formula. The
|
||||
rates themselves come from management inside `cost_meter`'s middleware
|
||||
config; this package holds no price list and reads no files.
|
||||
- `fixtures/` — captured request/response/stream bodies the tests replay.
|
||||
|
||||
The package carries zero proxy-framework dependencies so the same parsers can
|
||||
@@ -47,12 +48,9 @@ be reused later by a WASM adapter
|
||||
| `sse_test.go` | 175 | 12 tests; fixture replay + multiline + size limits |
|
||||
| `parser_test.go` | 53 | `Parsers()`, `DetectParser`, provider enum values |
|
||||
| `errors.go` | 31 | 6 sentinels: `Err{Unknown,Unsupported}Provider/Model`, `Err{NotLLM,Malformed}Response`, `ErrStreamingUnsupported`, `ErrMalformedRequest` |
|
||||
| `pricing/pricing.go` | 421 | `Loader`, `Table`, `Entry`; embedded defaults + atomic swap + mtime reload |
|
||||
| `pricing/pricing_unix.go` | 69 | `O_NOFOLLOW` + fstat-from-FD + 1 MiB cap |
|
||||
| `pricing/pricing_other.go` | 21 | Stub returning "not supported on this platform" |
|
||||
| `pricing/pricing_test.go` | 432 | 21 tests — symlink rejection, reload race, path traversal, oversize |
|
||||
| `pricing/defaults_pricing.yaml` | 85 | go:embed source of truth |
|
||||
| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream + pricing starter |
|
||||
| `pricing/pricing.go` | 234 | `Table`, `Entry`, `EntryJSON`, `Costs`; `NewTable`/`NewEntries` validation + `EntryCosts` formula. No I/O, no reload, no embedded rates |
|
||||
| `pricing/pricing_test.go` | 177 | 10 tests — provider-shape formulas, cached clamp, rate fallback, nil-safety, rate validation |
|
||||
| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream |
|
||||
|
||||
## Request body → parser dispatch
|
||||
|
||||
@@ -188,9 +186,11 @@ response leg, covering both Bedrock body shapes:
|
||||
`totalTokens`). `firstNonZero` folds the two naming conventions into one
|
||||
`Usage`; when Converse omits `totalTokens` the parser sums the buckets.
|
||||
|
||||
`ProviderName()` returns `"bedrock"` — its own `defaults_pricing.yaml` block,
|
||||
keyed by the **normalised** model id (region prefix + version suffix stripped by
|
||||
the request parser). `ParseResponse` returns `ErrStreamingUnsupported` for an
|
||||
`ProviderName()` returns `"bedrock"` — its own pricing surface in the table
|
||||
management ships, keyed by the **normalised** model id (region prefix + version
|
||||
suffix stripped by the request parser; management normalises its keys the same
|
||||
way at synth time so the two compare equal). `ParseResponse` returns
|
||||
`ErrStreamingUnsupported` for an
|
||||
AWS binary event-stream content-type (`application/vnd.amazon.eventstream`,
|
||||
`isAWSEventStream`) so the caller routes to the streaming accumulator instead.
|
||||
|
||||
@@ -205,11 +205,34 @@ response body. Streaming accumulators live in the middleware package
|
||||
([llm_response_parser/streaming.go](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go))
|
||||
but use `llm.NewScanner` so the framing contract stays here.
|
||||
|
||||
### Pricing catalog
|
||||
### Pricing table
|
||||
|
||||
`Table.Cost`
|
||||
([pricing.go:129–174](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
is the cost formula — most security-relevant math in this module:
|
||||
**Management is the sole pricing authority.** The proxy carries no embedded
|
||||
price list and reads no pricing file: the whole table arrives inside
|
||||
`cost_meter`'s `ConfigJSON` on the ordinary mapping push, and a price change
|
||||
is just another push — the chain rebuild constructs a fresh `Table`, so there
|
||||
is nothing to reload
|
||||
([pricing.go:1–7](../../../proxy/internal/llm/pricing/pricing.go)). The
|
||||
management side of the contract (catalog defaults, the operator's stored
|
||||
per-provider prices, and `AgentNetwork.PricingDefaultsFile`) is covered in the
|
||||
management-side module guide; `cost_meter`'s wire shape is in
|
||||
[31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md).
