Gate local metrics settings behind update-settings and MDM policy

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

@@ -5,13 +5,6 @@ on:
   schedule:
     - cron: "0 3 * * *"
   workflow_dispatch:
-    inputs:
-      bedrock_model:
-        description: >-
-          Bedrock inference-profile id to drive the matrix with, exactly as
-          AWS issues it. Leave empty for the Sonnet 4.6 default.
-        required: false
-        default: ""
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -58,9 +51,6 @@ jobs:
           # token (and URL, for gateways) is unset, so partial coverage is fine.
           OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
           ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
-          # Moonshot AI platform key (platform.kimi.ai); drives both Kimi wire
-          # shapes (OpenAI /v1 and Anthropic /anthropic) through kimi_api.
-          KIMI_TOKEN: ${{ secrets.E2E_KIMI_TOKEN }}
           VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
           VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
           OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
@@ -69,8 +59,6 @@ jobs:
           CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
           AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
           AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
-          # Bedrock model override: dispatch input wins, then the repo variable, else the test default.
-          AWS_BEDROCK_MODEL: ${{ inputs.bedrock_model || vars.E2E_AWS_BEDROCK_MODEL }}
           # Vertex (Anthropic-on-Vertex): SA + project required; region defaults
           # to "global", model to a pinned claude snapshot.
           GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}

.github/workflows/frontend-ui.yml

@@ -86,7 +86,7 @@ jobs:
             ${{ runner.os }}-pnpm-
 
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile --ignore-scripts
+        run: pnpm install --frozen-lockfile
 
       - name: Generate Wails bindings
         run: pnpm run bindings

.github/workflows/golangci-lint.yml

@@ -45,7 +45,7 @@ jobs:
             display_name: Linux
     name: ${{ matrix.display_name }}
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 25
+    timeout-minutes: 15
     steps:
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
@@ -79,4 +79,4 @@ jobs:
           skip-cache: true
           skip-save-cache: true
           cache-invalidation-interval: 0
-          args: --timeout=20m
+          args: --timeout=12m

.goreleaser.yaml

@@ -273,8 +273,8 @@ dockers_v2:
        - netbirdio/netbird
        - ghcr.io/netbirdio/netbird
      tags:
-       - "{{ .Version }}-rootless"
-       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}rootless-latest{{ end }}"
+       - "v{{ .Version }}-rootless"
+       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: client/Dockerfile-rootless
      extra_files:
        - client/netbird-entrypoint.sh

.goreleaser_ui.yaml

@@ -24,8 +24,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-amd64
     dir: client/ui
@@ -41,8 +39,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-arm64
     dir: client/ui
@@ -59,8 +55,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 archives:
   - id: linux-arch

.goreleaser_ui_darwin.yaml

@@ -29,8 +29,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 universal_binaries:
   - id: netbird-ui-darwin

client/android/client.go

@@ -75,24 +75,6 @@ type Client struct {
 	connectClient *internal.ConnectClient
 	config        *profilemanager.Config
 	cacheDir      string
-
-	stateChangeMu    sync.Mutex
-	stateChangeSubID string
-	eventSub         *peer.EventSubscription
-	// Closed to stop the watch goroutines from delivering buffered items to a
-	// listener that has been removed or replaced. See stopStateChangeWatchLocked.
-	stateChangeDone chan struct{}
-
-	// Latched "the server wants an interactive login": survives the engine
-	// restarts that replace the run loop's context state. See Client.Status.
-	// Guarded by loginRequiredMu together with loginCleared, which counts
-	// clears so a stale observation cannot re-latch over one.
-	loginRequiredMu sync.Mutex
-	loginRequired   bool
-	loginCleared    uint64
-
-	extendMu     sync.Mutex
-	extendCancel context.CancelFunc
 }
 
 func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
@@ -166,16 +148,11 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	if err != nil {
 		return err
 	}
+
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
 	c.setState(cfg, cacheDir, connectClient)
-	// This path runs the interactive SSO flow, so reaching here means the peer
-	// is authenticated again — release the latch Status() reports from. Clear
-	// only once the fresh connect client is installed: until then Status()
-	// still reads the previous run's context state, which holds the NeedsLogin
-	// that prompted this login, and would re-latch what was just cleared.
-	c.clearLoginRequired()
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
@@ -270,9 +247,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
 		deps.SyncResponse = resp
 
 		if e := cc.Engine(); e != nil {
-			deps.RefreshStatus = func() {
-				e.RunHealthProbes(context.Background(), true)
-			}
 			if cm := e.GetClientMetrics(); cm != nil {
 				deps.ClientMetrics = cm
 			}

client/android/profile_manager.go

@@ -189,19 +189,6 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 	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 fmt.Errorf("failed to rename profile: %w", err)
-	}
-
-	log.Infof("renamed profile %s to: %s", id, newName)
-	return nil
-}
-
 // RemoveProfile deletes a profile
 func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)

client/android/session.go

@@ -1,309 +0,0 @@
-//go:build android
-
-package android
-
-import (
-	"context"
-	"fmt"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/auth"
-	"github.com/netbirdio/netbird/client/internal/auth/sessionwatch"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	cProto "github.com/netbirdio/netbird/client/proto"
-)
-
-// StateChangeListener receives client state notifications.
-//
-// OnStateChanged is a payload-free wake-up whenever the state snapshot
-// changed: connection state, the run-loop status label (e.g. NeedsLogin) or
-// the session deadline. It mirrors the daemon's SubscribeStatus stream
-// trigger — on each signal the consumer pulls the fresh values via
-// Status() / SessionExpiresAtUnix().
-//
-// OnSessionExpiring forwards the engine's session-expiry warnings, fired at
-// sessionwatch.WarningLead before the deadline and again at FinalWarningLead
-// (finalWarning true). The second one is suppressed when the user dismissed
-// the first via DismissSessionWarning. The daemon turns the same events into
-// its tray notification.
-type StateChangeListener interface {
-	OnStateChanged()
-	OnSessionExpiring(expiresAtUnix int64, leadMinutes int64, finalWarning bool)
-}
-
-// Status returns the connect run-loop's status label — the same value the
-// desktop daemon serves in StatusResponse.Status. "NeedsLogin" means the
-// management server rejected the peer and an interactive login is required.
-//
-// The label is latched: the run loop keeps its status in a per-run context
-// state, which a restart replaces with a fresh Idle one, so an engine restart
-// (network change, always-on) would otherwise erase the fact that the peer
-// still needs to log in. Only a successful interactive login or extend clears
-// it — see clearLoginRequired.
-func (c *Client) Status() string {
-	latched, generation := c.loginRequiredState()
-	if latched {
-		return string(internal.StatusNeedsLogin)
-	}
-	cc := c.getConnectClient()
-	if cc == nil {
-		return string(internal.StatusIdle)
-	}
-	status := cc.Status()
-	if status == internal.StatusNeedsLogin {
-		c.latchLoginRequired(generation)
-	}
-	return string(status)
-}
-
-func (c *Client) loginRequiredState() (bool, uint64) {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	return c.loginRequired, c.loginCleared
-}
-
-// latchLoginRequired records a NeedsLogin observation, unless a clear landed
-// while the caller was reading the run loop's status: cc.Status() is read
-// outside the lock, so a login or extend completing in that window would
-// otherwise be undone by this stale observation, stranding the UI on
-// "login required" over a healthy session.
-func (c *Client) latchLoginRequired(observedGeneration uint64) {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	if c.loginCleared != observedGeneration {
-		return
-	}
-	c.loginRequired = true
-}
-
-// clearLoginRequired releases the latch after a successful interactive login
-// or session extend, and invalidates any observation already in flight.
-func (c *Client) clearLoginRequired() {
-	c.loginRequiredMu.Lock()
-	defer c.loginRequiredMu.Unlock()
-	c.loginRequired = false
-	c.loginCleared++
-}
-
-// SessionExpiresAtUnix returns the SSO session deadline as unix seconds, or 0
-// when no deadline is known (not SSO-registered, expiry disabled, or the
-// engine has not received one yet). A past value means the session expired.
-// Mirror of StatusResponse.sessionExpiresAt on the desktop daemon.
-func (c *Client) SessionExpiresAtUnix() int64 {
-	deadline := c.recorder.GetSessionExpiresAt()
-	if deadline.IsZero() {
-		return 0
-	}
-	return deadline.Unix()
-}
-
-// SetStateChangeListener registers the state notification listener.
-// Replaces any previously registered listener; remove it with
-// RemoveStateChangeListener.
-func (c *Client) SetStateChangeListener(listener StateChangeListener) {
-	c.stateChangeMu.Lock()
-	defer c.stateChangeMu.Unlock()
-	c.stopStateChangeWatchLocked()
-	if listener == nil {
-		return
-	}
-
-	// Both subscriptions are buffered (one pending tick, ten pending events),
-	// so unsubscribing is not enough to stop callbacks: the loops would drain
-	// what is already queued and deliver it to a listener the caller has
-	// already removed or replaced. Gate every callback on this registration's
-	// own signal, which is closed before unsubscribing.
-	done := make(chan struct{})
-	c.stateChangeDone = done
-
-	id, ch := c.recorder.SubscribeToStateChanges()
-	c.stateChangeSubID = id
-	// The channel is closed by UnsubscribeFromStateChanges, which ends the
-	// goroutine. Ticks are coalesced (buffer of one), so a burst of changes
-	// wakes the listener once.
-	go func() {
-		for range ch {
-			select {
-			case <-done:
-				return
-			default:
-			}
-			listener.OnStateChanged()
-		}
-	}()
-
-	c.eventSub = c.recorder.SubscribeToEvents()
-	go watchSessionWarnings(c.eventSub, listener, done)
-}
-
-// RemoveStateChangeListener unregisters the state notification listener.
-func (c *Client) RemoveStateChangeListener() {
-	c.stateChangeMu.Lock()
-	defer c.stateChangeMu.Unlock()
-	c.stopStateChangeWatchLocked()
-}
-
-// DismissSessionWarning records the user's "Dismiss" on the first expiry
-// warning and suppresses the final one for the current deadline. A refreshed
-// deadline re-arms both. No-op while the engine is not running.
-func (c *Client) DismissSessionWarning() {
-	cc := c.getConnectClient()
-	if cc == nil {
-		return
-	}
-	engine := cc.Engine()
-	if engine == nil {
-		return
-	}
-	engine.DismissSessionWarning()
-}
-
-// ExtendAuthSession runs the interactive SSO flow to obtain a fresh JWT and
-// asks the management server to extend the session deadline. The tunnel is
-// untouched: no resync, no reconnect. Async; the result arrives on the
-// listener. Mirror of the daemon's RequestExtendAuthSession /
-// WaitExtendAuthSession RPC pair, with URLOpener playing the "UI opens the
-// browser" role.
-//
-// Only one flow may be in flight: the PKCE step binds a fixed loopback port,
-// so a second concurrent flow would fail on that bind. Call
-// CancelExtendAuthSession when the user abandons the browser.
-func (c *Client) ExtendAuthSession(urlOpener URLOpener, isAndroidTV bool, resultListener ErrListener) {
-	ctx, err := c.beginExtend()
-	if err != nil {
-		resultListener.OnError(err)
-		return
-	}
-
-	go func() {
-		defer c.endExtend()
-		if err := c.extendAuthSession(ctx, urlOpener, isAndroidTV); err != nil {
-			resultListener.OnError(err)
-			return
-		}
-		resultListener.OnSuccess()
-	}()
-}
-
-// CancelExtendAuthSession aborts an in-flight ExtendAuthSession. The tunnel is
-// left alone — unlike the login flow, which cancels the whole client context
-// by stopping the engine. Without this the abandoned PKCE wait keeps its
-// loopback port for the full flow timeout and blocks every later attempt.
-// No-op when no flow is running.
-func (c *Client) CancelExtendAuthSession() {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		c.extendCancel()
-	}
-}
-
-func (c *Client) stopStateChangeWatchLocked() {
-	// Signal first, unsubscribe second: closing the channels only stops new
-	// items, and the loops would still hand whatever is buffered to a listener
-	// that is no longer registered.
-	if c.stateChangeDone != nil {
-		close(c.stateChangeDone)
-		c.stateChangeDone = nil
-	}
-	if c.stateChangeSubID != "" {
-		c.recorder.UnsubscribeFromStateChanges(c.stateChangeSubID)
-		c.stateChangeSubID = ""
-	}
-	if c.eventSub != nil {
-		// Closes the channel, which ends watchSessionWarnings.
-		c.recorder.UnsubscribeFromEvents(c.eventSub)
-		c.eventSub = nil
-	}
-}
-
-// watchSessionWarnings forwards the engine's session-expiry warnings to the
-// listener. The event stream also carries unrelated traffic — network-map
-// updates on every sync, DNS and route errors — so everything but an
-// AUTHENTICATION event carrying the session-warning marker is dropped. Exits
-// when the subscription is closed by UnsubscribeFromEvents, or earlier when
-// done is closed — the stream buffers up to ten events, and a deregistered
-// listener must not receive the ones already queued.
-func watchSessionWarnings(sub *peer.EventSubscription, listener StateChangeListener, done <-chan struct{}) {
-	for ev := range sub.Events() {
-		select {
-		case <-done:
-			return
-		default:
-		}
-		if ev.GetCategory() != cProto.SystemEvent_AUTHENTICATION {
-			continue
-		}
-		meta := ev.GetMetadata()
-		if meta[sessionwatch.MetaSessionWarning] != "true" {
-			// Other AUTHENTICATION events exist (e.g. a deadline rejected as
-			// out of range); they carry no warning marker.
-			continue
-		}
-		deadline, err := sessionwatch.ParseExpiresAt(meta[sessionwatch.MetaSessionExpiresAt])
-		if err != nil {
-			log.Warnf("session warning event with unparsable deadline: %v", err)
-			continue
-		}
-		lead, err := sessionwatch.ParseLeadMinutes(meta[sessionwatch.MetaSessionLeadMinutes])
-		if err != nil {
-			// Informational only — the deadline above is what drives the UI.
-			lead = 0
-		}
-		listener.OnSessionExpiring(deadline.Unix(), int64(lead),
-			meta[sessionwatch.MetaSessionFinal] == "true")
-	}
-}
-
-func (c *Client) beginExtend() (context.Context, error) {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		return nil, fmt.Errorf("session extend already in progress")
-	}
-	ctx, cancel := context.WithCancel(context.Background())
-	c.extendCancel = cancel
-	return ctx, nil
-}
-
-func (c *Client) endExtend() {
-	c.extendMu.Lock()
-	defer c.extendMu.Unlock()
-	if c.extendCancel != nil {
-		c.extendCancel()
-		c.extendCancel = nil
-	}
-}
-
-func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
-	cfg, _, cc := c.stateSnapshot()
-	if cfg == nil || cc == nil {
-		return fmt.Errorf("engine is not running")
-	}
-	engine := cc.Engine()
-	if engine == nil {
-		return fmt.Errorf("engine is not initialized")
-	}
-
-	authClient, err := auth.NewAuth(ctx, cfg.PrivateKey, cfg.ManagementURL, cfg)
-	if err != nil {
-		return fmt.Errorf("failed to create auth client: %v", err)
-	}
-	defer authClient.Close()
-
-	a := &Auth{ctx: ctx, config: cfg}
-	tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
-	if err != nil {
-		return fmt.Errorf("interactive sso login failed: %v", err)
-	}
-
-	if _, err := engine.ExtendAuthSession(ctx, tokenInfo.GetTokenToUse()); err != nil {
-		return err
-	}
-	c.clearLoginRequired()
-
-	go urlOpener.OnLoginSuccess()
-	return nil
-}

client/cmd/root.go

@@ -23,6 +23,7 @@ import (
 	"google.golang.org/grpc/credentials/insecure"
 
 	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"
@@ -79,6 +82,8 @@ var (
 	updateSettingsDisabled bool
 	captureEnabled         bool
 	networksDisabled       bool
+	localMetricsEnabled    bool
+	localMetricsAddr       string
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -212,6 +217,8 @@ func init() {
 	upCmd.PersistentFlags().BoolVar(&rosenpassEnabled, enableRosenpassFlag, false, "[Experimental] Enable Rosenpass feature. If enabled, the connection will be post-quantum secured via Rosenpass.")
 	upCmd.PersistentFlags().BoolVar(&rosenpassPermissive, rosenpassPermissiveFlag, false, "[Experimental] Enable Rosenpass in permissive mode to allow this peer to accept WireGuard connections without requiring Rosenpass functionality from peers that do not have Rosenpass enabled.")
 	upCmd.PersistentFlags().BoolVar(&autoConnectDisabled, disableAutoConnectFlag, false, "Disables auto-connect feature. If enabled, then the client won't connect automatically when the service starts.")
+	upCmd.PersistentFlags().BoolVar(&localMetricsEnabled, enableLocalMetricsFlag, false, "Enables a local Prometheus /metrics endpoint exposing connection state (peers, latency, P2P vs relay).")
+	upCmd.PersistentFlags().StringVar(&localMetricsAddr, localMetricsAddressFlag, localmetrics.DefaultListenAddress, "Listen address of the local Prometheus /metrics endpoint.")
 	upCmd.PersistentFlags().BoolVar(&lazyConnEnabled, enableLazyConnectionFlag, false, "Deprecated: no longer used. Lazy connections are controlled by the server and the NB_LAZY_CONN environment variable.")
 	_ = upCmd.PersistentFlags().MarkDeprecated(enableLazyConnectionFlag, "no longer used; lazy connections are controlled by the server and the NB_LAZY_CONN environment variable")
 

client/cmd/up.go

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

client/firewall/uspfilter/filter.go

@@ -121,7 +121,6 @@ type Manager struct {
 	udpTracker     *conntrack.UDPTracker
 	icmpTracker    *conntrack.ICMPTracker
 	tcpTracker     *conntrack.TCPTracker
-	fragments      *fragmentTracker
 	forwarder      atomic.Pointer[forwarder.Forwarder]
 	pendingCapture atomic.Pointer[forwarder.PacketCapture]
 	logger         *nblog.Logger
@@ -184,41 +183,6 @@ func (d *decoder) decodePacket(data []byte) error {
 	}
 }
 
-// decodeTransport decodes the transport header of a first fragment (which
-// gopacket leaves undecoded) into the decoder and appends its layer type to
-// decoded, so the ACL pipeline can evaluate it like a normal packet. It returns
-// false if the protocol is unsupported or the header is truncated.
-func (d *decoder) decodeTransport(proto layers.IPProtocol, payload []byte) bool {
-	var l4 gopacket.DecodingLayer
-	var layerType gopacket.LayerType
-	var minLen int
-	switch proto {
-	case layers.IPProtocolTCP:
-		l4, layerType, minLen = &d.tcp, layers.LayerTypeTCP, 20
-	case layers.IPProtocolUDP:
-		l4, layerType, minLen = &d.udp, layers.LayerTypeUDP, 8
-	case layers.IPProtocolICMPv4:
-		l4, layerType, minLen = &d.icmp4, layers.LayerTypeICMPv4, 8
-	case layers.IPProtocolICMPv6:
-		l4, layerType, minLen = &d.icmp6, layers.LayerTypeICMPv6, 8
-	default:
-		return false
-	}
-
-	// Reject a fragment too small to hold the full transport header before
-	// decoding: it can't be ACL-evaluated (tiny-fragment attack), and skipping
-	// the decode avoids gopacket allocating an error on the drop path.
-	if len(payload) < minLen {
-		return false
-	}
-
-	if err := l4.DecodeFromBytes(payload, gopacket.NilDecodeFeedback); err != nil {
-		return false
-	}
-	d.decoded = append(d.decoded, layerType)
-	return true
-}
-
 // Create userspace firewall manager constructor
 func Create(iface common.IFaceMapper, disableServerRoutes bool, flowLogger nftypes.FlowLogger, mtu uint16) (*Manager, error) {
 	return create(iface, nil, disableServerRoutes, flowLogger, mtu)
@@ -322,8 +286,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
 	if err := m.localipmanager.UpdateLocalIPs(iface); err != nil {
 		return nil, fmt.Errorf("update local IPs: %w", err)
 	}
-	m.fragments = newFragmentTracker(m.logger)
-
 	if disableConntrack {
 		log.Info("conntrack is disabled")
 	} else {
@@ -337,7 +299,6 @@ func create(iface common.IFaceMapper, nativeFirewall firewall.Manager, disableSe
 		}
 	}
 	if err := iface.SetFilter(m); err != nil {
-		m.fragments.Close()
 		return nil, fmt.Errorf("set filter: %w", err)
 	}
 	return m, nil
@@ -733,10 +694,6 @@ func (m *Manager) resetState() {
 		m.tcpTracker.Close()
 	}
 
-	if m.fragments != nil {
-		m.fragments.Close()
-	}
-
 	if fwder := m.forwarder.Load(); fwder != nil {
 		fwder.SetCapture(nil)
 		fwder.Stop()
@@ -1089,20 +1046,19 @@ func (m *Manager) filterInbound(packetData []byte, size int) bool {
 		return true
 	}
 
-	// gopacket does not decode the transport header of any IP fragment, so
-	// fragments take a dedicated path: the first fragment's header is decoded
-	// and ACL-evaluated here, and the remaining fragments inherit its verdict.
+	// TODO: pass fragments of routed packets to forwarder
 	if fragment {
-		return m.filterInboundFragment(d, srcIP, dstIP, size)
+		if m.logger.Enabled(nblog.LevelTrace) {
+			if d.decoded[0] == layers.LayerTypeIPv4 {
+				m.logger.Trace4("packet is a fragment: src=%v dst=%v id=%v flags=%v",
+					srcIP, dstIP, d.ip4.Id, d.ip4.Flags)
+			} else {
+				m.logger.Trace2("packet is an IPv6 fragment: src=%v dst=%v", srcIP, dstIP)
+			}
+		}
+		return false
 	}
 
-	return m.filterInboundDecoded(d, srcIP, dstIP, packetData, size)
-}
-
-// filterInboundDecoded runs the ACL, DNAT and conntrack pipeline on a fully
-// decoded (non-fragment) inbound packet. It returns true if the packet should
-// be dropped.
-func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
 	// TODO: optimize port DNAT by caching matched rules in conntrack
 	if translated := m.translateInboundPortDNAT(packetData, d, srcIP, dstIP); translated {
 		// Re-decode after port DNAT translation to update port information
@@ -1133,226 +1089,33 @@ func (m *Manager) filterInboundDecoded(d *decoder, srcIP, dstIP netip.Addr, pack
 	return m.handleRoutedTraffic(d, srcIP, dstIP, packetData, size)
 }
 
