Merge branch 'main' into client-local-metrics

# Conflicts:
#	client/internal/debug/debug.go

.github/workflows/pr-title-check.yml

@@ -16,8 +16,6 @@ jobs:
             const allowedTags = [
               'management',
               'client',
-              'android',
-              'ios',
               'signal',
               'proxy',
               'relay',

.github/workflows/release.yml

@@ -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

.goreleaser_ui.yaml

@@ -93,9 +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
+      - netbird
 
   - maintainer: Netbird <dev@netbird.io>
     description: Netbird client UI.
@@ -116,9 +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)
+      - netbird
 
     rpm:
       signature:

.goreleaser_ui_gtk3.yaml

@@ -1,131 +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
-
-  - 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)
-
-    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.
-  - 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
-    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
-    method: PUT

AGENTS.md

@@ -1,783 +0,0 @@
-# NetBird Agent Guidelines
-
-**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,
-**Signal** (`signal/`) brokers peer handshakes, **Relay** (`relay/`) carries
-traffic when a direct tunnel is impossible, and **Proxy** (`proxy/`) is the
-identity-aware proxy behind Agent Network.
-
-This file applies to the whole repository, and is the single source of truth for
-agent guidance here. `CLAUDE.md` is a one-line pointer to it — keep the guidance
-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)
-
-## STOP and ask the user before
-
-- **Opening a pull request for anything beyond a trivial fix, without an agreed
-  ticket.** Ask the user directly: *"Is there a discussion or issue for this
-  change?"* NetBird is discussion-first — community reports start in
-  [Discussions](https://github.com/netbirdio/netbird/discussions), DevRel
-  validates them, and only validated discussions become issues. A PR that
-  changes behavior with no linked issue may be closed on arrival. If there is no
-  ticket, offer to draft the discussion post **instead of** the PR, and wait for
-  the user's call. Only typos, broken links, documentation corrections, and
-  one-line fixes that already have an issue can skip this.
-- **Designing in any high-risk area** (see
-  [CONTRIBUTING.md](CONTRIBUTING.md#high-risk-areas)): public API and OpenAPI
-  schema, gRPC protos, behavior existing deployments would notice after an
-  upgrade, peer connectivity (ICE, NAT traversal, relay selection, WireGuard® or
-  Rosenpass key handling), client system integration (routing, firewall, DNS,
-  interface), authentication and authorization, CLI or service flags, config
-  file format, daemon IPC, store schema and migrations, or a new feature. The
-  design gets agreed in the ticket before code is written.
-- **Writing a store migration or changing a persisted model.** Migrations are
-  one-way in the field and both the GORM and pgx paths may need the change.
-- **Hand-editing generated code.** `*.pb.go`, `*.gen.go`, and mocks are outputs.
-  Edit the source (`.proto`, `openapi.yml`) and rerun the matching
-  `generate.sh`.
-- **Adding, removing, or bumping a dependency**, and never vendor a fork.
-- **Weakening a security control** — authentication, authorization, certificate
-  verification, privilege dropping, or peer identity checks — even when it is
-  the fastest way to make a test pass.
-- **Force-pushing to `main`**, force-pushing any branch that is already under
-  review, amending pushed commits, or bypassing hooks with `--no-verify`.
-
-## Quick reference
-
-```bash
-# Build
-go build ./...
-cd client && CGO_ENABLED=0 go build .        # agent
-cd management && go build .                  # management service
-cd signal && go build .                      # signal service
-
-# Verify (run before every push)
-go fmt ./...
-make lint            # golangci-lint on files changed vs origin/main (also the pre-push hook)
-make lint-all        # full-repository lint, matches CI
-make test-unit       # host-safe unit tests, -tags devcert, no sudo
-make test-privileged # privileged-tagged suite in a Docker container with NET_ADMIN
-make setup-hooks     # wire make lint into .githooks/pre-push
-
-# Narrow runs
-go test ./client/internal/dns/...
-go test -race -run TestPeerConn ./client/internal/peer/...
-PRIV_RUN=TestNftablesManager PRIV_PKGS=./client/firewall/nftables/... make test-privileged
-
-# Code generation (never hand-edit the output)
-./shared/management/http/api/generate.sh   # REST types from openapi.yml
-./shared/management/proto/generate.sh
-./shared/signal/proto/generate.sh
-./client/proto/generate.sh
-./flow/proto/generate.sh
-
-# Run locally (lab only, never on a machine you rely on)
-sudo ./client/netbird up --log-level debug --log-file console
-sudo ./client/netbird down                   # teardown: restores routing, firewall, DNS
-./signal/signal run --log-level debug --log-file console
-./management/management management --log-level debug --log-file console --config ./management.json
-```
-
-`netbird up` needs root and rewrites the host's routing table, firewall rules,
-DNS configuration, and WireGuard® interface. Run it only in a disposable test
-environment (a VM, container, or throwaway host) that you can rebuild, never on
-a workstation or server whose connectivity matters. Run `sudo netbird down`
-before you stop working, before rebuilding the binary, and on every failure
-path, so the host's networking state is restored instead of left half-applied.
-See [Pitfalls](#pitfalls) for why cleanup on every exit path matters.
-
-## Structure
-
-```text
-netbird/
-├── client/              NetBird agent
-│   ├── cmd/             agent CLI
-│   ├── internal/        agent business logic (engine, peer, dns, routemanager, ...)
-│   ├── server/          daemon for background execution
-│   ├── proto/           daemon gRPC protos
-│   ├── iface/           WireGuard® interface management
-│   ├── firewall/        nftables, iptables, pf, WFP, userspace backends
-│   ├── ssh/             built-in SSH server and client
-│   ├── ui/              desktop UI (Wails v3 + React)
-│   ├── android/, ios/   mobile bindings
-│   ├── wasm/            WebAssembly build
-│   └── mdm/, system/    MDM policy, host information
-├── management/          control plane
-│   └── server/          account, peer, groups, networks, posture, permissions,
-│                        settings, store, http (REST), idp, integrations, migration
-├── signal/              handshake broker (peer/, server/)
-├── relay/               relay service (protocol/, server/, healthcheck/)
-├── proxy/               identity-aware proxy (llm/, acme/, accesslog/, middleware/, tcp/, udp/)
-├── agent-network/       Agent Network overview
-├── shared/              imported by both agent and services
-│   ├── management/      proto/, client/, http/api (OpenAPI + generated types)
-│   ├── signal/          proto/, client/
-│   └── relay/, auth/, sshauth/, metrics/
-├── e2e/                 end-to-end suites and harness
-├── encryption/, dns/, route/, stun/, sharedsock/, util/, flow/
-├── infrastructure_files/  docker compose and getting-started templates
-└── release_files/       files packaged into releases
-```
-
-## Where to look
-
-| Task                        | Location                                                     |
-| --------------------------- | ------------------------------------------------------------ |
-| REST API / OpenAPI          | `shared/management/http/api/` + `management/server/http/`    |
-| Management gRPC protocol    | `shared/management/proto/`                                   |
-| Signal protocol             | `shared/signal/proto/`                                       |
-| Daemon IPC protocol         | `client/proto/`                                              |
-| Peer connection and NAT     | `client/internal/peer/`                                      |
-| Network map handling        | `client/internal/engine.go`, `shared/management/networkmap/` |
-| Routing                     | `client/internal/routemanager/`, `route/`                    |
-| Firewall backends           | `client/firewall/`                                           |
-| DNS                         | `client/internal/dns/`, `dns/`                               |
-| WireGuard® interface        | `client/iface/`                                              |
-| Persistence and migrations  | `management/server/store/`, `management/server/migration/`   |
-| IdP integrations            | `management/server/idp/`                                     |
-| Permissions model           | `management/server/permissions/`                             |
-| 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.
-   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
-   sentences with a period, starting with the identifier name.
-4. **Prefer private functions and constants.** Export only what a caller outside
-   the package genuinely needs.
-5. **Early returns and guard clauses.** Handle errors and edge cases first
-   instead of nesting `if`/`else` chains.
-6. **Split complex functions.** If a function trips a complexity warning, break
-   it into named helpers rather than silencing the warning.
-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.
-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.
-10. **Never hand-edit generated files.** Change the source and regenerate.
-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`:
-
-```go
-// Good
-if err := someCall(); err != nil {
-    return fmt.Errorf("context: %w", err)
-}
-
-// Bad - unnecessary split
-err := someCall()
-if err != nil {
-    return fmt.Errorf("context: %w", err)
-}
-```
-
-Use multiple assignment when the value is needed after the block:
-
-```go
-result, err := someCall()
-if err != nil {
-    return fmt.Errorf("context: %w", err)
-}
-```
-
-Add short, meaningful context, and **do not** start `fmt.Errorf` messages with
-obvious words like "failed to" or "error":
-
-```go
-// Good
-return fmt.Errorf("parse remote address: %w", err)
-return fmt.Errorf("listen on %s: %w", addr, err)
-
-// Bad
-return fmt.Errorf("failed to parse remote address: %w", err)
-return fmt.Errorf("error listening on %s: %w", addr, err)
-
-// "failed" is fine in log messages
-log.Debugf("failed to parse remote address: %v", err)
-```
-
-Skip the wrapping when a function only extracts or delegates and the wrap would
-add nothing:
-
-```go
-func parseAddr(addr string) (string, int, error) {
-    host, portStr, err := net.SplitHostPort(addr)
-    if err != nil {
-        return "", 0, err
-    }
-    // ...
-}
-```
-
-Log the errors you choose not to act on:
-
-- `log.Debugf()` for errors that do not affect program flow but help debugging.
-- `log.Tracef()` for very verbose errors that would otherwise spam logs.
-- **Never ignore** errors from writes, network sends, or critical cleanup.
-- 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
-when a hidden constraint or workaround would surprise a future reader. Never
-reference the current task, PR, or your own changes in a comment.
-
-```go
-// Bad - trailing comments explaining the obvious
-defer localConn.Close() // Close the connection
-if err != nil {         // Check if error occurred
-
-// Good
-defer localConn.Close()
-
-// Good - explains a non-obvious constraint
-// Use incremental checksum update per RFC 1624 for performance.
-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.
-
-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
-250 characters of prose, the code is doing too much. Fix the code:
-
-- **Extract a named function.** A well-named function replaces the comment: the
-  name says *what*, the body shows *how*, and the comment you no longer write
-  was the *what* anyway. Clean Code calls this "explain yourself in code".
-- **Extract a named constant or predicate.** `if isExpiredSetupKey(key)` needs
-  no comment; `if key.ExpiresAt.Before(now) && !key.Revoked && key.UsageLimit > 0`
-  does.
-- **Keep the surviving comment for the why** — the RFC, the kernel quirk, the
-  ordering constraint. That part is usually one or two lines.
-
-### Long switch and if/else chains
-
-A `switch` whose cases carry multi-line explanations is the usual place this
-budget is breached, and the comment is a symptom. In order of preference:
-
-1. **Extract each case body into a named function.** The case becomes one line,
-   the name carries the meaning, and the switch reads as a table of contents.
-2. **Replace the switch with a lookup table** — `map[Kind]handlerFunc` — when the
-   branches are uniform. Adding a case stops meaning editing a growing function.
-3. **Replace conditional with polymorphism** when branches vary by type and the
-   same switch shape starts appearing in more than one place. Clean Code's rule
-   of thumb: tolerate a switch statement if it appears **once**, is buried in a
-   factory that returns an interface, and no other switch dispatches on the same
-   type. A second switch over the same enum is the signal to introduce the
-   interface.
-
-Do not restructure a switch purely to satisfy the budget when the cases are one
-line each and self-evident — a flat, boring `switch` over an enum is fine and
-needs no comments at all.
-
-Explanatory comments in tests are welcome — they document the scenario being set
-up, and the 250-character budget does not apply to them.
-
-## Testing
-
-- **Unit tests** live beside the code as `_test.go`. `make test-unit` runs the
-  host-safe set with `-tags devcert` and no sudo.
-- **Privileged tests** carry the `privileged` build tag and mutate host
-  networking. They run through `make test-privileged`, inside a Docker container
-  with `NET_ADMIN`. Never bypass that harness by running them directly on the
-  host.
-- **End-to-end suites** live in `e2e/` with a shared harness.
-- **Test real behavior, not API existence.** Assert on the observable end state
-  a consumer would see — bytes that arrived, the packet after translation, the
-  row after the write — not merely that a method exists or returns an error.
-- **Avoid mocks for code we own.** Exercise the real store, manager, or
-  controller and assert what the caller actually receives.
-- **`require` for setup and preconditions, `assert` for the conditions under
-  test.** Use `require` whenever a later line would panic or be meaningless
-  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()
-require.NoError(t, err, "Test server setup must succeed")
-defer server.Close()
-
-result, err := client.DoOperation()
-assert.NoError(t, err)
-assert.Equal(t, expectedResult, result, "Result should match expected")
-```
-
-## Pitfalls
-
-- **The agent runs as root.** Anything touching routing, firewall, DNS, or the
-  interface can take a user's machine off the network. Prefer a reversible
-  change and make sure cleanup runs on every exit path.
-- **Management has two account loaders** (GORM and pgx). Adding a relation to an
-  account often means updating both, or it silently comes back empty in
-  production.
-- **`go test ./...` without `-tags devcert` skips tests** that need the
-  development certificate. Use `make test-unit`.
-- **`make lint` only checks the diff against `origin/main`.** CI runs
-  `make lint-all`; run it too before pushing a large change.
-- **Protos are consumed by released clients.** An old agent must keep working
-  against a new Management, so fields are added, never renumbered or removed.
-- **Windows requires the wintun driver**, and the daemon serves a named pipe
-  (`npipe://netbird`) rather than loopback TCP. Loopback TCP carries no caller
-  identity, so privileged operations are refused over it.
-
-## Commits, PRs, releases
-
-- **PR titles must start with a bracketed tag.** Before you propose a title,
-  **read [`.github/workflows/pr-title-check.yml`](.github/workflows/pr-title-check.yml)
-  and take the allowed tags from the `allowedTags` array in that file.** It is
-  the only source of truth, it changes as components are added, and the check
-  runs on every title edit — a tag that is not in that array is a red build. Do
-  not rely on a list memorized from anywhere else, including this file.
-
-  ```text
-  [client] Authorize daemon IPC callers by their local identity
-  [management,client] Add MDM policy support
-  ```
-
-  Multiple tags are comma-separated inside one pair of brackets. Match the tag
-  to the component you actually changed, not to the one you read the most.
-
-- **Use the repository's PR template.** Fill in
-  [`.github/pull_request_template.md`](.github/pull_request_template.md) rather
-  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.
-
-- **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;
-  the description exists to explain what the diff cannot say for itself. This is
-  well below what an agent will produce by default, so cut before you post.
-
-- **Body: why before what.** Lead with the problem and the reason for this
-  approach, then the shape of the change. No bullet list of files changed, no
-  per-function walkthrough, no restating the diff in prose, no trailing summary
-  section, no self-congratulatory closing line.
-
-- **No `Co-Authored-By` or tool-attribution trailers in the PR description**,
-  and none in commits either. Contributors own their contributions. Whatever
-  tooling produced the diff, the person opening the PR is its author: they have
-  read every line, they can explain why it works, they can answer review
-  questions without going back to a model, and they are accountable for the
-  consequences of merging it. Do not add a trailer, footer, or description line
-  that spreads that ownership onto a tool.
-
-- **Commit subjects follow the same `[scope] Subject` convention.** Keep the
-  subject short, and use the body for why before what. No bullet lists of files
-  changed.
-
-- **Push review fixes as separate commits.** The PR is squashed on merge, so
-  there is no reason to rewrite history mid-review; many small commits make the
-  re-review readable.
-
-- **Do not force-push a branch that is under review.** A force-push detaches
-  existing review comments from the lines they were written against, destroys
-  the "changes since your last review" diff a reviewer relies on, and discards
-  the CI history that showed which commit broke what. Add commits instead —
-  including for fixups and reverts. Force-push only when there is no
-  alternative: a rebase to clear a genuine conflict, or removing a secret or a
-  large binary that was committed by mistake. When you must, ask the user first,
-  then say so in a PR comment so reviewers know their anchors moved. Never
-  force-push `main`, and never force-push a branch you do not own.
-
-- **One PR, one purpose.** Split refactors out of fixes and fixes out of
-  features.
-
-- **Keep the PR small.** Size is the single strongest predictor of how long a PR
-  waits. Aim for **under ~400 changed lines across under ~20 files**; past
-  roughly **1000 lines or 50 files** a community PR is likely to be sent back to
-  be split, or left unreviewed until it is. Large PRs from outside the core team
-  may be blocked outright when the size was never agreed in the ticket —
-  reviewing a sprawling change against a privileged networking daemon is a
-  security risk in itself, not just a time cost.
-
-  Judge the size by hand-written code: exclude generated output, `go.sum`,
-  vendored files, and test fixtures from the estimate, but do not use their
-  presence to argue a 3000-line PR is small.
-
-  When a change genuinely cannot be small — a protocol migration, a
-  cross-component rename — agree the split in the ticket **before** writing
-  code, and land it as a sequence of PRs that each build, test, and make sense
-  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.
-
-## After you push: CI and review bots
-
-Opening the PR is not the end of the task. Watch the run, read what the bots
-say, and drive the PR to green before you report the work as done.
-
-```bash
-gh pr checks <pr>            --watch    # all checks, live
-gh run view <run-id> --log-failed       # only the failing steps
-gh pr view <pr> --comments              # bot and human review comments
-```
-
-**Never report a change as finished while checks are pending or red**, and never
-describe a red PR as passing. If you ran out of turn before CI finished, say
-which checks were still running.
-
-### The checks
-
-- **Go tests** — `golang-test-{linux,darwin,windows,freebsd}.yml`, sharded per
-  component. A failure in a component you did not touch is usually a real
-  interaction, not noise; read the log before assuming flake.
-- **golangci-lint** — `golangci-lint.yml` runs the full repository, while
-  `make lint` only checks your diff. A clean local lint does not guarantee green
-  CI on a large change.
-- **PR Title Check** — `pr-title-check.yml`, see above.
-- **Codecov** — uploaded from the Linux test workflow with per-component flags
-  (`unit,client`, `unit,management`, `unit,relay`, `unit,proxy`, `unit,signal`,
-  `integration,management`). Coverage on new code should not go backwards. Add
-  tests for the paths you introduced; do not adjust thresholds or exclude files
-  to clear the report.
-- **CodeRabbit** — configured in [`.coderabbit.yaml`](.coderabbit.yaml): `chill`
-  profile, auto-review on every non-draft PR, TypeScript/JavaScript/SVG paths
-  filtered out. Chat auto-reply is on, so `@coderabbitai` in a comment reaches
-  it.
-- **SonarCloud** — project `netbirdio_netbird`, quality gate on new code (bugs,
-  vulnerabilities, code smells, duplication, coverage).
-- **Snyk** — dependency and code scanning.
-
-Sonar and Snyk report as GitHub App checks rather than workflows in this
-repository, so their detail lives on the PR check, not in the Actions logs.
-
-### Handling bot findings
-
-- **Read every comment and act on it.** Either fix it, or reply with the reason
-  it does not apply. Do not bulk-resolve threads to clear the count, and do not
-  silently ignore a finding because the check is advisory.
-- **Bots are frequently wrong here.** NetBird has privileged, platform-specific,
-  and concurrency-heavy code that static analysis reads poorly. A confident
-  CodeRabbit or Sonar comment can still be nonsense. Verify the claim against
-  the code before you change anything — never edit correct code just to silence
-  a bot.
-- **Security findings get the opposite default.** For a Snyk or Sonar
-  vulnerability, or a CodeRabbit comment about authentication, authorization,
-  certificate verification, or key handling, assume it is real until you have
-  disproved it. Surface it to the user rather than dismissing it yourself.
-- **A new vulnerable dependency is a stop.** Bumping or replacing dependencies
-  needs the user's decision, as above.
-- **Never change a workflow, threshold, lint exclusion, or bot config to make a
-  check pass.** If a check is genuinely wrong, say so and let the user decide.
-- **Do not paper over flakes with blind re-runs.** Identify the failure first. If
-  it is a known flake, name it; if you cannot tell, report it as unresolved
-  rather than re-running until it goes green.
-
-## Discussion and support
-
-- Discussions: <https://github.com/netbirdio/netbird/discussions>
-- Slack: <https://docs.netbird.io/slack-url>
-- Docs: <https://docs.netbird.io>
-- Security: <https://github.com/netbirdio/netbird/security/policy> — never in public
-- Contribution process: [CONTRIBUTING.md](CONTRIBUTING.md)

CLAUDE.md

@@ -1 +0,0 @@
-See [AGENTS.md](AGENTS.md) for the agent guidelines in this repository.

