Merge branch 'main' into feature/policy-by-public-id

.devcontainer/Dockerfile

@@ -1,4 +1,4 @@
-FROM golang:1.25-bookworm
+FROM golang:1.26.7-bookworm
 
 RUN apt-get update && export DEBIAN_FRONTEND=noninteractive \
     && apt-get -y install --no-install-recommends\

.github/workflows/agent-network-e2e.yml

@@ -12,6 +12,13 @@ on:
           AWS issues it. Leave empty for the Sonnet 4.6 default.
         required: false
         default: ""
+      test_pattern:
+        description: >-
+          Package pattern to run. Defaults to the whole suite; narrow it to one
+          package (e.g. ./e2e/agentnetwork/...) when a run only needs that
+          package's answer and not the sixteen minutes the container suite costs.
+        required: false
+        default: "./e2e/..."
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -77,4 +84,8 @@ jobs:
           GOOGLE_VERTEX_PROJECT: ${{ secrets.E2E_GOOGLE_VERTEX_PROJECT }}
           GOOGLE_VERTEX_REGION: ${{ secrets.E2E_GOOGLE_VERTEX_REGION }}
           GOOGLE_VERTEX_MODEL: ${{ secrets.E2E_GOOGLE_VERTEX_MODEL }}
-        run: go test -tags e2e -timeout 40m -v ./e2e/...
+          # Read through an env var rather than interpolated into the run
+          # script: a dispatch input reaching a shell command directly is a
+          # script-injection seam, however trusted the dispatcher.
+          TEST_PATTERN: ${{ inputs.test_pattern || './e2e/...' }}
+        run: go test -tags e2e -timeout 40m -v "$TEST_PATTERN"

.github/workflows/buf.yml

@@ -0,0 +1,33 @@
+name: protobuf checks
+on:
+  push:
+    branches:
+      - main
+      - "release-*"
+  pull_request:
+    paths:
+      - ".github/workflows/buf.yml"
+      - "**/buf.yaml"
+      - "**/buf.lock"
+      - "**/buf.gen.yaml"
+      - "**.proto"
+permissions:
+  contents: read
+  pull-requests: read
+jobs:
+  buf:
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        with:
+          persist-credentials: false
+      - uses: bufbuild/buf-action@8c6a16e16f12ba20b6470afa9c2ba9b5ba8c97c3 # v1.5.0
+        with:
+          push: false
+          archive: false
+          pr_comment: false
+          build: false
+          lint: false
+          format: false
+          breaking: true

.github/workflows/golang-test-linux.yml

@@ -233,7 +233,7 @@ jobs:
             -e GOCACHE=${CONTAINER_GOCACHE} \
             -e GOMODCACHE=${CONTAINER_GOMODCACHE} \
             -e CONTAINER=${CONTAINER} \
-            golang:1.25-alpine \
+            golang:1.26.7-alpine \
             sh -c ' \
               apk update; apk add --no-cache \
                 ca-certificates iptables ip6tables dbus dbus-dev libpcap-dev build-base; \
@@ -730,6 +730,11 @@ jobs:
       - name: Install modules
         run: go mod tidy
 
+      - name: Run Mage
+        uses: magefile/mage-action@a662bd8c29d8106879588cfff83b2faf6e6f59db # v4.0.0
+        with:
+          install-only: true
+
       - name: check git status
         run: git --no-pager diff --exit-code
 
@@ -738,9 +743,7 @@ jobs:
           CGO_ENABLED=1 GOARCH=${{ matrix.arch }} \
           NETBIRD_STORE_ENGINE=${{ matrix.store }} \
           CI=true \
-          go test -tags=integration -coverprofile=coverage.txt \
+          mage integrationtest:all -gotestflags="-coverprofile=coverage.txt"
-          -exec 'sudo --preserve-env=CI,NETBIRD_STORE_ENGINE' \
-          -timeout 20m ./management/server/http/...
 
       - name: Upload coverage reports to Codecov
         if: matrix.arch == 'amd64'

.github/workflows/mobile-build-validation.yml

@@ -1,72 +0,0 @@
-name: Mobile
-
-on:
-  push:
-    branches:
-      - main
-      - "release-*"
-  pull_request:
-
-concurrency:
-  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
-  cancel-in-progress: true
-
-jobs:
-  android_build:
-    name: "Android / Build"
-    runs-on: ubuntu-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-      - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
-        with:
-          go-version-file: "go.mod"
-      - name: Setup Android SDK
-        uses: android-actions/setup-android@40fd30fb8d7440372e1316f5d1809ec01dcd3699 # v4.0.1
-        with:
-          cmdline-tools-version: 8512546
-      - name: Setup Java
-        uses: actions/setup-java@1bcf9fb12cf4aa7d266a90ae39939e61372fe520
-        with:
-          java-version: "11"
-          distribution: "adopt"
-      - name: NDK Cache
-        id: ndk-cache
-        uses: actions/cache@2c8a9bd7457de244a408f35966fab2fb45fda9c8 # v6.0.0
-        with:
-          path: /usr/local/lib/android/sdk/ndk
-          key: ndk-cache-23.1.7779620
-      - name: Setup NDK
-        run: /usr/local/lib/android/sdk/cmdline-tools/7.0/bin/sdkmanager --install "ndk;23.1.7779620"
-      - name: install gomobile
-        run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20251113184115-a159579294ab
-      - name: gomobile init
-        run: gomobile init
-      - name: build android netbird lib
-        run: PATH=$PATH:$(go env GOPATH) gomobile bind -o $GITHUB_WORKSPACE/netbird.aar -javapkg=io.netbird.gomobile -ldflags="-checklinkname=0 -X golang.zx2c4.com/wireguard/ipc.socketDirectory=/data/data/io.netbird.client/cache/wireguard -X github.com/netbirdio/netbird/version.version=buildtest"  $GITHUB_WORKSPACE/client/android
-        env:
-          CGO_ENABLED: 0
-          ANDROID_NDK_HOME: /usr/local/lib/android/sdk/ndk/23.1.7779620
-  ios_build:
-    name: "iOS / Build"
-    runs-on: macos-latest
-    steps:
-      - name: Checkout repository
-        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
-        with:
-          persist-credentials: false
-      - name: Install Go
-        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
-        with:
-          go-version-file: "go.mod"
-      - name: install gomobile
-        run: go install golang.org/x/mobile/cmd/gomobile@v0.0.0-20251113184115-a159579294ab
-      - name: gomobile init
-        run: gomobile init
-      - name: build iOS netbird lib
-        run: PATH=$PATH:$(go env GOPATH) gomobile bind -target=ios -bundleid=io.netbird.framework -ldflags="-X github.com/netbirdio/netbird/version.version=buildtest" -o ./NetBirdSDK.xcframework ./client/ios/NetBirdSDK
-        env:
-          CGO_ENABLED: 0

.github/workflows/no-new-replace.yml

@@ -0,0 +1,78 @@
+name: No New Replace Directives
+
+on:
+  pull_request:
+    paths:
+      - "go.mod"
+
+permissions:
+  contents: read
+
+concurrency:
+  group: ${{ github.workflow }}-${{ github.ref }}-${{ github.head_ref || github.actor_id }}
+  cancel-in-progress: true
+
+jobs:
+  check-replace-directives:
+    name: check-replace-directives
+    runs-on: ubuntu-latest
+    steps:
+      - name: Checkout code
+        uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
+        with:
+          persist-credentials: false
+          fetch-depth: 0
+
+      - name: Install Go
+        uses: actions/setup-go@924ae3a1cded613372ab5595356fb5720e22ba16 # v6.5.0
+        with:
+          go-version-file: go.mod
+
+      - name: Compare replace directives against the base branch
+        env:
+          BASE_SHA: ${{ github.event.pull_request.base.sha }}
+        run: |
+          set -euo pipefail
+
+          # A replace directive only applies when this module is the main
+          # module. Anything importing netbird as a library, the embedded
+          # clients among them, resolves the replaced path upstream instead and
+          # fails to build against whatever the replacement provides. Requiring
+          # a fork under its own module path avoids that; a replace does not.
+          #
+          # go.mod is parsed rather than diffed so that reordering, comments and
+          # single-line versus block syntax do not register as changes.
+          #
+          # Versions are part of the key because a replace can be scoped to one
+          # version of a module. Keyed on paths alone, retargeting such a
+          # directive at a different version would read as unchanged.
+          list_replaces() {
+            go mod edit -json "$1" \
+              | jq -r '
+                  def ref: .Path + (if (.Version // "") == "" then "" else " " + .Version end);
+                  (.Replace // [])[] | "\(.Old | ref) => \(.New | ref)"
+                ' \
+              | sort
+          }
+
+          git show "${BASE_SHA}:go.mod" > /tmp/base-go.mod
+          list_replaces /tmp/base-go.mod > /tmp/base-replaces
+          list_replaces go.mod > /tmp/head-replaces
+
+          added=$(comm -13 /tmp/base-replaces /tmp/head-replaces)
+          if [ -n "$added" ]; then
+            echo "::error::This PR adds a replace directive to go.mod:"
+            echo "$added" | sed 's/^/  /'
+            echo ""
+            echo "A replace directive applies only to the main module, so it does not"
+            echo "reach anything that imports netbird as a library. Require the module"
+            echo "under a path you control instead, as done for github.com/netbirdio/go-nat."
+            exit 1
+          fi
+
+          removed=$(comm -23 /tmp/base-replaces /tmp/head-replaces)
+          if [ -n "$removed" ]; then
+            echo "This PR removes replace directives:"
+            echo "$removed" | sed 's/^/  /'
+          fi
+          echo "No new replace directives."

.github/workflows/release.yml

@@ -215,7 +215,7 @@ jobs:
           echo "GPG_RPM_KEY_FILE=/tmp/gpg-rpm-signing-key.asc" >> $GITHUB_ENV
 
       - name: Install goversioninfo
-        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@233067e
+        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@b66839b # v1.7.0
       - name: Generate windows syso amd64
         run: goversioninfo  -icon client/ui/build/windows/icon.ico -manifest client/manifest.xml -product-name ${{ env.PRODUCT_NAME }} -copyright "${{ env.COPYRIGHT }}" -ver-major ${{ steps.semver_parser.outputs.major }} -ver-minor ${{ steps.semver_parser.outputs.minor }} -ver-patch ${{ steps.semver_parser.outputs.patch }} -ver-build 0 -file-version ${{ steps.semver_parser.outputs.fullversion }}.0 -product-version ${{ steps.semver_parser.outputs.fullversion }}.0 -o client/resources_windows_amd64.syso
       - name: Generate windows syso arm64
@@ -435,7 +435,7 @@ jobs:
           tar -xf llvm-mingw-20250709-ucrt-ubuntu-22.04-x86_64.tar.xz
           echo "/tmp/llvm-mingw-20250709-ucrt-ubuntu-22.04-x86_64/bin" >> $GITHUB_PATH
       - name: Install goversioninfo
-        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@233067e
+        run: go install github.com/josephspurrier/goversioninfo/cmd/goversioninfo@b66839b # v1.7.0
       - name: Install wails3 CLI
         # Version derived from go.mod so the binding generator always matches
         # the wails runtime the binary links against.

.github/workflows/sync-tag.yml

@@ -37,3 +37,16 @@ jobs:
           repo: netbirdio/ios-client
           token: ${{ secrets.NC_GITHUB_TOKEN }}
           inputs: '{ "tag": "${{ github.ref_name }}" }'
+
+  trigger_dashboard_bump:
+    runs-on: ubuntu-latest
+    if: github.event.created && !github.event.deleted && startsWith(github.ref, 'refs/tags/v') && !contains(github.ref_name, '-')
+    steps:
+      - name: Trigger dashboard wasm client bump
+        uses: benc-uk/workflow-dispatch@31e2b3319479a63f0ab15bf800eff9e913504e26 # v1.3.2
+        with:
+          workflow: bump-netbird.yml
+          ref: main
+          repo: netbirdio/dashboard
+          token: ${{ secrets.NC_GITHUB_TOKEN }}
+          inputs: '{ "tag": "${{ github.ref_name }}" }'

.goreleaser_ui.yaml

@@ -92,6 +92,11 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+      # Names the polkit action for the elevation prompt the app raises when an
+      # unprivileged user changes a privileged setting; without it the dialog
+      # shows a raw command line.
+      - src: client/ui/build/linux/polkit/io.netbird.settings.policy
+        dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
     dependencies:
       - netbird (>= 0.75.0)
       - libgtk-4-1 (>= 4.14)
@@ -116,6 +121,11 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+      # Names the polkit action for the elevation prompt the app raises when an
+      # unprivileged user changes a privileged setting; without it the dialog
+      # shows a raw command line.
+      - src: client/ui/build/linux/polkit/io.netbird.settings.policy
+        dst: /usr/share/polkit-1/actions/io.netbird.settings.policy
     dependencies:
       - netbird >= 0.75.0
       - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)

AGENTS.md

@@ -1,6 +1,6 @@
 # NetBird Agent Guidelines
 
-**NetBird** is an open-source connectivity platform: a WireGuard®-based overlay
+**NetBird** is an open source connectivity platform: a WireGuard®-based overlay
 network with a control plane. The **agent** (`client/`) runs on user machines as
 a privileged daemon and manages the WireGuard interface, routing, firewall, and
 DNS. **Management** (`management/`) is the control plane and REST/gRPC API,

CONTRIBUTING.md

@@ -192,7 +192,7 @@ dependencies are installed. Here is a short guide on how that can be done.
 
 ### Requirements
 
-#### Go 1.25
+#### Go 1.26
 
 Follow the installation guide from https://go.dev/
 
@@ -200,7 +200,7 @@ Follow the installation guide from https://go.dev/
 
 The desktop UI client (`client/ui`) is built with [Wails v3](https://v3.wails.io/) and a React frontend rendered in a WebView. To build it you need:
 
-- Go ≥ 1.25
+- Go ≥ 1.26
 - Node ≥ 20 and **pnpm** (`corepack enable && corepack prepare pnpm@latest --activate`)
 - The `wails3` CLI: `go install github.com/wailsapp/wails/v3/cmd/wails3@latest`
 - The `task` runner: `go install github.com/go-task/task/v3/cmd/task@latest`
@@ -479,7 +479,7 @@ go test -race ./client/internal/dns/...
 
 ## Checklist before submitting a PR
 
-As a critical network service and open-source project, we must enforce a few
+As a critical network service and open source project, we must enforce a few
 things before submitting a pull request. The
 [pull request template](/.github/pull_request_template.md) mirrors this list —
 fill it in rather than deleting it.

README.md

@@ -26,7 +26,7 @@
   <strong>
     Start using NetBird at <a href="https://netbird.io/pricing">netbird.io</a>
     <br/>
-    See <a href="https://netbird.io/docs/">Documentation</a>
+    See <a href="https://docs.netbird.io/">Documentation</a>
     <br/>
     Join our <a href="https://docs.netbird.io/slack-url">Slack channel</a> or our <a href="https://forum.netbird.io">Community forum</a>
   </strong>
@@ -130,7 +130,7 @@ In November 2022, NetBird joined the [StartUpSecure program](https://www.forschu
 ![CISPA_Logo_BLACK_EN_RZ_RGB (1)](https://user-images.githubusercontent.com/700848/203091324-c6d311a0-22b5-4b05-a288-91cbc6cdcc46.png)
 
 ### Acknowledgements
-We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
+We build on open source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
 
 ### Legal
 This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/.

SECURITY.md

@@ -14,7 +14,7 @@ Report security issues one of these two ways:
   on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
 - **Email** — `security@netbird.io`.
 
-If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than
+If the finding affects NetBird Cloud or our hosted infrastructure rather than the open source code, email us rather than
 filing a repository report.
 
 ### What to include

agent-network/README.md

@@ -40,6 +40,35 @@ You can then use this private endpoint to configure your AI agents, whether that
 Full step-by-step setup:
 **https://docs.netbird.io/agent-network/quickstart**
 
+## Client settings that don't follow the endpoint
+
+Most of an agent's traffic follows the base URL you hand it, but a few
+client-side checks call their vendor directly and never reach the proxy. On a
+network that blocks direct egress they fail even though inference works, so
+they are worth setting once when you roll the endpoint out.
+
+For Claude Code:
+
+- **Fast mode** checks availability against `api.anthropic.com` rather than the
+  configured base URL. Set `CLAUDE_CODE_SKIP_FAST_MODE_ORG_CHECK=1` when the
+  agent authenticates with `ANTHROPIC_AUTH_TOKEN` alone (the usual shape when
+  the proxy injects the real provider key) or when a TLS-inspecting proxy
+  answers the check itself. Set
+  `CLAUDE_CODE_SKIP_FAST_MODE_NETWORK_ERRORS=1` when the network refuses the
+  connection outright. Fast mode is an Anthropic-API feature, so it is
+  unavailable on a Bedrock- or Vertex-backed endpoint whatever you set.
+- **Model discovery** is off by default. Set
+  `CLAUDE_CODE_ENABLE_GATEWAY_MODEL_DISCOVERY=1` for the picker to list the
+  models your policies authorise; the proxy filters the response to that set.
+  The client gives discovery a three-second budget and treats any redirect as
+  a failure, so the endpoint must serve `/v1/models` directly.
+- **The WebFetch domain safety check** also calls `api.anthropic.com` directly
+  and is unaffected by the variables above.
+
+Allowing direct egress to `api.anthropic.com` covers the network cases but not
+the credential one, where the check reaches Anthropic and is rejected because
+the agent presents a proxy-issued key.
+
 ## Architecture 
 
 Agent Network is built on two existing NetBird capabilities:
@@ -67,6 +96,42 @@ components:
   — the management-side control plane: providers, policies, guardrails, limits, routing,
   and usage/access logs.
 
+## Access roles
+
+Agent Network permissions build on the account permission matrix
+([`management/server/permissions/`](../management/server/permissions)). The
+`agent_network` area is split into dotted submodules (`agent_network.providers`,
+`.policies`, `.guardrails`, `.budgets`, `.usage`, `.logs`, `.settings`); a role may
+grant a single submodule or the parent, which cascades to all of them.
+
+Two roles delegate Agent Network access without account-admin rights:
+
+- **`agent_network_admin`** — full control over the whole `agent_network` area plus
+  read-only users, groups, peers, and account info (needed to build policies).
+  Nothing else in the account.
+- **`usage_viewer`** — the regular User baseline plus read on
+  `agent_network.usage` (the aggregated usage and cost overview) and read-only
+  access to the resources the usage filters resolve against: users, groups,
+  peers, and the provider list (connection config redacted — no upstream URLs
+  or operator-supplied header values). No policies, and no account-wide
+  request-level access logs; like any caller, it still reads its own requests
+  through the self-scoped endpoints below.
+
+Every authenticated user, regardless of role, can read the caller-scoped
+self-service endpoint `GET /api/agent-network/agent-config` (the endpoint, providers,
+and models the caller's own policies allow — what a local AI tool needs and nothing
+more). The regular usage and access-log endpoints self-scope instead of denying:
+a caller without the account-wide grant gets their own rows back, so "my usage"
+and "my requests" are the same endpoints the admin dashboard uses. The provider
+list self-scopes the same way — a caller without the providers grant gets the
+providers their own policies authorize, reduced to the display surface, with
+each provider's model list cut to what the caller's policy guardrails and the
+provider's declared models effectively permit (the same computation the setup
+answer and the proxy use). This feeds the dashboard's provider and model
+filters. Role
+definitions live in
+[`management/server/permissions/roles/`](../management/server/permissions/roles).
+
 ## Documentation
 
 Full documentation, architecture, and quickstart:

client/android/client.go

@@ -26,6 +26,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/routemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netevents"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -40,11 +41,6 @@ const (
 	AnonymizeLevelStrict  = nbAnonymize.LevelStrictString
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // TunAdapter export internal TunAdapter for mobile
 type TunAdapter interface {
 	device.TunAdapter
@@ -85,6 +81,10 @@ type Client struct {
 	deviceName            string
 	uiVersion             string
 	networkChangeListener listener.NetworkChangeListener
+	// netMgr outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run and RunWithoutLogin inject its state and
+	// sweeper into each new ConnectClient.
+	netMgr *netevents.Manager
 
 	stateMu       sync.RWMutex
 	connectClient *internal.ConnectClient
@@ -148,14 +148,17 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
 	execWorkaround(androidSDKVersion)
 
 	net.SetAndroidProtectSocketFn(tunAdapter.ProtectSocket)
+	system.SetIFaceDiscover(iFaceDiscover)
+	recorder := peer.NewRecorder("")
 	return &Client{
 		deviceName:            deviceName,
 		uiVersion:             uiVersion,
 		tunAdapter:            tunAdapter,
 		iFaceDiscover:         iFaceDiscover,
-		recorder:              peer.NewRecorder(""),
+		recorder:              recorder,
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
+		netMgr:                netevents.NewManager(recorder),
 	}
 }
 
@@ -196,7 +199,9 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	}
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetEvents(c.netMgr))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	// This path runs the interactive SSO flow, so reaching here means the peer
 	// is authenticated again — release the latch Status() reports from. Clear
@@ -237,7 +242,8 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetEvents(c.netMgr))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
@@ -285,6 +291,26 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
 	}, nil
 }
 
+// SetNetworkAvailable feeds OS-reported network availability into the client.
+// While unavailable, the internal reconnect loops suspend their attempts and
+// the connection listener reports NoNetwork instead of Connecting; when
+// availability returns, the loops resume immediately with a fresh backoff.
+// Losing the last network also sweeps the registered connections: nothing can
+// redial while offline, so the stale sockets would otherwise stay silently
+// "connected" until their own timeouts and the client would keep reporting
+// Connected with no network at all.
+func (c *Client) SetNetworkAvailable(available bool) {
+	c.netMgr.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange marks the management, signal and relay connections
+// stale after the OS switched networks and schedules a sweep that cuts
+// whatever has not redialed on the new network by then. The engine and the
+// TUN device stay untouched.
+func (c *Client) NotifyNetworkChange() {
+	c.netMgr.NotifyNetworkChange()
+}
+
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.
 // It works both with and without a running engine. anonymizeLevel is "default"
 // or "strict"; strict also anonymizes internal IP ranges, peer names, and
@@ -525,7 +551,11 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	if listener == nil {
+		c.recorder.RemoveConnectionListener()
+		return
+	}
+	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
 }
 
 // RemoveConnectionListener remove connection listener

client/android/connection_listener.go

@@ -0,0 +1,41 @@
+//go:build android
+
+package android
+
+import (
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+// Client state values delivered via ConnectionListener.OnStateChanged,
+// re-exported as basic constants so gomobile emits them into the generated
+// Java bindings. They mirror peer.ClientState*: append-only, never reorder.
+const (
+	ClientStateDisconnected  = int(peer.ClientStateDisconnected)
+	ClientStateConnected     = int(peer.ClientStateConnected)
+	ClientStateConnecting    = int(peer.ClientStateConnecting)
+	ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
+	ClientStateNoNetwork     = int(peer.ClientStateNoNetwork)
+)
+
+// ConnectionListener export internal Listener for mobile. It mirrors
+// peer.Listener with OnStateChanged taking a plain int (one of the
+// ClientState* constants), because gomobile cannot bind named types.
+type ConnectionListener interface {
+	OnStateChanged(state int)
+	OnConnected()
+	OnDisconnected()
+	OnConnecting()
+	OnDisconnecting()
+	OnAddressChanged(string, string)
+	OnPeersListChanged(int)
+}
+
+// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
+// peer.Listener, converting the typed state to the int the binding carries.
+type connectionListenerAdapter struct {
+	ConnectionListener
+}
+
+func (a connectionListenerAdapter) OnStateChanged(state peer.ClientState) {
+	a.ConnectionListener.OnStateChanged(int(state))
+}

client/android/login.go

@@ -8,6 +8,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/mobile"
 	"github.com/netbirdio/netbird/client/system"
 )
 
@@ -181,7 +182,7 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 	// 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 {
+		if err := mobile.WriteProfileEmail(a.cfgPath, email); err != nil {
 			log.Warnf("failed to store profile account email: %v", err)
 		}
 	}
@@ -191,39 +192,49 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 	return nil
 }
 
-// loginHintSetter is implemented by both concrete flows (PKCE and device code)
-// but absent from the OAuthFlow interface, hence the assertion below — the same
-// way internal/auth wires it in authenticateWithPKCEFlow.
-type loginHintSetter interface {
-	SetLoginHint(hint string)
-}
-
 func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, isAndroidTV bool) (*auth.TokenInfo, error) {
-	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV)
+	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV, profileLoginHint(a.cfgPath))
 	if err != nil {
 		return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
 	}
 
-	// An empty hint is deliberate, not a fallback: a fresh or logged-out profile
+	return runOAuthFlow(a.ctx, oAuthFlow, urlOpener, nil)
-	// leaves the choice to the IdP, which is how accounts get switched.
+}
-	if a.cfgPath != "" {
+
-		if hint := readProfileEmail(a.cfgPath); hint != "" {
+// profileLoginHint returns the stored account email for the profile at cfgPath.
-			if setter, ok := oAuthFlow.(loginHintSetter); ok {
+// An empty hint is deliberate, not a fallback: a fresh profile leaves the
-				setter.SetLoginHint(hint)
+// choice to the IdP. Switching accounts is done by switching or removing
-			}
+// profiles, not by logging out — logout keeps the email.
-		}
+func profileLoginHint(cfgPath string) string {
+	if cfgPath == "" {
+		return ""
+	}
+	return mobile.ReadProfileEmail(cfgPath)
+}
+
+// runOAuthFlow drives an already acquired OAuth flow to a token: requests the
+// flow info, presents the verification URL through the opener and waits for
+// the browser round-trip. Open is called synchronously — it is what marks the
+// surface as opened on the client side, and a fast token's OnLoginSuccess is
+// a no-op until it has, so the dismissal would be dropped rather than
+// delayed. Openers must therefore not block: they post their UI work and
+// return. onWaiting, when set, runs after the URL is shown, right before the
+// blocking wait.
+func runOAuthFlow(ctx context.Context, flow auth.OAuthFlow, urlOpener URLOpener, onWaiting func()) (*auth.TokenInfo, error) {
+	flowInfo, err := flow.RequestAuthInfo(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("request auth info: %w", err)
 	}
 
-	flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO())
+	urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode)
-	if err != nil {
+
-		return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err)
+	if onWaiting != nil {
+		onWaiting()
 	}
 
-	go urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode)
+	tokenInfo, err := flow.WaitToken(ctx, flowInfo)
-
-	tokenInfo, err := oAuthFlow.WaitToken(a.ctx, flowInfo)
 	if err != nil {
-		return nil, fmt.Errorf("waiting for browser login failed: %v", err)
+		return nil, fmt.Errorf("wait for token: %w", err)
 	}
 
 	return &tokenInfo, nil

client/android/profile_manager.go

@@ -3,41 +3,37 @@
 package android
 
 import (
-	"fmt"
+	"github.com/netbirdio/netbird/client/mobile"
-	"os"
-	"path/filepath"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
 )
 
 const (
-	// Android uses a single user context per app (non-empty username required by ServiceManager)
+	// Android uses a single user context per app.
 	androidUsername = "android"
 )
 
-// Profile represents a profile for gomobile
+// 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.
+	// completed an SSO login. Kept across logouts; cleared when the profile is
+	// removed. See client/mobile/profile_state.go.
 	Email    string
 	IsActive bool
 }
 
-// ProfileArray wraps profiles for gomobile compatibility
+// ProfileArray wraps profiles for gomobile compatibility (gomobile cannot
+// bind Go slices directly).
 type ProfileArray struct {
 	items []*Profile
 }
 
-// Length returns the number of profiles
+// Length returns the number of profiles.
 func (p *ProfileArray) Length() int {
 	return len(p.items)
 }
 
-// Get returns the profile at index i
+// Get returns the profile at index i, or nil if out of range.
 func (p *ProfileArray) Get(i int) *Profile {
 	if i < 0 || i >= len(p.items) {
 		return nil
@@ -45,248 +41,98 @@ func (p *ProfileArray) Get(i int) *Profile {
 	return p.items[i]
 }
 
-/*
+// ProfileManager adapts the shared mobile profile manager (client/mobile) to
-
+// gomobile-friendly types. See that package for the on-disk layout and
-/data/data/io.netbird.client/files/           ← configDir parameter
+// semantics.
-├── netbird.cfg                                 ← Default profile config
-├── state.json                                  ← Default profile state
-├── active_profile.json                         ← Active profile tracker (JSON with Name + Username)
-└── profiles/                                   ← Subdirectory for non-default profiles
-    ├── work.json                              			← Legacy work profile config
-    ├── work.state.json                        			← Legacy work profile state
-    ├── 4c5f5c8198c3989cffb5b5394f5a7ae0.json  			← ID profile config
-    ├── 4c5f5c8198c3989cffb5b5394f5a7ae0.state.json ← ID profile state
-*/
-
-// ProfileManager manages profiles for Android
-// It wraps the internal profilemanager to provide Android-specific behavior
 type ProfileManager struct {
-	configDir  string
+	impl *mobile.ProfileManager
-	serviceMgr *profilemanager.ServiceManager
 }
 
-// NewProfileManager creates a new profile manager for Android
+// NewProfileManager creates a new profile manager for Android. configDir is
+// the app's files directory.
 func NewProfileManager(configDir string) *ProfileManager {
-	// Set the default config path for Android (stored in root configDir, not profiles/)
+	return &ProfileManager{impl: mobile.NewProfileManager(configDir, androidUsername)}
-	defaultConfigPath := filepath.Join(configDir, defaultConfigFilename)
-
-	// Set global paths for Android
-	profilemanager.DefaultConfigPathDir = configDir
-	profilemanager.DefaultConfigPath = defaultConfigPath
-	profilemanager.ActiveProfileStatePath = filepath.Join(configDir, "active_profile.json")
-
-	// Create ServiceManager with profiles/ subdirectory
-	// This avoids modifying the global ConfigDirOverride for profile listing
-	profilesDir := filepath.Join(configDir, profilesSubdir)
-	serviceMgr := profilemanager.NewServiceManagerWithProfilesDir(defaultConfigPath, profilesDir)
-
-	return &ProfileManager{
-		configDir:  configDir,
-		serviceMgr: serviceMgr,
-	}
 }
 
-// ListProfiles returns all available profiles
+// ListProfiles returns all available profiles, including the default profile,
+// with their active status set.
 func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
-	// Use ServiceManager (looks in profiles/ directory, checks active_profile.json for IsActive)
+	profiles, err := pm.impl.ListProfiles()
-	internalProfiles, err := pm.serviceMgr.ListProfiles(androidUsername)
 	if err != nil {
-		return nil, fmt.Errorf("failed to list profiles: %w", err)
+		return nil, err
 	}
 
-	// Convert internal profiles to Android Profile type
+	items := make([]*Profile, 0, len(profiles))
-	var profiles []*Profile
+	for i := range profiles {
-	for _, p := range internalProfiles {
+		items = append(items, fromMobileProfile(&profiles[i]))
-		profiles = append(profiles, &Profile{
-			ID:       p.ID.String(),
-			Name:     p.Name,
-			Email:    pm.profileEmail(p.ID.String()),
-			IsActive: p.IsActive,
-		})
 	}
-
+	return &ProfileArray{items: items}, nil
-	return &ProfileArray{items: profiles}, nil
 }
 
-// GetActiveProfile returns the currently active profile name
+// GetActiveProfile returns the currently active profile.
 func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
-	// Use ServiceManager to stay consistent with ListProfiles
+	p, err := pm.impl.GetActiveProfile()
-	// ServiceManager uses active_profile.json
-	activeState, err := pm.serviceMgr.GetActiveProfileState()
 	if err != nil {
-		return nil, fmt.Errorf("failed to get active profile: %w", err)
+		return nil, err
 	}
-
+	return fromMobileProfile(p), nil
-	// ActiveProfileState only stores the ID (and username), not the display
-	// name. Resolve the ID to the full profile so callers get the real Name.
-	prof, err := pm.serviceMgr.ResolveProfile(activeState.ID.String(), androidUsername)
-	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
+// SwitchProfile records the given profile ID as the active profile. The caller
-// an unresolvable path degrades to "" rather than an error.
+// must stop the VPN tunnel before switching.
-func (pm *ProfileManager) profileEmail(id string) string {
-	configPath, err := pm.getProfileConfigPath(id)
-	if err != nil {
-		return ""
-	}
-	return readProfileEmail(configPath)
-}
-
-// SwitchProfile switches to a different profile
 func (pm *ProfileManager) SwitchProfile(id string) error {
-	// Use ServiceManager to stay consistent with ListProfiles
+	return pm.impl.SwitchProfile(id)
-	// ServiceManager uses active_profile.json
-	err := pm.serviceMgr.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		ID:       profilemanager.ID(id),
-		Username: androidUsername,
-	})
-	if err != nil {
-		return fmt.Errorf("failed to switch profile: %w", err)
-	}
-
-	log.Infof("switched to profile: %s", id)
-	return nil
 }
 
-// AddProfile creates a new profile
+// AddProfile creates a new profile with the given display name and a
+// generated ID.
 func (pm *ProfileManager) AddProfile(profileName string) error {
-	// Use ServiceManager (creates profile in profiles/ directory)
+	_, err := pm.impl.AddProfile(profileName)
-	profile, err := pm.serviceMgr.AddProfile(profileName, androidUsername)
+	return err
-	if err != nil {
-		return fmt.Errorf("failed to add profile: %w", err)
-	}
-
-	log.Infof("created new profile: %s", profile.ID)
-	return nil
 }
 
-// LogoutProfile logs out from a profile (clears authentication)
+// RenameProfile changes the display name of the profile identified by id. The
-func (pm *ProfileManager) LogoutProfile(id string) error {
+// on-disk filename (the ID) is left unchanged.
-	configPath, err := pm.getProfileConfigPath(id)
-	if err != nil {
-		return err
-	}
-
-	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
-		return fmt.Errorf("id '%s' is not valid", id)
-	}
-
-	// Check if profile exists
-	if _, err := os.Stat(configPath); os.IsNotExist(err) {
-		return fmt.Errorf("profile '%s' does not exist", id)
-	}
-
-	// Read current config using internal profilemanager
-	config, err := profilemanager.ReadConfig(configPath)
-	if err != nil {
-		return fmt.Errorf("failed to read profile config: %w", err)
-	}
-
-	// Clear authentication by removing private key and SSH key
-	config.PrivateKey = ""
-	config.SSHKey = ""
-
-	// Save config using internal profilemanager
-	if err := profilemanager.WriteOutConfig(configPath, config); err != nil {
-		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
-}
-
-// RenameProfile changes a profile's display name. The profile ID, and therefore
-// its on-disk filename, is left untouched: only the "name" field of the config
-// is rewritten. This works for the default profile too, whose config lives in
-// netbird.cfg rather than under profiles/.
 func (pm *ProfileManager) RenameProfile(id string, newName string) error {
-	if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
+	return pm.impl.RenameProfile(id, newName)
-		return fmt.Errorf("failed to rename profile: %w", err)
-	}
-
-	log.Infof("renamed profile %s to: %s", id, newName)
-	return nil
 }
 
-// RemoveProfile deletes a profile
+// LogoutProfile clears authentication data for a profile, forcing a re-login.
+// The management URL and other settings are preserved.
+func (pm *ProfileManager) LogoutProfile(id string) error {
+	return pm.impl.LogoutProfile(id)
+}
+
+// RemoveProfile deletes a profile. The default profile and the active profile
+// cannot be removed.
 func (pm *ProfileManager) RemoveProfile(id string) error {
-	// Use ServiceManager (removes profile from profiles/ directory)
+	return pm.impl.RemoveProfile(id)
-	if err := pm.serviceMgr.RemoveProfile(profilemanager.ID(id), androidUsername); err != nil {
-		return fmt.Errorf("failed to remove profile: %w", err)
-	}
-
-	log.Infof("removed profile: %s", id)
-	return nil
 }
 
-// getProfileConfigPath returns the config file path for a profile
+// GetConfigPath returns the config file path for the given profile ID. Java
-// This is needed for Android-specific path handling (netbird.cfg for default profile)
+// should call this instead of constructing paths with Preferences.configFile().
-func (pm *ProfileManager) getProfileConfigPath(id string) (string, error) {
-	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
-		return "", fmt.Errorf("id %q is not valid", id)
-	}
-
-	if id == profilemanager.DefaultProfileName {
-		// Android uses netbird.cfg for default profile instead of default.json
-		// Default profile is stored in root configDir, not in profiles/
-		return filepath.Join(pm.configDir, defaultConfigFilename), nil
-	}
-
-	profilesDir := filepath.Join(pm.configDir, profilesSubdir)
-	return filepath.Join(profilesDir, id+".json"), nil
-}
-
-// GetConfigPath returns the config file path for a given profile id
-// Java should call this instead of constructing paths with Preferences.configFile()
 func (pm *ProfileManager) GetConfigPath(id string) (string, error) {
-	return pm.getProfileConfigPath(id)
+	return pm.impl.GetConfigPath(id)
 }
 
-// GetStateFilePath returns the state file path for a given profile
+// GetStateFilePath returns the state file path for the given profile ID. Java
-// Java should call this instead of constructing paths with Preferences.stateFile()
+// should call this instead of constructing paths with Preferences.stateFile().
 func (pm *ProfileManager) GetStateFilePath(id string) (string, error) {
-	if id == "" || id == profilemanager.DefaultProfileName {
+	return pm.impl.GetStateFilePath(id)
-		return filepath.Join(pm.configDir, "state.json"), nil
-	}
-
-	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
-		return "", fmt.Errorf("id %q is not valid", id)
-	}
-
-	profilesDir := filepath.Join(pm.configDir, profilesSubdir)
-	return filepath.Join(profilesDir, id+".state.json"), nil
 }
 