|
||||
|
||||
`EntryJSON`
|
||||
([pricing.go:36–45](../../../proxy/internal/llm/pricing/pricing.go)) is the
|
||||
management→proxy contract — five USD-per-1k rates under `input_per_1k`,
|
||||
`output_per_1k`, `cached_input_per_1k`, `cache_read_per_1k`,
|
||||
`cache_creation_per_1k`. Management's `pricing.Entry` marshals the identical
|
||||
names, and `EntryJSON`/`Entry` are field-identical so `NewEntries` converts by
|
||||
direct struct conversion rather than field-by-field copying (a new rate can't
|
||||
be silently dropped in transit).
|
||||
|
||||
`EntryCosts`
|
||||
([pricing.go:183–234](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
is the cost formula — most security-relevant math in this module. The
|
||||
**surface** (the `llm.provider` value the request parser stamped) selects the
|
||||
formula, never the tier the entry came from: a per-provider-record override on
|
||||
an Anthropic route still bills its cache buckets additively.
|
||||
|
||||
| Provider | Formula |
|
||||
|---|---|
|
||||
@@ -218,7 +241,7 @@ is the cost formula — most security-relevant math in this module:
|
||||
| default | `inTokens × InputPer1K + outTokens × OutputPer1K` |
|
||||
|
||||
`bedrock` shares the Anthropic additive-cache formula
|
||||
([pricing.go:172-174](../../../proxy/internal/llm/pricing/pricing.go)):
|
||||
([pricing.go:214–229](../../../proxy/internal/llm/pricing/pricing.go)):
|
||||
Anthropic-on-Bedrock reports the same additive cache buckets, while non-Anthropic
|
||||
Bedrock models (Nova, Llama) simply report zero in those buckets so cost reduces
|
||||
to `input + output`.
|
||||
@@ -226,15 +249,12 @@ to `input + output`.
|
||||
Each per-bucket rate falls back to `InputPer1K` when zero — operators opt in
|
||||
to discounts by setting the field.
|
||||
|
||||
`Loader`
|
||||
([pricing.go:212–268](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
overlays an optional `pricing.yaml` from data-dir on top of the go:embed
|
||||
defaults. Atomic pointer swap means readers never observe a partial update.
|
||||
The mtime-poll reloader (30s default cadence) keeps the previous table on
|
||||
parse failure so cost annotation never goes blank during a botched edit.
|
||||
|
||||
`defaults_pricing.yaml` is the source of truth for built-in pricing.
|
||||
Operator overrides only carry the entries they want to change.
|
||||
`Costs`
|
||||
([pricing.go:143–163](../../../proxy/internal/llm/pricing/pricing.go)) is the
|
||||
per-request split. The four per-bucket fields are the base; `TotalUSD` and
|
||||
`CacheUSD` are **derived** in `newCosts` so the aggregates can never drift from
|
||||
the breakdown. `InputUSD` is always the non-cached input bucket on both
|
||||
provider shapes, so input and cached-input never double-count.
|
||||
|
||||
## Public contracts
|
||||
|
||||
@@ -264,29 +284,38 @@ Order matters: `DetectFromURL` ties resolve by registration order.
|
||||
`ProviderBedrock = 3`. Numeric values are persisted in nothing today but treat
|
||||
them as wire-stable — new providers must take fresh numbers.
|
||||
|
||||
**`Pricing` lookup**
|
||||
([pricing.go:129](../../../proxy/internal/llm/pricing/pricing.go)):
|
||||
**`Pricing` construction + lookup**
|
||||
([pricing.go:60–130](../../../proxy/internal/llm/pricing/pricing.go)):
|
||||
|
||||
```go
|
||||
func NewEntries(raw map[string]map[string]EntryJSON) (map[string]map[string]Entry, error)
|
||||
func NewTable(raw map[string]map[string]EntryJSON) (*Table, error)
|
||||
|
||||
func (t *Table) Lookup(provider, model string) (Entry, bool)
|
||||
func (t *Table) Cost(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (float64, bool)
|
||||
func (t *Table) Costs(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (Costs, bool)
|
||||
func EntryCosts(entry Entry, surface string, inTokens, outTokens, cachedInput, cacheCreation int64) Costs
|
||||
```
|
||||
|
||||
Nil-safe: `t.Cost` on a nil receiver returns `(0, false)`
|
||||
([pricing.go:130–132](../../../proxy/internal/llm/pricing/pricing.go)).