CONTRIBUTING.md

@@ -66,41 +66,11 @@ Typical bug fixes, internal refactors, documentation updates, and tests do not
 need a design discussion, but should still be tied to an issue so the work is
 visible and nobody duplicates it.
 
-### Using AI coding agents
-
-We have no policy for or against using an AI agent to write NetBird code. That
-choice is yours, and we are not going to interrogate anyone about their tools.
-
-What we do have is a lot of incoming contributions that were plainly drafted with
-one, and enough experience reviewing them to see the same avoidable problems
-again and again: no ticket behind the change, a diff far too large to review, a
-description longer than the code it describes, an approach that was never going
-to be accepted, and an author who cannot answer questions about their own PR.
-None of that is caused by the tooling — it is what happens when a tool is pointed
-at a repository whose expectations it has never been told.
-
-So rather than a rule, there is a guide. [AGENTS.md](AGENTS.md) restates the
-expectations from this document in the form agents read automatically
-(`CLAUDE.md` points to it), so pointing your tool at the repository is usually
-enough. Among other things it tells the agent to ask you for the
-discussion or issue before drafting a PR, to keep the change small and
-single-purpose, to run the tests locally, to use this repository's PR template
-and title tags, and to write a description a reviewer can get through.
-
-The guardrails are the point, and they are the same ones we apply to everyone: an
-agreed ticket, a change you have actually run, a diff small enough to review with
-care, and an author who can explain it. Whatever wrote the diff, you are its
-author — you own every line you submit and the consequences of opening a PR with it.
-
-We may assess whether a contribution is maintainable and whether its merged code
-aligns with our security standards and design expectations.
-
 ## Contents
 
 - [Contributing to NetBird](#contributing-to-netbird)
     - [Ticket first, PR second](#ticket-first-pr-second)
         - [High-risk areas](#high-risk-areas)
-        - [Using AI coding agents](#using-ai-coding-agents)
     - [Contents](#contents)
     - [Code of conduct](#code-of-conduct)
     - [Directory structure](#directory-structure)

client/android/client.go

@@ -57,12 +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())
 }
@@ -82,8 +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
@@ -104,12 +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
 }
 
@@ -119,16 +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()
@@ -181,7 +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
@@ -189,7 +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()
@@ -230,7 +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)
 }
 
@@ -259,24 +240,6 @@ 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.
 func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (string, error) {

client/android/login.go

@@ -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)

client/android/login_test.go

@@ -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)
-	}
-}

client/android/profile_manager.go

@@ -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
 }

client/android/profile_state.go

@@ -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
-}

client/android/profile_state_test.go

@@ -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)
-}

client/android/session.go

@@ -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)

client/cmd/root.go

@@ -22,6 +22,7 @@ import (
 	"google.golang.org/grpc"
 
 	daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
+	"github.com/netbirdio/netbird/client/internal/localmetrics"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 )
 
@@ -30,6 +31,8 @@ const (
 	dnsResolverAddress       = "dns-resolver-address"
 	enableRosenpassFlag      = "enable-rosenpass"
 	rosenpassPermissiveFlag  = "rosenpass-permissive"
+	enableLocalMetricsFlag   = "enable-local-metrics"
+	localMetricsAddressFlag  = "local-metrics-address"
 	preSharedKeyFlag         = "preshared-key"
 	interfaceNameFlag        = "interface-name"
 	wireguardPortFlag        = "wireguard-port"
@@ -78,6 +81,8 @@ var (
 	updateSettingsDisabled bool
 	captureEnabled         bool
 	networksDisabled       bool
+	localMetricsEnabled    bool
+	localMetricsAddr       string
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -212,6 +217,8 @@ func init() {
 	upCmd.PersistentFlags().BoolVar(&rosenpassEnabled, enableRosenpassFlag, false, "[Experimental] Enable Rosenpass feature. If enabled, the connection will be post-quantum secured via Rosenpass.")
 	upCmd.PersistentFlags().BoolVar(&rosenpassPermissive, rosenpassPermissiveFlag, false, "[Experimental] Enable Rosenpass in permissive mode to allow this peer to accept WireGuard connections without requiring Rosenpass functionality from peers that do not have Rosenpass enabled.")
 	upCmd.PersistentFlags().BoolVar(&autoConnectDisabled, disableAutoConnectFlag, false, "Disables auto-connect feature. If enabled, then the client won't connect automatically when the service starts.")
+	upCmd.PersistentFlags().BoolVar(&localMetricsEnabled, enableLocalMetricsFlag, false, "Enables a local Prometheus /metrics endpoint exposing connection state (peers, latency, P2P vs relay).")
+	upCmd.PersistentFlags().StringVar(&localMetricsAddr, localMetricsAddressFlag, localmetrics.DefaultListenAddress, "Listen address of the local Prometheus /metrics endpoint.")
 	upCmd.PersistentFlags().BoolVar(&lazyConnEnabled, enableLazyConnectionFlag, false, "Deprecated: no longer used. Lazy connections are controlled by the server and the NB_LAZY_CONN environment variable.")
 	_ = upCmd.PersistentFlags().MarkDeprecated(enableLazyConnectionFlag, "no longer used; lazy connections are controlled by the server and the NB_LAZY_CONN environment variable")
 

client/cmd/up.go

@@ -499,6 +499,13 @@ func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, pro
 		req.DisableIpv6 = &disableIPv6
 	}
 
+	if cmd.Flag(enableLocalMetricsFlag).Changed {
+		req.EnableLocalMetrics = &localMetricsEnabled
+	}
+	if cmd.Flag(localMetricsAddressFlag).Changed {
+		req.LocalMetricsAddress = &localMetricsAddr
+	}
+
 	return &req
 }
 
@@ -616,6 +623,14 @@ func setupConfig(customDNSAddressConverted []byte, cmd *cobra.Command, configFil
 		ic.DisableIPv6 = &disableIPv6
 	}
 
+	if cmd.Flag(enableLocalMetricsFlag).Changed {
+		ic.LocalMetricsEnabled = &localMetricsEnabled
+	}
+
+	if cmd.Flag(localMetricsAddressFlag).Changed {
+		ic.LocalMetricsAddress = &localMetricsAddr
+	}
+
 	return &ic, nil
 }
 
@@ -678,6 +693,14 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte
 		loginRequest.DisableAutoConnect = &autoConnectDisabled
 	}
 
+	if cmd.Flag(enableLocalMetricsFlag).Changed {
+		loginRequest.EnableLocalMetrics = &localMetricsEnabled
+	}
+
+	if cmd.Flag(localMetricsAddressFlag).Changed {
+		loginRequest.LocalMetricsAddress = &localMetricsAddr
+	}
+
 	if cmd.Flag(interfaceNameFlag).Changed {
 		if err := parseInterfaceName(interfaceName); err != nil {
 			return nil, err

client/internal/connect.go

@@ -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,

client/internal/debug/debug.go

@@ -702,6 +702,8 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
 	configContent.WriteString(fmt.Sprintf("BlockLANAccess: %v\n", g.internalConfig.BlockLANAccess))
 	configContent.WriteString(fmt.Sprintf("BlockInbound: %v\n", g.internalConfig.BlockInbound))
 	configContent.WriteString(fmt.Sprintf("DisableIPv6: %v\n", g.internalConfig.DisableIPv6))
+	configContent.WriteString(fmt.Sprintf("LocalMetricsEnabled: %v\n", g.internalConfig.LocalMetricsEnabled))
+	configContent.WriteString(fmt.Sprintf("LocalMetricsAddress: %s\n", g.internalConfig.LocalMetricsAddress))
 	configContent.WriteString(fmt.Sprintf("SyncMessageVersion: %v\n", g.internalConfig.SyncMessageVersion))
 
 	if g.internalConfig.DisableNotifications != nil {

client/internal/dns/interface_index.go

@@ -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
-}

client/internal/dns/interface_index_test.go

@@ -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")
-	}
-}

client/internal/dns/notifier.go

@@ -51,5 +51,7 @@ func (n *notifier) notify() {
 		return
 	}
 
-	n.listener.OnNetworkChanged("")
+	go func(l listener.NetworkChangeListener) {
+		l.OnNetworkChanged("")
+	}(n.listener)
 }

client/internal/dns/server.go

@@ -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)

client/internal/dns/upstream_ios.go

@@ -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
+}

client/internal/engine.go

@@ -572,7 +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)
 	}
@@ -590,8 +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,
@@ -2095,6 +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 {
@@ -2129,7 +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() {
@@ -2142,7 +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
@@ -2154,7 +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,

client/internal/engine_tunsettings.go

@@ -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
-}

client/internal/localmetrics/localmetrics.go

@@ -0,0 +1,243 @@
+// Package localmetrics exposes client connection state as a local
+// Prometheus /metrics endpoint.
+package localmetrics
+
+import (
+	"context"
+	"errors"
+	"net"
+	"net/http"
+	"net/netip"
+	"sync"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+	"github.com/prometheus/client_golang/prometheus/promhttp"
+	dto "github.com/prometheus/client_model/go"
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+// DefaultListenAddress is used when local metrics are enabled without an explicit address.
+const DefaultListenAddress = "127.0.0.1:9191"
+
+const (
+	shutdownTimeout   = 3 * time.Second
+	readHeaderTimeout = 5 * time.Second
+	readTimeout       = 10 * time.Second
+	writeTimeout      = 30 * time.Second
+	idleTimeout       = time.Minute
+)
+
+// statusSource provides the connection state snapshots the collector reads on scrape.
+type statusSource interface {
+	GetPeerStates() []peer.State
+	GetManagementState() peer.ManagementState
+	GetSignalState() peer.SignalState
+}
+
+// GathererProvider returns the current client metrics gatherer, or nil when
+// no engine is running. It is called on every scrape.
+type GathererProvider func() prometheus.Gatherer
+
+// Manager runs the local /metrics HTTP endpoint according to the active
+// client configuration. Reconcile is safe to call on every config change.
+type Manager struct {
+	status        statusSource
+	clientMetrics GathererProvider
+
+	mu   sync.Mutex
+	srv  *http.Server
+	addr string
+}
+
+// NewManager creates a manager that serves metrics from status and
+// clientMetrics and shuts down when ctx is canceled.
+func NewManager(ctx context.Context, status statusSource, clientMetrics GathererProvider) *Manager {
+	m := &Manager{status: status, clientMetrics: clientMetrics}
+	go func() {
+		<-ctx.Done()
+		m.Stop()
+	}()
+	return m
+}
+
+// Reconcile starts, stops, or restarts the metrics endpoint to match the
+// desired state. An empty addr falls back to DefaultListenAddress.
+func (m *Manager) Reconcile(enabled bool, addr string) {
+	if addr == "" {
+		addr = DefaultListenAddress
+	}
+	warnIfNotLoopback(addr)
+
+	m.mu.Lock()
+	defer m.mu.Unlock()
+
+	if !enabled {
+		m.stop()
+		return
+	}
+	if m.srv != nil && m.addr == addr {
+		return
+	}
+	m.stop()
+
+	registry := prometheus.NewRegistry()
+	registry.MustRegister(newCollector(m.status))
+
+	gatherers := prometheus.Gatherers{registry, prometheus.GathererFunc(func() ([]*dto.MetricFamily, error) {
+		if m.clientMetrics == nil {
+			return nil, nil
+		}
+		g := m.clientMetrics()
+		if g == nil {
+			return nil, nil
+		}
+		return g.Gather()
+	})}
+
+	mux := http.NewServeMux()
+	mux.Handle("/metrics", promhttp.HandlerFor(gatherers, promhttp.HandlerOpts{}))
+
+	srv := &http.Server{
+		Addr:              addr,
+		Handler:           mux,
+		ReadHeaderTimeout: readHeaderTimeout,
+		ReadTimeout:       readTimeout,
+		WriteTimeout:      writeTimeout,
+		IdleTimeout:       idleTimeout,
+	}
+	m.srv = srv
+	m.addr = addr
+
+	log.Infof("serving local metrics on http://%s/metrics", addr)
+	go func() {
+		if err := srv.ListenAndServe(); err != nil && !errors.Is(err, http.ErrServerClosed) {
+			log.Errorf("failed to serve local metrics on %s: %v", addr, err)
+		}
+	}()
+}
+
+// Stop shuts down the metrics endpoint if it is running.
+func (m *Manager) Stop() {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.stop()
+}
+
+// stop shuts down the running server. Callers must hold m.mu.
+func (m *Manager) stop() {
+	if m.srv == nil {
+		return
+	}
+	ctx, cancel := context.WithTimeout(context.Background(), shutdownTimeout)
+	defer cancel()
+	if err := m.srv.Shutdown(ctx); err != nil {
+		log.Debugf("failed to shut down local metrics server: %v", err)
+	}
+	m.srv = nil
+	m.addr = ""
+}
+
+// collector converts status recorder snapshots into Prometheus metrics at scrape time.
+type collector struct {
+	status statusSource
+
+	managementConnected *prometheus.Desc
+	signalConnected     *prometheus.Desc
+	peersTotal          *prometheus.Desc
+	peersConnected      *prometheus.Desc
+	peerLatency         *prometheus.Desc
+}
+
+func newCollector(status statusSource) *collector {
+	return &collector{
+		status: status,
+		managementConnected: prometheus.NewDesc(
+			"netbird_management_connected",
+			"Whether the client is connected to the management service (1 connected, 0 disconnected).",
+			nil, nil,
+		),
+		signalConnected: prometheus.NewDesc(
+			"netbird_signal_connected",
+			"Whether the client is connected to the signal service (1 connected, 0 disconnected).",
+			nil, nil,
+		),
+		peersTotal: prometheus.NewDesc(
+			"netbird_peers",
+			"Number of peers known to this client.",
+			nil, nil,
+		),
+		peersConnected: prometheus.NewDesc(
+			"netbird_peers_connected",
+			"Number of connected peers by connection type.",
+			[]string{"connection_type"}, nil,
+		),
+		peerLatency: prometheus.NewDesc(
+			"netbird_peer_latency_seconds",
+			"Round-trip latency per directly connected peer; relayed connections have no latency measurement.",
+			[]string{"peer"}, nil,
+		),
+	}
+}
+
+// Describe implements prometheus.Collector.
+func (c *collector) Describe(ch chan<- *prometheus.Desc) {
+	ch <- c.managementConnected
+	ch <- c.signalConnected
+	ch <- c.peersTotal
+	ch <- c.peersConnected
+	ch <- c.peerLatency
+}
+
+// Collect implements prometheus.Collector.
+func (c *collector) Collect(ch chan<- prometheus.Metric) {
+	ch <- prometheus.MustNewConstMetric(c.managementConnected, prometheus.GaugeValue, boolToFloat(c.status.GetManagementState().Connected))
+	ch <- prometheus.MustNewConstMetric(c.signalConnected, prometheus.GaugeValue, boolToFloat(c.status.GetSignalState().Connected))
+
+	peers := c.status.GetPeerStates()
+	ch <- prometheus.MustNewConstMetric(c.peersTotal, prometheus.GaugeValue, float64(len(peers)))
+
+	var p2p, relayed float64
+	for _, p := range peers {
+		if p.ConnStatus != peer.StatusConnected {
+			continue
+		}
+		if p.Relayed {
+			relayed++
+			continue
+		}
+		p2p++
+
+		if latency := p.Latency.Seconds(); latency > 0 {
+			ch <- prometheus.MustNewConstMetric(c.peerLatency, prometheus.GaugeValue, latency, p.FQDN)
+		}
+	}
+	ch <- prometheus.MustNewConstMetric(c.peersConnected, prometheus.GaugeValue, p2p, "p2p")
+	ch <- prometheus.MustNewConstMetric(c.peersConnected, prometheus.GaugeValue, relayed, "relay")
+}
+
+func boolToFloat(b bool) float64 {
+	if b {
+		return 1
+	}
+	return 0
+}
+
+// warnIfNotLoopback logs a warning when the listen address cannot be
+// confirmed to be local-only, since the endpoint exposes peer and
+// connectivity details without authentication.
+func warnIfNotLoopback(addr string) {
+	host, _, err := net.SplitHostPort(addr)
+	if err != nil {
+		return
+	}
+	if host == "localhost" {
+		return
+	}
+	if ip, err := netip.ParseAddr(host); err == nil && ip.Unmap().IsLoopback() {
+		return
+	}
+	log.Warnf("local metrics endpoint listens on non-loopback address %s and is reachable from the network without authentication", addr)
+}

client/internal/localmetrics/localmetrics_test.go

@@ -0,0 +1,97 @@
+package localmetrics
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net"
+	"net/http"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus/testutil"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+type stubStatus struct {
+	peers      []peer.State
+	management peer.ManagementState
+	signal     peer.SignalState
+}
+
+func (s *stubStatus) GetPeerStates() []peer.State              { return s.peers }
+func (s *stubStatus) GetManagementState() peer.ManagementState { return s.management }
+func (s *stubStatus) GetSignalState() peer.SignalState         { return s.signal }
+
+func testStatus() *stubStatus {
+	return &stubStatus{
+		management: peer.ManagementState{Connected: true},
+		signal:     peer.SignalState{Connected: true},
+		peers: []peer.State{
+			{FQDN: "peer-a.netbird.cloud", IP: "100.90.0.1", ConnStatus: peer.StatusConnected, Relayed: false, Latency: 12 * time.Millisecond},
+			{FQDN: "peer-b.netbird.cloud", IP: "100.90.0.2", ConnStatus: peer.StatusConnected, Relayed: false, Latency: 36 * time.Millisecond},
+			{FQDN: "peer-c.netbird.cloud", IP: "100.90.0.3", ConnStatus: peer.StatusConnected, Relayed: true},
+			{FQDN: "peer-d.netbird.cloud", IP: "100.90.0.4", ConnStatus: peer.StatusIdle},
+		},
+	}
+}
+
+func TestCollector(t *testing.T) {
+	c := newCollector(testStatus())
+
+	expected := `
+# HELP netbird_management_connected Whether the client is connected to the management service (1 connected, 0 disconnected).
+# TYPE netbird_management_connected gauge
+netbird_management_connected 1
+# HELP netbird_peer_latency_seconds Round-trip latency per directly connected peer; relayed connections have no latency measurement.
+# TYPE netbird_peer_latency_seconds gauge
+netbird_peer_latency_seconds{peer="peer-a.netbird.cloud"} 0.012
+netbird_peer_latency_seconds{peer="peer-b.netbird.cloud"} 0.036
+# HELP netbird_peers Number of peers known to this client.
+# TYPE netbird_peers gauge
+netbird_peers 4
+# HELP netbird_peers_connected Number of connected peers by connection type.
+# TYPE netbird_peers_connected gauge
+netbird_peers_connected{connection_type="p2p"} 2
+netbird_peers_connected{connection_type="relay"} 1
+# HELP netbird_signal_connected Whether the client is connected to the signal service (1 connected, 0 disconnected).
+# TYPE netbird_signal_connected gauge
+netbird_signal_connected 1
+`
+	require.NoError(t, testutil.CollectAndCompare(c, strings.NewReader(expected)))
+}
+
+func TestServe(t *testing.T) {
+	ln, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err, "must find a free port")
+	addr := ln.Addr().String()
+	require.NoError(t, ln.Close())
+
+	ctx, cancel := context.WithCancel(context.Background())
+	t.Cleanup(cancel)
+	m := NewManager(ctx, testStatus(), nil)
+	m.Reconcile(true, addr)
+
+	var body string
+	require.Eventually(t, func() bool {
+		resp, err := http.Get(fmt.Sprintf("http://%s/metrics", addr))
+		if err != nil {
+			return false
+		}
+		defer resp.Body.Close()
+		data, err := io.ReadAll(resp.Body)
+		if err != nil || resp.StatusCode != http.StatusOK {
+			return false
+		}
+		body = string(data)
+		return true
+	}, 2*time.Second, 50*time.Millisecond, "metrics endpoint should come up")
+
+	assert.Contains(t, body, "netbird_peers 4")
+	assert.Contains(t, body, `netbird_peers_connected{connection_type="relay"} 1`)
+	assert.Contains(t, body, `netbird_peer_latency_seconds{peer="peer-a.netbird.cloud"} 0.012`)
+}

client/internal/metrics/influxdb.go

@@ -45,30 +45,13 @@ func (m *influxDBMetrics) RecordConnectionStages(
 	isReconnection bool,
 	timestamps ConnectionStageTimestamps,
 ) {
-	var signalingReceivedToConnection, connectionToWgHandshake, totalDuration float64
-
-	if !timestamps.SignalingReceived.IsZero() && !timestamps.ConnectionReady.IsZero() {
-		signalingReceivedToConnection = timestamps.ConnectionReady.Sub(timestamps.SignalingReceived).Seconds()
-	}
-
-	if !timestamps.ConnectionReady.IsZero() && !timestamps.WgHandshakeSuccess.IsZero() {
-		connectionToWgHandshake = timestamps.WgHandshakeSuccess.Sub(timestamps.ConnectionReady).Seconds()
-	}
-
-	if !timestamps.SignalingReceived.IsZero() && !timestamps.WgHandshakeSuccess.IsZero() {
-		totalDuration = timestamps.WgHandshakeSuccess.Sub(timestamps.SignalingReceived).Seconds()
-	}
-
-	attemptType := "initial"
-	if isReconnection {
-		attemptType = "reconnection"
-	}
+	signalingReceivedToConnection, connectionToWgHandshake, totalDuration := timestamps.Durations()
 
 	connTypeStr := connectionType.String()
 	tags := fmt.Sprintf("deployment_type=%s,connection_type=%s,attempt_type=%s,version=%s,os=%s,arch=%s,peer_id=%s,connection_pair_id=%s",
 		agentInfo.DeploymentType.String(),
 		connTypeStr,
-		attemptType,
+		attemptType(isReconnection),
 		agentInfo.Version,
 		agentInfo.OS,
 		agentInfo.Arch,
@@ -94,7 +77,7 @@ func (m *influxDBMetrics) RecordConnectionStages(
 	m.trimLocked()
 
 	log.Tracef("peer connection metrics [%s, %s, %s]: signalingReceived→connection: %.3fs, connection→wg_handshake: %.3fs, total: %.3fs",
-		agentInfo.DeploymentType.String(), connTypeStr, attemptType, signalingReceivedToConnection, connectionToWgHandshake, totalDuration)
+		agentInfo.DeploymentType.String(), connTypeStr, attemptType(isReconnection), signalingReceivedToConnection, connectionToWgHandshake, totalDuration)
 }
 
 func (m *influxDBMetrics) RecordSyncDuration(_ context.Context, agentInfo AgentInfo, duration time.Duration) {

client/internal/metrics/metrics.go

@@ -89,6 +89,21 @@ type ConnectionStageTimestamps struct {
 	WgHandshakeSuccess time.Time
 }
 
