[management] Remove proxy peer stale deduplication test and related logic

Adds a settings constraint: enabling `agent_network_only` requires `dashboard_features.agent_network` to be `true` in the same account update. Without the Agent Network menu flag, a focused account that later turns the focused view off would lose access to the Agent Network menu entirely, so the two must be set together.

The check runs in `updateAccountRequestSettings` against the parsed request state: if the resulting settings have `agent_network_only == true` but `dashboard_features.agent_network` is not `true`, the update is rejected with `status.InvalidArgument` (HTTP 422) before anything is persisted.

The OpenAPI field descriptions for `agent_network_only` and `dashboard_features.agent_network` document the requirement. Only the descriptions changed — `required` and the schema `$ref` are untouched — and `types.gen.go` was regenerated from the spec (diff is the two comment lines).

agent-network/README.md

@@ -1,16 +1,47 @@
 # NetBird Agent Network
 
-Agent Network is NetBird's access control layer for AI agents and the people who run
-them. It gives every agent a real identity, tied to your identity provider (IdP), and
-governs what it can reach — the LLM APIs and AI gateways it can call, and the internal
-resources it can access. Traffic flows only over the encrypted NetBird tunnel, scoped by
-policy, with no API keys to leak.
+Agent Network is NetBird's access control layer for AI agents and the people who run them. 
+It gives every agent a real identity, tied to an identity provider (IdP), and governs what it can reach: LLM APIs and 
+AI gateways it can call, and the internal resources it can access. Traffic flows only over the encrypted NetBird tunnel, 
+scoped by policy, with no API keys or other credentials to leak. It also gives you control over cost and token usage.
 
-> **Beta.** Agent Network is open source and can be self-hosted on your own
-> infrastructure.
+Because every LLM request passes through an
+identity-aware proxy, you can:
+
+- **Set spending and rate limits** per agent, per user, or per team — with hard caps
+  that stop requests once a budget is reached.
+- **Restrict models and providers** so agents can only call approved (and cost-appropriate)
+  endpoints, keeping expensive models off-limits unless explicitly allowed.
+- **Attribute usage** by tracking token consumption and cost per identity, group, or cost center so every
+  request is tied back to the agent and person responsible.
+- **Reuse your existing AI gateway** — point the proxy at a gateway you already run,
+  keeping its routing and config in place while it adds identity on top, so you skip
+  API key distribution.
+
+https://github.com/user-attachments/assets/44d18286-d8ab-49f8-a457-98ccd66f3268
+
+> **Beta.** Agent Network is in beta, but it's stable and already running in
+> production environments. It's fully open source and can be self-hosted on your own
+> infrastructure, with no vendor lock-in and no data leaving your environment.
 
 ## How it works
 
+Say you have a simple use case: your Engineering or IT team needs access to Claude Code or Codex, and you want visibility into usage plus the ability to enforce budgets.
+How can you do that without creating a dedicated API key for every team?
+
+With Agent Network you get a private endpoint inside your network, for example: https://mirror.netbird.ai
+Teams configure their agents to point to that endpoint instead of using individual API keys directly. 
+
+This endpoint is only reachable when users are connected to your NetBird network and authenticated through your IdP. Otherwise, it is not accessible from the public internet.
+You can then use this private endpoint to configure your AI agents, whether that is Claude Code, Codex, or another tool.
+
+## Quickstart
+
+Full step-by-step setup:
+**https://docs.netbird.io/agent-network/quickstart**
+
+## Architecture 
+
 Agent Network is built on two existing NetBird capabilities:
 
 - **Overlay network** — the encrypted WireGuard mesh between peers.
@@ -22,6 +53,9 @@ LLM traffic is routed through the proxy's identity-aware pipeline, while interna
 resources (databases, internal APIs, self-hosted models) are reached directly over
 peer-to-peer WireGuard tunnels, governed by the same identities and access policies.
 
+<img width="4720" height="2218" alt="image" src="https://github.com/user-attachments/assets/1afa5da1-4b82-4f8a-a7a8-f417efadf1eb" />
+
+
 ## Where the code lives
 
 There is no separate "agent-network" service — it reuses the reverse-proxy and management

client/internal/auth/device_flow.go

@@ -259,12 +259,18 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 	ticker := time.NewTicker(interval)
 	defer ticker.Stop()
 
+	log.Infof("device flow: waiting for user authorization, polling token endpoint every %s, code expires in %s", interval, timeout)
+
+	start := time.Now()
+	polls := 0
+
 	for {
 		select {
 		case <-waitCtx.Done():
 			return TokenInfo{}, waitCtx.Err()
 		case <-ticker.C:
 
+			polls++
 			tokenResponse, err := d.requestToken(info)
 			if err != nil {
 				return TokenInfo{}, fmt.Errorf("parsing token response failed with error: %v", err)
@@ -272,10 +278,12 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 
 			if tokenResponse.Error != "" {
 				if tokenResponse.Error == "authorization_pending" {
+					log.Tracef("device flow: authorization still pending after poll %d", polls)
 					continue
 				} else if tokenResponse.Error == "slow_down" {
 					interval += (3 * time.Second)
 					ticker.Reset(interval)
+					log.Infof("device flow: IdP requested slow_down, polling interval increased to %s", interval)
 					continue
 				}
 
@@ -296,6 +304,7 @@ func (d *DeviceAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowIn
 				return TokenInfo{}, fmt.Errorf("validate access token failed with error: %v", err)
 			}
 
+			log.Infof("device flow: user authorization confirmed after %d polls in %s", polls, time.Since(start).Round(time.Second))
 			return tokenInfo, err
 		}
 	}

client/internal/auth/pkce_flow.go

@@ -188,6 +188,8 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
 	waitCtx, cancel := context.WithTimeout(ctx, timeout)
 	defer cancel()
 
+	log.Infof("pkce flow: waiting for authorization callback on %s, timeout %s", p.oAuthConfig.RedirectURL, timeout)
+
 	tokenChan := make(chan *oauth2.Token, 1)
 	errChan := make(chan error, 1)
 
@@ -221,6 +223,7 @@ func (p *PKCEAuthorizationFlow) WaitToken(ctx context.Context, info AuthFlowInfo
 func (p *PKCEAuthorizationFlow) startServer(server *http.Server, tokenChan chan<- *oauth2.Token, errChan chan<- error) {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/", func(w http.ResponseWriter, req *http.Request) {
+		log.Infof("pkce flow: received authorization callback from IdP")
 		cert := p.providerConfig.ClientCertPair
 		if cert != nil {
 			tr := &http.Transport{
@@ -271,11 +274,18 @@ func (p *PKCEAuthorizationFlow) handleRequest(req *http.Request) (*oauth2.Token,
 		return nil, fmt.Errorf("authentication failed: missing code")
 	}
 
-	return p.oAuthConfig.Exchange(
+	exchangeStart := time.Now()
+	token, err := p.oAuthConfig.Exchange(
 		req.Context(),
 		code,
 		oauth2.SetAuthURLParam("code_verifier", p.codeVerifier),
 	)
+	if err != nil {
+		return nil, err
+	}
+
+	log.Infof("pkce flow: authorization code exchanged for token in %s", time.Since(exchangeStart).Round(time.Millisecond))
+	return token, nil
 }
 
 func (p *PKCEAuthorizationFlow) parseOAuthToken(token *oauth2.Token) (TokenInfo, error) {

client/internal/conn_mgr.go

@@ -109,7 +109,7 @@ func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) er
 			return nil
 		}
 
-		log.Warnf("lazy connection manager is enabled by management feature flag")
+		log.Infof("lazy connection manager is enabled by the management feature flag")
 		e.initLazyManager(ctx)
 		e.statusRecorder.UpdateLazyConnection(true)
 		return e.addPeersToLazyConnManager()

client/internal/debug/debug.go

@@ -480,7 +480,6 @@ func (g *BundleGenerator) addStatus() error {
 
 		fullStatus := g.statusRecorder.GetFullStatus()
 		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
-		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
 		overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, nbstatus.ConvertOptions{
 			Anonymize:     g.anonymize,
 			ProfileName:   profName,

client/internal/engine.go

@@ -551,7 +551,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		} else {
 			log.Infof("running rosenpass in strict mode")
 		}
-		e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName)
+		e.rpManager, err = rosenpass.NewManager(e.config.PreSharedKey, e.config.WgIfaceName, publicKey)
 		if err != nil {
 			return fmt.Errorf("create rosenpass manager: %w", err)
 		}

client/internal/netflow/store/event_aggregation_test.go

@@ -175,7 +175,9 @@ func TestFlowAggregationOfUnknownProtocols(t *testing.T) {
 }
 
 func TestResetAggregationWindow(t *testing.T) {
-	store := NewAggregatingMemoryStore()
+	now := time.Now()
+	nowFunc := func() time.Time { return now }
+	store := NewAggregatingMemoryStoreWithTimeFunc(nowFunc)
 	store.StoreEvent(&types.Event{
 		ID:        uuid.New(),
 		Timestamp: time.Now(),
@@ -198,6 +200,7 @@ func TestResetAggregationWindow(t *testing.T) {
 		},
 	})
 
+	now = now.Add(1 * time.Second)
 	reset := store.ResetAggregationWindow()
 	previousEvents, ok := reset.(*AggregatingMemory)
 	assert.True(t, ok)

client/internal/netflow/store/memory.go

@@ -29,6 +29,7 @@ type AggregatingMemory struct {
 	WindowStart time.Time
 	WindowEnd   time.Time
 	rnd         *v2.PCG
+	nowFunc     func() time.Time
 }
 
 func (m *Memory) StoreEvent(event *types.Event) {
@@ -62,14 +63,19 @@ func (m *Memory) DeleteEvents(ids []uuid.UUID) {
 }
 
 func NewAggregatingMemoryStore() *AggregatingMemory {
-	return &AggregatingMemory{WindowStart: time.Now(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
+	return NewAggregatingMemoryStoreWithTimeFunc(defaultNowFunc)
+}
+
+// used in tests when deterministic (less random) time intervals are required
+func NewAggregatingMemoryStoreWithTimeFunc(nowFunc func() time.Time) *AggregatingMemory {
+	return &AggregatingMemory{WindowStart: nowFunc(), Memory: Memory{events: make(map[uuid.UUID]*types.Event)}, nowFunc: nowFunc, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
 }
 
 func (am *AggregatingMemory) ResetAggregationWindow() types.FlowEventAggregator {
 	am.mux.Lock()
 	defer am.mux.Unlock()
 
-	now := time.Now()
+	now := am.nowFunc()
 	toret := AggregatingMemory{WindowStart: am.WindowStart, WindowEnd: now, Memory: Memory{events: am.events}, rnd: v2.NewPCG(rand.Uint64(), rand.Uint64())}
 
 	am.events = make(map[uuid.UUID]*types.Event)
@@ -152,3 +158,7 @@ func (am *AggregatingMemory) GetAggregatedEvents() []*types.Event {
 
 	return slices.Collect(maps.Values(aggregated)) // could return an iterator instead here
 }
+
+func defaultNowFunc() time.Time {
+	return time.Now()
+}

client/internal/peer/conn.go

@@ -30,6 +30,11 @@ import (
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
 
+// wgTimeoutEscalationThreshold is the number of consecutive WireGuard
+// handshake timeouts after which the rosenpass state for the peer is
+// considered desynced and gets reset.
+const wgTimeoutEscalationThreshold = 3
+
 // MetricsRecorder is an interface for recording peer connection metrics
 type MetricsRecorder interface {
 	RecordConnectionStages(
@@ -118,6 +123,9 @@ type Conn struct {
 	wgWatcher       *WGWatcher
 	wgWatcherWg     sync.WaitGroup
 	wgWatcherCancel context.CancelFunc
+	// wgTimeouts counts consecutive WireGuard handshake timeouts without a
+	// successful handshake in between. Guarded by mu.
+	wgTimeouts int
 
 	// used to store the remote Rosenpass key for Relayed connection in case of connection update from ice
 	rosenpassRemoteKey []byte
@@ -683,6 +691,29 @@ func (conn *Conn) onWGDisconnected() {
 	default:
 		conn.Log.Debugf("No active connection to close on WG timeout")
 	}
+
+	conn.escalateWGTimeoutLocked()
+}
+
+// escalateWGTimeoutLocked resets the peer's rosenpass state after repeated
+// handshake timeouts. With rosenpass enabled, persistent timeouts mean the
+// preshared keys have desynced; the renewal exchange runs over the dead
+// tunnel and cannot resync them. Reporting the peer disconnected drops its
+// rosenpass state, so the next connection configuration programs the
+// rendezvous key and the tunnel can bootstrap again. Callers must hold mu.
+func (conn *Conn) escalateWGTimeoutLocked() {
+	if conn.config.RosenpassConfig.PubKey == nil {
+		return
+	}
+
+	conn.wgTimeouts++
+	if conn.wgTimeouts < wgTimeoutEscalationThreshold || conn.onDisconnected == nil {
+		return
+	}
+	conn.wgTimeouts = 0
+
+	conn.Log.Warnf("%d consecutive WireGuard handshake timeouts, resetting rosenpass state for peer", wgTimeoutEscalationThreshold)
+	conn.onDisconnected(conn.config.WgConfig.RemoteKey)
 }
 
 func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []byte, updateTime time.Time) {
@@ -812,7 +843,7 @@ func (conn *Conn) enableWgWatcherIfNeeded(enabledTime time.Time) {
 	conn.wgWatcherWg.Add(1)
 	go func() {
 		defer conn.wgWatcherWg.Done()
-		conn.wgWatcher.EnableWgWatcher(wgWatcherCtx, enabledTime, conn.onWGDisconnected, conn.onWGHandshakeSuccess)
+		conn.wgWatcher.EnableWgWatcher(wgWatcherCtx, enabledTime, conn.onWGDisconnected, conn.onWGHandshakeSuccess, conn.onWGCheckSuccess)
 	}()
 }
 
@@ -892,6 +923,15 @@ func (conn *Conn) onWGHandshakeSuccess(when time.Time) {
 	conn.recordConnectionMetrics()
 }
 
+// onWGCheckSuccess is called for every watcher check that observed a fresh
+// handshake, including handshakes of connections that were already up when
+// the watcher started.
+func (conn *Conn) onWGCheckSuccess() {
+	conn.mu.Lock()
+	conn.wgTimeouts = 0
+	conn.mu.Unlock()
+}
+
 // recordConnectionMetrics records connection stage timestamps as metrics
 func (conn *Conn) recordConnectionMetrics() {
 	if conn.metricsRecorder == nil {

client/internal/peer/conn_test.go

@@ -7,6 +7,7 @@ import (
 	"testing"
 	"time"
 