|
||||
`ok=false` means provider or model is absent from the loaded table; the caller
|
||||
emits `cost.skipped=unknown_model`.
|
||||
`NewTable` is the surface-keyed defaults table; `NewEntries` returns the raw
|
||||
two-level map `cost_meter` uses for the per-provider-record tier (it looks up an
|
||||
`Entry` directly and calls `EntryCosts`, so it needs no `Table` wrapper). Both
|
||||
reject any non-finite or negative rate, so a corrupt config fails the chain
|
||||
build rather than mispricing silently. Nil input yields an empty,
|
||||
never-matching table.
|
||||
|
||||
Nil-safe: `t.Cost`/`t.Lookup` on a nil receiver returns `ok=false`
|
||||
([pricing.go:96–99](../../../proxy/internal/llm/pricing/pricing.go)).
|
||||
`ok=false` means the surface or model is absent from the table management sent;
|
||||
the caller emits `cost.skipped=unknown_model`.
|
||||
|
||||
## Invariants
|
||||
|
||||
1. **Cross-platform pricing build.** `pricing_unix.go` carries the only
|
||||
functional `loadPricing` (uses `syscall.O_NOFOLLOW` and `f.Stat()` on an
|
||||
open descriptor — both Unix-only). `pricing_other.go` is a build-tag
|
||||
fallback that returns `"not supported on this platform"`
|
||||
([pricing_other.go:14–16](../../../proxy/internal/llm/pricing/pricing_other.go)).
|
||||
The proxy is Linux-only in production today; a Windows port needs an
|
||||
equivalent path-as-handle implementation. Reviewers building on Windows
|
||||
should expect this surface to return an error at startup if an override
|
||||
file is configured.
|
||||
1. **The pricing package is pure and platform-independent.** No file I/O, no
|
||||
`//go:embed`, no goroutines, no build tags — the rates arrive as config, so
|
||||
there is nothing platform-specific left to port. Anything reintroducing a
|
||||
read-from-disk path here re-splits pricing authority between management and
|
||||
the proxy, which is exactly what this design removed.
|
||||
|
||||
2. **SSE scanner handles partial chunks.** A buffered prefix that doesn't end
|
||||
in `\n\n` still yields its accumulated event before `io.EOF`
|
||||
@@ -298,38 +327,45 @@ emits `cost.skipped=unknown_model`.
|
||||
usage rather than aborting
|
||||
([streaming.go:68–73, 144–150](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go)).
|
||||
|
||||
3. **`defaults_pricing.yaml` is the source of truth.** Compiled into the
|
||||
binary via `//go:embed`
|
||||
([pricing.go:29–30](../../../proxy/internal/llm/pricing/pricing.go)).
|
||||
`DefaultTable()` parses once and panics on parse failure
|
||||
([pricing.go:42–49](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
— by design: a broken embedded YAML must not ship to production.
|
||||
3. **Management is the only source of rates.** `Table` has no constructor that
|
||||
invents prices: the only way in is `NewTable`/`NewEntries` over the wire map
|
||||
management sent. A missing or empty `pricing` block therefore means *no
|
||||
prices at all* (`cost_meter` records `cost.skipped=unknown_model`, $0) —
|
||||
never a stale built-in fallback that would silently bill list price.
|
||||
|
||||
4. **Loader path validation.** `resolveMiddlewareDataPath`
|
||||
([pricing.go:370–394](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
rejects absolute paths, traversal segments, and basenames that fail
|
||||
`basenameRegex = ^[a-zA-Z0-9._-]+$`. The resolved path must remain
|
||||
inside `baseDir` even after `filepath.Clean`. Tests:
|
||||
`TestNewLoader_PathValidation`, `TestNewLoader_PathValidation_Extended`,
|
||||
`TestNewLoader_SymlinkOutsideBaseDirRejected`, `TestNewLoader_SymlinkRejected`.