-// GetActiveConfigPath returns the config file path for the currently active profile
+// GetActiveConfigPath returns the config file path for the currently active
-// Java should call this instead of Preferences.getActiveProfileName() + Preferences.configFile()
+// profile.
 func (pm *ProfileManager) GetActiveConfigPath() (string, error) {
-	activeProfile, err := pm.GetActiveProfile()
+	return pm.impl.GetActiveConfigPath()
-	if err != nil {
-		return "", fmt.Errorf("failed to get active profile: %w", err)
-	}
-	return pm.GetConfigPath(activeProfile.ID)
 }
 
-// GetActiveStateFilePath returns the state file path for the currently active profile
+// GetActiveStateFilePath returns the state file path for the currently active
-// Java should call this instead of Preferences.getActiveProfileName() + Preferences.stateFile()
+// profile.
 func (pm *ProfileManager) GetActiveStateFilePath() (string, error) {
-	activeProfile, err := pm.GetActiveProfile()
+	return pm.impl.GetActiveStateFilePath()
-	if err != nil {
+}
-		return "", fmt.Errorf("failed to get active profile: %w", err)
+
-	}
+func fromMobileProfile(p *mobile.Profile) *Profile {
-	return pm.GetStateFilePath(activeProfile.ID)
+	return &Profile{ID: p.ID, Name: p.Name, Email: p.Email, IsActive: p.IsActive}
 }

client/android/profile_prefs.go

@@ -0,0 +1,37 @@
+//go:build android
+
+package android
+
+import (
+	"fmt"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+)
+
+type prefsStore interface {
+	Get(namespace string, v any) (bool, error)
+	Put(namespace string, v any) error
+}
+
+type profilePrefs struct {
+	prefs *profilemanager.Prefs
+}
+
+func newProfilePrefs(configDir, profileID string) (*profilePrefs, error) {
+	if configDir == "" || profileID == "" {
+		return nil, fmt.Errorf("profile prefs require a config dir and profile ID")
+	}
+	prefs, err := NewProfileManager(configDir).impl.ProfilePrefs(profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &profilePrefs{prefs: prefs}, nil
+}
+
+func (p *profilePrefs) Get(namespace string, v any) (bool, error) {
+	return p.prefs.Get(namespace, v)
+}
+
+func (p *profilePrefs) Put(namespace string, v any) error {
+	return p.prefs.Put(namespace, v)
+}

client/android/split_tunnel.go

@@ -0,0 +1,125 @@
+package android
+
+// SplitTunnelMode is which of the two selections, if either, the tunnel applies.
+// Its values land in the profile's stored preferences, so the constants below
+// are append-only and must never be reordered.
+type SplitTunnelMode int
+
+const (
+	modeOff SplitTunnelMode = iota
+	modeExclude
+	modeInclude
+)
+
+// The same modes as basic ints. gomobile drops a constant whose type is not a
+// basic one, so these are what reaches the generated Java bindings, and they
+// keep the Android side tied to the values above instead of repeating 0, 1, 2.
+const (
+	SplitTunnelModeOff     = int(modeOff)
+	SplitTunnelModeExclude = int(modeExclude)
+	SplitTunnelModeInclude = int(modeInclude)
+)
+
+type splitTunnelSection struct {
+	Mode     SplitTunnelMode `json:"mode"`
+	Excluded []string        `json:"excluded"`
+	Included []string        `json:"included"`
+}
+
+// PackageList wraps []string for gomobile compatibility.
+type PackageList struct {
+	items []string
+}
+
+// NewPackageList creates an empty list to fill via Add.
+func NewPackageList() *PackageList {
+	return &PackageList{}
+}
+
+// Add appends a package name, ignoring empty ones.
+func (l *PackageList) Add(s string) {
+	if s == "" {
+		return
+	}
+	l.items = append(l.items, s)
+}
+
+// Size returns the number of entries.
+func (l *PackageList) Size() int {
+	return len(l.items)
+}
+
+// Get returns the entry at index i, or an empty string when out of range.
+func (l *PackageList) Get(i int) string {
+	if i < 0 || i >= len(l.items) {
+		return ""
+	}
+	return l.items[i]
+}
+
+// SplitTunnelSettings is one profile's choice of which applications the tunnel
+// carries. The two selections are kept apart because the platform applies one
+// or the other and never both, and so that switching mode does not throw away
+// the picks made in the other one.
+//
+// Mode is an int rather than a SplitTunnelMode because gomobile carries only
+// basic types across the binding. It holds one of the SplitTunnelMode*
+// constants.
+type SplitTunnelSettings struct {
+	Mode     int
+	Excluded *PackageList
+	Included *PackageList
+}
+
+// NewSplitTunnelSettings creates settings that carry every application.
+func NewSplitTunnelSettings() *SplitTunnelSettings {
+	return &SplitTunnelSettings{
+		Mode:     SplitTunnelModeOff,
+		Excluded: NewPackageList(),
+		Included: NewPackageList(),
+	}
+}
+
+func packagesOf(list *PackageList) []string {
+	if list == nil {
+		return nil
+	}
+	out := make([]string, 0, len(list.items))
+	out = append(out, list.items...)
+	return out
+}
+
+// normalizeSplitTunnelMode maps anything outside the known set to off, so a mode
+// written by a newer build degrades to carrying every application rather than to
+// some other mode's behaviour.
+func normalizeSplitTunnelMode(mode SplitTunnelMode) SplitTunnelMode {
+	switch mode {
+	case modeExclude, modeInclude:
+		return mode
+	default:
+		return modeOff
+	}
+}
+
+func settingsFromSection(section splitTunnelSection) *SplitTunnelSettings {
+	out := NewSplitTunnelSettings()
+	out.Mode = int(normalizeSplitTunnelMode(section.Mode))
+	for _, pkg := range section.Excluded {
+		out.Excluded.Add(pkg)
+	}
+	for _, pkg := range section.Included {
+		out.Included.Add(pkg)
+	}
+	return out
+}
+
+func sectionFromSettings(settings *SplitTunnelSettings) splitTunnelSection {
+	if settings == nil {
+		settings = NewSplitTunnelSettings()
+	}
+	return splitTunnelSection{
+		Mode:     normalizeSplitTunnelMode(SplitTunnelMode(settings.Mode)),
+		Excluded: packagesOf(settings.Excluded),
+		Included: packagesOf(settings.Included),
+	}
+}

client/android/split_tunnel_store.go

@@ -0,0 +1,34 @@
+//go:build android
+
+package android
+
+const splitTunnelNamespace = "split-tunnel"
+
+// SplitTunnelStore reads and writes a profile's split tunnelling settings.
+type SplitTunnelStore struct {
+	prefs prefsStore
+}
+
+// NewSplitTunnelStore opens the split tunnelling store of the given profile.
+func NewSplitTunnelStore(configDir, profileID string) (*SplitTunnelStore, error) {
+	prefs, err := newProfilePrefs(configDir, profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &SplitTunnelStore{prefs: prefs}, nil
+}
+
+// Load returns the stored settings, or settings that carry every application
+// when the profile has none saved.
+func (s *SplitTunnelStore) Load() (*SplitTunnelSettings, error) {
+	var section splitTunnelSection
+	if _, err := s.prefs.Get(splitTunnelNamespace, &section); err != nil {
+		return nil, err
+	}
+	return settingsFromSection(section), nil
+}
+
+// Save replaces the stored settings.
+func (s *SplitTunnelStore) Save(settings *SplitTunnelSettings) error {
+	return s.prefs.Put(splitTunnelNamespace, sectionFromSettings(settings))
+}

client/android/split_tunnel_test.go

@@ -0,0 +1,151 @@
+package android
+
+import (
+	"encoding/json"
+	"reflect"
+	"testing"
+)
+
+func TestNormalizeSplitTunnelMode(t *testing.T) {
+	tests := []struct {
+		name string
+		mode SplitTunnelMode
+		want SplitTunnelMode
+	}{
+		{name: "exclude is kept", mode: modeExclude, want: modeExclude},
+		{name: "include is kept", mode: modeInclude, want: modeInclude},
+		{name: "off is kept", mode: modeOff, want: modeOff},
+		{name: "a mode from a newer build falls back to off", mode: SplitTunnelMode(7), want: modeOff},
+		{name: "a negative mode falls back to off", mode: SplitTunnelMode(-1), want: modeOff},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := normalizeSplitTunnelMode(tt.mode); got != tt.want {
+				t.Errorf("normalizeSplitTunnelMode(%d) = %d, want %d", tt.mode, got, tt.want)
+			}
+		})
+	}
+}
+
+// The constants the Android side reads must stay the values the store writes:
+// gomobile carries the ints below, not the typed constants they mirror.
+func TestSplitTunnelModeConstantsMirrorTheTypedOnes(t *testing.T) {
+	if SplitTunnelModeOff != int(modeOff) {
+		t.Errorf("off = %d, want %d", SplitTunnelModeOff, modeOff)
+	}
+	if SplitTunnelModeExclude != int(modeExclude) {
+		t.Errorf("exclude = %d, want %d", SplitTunnelModeExclude, modeExclude)
+	}
+	if SplitTunnelModeInclude != int(modeInclude) {
+		t.Errorf("include = %d, want %d", SplitTunnelModeInclude, modeInclude)
+	}
+}
+
+func TestSettingsFromSection(t *testing.T) {
+	got := settingsFromSection(splitTunnelSection{
+		Mode:     modeExclude,
+		Excluded: []string{"com.example.a", "com.example.b"},
+		Included: []string{"com.example.c"},
+	})
+
+	if got.Mode != SplitTunnelModeExclude {
+		t.Errorf("mode = %d, want %d", got.Mode, SplitTunnelModeExclude)
+	}
+	if got.Excluded.Size() != 2 || got.Excluded.Get(0) != "com.example.a" {
+		t.Errorf("excluded = %v, want the two stored packages", packagesOf(got.Excluded))
+	}
+	if got.Included.Size() != 1 || got.Included.Get(0) != "com.example.c" {
+		t.Errorf("included = %v, want the stored package", packagesOf(got.Included))
+	}
+}
+
+// A profile that has never stored anything decodes into an empty section, and
+// must come back as settings that carry every application rather than as nil
+// lists the caller would have to guard against.
+func TestSettingsFromEmptySectionCarriesEverything(t *testing.T) {
+	got := settingsFromSection(splitTunnelSection{})
+
+	if got.Mode != SplitTunnelModeOff {
+		t.Errorf("mode = %d, want %d", got.Mode, SplitTunnelModeOff)
+	}
+	if got.Excluded == nil || got.Included == nil {
+		t.Fatal("both selections must be usable lists, not nil")
+	}
+	if got.Excluded.Size() != 0 || got.Included.Size() != 0 {
+		t.Errorf("selections = %v/%v, want both empty", packagesOf(got.Excluded), packagesOf(got.Included))
+	}
+}
+
+// The section is what the profile's preference file holds, so the mode has to
+// survive a JSON round trip as the number the constants name.
+func TestSectionEncodesTheModeAsItsNumber(t *testing.T) {
+	raw, err := json.Marshal(sectionFromSettings(&SplitTunnelSettings{Mode: SplitTunnelModeInclude}))
+	if err != nil {
+		t.Fatalf("marshal section: %v", err)
+	}
+
+	var back splitTunnelSection
+	if err := json.Unmarshal(raw, &back); err != nil {
+		t.Fatalf("unmarshal section: %v", err)
+	}
+	if back.Mode != modeInclude {
+		t.Errorf("mode = %d, want %d, from %s", back.Mode, modeInclude, raw)
+	}
+}
+
+func TestSectionFromSettingsRoundTrip(t *testing.T) {
+	settings := NewSplitTunnelSettings()
+	settings.Mode = SplitTunnelModeInclude
+	settings.Included.Add("com.example.a")
+	settings.Excluded.Add("com.example.b")
+
+	section := sectionFromSettings(settings)
+	back := settingsFromSection(section)
+
+	if back.Mode != SplitTunnelModeInclude {
+		t.Errorf("mode = %d, want %d", back.Mode, SplitTunnelModeInclude)
+	}
+	if !reflect.DeepEqual(packagesOf(back.Included), []string{"com.example.a"}) {
+		t.Errorf("included = %v, want [com.example.a]", packagesOf(back.Included))
+	}
+	// The inactive selection survives, so switching mode back does not make the
+	// user pick their applications again.
+	if !reflect.DeepEqual(packagesOf(back.Excluded), []string{"com.example.b"}) {
+		t.Errorf("excluded = %v, want [com.example.b]", packagesOf(back.Excluded))
+	}
+}
+
+// A mode the Java side never sets, such as one left by a newer build, must not
+// reach the stored section either.
+func TestSectionFromSettingsNormalizesAnUnknownMode(t *testing.T) {
+	section := sectionFromSettings(&SplitTunnelSettings{Mode: 7})
+
+	if section.Mode != modeOff {
+		t.Errorf("mode = %d, want %d", section.Mode, modeOff)
+	}
+}
+
+func TestSectionFromNilSettings(t *testing.T) {
+	section := sectionFromSettings(nil)
+
+	if section.Mode != modeOff {
+		t.Errorf("mode = %d, want %d", section.Mode, modeOff)
+	}
+	if len(section.Excluded) != 0 || len(section.Included) != 0 {
+		t.Errorf("selections = %v/%v, want both empty", section.Excluded, section.Included)
+	}
+}
+
+func TestPackageListIgnoresEmptyAndBounds(t *testing.T) {
+	list := NewPackageList()
+	list.Add("com.example.a")
+	list.Add("")
+
+	if list.Size() != 1 {
+		t.Errorf("size = %d, want 1", list.Size())
+	}
+	if list.Get(-1) != "" || list.Get(5) != "" {
+		t.Error("out of range access must return an empty string")
+	}
+}

client/android/ssh_client.go

@@ -0,0 +1,649 @@
+//go:build android
+
+package android
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	gossh "golang.org/x/crypto/ssh"
+
+	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/internal/auth"
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	nbssh "github.com/netbirdio/netbird/client/ssh"
+	"github.com/netbirdio/netbird/client/ssh/detection"
+)
+
+const (
+	sshDialTimeout      = 30 * time.Second
+	sshDetectionTimeout = 5 * time.Second
+)
+
+// PasswordRequiredMarker tells Java to prompt for a password and retry. It is
+// a string because gomobile flattens errors to their message, so a sentinel
+// value would not survive the binding.
+const PasswordRequiredMarker = "netbird-ssh-password-required"
+
+// HostKeyUnknownMarker tells Java to show the fingerprint and, on confirmation,
+// retry with TrustHostKey set. The presented fingerprint is appended after the
+// marker so the prompt can display it and the retry can guard against a key
+// that changed between the two connects. Only regular (non-NetBird) servers
+// reach this: NetBird peers verify against the registry.
+const HostKeyUnknownMarker = "netbird-ssh-hostkey-unknown"
+
+var (
+	errPasswordRequired = errors.New(PasswordRequiredMarker)
+	errClientClosed     = errors.New("ssh client closed")
+)
+
+// errHostKeyUnknown carries the presented fingerprint so Connect can build the
+// marker message the Java side parses.
+type errHostKeyUnknown struct {
+	fingerprint string
+}
+
+func (e *errHostKeyUnknown) Error() string {
+	return HostKeyUnknownMarker + ":" + e.fingerprint
+}
+
+// SSHTerminalListener receives SSH session events. It is implemented in Java.
+//
+// All callbacks are invoked from goroutines and may run concurrently with each
+// other; the implementation must be safe to call from any thread.
+type SSHTerminalListener interface {
+	OnConnected()
+	OnData(data []byte)
+	OnClose(reason string)
+	OnError(message string)
+}
+
+// SSHClient is a NetBird-aware SSH client exposed to Java via gomobile.
+//
+// It dials through the running NetBird tunnel and runs a standard SSH session
+// on top with PTY enabled. Host-key verification uses the NetBird-provided
+// peer SSH host keys, identical to the desktop client.
+type SSHClient struct {
+	nb        *Client
+	mu        sync.Mutex
+	listener  SSHTerminalListener
+	urlOpener URLOpener
+
+	sshClient *gossh.Client
+	session   *gossh.Session
+	stdin     io.WriteCloser
+	closed    bool
+
+	// gen identifies the current connection attempt. Connect and Close bump it,
+	// so an in-flight dial or a reader left over from a previous connection
+	// finds itself stale and stays silent instead of publishing OnConnected or
+	// OnClose for a connection the caller already abandoned.
+	gen        uint64
+	dialCancel context.CancelFunc
+
+	// knownHostsConfigDir and knownHostsProfile locate the TOFU store for
+	// regular SSH servers in the profile's preferences. Java supplies them,
+	// since an overlay IP is a different host under a different profile. Empty
+	// until set: without them a regular server cannot be verified and Connect
+	// refuses one.
+	knownHostsConfigDir string
+	knownHostsProfile   string
+	// trustHostKey carries the fingerprint the user confirmed on a previous
+	// attempt, so the retry accepts exactly that key and persists it.
+	trustHostKey string
+}
+
+// NewSSHClient creates a new SSH client bound to the running NetBird Client.
+func NewSSHClient(c *Client) *SSHClient {
+	return &SSHClient{nb: c}
+}
+
+// SetListener registers the Java listener. Must be called before Connect to
+// receive any events.
+func (s *SSHClient) SetListener(l SSHTerminalListener) {
+	s.mu.Lock()
+	s.listener = l
+	s.mu.Unlock()
+}
+
+// SetURLOpener registers the Java URL opener used to display the device-code
+// authorization page in a Custom Tabs window when the target peer requires
+// JWT authentication. Must be set before Connect to be effective.
+func (s *SSHClient) SetURLOpener(opener URLOpener) {
+	s.mu.Lock()
+	s.urlOpener = opener
+	s.mu.Unlock()
+}
+
+// SetKnownHostsStore points the TOFU host-key store at a profile's preferences.
+// Must be set before connecting to a regular SSH server; without it such a
+// server cannot be verified and Connect refuses one.
+func (s *SSHClient) SetKnownHostsStore(configDir, profileID string) {
+	s.mu.Lock()
+	s.knownHostsConfigDir = configDir
+	s.knownHostsProfile = profileID
+	s.mu.Unlock()
+}
+
+// TrustHostKey records the fingerprint the user confirmed for a regular server,
+// so the next Connect accepts that exact key and adds it to the known-hosts
+// store. Passing a fingerprint that no longer matches makes the connect fail
+// rather than trust a key that changed since the prompt.
+func (s *SSHClient) TrustHostKey(fingerprint string) {
+	s.mu.Lock()
+	s.trustHostKey = fingerprint
+	s.mu.Unlock()
+}
+
+// Connect dials the SSH server through the NetBird tunnel and performs the
+// SSH handshake. It auto-detects the server type via SSH banner inspection
+// and selects the appropriate authentication path:
+//
+//   - NetBird-SSH server requiring JWT: launches the OAuth 2.0 device-code
+//     flow, opens the verification URL through the registered URLOpener, and
+//     uses the resulting token as the SSH password. Host-key verification
+//     uses the NetBird peer registry.
+//   - NetBird-SSH server without JWT: authenticates with the NetBird SSH
+//     private key. Host-key verification uses the NetBird peer registry.
+//   - Regular SSH server (e.g. OpenSSH): authenticates with the NetBird key
+//     first (so a user-installed NetBird public key works), then falls back
+//     to the supplied password if non-empty. Host-key verification is
+//     trust-on-first-use against the per-profile known-hosts store.
+//
+// The password parameter is only consulted for regular SSH servers.
+func (s *SSHClient) Connect(host string, port int, user, password string) error {
+	if port < 1 || port > 65535 {
+		return fmt.Errorf("invalid port: %d", port)
+	}
+
+	cfg, cfgPath, cc := s.nb.authSnapshot()
+	if cc == nil {
+		return errors.New("netbird client not running")
+	}
+	if cfg == nil {
+		return errors.New("netbird config not loaded")
+	}
+	engine := cc.Engine()
+	if engine == nil {
+		return errors.New("netbird engine not available")
+	}
+
+	s.mu.Lock()
+	s.gen++
+	gen := s.gen
+	s.mu.Unlock()
+
+	serverType := detectServerType(host, port)
+	log.Debugf("SSH server type: %s", serverType)
+
+	authMethods, hostKeyCallback, err := s.buildAuth(cfg, cfgPath, engine, serverType, password)
+	if err != nil {
+		return err
+	}
+
+	clientConfig := &gossh.ClientConfig{
+		User:            user,
+		Auth:            authMethods,
+		HostKeyCallback: hostKeyCallback,
+		Timeout:         sshDialTimeout,
+	}
+	err = s.dialAndHandshake(gen, host, port, clientConfig)
+
+	// An unknown host key is a prompt, not a failure: return the marker intact
+	// (rootCause would unwrap it) so Java can show the fingerprint and retry.
+	var unknownHost *errHostKeyUnknown
+	if errors.As(err, &unknownHost) {
+		return errors.New(unknownHost.Error())
+	}
+
+	// A regular server may still accept a password, so let the caller ask for
+	// one instead of failing. NetBird servers never use a password, so a
+	// failure there is genuine.
+	if err != nil && serverType != detection.ServerTypeNetBirdJWT &&
+		serverType != detection.ServerTypeNetBirdNoJWT && isAuthFailure(err) &&
+		passwordCouldHelp(err, password != "") {
+		return errPasswordRequired
+	}
+	if err != nil {
+		return rootCause(err)
+	}
+	return nil
+}
+
+// StartSession requests a PTY and starts an interactive shell. Output from
+// the session is forwarded to the listener via OnData.
+func (s *SSHClient) StartSession(cols, rows int) error {
+	err := s.startSession(cols, rows)
+	if err != nil {
+		log.Infof("SSH: start session failed: %v", err)
+		return rootCause(err)
+	}
+	return nil
+}
+
+// Write sends data to the SSH session stdin.
+func (s *SSHClient) Write(data []byte) error {
+	s.mu.Lock()
+	stdin := s.stdin
+	s.mu.Unlock()
+	if stdin == nil {
+		return errors.New("ssh session not started")
+	}
+	if _, err := stdin.Write(data); err != nil {
+		return fmt.Errorf("write stdin: %w", err)
+	}
+	return nil
+}
+
+// Resize updates the PTY window size.
+func (s *SSHClient) Resize(cols, rows int) error {
+	s.mu.Lock()
+	session := s.session
+	s.mu.Unlock()
+	if session == nil {
+		return errors.New("ssh session not started")
+	}
+	return session.WindowChange(rows, cols)
+}
+
+// Reset makes a closed client usable for another Connect: Close leaves the
+// one-shot guard set, and clearing it lets the same client back a reconnect.
+func (s *SSHClient) Reset() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.closed = false
+}
+
+// Close terminates the SSH session and underlying connection. Safe to call
+// multiple times.
+func (s *SSHClient) Close() error {
+	s.mu.Lock()
+	s.gen++
+	if s.dialCancel != nil {
+		s.dialCancel()
+		s.dialCancel = nil
+	}
+	sshClient := s.sshClient
+	session := s.session
+	stdin := s.stdin
+	s.sshClient = nil
+	s.session = nil
+	s.stdin = nil
+	notify := !s.closed
+	s.closed = true
+	listener := s.listener
+	s.mu.Unlock()
+
+	if stdin != nil {
+		if err := stdin.Close(); err != nil {
+			log.Debugf("ssh: stdin close: %v", err)
+		}
+	}
+	if session != nil {
+		if err := session.Close(); err != nil && !errors.Is(err, io.EOF) {
+			log.Debugf("ssh: session close: %v", err)
+		}
+	}
+	var firstErr error
+	if sshClient != nil {
+		if err := sshClient.Close(); err != nil {
+			firstErr = err
+		}
+	}
+	if notify && listener != nil {
+		listener.OnClose("closed by client")
+	}
+	return firstErr
+}
+
+func (s *SSHClient) startSession(cols, rows int) error {
+	log.Debugf("SSH: starting session %dx%d", cols, rows)
+	s.mu.Lock()
+	sshClient := s.sshClient
+	gen := s.gen
+	s.mu.Unlock()
+
+	if sshClient == nil {
+		return errors.New("ssh client not connected")
+	}
+
+	pty, err := nbssh.StartPTYSession(sshClient, cols, rows)
+	if err != nil {
+		return err
+	}
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		closeQuiet(pty.Session, "stale session")
+		return errClientClosed
+	}
+	s.session = pty.Session
+	s.stdin = pty.Stdin
+	s.mu.Unlock()
+
+	readerDone := make(chan string, 2)
+	go func() { readerDone <- s.readLoop(pty.Stdout, "stdout") }()
+	go func() { readerDone <- s.readLoop(pty.Stderr, "stderr") }()
+	go func() {
+		reason := <-readerDone
+		if second := <-readerDone; reason == "" {
+			reason = second
+		}
+		s.notifyClose(gen, reason)
+	}()
+	log.Debug("SSH: session started, shell running")
+	return nil
+}
+
+func (s *SSHClient) buildAuth(cfg *profilemanager.Config, cfgPath string, engine *internal.Engine,
+	serverType detection.ServerType, password string) ([]gossh.AuthMethod, gossh.HostKeyCallback, error) {
+
+	switch serverType {
+	case detection.ServerTypeNetBirdJWT:
+		token, err := s.requestJWTToken(cfg, cfgPath)
+		if err != nil {
+			return nil, nil, fmt.Errorf("jwt: %w", err)
+		}
+		auths := []gossh.AuthMethod{gossh.Password(token)}
+		return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil
+
+	case detection.ServerTypeNetBirdNoJWT:
+		if cfg.SSHKey == "" {
+			return nil, nil, errors.New("no NetBird SSH key available")
+		}
+		signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey))
+		if err != nil {
+			return nil, nil, fmt.Errorf("parse netbird ssh key: %w", err)
+		}
+		auths := []gossh.AuthMethod{gossh.PublicKeys(signer)}
+		return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil
+
+	case detection.ServerTypeRegular:
+		var auths []gossh.AuthMethod
+		if cfg.SSHKey != "" {
+			if signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey)); err == nil {
+				auths = append(auths, gossh.PublicKeys(signer))
+			} else {
+				log.Debugf("ssh: parse netbird key for regular auth: %v", err)
+			}
+		}
+		if password != "" {
+			pw := password
+			auths = append(auths, gossh.Password(pw))
+			auths = append(auths, gossh.KeyboardInteractive(func(_, _ string, questions []string, _ []bool) ([]string, error) {
+				answers := make([]string, len(questions))
+				for i := range questions {
+					answers[i] = pw
+				}
+				return answers, nil
+			}))
+		}
+		if len(auths) == 0 {
+			// Nothing to offer at all: ask for a password rather than failing,
+			// so the caller can retry once the user supplies one.
+			return nil, nil, errPasswordRequired
+		}
+		callback, err := s.tofuHostKeyCallback()
+		if err != nil {
+			return nil, nil, err
+		}
+		return auths, callback, nil
+
+	default:
+		return nil, nil, fmt.Errorf("unsupported SSH server type: %v", serverType)
+	}
+}
+
+// tofuHostKeyCallback verifies a regular server's host key against the
+// per-profile known-hosts store. An unknown host returns errHostKeyUnknown so
+// Java can show the fingerprint and, once confirmed, retry with the key
+// trusted; a changed key is rejected outright, as OpenSSH does. When the user
+// has confirmed a fingerprint, the callback accepts exactly that key and
+// appends it to the store.
+func (s *SSHClient) tofuHostKeyCallback() (gossh.HostKeyCallback, error) {
+	s.mu.Lock()
+	configDir := s.knownHostsConfigDir
+	profileID := s.knownHostsProfile
+	trusted := s.trustHostKey
+	s.mu.Unlock()
+
+	if configDir == "" || profileID == "" {
+		return nil, errors.New("no known-hosts store configured for regular SSH")
+	}
+
+	store, err := openKnownHostsStore(configDir, profileID)
+	if err != nil {
+		return nil, fmt.Errorf("load known-hosts store: %w", err)
+	}
+
+	return func(hostname string, remote net.Addr, key gossh.PublicKey) error {
+		verdict, err := store.verify(hostname, remote, key)
+		if err != nil {
+			return err
+		}
+		if verdict == hostKeyMatched {
+			return nil
+		}
+		if verdict == hostKeyChanged {
+			return fmt.Errorf("SSH host key changed for %s (possible attack)", hostname)
+		}
+
+		fingerprint := gossh.FingerprintSHA256(key)
+		if trusted == "" {
+			return &errHostKeyUnknown{fingerprint: fingerprint}
+		}
+		if trusted != fingerprint {
+			return fmt.Errorf("SSH host key changed since it was confirmed for %s", hostname)
+		}
+		if err := store.append(hostname, remote, key); err != nil {
+			return fmt.Errorf("persist trusted host key: %w", err)
+		}
+		// The confirmation is spent: now that the key is stored, a later
+		// reconnect must verify against the file, not re-accept this fingerprint.
+		s.mu.Lock()
+		s.trustHostKey = ""
+		s.mu.Unlock()
+		return nil
+	}, nil
+}
+
+func (s *SSHClient) requestJWTToken(cfg *profilemanager.Config, cfgPath string) (string, error) {
+	s.mu.Lock()
+	urlOpener := s.urlOpener
+	s.mu.Unlock()
+	if urlOpener == nil {
+		return "", errors.New("URL opener not configured for JWT auth")
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
+	defer cancel()
+
+	flow, err := auth.NewOAuthFlow(ctx, cfg, false, true, profileLoginHint(cfgPath))
+	if err != nil {
+		return "", fmt.Errorf("create oauth flow: %w", err)
+	}
+
+	// The status callback covers the browser round-trip, which would
+	// otherwise leave the terminal blank.
+	tokenInfo, err := runOAuthFlow(ctx, flow, urlOpener, func() {
+		s.notifyStatus("Waiting for browser authentication...")
+	})
+	if err != nil {
+		return "", err
+	}
+
+	token := tokenInfo.GetTokenToUse()
+	if token == "" {
+		return "", errors.New("empty token returned by IdP")
+	}
+
+	// Tells the client the browser round-trip is over so it can dismiss the
+	// surface it opened, the same way the login and session-extend flows do.
+	// Without it the Custom Tab stays in front of the terminal even though the
+	// token has already been collected.
+	urlOpener.OnLoginSuccess()
+
+	return token, nil
+}
+
+func (s *SSHClient) dialAndHandshake(gen uint64, host string, port int, clientConfig *gossh.ClientConfig) error {
+	addr := net.JoinHostPort(host, strconv.Itoa(port))
+	ctx, cancel := context.WithTimeout(context.Background(), sshDialTimeout)
+	defer cancel()
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		return errClientClosed
+	}
+	s.dialCancel = cancel
+	s.mu.Unlock()
+
+	var dialer net.Dialer
+	conn, err := dialer.DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return fmt.Errorf("dial %s: %w", addr, err)
+	}
+
+	client, err := nbssh.Handshake(ctx, conn, addr, clientConfig)
+	if err != nil {
+		return err
+	}
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		closeQuiet(client, "stale ssh client")
+		return errClientClosed
+	}
+	s.sshClient = client
+	listener := s.listener
+	s.mu.Unlock()
+
+	if listener != nil {
+		listener.OnConnected()
+	}
+	return nil
+}
+
+func (s *SSHClient) readLoop(r io.Reader, name string) string {
+	buf := make([]byte, 4096)
+	for {
+		n, err := r.Read(buf)
+		if n > 0 {
+			s.mu.Lock()
+			listener := s.listener
+			s.mu.Unlock()
+			if listener != nil {
+				chunk := make([]byte, n)
+				copy(chunk, buf[:n])
+				listener.OnData(chunk)
+			}
+		}
+		if err != nil {
+			// EOF is a normal shell exit, so report it without a reason.
+			if errors.Is(err, io.EOF) {
+				return ""
+			}
+			log.Debugf("ssh %s read: %v", name, err)
+			return rootCause(err).Error()
+		}
+	}
+}
+
+// notifyStatus writes a progress line to the terminal through the normal
+// output path, so long steps are visible while nothing else is arriving.
+func (s *SSHClient) notifyStatus(text string) {
+	s.mu.Lock()
+	listener := s.listener
+	s.mu.Unlock()
+	if listener != nil {
+		listener.OnData([]byte("\r\n\x1b[33m" + text + "\x1b[0m\r\n"))
+	}
+}
+
+func (s *SSHClient) notifyClose(gen uint64, reason string) {
+	s.mu.Lock()
+	if gen != s.gen || s.closed {
+		s.mu.Unlock()
+		return
+	}
+	s.closed = true
+	listener := s.listener
+	s.mu.Unlock()
+	if listener != nil {
+		listener.OnClose(reason)
+	}
+}
+
+func closeQuiet(c io.Closer, label string) {
+	if c == nil {
+		return
+	}
+	if err := c.Close(); err != nil && !errors.Is(err, io.EOF) {
+		log.Debugf("ssh: close %s: %v", label, err)
+	}
+}
+
+func detectServerType(host string, port int) detection.ServerType {
+	ctx, cancel := context.WithTimeout(context.Background(), sshDetectionTimeout)
+	defer cancel()
+
+	dialer := &net.Dialer{}
+	serverType, err := detection.DetectSSHServerType(ctx, dialer, host, port)
+	if err != nil {
+		log.Debugf("ssh: server detection failed: %v (assuming regular SSH)", err)
+		return detection.ServerTypeRegular
+	}
+	return serverType
+}
+
+// rootCause returns the innermost error of a %w chain, so the terminal shows
+// "i/o timeout" rather than every layer that added context on the way up.
+func rootCause(err error) error {
+	for {
+		// A joined error has no single root, so keep it as-is.
+		if _, ok := err.(interface{ Unwrap() []error }); ok {
+			return err
+		}
+		next := errors.Unwrap(err)
+		if next == nil {
+			return err
+		}
+		err = next
+	}
+}
+
+// isAuthFailure distinguishes credential rejection from dial, timeout and
+// host-key errors, which retrying with a password would not fix.
+func isAuthFailure(err error) bool {
+	if errors.Is(err, errPasswordRequired) {
+		return true
+	}
+	var partial *gossh.PartialSuccessError
+	if errors.As(err, &partial) {
+		return true
+	}
+	return strings.Contains(err.Error(), "unable to authenticate")
+}
+
+// passwordCouldHelp reports whether prompting for a password again can change
+// the outcome. gossh lists a method under "attempted methods" only when the
+// server offered it, so a supplied password that was never attempted means the
+// server does not accept passwords and the real error should surface instead.
+func passwordCouldHelp(err error, passwordOffered bool) bool {
+	if !passwordOffered {
+		return true
+	}
+	msg := err.Error()
+	return strings.Contains(msg, "password") || strings.Contains(msg, "keyboard-interactive")
+}

client/android/ssh_known_hosts.go

@@ -0,0 +1,168 @@
+//go:build android
+
+package android
+
+import (
+	"bytes"
+	"net"
+	"strconv"
+	"strings"
+	"sync"
+
+	gossh "golang.org/x/crypto/ssh"
+	"golang.org/x/crypto/ssh/knownhosts"
+)
+
+const knownHostsNamespace = "ssh"
+
+const (
+	hostKeyUnknown hostKeyVerdict = iota
+	hostKeyMatched
+	hostKeyChanged
+)
+
+var knownHostsMu sync.Mutex
+
+type hostKeyVerdict uint8
+
+type knownHostsSection struct {
+	KnownHosts []string `json:"knownHosts"`
+}
+
+type knownHostsStore struct {
+	prefs prefsStore
+}
+
+// RemoveKnownHost deletes every known-hosts entry for host:port from the
+// profile's store, so a host trusted for a session that is being deleted does
+// not linger. Java calls this only once no session targets that host, so a
+// shared host stays trusted. A missing entry is not an error: the goal state
+// is "absent".
+func RemoveKnownHost(configDir, profileID, host string, port int) error {
+	store, err := openKnownHostsStore(configDir, profileID)
+	if err != nil {
+		return err
+	}
+	return store.removeHost(host, port)
+}
+
+func openKnownHostsStore(configDir, profileID string) (*knownHostsStore, error) {
+	prefs, err := newProfilePrefs(configDir, profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &knownHostsStore{prefs: prefs}, nil
+}
+
+func (st *knownHostsStore) verify(hostname string, remote net.Addr, key gossh.PublicKey) (hostKeyVerdict, error) {
+	lines, err := st.lines()
+	if err != nil {
+		return hostKeyUnknown, err
+	}
+	targets := knownHostsTargets(hostname, remote)
+
+	verdict := hostKeyUnknown
+	for _, line := range lines {
+		pubKey, ok := knownHostsLineKey(line, targets)
+		if !ok {
+			continue
+		}
+		if pubKey.Type() == key.Type() && bytes.Equal(pubKey.Marshal(), key.Marshal()) {
+			return hostKeyMatched, nil
+		}
+		verdict = hostKeyChanged
+	}
+	return verdict, nil
+}
+
+func (st *knownHostsStore) append(hostname string, remote net.Addr, key gossh.PublicKey) error {
+	line := knownhosts.Line(knownHostsTargets(hostname, remote), key)
+
+	knownHostsMu.Lock()
+	defer knownHostsMu.Unlock()
+
+	lines, err := st.lines()
+	if err != nil {
+		return err
+	}
+	return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: append(lines, line)})
+}
+
+func (st *knownHostsStore) removeHost(host string, port int) error {
+	target := knownhosts.Normalize(net.JoinHostPort(host, strconv.Itoa(port)))
+
+	knownHostsMu.Lock()
+	defer knownHostsMu.Unlock()
+
+	lines, err := st.lines()
+	if err != nil {
+		return err
+	}
+	kept := make([]string, 0, len(lines))
+	for _, line := range lines {
+		if knownHostsLineMatches(line, target) {
+			continue
+		}
+		kept = append(kept, line)
+	}
+	if len(kept) == len(lines) {
+		return nil
+	}
+	return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: kept})
+}
+
+func (st *knownHostsStore) lines() ([]string, error) {
+	var section knownHostsSection
+	if _, err := st.prefs.Get(knownHostsNamespace, &section); err != nil {
+		return nil, err
+	}
+	return section.KnownHosts, nil
+}
+
+func knownHostsTargets(hostname string, remote net.Addr) []string {
+	targets := []string{knownhosts.Normalize(hostname)}
+	if remote != nil {
+		if normalized := knownhosts.Normalize(remote.String()); normalized != targets[0] {
+			targets = append(targets, normalized)
+		}
+	}
+	return targets
+}
+
+func knownHostsLineKey(line string, targets []string) (gossh.PublicKey, bool) {
+	trimmed := strings.TrimSpace(line)
+	if trimmed == "" || strings.HasPrefix(trimmed, "#") {
+		return nil, false
+	}
+	_, hosts, pubKey, _, _, err := gossh.ParseKnownHosts([]byte(trimmed))
+	if err != nil {
+		return nil, false
+	}
+	for _, host := range hosts {
+		for _, target := range targets {
+			if host == target {
+				return pubKey, true
+			}
+		}
+	}
+	return nil, false
+}
+
+// knownHostsLineMatches reports whether a known-hosts line's address list
+// contains the normalized target. Comment and blank lines never match.
+func knownHostsLineMatches(line, target string) bool {
+	trimmed := strings.TrimSpace(line)
+	if trimmed == "" || strings.HasPrefix(trimmed, "#") {
+		return false
+	}
+	fields := strings.Fields(trimmed)
+	if len(fields) == 0 {
+		return false
+	}
+	for _, addr := range strings.Split(fields[0], ",") {
+		if addr == target {
+			return true
+		}
+	}
+	return false
+}