-// fragmentMeta holds the reassembly identity and layout of an IP fragment,
-// extracted uniformly for IPv4 and IPv6.
-type fragmentMeta struct {
-	key fragmentKey
-	// offset is the fragment offset in 8-byte units (zero for the first
-	// fragment).
-	offset uint16
-	// moreFragments is the More Fragments bit. A first fragment with it unset is
-	// an IPv6 atomic fragment (a complete datagram, RFC 6946): it has no trailing
-	// fragments to inherit a verdict, so it must not be recorded.
-	moreFragments bool
-	proto         layers.IPProtocol
-	// l4payload is the fragmentable payload of this fragment. For the first
-	// fragment it starts with the transport header.
-	l4payload []byte
-	// headerEndOctets is the first fragment's payload length in 8-byte units:
-	// the smallest offset a trailing fragment may start at without overlapping
-	// the inspected transport header.
-	headerEndOctets uint16
-}
-
-// fragmentMetadata extracts the fragment identity and layout from a decoded IP
-// fragment. It returns false for fragments it can't interpret (e.g. an IPv6
-// fragment header shorter than 8 bytes), which are then dropped.
-func fragmentMetadata(d *decoder, srcIP, dstIP netip.Addr) (fragmentMeta, bool) {
-	switch d.decoded[0] {
-	case layers.LayerTypeIPv4:
-		payload := d.ip4.Payload
-		return fragmentMeta{
-			key:             fragmentKey{srcIP: srcIP, dstIP: dstIP, id: uint32(d.ip4.Id), proto: uint8(d.ip4.Protocol)},
-			offset:          d.ip4.FragOffset,
-			moreFragments:   d.ip4.Flags&layers.IPv4MoreFragments != 0,
-			proto:           d.ip4.Protocol,
-			l4payload:       payload,
-			headerEndOctets: octets(len(payload)),
-		}, true
-
-	case layers.LayerTypeIPv6:
-		// IPv6 fragment extension header: 8 bytes, followed by the fragmentable
-		// payload. Layout: next header (1), reserved (1), offset+flags (2), id (4).
-		payload := d.ip6.Payload
-		if len(payload) < 8 {
-			return fragmentMeta{}, false
-		}
-		nextHeader := layers.IPProtocol(payload[0])
-		offsetFlags := binary.BigEndian.Uint16(payload[2:4])
-		id := binary.BigEndian.Uint32(payload[4:8])
-		l4 := payload[8:]
-		return fragmentMeta{
-			key:             fragmentKey{srcIP: srcIP, dstIP: dstIP, id: id, proto: uint8(nextHeader)},
-			offset:          offsetFlags >> 3,
-			moreFragments:   offsetFlags&1 != 0,
-			proto:           nextHeader,
-			l4payload:       l4,
-			headerEndOctets: octets(len(l4)),
-		}, true
-
-	default:
-		return fragmentMeta{}, false
-	}
-}
-
-// octets rounds a byte length up to whole 8-byte units, the granularity of the
-// IP fragment offset field.
-func octets(nbytes int) uint16 {
-	return uint16((nbytes + 7) / 8)
-}
-
-// filterInboundFragment decides the fate of an IP fragment. gopacket stops
-// decoding at the network layer for every fragment, so the first fragment's
-// transport header is decoded and ACL-evaluated here and its verdict recorded;
-// the remaining (headerless) fragments inherit that verdict. Anything that
-// cannot be tied to an allowed, non-overlapping first fragment is dropped.
-func (m *Manager) filterInboundFragment(d *decoder, srcIP, dstIP netip.Addr, size int) bool {
-	meta, ok := fragmentMetadata(d, srcIP, dstIP)
-	if !ok {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace2("dropping unsupported fragment: src=%v dst=%v", srcIP, dstIP)
-		}
-		return true
-	}
-
-	if meta.offset != 0 {
-		return m.filterTrailingFragment(meta, srcIP, dstIP)
-	}
-
-	// A new first fragment supersedes any recorded verdict for this datagram, so
-	// a re-sent or overlapping offset-zero fragment can't inherit the old one.
-	m.fragments.poison(meta.key)
-
-	// First fragment: decode its transport header so the ACL can evaluate it. A
-	// decode failure means the fragment is too small to hold the full transport
-	// header (RFC 1858 §3 tiny-fragment attack); it can't be evaluated, so drop it.
-	if !d.decodeTransport(meta.proto, meta.l4payload) {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping first fragment without full L4 header: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	}
-
-	return m.filterFirstFragment(d, meta, srcIP, dstIP, size)
-}
-
-// filterTrailingFragment applies a recorded first-fragment verdict to a
-// non-first fragment.
-func (m *Manager) filterTrailingFragment(meta fragmentMeta, srcIP, dstIP netip.Addr) bool {
-	switch m.fragments.verdict(meta.key, meta.offset) {
-	case fragmentAllow:
-		return false
-	case fragmentOverlap:
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping overlapping fragment rewriting inspected header: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	default:
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace3("dropping fragment with no allowed first fragment: src=%v dst=%v id=%v",
-				srcIP, dstIP, meta.key.id)
-		}
-		return true
-	}
-}
-
-// filterFirstFragment runs the verdict part of the inbound pipeline on a first
-// fragment with its transport header decoded. It mirrors filterInboundDecoded
-// but skips DNAT (port rewriting on fragments is unsupported) and forwarder
-// injection (fragments are left to the stack to reassemble, not forwarded).
-// Allowed fragments have their verdict recorded so the datagram's trailing
-// fragments inherit it.
-func (m *Manager) filterFirstFragment(d *decoder, meta fragmentMeta, srcIP, dstIP netip.Addr, size int) bool {
-	if m.stateful && m.isValidTrackedConnection(d, srcIP, dstIP, size) {
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	if m.localipmanager.IsLocalIP(dstIP) {
-		ruleID, blocked := m.peerACLsBlock(srcIP, d, nil)
-		if blocked {
-			m.storeDropFlow("Dropping local first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-				d, srcIP, dstIP, ruleID, size)
-			return true
-		}
-		m.trackInbound(d, srcIP, dstIP, ruleID, size)
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	if !m.routingEnabled.Load() {
-		if m.logger.Enabled(nblog.LevelTrace) {
-			m.logger.Trace2("Dropping routed fragment (routing disabled): src=%s dst=%s", srcIP, dstIP)
-		}
-		return true
-	}
-	if m.nativeRouter.Load() {
-		m.trackInbound(d, srcIP, dstIP, nil, size)
-		m.recordFirstFragment(meta)
-		return false
-	}
-
-	// TODO: pass fragments of routed packets to the forwarder; until then
-	// allowed routed fragments go to the native stack.
-	srcPort, dstPort := getPortsFromPacket(d)
-	ruleID, pass := m.routeACLsPass(srcIP, dstIP, d.decoded[1], srcPort, dstPort)
-	if !pass {
-		m.storeDropFlow("Dropping routed first fragment (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
-		return true
-	}
-
-	m.recordFirstFragment(meta)
-	return false
-}
-
-// recordFirstFragment caches an allowed first fragment's verdict for its
-// trailing fragments to inherit. Atomic fragments (no More Fragments bit) are
-// complete datagrams with no trailing fragments, so they are not cached and
-// cannot exhaust the verdict table.
-func (m *Manager) recordFirstFragment(meta fragmentMeta) {
-	if !meta.moreFragments {
-		return
-	}
-	m.fragments.recordAllowed(meta.key, meta.headerEndOctets)
-}
-
-// storeDropFlow logs and records a netflow drop event for an inbound packet
-// denied by the ACLs. msg is the trace format taking rule id, protocol, source
-// and destination.
-func (m *Manager) storeDropFlow(msg string, d *decoder, srcIP, dstIP netip.Addr, ruleID []byte, size int) {
-	pnum := getProtocolFromPacket(d)
-	srcPort, dstPort := getPortsFromPacket(d)
-
-	if m.logger.Enabled(nblog.LevelTrace) {
-		m.logger.Trace6(msg, ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
-	}
-
-	m.flowLogger.StoreEvent(nftypes.EventFields{
-		FlowID:     uuid.New(),
-		Type:       nftypes.TypeDrop,
-		RuleID:     ruleID,
-		Direction:  nftypes.Ingress,
-		Protocol:   pnum,
-		SourceIP:   srcIP,
-		DestIP:     dstIP,
-		SourcePort: srcPort,
-		DestPort:   dstPort,
-		// TODO: icmp type/code
-		RxPackets: 1,
-		RxBytes:   uint64(size),
-	})
-}
-
 // handleLocalTraffic handles local traffic.
 // If it returns true, the packet should be dropped.
 func (m *Manager) handleLocalTraffic(d *decoder, srcIP, dstIP netip.Addr, packetData []byte, size int) bool {
 	ruleID, blocked := m.peerACLsBlock(srcIP, d, packetData)
 	if blocked {
-		m.storeDropFlow("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
+		pnum := getProtocolFromPacket(d)
+		srcPort, dstPort := getPortsFromPacket(d)
+
+		if m.logger.Enabled(nblog.LevelTrace) {
+			m.logger.Trace6("Dropping local packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
+				ruleID, pnum, srcIP, srcPort, dstIP, dstPort)
+		}
+
+		m.flowLogger.StoreEvent(nftypes.EventFields{
+			FlowID:     uuid.New(),
+			Type:       nftypes.TypeDrop,
+			RuleID:     ruleID,
+			Direction:  nftypes.Ingress,
+			Protocol:   pnum,
+			SourceIP:   srcIP,
+			DestIP:     dstIP,
+			SourcePort: srcPort,
+			DestPort:   dstPort,
+			// TODO: icmp type/code
+			RxPackets: 1,
+			RxBytes:   uint64(size),
+		})
 		return true
 	}
 
@@ -1405,8 +1168,27 @@ func (m *Manager) handleRoutedTraffic(d *decoder, srcIP, dstIP netip.Addr, packe
 
 	ruleID, pass := m.routeACLsPass(srcIP, dstIP, protoLayer, srcPort, dstPort)
 	if !pass {
-		m.storeDropFlow("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
-			d, srcIP, dstIP, ruleID, size)
+		proto := getProtocolFromPacket(d)
+
+		if m.logger.Enabled(nblog.LevelTrace) {
+			m.logger.Trace6("Dropping routed packet (ACL denied): rule_id=%s proto=%v src=%s:%d dst=%s:%d",
+				ruleID, proto, srcIP, srcPort, dstIP, dstPort)
+		}
+
+		m.flowLogger.StoreEvent(nftypes.EventFields{
+			FlowID:     uuid.New(),
+			Type:       nftypes.TypeDrop,
+			RuleID:     ruleID,
+			Direction:  nftypes.Ingress,
+			Protocol:   proto,
+			SourceIP:   srcIP,
+			DestIP:     dstIP,
+			SourcePort: srcPort,
+			DestPort:   dstPort,
+			// TODO: icmp type/code
+			RxPackets: 1,
+			RxBytes:   uint64(size),
+		})
 		return true
 	}
 

client/firewall/uspfilter/forwarder/forwarder.go

@@ -5,9 +5,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"os"
 	"runtime"
-	"strconv"
 	"sync"
 	"time"
 
@@ -33,11 +31,6 @@ const (
 	defaultMaxInFlight   = 1024
 	iosReceiveWindow     = 16384
 	iosMaxInFlight       = 256
-
-	// envForceTCPRACK overrides the platform default for gVisor's RACK loss
-	// detection. Set to a truthy value to force RACK on, or a falsy value to
-	// force it off, on any platform.
-	envForceTCPRACK = "NB_FORCE_TCP_RACK"
 )
 
 type Forwarder struct {
@@ -159,8 +152,6 @@ func New(iface common.IFaceMapper, logger *nblog.Logger, flowLogger nftypes.Flow
 		maxInFlight = iosMaxInFlight
 	}
 
-	configureTCPRecovery(s)
-
 	tcpForwarder := tcp.NewForwarder(s, receiveWindow, maxInFlight, f.handleTCP)
 	s.SetTransportProtocolHandler(tcp.ProtocolNumber, tcpForwarder.HandlePacket)
 
@@ -475,31 +466,3 @@ func probeRawICMP(network, addr string, logger *nblog.Logger) bool {
 	logger.Debug1("forwarder: raw %s socket access available", network)
 	return true
 }
-
-// configureTCPRecovery disables gVisor's RACK loss detection on Windows, where
-// it interacts poorly with the host and collapses throughput on routed TCP
-// connections (gVisor issue #9778). Other platforms keep the default. The
-// EnvForceTCPRACK environment variable overrides the platform default.
-func configureTCPRecovery(s *stack.Stack) {
-	disableRACK := runtime.GOOS == "windows"
-
-	if val := os.Getenv(envForceTCPRACK); val != "" {
-		force, err := strconv.ParseBool(val)
-		if err != nil {
-			log.Warnf("parse %s: %v", envForceTCPRACK, err)
-		} else {
-			disableRACK = !force
-		}
-	}
-
-	if !disableRACK {
-		return
-	}
-
-	opt := tcpip.TCPRecovery(0)
-	if err := s.SetTransportProtocolOption(tcp.ProtocolNumber, &opt); err != nil {
-		log.Warnf("disable TCP RACK loss detection: %v", err)
-		return
-	}
-	log.Info("forwarder: TCP RACK loss detection disabled")
-}

client/firewall/uspfilter/fragment.go

@@ -1,204 +0,0 @@
-package uspfilter
-
-import (
-	"context"
-	"net/netip"
-	"os"
-	"strconv"
-	"sync"
-	"time"
-
-	nblog "github.com/netbirdio/netbird/client/firewall/uspfilter/log"
-)
-
-const (
-	// defaultFragmentTimeout bounds how long a first-fragment verdict is kept
-	// while the remaining fragments arrive. It mirrors the Linux IP reassembly
-	// timeout (net.ipv4.ipfrag_time).
-	defaultFragmentTimeout = 30 * time.Second
-	// fragmentCleanupInterval is how often expired verdicts are purged.
-	fragmentCleanupInterval = 10 * time.Second
-	// defaultMaxFragmentEntries caps the number of concurrently tracked
-	// fragmented datagrams. The table stays bounded because each datagram is a
-	// single small entry regardless of how many fragments it is split into, and
-	// the 13-bit IPv4 fragment-offset field limits any datagram to 64 KiB.
-	defaultMaxFragmentEntries = 16384
-
-	// EnvFragmentMaxEntries overrides defaultMaxFragmentEntries.
-	EnvFragmentMaxEntries = "NB_FRAGMENT_MAX_ENTRIES"
-)
-
-// fragmentVerdict is the decision for a trailing (headerless) fragment.
-type fragmentVerdict int
-
-const (
-	// fragmentDeny drops the fragment: no allowed first fragment is on record.
-	fragmentDeny fragmentVerdict = iota
-	// fragmentAllow passes the fragment: it belongs to an allowed datagram and
-	// does not overlap the already-inspected transport header.
-	fragmentAllow
-	// fragmentOverlap drops the fragment and poisons its datagram: it overlaps
-	// the transport header the ACL inspected (RFC 1858 §4, RFC 3128; RFC 5722
-	// requires discarding the whole datagram on overlap for IPv6).
-	fragmentOverlap
-)
-
-// fragmentKey identifies a fragmented datagram. It matches the RFC 791 / RFC
-// 8200 reassembly key: source, destination, protocol and identification. The id
-// is 32-bit to hold both the IPv4 (16-bit) and IPv6 (32-bit) identification.
-type fragmentKey struct {
-	srcIP netip.Addr
-	dstIP netip.Addr
-	id    uint32
-	proto uint8
-}
-
-// fragmentEntry records the verdict of an allowed first fragment.
-type fragmentEntry struct {
-	// headerEndOctets is the offset, in 8-byte units, at which the first
-	// fragment's payload ended. A trailing fragment starting before this
-	// overlaps bytes the ACL already inspected and is rejected.
-	headerEndOctets uint16
-	// recordedAt is when the first fragment was accepted. The verdict expires a
-	// fixed timeout later and is not refreshed, mirroring the kernel reassembly
-	// timer so a trailing-fragment flood can't keep a datagram alive.
-	recordedAt time.Time
-}
-
-// fragmentTracker records the ACL verdict of a datagram's first fragment so the
-// remaining fragments, which carry no L4 header, can inherit the decision
-// without reassembling the datagram. Only allowed first fragments are stored;
-// anything that cannot be tied to an allowed, non-overlapping first fragment is
-// dropped (fail closed).
-type fragmentTracker struct {
-	logger  *nblog.Logger
-	mutex   sync.Mutex
-	entries map[fragmentKey]fragmentEntry
-	timeout time.Duration
-	// maxEntries caps the table; atCapacity dedups the capacity warning until
-	// the table drains below the cap again.
-	maxEntries    int
-	atCapacity    bool
-	cleanupTicker *time.Ticker
-	cancel        context.CancelFunc
-}
-
-func newFragmentTracker(logger *nblog.Logger) *fragmentTracker {
-	ctx, cancel := context.WithCancel(context.Background())
-	t := &fragmentTracker{
-		logger:        logger,
-		entries:       make(map[fragmentKey]fragmentEntry),
-		timeout:       defaultFragmentTimeout,
-		maxEntries:    fragmentMaxEntries(logger),
-		cleanupTicker: time.NewTicker(fragmentCleanupInterval),
-		cancel:        cancel,
-	}
-	go t.cleanupRoutine(ctx)
-	return t
-}
-
-func fragmentMaxEntries(logger *nblog.Logger) int {
-	v := os.Getenv(EnvFragmentMaxEntries)
-	if v == "" {
-		return defaultMaxFragmentEntries
-	}
-	n, err := strconv.Atoi(v)
-	if err != nil || n <= 0 {
-		logger.Warn2("invalid %s=%q, using default", EnvFragmentMaxEntries, v)
-		return defaultMaxFragmentEntries
-	}
-	return n
-}
-
-// recordAllowed stores the verdict of an allowed first fragment. headerEndOctets
-// is the first fragment's payload length in 8-byte units. When the table is full
-// the record is dropped, which fails closed: the datagram's trailing fragments
-// will be denied.
-func (t *fragmentTracker) recordAllowed(key fragmentKey, headerEndOctets uint16) {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	if t.entries == nil {
-		return
-	}
-	if _, ok := t.entries[key]; !ok && len(t.entries) >= t.maxEntries {
-		if !t.atCapacity {
-			t.atCapacity = true
-			t.logger.Warn2("fragment verdict table at capacity (%d/%d): trailing fragments of new datagrams will be dropped",
-				len(t.entries), t.maxEntries)
-		}
-		return
-	}
-	t.entries[key] = fragmentEntry{
-		headerEndOctets: headerEndOctets,
-		recordedAt:      time.Now(),
-	}
-}
-
-// poison drops any recorded verdict for a datagram, so its later fragments are
-// denied until a new allowed first fragment is recorded. Called on every
-// offset-zero fragment to defeat offset-zero overlap rewrites (RFC 3128).
-func (t *fragmentTracker) poison(key fragmentKey) {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-	delete(t.entries, key)
-}
-
-// verdict decides the fate of a trailing fragment at fragOffsetOctets (the IPv4
-// fragment offset, in 8-byte units). A fragment overlapping the inspected
-// header poisons the datagram: the entry is removed so all further fragments of
-// that datagram are denied too.
-func (t *fragmentTracker) verdict(key fragmentKey, fragOffsetOctets uint16) fragmentVerdict {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	entry, ok := t.entries[key]
-	if !ok {
-		return fragmentDeny
-	}
-	if time.Since(entry.recordedAt) > t.timeout {
-		delete(t.entries, key)
-		return fragmentDeny
-	}
-	if fragOffsetOctets < entry.headerEndOctets {
-		delete(t.entries, key)
-		return fragmentOverlap
-	}
-	return fragmentAllow
-}
-
-func (t *fragmentTracker) cleanupRoutine(ctx context.Context) {
-	defer t.cleanupTicker.Stop()
-	for {
-		select {
-		case <-t.cleanupTicker.C:
-			t.cleanup()
-		case <-ctx.Done():
-			return
-		}
-	}
-}
-
-func (t *fragmentTracker) cleanup() {
-	t.mutex.Lock()
-	defer t.mutex.Unlock()
-
-	for key, entry := range t.entries {
-		if time.Since(entry.recordedAt) > t.timeout {
-			delete(t.entries, key)
-		}
-	}
-
-	if len(t.entries) < t.maxEntries {
-		t.atCapacity = false
-	}
-}
-
-// Close stops the cleanup routine and releases resources.
-func (t *fragmentTracker) Close() {
-	t.cancel()
-
-	t.mutex.Lock()
-	t.entries = nil
-	t.mutex.Unlock()
-}

client/firewall/uspfilter/fragment_bench_test.go

@@ -1,115 +0,0 @@
-package uspfilter
-
-import (
-	"encoding/binary"
-	"testing"
-)
-
-// benchFilterInbound drives filterInbound over a fixed packet in a tight loop.
-// Packets are built once, outside the timed region, so the benchmark measures
-// only pipeline cost, which is what an attacker can amplify.
-func benchFilterInbound(b *testing.B, pkt []byte) {
-	b.Helper()
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		m := benchManager
-		m.filterInbound(pkt, len(pkt))
-	}
-}
-
-// benchManager is a package-level manager reused across fragment benchmarks so
-// setup cost stays out of the timed region.
-var benchManager *Manager
-
-func setupBenchManager(b *testing.B) *Manager {
-	b.Helper()
-	m := newFragmentTestManager(b)
-	allowUDP(b, m, 8080)
-	// Disable conntrack so the allowed-first-fragment path measures transport
-	// decode + ACL every iteration instead of matching the connection tracked
-	// on the first iteration.
-	m.stateful = false
-	benchManager = m
-	return m
-}
-
-// BenchmarkInbound_NormalPacket is the baseline: a full, non-fragmented UDP
-// packet that passes the ACL. Fragment paths should stay comparable to this.
-func BenchmarkInbound_NormalPacket(b *testing.B) {
-	setupBenchManager(b)
-	pkt := normalUDPPacket(b, 8080, 32)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_FirstFragmentAllowed measures the first-fragment path:
-// transport decode + ACL evaluation + verdict record.
-func BenchmarkInbound_FirstFragmentAllowed(b *testing.B) {
-	setupBenchManager(b)
-	pkt := firstFragmentUDP(b, 0x2000, 8080, 32)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentAllowed measures the common trailing-fragment
-// path: a single map lookup after the first fragment is on record.
-func BenchmarkInbound_TrailingFragmentAllowed(b *testing.B) {
-	m := setupBenchManager(b)
-	first := firstFragmentUDP(b, 0x3000, 8080, 32)
-	m.filterInbound(first, len(first))
-	pkt := trailingFragment(b, 0x3000, 5, false, 24)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentNoFirst is the primary DoS vector: an
-// attacker floods trailing fragments with no first fragment on record. Each is
-// a map miss and must be cheap.
-func BenchmarkInbound_TrailingFragmentNoFirst(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x4000, 185, false, 40)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TinyFirstFragment measures the tiny-fragment drop path: a
-// first fragment too small to decode a transport header.
-func BenchmarkInbound_TinyFirstFragment(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x5000, 0, true, 4)
-	benchFilterInbound(b, pkt)
-}
-
-// BenchmarkInbound_TrailingFragmentDistinctIDs is the worst case for the
-// verdict table: an attacker varies the datagram id on every packet so no first
-// fragment ever matches. Verdict lookups always miss and nothing is recorded,
-// so the table cannot grow. Each iteration rewrites the id field in place.
-func BenchmarkInbound_TrailingFragmentDistinctIDs(b *testing.B) {
-	setupBenchManager(b)
-	pkt := trailingFragment(b, 0x6000, 185, false, 40)
-	m := benchManager
-
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		// IPv4 identification field is at bytes 4:6.
-		binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
-		m.filterInbound(pkt, len(pkt))
-	}
-}
-
-// BenchmarkInbound_FirstFragmentDistinctIDs measures sustained first-fragment
-// pressure with distinct ids: transport decode + ACL + verdict insert until the
-// table caps, exercising the map growth and capacity guard.
-func BenchmarkInbound_FirstFragmentDistinctIDs(b *testing.B) {
-	setupBenchManager(b)
-	pkt := firstFragmentUDP(b, 0x7000, 8080, 32)
-	m := benchManager
-
-	b.ReportAllocs()
-	b.SetBytes(int64(len(pkt)))
-	b.ResetTimer()
-	for i := 0; i < b.N; i++ {
-		binary.BigEndian.PutUint16(pkt[4:6], uint16(i))
-		m.filterInbound(pkt, len(pkt))
-	}
-}