|
||||
4. **Tables are immutable once built.** `Table.entries` is written only in
|
||||
`NewEntries` and never mutated afterwards, and `cost_meter`'s `perRecord`
|
||||
map is likewise build-time-only
|
||||
([pricing.go:47–52](../../../proxy/internal/llm/pricing/pricing.go)). This
|
||||
is what makes the no-reload design safe: a price change arrives as a mapping
|
||||
push that builds a new middleware instance over a new table, so concurrent
|
||||
readers can't observe a half-updated price list and no atomic swap or lock
|
||||
is needed on the hot path.
|
||||
|
||||
5. **Unix loader symlink safety.** `O_NOFOLLOW` on open, `f.Stat()` on the
|
||||
open descriptor (never re-stat by path), `info.Mode().IsRegular()` check,
|
||||
`io.LimitReader(f, maxPricingBytes+1)` with a final size assertion
|
||||
([pricing_unix.go:25–57](../../../proxy/internal/llm/pricing/pricing_unix.go)).
|
||||
A mid-read symlink swap is detected because the fstat is on the original
|
||||
fd. Test: `TestNewLoader_RejectsOversizedFile_FixesM4`.
|
||||
5. **Rate validation happens at chain-build time, not per request.**
|
||||
`NewEntries` rejects negative, NaN, and ±Inf rates field by field
|
||||
([pricing.go:60–83](../../../proxy/internal/llm/pricing/pricing.go)), naming
|
||||
the offending surface/model/field in the error. Management enforces the same
|
||||
constraints at its API boundary and in its YAML parser, so this is
|
||||
defense-in-depth — but it means a corrupt push fails loudly at build instead
|
||||
of producing negative costs on live traffic. Test:
|
||||
`TestNewTable_ValidatesRates`.
|
||||
|
||||
6. **`yaml.NewDecoder(...).KnownFields(true)`**
|
||||
([pricing.go:397–398](../../../proxy/internal/llm/pricing/pricing.go))
|
||||
rejects YAML files that carry fields not in the schema. A typo in an
|
||||
operator override file fails loud instead of silently zeroing rates.
|
||||
6. **New rates must be added to `Entry`, `EntryJSON`, *and* management's
|
||||
`pricing.Entry` together.** `NewEntries` converts by direct struct
|
||||
conversion `Entry(e)`
|
||||
([pricing.go:76–78](../../../proxy/internal/llm/pricing/pricing.go)), which
|
||||
only compiles while the two structs stay field-identical — so the proxy half
|
||||
is compiler-enforced. The management half is not: a rate added there but not
|
||||
here unmarshals into nothing and prices that bucket at `InputPer1K`.
|
||||
|
||||
## Things to scrutinise
|
||||
|
||||
**Correctness.** Verify OpenAI cached-prompt clamp at
|
||||
[pricing.go:147–149](../../../proxy/internal/llm/pricing/pricing.go)
|
||||
short-circuits before subtraction. `Anthropic.TotalTokens` sums all four
|
||||
**Correctness.** Verify the OpenAI cached-prompt clamp at
|
||||
[pricing.go:203–206](../../../proxy/internal/llm/pricing/pricing.go)
|
||||
short-circuits before subtraction. Negative token counts are clamped to zero up
|
||||
front ([pricing.go:186–197](../../../proxy/internal/llm/pricing/pricing.go)) so
|
||||
no formula can yield a negative cost. `Anthropic.TotalTokens` sums all four
|
||||
buckets (in + out + cache_read + cache_creation) — downstream dashboards
|
||||
need to know this differs from `input + output`.
|
||||
`OpenAIParser.ExtractPrompt` falls through `messages → input → prompt`; a
|
||||
@@ -338,22 +374,27 @@ noting).