+// Durations returns the stage durations in seconds. A duration is zero when
+// either of its timestamps is missing.
+func (c ConnectionStageTimestamps) Durations() (signalingToConnection, connectionToWgHandshake, total float64) {
+	if !c.SignalingReceived.IsZero() && !c.ConnectionReady.IsZero() {
+		signalingToConnection = c.ConnectionReady.Sub(c.SignalingReceived).Seconds()
+	}
+	if !c.ConnectionReady.IsZero() && !c.WgHandshakeSuccess.IsZero() {
+		connectionToWgHandshake = c.WgHandshakeSuccess.Sub(c.ConnectionReady).Seconds()
+	}
+	if !c.SignalingReceived.IsZero() && !c.WgHandshakeSuccess.IsZero() {
+		total = c.WgHandshakeSuccess.Sub(c.SignalingReceived).Seconds()
+	}
+	return signalingToConnection, connectionToWgHandshake, total
+}
+
 // String returns a human-readable representation of the connection stage timestamps
 func (c ConnectionStageTimestamps) String() string {
 	return fmt.Sprintf("ConnectionStageTimestamps{SignalingReceived=%v, ConnectionReady=%v, WgHandshakeSuccess=%v}",
@@ -279,3 +294,11 @@ func (c *ClientMetrics) stopPushLocked() {
 	c.wg.Wait()
 	c.push.Store(nil)
 }
+
+// attemptType returns the metric label for an initial vs reconnection attempt.
+func attemptType(isReconnection bool) string {
+	if isReconnection {
+		return "reconnection"
+	}
+	return "initial"
+}

client/internal/metrics/metrics_default.go

@@ -2,10 +2,24 @@
 
 package metrics
 
+import "github.com/prometheus/client_golang/prometheus"
+
 // NewClientMetrics creates a new ClientMetrics instance
 func NewClientMetrics(agentInfo AgentInfo) *ClientMetrics {
 	return &ClientMetrics{
-		impl:      newInfluxDBMetrics(),
+		impl:      newPrometheusMetrics(newInfluxDBMetrics()),
 		agentInfo: agentInfo,
 	}
 }
+
+// PrometheusGatherer returns the registry with the mirrored Prometheus
+// metrics, or nil when unavailable.
+func (c *ClientMetrics) PrometheusGatherer() prometheus.Gatherer {
+	if c == nil {
+		return nil
+	}
+	if pm, ok := c.impl.(*prometheusMetrics); ok {
+		return pm.Gatherer()
+	}
+	return nil
+}

client/internal/metrics/prometheus.go

@@ -0,0 +1,119 @@
+//go:build !js
+
+package metrics
+
+import (
+	"context"
+	"io"
+	"strconv"
+	"time"
+
+	"github.com/prometheus/client_golang/prometheus"
+)
+
+// prometheusMetrics mirrors recorded client metrics into a Prometheus
+// registry for the local /metrics endpoint, then delegates to the wrapped
+// implementation. Export and Reset pass through untouched: Prometheus
+// metrics are cumulative and pull-based.
+type prometheusMetrics struct {
+	next     metricsImplementation
+	registry *prometheus.Registry
+
+	connectionStages  *prometheus.HistogramVec
+	syncDuration      prometheus.Histogram
+	syncPhaseDuration *prometheus.HistogramVec
+	loginDuration     *prometheus.HistogramVec
+}
+
+func newPrometheusMetrics(next metricsImplementation) *prometheusMetrics {
+	connectionBuckets := []float64{.05, .1, .25, .5, 1, 2.5, 5, 10, 30, 60}
+
+	m := &prometheusMetrics{
+		next:     next,
+		registry: prometheus.NewRegistry(),
+		connectionStages: prometheus.NewHistogramVec(prometheus.HistogramOpts{
+			Name:    "netbird_peer_connection_stage_duration_seconds",
+			Help:    "Duration of peer connection establishment stages.",
+			Buckets: connectionBuckets,
+		}, []string{"stage", "connection_type", "attempt_type"}),
+		syncDuration: prometheus.NewHistogram(prometheus.HistogramOpts{
+			Name:    "netbird_sync_duration_seconds",
+			Help:    "Duration of management sync message processing.",
+			Buckets: prometheus.DefBuckets,
+		}),
+		syncPhaseDuration: prometheus.NewHistogramVec(prometheus.HistogramOpts{
+			Name:    "netbird_sync_phase_duration_seconds",
+			Help:    "Duration of individual sync processing phases.",
+			Buckets: prometheus.DefBuckets,
+		}, []string{"phase"}),
+		loginDuration: prometheus.NewHistogramVec(prometheus.HistogramOpts{
+			Name:    "netbird_login_duration_seconds",
+			Help:    "Duration of logins to the management service.",
+			Buckets: prometheus.DefBuckets,
+		}, []string{"success"}),
+	}
+
+	m.registry.MustRegister(m.connectionStages, m.syncDuration, m.syncPhaseDuration, m.loginDuration)
+	return m
+}
+
+// Gatherer returns the registry holding the mirrored metrics.
+func (m *prometheusMetrics) Gatherer() prometheus.Gatherer {
+	return m.registry
+}
+
+// RecordConnectionStages implements metricsImplementation.
+func (m *prometheusMetrics) RecordConnectionStages(
+	ctx context.Context,
+	agentInfo AgentInfo,
+	connectionPairID string,
+	connectionType ConnectionType,
+	isReconnection bool,
+	timestamps ConnectionStageTimestamps,
+) {
+	attempt := attemptType(isReconnection)
+	connType := connectionType.String()
+
+	signalingToConnection, connectionToWgHandshake, total := timestamps.Durations()
+	if signalingToConnection > 0 {
+		m.connectionStages.WithLabelValues("signaling_to_connection", connType, attempt).Observe(signalingToConnection)
+	}
+	if connectionToWgHandshake > 0 {
+		m.connectionStages.WithLabelValues("connection_to_wg_handshake", connType, attempt).Observe(connectionToWgHandshake)
+	}
+	if total > 0 {
+		m.connectionStages.WithLabelValues("total", connType, attempt).Observe(total)
+	}
+
+	m.next.RecordConnectionStages(ctx, agentInfo, connectionPairID, connectionType, isReconnection, timestamps)
+}
+
+// RecordSyncDuration implements metricsImplementation.
+func (m *prometheusMetrics) RecordSyncDuration(ctx context.Context, agentInfo AgentInfo, duration time.Duration) {
+	m.syncDuration.Observe(duration.Seconds())
+	m.next.RecordSyncDuration(ctx, agentInfo, duration)
+}
+
+// RecordSyncPhase implements metricsImplementation.
+func (m *prometheusMetrics) RecordSyncPhase(ctx context.Context, agentInfo AgentInfo, phase string, duration time.Duration) {
+	m.syncPhaseDuration.WithLabelValues(phase).Observe(duration.Seconds())
+	m.next.RecordSyncPhase(ctx, agentInfo, phase, duration)
+}
+
+// RecordLoginDuration implements metricsImplementation.
+func (m *prometheusMetrics) RecordLoginDuration(ctx context.Context, agentInfo AgentInfo, duration time.Duration, success bool) {
+	m.loginDuration.WithLabelValues(strconv.FormatBool(success)).Observe(duration.Seconds())
+	m.next.RecordLoginDuration(ctx, agentInfo, duration, success)
+}
+
+// Export implements metricsImplementation by delegating to the wrapped
+// implementation; Prometheus metrics are pulled via the registry instead.
+func (m *prometheusMetrics) Export(w io.Writer) error {
+	return m.next.Export(w)
+}
+
+// Reset implements metricsImplementation by delegating to the wrapped
+// implementation; Prometheus metrics must not be cleared on push.
+func (m *prometheusMetrics) Reset() {
+	m.next.Reset()
+}

client/internal/peer/status.go

@@ -1167,6 +1167,18 @@ func (d *Status) GetResolvedDomainsStates() map[domain.Domain]ResolvedDomainInfo
 	return maps.Clone(d.resolvedDomainsStates)
 }
 
+// GetPeerStates returns a snapshot of all known peer states.
+func (d *Status) GetPeerStates() []State {
+	d.mux.RLock()
+	defer d.mux.RUnlock()
+
+	states := make([]State, 0, len(d.peers))
+	for _, state := range d.peers {
+		states = append(states, state)
+	}
+	return states
+}
+
 // GetFullStatus gets full status
 func (d *Status) GetFullStatus() FullStatus {
 	fullStatus := FullStatus{

client/internal/profilemanager/config.go

@@ -103,6 +103,9 @@ type ConfigInput struct {
 	DNSLabels domain.List
 
 	MTU *uint16
+
+	LocalMetricsEnabled *bool
+	LocalMetricsAddress *string
 }
 
 // Config Configuration type
@@ -144,6 +147,11 @@ type Config struct {
 
 	DNSLabels domain.List
 
+	// LocalMetricsEnabled enables the local Prometheus /metrics endpoint.
+	LocalMetricsEnabled bool
+	// LocalMetricsAddress is the listen address of the local /metrics endpoint.
+	LocalMetricsAddress string
+
 	// SSHKey is a private SSH key in a PEM format
 	SSHKey string
 
@@ -388,6 +396,18 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 		updated = true
 	}
 
+	if input.LocalMetricsEnabled != nil && *input.LocalMetricsEnabled != config.LocalMetricsEnabled {
+		log.Infof("switching local metrics to %t", *input.LocalMetricsEnabled)
+		config.LocalMetricsEnabled = *input.LocalMetricsEnabled
+		updated = true
+	}
+
+	if input.LocalMetricsAddress != nil && *input.LocalMetricsAddress != config.LocalMetricsAddress {
+		log.Infof("switching local metrics address to %s", *input.LocalMetricsAddress)
+		config.LocalMetricsAddress = *input.LocalMetricsAddress
+		updated = true
+	}
+
 	if input.NetworkMonitor != nil && (config.NetworkMonitor == nil || *input.NetworkMonitor != *config.NetworkMonitor) {
 		log.Infof("switching Network Monitor to %t", *input.NetworkMonitor)
 		config.NetworkMonitor = input.NetworkMonitor
@@ -718,6 +738,12 @@ func (config *Config) applyMDMPolicy(policy *mdm.Policy) {
 	applyBool(mdm.KeyDisableAutoConnect, func(v bool) { config.DisableAutoConnect = v })
 	applyBool(mdm.KeyRosenpassEnabled, func(v bool) { config.RosenpassEnabled = v })
 	applyBool(mdm.KeyRosenpassPermissive, func(v bool) { config.RosenpassPermissive = v })
+	applyBool(mdm.KeyEnableLocalMetrics, func(v bool) { config.LocalMetricsEnabled = v })
+
+	if v, ok := policy.GetString(mdm.KeyLocalMetricsAddress); ok {
+		config.LocalMetricsAddress = v
+		logApplied(mdm.KeyLocalMetricsAddress, v)
+	}
 
 	if v, ok := policy.GetInt(mdm.KeyWireguardPort); ok {
 		// REG_DWORD is 32-bit; UDP port range is 1-65535. Clamp at the

client/internal/profilemanager/config_mdm_test.go

@@ -130,6 +130,32 @@ func TestApply_MDMBoolKeysOverrideOnDiskValue(t *testing.T) {
 	assert.True(t, cfg.Policy().HasKey(mdm.KeyRosenpassEnabled))
 }
 
+func TestApply_MDMLocalMetrics(t *testing.T) {
+	tmp := filepath.Join(t.TempDir(), "config.json")
+
+	// Seed without MDM.
+	withMDMPolicy(t, mdm.NewPolicy(nil))
+	_, err := UpdateOrCreateConfig(ConfigInput{
+		ConfigPath:          tmp,
+		LocalMetricsEnabled: boolPtr(false),
+	})
+	require.NoError(t, err)
+
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyEnableLocalMetrics:  true,
+		mdm.KeyLocalMetricsAddress: "127.0.0.1:9292",
+	}))
+
+	cfg, err := UpdateOrCreateConfig(ConfigInput{ConfigPath: tmp})
+	require.NoError(t, err)
+	require.NotNil(t, cfg)
+
+	assert.True(t, cfg.LocalMetricsEnabled, "MDM override should flip on-disk false to true")
+	assert.Equal(t, "127.0.0.1:9292", cfg.LocalMetricsAddress)
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyEnableLocalMetrics))
+	assert.True(t, cfg.Policy().HasKey(mdm.KeyLocalMetricsAddress))
+}
+
 func TestApply_MDMLazyConnection(t *testing.T) {
 	cases := []struct {
 		name string

client/internal/profilemanager/state.go

@@ -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

client/internal/routemanager/dnsinterceptor/handler.go

@@ -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)

client/internal/routemanager/manager.go

@@ -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

client/internal/routemanager/mock.go

@@ -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
 }
 

client/internal/routemanager/notifier/notifier_android.go

@@ -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
 }

client/internal/routemanager/notifier/notifier_ios.go

@@ -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
 }
 

client/internal/routemanager/notifier/notifier_other.go

@@ -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
 }

client/internal/updater/installer/installer_run_darwin.go

@@ -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)
 

client/ios/NetBirdSDK/client.go

@@ -158,19 +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) {}

client/ios/NetBirdSDK/login.go

@@ -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 := ""

client/mdm/policy.go

@@ -47,6 +47,8 @@ const (
 	KeyRosenpassEnabled    = "rosenpassEnabled"
 	KeyRosenpassPermissive = "rosenpassPermissive"
 	KeyWireguardPort       = "wireguardPort"
+	KeyEnableLocalMetrics  = "enableLocalMetrics"
+	KeyLocalMetricsAddress = "localMetricsAddress"
 
 	// Split tunnel is modeled as a single conceptual policy with two
 	// registry/plist values. KeySplitTunnelMode is the discriminator

client/proto/daemon.pb.go

@@ -343,6 +343,8 @@ type LoginRequest struct {
 	DisableSSHAuth                *bool   `protobuf:"varint,38,opt,name=disableSSHAuth,proto3,oneof" json:"disableSSHAuth,omitempty"`
 	SshJWTCacheTTL                *int32  `protobuf:"varint,39,opt,name=sshJWTCacheTTL,proto3,oneof" json:"sshJWTCacheTTL,omitempty"`
 	DisableIpv6                   *bool   `protobuf:"varint,40,opt,name=disable_ipv6,json=disableIpv6,proto3,oneof" json:"disable_ipv6,omitempty"`
+	EnableLocalMetrics            *bool   `protobuf:"varint,41,opt,name=enable_local_metrics,json=enableLocalMetrics,proto3,oneof" json:"enable_local_metrics,omitempty"`
+	LocalMetricsAddress           *string `protobuf:"bytes,42,opt,name=local_metrics_address,json=localMetricsAddress,proto3,oneof" json:"local_metrics_address,omitempty"`
 	unknownFields                 protoimpl.UnknownFields
 	sizeCache                     protoimpl.SizeCache
 }
@@ -658,6 +660,20 @@ func (x *LoginRequest) GetDisableIpv6() bool {
 	return false
 }
 
+func (x *LoginRequest) GetEnableLocalMetrics() bool {
+	if x != nil && x.EnableLocalMetrics != nil {
+		return *x.EnableLocalMetrics
+	}
+	return false
+}
+
+func (x *LoginRequest) GetLocalMetricsAddress() string {
+	if x != nil && x.LocalMetricsAddress != nil {
+		return *x.LocalMetricsAddress
+	}
+	return ""
+}
+
 type LoginResponse struct {
 	state                   protoimpl.MessageState `protogen:"open.v1"`
 	NeedsSSOLogin           bool                   `protobuf:"varint,1,opt,name=needsSSOLogin,proto3" json:"needsSSOLogin,omitempty"`
@@ -4221,6 +4237,8 @@ type SetConfigRequest struct {
 	DisableSSHAuth                *bool                `protobuf:"varint,33,opt,name=disableSSHAuth,proto3,oneof" json:"disableSSHAuth,omitempty"`
 	SshJWTCacheTTL                *int32               `protobuf:"varint,34,opt,name=sshJWTCacheTTL,proto3,oneof" json:"sshJWTCacheTTL,omitempty"`
 	DisableIpv6                   *bool                `protobuf:"varint,35,opt,name=disable_ipv6,json=disableIpv6,proto3,oneof" json:"disable_ipv6,omitempty"`
+	EnableLocalMetrics            *bool                `protobuf:"varint,36,opt,name=enable_local_metrics,json=enableLocalMetrics,proto3,oneof" json:"enable_local_metrics,omitempty"`
+	LocalMetricsAddress           *string              `protobuf:"bytes,37,opt,name=local_metrics_address,json=localMetricsAddress,proto3,oneof" json:"local_metrics_address,omitempty"`
 	unknownFields                 protoimpl.UnknownFields
 	sizeCache                     protoimpl.SizeCache
 }
@@ -4500,6 +4518,20 @@ func (x *SetConfigRequest) GetDisableIpv6() bool {
 	return false
 }
 