client/android/ssh_sessions.go

@@ -0,0 +1,104 @@
+//go:build android
+
+package android
+
+const (
+	sshSessionsNamespace = "ssh-sessions"
+	maxStoredSSHSessions = 50
+)
+
+type sshSessionRecord struct {
+	ID   string `json:"id"`
+	Host string `json:"host"`
+	Port int    `json:"port"`
+	User string `json:"user"`
+}
+
+type sshSessionsSection struct {
+	Sessions []sshSessionRecord `json:"sessions"`
+}
+
+// SSHSessionEntry is one stored SSH session, without any credential.
+type SSHSessionEntry struct {
+	ID   string
+	Host string
+	Port int
+	User string
+}
+
+// SSHSessionArray wraps stored SSH sessions for gomobile compatibility.
+type SSHSessionArray struct {
+	items []*SSHSessionEntry
+}
+
+// NewSSHSessionArray creates an empty session array to fill via Add.
+func NewSSHSessionArray() *SSHSessionArray {
+	return &SSHSessionArray{}
+}
+
+// Add appends a session entry, oldest first.
+func (a *SSHSessionArray) Add(id, host string, port int, user string) {
+	a.items = append(a.items, &SSHSessionEntry{ID: id, Host: host, Port: port, User: user})
+}
+
+// Length returns the number of entries.
+func (a *SSHSessionArray) Length() int {
+	return len(a.items)
+}
+
+// Get returns the entry at index i, or nil when out of range.
+func (a *SSHSessionArray) Get(i int) *SSHSessionEntry {
+	if i < 0 || i >= len(a.items) {
+		return nil
+	}
+	return a.items[i]
+}
+
+// SSHSessionStore reads and writes a profile's stored SSH sessions.
+type SSHSessionStore struct {
+	prefs prefsStore
+}
+
+// NewSSHSessionStore opens the session store of the given profile.
+func NewSSHSessionStore(configDir, profileID string) (*SSHSessionStore, error) {
+	prefs, err := newProfilePrefs(configDir, profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &SSHSessionStore{prefs: prefs}, nil
+}
+
+// Load returns the stored sessions, oldest first.
+func (s *SSHSessionStore) Load() (*SSHSessionArray, error) {
+	var section sshSessionsSection
+	if _, err := s.prefs.Get(sshSessionsNamespace, &section); err != nil {
+		return nil, err
+	}
+
+	out := NewSSHSessionArray()
+	for _, record := range section.Sessions {
+		if record.ID == "" || record.Host == "" {
+			continue
+		}
+		out.Add(record.ID, record.Host, record.Port, record.User)
+	}
+	return out, nil
+}
+
+// Save replaces the stored sessions, keeping only the newest entries when the
+// list exceeds the storage cap.
+func (s *SSHSessionStore) Save(sessions *SSHSessionArray) error {
+	var items []*SSHSessionEntry
+	if sessions != nil {
+		items = sessions.items
+	}
+	if len(items) > maxStoredSSHSessions {
+		items = items[len(items)-maxStoredSSHSessions:]
+	}
+
+	records := make([]sshSessionRecord, 0, len(items))
+	for _, item := range items {
+		records = append(records, sshSessionRecord{ID: item.ID, Host: item.Host, Port: item.Port, User: item.User})
+	}
+	return s.prefs.Put(sshSessionsNamespace, sshSessionsSection{Sessions: records})
+}

client/cmd/debug.go

@@ -3,7 +3,6 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"os/user"
 	"strings"
 	"time"
 
@@ -114,7 +113,7 @@ func debugConfigDump(cmd *cobra.Command, _ []string) error {
 	if err != nil {
 		return fmt.Errorf("get active profile: %v", err)
 	}
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %v", err)
 	}

client/cmd/jobs.go

@@ -0,0 +1,13 @@
+package cmd
+
+// remoteJobsAllowedFlag opts this peer into running remote jobs (e.g. debug
+// bundles) requested by the management server. It defaults to false: remote
+// jobs are an explicit opt-in, and enabling it is a privileged change (see the
+// daemon gate in client/server), mirroring the SSH server opt-in.
+const remoteJobsAllowedFlag = "allow-remote-jobs"
+
+var remoteJobsAllowed bool
+
+func init() {
+	upCmd.PersistentFlags().BoolVar(&remoteJobsAllowed, remoteJobsAllowedFlag, false, "Allow the management server to run remote jobs (e.g. debug bundles) on this peer")
+}

client/cmd/login.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"fmt"
 	"os"
-	"os/user"
 	"strings"
 
 	log "github.com/sirupsen/logrus"
@@ -53,7 +52,7 @@ var loginCmd = &cobra.Command{
 			// nolint
 			ctx = context.WithValue(ctx, system.DeviceNameCtxKey, hostName)
 		}
-		username, err := user.Current()
+		username, err := profilemanager.InvokingUser()
 		if err != nil {
 			return fmt.Errorf("get current user: %v", err)
 		}
@@ -74,7 +73,7 @@ var loginCmd = &cobra.Command{
 			if providedSetupKey != "" {
 				return fmt.Errorf("--extend cannot be combined with a setup key; setup keys can only enrol new peers")
 			}
-			if err := doExtendSession(ctx, cmd); err != nil {
+			if err := doExtendSession(ctx, cmd, activeProf); err != nil {
 				return fmt.Errorf("extend session failed: %v", err)
 			}
 			return nil
@@ -92,7 +91,7 @@ var loginCmd = &cobra.Command{
 			return fmt.Errorf("daemon login failed: %v", err)
 		}
 
-		cmd.Println("Logging successfully")
+		cmd.Println("Login successful")
 
 		return nil
 	},
@@ -176,7 +175,7 @@ func doDaemonLogin(ctx context.Context, cmd *cobra.Command, providedSetupKey str
 // (browser + verification URL) and the resulting JWT is forwarded to the
 // management server's ExtendAuthSession RPC. The tunnel stays up
 // throughout — no Down/Up, no network-map resync.
-func doExtendSession(ctx context.Context, cmd *cobra.Command) error {
+func doExtendSession(ctx context.Context, cmd *cobra.Command, activeProf *profilemanager.Profile) error {
 	conn, err := DialClientGRPCServer(ctx, daemonAddr)
 	if err != nil {
 		//nolint
@@ -190,14 +189,12 @@ func doExtendSession(ctx context.Context, cmd *cobra.Command) error {
 
 	// the CLI runs in the user's session, the daemon does not: tell it what we can see
 	req := &proto.RequestExtendAuthSessionRequest{HasGraphicalSession: util.HasGraphicalSession()}
-	// Pre-fill the IdP login hint from the active profile so the user
+	// Pre-fill the IdP login hint from the resolved profile so the user
 	// doesn't have to retype their email. Best-effort: we still proceed
 	// without a hint if the lookup fails.
 	pm := profilemanager.NewProfileManager()
-	if active, perr := pm.GetActiveProfile(); perr == nil {
+	if profState, perr := pm.GetProfileState(activeProf.ID); perr == nil && profState.Email != "" {
-		if profState, sperr := pm.GetProfileState(active.ID); sperr == nil && profState.Email != "" {
+		req.Hint = &profState.Email
-			req.Hint = &profState.Email
-		}
 	}
 
 	startResp, err := client.RequestExtendAuthSession(ctx, req)
@@ -235,9 +232,11 @@ func getActiveProfile(ctx context.Context, pm *profilemanager.ProfileManager, pr
 	// switch profile if provided
 
 	if profileName != "" {
-		if err := switchProfileOnDaemon(ctx, pm, profileName, username); err != nil {
+		prof, err := switchProfileOnDaemon(ctx, pm, profileName, username)
+		if err != nil {
 			return nil, fmt.Errorf("switch profile: %v", err)
 		}
+		return prof, nil
 	}
 
 	activeProf, err := pm.GetActiveProfile()
@@ -251,20 +250,19 @@ func getActiveProfile(ctx context.Context, pm *profilemanager.ProfileManager, pr
 	return activeProf, nil
 }
 
-func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManager, handle string, username string) error {
+func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManager, handle string, username string) (*profilemanager.Profile, error) {
 	resolvedID, err := switchProfile(ctx, handle, username)
 	if err != nil {
-		return fmt.Errorf("switch profile on daemon: %v", err)
+		return nil, fmt.Errorf("switch profile on daemon: %v", err)
 	}
 
 	if err := pm.SwitchProfile(resolvedID); err != nil {
-		return fmt.Errorf("switch profile: %v", err)
+		return nil, fmt.Errorf("switch profile: %v", err)
 	}
 
 	conn, err := DialClientGRPCServer(ctx, daemonAddr)
 	if err != nil {
-		log.Errorf("failed to connect to service CLI interface %v", err)
+		return nil, fmt.Errorf("connect to service CLI interface: %w", err)
-		return err
 	}
 	defer conn.Close()
 
@@ -272,17 +270,17 @@ func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManage
 
 	status, err := client.Status(ctx, &proto.StatusRequest{})
 	if err != nil {
-		return fmt.Errorf("unable to get daemon status: %v", err)
+		return nil, fmt.Errorf("unable to get daemon status: %v", err)
 	}
 
 	if status.Status == string(internal.StatusConnected) {
 		if _, err := client.Down(ctx, &proto.DownRequest{}); err != nil {
 			log.Errorf("call service down method: %v", err)
-			return err
+			return nil, err
 		}
 	}
 
-	return nil
+	return &profilemanager.Profile{ID: resolvedID}, nil
 }
 
 // switchProfile asks the daemon to switch to the profile identified by
@@ -345,7 +343,7 @@ func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string,
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)
 	}
-	cmd.Println("Logging successfully")
+	cmd.Println("Login successful")
 	return nil
 }
 

client/cmd/logout.go

@@ -3,11 +3,11 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"os/user"
 	"time"
 
 	"github.com/spf13/cobra"
 
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 )
 
@@ -37,7 +37,7 @@ var logoutCmd = &cobra.Command{
 		if profileName != "" {
 			req.ProfileName = &profileName
 
-			currUser, err := user.Current()
+			currUser, err := profilemanager.InvokingUser()
 			if err != nil {
 				return fmt.Errorf("get current user: %v", err)
 			}

client/cmd/profile.go

@@ -4,7 +4,6 @@ import (
 	"context"
 	"errors"
 	"fmt"
-	"os/user"
 	"strings"
 	"text/tabwriter"
 	"time"
@@ -97,7 +96,7 @@ func listProfilesFunc(cmd *cobra.Command, _ []string) error {
 	}
 	defer conn.Close()
 
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %w", err)
 	}
@@ -138,7 +137,7 @@ func addProfileFunc(cmd *cobra.Command, args []string) error {
 		return err
 	}
 
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %w", err)
 	}
@@ -179,7 +178,7 @@ func renameProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 	defer conn.Close()
 
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %w", err)
 	}
@@ -233,7 +232,7 @@ func removeProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 	defer conn.Close()
 
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %w", err)
 	}
@@ -261,7 +260,7 @@ func selectProfileFunc(cmd *cobra.Command, args []string) error {
 	profileManager := profilemanager.NewProfileManager()
 	handle := args[0]
 
-	currUser, err := user.Current()
+	currUser, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %w", err)
 	}

client/cmd/root.go

@@ -23,6 +23,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/anonymize"
 	daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
+	"github.com/netbirdio/netbird/client/internal/localmetrics"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 )
 
@@ -31,6 +32,8 @@ 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"
@@ -80,6 +83,8 @@ var (
 	updateSettingsDisabled bool
 	captureEnabled         bool
 	networksDisabled       bool
+	localMetricsEnabled    bool
+	localMetricsAddr       string
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -215,6 +220,8 @@ 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/service_controller.go

@@ -41,13 +41,15 @@ func daemonServerOptions(network string) []grpc.ServerOption {
 	if network == "tcp" {
 		log.Warnf("daemon is listening on TCP (%s): callers carry no verifiable identity over TCP, "+
 			"so privileged operations (SSH root login, SSH auth, enabling the SSH server, management URL changes, "+
-			"deregistration) will be denied. Use a unix socket, or npipe:// on Windows", daemonAddr)
+			"deregistration) will be denied, and the SSH JWT cache is neither filled nor served. "+
+			"Use a unix socket, or npipe:// on Windows", daemonAddr)
 		return nil
 	}
 
-	creds := ipcauth.NewTransportCredentials()
+	creds := ipcauth.NewTransportCredentials() //nolint:staticcheck
-	if creds == nil {
+	if creds == nil {                          //nolint:staticcheck // nil only on platforms without a peer-identity primitive
-		log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied", runtime.GOOS)
+		log.Warnf("daemon IPC has no peer-identity primitive on %s: privileged operations will be denied "+
+			"and the SSH JWT cache is neither filled nor served", runtime.GOOS)
 		return nil
 	}
 

client/cmd/service_socket.go

@@ -27,8 +27,8 @@ func listenOnAddress(addr string) (*socketListener, error) {
 	}
 
 	if network == "npipe" {
-		listener, path, err := listenNamedPipe(address)
+		listener, path, err := listenNamedPipe(address) //nolint:staticcheck
-		if err != nil {
+		if err != nil {                                 //nolint:staticcheck // always errors on non-Windows builds
 			return nil, err
 		}
 		return &socketListener{Listener: listener, network: network, address: path}, nil

client/cmd/testutil_test.go

@@ -6,7 +6,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/otel"
 	"google.golang.org/grpc"
@@ -124,7 +124,7 @@ func startManagement(t *testing.T, config *config.Config, testFile string) (*grp
 
 	updateManager := update_channel.NewPeersUpdateManager(metrics)
 	requestBuffer := mgmt.NewAccountRequestBuffer(ctx, store)
-	networkMapController := controller.NewController(ctx, store, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.cloud", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersmanager), config)
+	networkMapController := controller.NewController(ctx, store, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.cloud", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersmanager), config, nil)
 
 	accountManager, err := mgmt.BuildManager(ctx, config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, iv, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManagerMock, false, cacheStore)
 	if err != nil {

client/cmd/up.go

@@ -2,10 +2,10 @@ package cmd
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"net"
 	"net/netip"
-	"os/user"
 	"runtime"
 	"strings"
 	"time"
@@ -48,6 +48,8 @@ const (
 	profileNameDesc = "profile name to use for the login. If not specified, the last used profile will be used."
 )
 
+var errDaemonActiveProfileUnsupported = errors.New("daemon does not support active profile lookup")
+
 var (
 	foregroundMode     bool
 	dnsLabels          []string
@@ -122,23 +124,25 @@ func upFunc(cmd *cobra.Command, args []string) error {
 
 	pm := profilemanager.NewProfileManager()
 
-	username, err := user.Current()
+	username, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %v", err)
 	}
 
+	var activeProf *profilemanager.Profile
 	var profileSwitched bool
 	// switch profile if provided
 	if profileName != "" {
-		if err := switchOrCreateProfile(cmd.Context(), pm, profileName, username.Username); err != nil {
+		activeProf, err = switchOrCreateProfile(cmd.Context(), pm, profileName, username.Username)
+		if err != nil {
 			return fmt.Errorf("switch profile: %v", err)
 		}
 		profileSwitched = true
-	}
+	} else {
-
+		activeProf, err = pm.GetActiveProfile()
-	activeProf, err := pm.GetActiveProfile()
+		if err != nil {
-	if err != nil {
+			return fmt.Errorf("get active profile: %v", err)
-		return fmt.Errorf("get active profile: %v", err)
+		}
 	}
 
 	if foregroundMode {
@@ -150,13 +154,15 @@ func upFunc(cmd *cobra.Command, args []string) error {
 // switchOrCreateProfile switches the active profile to the one identified by
 // handle, creating it first when it does not exist yet. This restores the
 // pre-0.73 behaviour where `netbird up --profile <name>` auto-creates a
-// missing profile instead of failing.
+// missing profile instead of failing. Returns the daemon-resolved profile so
-func switchOrCreateProfile(ctx context.Context, pm *profilemanager.ProfileManager, handle, username string) error {
+// callers act on it directly instead of re-reading the local state, which is
+// not updated under sudo.
+func switchOrCreateProfile(ctx context.Context, pm *profilemanager.ProfileManager, handle, username string) (*profilemanager.Profile, error) {
 	resolvedID, err := switchProfile(ctx, handle, username)
 	if err != nil {
 		st, ok := gstatus.FromError(err)
 		if !ok || st.Code() != codes.NotFound {
-			return err
+			return nil, err
 		}
 		// Don't fail immediately on a create error: a concurrent run may
 		// have created the profile between the NotFound above and this
@@ -165,16 +171,16 @@ func switchOrCreateProfile(ctx context.Context, pm *profilemanager.ProfileManage
 		_, createErr := createProfile(ctx, handle, username)
 		if resolvedID, err = switchProfile(ctx, handle, username); err != nil {
 			if createErr != nil {
-				return fmt.Errorf("create profile: %w", createErr)
+				return nil, fmt.Errorf("create profile: %w", createErr)
 			}
-			return err
+			return nil, err
 		}
 	}
 
 	if err := pm.SwitchProfile(resolvedID); err != nil {
-		return err
+		return nil, err
 	}
-	return nil
+	return &profilemanager.Profile{ID: resolvedID}, nil
 }
 
 // createProfile dials the daemon and creates a new profile with the given
@@ -302,6 +308,30 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 		return fmt.Errorf("unable to get daemon status: %v", err)
 	}
 
+	// Under sudo the invoking user's local active-profile mirror is never
+	// written (the SwitchProfile write is a no-op), and plain root has no
+	// invoking user at all — so the mirror read into activeProf above is stale
+	// or defaulted and must not drive the daemon. With no --profile to make the
+	// choice explicit, take the profile the daemon already holds for this user
+	// instead: it stays on the user's current profile rather than silently
+	// switching to the mirror's default, and refuses when the daemon is on
+	// another user's profile.
+	if profileName == "" && !profilemanager.MirrorIsAuthoritative() {
+		u, err := profilemanager.InvokingUser()
+		if err != nil {
+			return fmt.Errorf("get current user: %v", err)
+		}
+		resolved, err := daemonActiveProfileForUser(ctx, client, u.Username)
+		switch {
+		case errors.Is(err, errDaemonActiveProfileUnsupported):
+			log.Warnf("keeping the locally resolved profile: %v", err)
+		case err != nil:
+			return err
+		default:
+			activeProf = resolved
+		}
+	}
+
 	if status.Status == string(internal.StatusConnected) {
 		if !profileSwitched {
 			cmd.Println("Already connected")
@@ -314,7 +344,7 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 		}
 	}
 
-	username, err := user.Current()
+	username, err := profilemanager.InvokingUser()
 	if err != nil {
 		return fmt.Errorf("get current user: %v", err)
 	}
@@ -398,26 +428,21 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 	return nil
 }
 
-func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, profileName, username string) *proto.SetConfigRequest {
+// setBoolPtrIfChanged points dst at a copy of val when the named bool flag was
-	var req proto.SetConfigRequest
+// explicitly set on cmd. It collapses the repeated
-	req.ProfileName = profileName
+// "if cmd.Flag(x).Changed { field = &val }" pattern in the request builders into
-	req.Username = username
+// a single call, keeping their cognitive complexity within bounds.
-
+func setBoolPtrIfChanged(cmd *cobra.Command, name string, dst **bool, val bool) {
-	req.ManagementUrl = managementURL
+	if cmd.Flag(name).Changed {
-	req.AdminURL = adminURL
+		dst2 := val
-	req.NatExternalIPs = natExternalIPs
+		*dst = &dst2
-	req.CustomDNSAddress = customDNSAddressConverted
-	req.ExtraIFaceBlacklist = extraIFaceBlackList
-	req.DnsLabels = dnsLabelsValidated.ToPunycodeList()
-	req.CleanDNSLabels = dnsLabels != nil && len(dnsLabels) == 0
-	req.CleanNATExternalIPs = natExternalIPs != nil && len(natExternalIPs) == 0
-
-	if cmd.Flag(enableRosenpassFlag).Changed {
-		req.RosenpassEnabled = &rosenpassEnabled
-	}
-	if cmd.Flag(rosenpassPermissiveFlag).Changed {
-		req.RosenpassPermissive = &rosenpassPermissive
 	}
+}
+
+// setSSHSetConfigFields copies the SSH server flags the user actually
+// passed into req, leaving the rest unset so the daemon keeps the
+// persisted values.
+func setSSHSetConfigFields(req *proto.SetConfigRequest, cmd *cobra.Command) {
 	if cmd.Flag(serverSSHAllowedFlag).Changed {
 		req.ServerSSHAllowed = &serverSSHAllowed
 	}
@@ -440,6 +465,31 @@ func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, pro
 		sshJWTCacheTTL32 := int32(sshJWTCacheTTL)
 		req.SshJWTCacheTTL = &sshJWTCacheTTL32
 	}
+}
+
+func setupSetConfigReq(customDNSAddressConverted []byte, cmd *cobra.Command, profileName, username string) *proto.SetConfigRequest {
+	var req proto.SetConfigRequest
+	req.ProfileName = profileName
+	req.Username = username
+
+	req.ManagementUrl = managementURL
+	req.AdminURL = adminURL
+	req.NatExternalIPs = natExternalIPs
+	req.CustomDNSAddress = customDNSAddressConverted
+	req.ExtraIFaceBlacklist = extraIFaceBlackList
+	req.DnsLabels = dnsLabelsValidated.ToPunycodeList()
+	req.CleanDNSLabels = dnsLabels != nil && len(dnsLabels) == 0
+	req.CleanNATExternalIPs = natExternalIPs != nil && len(natExternalIPs) == 0
+
+	if cmd.Flag(enableRosenpassFlag).Changed {
+		req.RosenpassEnabled = &rosenpassEnabled
+	}
+	if cmd.Flag(rosenpassPermissiveFlag).Changed {
+		req.RosenpassPermissive = &rosenpassPermissive
+	}
+	setSSHSetConfigFields(&req, cmd)
+	setBoolPtrIfChanged(cmd, remoteJobsAllowedFlag, &req.RemoteJobsAllowed, remoteJobsAllowed)
+
 	if cmd.Flag(interfaceNameFlag).Changed {
 		if err := parseInterfaceName(interfaceName); err != nil {
 			log.Errorf("parse interface name: %v", err)
@@ -499,6 +549,13 @@ 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
 }
 
@@ -523,6 +580,7 @@ func setupConfig(customDNSAddressConverted []byte, cmd *cobra.Command, configFil
 	if cmd.Flag(serverSSHAllowedFlag).Changed {
 		ic.ServerSSHAllowed = &serverSSHAllowed
 	}
+	setBoolPtrIfChanged(cmd, remoteJobsAllowedFlag, &ic.RemoteJobsAllowed, remoteJobsAllowed)
 
 	if cmd.Flag(enableSSHRootFlag).Changed {
 		ic.EnableSSHRoot = &enableSSHRoot
@@ -616,9 +674,45 @@ 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
 }
 
+// setSSHLoginFields copies the SSH server flags the user actually passed
+// into req, leaving the rest unset so the daemon keeps the persisted
+// values.
+func setSSHLoginFields(req *proto.LoginRequest, cmd *cobra.Command) {
+	if cmd.Flag(serverSSHAllowedFlag).Changed {
+		req.ServerSSHAllowed = &serverSSHAllowed
+	}
+	if cmd.Flag(enableSSHRootFlag).Changed {
+		req.EnableSSHRoot = &enableSSHRoot
+	}
+	if cmd.Flag(enableSSHSFTPFlag).Changed {
+		req.EnableSSHSFTP = &enableSSHSFTP
+	}
+	if cmd.Flag(enableSSHLocalPortForwardFlag).Changed {
+		req.EnableSSHLocalPortForwarding = &enableSSHLocalPortForward
+	}
+	if cmd.Flag(enableSSHRemotePortForwardFlag).Changed {
+		req.EnableSSHRemotePortForwarding = &enableSSHRemotePortForward
+	}
+	if cmd.Flag(disableSSHAuthFlag).Changed {
+		req.DisableSSHAuth = &disableSSHAuth
+	}
+	if cmd.Flag(sshJWTCacheTTLFlag).Changed {
+		sshJWTCacheTTL32 := int32(sshJWTCacheTTL)
+		req.SshJWTCacheTTL = &sshJWTCacheTTL32
+	}
+}
+
 func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte, cmd *cobra.Command) (*proto.LoginRequest, error) {
 	loginRequest := proto.LoginRequest{
 		SetupKey:            providedSetupKey,
@@ -645,39 +739,21 @@ func setupLoginRequest(providedSetupKey string, customDNSAddressConverted []byte
 		loginRequest.RosenpassPermissive = &rosenpassPermissive
 	}
 
-	if cmd.Flag(serverSSHAllowedFlag).Changed {
+	setSSHLoginFields(&loginRequest, cmd)
-		loginRequest.ServerSSHAllowed = &serverSSHAllowed
+	setBoolPtrIfChanged(cmd, remoteJobsAllowedFlag, &loginRequest.RemoteJobsAllowed, remoteJobsAllowed)
-	}
-
-	if cmd.Flag(enableSSHRootFlag).Changed {
-		loginRequest.EnableSSHRoot = &enableSSHRoot
-	}
-
-	if cmd.Flag(enableSSHSFTPFlag).Changed {
-		loginRequest.EnableSSHSFTP = &enableSSHSFTP
-	}
-
-	if cmd.Flag(enableSSHLocalPortForwardFlag).Changed {
-		loginRequest.EnableSSHLocalPortForwarding = &enableSSHLocalPortForward
-	}
-
-	if cmd.Flag(enableSSHRemotePortForwardFlag).Changed {
-		loginRequest.EnableSSHRemotePortForwarding = &enableSSHRemotePortForward
-	}
-
-	if cmd.Flag(disableSSHAuthFlag).Changed {
-		loginRequest.DisableSSHAuth = &disableSSHAuth
-	}
-
-	if cmd.Flag(sshJWTCacheTTLFlag).Changed {
-		sshJWTCacheTTL32 := int32(sshJWTCacheTTL)
-		loginRequest.SshJWTCacheTTL = &sshJWTCacheTTL32
-	}
 
 	if cmd.Flag(disableAutoConnectFlag).Changed {
 		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
@@ -849,3 +925,31 @@ func isValidAddrPort(input string) bool {
 	_, err := netip.ParseAddrPort(input)
 	return err == nil
 }
+
+// daemonActiveProfileForUser returns the profile the daemon currently holds for
+// username, for the no --profile case where the local mirror is not
+// authoritative (sudo or plain root). It returns that profile when the daemon
+// owns it for this user or when the profile is unowned (empty username, as on a
+// fresh install), so the caller acts on the daemon's real state instead of the
+// stale mirror. It denies with a --profile hint when the daemon is on another
+// user's profile, when the lookup fails, or when the daemon reports no active
+// profile. Returns errDaemonActiveProfileUnsupported when the daemon predates
+// the RPC; the caller keeps the mirror-derived profile in that case.
+func daemonActiveProfileForUser(ctx context.Context, client proto.DaemonServiceClient, username string) (*profilemanager.Profile, error) {
+	active, err := client.GetActiveProfile(ctx, &proto.GetActiveProfileRequest{})
+	if err != nil {
+		if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unimplemented {
+			return nil, fmt.Errorf("%w: %v", errDaemonActiveProfileUnsupported, err)
+		}
+		return nil, fmt.Errorf("pass --profile to choose the profile explicitly: the daemon's active profile could not be verified: %v", err)
+	}
+	if active.GetId() == "" {
+		return nil, fmt.Errorf("pass --profile to choose the profile explicitly: the daemon reported no active profile")
+	}
+	if active.GetUsername() != "" && active.GetUsername() != username {
+		return nil, fmt.Errorf(
+			"pass --profile to choose the profile explicitly: the daemon's active profile is %q (user %q) but this invocation runs for %q",
+			active.GetProfileName(), active.GetUsername(), username)
+	}
+	return &profilemanager.Profile{ID: profilemanager.ID(active.GetId())}, nil
+}

client/cmd/up_test.go

@@ -0,0 +1,88 @@
+package cmd
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/codes"
+	gstatus "google.golang.org/grpc/status"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+type fakeActiveProfileClient struct {
+	proto.DaemonServiceClient
+	resp *proto.GetActiveProfileResponse
+	err  error
+}
+
+func (f *fakeActiveProfileClient) GetActiveProfile(_ context.Context, _ *proto.GetActiveProfileRequest, _ ...grpc.CallOption) (*proto.GetActiveProfileResponse, error) {
+	return f.resp, f.err
+}
+
+func TestDaemonActiveProfileForUserReturnsOwnProfile(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{Id: "default", ProfileName: "default", Username: "root"}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.NoError(t, err)
+	require.NotNil(t, prof)
+	assert.Equal(t, profilemanager.ID("default"), prof.ID)
+}
+
+func TestDaemonActiveProfileForUserReturnsUnownedProfile(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{Id: "default", ProfileName: "default", Username: ""}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.NoError(t, err)
+	require.NotNil(t, prof)
+	assert.Equal(t, profilemanager.ID("default"), prof.ID)
+}
+
+func TestDaemonActiveProfileForUserKeepsDaemonProfileOverStaleMirror(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{Id: "ab12", ProfileName: "work", Username: "misha"}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "misha")
+	require.NoError(t, err)
+	require.NotNil(t, prof)
+	assert.Equal(t, profilemanager.ID("ab12"), prof.ID)
+}
+
+func TestDaemonActiveProfileForUserRejectsOtherUsersProfile(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{Id: "ab12", ProfileName: "work", Username: "misha"}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.Error(t, err)
+	assert.Nil(t, prof)
+	assert.Contains(t, err.Error(), "--profile")
+}
+
+func TestDaemonActiveProfileForUserRejectsOtherUsersDefaultProfile(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{Id: "default", ProfileName: "default", Username: "misha"}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.Error(t, err)
+	assert.Nil(t, prof)
+	assert.Contains(t, err.Error(), "--profile")
+}
+
+func TestDaemonActiveProfileForUserRejectsLookupError(t *testing.T) {
+	client := &fakeActiveProfileClient{err: gstatus.Error(codes.Internal, "boom")}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.Error(t, err)
+	assert.Nil(t, prof)
+	assert.Contains(t, err.Error(), "--profile")
+}
+
+func TestDaemonActiveProfileForUserRejectsEmptyResponse(t *testing.T) {
+	client := &fakeActiveProfileClient{resp: &proto.GetActiveProfileResponse{}}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.Error(t, err)
+	assert.Nil(t, prof)
+	assert.Contains(t, err.Error(), "--profile")
+}
+
+func TestDaemonActiveProfileForUserKeepsMirrorWhenDaemonWithoutRPC(t *testing.T) {
+	client := &fakeActiveProfileClient{err: gstatus.Error(codes.Unimplemented, "unknown method")}
+	prof, err := daemonActiveProfileForUser(context.Background(), client, "root")
+	require.ErrorIs(t, err, errDaemonActiveProfileUnsupported)
+	assert.Nil(t, prof)
+}

client/embed/embed.go

@@ -21,7 +21,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	sshcommon "github.com/netbirdio/netbird/client/ssh"
+	nbssh "github.com/netbirdio/netbird/client/ssh"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/shared/management/domain"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
@@ -85,12 +85,24 @@ type Options struct {
 	DisableIPv6 bool
 	// BlockInbound blocks all inbound connections from peers
 	BlockInbound bool
+	// EnableRosenpass enables the Rosenpass post-quantum key exchange.
+	EnableRosenpass bool
+	// RosenpassPermissive lets a Rosenpass-enabled peer still connect to peers
+	// that do not run Rosenpass (falling back to the plain WireGuard PSK).
+	RosenpassPermissive bool
 	// BlockLANAccess blocks the embedded peer from reaching the host's
 	// LAN (RFC 1918, link-local, loopback) when it's used as a routing
 	// peer. Mirrors profilemanager.ConfigInput.BlockLANAccess. Useful
 	// when the embedded client must never act as a stepping stone into
 	// the host's local network (e.g. the proxy's overlay peer).
 	BlockLANAccess bool
+	// LazyConnectionEnabled is a tri-state local override for lazy connections,
+	// mirroring the NB_LAZY_CONN env var. Nil defers to the management feature
+	// flag; a set value overrides it in both directions. A short-lived client
+	// that reaches only a few known peers can set this to false, so its peers
+	// connect eagerly and the first request does not wait for the connection to
+	// be established.
+	LazyConnectionEnabled *bool
 	// WireguardPort is the port for the tunnel interface. Use 0 for a random port.
 	WireguardPort *int
 	// MTU is the MTU for the tunnel interface.
@@ -203,6 +215,8 @@ func New(opts Options) (*Client, error) {
 		DisableIPv6:         &opts.DisableIPv6,
 		BlockInbound:        &opts.BlockInbound,
 		BlockLANAccess:      &opts.BlockLANAccess,
+		RosenpassEnabled:    &opts.EnableRosenpass,
+		RosenpassPermissive: &opts.RosenpassPermissive,
 		WireguardPort:       opts.WireguardPort,
 		MTU:                 opts.MTU,
 		DNSLabels:           parsedLabels,
@@ -220,6 +234,15 @@ func New(opts Options) (*Client, error) {
 		config.PrivateKey = opts.PrivateKey
 	}
 
+	if opts.LazyConnectionEnabled != nil {
+		// Runtime-only override, read back through lazyconn.ParseState; a set value
+		// wins over the management feature flag in both directions.
+		config.LazyConnection = "off"
+		if *opts.LazyConnectionEnabled {
+			config.LazyConnection = "on"
+		}
+	}
+
 	if opts.Performance.PreallocatedBuffersPerPool != nil {
 		wgdevice.SetPreallocatedBuffersPerPool(*opts.Performance.PreallocatedBuffersPerPool)
 	}
@@ -521,12 +544,7 @@ func (c *Client) VerifySSHHostKey(peerAddress string, key []byte) error {
 		return err
 	}
 
-	storedKey, found := engine.GetPeerSSHKey(peerAddress)
+	return nbssh.PeerKeyLookup(engine.GetPeerSSHKey).VerifySSHHostKey(peerAddress, key)
-	if !found {
-		return sshcommon.ErrPeerNotFound
-	}
-
-	return sshcommon.VerifyHostKey(storedKey, key, peerAddress)
 }
 
 // SetPerformance retunes a running Client. Only PreallocatedBuffersPerPool

client/embed/embed_test.go

@@ -6,7 +6,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/stretchr/testify/require"
 	"google.golang.org/grpc"
 
@@ -146,7 +146,7 @@ func startManagement(t *testing.T, signalAddr string) string {
 
 	updateManager := update_channel.NewPeersUpdateManager(metrics)
 	requestBuffer := mgmt.NewAccountRequestBuffer(context.Background(), testStore)
-	networkMapController := controller.NewController(context.Background(), testStore, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(testStore, peersManager), cfg)
+	networkMapController := controller.NewController(context.Background(), testStore, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(testStore, peersManager), cfg, nil)
 	accountManager, err := mgmt.BuildManager(context.Background(), cfg, testStore, networkMapController, jobManager, nil, "", eventStore, nil, false, iv, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false, cacheStore)
 	require.NoError(t, err)
 

client/firewall/nftables/router_linux.go

@@ -763,7 +763,7 @@ func (r *router) addNatRule(pair firewall.RouterPair) error {
 	exprs = append(exprs, sourceExp...)
 	exprs = append(exprs, destExp...)
 