|
||||
|
||||
**Security.** `Scanner.maxLine = 1 MiB`; a 2 MiB single-line `data:` event
|
||||
errors from `Scanner.Next` and both accumulators stop with partial usage.
|
||||
Pricing file 1 MiB cap is orders of magnitude larger than realistic. Confirm
|
||||
new schema additions are mirrored in both `pricingFile` and `Entry`;
|
||||
`KnownFields(true)` will reject silently-typo'd operator overrides
|
||||
otherwise.
|
||||
Pricing is no longer file-backed, so the loader's path-traversal / symlink /
|
||||
oversize surface is gone entirely — the config channel (an authenticated
|
||||
mapping push from management) is now the only way rates enter the proxy, and
|
||||
`NewEntries` is the validation boundary on it. A new rate added to management's
|
||||
`pricing.Entry` but not to `EntryJSON` here is the remaining silent-mispricing
|
||||
path (see invariant 6).
|
||||
|
||||
**Concurrency.** `Loader.table` is `atomic.Pointer[Table]`; readers never
|
||||
block or see a torn table. `Loader.Reload` is one goroutine, cancelled via
|
||||
context (`TestLoader_ReloadBackgroundLoopCancellation`). `DefaultTable()`
|
||||
uses `sync.Once`. Per-call `Scanner` instances mean no shared state across
|
||||
concurrent response-parser calls.
|
||||
**Concurrency.** Nothing in this package is shared mutable state: tables are
|
||||
built once and never written again, so `cost_meter`'s hot path is lock-free by
|
||||
construction rather than by atomic swap. Per-call `Scanner` instances mean no
|
||||
shared state across concurrent response-parser calls.
|
||||
|
||||
**Perf.** `Table.Cost` is two map lookups + multiplications, O(1).
|
||||
`Scanner.Next` is one `ReadString('\n')` per line. Pricing reload poll 30s.
|
||||
**Perf.** `Table.Cost` is two map lookups + multiplications, O(1); the
|
||||
per-provider-record tier adds at most one more lookup. `Scanner.Next` is one
|
||||
`ReadString('\n')` per line. No background goroutines and no per-request
|
||||
allocation of pricing state.
|
||||
|
||||
**Observability.** Reload failures count via `metric.Int64Counter` keyed
|
||||
`plugin`; warning log rate-limited at 5 min so a broken file doesn't flood.
|
||||
**Observability.** A config carrying no `pricing` block logs one warning at
|
||||
chain-build time (`cost_meter` factory) and then records
|
||||
`cost.skipped=unknown_model` per request, so an old-management deployment is
|
||||
visible in both logs and the access log rather than quietly reporting $0.
|
||||
Parser errors return sentinels — middleware uses `errors.Is` to map to the
|
||||
right `cost.skipped` reason.
|
||||
|
||||
@@ -365,7 +406,7 @@ right `cost.skipped` reason.
|
||||
| `openai_test.go` | 11 | Chat Completions + Responses API + legacy `prompt`; cached-tokens subset for both naming conventions; fixture replays |
|
||||
| `anthropic_test.go` | 7 | Messages + legacy `/v1/complete`; streaming REJECTED on `ParseResponse` (must use scanner); fixture replays |
|
||||
| `sse_test.go` | 12 | Fixture replay both providers; multiline `data:`; CRLF; comment skip; trailing-event-without-blank-line; oversize rejection |
|
||||
| `pricing/pricing_test.go` | 21 | Provider-shape switch; cached-rate fallback; cached-clamp; symlink rejection (target outside basedir + symlink to file); path validation matrix; oversize rejection; reload-keeps-previous-on-parse-error; mtime change detection; goroutine cancellation |
|
||||
| `pricing/pricing_test.go` | 10 | Provider-shape switch (surface selects the formula); cached-rate + cache-read/creation fallback to `InputPer1K`; cached-clamp; negative-token clamp; nil-receiver safety; rate validation (negative / NaN / Inf rejected); nil + empty table |
|
||||
|
||||
**Fixtures** ([proxy/internal/llm/fixtures/](../../../proxy/internal/llm/fixtures/)):
|
||||
`openai_chat_completion.json` (chat.completions with usage),
|
||||
@@ -373,14 +414,15 @@ right `cost.skipped` reason.