+	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 
 	"github.com/netbirdio/netbird/client/iface"
@@ -304,3 +305,84 @@ func TestConn_presharedKey_RosenpassManaged(t *testing.T) {
 		t.Fatalf("expected non-nil presharedKey before Rosenpass manages PSK")
 	}
 }
+
+func newWGTimeoutTestConn(rosenpassEnabled bool, disconnected *[]string) *Conn {
+	cfg := ConnConfig{
+		Key:      "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+		LocalKey: "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+		WgConfig: WgConfig{RemoteKey: "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU="},
+	}
+	if rosenpassEnabled {
+		cfg.RosenpassConfig = RosenpassConfig{PubKey: []byte("dummykey")}
+	}
+
+	conn := &Conn{
+		ctx:           context.Background(),
+		config:        cfg,
+		Log:           log.WithField("peer", cfg.Key),
+		metricsStages: &MetricsStages{},
+	}
+	conn.SetOnDisconnected(func(remotePeer string) {
+		*disconnected = append(*disconnected, remotePeer)
+	})
+	return conn
+}
+
+// TestConn_onWGDisconnected_EscalatesToRosenpassReset: repeated handshake
+// timeouts with rosenpass enabled mean the preshared keys have desynced. The
+// renewal exchange runs over the dead tunnel and cannot resync them, so after
+// wgTimeoutEscalationThreshold consecutive timeouts the conn must report the
+// peer disconnected, dropping its rosenpass state so the next configuration
+// programs the rendezvous key.
+func TestConn_onWGDisconnected_EscalatesToRosenpassReset(t *testing.T) {
+	var disconnected []string
+	conn := newWGTimeoutTestConn(true, &disconnected)
+
+	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
+		conn.onWGDisconnected()
+	}
+	assert.Empty(t, disconnected, "escalation must not fire below the threshold")
+
+	conn.onWGDisconnected()
+	assert.Equal(t, []string{conn.config.WgConfig.RemoteKey}, disconnected,
+		"reaching the threshold must report the peer disconnected once")
+
+	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
+		conn.onWGDisconnected()
+	}
+	assert.Len(t, disconnected, 1, "escalation must restart counting after firing")
+
+	conn.onWGDisconnected()
+	assert.Len(t, disconnected, 2, "continued timeouts must escalate again")
+}
+
+// TestConn_onWGDisconnected_CheckSuccessResetsEscalation: a successful
+// handshake between timeouts means the tunnel recovered; the counter must
+// start over.
+func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) {
+	var disconnected []string
+	conn := newWGTimeoutTestConn(true, &disconnected)
+
+	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
+		conn.onWGDisconnected()
+	}
+	conn.onWGCheckSuccess()
+
+	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
+		conn.onWGDisconnected()
+	}
+	assert.Empty(t, disconnected, "handshake success must reset the timeout count")
+}
+
+// TestConn_onWGDisconnected_NoEscalationWithoutRosenpass: without rosenpass
+// there is no per-peer key state to reset; repeated timeouts must not report
+// disconnects.
+func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) {
+	var disconnected []string
+	conn := newWGTimeoutTestConn(false, &disconnected)
+
+	for i := 0; i < wgTimeoutEscalationThreshold*3; i++ {
+		conn.onWGDisconnected()
+	}
+	assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections")
+}

client/internal/peer/wg_watcher.go

@@ -71,9 +71,11 @@ func (w *WGWatcher) PrepareInitialHandshake() (ok bool) {
 
 // EnableWgWatcher runs the WireGuard watcher loop using the handshake baseline captured by
 // PrepareInitialHandshake. The watcher runs until ctx is cancelled. Caller is responsible
-// for context lifecycle management.
-func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time)) {
-	w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, enabledTime, w.initialHandshake)
+// for context lifecycle management. onHandshakeSuccessFn is called only for the first
+// handshake observed by this run, onCheckSuccessFn for every check that observed a fresh
+// handshake, including the first.
+func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func()) {
+	w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, onCheckSuccessFn, enabledTime, w.initialHandshake)
 
 	w.muEnabled.Lock()
 	w.enabled = false
@@ -90,7 +92,7 @@ func (w *WGWatcher) Reset() {
 }
 
 // wgStateCheck help to check the state of the WireGuard handshake and relay connection
-func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), enabledTime time.Time, initialHandshake time.Time) {
+func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), onCheckSuccessFn func(), enabledTime time.Time, initialHandshake time.Time) {
 	w.log.Infof("WireGuard watcher started")
 
 	timer := time.NewTimer(wgHandshakeOvertime)
@@ -117,6 +119,10 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn
 				}
 			}
 
+			if onCheckSuccessFn != nil && ctx.Err() == nil {
+				onCheckSuccessFn()
+			}
+
 			lastHandshake = *handshake
 
 			resetTime := time.Until(handshake.Add(checkPeriod))

client/internal/peer/wg_watcher_test.go

@@ -24,6 +24,72 @@ func (m *MocWgIface) disconnect() {
 	m.stop = true
 }
 
+type mockHandshakeStats struct {
+	mu        sync.Mutex
+	handshake time.Time
+}
+
+func (m *mockHandshakeStats) GetStats() (map[string]configurer.WGStats, error) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	return map[string]configurer.WGStats{"": {LastHandshake: m.handshake}}, nil
+}
+
+func (m *mockHandshakeStats) advance() {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.handshake = time.Now()
+}
+
+// TestWGWatcher_CheckSuccessCallback: onCheckSuccessFn must fire for a fresh
+// handshake even when the watcher started with an existing handshake baseline,
+// the case where onHandshakeSuccessFn stays silent.
+func TestWGWatcher_CheckSuccessCallback(t *testing.T) {
+	// checkPeriod bounds how stale a handshake may be before the watcher treats it
+	// as a suspended-machine timeout. The first check fires after wgHandshakeOvertime,
+	// so keep checkPeriod well above any scheduling jitter to avoid a false timeout
+	// converting the expected success into a disconnect on a loaded runner.
+	checkPeriod = 1 * time.Minute
+	wgHandshakeOvertime = 1 * time.Second
+
+	mlog := log.WithField("peer", "tet")
+	// Use an old baseline so advance() yields a strictly newer handshake even on
+	// platforms with coarse clock resolution (Windows), where two time.Now() calls
+	// microseconds apart can return the same instant and read as a timed-out handshake.
+	stats := &mockHandshakeStats{handshake: time.Now().Add(-time.Hour)}
+	watcher := NewWGWatcher(mlog, stats, "", newStateDump("peer", mlog, &Status{}))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	require.True(t, watcher.PrepareInitialHandshake())
+
+	firstHandshake := make(chan struct{}, 1)
+	checkSuccess := make(chan struct{}, 1)
+	go watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {
+		firstHandshake <- struct{}{}
+	}, func() {
+		select {
+		case checkSuccess <- struct{}{}:
+		default:
+		}
+	})
+
+	stats.advance()
+
+	select {
+	case <-checkSuccess:
+	case <-time.After(10 * time.Second):
+		t.Errorf("timeout waiting for check success callback")
+	}
+
+	select {
+	case <-firstHandshake:
+		t.Errorf("first-handshake callback must not fire for a non-zero baseline")
+	default:
+	}
+}
+
 func TestWGWatcher_EnableWgWatcher(t *testing.T) {
 	checkPeriod = 5 * time.Second
 	wgHandshakeOvertime = 1 * time.Second
@@ -44,7 +110,7 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
 		onDisconnected <- struct{}{}
 	}, func(when time.Time) {
 		mlog.Infof("onHandshakeSuccess: %v", when)
-	})
+	}, nil)
 
 	// wait for initial reading
 	time.Sleep(2 * time.Second)
@@ -73,7 +139,7 @@ func TestWGWatcher_ReEnable(t *testing.T) {
 	wg.Add(1)
 	go func() {
 		defer wg.Done()
-		watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {})
+		watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {}, nil)
 	}()
 	cancel()
 
@@ -89,7 +155,7 @@ func TestWGWatcher_ReEnable(t *testing.T) {
 	onDisconnected := make(chan struct{}, 1)
 	go watcher.EnableWgWatcher(ctx, time.Now(), func() {
 		onDisconnected <- struct{}{}
-	}, func(when time.Time) {})
+	}, func(when time.Time) {}, nil)
 
 	time.Sleep(2 * time.Second)
 	mocWgIface.disconnect()

client/internal/profilemanager/service.go

@@ -11,6 +11,7 @@ import (
 	"runtime"
 	"sort"
 	"strings"
+	"syscall"
 
 	log "github.com/sirupsen/logrus"
 
@@ -439,7 +440,11 @@ func (s *ServiceManager) GetStatePath() string {
 
 	activeProf, err := s.GetActiveProfileState()
 	if err != nil {
-		log.Warnf("failed to get active profile state: %v", err)
+		if errors.Is(err, syscall.ENOSYS) {
+			log.Debugf("active profile state unavailable on this platform: %v", err)
+		} else {
+			log.Warnf("failed to get active profile state: %v", err)
+		}
 		return defaultStatePath
 	}
 

client/internal/rosenpass/manager.go

@@ -39,6 +39,7 @@ type rpServer interface {
 
 type Manager struct {
 	ifaceName    string
+	localWgKey   wgtypes.Key
 	spk          []byte
 	ssk          []byte
 	rpKeyHash    string
@@ -51,8 +52,9 @@ type Manager struct {
 	wgIface      PresharedKeySetter
 }
 
-// NewManager creates a new Rosenpass manager
-func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error) {
+// NewManager creates a new Rosenpass manager. localWgKey is the local
+// WireGuard public key, used to derive the per-peer rendezvous key.
+func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string, localWgKey wgtypes.Key) (*Manager, error) {
 	public, secret, err := rp.GenerateKeyPair()
 	if err != nil {
 		return nil, err
@@ -62,6 +64,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error)
 	log.Tracef("generated new rosenpass key pair with public key %s", rpKeyHash)
 	return &Manager{
 		ifaceName:    wgIfaceName,
+		localWgKey:   localWgKey,
 		rpKeyHash:    rpKeyHash,
 		spk:          public,
 		ssk:          secret,
@@ -73,7 +76,7 @@ func NewManager(preSharedKey *wgtypes.Key, wgIfaceName string) (*Manager, error)
 		// nil receiver in addPeer -> m.rpWgHandler.AddPeer. generateConfig will
 		// replace it with a fresh handler on each Run() to clear stale peer
 		// state from previous engine sessions.
-		rpWgHandler: NewNetbirdHandler(),
+		rpWgHandler: NewNetbirdHandler((*[32]byte)(preSharedKey), localWgKey),
 		lock:        sync.Mutex{},
 	}, nil
 }
@@ -161,7 +164,7 @@ func (m *Manager) generateConfig() (rp.Config, error) {
 	cfg.Peers = []rp.PeerConfig{}
 
 	m.lock.Lock()
-	m.rpWgHandler = NewNetbirdHandler()
+	m.rpWgHandler = NewNetbirdHandler(m.preSharedKey, m.localWgKey)
 	if m.wgIface != nil {
 		m.rpWgHandler.SetInterface(m.wgIface)
 	}

client/internal/rosenpass/manager_test.go

@@ -85,7 +85,7 @@ func newTestManager(spkFirstByte byte, mock *mockServer) *Manager {
 		ssk:         make([]byte, 32),
 		rpKeyHash:   "test-hash",
 		rpPeerIDs:   make(map[string]*rp.PeerID),
-		rpWgHandler: NewNetbirdHandler(),
+		rpWgHandler: NewNetbirdHandler(nil, wgtypes.Key{0x01}),
 		server:      mock,
 	}
 }
@@ -255,7 +255,7 @@ func TestAddPeer_NilServer_ReturnsErrorNoCrash(t *testing.T) {
 // issue #4341 cannot occur in the window between NewManager and Run().
 func TestNewManager_PreInitializesHandler(t *testing.T) {
 	psk := wgtypes.Key{}
-	m, err := NewManager(&psk, "wt0")
+	m, err := NewManager(&psk, "wt0", wgtypes.Key{0x01})
 	require.NoError(t, err)
 	require.NotNil(t, m.rpWgHandler, "rpWgHandler must be initialized in NewManager")
 }
@@ -329,10 +329,10 @@ func TestIsPresharedKeyInitialized_AddedButNotHandshaken_ReturnsFalse(t *testing
 	require.False(t, m.IsPresharedKeyInitialized(wgKey))
 }
 
-// --- NetbirdHandler.outputKey ----------------------------------------------
+// --- NetbirdHandler.applyKey ----------------------------------------------
 
-func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
-	h := NewNetbirdHandler()
+func TestHandler_ApplyKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	iface := &mockIface{}
 	h.SetInterface(iface)
 
@@ -348,8 +348,8 @@ func TestHandler_OutputKey_FirstCallUsesUpdateOnlyFalse(t *testing.T) {
 	require.Equal(t, wgKey.String(), iface.calls[0].peerKey)
 }
 
-func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
-	h := NewNetbirdHandler()
+func TestHandler_ApplyKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	iface := &mockIface{}
 	h.SetInterface(iface)
 
@@ -364,8 +364,8 @@ func TestHandler_OutputKey_SubsequentCallsUseUpdateOnlyTrue(t *testing.T) {
 	require.True(t, iface.calls[1].updateOnly, "subsequent rotations must use updateOnly=true")
 }
 
-func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) {
-	h := NewNetbirdHandler()
+func TestHandler_ApplyKey_NilInterface_NoCrashNoCall(t *testing.T) {
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	// no SetInterface — iface remains nil
 	pid := rp.PeerID{0x03}
 	h.AddPeer(pid, "wt0", rp.Key(wgtypes.Key{}))
@@ -374,8 +374,8 @@ func TestHandler_OutputKey_NilInterface_NoCrashNoCall(t *testing.T) {
 	h.HandshakeCompleted(pid, rp.Key{})
 }
 
-func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) {
-	h := NewNetbirdHandler()
+func TestHandler_ApplyKey_UnknownPeer_NoCall(t *testing.T) {
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	iface := &mockIface{}
 	h.SetInterface(iface)
 
@@ -384,7 +384,7 @@ func TestHandler_OutputKey_UnknownPeer_NoCall(t *testing.T) {
 }
 
 func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) {
-	h := NewNetbirdHandler()
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	iface := &mockIface{}
 	h.SetInterface(iface)
 
@@ -398,7 +398,7 @@ func TestHandler_RemovePeer_ClearsInitializedState(t *testing.T) {
 }
 
 func TestHandler_SetInterfaceAfterAddPeer_StillReceivesKey(t *testing.T) {
-	h := NewNetbirdHandler()
+	h := NewNetbirdHandler(nil, wgtypes.Key{0x01})
 	pid := rp.PeerID{0x05}
 	wgKey := wgtypes.Key{0xEE}
 	h.AddPeer(pid, "wt0", rp.Key(wgKey))

client/internal/rosenpass/netbird_handler.go

@@ -18,19 +18,34 @@ type PresharedKeySetter interface {
 type wireGuardPeer struct {
 	Interface string
 	PublicKey rp.Key
+	// initialized is true once a completed exchange has set a
+	// Rosenpass-managed PSK for this peer.
+	initialized bool
+	// chainKey is the key output by the last completed exchange, advanced by
+	// one ratchet step on expiry. Nil until the first exchange completes and
+	// after the peer has fallen back to the rendezvous key.
+	chainKey *wgtypes.Key
+	// expiries counts failed renewals since the last completed exchange.
+	expiries int
 }
 
 type NetbirdHandler struct {
-	mu               sync.Mutex
-	iface            PresharedKeySetter
-	peers            map[rp.PeerID]wireGuardPeer
-	initializedPeers map[rp.PeerID]bool
+	mu    sync.Mutex
+	iface PresharedKeySetter
+	// preSharedKey is the account-level preshared key, used as the rendezvous
+	// key when set. Nil means the deterministic seed key is used instead.
+	preSharedKey *[32]byte
+	// localWgKey is the local WireGuard public key, one of the two inputs to
+	// the deterministic seed key.
+	localWgKey wgtypes.Key
+	peers      map[rp.PeerID]*wireGuardPeer
 }
 
-func NewNetbirdHandler() *NetbirdHandler {
+func NewNetbirdHandler(preSharedKey *[32]byte, localWgKey wgtypes.Key) *NetbirdHandler {
 	return &NetbirdHandler{
-		peers:            map[rp.PeerID]wireGuardPeer{},
-		initializedPeers: map[rp.PeerID]bool{},
+		preSharedKey: preSharedKey,
+		localWgKey:   localWgKey,
+		peers:        map[rp.PeerID]*wireGuardPeer{},
 	}
 }
 
@@ -42,10 +57,16 @@ func (h *NetbirdHandler) SetInterface(iface PresharedKeySetter) {
 	h.iface = iface
 }
 
+// AddPeer registers a peer with the handler. Re-adding a known peer (every
+// reconnection does) keeps its key recovery state.
 func (h *NetbirdHandler) AddPeer(pid rp.PeerID, intf string, pk rp.Key) {
 	h.mu.Lock()
 	defer h.mu.Unlock()
-	h.peers[pid] = wireGuardPeer{
+	if existing, ok := h.peers[pid]; ok && existing.PublicKey == pk {
+		existing.Interface = intf
+		return
+	}
+	h.peers[pid] = &wireGuardPeer{
 		Interface: intf,
 		PublicKey: pk,
 	}
@@ -55,7 +76,6 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) {
 	h.mu.Lock()
 	defer h.mu.Unlock()
 	delete(h.peers, pid)
-	delete(h.initializedPeers, pid)
 }
 
 // IsPeerInitialized returns true if Rosenpass has completed a handshake
@@ -63,50 +83,120 @@ func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) {
 func (h *NetbirdHandler) IsPeerInitialized(pid rp.PeerID) bool {
 	h.mu.Lock()
 	defer h.mu.Unlock()
-	return h.initializedPeers[pid]
+	peer, ok := h.peers[pid]
+	return ok && peer.initialized
 }
 
+// HandshakeCompleted programs the freshly exchanged output key and resets the
+// peer's key recovery state.
 func (h *NetbirdHandler) HandshakeCompleted(pid rp.PeerID, key rp.Key) {
-	h.outputKey(rp.KeyOutputReasonStale, pid, key)
-}
+	psk := wgtypes.Key(key)
 