-	var markValue uint32 = nbnet.PreroutingFwmarkMasquerade
+	markValue := nbnet.PreroutingFwmarkMasquerade
 	if pair.Inverse {
 		markValue = nbnet.PreroutingFwmarkMasqueradeReturn
 	}

client/firewall/uspfilter/filter_filter_test.go

@@ -5,7 +5,7 @@ import (
 	"net/netip"
 	"testing"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/google/gopacket"
 	"github.com/google/gopacket/layers"
 	"github.com/stretchr/testify/require"

client/firewall/uspfilter/filter_routeacl_test.go

@@ -4,7 +4,7 @@ import (
 	"net/netip"
 	"testing"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/google/gopacket/layers"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"

client/grpc/dialer_generic.go

@@ -16,28 +16,52 @@ import (
 	"google.golang.org/grpc"
 
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netevents/sweep"
 )
 
+// Sweeper registers in-flight dials for the network change sweep.
+type Sweeper interface {
+	StartDial(ctx context.Context) *sweep.Dial
+}
+
 func WithCustomDialer(_ bool, _ string) grpc.DialOption {
+	return grpc.WithContextDialer(dialContext)
+}
+
+// WithSweeper dials like WithCustomDialer but registers connections and
+// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
+// dial options in order, so the later context dialer wins.
+func WithSweeper(sweeper Sweeper) grpc.DialOption {
 	return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
-		if runtime.GOOS == "linux" {
+		dial := sweeper.StartDial(ctx)
-			currentUser, err := user.Current()
+		defer dial.Release()
-			if err != nil {
-				return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
-			}
 
-			// the custom dialer requires root permissions which are not required for use cases run as non-root
+		conn, err := dialContext(dial.Ctx(), addr)
-			if currentUser.Uid != "0" {
-				log.Debug("Not running as root, using standard dialer")
-				dialer := &net.Dialer{}
-				return dialer.DialContext(ctx, "tcp", addr)
-			}
-		}
-
-		conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
 		if err != nil {
-			return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+			return nil, err
 		}
-		return conn, nil
+		return dial.WrapConn(conn)
 	})
 }
+
+func dialContext(ctx context.Context, addr string) (net.Conn, error) {
+	if runtime.GOOS == "linux" {
+		currentUser, err := user.Current()
+		if err != nil {
+			return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
+		}
+
+		// the custom dialer requires root permissions which are not required for use cases run as non-root
+		if currentUser.Uid != "0" {
+			log.Debug("Not running as root, using standard dialer")
+			dialer := &net.Dialer{}
+			return dialer.DialContext(ctx, "tcp", addr)
+		}
+	}
+
+	conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+	}
+	return conn, nil
+}

client/grpc/dialer_js.go

@@ -1,13 +1,26 @@
 package grpc
 
 import (
+	"context"
+
 	"google.golang.org/grpc"
 
+	"github.com/netbirdio/netbird/client/netevents/sweep"
 	"github.com/netbirdio/netbird/util/wsproxy/client"
 )
 
+// Sweeper registers in-flight dials for the network change sweep.
+type Sweeper interface {
+	StartDial(ctx context.Context) *sweep.Dial
+}
+
 // WithCustomDialer returns a gRPC dial option that uses WebSocket transport for WASM/JS environments.
 // The component parameter specifies the WebSocket proxy component path (e.g., "/management", "/signal").
 func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
 	return client.WithWebSocketDialer(tlsEnabled, component)
 }
+
+// WithSweeper is a no-op on WASM/JS: there is no network change signal.
+func WithSweeper(_ Sweeper) grpc.DialOption {
+	return grpc.EmptyDialOption{}
+}

client/grpc/retry.go

@@ -0,0 +1,56 @@
+package grpc
+
+import (
+	"context"
+	"errors"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+)
+
+// ChangeWatcher exposes OS network availability transitions.
+type ChangeWatcher interface {
+	Changed() <-chan struct{}
+}
+
+// Retry mirrors backoff.Retry, but the sleep between attempts also wakes on
+// OS network availability transitions: an operation cut down by a network
+// change retries the moment the network settles instead of sleeping through
+// the recovery. A nil watcher never fires, leaving plain backoff.Retry
+// behavior.
+func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, watcher ChangeWatcher) error {
+	bo.Reset()
+	for {
+		err := operation()
+		if err == nil {
+			return nil
+		}
+
+		var permanent *backoff.PermanentError
+		if errors.As(err, &permanent) {
+			return permanent.Err
+		}
+
+		next := bo.NextBackOff()
+		if next == backoff.Stop {
+			if cerr := ctx.Err(); cerr != nil {
+				return cerr
+			}
+			return err
+		}
+
+		var changed <-chan struct{}
+		if watcher != nil {
+			changed = watcher.Changed()
+		}
+		timer := time.NewTimer(next)
+		select {
+		case <-timer.C:
+		case <-changed:
+			timer.Stop()
+		case <-ctx.Done():
+			timer.Stop()
+			return ctx.Err()
+		}
+	}
+}

client/grpc/retry_test.go

@@ -0,0 +1,91 @@
+package grpc
+
+import (
+	"context"
+	"errors"
+	"testing"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/netevents/netstate"
+)
+
+func TestRetryWakesOnNetworkChange(t *testing.T) {
+	ns := netstate.New()
+	attempts := 0
+	operation := func() error {
+		attempts++
+		if attempts == 1 {
+			return errors.New("cut by network change")
+		}
+		return nil
+	}
+
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		ns.Set(false)
+	}()
+
+	start := time.Now()
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Minute), ns)
+
+	require.NoError(t, err)
+	assert.Equal(t, 2, attempts, "network change must cause one immediate retry")
+	assert.Less(t, time.Since(start), time.Second, "the transition must cut the minute-long sleep short")
+}
+
+func TestRetryPermanentError(t *testing.T) {
+	sentinel := errors.New("permission denied")
+	operation := func() error {
+		return backoff.Permanent(sentinel)
+	}
+
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
+	assert.ErrorIs(t, err, sentinel, "permanent errors must stop retries")
+}
+
+func TestRetryNilNetState(t *testing.T) {
+	attempts := 0
+	operation := func() error {
+		attempts++
+		if attempts < 3 {
+			return errors.New("transient")
+		}
+		return nil
+	}
+
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
+	require.NoError(t, err)
+	assert.Equal(t, 3, attempts, "nil network state must preserve timed retries")
+}
+
+func TestRetryStops(t *testing.T) {
+	failure := errors.New("still failing")
+	operation := func() error {
+		return failure
+	}
+
+	err := Retry(context.Background(), operation, &backoff.StopBackOff{}, nil)
+	assert.ErrorIs(t, err, failure, "stop backoff must return the operation error")
+}
+
+func TestRetryCtxCancelDuringSleep(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	operation := func() error {
+		return errors.New("failing")
+	}
+
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		cancel()
+	}()
+
+	start := time.Now()
+	err := Retry(ctx, operation, backoff.NewConstantBackOff(time.Minute), netstate.New())
+
+	assert.ErrorIs(t, err, context.Canceled, "context cancellation must stop the retry loop")
+	assert.Less(t, time.Since(start), time.Second, "context cancellation must interrupt backoff sleep")
+}

client/iface/bind/ice_bind.go

@@ -57,10 +57,13 @@ type ICEBind struct {
 	endpoints   map[netip.Addr]net.Conn
 	endpointsMu sync.Mutex
 	recvChan    chan recvMessage
-	// every time when Close() is called (i.e. BindUpdate()) we need to close exit from the receiveRelayed and create a
+	// Close() (i.e. BindUpdate()) closes closedChan to release receiveRelayed,
-	// new closed channel. With the closedChanMu we can safely close the channel and create a new one
+	// and the following Open() installs a fresh one. closedChanMu guards both
+	// closedChan and closed: readers only ever hold it long enough to copy the
+	// channel, never across a blocking receive, so Open cannot be starved by a
+	// parked receiver.
 	closedChan       chan struct{}
-	closedChanMu     sync.RWMutex // protect the closeChan recreation from reading from it.
+	closedChanMu     sync.RWMutex
 	closed           bool
 	activityRecorder *ActivityRecorder
 
@@ -92,24 +95,41 @@ func NewICEBind(transportNet transport.Net, address wgaddr.Address, mtu uint16)
 }
 
 func (s *ICEBind) Open(uport uint16) ([]wgConn.ReceiveFunc, uint16, error) {
-	s.closed = false
 	s.closedChanMu.Lock()
-	s.closedChan = make(chan struct{})
+	defer s.closedChanMu.Unlock()
-	s.closedChanMu.Unlock()
+
+	// Open the underlying bind before touching any state, so a failure leaves
+	// the current generation exactly as it was. Publishing the new generation
+	// first would strand it: StdNetBind rejects an Open while it is already
+	// open, and a Close arriving in that window would mark the bind closed
+	// while this call went on to install live sockets, after which every later
+	// Close returns early and never shuts them down.
 	fns, port, err := s.StdNetBind.Open(uport)
 	if err != nil {
 		return nil, 0, err
 	}
+
+	// Release whoever is parked on the outgoing generation before replacing it.
+	// An Open that follows an Open rather than a Close would otherwise leave
+	// them waiting on a channel no later Close can reach.
+	if !s.closed {
+		close(s.closedChan)
+	}
+	s.closed = false
+	s.closedChan = make(chan struct{})
+
 	fns = append(fns, s.receiveRelayed)
 	return fns, port, nil
 }
 
 func (s *ICEBind) Close() error {
+	s.closedChanMu.Lock()
+	defer s.closedChanMu.Unlock()
+
 	if s.closed {
 		return nil
 	}
 	s.closed = true
-
 	close(s.closedChan)
 
 	s.muUDPMux.Lock()
@@ -121,6 +141,15 @@ func (s *ICEBind) Close() error {
 	return s.StdNetBind.Close()
 }
 
+// currentClosedChan copies the channel that signals the current Open
+// generation is closing. Callers select on the copy so the lock is never held
+// across a blocking receive, which would otherwise stall the next Open.
+func (s *ICEBind) currentClosedChan() chan struct{} {
+	s.closedChanMu.RLock()
+	defer s.closedChanMu.RUnlock()
+	return s.closedChan
+}
+
 func (s *ICEBind) ActivityRecorder() *ActivityRecorder {
 	return s.activityRecorder
 }
@@ -150,8 +179,10 @@ func (b *ICEBind) RemoveEndpoint(fakeIP netip.Addr) {
 }
 
 func (b *ICEBind) ReceiveFromEndpoint(ctx context.Context, ep *Endpoint, buf []byte) {
+	closedChan := b.currentClosedChan()
+
 	select {
-	case <-b.closedChan:
+	case <-closedChan:
 		return
 	case <-ctx.Done():
 		return
@@ -333,11 +364,10 @@ func (s *ICEBind) parseSTUNMessage(raw []byte) (*stun.Message, error) {
 // receiveRelayed is a receive function that is used to receive packets from the relayed connection and forward to the
 // WireGuard. Critical part is do not block if the Closed() has been called.
 func (c *ICEBind) receiveRelayed(buffs [][]byte, sizes []int, eps []wgConn.Endpoint) (int, error) {
-	c.closedChanMu.RLock()
+	closedChan := c.currentClosedChan()
-	defer c.closedChanMu.RUnlock()
 
 	select {
-	case <-c.closedChan:
+	case <-closedChan:
 		return 0, net.ErrClosed
 	case msg, ok := <-c.recvChan:
 		if !ok {

client/iface/bind/ice_bind_close_test.go

@@ -0,0 +1,261 @@
+package bind
+
+import (
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	wgConn "golang.zx2c4.com/wireguard/conn"
+)
+
+// startReceivers runs every receive function the way wireguard-go's device
+// does: one goroutine per function, all tracked by a single WaitGroup. After
+// calling Bind.Close, closeBindLocked waits on exactly that WaitGroup while
+// holding device.net, so a receive function that never returns wedges the
+// device and every goroutine that needs the same lock.
+func startReceivers(fns []wgConn.ReceiveFunc) *sync.WaitGroup {
+	wg, _ := startReceiversEntered(fns)
+	return wg
+}
+
+// startReceiversEntered also returns a channel closed once every receive
+// function has been called at least once. A receive function that has been
+// entered is either inside its blocking receive or about to be, which is a
+// stronger signal to synchronise on than a bare sleep.
+func startReceiversEntered(fns []wgConn.ReceiveFunc) (*sync.WaitGroup, <-chan struct{}) {
+	var wg sync.WaitGroup
+	var entered sync.WaitGroup
+	wg.Add(len(fns))
+	entered.Add(len(fns))
+
+	for i := range fns {
+		go func(fn wgConn.ReceiveFunc) {
+			defer wg.Done()
+			buffs := [][]byte{make([]byte, 1500)}
+			sizes := make([]int, 1)
+			eps := make([]wgConn.Endpoint, 1)
+			first := true
+			for {
+				if first {
+					entered.Done()
+					first = false
+				}
+				if _, err := fn(buffs, sizes, eps); err != nil {
+					return
+				}
+			}
+		}(fns[i])
+	}
+
+	allEntered := make(chan struct{})
+	go func() {
+		entered.Wait()
+		close(allEntered)
+	}()
+	return &wg, allEntered
+}
+
+// closeBounded runs Close off the caller's goroutine so a regression that
+// wedges it fails the test instead of hanging teardown, and reports whether it
+// returned in time.
+func closeBounded(iceBind *ICEBind, timeout time.Duration) bool {
+	done := make(chan struct{})
+	go func() {
+		_ = iceBind.Close()
+		close(done)
+	}()
+	select {
+	case <-done:
+		return true
+	case <-time.After(timeout):
+		return false
+	}
+}
+
+// isClosed reports whether the bind's current generation channel is closed.
+func isClosed(iceBind *ICEBind) bool {
+	iceBind.closedChanMu.RLock()
+	ch := iceBind.closedChan
+	iceBind.closedChanMu.RUnlock()
+	select {
+	case <-ch:
+		return true
+	default:
+		return false
+	}
+}
+
+// receiversStopped reports whether every receive function returned before the
+// timeout, mirroring device.net.stopping.Wait() inside closeBindLocked.
+func receiversStopped(wg *sync.WaitGroup, timeout time.Duration) bool {
+	done := make(chan struct{})
+	go func() {
+		wg.Wait()
+		close(done)
+	}()
+	select {
+	case <-done:
+		return true
+	case <-time.After(timeout):
+		return false
+	}
+}
+
+// TestICEBindCloseReleasesReceivers covers the contract closeBindLocked relies
+// on: once Close returns, every receive function handed out by Open must stop.
+func TestICEBindCloseReleasesReceivers(t *testing.T) {
+	iceBind := setupICEBind(t)
+
+	fns, _, err := iceBind.Open(0)
+	require.NoError(t, err, "opening the bind must succeed")
+
+	wg := startReceivers(fns)
+	require.NoError(t, iceBind.Close())
+
+	require.True(t, receiversStopped(wg, 5*time.Second),
+		"every receive function must return once Close returns")
+}
+
+// TestICEBindOpenDoesNotBlockOnParkedReceiver reproduces the deadlock that
+// wedges interface creation.
+//
+// receiveRelayed used to hold closedChanMu for the whole of its blocking
+// select, so a parked receiver kept the read lock indefinitely. Open takes the
+// same mutex for writing to install a fresh closedChan, so it could never
+// acquire it while a receiver was parked. wireguard-go reaches Open from
+// Device.IpcSet and Device.Up with device.net held, so the stall takes the
+// device's lock with it and every other device goroutine queues behind it.
+//
+// Failing here means Open never returned.
+func TestICEBindOpenDoesNotBlockOnParkedReceiver(t *testing.T) {
+	iceBind := setupICEBind(t)
+
+	fns, _, err := iceBind.Open(0)
+	require.NoError(t, err, "the first Open must succeed")
+
+	wg, entered := startReceiversEntered(fns)
+	t.Cleanup(func() {
+		// Both bounded: a regression that wedges Close must surface as the
+		// assertion below, not as a hung teardown.
+		if !closeBounded(iceBind, 5*time.Second) {
+			t.Error("Close did not return during teardown; the bind lifecycle is wedged even though the assertion above passed")
+		}
+		if !receiversStopped(wg, 5*time.Second) {
+			t.Error("receive functions were still running after teardown Close, which is what closeBindLocked blocks on")
+		}
+	})
+
+	select {
+	case <-entered:
+	case <-time.After(5 * time.Second):
+		t.Fatal("receive functions never started")
+	}
+	// Entered is not yet parked, so still allow the blocking receive to be
+	// reached. Parking takes microseconds; this margin is six orders larger.
+	time.Sleep(500 * time.Millisecond)
+
+	reopened := make(chan struct{})
+	go func() {
+		// The error is irrelevant; StdNetBind rejects a second Open. What
+		// matters is that the call returns at all.
+		_, _, _ = iceBind.Open(0)
+		close(reopened)
+	}()
+
+	select {
+	case <-reopened:
+	case <-time.After(10 * time.Second):
+		t.Fatal("Open blocked while a receive function was parked; wireguard-go makes this call with device.net held, which is what stalls interface creation")
+	}
+}
+
+// TestICEBindConcurrentOpenClose exercises Open and Close from separate
+// goroutines, the way Device.IpcSet and Device.Up reach the bind, and is meant
+// to be run under -race.
+//
+// closed and closedChan must be updated together. When they were not, Close
+// could observe a stale closed and either skip close(closedChan) and
+// StdNetBind.Close entirely, leaving the receive functions running, or race a
+// second Close and close the same channel twice.
+//
+// Receive functions are deliberately not started here: this test is about the
+// shared state, and parking them would turn a race report into a hang.
+func TestICEBindConcurrentOpenClose(t *testing.T) {
+	iceBind := setupICEBind(t)
+
+	var wg sync.WaitGroup
+	wg.Add(2)
+
+	// Release both loops together so the calls genuinely interleave rather
+	// than depending on goroutine start order.
+	start := make(chan struct{})
+
+	go func() {
+		defer wg.Done()
+		<-start
+		for i := 0; i < 200; i++ {
+			_, _, _ = iceBind.Open(0)
+		}
+	}()
+	go func() {
+		defer wg.Done()
+		<-start
+		for i := 0; i < 200; i++ {
+			_ = iceBind.Close()
+		}
+	}()
+
+	close(start)
+	wg.Wait()
+	require.NoError(t, iceBind.Close())
+	require.True(t, isClosed(iceBind), "the final Close must leave the current generation channel closed")
+}
+
+// TestICEBindCloseReleasesReceiversUnderConcurrentClose runs full Open, receive,
+// Close cycles with a second Close and an Open racing the first Close. Any
+// iteration where the receive functions outlive Close, or where the surviving
+// generation channel is left open, is the state closeBindLocked deadlocks on.
+func TestICEBindCloseReleasesReceiversUnderConcurrentClose(t *testing.T) {
+	if testing.Short() {
+		t.Skip("stress test")
+	}
+
+	for i := 0; i < 200; i++ {
+		iceBind := setupICEBind(t)
+
+		fns, _, err := iceBind.Open(0)
+		require.NoError(t, err, "iteration %d: opening the bind must succeed", i)
+		wg := startReceivers(fns)
+
+		start := make(chan struct{})
+		var racers sync.WaitGroup
+		racers.Add(3)
+		for c := 0; c < 2; c++ {
+			go func() {
+				defer racers.Done()
+				<-start
+				_ = iceBind.Close()
+			}()
+		}
+		// An Open overlapping the Closes is what produces a generation whose
+		// channel outlives the flag saying the bind is closed.
+		go func() {
+			defer racers.Done()
+			<-start
+			_, _, _ = iceBind.Open(0)
+		}()
+		close(start)
+		racers.Wait()
+
+		// Settle on a closed bind whatever order the racers landed in.
+		_ = iceBind.Close()
+
+		if !receiversStopped(wg, 5*time.Second) {
+			t.Fatalf("iteration %d: receive functions still running after Close; closeBindLocked would block here on device.net.stopping.Wait", i)
+		}
+		if !isClosed(iceBind) {
+			t.Fatalf("iteration %d: Close returned with the current generation channel still open, so nothing will ever release its receivers", i)
+		}
+	}
+}

client/iface/configurer/usp.go

@@ -502,7 +502,7 @@ func toBytes(s string) (int64, error) {
 
 func getFwmark() int {
 	if nbnet.AdvancedRouting() && runtime.GOOS == "linux" {
-		return nbnet.ControlPlaneMark
+		return int(nbnet.ControlPlaneMark)
 	}
 	return 0
 }

client/iface/device/device_filter_test.go

@@ -4,7 +4,7 @@ import (
 	"net"
 	"testing"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/google/gopacket"
 	"github.com/google/gopacket/layers"
 

client/iface/mocks/filter.go

@@ -8,7 +8,7 @@ import (
 	"net/netip"
 	reflect "reflect"
 
-	gomock "github.com/golang/mock/gomock"
+	gomock "go.uber.org/mock/gomock"
 )
 
 // MockPacketFilter is a mock of PacketFilter interface.

client/iface/mocks/tun.go

@@ -8,7 +8,7 @@ import (
 	os "os"
 	reflect "reflect"
 
-	gomock "github.com/golang/mock/gomock"
+	gomock "go.uber.org/mock/gomock"
 	tun "golang.zx2c4.com/wireguard/tun"
 )
 

client/iface/wgproxy/bind/proxy.go

@@ -53,15 +53,15 @@ func NewProxyBind(bind Bind, mtu uint16) *ProxyBind {
 	return p
 }
 
-// AddTurnConn adds a new connection to the bind.
+// AddRelayedConn adds a new connection to the bind.
 // endpoint is the NetBird address of the remote peer. The SetEndpoint return with the address what will be used in the
 // WireGuard configuration.
 //
 // Parameters:
 //   - ctx: Context is used for proxyToLocal to avoid unnecessary error messages
 //   - nbAddr: The NetBird UDP address of the remote peer, it required to generate fake address
-//   - remoteConn: The established TURN connection to the remote peer
+//   - remoteConn: The established relayed connection to the remote peer
-func (p *ProxyBind) AddTurnConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error {
+func (p *ProxyBind) AddRelayedConn(ctx context.Context, nbAddr *net.UDPAddr, remoteConn net.Conn) error {
 	fakeNetIP, err := fakeAddress(nbAddr)
 	if err != nil {
 		return err

client/iface/wgproxy/ebpf/proxy.go

@@ -30,9 +30,9 @@ type WGEBPFProxy struct {
 	proxyPort         int
 	mtu               uint16
 
-	ebpfManager   ebpfMgr.Manager
+	ebpfManager      ebpfMgr.Manager
-	turnConnStore map[uint16]net.Conn
+	relayedConnStore map[uint16]net.Conn
-	turnConnMutex sync.Mutex
+	relayedConnMutex sync.Mutex
 
 	lastUsedPort uint16
 	rawConnIPv4  net.PacketConn
@@ -50,7 +50,7 @@ func NewWGEBPFProxy(wgPort int, mtu uint16) *WGEBPFProxy {
 		localWGListenPort: wgPort,
 		mtu:               mtu,
 		ebpfManager:       ebpf.GetEbpfManagerInstance(),
-		turnConnStore:     make(map[uint16]net.Conn),
+		relayedConnStore:  make(map[uint16]net.Conn),
 	}
 	return wgProxy
 }
@@ -110,14 +110,14 @@ func (p *WGEBPFProxy) Listen() error {
 	return nil
 }
 
-// AddTurnConn add new turn connection for the proxy
+// AddRelayedConn add new relayed connection for the proxy
-func (p *WGEBPFProxy) AddTurnConn(turnConn net.Conn) (*net.UDPAddr, error) {
+func (p *WGEBPFProxy) AddRelayedConn(relayedConn net.Conn) (*net.UDPAddr, error) {
-	wgEndpointPort, err := p.storeTurnConn(turnConn)
+	wgEndpointPort, err := p.storeRelayedConn(relayedConn)
 	if err != nil {
 		return nil, err
 	}
 
-	log.Infof("turn conn added to wg proxy store: %s, endpoint port: :%d", turnConn.RemoteAddr(), wgEndpointPort)
+	log.Infof("relayed conn added to wg proxy store: %s, endpoint port: :%d", relayedConn.RemoteAddr(), wgEndpointPort)
 
 	wgEndpoint := &net.UDPAddr{
 		IP:   net.ParseIP(loopbackAddr),
@@ -186,48 +186,48 @@ func (p *WGEBPFProxy) readAndForwardPacket(buf []byte) error {
 		return fmt.Errorf("failed to read UDP packet from WG: %w", err)
 	}
 
-	p.turnConnMutex.Lock()
+	p.relayedConnMutex.Lock()
-	conn, ok := p.turnConnStore[uint16(addr.Port)]
+	conn, ok := p.relayedConnStore[uint16(addr.Port)]
-	p.turnConnMutex.Unlock()
+	p.relayedConnMutex.Unlock()
 	if !ok {
 		if p.ctx.Err() == nil {
-			log.Debugf("turn conn not found by port because conn already has been closed: %d", addr.Port)
+			log.Debugf("relayed conn not found by port because conn already has been closed: %d", addr.Port)
 		}
 		return nil
 	}
 
 	if _, err := conn.Write(buf[:n]); err != nil {
-		return fmt.Errorf("failed to forward local WG packet (%d) to remote turn conn: %w", addr.Port, err)
+		return fmt.Errorf("forward local WG packet (%d) to remote relayed conn: %w", addr.Port, err)
 	}
 	return nil
 }
 
-func (p *WGEBPFProxy) storeTurnConn(turnConn net.Conn) (uint16, error) {
+func (p *WGEBPFProxy) storeRelayedConn(relayedConn net.Conn) (uint16, error) {
-	p.turnConnMutex.Lock()
+	p.relayedConnMutex.Lock()
-	defer p.turnConnMutex.Unlock()
+	defer p.relayedConnMutex.Unlock()
 
 	np, err := p.nextFreePort()
 	if err != nil {
 		return np, err
 	}
-	p.turnConnStore[np] = turnConn
+	p.relayedConnStore[np] = relayedConn
 	return np, nil
 }
 
-func (p *WGEBPFProxy) removeTurnConn(turnConnID uint16) {
+func (p *WGEBPFProxy) removeRelayedConn(relayedConnID uint16) {
-	p.turnConnMutex.Lock()
+	p.relayedConnMutex.Lock()
-	defer p.turnConnMutex.Unlock()
+	defer p.relayedConnMutex.Unlock()
 
-	_, ok := p.turnConnStore[turnConnID]
+	_, ok := p.relayedConnStore[relayedConnID]
 	if ok {
-		log.Debugf("remove turn conn from store by port: %d", turnConnID)
+		log.Debugf("remove relayed conn from store by port: %d", relayedConnID)
 	}
-	delete(p.turnConnStore, turnConnID)
+	delete(p.relayedConnStore, relayedConnID)
 }
 
 func (p *WGEBPFProxy) nextFreePort() (uint16, error) {
-	if len(p.turnConnStore) == 65535 {
+	if len(p.relayedConnStore) == 65535 {
-		return 0, fmt.Errorf("reached maximum turn connection numbers")
+		return 0, fmt.Errorf("reached maximum relayed connection numbers")
 	}
 generatePort:
 	if p.lastUsedPort == 65535 {
@@ -236,7 +236,7 @@ generatePort:
 		p.lastUsedPort++
 	}
 
-	if _, ok := p.turnConnStore[p.lastUsedPort]; ok {
+	if _, ok := p.relayedConnStore[p.lastUsedPort]; ok {
 		goto generatePort
 	}
 	return p.lastUsedPort, nil

client/iface/wgproxy/ebpf/proxy_test.go

@@ -9,32 +9,32 @@ import (
 func TestWGEBPFProxy_connStore(t *testing.T) {
 	wgProxy := NewWGEBPFProxy(1, 1280)
 
-	p, _ := wgProxy.storeTurnConn(nil)
+	p, _ := wgProxy.storeRelayedConn(nil)
 	if p != 1 {
 		t.Errorf("invalid initial port: %d", wgProxy.lastUsedPort)
 	}
 
 	numOfConns := 10
 	for i := 0; i < numOfConns; i++ {
-		p, _ = wgProxy.storeTurnConn(nil)
+		p, _ = wgProxy.storeRelayedConn(nil)
 	}
 	if p != uint16(numOfConns)+1 {
 		t.Errorf("invalid last used port: %d, expected: %d", p, numOfConns+1)
 	}
-	if len(wgProxy.turnConnStore) != numOfConns+1 {
+	if len(wgProxy.relayedConnStore) != numOfConns+1 {
-		t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), numOfConns+1)
+		t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), numOfConns+1)
 	}
 }
 
 func TestWGEBPFProxy_portCalculation_overflow(t *testing.T) {
 	wgProxy := NewWGEBPFProxy(1, 1280)
 
-	_, _ = wgProxy.storeTurnConn(nil)
+	_, _ = wgProxy.storeRelayedConn(nil)
 	wgProxy.lastUsedPort = 65535
-	p, _ := wgProxy.storeTurnConn(nil)
+	p, _ := wgProxy.storeRelayedConn(nil)
 
-	if len(wgProxy.turnConnStore) != 2 {
+	if len(wgProxy.relayedConnStore) != 2 {
-		t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.turnConnStore), 2)
+		t.Errorf("invalid store size: %d, expected: %d", len(wgProxy.relayedConnStore), 2)
 	}
 
 	if p != 2 {
@@ -46,11 +46,11 @@ func TestWGEBPFProxy_portCalculation_maxConn(t *testing.T) {
 	wgProxy := NewWGEBPFProxy(1, 1280)
 
 	for i := 0; i < 65535; i++ {
-		_, _ = wgProxy.storeTurnConn(nil)
+		_, _ = wgProxy.storeRelayedConn(nil)
 	}
 
-	_, err := wgProxy.storeTurnConn(nil)
+	_, err := wgProxy.storeRelayedConn(nil)
 	if err == nil {
-		t.Errorf("invalid turn conn store calculation")
+		t.Errorf("invalid relayed conn store calculation")
 	}
 }

client/iface/wgproxy/ebpf/wrapper.go

@@ -121,10 +121,10 @@ func NewProxyWrapper(proxy *WGEBPFProxy) *ProxyWrapper {
 	}
 }
 
-func (p *ProxyWrapper) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
+func (p *ProxyWrapper) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
-	addr, err := p.wgeBPFProxy.AddTurnConn(remoteConn)
+	addr, err := p.wgeBPFProxy.AddRelayedConn(remoteConn)
 	if err != nil {
-		return fmt.Errorf("add turn conn: %w", err)
+		return fmt.Errorf("add relayed conn: %w", err)
 	}
 
 	headers, err := NewPacketHeaders(p.wgeBPFProxy.localWGListenPort, addr)
@@ -252,7 +252,7 @@ func (p *ProxyWrapper) CloseConn() error {
 }
 
 func (p *ProxyWrapper) proxyToLocal(ctx context.Context) {
-	defer p.wgeBPFProxy.removeTurnConn(uint16(p.wgRelayedEndpointAddr.Port))
+	defer p.wgeBPFProxy.removeRelayedConn(uint16(p.wgRelayedEndpointAddr.Port))
 
 	buf := make([]byte, p.wgeBPFProxy.mtu+bufsize.WGBufferOverhead)
 	for {
@@ -273,7 +273,7 @@ func (p *ProxyWrapper) proxyToLocal(ctx context.Context) {
 			if ctx.Err() != nil {
 				return
 			}
-			log.Errorf("failed to write out turn pkg to local conn: %v", err)
+			log.Errorf("failed to write out relayed pkg to local conn: %v", err)
 		}
 	}
 }
@@ -286,7 +286,7 @@ func (p *ProxyWrapper) readFromRemote(ctx context.Context, buf []byte) (int, err
 		}
 		p.closeListener.Notify()
 		if !errors.Is(err, io.EOF) {
-			log.Errorf("failed to read from turn conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err)
+			log.Errorf("failed to read from relayed conn (endpoint: :%d): %s", p.wgRelayedEndpointAddr.Port, err)
 		}
 		return 0, err
 	}

client/iface/wgproxy/proxy.go

@@ -7,7 +7,7 @@ import (
 
 // Proxy is a transfer layer between the relayed connection and the WireGuard
 type Proxy interface {
-	AddTurnConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error
+	AddRelayedConn(ctx context.Context, endpoint *net.UDPAddr, remoteConn net.Conn) error
 	EndpointAddr() *net.UDPAddr // EndpointAddr returns the address of the WireGuard peer endpoint
 	Work()                      // Work start or resume the proxy
 	Pause()                     // Pause to forward the packages from remote connection to WireGuard. The opposite way still works.

client/iface/wgproxy/proxy_test.go

@@ -95,7 +95,7 @@ func TestProxyCloseByRemoteConn(t *testing.T) {
 		t.Run(tt.name, func(t *testing.T) {
 			addr, _ := net.ResolveUDPAddr("udp", "100.108.135.221:51892")
 			relayedConn := newMockConn()
-			err := tt.proxy.AddTurnConn(ctx, addr, relayedConn)
+			err := tt.proxy.AddRelayedConn(ctx, addr, relayedConn)
 			if err != nil {
 				t.Errorf("error: %v", err)
 			}
@@ -157,7 +157,7 @@ func redirectTraffic(t *testing.T, proxy Proxy, wgPort int, endPointAddr *net.UD
 		_ = relayedServer.Close()
 	}()
 
-	if err := proxy.AddTurnConn(context.Background(), endPointAddr, relayedConn); err != nil {
+	if err := proxy.AddRelayedConn(context.Background(), endPointAddr, relayedConn); err != nil {
 		t.Errorf("error: %v", err)
 	}
 	defer func() {

client/iface/wgproxy/rawsocket/rawsocket.go

@@ -10,8 +10,6 @@ import (
 
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/sys/unix"
-
-	nbnet "github.com/netbirdio/netbird/client/net"
 )
 
 // PrepareSenderRawSocketIPv4 creates and configures a raw socket for sending IPv4 packets
@@ -60,14 +58,12 @@ func prepareSenderRawSocket(family int, isIPv4 bool) (net.PacketConn, error) {
 		return nil, fmt.Errorf("binding to lo interface failed: %w", err)
 	}
 
-	// Set the fwmark on the socket.
+	// The socket is bound to lo and only ever sends to the local WireGuard
-	err = nbnet.SetSocketOpt(fd)
+	// instance, a destination the local routing table resolves without help, so
-	if err != nil {
+	// it carries no fwmark. Staying unmarked also keeps these packets out of
-		if closeErr := syscall.Close(fd); closeErr != nil {
+	// third-party NAT rules that match on marks: such a rule rewriting the
-			log.Warnf("failed to close raw socket fd: %v", closeErr)
+	// source would make WireGuard adopt the rewritten address as the peer
-		}
+	// endpoint.
-		return nil, fmt.Errorf("setting fwmark failed: %w", err)
-	}
 
 	// Convert the file descriptor to a PacketConn.
 	file := os.NewFile(uintptr(fd), fmt.Sprintf("fd %d", fd))

client/iface/wgproxy/rawsocket/rawsocket_privileged_test.go

@@ -0,0 +1,77 @@
+//go:build linux && !android && privileged
+
+package rawsocket
+
+import (
+	"net"
+	"syscall"
+	"testing"
+
+	"golang.org/x/sys/unix"
+
+	nbnet "github.com/netbirdio/netbird/client/net"
+)
+
+// The sender sockets must stay unmarked: a NAT rule matching on fwmark that
+// rewrites the source of an injected packet makes WireGuard adopt the rewritten
+// address as the peer endpoint.
+func TestSenderRawSocketsCarryNoFwmark(t *testing.T) {
+	// the mark is only ever applied when advanced routing is available, so
+	// without it the assertion below would hold for the wrong reason
+	nbnet.Init()
+	if !nbnet.AdvancedRouting() {
+		t.Skip("advanced routing unsupported, the sockets carry no mark either way")
+	}
+
+	tests := []struct {
+		name    string
+		prepare func() (net.PacketConn, error)
+		// the proxy treats the IPv6 socket as optional, so a host without IPv6
+		// is a reason to skip rather than to fail
+		optional bool
+	}{
+		{name: "IPv4", prepare: PrepareSenderRawSocketIPv4},
+		{name: "IPv6", prepare: PrepareSenderRawSocketIPv6, optional: true},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			conn, err := tc.prepare()
+			if err != nil {
+				if tc.optional {
+					t.Skipf("prepare raw socket: %v", err)
+				}
+				t.Fatalf("prepare raw socket: %v", err)
+			}
+			defer func() {
+				if err := conn.Close(); err != nil {
+					t.Logf("close raw socket: %v", err)
+				}
+			}()
+
+			syscallConn, ok := conn.(syscall.Conn)
+			if !ok {
+				t.Fatalf("raw socket %T does not expose a syscall conn", conn)
+			}
+			raw, err := syscallConn.SyscallConn()
+			if err != nil {
+				t.Fatalf("syscall conn: %v", err)
+			}
+
+			var mark int
+			var markErr error
+			if err := raw.Control(func(fd uintptr) {
+				mark, markErr = unix.GetsockoptInt(int(fd), unix.SOL_SOCKET, unix.SO_MARK)
+			}); err != nil {
+				t.Fatalf("control: %v", err)
+			}
+			if markErr != nil {
+				t.Fatalf("get SO_MARK: %v", markErr)
+			}
+
+			if mark != 0 {
+				t.Errorf("SO_MARK = %#x, want 0", mark)
+			}
+		})
+	}
+}

client/iface/wgproxy/redirect_test.go

@@ -119,9 +119,9 @@ func testRedirectAs(t *testing.T, proxy Proxy, wgPort int, nbAddr, p2pEndpoint *
 	}
 	defer relayConn.Close()
 