|
||||
`openai_stream.txt` (3 deltas + usage + `[DONE]`),
|
||||
`anthropic_messages.json` (Messages API non-streaming),
|
||||
`anthropic_stream.txt` (full 7-event sequence: message_start →
|
||||
content_block_{start,delta×2,stop} → message_delta (usage) → message_stop),
|
||||
`pricing.yaml` (realistic-pricing starter for operator overrides).
|
||||
content_block_{start,delta×2,stop} → message_delta (usage) → message_stop).
|
||||
No pricing fixture: the table is config-delivered, so pricing tests construct
|
||||
it in-process from a wire-shape map.
|
||||
|
||||
## Cross-references
|
||||
|
||||
- Sibling: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md)
|
||||
— the chain that calls `llm.Parsers()`, `llm.ParserByName`,
|
||||
`llm.NewScanner`, `pricing.NewLoader`.
|
||||
`llm.NewScanner`, `pricing.NewTable` / `pricing.NewEntries`.
|
||||
- Path-routed providers (Vertex AI + Bedrock), credential syntax, and the
|
||||
Bedrock AWS event-stream accumulator:
|
||||
[50-path-routed-providers.md](./50-path-routed-providers.md).
|
||||
|
||||
@@ -1,7 +1,7 @@
|
||||
# proxy/runtime — translate + serve + log
|
||||
|
||||
> **Risk level:** High — every config push from management is translated here, and the chain runs on every HTTP request to a synth target.
|
||||
> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareDataDir`, `MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path.
|
||||
> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path. Middleware config is entirely wire-delivered — no proxy-side data dir is involved, including for LLM pricing, which management ships inside `cost_meter`'s config.
|
||||
|
||||
## Module boundary
|
||||
|
||||
@@ -114,8 +114,7 @@ At **request time** the access-log middleware stamps `CapturedData`; the auth ch
|
||||
|
||||
## Public contracts touched
|
||||
|
||||
- `proxy.Server.MiddlewareDataDir` (string) — base dir for file-backed middleware config (server.go:238-241).
|
||||
- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:248-250).
|
||||
- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:249-253). There is no `MiddlewareDataDir`: no built-in middleware reads config from disk, so `builtin.FactoryContext` carries only the proxy-lifetime context, meter, logger, and management client.
|
||||
- `proxy/internal/proxy.WithMiddlewareManager(*middleware.Manager) Option` — new option on `NewReverseProxy`; nil keeps the fast path (reverseproxy.go:48-56).
|
||||
- `proxy/internal/proxy.PathTarget` adds `Middlewares`, `CaptureConfig`, `AgentNetwork`, `DisableAccessLog` (servicemapping.go:27-51), all zero-default.
|
||||
- `proxy/internal/proxy.CapturedData` adds `agentNetwork`, `suppressAccessLog`, `userGroupNames` behind `sync.RWMutex`; slices deep-copied (context.go:47-66, 183-258).
|
||||
|
||||
@@ -87,9 +87,9 @@ strips the `@version` suffix from the model, and maps the publisher to a parser
|
||||
surface via `vertexPublisherVendor`:
|
||||
|
||||
- `anthropic` → `llm.provider="anthropic"` → metered through the Anthropic
|
||||
parser, priced under the **`anthropic`** block in `defaults_pricing.yaml`
|
||||
(the parser emits the standard Anthropic provider label, so Vertex Claude
|
||||
reuses first-party Anthropic prices).
|
||||
parser, priced under the **`anthropic`** surface of the pricing table
|
||||
management ships (the parser emits the standard Anthropic provider label, so
|
||||
Vertex Claude reuses first-party Anthropic prices).
|
||||
- `openai` → `llm.provider="openai"` (reserved; not in the catalog lineup
|
||||
today).
|
||||
- anything else (notably `google` / Gemini) → empty vendor → **no parser**.
|
||||
@@ -104,8 +104,9 @@ is omitted from the catalog.