-func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) {
-	key, _ := rp.GeneratePresharedKey()
-	h.outputKey(rp.KeyOutputReasonStale, pid, key)
-}
-
-func (h *NetbirdHandler) outputKey(_ rp.KeyOutputReason, pid rp.PeerID, psk rp.Key) {
 	h.mu.Lock()
-	iface := h.iface
-	wg, ok := h.peers[pid]
-	isInitialized := h.initializedPeers[pid]
-	h.mu.Unlock()
+	defer h.mu.Unlock()
 
-	if iface == nil {
-		log.Warn("rosenpass: interface not set, cannot update preshared key")
+	peer, ok := h.peers[pid]
+	if !ok {
 		return
 	}
+	if peer.expiries > 0 {
+		log.Infof("rosenpass exchange completed for peer %s after %d expired renewals", wgtypes.Key(peer.PublicKey), peer.expiries)
+	}
+	// chainKey tracks the shared exchange output regardless of the local write
+	// outcome, so both ends still converge on the next expiry.
+	peer.chainKey = &psk
+	peer.expiries = 0
+	if !h.applyKeyLocked(pid, psk, peer.initialized) {
+		return
+	}
+	peer.initialized = true
+}
 
+// HandshakeExpired replaces the expired key. The renewal exchange runs over
+// the tunnel keyed by the PSK itself, so the replacement must be derivable on
+// both ends without communication: the first expiry ratchets the last shared
+// key forward, repeated expiries (and expiries without a completed exchange)
+// fall back to the rendezvous key and drop the peer out of the initialized
+// state so connection reconfigurations reprogram the rendezvous key as well.
+func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+
+	peer, ok := h.peers[pid]
 	if !ok {
 		return
 	}
 
-	peerKey := wgtypes.Key(wg.PublicKey).String()
-	pskKey := wgtypes.Key(psk)
+	peer.expiries++
 
-	// Use updateOnly=true for later rotations (peer already has Rosenpass PSK)
-	// Use updateOnly=false for first rotation (peer has original/empty PSK)
-	if err := iface.SetPresharedKey(peerKey, pskKey, isInitialized); err != nil {
+	var psk wgtypes.Key
+	if peer.chainKey != nil && peer.expiries == 1 {
+		log.Infof("rosenpass key for peer %s expired without renewal, advancing to ratcheted key", wgtypes.Key(peer.PublicKey))
+		psk = RatchetKey(*peer.chainKey)
+		peer.chainKey = &psk
+	} else {
+		rendezvous, err := h.rendezvousKey(peer)
+		if err != nil {
+			// Fail closed: without a rendezvous key the expired key must
+			// still be rotated out, even if the replacement is unusable.
+			log.Errorf("failed to derive rendezvous key, replacing expired key with a random one: %v", err)
+			h.applyRandomKeyLocked(pid)
+			return
+		}
+		log.Warnf("rosenpass key for peer %s expired %d times without renewal, falling back to the rendezvous key", wgtypes.Key(peer.PublicKey), peer.expiries)
+		psk = rendezvous
+		peer.chainKey = nil
+		peer.initialized = false
+	}
+
+	h.applyKeyLocked(pid, psk, true)
+}
+
+// rendezvousKey returns the key both ends converge on without communication:
+// the account-level preshared key when configured, the deterministic seed key
+// otherwise. It mirrors the key that peer connections program when Rosenpass
+// does not manage the peer yet.
+func (h *NetbirdHandler) rendezvousKey(peer *wireGuardPeer) (wgtypes.Key, error) {
+	if h.preSharedKey != nil {
+		return *h.preSharedKey, nil
+	}
+
+	seed, err := DeterministicSeedKey(h.localWgKey.String(), wgtypes.Key(peer.PublicKey).String())
+	if err != nil {
+		return wgtypes.Key{}, err
+	}
+	return *seed, nil
+}
+
+// applyKeyLocked writes the preshared key for the peer to the WireGuard
+// interface and reports whether the write succeeded. Callers must hold h.mu
+// for the whole state-mutation-plus-write so that a concurrent completion and
+// expiry cannot reorder their writes relative to the in-memory chain key.
+func (h *NetbirdHandler) applyKeyLocked(pid rp.PeerID, psk wgtypes.Key, updateOnly bool) bool {
+	peer, ok := h.peers[pid]
+	if !ok {
+		return false
+	}
+
+	if h.iface == nil {
+		log.Warn("rosenpass: interface not set, cannot update preshared key")
+		return false
+	}
+
+	peerKey := wgtypes.Key(peer.PublicKey).String()
+	if err := h.iface.SetPresharedKey(peerKey, psk, updateOnly); err != nil {
 		log.Errorf("Failed to apply rosenpass key: %v", err)
+		return false
+	}
+
+	return true
+}
+
+func (h *NetbirdHandler) applyRandomKeyLocked(pid rp.PeerID) {
+	key, err := rp.GeneratePresharedKey()
+	if err != nil {
+		log.Errorf("failed to generate random preshared key: %v", err)
 		return
 	}
-
-	// Mark peer as isInitialized after the successful first rotation
-	if !isInitialized {
-		h.mu.Lock()
-		if _, exists := h.peers[pid]; exists {
-			h.initializedPeers[pid] = true
-		}
-		h.mu.Unlock()
-	}
+	h.applyKeyLocked(pid, wgtypes.Key(key), true)
 }

client/internal/rosenpass/netbird_handler_test.go

@@ -0,0 +1,250 @@
+package rosenpass
+
+import (
+	"testing"
+
+	rp "cunicu.li/go-rosenpass"
+	"github.com/stretchr/testify/require"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+)
+
+// handlerTestLink wires two NetbirdHandlers as the two ends of a single
+// tunnel: handler A manages the rosenpass peer B and vice versa, the way two
+// NetBird clients see each other.
+type handlerTestLink struct {
+	handlerA, handlerB *NetbirdHandler
+	ifaceA, ifaceB     *mockIface
+	pidA, pidB         rp.PeerID
+	wgKeyA, wgKeyB     wgtypes.Key
+}
+
+func newHandlerTestLink(t *testing.T, preSharedKey *[32]byte) *handlerTestLink {
+	t.Helper()
+
+	link := &handlerTestLink{
+		ifaceA: &mockIface{},
+		ifaceB: &mockIface{},
+	}
+	link.pidA[0] = 0xaa
+	link.pidB[0] = 0xbb
+	link.wgKeyA[31] = 1
+	link.wgKeyB[31] = 2
+
+	link.handlerA = NewNetbirdHandler(preSharedKey, link.wgKeyA)
+	link.handlerB = NewNetbirdHandler(preSharedKey, link.wgKeyB)
+
+	link.handlerA.SetInterface(link.ifaceA)
+	link.handlerB.SetInterface(link.ifaceB)
+
+	link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB))
+	link.handlerB.AddPeer(link.pidA, "wt0", rp.Key(link.wgKeyA))
+
+	return link
+}
+
+// complete simulates a completed rosenpass exchange: both ends derive the
+// same output key.
+func (l *handlerTestLink) complete(osk rp.Key) {
+	l.handlerA.HandshakeCompleted(l.pidB, osk)
+	l.handlerB.HandshakeCompleted(l.pidA, osk)
+}
+
+// expire simulates a failed key renewal on both ends.
+func (l *handlerTestLink) expire() {
+	l.handlerA.HandshakeExpired(l.pidB)
+	l.handlerB.HandshakeExpired(l.pidA)
+}
+
+func lastPSK(t *testing.T, m *mockIface) wgtypes.Key {
+	t.Helper()
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	require.NotEmpty(t, m.calls, "expected at least one SetPresharedKey call")
+	return m.calls[len(m.calls)-1].psk
+}
+
+func TestHandshakeCompleted_SetsKeyAndInitializes(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	require.Equal(t, wgtypes.Key(osk), lastPSK(t, link.ifaceA), "completed exchange must program the osk")
+	require.False(t, link.ifaceA.calls[0].updateOnly, "first rotation must not be update-only")
+	require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized after first completed exchange")
+
+	link.complete(osk)
+	require.True(t, link.ifaceA.calls[1].updateOnly, "later rotations must be update-only")
+}
+
+// TestHandshakeExpired_BothSidesConverge encodes the core recovery invariant:
+// rosenpass renewals run over the tunnel that the PSK itself keys, so when a
+// renewal fails on both ends, both ends must fall back to the same key or the
+// tunnel can never handshake again.
+func TestHandshakeExpired_BothSidesConverge(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	keyA := lastPSK(t, link.ifaceA)
+	keyB := lastPSK(t, link.ifaceB)
+	require.NotEqual(t, wgtypes.Key(osk), keyA, "expired key must be rotated out")
+	require.Equal(t, keyA, keyB, "both ends must converge on the same key after expiry")
+
+	link.expire()
+	require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
+		"both ends must still converge after repeated expiries")
+}
+
+// TestHandshakeExpired_ExpiryWithoutCompletionConverges covers the bootstrap
+// case: the initial exchange never completed (the tunnel ran on the rendezvous
+// key), so an expiry must not replace the working key with an unrecoverable
+// one on either end.
+func TestHandshakeExpired_ExpiryWithoutCompletionConverges(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	link.expire()
+	require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
+		"both ends must converge when the exchange never completed")
+}
+
+// TestHandshakeExpired_RepeatedExpiryClearsInitialized: once renewals keep
+// failing, the peer must drop out of the initialized state so the next
+// connection reconfiguration reprograms the rendezvous key instead of
+// preserving a poisoned rosenpass-managed key.
+func TestHandshakeExpired_RepeatedExpiryClearsInitialized(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	link.expire()
+
+	require.False(t, link.handlerA.IsPeerInitialized(link.pidB),
+		"repeated expiries must clear the initialized state")
+	require.False(t, link.handlerB.IsPeerInitialized(link.pidA),
+		"repeated expiries must clear the initialized state")
+}
+
+// TestHandshakeCompleted_AfterExpiryRecovers: a completed exchange after a
+// desync must fully reset the recovery state.
+func TestHandshakeCompleted_AfterExpiryRecovers(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk1, osk2 rp.Key
+	osk1[0] = 1
+	osk2[0] = 2
+
+	link.complete(osk1)
+	link.expire()
+	link.expire()
+
+	link.complete(osk2)
+	require.Equal(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "new exchange must program the fresh osk")
+	require.True(t, link.handlerA.IsPeerInitialized(link.pidB), "peer must be initialized again after recovery")
+
+	link.expire()
+	require.Equal(t, lastPSK(t, link.ifaceA), lastPSK(t, link.ifaceB),
+		"recovered link must converge again on the next expiry")
+	require.NotEqual(t, wgtypes.Key(osk2), lastPSK(t, link.ifaceA), "expired key must be rotated out")
+}
+
+// TestHandshakeExpired_FirstExpiryRatchetsLastKey: the first expiry must
+// derive the replacement from the last shared key, so an attacker who only
+// blocks the renewal exchange gains nothing over the previous key.
+func TestHandshakeExpired_FirstExpiryRatchetsLastKey(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	require.Equal(t, RatchetKey(wgtypes.Key(osk)), lastPSK(t, link.ifaceA),
+		"first expiry must program the ratcheted key")
+	require.True(t, link.handlerA.IsPeerInitialized(link.pidB),
+		"ratchet step must keep the peer initialized so reconfigurations preserve the key")
+}
+
+// TestHandshakeExpired_RepeatedExpiryFallsBackToSeed: once the ratchet key
+// also fails, both ends must land on the same key that peer connections
+// program for uninitialized peers, so a reconnect completes the recovery.
+func TestHandshakeExpired_RepeatedExpiryFallsBackToSeed(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	link.expire()
+
+	seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String())
+	require.NoError(t, err)
+	require.Equal(t, *seed, lastPSK(t, link.ifaceA), "repeated expiry must fall back to the seed key")
+	require.Equal(t, *seed, lastPSK(t, link.ifaceB), "repeated expiry must fall back to the seed key")
+}
+
+// TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous: with an account-level
+// preshared key configured, the fallback must be that key, matching what peer
+// connections program for uninitialized peers.
+func TestHandshakeExpired_ConfiguredPSKUsedAsRendezvous(t *testing.T) {
+	psk := &[32]byte{0x77}
+	link := newHandlerTestLink(t, psk)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	link.expire()
+
+	require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceA),
+		"fallback must be the configured preshared key")
+	require.Equal(t, wgtypes.Key(*psk), lastPSK(t, link.ifaceB),
+		"fallback must be the configured preshared key on both ends")
+}
+
+// TestHandshakeExpired_ExpiryWritesAreUpdateOnly: expiry replacements must
+// never create a WireGuard peer that connection management has removed.
+func TestHandshakeExpired_ExpiryWritesAreUpdateOnly(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+
+	link.expire()
+	link.expire()
+
+	for _, call := range link.ifaceA.calls[1:] {
+		require.True(t, call.updateOnly, "expiry writes must be update-only")
+	}
+}
+
+// TestAddPeer_ReAddKeepsRecoveryState: reconnections re-add the peer on every
+// OnConnected; that must not reset the expiry chain state.
+func TestAddPeer_ReAddKeepsRecoveryState(t *testing.T) {
+	link := newHandlerTestLink(t, nil)
+
+	var osk rp.Key
+	osk[0] = 0x42
+	link.complete(osk)
+	link.expire()
+
+	link.handlerA.AddPeer(link.pidB, "wt0", rp.Key(link.wgKeyB))
+	require.True(t, link.handlerA.IsPeerInitialized(link.pidB),
+		"re-adding a known peer must keep its state")
+
+	link.expire()
+	seed, err := DeterministicSeedKey(link.wgKeyA.String(), link.wgKeyB.String())
+	require.NoError(t, err)
+	require.Equal(t, *seed, lastPSK(t, link.ifaceA),
+		"second expiry after re-add must continue to the seed fallback")
+}

client/internal/rosenpass/seed.go

@@ -1,11 +1,28 @@
 package rosenpass
 
 import (
+	"crypto/sha256"
 	"fmt"
 
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
 
+// ratchetLabel domain-separates the expiry ratchet from other uses of the
+// rosenpass output key.
+const ratchetLabel = "netbird-rosenpass-expiry-ratchet"
+
+// RatchetKey derives the successor preshared key from the previous Rosenpass
+// output key. When a key expires without a completed renewal, both peers
+// advance their last shared key by one ratchet step: the expired key is
+// rotated out while both ends still converge on an identical, non-public
+// replacement without communicating.
+func RatchetKey(prev wgtypes.Key) wgtypes.Key {
+	input := make([]byte, 0, len(ratchetLabel)+len(prev))
+	input = append(input, ratchetLabel...)
+	input = append(input, prev[:]...)
+	return sha256.Sum256(input)
+}
+
 // DeterministicSeedKey derives a 32-byte WireGuard preshared key from a pair
 // of peer public keys. Both peers, given the same key pair, produce the same
 // output regardless of which side runs the function: the inputs are ordered

client/internal/routemanager/manager.go

@@ -12,6 +12,7 @@ import (
 	"strings"
 	"sync"
 	"sync/atomic"
+	"syscall"
 	"time"
 
 	"github.com/google/uuid"
@@ -264,7 +265,11 @@ func (m *DefaultManager) initSelector() *routeselector.RouteSelector {
 