client/firewall/uspfilter/fragment_test.go

@@ -1,554 +0,0 @@
-package uspfilter
-
-import (
-	"encoding/binary"
-	"net"
-	"net/netip"
-	"testing"
-	"time"
-
-	"github.com/google/gopacket"
-	"github.com/google/gopacket/layers"
-	"github.com/stretchr/testify/require"
-
-	fw "github.com/netbirdio/netbird/client/firewall/manager"
-	nbiface "github.com/netbirdio/netbird/client/iface"
-	"github.com/netbirdio/netbird/client/iface/device"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
-)
-
-const (
-	fragTestSrc   = "100.10.0.1"
-	fragTestDst   = "100.10.0.100"
-	fragTestSrcV6 = "fd00::1"
-	fragTestDstV6 = "fd00::100"
-)
-
-func newFragmentTestManager(tb testing.TB) *Manager {
-	tb.Helper()
-
-	ifaceMock := &IFaceMock{
-		SetFilterFunc: func(device.PacketFilter) error { return nil },
-		AddressFunc: func() wgaddr.Address {
-			return wgaddr.Address{
-				IP:      netip.MustParseAddr(fragTestDst),
-				Network: netip.MustParsePrefix("100.10.0.0/16"),
-				IPv6:    netip.MustParseAddr(fragTestDstV6),
-				IPv6Net: netip.MustParsePrefix("fd00::/64"),
-			}
-		},
-	}
-
-	m, err := Create(ifaceMock, false, flowLogger, nbiface.DefaultMTU)
-	require.NoError(tb, err)
-	require.NoError(tb, m.UpdateLocalIPs())
-	tb.Cleanup(func() { require.NoError(tb, m.Close(nil)) })
-	return m
-}
-
-// firstFragmentUDPTo builds the first fragment of a fragmented UDP datagram to
-// the given destination: it carries the full UDP header plus payloadLen bytes
-// of data, with the More Fragments flag set and offset zero.
-func firstFragmentUDPTo(tb testing.TB, dst string, id uint16, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       id,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(dst),
-		Flags:    layers.IPv4MoreFragments,
-	}
-	udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func firstFragmentUDP(tb testing.TB, id uint16, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-	return firstFragmentUDPTo(tb, fragTestDst, id, dstPort, payloadLen)
-}
-
-// firstFragmentTCP builds the first fragment of a fragmented TCP datagram: the
-// full 20-byte TCP header plus 12 bytes of data, with the More Fragments flag
-// set and offset zero.
-func firstFragmentTCP(tb testing.TB, id uint16, dstPort uint16) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       id,
-		Protocol: layers.IPProtocolTCP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(fragTestDst),
-		Flags:    layers.IPv4MoreFragments,
-	}
-	tcp := &layers.TCP{SrcPort: 40000, DstPort: layers.TCPPort(dstPort), SYN: true, Window: 64240}
-	require.NoError(tb, tcp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, tcp, gopacket.Payload(make([]byte, 12))))
-	return buf.Bytes()
-}
-
-// trailingFragmentTo builds a non-first fragment to the given destination: an
-// IPv4 header at the given fragment offset (in 8-byte units) carrying raw
-// payload and no L4 header.
-func trailingFragmentTo(tb testing.TB, dst string, proto layers.IPProtocol, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:    4,
-		TTL:        64,
-		Id:         id,
-		Protocol:   proto,
-		SrcIP:      net.ParseIP(fragTestSrc),
-		DstIP:      net.ParseIP(dst),
-		FragOffset: fragOffsetOctets,
-	}
-	if moreFragments {
-		ip.Flags = layers.IPv4MoreFragments
-	}
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func trailingFragment(tb testing.TB, id uint16, fragOffsetOctets uint16, moreFragments bool, payloadLen int) []byte {
-	tb.Helper()
-	return trailingFragmentTo(tb, fragTestDst, layers.IPProtocolUDP, id, fragOffsetOctets, moreFragments, payloadLen)
-}
-
-// outboundUDPPacket builds a complete outbound UDP packet from the local
-// address, used to establish conntrack state for reply-direction tests.
-func outboundUDPPacket(tb testing.TB, srcPort, dstPort uint16) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       1,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestDst),
-		DstIP:    net.ParseIP(fragTestSrc),
-	}
-	udp := &layers.UDP{SrcPort: layers.UDPPort(srcPort), DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, 16))))
-	return buf.Bytes()
-}
-
-// normalUDPPacket builds a complete, non-fragmented UDP packet for baseline
-// comparisons against the fragment paths.
-func normalUDPPacket(tb testing.TB, dstPort uint16, payloadLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv4{
-		Version:  4,
-		TTL:      64,
-		Id:       1,
-		Protocol: layers.IPProtocolUDP,
-		SrcIP:    net.ParseIP(fragTestSrc),
-		DstIP:    net.ParseIP(fragTestDst),
-	}
-	udp := &layers.UDP{SrcPort: 40000, DstPort: layers.UDPPort(dstPort)}
-	require.NoError(tb, udp.SetNetworkLayerForChecksum(ip))
-
-	buf := gopacket.NewSerializeBuffer()
-	opts := gopacket.SerializeOptions{ComputeChecksums: true, FixLengths: true}
-	require.NoError(tb, gopacket.SerializeLayers(buf, opts, ip, udp, gopacket.Payload(make([]byte, payloadLen))))
-	return buf.Bytes()
-}
-
-func allowUDP(tb testing.TB, m *Manager, dstPort uint16) {
-	tb.Helper()
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{dstPort}}, fw.ActionAccept, "")
-	require.NoError(tb, err)
-}
-
-// TestFragment_TrailingWithoutFirstDropped is the core bypass repro: a trailing
-// fragment with no allowed first fragment on record must be dropped. Before the
-// fix, filterInbound returned false (allow) for any fragment.
-func TestFragment_TrailingWithoutFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	frag := trailingFragment(t, 0x1234, 185, false, 40)
-	require.True(t, m.filterInbound(frag, len(frag)),
-		"trailing fragment without an allowed first fragment must be dropped")
-}
-
-// TestFragment_AllowedFirstPassesTrailing verifies that once a first fragment
-// passes the ACL, its trailing fragments inherit the allow verdict.
-func TestFragment_AllowedFirstPassesTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	// First fragment: UDP header (8) + 32 payload = 40 octets -> headerEnd = 5.
-	first := firstFragmentUDP(t, 0x2222, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed first fragment should pass and be recorded")
-
-	trailing := trailingFragment(t, 0x2222, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed datagram should pass")
-}
-
-// TestFragment_DeniedFirstDropsTrailing verifies that a first fragment blocked
-// by the ACL leaves no verdict, so its trailing fragments are dropped.
-func TestFragment_DeniedFirstDropsTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	// No accept rule: local traffic defaults to deny.
-
-	first := firstFragmentUDP(t, 0x3333, 9999, 32)
-	require.True(t, m.filterInbound(first, len(first)),
-		"first fragment to a blocked port should be dropped by the ACL")
-
-	trailing := trailingFragment(t, 0x3333, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of a denied datagram must be dropped")
-}
-
-// TestFragment_OverlappingHeaderDropped covers the RFC 1858 §4 / RFC 3128
-// overlapping-fragment rewrite: a trailing fragment starting inside the range
-// the ACL already inspected is dropped and poisons the datagram. TCP is used so
-// the overlap lands on real header bytes (the flags at byte 13).
-func TestFragment_OverlappingHeaderDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// First fragment: TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
-	first := firstFragmentTCP(t, 0x4444, 8080)
-	require.False(t, m.filterInbound(first, len(first)))
-
-	// Overlapping fragment at offset 1 (byte 8) falls inside the inspected TCP
-	// header, so it could rewrite the flags or port on reassembly.
-	overlap := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 1, true, 32)
-	require.True(t, m.filterInbound(overlap, len(overlap)),
-		"fragment overlapping the inspected header must be dropped")
-
-	// The datagram is now poisoned: a later, non-overlapping fragment is also
-	// dropped because the verdict was removed.
-	later := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x4444, 4, false, 24)
-	require.True(t, m.filterInbound(later, len(later)),
-		"fragments after an overlap must be dropped (datagram poisoned)")
-}
-
-// TestFragment_OffsetZeroOverlapPoisons covers the RFC 3128 offset-zero rewrite:
-// an allowed first fragment followed by a denied offset-zero fragment for the
-// same datagram must not leave the earlier allow verdict in place.
-func TestFragment_OffsetZeroOverlapPoisons(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	allowed := firstFragmentUDP(t, 0x5A5A, 8080, 32)
-	require.False(t, m.filterInbound(allowed, len(allowed)),
-		"allowed first fragment should pass and be recorded")
-
-	// A second offset-zero fragment to a denied port supersedes the datagram's
-	// verdict; it is dropped and must not leave the allow in place.
-	denied := firstFragmentUDP(t, 0x5A5A, 9999, 32)
-	require.True(t, m.filterInbound(denied, len(denied)),
-		"denied offset-zero fragment must be dropped")
-
-	trailing := trailingFragment(t, 0x5A5A, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment must be denied after the datagram was poisoned")
-}
-
-// TestFragment_TinyFirstDropped covers the tiny-fragment attack: a first
-// fragment too small to contain the full transport header can't be
-// ACL-evaluated and must be dropped.
-func TestFragment_TinyFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	// IPv4 header + 4 raw bytes, MF set, offset 0: too small for the 8-byte UDP
-	// header, so it decodes to L3 only.
-	tiny := trailingFragment(t, 0x5555, 0, true, 4)
-	require.True(t, m.filterInbound(tiny, len(tiny)),
-		"tiny first fragment without a full L4 header must be dropped")
-}
-
-// TestFragment_TCPFirstFragment verifies the TCP arm of the transport decode: a
-// first fragment carrying the full 20-byte TCP header is ACL-evaluated and its
-// trailing fragments inherit the verdict.
-func TestFragment_TCPFirstFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// TCP header (20) + 12 data = 32 bytes -> headerEnd = 4 octets.
-	first := firstFragmentTCP(t, 0x6666, 8080)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed TCP first fragment should pass and be recorded")
-
-	trailing := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x6666, 4, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed TCP datagram should pass")
-}
-
-// TestFragment_TCPTinyFirstDropped verifies the TCP minimum header length: 12
-// bytes would satisfy a UDP header but falls short of the 20-byte TCP header.
-func TestFragment_TCPTinyFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrc), fw.ProtocolTCP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	tiny := trailingFragmentTo(t, fragTestDst, layers.IPProtocolTCP, 0x7777, 0, true, 12)
-	require.True(t, m.filterInbound(tiny, len(tiny)),
-		"first fragment shorter than the TCP header must be dropped")
-}
-
-// TestFragment_ConntrackAllowsFirstFragment verifies the conntrack branch: reply
-// fragments of an outbound-established UDP flow pass without any inbound rule.
-func TestFragment_ConntrackAllowsFirstFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	out := outboundUDPPacket(t, 12345, 40000)
-	require.False(t, m.filterOutbound(out, len(out)))
-
-	first := firstFragmentUDP(t, 0x8888, 12345, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"reply first fragment should pass via conntrack")
-
-	trailing := trailingFragment(t, 0x8888, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of a tracked flow should pass")
-}
-
-// TestFragment_RoutingDisabledDropsFragment verifies routed first fragments are
-// dropped when routing is disabled.
-func TestFragment_RoutingDisabledDropsFragment(t *testing.T) {
-	m := newFragmentTestManager(t)
-	m.routingEnabled.Store(false)
-
-	first := firstFragmentUDPTo(t, "198.51.100.10", 0x9999, 8080, 32)
-	require.True(t, m.filterInbound(first, len(first)),
-		"routed first fragment must be dropped when routing is disabled")
-}
-
-// TestFragment_RouteACL verifies the route-ACL branch: fragments to a non-local
-// destination follow the route rules, allowed datagrams pass their trailing
-// fragments and denied ones don't.
-func TestFragment_RouteACL(t *testing.T) {
-	m := newFragmentTestManager(t)
-	m.routingEnabled.Store(true)
-	m.nativeRouter.Store(false)
-
-	_, err := m.AddRouteFiltering(
-		[]byte("rt-1"),
-		[]netip.Prefix{netip.MustParsePrefix("100.10.0.0/16")},
-		fw.Network{Prefix: netip.MustParsePrefix("198.51.100.0/24")},
-		fw.ProtocolUDP,
-		nil,
-		&fw.Port{Values: []uint16{8080}},
-		fw.ActionAccept,
-	)
-	require.NoError(t, err)
-
-	first := firstFragmentUDPTo(t, "198.51.100.10", 0xAAAA, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"route-ACL-allowed first fragment should pass")
-	trailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xAAAA, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed routed datagram should pass")
-
-	denied := firstFragmentUDPTo(t, "198.51.100.10", 0xBBBB, 9999, 32)
-	require.True(t, m.filterInbound(denied, len(denied)),
-		"route-ACL-denied first fragment must be dropped")
-	deniedTrailing := trailingFragmentTo(t, "198.51.100.10", layers.IPProtocolUDP, 0xBBBB, 5, false, 24)
-	require.True(t, m.filterInbound(deniedTrailing, len(deniedTrailing)),
-		"trailing fragment of a denied routed datagram must be dropped")
-}
-
-// TestFragment_ExpiredVerdictDropsTrailing verifies a verdict older than the
-// tracker timeout no longer admits trailing fragments.
-func TestFragment_ExpiredVerdictDropsTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	first := firstFragmentUDP(t, 0xCCCC, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)))
-
-	m.fragments.mutex.Lock()
-	for key, entry := range m.fragments.entries {
-		entry.recordedAt = time.Now().Add(-defaultFragmentTimeout - time.Second)
-		m.fragments.entries[key] = entry
-	}
-	m.fragments.mutex.Unlock()
-
-	trailing := trailingFragment(t, 0xCCCC, 5, false, 24)
-	require.True(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment after verdict expiry must be dropped")
-}
-
-// TestFragment_CapacityFailsClosed verifies the table cap: at capacity, new
-// datagram verdicts are not recorded (their trailing fragments are dropped)
-// while already-recorded datagrams keep working.
-func TestFragment_CapacityFailsClosed(t *testing.T) {
-	m := newFragmentTestManager(t)
-	allowUDP(t, m, 8080)
-
-	m.fragments.mutex.Lock()
-	m.fragments.maxEntries = 1
-	m.fragments.mutex.Unlock()
-
-	first1 := firstFragmentUDP(t, 0x0101, 8080, 32)
-	require.False(t, m.filterInbound(first1, len(first1)))
-
-	first2 := firstFragmentUDP(t, 0x0202, 8080, 32)
-	require.False(t, m.filterInbound(first2, len(first2)),
-		"first fragment itself still passes at capacity")
-
-	trailing2 := trailingFragment(t, 0x0202, 5, false, 24)
-	require.True(t, m.filterInbound(trailing2, len(trailing2)),
-		"trailing fragment of an unrecorded datagram must be dropped at capacity")
-
-	trailing1 := trailingFragment(t, 0x0101, 5, false, 24)
-	require.False(t, m.filterInbound(trailing1, len(trailing1)),
-		"already-recorded datagram should keep passing at capacity")
-}
-
-// v6FragmentHeader builds the 8-byte IPv6 fragment extension header for the
-// given inner protocol, offset (8-byte units), More Fragments bit and id.
-func v6FragmentHeader(proto layers.IPProtocol, offsetOctets uint16, moreFragments bool, id uint32) []byte {
-	offsetFlags := offsetOctets << 3
-	if moreFragments {
-		offsetFlags |= 1
-	}
-	hdr := make([]byte, 8)
-	hdr[0] = uint8(proto)
-	binary.BigEndian.PutUint16(hdr[2:4], offsetFlags)
-	binary.BigEndian.PutUint32(hdr[4:8], id)
-	return hdr
-}
-
-func v6UDPHeader(dstPort uint16, dataLen int) []byte {
-	hdr := make([]byte, 8)
-	binary.BigEndian.PutUint16(hdr[0:2], 40000)
-	binary.BigEndian.PutUint16(hdr[2:4], dstPort)
-	binary.BigEndian.PutUint16(hdr[4:6], uint16(8+dataLen))
-	return hdr
-}
-
-// firstFragmentUDPv6 builds the first fragment of a fragmented IPv6 UDP
-// datagram: fragment header (offset 0, More Fragments set) + full UDP header +
-// data.
-func firstFragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int) []byte {
-	tb.Helper()
-	return fragmentUDPv6(tb, id, dstPort, dataLen, true)
-}
-
-// fragmentUDPv6 builds an offset-zero IPv6 UDP fragment. With moreFragments
-// false it is an atomic fragment (a complete datagram, RFC 6946).
-func fragmentUDPv6(tb testing.TB, id uint32, dstPort uint16, dataLen int, moreFragments bool) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv6{
-		Version:    6,
-		NextHeader: layers.IPProtocolIPv6Fragment,
-		HopLimit:   64,
-		SrcIP:      net.ParseIP(fragTestSrcV6),
-		DstIP:      net.ParseIP(fragTestDstV6),
-	}
-	payload := append(v6FragmentHeader(layers.IPProtocolUDP, 0, moreFragments, id), v6UDPHeader(dstPort, dataLen)...)
-	payload = append(payload, make([]byte, dataLen)...)
-
-	buf := gopacket.NewSerializeBuffer()
-	require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
-	return buf.Bytes()
-}
-
-// trailingFragmentV6 builds a non-first IPv6 fragment: fragment header at the
-// given offset carrying raw data and no transport header.
-func trailingFragmentV6(tb testing.TB, id uint32, offsetOctets uint16, moreFragments bool, dataLen int) []byte {
-	tb.Helper()
-
-	ip := &layers.IPv6{
-		Version:    6,
-		NextHeader: layers.IPProtocolIPv6Fragment,
-		HopLimit:   64,
-		SrcIP:      net.ParseIP(fragTestSrcV6),
-		DstIP:      net.ParseIP(fragTestDstV6),
-	}
-	payload := append(v6FragmentHeader(layers.IPProtocolUDP, offsetOctets, moreFragments, id), make([]byte, dataLen)...)
-
-	buf := gopacket.NewSerializeBuffer()
-	require.NoError(tb, gopacket.SerializeLayers(buf, gopacket.SerializeOptions{FixLengths: true}, ip, gopacket.Payload(payload)))
-	return buf.Bytes()
-}
-
-// TestFragmentV6_TrailingWithoutFirstDropped verifies the IPv6 bypass is closed:
-// a trailing fragment with no allowed first fragment is dropped.
-func TestFragmentV6_TrailingWithoutFirstDropped(t *testing.T) {
-	m := newFragmentTestManager(t)
-
-	frag := trailingFragmentV6(t, 0xAABBCCDD, 100, false, 40)
-	require.True(t, m.filterInbound(frag, len(frag)),
-		"IPv6 trailing fragment without an allowed first fragment must be dropped")
-}
-
-// TestFragmentV6_AllowedFirstPassesTrailing verifies IPv6 fragments are
-// evaluated like IPv4: an allowed first fragment lets its trailing fragments
-// through.
-func TestFragmentV6_AllowedFirstPassesTrailing(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	// First fragment: UDP header (8) + 32 data = 40 octets -> headerEnd = 5.
-	first := firstFragmentUDPv6(t, 0xAABBCCDD, 8080, 32)
-	require.False(t, m.filterInbound(first, len(first)),
-		"allowed IPv6 first fragment should pass and be recorded")
-
-	trailing := trailingFragmentV6(t, 0xAABBCCDD, 5, false, 24)
-	require.False(t, m.filterInbound(trailing, len(trailing)),
-		"trailing fragment of an allowed IPv6 datagram should pass")
-}
-
-// TestFragmentV6_AtomicNotCached verifies an IPv6 atomic fragment (fragment
-// header with offset 0 and no More Fragments, a complete datagram per RFC 6946)
-// is evaluated but not recorded, so a flood of allowed atomic fragments can't
-// exhaust the verdict table.
-func TestFragmentV6_AtomicNotCached(t *testing.T) {
-	m := newFragmentTestManager(t)
-	_, err := m.AddPeerFiltering(nil, net.ParseIP(fragTestSrcV6), fw.ProtocolUDP, nil,
-		&fw.Port{Values: []uint16{8080}}, fw.ActionAccept, "")
-	require.NoError(t, err)
-
-	atomic := fragmentUDPv6(t, 0xA70301C, 8080, 16, false)
-	require.False(t, m.filterInbound(atomic, len(atomic)),
-		"allowed IPv6 atomic fragment should pass")
-
-	m.fragments.mutex.Lock()
-	n := len(m.fragments.entries)
-	m.fragments.mutex.Unlock()
-	require.Zero(t, n, "atomic fragment must not create a verdict entry")
-
-	// A genuine fragmented datagram (More Fragments set) is still recorded.
-	first := fragmentUDPv6(t, 0xBEEF, 8080, 32, true)
-	require.False(t, m.filterInbound(first, len(first)))
-	m.fragments.mutex.Lock()
-	n = len(m.fragments.entries)
-	m.fragments.mutex.Unlock()
-	require.Equal(t, 1, n, "genuine first fragment must record a verdict")
-}

client/iface/iface_test.go

@@ -464,8 +464,6 @@ func Test_RemovePeer(t *testing.T) {
 }
 
 func Test_ConnectPeers(t *testing.T) {
-	t.Setenv("NB_DISABLE_EBPF_WG_PROXY", "true")
-
 	peer1ifaceName := fmt.Sprintf("utun%d", WgIntNumber+400)
 	peer1wgIP := netip.MustParsePrefix("10.99.99.17/30")
 	peer1Key, _ := wgtypes.GeneratePrivateKey()
@@ -507,8 +505,12 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	localIP1 := "127.0.0.1"
-	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort))
+	localIP, err := getLocalIP()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer1wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -544,8 +546,7 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	localIP2 := "127.0.0.1"
-	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort))
+	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer2wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -568,17 +569,17 @@ func Test_ConnectPeers(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	// The peers use userspace WireGuard (stdnet transport). A tight busy-loop
-	// here starves the wireguard-go goroutines that process the handshake, so
-	// poll on a ticker instead and yield the CPU between checks. WireGuard also
-	// only retries a lost handshake initiation every REKEY_TIMEOUT (5s), which
-	// is why the overall wait can occasionally stretch to tens of seconds.
+	// todo: investigate why in some tests execution we need 30s
 	timeout := 30 * time.Second
 	timeoutChannel := time.After(timeout)
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
 
 	for {
+		select {
+		case <-timeoutChannel:
+			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
+		default:
+		}
+
 		peer, gpErr := getPeer(peer1ifaceName, peer2Key.PublicKey().String())
 		if gpErr != nil {
 			t.Fatal(gpErr)
@@ -587,12 +588,6 @@ func Test_ConnectPeers(t *testing.T) {
 			t.Log("peers successfully handshake")
 			break
 		}
-
-		select {
-		case <-timeoutChannel:
-			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
-		case <-ticker.C:
-		}
 	}
 
 }
@@ -620,3 +615,28 @@ func getPeer(ifaceName, peerPubKey string) (wgtypes.Peer, error) {
 	}
 	return wgtypes.Peer{}, fmt.Errorf("peer not found")
 }
+
+func getLocalIP() (string, error) {
+	// Get all interfaces
+	addrs, err := net.InterfaceAddrs()
+	if err != nil {
+		return "", err
+	}
+
+	for _, addr := range addrs {
+		ipNet, ok := addr.(*net.IPNet)
+		if !ok {
+			continue
+		}
+		if ipNet.IP.IsLoopback() {
+			continue
+		}
+
+		if ipNet.IP.To4() == nil {
+			continue
+		}
+		return ipNet.IP.String(), nil
+	}
+
+	return "", fmt.Errorf("no local IP found")
+}

client/iface/netstack/env.go

@@ -3,31 +3,14 @@
 package netstack
 
 import (
-	"net"
+	"fmt"
 	"os"
 	"strconv"
 
 	log "github.com/sirupsen/logrus"
 )
 
-const (
-	EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
-
-	// EnvSocks5ListenerPort overrides the port the SOCKS5 proxy listens on.
-	EnvSocks5ListenerPort = "NB_SOCKS5_LISTENER_PORT"
-
-	// EnvSocks5ListenerAddress overrides the host/IP the SOCKS5 proxy binds to.
-	// The proxy is a bridge for local host applications into the userspace
-	// WireGuard netstack, so it binds to loopback by default. Override this only
-	// when the proxy must be reachable from other hosts (e.g. a container
-	// gateway); doing so exposes an unauthenticated SOCKS5 proxy on that
-	// address.
-	EnvSocks5ListenerAddress = "NB_SOCKS5_LISTENER_ADDRESS"
-
-	// defaultSocks5Host is the loopback address the SOCKS5 proxy binds to unless
-	// overridden via EnvSocks5ListenerAddress.
-	defaultSocks5Host = "127.0.0.1"
-)
+const EnvUseNetstackMode = "NB_USE_NETSTACK_MODE"
 
 // IsEnabled todo: move these function to cmd layer
 func IsEnabled() bool {
@@ -35,40 +18,24 @@ func IsEnabled() bool {
 }
 
 func ListenAddr() string {
-	return net.JoinHostPort(listenHost(), strconv.Itoa(listenPort()))
-}
-
-// listenHost returns the host/IP the SOCKS5 proxy binds to. It defaults to
-// loopback and only honors EnvSocks5ListenerAddress when it holds a valid IP.
-func listenHost() string {
-	addr := os.Getenv(EnvSocks5ListenerAddress)
-	if addr == "" {
-		return defaultSocks5Host
-	}
-	if net.ParseIP(addr) == nil {
-		log.Warnf("invalid socks5 listener address %q, falling back to default: %s", addr, defaultSocks5Host)
-		return defaultSocks5Host
-	}
-	return addr
-}
-
-// listenPort returns the port the SOCKS5 proxy binds to, defaulting to
-// DefaultSocks5Port when EnvSocks5ListenerPort is unset or invalid.
-func listenPort() int {
-	sPort := os.Getenv(EnvSocks5ListenerPort)
+	sPort := os.Getenv("NB_SOCKS5_LISTENER_PORT")
 	if sPort == "" {
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 
 	port, err := strconv.Atoi(sPort)
 	if err != nil {
 		log.Warnf("invalid socks5 listener port, unable to convert it to int, falling back to default: %d", DefaultSocks5Port)
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 	if port < 1 || port > 65535 {
 		log.Warnf("invalid socks5 listener port, it should be in the range 1-65535, falling back to default: %d", DefaultSocks5Port)
-		return DefaultSocks5Port
+		return listenAddr(DefaultSocks5Port)
 	}
 
-	return port
+	return listenAddr(port)
+}
+
+func listenAddr(port int) string {
+	return fmt.Sprintf("0.0.0.0:%d", port)
 }

client/iface/netstack/env_test.go

@@ -1,63 +0,0 @@
-//go:build !js
-
-package netstack
-
-import (
-	"net"
-	"strconv"
-	"testing"
-)
-
-func TestListenAddr_DefaultsToLoopback(t *testing.T) {
-	// No env overrides: must bind loopback, never all interfaces.
-	got := ListenAddr()
-	want := net.JoinHostPort("127.0.0.1", strconv.Itoa(DefaultSocks5Port))
-	if got != want {
-		t.Fatalf("ListenAddr() = %q, want %q", got, want)
-	}
-}
-
-func TestListenAddr_AddressOverride(t *testing.T) {
-	tests := []struct {
-		name string
-		env  string
-		want string
-	}{
-		{name: "valid override honored", env: "0.0.0.0", want: "0.0.0.0"},
-		{name: "valid specific ip honored", env: "10.0.0.5", want: "10.0.0.5"},
-		{name: "ipv6 loopback bracketed", env: "::1", want: "::1"},
-		{name: "invalid falls back to loopback", env: "not-an-ip", want: "127.0.0.1"},
-		{name: "empty falls back to loopback", env: "", want: "127.0.0.1"},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(EnvSocks5ListenerAddress, tc.env)
-			want := net.JoinHostPort(tc.want, strconv.Itoa(DefaultSocks5Port))
-			if got := ListenAddr(); got != want {
-				t.Fatalf("ListenAddr() = %q, want %q", got, want)
-			}
-		})
-	}
-}
-
-func TestListenAddr_PortOverride(t *testing.T) {
-	tests := []struct {
-		name string
-		env  string
-		want int
-	}{
-		{name: "valid port honored", env: "1081", want: 1081},
-		{name: "non-numeric falls back", env: "abc", want: DefaultSocks5Port},
-		{name: "out of range falls back", env: "70000", want: DefaultSocks5Port},
-		{name: "zero falls back", env: "0", want: DefaultSocks5Port},
-	}
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(EnvSocks5ListenerPort, tc.env)
-			want := net.JoinHostPort("127.0.0.1", strconv.Itoa(tc.want))
-			if got := ListenAddr(); got != want {
-				t.Fatalf("ListenAddr() = %q, want %q", got, want)
-			}
-		})
-	}
-}

client/internal/auth/auth.go

@@ -351,7 +351,6 @@ func (a *Auth) setSystemInfoFlags(info *system.Info) {
 		a.config.BlockLANAccess,
 		a.config.BlockInbound,
 		a.config.DisableIPv6,
-		a.config.SyncMessageVersion,
 		a.config.EnableSSHRoot,
 		a.config.EnableSSHSFTP,
 		a.config.EnableSSHLocalPortForwarding,

client/internal/auth/device_flow.go

@@ -299,7 +299,7 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 				UseIDToken:   d.providerConfig.UseIDToken,
 			}
 
-			err = validateTokenAudience(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
+			err = isValidAccessToken(tokenInfo.GetTokenToUse(), d.providerConfig.Audience)
 			if err != nil {
 				return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
 			}

client/internal/auth/pkce_flow.go

@@ -306,7 +306,7 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
 		audience = p.providerConfig.ClientID
 	}
 
-	if err := validateTokenAudience(tokenInfo.GetTokenToUse(), audience); err != nil {
+	if err := isValidAccessToken(tokenInfo.GetTokenToUse(), audience); err != nil {
 		return TokenInfo{}, fmt.Errorf("authentication failed: invalid access token - %w", err)
 	}
 
@@ -320,11 +320,6 @@ func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo,
 	return tokenInfo, nil
 }
 
-// parseEmailFromIDToken extracts the email (or name) claim from an ID token
-// without verifying its signature. The value is best-effort and used only as a
-// UX convenience (login hint prefill and display); it never drives an
-// authorization decision. The authoritative identity is established server-side
-// from the signature-verified token.
 func parseEmailFromIDToken(token string) (string, error) {
 	parts := strings.Split(token, ".")
 	if len(parts) < 2 {

client/internal/auth/sessionwatch/watcher.go

@@ -24,7 +24,11 @@ import (
 )
 
 const (
-	maxPastHorizon = 30 * 24 * time.Hour
+	// Skew tolerates a small clock difference between the management
+	// server and this peer before treating a deadline as "in the past".
+	// Slightly above typical NTP drift; tight enough that the UI doesn't
+	// paint a stale expiry as if it were valid.
+	Skew = 30 * time.Second
 
 	// maxDeadlineHorizon caps how far in the future an accepted deadline
 	// can sit. A timestamp beyond this is almost certainly a protocol
@@ -53,7 +57,7 @@ var (
 	ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future")
 
 	// ErrDeadlineInPast is returned by Update when the supplied deadline
-	// is more than maxPastHorizon in the past.
+	// is more than Skew in the past.
 	ErrDeadlineInPast = errors.New("session deadline in the past")
 )
 
@@ -62,14 +66,15 @@ var (
 // for deadline change/clear, PublishEvent for the two warnings); tests pass
 // a fake recorder so the same surface is observable without an engine.
 //
-// While the watcher runs, it owns the deadline propagated to the recorder:
-// every set, clear and sanity-check rejection routes the value through
-// SetSessionExpiresAt, so the SubscribeStatus snapshot the UI reads can
-// never drift from the watcher's timer state. (SetSessionExpiresAt fans
-// out its own state-change notification, so no separate notify is needed.)
-// The recorder is server-scoped and outlives this engine-scoped watcher;
-// Close deliberately leaves the recorder value in place so transient engine
-// restarts don't blank it — the client run loop clears it on real teardown.
+// The watcher is the single owner of the deadline propagated to the
+// recorder: every set, clear, sanity-check rejection and Close routes the
+// value through SetSessionExpiresAt, so the SubscribeStatus snapshot the UI
+// reads can never drift from the watcher's timer state. (SetSessionExpiresAt
+// fans out its own state-change notification, so no separate notify is
+// needed.) The recorder is server-scoped and outlives this engine-scoped
+// watcher — without the Close-time clear a teardown (Down, or the Down+Up of
+// a profile switch) would leave the next session showing the previous one's
+// stale "expires in" value.
 //
 // PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher
 // composes the metadata internally so the wire format (MetaSession*) is
@@ -130,13 +135,10 @@ func NewWithLeads(lead, final time.Duration, recorder StatusRecorder) *Watcher {
 // was disabled).
 //
 // Same-value updates are no-ops. A different non-zero value cancels any
-// pending timer, resets the "already fired" guards, and — when the
-// deadline lies in the future — arms fresh warning timers. A deadline
-// already in the past (within maxPastHorizon) is recorded as-is with no
-// timers: the session has expired and consumers render it that way.
+// pending timer, resets the "already fired" guard, and arms a new one.
 //
 // Returns one of the sentinel Err* values when the deadline fails the
-// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon).
+// sanity checks (pre-epoch, far future, or in the past beyond Skew).
 // In every error case the watcher first clears its state so it stays
 // consistent with what the caller will push into its other sinks (e.g.
 // applySessionDeadline forces a zero deadline into the status recorder
@@ -161,7 +163,7 @@ func (w *Watcher) Update(deadline time.Time) error {
 	case deadline.After(now.Add(maxDeadlineHorizon)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v", ErrDeadlineTooFarFuture, deadline)
-	case deadline.Before(now.Add(-maxPastHorizon)):
+	case deadline.Before(now.Add(-Skew)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now)
 	}
@@ -181,9 +183,7 @@ func (w *Watcher) Update(deadline time.Time) error {
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
 