+func (x *SetConfigRequest) GetEnableLocalMetrics() bool {
+	if x != nil && x.EnableLocalMetrics != nil {
+		return *x.EnableLocalMetrics
+	}
+	return false
+}
+
+func (x *SetConfigRequest) GetLocalMetricsAddress() string {
+	if x != nil && x.LocalMetricsAddress != nil {
+		return *x.LocalMetricsAddress
+	}
+	return ""
+}
+
 type SetConfigResponse struct {
 	state         protoimpl.MessageState `protogen:"open.v1"`
 	unknownFields protoimpl.UnknownFields
@@ -6998,7 +7030,7 @@ var File_daemon_proto protoreflect.FileDescriptor
 const file_daemon_proto_rawDesc = "" +
 	"\n" +
 	"\fdaemon.proto\x12\x06daemon\x1a google/protobuf/descriptor.proto\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x1egoogle/protobuf/duration.proto\"\x0e\n" +
-	"\fEmptyRequest\"\xef\x12\n" +
+	"\fEmptyRequest\"\x92\x14\n" +
 	"\fLoginRequest\x12\x1a\n" +
 	"\bsetupKey\x18\x01 \x01(\tR\bsetupKey\x12&\n" +
 	"\fpreSharedKey\x18\x02 \x01(\tB\x02\x18\x01R\fpreSharedKey\x12$\n" +
@@ -7043,7 +7075,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1denableSSHRemotePortForwarding\x18% \x01(\bH\x18R\x1denableSSHRemotePortForwarding\x88\x01\x01\x12+\n" +
 	"\x0edisableSSHAuth\x18& \x01(\bH\x19R\x0edisableSSHAuth\x88\x01\x01\x12+\n" +
 	"\x0esshJWTCacheTTL\x18' \x01(\x05H\x1aR\x0esshJWTCacheTTL\x88\x01\x01\x12&\n" +
-	"\fdisable_ipv6\x18( \x01(\bH\x1bR\vdisableIpv6\x88\x01\x01B\x13\n" +
+	"\fdisable_ipv6\x18( \x01(\bH\x1bR\vdisableIpv6\x88\x01\x01\x125\n" +
+	"\x14enable_local_metrics\x18) \x01(\bH\x1cR\x12enableLocalMetrics\x88\x01\x01\x127\n" +
+	"\x15local_metrics_address\x18* \x01(\tH\x1dR\x13localMetricsAddress\x88\x01\x01B\x13\n" +
 	"\x11_rosenpassEnabledB\x10\n" +
 	"\x0e_interfaceNameB\x10\n" +
 	"\x0e_wireguardPortB\x17\n" +
@@ -7071,7 +7105,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1e_enableSSHRemotePortForwardingB\x11\n" +
 	"\x0f_disableSSHAuthB\x11\n" +
 	"\x0f_sshJWTCacheTTLB\x0f\n" +
-	"\r_disable_ipv6\"\xb5\x01\n" +
+	"\r_disable_ipv6B\x17\n" +
+	"\x15_enable_local_metricsB\x18\n" +
+	"\x16_local_metrics_address\"\xb5\x01\n" +
 	"\rLoginResponse\x12$\n" +
 	"\rneedsSSOLogin\x18\x01 \x01(\bR\rneedsSSOLogin\x12\x1a\n" +
 	"\buserCode\x18\x02 \x01(\tR\buserCode\x12(\n" +
@@ -7365,7 +7401,7 @@ const file_daemon_proto_rawDesc = "" +
 	"\f_profileNameB\v\n" +
 	"\t_username\"'\n" +
 	"\x15SwitchProfileResponse\x12\x0e\n" +
-	"\x02id\x18\x01 \x01(\tR\x02id\"\x98\x11\n" +
+	"\x02id\x18\x01 \x01(\tR\x02id\"\xbb\x12\n" +
 	"\x10SetConfigRequest\x12\x1a\n" +
 	"\busername\x18\x01 \x01(\tR\busername\x12 \n" +
 	"\vprofileName\x18\x02 \x01(\tR\vprofileName\x12$\n" +
@@ -7405,7 +7441,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1denableSSHRemotePortForwarding\x18  \x01(\bH\x15R\x1denableSSHRemotePortForwarding\x88\x01\x01\x12+\n" +
 	"\x0edisableSSHAuth\x18! \x01(\bH\x16R\x0edisableSSHAuth\x88\x01\x01\x12+\n" +
 	"\x0esshJWTCacheTTL\x18\" \x01(\x05H\x17R\x0esshJWTCacheTTL\x88\x01\x01\x12&\n" +
-	"\fdisable_ipv6\x18# \x01(\bH\x18R\vdisableIpv6\x88\x01\x01B\x13\n" +
+	"\fdisable_ipv6\x18# \x01(\bH\x18R\vdisableIpv6\x88\x01\x01\x125\n" +
+	"\x14enable_local_metrics\x18$ \x01(\bH\x19R\x12enableLocalMetrics\x88\x01\x01\x127\n" +
+	"\x15local_metrics_address\x18% \x01(\tH\x1aR\x13localMetricsAddress\x88\x01\x01B\x13\n" +
 	"\x11_rosenpassEnabledB\x10\n" +
 	"\x0e_interfaceNameB\x10\n" +
 	"\x0e_wireguardPortB\x17\n" +
@@ -7430,7 +7468,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1e_enableSSHRemotePortForwardingB\x11\n" +
 	"\x0f_disableSSHAuthB\x11\n" +
 	"\x0f_sshJWTCacheTTLB\x0f\n" +
-	"\r_disable_ipv6\"\x13\n" +
+	"\r_disable_ipv6B\x17\n" +
+	"\x15_enable_local_metricsB\x18\n" +
+	"\x16_local_metrics_address\"\x13\n" +
 	"\x11SetConfigResponse\"Q\n" +
 	"\x11AddProfileRequest\x12\x1a\n" +
 	"\busername\x18\x01 \x01(\tR\busername\x12 \n" +

client/proto/daemon.proto

@@ -242,6 +242,9 @@ message LoginRequest {
   optional bool disableSSHAuth = 38;
   optional int32 sshJWTCacheTTL = 39;
   optional bool disable_ipv6 = 40;
+
+  optional bool enable_local_metrics = 41;
+  optional string local_metrics_address = 42;
 }
 
 message LoginResponse {
@@ -761,6 +764,9 @@ message SetConfigRequest {
   optional bool disableSSHAuth = 33;
   optional int32 sshJWTCacheTTL = 34;
   optional bool disable_ipv6 = 35;
+
+  optional bool enable_local_metrics = 36;
+  optional string local_metrics_address = 37;
 }
 
 message SetConfigResponse{}

client/server/login_outcome_test.go

@@ -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))
-}

client/server/mdm.go

@@ -301,6 +301,8 @@ func mdmManagedFieldConflicts(msg *proto.SetConfigRequest, policy *mdm.Policy) [
 		conflictBool(mdm.KeyDisableServerRoutes, msg.DisableServerRoutes),
 		conflictBool(mdm.KeyBlockInbound, msg.BlockInbound),
 		conflictInt64(mdm.KeyWireguardPort, msg.WireguardPort),
+		conflictBool(mdm.KeyEnableLocalMetrics, msg.EnableLocalMetrics),
+		conflictString(mdm.KeyLocalMetricsAddress, msg.GetLocalMetricsAddress()),
 	})
 }
 
@@ -346,7 +348,9 @@ func setConfigRequestHasConfigOverrides(msg *proto.SetConfigRequest) bool {
 		msg.EnableSSHLocalPortForwarding != nil ||
 		msg.EnableSSHRemotePortForwarding != nil ||
 		msg.DisableSSHAuth != nil ||
-		msg.SshJWTCacheTTL != nil
+		msg.SshJWTCacheTTL != nil ||
+		msg.EnableLocalMetrics != nil ||
+		msg.LocalMetricsAddress != nil
 }
 
 // loginRequestHasConfigOverrides reports whether the LoginRequest
@@ -381,7 +385,9 @@ func loginRequestHasConfigOverrides(msg *proto.LoginRequest) bool {
 		msg.BlockLanAccess != nil ||
 		msg.DisableNotifications != nil ||
 		len(msg.DnsLabels) > 0 || msg.CleanDNSLabels ||
-		msg.BlockInbound != nil
+		msg.BlockInbound != nil ||
+		msg.EnableLocalMetrics != nil ||
+		msg.LocalMetricsAddress != nil
 }
 
 // loginRequestMDMConflicts mirrors mdmManagedFieldConflicts but for the
@@ -422,6 +428,8 @@ func loginRequestMDMConflicts(msg *proto.LoginRequest, policy *mdm.Policy) []str
 		conflictBool(mdm.KeyDisableServerRoutes, msg.DisableServerRoutes),
 		conflictBool(mdm.KeyBlockInbound, msg.BlockInbound),
 		conflictInt64(mdm.KeyWireguardPort, msg.WireguardPort),
+		conflictBool(mdm.KeyEnableLocalMetrics, msg.EnableLocalMetrics),
+		conflictString(mdm.KeyLocalMetricsAddress, msg.GetLocalMetricsAddress()),
 	})
 }
 

client/server/server.go

@@ -23,6 +23,9 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/expose"
+	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/netbirdio/netbird/client/internal/localmetrics"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	sleephandler "github.com/netbirdio/netbird/client/internal/sleep/handler"
 	"github.com/netbirdio/netbird/client/mdm"
@@ -108,6 +111,7 @@ type Server struct {
 
 	statusRecorder *peer.Status
 	sessionWatcher *internal.SessionWatcher
+	localMetrics   *localmetrics.Manager
 
 	probeThrottle       *probeThrottle
 	persistSyncResponse bool
@@ -135,13 +139,6 @@ 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 {
@@ -171,9 +168,28 @@ func New(ctx context.Context, logFile string, configFile string, profilesDisable
 	s.sleepHandler = sleephandler.New(agent)
 	s.startSleepDetector()
 
+	s.localMetrics = localmetrics.NewManager(ctx, s.statusRecorder, s.clientMetricsGatherer)
+
 	return s
 }
 
+// clientMetricsGatherer returns the Prometheus gatherer of the running
+// engine's client metrics, or nil when no engine is running.
+func (s *Server) clientMetricsGatherer() prometheus.Gatherer {
+	s.mutex.Lock()
+	connectClient := s.connectClient
+	s.mutex.Unlock()
+
+	if connectClient == nil {
+		return nil
+	}
+	engine := connectClient.Engine()
+	if engine == nil {
+		return nil
+	}
+	return engine.GetClientMetrics().PrometheusGatherer()
+}
+
 func (s *Server) Start() error {
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
@@ -254,6 +270,7 @@ func (s *Server) Start() error {
 
 	s.statusRecorder.UpdateManagementAddress(config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(config.RosenpassEnabled, config.RosenpassPermissive)
+	s.localMetrics.Reconcile(config.LocalMetricsEnabled, config.LocalMetricsAddress)
 
 	if s.sessionWatcher == nil {
 		s.sessionWatcher = internal.NewSessionWatcher(s.rootCtx, s.statusRecorder)
@@ -377,34 +394,7 @@ 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 {
@@ -477,11 +467,18 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques
 		return nil, err
 	}
 
-	if _, err := profilemanager.UpdateConfig(config); err != nil {
+	updatedConf, err := profilemanager.UpdateConfig(config)
+	if err != nil {
 		log.Errorf("failed to update profile config: %v", err)
 		return nil, fmt.Errorf("failed to update profile config: %w", err)
 	}
 
+	if activeProf, err := s.profileManager.GetActiveProfileState(); err == nil {
+		if activePath, err := activeProf.FilePath(); err == nil && activePath == config.ConfigPath {
+			s.localMetrics.Reconcile(updatedConf.LocalMetricsEnabled, updatedConf.LocalMetricsAddress)
+		}
+	}
+
 	return &proto.SetConfigResponse{}, nil
 }
 
@@ -551,6 +548,8 @@ func (s *Server) setConfigInputFromRequest(msg *proto.SetConfigRequest) (profile
 
 	config.RosenpassEnabled = msg.RosenpassEnabled
 	config.RosenpassPermissive = msg.RosenpassPermissive
+	config.LocalMetricsEnabled = msg.EnableLocalMetrics
+	config.LocalMetricsAddress = msg.LocalMetricsAddress
 	config.DisableAutoConnect = msg.DisableAutoConnect
 	config.ServerSSHAllowed = msg.ServerSSHAllowed
 	config.NetworkMonitor = msg.NetworkMonitor
@@ -657,19 +656,7 @@ 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 +717,7 @@ 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 +872,7 @@ 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
 	}
@@ -1007,6 +994,7 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 
 	s.statusRecorder.UpdateManagementAddress(s.config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(s.config.RosenpassEnabled, s.config.RosenpassPermissive)
+	s.localMetrics.Reconcile(s.config.LocalMetricsEnabled, s.config.LocalMetricsAddress)
 
 	s.clientRunning = true
 	s.clientRunningChan = make(chan struct{})
@@ -1815,9 +1803,6 @@ 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 {

client/server/setconfig_mdm_test.go

@@ -136,6 +136,30 @@ func TestSetConfig_MDMReject_MultipleFields(t *testing.T) {
 	}, v.GetFields())
 }
 
+func TestSetConfig_MDMReject_LocalMetrics(t *testing.T) {
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyEnableLocalMetrics:  true,
+		mdm.KeyLocalMetricsAddress: "127.0.0.1:9191",
+	}))
+
+	s, ctx, profName, username, _ := setupServerWithProfile(t)
+
+	enabled := false
+	addr := "0.0.0.0:9999"
+	_, err := s.SetConfig(ctx, &proto.SetConfigRequest{
+		ProfileName:         profName,
+		Username:            username,
+		EnableLocalMetrics:  &enabled,
+		LocalMetricsAddress: &addr,
+	})
+
+	v := extractViolation(t, err)
+	assert.ElementsMatch(t, []string{
+		mdm.KeyEnableLocalMetrics,
+		mdm.KeyLocalMetricsAddress,
+	}, v.GetFields())
+}
+
 func TestSetConfig_MDMReject_AllOrNothing(t *testing.T) {
 	// MDM enforces ManagementURL only; user request touches both the
 	// enforced field AND a non-enforced field (RosenpassEnabled).

client/server/setconfig_test.go

@@ -76,6 +76,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	disableIPv6 := true
 	mtu := int64(1280)
 	sshJWTCacheTTL := int32(300)
+	enableLocalMetrics := true
+	localMetricsAddress := "127.0.0.1:9292"
 
 	req := &proto.SetConfigRequest{
 		ProfileName:          profName,
@@ -107,6 +109,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 		DnsRouteInterval:     durationpb.New(2 * time.Minute),
 		Mtu:                  &mtu,
 		SshJWTCacheTTL:       &sshJWTCacheTTL,
+		EnableLocalMetrics:   &enableLocalMetrics,
+		LocalMetricsAddress:  &localMetricsAddress,
 	}
 
 	_, err = s.SetConfig(ctx, req)
@@ -153,6 +157,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	require.Equal(t, uint16(mtu), cfg.MTU)
 	require.NotNil(t, cfg.SSHJWTCacheTTL)
 	require.Equal(t, int(sshJWTCacheTTL), *cfg.SSHJWTCacheTTL)
+	require.Equal(t, enableLocalMetrics, cfg.LocalMetricsEnabled)
+	require.Equal(t, localMetricsAddress, cfg.LocalMetricsAddress)
 
 	verifyAllFieldsCovered(t, req)
 }
@@ -205,6 +211,8 @@ func verifyAllFieldsCovered(t *testing.T, req *proto.SetConfigRequest) {
 		"EnableSSHRemotePortForwarding": true,
 		"DisableSSHAuth":                true,
 		"SshJWTCacheTTL":                true,
+		"EnableLocalMetrics":            true,
+		"LocalMetricsAddress":           true,
 	}
 
 	val := reflect.ValueOf(req).Elem()
@@ -264,6 +272,8 @@ func TestCLIFlags_MappedToSetConfig(t *testing.T) {
 		"enable-ssh-remote-port-forwarding": "EnableSSHRemotePortForwarding",
 		"disable-ssh-auth":                  "DisableSSHAuth",
 		"ssh-jwt-cache-ttl":                 "SshJWTCacheTTL",
+		"enable-local-metrics":              "EnableLocalMetrics",
+		"local-metrics-address":             "LocalMetricsAddress",
 	}
 
 	// SetConfigRequest fields that don't have CLI flags (settable only via UI or other means).

client/ui/build/linux/nfpm/nfpm.yaml

@@ -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

client/ui/frontend/src/hooks/useKeepConnectedOnQuit.ts

@@ -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 };
-};

client/ui/frontend/src/lib/connection.ts

@@ -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: "" },
     );
 

client/ui/frontend/src/modules/session/SessionExpirationDialog.tsx

@@ -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")}

client/ui/frontend/src/modules/settings/SettingsGeneral.tsx

@@ -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 && (

client/ui/i18n/locales/de/common.json

@@ -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"
     },

client/ui/i18n/locales/en/common.json

@@ -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."

client/ui/i18n/locales/es/common.json

@@ -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"
     },

client/ui/i18n/locales/fr/common.json

@@ -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"
     },

client/ui/i18n/locales/hu/common.json

@@ -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"
     },

client/ui/i18n/locales/it/common.json

@@ -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"
     },

client/ui/i18n/locales/ja/common.json

@@ -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"
     },

client/ui/i18n/locales/pt/common.json

@@ -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"
     },

client/ui/i18n/locales/ru/common.json

@@ -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"
     },

client/ui/i18n/locales/zh-CN/common.json

@@ -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"
     },

client/ui/main.go

@@ -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)

client/ui/notifier.go

@@ -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)
-}

client/ui/preferences/store.go

@@ -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)

client/ui/preferences/store_test.go

@@ -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)
 

client/ui/services/connection.go

@@ -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
 }
 

client/ui/services/cursor_linux.go

@@ -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
 }

client/ui/services/preferences.go

@@ -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)
-}

client/ui/services/profile.go

@@ -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

client/ui/tray.go

@@ -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()
 }

client/ui/tray_click_linux.go

@@ -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

client/ui/tray_notify.go

@@ -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)

client/ui/tray_session.go

@@ -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 {

client/ui/tray_update.go

@@ -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,

client/ui/xembed_host_gtk3_linux.go

@@ -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")
-}

client/ui/xembed_host_linux.go

@@ -1,4 +1,4 @@
-//go:build linux && !gtk3 && !(linux && 386)
+//go:build linux && !(linux && 386)
 
 package main
 

client/ui/xembed_tray_linux.c

@@ -1,5 +1,3 @@
-//go:build linux && !gtk3 && !(linux && 386)
-
 #include "xembed_tray_linux.h"
 
 #include <X11/Xatom.h>

e2e/agentnetwork/management_test.go

@@ -160,19 +160,8 @@ func TestSettingsRoundTrip(t *testing.T) {
 	assert.Equal(t, before.Cluster, flipped.Cluster, "cluster must be immutable across updates")
 	assert.Equal(t, before.Subdomain, flipped.Subdomain, "subdomain must be immutable across updates")
 
-	// A cluster different from the pinned one must be rejected; echoing the
-	// pinned one back is valid.
-	_, err = srv.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		Cluster:                ptr("attacker.cluster.invalid"),
-		EnableLogCollection:    before.EnableLogCollection,
-		EnablePromptCollection: before.EnablePromptCollection,
-		RedactPii:              before.RedactPii,
-	})
-	requireClientError(t, err)
-
 	// Restore the original toggles.
 	_, err = srv.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		Cluster:                ptr(before.Cluster),
 		EnableLogCollection:    before.EnableLogCollection,
 		EnablePromptCollection: before.EnablePromptCollection,
 		RedactPii:              before.RedactPii,