-	// Add TURN connection to proxy
+	// Add relayed connection to proxy
-	if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil {
+	if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil {
-		t.Fatalf("failed to add TURN connection: %v", err)
+		t.Fatalf("failed to add relayed connection: %v", err)
 	}
 	defer func() {
 		if err := proxy.CloseConn(); err != nil {
@@ -304,8 +304,8 @@ func TestRedirectAs_Multiple_Switches(t *testing.T) {
 		Port: 38746,
 	}
 
-	if err := proxy.AddTurnConn(ctx, nbAddr, relayConn); err != nil {
+	if err := proxy.AddRelayedConn(ctx, nbAddr, relayConn); err != nil {
-		t.Fatalf("failed to add TURN connection: %v", err)
+		t.Fatalf("failed to add relayed connection: %v", err)
 	}
 	defer func() {
 		if err := proxy.CloseConn(); err != nil {

client/iface/wgproxy/udp/proxy.go

@@ -51,12 +51,12 @@ func NewWGUDPProxy(wgPort int, mtu uint16) *WGUDPProxy {
 	return p
 }
 
-// AddTurnConn
+// AddRelayedConn dials the local WireGuard port and stores the relayed connection.
 // The provided Context must be non-nil. If the context expires before
 // the connection is complete, an error is returned. Once successfully
 // connected, any expiration of the context will not affect the
 // connection.
-func (p *WGUDPProxy) AddTurnConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
+func (p *WGUDPProxy) AddRelayedConn(ctx context.Context, _ *net.UDPAddr, remoteConn net.Conn) error {
 	dialer := net.Dialer{}
 	localConn, err := dialer.DialContext(ctx, "udp", fmt.Sprintf(":%d", p.localWGListenPort))
 	if err != nil {

client/internal/acl/manager.go

@@ -116,11 +116,11 @@ func (d *DefaultManager) ApplyFiltering(networkMap *mgmProto.NetworkMap, dnsRout
 // firewall state, so an identical hash means an identical resulting ruleset.
 func (d *DefaultManager) firewallConfigHash(networkMap *mgmProto.NetworkMap, dnsRouteFeatureFlag bool) (uint64, error) {
 	return hashstructure.Hash(struct {
-		PeerRules            []*mgmProto.FirewallRule
+		PeerRules           []*mgmProto.FirewallRule
-		PeerRulesIsEmpty     bool
+		PeerRulesIsEmpty    bool
-		RouteRules           []*mgmProto.RouteFirewallRule
+		RouteRules          []*mgmProto.RouteFirewallRule
-		RouteRulesIsEmpty    bool
+		RouteRulesIsEmpty   bool
-		DNSRouteFeatureFlag  bool
+		DNSRouteFeatureFlag bool
 	}{
 		PeerRules:           networkMap.GetFirewallRules(),
 		PeerRulesIsEmpty:    networkMap.GetFirewallRulesIsEmpty(),
@@ -144,13 +144,13 @@ func (d *DefaultManager) applyPeerACLs(networkMap *mgmProto.NetworkMap) {
 		log.Warn("this peer is connected to a NetBird Management service with an older version. Allowing all traffic from connected peers")
 		rules = append(rules,
 			&mgmProto.FirewallRule{
-				PeerIP:    "0.0.0.0",
+				PeerIP:    "0.0.0.0", //nolint:staticcheck
 				Direction: mgmProto.RuleDirection_IN,
 				Action:    mgmProto.RuleAction_ACCEPT,
 				Protocol:  mgmProto.RuleProtocol_ALL,
 			},
 			&mgmProto.FirewallRule{
-				PeerIP:    "0.0.0.0",
+				PeerIP:    "0.0.0.0", //nolint:staticcheck
 				Direction: mgmProto.RuleDirection_OUT,
 				Action:    mgmProto.RuleAction_ACCEPT,
 				Protocol:  mgmProto.RuleProtocol_ALL,
@@ -407,7 +407,6 @@ func (d *DefaultManager) getRuleGroupingSelector(rule *mgmProto.FirewallRule) st
 	return fmt.Sprintf("%v:%v:%v:%s:%v", strconv.Itoa(int(rule.Direction)), rule.Action, rule.Protocol, rule.Port, rule.PortInfo)
 }
 
-
 // extractRuleIP extracts the peer IP from a firewall rule.
 // If sourcePrefixes is populated (new management), decode the first entry and use its address.
 // Otherwise fall back to the deprecated PeerIP string field (old management).

client/internal/acl/manager_test.go

@@ -5,9 +5,9 @@ import (
 	"net/netip"
 	"testing"
 
-	"github.com/golang/mock/gomock"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+	"go.uber.org/mock/gomock"
 
 	"github.com/netbirdio/netbird/client/firewall"
 	"github.com/netbirdio/netbird/client/iface"
@@ -87,7 +87,7 @@ func TestDefaultManager(t *testing.T) {
 		networkMap.FirewallRules = append(
 			networkMap.FirewallRules,
 			&mgmProto.FirewallRule{
-				PeerIP:    "10.93.0.3",
+				PeerIP:    "10.93.0.3", //nolint:staticcheck
 				Direction: mgmProto.RuleDirection_IN,
 				Action:    mgmProto.RuleAction_DROP,
 				Protocol:  mgmProto.RuleProtocol_ICMP,
@@ -556,12 +556,12 @@ func TestApplyFilteringSkipsUnchangedConfig(t *testing.T) {
 
 func buildNetworkMap(peerRules, routeRules int) *mgmProto.NetworkMap {
 	nm := &mgmProto.NetworkMap{
-		FirewallRulesIsEmpty:      peerRules == 0,
+		FirewallRulesIsEmpty:       peerRules == 0,
 		RoutesFirewallRulesIsEmpty: routeRules == 0,
 	}
 	for i := range peerRules {
 		nm.FirewallRules = append(nm.FirewallRules, &mgmProto.FirewallRule{
-			PeerIP:    fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff),
+			PeerIP:    fmt.Sprintf("10.%d.%d.%d", i>>16&0xff, i>>8&0xff, i&0xff), //nolint:staticcheck
 			Direction: mgmProto.RuleDirection_IN,
 			Action:    mgmProto.RuleAction_ACCEPT,
 			Protocol:  mgmProto.RuleProtocol_TCP,

client/internal/acl/mocks/iface_mapper.go

@@ -7,7 +7,7 @@ package mocks
 import (
 	reflect "reflect"
 
-	gomock "github.com/golang/mock/gomock"
+	gomock "go.uber.org/mock/gomock"
 	wgdevice "golang.zx2c4.com/wireguard/device"
 
 	"github.com/netbirdio/netbird/client/iface/device"

client/internal/auth/auth.go

@@ -138,26 +138,37 @@ func (a *Auth) IsSSOSupported(ctx context.Context) (bool, error) {
 
 // GetOAuthFlow returns an OAuth flow (PKCE or Device) using the existing management connection
 // This avoids creating a new connection to the management server
-func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool) (OAuthFlow, error) {
+func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool, hint string) (OAuthFlow, error) {
 	var flow OAuthFlow
-	var err error
 
-	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+	err := a.withRetry(ctx, func(client *mgm.GrpcClient) error {
 		if forceDeviceAuth {
-			flow, err = a.getDeviceFlow(client)
+			deviceFlow, err := a.getDeviceFlow(client)
-			return err
+			if err != nil {
+				return err
+			}
+			deviceFlow.SetLoginHint(hint)
+			flow = deviceFlow
+			return nil
 		}
 
 		// Try PKCE flow first
-		flow, err = a.getPKCEFlow(client)
+		pkceFlow, err := a.getPKCEFlow(client)
 		if err != nil {
 			// If PKCE not supported, try Device flow
 			if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
-				flow, err = a.getDeviceFlow(client)
+				deviceFlow, err := a.getDeviceFlow(client)
-				return err
+				if err != nil {
+					return err
+				}
+				deviceFlow.SetLoginHint(hint)
+				flow = deviceFlow
+				return nil
 			}
 			return err
 		}
+		pkceFlow.SetLoginHint(hint)
+		flow = pkceFlow
 		return nil
 	})
 
@@ -357,6 +368,7 @@ func (a *Auth) setSystemInfoFlags(info *system.Info) {
 		a.config.EnableSSHLocalPortForwarding,
 		a.config.EnableSSHRemotePortForwarding,
 		a.config.DisableSSHAuth,
+		a.config.RemoteJobsAllowed,
 	)
 }
 

client/internal/auth/device_flow.go

@@ -304,6 +304,16 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 				return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
 			}
 
+			// Same as the PKCE flow: the account the token belongs to is what
+			// callers store to send back as the login_hint. Without it a client
+			// driven through the device flow — Android TV and tvOS — never binds
+			// an account to its profile and every later login goes out blind.
+			if email, err := parseEmailFromIDToken(tokenInfo.IDToken); err != nil {
+				log.Warnf("failed to parse email from ID token: %v", err)
+			} else {
+				tokenInfo.Email = email
+			}
+
 			log.Infof("device flow: user authorization confirmed after %d polls in %s", polls, time.Since(start).Round(time.Second))
 			return tokenInfo, err
 		}

client/internal/auth/oauth.go

@@ -97,9 +97,7 @@ func authenticateWithPKCEFlow(ctx context.Context, config *profilemanager.Config
 		return nil, fmt.Errorf("getting pkce authorization flow info failed with error: %v", err)
 	}
 
-	if hint != "" {
+	pkceFlowInfo.SetLoginHint(hint)
-		pkceFlowInfo.SetLoginHint(hint)
-	}
 
 	return pkceFlowInfo, nil
 }
@@ -127,9 +125,7 @@ func authenticateWithDeviceCodeFlow(ctx context.Context, config *profilemanager.
 		}
 	}
 
-	if hint != "" {
+	deviceFlowInfo.SetLoginHint(hint)
-		deviceFlowInfo.SetLoginHint(hint)
-	}
 
 	return deviceFlowInfo, nil
 }

client/internal/conn_mgr.go

@@ -2,6 +2,7 @@ package internal
 
 import (
 	"context"
+	"maps"
 	"os"
 	"strconv"
 	"sync"
@@ -14,6 +15,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/route"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 // lazyForce is the resolved local decision for lazy connections, layered above the
@@ -37,11 +39,13 @@ const (
 // The only exception is ActivatePeer, which is safe for concurrent use so the
 // DNS warm-up path can call it without contending on the engine mutex.
 type ConnMgr struct {
-	peerStore        *peerstore.Store
+	peerStore      *peerstore.Store
-	statusRecorder   *peer.Status
+	statusRecorder *peer.Status
-	iface            lazyconn.WGIface
+	iface          lazyconn.WGIface
-	force            lazyForce
+	force          lazyForce
-	rosenpassEnabled bool
+	// remoteLazyEnabled caches the account-wide lazy feature flag from management.
+	// It is the default for peers that do not carry a per-peer lazy hint.
+	remoteLazyEnabled bool
 
 	lazyConnMgr *manager.Manager
 	// lazyConnMgrMu guards the lazyConnMgr pointer for readers outside the
@@ -53,6 +57,10 @@ type ConnMgr struct {
 	// (re)armed (Mode A at arm time). Injected by the engine; nil disables the reconcile.
 	reconcileRoutedIPs func(peerKey string) error
 
+	// appliedExcludeList is the exclude set last handed to the lazy manager, kept so an
+	// unchanged set on the next sync skips the O(n) reconciliation.
+	appliedExcludeList map[string]bool
+
 	wg            sync.WaitGroup
 	lazyCtx       context.Context
 	lazyCtxCancel context.CancelFunc
@@ -66,78 +74,59 @@ func (e *ConnMgr) SetRoutedIPsReconciler(fn func(peerKey string) error) {
 
 func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
 	e := &ConnMgr{
-		peerStore:        peerStore,
+		peerStore:      peerStore,
-		statusRecorder:   statusRecorder,
+		statusRecorder: statusRecorder,
-		iface:            iface,
+		iface:          iface,
-		force:            resolveLazyForce(engineConfig.LazyConnection),
+		force:          resolveLazyForce(engineConfig.LazyConnection),
-		rosenpassEnabled: engineConfig.RosenpassEnabled,
 	}
 	return e
 }
 
-// Start initializes the connection manager. It starts the lazy connection manager when a
+// Start initializes the connection manager. The lazy connection manager always runs so that
-// local override forces it on; with no local override it waits for the management feature flag.
+// per-peer lazy defaults (e.g. proxy peers) work even when the account flag is off; the
+// account flag and the local override decide the default lazy state per peer (see
+// PeerLazyDefault). Rosenpass peers stay lazy-capable too: their connections just never idle
+// on their own, since rosenpass rekey traffic keeps them active.
 func (e *ConnMgr) Start(ctx context.Context) {
 	if e.lazyConnMgr != nil {
 		log.Errorf("lazy connection manager is already started")
 		return
 	}
 
-	switch e.force {
-	case lazyForceOff:
-		log.Infof("lazy connection manager is disabled by local override (%s or MDM policy)", lazyconn.EnvLazyConn)
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	case lazyForceNone:
-		log.Infof("lazy connection manager is managed by the management feature flag")
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	}
-
-	if e.rosenpassEnabled {
-		log.Warnf("rosenpass connection manager is enabled, lazy connection manager will not be started")
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	}
-
 	e.initLazyManager(ctx)
-	e.statusRecorder.UpdateLazyConnection(true)
+	e.statusRecorder.UpdateLazyConnection(e.PeerLazyDefault(mgmProto.LazyState_LazyStateDefault))
 }
 
-// UpdatedRemoteFeatureFlag is called when the remote feature flag is updated.
+// UpdatedRemoteFeatureFlag caches the account-wide lazy feature flag. The manager itself is
-// If enabled, it initializes the lazy connection manager and start it. Do not need to call Start() again.
+// not started or stopped here; the per-sync exclude-list reconciliation moves normal peers
-// If disabled, then it closes the lazy connection manager and open the connections to all peers.
+// between the lazy and always-active sets when the flag flips.
-func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) error {
+func (e *ConnMgr) UpdatedRemoteFeatureFlag(_ context.Context, enabled bool) error {
-	// a local override (NB_LAZY_CONN or local config) takes precedence over management
+	e.remoteLazyEnabled = enabled
-	if e.force != lazyForceNone {
+	if e.isStartedWithLazyMgr() {
-		return nil
+		e.statusRecorder.UpdateLazyConnection(e.PeerLazyDefault(mgmProto.LazyState_LazyStateDefault))
+	}
+	return nil
+}
+
+// PeerLazyDefault reports whether a peer should be lazy. The local override
+// (NB_LAZY_CONN/MDM) wins over everything; without a local override the
+// management per-peer state applies (LazyStateLazy/Eager force the decision),
+// and LazyStateDefault follows the account-wide flag.
+func (e *ConnMgr) PeerLazyDefault(state mgmProto.LazyState) bool {
+	switch e.force {
+	case lazyForceOn:
+		return true
+	case lazyForceOff:
+		return false
 	}
 
-	if enabled {
+	switch state {
-		// if the lazy connection manager is already started, do not start it again
+	case mgmProto.LazyState_LazyStateLazy:
-		if e.lazyConnMgr != nil {
+		return true
-			return nil
+	case mgmProto.LazyState_LazyStateEager:
-		}
+		return false
-
+	default:
-		if e.rosenpassEnabled {
+		return e.remoteLazyEnabled
-			log.Infof("rosenpass connection manager is enabled, lazy connection manager will not be started")
-			e.statusRecorder.UpdateLazyConnection(false)
-			return nil
-		}
-
-		log.Infof("lazy connection manager is enabled by the management feature flag")
-		e.initLazyManager(ctx)
-		e.statusRecorder.UpdateLazyConnection(true)
-		return e.addPeersToLazyConnManager()
-	} else {
-		if e.lazyConnMgr == nil {
-			e.statusRecorder.UpdateLazyConnection(false)
-			return nil
-		}
-		log.Infof("lazy connection manager is disabled by management feature flag")
-		e.closeManager(ctx)
-		e.statusRecorder.UpdateLazyConnection(false)
-		return nil
 	}
 }
 
@@ -157,6 +146,13 @@ func (e *ConnMgr) SetExcludeList(ctx context.Context, peerIDs map[string]bool) {
 		return
 	}
 
+	// The exclude set is recomputed every sync but rarely changes; skip the O(n)
+	// store lookups and reconciliation when it matches what was already applied.
+	if maps.Equal(peerIDs, e.appliedExcludeList) {
+		return
+	}
+	e.appliedExcludeList = maps.Clone(peerIDs)
+
 	excludedPeers := make([]lazyconn.PeerConfig, 0, len(peerIDs))
 
 	for peerID := range peerIDs {
@@ -192,12 +188,16 @@ func (e *ConnMgr) SetExcludeList(ctx context.Context, peerIDs map[string]bool) {
 	}
 }
 
-func (e *ConnMgr) AddPeerConn(ctx context.Context, peerKey string, conn *peer.Conn) (exists bool) {
+// AddPeerConn registers a peer connection. permanent requests an always-active connection
+// (the peer belongs to the exclude set: a forwarder, or a peer that is not lazy by policy).
+// Non-permanent peers are handed to the lazy manager. The subsequent SetExcludeList call
+// reconciles membership for existing peers across flag flips.
+func (e *ConnMgr) AddPeerConn(ctx context.Context, peerKey string, conn *peer.Conn, permanent bool) (exists bool) {
 	if success := e.peerStore.AddPeerConn(peerKey, conn); !success {
 		return true
 	}
 
-	if !e.isStartedWithLazyMgr() {
+	if !e.isStartedWithLazyMgr() || permanent {
 		if err := conn.Open(ctx); err != nil {
 			conn.Log.Errorf("failed to open connection: %v", err)
 		}
@@ -296,6 +296,8 @@ func (e *ConnMgr) Close() {
 	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
 	e.lazyConnMgrMu.Unlock()
+
+	e.appliedExcludeList = nil
 }
 
 func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
@@ -309,6 +311,8 @@ func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
 	e.lazyConnMgrMu.Unlock()
 
+	e.appliedExcludeList = nil
+
 	e.wg.Add(1)
 	go func() {
 		defer e.wg.Done()
@@ -316,46 +320,6 @@ func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	}()
 }
 
-func (e *ConnMgr) addPeersToLazyConnManager() error {
-	peers := e.peerStore.PeersPubKey()
-	lazyPeerCfgs := make([]lazyconn.PeerConfig, 0, len(peers))
-	for _, peerID := range peers {
-		var peerConn *peer.Conn
-		var exists bool
-		if peerConn, exists = e.peerStore.PeerConn(peerID); !exists {
-			log.Warnf("failed to find peer conn for peerID: %s", peerID)
-			continue
-		}
-
-		lazyPeerCfg := lazyconn.PeerConfig{
-			PublicKey:  peerID,
-			AllowedIPs: peerConn.WgConfig().AllowedIps,
-			PeerConnID: peerConn.ConnID(),
-			Log:        peerConn.Log,
-		}
-		lazyPeerCfgs = append(lazyPeerCfgs, lazyPeerCfg)
-	}
-
-	return e.lazyConnMgr.AddActivePeers(lazyPeerCfgs)
-}
-
-func (e *ConnMgr) closeManager(ctx context.Context) {
-	if e.lazyConnMgr == nil {
-		return
-	}
-
-	e.lazyCtxCancel()
-	e.wg.Wait()
-
-	e.lazyConnMgrMu.Lock()
-	e.lazyConnMgr = nil
-	e.lazyConnMgrMu.Unlock()
-
-	for _, peerID := range e.peerStore.PeersPubKey() {
-		e.peerStore.PeerConnOpen(ctx, peerID)
-	}
-}
-
 func (e *ConnMgr) isStartedWithLazyMgr() bool {
 	return e.lazyConnMgr != nil && e.lazyCtxCancel != nil
 }

client/internal/conn_mgr_test.go

@@ -16,6 +16,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/monotime"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 func TestResolveLazyForce(t *testing.T) {
@@ -138,4 +139,91 @@ func TestInactivityThresholdEnv(t *testing.T) {
 	}
 }
 
+func TestPeerLazyDefault(t *testing.T) {
+	tests := []struct {
+		name          string
+		force         lazyForce
+		remoteEnabled bool
+		state         mgmProto.LazyState
+		want          bool
+	}{
+		{name: "force on wins over eager state", force: lazyForceOn, state: mgmProto.LazyState_LazyStateEager, want: true},
+		{name: "force off wins over lazy state", force: lazyForceOff, remoteEnabled: true, state: mgmProto.LazyState_LazyStateLazy, want: false},
+		{name: "none, default, account off -> active", force: lazyForceNone, state: mgmProto.LazyState_LazyStateDefault, want: false},
+		{name: "none, default, account on -> lazy", force: lazyForceNone, remoteEnabled: true, state: mgmProto.LazyState_LazyStateDefault, want: true},
+		{name: "none, lazy state, account off -> lazy", force: lazyForceNone, state: mgmProto.LazyState_LazyStateLazy, want: true},
+		{name: "none, eager state, account on -> active", force: lazyForceNone, remoteEnabled: true, state: mgmProto.LazyState_LazyStateEager, want: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			e := &ConnMgr{force: tt.force, remoteLazyEnabled: tt.remoteEnabled}
+			if got := e.PeerLazyDefault(tt.state); got != tt.want {
+				t.Fatalf("PeerLazyDefault(%v) = %v, want %v", tt.state, got, tt.want)
+			}
+		})
+	}
+}
+
 func durPtr(d time.Duration) *time.Duration { return &d }
+
+// TestToExcludedLazyPeers covers the per-peer lazy classification (proxy vs
+// normal, across the force/account-flag matrix). Forwarder-target exclusion is
+// covered by TestToExcludedLazyPeers_ForwardTarget.
+func TestToExcludedLazyPeers(t *testing.T) {
+	const (
+		normalKey = "normal"
+		lazyKey   = "lazy-state"
+		eagerKey  = "eager-state"
+	)
+
+	peers := []*mgmProto.RemotePeerConfig{
+		{WgPubKey: normalKey, AllowedIps: []string{"100.64.0.1/32"}},
+		{WgPubKey: lazyKey, AllowedIps: []string{"100.64.0.2/32"}, LazyState: mgmProto.LazyState_LazyStateLazy},
+		{WgPubKey: eagerKey, AllowedIps: []string{"100.64.0.3/32"}, LazyState: mgmProto.LazyState_LazyStateEager},
+	}
+
+	tests := []struct {
+		name          string
+		force         lazyForce
+		remoteEnabled bool
+		want          map[string]bool
+	}{
+		{
+			name:  "account off: lazy-state peer lazy, normal + eager active",
+			force: lazyForceNone, remoteEnabled: false,
+			want: map[string]bool{normalKey: true, eagerKey: true},
+		},
+		{
+			name:  "account on: only eager-state peer active",
+			force: lazyForceNone, remoteEnabled: true,
+			want: map[string]bool{eagerKey: true},
+		},
+		{
+			name:  "force off: everything active",
+			force: lazyForceOff, remoteEnabled: true,
+			want: map[string]bool{normalKey: true, lazyKey: true, eagerKey: true},
+		},
+		{
+			name:  "force on: nothing active",
+			force: lazyForceOn, remoteEnabled: false,
+			want: map[string]bool{},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			e := &Engine{connMgr: &ConnMgr{force: tt.force, remoteLazyEnabled: tt.remoteEnabled}}
+			got := e.toExcludedLazyPeers(peers)
+
+			if len(got) != len(tt.want) {
+				t.Fatalf("toExcludedLazyPeers() = %v, want %v", got, tt.want)
+			}
+			for k := range tt.want {
+				if !got[k] {
+					t.Fatalf("expected peer %s excluded, got %v", k, got)
+				}
+			}
+		})
+	}
+}

client/internal/connect.go

@@ -38,6 +38,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netevents"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/ssh"
 	sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -70,18 +71,31 @@ type ConnectClient struct {
 	updateManager *updater.Manager
 
 	persistSyncResponse bool
+
+	// netMgr gates every reconnection loop on OS-reported network
+	// availability and sweeps connections on network change.
+	netMgr *netevents.Manager
+}
+
+// ConnectClientOption configures optional ConnectClient behavior.
+type ConnectClientOption func(*ConnectClient)
+
+// WithNetEvents injects the OS network event handling.
+func WithNetEvents(events *netevents.Manager) ConnectClientOption {
+	return func(c *ConnectClient) { c.netMgr = events }
 }
 
 func NewConnectClient(
 	ctx context.Context,
 	config *profilemanager.Config,
 	statusRecorder *peer.Status,
+	opts ...ConnectClientOption,
 ) *ConnectClient {
 	// Derive the run context here so Stop owns the cancel that unblocks the run
 	// loop. runCancel is set once at construction, so Stop can call it without
 	// racing the run loop's startup. Callers therefore need not cancel before Stop.
 	runCtx, runCancel := context.WithCancel(ctx)
-	return &ConnectClient{
+	c := &ConnectClient{
 		ctx:            runCtx,
 		runCancel:      runCancel,
 		runExited:      make(chan struct{}),
@@ -89,6 +103,10 @@ func NewConnectClient(
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
 	}
+	for _, opt := range opts {
+		opt(c)
+	}
+	return c
 }
 
 func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -224,7 +242,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	wrapErr := state.Wrap
 	myPrivateKey, err := wgtypes.ParseKey(c.config.PrivateKey)
 	if err != nil {
-		log.Errorf("failed parsing Wireguard key %s: [%s]", c.config.PrivateKey, err.Error())
+		log.Errorf("failed parsing Wireguard key: %s", err)
 		return wrapErr(err)
 	}
 
@@ -274,6 +292,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			return nil
 		}
 
+		// suspend connection attempts while the OS reports no usable network
+		if waited, err := c.netMgr.Wait(c.ctx); err != nil {
+			return nil
+		} else if waited {
+			backOff.Reset()
+		}
+
 		state.Set(StatusConnecting)
 
 		engineCtx, cancel := context.WithCancel(c.ctx)
@@ -285,7 +310,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
-		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
+		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
+			mgm.WithNetEvents(c.netMgr))
 		if err != nil {
 			// On daemon shutdown / Down() the parent context is cancelled
 			// and the dial fails with "context canceled". Wrapping that
@@ -360,7 +386,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
-		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
+		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netMgr)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -396,7 +422,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			engineConfig.StateDir = filepath.Dir(path)
 		}
 
-		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
+		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
+			relayClient.WithNetEvents(c.netMgr))
 		c.statusRecorder.SetRelayMgr(relayManager)
 		if len(relayURLs) > 0 {
 			if token != nil {
@@ -424,6 +451,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			UpdateManager:  c.updateManager,
 			ClientMetrics:  c.clientMetrics,
 			MetricsCtx:     c.ctx,
+			NetMgr:         c.netMgr,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine
@@ -480,6 +508,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	// status stream stuck at Connecting.
 	err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx))
 	if err != nil {
+		// Once the client context is cancelled backoff.WithContext surfaces the
+		// bare context error, and any attempt torn down mid-flight reports the
+		// same. That cancellation is the caller asking us to stop (Stop, Down or
+		// an engine restart), so exit cleanly instead of handing back a failure
+		// the caller would have to distinguish from a real one.
+		if c.ctx.Err() != nil && errors.Is(err, context.Canceled) {
+			log.Info("exiting client retry loop, context cancelled")
+			return nil
+		}
+
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 			state.Set(StatusNeedsLogin)
@@ -614,6 +652,7 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 		RosenpassEnabled:              config.RosenpassEnabled,
 		RosenpassPermissive:           config.RosenpassPermissive,
 		ServerSSHAllowed:              util.ReturnBoolWithDefaultTrue(config.ServerSSHAllowed),
+		RemoteJobsAllowed:             util.ReturnBoolWithDefaultFalse(config.RemoteJobsAllowed),
 		EnableSSHRoot:                 config.EnableSSHRoot,
 		EnableSSHSFTP:                 config.EnableSSHSFTP,
 		EnableSSHLocalPortForwarding:  config.EnableSSHLocalPortForwarding,
@@ -673,7 +712,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
 }
 
 // connectToSignal creates Signal Service client and established a connection
-func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
+func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netMgr *netevents.Manager) (*signal.GrpcClient, error) {
 	var sigTLSEnabled bool
 	if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
 		sigTLSEnabled = true
@@ -681,7 +720,8 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 		sigTLSEnabled = false
 	}
 
-	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
+	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
+		signal.WithNetEvents(netMgr))
 	if err != nil {
 		log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
 		return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)
@@ -710,6 +750,7 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.EnableSSHLocalPortForwarding,
 		config.EnableSSHRemotePortForwarding,
 		config.DisableSSHAuth,
+		config.RemoteJobsAllowed,
 	)
 	return client.Login(sysInfo, pubSSHKey, config.DNSLabels)
 }

client/internal/daemonaddr/identity.go

@@ -0,0 +1,17 @@
+package daemonaddr
+
+import "strings"
+
+// CarriesIdentity reports whether the control channel at addr conveys the
+// connecting process's identity to the daemon. A Unix socket carries peer
+// credentials and a named pipe carries the client's token. Nothing else does, TCP
+// included, and there the daemon can authorize a privileged operation for nobody
+// at all: see ResolveDaemonAddr, which says as much to anyone still reaching the
+// Windows daemon on the address it served before it had a pipe.
+//
+// A client uses this to tell whether becoming privileged would get it anywhere.
+// It answers from the scheme and nothing else, so an address it does not
+// recognise counts as carrying no identity.
+func CarriesIdentity(addr string) bool {
+	return strings.HasPrefix(addr, "unix://") || strings.HasPrefix(addr, pipeScheme)
+}

client/internal/daemonaddr/identity_test.go

@@ -0,0 +1,29 @@
+package daemonaddr
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestCarriesIdentity(t *testing.T) {
+	tests := []struct {
+		addr string
+		want bool
+	}{
+		{"unix:///var/run/netbird.sock", true},
+		{"unix:///var/run/netbird/default.sock", true},
+		{"npipe://netbird", true},
+		{`npipe://\\.\pipe\ProtectedPrefix\Administrators\netbird`, true},
+		{"tcp://127.0.0.1:41731", false},
+		{"tcp://localhost:41731", false},
+		{"", false},
+		{"/var/run/netbird.sock", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.addr, func(t *testing.T) {
+			assert.Equal(t, tt.want, CarriesIdentity(tt.addr), "address %q", tt.addr)
+		})
+	}
+}

client/internal/debug/debug.go

@@ -711,6 +711,9 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
 	if g.internalConfig.ServerSSHAllowed != nil {
 		configContent.WriteString(fmt.Sprintf("ServerSSHAllowed: %v\n", *g.internalConfig.ServerSSHAllowed))
 	}
+	if g.internalConfig.RemoteJobsAllowed != nil {
+		configContent.WriteString(fmt.Sprintf("RemoteJobsAllowed: %v\n", *g.internalConfig.RemoteJobsAllowed))
+	}
 	if g.internalConfig.EnableSSHRoot != nil {
 		configContent.WriteString(fmt.Sprintf("EnableSSHRoot: %v\n", *g.internalConfig.EnableSSHRoot))
 	}
@@ -737,6 +740,8 @@ 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/debug/debug_test.go

@@ -839,12 +839,13 @@ COMMIT`
 // the excluded set with a justification.
 func TestAddConfig_AllFieldsCovered(t *testing.T) {
 	excluded := map[string]string{
-		"PrivateKey":        "sensitive: WireGuard private key",
+		"PrivateKey":           "sensitive: WireGuard private key",
-		"PreSharedKey":      "sensitive: WireGuard pre-shared key",
+		"PreSharedKey":         "sensitive: WireGuard pre-shared key",
-		"SSHKey":            "sensitive: SSH private key",
+		"SSHKey":               "sensitive: SSH private key",
-		"ClientCertKeyPair": "non-config: parsed cert pair, not serialized",
+		"ClientCertKeyPair":    "non-config: parsed cert pair, not serialized",
-		"Name":              "non-config: profile name is not needed for debug purposes",
+		"Name":                 "non-config: profile name is not needed for debug purposes",
-		"policy":            "non-config: in-memory MDM policy snapshot, surfaced via Config.Policy() / GetConfigResponse.MDMManagedFields",
+		"policy":               "non-config: in-memory MDM policy snapshot, surfaced via Config.Policy() / GetConfigResponse.MDMManagedFields",
+		"DebugBundleUploadURL": "sensitive: MDM-provided upload URL may carry credentials or query tokens; kept out of the shared bundle",
 	}
 
 	mURL, _ := url.Parse("https://api.example.com:443")
@@ -864,6 +865,7 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		RosenpassEnabled:              true,
 		RosenpassPermissive:           true,
 		ServerSSHAllowed:              &bTrue,
+		RemoteJobsAllowed:             &bTrue,
 		EnableSSHRoot:                 &bTrue,
 		EnableSSHSFTP:                 &bTrue,
 		EnableSSHLocalPortForwarding:  &bTrue,
@@ -886,6 +888,7 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		ClientCertPath:                "/tmp/cert",
 		ClientCertKeyPath:             "/tmp/key",
 		LazyConnection:                "on",
+		DebugBundleUploadURL:          "https://upload.example.test/bundle?token=secret",
 		MTU:                           1280,
 		DisableIPv6:                   true,
 		SyncMessageVersion:            func(v int) *int { return &v }(1),
@@ -903,6 +906,13 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 			g.addCommonConfigFields(&sb)
 			rendered := sb.String() + renderAddConfigSpecific(g)
 
+			// DebugBundleUploadURL is an MDM-provided value that can carry
+			// credentials or signed query tokens. It is deliberately excluded
+			// above; assert it never reaches the rendered bundle — neither the
+			// field name nor the token — in either anonymize mode.
+			assert.NotContains(t, rendered, "DebugBundleUploadURL:", "MDM upload URL field must not be serialized into the debug bundle")
+			assert.NotContains(t, rendered, "token=secret", "MDM upload URL value must not leak into the debug bundle")
+
 			val := reflect.ValueOf(cfg).Elem()
 			typ := val.Type()
 			var missing []string

client/internal/dns/host_windows.go

@@ -6,8 +6,10 @@ import (
 	"fmt"
 	"io"
 	"net/netip"
+	"os"
 	"os/exec"
 	"slices"
+	"strconv"
 	"strings"
 	"syscall"
 	"time"
@@ -34,8 +36,16 @@ var (
 // Registry locations of the host DNS configuration this package programs,
 // exported so a diagnostic reader reports the same locations that are written.
 const (
-	// NRPTKeyPrefix starts the name of every NRPT rule key this client creates.
+	// NRPTKeyPrefix starts the name of every NRPT rule key this client creates:
-	NRPTKeyPrefix = "NetBird-Match"
+	// the match rules, the catch-all, and the .local exemption. Cleanup
+	// enumerates by this prefix, so a new kind of rule is removed by existing
+	// code as long as its key starts here.
+	NRPTKeyPrefix = "NetBird-"
+
+	// nrptMatchKeyName names the match-domain rules. Older versions used
+	// different layouts under the same name: a single unsuffixed key, then one
+	// key per domain, now one key per batch of domains.
+	nrptMatchKeyName = NRPTKeyPrefix + "Match"
 
 	// DNSPolicyConfigRoot holds the NRPT rules of the local policy store.
 	DNSPolicyConfigRoot = `SYSTEM\CurrentControlSet\Services\Dnscache\Parameters\DnsPolicyConfig`
@@ -51,8 +61,24 @@ const (
 )
 
 const (
-	dnsPolicyConfigMatchPath    = DNSPolicyConfigRoot + `\` + NRPTKeyPrefix
+	dnsPolicyConfigMatchPath    = DNSPolicyConfigRoot + `\` + nrptMatchKeyName
-	gpoDnsPolicyConfigMatchPath = GPODNSPolicyConfigRoot + `\` + NRPTKeyPrefix
+	gpoDnsPolicyConfigMatchPath = GPODNSPolicyConfigRoot + `\` + nrptMatchKeyName
+
+	dnsPolicyConfigExemptLocalPath    = DNSPolicyConfigRoot + `\` + NRPTKeyPrefix + `ExemptLocal`
+	gpoDnsPolicyConfigExemptLocalPath = GPODNSPolicyConfigRoot + `\` + NRPTKeyPrefix + `ExemptLocal`
+
+	nrptCatchAllNamespace = "."
+	// nrptLocalNamespace is reserved for multicast DNS by RFC 6762: a unicast
+	// resolver must not answer for it. The catch-all rule would hand it to us
+	// anyway, so it gets an exemption rule of its own.
+	nrptLocalNamespace = ".local"
+
+	// envLegacyDNSResolution restores the pre-catch-all behaviour: the adapter's
+	// NameServer alone, leaving the OS free to query other adapters' resolvers in
+	// parallel. An escape hatch for setups that depend on a resolver of theirs
+	// still being reachable while connected, at the cost of the leak and of the
+	// race the catch-all rule exists to close.
+	envLegacyDNSResolution = "NB_USE_LEGACY_DNS_RESOLUTION"
 
 	dnsPolicyConfigVersionKey           = "Version"
 	dnsPolicyConfigVersionValue         = 2
@@ -89,7 +115,6 @@ type registryConfigurator struct {
 	guid            string
 	routingAll      bool
 	gpo             bool
-	nrptEntryCount  int
 	origNameservers []netip.Addr
 }
 