 	// restore selector state if it exists
 	if err := m.stateManager.LoadState(state); err != nil {
-		log.Warnf("failed to load state: %v", err)
+		if errors.Is(err, syscall.ENOSYS) {
+			log.Debugf("route selector state unavailable on this platform: %v", err)
+		} else {
+			log.Warnf("failed to load state: %v", err)
+		}
 		return routeselector.NewRouteSelector()
 	}
 

client/mdm/canonical_loaders.go

@@ -22,6 +22,7 @@ var allKeys = []string{
 	KeyDisableMetricsCollection,
 	KeyAllowServerSSH,
 	KeyDisableAutoConnect,
+	KeyDisableAutostart,
 	KeyPreSharedKey,
 	KeyRosenpassEnabled,
 	KeyRosenpassPermissive,

client/mdm/policy.go

@@ -20,10 +20,10 @@ import (
 // names (lowerCamelCase) so the daemon can map a Policy key directly to a
 // configuration field.
 const (
-	KeyManagementURL            = "managementURL"
-	KeyDisableUpdateSettings    = "disableUpdateSettings"
-	KeyDisableProfiles          = "disableProfiles"
-	KeyDisableNetworks          = "disableNetworks"
+	KeyManagementURL         = "managementURL"
+	KeyDisableUpdateSettings = "disableUpdateSettings"
+	KeyDisableProfiles       = "disableProfiles"
+	KeyDisableNetworks       = "disableNetworks"
 	// KeyDisableAdvancedView gates the advanced-view section in the
 	// upcoming UI revision. UI-only: NOT stored on Config, not
 	// applied by applyMDMPolicy, not rejectable via SetConfig. The
@@ -37,10 +37,16 @@ const (
 	KeyDisableMetricsCollection = "disableMetricsCollection"
 	KeyAllowServerSSH           = "allowServerSSH"
 	KeyDisableAutoConnect       = "disableAutoConnect"
-	KeyPreSharedKey             = "preSharedKey"
-	KeyRosenpassEnabled         = "rosenpassEnabled"
-	KeyRosenpassPermissive      = "rosenpassPermissive"
-	KeyWireguardPort            = "wireguardPort"
+	// KeyDisableAutostart suppresses the GUI's fresh-install
+	// launch-on-login default and marks the Settings toggle as
+	// MDM-managed. UI-only: NOT stored on Config and not applied by
+	// applyMDMPolicy; the GUI reads it directly and it appears in
+	// GetConfigResponse.mDMManagedFields when set.
+	KeyDisableAutostart    = "disableAutostart"
+	KeyPreSharedKey        = "preSharedKey"
+	KeyRosenpassEnabled    = "rosenpassEnabled"
+	KeyRosenpassPermissive = "rosenpassPermissive"
+	KeyWireguardPort       = "wireguardPort"
 
 	// Split tunnel is modeled as a single conceptual policy with two
 	// registry/plist values. KeySplitTunnelMode is the discriminator

client/proto/daemon.pb.gw.go

@@ -131,6 +131,26 @@ func local_request_DaemonService_Status_0(ctx context.Context, marshaler runtime
 	return msg, metadata, err
 }
 
+func request_DaemonService_SubscribeStatus_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (DaemonService_SubscribeStatusClient, runtime.ServerMetadata, error) {
+	var (
+		protoReq StatusRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	stream, err := client.SubscribeStatus(ctx, &protoReq)
+	if err != nil {
+		return nil, metadata, err
+	}
+	header, err := stream.Header()
+	if err != nil {
+		return nil, metadata, err
+	}
+	metadata.HeaderMD = header
+	return stream, metadata, nil
+}
+
 func request_DaemonService_Down_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
 	var (
 		protoReq DownRequest
@@ -579,6 +599,30 @@ func local_request_DaemonService_GetEvents_0(ctx context.Context, marshaler runt
 	return msg, metadata, err
 }
 
+func request_DaemonService_RegisterUILog_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq RegisterUILogRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := client.RegisterUILog(ctx, &protoReq, grpc.Header(&metadata.HeaderMD), grpc.Trailer(&metadata.TrailerMD))
+	return msg, metadata, err
+}
+
+func local_request_DaemonService_RegisterUILog_0(ctx context.Context, marshaler runtime.Marshaler, server DaemonServiceServer, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq RegisterUILogRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := server.RegisterUILog(ctx, &protoReq)
+	return msg, metadata, err
+}
+
 func request_DaemonService_SwitchProfile_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
 	var (
 		protoReq SwitchProfileRequest
@@ -891,6 +935,78 @@ func local_request_DaemonService_WaitJWTToken_0(ctx context.Context, marshaler r
 	return msg, metadata, err
 }
 
+func request_DaemonService_RequestExtendAuthSession_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq RequestExtendAuthSessionRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := client.RequestExtendAuthSession(ctx, &protoReq, grpc.Header(&metadata.HeaderMD), grpc.Trailer(&metadata.TrailerMD))
+	return msg, metadata, err
+}
+
+func local_request_DaemonService_RequestExtendAuthSession_0(ctx context.Context, marshaler runtime.Marshaler, server DaemonServiceServer, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq RequestExtendAuthSessionRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := server.RequestExtendAuthSession(ctx, &protoReq)
+	return msg, metadata, err
+}
+
+func request_DaemonService_WaitExtendAuthSession_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq WaitExtendAuthSessionRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := client.WaitExtendAuthSession(ctx, &protoReq, grpc.Header(&metadata.HeaderMD), grpc.Trailer(&metadata.TrailerMD))
+	return msg, metadata, err
+}
+
+func local_request_DaemonService_WaitExtendAuthSession_0(ctx context.Context, marshaler runtime.Marshaler, server DaemonServiceServer, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq WaitExtendAuthSessionRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := server.WaitExtendAuthSession(ctx, &protoReq)
+	return msg, metadata, err
+}
+
+func request_DaemonService_DismissSessionWarning_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq DismissSessionWarningRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := client.DismissSessionWarning(ctx, &protoReq, grpc.Header(&metadata.HeaderMD), grpc.Trailer(&metadata.TrailerMD))
+	return msg, metadata, err
+}
+
+func local_request_DaemonService_DismissSessionWarning_0(ctx context.Context, marshaler runtime.Marshaler, server DaemonServiceServer, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq DismissSessionWarningRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := server.DismissSessionWarning(ctx, &protoReq)
+	return msg, metadata, err
+}
+
 func request_DaemonService_StartCPUProfile_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
 	var (
 		protoReq StartCPUProfileRequest
@@ -983,6 +1099,30 @@ func request_DaemonService_ExposeService_0(ctx context.Context, marshaler runtim
 	return stream, metadata, nil
 }
 
+func request_DaemonService_WailsUIReady_0(ctx context.Context, marshaler runtime.Marshaler, client DaemonServiceClient, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq WailsUIReadyRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := client.WailsUIReady(ctx, &protoReq, grpc.Header(&metadata.HeaderMD), grpc.Trailer(&metadata.TrailerMD))
+	return msg, metadata, err
+}
+
+func local_request_DaemonService_WailsUIReady_0(ctx context.Context, marshaler runtime.Marshaler, server DaemonServiceServer, req *http.Request, pathParams map[string]string) (proto.Message, runtime.ServerMetadata, error) {
+	var (
+		protoReq WailsUIReadyRequest
+		metadata runtime.ServerMetadata
+	)
+	if err := marshaler.NewDecoder(req.Body).Decode(&protoReq); err != nil && !errors.Is(err, io.EOF) {
+		return nil, metadata, status.Errorf(codes.InvalidArgument, "%v", err)
+	}
+	msg, err := server.WailsUIReady(ctx, &protoReq)
+	return msg, metadata, err
+}
+
 // RegisterDaemonServiceHandlerServer registers the http handlers for service DaemonService to "mux".
 // UnaryRPC     :call DaemonServiceServer directly.
 // StreamingRPC :currently unsupported pending https://github.com/grpc/grpc-go/issues/906.
@@ -1069,6 +1209,13 @@ func RegisterDaemonServiceHandlerServer(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_Status_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+
+	mux.Handle(http.MethodPost, pattern_DaemonService_SubscribeStatus_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		err := status.Error(codes.Unimplemented, "streaming calls are not yet supported in the in-process transport")
+		_, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+		return
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_Down_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -1423,6 +1570,26 @@ func RegisterDaemonServiceHandlerServer(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_GetEvents_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_RegisterUILog_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		var stream runtime.ServerTransportStream
+		ctx = grpc.NewContextWithServerTransportStream(ctx, &stream)
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateIncomingContext(ctx, mux, req, "/daemon.DaemonService/RegisterUILog", runtime.WithHTTPPathPattern("/daemon.DaemonService/RegisterUILog"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := local_request_DaemonService_RegisterUILog_0(annotatedContext, inboundMarshaler, server, req, pathParams)
+		md.HeaderMD, md.TrailerMD = metadata.Join(md.HeaderMD, stream.Header()), metadata.Join(md.TrailerMD, stream.Trailer())
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_RegisterUILog_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_SwitchProfile_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -1683,6 +1850,66 @@ func RegisterDaemonServiceHandlerServer(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_WaitJWTToken_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_RequestExtendAuthSession_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		var stream runtime.ServerTransportStream
+		ctx = grpc.NewContextWithServerTransportStream(ctx, &stream)
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateIncomingContext(ctx, mux, req, "/daemon.DaemonService/RequestExtendAuthSession", runtime.WithHTTPPathPattern("/daemon.DaemonService/RequestExtendAuthSession"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := local_request_DaemonService_RequestExtendAuthSession_0(annotatedContext, inboundMarshaler, server, req, pathParams)
+		md.HeaderMD, md.TrailerMD = metadata.Join(md.HeaderMD, stream.Header()), metadata.Join(md.TrailerMD, stream.Trailer())
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_RequestExtendAuthSession_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_WaitExtendAuthSession_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		var stream runtime.ServerTransportStream
+		ctx = grpc.NewContextWithServerTransportStream(ctx, &stream)
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateIncomingContext(ctx, mux, req, "/daemon.DaemonService/WaitExtendAuthSession", runtime.WithHTTPPathPattern("/daemon.DaemonService/WaitExtendAuthSession"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := local_request_DaemonService_WaitExtendAuthSession_0(annotatedContext, inboundMarshaler, server, req, pathParams)
+		md.HeaderMD, md.TrailerMD = metadata.Join(md.HeaderMD, stream.Header()), metadata.Join(md.TrailerMD, stream.Trailer())
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_WaitExtendAuthSession_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_DismissSessionWarning_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		var stream runtime.ServerTransportStream
+		ctx = grpc.NewContextWithServerTransportStream(ctx, &stream)
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateIncomingContext(ctx, mux, req, "/daemon.DaemonService/DismissSessionWarning", runtime.WithHTTPPathPattern("/daemon.DaemonService/DismissSessionWarning"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := local_request_DaemonService_DismissSessionWarning_0(annotatedContext, inboundMarshaler, server, req, pathParams)
+		md.HeaderMD, md.TrailerMD = metadata.Join(md.HeaderMD, stream.Header()), metadata.Join(md.TrailerMD, stream.Trailer())
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_DismissSessionWarning_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_StartCPUProfile_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -1750,6 +1977,26 @@ func RegisterDaemonServiceHandlerServer(ctx context.Context, mux *runtime.ServeM
 		runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
 		return
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_WailsUIReady_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		var stream runtime.ServerTransportStream
+		ctx = grpc.NewContextWithServerTransportStream(ctx, &stream)
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateIncomingContext(ctx, mux, req, "/daemon.DaemonService/WailsUIReady", runtime.WithHTTPPathPattern("/daemon.DaemonService/WailsUIReady"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := local_request_DaemonService_WailsUIReady_0(annotatedContext, inboundMarshaler, server, req, pathParams)
+		md.HeaderMD, md.TrailerMD = metadata.Join(md.HeaderMD, stream.Header()), metadata.Join(md.TrailerMD, stream.Trailer())
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_WailsUIReady_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 
 	return nil
 }
@@ -1858,6 +2105,23 @@ func RegisterDaemonServiceHandlerClient(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_Status_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_SubscribeStatus_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/SubscribeStatus", runtime.WithHTTPPathPattern("/daemon.DaemonService/SubscribeStatus"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_SubscribeStatus_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_SubscribeStatus_0(annotatedContext, mux, outboundMarshaler, w, req, func() (proto.Message, error) { return resp.Recv() }, mux.GetForwardResponseOptions()...)
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_Down_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -2181,6 +2445,23 @@ func RegisterDaemonServiceHandlerClient(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_GetEvents_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_RegisterUILog_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/RegisterUILog", runtime.WithHTTPPathPattern("/daemon.DaemonService/RegisterUILog"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_RegisterUILog_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_RegisterUILog_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_SwitchProfile_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -2402,6 +2683,57 @@ func RegisterDaemonServiceHandlerClient(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_WaitJWTToken_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_RequestExtendAuthSession_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/RequestExtendAuthSession", runtime.WithHTTPPathPattern("/daemon.DaemonService/RequestExtendAuthSession"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_RequestExtendAuthSession_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_RequestExtendAuthSession_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_WaitExtendAuthSession_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/WaitExtendAuthSession", runtime.WithHTTPPathPattern("/daemon.DaemonService/WaitExtendAuthSession"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_WaitExtendAuthSession_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_WaitExtendAuthSession_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_DismissSessionWarning_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/DismissSessionWarning", runtime.WithHTTPPathPattern("/daemon.DaemonService/DismissSessionWarning"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_DismissSessionWarning_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_DismissSessionWarning_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 	mux.Handle(http.MethodPost, pattern_DaemonService_StartCPUProfile_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
 		ctx, cancel := context.WithCancel(req.Context())
 		defer cancel()
@@ -2470,6 +2802,23 @@ func RegisterDaemonServiceHandlerClient(ctx context.Context, mux *runtime.ServeM
 		}
 		forward_DaemonService_ExposeService_0(annotatedContext, mux, outboundMarshaler, w, req, func() (proto.Message, error) { return resp.Recv() }, mux.GetForwardResponseOptions()...)
 	})
+	mux.Handle(http.MethodPost, pattern_DaemonService_WailsUIReady_0, func(w http.ResponseWriter, req *http.Request, pathParams map[string]string) {
+		ctx, cancel := context.WithCancel(req.Context())
+		defer cancel()
+		inboundMarshaler, outboundMarshaler := runtime.MarshalerForRequest(mux, req)
+		annotatedContext, err := runtime.AnnotateContext(ctx, mux, req, "/daemon.DaemonService/WailsUIReady", runtime.WithHTTPPathPattern("/daemon.DaemonService/WailsUIReady"))
+		if err != nil {
+			runtime.HTTPError(ctx, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		resp, md, err := request_DaemonService_WailsUIReady_0(annotatedContext, inboundMarshaler, client, req, pathParams)
+		annotatedContext = runtime.NewServerMetadataContext(annotatedContext, md)
+		if err != nil {
+			runtime.HTTPError(annotatedContext, mux, outboundMarshaler, w, req, err)
+			return
+		}
+		forward_DaemonService_WailsUIReady_0(annotatedContext, mux, outboundMarshaler, w, req, resp, mux.GetForwardResponseOptions()...)
+	})
 	return nil
 }
 