e2e/agentnetwork/settings_bootstrap_test.go

@@ -1,114 +0,0 @@
-//go:build e2e
-
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/e2e/harness"
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// harnessStartFresh boots a dedicated combined server with its own fresh
-// account and registers its teardown on t.
-func harnessStartFresh(ctx context.Context, t *testing.T) (*harness.Combined, error) {
-	t.Helper()
-	fresh, err := harness.StartCombined(ctx)
-	if err != nil {
-		return nil, err
-	}
-	t.Cleanup(func() { _ = fresh.Terminate(context.Background()) })
-	if _, err := fresh.Bootstrap(ctx); err != nil {
-		return nil, err
-	}
-	return fresh, nil
-}
-
-// TestSettingsBootstrapViaPut covers the settings-first bootstrap path on an
-// account that has never been bootstrapped: the GET reads as the defaults
-// with an empty cluster/subdomain/endpoint, a PUT without a cluster has
-// nothing to pin and fails, and a PUT carrying a cluster creates the row and
-// pins it immutably. The shared srv cannot provide that starting state (any
-// provider-creating test bootstraps it, and test order is deliberately not
-// relied on), so this boots a dedicated combined server — the image is
-// already built and cached by TestMain's StartCombined, so the extra cost is
-// one container start.
-func TestSettingsBootstrapViaPut(t *testing.T) {
-	ctx := context.Background()
-
-	fresh, err := harnessStartFresh(ctx, t)
-	require.NoError(t, err, "start dedicated combined server")
-
-	// Before agent-network bootstrap the settings read as the defaults, not
-	// as an error and not as a null body.
-	before, err := fresh.GetSettings(ctx)
-	require.NoError(t, err, "get settings on a fresh account must succeed")
-	assert.Empty(t, before.Cluster, "cluster must be empty before bootstrap")
-	assert.Empty(t, before.Subdomain, "subdomain must be empty before bootstrap")
-	assert.Empty(t, before.Endpoint, "endpoint must be empty before bootstrap, not a bare dot")
-	assert.True(t, before.EnableLogCollection, "defaults must show log collection on, matching bootstrap")
-	assert.False(t, before.EnablePromptCollection, "defaults must show prompt collection off")
-
-	// A PUT without a cluster has nothing to pin the account to.
-	_, err = fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		EnableLogCollection: true,
-	})
-	requireClientError(t, err)
-
-	// A PUT carrying a cluster bootstraps the account and applies the
-	// mutable fields from the same request. Every toggle is set away from
-	// its bootstrap default so each assertion can actually fail.
-	const cluster = "e2e.bootstrap.netbird.selfhosted"
-	bootstrapped, err := fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		Cluster:                ptr(cluster),
-		EnableLogCollection:    false,
-		EnablePromptCollection: true,
-		RedactPii:              true,
-	})
-	require.NoError(t, err, "bootstrap settings via PUT must succeed")
-	assert.Equal(t, cluster, bootstrapped.Cluster, "cluster must be pinned from the request")
-	require.NotEmpty(t, bootstrapped.Subdomain, "subdomain must be assigned at bootstrap")
-	assert.Equal(t, bootstrapped.Subdomain+"."+cluster, bootstrapped.Endpoint, "endpoint must combine subdomain and cluster")
-	assert.False(t, bootstrapped.EnableLogCollection, "log collection from the bootstrap request must override the default")
-	assert.True(t, bootstrapped.EnablePromptCollection, "prompt collection from the bootstrap request must apply")
-	assert.True(t, bootstrapped.RedactPii, "redact toggle from the bootstrap request must apply")
-
-	// The row is persisted: an independent read agrees on every field.
-	after, err := fresh.GetSettings(ctx)
-	require.NoError(t, err, "get settings after bootstrap must succeed")
-	assert.Equal(t, bootstrapped.Endpoint, after.Endpoint, "bootstrap must persist across reads")
-	assert.Equal(t, bootstrapped.EnableLogCollection, after.EnableLogCollection, "log collection must persist")
-	assert.Equal(t, bootstrapped.EnablePromptCollection, after.EnablePromptCollection, "prompt collection must persist")
-	assert.Equal(t, bootstrapped.RedactPii, after.RedactPii, "redact toggle must persist")
-
-	// Once bootstrapped, later updates may omit the cluster entirely.
-	persisted, err := fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		EnableLogCollection:    true,
-		EnablePromptCollection: false,
-		RedactPii:              true,
-	})
-	require.NoError(t, err, "post-bootstrap update without cluster must succeed")
-	assert.Equal(t, cluster, persisted.Cluster, "omitted cluster must keep the pinned value")
-	assert.True(t, persisted.EnableLogCollection, "post-bootstrap toggle must apply")
-	assert.False(t, persisted.EnablePromptCollection, "post-bootstrap toggle must apply")
-
-	// The cluster is immutable: a different value is rejected rather than
-	// silently ignored, and the rejected update must not disturb anything.
-	_, err = fresh.UpdateSettings(ctx, api.AgentNetworkSettingsRequest{
-		Cluster:             ptr("other.cluster.invalid"),
-		EnableLogCollection: false,
-	})
-	requireClientError(t, err)
-
-	final, err := fresh.GetSettings(ctx)
-	require.NoError(t, err, "get settings after the rejected cluster change must succeed")
-	assert.Equal(t, persisted.Cluster, final.Cluster, "rejected update must not change the cluster")
-	assert.Equal(t, persisted.Endpoint, final.Endpoint, "rejected update must not change the endpoint")
-	assert.Equal(t, persisted.EnableLogCollection, final.EnableLogCollection, "rejected update must not apply its toggles")
-	assert.Equal(t, persisted.EnablePromptCollection, final.EnablePromptCollection, "rejected update must not apply its toggles")
-	assert.Equal(t, persisted.RedactPii, final.RedactPii, "rejected update must not apply its toggles")
-}

go.mod

@@ -99,6 +99,7 @@ require (
 	github.com/pires/go-proxyproto v0.11.0
 	github.com/pkg/sftp v1.13.9
 	github.com/prometheus/client_golang v1.23.2
+	github.com/prometheus/client_model v0.6.2
 	github.com/quic-go/quic-go v0.55.0
 	github.com/redis/go-redis/v9 v9.7.3
 	github.com/rs/xid v1.3.0
@@ -114,7 +115,7 @@ require (
 	github.com/ti-mo/conntrack v0.5.1
 	github.com/ti-mo/netfilter v0.5.2
 	github.com/vmihailenco/msgpack/v5 v5.4.1
-	github.com/wailsapp/wails/v3 v3.0.0-beta.3
+	github.com/wailsapp/wails/v3 v3.0.0-alpha2.117
 	github.com/yusufpapurcu/wmi v1.2.4
 	github.com/zcalusic/sysinfo v1.1.3
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.67.0
@@ -250,6 +251,7 @@ require (
 	github.com/klauspost/cpuid/v2 v2.3.0 // indirect
 	github.com/koron/go-ssdp v0.0.4 // indirect
 	github.com/kr/fs v0.1.0 // indirect
+	github.com/kylelemons/godebug v1.1.0 // indirect
 	github.com/lib/pq v1.12.3 // indirect
 	github.com/libdns/libdns v0.2.2 // indirect
 	github.com/lufia/plan9stats v0.0.0-20240513124658-fba389f38bae // indirect
@@ -290,7 +292,6 @@ require (
 	github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 // indirect
 	github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 // indirect
 	github.com/pquerna/otp v1.5.0 // indirect
-	github.com/prometheus/client_model v0.6.2 // indirect
 	github.com/prometheus/common v0.67.5 // indirect
 	github.com/prometheus/otlptranslator v1.0.0 // indirect
 	github.com/prometheus/procfs v0.19.2 // indirect
@@ -339,5 +340,3 @@ replace github.com/dexidp/dex => github.com/netbirdio/dex v0.244.1-0.20260716205
 replace github.com/dexidp/dex/api/v2 => github.com/netbirdio/dex/api/v2 v2.0.0-20260512110716-8d70ad8647c1
 
 replace github.com/mailru/easyjson => github.com/netbirdio/easyjson v0.9.0
-
-replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4

go.sum

@@ -490,8 +490,6 @@ github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502 h1:3tHlFmhTdX9ax
 github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502/go.mod h1:CIMRFEJVL+0DS1a3Nx06NaMn4Dz63Ng6O7dl0qH0zVM=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45 h1:ujgviVYmx243Ksy7NdSwrdGPSRNE3pb8kEDSpH0QuAQ=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45/go.mod h1:5/sjFmLb8O96B5737VCqhHyGRzNFIaN/Bu7ZodXc3qQ=
-github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4 h1:UKztc3QjWvzU5DZk+uYaOWN0x62NSe/pkxuPvzqZIy4=
-github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4/go.mod h1:BzATbK71VFikMMMCo434wAi0QcaI03P+xeaWgDvQvjw=
 github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a h1:3CWK+yTvRKOcC0Q8VCTGy4l60TEb27CQVS7LkMxwjmw=
 github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw=
 github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=
@@ -662,6 +660,8 @@ github.com/vmihailenco/msgpack/v5 v5.4.1 h1:cQriyiUvjTwOHg8QZaPihLWeRAAVoCpE00IU
 github.com/vmihailenco/msgpack/v5 v5.4.1/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
 github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
 github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
+github.com/wailsapp/wails/v3 v3.0.0-alpha2.117 h1:udyjqPG3AIgkod5QDR/WblCkpV8R86BFPSrsWxSyt5Y=
+github.com/wailsapp/wails/v3 v3.0.0-alpha2.117/go.mod h1:74WH2FScMsgucZvHHvv7eOefDXCm/CjuIxqhhZgPhKg=
 github.com/wlynxg/anet v0.0.5 h1:J3VJGi1gvo0JwZ/P1/Yc/8p63SoW98B5dHkYDmpgvvU=
 github.com/wlynxg/anet v0.0.5/go.mod h1:eay5PRQr7fIVAMbTbchTnO9gG65Hg/uYGdc7mguHxoA=
 github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=

infrastructure_files/getting-started-enterprise.sh

@@ -11,10 +11,6 @@ SED_STRIP_PADDING='s/=//g'
 
 NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA"
 
-# Static IP for Traefik inside the compose bridge network. The management
-# server trusts X-Forwarded-* headers from this address only.
-TRAEFIK_IP="172.30.0.10"
-
 check_docker_compose() {
   if command -v docker-compose &> /dev/null; then
     echo "docker-compose"
@@ -84,7 +80,7 @@ read_nb_domain() {
   if ! check_domain_resolves "$value"; then
     echo "" > /dev/stderr
     echo "Warning: '$value' does not resolve via DNS from this host." > /dev/stderr
-    echo "Traefik will not be able to issue TLS certificates until it does." > /dev/stderr
+    echo "Caddy will not be able to issue TLS certificates until it does." > /dev/stderr
     local confirm=""
     echo -n "Continue anyway? [y/N]: " > /dev/stderr
     read -r confirm < /dev/tty
@@ -96,23 +92,6 @@ read_nb_domain() {
   echo "$value"
 }
 
-read_letsencrypt_email() {
-  if [[ -n "${NETBIRD_LETSENCRYPT_EMAIL:-}" ]]; then
-    echo "$NETBIRD_LETSENCRYPT_EMAIL"
-    return
-  fi
-  local value=""
-  echo "Enter your email for Let's Encrypt certificate notifications." > /dev/stderr
-  echo -n "Email address: " > /dev/stderr
-  read -r value < /dev/tty
-  if [[ -z "$value" ]]; then
-    echo "Email is required for Let's Encrypt." > /dev/stderr
-    read_letsencrypt_email
-    return
-  fi
-  echo "$value"
-}
-
 read_required() {
   local prompt="$1"
   local value=""
@@ -225,11 +204,11 @@ init_environment() {
   check_openssl
   DOCKER_COMPOSE_COMMAND=$(check_docker_compose)
 
-  if [[ -f .env ]] || [[ -f docker-compose.yml ]] || [[ -f config.yaml ]]; then
+  if [[ -f .env ]] || [[ -f docker-compose.yml ]] || [[ -f config.yaml ]] || [[ -f Caddyfile ]]; then
     echo "Generated files already exist in $(pwd)."
     echo "If you want to reinitialize the environment, please remove them first:"
     echo "  $DOCKER_COMPOSE_COMMAND down --volumes # removes all containers and volumes"
-    echo "  rm -f .env docker-compose.yml config.yaml"
+    echo "  rm -f .env docker-compose.yml Caddyfile config.yaml"
     echo "Be aware this will remove all data from the database."
     exit 1
   fi
@@ -251,9 +230,6 @@ init_environment() {
   echo ""
   NETBIRD_DOMAIN=$(read_nb_domain)
 
-  echo ""
-  NETBIRD_LETSENCRYPT_EMAIL=$(read_letsencrypt_email)
-
   echo ""
 
   NETBIRD_LICENSE_KEY=$(read_secret "Enter license key (input hidden)")
@@ -271,7 +247,6 @@ init_environment() {
   echo "Selected:"
   echo "  Traffic flow: ${NETBIRD_TRAFFIC_FLOW}"
   echo "  Domain:       ${NETBIRD_DOMAIN}"
-  echo "  ACME email:   ${NETBIRD_LETSENCRYPT_EMAIL}"
   echo ""
   echo "Rendering files into $(pwd) ..."
   install -m 600 /dev/null .env
@@ -281,6 +256,7 @@ init_environment() {
   if [[ -z "${NETBIRD_LICENSE_SERVER_BASE_URL:-}" ]]; then
     sed -i.bak '/NETBIRD_LICENSE_SERVER_BASE_URL/d' docker-compose.yml && rm -f docker-compose.yml.bak
   fi
+  render_caddyfile > Caddyfile
   install -m 600 /dev/null config.yaml
   render_config_yaml >> config.yaml
 
@@ -307,7 +283,7 @@ init_environment() {
   echo "All configuration and secrets are stored (mode 600) in $(pwd)/.env"
   echo ""
   echo "Tail logs:"
-  echo "  cd $(pwd) && $DOCKER_COMPOSE_COMMAND logs -f netbird-server traefik"
+  echo "  cd $(pwd) && $DOCKER_COMPOSE_COMMAND logs -f netbird-server caddy"
 }
 
 # ------------------------------------------------------------------
@@ -330,11 +306,6 @@ NETBIRD_TRAFFIC_FLOW_ENABLED=${NETBIRD_TRAFFIC_FLOW}
 # Domain
 NETBIRD_DOMAIN=${NETBIRD_DOMAIN}
 
-# Reverse proxy (Traefik)
-NETBIRD_LETSENCRYPT_EMAIL=${NETBIRD_LETSENCRYPT_EMAIL}
-NETBIRD_TRAEFIK_TAG=${NETBIRD_TRAEFIK_TAG:-v3.6}
-NETBIRD_TRAEFIK_IP=${TRAEFIK_IP}
-
 # Image tags. Default to "latest"
 NETBIRD_DASHBOARD_TAG=${NETBIRD_DASHBOARD_TAG:-latest}
 NETBIRD_SERVER_TAG=${NETBIRD_SERVER_TAG:-latest}
@@ -407,78 +378,26 @@ EOF
 
 render_compose_common() {
   cat <<'EOF'
-  # Reverse proxy with automatic TLS via Let's Encrypt. Routes are declared as
-  # labels on the services below and picked up through the Docker provider.
-  traefik:
+  caddy:
     <<: *default
-    image: traefik:${NETBIRD_TRAEFIK_TAG}
-    container_name: netbird-traefik
-    networks:
-      netbird:
-        ipv4_address: ${NETBIRD_TRAEFIK_IP}
-    command:
-      # Logging
-      - "--log.level=INFO"
-      - "--accesslog=true"
-      # Docker provider
-      - "--providers.docker=true"
-      - "--providers.docker.exposedbydefault=false"
-      - "--providers.docker.network=netbird"
-      # Entrypoints
-      - "--entrypoints.web.address=:80"
-      - "--entrypoints.websecure.address=:443"
-      - "--entrypoints.websecure.allowACMEByPass=true"
-      # readTimeout bounds the whole request, and gRPC streams / relay WebSockets
-      # never end one; idleTimeout would close the keep-alive connection they
-      # are reused over. Entrypoint-wide is the only scope Traefik offers here.
-      # writeTimeout is left alone: it already defaults to 0.
-      - "--entrypoints.websecure.transport.respondingTimeouts.readTimeout=0"
-      - "--entrypoints.websecure.transport.respondingTimeouts.idleTimeout=0"
-      # HTTP to HTTPS redirect
-      - "--entrypoints.web.http.redirections.entrypoint.to=websecure"
-      - "--entrypoints.web.http.redirections.entrypoint.scheme=https"
-      # Let's Encrypt ACME
-      - "--certificatesresolvers.letsencrypt.acme.email=${NETBIRD_LETSENCRYPT_EMAIL}"
-      - "--certificatesresolvers.letsencrypt.acme.storage=/letsencrypt/acme.json"
-      - "--certificatesresolvers.letsencrypt.acme.tlschallenge=true"
+    image: caddy:2
+    container_name: netbird-caddy
+    networks: [netbird]
+    environment:
+      - CADDY_SECURE_DOMAIN=${NETBIRD_DOMAIN}
     ports:
       - '443:443'
+      - '443:443/udp'
       - '80:80'
     volumes:
-      - /var/run/docker.sock:/var/run/docker.sock:ro
-      - netbird_traefik_letsencrypt:/letsencrypt
-    labels:
-      - traefik.enable=true
-      # Shared security headers, referenced by every NetBird router below. A
-      # label-declared middleware only exists while its container runs, so this
-      # lives on Traefik itself: declaring it on an app container would drop
-      # every router referencing it whenever that container restarts.
-      - traefik.http.middlewares.nb-security.headers.stsSeconds=3600
-      - traefik.http.middlewares.nb-security.headers.stsIncludeSubdomains=true
-      - traefik.http.middlewares.nb-security.headers.contentTypeNosniff=true
-      - traefik.http.middlewares.nb-security.headers.browserXssFilter=true
-      - traefik.http.middlewares.nb-security.headers.referrerPolicy=strict-origin-when-cross-origin
-      - traefik.http.middlewares.nb-security.headers.customResponseHeaders.X-Frame-Options=SAMEORIGIN
-      # Empty value strips the header. Only the dashboard's nginx sets one; the
-      # server emits none. Do not quote it — "" would send a literal Server: "".
-      - traefik.http.middlewares.nb-security.headers.customResponseHeaders.Server=
+      - netbird_caddy_data:/data
+      - ./Caddyfile:/etc/caddy/Caddyfile
 
   dashboard:
     <<: *default
     image: ghcr.io/netbirdio/dashboard-cloud:${NETBIRD_DASHBOARD_TAG}
     container_name: netbird-dashboard
     networks: [netbird]
-    labels:
-      - traefik.enable=true
-      # Dashboard catch-all: lowest priority so every route below wins
-      - traefik.http.routers.netbird-dashboard.rule=Host(`${NETBIRD_DOMAIN}`)
-      - traefik.http.routers.netbird-dashboard.entrypoints=websecure
-      - traefik.http.routers.netbird-dashboard.tls=true
-      - traefik.http.routers.netbird-dashboard.tls.certresolver=letsencrypt
-      - traefik.http.routers.netbird-dashboard.middlewares=nb-security@docker
-      - traefik.http.routers.netbird-dashboard.service=dashboard
-      - traefik.http.routers.netbird-dashboard.priority=1
-      - traefik.http.services.dashboard.loadbalancer.server.port=80
     environment:
       - NETBIRD_MGMT_API_ENDPOINT=https://${NETBIRD_DOMAIN}
       - NETBIRD_MGMT_GRPC_API_ENDPOINT=https://${NETBIRD_DOMAIN}
@@ -516,28 +435,6 @@ render_compose_server() {
       - netbird_data:/var/lib/netbird
       - ./config.yaml:/etc/netbird/config.yaml
     command: ["--config", "/etc/netbird/config.yaml"]
-    labels:
-      - traefik.enable=true
-      # Signal + Management gRPC (needs an h2c backend for HTTP/2 cleartext)
-      - traefik.http.routers.netbird-grpc.rule=Host(`${NETBIRD_DOMAIN}`) && (PathPrefix(`/signalexchange.SignalExchange/`) || PathPrefix(`/management.ManagementService/`) || PathPrefix(`/management.ProxyService/`))
-      - traefik.http.routers.netbird-grpc.entrypoints=websecure
-      - traefik.http.routers.netbird-grpc.tls=true
-      - traefik.http.routers.netbird-grpc.tls.certresolver=letsencrypt
-      - traefik.http.routers.netbird-grpc.middlewares=nb-security@docker
-      - traefik.http.routers.netbird-grpc.service=netbird-server-h2c
-      - traefik.http.routers.netbird-grpc.priority=100
-      # Relay WebSocket, management API, and the embedded IdP
-      - traefik.http.routers.netbird-backend.rule=Host(`${NETBIRD_DOMAIN}`) && (PathPrefix(`/relay`) || PathPrefix(`/ws-proxy/`) || PathPrefix(`/api`) || PathPrefix(`/oauth2`))
-      - traefik.http.routers.netbird-backend.entrypoints=websecure
-      - traefik.http.routers.netbird-backend.tls=true
-      - traefik.http.routers.netbird-backend.tls.certresolver=letsencrypt
-      - traefik.http.routers.netbird-backend.middlewares=nb-security@docker
-      - traefik.http.routers.netbird-backend.service=netbird-server
-      - traefik.http.routers.netbird-backend.priority=100
-      # Services
-      - traefik.http.services.netbird-server.loadbalancer.server.port=80
-      - traefik.http.services.netbird-server-h2c.loadbalancer.server.port=80
-      - traefik.http.services.netbird-server-h2c.loadbalancer.server.scheme=h2c
     environment:
       - NB_LICENSE_KEY=${NETBIRD_LICENSE_KEY}
       - NETBIRD_LICENSE_SERVER_BASE_URL=${NETBIRD_LICENSE_SERVER_BASE_URL}
@@ -600,18 +497,6 @@ render_compose_flow() {
       - NB_FLOW_NATS_ENDPOINTS=nats://nats:4222
       - NB_FLOW_NATS_STREAM=traffic-events
       - NB_FLOW_AUTH_SECRET=${NETBIRD_RELAY_AUTH_SECRET}
-    labels:
-      - traefik.enable=true
-      # Flow receiver gRPC (h2c backend)
-      - traefik.http.routers.netbird-flow.rule=Host(`${NETBIRD_DOMAIN}`) && PathPrefix(`/flow.FlowService/`)
-      - traefik.http.routers.netbird-flow.entrypoints=websecure
-      - traefik.http.routers.netbird-flow.tls=true
-      - traefik.http.routers.netbird-flow.tls.certresolver=letsencrypt
-      - traefik.http.routers.netbird-flow.middlewares=nb-security@docker
-      - traefik.http.routers.netbird-flow.service=netbird-flow-h2c
-      - traefik.http.routers.netbird-flow.priority=100
-      - traefik.http.services.netbird-flow-h2c.loadbalancer.server.port=80
-      - traefik.http.services.netbird-flow-h2c.loadbalancer.server.scheme=h2c
 