|
||||
|
||||
> Caveat: cross-region inference profiles in `eu` / `apac` carry a ~10% price
|
||||
> premium that the base per-token rates do **not** model — cost annotations for
|
||||
> those regions read low. Operators who need exact regional billing override
|
||||
> the affected entries in `pricing.yaml`.
|
||||
> those regions read low. Operators who need exact regional billing set the
|
||||
> affected models' prices on the provider record, or replace the default entries
|
||||
> via management's `AgentNetwork.PricingDefaultsFile`.
|
||||
|
||||
## AWS Bedrock (`bedrock_api`)
|
||||
|
||||
@@ -211,15 +212,19 @@ so a model-listing call can't be rewritten onto an upstream that would 404 it.
|
||||
## Catalog ↔ pricing cross-check
|
||||
|
||||
Catalog prices and context windows are cross-checked against LiteLLM's
|
||||
`model_prices_and_context_window.json`. The proxy's embedded
|
||||
`defaults_pricing.yaml` covers **every metered first-party model** the catalog
|
||||
enumerates — guarded by
|
||||
`TestDefaultTable_FirstPartyModelCoverage`
|
||||
([pricing/defaults_coverage_test.go](../../../proxy/internal/llm/pricing/defaults_coverage_test.go)),
|
||||
which fails if a catalog model has no embedded price. Bedrock entries are keyed
|
||||
by the **normalised** id the request parser emits (region prefix + version
|
||||
suffix stripped). Vertex Claude carries no Bedrock-style prefix, so it prices
|
||||
straight off the `anthropic` block.
|
||||
`model_prices_and_context_window.json`. The **catalog is the source of default
|
||||
prices**: management's `pricing.DefaultTable` folds every catalog provider's
|
||||
models into the surfaces that provider declares (`PricingSurfaces`), so coverage
|
||||
is structural rather than maintained in a parallel file
|
||||
([pricing/defaults.go](../../../management/internals/modules/agentnetwork/pricing/defaults.go)).
|
||||
`TestDefaultTable_CoversEveryCatalogModel` fails if a catalog model ends up
|
||||
unpriced, and `TestDefaultTable_NoConflictingContributions` fails if two
|
||||
providers contribute the same (surface, model) at different rates. Bedrock
|
||||
entries are keyed by the **normalised** id the request parser emits (region
|
||||
prefix + version suffix stripped) — management applies the same normalisation to
|
||||
per-provider prices at synth time, so the two keys compare equal. Vertex Claude
|
||||
carries no Bedrock-style prefix, so it prices straight off the `anthropic`
|
||||
surface.
|
||||
|
||||
## Things to scrutinise
|
||||
|
||||
@@ -232,16 +237,17 @@ operator-misconfigured Vertex provider and unmetered Gemini traffic; verify
|
||||
publishers).
|
||||
|
||||
**Correctness.** `normalizeBedrockModel` is the join between the wire id and the
|
||||
pricing key — a model that normalises to something not in `defaults_pricing.yaml`
|
||||
meters at `cost.skipped=unknown_model` rather than failing the request. The
|
||||
pricing key — a model that normalises to something absent from the shipped
|
||||
pricing table meters at `cost.skipped=unknown_model` rather than failing the
|
||||
request. The
|
||||
`/bedrock` prefix strip must run on both the parser side (so the model is
|
||||
extracted) and the router side (so the upstream path is native); a regression in
|
||||
either silently breaks the other.
|
||||
|
||||
**Metering caveats.** eu/apac cross-region Bedrock + Vertex profiles carry a
|
||||
~10% premium not modelled by base pricing — flagged in both the catalog comment
|
||||
and `defaults_pricing.yaml`. Operators needing exact regional billing override
|
||||
the relevant entries.
|
||||
~10% premium not modelled by base pricing — flagged in the catalog comment.
|
||||
Operators needing exact regional billing set per-provider prices on the model
|
||||
rows (or replace the default entries via `AgentNetwork.PricingDefaultsFile`).
|
||||
|
||||
## Cross-references
|
||||
|
||||
|
||||
@@ -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) })
|
||||
|
||||
Some files were not shown because too many files have changed in this diff Show More
Reference in New Issue
Block a user