@@ -2478,6 +2827,7 @@ var (
 	pattern_DaemonService_WaitSSOLogin_0               = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "WaitSSOLogin"}, ""))
 	pattern_DaemonService_Up_0                         = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "Up"}, ""))
 	pattern_DaemonService_Status_0                     = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "Status"}, ""))
+	pattern_DaemonService_SubscribeStatus_0            = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "SubscribeStatus"}, ""))
 	pattern_DaemonService_Down_0                       = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "Down"}, ""))
 	pattern_DaemonService_GetConfig_0                  = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "GetConfig"}, ""))
 	pattern_DaemonService_ListNetworks_0               = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "ListNetworks"}, ""))
@@ -2497,6 +2847,7 @@ var (
 	pattern_DaemonService_StopBundleCapture_0          = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "StopBundleCapture"}, ""))
 	pattern_DaemonService_SubscribeEvents_0            = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "SubscribeEvents"}, ""))
 	pattern_DaemonService_GetEvents_0                  = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "GetEvents"}, ""))
+	pattern_DaemonService_RegisterUILog_0              = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "RegisterUILog"}, ""))
 	pattern_DaemonService_SwitchProfile_0              = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "SwitchProfile"}, ""))
 	pattern_DaemonService_SetConfig_0                  = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "SetConfig"}, ""))
 	pattern_DaemonService_AddProfile_0                 = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "AddProfile"}, ""))
@@ -2510,10 +2861,14 @@ var (
 	pattern_DaemonService_GetPeerSSHHostKey_0          = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "GetPeerSSHHostKey"}, ""))
 	pattern_DaemonService_RequestJWTAuth_0             = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "RequestJWTAuth"}, ""))
 	pattern_DaemonService_WaitJWTToken_0               = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "WaitJWTToken"}, ""))
+	pattern_DaemonService_RequestExtendAuthSession_0   = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "RequestExtendAuthSession"}, ""))
+	pattern_DaemonService_WaitExtendAuthSession_0      = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "WaitExtendAuthSession"}, ""))
+	pattern_DaemonService_DismissSessionWarning_0      = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "DismissSessionWarning"}, ""))
 	pattern_DaemonService_StartCPUProfile_0            = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "StartCPUProfile"}, ""))
 	pattern_DaemonService_StopCPUProfile_0             = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "StopCPUProfile"}, ""))
 	pattern_DaemonService_GetInstallerResult_0         = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "GetInstallerResult"}, ""))
 	pattern_DaemonService_ExposeService_0              = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "ExposeService"}, ""))
+	pattern_DaemonService_WailsUIReady_0               = runtime.MustPattern(runtime.NewPattern(1, []int{2, 0, 2, 1}, []string{"daemon.DaemonService", "WailsUIReady"}, ""))
 )
 
 var (
@@ -2521,6 +2876,7 @@ var (
 	forward_DaemonService_WaitSSOLogin_0               = runtime.ForwardResponseMessage
 	forward_DaemonService_Up_0                         = runtime.ForwardResponseMessage
 	forward_DaemonService_Status_0                     = runtime.ForwardResponseMessage
+	forward_DaemonService_SubscribeStatus_0            = runtime.ForwardResponseStream
 	forward_DaemonService_Down_0                       = runtime.ForwardResponseMessage
 	forward_DaemonService_GetConfig_0                  = runtime.ForwardResponseMessage
 	forward_DaemonService_ListNetworks_0               = runtime.ForwardResponseMessage
@@ -2540,6 +2896,7 @@ var (
 	forward_DaemonService_StopBundleCapture_0          = runtime.ForwardResponseMessage
 	forward_DaemonService_SubscribeEvents_0            = runtime.ForwardResponseStream
 	forward_DaemonService_GetEvents_0                  = runtime.ForwardResponseMessage
+	forward_DaemonService_RegisterUILog_0              = runtime.ForwardResponseMessage
 	forward_DaemonService_SwitchProfile_0              = runtime.ForwardResponseMessage
 	forward_DaemonService_SetConfig_0                  = runtime.ForwardResponseMessage
 	forward_DaemonService_AddProfile_0                 = runtime.ForwardResponseMessage
@@ -2553,8 +2910,12 @@ var (
 	forward_DaemonService_GetPeerSSHHostKey_0          = runtime.ForwardResponseMessage
 	forward_DaemonService_RequestJWTAuth_0             = runtime.ForwardResponseMessage
 	forward_DaemonService_WaitJWTToken_0               = runtime.ForwardResponseMessage
+	forward_DaemonService_RequestExtendAuthSession_0   = runtime.ForwardResponseMessage
+	forward_DaemonService_WaitExtendAuthSession_0      = runtime.ForwardResponseMessage
+	forward_DaemonService_DismissSessionWarning_0      = runtime.ForwardResponseMessage
 	forward_DaemonService_StartCPUProfile_0            = runtime.ForwardResponseMessage
 	forward_DaemonService_StopCPUProfile_0             = runtime.ForwardResponseMessage
 	forward_DaemonService_GetInstallerResult_0         = runtime.ForwardResponseMessage
 	forward_DaemonService_ExposeService_0              = runtime.ForwardResponseStream
+	forward_DaemonService_WailsUIReady_0               = runtime.ForwardResponseMessage
 )

client/server/server.go

@@ -828,6 +828,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 		return nil, err
 	}
 
+	log.Infof("SSO login flow finished, returning success to caller")
 	return &proto.WaitSSOLoginResponse{
 		Email: tokenInfo.Email,
 	}, nil
@@ -835,6 +836,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 
 // Up starts engine work in the daemon.
 func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpResponse, error) {
+	log.Infof("up request received")
 	s.mutex.Lock()
 	// clientRunning is the daemon-intent flag (set by previous Up/Start, cleared
 	// by Down). connectionGoroutineRunning() reports whether the previous retry-loop

client/status/status.go

@@ -746,6 +746,8 @@ func ToProtoFullStatus(fullStatus peer.FullStatus) *proto.FullStatus {
 		pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
 	}
 
+	pbFullStatus.Events = fullStatus.Events
+
 	return &pbFullStatus
 }
 

client/system/process.go

@@ -7,7 +7,7 @@ import (
 	"os"
 	"slices"
 
-	"github.com/shirou/gopsutil/v3/process"
+	"github.com/shirou/gopsutil/v4/process"
 )
 
 // getRunningProcesses returns a list of running process paths. The context bounds the work:

client/system/process_test.go

@@ -4,7 +4,7 @@ import (
 	"context"
 	"testing"
 
-	"github.com/shirou/gopsutil/v3/process"
+	"github.com/shirou/gopsutil/v4/process"
 )
 
 func Benchmark_getRunningProcesses(b *testing.B) {

client/ui/autostart_default.go

@@ -0,0 +1,107 @@
+//go:build !android && !ios && !freebsd && !js
+
+package main
+
+import (
+	"context"
+	"os"
+	"path/filepath"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/mdm"
+	"github.com/netbirdio/netbird/client/ui/preferences"
+	"github.com/netbirdio/netbird/client/ui/services"
+)
+
+// autostartDefaultState carries the guard inputs of the one-time autostart
+// default decision so the decision itself stays a pure, testable function.
+type autostartDefaultState struct {
+	supported    bool
+	mdmDisabled  bool
+	priorInstall bool
+}
+
+// shouldEnableAutostartDefault applies the first-run guards in order and
+// returns whether autostart may be enabled, plus the reason when it may not.
+func shouldEnableAutostartDefault(s autostartDefaultState) (bool, string) {
+	switch {
+	case !s.supported:
+		return false, "autostart not supported on this platform"
+	case s.mdmDisabled:
+		return false, "autostart disabled by MDM policy"
+	case s.priorInstall:
+		return false, "existing NetBird installation"
+	}
+	return true, ""
+}
+
+// autostartDisabledByMDM reports whether the MDM policy manages the
+// disableAutostart key in a way that must suppress the default. An
+// unparseable managed value is treated as disabled to stay on the safe side.
+func autostartDisabledByMDM(policy *mdm.Policy) bool {
+	if !policy.HasKey(mdm.KeyDisableAutostart) {
+		return false
+	}
+	disabled, ok := policy.GetBool(mdm.KeyDisableAutostart)
+	return !ok || disabled
+}
+
+// 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 login-item write.
+func netbirdFootprintExists() bool {
+	candidates := []string{
+		profilemanager.DefaultConfigPath,
+		filepath.Join(profilemanager.DefaultConfigPathDir, "config.json"),
+		filepath.Join(profilemanager.DefaultConfigPathDir, "state.json"),
+	}
+	for _, path := range candidates {
+		if path != "" && fileExists(path) {
+			return true
+		}
+	}
+	return false
+}
+
+// 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 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) {
+	priorFootprint := netbirdFootprintExists() || prefsFileExisted
+
+	if prefs.Get().AutostartInitialized {
+		return
+	}
+	if err := prefs.SetAutostartInitialized(true); err != nil {
+		log.Warnf("persist autostart marker, skipping autostart default: %v", err)
+		return
+	}
+
+	state := autostartDefaultState{
+		supported:    autostart.Supported(ctx),
+		mdmDisabled:  autostartDisabledByMDM(mdm.LoadPolicy()),
+		priorInstall: priorFootprint,
+	}
+	enable, reason := shouldEnableAutostartDefault(state)
+	if !enable {
+		log.Debugf("skipping autostart default: %s", reason)
+		return
+	}
+
+	if err := autostart.SetEnabled(ctx, true); err != nil {
+		log.Warnf("enable autostart on fresh install: %v", err)
+		return
+	}
+	log.Info("autostart enabled by default on fresh install")
+}
+
+// fileExists reports whether path exists.
+func fileExists(path string) bool {
+	_, err := os.Stat(path)
+	return err == nil
+}

client/ui/autostart_default_test.go

@@ -0,0 +1,125 @@
+//go:build !android && !ios && !freebsd && !js
+
+package main
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/netbirdio/netbird/client/mdm"
+)
+
+func TestShouldEnableAutostartDefault(t *testing.T) {
+	allPass := autostartDefaultState{
+		supported:    true,
+		mdmDisabled:  false,
+		priorInstall: false,
+	}
+
+	tests := []struct {
+		name       string
+		mutate     func(*autostartDefaultState)
+		wantEnable bool
+		wantReason string
+	}{
+		{
+			name:       "fresh install with all guards passing enables",
+			mutate:     func(*autostartDefaultState) {},
+			wantEnable: true,
+		},
+		{
+			name:       "unsupported platform skips",
+			mutate:     func(s *autostartDefaultState) { s.supported = false },
+			wantReason: "autostart not supported on this platform",
+		},
+		{
+			name:       "MDM disable skips",
+			mutate:     func(s *autostartDefaultState) { s.mdmDisabled = true },
+			wantReason: "autostart disabled by MDM policy",
+		},
+		{
+			name:       "existing installation (upgrade) skips",
+			mutate:     func(s *autostartDefaultState) { s.priorInstall = true },
+			wantReason: "existing NetBird installation",
+		},
+		{
+			name: "unsupported wins over every other guard",
+			mutate: func(s *autostartDefaultState) {
+				s.supported = false
+				s.mdmDisabled = true
+				s.priorInstall = true
+			},
+			wantReason: "autostart not supported on this platform",
+		},
+		{
+			name: "MDM disable wins over prior install",
+			mutate: func(s *autostartDefaultState) {
+				s.mdmDisabled = true
+				s.priorInstall = true
+			},
+			wantReason: "autostart disabled by MDM policy",
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			state := allPass
+			tc.mutate(&state)
+			enable, reason := shouldEnableAutostartDefault(state)
+			assert.Equal(t, tc.wantEnable, enable, "enable decision should match for state %+v", state)
+			assert.Equal(t, tc.wantReason, reason, "skip reason should identify the failing guard")
+		})
+	}
+}
+
+func TestAutostartDisabledByMDM(t *testing.T) {
+	tests := []struct {
+		name   string
+		values map[string]any
+		want   bool
+	}{
+		{
+			name:   "empty policy does not disable",
+			values: nil,
+			want:   false,
+		},
+		{
+			name:   "unrelated managed keys do not disable",
+			values: map[string]any{mdm.KeyDisableAutoConnect: true},
+			want:   false,
+		},
+		{
+			name:   "disableAutostart true disables",
+			values: map[string]any{mdm.KeyDisableAutostart: true},
+			want:   true,
+		},
+		{
+			name:   "disableAutostart registry DWORD 1 disables",
+			values: map[string]any{mdm.KeyDisableAutostart: int64(1)},
+			want:   true,
+		},
+		{
+			name:   "disableAutostart string true disables",
+			values: map[string]any{mdm.KeyDisableAutostart: "true"},
+			want:   true,
+		},
+		{
+			name:   "disableAutostart explicit false allows",
+			values: map[string]any{mdm.KeyDisableAutostart: false},
+			want:   false,
+		},
+		{
+			name:   "unparseable managed value is treated as disabled",
+			values: map[string]any{mdm.KeyDisableAutostart: "not-a-bool"},
+			want:   true,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			got := autostartDisabledByMDM(mdm.NewPolicy(tc.values))
+			assert.Equal(t, tc.want, got, "MDM disable decision should match for values %v", tc.values)
+		})
+	}
+}

client/ui/frontend/src/app.tsx

@@ -16,10 +16,13 @@ import LoginWaitingForBrowserDialog from "@/modules/login/LoginWaitingForBrowser
 import { initI18n } from "@/lib/i18n";
 import { initPlatform } from "@/lib/platform";
 import { initLogForwarding } from "@/lib/logs";
+import { initStallWatch } from "@/lib/stallwatch";
 
 // Must run first so even init-time logs reach the Go log pipeline.
 initLogForwarding();
 
+initStallWatch();
+
 welcome();
 
 Promise.all([

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

@@ -51,7 +51,14 @@ async function runSsoLogin(
     if (uri) await openBrowserLoginUri(uri);
 
     const cancelPromise = buildSsoCancelPromise(state, signal);
-    const waitPromise = Connection.WaitSSOLogin({ userCode: result.userCode, hostname: "" });
+    // Combine wait + up in Go so the connection comes up the moment SSO
+    // completes. During SSO the tray window is hidden and the webview is
+    // suspended, so a frontend-driven Up (a promise continuation) would not
+    // fire until the user woke the window (e.g. hovering the tray icon).
+    const waitPromise = Connection.WaitSSOLoginAndUp(
+        { userCode: result.userCode, hostname: "" },
+        { profileName: "", username: "" },
+    );
 
     try {
         await Promise.race([waitPromise, cancelPromise]);
@@ -89,13 +96,13 @@ export async function startConnection(onSettled?: () => void, signal?: AbortSign
         if (signal?.aborted) state.cancelled = true;
 
         if (!state.cancelled && result.needsSsoLogin) {
+            // runSsoLogin brings the connection up in Go once SSO completes.
             await runSsoLogin(result, state, signal);
-        }
-
-        if (!state.cancelled && signal?.aborted) state.cancelled = true;
-
-        if (!state.cancelled) {
-            await Connection.Up({ profileName: "", username: "" });
+        } else {
+            if (!state.cancelled && signal?.aborted) state.cancelled = true;
+            if (!state.cancelled) {
+                await Connection.Up({ profileName: "", username: "" });
+            }
         }
     } catch (e) {
         WindowManager.CloseBrowserLogin().catch(console.error);

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

@@ -0,0 +1,31 @@
+// Detects webview suspension (macOS App Nap / hidden-window timer throttling).
+// While the webview is suspended no JS runs at all, so detection happens on
+// resume: a 1s interval measures wall-clock drift and reports how long timers
+// were frozen. Silent unless a stall actually occurred; a stalled webview is
+// what delays promise continuations such as the WaitSSOLogin → Up handoff.
+
+const INTERVAL_MS = 1000;
+const STALL_THRESHOLD_MS = 5000;
+const REPORT_COOLDOWN_MS = 60_000;
+
+let started = false;
+
+export function initStallWatch() {
+    if (started) return;
+    started = true;
+
+    let last = Date.now();
+    let lastReport = 0;
+    setInterval(() => {
+        const now = Date.now();
+        const stall = now - last - INTERVAL_MS;
+        last = now;
+        if (stall < STALL_THRESHOLD_MS) return;
+        if (now - lastReport < REPORT_COOLDOWN_MS) return;
+        lastReport = now;
+        console.warn(
+            `webview timers were suspended for ${(stall / 1000).toFixed(1)}s ` +
+                `(App Nap / hidden-window throttling); pending UI work ran late`,
+        );
+    }, INTERVAL_MS);
+}

client/ui/main.go

@@ -197,6 +197,9 @@ func main() {
 		// daemon may keep the main window from showing, so the OS toast is the
 		// only reliable signal the user gets.
 		go notifyIfDaemonOutdated(compat, notifier, localizer)
+		// One-time launch-on-login default for fresh installs; gated by the
+		// NetBird footprint check, MDM policy, and the persisted marker.
+		go applyAutostartDefault(context.Background(), services.NewAutostart(app.Autostart), prefStore, prefStore.ExistedAtLoad())
 	})
 
 	if err := app.Run(); err != nil {

client/ui/preferences/store.go

@@ -54,6 +54,10 @@ type UIPreferences struct {
 	Language            i18n.LanguageCode `json:"language"`
 	ViewMode            ViewMode          `json:"viewMode"`
 	OnboardingCompleted bool              `json:"onboardingCompleted"`
+	// AutostartInitialized records that the one-time autostart default
+	// decision has run for this OS user. It only ever transitions to true
+	// and is never reset, so the default-on flow runs at most once, ever.
+	AutostartInitialized bool `json:"autostartInitialized"`
 }
 
 // LanguageValidator rejects SetLanguage inputs with no shipped bundle.
@@ -72,8 +76,9 @@ type Emitter interface {
 type Store struct {
 	path string
 
-	mu      sync.RWMutex
-	current UIPreferences
+	mu            sync.RWMutex
+	current       UIPreferences
+	existedAtLoad bool
 
 	subsMu sync.Mutex
 	subs   []chan UIPreferences
@@ -157,6 +162,27 @@ func (s *Store) SetOnboardingCompleted(done bool) error {
 	return nil
 }
 