 EOF
 }
@@ -651,16 +536,61 @@ EOF
   fi
   cat <<'EOF'
   netbird_postgres:
-  netbird_traefik_letsencrypt:
+  netbird_caddy_data:
 
 networks:
   netbird:
-    name: netbird
-    driver: bridge
-    ipam:
-      config:
-        - subnet: 172.30.0.0/24
-          gateway: 172.30.0.1
+EOF
+}
+
+render_caddyfile() {
+  cat <<'EOF'
+{
+  servers :80,:443 {
+    protocols h1 h2c h2 h3
+  }
+}
+
+(security_headers) {
+    header * {
+        Strict-Transport-Security "max-age=3600; includeSubDomains; preload"
+        X-Content-Type-Options "nosniff"
+        X-Frame-Options "SAMEORIGIN"
+        X-XSS-Protection "1; mode=block"
+        -Server
+        Referrer-Policy strict-origin-when-cross-origin
+    }
+}
+
+:80 {
+    redir https://{$CADDY_SECURE_DOMAIN}{uri} permanent
+}
+
+{$CADDY_SECURE_DOMAIN}:443 {
+    import security_headers
+    # Signal (gRPC over h2c)
+    reverse_proxy /signalexchange.SignalExchange/* h2c://netbird-server:80
+    # Management (gRPC over h2c + HTTP)
+    reverse_proxy /management.ManagementService/* h2c://netbird-server:80
+    reverse_proxy /api/* netbird-server:80
+    reverse_proxy /ws-proxy/* netbird-server:80
+    # Embedded IdP (OAuth2 endpoints served by netbird server)
+    reverse_proxy /oauth2/* netbird-server:80
+    # Relay (WebSocket multiplexed on the same port)
+    reverse_proxy /relay* netbird-server:80
+EOF
+
+  if [[ "$NETBIRD_TRAFFIC_FLOW" == "yes" ]]; then
+    cat <<'EOF'
+    # Flow receiver (gRPC over h2c)
+    reverse_proxy /flow.FlowService/* h2c://receiver:80
+EOF
+  fi
+
+  cat <<'EOF'
+    # Dashboard
+    reverse_proxy /* dashboard:80
+}
 EOF
 }
 
@@ -679,7 +609,7 @@ server:
   logLevel: "info"
   logFile: "console"
 
-  # TLS is terminated by Traefik in front; leave this block empty.
+  # TLS is terminated by Caddy in front; leave this block empty.
   tls:
     certFile: ""
     keyFile: ""
@@ -702,16 +632,6 @@ server:
     cliRedirectURIs:
       - "http://localhost:53000/"
 
-  # Trust X-Forwarded-* only from the Traefik container's static address. Both
-  # keys must stay in step with the ipv4_address pinned in docker-compose.yml:
-  # trustedPeers decides whether forwarded headers are read at all, and leaving
-  # it unset falls back to 0.0.0.0/0.
-  reverseProxy:
-    trustedPeers:
-      - "${TRAEFIK_IP}/32"
-    trustedHTTPProxies:
-      - "${TRAEFIK_IP}/32"
-
   store:
     engine: "postgres"
     dsn: "${POSTGRES_DSN}"

infrastructure_files/migrate-to-enterprise.sh

@@ -15,11 +15,7 @@ set -o pipefail
 #   2. Postgres migration — add Postgres, migrate SQLite data via migrate-store.
 #   3. Traffic flow       — add NATS + flow-enricher + flow-receiver.
 #
-# If any step fails once the stack has been touched, the script rolls itself
-# back automatically: generated files are removed, the Postgres volume this run
-# created is dropped, and the original deployment is started again.
-#
-# To revert a successful migration:
+# To revert:
 #   docker compose down
 #   rm -f docker-compose.override.yml config.yaml.enterprise
 #   # If Postgres migration was done, also restore the SQLite backup printed
@@ -29,15 +25,6 @@ set -o pipefail
 OVERRIDE_FILE="docker-compose.override.yml"
 ENTERPRISE_CONFIG_FILE="config.yaml.enterprise"
 
-# Rollback bookkeeping. ROLLBACK_STATE flips to "armed" the moment the script
-# starts mutating the deployment, and back to "disarmed" once the migration has
-# completed successfully.
-ROLLBACK_STATE="disarmed"
-ENV_EXISTED="unknown"
-ENV_BACKUP=""
-PG_VOLUME_NAME=""
-BACKUP_DIR=""
-
 NETBIRD_EULA_URL="https://netbird.io/self-hosted-EULA"
 
 check_docker_compose() {
@@ -374,77 +361,7 @@ render_enterprise_config() {
 # Execution steps
 # ---------------------------------------------------------------------------
 
-combined_container_id() {
-  $DOCKER_COMPOSE_COMMAND ps -aq "$COMBINED_SERVICE" 2>/dev/null | head -1
-}
-
-container_data_mount() {
-  local container="$1"
-  [[ -n "$container" ]] || return 0
-  docker inspect "$container" --format \
-    '{{range .Mounts}}{{if eq .Destination "/var/lib/netbird"}}{{if .Name}}{{.Name}}{{else}}{{.Source}}{{end}}{{end}}{{end}}' 2>/dev/null
-}
-
-# The name comes from the container, so `-v` cannot invent an empty volume here.
-# 0 = empty, 1 = holds data, 2 = could not determine. A failed listing must not
-# be reported as empty: that would abort a healthy migration over a pull error
-# or an unreadable bind mount.
-data_dir_state() {
-  local src="$1" out
-  if [[ "$src" == /* ]]; then
-    [[ -d "$src" ]] || return 2
-    out=$(ls -A "$src" 2>/dev/null) || return 2
-  else
-    docker volume inspect "$src" &> /dev/null || return 0
-    out=$(docker run --rm -v "${src}:/d:ro" busybox sh -c 'ls -A /d' 2>/dev/null) || return 2
-  fi
-  [[ -z "$out" ]] && return 0
-  return 1
-}
-
-check_data_directory() {
-  [[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0
-
-  local container
-  container=$(combined_container_id)
-  if [[ -z "$container" ]]; then
-    echo "" > /dev/stderr
-    echo "No container found for service '$COMBINED_SERVICE'." > /dev/stderr
-    echo "The migration backs up the store by copying it out of that container," > /dev/stderr
-    echo "so it has to exist. Start the deployment and re-run:" > /dev/stderr
-    echo "  $DOCKER_COMPOSE_COMMAND up -d" > /dev/stderr
-    exit 1
-  fi
-
-  local src
-  src=$(container_data_mount "$container")
-  if [[ -z "$src" ]]; then
-    echo "" > /dev/stderr
-    echo "The '$COMBINED_SERVICE' container has nothing mounted at /var/lib/netbird." > /dev/stderr
-    echo "Cannot locate the NetBird store to back it up." > /dev/stderr
-    exit 1
-  fi
-
-  local state=0
-  data_dir_state "$src" || state=$?
-  if [[ $state -eq 0 ]]; then
-    echo "" > /dev/stderr
-    echo "The NetBird data directory is empty:" > /dev/stderr
-    echo "  $src" > /dev/stderr
-    echo "There is nothing to migrate. Check that you are running this from the" > /dev/stderr
-    echo "deployment directory of the NetBird install you mean to migrate." > /dev/stderr
-    exit 1
-  fi
-  if [[ $state -eq 2 ]]; then
-    echo "  ⚠ Could not read $src to confirm it holds data — continuing." > /dev/stderr
-    echo "    The backup step still fails loudly if it turns out to be empty." > /dev/stderr
-  fi
-
-  echo "  Data directory:   $src"
-}
-
-# Only for the Postgres volume, which has no container to read it off yet.
-resolve_compose_volume() {
+resolve_data_volume() {
   local short="$1"
   local actual
   # Resolve project-prefixed volume name from Docker Compose config first.
@@ -474,21 +391,18 @@ resolve_compose_volume() {
 backup_sqlite() {
   BACKUP_DIR="$(pwd)/backups/sqlite-pre-enterprise-$(date +%Y%m%d-%H%M%S)"
   mkdir -p "$BACKUP_DIR"
-
-  local container
-  container=$(combined_container_id)
-  if [[ -z "$container" ]]; then
-    echo "  ⚠ No container found for '$COMBINED_SERVICE' — cannot back up the store." > /dev/stderr
-    exit 1
-  fi
-
-  echo "Backing up the NetBird store to $BACKUP_DIR ..."
-  docker cp "${container}:/var/lib/netbird/." "$BACKUP_DIR/"
-
+  local data_volume_actual
+  data_volume_actual=$(resolve_data_volume "$DATA_VOLUME")
+  echo "Backing up SQLite store from volume '$data_volume_actual' to $BACKUP_DIR ..."
+  docker run --rm \
+    -v "${data_volume_actual}:/var/lib/netbird:ro" \
+    -v "${BACKUP_DIR}:/backup" \
+    busybox \
+    sh -c 'cp -a /var/lib/netbird/. /backup/ 2>/dev/null || true'
   local copied
   copied=$(find "$BACKUP_DIR" -mindepth 1 | head -1)
   if [[ -z "$copied" ]]; then
-    echo "  ⚠ Backup directory is empty — /var/lib/netbird held no data. Aborting." > /dev/stderr
+    echo "  ⚠ Backup directory is empty — the volume '$data_volume_actual' didn't contain data. Aborting." > /dev/stderr
     exit 1
   fi
   echo "  done"
@@ -500,135 +414,6 @@ run_migrate_store() {
   echo "  done"
 }
 
-# ---------------------------------------------------------------------------
-# Rollback — a failed run must not leave the operator with a stopped stack and
-# half-written artifacts.
-# ---------------------------------------------------------------------------
-
-# Resolve the name Compose would give the Postgres volume before the override
-# exists, so a leftover volume can be spotted up front.
-compose_project_name() {
-  local container project
-  container=$($DOCKER_COMPOSE_COMMAND ps -aq 2>/dev/null | head -1)
-  if [[ -n "$container" ]]; then
-    project=$(docker inspect "$container" \
-      --format '{{index .Config.Labels "com.docker.compose.project"}}' 2>/dev/null)
-    if [[ -n "$project" ]]; then
-      echo "$project"
-      return 0
-    fi
-  fi
-  project=$($DOCKER_COMPOSE_COMMAND config 2>/dev/null | yq eval '.name // ""' - 2>/dev/null)
-  if [[ -n "$project" ]] && [[ "$project" != "null" ]]; then
-    echo "$project"
-  fi
-  return 0
-}
-
-postgres_volume_name() {
-  local project
-  project=$(compose_project_name)
-  if [[ -n "$project" ]]; then
-    echo "${project}_netbird_postgres"
-  fi
-  return 0
-}
-
-# Postgres skips initdb when its data directory is non-empty, so a volume left
-# behind by an interrupted run would keep the old password and old contents,
-# and migrate-store would fail against it.
-check_stale_postgres_volume() {
-  [[ "$MIGRATE_POSTGRES" == "yes" ]] || return 0
-
-  PG_VOLUME_NAME=$(postgres_volume_name)
-  if [[ -z "$PG_VOLUME_NAME" ]]; then
-    echo ""
-    echo "  ⚠ Could not determine the Compose project name, so a Postgres volume"
-    echo "    left over from an earlier attempt cannot be checked for. If a"
-    echo "    previous run failed, remove it before continuing:"
-    echo "      docker volume ls | grep netbird_postgres"
-    return 0
-  fi
-  docker volume inspect "$PG_VOLUME_NAME" &> /dev/null || return 0
-
-  echo ""
-  echo "  ⚠  A Postgres volume from an earlier attempt already exists:"
-  echo "       $PG_VOLUME_NAME"
-  echo "     Postgres does not re-initialise a non-empty data directory, so the"
-  echo "     migration would run against stale credentials and stale data."
-  local remove
-  remove=$(read_yes_no "  Remove it and continue?" "y")
-  if [[ "$remove" != "yes" ]]; then
-    echo "" > /dev/stderr
-    echo "Aborted. Remove it manually with: docker volume rm $PG_VOLUME_NAME" > /dev/stderr
-    exit 1
-  fi
-  docker volume rm "$PG_VOLUME_NAME" > /dev/null
-  echo "  Removed."
-}
-
-# Undo whatever this run changed and start the previous deployment again.
-rollback() {
-  ROLLBACK_STATE="done"
-
-  echo ""
-  echo "──────────────────────────────────────────────────────────────────────"
-  echo " Migration failed — restoring the previous deployment"
-  echo "──────────────────────────────────────────────────────────────────────"
-
-  # Resolve while the override is still present; without it Compose no longer
-  # knows about the Postgres volume.
-  local pg_volume="$PG_VOLUME_NAME"
-  if [[ -z "$pg_volume" ]] && [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
-    pg_volume=$(postgres_volume_name)
-  fi
-
-  echo ""
-  echo "Stopping services ..."
-  $DOCKER_COMPOSE_COMMAND down || true
-
-  echo "Removing generated files ..."
-  rm -f "$OVERRIDE_FILE" "$ENTERPRISE_CONFIG_FILE"
-
-  # Restore .env to exactly what it was, or remove it if this run created it.
-  if [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]]; then
-    mv -f "$ENV_BACKUP" .env || echo "  ⚠ Could not restore .env from $ENV_BACKUP." > /dev/stderr
-  elif [[ "$ENV_EXISTED" == "no" ]]; then
-    rm -f .env || true
-  fi
-
-  # Only ever the volume this run created — never the NetBird data volume.
-  if [[ -n "$pg_volume" ]] && [[ "$pg_volume" != "null" ]]; then
-    echo "Removing Postgres volume $pg_volume ..."
-    docker volume rm "$pg_volume" &> /dev/null || true
-  fi
-
-  echo "Starting the previous deployment ..."
-  if ! $DOCKER_COMPOSE_COMMAND up -d; then
-    echo ""
-    echo "  ⚠ Could not start the previous deployment automatically." > /dev/stderr
-    echo "    Run: $DOCKER_COMPOSE_COMMAND up -d" > /dev/stderr
-  fi
-
-  echo ""
-  echo "Rolled back. Your docker-compose.yml, config.yaml and the NetBird data"
-  echo "volume were never modified."
-  if [[ -n "$BACKUP_DIR" ]] && [[ -d "$BACKUP_DIR" ]]; then
-    echo "The SQLite backup taken during this run is kept at:"
-    echo "  $BACKUP_DIR"
-  fi
-  echo "──────────────────────────────────────────────────────────────────────"
-}
-
-on_exit() {
-  local code=$?
-  trap - EXIT
-  if [[ $code -ne 0 ]] && [[ "$ROLLBACK_STATE" == "armed" ]]; then
-    rollback
-  fi
-  exit $code
-}
-
 # ---------------------------------------------------------------------------
 # Main
 # ---------------------------------------------------------------------------
@@ -756,15 +541,9 @@ init_migration() {
     ENABLE_FLOW="no"
     echo "Step 3 (traffic flow) skipped — requires Postgres."
   fi
-
-  check_data_directory
-  check_stale_postgres_volume
 }
 
 apply_changes() {
-  # From here on a failure must roll the deployment back.
-  ROLLBACK_STATE="armed"
-
   echo ""
   echo "Writing $OVERRIDE_FILE ..."
   install -m 644 /dev/null "$OVERRIDE_FILE"
@@ -785,14 +564,6 @@ apply_changes() {
   # picks it up automatically.
   echo "Writing .env additions (mode 600) ..."
   local ENV_FILE=".env"
-  # Snapshot the operator's .env so a rollback can restore it byte for byte.
-  if [[ -f "$ENV_FILE" ]]; then
-    ENV_EXISTED="yes"
-    ENV_BACKUP="${ENV_FILE}.pre-enterprise-$(date +%Y%m%d-%H%M%S)"
-    cp -p "$ENV_FILE" "$ENV_BACKUP"
-  else
-    ENV_EXISTED="no"
-  fi
   touch "$ENV_FILE"
   chmod 600 "$ENV_FILE"
   {
@@ -821,16 +592,11 @@ apply_changes() {
 
   if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
     echo ""
-    # Stop, but keep the containers: the backup reads the store out of one.
-    echo "Stopping services so the store is quiescent ..."
-    $DOCKER_COMPOSE_COMMAND stop
+    echo "Stopping existing services (volumes preserved) ..."
+    $DOCKER_COMPOSE_COMMAND down
 
     backup_sqlite
 
-    echo ""
-    echo "Removing stopped containers (volumes preserved) ..."
-    $DOCKER_COMPOSE_COMMAND down
-
     echo ""
     echo "Starting Postgres ..."
     $DOCKER_COMPOSE_COMMAND up -d postgres
@@ -860,9 +626,6 @@ apply_changes() {
 
   echo ""
   echo "Migration complete."
-
-  # Nothing left to undo.
-  ROLLBACK_STATE="disarmed"
 }
 
 print_summary() {
@@ -880,7 +643,6 @@ print_summary() {
   echo "    $OVERRIDE_FILE"
   [[ "$MIGRATE_POSTGRES" == "yes" ]] && echo "    $ENTERPRISE_CONFIG_FILE"
   echo "    .env  (license key + secrets, mode 600)"
-  [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]] && echo "    $ENV_BACKUP  (.env as it was before this run)"
   [[ "$MIGRATE_POSTGRES" == "yes" ]] && echo "    backups/sqlite-pre-enterprise-*/  (SQLite backup)"
   echo ""
   echo " Tail logs:"
@@ -889,27 +651,19 @@ print_summary() {
   echo "──────────────────────────────────────────────────────────────────────"
   echo " To revert"
   echo "──────────────────────────────────────────────────────────────────────"
+  echo "  $DOCKER_COMPOSE_COMMAND down"
   if [[ "$MIGRATE_POSTGRES" == "yes" ]]; then
-    # Resolve the project-prefixed volume name now, before the override is gone.
-    local pg_volume
-    pg_volume=$(resolve_compose_volume "netbird_postgres")
-    echo "  # Stop, but keep the containers so the store can be copied back in:"
-    echo "  $DOCKER_COMPOSE_COMMAND stop"
-    echo "  # Restore SQLite from the backup created during this run:"
-    echo "  docker cp ${BACKUP_DIR}/. \$($DOCKER_COMPOSE_COMMAND ps -aq $COMBINED_SERVICE):/var/lib/netbird/"
-    echo "  $DOCKER_COMPOSE_COMMAND down"
+    # Resolve project-prefixed volume names now (before override is removed).
+    local pg_volume data_volume_actual
+    pg_volume=$(resolve_data_volume "netbird_postgres")
+    data_volume_actual=$(resolve_data_volume "$DATA_VOLUME")
+    echo "  # Remove the Postgres volume FIRST, before deleting the override file:"
     echo "  docker volume rm $pg_volume"
-  else
-    echo "  $DOCKER_COMPOSE_COMMAND down"
+    echo "  # Restore SQLite from the backup created during this run:"
+    echo "  docker run --rm -v ${data_volume_actual}:/var/lib/netbird -v ${BACKUP_DIR}:/backup busybox sh -c 'cp -a /backup/. /var/lib/netbird/'"
   fi
   echo "  rm -f $OVERRIDE_FILE $ENTERPRISE_CONFIG_FILE"
-  if [[ "$ENV_EXISTED" == "yes" ]] && [[ -f "$ENV_BACKUP" ]]; then
-    echo "  mv $ENV_BACKUP .env   # restores .env as it was before this run"
-  elif [[ "$ENV_EXISTED" == "no" ]]; then
-    echo "  rm -f .env   # created by this run"
-  else
-    echo "  # Remove migrate-to-enterprise.sh additions from .env (search for the timestamp marker)"
-  fi
+  echo "  # Remove migrate-to-enterprise.sh additions from .env (search for the timestamp marker)"
   echo "  $DOCKER_COMPOSE_COMMAND up -d"
   echo "──────────────────────────────────────────────────────────────────────"
 }
@@ -918,10 +672,6 @@ print_summary() {
 # Run
 # ---------------------------------------------------------------------------
 
-trap on_exit EXIT
-# Turn signals into a normal exit so the EXIT trap can roll back.
-trap 'exit 130' INT TERM
-
 init_migration
 apply_changes
 print_summary

management/internals/modules/agentnetwork/handlers/handlers_test.go

@@ -17,7 +17,6 @@ import (
 
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-	"github.com/netbirdio/netbird/management/server/account"
 	nbcontext "github.com/netbirdio/netbird/management/server/context"
 	"github.com/netbirdio/netbird/management/server/permissions"
 	"github.com/netbirdio/netbird/management/server/store"
@@ -62,23 +61,10 @@ func newAgentNetworkHandlerFixture(t *testing.T) *agentNetworkHandlerFixture {
 		Return(true, context.Background(), nil).
 		AnyTimes()
 