@@ -292,6 +317,13 @@ func (r *registryConfigurator) disableWINSForInterface() error {
 }
 
 func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager *statemanager.Manager) error {
+	// Clear every rule the previous apply installed before installing any new
+	// one, including a leftover catch-all: removal is unconditional so a rule
+	// from an earlier run cannot survive into a config that no longer wants it.
+	if err := r.removeDNSMatchPolicies(); err != nil {
+		log.Errorf("cleanup old dns match policies: %s", err)
+	}
+
 	if config.RouteAll {
 		if err := r.addDNSSetupForAll(config.ServerIP); err != nil {
 			return fmt.Errorf("add dns setup: %w", err)
@@ -317,19 +349,28 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager
 		matchDomains = append(matchDomains, "."+strings.TrimSuffix(dConf.Domain, "."))
 	}
 
-	if err := r.removeDNSMatchPolicies(); err != nil {
+	// The root namespace is a match domain like any other: it just happens to
-		log.Errorf("cleanup old dns match policies: %s", err)
+	// match every name. Without it the adapter's NameServer only adds one more
+	// resolver to the set Windows queries in parallel, keeping whichever answer
+	// comes back first — which leaks every query to the local network and lets a
+	// resolver other than ours answer for a name we are authoritative for.
+	if config.RouteAll {
+		if parseBoolEnv(envLegacyDNSResolution) {
+			log.Infof("%s is set, leaving DNS resolution shared with the other adapters' resolvers instead of forcing it through %s", envLegacyDNSResolution, config.ServerIP)
+		} else {
+			matchDomains = append(matchDomains, nrptCatchAllNamespace)
+			log.Infof("routing every namespace through %s: DNS resolution is now exclusive to NetBird", config.ServerIP)
+
+			if err := r.addDNSExemptLocalPolicy(); err != nil {
+				return fmt.Errorf("add dns exempt policy: %w", err)
+			}
+		}
 	}
 
 	if len(matchDomains) != 0 {
-		count, err := r.addDNSMatchPolicy(matchDomains, config.ServerIP)
+		if err := r.addDNSMatchPolicy(matchDomains, config.ServerIP); err != nil {
-		// Update count even on error to ensure cleanup covers partially created rules
-		r.nrptEntryCount = count
-		if err != nil {
 			return fmt.Errorf("add dns match policy: %w", err)
 		}
-	} else {
-		r.nrptEntryCount = 0
 	}
 
 	r.updateState(stateManager)
@@ -345,9 +386,8 @@ func (r *registryConfigurator) applyDNSConfig(config HostDNSConfig, stateManager
 
 func (r *registryConfigurator) updateState(stateManager *statemanager.Manager) {
 	if err := stateManager.UpdateState(&ShutdownState{
-		Guid:           r.guid,
+		Guid: r.guid,
-		GPO:            r.gpo,
+		GPO:  r.gpo,
-		NRPTEntryCount: r.nrptEntryCount,
 	}); err != nil {
 		log.Errorf("failed to update shutdown state: %s", err)
 	}
@@ -362,7 +402,7 @@ func (r *registryConfigurator) addDNSSetupForAll(ip netip.Addr) error {
 	return nil
 }
 
-func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) (int, error) {
+func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr) error {
 	// if the gpo key is present, we need to put our DNS settings there, otherwise our config might be ignored
 	// see https://learn.microsoft.com/en-us/openspecs/windows_protocols/ms-gpnrpt/8cc31cb9-20cb-4140-9e85-3e08703b4745
 
@@ -379,19 +419,17 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr
 		gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, ruleIndex)
 
 		if err := r.configureDNSPolicy(localPath, batchDomains, ip); err != nil {
-			return ruleIndex, fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err)
+			return fmt.Errorf("configure DNS Local policy for rule %d: %w", ruleIndex, err)
 		}
 
-		// Increment immediately so the caller's cleanup path knows about this rule
-		ruleIndex++
-
 		if r.gpo {
 			if err := r.configureDNSPolicy(gpoPath, batchDomains, ip); err != nil {
-				return ruleIndex, fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex-1, err)
+				return fmt.Errorf("configure gpo DNS policy for rule %d: %w", ruleIndex, err)
 			}
 		}
 
-		log.Debugf("added NRPT rule %d with %d domains", ruleIndex-1, len(batchDomains))
+		log.Debugf("added NRPT rule %d with %d domains", ruleIndex, len(batchDomains))
+		ruleIndex++
 	}
 
 	if r.gpo {
@@ -401,9 +439,45 @@ func (r *registryConfigurator) addDNSMatchPolicy(domains []string, ip netip.Addr
 	}
 
 	log.Infof("added %d NRPT rules for %d domains", ruleIndex, len(domains))
-	return ruleIndex, nil
+	return nil
 }
 
+// addDNSExemptLocalPolicy carves .local back out of the catch-all. RFC 6762
+// reserves it for multicast DNS, so forwarding those names to a unicast
+// upstream answers NXDOMAIN for hosts that do exist - printers, NAS boxes, and
+// anything else announcing itself on the link - and the answer is authoritative
+// enough that Windows stops looking. A rule naming the namespace with no
+// servers hands it back to the DNS client untouched. A more specific rule still
+// wins, so a match domain under .local keeps going through us.
+func (r *registryConfigurator) addDNSExemptLocalPolicy() error {
+	var noServers netip.Addr
+
+	if err := r.configureDNSPolicy(dnsPolicyConfigExemptLocalPath, []string{nrptLocalNamespace}, noServers); err != nil {
+		return fmt.Errorf("configure exempt policy for %s: %w", nrptLocalNamespace, err)
+	}
+
+	if r.gpo {
+		if err := r.configureDNSPolicy(gpoDnsPolicyConfigExemptLocalPath, []string{nrptLocalNamespace}, noServers); err != nil {
+			return fmt.Errorf("configure gpo exempt policy for %s: %w", nrptLocalNamespace, err)
+		}
+		if err := refreshGroupPolicy(); err != nil {
+			log.Warnf("failed to refresh group policy: %v", err)
+		}
+	}
+
+	log.Infof("added NRPT exemption for %s, leaving it to the OS resolver", nrptLocalNamespace)
+	return nil
+}
+
+// configureDNSPolicy writes one NRPT rule. An invalid ip writes an exemption
+// rule: the namespace with an empty server list, which tells the DNS client to
+// resolve those names the way it would without any rule at all.
+//
+// The empty string is the whole difference, and it has to be written: dropping
+// the value and clearing ConfigOptions instead produces a rule Windows treats
+// as a no-op, keeps out of Get-DnsClientNrptPolicy -Effective, and ignores in
+// favour of the catch-all. 0x8 says the server list is the meaningful part of
+// the rule, and an empty list then means "no server, resolve normally".
 func (r *registryConfigurator) configureDNSPolicy(policyPath string, domains []string, ip netip.Addr) error {
 	if err := removeRegistryKeyFromDNSPolicyConfig(policyPath); err != nil {
 		return fmt.Errorf("remove existing dns policy: %w", err)
@@ -423,7 +497,11 @@ func (r *registryConfigurator) configureDNSPolicy(policyPath string, domains []s
 		return fmt.Errorf("set %s: %w", dnsPolicyConfigNameKey, err)
 	}
 
-	if err := regKey.SetStringValue(dnsPolicyConfigGenericDNSServersKey, ip.String()); err != nil {
+	var servers string
+	if ip.IsValid() {
+		servers = ip.String()
+	}
+	if err := regKey.SetStringValue(dnsPolicyConfigGenericDNSServersKey, servers); err != nil {
 		return fmt.Errorf("set %s: %w", dnsPolicyConfigGenericDNSServersKey, err)
 	}
 
@@ -466,7 +544,7 @@ func (r *registryConfigurator) flushDNSCache() {
 
 	ret, _, err := dnsFlushResolverCacheFn.Call()
 	if ret == 0 {
-		if err != nil && !errors.Is(err, syscall.Errno(0)) {
+		if !errors.Is(err, syscall.Errno(0)) {
 			log.Errorf("DnsFlushResolverCache failed: %v", err)
 			return
 		}
@@ -521,8 +599,11 @@ func (r *registryConfigurator) getInterfaceRegistryKey() (registry.Key, error) {
 }
 
 func (r *registryConfigurator) restoreHostDNS() error {
+	// Propagated, unlike in applyDNSConfig: there we are about to write fresh
+	// rules over whatever survived, here we are leaving, and a rule left behind
+	// keeps sending every query to an address that is about to disappear.
 	if err := r.removeDNSMatchPolicies(); err != nil {
-		log.Errorf("remove dns match policies: %s", err)
+		return fmt.Errorf("remove dns match policies: %w", err)
 	}
 
 	if err := r.deleteInterfaceRegistryKeyProperty(interfaceConfigSearchListKey); err != nil {
@@ -534,28 +615,28 @@ func (r *registryConfigurator) restoreHostDNS() error {
 	return nil
 }
 
+// removeDNSMatchPolicies deletes every NRPT rule this client may have created,
+// from the local and the GPO policy store. The rules are found by enumerating
+// the registry, the only authoritative record of what was written. Cleanup must
+// not depend on a rule count: the in-memory one is scoped to a single
+// registryConfigurator and the persisted one is deleted on every clean
+// disconnect, and a rule left behind keeps resolving names over an interface
+// that is gone, until reboot discards the volatile key.
 func (r *registryConfigurator) removeDNSMatchPolicies() error {
 	var merr *multierror.Error
 
-	// Try to remove the base entries (for backward compatibility)
+	for _, root := range []string{DNSPolicyConfigRoot, GPODNSPolicyConfigRoot} {
-	if err := removeRegistryKeyFromDNSPolicyConfig(dnsPolicyConfigMatchPath); err != nil {
+		names, err := listNRPTRuleKeys(root)
-		merr = multierror.Append(merr, fmt.Errorf("remove local base entry: %w", err))
+		if err != nil {
-	}
+			merr = multierror.Append(merr, fmt.Errorf("list rule keys under %s: %w", root, err))
-
+			continue
-	if err := removeRegistryKeyFromDNSPolicyConfig(gpoDnsPolicyConfigMatchPath); err != nil {
-		merr = multierror.Append(merr, fmt.Errorf("remove GPO base entry: %w", err))
-	}
-
-	for i := 0; i < r.nrptEntryCount; i++ {
-		localPath := fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i)
-		gpoPath := fmt.Sprintf("%s-%d", gpoDnsPolicyConfigMatchPath, i)
-
-		if err := removeRegistryKeyFromDNSPolicyConfig(localPath); err != nil {
-			merr = multierror.Append(merr, fmt.Errorf("remove local entry %d: %w", i, err))
 		}
 
-		if err := removeRegistryKeyFromDNSPolicyConfig(gpoPath); err != nil {
+		for _, name := range names {
-			merr = multierror.Append(merr, fmt.Errorf("remove GPO entry %d: %w", i, err))
+			path := root + `\` + name
+			if err := removeRegistryKeyFromDNSPolicyConfig(path); err != nil {
+				merr = multierror.Append(merr, fmt.Errorf("remove entry %s: %w", path, err))
+			}
 		}
 	}
 
@@ -570,11 +651,52 @@ func (r *registryConfigurator) restoreUncleanShutdownDNS() error {
 	return r.restoreHostDNS()
 }
 
+// listNRPTRuleKeys returns the names of our NRPT rule keys under a policy store
+// root. An absent root holds nothing to clean up, which is the normal state of
+// the GPO store on a machine without DNS Client policy.
+func listNRPTRuleKeys(root string) ([]string, error) {
+	k, err := registry.OpenKey(registry.LOCAL_MACHINE, root, registry.ENUMERATE_SUB_KEYS)
+	switch {
+	case errors.Is(err, registry.ErrNotExist), errors.Is(err, syscall.ERROR_PATH_NOT_FOUND):
+		// the GPO store is absent on a machine without DNS client policy
+		log.Debugf("HKEY_LOCAL_MACHINE\\%s does not exist", root)
+		return nil, nil
+	case err != nil:
+		// any other failure has to reach the caller: reporting no rules would
+		// report a successful cleanup while leaving the rules in place
+		return nil, fmt.Errorf("open HKEY_LOCAL_MACHINE\\%s: %w", root, err)
+	}
+	defer closer(k)
+
+	names, err := k.ReadSubKeyNames(-1)
+	if err != nil {
+		return nil, fmt.Errorf("read subkey names: %w", err)
+	}
+
+	var ruleKeys []string
+	for _, name := range names {
+		// registry key names are case insensitive
+		if strings.HasPrefix(strings.ToLower(name), strings.ToLower(NRPTKeyPrefix)) {
+			ruleKeys = append(ruleKeys, name)
+		}
+	}
+
+	return ruleKeys, nil
+}
+
 func removeRegistryKeyFromDNSPolicyConfig(regKeyPath string) error {
 	k, err := registry.OpenKey(registry.LOCAL_MACHINE, regKeyPath, registry.QUERY_VALUE)
-	if err != nil {
+	switch {
-		log.Debugf("failed to open HKEY_LOCAL_MACHINE\\%s: %v", regKeyPath, err)
+	case errors.Is(err, registry.ErrNotExist), errors.Is(err, syscall.ERROR_PATH_NOT_FOUND):
+		// nothing to remove, which is the normal case for a rule this config
+		// never installed
+		log.Debugf("HKEY_LOCAL_MACHINE\\%s does not exist", regKeyPath)
 		return nil
+	case err != nil:
+		// anything else has to reach the caller: reporting success here would
+		// leave the rule in force while claiming it was removed, which is how a
+		// stale rule outlives the interface it points at
+		return fmt.Errorf("open HKEY_LOCAL_MACHINE\\%s: %w", regKeyPath, err)
 	}
 
 	closer(k)
@@ -601,7 +723,7 @@ func refreshGroupPolicy() error {
 	)
 
 	if ret == 0 {
-		if err != nil && !errors.Is(err, syscall.Errno(0)) {
+		if !errors.Is(err, syscall.Errno(0)) {
 			return fmt.Errorf("RefreshPolicyEx failed: %w", err)
 		}
 		return fmt.Errorf("RefreshPolicyEx failed")
@@ -610,6 +732,20 @@ func refreshGroupPolicy() error {
 	return nil
 }
 
+func parseBoolEnv(key string) bool {
+	val := os.Getenv(key)
+	if val == "" {
+		return false
+	}
+
+	parsed, err := strconv.ParseBool(val)
+	if err != nil {
+		log.Warnf("failed to parse %s=%q: %v", key, val, err)
+		return false
+	}
+	return parsed
+}
+
 func closer(closer io.Closer) {
 	if err := closer.Close(); err != nil {
 		log.Errorf("failed to close: %s", err)

client/internal/dns/host_windows_test.go

@@ -25,7 +25,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) {
 
 	// Create a test interface registry key so updateSearchDomains doesn't fail
 	testGUID := "{12345678-1234-1234-1234-123456789ABC}"
-	interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID
+	interfacePath := InterfaceConfigPath + `\` + testGUID
 	testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE)
 	require.NoError(t, err, "Should create test interface registry key")
 	testKey.Close()
@@ -56,7 +56,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) {
 	require.NoError(t, err)
 
 	// Verify 3 NRPT rules exist
-	assert.Equal(t, 3, cfg.nrptEntryCount, "Should create 3 NRPT rules for 125 domains")
+	assert.Equal(t, 3, countNRPTRuleKeys(t), "Should create 3 NRPT rules for 125 domains")
 	for i := 0; i < 3; i++ {
 		exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i))
 		require.NoError(t, err)
@@ -81,7 +81,7 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) {
 	require.NoError(t, err)
 
 	// Verify first 2 NRPT rules exist
-	assert.Equal(t, 2, cfg.nrptEntryCount, "Should create 2 NRPT rules for 75 domains")
+	assert.Equal(t, 2, countNRPTRuleKeys(t), "Should create 2 NRPT rules for 75 domains")
 	for i := 0; i < 2; i++ {
 		exists, err := registryKeyExists(fmt.Sprintf("%s-%d", dnsPolicyConfigMatchPath, i))
 		require.NoError(t, err)
@@ -94,6 +94,145 @@ func TestNRPTEntriesCleanupOnConfigChange(t *testing.T) {
 	assert.False(t, exists, "NRPT rule 2 should NOT exist after reducing to 75 domains")
 }
 
+// TestNRPTCatchAllRule verifies that RouteAll adds the root namespace to the
+// match rule instead of a rule of its own, that .local is carved back out with
+// an empty server list, and that both go away when RouteAll is cleared or the
+// host DNS is restored.
+func TestNRPTCatchAllRule(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping registry integration test in short mode")
+	}
+
+	defer cleanupRegistryKeys(t)
+	cleanupRegistryKeys(t)
+
+	testIP := netip.MustParseAddr("100.64.0.1")
+	testGUID := "{12345678-1234-1234-1234-123456789ABC}"
+	interfacePath := InterfaceConfigPath + `\` + testGUID
+	testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE)
+	require.NoError(t, err, "Should create test interface registry key")
+	require.NoError(t, testKey.Close(), "close test interface registry key")
+	defer func() {
+		assert.NoError(t, registry.DeleteKey(registry.LOCAL_MACHINE, interfacePath), "delete test interface registry key")
+	}()
+
+	cfg := &registryConfigurator{guid: testGUID}
+
+	matchOnly := HostDNSConfig{
+		ServerIP: testIP,
+		Domains:  []DomainConfig{{Domain: "example.com", MatchOnly: true}},
+	}
+	primary := HostDNSConfig{
+		ServerIP: testIP,
+		RouteAll: true,
+		Domains:  []DomainConfig{{Domain: "example.com", MatchOnly: true}},
+	}
+	firstRule := fmt.Sprintf("%s-0", dnsPolicyConfigMatchPath)
+
+	// The root namespace is not a rule of its own: it rides in the match rule,
+	// which is the point of it not being a special case.
+	require.NoError(t, cfg.applyDNSConfig(matchOnly, nil))
+	names := ruleNamespaces(t, firstRule)
+	assert.Contains(t, names, ".example.com")
+	assert.NotContains(t, names, nrptCatchAllNamespace, "a match-only config must not claim every namespace")
+
+	require.NoError(t, cfg.applyDNSConfig(primary, nil))
+	names = ruleNamespaces(t, firstRule)
+	assert.Contains(t, names, ".example.com")
+	assert.Contains(t, names, nrptCatchAllNamespace, "RouteAll should add the root namespace to the match rule")
+
+	k, err := registry.OpenKey(registry.LOCAL_MACHINE, firstRule, registry.QUERY_VALUE)
+	require.NoError(t, err)
+	servers, _, err := k.GetStringValue(dnsPolicyConfigGenericDNSServersKey)
+	require.NoError(t, err)
+	assert.Equal(t, testIP.String(), servers, "every namespace in the rule resolves through our resolver")
+	require.NoError(t, k.Close(), "close match rule key")
+
+	// .local is carved back out: RFC 6762 reserves it for mDNS, so it needs a
+	// rule of its own — it is the one rule with a different server list.
+	ek, err := registry.OpenKey(registry.LOCAL_MACHINE, dnsPolicyConfigExemptLocalPath, registry.QUERY_VALUE)
+	require.NoError(t, err, "exemption rule should exist once the root namespace is claimed")
+
+	exemptNames, _, err := ek.GetStringsValue(dnsPolicyConfigNameKey)
+	require.NoError(t, err)
+	assert.Equal(t, []string{nrptLocalNamespace}, exemptNames, "the exemption should name only the mDNS namespace")
+
+	exemptServers, _, err := ek.GetStringValue(dnsPolicyConfigGenericDNSServersKey)
+	require.NoError(t, err, "the value has to be present, empty: without it Windows drops the rule")
+	assert.Empty(t, exemptServers, "an exemption rule lists no servers")
+
+	exemptOpts, _, err := ek.GetIntegerValue(dnsPolicyConfigConfigOptionsKey)
+	require.NoError(t, err)
+	assert.EqualValues(t, dnsPolicyConfigConfigOptionsValue, exemptOpts, "same options as a normal rule; the empty server list is what makes it an exemption")
+	require.NoError(t, ek.Close(), "close exemption rule key")
+
+	require.NoError(t, cfg.applyDNSConfig(matchOnly, nil))
+	names = ruleNamespaces(t, firstRule)
+	assert.NotContains(t, names, nrptCatchAllNamespace, "clearing RouteAll should drop the root namespace")
+
+	exists, err := registryKeyExists(dnsPolicyConfigExemptLocalPath)
+	require.NoError(t, err)
+	assert.False(t, exists, "exemption rule should go with the namespace it carves out of")
+
+	require.NoError(t, cfg.applyDNSConfig(primary, nil))
+	require.NoError(t, cfg.restoreHostDNS())
+	exists, err = registryKeyExists(firstRule)
+	require.NoError(t, err)
+	assert.False(t, exists, "restore should leave no rule behind")
+}
+
+// ruleNamespaces returns the namespaces an NRPT rule key claims.
+func ruleNamespaces(t *testing.T, path string) []string {
+	t.Helper()
+	k, err := registry.OpenKey(registry.LOCAL_MACHINE, path, registry.QUERY_VALUE)
+	require.NoError(t, err, "rule key %s should exist", path)
+	defer k.Close()
+
+	names, _, err := k.GetStringsValue(dnsPolicyConfigNameKey)
+	require.NoError(t, err)
+	return names
+}
+
+// TestNRPTCatchAllRuleLegacyEnv verifies that NB_USE_LEGACY_DNS_RESOLUTION
+// leaves the root namespace unclaimed, so no rule is written for a RouteAll
+// config that carries no match domains.
+func TestNRPTCatchAllRuleLegacyEnv(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping registry integration test in short mode")
+	}
+
+	defer cleanupRegistryKeys(t)
+	cleanupRegistryKeys(t)
+
+	t.Setenv(envLegacyDNSResolution, "true")
+
+	testGUID := "{12345678-1234-1234-1234-123456789ABC}"
+	interfacePath := InterfaceConfigPath + `\` + testGUID
+	testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE)
+	require.NoError(t, err, "Should create test interface registry key")
+	require.NoError(t, testKey.Close(), "close test interface registry key")
+	defer func() {
+		assert.NoError(t, registry.DeleteKey(registry.LOCAL_MACHINE, interfacePath), "delete test interface registry key")
+	}()
+
+	cfg := &registryConfigurator{guid: testGUID}
+	config := HostDNSConfig{
+		ServerIP: netip.MustParseAddr("100.64.0.1"),
+		RouteAll: true,
+	}
+
+	require.NoError(t, cfg.applyDNSConfig(config, nil))
+
+	// RouteAll with no match domains and the switch set leaves nothing to write.
+	exists, err := registryKeyExists(fmt.Sprintf("%s-0", dnsPolicyConfigMatchPath))
+	require.NoError(t, err)
+	assert.False(t, exists, "no rule should be written when the legacy env var is set")
+
+	exists, err = registryKeyExists(dnsPolicyConfigExemptLocalPath)
+	require.NoError(t, err)
+	assert.False(t, exists, "no exemption without a claimed root namespace")
+}
+
 func registryKeyExists(path string) (bool, error) {
 	k, err := registry.OpenKey(registry.LOCAL_MACHINE, path, registry.QUERY_VALUE)
 	if err != nil {
@@ -106,9 +245,65 @@ func registryKeyExists(path string) (bool, error) {
 	return true, nil
 }
 
+// TestNRPTCleanupWithoutRuleCount verifies that rules written by a previous run
+// are removed by a configurator that has no record of how many there are: an
+// unclean exit loses the in-memory count and a clean disconnect deletes the
+// persisted one, so cleanup cannot depend on either.
+func TestNRPTCleanupWithoutRuleCount(t *testing.T) {
+	if testing.Short() {
+		t.Skip("skipping registry integration test in short mode")
+	}
+
+	defer cleanupRegistryKeys(t)
+	cleanupRegistryKeys(t)
+
+	testIP := netip.MustParseAddr("100.64.0.1")
+
+	// 75 domains produce two indexed rules, as the current layout does
+	domains := make([]string, 75)
+	for i := range domains {
+		domains[i] = fmt.Sprintf(".domain%d.com", i+1)
+	}
+
+	previousRun := &registryConfigurator{}
+	require.NoError(t, previousRun.addDNSMatchPolicy(domains, testIP))
+
+	// the unsuffixed key an older version would have written
+	require.NoError(t, previousRun.configureDNSPolicy(dnsPolicyConfigMatchPath, []string{".legacy.example.com"}, testIP))
+
+	// a policy owned by someone else, which cleanup must not touch
+	foreignPath := DNSPolicyConfigRoot + `\DnsPolicyConfigTestForeign`
+	foreignKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, foreignPath, registry.SET_VALUE)
+	require.NoError(t, err, "Should create foreign policy key")
+	foreignKey.Close()
+	defer func() {
+		_ = registry.DeleteKey(registry.LOCAL_MACHINE, foreignPath)
+	}()
+
+	require.Equal(t, 3, countNRPTRuleKeys(t), "Should have two indexed rules and the legacy one")
+
+	// a configurator that never applied a DNS config, as one built after a
+	// restart or from a shutdown state without a count is
+	freshRun := &registryConfigurator{}
+	require.NoError(t, freshRun.removeDNSMatchPolicies())
+
+	assert.Equal(t, 0, countNRPTRuleKeys(t), "Should remove every rule left by the previous run")
+
+	exists, err := registryKeyExists(foreignPath)
+	require.NoError(t, err)
+	assert.True(t, exists, "Should not remove a policy that is not ours")
+}
+
+func countNRPTRuleKeys(t *testing.T) int {
+	t.Helper()
+
+	names, err := listNRPTRuleKeys(DNSPolicyConfigRoot)
+	require.NoError(t, err, "Should list NRPT rule keys")
+	return len(names)
+}
+
 func cleanupRegistryKeys(*testing.T) {
-	// Clean up more entries to account for batching tests with many domains
+	cfg := &registryConfigurator{}
-	cfg := &registryConfigurator{nrptEntryCount: 20}
 	_ = cfg.removeDNSMatchPolicies()
 }
 
@@ -125,7 +320,7 @@ func TestNRPTDomainBatching(t *testing.T) {
 
 	// Create a test interface registry key so updateSearchDomains doesn't fail
 	testGUID := "{12345678-1234-1234-1234-123456789ABC}"
-	interfacePath := `SYSTEM\CurrentControlSet\Services\Tcpip\Parameters\Interfaces\` + testGUID
+	interfacePath := InterfaceConfigPath + `\` + testGUID
 	testKey, _, err := registry.CreateKey(registry.LOCAL_MACHINE, interfacePath, registry.SET_VALUE)
 	require.NoError(t, err, "Should create test interface registry key")
 	testKey.Close()
@@ -193,7 +388,7 @@ func TestNRPTDomainBatching(t *testing.T) {
 			require.NoError(t, err)
 
 			// Verify that exactly expectedRuleCount rules were created
-			assert.Equal(t, tc.expectedRuleCount, cfg.nrptEntryCount,
+			assert.Equal(t, tc.expectedRuleCount, countNRPTRuleKeys(t),
 				"Should create %d NRPT rules for %d domains", tc.expectedRuleCount, tc.domainCount)
 
 			// Verify all expected rules exist

client/internal/dns/mgmt/mgmt_refresh_test.go

@@ -224,6 +224,7 @@ func TestResolver_StaleTriggersAsyncRefresh(t *testing.T) {
 }
 
 func TestResolver_ConcurrentStaleHitsCollapseRefresh(t *testing.T) {
+	semaphore := make(chan struct{})
 	r := NewResolver()
 	chain := newFakeChain()
 	chain.setAnswer("mgmt.example.com.", dns.TypeA, "10.0.0.2")
@@ -239,7 +240,7 @@ func TestResolver_ConcurrentStaleHitsCollapseRefresh(t *testing.T) {
 				break
 			}
 		}
-		time.Sleep(50 * time.Millisecond) // hold inflight long enough to collide
+		<-semaphore // block the call to force request collision
 	}
 
 	r.SetChainResolver(chain, 50)
@@ -255,17 +256,17 @@ func TestResolver_ConcurrentStaleHitsCollapseRefresh(t *testing.T) {
 
 	var wg sync.WaitGroup
 	for i := 0; i < 50; i++ {
-		wg.Add(1)
+		wg.Go(func() {
-		go func() {
-			defer wg.Done()
 			queryA(t, r, "mgmt.example.com.")
-		}()
+		})
 	}
+
+	assert.Eventually(t, func() bool { return inflight.Load() >= 1 }, 2*time.Second, 100*time.Millisecond)
+
+	close(semaphore)
 	wg.Wait()
 
-	waitFor(t, 2*time.Second, func() bool {
+	assert.Eventually(t, func() bool { return inflight.Load() == 0 }, 2*time.Second, 100*time.Millisecond)
-		return inflight.Load() == 0
-	})
 
 	calls := chain.callCount("mgmt.example.com.", dns.TypeA)
 	assert.LessOrEqual(t, calls, 2, "singleflight must collapse concurrent refreshes (got %d)", calls)

client/internal/dns/response_writer_test.go

@@ -4,7 +4,7 @@ import (
 	"net"
 	"testing"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/google/gopacket"
 	"github.com/google/gopacket/layers"
 	"github.com/miekg/dns"

client/internal/dns/server_privileged_test.go

@@ -9,7 +9,7 @@ import (
 	"os"
 	"testing"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/miekg/dns"
 	"github.com/stretchr/testify/assert"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"

client/internal/dns/unclean_shutdown_windows.go

@@ -5,9 +5,8 @@ import (
 )
 
 type ShutdownState struct {
-	Guid           string
+	Guid string
-	GPO            bool
+	GPO  bool
-	NRPTEntryCount int
 }
 
 func (s *ShutdownState) Name() string {
@@ -16,9 +15,8 @@ func (s *ShutdownState) Name() string {
 
 func (s *ShutdownState) Cleanup() error {
 	manager := &registryConfigurator{
-		guid:           s.Guid,
+		guid: s.Guid,
-		gpo:            s.GPO,
+		gpo:  s.GPO,
-		nrptEntryCount: s.NRPTEntryCount,
 	}
 
 	if err := manager.restoreUncleanShutdownDNS(); err != nil {

client/internal/dns_test.go

@@ -8,7 +8,9 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	nbdns "github.com/netbirdio/netbird/dns"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 func TestCreatePTRRecord_IPv4(t *testing.T) {
@@ -136,3 +138,88 @@ func TestAddReverseZone_IPv6(t *testing.T) {
 	assert.Len(t, reverseZone.Records, 1)
 	assert.Equal(t, int(dns.TypePTR), reverseZone.Records[0].Type)
 }
+
+// TestToDNSConfig_ZoneFlagsPreserved pins the per-zone NonAuthoritative flag
+// through the legacy DNSConfig path. A non-authoritative zone is match-only:
+// the local resolver falls through to the upstream for an in-zone name it does
+// not define. The built-in peer zone is the authoritative one and must stay
+// that way, so the flag has to travel per zone rather than be derived.
+func TestToDNSConfig_ZoneFlagsPreserved(t *testing.T) {
+	config := toDNSConfig(&mgmProto.DNSConfig{
+		ServiceEnable: true,
+		CustomZones: []*mgmProto.CustomZone{
+			{
+				Domain: "netbird.cloud.",
+				Records: []*mgmProto.SimpleRecord{
+					{Name: "peer1.netbird.cloud.", Type: int64(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.1"},
+				},
+			},
+			{
+				Domain:               "corp.internal.",
+				NonAuthoritative:     true,
+				SearchDomainDisabled: true,
+				Records: []*mgmProto.SimpleRecord{
+					{Name: "db.corp.internal.", Type: int64(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.10.0.5"},
+				},
+			},
+		},
+	}, wgaddr.Address{
+		IP:      netip.MustParseAddr("100.64.0.1"),
+		Network: netip.MustParsePrefix("100.64.0.0/16"),
+	})
+
+	zones := make(map[string]nbdns.CustomZone, len(config.CustomZones))
+	for _, zone := range config.CustomZones {
+		zones[zone.Domain] = zone
+	}
+
+	peerZone, ok := zones["netbird.cloud."]
+	require.True(t, ok, "peer zone must survive")
+	assert.False(t, peerZone.NonAuthoritative, "the built-in peer zone owns the account domain and stays authoritative")
+
+	accountZone, ok := zones["corp.internal."]
+	require.True(t, ok, "account zone must survive")
+	assert.True(t, accountZone.NonAuthoritative, "an account zone stays match-only, else undefined in-zone names get black-holed")
+	assert.True(t, accountZone.SearchDomainDisabled)
+}
+
+// TestToDNSConfig_SingleZoneForcedAuthoritative pins the compatibility clause
+// in toDNSConfig: a config carrying exactly one zone is treated as
+// authoritative no matter what the server said, because servers that predate
+// the NonAuthoritative field send only the peer FQDN zone.
+//
+// The clause can only ever downgrade an explicit true to false, so a server
+// that legitimately sends a single non-authoritative zone — an account whose
+// only zone is a custom one, with no peer records to build the built-in zone
+// from — gets that zone's whole apex black-holed on the client. Real accounts
+// always carry the peer zone alongside, which is why this is latent. Narrowing
+// it needs a way to tell "unset" from "false" on the wire, or the account
+// domain passed down here; until then this test states the contract so a
+// change to it is deliberate.
+func TestToDNSConfig_SingleZoneForcedAuthoritative(t *testing.T) {
+	config := toDNSConfig(&mgmProto.DNSConfig{
+		ServiceEnable: true,
+		CustomZones: []*mgmProto.CustomZone{
+			{
+				Domain:           "corp.internal.",
+				NonAuthoritative: true,
+				Records: []*mgmProto.SimpleRecord{
+					{Name: "db.corp.internal.", Type: int64(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.10.0.5"},
+				},
+			},
+		},
+	}, wgaddr.Address{
+		IP:      netip.MustParseAddr("100.64.0.1"),
+		Network: netip.MustParsePrefix("100.64.0.0/16"),
+	})
+
+	require.NotEmpty(t, config.CustomZones)
+	assert.Equal(t, "corp.internal.", config.CustomZones[0].Domain)
+	assert.False(t, config.CustomZones[0].NonAuthoritative,
+		"a lone zone is forced authoritative for pre-NonAuthoritative servers")
+
+	// The reverse zone the config gains afterwards must not feed back into the
+	// decision: the compat gate counts the zones the server sent.
+	require.Len(t, config.CustomZones, 2, "a reverse zone is appended for the overlay prefix")
+	assert.Equal(t, "64.100.in-addr.arpa.", config.CustomZones[1].Domain)
+}

client/internal/dnsfwd/manager.go

@@ -101,7 +101,7 @@ func (m *Manager) Start(fwdEntries []*ForwarderEntry) error {
 	m.dnsForwarder = NewDNSForwarder(listenAddress, dnsTTL, m.firewall, m.statusRecorder, m.wgIface)
 
 	go func() {
-		if err := m.dnsForwarder.Listen(fwdEntries); err != nil {
+		if err := m.dnsForwarder.Listen(fwdEntries); err != nil { //nolint:staticcheck
 			// todo handle close error if it is exists
 			log.Errorf("failed to start DNS forwarder, err: %v", err)
 		}

client/internal/elevate/elevate.go

@@ -0,0 +1,74 @@
+// Package elevate re-runs this very executable under the operating system's own
+// privilege-elevation mechanism and waits for it to finish.
+//
+// It exists so that a change the daemon restricts to root/administrator can be
+// authorized from the GUI, by the user, at the moment they ask for it: Windows
+// shows the UAC consent dialog, macOS the system authentication dialog, and
+// Linux/FreeBSD the session's polkit agent. The credentials, where any are
+// asked for, are collected by the operating system and never pass through
+// NetBird.
+//
+// What the elevated process then does is the caller's business: it is the same
+// binary, in a one-shot mode, and it is authorized by the daemon exactly like
+// any other privileged caller, from the identity the kernel reports on the
+// control channel. Nothing here grants privilege, and the daemon gains no new
+// way to be talked into something: elevation only changes who is calling it.
+package elevate
+
+import (
+	"context"
+	"errors"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// AppliedMarker is what the elevated process prints on standard output once it has
+// done what it was run for.
+//
+// macOS's AuthorizationExecuteWithPrivileges reports no exit status and does not
+// say which process it started, so there this line is the only evidence that the
+// change was applied. The other platforms have an exit code and ignore it.
+const AppliedMarker = "netbird-elevated: applied"
+
+var (
+	// ErrDeclined reports that the user dismissed the prompt or did not
+	// authenticate. Nothing happened and nothing is wrong: a caller undoes its
+	// optimistic update and stays quiet.
+	ErrDeclined = errors.New("authorization declined")
+
+	// ErrUnavailable reports that this host has no elevation mechanism we can
+	// drive: no polkit on a Unix desktop, or an executable we decline to run as
+	// root. A caller falls back to telling the user which command to run.
+	ErrUnavailable = errors.New("no privilege elevation mechanism available")
+)
+
+// Run runs this executable with args under the platform's elevation mechanism
+// and waits for it to exit. A non-zero exit is returned as an error, so the
+// caller can treat a completed Run as the operation having succeeded.
+//
+// The args are the caller's own command line, so they cross no privilege
+// boundary: only a user who has just authenticated as an administrator can get
+// them run at all.
+func Run(ctx context.Context, args ...string) error {
+	self, err := trustedSelf()
+	if err != nil {
+		return err
+	}
+	return run(ctx, self, args)
+}
+
+// Available reports whether Run has a mechanism to use on this host, so a caller
+// can offer the prompt only when there is one and otherwise fall back to
+// guidance the user can act on. It answers from what is installed, not from what
+// the user is allowed to do: an administrator's password may still be required
+// and may still not be given, which is ErrDeclined from Run.
+func Available() bool {
+	if _, err := trustedSelf(); err != nil {
+		// Worth a line: this is also what a build run from a group-writable
+		// directory hits, and there is nothing in the UI to say why the offer is
+		// missing.
+		log.Debugf("not offering privilege elevation: %v", err)
+		return false
+	}
+	return mechanismAvailable()
+}