-	if deadline.After(now) {
-		w.armTimerLocked(deadline)
-	}
+	w.armTimerLocked(deadline)
 	recorder := w.recorder
 	w.mu.Unlock()
 	if recorder != nil {
@@ -227,25 +227,30 @@ func (w *Watcher) Dismiss() {
 	log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339))
 }
 
-// Close stops any pending timer. Update calls after Close are ignored.
-// The recorder keeps its deadline: the watcher is engine-scoped and closes
-// on every engine restart (network change, sleep/wake, stream errors)
-// while the SSO deadline stays valid across those, so clearing here would
-// blank the UI's "expires in" row on every transient reconnect. The
-// client run loop clears the server-scoped recorder when it exits for
-// real (Down, profile switch, permanent login failure).
+// Close stops any pending timer and drops the deadline on the status
+// recorder. Update calls after Close are ignored. Clearing the recorder
+// here is what keeps a teardown (Down, or the Down+Up of a profile switch)
+// from leaving the next session showing this one's stale "expires in"
+// value — the recorder is server-scoped and outlives this engine-scoped
+// watcher, so nothing else drops the anchor on teardown.
 func (w *Watcher) Close() {
 	w.mu.Lock()
-	defer w.mu.Unlock()
 	if w.closed {
+		w.mu.Unlock()
 		return
 	}
 	w.closed = true
 	w.stopTimerLocked()
+	hadDeadline := !w.current.IsZero()
 	w.current = time.Time{}
 	w.firedAt = time.Time{}
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
+	recorder := w.recorder
+	w.mu.Unlock()
+	if recorder != nil && hadDeadline {
+		recorder.SetSessionExpiresAt(time.Time{})
+	}
 }
 
 // clearLocked drops the tracked deadline and notifies the recorder so

client/internal/auth/sessionwatch/watcher_test.go

@@ -224,13 +224,11 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) {
 
 func TestRefreshAfterFireArmsNewWarning(t *testing.T) {
 	r := &fakeRecorder{}
-	lead := 150 * time.Millisecond
+	lead := 30 * time.Millisecond
 	w := newWatcher(lead, r)
 	defer w.Close()
 
-	// Warning fires ~20ms in; the deadline itself stays 150ms away so the
-	// replacement below lands well before it.
-	first := time.Now().Add(170 * time.Millisecond)
+	first := time.Now().Add(50 * time.Millisecond)
 	_ = w.Update(first)
 
 	// Wait for stateChange + warning of the first cycle.
@@ -308,29 +306,7 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) {
 	}
 }
 
-func TestUpdateRecentPastRecordedAsExpired(t *testing.T) {
-	r := &fakeRecorder{}
-	w := newWatcher(50*time.Millisecond, r)
-	defer w.Close()
-
-	d := time.Now().Add(-1 * time.Hour)
-	if err := w.Update(d); err != nil {
-		t.Fatalf("recent-past Update should succeed, got %v", err)
-	}
-	if !w.Deadline().Equal(d) {
-		t.Fatalf("expected deadline to be recorded, got %v want %v", w.Deadline(), d)
-	}
-	if got := r.deadline(); !got.Equal(d) {
-		t.Fatalf("recorder deadline = %v, want %v", got, d)
-	}
-
-	time.Sleep(80 * time.Millisecond)
-	if n := countWhere(r.snapshot(), func(e event) bool { return e.kind == publish }); n != 0 {
-		t.Fatalf("no warning events may fire for an already-past deadline, got %+v", r.snapshot())
-	}
-}
-
-func TestUpdateAncientPastRejected(t *testing.T) {
+func TestUpdateInPastClearsDeadline(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	defer w.Close()
@@ -342,12 +318,12 @@ func TestUpdateAncientPastRejected(t *testing.T) {
 	// Drain the stateChange from the seed.
 	waitForEvents(t, r, 1)
 
-	err := w.Update(time.Now().Add(-31 * 24 * time.Hour))
+	err := w.Update(time.Now().Add(-1 * time.Hour))
 	if !errors.Is(err, ErrDeadlineInPast) {
 		t.Fatalf("want ErrDeadlineInPast, got %v", err)
 	}
 	if !w.Deadline().IsZero() {
-		t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline())
+		t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline())
 	}
 	events := waitForEvents(t, r, 2)
 	if events[1].kind != stateChange {
@@ -355,25 +331,39 @@ func TestUpdateAncientPastRejected(t *testing.T) {
 	}
 }
 
+func TestUpdateWithinSkewAccepted(t *testing.T) {
+	r := &fakeRecorder{}
+	w := newWatcher(50*time.Millisecond, r)
+	defer w.Close()
+
+	// 5 seconds in the past is within the 30s Skew tolerance — accept it.
+	d := time.Now().Add(-5 * time.Second)
+	if err := w.Update(d); err != nil {
+		t.Fatalf("within-skew Update should succeed, got %v", err)
+	}
+	if !w.Deadline().Equal(d) {
+		t.Fatalf("expected deadline to be applied, got %v want %v", w.Deadline(), d)
+	}
+}
+
 func TestCloseSilencesUpdates(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	w.Close()
 
-	if err := w.Update(time.Now().Add(time.Hour)); err != nil {
-		t.Fatalf("Update after Close: want nil, got %v", err)
-	}
+	_ = w.Update(time.Now().Add(time.Hour))
+
+	time.Sleep(20 * time.Millisecond)
 	if got := r.snapshot(); len(got) != 0 {
 		t.Fatalf("expected no events after Close, got %+v", got)
 	}
 }
 
-// TestCloseKeepsRecorderDeadline pins the reconnect-flap fix: the watcher
-// closes on every engine restart (network change, sleep/wake) while the
-// SSO deadline stays valid across those, so Close must leave the
-// server-scoped recorder's value in place. The client run loop clears the
-// recorder when it exits for real.
-func TestCloseKeepsRecorderDeadline(t *testing.T) {
+// TestCloseClearsRecorderDeadline pins the profile-switch fix: a watcher
+// holding a live deadline must zero the recorder on Close so the next
+// engine's watcher (and the UI reading the shared server-scoped recorder)
+// doesn't start out showing the previous session's stale "expires in".
+func TestCloseClearsRecorderDeadline(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(time.Hour, r)
 
@@ -387,8 +377,8 @@ func TestCloseKeepsRecorderDeadline(t *testing.T) {
 
 	w.Close()
 
-	if got := r.deadline(); !got.Equal(d) {
-		t.Fatalf("recorder deadline after Close = %v, want %v", got, d)
+	if got := r.deadline(); !got.IsZero() {
+		t.Fatalf("recorder deadline after Close = %v, want zero", got)
 	}
 }
 

client/internal/auth/util.go

@@ -20,26 +20,14 @@ func randomBytesInHex(count int) (string, error) {
 	return hex.EncodeToString(buf), nil
 }
 
-// validateTokenAudience checks that the token is a well-formed JWT whose
-// audience claim matches the expected audience.
-//
-// It does NOT verify the token's cryptographic signature and therefore must not
-// be treated as an authenticity check. The token is obtained by the client
-// directly from the IdP token endpoint over TLS, and its signature is verified
-// server-side by the management server against the IdP's JWKS
-// (see shared/auth/jwt/validator.go). This function is only a client-side
-// sanity check that the returned token targets the expected audience.
-func validateTokenAudience(token string, audience string) error {
+// isValidAccessToken is a simple validation of the access token
+func isValidAccessToken(token string, audience string) error {
 	if token == "" {
 		return fmt.Errorf("token received is empty")
 	}
 
-	parts := strings.Split(token, ".")
-	if len(parts) != 3 {
-		return fmt.Errorf("token is not a well-formed JWT")
-	}
-
-	claimsString, err := base64.RawURLEncoding.DecodeString(parts[1])
+	encodedClaims := strings.Split(token, ".")[1]
+	claimsString, err := base64.RawURLEncoding.DecodeString(encodedClaims)
 	if err != nil {
 		return err
 	}

client/internal/auth/util_test.go

@@ -1,108 +0,0 @@
-package auth
-
-import (
-	"encoding/base64"
-	"encoding/json"
-	"testing"
-)
-
-// makeJWT builds an unsigned JWT-shaped string (header.payload.signature) with
-// the given claims payload. The signature part is arbitrary because
-// validateTokenAudience intentionally does not verify it.
-func makeJWT(t *testing.T, claims map[string]interface{}) string {
-	t.Helper()
-	header := base64.RawURLEncoding.EncodeToString([]byte(`{"alg":"RS256","typ":"JWT"}`))
-	payloadBytes, err := json.Marshal(claims)
-	if err != nil {
-		t.Fatalf("marshal claims: %v", err)
-	}
-	payload := base64.RawURLEncoding.EncodeToString(payloadBytes)
-	return header + "." + payload + ".unverified-signature"
-}
-
-func TestValidateTokenAudience(t *testing.T) {
-	tests := []struct {
-		name     string
-		token    string
-		audience string
-		wantErr  bool
-	}{
-		{
-			name:     "empty token",
-			token:    "",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "not a JWT - no dots",
-			token:    "notajwt",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "not a JWT - two parts only",
-			token:    "header.payload",
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "matching string audience",
-			token:    makeJWT(t, map[string]interface{}{"aud": "netbird"}),
-			audience: "netbird",
-			wantErr:  false,
-		},
-		{
-			name:     "mismatching string audience",
-			token:    makeJWT(t, map[string]interface{}{"aud": "other"}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "matching audience in array",
-			token:    makeJWT(t, map[string]interface{}{"aud": []interface{}{"other", "netbird"}}),
-			audience: "netbird",
-			wantErr:  false,
-		},
-		{
-			name:     "mismatching audience array",
-			token:    makeJWT(t, map[string]interface{}{"aud": []interface{}{"a", "b"}}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "missing audience claim",
-			token:    makeJWT(t, map[string]interface{}{"sub": "user"}),
-			audience: "netbird",
-			wantErr:  true,
-		},
-		{
-			name:     "invalid base64 payload",
-			token:    "header.!!!not-base64!!!.sig",
-			audience: "netbird",
-			wantErr:  true,
-		},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			err := validateTokenAudience(tc.token, tc.audience)
-			if tc.wantErr && err == nil {
-				t.Fatalf("expected error, got nil")
-			}
-			if !tc.wantErr && err != nil {
-				t.Fatalf("expected no error, got %v", err)
-			}
-		})
-	}
-}
-
-// TestValidateTokenAudienceNoPanic guards the regression where a non-empty
-// token without the JWT dot structure caused an index-out-of-range panic.
-func TestValidateTokenAudienceNoPanic(t *testing.T) {
-	inputs := []string{"a", ".", "a.", "aaaa", "no-dots-here"}
-	for _, in := range inputs {
-		if err := validateTokenAudience(in, "netbird"); err == nil {
-			t.Fatalf("expected error for malformed token %q, got nil", in)
-		}
-	}
-}

client/internal/conn_mgr.go

@@ -34,8 +34,6 @@ const (
 // - Handling connection establishment based on peer signaling
 //
 // The implementation is not thread-safe; it is protected by engine.syncMsgMux.
-// 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
 	statusRecorder   *peer.Status
@@ -44,26 +42,12 @@ type ConnMgr struct {
 	rosenpassEnabled bool
 
 	lazyConnMgr *manager.Manager
-	// lazyConnMgrMu guards the lazyConnMgr pointer for readers outside the
-	// engine loop (ActivatePeer). Writers hold it in addition to
-	// engine.syncMsgMux; all other reads stay under engine.syncMsgMux only.
-	lazyConnMgrMu sync.RWMutex
-
-	// reconcileRoutedIPs re-applies a peer's routed allowed IPs after its lazy wake endpoint is
-	// (re)armed (Mode A at arm time). Injected by the engine; nil disables the reconcile.
-	reconcileRoutedIPs func(peerKey string) error
 
 	wg            sync.WaitGroup
 	lazyCtx       context.Context
 	lazyCtxCancel context.CancelFunc
 }
 
-// SetRoutedIPsReconciler injects the callback used to re-apply a peer's routed allowed IPs when
-// its lazy wake endpoint is (re)armed. Must be called before the lazy manager starts.
-func (e *ConnMgr) SetRoutedIPsReconciler(fn func(peerKey string) error) {
-	e.reconcileRoutedIPs = fn
-}
-
 func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
 	e := &ConnMgr{
 		peerStore:        peerStore,
@@ -254,20 +238,12 @@ func (e *ConnMgr) RemovePeerConn(peerKey string) {
 	conn.Log.Infof("removed peer from lazy conn manager")
 }
 
-// ActivatePeer wakes an idle lazy connection. Unlike the rest of ConnMgr it is
-// safe for concurrent use: the lazy manager pointer is read under lazyConnMgrMu
-// and the manager itself is internally synchronized, so callers outside the
-// engine loop (DNS warm-up) do not need engine.syncMsgMux.
 func (e *ConnMgr) ActivatePeer(ctx context.Context, conn *peer.Conn) {
-	e.lazyConnMgrMu.RLock()
-	lazyConnMgr := e.lazyConnMgr
-	started := lazyConnMgr != nil && e.lazyCtxCancel != nil
-	e.lazyConnMgrMu.RUnlock()
-	if !started {
+	if !e.isStartedWithLazyMgr() {
 		return
 	}
 
-	if found := lazyConnMgr.ActivatePeer(conn.GetKey()); found {
+	if found := e.lazyConnMgr.ActivatePeer(conn.GetKey()); found {
 		if err := conn.Open(ctx); err != nil {
 			conn.Log.Errorf("failed to open connection: %v", err)
 		}
@@ -292,22 +268,16 @@ func (e *ConnMgr) Close() {
 
 	e.lazyCtxCancel()
 	e.wg.Wait()
-
-	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
-	e.lazyConnMgrMu.Unlock()
 }
 
 func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	cfg := manager.Config{
 		InactivityThreshold: inactivityThresholdEnv(),
-		ReconcileAllowedIPs: e.reconcileRoutedIPs,
 	}
-
-	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
+
 	e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
-	e.lazyConnMgrMu.Unlock()
 
 	e.wg.Add(1)
 	go func() {
@@ -346,10 +316,7 @@ func (e *ConnMgr) closeManager(ctx context.Context) {
 
 	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)

client/internal/conn_mgr_test.go

@@ -1,21 +1,10 @@
 package internal
 
 import (
-	"context"
-	"net"
-	"net/netip"
 	"os"
-	"sync"
 	"testing"
-	"time"
 
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-	"github.com/netbirdio/netbird/monotime"
 )
 
 func TestResolveLazyForce(t *testing.T) {
@@ -49,58 +38,3 @@ func TestResolveLazyForce(t *testing.T) {
 		})
 	}
 }
-
-type mockLazyWGIface struct{}
-
-func (mockLazyWGIface) RemovePeer(string) error { return nil }
-func (mockLazyWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
-	return nil
-}
-func (mockLazyWGIface) IsUserspaceBind() bool                    { return false }
-func (mockLazyWGIface) Address() wgaddr.Address                  { return wgaddr.Address{} }
-func (mockLazyWGIface) LastActivities() map[string]monotime.Time { return nil }
-func (mockLazyWGIface) MTU() uint16                              { return 1280 }
-
-// TestConnMgr_ActivatePeerConcurrentWithLifecycle exercises ActivatePeer from
-// non-engine goroutines (the DNS warm-up path) racing the manager lifecycle,
-// which stays on the engine loop. Run with -race: it fails if ActivatePeer
-// still requires engine.syncMsgMux for safety.
-func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
-	t.Setenv(lazyconn.EnvLazyConn, "on")
-
-	status := peer.NewRecorder("https://mgm")
-	store := peerstore.NewConnStore()
-	connMgr := NewConnMgr(&EngineConfig{}, status, store, mockLazyWGIface{})
-
-	conn := newTestPeerConn(t, "peerA")
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-	connMgr.Start(ctx)
-
-	done := make(chan struct{})
-	var wg sync.WaitGroup
-	for range 4 {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			for {
-				select {
-				case <-done:
-					return
-				default:
-					connMgr.ActivatePeer(ctx, conn)
-				}
-			}
-		}()
-	}
-
-	// Let the activators spin against the started manager, then tear it down
-	// underneath them and let them spin against the stopped manager.
-	time.Sleep(100 * time.Millisecond)
-	connMgr.Close()
-	time.Sleep(50 * time.Millisecond)
-
-	close(done)
-	wg.Wait()
-}

client/internal/connect.go

@@ -257,10 +257,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Errorf("failed to clean up temporary installer file: %v", err)
 	}
 
-	defer func() {
-		c.statusRecorder.SetSessionExpiresAt(time.Time{})
-		c.statusRecorder.ClientStop()
-	}()
+	defer c.statusRecorder.ClientStop()
 	operation := func() error {
 		// if context cancelled we not start new backoff cycle
 		if c.ctx.Err() != nil {
@@ -621,7 +618,6 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 		BlockLANAccess:      config.BlockLANAccess,
 		BlockInbound:        config.BlockInbound,
 		DisableIPv6:         config.DisableIPv6,
-		SyncMessageVersion:  config.SyncMessageVersion,
 
 		LazyConnection: lazyconn.ParseState(config.LazyConnection),
 
@@ -697,7 +693,6 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.BlockLANAccess,
 		config.BlockInbound,
 		config.DisableIPv6,
-		config.SyncMessageVersion,
 		config.EnableSSHRoot,
 		config.EnableSSHSFTP,
 		config.EnableSSHLocalPortForwarding,

client/internal/debug/debug.go

@@ -676,7 +676,8 @@ 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("SyncMessageVersion: %v\n", g.internalConfig.SyncMessageVersion))
+	configContent.WriteString(fmt.Sprintf("LocalMetricsEnabled: %v\n", g.internalConfig.LocalMetricsEnabled))
+	configContent.WriteString(fmt.Sprintf("LocalMetricsAddress: %s\n", g.internalConfig.LocalMetricsAddress))
 
 	if g.internalConfig.DisableNotifications != nil {
 		configContent.WriteString(fmt.Sprintf("DisableNotifications: %v\n", *g.internalConfig.DisableNotifications))

client/internal/debug/debug_test.go

@@ -887,8 +887,6 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		ClientCertKeyPath:             "/tmp/key",
 		LazyConnection:                "on",
 		MTU:                           1280,
-		DisableIPv6:                   true,
-		SyncMessageVersion:            func(v int) *int { return &v }(1),
 	}
 
 	for _, anonymize := range []bool{false, true} {

client/internal/dns/local/local.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"os"
 	"slices"
 	"strings"
 	"sync"
@@ -37,43 +36,7 @@ type resolver interface {
 // record is left alone (it points at something outside our mesh, e.g.
 // a non-peer upstream).
 type PeerConnectivity interface {
-	IsConnectedByIP(ip netip.Addr) (known, connected bool)
-}
-
-// PeerActivator wakes lazy-connection peers on demand. The local resolver calls
-// it with the tunnel IPs an answer points at, so a peer that is idle (lazily
-// disconnected) starts connecting at DNS-resolution time rather than racing the
-// client's first request packet. nil disables warm-up.
-type PeerActivator interface {
-	// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and blocks
-	// until one is connected or ctx (a short per-query budget) expires. It is a
-	// fast no-op for unknown or already-connected addresses.
-	ActivatePeersByIP(ctx context.Context, addrs []netip.Addr)
-}
-
-const (
-	defaultLazyWarmupTimeout = 2 * time.Second
-	envLazyWarmupTimeout     = "NB_DNS_LAZY_WARMUP_TIMEOUT"
-)
-
-// lazyWarmupTimeoutFromEnv returns the per-query budget for waking a
-// lazy-connection peer a DNS answer points at. Tunable via
-// NB_DNS_LAZY_WARMUP_TIMEOUT (a Go duration). Parsed once at construction time.
-func lazyWarmupTimeoutFromEnv() time.Duration {
-	v := os.Getenv(envLazyWarmupTimeout)
-	if v == "" {
-		return defaultLazyWarmupTimeout
-	}
-	d, err := time.ParseDuration(v)
-	if err != nil {
-		log.Warnf("invalid %s value %q, using default %s: %v", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout, err)
-		return defaultLazyWarmupTimeout
-	}
-	if d <= 0 {
-		log.Warnf("non-positive %s value %q, using default %s", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout)
-		return defaultLazyWarmupTimeout
-	}
-	return d
+	IsConnectedByIP(ip string) (known, connected bool)
 }
 
 type Resolver struct {
@@ -88,12 +51,6 @@ type Resolver struct {
 	// filter and preserves the legacy "return whatever is registered"
 	// behaviour for callers that never wire a status source.
 	peerConn PeerConnectivity
-	// peerActivator, when non-nil, is called at resolution time to warm the
-	// lazy connection to the peer(s) an answer points at. nil disables warm-up.
-	peerActivator PeerActivator
-	// warmupTimeout is the per-query budget for the lazy-connection warm-up
-	// wait, resolved from the environment once at construction time.
-	warmupTimeout time.Duration
 
 	ctx    context.Context
 	cancel context.CancelFunc
@@ -102,12 +59,11 @@ type Resolver struct {
 func NewResolver() *Resolver {
 	ctx, cancel := context.WithCancel(context.Background())
 	return &Resolver{
-		records:       make(map[dns.Question][]dns.RR),
-		domains:       make(map[domain.Domain]struct{}),
-		zones:         make(map[domain.Domain]bool),
-		warmupTimeout: lazyWarmupTimeoutFromEnv(),
-		ctx:           ctx,
-		cancel:        cancel,
+		records: make(map[dns.Question][]dns.RR),
+		domains: make(map[domain.Domain]struct{}),
+		zones:   make(map[domain.Domain]bool),
+		ctx:     ctx,
+		cancel:  cancel,
 	}
 }
 
@@ -120,14 +76,6 @@ func (d *Resolver) SetPeerConnectivity(p PeerConnectivity) {
 	d.peerConn = p
 }
 
-// SetPeerActivator wires the DNS-time lazy-connection warm-up. Pass nil to
-// disable. Safe to call multiple times; the latest value wins.
-func (d *Resolver) SetPeerActivator(a PeerActivator) {
-	d.mu.Lock()
-	defer d.mu.Unlock()
-	d.peerActivator = a
-}
-
 func (d *Resolver) MatchSubdomains() bool {
 	return true
 }
@@ -174,9 +122,6 @@ func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	replyMessage.RecursionAvailable = true
 
 	result := d.lookupRecords(logger, question)
-	// Warm before filtering: activation flips a lazily-idle target to connected,
-	// which then lets it survive the disconnected-peer filter below.
-	d.warmLazyPeers(question, result.records)
 	result.records = d.filterDisconnectedPeerAnswers(logger, question, result.records)
 	replyMessage.Authoritative = !result.hasExternalData
 	replyMessage.Answer = result.records
@@ -550,8 +495,8 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	kept := make([]dns.RR, 0, len(records))
 	var dropped int
 	for _, rr := range records {
-		ip, ok := extractRecordAddr(rr)
-		if !ok {
+		ip := extractRecordIP(rr)
+		if ip == "" {
 			kept = append(kept, rr)
 			continue
 		}
@@ -573,57 +518,22 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	return kept
 }
 
-// warmLazyPeers triggers lazy-connection wake-up for the peers a resolved
-// answer points at and waits briefly for one to connect, so the caller's first
-// request doesn't race the connection establishment. Warm-up is scoped to
-// match-only (non-authoritative) zones — the synthesized private-service zones
-// and user-created zones whose records point at specific peers. The account's
-// peer zone is authoritative, so plain peer-name lookups never trigger warm-up;
-// otherwise resolving any peer's name would wake its idle connection, defeating
-// laziness mesh-wide. No-op when no activator is wired (lazy connections
-// disabled) or the answer carries no peer IPs.
-func (d *Resolver) warmLazyPeers(question dns.Question, records []dns.RR) {
-	if len(records) < 2 {
-		return
-	}
-	d.mu.RLock()
-	activator := d.peerActivator
-	var nonAuth, found bool
-	if activator != nil {
-		nonAuth, found = d.findZone(question.Name)
-	}
-	d.mu.RUnlock()
-	if activator == nil || !found || !nonAuth {
-		return
-	}
-
-	var addrs []netip.Addr
-	for _, rr := range records {
-		if addr, ok := extractRecordAddr(rr); ok {
-			addrs = append(addrs, addr)
-		}
-	}
-	if len(addrs) == 0 {
-		return
-	}
-
-	ctx, cancel := context.WithTimeout(d.ctx, d.warmupTimeout)
-	defer cancel()
-	activator.ActivatePeersByIP(ctx, addrs)
-}
-
-// extractRecordAddr returns the IP address carried by an A or AAAA record.
-// ok is false for any other record type or a record with no address.
-func extractRecordAddr(rr dns.RR) (netip.Addr, bool) {
+// extractRecordIP returns the dotted-decimal / colon-hex IP carried by
+// an A or AAAA record, or "" for any other record type.
+func extractRecordIP(rr dns.RR) string {
 	switch r := rr.(type) {
 	case *dns.A:
-		addr, ok := netip.AddrFromSlice(r.A)
-		return addr.Unmap(), ok
+		if r.A == nil {
+			return ""
+		}
+		return r.A.String()
 	case *dns.AAAA:
-		addr, ok := netip.AddrFromSlice(r.AAAA)
-		return addr.Unmap(), ok
+		if r.AAAA == nil {
+			return ""
+		}
+		return r.AAAA.String()
 	}
-	return netip.Addr{}, false
+	return ""
 }
 
 // Update replaces all zones and their records

client/internal/dns/local/local_test.go

@@ -37,8 +37,8 @@ type mockPeerConnectivity struct {
 	byIP map[string]struct{ known, connected bool }
 }
 