+// SetAutostartInitialized persists the one-time autostart decision marker.
+// No-op if unchanged.
+func (s *Store) SetAutostartInitialized(done bool) error {
+	s.mu.Lock()
+	if s.current.AutostartInitialized == done {
+		s.mu.Unlock()
+		return nil
+	}
+	next := s.current
+	next.AutostartInitialized = done
+	if err := s.persistLocked(next); err != nil {
+		s.mu.Unlock()
+		return fmt.Errorf("persist preferences: %w", err)
+	}
+	s.current = next
+	s.mu.Unlock()
+
+	s.broadcast(next)
+	return nil
+}
+
 // SetLanguage validates, persists, and broadcasts. No-op if unchanged.
 func (s *Store) SetLanguage(lang i18n.LanguageCode) error {
 	if lang == "" {
@@ -206,13 +232,29 @@ func (s *Store) Subscribe() (<-chan UIPreferences, func()) {
 	return ch, unsubscribe
 }
 
+// ExistedAtLoad reports whether the backing preferences file was present on
+// disk when the store loaded. It distinguishes a user who ran a prior GUI
+// version from a brand-new OS user with no preferences yet.
+func (s *Store) ExistedAtLoad() bool {
+	s.mu.RLock()
+	defer s.mu.RUnlock()
+	return s.existedAtLoad
+}
+
 // load reads the file into current. A missing file is not an error (the
 // in-memory default stands); malformed contents return an error.
 func (s *Store) load() error {
-	if _, err := os.Stat(s.path); errors.Is(err, os.ErrNotExist) {
-		return nil
+	if _, err := os.Stat(s.path); err != nil {
+		if errors.Is(err, os.ErrNotExist) {
+			return nil
+		}
+		return fmt.Errorf("stat preferences: %w", err)
 	}
 
+	s.mu.Lock()
+	s.existedAtLoad = true
+	s.mu.Unlock()
+
 	var loaded UIPreferences
 	if _, err := util.ReadJson(s.path, &loaded); err != nil {
 		return err

client/ui/preferences/store_test.go

@@ -215,6 +215,46 @@ func TestStore_FileShapeIsJSON(t *testing.T) {
 	assert.Equal(t, i18n.LanguageCode("hu"), parsed.Language)
 }
 
+func TestStore_SetAutostartInitializedPersistsAcrossReload(t *testing.T) {
+	withTempConfigDir(t)
+	emitter := &recordingEmitter{}
+	s, err := NewStore(nil, emitter)
+	require.NoError(t, err)
+
+	assert.False(t, s.Get().AutostartInitialized, "marker must default to false when no file is on disk")
+
+	require.NoError(t, s.SetAutostartInitialized(true))
+	assert.True(t, s.Get().AutostartInitialized, "Get should reflect the persisted marker")
+	require.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "first marker write should broadcast")
+
+	// Re-setting the same value must be a no-op: no disk write, no broadcast.
+	require.NoError(t, s.SetAutostartInitialized(true))
+	assert.Len(t, emitter.calledWith(EventPreferencesChanged), 1, "idempotent marker write should not broadcast again")
+
+	// A fresh Store (new GUI launch) must see the marker so the autostart
+	// default decision never runs twice.
+	reloaded, err := NewStore(nil, nil)
+	require.NoError(t, err)
+	assert.True(t, reloaded.Get().AutostartInitialized, "marker must survive a reload from disk")
+}
+
+func TestStore_ExistedAtLoad(t *testing.T) {
+	withTempConfigDir(t)
+
+	// Brand-new OS user: no preferences file on disk yet.
+	fresh, err := NewStore(nil, nil)
+	require.NoError(t, err)
+	assert.False(t, fresh.ExistedAtLoad(), "ExistedAtLoad must be false when no file is on disk")
+
+	// Persisting a value writes the file to disk.
+	require.NoError(t, fresh.SetLanguage("en"))
+
+	// A subsequent GUI launch reopens the now-present file.
+	reopened, err := NewStore(nil, nil)
+	require.NoError(t, err)
+	assert.True(t, reopened.ExistedAtLoad(), "ExistedAtLoad must be true after the store has persisted and is reopened")
+}
+
 func TestStore_ErrUnsupportedSentinel(t *testing.T) {
 	// Verifies callers can match on the sentinel error rather than parsing
 	// strings — protects against accidental %v -> %w changes that would

client/ui/services/connection.go

@@ -35,7 +35,7 @@ type LoginResult struct {
 	VerificationURIComplete string `json:"verificationUriComplete"`
 }
 
-// WaitSSOParams are the inputs to WaitSSOLogin.
+// WaitSSOParams are the inputs to waitSSOLogin.
 type WaitSSOParams struct {
 	UserCode string `json:"userCode"`
 	Hostname string `json:"hostname"`
@@ -116,6 +116,7 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 	if err != nil {
 		return LoginResult{}, s.classifyDaemonError(err)
 	}
+	log.Infof("daemon login response received, needs SSO login: %v", resp.GetNeedsSSOLogin())
 	return LoginResult{
 		NeedsSSOLogin:           resp.GetNeedsSSOLogin(),
 		UserCode:                resp.GetUserCode(),
@@ -124,26 +125,12 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 	}, nil
 }
 
-func (s *Connection) WaitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) {
-	cli, err := s.conn.Client()
-	if err != nil {
-		return "", err
-	}
-	resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{
-		UserCode: p.UserCode,
-		Hostname: p.Hostname,
-	})
-	if err != nil {
-		return "", s.classifyDaemonError(err)
-	}
-	return resp.GetEmail(), nil
-}
-
 func (s *Connection) Up(ctx context.Context, p UpParams) error {
 	cli, err := s.conn.Client()
 	if err != nil {
 		return err
 	}
+	log.Infof("sending up request to daemon")
 	// Always async: status updates flow via SubscribeStatus.
 	req := &proto.UpRequest{Async: true}
 	if p.ProfileName != "" {
@@ -158,6 +145,27 @@ func (s *Connection) Up(ctx context.Context, p UpParams) error {
 	return nil
 }
 
+// WaitSSOLoginAndUp blocks until the SSO login completes and then brings the
+// connection up, both from the Go side. Keeping the post-login Up here rather
+// than as a frontend continuation is deliberate: during SSO the tray window is
+// hidden and the webview is suspended (macOS App Nap / hidden-window timer
+// throttling), so a frontend-driven Up would not run until the user woke the
+// window (e.g. by hovering the tray icon). Doing it in Go connects the moment
+// the daemon reports SSO success. Returns the authenticated user's email.
+func (s *Connection) WaitSSOLoginAndUp(ctx context.Context, wait WaitSSOParams, up UpParams) (string, error) {
+	email, err := s.waitSSOLogin(ctx, wait)
+	if err != nil {
+		return "", err
+	}
+	if err := ctx.Err(); err != nil {
+		return "", err
+	}
+	if err := s.Up(ctx, up); err != nil {
+		return "", err
+	}
+	return email, nil
+}
+
 func (s *Connection) Down(ctx context.Context) error {
 	cli, err := s.conn.Client()
 	if err != nil {
@@ -217,6 +225,26 @@ func (s *Connection) Logout(ctx context.Context, p LogoutParams) error {
 	return nil
 }
 
+// waitSSOLogin blocks until the daemon reports the SSO login result and returns
+// the authenticated user's email. It is unexported because the frontend drives
+// SSO through the exported WaitSSOLoginAndUp.
+func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string, error) {
+	cli, err := s.conn.Client()
+	if err != nil {
+		return "", err
+	}
+	log.Infof("waiting for SSO login to complete")
+	resp, err := cli.WaitSSOLogin(ctx, &proto.WaitSSOLoginRequest{
+		UserCode: p.UserCode,
+		Hostname: p.Hostname,
+	})
+	if err != nil {
+		return "", s.classifyDaemonError(err)
+	}
+	log.Infof("SSO login completed, daemon reported success")
+	return resp.GetEmail(), nil
+}
+
 // classifyDaemonError maps a gRPC error to a localised ClientError.
 func (s *Connection) classifyDaemonError(err error) *ClientError {
 	return s.classifier.classify(err)

client/ui/services/settings.go

@@ -20,11 +20,12 @@ type MDMFields struct {
 	DisableServerRoutes      bool   `json:"disableServerRoutes"`
 	AllowServerSSH           *bool  `json:"allowServerSSH"`
 	DisableAutoConnect       bool   `json:"disableAutoConnect"`
+	DisableAutostart         bool   `json:"disableAutostart"`
 	BlockInbound             bool   `json:"blockInbound"`
 	DisableMetricsCollection bool   `json:"disableMetricsCollection"`
 	SplitTunnelMode          bool   `json:"splitTunnelMode"`
 	SplitTunnelApps          bool   `json:"splitTunnelApps"`
-	DisableAdvancedView bool `json:"disableAdvancedView"`
+	DisableAdvancedView      bool   `json:"disableAdvancedView"`
 }
 
 type Features struct {

client/wasm/internal/rdp/rdcleanpath.go

@@ -23,7 +23,7 @@ const (
 	RDCleanPathProxyHost   = "rdcleanpath.proxy.local"
 	RDCleanPathProxyScheme = "ws"
 
-	rdpDialTimeout = 15 * time.Second
+	rdpDialTimeout = 30 * time.Second
 
 	GeneralErrorCode = 1
 	WSAETimedOut     = 10060

go.mod

@@ -2,7 +2,7 @@ module github.com/netbirdio/netbird
 
 go 1.25.5
 
-toolchain go1.25.11
+toolchain go1.25.12
 
 require (
 	cunicu.li/go-rosenpass v0.5.42
@@ -19,8 +19,8 @@ require (
 	github.com/spf13/cobra v1.10.2
 	github.com/spf13/pflag v1.0.10
 	github.com/vishvananda/netlink v1.3.1
-	golang.org/x/crypto v0.50.0
-	golang.org/x/sys v0.43.0
+	golang.org/x/crypto v0.54.0
+	golang.org/x/sys v0.47.0
 	golang.zx2c4.com/wireguard v0.0.0-20231211153847-12269c276173
 	golang.zx2c4.com/wireguard/wgctrl v0.0.0-20241231184526-a9ab2273dd10
 	golang.zx2c4.com/wireguard/windows v0.5.3
@@ -101,7 +101,7 @@ require (
 	github.com/quic-go/quic-go v0.55.0
 	github.com/redis/go-redis/v9 v9.7.3
 	github.com/rs/xid v1.3.0
-	github.com/shirou/gopsutil/v3 v3.24.4
+	github.com/shirou/gopsutil/v4 v4.25.8
 	github.com/skratchdot/open-golang v0.0.0-20200116055534-eef842397966
 	github.com/songgao/water v0.0.0-20200317203138-2b4b6d7c09d8
 	github.com/stretchr/testify v1.11.1
@@ -126,11 +126,11 @@ require (
 	goauthentik.io/api/v3 v3.2023051.3
 	golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f
 	golang.org/x/mobile v0.0.0-20251113184115-a159579294ab
-	golang.org/x/mod v0.35.0
-	golang.org/x/net v0.53.0
+	golang.org/x/mod v0.37.0
+	golang.org/x/net v0.56.0
 	golang.org/x/oauth2 v0.36.0
-	golang.org/x/sync v0.20.0
-	golang.org/x/term v0.42.0
+	golang.org/x/sync v0.22.0
+	golang.org/x/term v0.45.0
 	golang.org/x/time v0.15.0
 	google.golang.org/api v0.276.0
 	gopkg.in/yaml.v3 v3.0.1
@@ -295,8 +295,6 @@ require (
 	github.com/prometheus/procfs v0.19.2 // indirect
 	github.com/russellhaering/goxmldsig v1.6.0 // indirect
 	github.com/ryanuber/go-glob v1.0.0 // indirect
-	github.com/shirou/gopsutil/v4 v4.25.8 // indirect
-	github.com/shoenig/go-m1cpu v0.2.1 // indirect
 	github.com/shopspring/decimal v1.4.0 // indirect
 	github.com/spf13/cast v1.10.0 // indirect
 	github.com/stretchr/objx v0.5.2 // indirect
@@ -316,8 +314,8 @@ require (
 	go.opentelemetry.io/otel/trace v1.43.0 // indirect
 	go.uber.org/multierr v1.11.0 // indirect
 	go.yaml.in/yaml/v2 v2.4.3 // indirect
-	golang.org/x/text v0.37.0 // indirect
-	golang.org/x/tools v0.44.0 // indirect
+	golang.org/x/text v0.40.0 // indirect
+	golang.org/x/tools v0.47.0 // indirect
 	golang.zx2c4.com/wintun v0.0.0-20230126152724-0fa3db229ce2 // indirect
 	google.golang.org/genproto/googleapis/api v0.0.0-20260319201613-d00831a3d3e7 // indirect
 	google.golang.org/genproto/googleapis/rpc v0.0.0-20260401024825-9d38bb4040a9 // indirect