-	// Swallow activity events so the mutation paths (create/update/delete)
-	// are exercisable through the HTTP layer.
-	accounts := account.NewMockManager(ctrl)
-	accounts.EXPECT().
-		StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).
-		AnyTimes()
-	accounts.EXPECT().
-		UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).
-		AnyTimes()
-
-	manager := agentnetwork.NewManager(st, perms, accounts, nil)
+	manager := agentnetwork.NewManager(st, perms, nil, nil)
 	h := &handler{manager: manager}
 
 	router := mux.NewRouter()
-	router.HandleFunc("/agent-network/providers", h.createProvider).Methods("POST")
-	router.HandleFunc("/agent-network/providers/{providerId}", h.getProvider).Methods("GET")
-	router.HandleFunc("/agent-network/providers/{providerId}", h.updateProvider).Methods("PUT")
 	h.addPolicyEndpoints(router)
 	h.addConsumptionEndpoints(router)
 	h.addBudgetRuleEndpoints(router)

management/internals/modules/agentnetwork/handlers/providers_handler_test.go

@@ -1,9 +1,7 @@
 package handlers
 
 import (
-	"encoding/json"
 	"math"
-	nethttp "net/http"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -53,50 +51,3 @@ func TestValidate_ModelRates(t *testing.T) {
 		assert.Error(t, validate(base(m), true), "case %q must be rejected", name)
 	}
 }
-
-// TestProviderHandler_UpdateReplacesFullState pins the update contract shared
-// with the other PUT endpoints: the request replaces the provider's mutable
-// state, so optional fields absent from the JSON land as their zero values.
-// The two exceptions are server-side: the api_key (a secret — omitted means
-// "not rotated") and the session keypair, both preserved by the manager. The
-// identity headers stay on the wire as explicit empty strings so a cleared
-// value round-trips.
-func TestProviderHandler_UpdateReplacesFullState(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	create := `{
-        "provider_id": "openai_api",
-        "name": "openai",
-        "upstream_url": "https://api.openai.com",
-        "api_key": "sk-test",
-        "enabled": true,
-        "metadata_disabled": true,
-        "skip_tls_verification": true,
-        "extra_values": {"x-portkey-config": "pc-prod-3f2a"},
-        "identity_header_user_id": "x-bf-dim-netbird_user_id",
-        "models": [{"id": "gpt-4o", "input_per_1k": 0.0025, "output_per_1k": 0.01}]
-    }`
-	rec := f.do(t, nethttp.MethodPost, "/agent-network/providers", create)
-	require.Equal(t, nethttp.StatusOK, rec.Code, "create must succeed: %s", rec.Body.String())
-
-	var created api.AgentNetworkProvider
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &created))
-
-	// Minimal update: only the required fields, no api_key. Everything
-	// optional must land as its zero value.
-	update := `{"provider_id": "openai_api", "name": "openai-renamed", "upstream_url": "https://api.openai.com", "enabled": true}`
-	rec = f.do(t, nethttp.MethodPut, "/agent-network/providers/"+created.Id, update)
-	require.Equal(t, nethttp.StatusOK, rec.Code, "update without api_key must succeed (key is preserved): %s", rec.Body.String())
-
-	var updated api.AgentNetworkProvider
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &updated))
-	assert.Equal(t, "openai-renamed", updated.Name, "sent field must apply")
-	assert.True(t, updated.Enabled, "sent field must apply")
-	assert.False(t, updated.MetadataDisabled, "omitted metadata_disabled must land as false — PUT replaces the full state")
-	assert.False(t, updated.SkipTlsVerification, "omitted skip_tls_verification must land as false")
-	assert.Nil(t, updated.ExtraValues, "omitted extra_values must be cleared")
-	assert.Equal(t, "", updated.IdentityHeaderUserId, "omitted identity header must be cleared yet stay on the wire")
-	assert.Empty(t, updated.Models, "omitted models must be cleared")
-	assert.Contains(t, rec.Body.String(), `"identity_header_user_id":""`,
-		"cleared identity header must round-trip as an explicit empty string")
-}

management/internals/modules/agentnetwork/handlers/settings_handler.go

@@ -2,6 +2,7 @@ package handlers
 
 import (
 	"encoding/json"
+	"errors"
 	"net/http"
 
 	"github.com/gorilla/mux"
@@ -10,20 +11,19 @@ import (
 	nbcontext "github.com/netbirdio/netbird/management/server/context"
 	"github.com/netbirdio/netbird/shared/management/http/api"
 	"github.com/netbirdio/netbird/shared/management/http/util"
+	"github.com/netbirdio/netbird/shared/management/status"
 )
 
 // addSettingsEndpoints registers the Agent Network settings routes. The
-// settings row is bootstrapped server-side on first provider create or on the
-// first PUT carrying a cluster; GET reads it and PUT applies a partial update
-// of the mutable collection toggles (cluster/subdomain stay immutable).
+// settings row is bootstrapped server-side on first provider create; GET reads
+// it and PUT updates the mutable collection toggles (cluster/subdomain stay
+// immutable).
 func (h *handler) addSettingsEndpoints(router *mux.Router) {
 	router.HandleFunc("/agent-network/settings", h.getSettings).Methods("GET", "OPTIONS")
 	router.HandleFunc("/agent-network/settings", h.updateSettings).Methods("PUT", "OPTIONS")
 }
 
-// updateSettings replaces the mutable settings fields on the account's row.
-// A request carrying a cluster bootstraps the row when the account doesn't
-// have one yet.
+// updateSettings applies the collection toggles to the account's settings row.
 func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) {
 	userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
 	if err != nil {
@@ -48,9 +48,11 @@ func (h *handler) updateSettings(w http.ResponseWriter, r *http.Request) {
 	util.WriteJSONObject(r.Context(), w, updated.ToAPIResponse())
 }
 
-// getSettings returns the account's agent-network settings. Accounts that
-// haven't been bootstrapped yet read as the defaults with an empty cluster,
-// subdomain and endpoint; the manager synthesises that view.
+// getSettings returns the account's agent-network settings. The settings
+// row is bootstrapped on first provider create, so freshly-onboarded
+// accounts have nothing to read. Rather than 404-ing in that case (which
+// the dashboard would have to special-case), return a JSON null with 200
+// so consumers can branch on the body alone.
 func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
 	userAuth, err := nbcontext.GetUserAuthFromContext(r.Context())
 	if err != nil {
@@ -60,6 +62,11 @@ func (h *handler) getSettings(w http.ResponseWriter, r *http.Request) {
 
 	settings, err := h.manager.GetSettings(r.Context(), userAuth.AccountId, userAuth.UserId)
 	if err != nil {
+		var sErr *status.Error
+		if errors.As(err, &sErr) && sErr.Type() == status.NotFound {
+			util.WriteJSONObject(r.Context(), w, nil)
+			return
+		}
 		util.WriteError(r.Context(), err, w)
 		return
 	}

management/internals/modules/agentnetwork/handlers/settings_handler_test.go

@@ -1,137 +0,0 @@
-package handlers
-
-import (
-	"encoding/json"
-	"net/http"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// TestSettingsHandler_GetUnbootstrappedReturnsDefaults pins the settings-read
-// convention shared with the account and DNS settings endpoints: settings
-// always read as a JSON object. Before bootstrap that object carries the
-// defaults with an empty cluster/subdomain/endpoint (the "not bootstrapped"
-// signal) and no timestamps — never a 404 and never the legacy null body.
-func TestSettingsHandler_GetUnbootstrappedReturnsDefaults(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	rec := f.do(t, http.MethodGet, "/agent-network/settings", "")
-	require.Equal(t, http.StatusOK, rec.Code,
-		"unbootstrapped account must read as 200 with defaults: got %d body=%s", rec.Code, rec.Body.String())
-	require.NotEqual(t, "null", trimSpace(rec.Body.String()),
-		"the legacy 200+null shape must not come back")
-
-	var got api.AgentNetworkSettings
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
-	assert.Empty(t, got.Cluster, "cluster must be empty until bootstrapped")
-	assert.Empty(t, got.Subdomain, "subdomain must be empty until bootstrapped")
-	assert.Empty(t, got.Endpoint, "endpoint must be empty until bootstrapped, not a bare dot")
-	assert.True(t, got.EnableLogCollection, "defaults must show log collection on, matching bootstrap")
-	assert.False(t, got.EnablePromptCollection, "defaults must show prompt collection off")
-	assert.False(t, got.RedactPii, "defaults must show redaction off")
-	require.NotNil(t, got.AccessLogRetentionDays)
-	assert.Equal(t, 30, *got.AccessLogRetentionDays, "defaults must show the bootstrap retention")
-	assert.Nil(t, got.CreatedAt, "no timestamps before a row exists")
-	assert.Nil(t, got.UpdatedAt, "no timestamps before a row exists")
-}
-
-// TestSettingsHandler_PutBootstrapsWithCluster covers the settings-first
-// bootstrap path: a PUT carrying a cluster on an unbootstrapped account
-// creates the row (cluster pinned, subdomain assigned) and applies the
-// mutable fields from the same request.
-func TestSettingsHandler_PutBootstrapsWithCluster(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	rec := f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": false, "access_log_retention_days": 30}`)
-	require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
-
-	var got api.AgentNetworkSettings
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
-	assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be pinned from the request")
-	assert.NotEmpty(t, got.Subdomain, "subdomain must be assigned at bootstrap")
-	assert.Equal(t, got.Subdomain+".eu.proxy.netbird.io", got.Endpoint, "endpoint must combine subdomain and cluster")
-	assert.True(t, got.EnableLogCollection, "toggle from the bootstrap request must apply")
-	assert.True(t, got.EnablePromptCollection, "toggle from the bootstrap request must apply")
-	require.NotNil(t, got.AccessLogRetentionDays)
-	assert.Equal(t, 30, *got.AccessLogRetentionDays, "retention from the bootstrap request must apply")
-
-	// The row is now readable via GET.
-	rec = f.do(t, http.MethodGet, "/agent-network/settings", "")
-	require.Equal(t, http.StatusOK, rec.Code, "GET after bootstrap must succeed")
-}
-
-// TestSettingsHandler_PutWithoutClusterOnUnbootstrapped pins that a PUT
-// without a cluster cannot conjure a settings row out of nothing — there is
-// no cluster to pin — and surfaces as 404 like the GET.
-func TestSettingsHandler_PutWithoutClusterOnUnbootstrapped(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	rec := f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"enable_log_collection": false, "enable_prompt_collection": false, "redact_pii": false}`)
-	assert.Equal(t, http.StatusNotFound, rec.Code,
-		"cluster-less PUT on an unbootstrapped account must 404: got %d body=%s", rec.Code, rec.Body.String())
-	assert.Contains(t, rec.Body.String(), "cluster",
-		"the error must point the caller at the bootstrap paths: %s", rec.Body.String())
-}
-
-// TestSettingsHandler_PutReplacesMutableFields pins the update contract shared
-// with the other PUT endpoints: the request replaces every mutable field, so a
-// toggle absent from the JSON lands as its zero value rather than being
-// preserved. Cluster and subdomain survive untouched.
-func TestSettingsHandler_PutReplacesMutableFields(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	rec := f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": true, "redact_pii": true, "access_log_retention_days": 14}`)
-	require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
-
-	var before api.AgentNetworkSettings
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &before))
-
-	rec = f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
-	require.Equal(t, http.StatusOK, rec.Code, "update PUT must succeed: %s", rec.Body.String())
-
-	var got api.AgentNetworkSettings
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
-	assert.True(t, got.EnableLogCollection, "sent toggle must apply")
-	assert.False(t, got.EnablePromptCollection, "sent toggle must apply")
-	assert.False(t, got.RedactPii, "sent toggle must apply")
-	require.NotNil(t, got.AccessLogRetentionDays)
-	assert.Equal(t, 0, *got.AccessLogRetentionDays,
-		"retention absent from the request must land as the zero value — PUT replaces all mutable fields")
-	assert.Equal(t, before.Cluster, got.Cluster, "cluster must survive updates untouched")
-	assert.Equal(t, before.Subdomain, got.Subdomain, "subdomain must survive updates untouched")
-}
-
-// TestSettingsHandler_PutRejectsClusterChange pins cluster immutability: once
-// assigned, a differing cluster is rejected as a validation error instead of
-// being silently ignored, so callers never observe a value other than the one
-// they sent. Echoing the assigned cluster back stays valid, which lets
-// declarative clients send their full desired state idempotently.
-func TestSettingsHandler_PutRejectsClusterChange(t *testing.T) {
-	f := newAgentNetworkHandlerFixture(t)
-
-	rec := f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
-	require.Equal(t, http.StatusOK, rec.Code, "bootstrap PUT must succeed: %s", rec.Body.String())
-
-	rec = f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"cluster": "us.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": false}`)
-	assert.Equal(t, http.StatusUnprocessableEntity, rec.Code,
-		"cluster change must be rejected as a validation error: got %d body=%s", rec.Code, rec.Body.String())
-
-	rec = f.do(t, http.MethodPut, "/agent-network/settings",
-		`{"cluster": "eu.proxy.netbird.io", "enable_log_collection": true, "enable_prompt_collection": false, "redact_pii": true}`)
-	require.Equal(t, http.StatusOK, rec.Code, "echoing the assigned cluster must stay valid: %s", rec.Body.String())
-
-	var got api.AgentNetworkSettings
-	require.NoError(t, json.Unmarshal(rec.Body.Bytes(), &got))
-	assert.Equal(t, "eu.proxy.netbird.io", got.Cluster, "cluster must be unchanged")
-	assert.True(t, got.RedactPii, "toggle sent alongside the echoed cluster must apply")
-}

management/internals/modules/agentnetwork/manager.go

@@ -157,14 +157,14 @@ func NewManager(
 }
 
 func (m *managerImpl) GetAllProviders(ctx context.Context, accountID, userID string) ([]*types.Provider, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, providerID string) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, providerID)
@@ -175,14 +175,9 @@ func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, provid
 // been created yet; otherwise it is ignored (the cluster is pinned on
 // Settings and every provider in the account routes through it).
 func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
-	if strings.TrimSpace(bootstrapCluster) != "" {
-		if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil {
-			return nil, err
-		}
-	}
 
 	// An empty api_key would silently produce a synthesised service
 	// that 401s on every upstream request. Surface the misconfiguration
@@ -207,7 +202,7 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
 	}
 
 	if strings.TrimSpace(bootstrapCluster) != "" {
-		if _, err := m.bootstrapSettingsIfNeeded(ctx, m.store, provider.AccountID, bootstrapCluster); err != nil {
+		if _, err := m.bootstrapSettingsIfNeeded(ctx, provider.AccountID, bootstrapCluster); err != nil {
 			// The provider create has already succeeded; logging the
 			// bootstrap miss matches the plan's PoC behaviour. The synth
 			// path treats a missing settings row as a no-op, and the next
@@ -223,7 +218,7 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
 }
 
 func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -262,7 +257,7 @@ func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provide
 }
 
 func (m *managerImpl) DeleteProvider(ctx context.Context, accountID, userID, providerID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -311,21 +306,21 @@ func pluralize(n int, singular, plural string) string {
 }
 
 func (m *managerImpl) GetAllPolicies(ctx context.Context, accountID, userID string) ([]*types.Policy, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkPolicies(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetPolicy(ctx context.Context, accountID, userID, policyID string) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkPolicyByID(ctx, store.LockingStrengthNone, accountID, policyID)
 }
 
 func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -351,7 +346,7 @@ func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *t
 }
 
 func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -378,7 +373,7 @@ func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *t
 }
 
 func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, policyID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -398,21 +393,21 @@ func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, polic
 }
 
 func (m *managerImpl) GetAllGuardrails(ctx context.Context, accountID, userID string) ([]*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkGuardrails(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetGuardrail(ctx context.Context, accountID, userID, guardrailID string) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkGuardrailByID(ctx, store.LockingStrengthNone, accountID, guardrailID)
 }
 
 func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -434,7 +429,7 @@ func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardr
 }
 
 func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -457,7 +452,7 @@ func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardr
 }
 
 func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, guardrailID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -478,7 +473,7 @@ func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, gu
 
 // GetAllBudgetRules returns every account-level budget rule for the account.
 func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID string) ([]*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkBudgetRules(ctx, store.LockingStrengthNone, accountID)
@@ -486,7 +481,7 @@ func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID s
 
 // GetBudgetRule returns a single account-level budget rule.
 func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, ruleID string) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkBudgetRuleByID(ctx, store.LockingStrengthNone, accountID, ruleID)
@@ -496,7 +491,7 @@ func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, rule
 // enforced at request time (CheckLLMPolicyLimits), not baked into the synth
 // proxy config, so no reconcile is needed.
 func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -518,7 +513,7 @@ func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule
 
 // UpdateBudgetRule updates an existing account-level budget rule.
 func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -541,7 +536,7 @@ func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule
 
 // DeleteBudgetRule removes an account-level budget rule.
 func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, ruleID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -559,83 +554,40 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r
 	return nil
 }
 
-// UpdateSettings replaces the mutable account-level settings — the collection
-// toggles and retention — on the account's row. When the account has no
-// settings row yet, a non-empty settings.Cluster bootstraps one (same path as
-// first provider create); without it the update fails with NotFound. On an
-// existing row the cluster and subdomain are immutable: a differing
-// settings.Cluster is rejected rather than silently ignored so callers never
-// observe a value other than what they sent. Because the collection toggles
-// change the synthesised service config (prompt-capture gating, access-log
-// emission), a reconcile is triggered so the proxy and peer network maps
-// converge on the new state.
+// UpdateSettings applies the mutable account-level settings — the collection
+// toggles — onto the existing row. Cluster and Subdomain are immutable and are
+// preserved from the persisted row regardless of the input. Because the
+// collection toggles change the synthesised service config (prompt-capture
+// gating, access-log emission), a reconcile is triggered so the proxy and peer
+// network maps converge on the new state.
 func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) {
-	if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, settings.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
-	requestedCluster := strings.TrimSpace(settings.Cluster)
-
-	// The row lock from LockingStrengthUpdate only holds for the duration of
-	// the surrounding transaction, so the read, the cluster-immutability
-	// check, and the save must share one — otherwise concurrent PUTs could
-	// interleave between them.
-	var updated *types.Settings
-	err := m.store.ExecuteInTransaction(ctx, func(tx store.Store) error {
-		existing, err := tx.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
-		switch {
-		case err == nil:
-			if requestedCluster != "" && requestedCluster != existing.Cluster {
-				return status.Errorf(status.InvalidArgument, "cluster is immutable once assigned (current: %s)", existing.Cluster)
-			}
-		case isNotFound(err):
-			if requestedCluster == "" {
-				return status.Errorf(status.NotFound, "agent network settings have not been bootstrapped yet; pass cluster to bootstrap them, or create a provider with bootstrap_cluster set")
-			}
-			// Bootstrapping pins the cluster and subdomain — a settings
-			// create on top of the update the caller already passed, matching
-			// the gate on the provider-create bootstrap path.
-			if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Create); err != nil {
-				return err
-			}
-			existing, err = m.bootstrapSettingsIfNeeded(ctx, tx, settings.AccountID, requestedCluster)
-			if err != nil {
-				return err
-			}
-		default:
-			return fmt.Errorf("get agent network settings: %w", err)
-		}
-
-		existing.EnableLogCollection = settings.EnableLogCollection
-		existing.EnablePromptCollection = settings.EnablePromptCollection
-		existing.RedactPii = settings.RedactPii
-		existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
-		existing.UpdatedAt = time.Now().UTC()
-
-		if err := tx.SaveAgentNetworkSettings(ctx, existing); err != nil {
-			return fmt.Errorf("save agent network settings: %w", err)
-		}
-		updated = existing
-		return nil
-	})
+	existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthUpdate, settings.AccountID)
 	if err != nil {
-		return nil, err
+		return nil, fmt.Errorf("get agent network settings: %w", err)
+	}
+
+	existing.EnableLogCollection = settings.EnableLogCollection
+	existing.EnablePromptCollection = settings.EnablePromptCollection
+	existing.RedactPii = settings.RedactPii
+	existing.AccessLogRetentionDays = settings.AccessLogRetentionDays
+	existing.UpdatedAt = time.Now().UTC()
+
+	if err := m.store.SaveAgentNetworkSettings(ctx, existing); err != nil {
+		return nil, fmt.Errorf("save agent network settings: %w", err)
 	}
 
 	m.accountManager.StoreEvent(ctx, userID, settings.AccountID, settings.AccountID, activity.AgentNetworkSettingsUpdated, map[string]any{
-		"log_collection":    updated.EnableLogCollection,
-		"prompt_collection": updated.EnablePromptCollection,
-		"redact_pii":        updated.RedactPii,
+		"log_collection":    existing.EnableLogCollection,
+		"prompt_collection": existing.EnablePromptCollection,
+		"redact_pii":        existing.RedactPii,
 	})
 	m.reconcile(ctx, settings.AccountID)
 