-func (m mockPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
-	v, ok := m.byIP[ip.String()]
+func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
+	v, ok := m.byIP[ip]
 	if !ok {
 		return false, false
 	}

client/internal/dns/local/warmup_test.go

@@ -1,204 +0,0 @@
-package local
-
-import (
-	"context"
-	"net"
-	"net/netip"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/miekg/dns"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/dns/test"
-	nbdns "github.com/netbirdio/netbird/dns"
-)
-
-// recordingActivator records the addresses it was asked to warm and returns
-// immediately, so ServeDNS is not blocked by the test.
-type recordingActivator struct {
-	mu     sync.Mutex
-	called bool
-	addrs  []netip.Addr
-}
-
-func (r *recordingActivator) ActivatePeersByIP(_ context.Context, addrs []netip.Addr) {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	r.called = true
-	r.addrs = append(r.addrs, addrs...)
-}
-
-func serveA(t *testing.T, resolver *Resolver, name string) *dns.Msg {
-	t.Helper()
-	var resp *dns.Msg
-	w := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { resp = m; return nil }}
-	resolver.ServeDNS(w, new(dns.Msg).SetQuestion(name, dns.TypeA))
-	return resp
-}
-
-// serviceZone registers rec in a match-only (non-authoritative) zone, the shape
-// the synthesized private-service zones arrive in.
-func serviceZone(t *testing.T, resolver *Resolver, zone string, records ...nbdns.SimpleRecord) {
-	t.Helper()
-	resolver.Update([]nbdns.CustomZone{{
-		Domain:           zone,
-		Records:          records,
-		NonAuthoritative: true,
-	}})
-}
-
-func TestLocalResolver_WarmsLazyPeerOnResolve(t *testing.T) {
-	// Warm-up fires only for multi-record answers (the HA / round-robin shape of
-	// the synthesized private-service zones), so register two peer targets.
-	const name = "svc.proxy.netbird.cloud."
-	recs := []nbdns.SimpleRecord{
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"},
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.8"},
-	}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", recs...)
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.True(t, act.called, "activator must be invoked for a multi-record service-zone answer")
-	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.7"), "activator must receive the first peer IP")
-	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.8"), "activator must receive the second peer IP")
-}
-
-func TestLocalResolver_NoWarmupForSingleRecord(t *testing.T) {
-	// A single-record answer does not trigger warm-up; the resolver only warms
-	// multi-record answers.
-	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, rec.Name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked for a single-record answer")
-}
-
-func TestLocalResolver_NoActivatorNoWarmup(t *testing.T) {
-	// With no activator wired the resolver behaves exactly as before.
-	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
-
-	resp := serveA(t, resolver, rec.Name)
-	require.NotNil(t, resp, "resolver must still answer without an activator")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
-}
-
-func TestLocalResolver_NoWarmupForMissingRecord(t *testing.T) {
-	// A query that resolves to nothing must not invoke the activator (no IPs).
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud",
-		nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"})
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	serveA(t, resolver, "absent.proxy.netbird.cloud.")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked when there is no answer")
-}
-
-func TestLocalResolver_NoWarmupInAuthoritativeZone(t *testing.T) {
-	// The account's peer zone is authoritative; resolving a peer's name there
-	// must not wake its lazy connection — warm-up is scoped to match-only
-	// (non-authoritative) zones such as the synthesized private-service zones.
-	// Use a multi-record answer so the authoritative-zone scoping is the only
-	// reason warm-up is skipped, not the single-record guard.
-	const name = "peer.netbird.cloud."
-	recs := []nbdns.SimpleRecord{
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.9"},
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.10"},
-	}
-	resolver := NewResolver()
-	resolver.Update([]nbdns.CustomZone{{
-		Domain:  "netbird.cloud",
-		Records: recs,
-	}})
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked for authoritative-zone answers")
-}
-
-func TestLazyWarmupTimeoutFromEnv(t *testing.T) {
-	tests := []struct {
-		name   string
-		value  string
-		envSet bool
-		want   time.Duration
-	}{
-		{name: "unset uses default", want: defaultLazyWarmupTimeout},
-		{name: "valid overrides", value: "5s", envSet: true, want: 5 * time.Second},
-		{name: "invalid falls back", value: "not-a-duration", envSet: true, want: defaultLazyWarmupTimeout},
-		{name: "negative falls back", value: "-1s", envSet: true, want: defaultLazyWarmupTimeout},
-		{name: "zero falls back", value: "0s", envSet: true, want: defaultLazyWarmupTimeout},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if tt.envSet {
-				t.Setenv(envLazyWarmupTimeout, tt.value)
-			}
-			assert.Equal(t, tt.want, lazyWarmupTimeoutFromEnv())
-			assert.Equal(t, tt.want, NewResolver().warmupTimeout, "constructor must resolve the timeout once")
-		})
-	}
-}
-
-func TestExtractRecordAddr(t *testing.T) {
-	t.Run("A record yields unmapped v4", func(t *testing.T) {
-		// net.ParseIP returns the 16-byte v4-in-v6 form, the same shape
-		// miekg/dns stores after parsing an A record; the extracted address
-		// must compare equal to a plain v4 netip.Addr.
-		addr, ok := extractRecordAddr(&dns.A{A: net.ParseIP("100.64.0.7")})
-		require.True(t, ok)
-		assert.True(t, addr.Is4())
-		assert.Equal(t, netip.MustParseAddr("100.64.0.7"), addr)
-	})
-
-	t.Run("AAAA record yields v6", func(t *testing.T) {
-		addr, ok := extractRecordAddr(&dns.AAAA{AAAA: net.ParseIP("fd00::1")})
-		require.True(t, ok)
-		assert.Equal(t, netip.MustParseAddr("fd00::1"), addr)
-	})
-
-	t.Run("A record without address", func(t *testing.T) {
-		_, ok := extractRecordAddr(&dns.A{})
-		assert.False(t, ok)
-	})
-
-	t.Run("non-address record", func(t *testing.T) {
-		_, ok := extractRecordAddr(&dns.CNAME{Target: "target.netbird.cloud."})
-		assert.False(t, ok)
-	})
-}

client/internal/dns/mock_server.go

@@ -8,7 +8,6 @@ import (
 	"github.com/miekg/dns"
 
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
-	"github.com/netbirdio/netbird/client/internal/dns/local"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -93,11 +92,6 @@ func (m *MockServer) SetFirewall(Firewall) {
 	// Mock implementation - no-op
 }
 
-// SetPeerActivator mock implementation of SetPeerActivator from Server interface
-func (m *MockServer) SetPeerActivator(local.PeerActivator) {
-	// Mock implementation - no-op
-}
-
 // BeginBatch mock implementation of BeginBatch from Server interface
 func (m *MockServer) BeginBatch() {
 	// Mock implementation - no-op

client/internal/dns/server.go

@@ -82,7 +82,6 @@ type Server interface {
 	PopulateManagementDomain(mgmtURL *url.URL) error
 	SetRouteSources(selected, active func() route.HAMap)
 	SetFirewall(Firewall)
-	SetPeerActivator(local.PeerActivator)
 }
 
 type nsGroupsByDomain struct {
@@ -492,13 +491,6 @@ func (s *DefaultServer) SetFirewall(fw Firewall) {
 	}
 }
 
-// SetPeerActivator wires the DNS-time lazy-connection warm-up on the local
-// resolver. Injected after the connection manager exists (it does not at
-// DNS-server construction time). Pass nil to disable.
-func (s *DefaultServer) SetPeerActivator(a local.PeerActivator) {
-	s.localResolver.SetPeerActivator(a)
-}
-
 // Stop stops the server
 func (s *DefaultServer) Stop() {
 	s.ctxCancel()
@@ -1443,11 +1435,11 @@ type localPeerConnectivity struct {
 
 // IsConnectedByIP looks the IP up in the peerstore and surfaces both
 // the known and connected bits. Used by Resolver.filterDisconnectedPeerAnswers.
-func (l localPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
+func (l localPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
 	if l.status == nil {
 		return false, false
 	}
-	state, ok := l.status.PeerStateByIP(ip.String())
+	state, ok := l.status.PeerStateByIP(ip)
 	if !ok {
 		return false, false
 	}

client/internal/dns/service_listener.go

@@ -292,16 +292,18 @@ func (s *serviceViaListener) generateFreePort() (uint16, error) {
 		return customPort, nil
 	}
 
-	probeListener, err := net.ListenUDP("udp4", &net.UDPAddr{})
+	udpAddr := net.UDPAddrFromAddrPort(netip.MustParseAddrPort("0.0.0.0:0"))
+	probeListener, err := net.ListenUDP("udp", udpAddr)
 	if err != nil {
 		log.Debugf("failed to bind random port for DNS: %s", err)
 		return 0, err
 	}
 
-	port := uint16(probeListener.LocalAddr().(*net.UDPAddr).Port)
-	if err = probeListener.Close(); err != nil {
+	addrPort := netip.MustParseAddrPort(probeListener.LocalAddr().String()) // might panic if address is incorrect
+	err = probeListener.Close()
+	if err != nil {
 		log.Debugf("failed to free up DNS port: %s", err)
 		return 0, err
 	}
-	return port, nil
+	return addrPort.Port(), nil
 }

client/internal/dns_peer_activator.go

@@ -1,76 +0,0 @@
-package internal
-
-import (
-	"context"
-	"net/netip"
-	"time"
-
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-)
-
-const dnsActivationPollInterval = 50 * time.Millisecond
-
-// dnsPeerActivator wakes lazy-connection peers from the DNS resolution path. It
-// implements dns/local.PeerActivator. DNS queries run on their own goroutines,
-// so it only touches state that is safe for concurrent use — ConnMgr.ActivatePeer,
-// peerstore.Store and peer.Status — and never takes the engine's syncMsgMux,
-// keeping DNS resolution from contending with network-map processing.
-type dnsPeerActivator struct {
-	connMgr   *ConnMgr
-	peerStore *peerstore.Store
-	status    *peer.Status
-	// ctx is the engine's long-lived context. The connection dial is tied to it
-	// (not the per-query DNS wait budget) so a handshake that outlasts the wait
-	// still completes in the background rather than being cancelled at the deadline.
-	ctx context.Context
-}
-
-// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and waits
-// until one is connected or ctx (the per-query DNS wait budget) expires.
-// Activation itself is tied to the engine's long-lived context so the dial
-// survives a wait that times out. Unknown or already-connected addresses are
-// skipped, so the steady-state (warm) path adds no latency.
-func (a *dnsPeerActivator) ActivatePeersByIP(ctx context.Context, addrs []netip.Addr) {
-	if a == nil || a.connMgr == nil {
-		return
-	}
-
-	var pending []string
-	for _, addr := range addrs {
-		ip := addr.String()
-		st, ok := a.status.PeerStateByIP(ip)
-		if !ok || st.ConnStatus == peer.StatusConnected {
-			continue
-		}
-		conn, ok := a.peerStore.PeerConn(st.PubKey)
-		if !ok {
-			continue
-		}
-		a.connMgr.ActivatePeer(a.ctx, conn)
-		pending = append(pending, ip)
-	}
-
-	if len(pending) == 0 {
-		return
-	}
-	a.waitConnected(ctx, pending)
-}
-
-// waitConnected blocks until any of ips reports a connected peer or ctx expires.
-func (a *dnsPeerActivator) waitConnected(ctx context.Context, ips []string) {
-	ticker := time.NewTicker(dnsActivationPollInterval)
-	defer ticker.Stop()
-	for {
-		for _, ip := range ips {
-			if st, ok := a.status.PeerStateByIP(ip); ok && st.ConnStatus == peer.StatusConnected {
-				return
-			}
-		}
-		select {
-		case <-ctx.Done():
-			return
-		case <-ticker.C:
-		}
-	}
-}

client/internal/dns_peer_activator_test.go

@@ -1,129 +0,0 @@
-package internal
-
-import (
-	"context"
-	"net/netip"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-)
-
-func newTestPeerConn(t *testing.T, key string) *peer.Conn {
-	t.Helper()
-	conn, err := peer.NewConn(peer.ConnConfig{
-		Key:      key,
-		LocalKey: "local",
-		WgConfig: peer.WgConfig{
-			AllowedIps: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
-		},
-	}, peer.ServiceDependencies{})
-	require.NoError(t, err)
-	return conn
-}
-
-func newTestDNSPeerActivator(t *testing.T) (*dnsPeerActivator, *peer.Status, *peerstore.Store) {
-	t.Helper()
-	status := peer.NewRecorder("https://mgm")
-	store := peerstore.NewConnStore()
-	// ConnMgr without Start: the lazy manager is nil, so ActivatePeer is a
-	// no-op — these tests exercise the activator's skip/wait logic.
-	connMgr := NewConnMgr(&EngineConfig{}, status, store, nil)
-	return &dnsPeerActivator{
-		connMgr:   connMgr,
-		peerStore: store,
-		status:    status,
-		ctx:       context.Background(),
-	}, status, store
-}
-
-func TestDNSPeerActivator_NilSafe(t *testing.T) {
-	var a *dnsPeerActivator
-	a.ActivatePeersByIP(context.Background(), []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-}
-
-// TestDNSPeerActivator_SkipsUnknownAndConnectedPeers verifies the steady-state
-// (warm) path adds no latency: already-connected and unknown addresses never
-// enter the wait loop.
-func TestDNSPeerActivator_SkipsUnknownAndConnectedPeers(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", "fd00::1"))
-	require.NoError(t, status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected}))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{
-		netip.MustParseAddr("100.64.0.1"),  // known, connected -> skipped
-		netip.MustParseAddr("fd00::1"),     // known via IPv6, connected -> skipped
-		netip.MustParseAddr("100.64.0.99"), // unknown -> skipped
-	})
-	require.Less(t, time.Since(start), time.Second, "no pending peer must mean no wait")
-}
-
-// TestDNSPeerActivator_WaitsForPendingPeerToConnect verifies the wait loop
-// returns as soon as a pending peer reports connected, well before the
-// per-query budget expires.
-func TestDNSPeerActivator_WaitsForPendingPeerToConnect(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	go func() {
-		time.Sleep(150 * time.Millisecond)
-		_ = status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected})
-	}()
-
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	elapsed := time.Since(start)
-
-	require.GreaterOrEqual(t, elapsed, 100*time.Millisecond, "must wait for the pending peer")
-	require.Less(t, elapsed, 5*time.Second, "must return on connect, not at the deadline")
-}
-
-// TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle verifies a peer that
-// never connects releases the DNS response at the per-query budget instead of
-// blocking it indefinitely.
-func TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 300*time.Millisecond)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	elapsed := time.Since(start)
-
-	require.GreaterOrEqual(t, elapsed, 250*time.Millisecond, "must wait out the budget for a pending peer")
-	require.Less(t, elapsed, 5*time.Second, "must not block past the budget")
-}
-
-// TestDNSPeerActivator_NoWaitWithoutPeerConn verifies a known-but-idle peer
-// with no connection object in the store is not waited on: there is nothing to
-// activate, so waiting could only ever time out.
-func TestDNSPeerActivator_NoWaitWithoutPeerConn(t *testing.T) {
-	a, status, _ := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	require.Less(t, time.Since(start), time.Second, "peer without a conn must not be waited on")
-}

client/internal/ebpf/ebpf/src/dns_fwd.c

@@ -52,14 +52,11 @@ int xdp_dns_fwd(struct iphdr  *ip, struct udphdr *udp) {
 
     if (udp->dest == GENERAL_DNS_PORT && ip->daddr == dns_ip) {
         udp->dest = dns_port;
-        // Clear the now-stale checksum; zero means "not computed" for IPv4.
-        udp->check = 0;
         return XDP_PASS;
     }
 
     if (udp->source == dns_port && ip->saddr == dns_ip) {
         udp->source = GENERAL_DNS_PORT;
-        udp->check = 0;
         return XDP_PASS;
     }
 

client/internal/ebpf/ebpf/src/wg_proxy.c

@@ -50,11 +50,5 @@ int xdp_wg_proxy(struct iphdr  *ip, struct udphdr *udp) {
     __be16 new_dst_port = htons(proxy_port);
     udp->dest = new_dst_port;
     udp->source = new_src_port;
-
-    // The ports are covered by the UDP checksum. This is an IPv4 loopback hop
-    // and the payload is already integrity-protected, so clear the checksum (a
-    // zero UDP checksum means "not computed" for IPv4) rather than leave a
-    // stale value the kernel would drop as UDP_CSUM.
-    udp->check = 0;
 	return XDP_PASS;
 }

client/internal/engine.go

@@ -64,10 +64,7 @@ import (
 	"github.com/netbirdio/netbird/route"
 	mgm "github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/management/domain"
-	sharedgrpc "github.com/netbirdio/netbird/shared/management/grpc"
-	nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-	types "github.com/netbirdio/netbird/shared/management/types"
 	"github.com/netbirdio/netbird/shared/netiputil"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
@@ -150,7 +147,6 @@ type EngineConfig struct {
 	BlockLANAccess      bool
 	BlockInbound        bool
 	DisableIPv6         bool
-	SyncMessageVersion  *int
 
 	// LazyConnection is the MDM-sourced lazy-connection override; StateUnset defers to
 	// the env var and management feature flag.
@@ -224,13 +220,6 @@ type Engine struct {
 	// networkSerial is the latest CurrentSerial (state ID) of the network sent by the Management service
 	networkSerial uint64
 
-	// latestComponents is the most-recent NetworkMapComponents decoded from
-	// a NetworkMapEnvelope (capability=3 peers only). Held alongside the
-	// NetworkMap that Calculate() produced from it so future incremental
-	// updates have a base to apply changes against. nil for legacy-format
-	// peers. Guarded by syncMsgMux.
-	latestComponents *types.NetworkMapComponents
-
 	networkMonitor *networkmonitor.NetworkMonitor
 
 	sshServer sshServer
@@ -663,24 +652,8 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	iceCfg := e.createICEConfig()
 
 	e.connMgr = NewConnMgr(e.config, e.statusRecorder, e.peerStore, wgIface)
-	e.connMgr.SetRoutedIPsReconciler(func(peerKey string) error {
-		if e.routeManager == nil {
-			return nil
-		}
-		return e.routeManager.ReconcilePeerAllowedIPs(peerKey)
-	})
 	e.connMgr.Start(e.ctx)
 
-	// Wire DNS-time lazy-connection warm-up now that the connection manager
-	// exists (it does not at DNS-server construction time). A DNS answer that
-	// points at an idle peer then wakes it before the client's first request.
-	e.dnsServer.SetPeerActivator(&dnsPeerActivator{
-		connMgr:   e.connMgr,
-		peerStore: e.peerStore,
-		status:    e.statusRecorder,
-		ctx:       e.ctx,
-	})
-
 	e.srWatcher = guard.NewSRWatcher(e.signal, e.relayManager, e.mobileDep.IFaceDiscover, iceCfg)
 	e.srWatcher.Start(peer.IsForceRelayed())
 
@@ -990,12 +963,8 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 
 	e.ApplySessionDeadline(update.GetSessionExpiresAt())
 
-	// Envelope sync responses carry PeerConfig at the top level; legacy
-	// NetworkMap syncs carry it under NetworkMap.PeerConfig.
-	if pc := update.GetPeerConfig(); pc != nil {
-		e.handleAutoUpdateVersion(pc.GetAutoUpdate())
-	} else if nm := update.GetNetworkMap(); nm != nil && nm.GetPeerConfig() != nil {
-		e.handleAutoUpdateVersion(nm.GetPeerConfig().GetAutoUpdate())
+	if update.NetworkMap != nil && update.NetworkMap.PeerConfig != nil {
+		e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate)
 	}
 
 	done := e.phase("netbird_config")
@@ -1005,47 +974,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return err
 	}
 
-	// Decode the network map from either the components envelope or the
-	// legacy proto.NetworkMap before the posture-check gating below, so the
-	// "is there a network map" decision covers both wire shapes.
-	var (
-		nm         *mgmProto.NetworkMap
-		components *types.NetworkMapComponents
-	)
-	if version := update.GetVersion(); version == int32(sharedgrpc.ComponentNetworkMap) {
-		// Components-format peer: decode the envelope back to typed
-		// components, run Calculate() locally, and convert to the wire
-		// NetworkMap shape the rest of the engine consumes. Components are
-		// retained so future incremental updates can apply deltas instead
-		// of doing a full reconstruction.
-		envelope := update.GetNetworkMapEnvelope()
-		if envelope == nil {
-			return fmt.Errorf("received a SyncReponse indicating use of components network map, but components are missing")
-		}
-
-		localKey := e.config.WgPrivateKey.PublicKey().String()
-		dnsName := ""
-		if pc := update.GetPeerConfig(); pc != nil {
-			// PeerConfig.Fqdn = "<dns_label>.<dns_domain>" — extract the
-			// shared domain by stripping the peer's own label prefix. Falls
-			// back to empty if the FQDN doesn't have the expected shape.
-			dnsName = extractDNSDomainFromFQDN(pc.GetFqdn())
-		}
-		result, err := nbnetworkmap.EnvelopeToNetworkMap(e.ctx, envelope, localKey, dnsName)
-		if err != nil {
-			return fmt.Errorf("decode network map envelope: %w", err)
-		}
-		nm = result.NetworkMap
-		components = result.Components
-	} else {
-		nm = update.GetNetworkMap()
-	}
-
 	// Posture checks are bound to the network map presence:
 	//   NetworkMap != nil, checks present -> apply the received checks
 	//   NetworkMap != nil, checks nil     -> posture checks were removed, clear them
 	//   NetworkMap == nil                 -> config-only update (e.g. relay token rotation),
 	//                                        leave the previously applied checks untouched
+	nm := update.GetNetworkMap()
 	if nm == nil {
 		return nil
 	}
@@ -1058,14 +992,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	}
 
 	done = e.phase("persist")
-	// Only retain the components view when the server sent the envelope
-	// path. A legacy proto.NetworkMap means components == nil; writing it
-	// here would clobber a previously-cached snapshot, breaking the
-	// incremental-delta base on a future envelope sync.
-	if components != nil {
-		e.latestComponents = components
-	}
-
 	e.persistSyncResponse(update)
 	done()
 
@@ -1079,19 +1005,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	return nil
 }
 
-// extractDNSDomainFromFQDN returns the trailing dotted domain part of the
-// receiving peer's FQDN — the same value the management server fills as
-// dnsName when it builds the legacy NetworkMap. "peer42.netbird.cloud" →
-// "netbird.cloud". An empty string is returned for unrecognized formats.
-func extractDNSDomainFromFQDN(fqdn string) string {
-	for i := 0; i < len(fqdn); i++ {
-		if fqdn[i] == '.' && i+1 < len(fqdn) {
-			return fqdn[i+1:]
-		}
-	}
-	return ""
-}
-
 // updateNetbirdConfig applies the management-provided NetBird configuration:
 // STUN/TURN and relay servers, flow logging and DNS settings. A nil config is a no-op,
 // which is the case for sync updates carrying only a network map.
@@ -1251,7 +1164,6 @@ func (e *Engine) applyInfoFlags(info *system.Info) {
 		e.config.BlockLANAccess,
 		e.config.BlockInbound,
 		e.config.DisableIPv6,
-		e.config.SyncMessageVersion,
 		e.config.EnableSSHRoot,
 		e.config.EnableSSHSFTP,
 		e.config.EnableSSHLocalPortForwarding,
@@ -2120,7 +2032,6 @@ func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, err
 		e.config.BlockLANAccess,
 		e.config.BlockInbound,
 		e.config.DisableIPv6,
-		e.config.SyncMessageVersion,
 		e.config.EnableSSHRoot,
 		e.config.EnableSSHSFTP,
 		e.config.EnableSSHLocalPortForwarding,

client/internal/engine_session_deadline_test.go

@@ -75,14 +75,4 @@ func TestApplySessionDeadline_ThreeState(t *testing.T) {
 		require.True(t, e.statusRecorder.GetSessionExpiresAt().IsZero(),
 			"invalid timestamp must clear the deadline")
 	})
-
-	t.Run("recently expired timestamp stays visible as expired", func(t *testing.T) {
-		e := newEngine()
-		expired := time.Now().Add(-5 * time.Minute).UTC().Truncate(time.Second)
-
-		e.ApplySessionDeadline(timestamppb.New(expired))
-
-		require.True(t, e.statusRecorder.GetSessionExpiresAt().Equal(expired),
-			"recently-expired deadline must stay on the recorder so consumers render it as expired")
-	})
 }

client/internal/lazyconn/manager/manager.go

@@ -29,11 +29,6 @@ type managedPeer struct {
 
 type Config struct {
 	InactivityThreshold *time.Duration
-	// ReconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is
-	// armed. The activity listener creates the wake peer with the overlay /32 only; without the
-	// routed prefixes WireGuard would not steer subnet-bound traffic to the wake endpoint, so an
-	// idle routing peer could never be woken by that traffic. Optional; nil disables the reconcile.
-	ReconcileAllowedIPs func(peerKey string) error
 }
 
 // Manager manages lazy connections
@@ -61,9 +56,6 @@ type Manager struct {
 	peerToHAGroups map[string][]route.HAUniqueID // peer ID -> HA groups they belong to
 	haGroupToPeers map[route.HAUniqueID][]string // HA group -> peer IDs in the group
 	routesMu       sync.RWMutex
-
-	// reconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is armed.
-	reconcileAllowedIPs func(peerKey string) error
 }
 
 // NewManager creates a new lazy connection manager
@@ -81,7 +73,6 @@ func NewManager(config Config, engineCtx context.Context, peerStore *peerstore.S
 		activityManager:      activity.NewManager(wgIface),
 		peerToHAGroups:       make(map[string][]route.HAUniqueID),
 		haGroupToPeers:       make(map[route.HAUniqueID][]string),
-		reconcileAllowedIPs:  config.ReconcileAllowedIPs,
 	}
 
 	if wgIface.IsUserspaceBind() {
@@ -210,7 +201,7 @@ func (m *Manager) AddPeer(peerCfg lazyconn.PeerConfig) (bool, error) {
 		return false, nil
 	}
 
-	if err := m.armActivityListener(peerCfg); err != nil {
+	if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
 		return false, err
 	}
 
@@ -297,7 +288,7 @@ func (m *Manager) DeactivatePeer(peerID peerid.ConnID) {
 
 	m.inactivityManager.RemovePeer(mp.peerCfg.PublicKey)
 
-	if err := m.armActivityListener(*mp.peerCfg); err != nil {
+	if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
 		mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
 		return
 	}
@@ -474,31 +465,6 @@ func (m *Manager) close() {
 }
 
 // shouldDeferIdleForHA checks if peer should stay connected due to HA group requirements
-// armRoutedAllowedIPs re-applies the peer's routed allowed IPs onto its freshly armed wake
-// endpoint. The activity listener creates the wake peer with the overlay /32 only, so without
-// this the routed prefixes would be missing and traffic to a routed subnet could not wake the
-// idle routing peer. It is a no-op when no reconciler is configured.
-// armActivityListener (re)arms the peer's wake endpoint via the activity manager and then
-// re-applies its routed allowed IPs, so traffic to a routed subnet can wake an idle routing
-// peer. The routed prefixes must be re-applied after the wake endpoint exists because the
-// listener creates it with the overlay /32 only.
-func (m *Manager) armActivityListener(peerCfg lazyconn.PeerConfig) error {
-	if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
-		return err
-	}
-	m.armRoutedAllowedIPs(&peerCfg)
-	return nil
-}
-
-func (m *Manager) armRoutedAllowedIPs(peerCfg *lazyconn.PeerConfig) {
-	if m.reconcileAllowedIPs == nil {
-		return
-	}
-	if err := m.reconcileAllowedIPs(peerCfg.PublicKey); err != nil {
-		peerCfg.Log.Errorf("failed to reconcile routed allowed IPs on wake endpoint: %v", err)
-	}
-}
-
 func (m *Manager) shouldDeferIdleForHA(inactivePeers map[string]struct{}, peerID string) bool {
 	m.routesMu.RLock()
 	defer m.routesMu.RUnlock()
@@ -611,7 +577,7 @@ func (m *Manager) onPeerInactivityTimedOut(peerIDs map[string]struct{}) {
 
 		mp.peerCfg.Log.Infof("start activity monitor")
 
-		if err := m.armActivityListener(*mp.peerCfg); err != nil {
+		if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
 			mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
 			continue
 		}

client/internal/localmetrics/localmetrics.go

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

client/internal/localmetrics/localmetrics_test.go

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

client/internal/metrics/influxdb.go

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

client/internal/metrics/metrics.go

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

client/internal/metrics/metrics_default.go

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

client/internal/metrics/prometheus.go

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

client/internal/peer/status.go

@@ -813,14 +813,19 @@ func (d *Status) SetSessionExpiresAt(deadline time.Time) {
 }
 