go.sum

@@ -271,9 +271,7 @@ github.com/google/go-cmp v0.3.1/go.mod h1:8QqcDgzrUqlUb/G2PQTWiueGozuR1884gddMyw
 github.com/google/go-cmp v0.4.0/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.2/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.5/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
-github.com/google/go-cmp v0.5.6/go.mod h1:v8dTdLbMG2kIc/vJvl+f65V22dbkXbowE6jgT/gNBxE=
 github.com/google/go-cmp v0.5.8/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
-github.com/google/go-cmp v0.5.9/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.6.0/go.mod h1:17dUlkBOakJ0+DkrSSNjCkIjxS6bF9zb3elmeNGIjoY=
 github.com/google/go-cmp v0.7.0 h1:wk8382ETsv4JYUZwIsn6YpYiWiBsYLSJiTsyBybVuN8=
 github.com/google/go-cmp v0.7.0/go.mod h1:pXiqmnSA92OHEEa9HXL2W4E7lf9JzCmGVUdgjX3N/iU=
@@ -417,7 +415,6 @@ github.com/libp2p/go-netroute v0.4.0 h1:sZZx9hyANYUx9PZyqcgE/E1GUG3iEtTZHUEvdtXT
 github.com/libp2p/go-netroute v0.4.0/go.mod h1:Nkd5ShYgSMS5MUKy/MU2T57xFoOKvvLR92Lic48LEyA=
 github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81 h1:J56rFEfUTFT9j9CiRXhi1r8lUJ4W5idG3CiaBZGojNU=
 github.com/lrh3321/ipset-go v0.0.0-20250619021614-54a0a98ace81/go.mod h1:RD8ML/YdXctQ7qbcizZkw5mZ6l8Ogrl1dodBzVJduwI=
-github.com/lufia/plan9stats v0.0.0-20211012122336-39d0f177ccd0/go.mod h1:zJYVVT2jmtg6P3p1VtQj7WsuWi/y4VnjVBn7F8KPB3I=
 github.com/lufia/plan9stats v0.0.0-20240513124658-fba389f38bae h1:dIZY4ULFcto4tAFlj1FYZl8ztUZ13bdq+PLY+NOfbyI=
 github.com/lufia/plan9stats v0.0.0-20240513124658-fba389f38bae/go.mod h1:ilwx/Dta8jXAgpFYFvSWEMwxmbWXyiUHkd5FwyKhb5k=
 github.com/magiconair/properties v1.8.10 h1:s31yESBquKXCV9a/ScB3ESkOjUYYv+X0rg8SYxI99mE=
@@ -569,7 +566,6 @@ github.com/pkg/sftp v1.13.9/go.mod h1:OBN7bVXdstkFFN/gdnHPUb5TE8eb8G1Rp9wCItqjkk
 github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2 h1:Jamvg5psRIccs7FGNTlIRMkT8wgtp5eCXdBlqhYGL6U=
 github.com/pmezard/go-difflib v1.0.1-0.20181226105442-5d4384ee4fb2/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
-github.com/power-devops/perfstat v0.0.0-20210106213030-5aafc221ea8c/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE=
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55 h1:o4JXh1EVt9k/+g42oCprj/FisM4qX9L3sZB3upGN2ZU=
 github.com/power-devops/perfstat v0.0.0-20240221224432-82ca36839d55/go.mod h1:OmDBASR4679mdNQnz2pUhc2G8CO2JrUAVFDRBDP/hJE=
 github.com/pquerna/otp v1.5.0 h1:NMMR+WrmaqXU4EzdGJEE1aUUI0AMRzsp96fFFWNPwxs=
@@ -599,16 +595,8 @@ github.com/russellhaering/goxmldsig v1.6.0/go.mod h1:TrnaquDcYxWXfJrOjeMBTX4mLBe
 github.com/russross/blackfriday/v2 v2.1.0/go.mod h1:+Rmxgy9KzJVeS9/2gXHxylqXiyQDYRxCVz55jmeOWTM=
 github.com/ryanuber/go-glob v1.0.0 h1:iQh3xXAumdQ+4Ufa5b25cRpC5TYKlno6hsv6Cb3pkBk=
 github.com/ryanuber/go-glob v1.0.0/go.mod h1:807d1WSdnB0XRJzKNil9Om6lcp/3a0v4qIHxIXzX/Yc=
-github.com/shirou/gopsutil/v3 v3.24.4 h1:dEHgzZXt4LMNm+oYELpzl9YCqV65Yr/6SfrvgRBtXeU=
-github.com/shirou/gopsutil/v3 v3.24.4/go.mod h1:lTd2mdiOspcqLgAnr9/nGi71NkeMpWKdmhuxm9GusH8=
 github.com/shirou/gopsutil/v4 v4.25.8 h1:NnAsw9lN7587WHxjJA9ryDnqhJpFH6A+wagYWTOH970=
 github.com/shirou/gopsutil/v4 v4.25.8/go.mod h1:q9QdMmfAOVIw7a+eF86P7ISEU6ka+NLgkUxlopV4RwI=
-github.com/shoenig/go-m1cpu v0.1.6/go.mod h1:1JJMcUBvfNwpq05QDQVAnx3gUHr9IYF7GNg9SUEw2VQ=
-github.com/shoenig/go-m1cpu v0.2.1 h1:yqRB4fvOge2+FyRXFkXqsyMoqPazv14Yyy+iyccT2E4=
-github.com/shoenig/go-m1cpu v0.2.1/go.mod h1:KkDOw6m3ZJQAPHbrzkZki4hnx+pDRR1Lo+ldA56wD5w=
-github.com/shoenig/test v0.6.4/go.mod h1:byHiCGXqrVaflBLAMq/srcZIHynQPQgeyvkvXnjqq0k=
-github.com/shoenig/test v1.7.0 h1:eWcHtTXa6QLnBvm0jgEabMRN/uJ4DMV3M8xUGgRkZmk=
-github.com/shoenig/test v1.7.0/go.mod h1:UxJ6u/x2v/TNs/LoLxBNJRV9DiwBBKYxXSyczsBHFoI=
 github.com/shopspring/decimal v1.4.0 h1:bxl37RwXBklmTi0C79JfXCEBD1cqqHt0bbgBAGFp81k=
 github.com/shopspring/decimal v1.4.0/go.mod h1:gawqmDU56v4yIKSwfBSFip1HdCCXN8/+DMd9qYNcwME=
 github.com/sirupsen/logrus v1.9.4 h1:TsZE7l11zFCLZnZ+teH4Umoq5BhEIfIzfRDZ1Uzql2w=
@@ -640,7 +628,6 @@ github.com/stretchr/testify v1.7.1/go.mod h1:6Fq8oRcR53rry900zMqJjRRixrwX3KX962/
 github.com/stretchr/testify v1.8.0/go.mod h1:yNjHg4UonilssWZ8iaSj1OCr/vHnekPRkoO+kdMU+MU=
 github.com/stretchr/testify v1.8.3/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
 github.com/stretchr/testify v1.8.4/go.mod h1:sz/lmYIOXD/1dqDmKjjqLyZ2RngseejIcXlSw2iwfAo=
-github.com/stretchr/testify v1.9.0/go.mod h1:r2ic/lqez/lEtzL7wO/rwa5dbSLXVDPFyf8C91i36aY=
 github.com/stretchr/testify v1.11.1 h1:7s2iGBzp5EwR7/aIZr8ao5+dra3wiQyKjjFuvgVKu7U=
 github.com/stretchr/testify v1.11.1/go.mod h1:wZwfW3scLgRK+23gO65QZefKpKQRnfz6sD981Nm4B6U=
 github.com/testcontainers/testcontainers-go v0.37.0 h1:L2Qc0vkTw2EHWQ08djon0D2uw7Z/PtHS/QzZZ5Ra/hg=
@@ -659,10 +646,8 @@ github.com/ti-mo/netfilter v0.5.2 h1:CTjOwFuNNeZ9QPdRXt1MZFLFUf84cKtiQutNauHWd40
 github.com/ti-mo/netfilter v0.5.2/go.mod h1:Btx3AtFiOVdHReTDmP9AE+hlkOcvIy403u7BXXbWZKo=
 github.com/tinylib/msgp v1.6.3 h1:bCSxiTz386UTgyT1i0MSCvdbWjVW+8sG3PjkGsZQt4s=
 github.com/tinylib/msgp v1.6.3/go.mod h1:RSp0LW9oSxFut3KzESt5Voq4GVWyS+PSulT77roAqEA=
-github.com/tklauser/go-sysconf v0.3.12/go.mod h1:Ho14jnntGE1fpdOqQEEaiKRpvIavV0hSfmBq8nJbHYI=
 github.com/tklauser/go-sysconf v0.3.15 h1:VE89k0criAymJ/Os65CSn1IXaol+1wrsFHEB8Ol49K4=
 github.com/tklauser/go-sysconf v0.3.15/go.mod h1:Dmjwr6tYFIseJw7a3dRLJfsHAMXZ3nEnL/aZY+0IuI4=
-github.com/tklauser/numcpus v0.6.1/go.mod h1:1XfjsgE2zo8GVw7POkMbHENHzVg3GzmoZ9fESEdAacY=
 github.com/tklauser/numcpus v0.10.0 h1:18njr6LDBk1zuna922MgdjQuJFjrdppsZG60sHGfjso=
 github.com/tklauser/numcpus v0.10.0/go.mod h1:BiTKazU708GQTYF4mB+cmlpT2Is1gLk7XVuEeem8LsQ=
 github.com/ugorji/go v1.1.7/go.mod h1:kZn38zHttfInRq0xu/PH0az30d+z6vm202qpg1oXVMw=
@@ -747,8 +732,8 @@ golang.org/x/crypto v0.18.0/go.mod h1:R0j02AL6hcrfOiy9T4ZYp/rcWeMxM3L6QYxlOuEG1m
 golang.org/x/crypto v0.19.0/go.mod h1:Iy9bg/ha4yyC70EfRS8jz+B6ybOBKMaSxLj6P6oBDfU=
 golang.org/x/crypto v0.23.0/go.mod h1:CKFgDieR+mRhux2Lsu27y0fO304Db0wZe70UKqHu0v8=
 golang.org/x/crypto v0.31.0/go.mod h1:kDsLvtWBEx7MV9tJOj9bnXsPbxwJQ6csT/x4KIN4Ssk=
-golang.org/x/crypto v0.50.0 h1:zO47/JPrL6vsNkINmLoo/PH1gcxpls50DNogFvB5ZGI=
-golang.org/x/crypto v0.50.0/go.mod h1:3muZ7vA7PBCE6xgPX7nkzzjiUq87kRItoJQM1Yo8S+Q=
+golang.org/x/crypto v0.54.0 h1:YLIA59K4fiNzHzjnZt2tUJQjQtUWfWbeHBqKtk3eScw=
+golang.org/x/crypto v0.54.0/go.mod h1:KWL8ny2AZdGR2cWmzeHrp2azQPGogOv+HeQaVEXC2dk=
 golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f h1:W3F4c+6OLc6H2lb//N1q4WpJkhzJCK5J6kUi1NTVXfM=
 golang.org/x/exp v0.0.0-20260410095643-746e56fc9e2f/go.mod h1:J1xhfL/vlindoeF/aINzNzt2Bket5bjo9sdOYzOsU80=
 golang.org/x/lint v0.0.0-20200302205851-738671d3881b/go.mod h1:3xt1FjdF8hUf6vQPIChWIBhFzV8gjjsPE/fR3IyQdNY=
@@ -763,8 +748,8 @@ golang.org/x/mod v0.8.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/mod v0.12.0/go.mod h1:iBbtSCu2XBx23ZKBPSOrRkjjQPZFPuis4dIYUhu/chs=
 golang.org/x/mod v0.15.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
 golang.org/x/mod v0.17.0/go.mod h1:hTbmBsO62+eylJbnUtE2MGJUyE7QWk4xUqPFrRgJ+7c=
-golang.org/x/mod v0.35.0 h1:Ww1D637e6Pg+Zb2KrWfHQUnH2dQRLBQyAtpr/haaJeM=
-golang.org/x/mod v0.35.0/go.mod h1:+GwiRhIInF8wPm+4AoT6L0FA1QWAad3OMdTRx4tFYlU=
+golang.org/x/mod v0.37.0 h1:vF1DjpVEshcIqoEaauuHebaLk1O1forxjxBaVn884JQ=
+golang.org/x/mod v0.37.0/go.mod h1:m8S8VeM9r4dzDwjrKO0a1sZP3YjeMamRRlD+fmR2Q/0=
 golang.org/x/net v0.0.0-20180906233101-161cd47e91fd/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
 golang.org/x/net v0.0.0-20190404232315-eb5bcb51f2a3/go.mod h1:t9HGtf8HONx5eT2rtn7q6eTqICYqUVnKs3thJo3Qplg=
 golang.org/x/net v0.0.0-20190603091049-60506f45cf65/go.mod h1:HSz+uSET+XFnRR8LxR5pz3Of3rY3CfYBVs4xY44aLks=
@@ -783,8 +768,8 @@ golang.org/x/net v0.15.0/go.mod h1:idbUs1IY1+zTqbi8yxTbhexhEEk5ur9LInksu6HrEpk=
 golang.org/x/net v0.20.0/go.mod h1:z8BVo6PvndSri0LbOE3hAn0apkU+1YvI6E70E9jsnvY=
 golang.org/x/net v0.21.0/go.mod h1:bIjVDfnllIU7BJ2DNgfnXvpSvtn8VRwhlsaeUTyUS44=
 golang.org/x/net v0.25.0/go.mod h1:JkAGAh7GEvH74S6FOH42FLoXpXbE/aqXSrIQjXgsiwM=
-golang.org/x/net v0.53.0 h1:d+qAbo5L0orcWAr0a9JweQpjXF19LMXJE8Ey7hwOdUA=
-golang.org/x/net v0.53.0/go.mod h1:JvMuJH7rrdiCfbeHoo3fCQU24Lf5JJwT9W3sJFulfgs=
+golang.org/x/net v0.56.0 h1:Rw8j/hFzGvJUZwNBXnAtf5sVDVt+65SK2C7IxCxZt5o=
+golang.org/x/net v0.56.0/go.mod h1:D3Ku6r+V6JROoZK144D2XfMHFcMq/0zSfLelVTCFKec=
 golang.org/x/oauth2 v0.8.0/go.mod h1:yr7u4HXZRm1R1kBWqr/xKNqewf0plRYoB7sla+BCIXE=
 golang.org/x/oauth2 v0.36.0 h1:peZ/1z27fi9hUOFCAZaHyrpWG5lwe0RJEEEeH0ThlIs=
 golang.org/x/oauth2 v0.36.0/go.mod h1:YDBUJMTkDnJS+A4BP4eZBjCqtokkg1hODuPjwiGPO7Q=
@@ -799,8 +784,8 @@ golang.org/x/sync v0.3.0/go.mod h1:FU7BRWz2tNW+3quACPkgCx/L+uEAv1htQ0V83Z9Rj+Y=
 golang.org/x/sync v0.6.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sync v0.7.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
 golang.org/x/sync v0.10.0/go.mod h1:Czt+wKu1gCyEFDUtn0jG5QVvpJ6rzVqr5aXyt9drQfk=
-golang.org/x/sync v0.20.0 h1:e0PTpb7pjO8GAtTs2dQ6jYa5BWYlMuX047Dco/pItO4=
-golang.org/x/sync v0.20.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
+golang.org/x/sync v0.22.0 h1:SZjpbeLmrCk4xhRSZFNZW5gFUeCeFgjekvI/+gfScek=
+golang.org/x/sync v0.22.0/go.mod h1:9xrNwdLfx4jkKbNva9FpL6vEN7evnE43NNNJQ2LF3+0=
 golang.org/x/sys v0.0.0-20180909124046-d0be0721c37e/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190215142949-d0b11bdaac8a/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY=
 golang.org/x/sys v0.0.0-20190412213103-97732733099d/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs=
@@ -834,11 +819,10 @@ golang.org/x/sys v0.11.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.12.0/go.mod h1:oPkhp1MJrh7nUepCBck5+mAzfO9JrbApNNgaTdGDITg=
 golang.org/x/sys v0.16.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.17.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.19.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.20.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
 golang.org/x/sys v0.28.0/go.mod h1:/VUhepiaJMQUp4+oa/7Zr1D23ma6VTLIYjOOTFZPUcA=
-golang.org/x/sys v0.43.0 h1:Rlag2XtaFTxp19wS8MXlJwTvoh8ArU6ezoyFsMyCTNI=
-golang.org/x/sys v0.43.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
+golang.org/x/sys v0.47.0 h1:o7XGOvZQCADBQQ4Y7VNq2dRWQR7JmOUW8Kxx4ZsNgWs=
+golang.org/x/sys v0.47.0/go.mod h1:4GL1E5IUh+htKOUEOaiffhrAeqysfVGipDYzABqnCmw=
 golang.org/x/telemetry v0.0.0-20240228155512-f48c80bd79b2/go.mod h1:TeRTkGYfJXctD9OcfyVLyj2J3IxLnKwHJR8f4D8a3YE=
 golang.org/x/term v0.0.0-20201126162022-7de9c90e9dd1/go.mod h1:bj7SfCRtBDWHUb9snDiAeCFNEtKQo2Wmx5Cou7ajbmo=
 golang.org/x/term v0.0.0-20210927222741-03fcf44c2211/go.mod h1:jbD1KX2456YbFQfuXm/mYQcufACuNUgVhRMnK/tPxf8=
@@ -851,8 +835,8 @@ golang.org/x/term v0.16.0/go.mod h1:yn7UURbUtPyrVJPGPq404EukNFxcm/foM+bV/bfcDsY=
 golang.org/x/term v0.17.0/go.mod h1:lLRBjIVuehSbZlaOtGMbcMncT+aqLLLmKrsjNrUguwk=
 golang.org/x/term v0.20.0/go.mod h1:8UkIAJTvZgivsXaD6/pH6U9ecQzZ45awqEOzuCvwpFY=
 golang.org/x/term v0.27.0/go.mod h1:iMsnZpn0cago0GOrHO2+Y7u7JPn5AylBrcoWkElMTSM=
-golang.org/x/term v0.42.0 h1:UiKe+zDFmJobeJ5ggPwOshJIVt6/Ft0rcfrXZDLWAWY=
-golang.org/x/term v0.42.0/go.mod h1:Dq/D+snpsbazcBG5+F9Q1n2rXV8Ma+71xEjTRufARgY=
+golang.org/x/term v0.45.0 h1:NwWyBmoJCbfTHpxrWoZ9C6/VxOf7ic219I8xZZFdrf0=
+golang.org/x/term v0.45.0/go.mod h1:9aqxs0blBcrm/n0L9QW0aRVD+ktan8ssZromtqJC43w=
 golang.org/x/text v0.3.0/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ=
 golang.org/x/text v0.3.2/go.mod h1:bEr9sfX3Q8Zfm5fL9x+3itogRgK3+ptLWKqgva+5dAk=
 golang.org/x/text v0.3.3/go.mod h1:5Zoc/QRtKVWzQhOtBMvqHzDpF6irO9z98xDceosuGiQ=
@@ -864,8 +848,8 @@ golang.org/x/text v0.13.0/go.mod h1:TvPlkZtksWOMsz7fbANvkp4WM8x/WCo/om8BMLbz+aE=
 golang.org/x/text v0.14.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.15.0/go.mod h1:18ZOQIKpY8NJVqYksKHtTdi31H5itFRjB5/qKTNYzSU=
 golang.org/x/text v0.21.0/go.mod h1:4IBbMaMmOPCJ8SecivzSH54+73PCFmPWxNTLm+vZkEQ=
-golang.org/x/text v0.37.0 h1:Cqjiwd9eSg8e0QAkyCaQTNHFIIzWtidPahFWR83rTrc=
-golang.org/x/text v0.37.0/go.mod h1:a5sjxXGs9hsn/AJVwuElvCAo9v8QYLzvavO5z2PiM38=
+golang.org/x/text v0.40.0 h1:Ub2Z6/xjgF1WrYQz2nuITOEegKFtiIy+rieRJ5lHZKs=
+golang.org/x/text v0.40.0/go.mod h1:hpnzDAfGV753zIKo+wk3u1bVKCGPbrnF7+7LBF/UHVY=
 golang.org/x/time v0.15.0 h1:bbrp8t3bGUeFOx08pvsMYRTCVSMk89u4tKbNOZbp88U=
 golang.org/x/time v0.15.0/go.mod h1:Y4YMaQmXwGQZoFaVFk4YpCt4FLQMYKZe9oeV/f4MSno=
 golang.org/x/tools v0.0.0-20180917221912-90fa682c2a6e/go.mod h1:n7NCudcB/nEzxVGmLbDWY5pfWTLqBcC2KZ6jyYvM4mQ=
@@ -879,8 +863,8 @@ golang.org/x/tools v0.1.12/go.mod h1:hNGJHUnrk76NpqgfD5Aqm5Crs+Hm0VOH/i9J2+nxYbc
 golang.org/x/tools v0.6.0/go.mod h1:Xwgl3UAJ/d3gWutnCtw505GrjyAbvKui8lOU390QaIU=
 golang.org/x/tools v0.13.0/go.mod h1:HvlwmtVNQAhOuCjW7xxvovg8wbNq7LwfXh/k7wXUl58=
 golang.org/x/tools v0.21.1-0.20240508182429-e35e4ccd0d2d/go.mod h1:aiJjzUbINMkxbQROHiO6hDPo2LHcIPhhQsa9DLh0yGk=
-golang.org/x/tools v0.44.0 h1:UP4ajHPIcuMjT1GqzDWRlalUEoY+uzoZKnhOjbIPD2c=
-golang.org/x/tools v0.44.0/go.mod h1:KA0AfVErSdxRZIsOVipbv3rQhVXTnlU6UhKxHd1seDI=
+golang.org/x/tools v0.47.0 h1:7Kn5x/d1svx/PzryTsqeoZN4TZwqeH5pGWjefhLi/1Q=
+golang.org/x/tools v0.47.0/go.mod h1:dFHnyTvFWY212G+h7ZY4Vsp/K3U4/7W9TyVaAul8uCA=
 golang.org/x/xerrors v0.0.0-20190717185122-a985d3407aa7/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191011141410-1b5146add898/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=
 golang.org/x/xerrors v0.0.0-20191204190536-9bdfabe68543/go.mod h1:I/5z698sn9Ka8TeJc9MKroUUfqBBauWjQqLJ2OPfmY0=