client/internal/elevate/output.go

@@ -0,0 +1,18 @@
+package elevate
+
+import "strings"
+
+// noOutput stands in for a process that said nothing, so that a report of what it
+// said still reads as a sentence.
+const noOutput = "no output"
+
+func firstLine(s string) string {
+	s = strings.TrimSpace(s)
+	if s == "" {
+		return noOutput
+	}
+	if i := strings.IndexByte(s, '\n'); i >= 0 {
+		return s[:i]
+	}
+	return s
+}

client/internal/elevate/output_test.go

@@ -0,0 +1,21 @@
+package elevate
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+func TestFirstLine(t *testing.T) {
+	tests := []struct{ in, want string }{
+		{in: "", want: noOutput},
+		{in: "  \n ", want: noOutput},
+		{in: "one line", want: "one line"},
+		{in: "first\nsecond", want: "first"},
+		{in: "\nsecond\n", want: "second"},
+	}
+
+	for _, tt := range tests {
+		assert.Equal(t, tt.want, firstLine(tt.in), "input %q", tt.in)
+	}
+}

client/internal/elevate/run_darwin.go

@@ -0,0 +1,359 @@
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"runtime"
+	"strings"
+	"sync"
+	"syscall"
+	"unsafe"
+
+	"github.com/ebitengine/purego"
+	log "github.com/sirupsen/logrus"
+)
+
+// Authorization Services, reached through purego rather than cgo so the released
+// binaries keep building with CGO_ENABLED=0.
+//
+// The prompt belongs to this process, which is what makes it carry the
+// application's name and our own explanation. Going through osascript instead puts
+// the very same trampoline behind a dialog attributed to osascript, and means
+// handing a shell a command line to re-parse.
+//
+// # On AuthorizationExecuteWithPrivileges
+//
+// It is deprecated, and Apple's guidance (Quinn, "BSD Privilege Escalation on
+// macOS", developer.apple.com/forums/thread/708765) is "while it still works, it's
+// been deprecated for many years. Do not use it in a widely distributed product."
+// It is used here anyway, knowingly, because the alternatives Apple offers are for
+// *obtaining* ongoing privileges — an installer package, SMAppService, SMJobBless —
+// and NetBird already has what they would install: a launchd daemon running as
+// root. What is missing is only a way for an unprivileged client to ask it to act.
+//
+// The way to that without a deprecated call is to authorize the client instead of
+// elevating one: the app takes the right with AuthorizationCreate, passes the
+// AuthorizationExternalForm to the daemon, and the daemon checks it with
+// AuthorizationCopyRights before acting — none of which is deprecated. It is the
+// better design and it is where this should end up. It also means the daemon
+// accepting an authorization over its control socket, which is a new way to be
+// asked for privileged work and wants reviewing as such, so it is deliberately not
+// bundled in with the rest of this.
+//
+// Until then, three things keep the deprecation from being a trap. Every symbol is
+// resolved with an error rather than a panic, so a macOS that has dropped this
+// function leaves the app offering the user a command instead of crashing on the
+// way to a prompt. A failure to run the tool is reported as ErrUnavailable, so the
+// fallback is the same one an agent-less Linux session gets. And the whole path
+// runs under guard, which turns a panic out of the FFI layer into that same
+// fallback.
+//
+// The trampoline passes on the environment it was given, so what it starts as root
+// must be an executable this user's peers cannot influence: that is what
+// trustedSelf refuses, and what signing the binary settles for the loader.
+
+const (
+	securityFramework = "/System/Library/Frameworks/Security.framework/Security"
+	libSystem         = "/usr/lib/libSystem.B.dylib"
+
+	// trampoline is what the framework hands the tool to. Present on every macOS,
+	// and worth confirming before offering a prompt rather than mid-prompt.
+	trampoline = "/usr/libexec/security_authtrampoline"
+)
+
+// rightExecute is the right an administrator holds, and what
+// AuthorizationExecuteWithPrivileges requires of us.
+const rightExecute = "system.privilege.admin"
+
+// promptKey is kAuthorizationEnvironmentPrompt, which puts a sentence of ours above
+// the system's in the dialog. It is about the change rather than the mechanism.
+const (
+	promptKey  = "prompt"
+	promptText = "NetBird needs to change a setting that grants SSH access to this computer."
+)
+
+// OSStatus values from SecBase.h that mean something to us; anything else is
+// reported as it comes.
+const (
+	errAuthorizationSuccess               = 0
+	errAuthorizationDenied                = -60005
+	errAuthorizationCanceled              = -60006
+	errAuthorizationInteractionNotAllowed = -60007
+	errAuthorizationToolExecuteFailure    = -60031
+	errAuthorizationToolEnvironmentError  = -60032
+)
+
+// AuthorizationFlags from Authorization.h.
+const (
+	flagDefaults           = 0
+	flagInteractionAllowed = 1 << 0
+	flagExtendRights       = 1 << 1
+	flagDestroyRights      = 1 << 3
+	flagPreAuthorize       = 1 << 4
+)
+
+// authorizationItem mirrors AuthorizationItem: a name, and a value the name gives
+// meaning to. 32 bytes on both amd64 and arm64.
+type authorizationItem struct {
+	name        *byte
+	valueLength uintptr
+	value       unsafe.Pointer
+	// flags is reserved by the API and always zero. Declared because the layout
+	// is the contract: without it the struct is 24 bytes where C reads 32.
+	flags uint32 //nolint:unused // part of the C layout
+}
+
+// authorizationItemSet mirrors AuthorizationItemSet, which serves as both an
+// AuthorizationRights and an AuthorizationEnvironment.
+type authorizationItemSet struct {
+	count uint32
+	items *authorizationItem
+}
+
+var (
+	authorizationCreate                func(rights, environment *authorizationItemSet, flags uint32, authorization *uintptr) int32
+	authorizationExecuteWithPrivileges func(authorization uintptr, pathToTool string, options uint32, arguments *uintptr, communicationsPipe *uintptr) int32
+	authorizationFree                  func(authorization uintptr, flags uint32) int32
+	fileno                             func(stream uintptr) int32
+	fclose                             func(stream uintptr) int32
+
+	loadOnce sync.Once
+	loadErr  error
+)
+
+// load resolves the functions once. A framework that cannot be opened, or a symbol
+// that is no longer there, leaves the host without a mechanism rather than taking
+// the process down with it: see the note on deprecation above.
+func load() error {
+	loadOnce.Do(func() { loadErr = guard("loading Security.framework", resolve) })
+	return loadErr
+}
+
+// guard turns a panic out of the FFI layer into an error, so an API that has
+// changed under us costs the user a prompt rather than the window they were
+// clicking in. purego panics on a signature it cannot map, and this is the one
+// place in the client that calls a deprecated system function.
+//
+// It catches Go panics, which is what purego raises. A fault inside the framework
+// itself is not a panic and not recoverable; the layout the tests pin down is what
+// stands between us and that.
+func guard(what string, fn func() error) (err error) {
+	defer func() {
+		r := recover()
+		if r == nil {
+			return
+		}
+		log.Errorf("%s panicked: %v", what, r)
+		err = fmt.Errorf("%w: %s: %v", ErrUnavailable, what, r)
+	}()
+	return fn()
+}
+
+func resolve() error {
+	security, err := purego.Dlopen(securityFramework, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
+	if err != nil {
+		return fmt.Errorf("open %s: %w", securityFramework, err)
+	}
+	system, err := purego.Dlopen(libSystem, purego.RTLD_LAZY|purego.RTLD_GLOBAL)
+	if err != nil {
+		return fmt.Errorf("open %s: %w", libSystem, err)
+	}
+
+	// purego.RegisterLibFunc panics on a symbol it cannot find, which is not how a
+	// deprecated function's disappearance should reach the user.
+	for _, fn := range []struct {
+		ptr    any
+		handle uintptr
+		name   string
+	}{
+		{&authorizationCreate, security, "AuthorizationCreate"},
+		{&authorizationExecuteWithPrivileges, security, "AuthorizationExecuteWithPrivileges"},
+		{&authorizationFree, security, "AuthorizationFree"},
+		{&fileno, system, "fileno"},
+		{&fclose, system, "fclose"},
+	} {
+		symbol, err := purego.Dlsym(fn.handle, fn.name)
+		if err != nil {
+			return fmt.Errorf("resolve %s: %w", fn.name, err)
+		}
+		if symbol == 0 {
+			return fmt.Errorf("resolve %s: not present on this system", fn.name)
+		}
+		purego.RegisterFunc(fn.ptr, symbol)
+	}
+	return nil
+}
+
+// run asks the system to run self as root: first for the right, which is what puts
+// up the authentication dialog and collects the password or takes the Touch ID,
+// then for the tool. The credentials go to the system's authorization trampoline
+// and never to us.
+//
+// The context bounds only our own waiting; the dialog belongs to the system and
+// closes when the user answers it.
+func run(ctx context.Context, self string, args []string) error {
+	if err := load(); err != nil {
+		return fmt.Errorf("%w: %v", ErrUnavailable, err)
+	}
+
+	return guard("asking for privileges", func() error {
+		authorization, err := authorize()
+		if err != nil {
+			return err
+		}
+		defer authorizationFree(authorization, flagDestroyRights)
+
+		return execute(ctx, authorization, self, args)
+	})
+}
+
+func mechanismAvailable() bool {
+	if err := load(); err != nil {
+		return false
+	}
+	info, err := os.Stat(trampoline)
+	return err == nil && !info.IsDir()
+}
+
+// authorize obtains the right, prompting for it. A dismissed dialog comes back as
+// errAuthorizationCanceled and a password given up on as errAuthorizationDenied;
+// both are the user's answer rather than a failure.
+func authorize() (uintptr, error) {
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
+	environment := itemSet(&pinner, promptItem(&pinner))
+
+	var authorization uintptr
+	status := authorizationCreate(rights, environment,
+		flagDefaults|flagInteractionAllowed|flagPreAuthorize|flagExtendRights, &authorization)
+
+	switch status {
+	case errAuthorizationSuccess:
+		return authorization, nil
+	case errAuthorizationCanceled, errAuthorizationDenied:
+		return 0, ErrDeclined
+	case errAuthorizationInteractionNotAllowed:
+		// Nowhere to put a dialog, so there is nobody to ask: a launch daemon, or
+		// a session with no window server.
+		return 0, fmt.Errorf("%w: this session cannot show an authorization prompt", ErrUnavailable)
+	default:
+		return 0, fmt.Errorf("request %s: OSStatus %d", rightExecute, status)
+	}
+}
+
+// execute runs the tool with the right in hand and waits for it by reading the pipe
+// it is given until the tool closes it.
+//
+// AuthorizationExecuteWithPrivileges reports no exit status and does not say what
+// process it started, which is why the one-shot says so itself: what it prints is
+// the only evidence that the change was applied.
+func execute(ctx context.Context, authorization uintptr, self string, args []string) error {
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	argv := make([]uintptr, 0, len(args)+1)
+	for _, arg := range args {
+		argv = append(argv, uintptr(unsafe.Pointer(cString(&pinner, arg))))
+	}
+	argv = append(argv, 0)
+	pinner.Pin(&argv[0])
+
+	var pipe uintptr
+	status := authorizationExecuteWithPrivileges(authorization, self, flagDefaults, &argv[0], &pipe)
+	switch status {
+	case errAuthorizationSuccess:
+	case errAuthorizationCanceled:
+		return ErrDeclined
+	case errAuthorizationToolExecuteFailure, errAuthorizationToolEnvironmentError:
+		// The right was granted and the tool still did not start. Nothing the user
+		// can do about it from here, so point them at the command instead.
+		return fmt.Errorf("%w: the system would not run %s elevated (OSStatus %d)", ErrUnavailable, self, status)
+	default:
+		return fmt.Errorf("run %s elevated: OSStatus %d", self, status)
+	}
+
+	out, err := readPipe(ctx, pipe)
+	if err != nil {
+		return err
+	}
+	return checkApplied(out)
+}
+
+// checkApplied reads the one-shot's report, which stands in for the exit status
+// there is no way to ask for here. A run that said nothing did not apply the
+// change, whatever else went on.
+func checkApplied(out string) error {
+	if !strings.Contains(out, AppliedMarker) {
+		return fmt.Errorf("elevated netbird did not report the change as applied: %s", firstLine(out))
+	}
+	return nil
+}
+
+// readPipe drains the tool's output, which ends when the tool exits and is
+// therefore also how we wait for it.
+func readPipe(ctx context.Context, pipe uintptr) (string, error) {
+	if pipe == 0 {
+		return "", nil
+	}
+	defer fclose(pipe)
+
+	fd := int(fileno(pipe))
+	if fd < 0 {
+		return "", nil
+	}
+
+	var out strings.Builder
+	buf := make([]byte, 4096)
+	for {
+		if err := ctx.Err(); err != nil {
+			return out.String(), err
+		}
+		n, err := syscall.Read(fd, buf)
+		if n > 0 {
+			out.Write(buf[:n])
+		}
+		switch {
+		case errors.Is(err, syscall.EINTR):
+			// A signal landed mid-read, which says nothing about the tool.
+			continue
+		case err != nil:
+			log.Debugf("read the elevated process's output: %v", err)
+			return out.String(), nil
+		case n <= 0:
+			// End of file: the tool closed the pipe, which is how it exiting
+			// reaches us.
+			return out.String(), nil
+		}
+	}
+}
+
+// itemSet builds an AuthorizationItemSet over items, pinned for the call.
+func itemSet(pinner *runtime.Pinner, items ...authorizationItem) *authorizationItemSet {
+	pinner.Pin(&items[0])
+	set := &authorizationItemSet{count: uint32(len(items)), items: &items[0]}
+	pinner.Pin(set)
+	return set
+}
+
+// promptItem is the environment entry carrying our sentence for the dialog.
+func promptItem(pinner *runtime.Pinner) authorizationItem {
+	value := []byte(promptText)
+	pinner.Pin(&value[0])
+	return authorizationItem{
+		name:        cString(pinner, promptKey),
+		valueLength: uintptr(len(value)),
+		value:       unsafe.Pointer(&value[0]),
+	}
+}
+
+// cString returns a NUL-terminated copy of s, pinned so the C side may hold it for
+// the duration of the call.
+func cString(pinner *runtime.Pinner, s string) *byte {
+	b := append([]byte(s), 0)
+	pinner.Pin(&b[0])
+	return &b[0]
+}

client/internal/elevate/run_darwin_test.go

@@ -0,0 +1,111 @@
+package elevate
+
+import (
+	"errors"
+	"runtime"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The framework has to load and the symbols have to resolve, or nothing else here
+// means anything.
+func TestSecurityFrameworkLoads(t *testing.T) {
+	require.NoError(t, load(), "Security.framework must open")
+
+	for name, fn := range map[string]any{
+		"AuthorizationCreate":                authorizationCreate,
+		"AuthorizationExecuteWithPrivileges": authorizationExecuteWithPrivileges,
+		"AuthorizationFree":                  authorizationFree,
+		"fileno":                             fileno,
+		"fclose":                             fclose,
+	} {
+		assert.NotNil(t, fn, "%s must resolve", name)
+	}
+}
+
+// A request with no interaction allowed exercises the whole call — the rights and
+// environment structs, and the OSStatus that comes back — without a dialog anybody
+// has to answer. What the system decides is its business; that it decides at all is
+// what this asserts.
+func TestAuthorizationCreateWithoutInteraction(t *testing.T) {
+	if err := load(); err != nil {
+		t.Skipf("Security.framework did not open: %v", err)
+	}
+
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, rightExecute)})
+	environment := itemSet(&pinner, promptItem(&pinner))
+	require.EqualValues(t, 1, rights.count, "the rights struct layout must match the C one")
+
+	var authorization uintptr
+	status := authorizationCreate(rights, environment, flagDefaults|flagExtendRights, &authorization)
+
+	switch status {
+	case errAuthorizationSuccess:
+		// Credentials were already cached for this session.
+		authorizationFree(authorization, flagDestroyRights)
+	case errAuthorizationDenied, errAuthorizationInteractionNotAllowed:
+		// The expected answers when nobody may be asked.
+	default:
+		require.Failf(t, "unknown OSStatus", "AuthorizationCreate returned %d, want a status we recognise", status)
+	}
+}
+
+// Asking with a right nobody has must not be mistaken for a declined prompt: the
+// caller would report nothing at all.
+func TestAuthorizeUnknownRightIsNotDeclined(t *testing.T) {
+	if err := load(); err != nil {
+		t.Skipf("Security.framework did not open: %v", err)
+	}
+
+	var pinner runtime.Pinner
+	defer pinner.Unpin()
+
+	rights := itemSet(&pinner, authorizationItem{name: cString(&pinner, "io.netbird.right.that.does.not.exist")})
+
+	var authorization uintptr
+	status := authorizationCreate(rights, nil, flagDefaults|flagExtendRights, &authorization)
+	if status == errAuthorizationSuccess {
+		authorizationFree(authorization, flagDestroyRights)
+	}
+	assert.NotEqual(t, int32(errAuthorizationSuccess), status, "a right that does not exist must not be granted")
+}
+
+func TestMechanismAvailable(t *testing.T) {
+	assert.True(t, mechanismAvailable(), "the trampoline exists on every macOS")
+}
+
+// The one-shot's report is what stands in for an exit status here, so a run that
+// says nothing must not read as success.
+func TestCheckApplied(t *testing.T) {
+	require.NoError(t, checkApplied(AppliedMarker+"\n"), "the report the one-shot prints")
+	require.NoError(t, checkApplied("some warning\n"+AppliedMarker+"\n"), "the report after other output")
+
+	assert.Error(t, checkApplied(""), "a run that printed nothing did not apply the change")
+	assert.Error(t, checkApplied("dyld: library not loaded\n"), "output that is not the report")
+}
+
+// A panic out of the FFI layer has to reach the caller as "no mechanism", which is
+// the outcome that offers the user the command instead of taking the window down.
+func TestGuardTurnsAPanicIntoUnavailable(t *testing.T) {
+	err := guard("pretending to call something", func() error {
+		panic("purego: signature it cannot map")
+	})
+
+	require.ErrorIs(t, err, ErrUnavailable, "a panic must read as a missing mechanism")
+	assert.Contains(t, err.Error(), "pretending to call something", "what panicked")
+}
+
+// guard wraps every darwin path, so what a caller switches on has to survive it.
+func TestGuardPassesErrorsThrough(t *testing.T) {
+	sentinel := errors.New("the call itself failed")
+	assert.ErrorIs(t, guard("calling", func() error { return sentinel }), sentinel,
+		"the error it was given")
+	assert.ErrorIs(t, guard("calling", func() error { return ErrDeclined }), ErrDeclined,
+		"a declined prompt stays declined")
+	assert.NoError(t, guard("calling", func() error { return nil }), "a call that worked")
+}

client/internal/elevate/run_unix.go

@@ -0,0 +1,117 @@
+//go:build linux
+
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"os"
+	"os/exec"
+	"strings"
+)
+
+// pkexec exit codes that are about the authorization rather than about the program
+// we asked it to run. The manual page reserves both.
+const (
+	// exitDismissed is returned when the user dismissed the authentication
+	// dialog.
+	exitDismissed = 126
+	// exitNotAuthorized is returned when the authorization was not obtained. That
+	// covers the user saying no as well as pkexec having had nobody to ask: see
+	// noAgentMarkers.
+	exitNotAuthorized = 127
+)
+
+// exitNotAuthorized covers three different endings that only pkexec's own words
+// tell apart, so they are matched here. Read with LC_ALL=C so the words are the
+// ones written below.
+//
+// refusedMarker is a refusal: the user said no, gave up on the password, or holds
+// an account that may not elevate at all.
+const refusedMarker = "Not authorized"
+
+// noAgentMarkers say pkexec had no way to ask: no agent registered for the
+// session, and no controlling terminal for the textual agent it falls back to.
+var noAgentMarkers = []string{"authentication agent", "controlling terminal"}
+
+// run asks polkit to run self as root. pkexec hands the request to the session's
+// polkit agent, which is what prompts and what collects any password; we see only
+// its verdict.
+//
+// The environment is otherwise deliberately not passed through: pkexec clears it
+// bar a small allowlist, and the one-shot needs nothing from it.
+func run(ctx context.Context, self string, args []string) error {
+	pkexec, err := exec.LookPath("pkexec")
+	if err != nil {
+		return fmt.Errorf("%w: pkexec is not installed", ErrUnavailable)
+	}
+
+	cmd := exec.CommandContext(ctx, pkexec, append([]string{self}, args...)...)
+	// C locale so pkexec's own diagnostics are the ones noAgentMarkers knows.
+	cmd.Env = append(os.Environ(), "LC_ALL=C")
+	var stderr strings.Builder
+	cmd.Stderr = &stderr
+	// The one-shot reports itself on stdout for macOS's sake, where there is no
+	// exit status to read. Here there is one, so that line is noise.
+	cmd.Stdout = io.Discard
+
+	err = cmd.Run()
+	if err == nil {
+		return nil
+	}
+
+	var exitErr *exec.ExitError
+	if !errors.As(err, &exitErr) {
+		return fmt.Errorf("run pkexec: %w", err)
+	}
+
+	// Matched against everything pkexec said, reported as one line: a complaint
+	// that is not the first thing printed still has to be recognised, and reading
+	// it as a refusal would swallow it.
+	full := stderr.String()
+	out := firstLine(full)
+
+	switch exitErr.ExitCode() {
+	case exitDismissed:
+		return ErrDeclined
+	case exitNotAuthorized:
+		return notAuthorized(full, out)
+	default:
+		return fmt.Errorf("elevated netbird exited with %d: %s", exitErr.ExitCode(), out)
+	}
+}
+
+// notAuthorized sorts out the three endings pkexec reports as exitNotAuthorized.
+//
+// It also returns that code when the authorization succeeded and it then could
+// not run the program, so a refusal has to be recognised rather than assumed:
+// reading every one of these as "the user said no" would revert the control in
+// silence on a host where elevation is broken.
+func notAuthorized(full, out string) error {
+	switch {
+	case hasAny(full, noAgentMarkers):
+		return fmt.Errorf("%w: polkit had no way to ask: %s", ErrUnavailable, out)
+	case out == noOutput, strings.Contains(full, refusedMarker):
+		// The user said no, which needs no message; that an account barred from
+		// elevating altogether lands here too is why the reason is kept.
+		return fmt.Errorf("%w: %s", ErrDeclined, out)
+	default:
+		return fmt.Errorf("pkexec could not run elevated netbird: %s", out)
+	}
+}
+
+func hasAny(s string, markers []string) bool {
+	for _, marker := range markers {
+		if strings.Contains(s, marker) {
+			return true
+		}
+	}
+	return false
+}
+
+func mechanismAvailable() bool {
+	_, err := exec.LookPath("pkexec")
+	return err == nil
+}

client/internal/elevate/run_unix_test.go

@@ -0,0 +1,110 @@
+//go:build linux
+
+package elevate
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// fakePkexec puts a pkexec on PATH that exits with the given code, so the
+// mapping from polkit's exit codes onto our errors can be exercised without a
+// polkit agent.
+func fakePkexec(t *testing.T, exitCode int, stderr string) {
+	t.Helper()
+
+	dir := t.TempDir()
+	script := fmt.Sprintf("#!/bin/sh\necho %s >&2\nexit %d\n", shellQuote(stderr), exitCode)
+	require.NoError(t, os.WriteFile(filepath.Join(dir, "pkexec"), []byte(script), 0o700), "write the fake pkexec")
+	t.Setenv("PATH", dir)
+}
+
+func shellQuote(s string) string {
+	return "'" + strings.ReplaceAll(s, "'", `'\''`) + "'"
+}
+
+func TestRunMapsPkexecExitCodes(t *testing.T) {
+	tests := []struct {
+		name     string
+		exitCode int
+		stderr   string
+		wantErr  error
+	}{
+		{name: "applied", exitCode: 0},
+		{
+			name:     "dialog dismissed",
+			exitCode: exitDismissed,
+			stderr:   "Error executing command as another user: Request dismissed",
+			wantErr:  ErrDeclined,
+		},
+		{
+			// What a graphical agent reports for a cancelled prompt. Not a
+			// failure: the user was asked and answered.
+			name:     "prompt cancelled",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error executing command as another user: Not authorized",
+			wantErr:  ErrDeclined,
+		},
+		{
+			// The same status, but pkexec never got to ask anybody.
+			name:     "no agent and no terminal to fall back on",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error creating textual authentication agent: Error opening current controlling terminal for the process (`/dev/tty'): No such device or address",
+			wantErr:  ErrUnavailable,
+		},
+		{
+			// And the same status again once the authorization succeeded and
+			// pkexec could not run what it had been authorized to run. Reading
+			// that as a refusal would revert the control in silence on a host
+			// where elevation is broken.
+			name:     "authorized but not runnable",
+			exitCode: exitNotAuthorized,
+			stderr:   "Error executing command as another user: No such file or directory",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			fakePkexec(t, tt.exitCode, tt.stderr)
+
+			err := run(context.Background(), "/nonexistent/netbird-ui", []string{"--flag"})
+			switch {
+			case tt.wantErr != nil:
+				require.ErrorIs(t, err, tt.wantErr, "exit %d said %q", tt.exitCode, tt.stderr)
+			case tt.exitCode == 0:
+				require.NoError(t, err, "a pkexec that exited cleanly applied the change")
+			default:
+				require.Error(t, err, "exit %d said %q", tt.exitCode, tt.stderr)
+				assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
+				assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
+			}
+		})
+	}
+}
+
+// An exit code that is not polkit's is the one-shot's own failure, and has to
+// stay distinguishable from a declined prompt: the caller reports it.
+func TestRunReportsOneShotFailure(t *testing.T) {
+	fakePkexec(t, 3, "the one-shot said no")
+
+	err := run(context.Background(), "/nonexistent/netbird-ui", nil)
+
+	require.Error(t, err, "a one-shot that failed is not a prompt that was answered")
+	assert.NotErrorIs(t, err, ErrDeclined, "not the user's answer")
+	assert.NotErrorIs(t, err, ErrUnavailable, "not a missing mechanism")
+}
+
+func TestRunWithoutPkexecIsUnavailable(t *testing.T) {
+	t.Setenv("PATH", t.TempDir())
+
+	err := run(context.Background(), "/nonexistent/netbird-ui", nil)
+	require.ErrorIs(t, err, ErrUnavailable, "no pkexec means no mechanism")
+	assert.False(t, mechanismAvailable(), "mechanismAvailable without pkexec on PATH")
+}

client/internal/elevate/run_unsupported.go

@@ -0,0 +1,19 @@
+//go:build !windows && !darwin && !linux
+
+package elevate
+
+import "context"
+
+// run reports that this platform has no elevation prompt to drive.
+//
+// The desktop app is the only caller and is not built for any of these: mobile
+// and WASM have no local user to ask, and the FreeBSD client ships without a UI.
+// pkexec would be the mechanism there, and run_unix.go is what to widen if that
+// changes.
+func run(context.Context, string, []string) error {
+	return ErrUnavailable
+}
+
+func mechanismAvailable() bool {
+	return false
+}

client/internal/elevate/run_windows.go

@@ -0,0 +1,187 @@
+package elevate
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"runtime"
+	"unsafe"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sys/windows"
+)
+
+const (
+	// seeMaskNoCloseProcess keeps the started process's handle open in
+	// hProcess so we can wait for it.
+	seeMaskNoCloseProcess = 0x00000040
+	// seeMaskNoAsync makes ShellExecuteExW finish its work before returning,
+	// which it must when the calling thread does not pump messages.
+	seeMaskNoAsync = 0x00000100
+	// seeMaskFlagNoUI suppresses the shell's own error dialogs; the UAC consent
+	// dialog is not one of them and still appears.
+	seeMaskFlagNoUI = 0x00000400
+
+	// swHide: the one-shot has no window to show.
+	swHide = 0
+)
+
+// shellExecuteInfoW mirrors SHELLEXECUTEINFOW. The field order and Go's own
+// padding match the C layout on both 386 and amd64.
+type shellExecuteInfoW struct {
+	cbSize         uint32
+	fMask          uint32
+	hwnd           windows.HWND
+	lpVerb         *uint16
+	lpFile         *uint16
+	lpParameters   *uint16
+	lpDirectory    *uint16
+	nShow          int32
+	hInstApp       windows.Handle
+	lpIDList       uintptr
+	lpClass        *uint16
+	hkeyClass      windows.Handle
+	dwHotKey       uint32
+	hIconOrMonitor windows.Handle
+	hProcess       windows.Handle
+}
+
+var (
+	shell32            = windows.NewLazySystemDLL("shell32.dll")
+	procShellExecuteEx = shell32.NewProc("ShellExecuteExW")
+)
+
+// run starts self elevated with the "runas" verb, which is what raises the UAC
+// consent dialog, and waits for it to finish. Windows decides whether consent is
+// enough or an administrator's credentials are needed, and collects them itself.
+func run(ctx context.Context, self string, args []string) error {
+	verb, err := windows.UTF16PtrFromString("runas")
+	if err != nil {
+		return fmt.Errorf("encode verb: %w", err)
+	}
+	file, err := windows.UTF16PtrFromString(self)
+	if err != nil {
+		return fmt.Errorf("encode %s: %w", self, err)
+	}
+	params, err := windows.UTF16PtrFromString(windows.ComposeCommandLine(args))
+	if err != nil {
+		return fmt.Errorf("encode arguments: %w", err)
+	}
+
+	info := shellExecuteInfoW{
+		fMask:        seeMaskNoCloseProcess | seeMaskNoAsync | seeMaskFlagNoUI,
+		hwnd:         ownerWindow(),
+		lpVerb:       verb,
+		lpFile:       file,
+		lpParameters: params,
+		nShow:        swHide,
+	}
+	info.cbSize = uint32(unsafe.Sizeof(info))
+
+	process, err := shellExecute(&info)
+	if err != nil {
+		return err
+	}
+	defer func() {
+		if err := windows.CloseHandle(process); err != nil {
+			log.Debugf("close elevated process handle: %v", err)
+		}
+	}()
+
+	return waitForProcess(ctx, process)
+}
+
+// shellExecute performs the call itself. ShellExecuteExW wants COM initialised on
+// the calling thread, so the goroutine is pinned to one for the duration and COM
+// is set up on it; an "already initialised, different mode" answer is fine,
+// because then somebody else has done it for us.
+func shellExecute(info *shellExecuteInfoW) (windows.Handle, error) {
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+
+	switch err := windows.CoInitializeEx(0, windows.COINIT_APARTMENTTHREADED); {
+	case err == nil, isHResult(err, windows.S_FALSE):
+		// Ours, or already initialised in the same mode: either way this call
+		// counts and has to be balanced.
+		defer windows.CoUninitialize()
+	case isHResult(err, windows.RPC_E_CHANGED_MODE):
+		// The thread is already in the other apartment model. ShellExecuteExW
+		// works there too, and there is nothing of ours to balance.
+	default:
+		return 0, fmt.Errorf("initialise COM: %w", err)
+	}
+
+	ret, _, lastErr := procShellExecuteEx.Call(uintptr(unsafe.Pointer(info)))
+	if ret != 0 {
+		return info.hProcess, nil
+	}
+
+	if errors.Is(lastErr, windows.ERROR_CANCELLED) {
+		return 0, ErrDeclined
+	}
+	return 0, fmt.Errorf("run elevated: %w", lastErr)
+}
+
+// ownerWindow returns this process's foreground window, and 0 when the window in
+// front belongs to somebody else or cannot be attributed. ShellExecuteExW takes it
+// as the parent for the UI it raises, which is what keeps the consent dialog in
+// front of the window the user was just clicking in instead of behind it. It is
+// also what a remote-desktop session needs to place the dialog at all when the
+// secure desktop is switched off.
+func ownerWindow() windows.HWND {
+	hwnd := windows.GetForegroundWindow()
+	if hwnd == 0 {
+		return 0
+	}
+
+	var pid uint32
+	if _, err := windows.GetWindowThreadProcessId(hwnd, &pid); err != nil {
+		log.Debugf("cannot attribute the foreground window, raising the prompt without an owner: %v", err)
+		return 0
+	}
+	if pid != windows.GetCurrentProcessId() {
+		return 0
+	}
+	return hwnd
+}
+
+// isHResult reports whether err carries the given HRESULT. CoInitializeEx
+// returns its HRESULT as an Errno, so the comparison is on the raw value.
+func isHResult(err error, hresult windows.Handle) bool {
+	var errno windows.Errno
+	return errors.As(err, &errno) && uintptr(errno) == uintptr(hresult)
+}
+
+func waitForProcess(ctx context.Context, process windows.Handle) error {
+	// The wait is interruptible so a cancelled context stops us waiting on a
+	// consent dialog nobody is going to answer. The elevated process is not
+	// ours to kill, and it either applies the change or does not.
+	for {
+		event, err := windows.WaitForSingleObject(process, 250)
+		if err != nil {
+			return fmt.Errorf("wait for the elevated process: %w", err)
+		}
+		if event == uint32(windows.WAIT_OBJECT_0) {
+			break
+		}
+		if err := ctx.Err(); err != nil {
+			return err
+		}
+	}
+
+	var code uint32
+	if err := windows.GetExitCodeProcess(process, &code); err != nil {
+		return fmt.Errorf("read the elevated process's exit code: %w", err)
+	}
+	if code != 0 {
+		return fmt.Errorf("elevated netbird exited with %d", code)
+	}
+	return nil
+}
+
+// mechanismAvailable is true on Windows: UAC prompts for consent when the user
+// is an administrator and for an administrator's credentials when they are not,
+// so there is always something to ask.
+func mechanismAvailable() bool {
+	return true
+}

client/internal/elevate/trusted.go

@@ -0,0 +1,40 @@
+package elevate
+
+import (
+	"fmt"
+	"os"
+	"path/filepath"
+)
+
+// trustedSelf returns the path of this executable, provided it is one we are
+// willing to have run as root.
+//
+// The check is what keeps elevation from becoming a way to launder someone
+// else's code into a root process: the user consents to NetBird being elevated,
+// having been shown NetBird's name, so what runs must be the file NetBird was
+// installed as and not something a third party could have swapped for it. An
+// executable only its owner can write is that; anything wider is refused, and
+// the caller falls back to showing the command instead.
+//
+// The owner writing to their own executable is not part of that threat: code
+// running as the user can already prompt them for anything, and could just as
+// well ask them to run the command by hand. What matters is that no *other*
+// unprivileged account can reach it.
+func trustedSelf() (string, error) {
+	exe, err := os.Executable()
+	if err != nil {
+		return "", fmt.Errorf("locate this executable: %w", err)
+	}
+
+	// Resolve symlinks so the checks below apply to the file that would actually
+	// be executed, not to a link somebody else may control.
+	resolved, err := filepath.EvalSymlinks(exe)
+	if err != nil {
+		return "", fmt.Errorf("resolve %s: %w", exe, err)
+	}
+
+	if err := checkOnlyOwnerWritable(resolved); err != nil {
+		return "", fmt.Errorf("%w: %s cannot be trusted to run as root: %w", ErrUnavailable, resolved, err)
+	}
+	return resolved, nil
+}

client/internal/elevate/trusted_group_darwin.go

@@ -0,0 +1,10 @@
+package elevate
+
+// adminWriteGIDs are the groups whose write access to an executable does not
+// widen who could authorize elevating it.
+//
+// macOS installs applications as root:admin, mode 0775, /Applications included,
+// so requiring owner-only write would reject every normal install. Group admin
+// (gid 80) is exactly the set of accounts that can answer the authentication
+// dialog, so its write access grants nothing the prompt would not.
+var adminWriteGIDs = []uint32{0, 80}

client/internal/elevate/trusted_group_unix.go

@@ -0,0 +1,9 @@
+//go:build !windows && !darwin
+
+package elevate
+
+// adminWriteGIDs are the groups whose write access to an executable does not
+// widen who could authorize elevating it. Only root's own group qualifies here:
+// a distribution installs into root-owned directories, and there is no
+// system-wide administrators group that both writes them and answers polkit.
+var adminWriteGIDs = []uint32{0}