-	return updated, nil
-}
-
-// isNotFound reports whether err is a status.NotFound error.
-func isNotFound(err error) bool {
-	var sErr *status.Error
-	return errors.As(err, &sErr) && sErr.Type() == status.NotFound
+	return existing, nil
 }
 
 // validateProviderRefs ensures every destination provider id refers to a
@@ -659,38 +611,14 @@ func (m *managerImpl) validateProviderRefs(ctx context.Context, accountID string
 	return nil
 }
 
-// GetSettings returns the agent-network settings row for the account. When no
-// row has been bootstrapped yet, the defaults are returned (without
-// persisting) with cluster and subdomain empty — settings always read as an
-// object, like the account and DNS settings endpoints.
+// GetSettings returns the agent-network settings row for the account.
+// Returns the underlying status.NotFound when no row has been
+// bootstrapped yet (i.e. the account has no providers).
 func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
-	settings, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
-	switch {
-	case err == nil:
-		return settings, nil
-	case isNotFound(err):
-		return types.DefaultSettings(accountID), nil
-	default:
-		return nil, err
-	}
-}
-
-// requireSettingsBootstrapPermission gates the one-time settings bootstrap a
-// first provider create performs. Pinning the account's cluster and subdomain
-// is a settings write, so it needs the settings permission on top of the
-// provider one. No-op once the settings row exists.
-func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, accountID, userID string) error {
-	_, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
-	if err == nil {
-		return nil
-	}
-	if !isNotFound(err) {
-		return fmt.Errorf("get agent network settings: %w", err)
-	}
-	return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create)
+	return m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
 }
 
 // bootstrapSettingsIfNeeded creates the per-account agent-network
@@ -698,9 +626,8 @@ func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, ac
 // hint the dashboard sends (auto-picked from the active cluster list);
 // the subdomain is picked from the curated wordlist avoiding
 // collisions on the same cluster. Idempotent: if a row already exists
-// it is returned untouched and the hint is ignored. st is the store to
-// operate on — pass the transaction store when calling from within one.
-func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.Store, accountID, providerCluster string) (*types.Settings, error) {
+// it is returned untouched and the hint is ignored.
+func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID, providerCluster string) (*types.Settings, error) {
 	if accountID == "" {
 		return nil, fmt.Errorf("bootstrap settings: account id is required")
 	}
@@ -708,15 +635,16 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.St
 		return nil, fmt.Errorf("bootstrap settings: provider cluster is required")
 	}
 
-	existing, err := st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
+	existing, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
 	if err == nil {
 		return existing, nil
 	}
-	if !isNotFound(err) {
+	var sErr *status.Error
+	if !errors.As(err, &sErr) || sErr.Type() != status.NotFound {
 		return nil, fmt.Errorf("get agent network settings: %w", err)
 	}
 
-	siblings, err := st.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
+	siblings, err := m.store.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
 	if err != nil {
 		return nil, fmt.Errorf("list agent network settings on cluster: %w", err)
 	}
@@ -735,12 +663,18 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.St
 	m.labelRngMu.Unlock()
 
 	now := time.Now().UTC()
-	settings := types.DefaultSettings(accountID)
-	settings.Cluster = providerCluster
-	settings.Subdomain = subdomain
-	settings.CreatedAt = now
-	settings.UpdatedAt = now
-	if err := st.SaveAgentNetworkSettings(ctx, settings); err != nil {
+	settings := &types.Settings{
+		AccountID: accountID,
+		Cluster:   providerCluster,
+		Subdomain: subdomain,
+		// Logs on by default; usage is collected regardless. Retention bounds
+		// how long full log rows are kept.
+		EnableLogCollection:    true,
+		AccessLogRetentionDays: types.DefaultAccessLogRetentionDays,
+		CreatedAt:              now,
+		UpdatedAt:              now,
+	}
+	if err := m.store.SaveAgentNetworkSettings(ctx, settings); err != nil {
 		return nil, fmt.Errorf("save agent network settings: %w", err)
 	}
 	return settings, nil
@@ -751,7 +685,7 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, st store.St
 // counter view; permission gate is the same Read role that gates
 // every other agent-network surface.
 func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID string) ([]*types.Consumption, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.ListAgentNetworkConsumption(ctx, store.LockingStrengthNone, accountID)
@@ -760,7 +694,7 @@ func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID str
 // ListAccessLogs returns a paginated, server-side-filtered page of
 // agent-network access logs plus the total count matching the filter.
 func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLog, int64, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, 0, err
 	}
 	return m.store.GetAgentNetworkAccessLogs(ctx, store.LockingStrengthNone, accountID, filter)
@@ -770,7 +704,7 @@ func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID stri
 // agent-network access logs grouped by session, plus the total number of
 // sessions matching the filter.
 func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLogSession, int64, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, 0, err
 	}
 	return m.store.GetAgentNetworkAccessLogSessions(ctx, store.LockingStrengthNone, accountID, filter)
@@ -779,7 +713,7 @@ func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, user
 // GetUsageOverview returns the filtered usage rows aggregated into time buckets
 // at the requested granularity, oldest-first.
 func (m *managerImpl) GetUsageOverview(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter, granularity types.UsageGranularity) ([]*types.AgentNetworkUsageBucket, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	rows, err := m.store.GetAgentNetworkUsageRows(ctx, store.LockingStrengthNone, accountID, filter)
@@ -853,8 +787,8 @@ func (m *managerImpl) RecordConsumption(ctx context.Context, accountID string, k
 	return m.store.IncrementAgentNetworkConsumption(ctx, accountID, kind, dimID, windowSeconds, windowStart, tokensIn, tokensOut, costUSD)
 }
 
-func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, module modules.Module, op operations.Operation) error {
-	ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, module, op)
+func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, op operations.Operation) error {
+	ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.AgentNetwork, op)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}
@@ -943,8 +877,8 @@ func (*mockManager) UpdateBudgetRule(_ context.Context, _ string, r *types.Accou
 
 func (*mockManager) DeleteBudgetRule(_ context.Context, _, _, _ string) error { return nil }
 
-func (*mockManager) GetSettings(_ context.Context, accountID, _ string) (*types.Settings, error) {
-	return types.DefaultSettings(accountID), nil
+func (*mockManager) GetSettings(_ context.Context, _, _ string) (*types.Settings, error) {
+	return nil, status.Errorf(status.NotFound, "agent network settings not found")
 }
 
 func (*mockManager) UpdateSettings(_ context.Context, _ string, s *types.Settings) (*types.Settings, error) {

management/internals/modules/agentnetwork/provider_bootstrap_test.go

@@ -1,134 +0,0 @@
-package agentnetwork
-
-import (
-	"context"
-	"runtime"
-	"testing"
-
-	"github.com/golang/mock/gomock"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-	"github.com/netbirdio/netbird/management/server/account"
-	"github.com/netbirdio/netbird/management/server/permissions"
-	"github.com/netbirdio/netbird/management/server/permissions/modules"
-	"github.com/netbirdio/netbird/management/server/permissions/operations"
-	"github.com/netbirdio/netbird/management/server/store"
-	nbtypes "github.com/netbirdio/netbird/management/server/types"
-	"github.com/netbirdio/netbird/shared/management/status"
-)
-
-// bootstrapFixture wires a real sqlite store to a gomock permissions manager
-// so tests can grant the provider permission while denying (or never
-// expecting) the settings one.
-type bootstrapFixture struct {
-	manager Manager
-	store   store.Store
-	perms   *permissions.MockManager
-}
-
-func newBootstrapFixture(t *testing.T) *bootstrapFixture {
-	t.Helper()
-	if runtime.GOOS == "windows" {
-		t.Skip("sqlite store not properly supported on Windows yet")
-	}
-	t.Setenv("NETBIRD_STORE_ENGINE", string(nbtypes.SqliteStoreEngine))
-
-	st, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
-	require.NoError(t, err, "test store setup must succeed")
-	t.Cleanup(cleanUp)
-
-	ctrl := gomock.NewController(t)
-	perms := permissions.NewMockManager(ctrl)
-
-	accounts := account.NewMockManager(ctrl)
-	accounts.EXPECT().StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-	accounts.EXPECT().UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-	accounts.EXPECT().BufferUpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-
-	return &bootstrapFixture{
-		manager: NewManager(st, perms, accounts, nil),
-		store:   st,
-		perms:   perms,
-	}
-}
-
-func (f *bootstrapFixture) expectPermission(accountID, userID string, module modules.Module, op operations.Operation, allowed bool) {
-	f.perms.EXPECT().
-		ValidateUserPermissions(gomock.Any(), accountID, userID, module, op).
-		Return(allowed, context.Background(), nil)
-}
-
-func newBootstrapProvider(accountID string) *types.Provider {
-	p := types.NewProvider(accountID)
-	p.Name = "openai"
-	p.UpstreamURL = "https://api.openai.com"
-	p.APIKey = "sk-test"
-	p.Enabled = true
-	return p
-}
-
-// TestCreateProviderBootstrapRequiresSettingsPermission pins the gate on the
-// one-time settings bootstrap: creating the first provider with a
-// bootstrap_cluster pins the account's cluster and subdomain, which is a
-// settings write and must not ride on the providers permission alone.
-func TestCreateProviderBootstrapRequiresSettingsPermission(t *testing.T) {
-	ctx := context.Background()
-
-	t.Run("denied without settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-		f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, false)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.Error(t, err, "bootstrap without settings permission must fail")
-		var sErr *status.Error
-		require.ErrorAs(t, err, &sErr)
-		assert.Equal(t, status.PermissionDenied, sErr.Type(), "denial should surface as permission denied")
-
-		providers, err := f.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, "account1")
-		require.NoError(t, err)
-		assert.Empty(t, providers, "provider must not be persisted when bootstrap is denied")
-		_, err = f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-		assert.Error(t, err, "settings row must not be created when bootstrap is denied")
-	})
-
-	t.Run("allowed with settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-		f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, true)
-
-		created, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.NoError(t, err, "bootstrap with both permissions must succeed")
-		require.NotNil(t, created)
-
-		settings, err := f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-		require.NoError(t, err, "bootstrap must create the settings row")
-		assert.Equal(t, "cluster1.example.com", settings.Cluster, "settings should pin the bootstrap cluster")
-	})
-
-	t.Run("existing settings need no settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		require.NoError(t, f.store.SaveAgentNetworkSettings(ctx, &types.Settings{
-			AccountID: "account1",
-			Cluster:   "cluster1.example.com",
-			Subdomain: "existing",
-		}), "pre-existing settings row setup must succeed")
-
-		// Only the providers permission may be consulted: gomock fails the
-		// test on any unexpected settings-permission call.
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.NoError(t, err, "create with existing settings must not require the settings permission")
-	})
-
-	t.Run("no bootstrap cluster needs no settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "")
-		require.NoError(t, err, "create without bootstrap must not require the settings permission")
-	})
-}

management/internals/modules/agentnetwork/types/provider.go

@@ -164,7 +164,9 @@ func (p *Provider) FromAPIRequest(req *api.AgentNetworkProviderRequest) {
 		p.MetadataDisabled = *req.MetadataDisabled
 	}
 	// Identity-header overrides for catalogs flagged Customizable.
-	// Empty or omitted disables stamping for this dimension.
+	// nil pointer = "field omitted on the wire" → leave the stored
+	// value untouched (per the openapi description). Empty string is
+	// an explicit clear that disables stamping for this dimension.
 	if req.IdentityHeaderUserId != nil {
 		p.IdentityHeaderUserID = strings.TrimSpace(*req.IdentityHeaderUserId)
 	}
@@ -190,20 +192,16 @@ func (p *Provider) ToAPIResponse() *api.AgentNetworkProvider {
 	created := p.CreatedAt
 	updated := p.UpdatedAt
 	resp := &api.AgentNetworkProvider{
-		Id:          p.ID,
-		ProviderId:  p.ProviderID,
-		Name:        p.Name,
-		UpstreamUrl: p.UpstreamURL,
-		Models:      models,
-		// Always present on the wire so an explicitly cleared header
-		// round-trips as "" instead of vanishing from the response.
-		IdentityHeaderUserId: p.IdentityHeaderUserID,
-		IdentityHeaderGroups: p.IdentityHeaderGroups,
-		Enabled:              p.Enabled,
-		SkipTlsVerification:  p.SkipTLSVerification,
-		MetadataDisabled:     p.MetadataDisabled,
-		CreatedAt:            &created,
-		UpdatedAt:            &updated,
+		Id:                  p.ID,
+		ProviderId:          p.ProviderID,
+		Name:                p.Name,
+		UpstreamUrl:         p.UpstreamURL,
+		Models:              models,
+		Enabled:             p.Enabled,
+		SkipTlsVerification: p.SkipTLSVerification,
+		MetadataDisabled:    p.MetadataDisabled,
+		CreatedAt:           &created,
+		UpdatedAt:           &updated,
 	}
 	if len(p.ExtraValues) > 0 {
 		out := make(map[string]string, len(p.ExtraValues))
@@ -212,6 +210,14 @@ func (p *Provider) ToAPIResponse() *api.AgentNetworkProvider {
 		}
 		resp.ExtraValues = &out
 	}
+	if p.IdentityHeaderUserID != "" {
+		v := p.IdentityHeaderUserID
+		resp.IdentityHeaderUserId = &v
+	}
+	if p.IdentityHeaderGroups != "" {
+		v := p.IdentityHeaderGroups
+		resp.IdentityHeaderGroups = &v
+	}
 	return resp
 }
 

management/internals/modules/agentnetwork/types/provider_test.go

@@ -77,41 +77,3 @@ func TestProvider_MetadataDisabled_RoundTrip(t *testing.T) {
 	assert.False(t, p.MetadataDisabled, "explicit false must clear metadata_disabled")
 	assert.False(t, p.ToAPIResponse().MetadataDisabled, "response must reflect the cleared value")
 }
-
-// TestProvider_IdentityHeaders_AlwaysOnWire pins that the identity header
-// fields are always present in the API response — an explicitly cleared
-// ("") header must round-trip as "" rather than vanish, so API consumers
-// (e.g. the Terraform provider) never observe a value other than the one
-// they wrote.
-func TestProvider_IdentityHeaders_AlwaysOnWire(t *testing.T) {
-	set := "x-bf-dim-netbird_user_id"
-	empty := ""
-
-	base := func() *api.AgentNetworkProviderRequest {
-		return &api.AgentNetworkProviderRequest{
-			ProviderId:  "custom",
-			Name:        "bifrost",
-			UpstreamUrl: "https://bifrost.internal",
-		}
-	}
-
-	p := NewProvider("acc-1")
-	resp := p.ToAPIResponse()
-	assert.Equal(t, "", resp.IdentityHeaderUserId, "unset header must surface as empty string, not be omitted")
-	assert.Equal(t, "", resp.IdentityHeaderGroups, "unset header must surface as empty string, not be omitted")
-
-	req := base()
-	req.IdentityHeaderUserId = &set
-	p.FromAPIRequest(req)
-	assert.Equal(t, set, p.ToAPIResponse().IdentityHeaderUserId, "configured header must round-trip")
-
-	// Omitting the field preserves it.
-	p.FromAPIRequest(base())
-	assert.Equal(t, set, p.ToAPIResponse().IdentityHeaderUserId, "omitted header must preserve the stored value")
-
-	// An explicit "" clears it AND stays visible on the wire.
-	req = base()
-	req.IdentityHeaderUserId = &empty
-	p.FromAPIRequest(req)
-	assert.Equal(t, "", p.ToAPIResponse().IdentityHeaderUserId, "cleared header must round-trip as empty string")
-}

management/internals/modules/agentnetwork/types/settings.go

@@ -1,7 +1,6 @@
 package types
 
 import (
-	"strings"
 	"time"
 
 	"github.com/netbirdio/netbird/shared/management/http/api"
@@ -43,34 +42,18 @@ type Settings struct {
 // schema cohesive.
 func (Settings) TableName() string { return "agent_network_settings" }
 
-// DefaultSettings returns the settings an account observes before its row is
-// bootstrapped: log collection on with the default retention, everything else
-// off, and no cluster/subdomain assigned yet. Bootstrap persists exactly these
-// values plus the assigned cluster and subdomain, so the pre-bootstrap read
-// and the freshly bootstrapped row agree.
-func DefaultSettings(accountID string) *Settings {
-	return &Settings{
-		AccountID:              accountID,
-		EnableLogCollection:    true,
-		AccessLogRetentionDays: DefaultAccessLogRetentionDays,
-	}
-}
-
 // Endpoint returns the bare hostname agents reach this account at:
-// `<subdomain>.<cluster>`. Empty until both halves are assigned at bootstrap.
+// `<subdomain>.<cluster>`.
 func (s *Settings) Endpoint() string {
-	if s.Cluster == "" || s.Subdomain == "" {
-		return ""
-	}
 	return s.Subdomain + "." + s.Cluster
 }
 
-// ToAPIResponse renders the settings as the API representation. The
-// timestamps are omitted while zero — a default (not yet bootstrapped) view
-// has no persisted row to date.
+// ToAPIResponse renders the settings as the API representation.
 func (s *Settings) ToAPIResponse() *api.AgentNetworkSettings {
+	created := s.CreatedAt
+	updated := s.UpdatedAt
 	retention := s.AccessLogRetentionDays
-	resp := &api.AgentNetworkSettings{
+	return &api.AgentNetworkSettings{
 		Cluster:                s.Cluster,
 		Subdomain:              s.Subdomain,
 		Endpoint:               s.Endpoint(),
@@ -78,27 +61,14 @@ func (s *Settings) ToAPIResponse() *api.AgentNetworkSettings {
 		EnablePromptCollection: s.EnablePromptCollection,
 		RedactPii:              s.RedactPii,
 		AccessLogRetentionDays: &retention,
+		CreatedAt:              &created,
+		UpdatedAt:              &updated,
 	}
-	if !s.CreatedAt.IsZero() {
-		created := s.CreatedAt
-		resp.CreatedAt = &created
-	}
-	if !s.UpdatedAt.IsZero() {
-		updated := s.UpdatedAt
-		resp.UpdatedAt = &updated
-	}
-	return resp
 }
 
-// FromAPIRequest applies the request onto the receiver. The mutable
-// collection fields are always replaced with the request values. Cluster
-// participates only in bootstrap and the immutability check (see
-// Manager.UpdateSettings); Subdomain is server-assigned and never taken
-// from a request.
+// FromAPIRequest applies the mutable settings fields from the request. Cluster
+// and Subdomain are immutable and intentionally not touched here.
 func (s *Settings) FromAPIRequest(req *api.AgentNetworkSettingsRequest) {
-	if req.Cluster != nil {
-		s.Cluster = strings.TrimSpace(*req.Cluster)
-	}
 	s.EnableLogCollection = req.EnableLogCollection
 	s.EnablePromptCollection = req.EnablePromptCollection
 	s.RedactPii = req.RedactPii

management/internals/server/boot.go

@@ -24,13 +24,13 @@ import (
 
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/formatter/hook"
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
 	accesslogsmanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs/manager"
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
 	"github.com/netbirdio/netbird/management/server/activity"
 	activitystore "github.com/netbirdio/netbird/management/server/activity/store"
+	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	nbcache "github.com/netbirdio/netbird/management/server/cache"
 	nbContext "github.com/netbirdio/netbird/management/server/context"
 	nbhttp "github.com/netbirdio/netbird/management/server/http"
@@ -184,10 +184,6 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
 			grpc.ChainStreamInterceptor(realip.StreamServerInterceptorOpts(realipOpts...), streamInterceptor, proxyStream),
 		}
 
-		// Append interceptors contributed by registered gRPC extensions. These
-		// run after the built-in chain (ChainUnaryInterceptor is additive).
-		gRPCOpts = appendExtensionInterceptors(gRPCOpts, s.grpcExtensions)
-
 		if s.Config.HttpConfig.LetsEncryptDomain != "" {
 			certManager, err := encryption.CreateCertManager(s.Config.Datadir, s.Config.HttpConfig.LetsEncryptDomain)
 			if err != nil {
@@ -219,9 +215,6 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
 		mgmtProto.RegisterProxyServiceServer(gRPCAPIHandler, s.ReverseProxyGRPCServer())
 		log.Info("ProxyService registered on gRPC server")
 
-		// Register services contributed by external modules via the extension seam.
-		registerExtensions(gRPCAPIHandler, s.grpcExtensions)
-
 		return gRPCAPIHandler
 	})
 }