 // GetSessionExpiresAt returns the most recently recorded SSO session deadline,
-// or the zero value when no deadline is tracked. A deadline in the past is
-// returned as-is: it means the session has expired, and consumers (tray row,
-// CLI status) render it as "expired" rather than hiding it — masking it as
-// "none" would blank the UI at the exact moment it should say the session
-// ended.
+// or the zero value when no deadline is tracked. A deadline that has already
+// slipped into the past reports as "none": once the session has expired it is
+// no longer a meaningful countdown, and the sessionwatch.Watcher does not
+// arm a timer at the deadline itself to clear it (only the two pre-expiry
+// warnings). Without this guard the UI would keep painting a stale
+// "expires in …" against a moment that has passed until the next login,
+// extend, or teardown rewrote the value.
 func (d *Status) GetSessionExpiresAt() time.Time {
 	d.mux.Lock()
 	defer d.mux.Unlock()
+	if !d.sessionExpiresAt.IsZero() && d.sessionExpiresAt.Before(time.Now()) {
+		return time.Time{}
+	}
 	return d.sessionExpiresAt
 }
 
@@ -1167,6 +1172,18 @@ func (d *Status) GetResolvedDomainsStates() map[domain.Domain]ResolvedDomainInfo
 	return maps.Clone(d.resolvedDomainsStates)
 }
 
+// GetPeerStates returns a snapshot of all known peer states.
+func (d *Status) GetPeerStates() []State {
+	d.mux.RLock()
+	defer d.mux.RUnlock()
+
+	states := make([]State, 0, len(d.peers))
+	for _, state := range d.peers {
+		states = append(states, state)
+	}
+	return states
+}
+
 // GetFullStatus gets full status
 func (d *Status) GetFullStatus() FullStatus {
 	fullStatus := FullStatus{

client/internal/profilemanager/config.go

@@ -96,13 +96,15 @@ type ConfigInput struct {
 	BlockLANAccess      *bool
 	BlockInbound        *bool
 	DisableIPv6         *bool
-	SyncMessageVersion  *int
 
 	DisableNotifications *bool
 
 	DNSLabels domain.List
 
 	MTU *uint16
+
+	LocalMetricsEnabled *bool
+	LocalMetricsAddress *string
 }
 
 // Config Configuration type
@@ -138,12 +140,16 @@ type Config struct {
 	BlockLANAccess      bool
 	BlockInbound        bool
 	DisableIPv6         bool
-	SyncMessageVersion  *int
 
 	DisableNotifications *bool
 
 	DNSLabels domain.List
 
+	// LocalMetricsEnabled enables the local Prometheus /metrics endpoint.
+	LocalMetricsEnabled bool
+	// LocalMetricsAddress is the listen address of the local /metrics endpoint.
+	LocalMetricsAddress string
+
 	// SSHKey is a private SSH key in a PEM format
 	SSHKey string
 
@@ -388,6 +394,18 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 		updated = true
 	}
 
+	if input.LocalMetricsEnabled != nil && *input.LocalMetricsEnabled != config.LocalMetricsEnabled {
+		log.Infof("switching local metrics to %t", *input.LocalMetricsEnabled)
+		config.LocalMetricsEnabled = *input.LocalMetricsEnabled
+		updated = true
+	}
+
+	if input.LocalMetricsAddress != nil && *input.LocalMetricsAddress != config.LocalMetricsAddress {
+		log.Infof("switching local metrics address to %s", *input.LocalMetricsAddress)
+		config.LocalMetricsAddress = *input.LocalMetricsAddress
+		updated = true
+	}
+
 	if input.NetworkMonitor != nil && (config.NetworkMonitor == nil || *input.NetworkMonitor != *config.NetworkMonitor) {
 		log.Infof("switching Network Monitor to %t", *input.NetworkMonitor)
 		config.NetworkMonitor = input.NetworkMonitor
@@ -589,12 +607,6 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 		updated = true
 	}
 
-	if input.SyncMessageVersion != nil && *input.SyncMessageVersion != *config.SyncMessageVersion {
-		log.Infof("setting SyncMessageVersion to %v", *input.SyncMessageVersion)
-		*config.SyncMessageVersion = *input.SyncMessageVersion
-		updated = true
-	}
-
 	if input.DisableNotifications != nil && (config.DisableNotifications == nil || *input.DisableNotifications != *config.DisableNotifications) {
 		if *input.DisableNotifications {
 			log.Infof("disabling notifications")
@@ -718,6 +730,12 @@ func (config *Config) applyMDMPolicy(policy *mdm.Policy) {
 	applyBool(mdm.KeyDisableAutoConnect, func(v bool) { config.DisableAutoConnect = v })
 	applyBool(mdm.KeyRosenpassEnabled, func(v bool) { config.RosenpassEnabled = v })
 	applyBool(mdm.KeyRosenpassPermissive, func(v bool) { config.RosenpassPermissive = v })
+	applyBool(mdm.KeyEnableLocalMetrics, func(v bool) { config.LocalMetricsEnabled = v })
+
+	if v, ok := policy.GetString(mdm.KeyLocalMetricsAddress); ok {
+		config.LocalMetricsAddress = v
+		logApplied(mdm.KeyLocalMetricsAddress, v)
+	}
 
 	if v, ok := policy.GetInt(mdm.KeyWireguardPort); ok {
 		// REG_DWORD is 32-bit; UDP port range is 1-65535. Clamp at the

client/internal/profilemanager/config_mdm_test.go

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

client/internal/routemanager/dnsinterceptor/handler.go

@@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error {
 
 			// AllowedIPs should use real IPs
 			if d.currentPeerKey != "" {
-				if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+				if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 					merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 				}
 			}
@@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error {
 	}
 
 	// AllowedIPs use real IPs
-	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil {
+	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil {
 		return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err)
 	}
 
@@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
 	for _, prefixes := range d.interceptedDomains {
 		for _, prefix := range prefixes {
 			// AllowedIPs use real IPs
-			if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+			if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 			}
 		}

client/internal/routemanager/dynamic/route.go

@@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error {
 	var merr *multierror.Error
 	for _, domainPrefixes := range r.dynamicDomains {
 		for _, prefix := range domainPrefixes {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -185,7 +185,7 @@ func (r *Route) startResolver(ctx context.Context) {
 }
 
 func (r *Route) update(ctx context.Context) error {
-	resolved, err := r.resolveDomains(ctx)
+	resolved, err := r.resolveDomains()
 	if err != nil {
 		if len(resolved) == 0 {
 			return fmt.Errorf("resolve domains: %w", err)
@@ -199,9 +199,9 @@ func (r *Route) update(ctx context.Context) error {
 	return nil
 }
 
-func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
+func (r *Route) resolveDomains() (domainMap, error) {
 	results := make(chan resolveResult)
-	go r.resolve(ctx, results)
+	go r.resolve(results)
 
 	resolved := domainMap{}
 	var merr *multierror.Error
@@ -217,7 +217,7 @@ func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
 	return resolved, nberrors.FormatErrorOrNil(merr)
 }
 
-func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
+func (r *Route) resolve(results chan resolveResult) {
 	var wg sync.WaitGroup
 
 	for _, d := range r.route.Domains {
@@ -225,10 +225,10 @@ func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
 		go func(domain domain.Domain) {
 			defer wg.Done()
 
-			ips, err := r.getIPsFromResolver(ctx, domain)
+			ips, err := r.getIPsFromResolver(domain)
 			if err != nil {
 				log.Tracef("Failed to resolve domain %s with private resolver: %v", domain.SafeString(), err)
-				ips, err = lookupHostIPs(ctx, domain)
+				ips, err = net.LookupIP(domain.PunycodeString())
 				if err != nil {
 					results <- resolveResult{domain: domain, err: fmt.Errorf("resolve d %s: %w", domain.SafeString(), err)}
 					return
@@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) {
 			merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err))
 		}
 		if r.currentPeerKey != "" {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -364,20 +364,6 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR
 	return
 }
 
-// lookupHostIPs resolves d via the system resolver, honoring ctx cancellation.
-func lookupHostIPs(ctx context.Context, d domain.Domain) ([]net.IP, error) {
-	addrs, err := net.DefaultResolver.LookupIPAddr(ctx, d.PunycodeString())
-	if err != nil {
-		return nil, err
-	}
-
-	ips := make([]net.IP, 0, len(addrs))
-	for _, addr := range addrs {
-		ips = append(ips, addr.IP)
-	}
-	return ips, nil
-}
-
 func combinePrefixes(oldPrefixes, removedPrefixes, addedPrefixes []netip.Prefix) []netip.Prefix {
 	prefixSet := make(map[netip.Prefix]struct{})
 	for _, prefix := range oldPrefixes {

client/internal/routemanager/dynamic/route_generic.go

@@ -3,12 +3,11 @@
 package dynamic
 
 import (
-	"context"
 	"net"
 
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
-func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
-	return lookupHostIPs(ctx, domain)
+func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
+	return net.LookupIP(domain.PunycodeString())
 }

client/internal/routemanager/dynamic/route_ios.go

@@ -3,7 +3,6 @@
 package dynamic
 
 import (
-	"context"
 	"fmt"
 	"net"
 	"time"
@@ -17,7 +16,7 @@ import (
 
 const dialTimeout = 10 * time.Second
 
-func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
+func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
 	privateClient, err := nbdns.GetClientPrivate(r.wgInterface, r.resolverAddr.Addr(), dialTimeout)
 	if err != nil {
 		return nil, fmt.Errorf("error while creating private client: %s", err)
@@ -33,7 +32,7 @@ func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([
 		msg := new(dns.Msg)
 		msg.SetQuestion(fqdn, qtype)
 
-		response, _, err := nbdns.ExchangeWithFallback(ctx, privateClient, msg, r.resolverAddr.String())
+		response, _, err := nbdns.ExchangeWithFallback(nil, privateClient, msg, r.resolverAddr.String())
 		if err != nil {
 			if queryErr == nil {
 				queryErr = fmt.Errorf("DNS query for %s (type %d) after %s: %w", domain.SafeString(), qtype, time.Since(startTime), err)

client/internal/routemanager/manager.go

@@ -61,7 +61,6 @@ type Manager interface {
 	InitialRouteRange() []string
 	SetFirewall(firewall.Manager) error
 	SetDNSForwarderPort(port uint16)
-	ReconcilePeerAllowedIPs(peerKey string) error
 	Stop(stateManager *statemanager.Manager)
 }
 
@@ -216,7 +215,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 		)
 	}
 
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New(
 		func(prefix netip.Prefix, peerKey string) (string, error) {
 			// save peerKey to use it in the remove function
 			return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix)
@@ -233,30 +232,6 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 	)
 }
 
-// ReconcilePeerAllowedIPs re-applies every routed allowed IP currently tracked for the peer
-// onto the WireGuard device. The allowed-IP refcounter only calls its AddFunc (which pushes to
-// the device) on a prefix's 0->1 transition, so a peer whose device entry was rebuilt without a
-// matching refcounter change — e.g. a lazy connection cycling through idle->wake, which recreates
-// the WireGuard peer with the overlay /32 only — ends up missing routed prefixes the refcounter
-// still considers installed, and nothing retries. Calling this when the peer's WireGuard entry is
-// (re)created restores convergence. It is add-only and idempotent: AddAllowedIP is update-only, so
-// prefixes are re-added to an existing peer and an absent peer is left untouched.
-func (m *DefaultManager) ReconcilePeerAllowedIPs(peerKey string) error {
-	if m.allowedIPsRefCounter == nil {
-		return nil
-	}
-
-	return m.allowedIPsRefCounter.ReapplyMatching(
-		func(out string) bool { return out == peerKey },
-		func(prefix netip.Prefix) error {
-			if err := m.wgInterface.AddAllowedIP(peerKey, prefix); err != nil {
-				return fmt.Errorf("add allowed IP %s for peer %s: %w", prefix, peerKey, err)
-			}
-			return nil
-		},
-	)
-}
-
 // Init sets up the routing
 func (m *DefaultManager) Init() error {
 	m.routeSelector = m.initSelector()

client/internal/routemanager/mock.go

@@ -112,11 +112,6 @@ func (m *MockManager) SetFirewall(firewall.Manager) error {
 func (m *MockManager) SetDNSForwarderPort(port uint16) {
 }
 
-// ReconcilePeerAllowedIPs mock implementation of ReconcilePeerAllowedIPs from Manager interface
-func (m *MockManager) ReconcilePeerAllowedIPs(peerKey string) error {
-	return nil
-}
-
 // Stop mock implementation of Stop from Manager interface
 func (m *MockManager) Stop(stateManager *statemanager.Manager) {
 	if m.StopFunc != nil {

client/internal/routemanager/reconcile_test.go

@@ -1,90 +0,0 @@
-//go:build !windows
-
-package routemanager
-
-import (
-	"net"
-	"net/netip"
-	"sync"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"golang.zx2c4.com/wireguard/tun/netstack"
-
-	"github.com/netbirdio/netbird/client/iface/device"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
-	"github.com/netbirdio/netbird/client/internal/routemanager/refcounter"
-)
-
-// reconcileWGMock is a minimal iface.WGIface that only records AddAllowedIP calls; every other
-// method is an inert stub because ReconcilePeerAllowedIPs exercises none of them.
-type reconcileWGMock struct {
-	mu   sync.Mutex
-	adds map[string][]netip.Prefix
-}
-
-func (m *reconcileWGMock) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
-	m.mu.Lock()
-	defer m.mu.Unlock()
-	if m.adds == nil {
-		m.adds = map[string][]netip.Prefix{}
-	}
-	m.adds[peerKey] = append(m.adds[peerKey], allowedIP)
-	return nil
-}
-
-func (m *reconcileWGMock) added(peerKey string) []netip.Prefix {
-	m.mu.Lock()
-	defer m.mu.Unlock()
-	return m.adds[peerKey]
-}
-
-func (m *reconcileWGMock) RemoveAllowedIP(string, netip.Prefix) error { return nil }
-func (m *reconcileWGMock) Name() string                               { return "utun-test" }
-func (m *reconcileWGMock) Address() wgaddr.Address                    { return wgaddr.Address{} }
-func (m *reconcileWGMock) ToInterface() *net.Interface                { return nil }
-func (m *reconcileWGMock) IsUserspaceBind() bool                      { return false }
-func (m *reconcileWGMock) GetFilter() device.PacketFilter             { return nil }
-func (m *reconcileWGMock) GetDevice() *device.FilteredDevice          { return nil }
-func (m *reconcileWGMock) GetNet() *netstack.Net                      { return nil }
-
-// TestReconcilePeerAllowedIPs verifies the declarative reconcile re-applies every routed prefix
-// tracked for the peer (self-heal, independent of refcount level) and stays scoped to that peer.
-func TestReconcilePeerAllowedIPs(t *testing.T) {
-	wg := &reconcileWGMock{}
-	m := &DefaultManager{wgInterface: wg}
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
-		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
-		func(netip.Prefix, string) error { return nil },
-	)
-
-	peerA1 := netip.MustParsePrefix("10.0.0.0/24")
-	peerA2 := netip.MustParsePrefix("10.1.0.0/24")
-	peerB1 := netip.MustParsePrefix("10.2.0.0/24")
-
-	for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
-		_, err := m.allowedIPsRefCounter.Increment(prefix, peer)
-		require.NoError(t, err)
-	}
-	// Extra reference: reconcile must still re-apply the prefix even though its refcount never
-	// hit 0 again (the exact case the plain incremental path skips).
-	_, err := m.allowedIPsRefCounter.Increment(peerA1, "peerA")
-	require.NoError(t, err)
-
-	require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
-
-	assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, wg.added("peerA"),
-		"reconcile must re-apply all routed prefixes of the peer")
-	assert.Empty(t, wg.added("peerB"), "reconcile must not touch another peer's prefixes")
-}
-
-// TestReconcilePeerAllowedIPsNoCounter verifies reconcile is a safe no-op before the refcounter is
-// set up.
-func TestReconcilePeerAllowedIPsNoCounter(t *testing.T) {
-	wg := &reconcileWGMock{}
-	m := &DefaultManager{wgInterface: wg}
-
-	require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
-	assert.Empty(t, wg.added("peerA"))
-}

client/internal/routemanager/refcounter/allowedips.go

@@ -1,206 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"fmt"
-	"net/netip"
-	"sort"
-	"sync"
-
-	"github.com/hashicorp/go-multierror"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-)
-
-// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is
-// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most
-// one peer is active at a time even when several peers reference the prefix.
-type allowedIPsEntry struct {
-	// peers maps a peerKey to the number of references holding the prefix for that peer.
-	peers map[string]int
-	// active is the peerKey currently installed in WireGuard for this prefix ("" if none).
-	active string
-	// total is the sum of all per-peer reference counts (kept in sync with peers).
-	total int
-}
-
-// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs.
-//
-// The generic Counter keys only by prefix and remembers a single Out value set by the first
-// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or
-// multiple resolved domains) can reference the same prefix through different peers, and when the
-// peer currently installed in WireGuard releases its last reference the prefix must be handed over
-// to a surviving peer instead of being left pointing at the released one.
-//
-// It calls add/remove (which program WireGuard) only on the transitions that matter:
-//   - add on the first reference for a prefix, or when swapping the active peer;
-//   - remove on the last reference for a prefix, or on the old peer during a swap.
-type AllowedIPsRefCounter struct {
-	mu      sync.Mutex
-	entries map[netip.Prefix]*allowedIPsEntry
-	add     AddFunc[netip.Prefix, string, string]
-	remove  RemoveFunc[netip.Prefix, string]
-}
-
-// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter.
-// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer.
-// remove unprograms the prefix from the given peer.
-func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter {
-	return &AllowedIPsRefCounter{
-		entries: map[netip.Prefix]*allowedIPsEntry{},
-		add:     add,
-		remove:  remove,
-	}
-}
-
-// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first
-// reference to a prefix; while a different peer is already installed the prefix is left with it
-// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept.
-func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		e = &allowedIPsEntry{peers: map[string]int{}}
-		rm.entries[prefix] = e
-	}
-
-	logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-		prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active)
-
-	// Program WireGuard only when nothing is installed yet for this prefix.
-	if e.active == "" {
-		out, err := rm.add(prefix, peerKey)
-		if errors.Is(err, ErrIgnore) {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{Count: e.total, Out: e.active}, nil
-		}
-		if err != nil {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err)
-		}
-		e.active = out
-	}
-
-	e.peers[peerKey]++
-	e.total++
-
-	return Ref[string]{Count: e.total, Out: e.active}, nil
-}
-
-// Decrement removes a reference to prefix for peerKey. When the peer currently installed in
-// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists,
-// otherwise it is removed from WireGuard.
-func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		logCallerF("No allowed IP reference found for prefix %v", prefix)
-		return Ref[string]{}, nil
-	}
-
-	if e.peers[peerKey] > 0 {
-		logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-			prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active)
-		e.peers[peerKey]--
-		e.total--
-		if e.peers[peerKey] == 0 {
-			delete(e.peers, peerKey)
-		}
-	} else {
-		logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey)
-	}
-
-	// If the peer currently installed in WireGuard still holds references, nothing to reprogram.
-	// Keying the check on the active peer (not the one just released) makes this self-healing:
-	// a prior swap whose remove/add failed leaves e.active pointing at a peer with no references,
-	// and this retries the hand-off on the next Decrement instead of getting stuck.
-	if e.active != "" && e.peers[e.active] > 0 {
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	// Detach the stale/gone active peer from WireGuard before reprogramming.
-	if e.active != "" {
-		if err := rm.remove(prefix, e.active); err != nil {
-			return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)
-		}
-		e.active = ""
-	}
-
-	// Hand the prefix over to a surviving peer, or drop the entry when none remain.
-	if survivor, ok := pickSurvivor(e.peers); ok {
-		out, err := rm.add(prefix, survivor)
-		if err != nil {
-			return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err)
-		}
-		e.active = out
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	delete(rm.entries, prefix)
-	return Ref[string]{Count: 0, Out: ""}, nil
-}
-
-// Flush removes all prefixes from WireGuard and clears the counter.
-func (rm *AllowedIPsRefCounter) Flush() error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active == "" {
-			continue
-		}
-		logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active)
-		if err := rm.remove(prefix, e.active); err != nil {
-			merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err))
-		}
-	}
-
-	clear(rm.entries)
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies
-// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose
-// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching
-// refcounter change, which would otherwise leave the prefix installed in the counter but missing
-// on the device. Only the active peer is considered — a prefix that lost its installed peer to a
-// failed swap is skipped here and reconciled by the next Increment/Decrement.
-func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active != "" && pred(e.active) {
-			if err := apply(prefix); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do
-// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable
-// (lowest peerKey) for predictable behavior and testability.
-func pickSurvivor(peers map[string]int) (string, bool) {
-	if len(peers) == 0 {
-		return "", false
-	}
-	keys := make([]string, 0, len(peers))
-	for k := range peers {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	return keys[0], true
-}

client/internal/routemanager/refcounter/allowedips_test.go

@@ -1,241 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"net/netip"
-	"testing"
-)
-
-// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer.
-// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths.
-type fakeWG struct {
-	installed  map[netip.Prefix]string
-	adds       int
-	removes    int
-	failAdd    bool
-	failRemove bool
-}
-
-func newFakeWG() *fakeWG {
-	return &fakeWG{installed: map[netip.Prefix]string{}}
-}
-
-func (f *fakeWG) counter() *AllowedIPsRefCounter {
-	return NewAllowedIPs(
-		func(prefix netip.Prefix, peerKey string) (string, error) {
-			if f.failAdd {
-				f.failAdd = false
-				return "", errors.New("add failed")
-			}
-			f.adds++
-			f.installed[prefix] = peerKey
-			return peerKey, nil
-		},
-		func(prefix netip.Prefix, peerKey string) error {
-			if f.failRemove {
-				f.failRemove = false
-				return errors.New("remove failed")
-			}
-			f.removes++
-			// only clear if this peer is the one installed, mirroring wg semantics
-			if f.installed[prefix] == peerKey {
-				delete(f.installed, prefix)
-			}
-			return nil
-		},
-	)
-}
-
-func mustPrefix(t *testing.T, s string) netip.Prefix {
-	t.Helper()
-	p, err := netip.ParsePrefix(s)
-	if err != nil {
-		t.Fatalf("parse prefix %q: %v", s, err)
-	}
-	return p
-}
-
-func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Increment(p, peer)
-	if err != nil {
-		t.Fatalf("Increment(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Decrement(p, peer)
-	if err != nil {
-		t.Fatalf("Decrement(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same
-// prefix routed by different peers. Removing the network whose peer is installed must hand the
-// prefix over to the surviving peer instead of leaving it on the removed one.
-func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	// First peer wins while both are present.
-	if got := f.installed[p]; got != "peerA" {
-		t.Fatalf("expected peerA installed, got %q", got)
-	}
-
-	// Remove the active peer's network -> must swap to peerB.
-	mustDecrement(t, c, p, "peerA")
-	if got := f.installed[p]; got != "peerB" {
-		t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got)
-	}
-
-	// Remove the last one -> prefix gone.
-	mustDecrement(t, c, p, "peerB")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix removed, still installed on %q", f.installed[p])
-	}
-}
-
-// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard.
-func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	removesBefore := f.removes
-
-	mustDecrement(t, c, p, "peerB")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("active peer must stay peerA, got %q", f.installed[p])
-	}
-	if f.removes != removesBefore {
-		t.Fatalf("removing a non-active peer must not call wg remove")
-	}
-}
-
-// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until
-// the last reference is released (the reason the per-peer count must be an int, not a set).
-func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerA")
-	if f.adds != 1 {
-		t.Fatalf("expected a single wg add for the same peer, got %d", f.adds)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p])
-	}
-	if f.removes != 0 {
-		t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("prefix must be removed after last reference")
-	}
-}
-
-// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log).
-func TestAllowedIPs_RefCountAndActive(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	ref := mustIncrement(t, c, p, "peerA")
-	if ref.Count != 1 || ref.Out != "peerA" {
-		t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-	ref = mustIncrement(t, c, p, "peerB")
-	if ref.Count != 2 || ref.Out != "peerA" {
-		t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-}
-
-// TestAllowedIPs_Flush removes everything installed and clears the counter.
-func TestAllowedIPs_Flush(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p1 := mustPrefix(t, "10.44.8.0/24")
-	p2 := mustPrefix(t, "10.44.9.0/24")
-
-	mustIncrement(t, c, p1, "peerA")
-	mustIncrement(t, c, p2, "peerB")
-
-	if err := c.Flush(); err != nil {
-		t.Fatal(err)
-	}
-	if len(f.installed) != 0 {
-		t.Fatalf("expected all prefixes removed, got %v", f.installed)
-	}
-	// After flush, a fresh increment must add again.
-	mustIncrement(t, c, p1, "peerC")
-	if f.installed[p1] != "peerC" {
-		t.Fatalf("counter not reset after flush")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently
-// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer.
-func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	mustIncrement(t, c, p, "peerC")
-
-	// Removing the active peerA triggers a swap to a survivor; make the add fail once.
-	f.failAdd = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed swap add")
-	}
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p])
-	}
-
-	// A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck.
-	ref := mustDecrement(t, c, p, "peerC")
-	if got := f.installed[p]; got == "" {
-		t.Fatalf("self-heal failed: prefix left unrouted after add recovered")
-	}
-	if ref.Out == "" {
-		t.Fatalf("expected an active peer after self-heal, got empty")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead
-// of leaving e.active stuck on a peer that no longer holds references.
-func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-
-	// Releasing active peerA must detach it (remove) then add peerB; fail the remove once.
-	f.failRemove = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed remove")
-	}
-
-	// Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB.
-	mustDecrement(t, c, p, "peerB")
-	// peerB had only one ref, so after retry the prefix is fully released.
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p])
-	}
-}

client/internal/routemanager/refcounter/refcounter.go

@@ -94,26 +94,6 @@ func (rm *Counter[Key, I, O]) Get(key Key) (Ref[O], bool) {
 	return ref, ok
 }
 