client/internal/elevate/trusted_unix.go

@@ -0,0 +1,119 @@
+//go:build !windows
+
+package elevate
+
+import (
+	"errors"
+	"fmt"
+	"os"
+	"path/filepath"
+	"slices"
+	"strconv"
+	"syscall"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/getent"
+)
+
+// checkOnlyOwnerWritable reports an error unless path, and every directory leading
+// to it, is owned by either root or this user and writable by nobody who could not
+// already act as its owner. A writable directory is as good as a writable file,
+// since anything in it can be replaced, so the whole chain is checked.
+func checkOnlyOwnerWritable(path string) error {
+	self := uint32(os.Getuid())
+
+	for dir := path; ; dir = filepath.Dir(dir) {
+		info, err := os.Lstat(dir)
+		if err != nil {
+			return fmt.Errorf("stat %s: %w", dir, err)
+		}
+
+		stat, ok := info.Sys().(*syscall.Stat_t)
+		if !ok {
+			return errors.New("file ownership is unavailable on this platform")
+		}
+		if stat.Uid != 0 && stat.Uid != self {
+			return fmt.Errorf("%s is owned by uid %d, neither root nor this user", dir, stat.Uid)
+		}
+
+		if err := checkWriteBits(dir, info, stat.Uid, stat.Gid); err != nil {
+			return err
+		}
+
+		if parent := filepath.Dir(dir); parent == dir {
+			return nil
+		}
+	}
+}
+
+func checkWriteBits(path string, info os.FileInfo, uid, gid uint32) error {
+	// On a directory the sticky bit stands in for the write bits: whoever may
+	// write there still cannot replace an entry they do not own, which is the
+	// only thing that would matter to us. /tmp is the usual example.
+	sticky := info.IsDir() && info.Mode()&os.ModeSticky != 0
+
+	return writeBitsAllow(path, info.Mode().Perm(), sticky, groupWriteAllowed(uid, gid))
+}
+
+// writeBitsAllow decides on the permission bits alone, given whether the group's
+// write access has been vouched for.
+func writeBitsAllow(path string, perm os.FileMode, sticky, groupAllowed bool) error {
+	if sticky {
+		return nil
+	}
+	if perm&0o020 != 0 && !groupAllowed {
+		return fmt.Errorf("%s is writable by a group with members other than its owner (%v)", path, perm)
+	}
+	if perm&0o002 != 0 {
+		return fmt.Errorf("%s is world-writable (%v)", path, perm)
+	}
+	return nil
+}
+
+// groupWriteAllowed reports whether a group's write access to a file owned by uid
+// puts it in reach of anyone who could not already act as that owner.
+//
+// Two ways it does not. A group in adminWriteGIDs holds the accounts that can
+// answer the elevation prompt anyway. And a user private group is how Debian,
+// Ubuntu and Fedora ship: their umask of 002 makes a home directory and
+// everything built in it group-writable, so refusing that would refuse every
+// build not installed from a package.
+func groupWriteAllowed(uid, gid uint32) bool {
+	if slices.Contains(adminWriteGIDs, gid) {
+		return true
+	}
+
+	group, err := getent.LookupGroupID(strconv.FormatUint(uint64(gid), 10))
+	if err != nil {
+		log.Debugf("cannot look up group %d, treating it as shared: %v", gid, err)
+		return false
+	}
+	owner, err := getent.LookupUserID(strconv.FormatUint(uint64(uid), 10))
+	if err != nil {
+		log.Debugf("cannot look up uid %d, treating its group as shared: %v", uid, err)
+		return false
+	}
+
+	if group.Name != owner.Username {
+		return false
+	}
+	return !groupHasOtherMembers(group.Name, owner.Username)
+}
+
+// groupHasOtherMembers reports whether the group lists a member besides owner.
+//
+// Sharing the owner's name is what a user private group is recognised by, and it
+// says nothing about who is in it: a group that has since gained a member is
+// still named that way, and that member can write whatever the group can. So the
+// membership is read rather than assumed. A group whose members cannot be
+// listed, because no source on this host describes it, is treated as shared:
+// the name alone cannot vouch for who writes through it.
+func groupHasOtherMembers(name, owner string) bool {
+	members, err := getent.GroupMembers(name)
+	if err != nil {
+		log.Debugf("cannot list the members of group %q, treating it as shared: %v", name, err)
+		return true
+	}
+	return slices.ContainsFunc(members, func(member string) bool { return member != owner })
+}

client/internal/elevate/trusted_unix_test.go

@@ -0,0 +1,148 @@
+//go:build !windows
+
+package elevate
+
+import (
+	"os"
+	"os/user"
+	"path/filepath"
+	"strconv"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// ownerOnlyDir is t.TempDir() with the write bits tightened. testing creates its
+// numbered directory with 0777 minus the umask, so under the common 002 umask it
+// is group-writable and would fail the check under test on its own.
+func ownerOnlyDir(t *testing.T) string {
+	t.Helper()
+	dir := t.TempDir()
+	require.NoError(t, os.Chmod(dir, 0o755), "tighten the temporary directory")
+	return dir
+}
+
+// writeExecutable creates a plain executable file, the shape trustedSelf checks.
+func writeExecutable(t *testing.T, dir string) string {
+	t.Helper()
+	path := filepath.Join(dir, "netbird-ui")
+	require.NoError(t, os.WriteFile(path, []byte("#!/bin/sh\n"), 0o755), "write the executable")
+	require.NoError(t, os.Chmod(path, 0o755), "set the executable's mode")
+	return path
+}
+
+func TestCheckOnlyOwnerWritableAcceptsOwnerOnly(t *testing.T) {
+	err := checkOnlyOwnerWritable(writeExecutable(t, ownerOnlyDir(t)))
+	assert.NoError(t, err, "an owner-only writable executable is trustworthy")
+}
+
+func TestCheckOnlyOwnerWritableRejectsWorldWritableFile(t *testing.T) {
+	path := writeExecutable(t, ownerOnlyDir(t))
+	require.NoError(t, os.Chmod(path, 0o777), "make the executable world-writable")
+
+	assert.Error(t, checkOnlyOwnerWritable(path), "a world-writable executable must be refused")
+}
+
+// The permission policy on its own, without a filesystem to arrange: whether the
+// group has been vouched for is the only thing that makes group write acceptable.
+func TestWriteBitsAllow(t *testing.T) {
+	tests := []struct {
+		name         string
+		perm         os.FileMode
+		sticky       bool
+		groupAllowed bool
+		wantErr      bool
+	}{
+		{name: "owner only", perm: 0o755},
+		{name: "group write in a private group", perm: 0o775, groupAllowed: true},
+		{name: "group write in a shared group", perm: 0o775, wantErr: true},
+		{name: "world write", perm: 0o777, groupAllowed: true, wantErr: true},
+		{name: "world write on a sticky directory", perm: 0o777, sticky: true},
+		{name: "group write on a sticky directory", perm: 0o775, sticky: true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := writeBitsAllow("/path", tt.perm, tt.sticky, tt.groupAllowed)
+			if tt.wantErr {
+				assert.Error(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
+				return
+			}
+			assert.NoError(t, err, "perm %v, sticky %v, group allowed %v", tt.perm, tt.sticky, tt.groupAllowed)
+		})
+	}
+}
+
+// A build under a home directory on a distribution with a 002 umask, which is what
+// a locally built or tarball-installed binary looks like. Its group has no members
+// but its owner, so it is as good as owner-only.
+//
+// Whether this host is such a distribution is read from the environment rather than
+// from groupWriteAllowed: asking the function under test whether to run would let
+// it skip its own coverage away if it regressed to refusing everything.
+func TestCheckOnlyOwnerWritableAcceptsOwnPrivateGroup(t *testing.T) {
+	requirePrivatePrimaryGroup(t)
+
+	dir := ownerOnlyDir(t)
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o775), "make the directory group-writable")
+	require.NoError(t, os.Chmod(path, 0o775), "make the executable group-writable")
+
+	err := checkOnlyOwnerWritable(path)
+	assert.NoError(t, err, "group write in the owner's own private group reaches nobody else")
+}
+
+// A group whose membership no source can answer for is treated as shared: the
+// private-group allowance must not stand on a name nobody can vouch for. The
+// membership listing itself lives in the getent package and is tested there.
+func TestGroupHasOtherMembersRejectsAnUnknownGroup(t *testing.T) {
+	assert.True(t, groupHasOtherMembers("nonexistent_group_xyzzy_12345", "vma"),
+		"a group no source describes")
+}
+
+// A writable directory is as good as a writable file: whoever can write the
+// directory can put a different binary at the same path.
+func TestCheckOnlyOwnerWritableRejectsWritableDirectory(t *testing.T) {
+	dir := filepath.Join(ownerOnlyDir(t), "bin")
+	require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o777), "make the directory world-writable")
+
+	assert.Error(t, checkOnlyOwnerWritable(path), "an executable in a world-writable directory must be refused")
+}
+
+// A sticky world-writable directory is exempt: the sticky bit is what stops one
+// user replacing another's entries. /tmp is why this matters.
+func TestCheckOnlyOwnerWritableAcceptsStickyDirectory(t *testing.T) {
+	dir := filepath.Join(ownerOnlyDir(t), "sticky")
+	require.NoError(t, os.Mkdir(dir, 0o755), "create the directory")
+	path := writeExecutable(t, dir)
+	require.NoError(t, os.Chmod(dir, 0o777|os.ModeSticky), "make the directory sticky and world-writable")
+
+	err := checkOnlyOwnerWritable(path)
+	assert.NoError(t, err, "the sticky bit stops another user replacing the executable")
+}
+
+func TestCheckOnlyOwnerWritableRejectsMissingFile(t *testing.T) {
+	err := checkOnlyOwnerWritable(filepath.Join(ownerOnlyDir(t), "absent"))
+	assert.Error(t, err, "an executable that is not there must be refused")
+}
+
+// requirePrivatePrimaryGroup skips unless this user's primary group is their own,
+// which is what the user-private-group allowance is about.
+func requirePrivatePrimaryGroup(t *testing.T) {
+	t.Helper()
+
+	self, err := user.Current()
+	require.NoError(t, err, "look up the test user")
+	group, err := user.LookupGroupId(strconv.Itoa(os.Getgid()))
+	require.NoError(t, err, "look up the test user's primary group")
+
+	if group.Name != self.Username {
+		t.Skipf("the test user's primary group is %q, not their own, so there is nothing to assert here", group.Name)
+	}
+	if groupHasOtherMembers(group.Name, self.Username) {
+		t.Skipf("group %q has other members, so it is not a private group", group.Name)
+	}
+}

client/internal/elevate/trusted_windows.go

@@ -0,0 +1,215 @@
+package elevate
+
+import (
+	"errors"
+	"fmt"
+	"path/filepath"
+	"slices"
+	"unsafe"
+
+	"golang.org/x/sys/windows"
+)
+
+const (
+	// fileDeleteChild is FILE_DELETE_CHILD, which x/sys does not define: the
+	// right to delete an entry of a directory without holding DELETE on it.
+	fileDeleteChild = 0x00000040
+
+	// accessAllowedCallbackACEType is an allow ACE with a condition appended to
+	// the ACCESS_ALLOWED_ACE layout, so its trustee is still at SidStart.
+	accessAllowedCallbackACEType = 0x9
+
+	// The allow ACE types that carry object GUIDs ahead of the trustee, so the
+	// SID is not at SidStart. They occur on directory-service objects rather
+	// than files, and are refused rather than skipped: see aceTrustee.
+	accessAllowedObjectACEType         = 0x5
+	accessAllowedCallbackObjectACEType = 0xB
+)
+
+// fileWriteAccess are the rights that let a trustee rewrite or replace a file,
+// or take it over and then do so.
+const fileWriteAccess = windows.FILE_WRITE_DATA | windows.FILE_APPEND_DATA |
+	windows.DELETE | windows.WRITE_DAC | windows.WRITE_OWNER |
+	windows.GENERIC_WRITE | windows.GENERIC_ALL
+
+// dirWriteAccess are the rights over a directory that let a trustee replace an
+// entry somebody else owns. Creating a new entry is not one of them, which is
+// what the Unix sticky bit says in one bit: the root of every volume grants
+// BUILTIN\Users the right to add directories under it, and that reaches nothing
+// already there.
+const dirWriteAccess = fileDeleteChild | windows.DELETE |
+	windows.WRITE_DAC | windows.WRITE_OWNER | windows.GENERIC_ALL
+
+// trustedInstallerSID owns much of what Windows itself installs. x/sys has no
+// well-known constant for it.
+const trustedInstallerSID = "S-1-5-80-956008885-3418522649-1831038044-1853292631-2271478464"
+
+// checkOnlyOwnerWritable reports an error unless path, and every directory
+// leading to it, is owned by an account that can elevate (or by this user) and
+// grants write access to nobody else. A writable directory is as good as a
+// writable file, since an entry in it can be replaced, so the whole chain is
+// checked.
+func checkOnlyOwnerWritable(path string) error {
+	owners, err := trustedOwners()
+	if err != nil {
+		return err
+	}
+	writers, err := trustedWriters(owners)
+	if err != nil {
+		return err
+	}
+
+	writeAccess := windows.ACCESS_MASK(fileWriteAccess)
+	for target := path; ; target = filepath.Dir(target) {
+		if err := checkSecurity(target, writeAccess, owners, writers); err != nil {
+			return err
+		}
+		if parent := filepath.Dir(target); parent == target {
+			return nil
+		}
+		writeAccess = dirWriteAccess
+	}
+}
+
+// trustedOwners are the accounts we accept as the owner of the executable and of
+// the directories above it: the ones that can already answer the UAC prompt,
+// plus this user, whose own executable is theirs to write. Code running as the
+// user could prompt them for anything anyway; what matters is that no *other*
+// unprivileged account can reach it.
+func trustedOwners() ([]*windows.SID, error) {
+	self, err := currentUserSID()
+	if err != nil {
+		return nil, err
+	}
+
+	owners := []*windows.SID{self}
+	for _, wellKnown := range []windows.WELL_KNOWN_SID_TYPE{
+		windows.WinLocalSystemSid,
+		windows.WinBuiltinAdministratorsSid,
+	} {
+		sid, err := windows.CreateWellKnownSid(wellKnown)
+		if err != nil {
+			return nil, fmt.Errorf("build well-known SID %d: %w", wellKnown, err)
+		}
+		owners = append(owners, sid)
+	}
+
+	installer, err := windows.StringToSid(trustedInstallerSID)
+	if err != nil {
+		return nil, fmt.Errorf("parse TrustedInstaller SID: %w", err)
+	}
+	return append(owners, installer), nil
+}
+
+// trustedWriters are the trustees whose write access does not widen who could
+// decide what runs behind the prompt. The owners, and CREATOR OWNER, which
+// resolves to the object's owner and is therefore already vetted.
+func trustedWriters(owners []*windows.SID) ([]*windows.SID, error) {
+	creatorOwner, err := windows.CreateWellKnownSid(windows.WinCreatorOwnerSid)
+	if err != nil {
+		return nil, fmt.Errorf("build the CREATOR OWNER SID: %w", err)
+	}
+	return append(slices.Clone(owners), creatorOwner), nil
+}
+
+func checkSecurity(path string, writeAccess windows.ACCESS_MASK, owners, writers []*windows.SID) error {
+	sd, err := windows.GetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
+		windows.OWNER_SECURITY_INFORMATION|windows.DACL_SECURITY_INFORMATION)
+	if err != nil {
+		return fmt.Errorf("read security descriptor of %s: %w", path, err)
+	}
+
+	owner, _, err := sd.Owner()
+	if err != nil {
+		return fmt.Errorf("read owner of %s: %w", path, err)
+	}
+	if !containsSID(owners, owner) {
+		return fmt.Errorf("%s is owned by %s, which is neither this user nor an account that can elevate", path, owner)
+	}
+
+	dacl, _, err := sd.DACL()
+	if err != nil {
+		return fmt.Errorf("read DACL of %s: %w", path, err)
+	}
+	// A NULL DACL grants everyone everything; only an absent security
+	// descriptor would have got us here without one, and neither is trustworthy.
+	if dacl == nil {
+		return fmt.Errorf("%s has no DACL, so it grants write access to everyone", path)
+	}
+
+	return checkDACL(path, dacl, writeAccess, writers)
+}
+
+// checkDACL refuses an ACL that grants write access to a trustee outside
+// writers.
+//
+// An allowlist, because the trustees that must not have it cannot be listed: an
+// ACE naming an ordinary user account hands that account the same power as one
+// naming Everyone, and only the accounts that may hold it are knowable.
+func checkDACL(path string, dacl *windows.ACL, writeAccess windows.ACCESS_MASK, writers []*windows.SID) error {
+	for i := uint32(0); i < uint32(dacl.AceCount); i++ {
+		var ace *windows.ACCESS_ALLOWED_ACE
+		if err := windows.GetAce(dacl, i, &ace); err != nil {
+			return fmt.Errorf("read ACE %d of %s: %w", i, path, err)
+		}
+		// An inherit-only ACE says what children of this object get, not what
+		// this object grants.
+		if ace.Header.AceFlags&windows.INHERIT_ONLY_ACE != 0 {
+			continue
+		}
+		if ace.Mask&writeAccess == 0 {
+			continue
+		}
+		// Only an allow ACE grants anything; a deny ACE narrows what one gave.
+		if !isAllowACE(ace.Header.AceType) {
+			continue
+		}
+
+		trustee, err := aceTrustee(ace)
+		if err != nil {
+			return fmt.Errorf("read the trustee of ACE %d of %s: %w", i, path, err)
+		}
+		if !containsSID(writers, trustee) {
+			return fmt.Errorf("%s grants write access to %s", path, trustee)
+		}
+	}
+	return nil
+}
+
+// isAllowACE reports whether an ACE type grants rights, rather than denying,
+// auditing or labelling them.
+func isAllowACE(aceType uint8) bool {
+	switch aceType {
+	case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType,
+		accessAllowedObjectACEType, accessAllowedCallbackObjectACEType:
+		return true
+	default:
+		return false
+	}
+}
+
+// aceTrustee returns who an allow ACE grants its rights to. An ACE whose trustee
+// cannot be located is an error rather than something to skip past: being unable
+// to read who is being given write access is a refusal.
+func aceTrustee(ace *windows.ACCESS_ALLOWED_ACE) (*windows.SID, error) {
+	switch ace.Header.AceType {
+	case windows.ACCESS_ALLOWED_ACE_TYPE, accessAllowedCallbackACEType:
+		//nolint:gosec // SidStart is the first uint32 of the variable-length SID that follows the ACE header.
+		return (*windows.SID)(unsafe.Pointer(&ace.SidStart)), nil
+	default:
+		return nil, errors.New("an object-type allow ACE does not carry its trustee where we can read it")
+	}
+}
+
+func containsSID(sids []*windows.SID, sid *windows.SID) bool {
+	return slices.ContainsFunc(sids, sid.Equals)
+}
+
+func currentUserSID() (*windows.SID, error) {
+	token := windows.GetCurrentProcessToken()
+	user, err := token.GetTokenUser()
+	if err != nil {
+		return nil, fmt.Errorf("read this process's user: %w", err)
+	}
+	return user.User.Sid, nil
+}

client/internal/elevate/trusted_windows_test.go

@@ -0,0 +1,126 @@
+package elevate
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"golang.org/x/sys/windows"
+)
+
+// A file the test user created under their own profile, which is what a per-user
+// install looks like. The whole chain up to the volume root is walked, so this is
+// also what says the walk does not refuse an ordinary Windows installation: the
+// root of every volume grants BUILTIN\Users rights that are not ours to worry
+// about.
+func TestCheckOnlyOwnerWritableAcceptsOwnFile(t *testing.T) {
+	err := checkOnlyOwnerWritable(writeExecutable(t))
+	assert.NoError(t, err, "a file the test user owns, under directories only administrators can write")
+}
+
+// Write access held by an account that cannot answer the UAC prompt means that
+// account decides what runs behind it, whoever the ACE names. The trustees that
+// must not have it cannot be listed, so the check names the ones that may.
+func TestCheckOnlyOwnerWritableRejectsUntrustedWriters(t *testing.T) {
+	tests := []struct {
+		name      string
+		wellKnown windows.WELL_KNOWN_SID_TYPE
+	}{
+		{name: "everyone", wellKnown: windows.WinWorldSid},
+		{name: "authenticated users", wellKnown: windows.WinAuthenticatedUserSid},
+		{name: "builtin users", wellKnown: windows.WinBuiltinUsersSid},
+		// A service account, which no denylist of the obvious groups would name
+		// and which cannot elevate any more than Everyone can.
+		{name: "local service", wellKnown: windows.WinLocalServiceSid},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			path := writeExecutable(t)
+			grantWrite(t, path, tt.wellKnown)
+
+			assert.Error(t, checkOnlyOwnerWritable(path),
+				"write access for %s must be refused", tt.name)
+		})
+	}
+}
+
+// The masks are the policy: on a file any write reaches its contents, while on a
+// directory only deleting or taking over an entry reaches something already
+// there. Adding an entry does not, which is why the walk survives a volume root.
+func TestWriteAccessMasks(t *testing.T) {
+	assert.NotZero(t, fileWriteAccess&windows.FILE_WRITE_DATA, "writing a file's data reaches its contents")
+	assert.NotZero(t, fileWriteAccess&windows.FILE_APPEND_DATA, "appending to a file reaches its contents")
+
+	assert.Zero(t, dirWriteAccess&windows.FILE_WRITE_DATA, "adding a file to a directory replaces nothing")
+	assert.Zero(t, dirWriteAccess&windows.FILE_APPEND_DATA, "adding a subdirectory replaces nothing")
+	assert.NotZero(t, dirWriteAccess&fileDeleteChild, "deleting an entry replaces it")
+	assert.NotZero(t, dirWriteAccess&windows.DELETE, "deleting the directory takes its entries with it")
+}
+
+func TestIsAllowACE(t *testing.T) {
+	tests := []struct {
+		name    string
+		aceType uint8
+		want    bool
+	}{
+		{name: "allowed", aceType: windows.ACCESS_ALLOWED_ACE_TYPE, want: true},
+		{name: "allowed callback", aceType: accessAllowedCallbackACEType, want: true},
+		{name: "allowed object", aceType: accessAllowedObjectACEType, want: true},
+		{name: "allowed callback object", aceType: accessAllowedCallbackObjectACEType, want: true},
+		{name: "denied", aceType: windows.ACCESS_DENIED_ACE_TYPE},
+		// SYSTEM_AUDIT_ACE_TYPE, which x/sys does not define: an ACE that records
+		// access rather than granting it.
+		{name: "audit", aceType: 0x2},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			assert.Equal(t, tt.want, isAllowACE(tt.aceType), "ACE type %#x", tt.aceType)
+		})
+	}
+}
+
+// writeExecutable creates a plain file under the test's own directory, the shape
+// trustedSelf checks.
+func writeExecutable(t *testing.T) string {
+	t.Helper()
+	path := filepath.Join(t.TempDir(), "netbird-ui.exe")
+	require.NoError(t, os.WriteFile(path, []byte("MZ"), 0o755), "write the executable")
+	return path
+}
+
+// grantWrite replaces the file's DACL with one that grants a well-known trustee
+// everything, keeping the test user's own access so the file stays deletable.
+func grantWrite(t *testing.T, path string, wellKnown windows.WELL_KNOWN_SID_TYPE) {
+	t.Helper()
+
+	trustee, err := windows.CreateWellKnownSid(wellKnown)
+	require.NoError(t, err, "build the trustee SID")
+	self, err := currentUserSID()
+	require.NoError(t, err, "read the test user's SID")
+
+	acl, err := windows.ACLFromEntries([]windows.EXPLICIT_ACCESS{
+		fullControl(self, windows.TRUSTEE_IS_USER),
+		fullControl(trustee, windows.TRUSTEE_IS_WELL_KNOWN_GROUP),
+	}, nil)
+	require.NoError(t, err, "build the ACL")
+
+	require.NoError(t, windows.SetNamedSecurityInfo(path, windows.SE_FILE_OBJECT,
+		windows.DACL_SECURITY_INFORMATION|windows.PROTECTED_DACL_SECURITY_INFORMATION,
+		nil, nil, acl, nil), "set the DACL")
+}
+
+func fullControl(sid *windows.SID, trusteeType uint32) windows.EXPLICIT_ACCESS {
+	return windows.EXPLICIT_ACCESS{
+		AccessPermissions: windows.GENERIC_ALL,
+		AccessMode:        windows.GRANT_ACCESS,
+		Trustee: windows.TRUSTEE{
+			TrusteeForm:  windows.TRUSTEE_IS_SID,
+			TrusteeType:  windows.TRUSTEE_TYPE(trusteeType),
+			TrusteeValue: windows.TrusteeValueFromSID(sid),
+		},
+	}
+}

client/internal/engine.go

@@ -59,6 +59,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/syncstore"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/jobexec"
+	"github.com/netbirdio/netbird/client/netevents"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -136,6 +137,7 @@ type EngineConfig struct {
 	RosenpassPermissive bool
 
 	ServerSSHAllowed              bool
+	RemoteJobsAllowed             bool
 	EnableSSHRoot                 *bool
 	EnableSSHSFTP                 *bool
 	EnableSSHLocalPortForwarding  *bool
@@ -181,6 +183,9 @@ type EngineServices struct {
 	UpdateManager  *updater.Manager
 	ClientMetrics  *metrics.ClientMetrics
 	MetricsCtx     context.Context
+	// NetMgr gates the reconnection loops on OS-reported network
+	// availability; nil disables gating.
+	NetMgr *netevents.Manager
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -204,6 +209,10 @@ type Engine struct {
 	config    *EngineConfig
 	mobileDep MobileDependency
 
+	// netMgr gates the peer reconnection guards on OS-reported network
+	// availability; nil disables gating.
+	netMgr *netevents.Manager
+
 	// STUNs is a list of STUN servers used by ICE
 	STUNs []*stun.URI
 	// TURNs is a list of STUN servers used by ICE
@@ -337,6 +346,7 @@ func NewEngine(
 		syncMsgMux:         &sync.Mutex{},
 		config:             config,
 		mobileDep:          mobileDep,
+		netMgr:             services.NetMgr,
 		STUNs:              []*stun.URI{},
 		TURNs:              []*stun.URI{},
 		networkSerial:      0,
@@ -863,8 +873,7 @@ func (e *Engine) modifyPeers(peersUpdate []*mgmProto.RemotePeerConfig) error {
 	}
 	// third, add the peer connections again
 	for _, p := range modified {
-		err := e.addNewPeer(p)
+		if err := e.addNewPeer(p); err != nil {
-		if err != nil {
 			return err
 		}
 	}
@@ -1251,6 +1260,7 @@ func (e *Engine) applyInfoFlags(info *system.Info) {
 		e.config.EnableSSHLocalPortForwarding,
 		e.config.EnableSSHRemotePortForwarding,
 		e.config.DisableSSHAuth,
+		&e.config.RemoteJobsAllowed,
 	)
 }
 
@@ -1336,6 +1346,13 @@ func (e *Engine) receiveJobEvents() {
 				ID:     msg.ID,
 				Status: mgmProto.JobStatus_failed,
 			}
+			// Remote jobs are an explicit opt-in. When not enabled on this
+			// peer, every job is refused before any work is done.
+			if !e.config.RemoteJobsAllowed {
+				log.Warnf("refusing remote job: remote jobs are not enabled on this peer (enable with --allow-remote-jobs)")
+				resp.Reason = []byte("remote jobs are not enabled on this peer")
+				return &resp
+			}
 			switch params := msg.WorkloadParameters.(type) {
 			case *mgmProto.JobRequest_Bundle:
 				bundleResult, err := e.handleBundle(params.Bundle)
@@ -1365,7 +1382,25 @@ func (e *Engine) receiveJobEvents() {
 }
 
 func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobResponse_Bundle, error) {
-	log.Infof("handle remote debug bundle request: %s", params.String())
+	// The upload URL can carry a host, credentials, or query tokens, so it is
+	// kept out of the info-level line; the full parameters stay available at
+	// debug level for troubleshooting.
+	log.Infof("handle remote debug bundle request: anonymize=%v anonymize_level=%q log_file_count=%d bundle_for=%v bundle_for_time=%d",
+		params.GetAnonymize(), params.GetAnonymizeLevel(), params.GetLogFileCount(), params.GetBundleFor(), params.GetBundleForTime())
+	log.Debugf("remote debug bundle request parameters: %s", params.String())
+
+	// Resolve the upload destination: an MDM override, when set, takes
+	// precedence over the management-supplied URL. Both are validated the same
+	// way; an empty result falls back to the default upload server downstream.
+	uploadURL := params.GetUploadUrl()
+	if override := e.config.ProfileConfig.DebugBundleUploadURL; override != "" {
+		log.Infof("using MDM debug bundle upload URL override instead of the management-supplied value")
+		uploadURL = override
+	}
+	if err := validateBundleUploadURL(uploadURL); err != nil {
+		return nil, err
+	}
+
 	syncResponse, err := e.GetLatestSyncResponse()
 	if err != nil {
 		log.Warnf("get latest sync response: %v", err)
@@ -1393,7 +1428,7 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 
 	waitFor := time.Duration(params.BundleForTime) * time.Minute
 
-	uploadKey, err := e.jobExecutor.BundleJob(e.ctx, bundleDeps, bundleJobParams, waitFor, e.config.ProfileConfig.ManagementURL.String())
+	uploadKey, err := e.jobExecutor.BundleJob(e.ctx, bundleDeps, bundleJobParams, waitFor, e.config.ProfileConfig.ManagementURL.String(), uploadURL)
 	if err != nil {
 		return nil, err
 	}
@@ -1406,6 +1441,16 @@ func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobR
 	return response, nil
 }
 
+// validateBundleUploadURL sanity-checks a management-supplied upload URL for a
+// remote debug bundle job. It delegates to profilemanager.ValidateBundleUploadURL
+// so the executor and the MDM policy override share one definition of the rule
+// (empty accepted; otherwise a well-formed https URL with a host) and cannot
+// drift. The host is deliberately left unconstrained pending a decision on
+// management-directed uploads.
+func validateBundleUploadURL(raw string) error {
+	return profilemanager.ValidateBundleUploadURL(raw)
+}
+
 // receiveManagementEvents connects to the Management Service event stream to receive updates from the management service
 // E.g. when a new peer has been registered and we are allowed to connect to it.
 func (e *Engine) receiveManagementEvents() {
@@ -1486,8 +1531,12 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 		return nil
 	}
 
-	if err := e.connMgr.UpdatedRemoteFeatureFlag(e.ctx, networkMap.GetPeerConfig().GetLazyConnectionEnabled()); err != nil {
+	// Only update the flag when the sync carries a peer config; a nil peer config
-		log.Errorf("failed to update lazy connection feature flag: %v", err)
+	// (e.g. a partial update) must not reset the cached flag to false.
+	if peerConfig := networkMap.GetPeerConfig(); peerConfig != nil {
+		if err := e.connMgr.UpdatedRemoteFeatureFlag(e.ctx, peerConfig.GetLazyConnectionEnabled()); err != nil {
+			log.Errorf("failed to update lazy connection feature flag: %v", err)
+		}
 	}
 
 	if e.firewall != nil {
@@ -1553,8 +1602,7 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	// Ingress forward rules
 	done = e.phase("forward_rules")
-	forwardingRules, err := e.updateForwardRules(networkMap.GetForwardingRules())
+	if _, err := e.updateForwardRules(networkMap.GetForwardingRules()); err != nil {
-	if err != nil {
 		log.Errorf("failed to update forward rules, err: %v", err)
 	}
 	done()
@@ -1572,8 +1620,7 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	// must set the exclude list after the peers are added. Without it the manager can not figure out the peers parameters from the store
 	done = e.phase("lazy_exclude")
-	excludedLazyPeers := e.toExcludedLazyPeers(forwardingRules, remotePeers)
+	e.connMgr.SetExcludeList(e.ctx, e.toExcludedLazyPeers(remotePeers))
-	e.connMgr.SetExcludeList(e.ctx, excludedLazyPeers)
 	done()
 
 	e.networkSerial = serial
@@ -1817,15 +1864,15 @@ func addrToString(addr netip.Addr) string {
 // addNewPeers adds peers that were not know before but arrived from the Management service with the update
 func (e *Engine) addNewPeers(peersUpdate []*mgmProto.RemotePeerConfig) error {
 	for _, p := range peersUpdate {
-		err := e.addNewPeer(p)
+		if err := e.addNewPeer(p); err != nil {
-		if err != nil {
 			return err
 		}
 	}
 	return nil
 }
 
-// addNewPeer add peer if connection doesn't exist
+// addNewPeer add peer if connection doesn't exist. A peer that is not lazy by
+// policy gets an always-active connection instead.
 func (e *Engine) addNewPeer(peerConfig *mgmProto.RemotePeerConfig) error {
 	peerKey := peerConfig.GetWgPubKey()
 	peerIPs := make([]netip.Prefix, 0, len(peerConfig.GetAllowedIps()))
@@ -1860,7 +1907,8 @@ func (e *Engine) addNewPeer(peerConfig *mgmProto.RemotePeerConfig) error {
 		log.Warnf("error adding peer %s to status recorder, got error: %v", peerKey, err)
 	}
 
-	if exists := e.connMgr.AddPeerConn(e.ctx, peerKey, conn); exists {
+	permanent := !e.connMgr.PeerLazyDefault(peerConfig.GetLazyState())
+	if exists := e.connMgr.AddPeerConn(e.ctx, peerKey, conn, permanent); exists {
 		conn.Close(false)
 		return fmt.Errorf("peer already exists: %s", peerKey)
 	}
@@ -1894,6 +1942,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 			PermissiveMode: e.config.RosenpassPermissive,
 		},
 		ICEConfig: e.createICEConfig(),
+		NetMgr:    e.netMgr,
 	}
 
 	serviceDependencies := peer.ServiceDependencies{
@@ -2562,7 +2611,7 @@ func (e *Engine) SetCapture(pc device.PacketCapture) error {
 	}
 
 	afc := capture.NewAFPacketCapture(intf.Name(), sess)
-	if err := afc.Start(); err != nil {
+	if err := afc.Start(); err != nil { //nolint:staticcheck // always errors on non-Linux builds
 		return fmt.Errorf("start AF_PACKET capture on %s: %w", intf.Name(), err)
 	}
 	e.afpacketCapture = afc
@@ -2651,46 +2700,19 @@ func (e *Engine) updateForwardRules(rules []*mgmProto.ForwardingRule) ([]firewal
 	return forwardingRules, nberrors.FormatErrorOrNil(merr)
 }
 
-func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers []*mgmProto.RemotePeerConfig) map[string]bool {
+// toExcludedLazyPeers returns the peers that must have an always-active
+// connection: those that are not lazy by policy (the per-peer lazy state or the
+// account flag, subject to the local override).
+func (e *Engine) toExcludedLazyPeers(peers []*mgmProto.RemotePeerConfig) map[string]bool {
 	excludedPeers := make(map[string]bool)
-
+	for _, p := range peers {
-	// Ingress forward targets: inbound forwarded traffic is initiated remotely and
+		if !e.connMgr.PeerLazyDefault(p.GetLazyState()) {
-	// cannot wake a lazy connection, so the peer routing the target must stay
+			excludedPeers[p.GetWgPubKey()] = true
-	// permanently connected. AllowedIPs are already parsed on the peer conn, so
-	// reuse those typed prefixes instead of re-parsing the network map strings.
-	for _, r := range rules {
-		for _, p := range peers {
-			if e.peerRoutesAddr(p, r.TranslatedAddress) {
-				log.Infof("exclude forwarder peer from lazy connection: %s", p.GetWgPubKey())
-				excludedPeers[p.GetWgPubKey()] = true
-			}
 		}
 	}
-
 	return excludedPeers
 }
 
-// peerRoutesAddr reports whether the peer is a router for addr, matched against
-// the peer's already-parsed AllowedIPs from the store (the same typed value the
-// lazy manager consumes) rather than re-parsing the network map strings.
-func (e *Engine) peerRoutesAddr(p *mgmProto.RemotePeerConfig, addr netip.Addr) bool {
-	prefixes, ok := e.peerStore.AllowedIPs(p.GetWgPubKey())
-	if !ok {
-		return false
-	}
-	return prefixesContain(prefixes, addr)
-}
-
-// prefixesContain reports whether addr falls within any of the prefixes.
-func prefixesContain(prefixes []netip.Prefix, addr netip.Addr) bool {
-	for _, prefix := range prefixes {
-		if prefix.Contains(addr) {
-			return true
-		}
-	}
-	return false
-}
-
 // isChecksEqual checks if two slices of checks are equal.
 func isChecksEqual(checks1, checks2 []*mgmProto.Checks) bool {
 	normalize := func(checks []*mgmProto.Checks) []string {

client/internal/engine_bundle_test.go

@@ -0,0 +1,36 @@
+package internal
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestValidateBundleUploadURL covers the sanity check applied to a
+// management-supplied upload URL before a remote debug bundle is generated.
+func TestValidateBundleUploadURL(t *testing.T) {
+	for _, tc := range []struct {
+		name    string
+		raw     string
+		wantErr bool
+	}{
+		{name: "empty falls back to default", raw: ""},
+		{name: "https with host", raw: "https://upload.debug.netbird.io/upload"},
+		{name: "https self-hosted host", raw: "https://upload.example.com"},
+		{name: "plaintext rejected", raw: "http://upload.example.com", wantErr: true},
+		{name: "missing host rejected", raw: "https:///upload", wantErr: true},
+		{name: "port-only authority rejected", raw: "https://:443", wantErr: true},
+		{name: "non-url scheme rejected", raw: "ftp://upload.example.com", wantErr: true},
+		{name: "garbage rejected", raw: "://not a url", wantErr: true},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			err := validateBundleUploadURL(tc.raw)
+			if tc.wantErr {
+				require.Error(t, err, "an invalid upload URL must be rejected")
+				return
+			}
+			assert.NoError(t, err, "a valid or empty upload URL must be accepted")
+		})
+	}
+}