-// ReapplyMatching calls apply for every key whose stored Out satisfies pred, holding the
-// counter lock for the whole pass. Running apply under the lock keeps it atomic with respect
-// to Increment/Decrement: a prefix dropped to zero is removed from the map (and had its
-// RemoveFunc called) before this pass observes it, so a stale key can never be re-applied.
-// pred and apply are invoked under the lock, so they must not call back into the counter.
-func (rm *Counter[Key, I, O]) ReapplyMatching(pred func(out O) bool, apply func(key Key) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for key, ref := range rm.refCountMap {
-		if pred(ref.Out) {
-			if err := apply(key); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
 // Increment increments the reference count for the given key.
 // If this is the first reference to the key, the AddFunc is called.
 func (rm *Counter[Key, I, O]) Increment(key Key, in I) (Ref[O], error) {

client/internal/routemanager/refcounter/refcounter_test.go

@@ -1,47 +0,0 @@
-package refcounter
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-// TestReapplyMatching verifies ReapplyMatching invokes apply for exactly the keys whose stored
-// Out satisfies the predicate (no duplicates for multiply-referenced keys) — the primitive
-// ReconcilePeerAllowedIPs relies on to re-apply a single peer's routed prefixes.
-func TestReapplyMatching(t *testing.T) {
-	rc := New[netip.Prefix, string, string](
-		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
-		func(netip.Prefix, string) error { return nil },
-	)
-
-	peerA1 := netip.MustParsePrefix("10.0.0.0/24")
-	peerA2 := netip.MustParsePrefix("10.1.0.0/24")
-	peerB1 := netip.MustParsePrefix("10.2.0.0/24")
-
-	for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
-		_, err := rc.Increment(prefix, peer)
-		require.NoError(t, err)
-	}
-	// a second reference must not make the key applied twice
-	_, err := rc.Increment(peerA1, "peerA")
-	require.NoError(t, err)
-
-	var applied []netip.Prefix
-	err = rc.ReapplyMatching(
-		func(out string) bool { return out == "peerA" },
-		func(key netip.Prefix) error { applied = append(applied, key); return nil },
-	)
-	require.NoError(t, err)
-	assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, applied)
-
-	var none []netip.Prefix
-	err = rc.ReapplyMatching(
-		func(out string) bool { return out == "missing" },
-		func(key netip.Prefix) error { none = append(none, key); return nil },
-	)
-	require.NoError(t, err)
-	assert.Empty(t, none)
-}

client/internal/routemanager/refcounter/types.go

@@ -5,7 +5,5 @@ import "net/netip"
 // RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement
 type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}]
 
-// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware:
-// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer,
-// so the counter records the per-peer reference count and swaps the installed peer when the active one is released.
-// See allowedips.go.
+// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement
+type AllowedIPsRefCounter = Counter[netip.Prefix, string, string]

client/internal/routemanager/static/route.go

@@ -15,11 +15,6 @@ type Route struct {
 	route                *route.Route
 	routeRefCounter      *refcounter.RouteRefCounter
 	allowedIPsRefcounter *refcounter.AllowedIPsRefCounter
-	// currentPeerKey is the routing peer this watcher currently has the prefix installed on
-	// (the HA winner elected by the watcher). It can differ from route.Peer and change on
-	// failover, so it is recorded on AddAllowedIPs and used on RemoveAllowedIPs to decrement
-	// the exact peer that was incremented.
-	currentPeerKey string
 }
 
 func NewRoute(params common.HandlerParams) *Route {
@@ -57,15 +52,12 @@ func (r *Route) AddAllowedIPs(peerKey string) error {
 			ref.Out,
 		)
 	}
-	r.currentPeerKey = peerKey
 	return nil
 }
 
 func (r *Route) RemoveAllowedIPs() error {
-	var err error
-	if _, decErr := r.allowedIPsRefcounter.Decrement(r.route.Network, r.currentPeerKey); decErr != nil {
-		err = fmt.Errorf("remove allowed IP %s: %w", r.route.Network, decErr)
+	if _, err := r.allowedIPsRefcounter.Decrement(r.route.Network); err != nil {
+		return err
 	}
-	r.currentPeerKey = ""
-	return err
+	return nil
 }

client/internal/routemanager/sysctl/sysctl_linux.go

@@ -20,8 +20,6 @@ const (
 	rpFilterPath          = "net.ipv4.conf.all.rp_filter"
 	rpFilterInterfacePath = "net.ipv4.conf.%s.rp_filter"
 	srcValidMarkPath      = "net.ipv4.conf.all.src_valid_mark"
-	percentEscape         = "%25"
-	dotEscape             = "%2E"
 )
 
 type iface interface {
@@ -58,11 +56,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 			continue
 		}
 
-		// Escape '%' and '.' so they survive the dot-to-slash conversion in Set()
-		safeName := strings.ReplaceAll(intf.Name, "%", percentEscape)
-		safeName = strings.ReplaceAll(safeName, ".", dotEscape)
-
-		i := fmt.Sprintf(rpFilterInterfacePath, safeName)
+		i := fmt.Sprintf(rpFilterInterfacePath, intf.Name)
 		oldVal, err := Set(i, 2, true)
 		if err != nil {
 			result = multierror.Append(result, err)
@@ -76,11 +70,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 
 // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1
 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) {
-	path := strings.ReplaceAll(key, ".", "/")
-	// Unescape interface dots and percent signs
-	path = strings.ReplaceAll(path, dotEscape, ".")
-	path = strings.ReplaceAll(path, percentEscape, "%")
-	path = fmt.Sprintf("/proc/sys/%s", path)
+	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
 	currentValue, err := os.ReadFile(path)
 	if err != nil {
 		return -1, fmt.Errorf("read sysctl %s: %w", key, err)

client/internal/statemanager/manager.go

@@ -1,7 +1,6 @@
 package statemanager
 
 import (
-	"bytes"
 	"context"
 	"encoding/json"
 	"errors"
@@ -306,11 +305,6 @@ func (m *Manager) loadStateFile(deleteCorrupt bool) (map[string]json.RawMessage,
 
 	var rawStates map[string]json.RawMessage
 	if err := json.Unmarshal(data, &rawStates); err != nil {
-		if len(bytes.TrimSpace(data)) == 0 {
-			log.Warnf("state file %s is empty (%d bytes)", m.filePath, len(data))
-		} else {
-			log.Warnf("state file %s has malformed content (%d bytes)", m.filePath, len(data))
-		}
 		m.handleCorruptedState(deleteCorrupt)
 		return nil, fmt.Errorf("unmarshal states: %w", err)
 	}

client/ios/NetBirdSDK/client.go

@@ -233,9 +233,6 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) {
 		deps.SyncResponse = resp
 
 		if e := cc.Engine(); e != nil {
-			deps.RefreshStatus = func() {
-				e.RunHealthProbes(context.Background(), true)
-			}
 			if cm := e.GetClientMetrics(); cm != nil {
 				deps.ClientMetrics = cm
 			}

client/ios/NetBirdSDK/login.go

@@ -44,25 +44,10 @@ type Auth struct {
 // NewAuth instantiate Auth struct and validate the management URL
 func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
 	inputCfg := profilemanager.ConfigInput{
-		ConfigPath:    cfgPath,
 		ManagementURL: mgmURL,
 	}
 
-	// Load the existing config when a config file is already present so an
-	// interactive re-login reuses the peer's persisted WireGuard private key
-	// (and thus its identity) instead of generating a fresh one. Generating a
-	// new key registers a brand-new peer on the management server on every
-	// re-auth (named after the fallback hostname). Only fall back to a fresh
-	// in-memory config for the first-time login when no config file exists yet.
-	// DirectUpdateOrCreateConfig uses non-atomic writes so it also works inside
-	// the tvOS App Group sandbox where atomic temp-file+rename is blocked.
-	var cfg *profilemanager.Config
-	var err error
-	if cfgPath != "" {
-		cfg, err = profilemanager.DirectUpdateOrCreateConfig(inputCfg)
-	} else {
-		cfg, err = profilemanager.CreateInMemoryConfig(inputCfg)
-	}
+	cfg, err := profilemanager.CreateInMemoryConfig(inputCfg)
 	if err != nil {
 		return nil, err
 	}

client/ios/NetBirdSDK/version.go

@@ -1,12 +0,0 @@
-//go:build ios
-
-package NetBirdSDK
-
-import "github.com/netbirdio/netbird/version"
-
-// GoClientVersion returns the NetBird Go client version that was baked into
-// the framework at compile time via
-// -ldflags "-X github.com/netbirdio/netbird/version.version=<version>".
-func GoClientVersion() string {
-	return version.NetbirdVersion()
-}

client/mdm/policy.go

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

client/proto/daemon.pb.go

@@ -343,6 +343,8 @@ type LoginRequest struct {
 	DisableSSHAuth                *bool   `protobuf:"varint,38,opt,name=disableSSHAuth,proto3,oneof" json:"disableSSHAuth,omitempty"`
 	SshJWTCacheTTL                *int32  `protobuf:"varint,39,opt,name=sshJWTCacheTTL,proto3,oneof" json:"sshJWTCacheTTL,omitempty"`
 	DisableIpv6                   *bool   `protobuf:"varint,40,opt,name=disable_ipv6,json=disableIpv6,proto3,oneof" json:"disable_ipv6,omitempty"`
+	EnableLocalMetrics            *bool   `protobuf:"varint,41,opt,name=enable_local_metrics,json=enableLocalMetrics,proto3,oneof" json:"enable_local_metrics,omitempty"`
+	LocalMetricsAddress           *string `protobuf:"bytes,42,opt,name=local_metrics_address,json=localMetricsAddress,proto3,oneof" json:"local_metrics_address,omitempty"`
 	unknownFields                 protoimpl.UnknownFields
 	sizeCache                     protoimpl.SizeCache
 }
@@ -658,6 +660,20 @@ func (x *LoginRequest) GetDisableIpv6() bool {
 	return false
 }
 
+func (x *LoginRequest) GetEnableLocalMetrics() bool {
+	if x != nil && x.EnableLocalMetrics != nil {
+		return *x.EnableLocalMetrics
+	}
+	return false
+}
+
+func (x *LoginRequest) GetLocalMetricsAddress() string {
+	if x != nil && x.LocalMetricsAddress != nil {
+		return *x.LocalMetricsAddress
+	}
+	return ""
+}
+
 type LoginResponse struct {
 	state                   protoimpl.MessageState `protogen:"open.v1"`
 	NeedsSSOLogin           bool                   `protobuf:"varint,1,opt,name=needsSSOLogin,proto3" json:"needsSSOLogin,omitempty"`
@@ -4210,6 +4226,8 @@ type SetConfigRequest struct {
 	DisableSSHAuth                *bool                `protobuf:"varint,33,opt,name=disableSSHAuth,proto3,oneof" json:"disableSSHAuth,omitempty"`
 	SshJWTCacheTTL                *int32               `protobuf:"varint,34,opt,name=sshJWTCacheTTL,proto3,oneof" json:"sshJWTCacheTTL,omitempty"`
 	DisableIpv6                   *bool                `protobuf:"varint,35,opt,name=disable_ipv6,json=disableIpv6,proto3,oneof" json:"disable_ipv6,omitempty"`
+	EnableLocalMetrics            *bool                `protobuf:"varint,36,opt,name=enable_local_metrics,json=enableLocalMetrics,proto3,oneof" json:"enable_local_metrics,omitempty"`
+	LocalMetricsAddress           *string              `protobuf:"bytes,37,opt,name=local_metrics_address,json=localMetricsAddress,proto3,oneof" json:"local_metrics_address,omitempty"`
 	unknownFields                 protoimpl.UnknownFields
 	sizeCache                     protoimpl.SizeCache
 }
@@ -4489,6 +4507,20 @@ func (x *SetConfigRequest) GetDisableIpv6() bool {
 	return false
 }
 
+func (x *SetConfigRequest) GetEnableLocalMetrics() bool {
+	if x != nil && x.EnableLocalMetrics != nil {
+		return *x.EnableLocalMetrics
+	}
+	return false
+}
+
+func (x *SetConfigRequest) GetLocalMetricsAddress() string {
+	if x != nil && x.LocalMetricsAddress != nil {
+		return *x.LocalMetricsAddress
+	}
+	return ""
+}
+
 type SetConfigResponse struct {
 	state         protoimpl.MessageState `protogen:"open.v1"`
 	unknownFields protoimpl.UnknownFields
@@ -6987,7 +7019,7 @@ var File_daemon_proto protoreflect.FileDescriptor
 const file_daemon_proto_rawDesc = "" +
 	"\n" +
 	"\fdaemon.proto\x12\x06daemon\x1a google/protobuf/descriptor.proto\x1a\x1fgoogle/protobuf/timestamp.proto\x1a\x1egoogle/protobuf/duration.proto\"\x0e\n" +
-	"\fEmptyRequest\"\xef\x12\n" +
+	"\fEmptyRequest\"\x92\x14\n" +
 	"\fLoginRequest\x12\x1a\n" +
 	"\bsetupKey\x18\x01 \x01(\tR\bsetupKey\x12&\n" +
 	"\fpreSharedKey\x18\x02 \x01(\tB\x02\x18\x01R\fpreSharedKey\x12$\n" +
@@ -7032,7 +7064,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1denableSSHRemotePortForwarding\x18% \x01(\bH\x18R\x1denableSSHRemotePortForwarding\x88\x01\x01\x12+\n" +
 	"\x0edisableSSHAuth\x18& \x01(\bH\x19R\x0edisableSSHAuth\x88\x01\x01\x12+\n" +
 	"\x0esshJWTCacheTTL\x18' \x01(\x05H\x1aR\x0esshJWTCacheTTL\x88\x01\x01\x12&\n" +
-	"\fdisable_ipv6\x18( \x01(\bH\x1bR\vdisableIpv6\x88\x01\x01B\x13\n" +
+	"\fdisable_ipv6\x18( \x01(\bH\x1bR\vdisableIpv6\x88\x01\x01\x125\n" +
+	"\x14enable_local_metrics\x18) \x01(\bH\x1cR\x12enableLocalMetrics\x88\x01\x01\x127\n" +
+	"\x15local_metrics_address\x18* \x01(\tH\x1dR\x13localMetricsAddress\x88\x01\x01B\x13\n" +
 	"\x11_rosenpassEnabledB\x10\n" +
 	"\x0e_interfaceNameB\x10\n" +
 	"\x0e_wireguardPortB\x17\n" +
@@ -7060,7 +7094,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1e_enableSSHRemotePortForwardingB\x11\n" +
 	"\x0f_disableSSHAuthB\x11\n" +
 	"\x0f_sshJWTCacheTTLB\x0f\n" +
-	"\r_disable_ipv6\"\xb5\x01\n" +
+	"\r_disable_ipv6B\x17\n" +
+	"\x15_enable_local_metricsB\x18\n" +
+	"\x16_local_metrics_address\"\xb5\x01\n" +
 	"\rLoginResponse\x12$\n" +
 	"\rneedsSSOLogin\x18\x01 \x01(\bR\rneedsSSOLogin\x12\x1a\n" +
 	"\buserCode\x18\x02 \x01(\tR\buserCode\x12(\n" +
@@ -7353,7 +7389,7 @@ const file_daemon_proto_rawDesc = "" +
 	"\f_profileNameB\v\n" +
 	"\t_username\"'\n" +
 	"\x15SwitchProfileResponse\x12\x0e\n" +
-	"\x02id\x18\x01 \x01(\tR\x02id\"\x98\x11\n" +
+	"\x02id\x18\x01 \x01(\tR\x02id\"\xbb\x12\n" +
 	"\x10SetConfigRequest\x12\x1a\n" +
 	"\busername\x18\x01 \x01(\tR\busername\x12 \n" +
 	"\vprofileName\x18\x02 \x01(\tR\vprofileName\x12$\n" +
@@ -7393,7 +7429,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1denableSSHRemotePortForwarding\x18  \x01(\bH\x15R\x1denableSSHRemotePortForwarding\x88\x01\x01\x12+\n" +
 	"\x0edisableSSHAuth\x18! \x01(\bH\x16R\x0edisableSSHAuth\x88\x01\x01\x12+\n" +
 	"\x0esshJWTCacheTTL\x18\" \x01(\x05H\x17R\x0esshJWTCacheTTL\x88\x01\x01\x12&\n" +
-	"\fdisable_ipv6\x18# \x01(\bH\x18R\vdisableIpv6\x88\x01\x01B\x13\n" +
+	"\fdisable_ipv6\x18# \x01(\bH\x18R\vdisableIpv6\x88\x01\x01\x125\n" +
+	"\x14enable_local_metrics\x18$ \x01(\bH\x19R\x12enableLocalMetrics\x88\x01\x01\x127\n" +
+	"\x15local_metrics_address\x18% \x01(\tH\x1aR\x13localMetricsAddress\x88\x01\x01B\x13\n" +
 	"\x11_rosenpassEnabledB\x10\n" +
 	"\x0e_interfaceNameB\x10\n" +
 	"\x0e_wireguardPortB\x17\n" +
@@ -7418,7 +7456,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x1e_enableSSHRemotePortForwardingB\x11\n" +
 	"\x0f_disableSSHAuthB\x11\n" +
 	"\x0f_sshJWTCacheTTLB\x0f\n" +
-	"\r_disable_ipv6\"\x13\n" +
+	"\r_disable_ipv6B\x17\n" +
+	"\x15_enable_local_metricsB\x18\n" +
+	"\x16_local_metrics_address\"\x13\n" +
 	"\x11SetConfigResponse\"Q\n" +
 	"\x11AddProfileRequest\x12\x1a\n" +
 	"\busername\x18\x01 \x01(\tR\busername\x12 \n" +

client/proto/daemon.proto

@@ -242,6 +242,9 @@ message LoginRequest {
   optional bool disableSSHAuth = 38;
   optional int32 sshJWTCacheTTL = 39;
   optional bool disable_ipv6 = 40;
+
+  optional bool enable_local_metrics = 41;
+  optional string local_metrics_address = 42;
 }
 
 message LoginResponse {
@@ -757,6 +760,9 @@ message SetConfigRequest {
   optional bool disableSSHAuth = 33;
   optional int32 sshJWTCacheTTL = 34;
   optional bool disable_ipv6 = 35;
+
+  optional bool enable_local_metrics = 36;
+  optional string local_metrics_address = 37;
 }
 
 message SetConfigResponse{}

client/server/mdm.go

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

client/server/server.go

@@ -23,6 +23,9 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/expose"
+	"github.com/prometheus/client_golang/prometheus"
+
+	"github.com/netbirdio/netbird/client/internal/localmetrics"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	sleephandler "github.com/netbirdio/netbird/client/internal/sleep/handler"
 	"github.com/netbirdio/netbird/client/mdm"
@@ -99,6 +102,7 @@ type Server struct {
 
 	statusRecorder *peer.Status
 	sessionWatcher *internal.SessionWatcher
+	localMetrics   *localmetrics.Manager
 
 	probeThrottle       *probeThrottle
 	persistSyncResponse bool
@@ -155,9 +159,28 @@ func New(ctx context.Context, logFile string, configFile string, profilesDisable
 	s.sleepHandler = sleephandler.New(agent)
 	s.startSleepDetector()
 
+	s.localMetrics = localmetrics.NewManager(ctx, s.statusRecorder, s.clientMetricsGatherer)
+
 	return s
 }
 
+// clientMetricsGatherer returns the Prometheus gatherer of the running
+// engine's client metrics, or nil when no engine is running.
+func (s *Server) clientMetricsGatherer() prometheus.Gatherer {
+	s.mutex.Lock()
+	connectClient := s.connectClient
+	s.mutex.Unlock()
+
+	if connectClient == nil {
+		return nil
+	}
+	engine := connectClient.Engine()
+	if engine == nil {
+		return nil
+	}
+	return engine.GetClientMetrics().PrometheusGatherer()
+}
+
 func (s *Server) Start() error {
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
@@ -238,6 +261,7 @@ func (s *Server) Start() error {
 
 	s.statusRecorder.UpdateManagementAddress(config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(config.RosenpassEnabled, config.RosenpassPermissive)
+	s.localMetrics.Reconcile(config.LocalMetricsEnabled, config.LocalMetricsAddress)
 
 	if s.sessionWatcher == nil {
 		s.sessionWatcher = internal.NewSessionWatcher(s.rootCtx, s.statusRecorder)
@@ -416,11 +440,18 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques
 		return nil, err
 	}
 
-	if _, err := profilemanager.UpdateConfig(config); err != nil {
+	updatedConf, err := profilemanager.UpdateConfig(config)
+	if err != nil {
 		log.Errorf("failed to update profile config: %v", err)
 		return nil, fmt.Errorf("failed to update profile config: %w", err)
 	}
 
+	if activeProf, err := s.profileManager.GetActiveProfileState(); err == nil {
+		if activePath, err := activeProf.FilePath(); err == nil && activePath == config.ConfigPath {
+			s.localMetrics.Reconcile(updatedConf.LocalMetricsEnabled, updatedConf.LocalMetricsAddress)
+		}
+	}
+
 	return &proto.SetConfigResponse{}, nil
 }
 
@@ -490,6 +521,8 @@ func (s *Server) setConfigInputFromRequest(msg *proto.SetConfigRequest) (profile
 
 	config.RosenpassEnabled = msg.RosenpassEnabled
 	config.RosenpassPermissive = msg.RosenpassPermissive
+	config.LocalMetricsEnabled = msg.EnableLocalMetrics
+	config.LocalMetricsAddress = msg.LocalMetricsAddress
 	config.DisableAutoConnect = msg.DisableAutoConnect
 	config.ServerSSHAllowed = msg.ServerSSHAllowed
 	config.NetworkMonitor = msg.NetworkMonitor
@@ -945,6 +978,7 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 
 	s.statusRecorder.UpdateManagementAddress(s.config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(s.config.RosenpassEnabled, s.config.RosenpassPermissive)
+	s.localMetrics.Reconcile(s.config.LocalMetricsEnabled, s.config.LocalMetricsAddress)
 
 	s.clientRunning = true
 	s.clientRunningChan = make(chan struct{})
@@ -1081,10 +1115,7 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
 
 	if err := s.cleanupConnection(); err != nil {
 		s.mutex.Unlock()
-		if errors.Is(err, ErrServiceNotUp) {
-			log.Debugf("Down called while service not up: %v", err)
-			return nil, err
-		}
+		// todo review to update the status in case any type of error
 		log.Errorf("failed to shut down properly: %v", err)
 		return nil, err
 	}
@@ -1157,7 +1188,7 @@ func (s *Server) cleanupConnection() error {
 	// making the run loop the sole owner of engine shutdown.
 	if engine != nil {
 		if err := engine.Stop(); err != nil {
-			log.Errorf("failed to stop engine during cleanup: %v", err)
+			return err
 		}
 	}
 

client/server/setconfig_mdm_test.go

@@ -132,6 +132,30 @@ func TestSetConfig_MDMReject_MultipleFields(t *testing.T) {
 	}, v.GetFields())
 }
 
+func TestSetConfig_MDMReject_LocalMetrics(t *testing.T) {
+	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
+		mdm.KeyEnableLocalMetrics:  true,
+		mdm.KeyLocalMetricsAddress: "127.0.0.1:9191",
+	}))
+
+	s, ctx, profName, username, _ := setupServerWithProfile(t)
+
+	enabled := false
+	addr := "0.0.0.0:9999"
+	_, err := s.SetConfig(ctx, &proto.SetConfigRequest{
+		ProfileName:         profName,
+		Username:            username,
+		EnableLocalMetrics:  &enabled,
+		LocalMetricsAddress: &addr,
+	})
+
+	v := extractViolation(t, err)
+	assert.ElementsMatch(t, []string{
+		mdm.KeyEnableLocalMetrics,
+		mdm.KeyLocalMetricsAddress,
+	}, v.GetFields())
+}
+
 func TestSetConfig_MDMReject_AllOrNothing(t *testing.T) {
 	// MDM enforces ManagementURL only; user request touches both the
 	// enforced field AND a non-enforced field (RosenpassEnabled).

client/server/setconfig_test.go

@@ -73,6 +73,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	disableIPv6 := true
 	mtu := int64(1280)
 	sshJWTCacheTTL := int32(300)
+	enableLocalMetrics := true
+	localMetricsAddress := "127.0.0.1:9292"
 
 	req := &proto.SetConfigRequest{
 		ProfileName:          profName,
@@ -104,6 +106,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 		DnsRouteInterval:     durationpb.New(2 * time.Minute),
 		Mtu:                  &mtu,
 		SshJWTCacheTTL:       &sshJWTCacheTTL,
+		EnableLocalMetrics:   &enableLocalMetrics,
+		LocalMetricsAddress:  &localMetricsAddress,
 	}
 
 	_, err = s.SetConfig(ctx, req)
@@ -150,6 +154,8 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	require.Equal(t, uint16(mtu), cfg.MTU)
 	require.NotNil(t, cfg.SSHJWTCacheTTL)
 	require.Equal(t, int(sshJWTCacheTTL), *cfg.SSHJWTCacheTTL)
+	require.Equal(t, enableLocalMetrics, cfg.LocalMetricsEnabled)
+	require.Equal(t, localMetricsAddress, cfg.LocalMetricsAddress)
 
 	verifyAllFieldsCovered(t, req)
 }
@@ -202,6 +208,8 @@ func verifyAllFieldsCovered(t *testing.T, req *proto.SetConfigRequest) {
 		"EnableSSHRemotePortForwarding": true,
 		"DisableSSHAuth":                true,
 		"SshJWTCacheTTL":                true,
+		"EnableLocalMetrics":            true,
+		"LocalMetricsAddress":           true,
 	}
 
 	val := reflect.ValueOf(req).Elem()
@@ -261,6 +269,8 @@ func TestCLIFlags_MappedToSetConfig(t *testing.T) {
 		"enable-ssh-remote-port-forwarding": "EnableSSHRemotePortForwarding",
 		"disable-ssh-auth":                  "DisableSSHAuth",
 		"ssh-jwt-cache-ttl":                 "SshJWTCacheTTL",
+		"enable-local-metrics":              "EnableLocalMetrics",
+		"local-metrics-address":             "LocalMetricsAddress",
 	}
 
 	// SetConfigRequest fields that don't have CLI flags (settable only via UI or other means).

client/ssh/config/manager.go

@@ -14,7 +14,6 @@ import (
 	log "github.com/sirupsen/logrus"
 
 	nbssh "github.com/netbirdio/netbird/client/ssh"
-	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
 const (
@@ -219,20 +218,11 @@ func (m *Manager) buildHostPatterns(peer PeerSSHInfo) []string {
 	if peer.IPv6.IsValid() {
 		hostPatterns = append(hostPatterns, peer.IPv6.String())
 	}
-	// Peer FQDNs and hostnames originate from remote peers, so they must be
-	// validated as plain DNS names before being embedded in the ssh_config
-	// "Match host" pattern list. This prevents injection of arbitrary
-	// ssh_config directives via embedded quotes, whitespace, newlines, the
-	// comma pattern separator, or the "*"/"?" pattern metacharacters.
-	if domain.IsValidDomainNoWildcard(peer.FQDN) {
+	if peer.FQDN != "" {
 		hostPatterns = append(hostPatterns, peer.FQDN)
-	} else if peer.FQDN != "" {
-		log.Warnf("skipping peer FQDN with invalid characters in SSH config: %q", peer.FQDN)
 	}
-	if peer.Hostname != peer.FQDN && domain.IsValidDomainNoWildcard(peer.Hostname) {
+	if peer.Hostname != "" && peer.Hostname != peer.FQDN {
 		hostPatterns = append(hostPatterns, peer.Hostname)
-	} else if peer.Hostname != "" && peer.Hostname != peer.FQDN {
-		log.Warnf("skipping peer hostname with invalid characters in SSH config: %q", peer.Hostname)
 	}
 	return hostPatterns
 }

client/ssh/config/manager_test.go

@@ -148,45 +148,6 @@ func TestManager_MatchHostFormat(t *testing.T) {
 		"should use Match host with comma-separated patterns")
 }
 
-func TestManager_HostPatternInjection(t *testing.T) {
-	tempDir, err := os.MkdirTemp("", "netbird-ssh-config-test")
-	require.NoError(t, err)
-	defer func() { assert.NoError(t, os.RemoveAll(tempDir)) }()
-
-	manager := &Manager{
-		sshConfigDir:  filepath.Join(tempDir, "ssh_config.d"),
-		sshConfigFile: "99-netbird.conf",
-	}
-
-	// A malicious peer FQDN/hostname attempts to break out of the Match host
-	// directive and inject arbitrary ssh_config (a ProxyCommand executing a
-	// command). It must be rejected, not written to the config.
-	peers := []PeerSSHInfo{
-		{
-			Hostname: "evil\"\n    ProxyCommand touch /tmp/pwned\nHost x",
-			IP:       netip.MustParseAddr("100.125.1.1"),
-			FQDN:     "evil\"\n    ProxyCommand touch /tmp/pwned\nHost x.nb.internal",
-		},
-		{Hostname: "peer2", IP: netip.MustParseAddr("100.125.1.2"), FQDN: "peer2.nb.internal"},
-	}
-
-	err = manager.SetupSSHClientConfig(peers)
-	require.NoError(t, err)
-
-	configPath := filepath.Join(manager.sshConfigDir, manager.sshConfigFile)
-	content, err := os.ReadFile(configPath)
-	require.NoError(t, err)
-	configStr := string(content)
-
-	assert.NotContains(t, configStr, "ProxyCommand touch /tmp/pwned",
-		"injected directive must not appear in generated config")
-	assert.NotContains(t, configStr, "evil",
-		"malicious pattern must be dropped entirely")
-	// The valid peer must still be present, on a single Match host line.
-	assert.Contains(t, configStr, "Match host \"100.125.1.1,100.125.1.2,peer2.nb.internal,peer2\"",
-		"valid peers must survive, injected patterns dropped")
-}
-
 func TestManager_ForcedSSHConfig(t *testing.T) {
 	// Set force environment variable
 	t.Setenv(EnvForceSSHConfig, "true")

client/ssh/server/getent_unix.go

@@ -69,8 +69,7 @@ func parseGetentPasswd(output string) (*user.User, string, error) {
 
 // validateGetentInput checks that the input is safe to pass to getent or id.
 // Allows POSIX usernames, numeric UIDs, and common NSS extensions
-// (@ for Kerberos, $ for Samba, + for NIS compat). A leading hyphen is
-// rejected so the input can never be parsed as a command-line flag.
+// (@ for Kerberos, $ for Samba, + for NIS compat).
 func validateGetentInput(input string) bool {
 	maxLen := 32
 	if runtime.GOOS == "linux" {
@@ -81,10 +80,6 @@ func validateGetentInput(input string) bool {
 		return false
 	}
 
-	if input[0] == '-' {
-		return false
-	}
-
 	for _, r := range input {
 		if isAllowedGetentChar(r) {
 			continue

client/ssh/server/getent_unix_test.go

@@ -157,9 +157,6 @@ func TestValidateGetentInput(t *testing.T) {
 		{"numeric UID", "1001", true},
 		{"dots and underscores", "alice.bob_test", true},
 		{"hyphen", "alice-bob", true},
-		{"leading hyphen rejected", "-i", false},
-		{"leading double hyphen rejected", "--no-idn", false},
-		{"lone hyphen rejected", "-", false},
 		{"kerberos principal", "user@REALM", true},
 		{"samba machine account", "MACHINE$", true},
 		{"NIS compat", "+user", true},

client/system/info.go

@@ -79,15 +79,13 @@ type Info struct {
 	EnableSSHLocalPortForwarding  bool
 	EnableSSHRemotePortForwarding bool
 	DisableSSHAuth                bool
-
-	SyncMessageVersion *int
 }
 
 func (i *Info) SetFlags(
 	rosenpassEnabled, rosenpassPermissive bool,
 	serverSSHAllowed *bool,
 	disableClientRoutes, disableServerRoutes,
-	disableDNS, disableFirewall, blockLANAccess, blockInbound, disableIPv6 bool, syncMessageVersion *int,
+	disableDNS, disableFirewall, blockLANAccess, blockInbound, disableIPv6 bool,
 	enableSSHRoot, enableSSHSFTP, enableSSHLocalPortForwarding, enableSSHRemotePortForwarding *bool,
 	disableSSHAuth *bool,
 ) {
@@ -105,8 +103,6 @@ func (i *Info) SetFlags(
 	i.BlockInbound = blockInbound
 	i.DisableIPv6 = disableIPv6
 
-	i.SyncMessageVersion = syncMessageVersion
-
 	if enableSSHRoot != nil {
 		i.EnableSSHRoot = *enableSSHRoot
 	}

client/ui/autostart_default.go

@@ -51,7 +51,7 @@ func autostartDisabledByMDM(policy *mdm.Policy) bool {
 // netbirdFootprintExists reports whether the machine already carries NetBird
 // daemon config or state, meaning this is not a genuinely fresh install. It is
 // the update-safety gate for the autostart default: upgrading users always
-// have a footprint, so an update can never trigger a autostart entry write.
+// have a footprint, so an update can never trigger a login-item write.
 func netbirdFootprintExists() bool {
 	candidates := []string{
 		profilemanager.DefaultConfigPath,
@@ -69,23 +69,9 @@ func netbirdFootprintExists() bool {
 // applyAutostartDefault runs the one-time launch-on-login default for genuinely
 // fresh installs. The autostartInitialized marker is persisted before any
 // enable attempt so a crash mid-flow degrades to "never enabled" instead of
-// retrying autostart entry writes on every launch. A user's later disable in
+// retrying login-item writes on every launch. A user's later disable in
 // Settings is never overridden: the marker guarantees at-most-once, ever.
 func applyAutostartDefault(ctx context.Context, autostart *services.Autostart, prefs *preferences.Store, prefsFileExisted bool) {
-	mdmDisabled := autostartDisabledByMDM(mdm.LoadPolicy())
-
-	if mdmDisabled {
-		if enabled, err := autostart.IsEnabled(ctx); err != nil {
-			log.Warnf("MDM disableAutostart: read autostart state: %v", err)
-		} else if enabled {
-			if err := autostart.SetEnabled(ctx, false); err != nil {
-				log.Warnf("MDM disableAutostart: force off failed: %v", err)
-			} else {
-				log.Info("MDM disableAutostart enforced: autostart turned off")
-			}
-		}
-	}
-
 	priorFootprint := netbirdFootprintExists() || prefsFileExisted
 
 	if prefs.Get().AutostartInitialized {
@@ -98,7 +84,7 @@ func applyAutostartDefault(ctx context.Context, autostart *services.Autostart, p
 
 	state := autostartDefaultState{
 		supported:    autostart.Supported(ctx),
-		mdmDisabled:  mdmDisabled,
+		mdmDisabled:  autostartDisabledByMDM(mdm.LoadPolicy()),
 		priorInstall: priorFootprint,
 	}
 	enable, reason := shouldEnableAutostartDefault(state)

client/ui/frontend/src/components/empty-state/DaemonOutdatedOverlay.tsx

@@ -1,13 +1,10 @@
-import { useEffect, useState } from "react";
 import { useTranslation } from "react-i18next";
 import { AlertTriangleIcon, DownloadIcon } from "lucide-react";
 import { Browser } from "@wailsio/runtime";
-import { Version } from "@bindings/services";
 import { Button } from "@/components/buttons/Button";
 import { useStatus } from "@/contexts/StatusContext.tsx";
 
 const RELEASES_URL = "https://github.com/netbirdio/netbird/releases/latest";
-const RC_RELEASES_URL = "https://pkgs.netbird.io/releases/rc";
 
 function openUrl(url: string) {
     Browser.OpenURL(url).catch(() => globalThis.open(url, "_blank"));
@@ -15,26 +12,7 @@ function openUrl(url: string) {
 
 export const DaemonOutdatedOverlay = () => {
     const { t } = useTranslation();
-    const { status, isDaemonOutdated } = useStatus();
-
-    const [guiVersion, setGuiVersion] = useState<string>("-");
-    const clientVersion = status?.daemonVersion ?? "—";
-
-    const isRc = /-rc/i.test(guiVersion) || /-rc/i.test(clientVersion);
-    const downloadUrl = isRc ? RC_RELEASES_URL : RELEASES_URL;
-
-    useEffect(() => {
-        if (!isDaemonOutdated) return;
-        let cancelled = false;
-        Version.GUI()
-            .then((v) => {
-                if (!cancelled) setGuiVersion(v);
-            })
-            .catch((err) => console.error("[DaemonOutdatedOverlay] GUI version error", err));
-        return () => {
-            cancelled = true;
-        };
-    }, [isDaemonOutdated]);
+    const { isDaemonOutdated } = useStatus();
 
     if (!isDaemonOutdated) return null;
 
@@ -60,37 +38,10 @@ export const DaemonOutdatedOverlay = () => {
                     <p className={"text-sm text-nb-gray-300"}>{t("daemon.outdated.description")}</p>
                 </div>
 
-                <div className={"flex flex-col items-center gap-0.5 text-center"}>
-                    <p className={"text-sm font-semibold text-nb-gray-100"}>
-                        {clientVersion === "development" ? (
-                            <span>
-                                {t("settings.about.clientName")}{" "}
-                                <span className={"font-mono text-yellow-400"}>
-                                    {t("settings.about.development")}
-                                </span>
-                            </span>
-                        ) : (
-                            t("settings.about.client", { version: clientVersion })
-                        )}
-                    </p>
-                    <p className={"text-sm font-medium text-nb-gray-250"}>
-                        {guiVersion === "development" ? (
-                            <span>
-                                {t("settings.about.guiName")}{" "}
-                                <span className={"font-mono text-yellow-400"}>
-                                    {t("settings.about.development")}
-                                </span>
-                            </span>
-                        ) : (
-                            t("settings.about.gui", { version: guiVersion })
-                        )}
-                    </p>
-                </div>
-
                 <div className={"wails-no-draggable"}>
-                    <Button variant={"primary"} size={"xs"} onClick={() => openUrl(downloadUrl)}>
+                    <Button variant={"primary"} size={"xs"} onClick={() => openUrl(RELEASES_URL)}>
                         <DownloadIcon size={14} />
-                        {t("daemon.outdated.download")}
+                        {t("update.card.getInstaller")}
                     </Button>
                 </div>
             </div>

client/ui/frontend/src/contexts/ProfileContext.tsx

@@ -28,7 +28,6 @@ type ProfileContextValue = {
     loaded: boolean;
     refresh: () => Promise<void>;
     switchProfile: (id: string) => Promise<void>;
-    switchProfileNoConnect: (id: string) => Promise<void>;
     addProfile: (name: string) => Promise<string>;
     removeProfile: (id: string) => Promise<void>;
     renameProfile: (id: string, newName: string) => Promise<void>;
@@ -113,16 +112,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
         [username, refresh],
     );
 
-    // Manage-profiles variant: switches without connecting, so the user can
-    // still adjust the management URL before bringing the connection up.
-    const switchProfileNoConnect = useCallback(
-        async (id: string) => {
-            await ProfileSwitcher.SwitchActiveNoConnect({ profileName: id, username });
-            await refresh();
-        },
-        [username, refresh],
-    );
-
     // addProfile creates a profile by display name and returns the
     // daemon-generated ID, so the caller can immediately address it by ID.
     const addProfile = useCallback(
@@ -169,7 +158,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
             loaded,
             refresh,
             switchProfile,
-            switchProfileNoConnect,
             addProfile,
             removeProfile,
             renameProfile,
@@ -183,7 +171,6 @@ export const ProfileProvider = ({ children }: { children: ReactNode }) => {
             loaded,
             refresh,
             switchProfile,
-            switchProfileNoConnect,
             addProfile,
             removeProfile,
             renameProfile,

client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx

@@ -2,7 +2,6 @@ import { type ReactNode } from "react";
 import { useTranslation } from "react-i18next";
 import { Browser } from "@wailsio/runtime";
 import { DownloadIcon, NotepadText } from "lucide-react";
-import { Update as UpdateSvc } from "@bindings/services";
 import { Button } from "@/components/buttons/Button";
 import { useClientVersion } from "@/contexts/ClientVersionContext";
 import { cn } from "@/lib/cn";
@@ -15,12 +14,6 @@ function openUrl(url: string) {
     });
 }
 
-function openInstallerDownload() {
-    UpdateSvc.DownloadURL()
-        .then(openUrl)
-        .catch(() => openUrl(GITHUB_RELEASES));
-}
-
 export function UpdateVersionCard() {
     const { t } = useTranslation();
     const { updateVersion, enforced, triggerUpdate } = useClientVersion();
@@ -44,7 +37,11 @@ export function UpdateVersionCard() {
                         {t("update.card.installNow")}
                     </Button>
                 ) : (
-                    <Button variant={"primary"} size={"xs"} onClick={openInstallerDownload}>
+                    <Button
+                        variant={"primary"}
+                        size={"xs"}
+                        onClick={() => openUrl(GITHUB_RELEASES)}
+                    >
                         <DownloadIcon size={14} />
                         {t("update.card.getInstaller")}
                     </Button>

client/ui/frontend/src/modules/profiles/ProfilesTab.tsx

@@ -45,7 +45,7 @@ export function ProfilesTab() {
         activeProfileId,
         loaded,
         username,
-        switchProfileNoConnect,
+        switchProfile,
         addProfile,
         removeProfile,
         renameProfile,
@@ -100,7 +100,7 @@ export function ProfilesTab() {
             confirmLabel: t("profile.switch.confirm"),
         });
         if (!ok) return;
-        await guarded(i18next.t("profile.error.switchTitle"), () => switchProfileNoConnect(id));
+        await guarded(i18next.t("profile.error.switchTitle"), () => switchProfile(id));
     };
 
     const handleDeregister = async (id: string, name: string) => {
@@ -129,13 +129,14 @@ export function ProfilesTab() {
         await guarded(i18next.t("profile.error.createTitle"), async () => {
             const id = await addProfile(name);
             // SetConfig is keyed by the new profile's ID, so it writes the
-            // not-yet-active profile before the switch makes it current.
+            // not-yet-active profile. Write before switching so any reconnect
+            // targets the right deployment.
             if (!isNetbirdCloud(managementUrl)) {
                 await SettingsSvc.SetConfig(
                     new SetConfigParams({ profileName: id, username, managementUrl }),
                 );
             }
-            await switchProfileNoConnect(id);
+            await switchProfile(id);
         });
     };
 

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

@@ -73,13 +73,6 @@ export default function SessionExpirationDialog() {
 
         let offCancel: (() => void) | undefined;
 
-        // Return the dialog to its interactive state and dismiss the browser popup
-        const resetDialog = () => {
-            offCancel?.();
-            WindowManager.CloseBrowserLogin().catch(console.error);
-            setBusy(false);
-        };
-
         try {
             const start = await Session.RequestExtend({ hint: "" });
             const uri = start.verificationUriComplete || start.verificationUri;
@@ -112,22 +105,25 @@ export default function SessionExpirationDialog() {
             if (outcome.kind === "cancel") {
                 waitPromise.cancel?.();
                 waitPromise.catch(() => {});
-                resetDialog();
                 return;
             }
 
             // Another surface owns this flow; keep the dialog open to retry.
             if (outcome.result.preempted) {
-                resetDialog();
                 return;
             }
-            WindowManager.CloseRenewFlow().catch(console.error);
+
+            // Close before the popup so the restore can't flash this window back.
+            WindowManager.CloseSessionExpiration().catch(console.error);
         } catch (e) {
-            resetDialog();
             await errorDialog({
                 Title: t("sessionExpiration.extendFailedTitle"),
                 Message: formatErrorMessage(e),
             });
+        } finally {
+            offCancel?.();
+            WindowManager.CloseBrowserLogin().catch(console.error);
+            setBusy(false);
         }
     }, [busy, t]);
 
@@ -143,11 +139,12 @@ export default function SessionExpirationDialog() {
             });
             WindowManager.CloseSessionExpiration().catch(console.error);
         } catch (e) {
-            setBusy(false);
             await errorDialog({
                 Title: t("sessionExpiration.logoutFailedTitle"),
                 Message: formatErrorMessage(e),
             });
+        } finally {
+            setBusy(false);
         }
     }, [busy, t]);
 

client/ui/frontend/src/modules/welcome/WelcomeStepTray.tsx

@@ -22,9 +22,6 @@ type WelcomeStepTrayProps = {
 export function WelcomeStepTray({ onContinue }: Readonly<WelcomeStepTrayProps>) {
     const { t } = useTranslation();
     const trayScreenshot = trayScreenshotForOS();
-    // macOS has no tray — the icon sits in the menu bar, so the copy says so.
-    const titleKey = isMacOS() ? "welcome.titleMac" : "welcome.title";
-    const descriptionKey = isMacOS() ? "welcome.descriptionMac" : "welcome.description";
 
     return (
         <>
@@ -39,9 +36,9 @@ export function WelcomeStepTray({ onContinue }: Readonly<WelcomeStepTrayProps>)
 
             <div className={"flex w-full flex-col gap-1"}>
                 <DialogHeading id={"nb-welcome-title"} align={"left"}>
-                    {t(titleKey)}
+                    {t("welcome.title")}
                 </DialogHeading>
-                <DialogDescription align={"left"}>{t(descriptionKey)}</DialogDescription>
+                <DialogDescription align={"left"}>{t("welcome.description")}</DialogDescription>
             </div>
 
             <DialogActions>

client/ui/i18n/locales/_index.json

@@ -8,7 +8,6 @@
         {"code": "fr", "displayName": "Français", "englishName": "French"},
         {"code": "it", "displayName": "Italiano", "englishName": "Italian"},
         {"code": "pt", "displayName": "Português", "englishName": "Portuguese"},
-        {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"},
-        {"code": "ja", "displayName": "日本語", "englishName": "Japanese"}
+        {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"}
     ]
 }

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

@@ -1034,15 +1034,9 @@
     "welcome.title": {
         "message": "Suchen Sie NetBird in der Taskleiste"
     },
-    "welcome.titleMac": {
-        "message": "Suchen Sie NetBird in der Menüleiste"
-    },
     "welcome.description": {
         "message": "NetBird läuft in Ihrer Taskleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen."
     },
-    "welcome.descriptionMac": {
-        "message": "NetBird läuft in Ihrer Menüleiste. Klicken Sie auf das Symbol, um sich zu verbinden, Profile zu wechseln oder die Einstellungen zu öffnen."
-    },
     "welcome.continue": {
         "message": "Weiter"
     },
@@ -1299,13 +1293,10 @@
         "message": "Dokumentation"
     },
     "daemon.outdated.title": {
-        "message": "NetBird Client ist veraltet"
+        "message": "NetBird-Dienst ist veraltet"
     },
     "daemon.outdated.description": {
-        "message": "Die neue GUI ist nicht mit Ihrem älteren Client kompatibel. Aktualisieren Sie Ihren Client, um die neue Anwendung zu verwenden."
-    },
-    "daemon.outdated.download": {
-        "message": "Neueste Version herunterladen"
+        "message": "Aktualisieren Sie den NetBird-Dienst, um diese App zu verwenden."
     },
     "error.jwt_clock_skew": {
         "message": "Anmeldung fehlgeschlagen: Die Uhr dieses Geräts ist nicht mit dem Server synchron. Bitte synchronisieren Sie die Systemuhr und versuchen Sie es erneut."

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

@@ -1377,19 +1377,11 @@
     },
     "welcome.title": {
         "message": "Look for NetBird in your tray",
-        "description": "Heading on the first onboarding step, pointing the user to the tray icon. Shown on Windows and Linux; macOS uses welcome.titleMac."
-    },
-    "welcome.titleMac": {
-        "message": "Look for NetBird in your menu bar",
-        "description": "Heading on the first onboarding step on macOS, pointing the user to the menu bar icon. Use your language's Apple term for the macOS menu bar."
+        "description": "Heading on the first onboarding step, pointing the user to the tray icon. 'tray' = system tray / menu bar."
     },
     "welcome.description": {
         "message": "NetBird lives in your tray. Click the icon to connect, switch profiles, or open settings.",
-        "description": "Body of the first onboarding step explaining the tray icon. Shown on Windows and Linux; macOS uses welcome.descriptionMac."
-    },
-    "welcome.descriptionMac": {
-        "message": "NetBird lives in your menu bar. Click the icon to connect, switch profiles, or open settings.",
-        "description": "Body of the first onboarding step on macOS explaining the menu bar icon. Use your language's Apple term for the macOS menu bar."
+        "description": "Body of the first onboarding step explaining the tray icon."
     },
     "welcome.continue": {
         "message": "Continue",
@@ -1732,16 +1724,12 @@
         "description": "Documentation link on the daemon-unavailable overlay."
     },
     "daemon.outdated.title": {
-        "message": "NetBird Client Is Outdated",
-        "description": "Title of the overlay shown when the NetBird client (daemon) is too old to drive this UI."
+        "message": "NetBird Service Is Outdated",
+        "description": "Title of the overlay shown when the NetBird background service is too old to drive this UI."
     },
     "daemon.outdated.description": {
-        "message": "The new GUI isn't compatible with the older NetBird client. Update your client to use the new application.",
-        "description": "Body of the daemon-outdated overlay explaining that the GUI is newer than the client and the client must be updated."
-    },
-    "daemon.outdated.download": {
-        "message": "Download Latest",
-        "description": "Button on the daemon-outdated overlay that opens the download page for the latest release."
+        "message": "Update the NetBird service to use this app.",
+        "description": "Body of the daemon-outdated overlay telling the user to upgrade the service."
     },
     "error.jwt_clock_skew": {
         "message": "Sign-in failed: this device's clock is out of sync with the server. Please sync your system clock and try again.",

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

@@ -1034,15 +1034,9 @@
     "welcome.title": {
         "message": "Busque NetBird en su bandeja del sistema"
     },
-    "welcome.titleMac": {
-        "message": "Busque NetBird en su barra de menús"
-    },
     "welcome.description": {
         "message": "NetBird reside en su bandeja del sistema. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración."
     },
-    "welcome.descriptionMac": {
-        "message": "NetBird reside en su barra de menús. Haga clic en el icono para conectarse, cambiar de perfil o abrir la configuración."
-    },
     "welcome.continue": {
         "message": "Continuar"
     },
@@ -1299,13 +1293,10 @@
         "message": "Documentación"
     },
     "daemon.outdated.title": {
-        "message": "NetBird Client está desactualizado"
+        "message": "El servicio de NetBird está desactualizado"
     },
     "daemon.outdated.description": {
-        "message": "La nueva GUI no es compatible con su cliente anterior. Actualice su cliente para usar la nueva aplicación."
-    },
-    "daemon.outdated.download": {
-        "message": "Descargar la última versión"
+        "message": "Actualice el servicio de NetBird para usar esta aplicación."
     },
     "error.jwt_clock_skew": {
         "message": "Error al iniciar sesión: el reloj de este dispositivo no está sincronizado con el servidor. Sincronice el reloj del sistema e inténtelo de nuevo."

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

@@ -1034,15 +1034,9 @@
     "welcome.title": {
         "message": "Cherchez NetBird dans votre barre d’état système"
     },
-    "welcome.titleMac": {
-        "message": "Cherchez NetBird dans votre barre des menus"
-    },
     "welcome.description": {
         "message": "NetBird se trouve dans votre barre d’état système. Cliquez sur l’icône pour vous connecter, changer de profil ou ouvrir les paramètres."
     },
-    "welcome.descriptionMac": {
-        "message": "NetBird se trouve dans votre barre des menus. Cliquez sur l’icône pour vous connecter, changer de profil ou ouvrir les paramètres."
-    },
     "welcome.continue": {
         "message": "Continuer"
     },
@@ -1299,13 +1293,10 @@
         "message": "Documentation"
     },
     "daemon.outdated.title": {
-        "message": "Le Client NetBird est obsolète"
+        "message": "Le service NetBird est obsolète"
     },
     "daemon.outdated.description": {
-        "message": "La nouvelle GUI n'est pas compatible avec votre ancien client. Mettez à jour votre client pour utiliser la nouvelle application."
-    },
-    "daemon.outdated.download": {
-        "message": "Télécharger la dernière version"
+        "message": "Mettez à jour le service NetBird pour utiliser cette application."
     },
     "error.jwt_clock_skew": {
         "message": "Échec de la connexion : l’horloge de cet appareil n’est pas synchronisée avec le serveur. Veuillez synchroniser l’horloge de votre système et réessayer."

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

@@ -1034,15 +1034,9 @@
     "welcome.title": {
         "message": "Keresse a NetBirdöt a tálcán"
     },
-    "welcome.titleMac": {
-        "message": "Keresse a NetBirdöt a menüsorban"
-    },
     "welcome.description": {
         "message": "A NetBird a tálcán fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához."
     },
-    "welcome.descriptionMac": {
-        "message": "A NetBird a menüsorban fut. Kattintson az ikonra a csatlakozáshoz, profilváltáshoz vagy a beállítások megnyitásához."
-    },
     "welcome.continue": {
         "message": "Folytatás"
     },
@@ -1299,13 +1293,10 @@
         "message": "Dokumentáció"
     },
     "daemon.outdated.title": {
-        "message": "A NetBird Kliens elavult"
+        "message": "A NetBird szolgáltatás elavult"
     },
     "daemon.outdated.description": {
-        "message": "Az új GUI nem kompatibilis a régebbi klienseddel. Frissítsd a klienst az új alkalmazás használatához."
-    },
-    "daemon.outdated.download": {
-        "message": "Legújabb letöltése"
+        "message": "Frissítsd a NetBird szolgáltatást az alkalmazás használatához."
     },
     "error.jwt_clock_skew": {
         "message": "A bejelentkezés sikertelen: az eszköz órája eltér a szerverétől. Kérjük, szinkronizálja a rendszer óráját, majd próbálja újra."

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

@@ -1034,15 +1034,9 @@
     "welcome.title": {
         "message": "Cerchi NetBird nella tray"
     },
-    "welcome.titleMac": {
-        "message": "Cerchi NetBird nella barra dei menu"
-    },
     "welcome.description": {
         "message": "NetBird risiede nella tray. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni."
     },
-    "welcome.descriptionMac": {
-        "message": "NetBird risiede nella barra dei menu. Clicchi sull'icona per connettersi, cambiare profilo o aprire le impostazioni."
-    },
     "welcome.continue": {
         "message": "Continua"
     },
@@ -1299,13 +1293,10 @@
         "message": "Documentazione"
     },
     "daemon.outdated.title": {
-        "message": "NetBird Client è obsoleto"
+        "message": "Il servizio NetBird è obsoleto"
     },
     "daemon.outdated.description": {
-        "message": "La nuova GUI non è compatibile con il tuo client precedente. Aggiorna il client per usare la nuova applicazione."
-    },
-    "daemon.outdated.download": {
-        "message": "Scarica l'ultima versione"
+        "message": "Aggiorna il servizio NetBird per usare questa app."
     },
     "error.jwt_clock_skew": {
         "message": "Accesso non riuscito: l'orologio di questo dispositivo non è sincronizzato con il server. Sincronizzi l'orologio di sistema e riprovi."