management/internals/modules/peers/ephemeral/manager/ephemeral.go

@@ -215,7 +215,7 @@ func (e *EphemeralManager) cleanup(ctx context.Context) {
 	}
 
 	for accountID, peerIDs := range peerIDsPerAccount {
-		log.WithContext(ctx).Tracef("cleanup: deleting %d ephemeral peers for account %s", len(peerIDs), accountID)
+		log.WithContext(ctx).Debugf("cleanup: deleting %d ephemeral peers for account %s: %s", len(peerIDs), accountID, peerIDs)
 		err := e.peersManager.DeletePeers(ctx, accountID, peerIDs, activity.SystemInitiator, true)
 		if err != nil {
 			log.WithContext(ctx).Errorf("failed to delete ephemeral peers: %s", err)

management/internals/modules/peers/manager.go

@@ -184,6 +184,8 @@ func (m *managerImpl) DeletePeers(ctx context.Context, accountID string, peerIDs
 				return err
 			}
 
+			log.WithContext(ctx).Debugf("DeletePeers: deleted peer %s", peerID)
+
 			if !(peer.ProxyMeta.Embedded || peer.Meta.KernelVersion == "wasm") {
 				eventsToStore = append(eventsToStore, func() {
 					m.accountManager.StoreEvent(ctx, userID, peer.ID, accountID, activity.PeerRemovedByUser, peer.EventMeta(dnsDomain))
@@ -224,30 +226,6 @@ func (m *managerImpl) CreateProxyPeer(ctx context.Context, accountID string, pee
 		return nil
 	}
 
-	// Dedupe stale embedded peer records for the same (account, cluster).
-	// The proxy generates a fresh WireGuard keypair on every startup
-	// (proxy/internal/roundtrip/netbird.go), so without this sweep the
-	// prior embedded peer would linger forever — holding its CGNAT IP
-	// allocation, polluting other peers' rosters, and (most visibly)
-	// leaving the synth DNS pointing at the dead address. The
-	// (account, cluster) tuple identifies "the embedded peer for this
-	// proxy instance at this cluster"; any record matching that tuple
-	// with a different pubkey is by definition stale and must go.
-	staleIDs, err := m.findStaleEmbeddedProxyPeers(ctx, accountID, cluster, peerKey)
-	if err != nil {
-		return fmt.Errorf("scan for stale embedded proxy peers: %w", err)
-	}
-	if len(staleIDs) > 0 {
-		// userID="" + checkConnected=false: the deletion is initiated
-		// by management itself on behalf of the freshly-registering
-		// proxy, not by an end user; the stale peer may still be
-		// marked Connected from its prior session, but its session is
-		// dead by definition (its key no longer exists).
-		if err := m.DeletePeers(ctx, accountID, staleIDs, "", false); err != nil {
-			return fmt.Errorf("delete stale embedded proxy peers %v: %w", staleIDs, err)
-		}
-	}
-
 	name := fmt.Sprintf("proxy-%s", xid.New().String())
 	newPeer := &peer.Peer{
 		Ephemeral: true,
@@ -273,29 +251,3 @@ func (m *managerImpl) CreateProxyPeer(ctx context.Context, accountID string, pee
 
 	return nil
 }
-
-// findStaleEmbeddedProxyPeers returns the peer IDs of embedded proxy peer
-// records in accountID that target the same cluster but carry a different
-// WireGuard pubkey than the freshly-registering one. Used by CreateProxyPeer
-// to garbage-collect stale records left behind when the proxy restarts with a
-// regenerated keypair.
-func (m *managerImpl) findStaleEmbeddedProxyPeers(ctx context.Context, accountID, cluster, newKey string) ([]string, error) {
-	account, err := m.store.GetAccount(ctx, accountID)
-	if err != nil {
-		return nil, err
-	}
-	var stale []string
-	for _, p := range account.Peers {
-		if p == nil || !p.ProxyMeta.Embedded {
-			continue
-		}
-		if p.ProxyMeta.Cluster != cluster {
-			continue
-		}
-		if p.Key == newKey {
-			continue
-		}
-		stale = append(stale, p.ID)
-	}
-	return stale, nil
-}

management/internals/server/server.go

@@ -15,7 +15,7 @@ import (
 	"go.opentelemetry.io/otel/metric"
 	"golang.org/x/crypto/acme/autocert"
 	"golang.org/x/net/http2"
-	"golang.org/x/net/http2/h2c"
+	"golang.org/x/net/http2/h2c" //nolint:staticcheck
 	"google.golang.org/grpc"
 
 	"github.com/netbirdio/netbird/encryption"
@@ -382,6 +382,7 @@ func (s *BaseServer) serveGRPCWithHTTP(ctx context.Context, listener net.Listene
 			// the following magic is needed to support HTTP2 without TLS
 			// and still share a single port between gRPC and HTTP APIs
 			h1s := &http.Server{
+				//nolint:staticcheck // h2c also handles the HTTP/1 Upgrade mechanism, which http.Server's UnencryptedHTTP2 does not
 				Handler: h2c.NewHandler(handler, &http2.Server{}),
 			}
 			err = h1s.Serve(listener)

management/internals/shared/grpc/token_mgr.go

@@ -161,6 +161,8 @@ func (m *TimeBasedAuthSecretsManager) SetupRefresh(ctx context.Context, accountI
 		m.turnCancelMap[peerID] = turnCancel
 		go m.refreshTURNTokens(ctx, accountID, peerID, turnCancel)
 		log.WithContext(ctx).Debugf("starting TURN refresh for %s", peerID)
+	} else {
+		log.WithContext(ctx).Debugf("no TURN configuration, skipping TURN refresh for %s", peerID)
 	}
 
 	if m.relayCfg != nil {
@@ -168,6 +170,8 @@ func (m *TimeBasedAuthSecretsManager) SetupRefresh(ctx context.Context, accountI
 		m.relayCancelMap[peerID] = relayCancel
 		go m.refreshRelayTokens(ctx, accountID, peerID, relayCancel)
 		log.WithContext(ctx).Tracef("starting relay refresh for %s", peerID)
+	} else {
+		log.WithContext(ctx).Tracef("no relay configuration, skipping relay refresh for %s", peerID)
 	}
 }
 

management/server/agentnetwork_proxypeer_restart_test.go

@@ -1,199 +0,0 @@
-package server
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/internals/modules/peers"
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
-	agenttypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-	nbpeer "github.com/netbirdio/netbird/management/server/peer"
-	"github.com/netbirdio/netbird/management/server/permissions"
-	"github.com/netbirdio/netbird/management/server/store"
-	"github.com/netbirdio/netbird/management/server/types"
-)
-
-// TestAgentNetwork_ProxyRestart_PropagatesNewPeerAndDropsStale is the no-mock
-// regression guard for the bug the user reported: restarting the proxy creates
-// a fresh embedded peer with a NEW WireGuard public key (the proxy generates
-// the keypair on every startup at proxy/internal/roundtrip/netbird.go:312).
-// The PRIOR embedded peer record is never deleted on management, so the
-// account accumulates a stale peer holding a stale CGNAT IP. Other peers
-// in the account either keep routing to the dead IP, or — if synth DNS
-// picks the wrong record — never see the new IP at all.
-//
-// What this test exercises (no mocks):
-//   - real SQLite test store
-//   - real DefaultAccountManager, network-map controller, peer-update channels
-//   - real peers.Manager.CreateProxyPeer path (the very method the proxy
-//     invokes over gRPC on every startup)
-//   - real agentnetwork.Manager + synth chain so the client receives a
-//     concrete DNS record that must point at the LATEST proxy peer.
-//
-// Pre-fix expected behavior (red): two embedded peers exist after the
-// "restart"; the synth DNS record points at the stale one; the client
-// receives an update reflecting the new peer but the old one lingers.
-// Post-fix expected behavior (green): exactly one embedded peer exists
-// after restart (with the new key) AND the client's network map carries
-// the synth DNS pointing at that new peer's CGNAT IP.
-func TestAgentNetwork_ProxyRestart_PropagatesNewPeerAndDropsStale(t *testing.T) {
-	am, updateManager, err := createManager(t)
-	require.NoError(t, err, "createManager must succeed")
-	ctx := context.Background()
-
-	const (
-		accountID   = "an-restart-acct"
-		adminUserID = "an-restart-admin"
-		groupAID    = "an-restart-grp-A"
-		clusterAddr = "eu.proxy.netbird.io"
-		clientKey   = "BhRPtynAAYRDy08+q4HTMsos8fs4plTP4NOSh7C1ry8="
-		// Two different proxy pubkeys — the "before" and "after" of a
-		// proxy-process restart with fresh-keypair generation.
-		proxyKey1 = "Aaaaa1aaaaYRDy08+q4HTMsos8fs4plTP4NOSh7C1ry8="
-		proxyKey2 = "Bbbbb2bbbbYRDy08+q4HTMsos8fs4plTP4NOSh7C1ry8="
-	)
-
-	// --- Account scaffold ---
-	account := newAccountWithId(ctx, accountID, adminUserID, "an-restart.test", "", "", false)
-	require.NoError(t, am.Store.SaveAccount(ctx, account))
-
-	clientPeer := &nbpeer.Peer{
-		Key:      clientKey,
-		Name:     "an-restart-client",
-		DNSLabel: "an-restart-client",
-		Meta:     nbpeer.PeerSystemMeta{Hostname: "an-restart-client", GoOS: "linux", WtVersion: "development"},
-	}
-	addedClient, _, _, _, err := am.AddPeer(ctx, "", "", adminUserID, clientPeer, false)
-	require.NoError(t, err, "AddPeer for client must succeed")
-	require.NoError(t, am.MarkPeerConnected(ctx, clientKey, accountID, time.Now().UnixNano(), &types.NetworkMap{}),
-		"MarkPeerConnected for the client peer must succeed (affected-peer fan-out skips disconnected peers)")
-
-	// Place the client in group A so the synth policy reaches it.
-	account, err = am.Store.GetAccount(ctx, accountID)
-	require.NoError(t, err)
-	account.Groups[groupAID] = &types.Group{ID: groupAID, Name: "groupA", Peers: []string{addedClient.ID}}
-	require.NoError(t, am.Store.SaveAccount(ctx, account), "SaveAccount must persist group A")
-
-	// --- Real peers + agent-network managers ---
-	permMgr := permissions.NewManager(am.Store)
-	peersMgr := peers.NewManager(am.Store, permMgr)
-	peersMgr.SetAccountManager(am)
-	peersMgr.SetNetworkMapController(am.networkMapController)
-	agentMgr := agentnetwork.NewManager(am.Store, permMgr, am, nil)
-
-	// Subscribe BEFORE any state-mutating call so we don't lose the update
-	// that contains the synth DNS record.
-	clientCh := updateManager.CreateChannel(ctx, addedClient.ID)
-	t.Cleanup(func() { updateManager.CloseChannel(ctx, addedClient.ID) })
-	drain(clientCh)
-
-	// --- First proxy startup: register peer key K1, then mark it
-	// connected. In production the proxy follows CreateProxyPeer with the
-	// regular sync stream which lands on MarkPeerConnected; the synth DNS
-	// path filters out peers that aren't Connected (types/account.go:323),
-	// so without this step no DNS record would be emitted.
-	require.NoError(t, peersMgr.CreateProxyPeer(ctx, accountID, proxyKey1, clusterAddr),
-		"first CreateProxyPeer (proxy startup) must succeed")
-
-	peer1ID, err := am.Store.GetPeerIDByKey(ctx, store.LockingStrengthNone, proxyKey1)
-	require.NoError(t, err, "proxy peer for K1 must be persisted after CreateProxyPeer")
-	require.NotEmpty(t, peer1ID)
-
-	require.NoError(t, am.MarkPeerConnected(ctx, proxyKey1, accountID, time.Now().UnixNano(), &types.NetworkMap{}),
-		"MarkPeerConnected for K1 must succeed")
-
-	account, err = am.Store.GetAccount(ctx, accountID)
-	require.NoError(t, err)
-	proxyIP1 := account.Peers[peer1ID].IP.String()
-	require.NotEmpty(t, proxyIP1, "K1 must have an assigned overlay IP")
-
-	// --- Provider + policy. CreateProvider / CreatePolicy trigger the
-	// agentnetwork reconcile which runs UpdateAccountPeers; the resulting
-	// NetworkMap delivered to the client carries the synth DNS record
-	// pointing at K1's IP. ---
-	provider, err := agentMgr.CreateProvider(ctx, adminUserID, &agenttypes.Provider{
-		AccountID:   accountID,
-		ProviderID:  "openai_api",
-		Name:        "openai-test",
-		UpstreamURL: "https://api.openai.com",
-		APIKey:      "sk-test-key",
-		Enabled:     true,
-		Models:      []agenttypes.ProviderModel{{ID: "gpt-5.4"}},
-	}, clusterAddr)
-	require.NoError(t, err, "CreateProvider must succeed")
-
-	_, err = agentMgr.CreatePolicy(ctx, adminUserID, &agenttypes.Policy{
-		AccountID:              accountID,
-		Name:                   "p1",
-		Enabled:                true,
-		SourceGroups:           []string{groupAID},
-		DestinationProviderIDs: []string{provider.ID},
-	})
-	require.NoError(t, err, "CreatePolicy must succeed")
-
-	settings, err := am.Store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
-	require.NoError(t, err)
-	fqdn := settings.Endpoint()
-
-	rdata1 := awaitZoneRData(clientCh, clusterAddr, fqdn, true)
-	require.Equal(t, proxyIP1, rdata1,
-		"client must receive a synth DNS record pointing at K1's overlay IP after the synth path runs")
-	drain(clientCh)
-
-	// --- Proxy restart: NEW keypair K2, same account, same cluster ---
-	require.NoError(t, peersMgr.CreateProxyPeer(ctx, accountID, proxyKey2, clusterAddr),
-		"second CreateProxyPeer (proxy restart with fresh keypair) must succeed")
-
-	peer2ID, err := am.Store.GetPeerIDByKey(ctx, store.LockingStrengthNone, proxyKey2)
-	require.NoError(t, err, "proxy peer for K2 must be persisted after restart")
-	require.NotEmpty(t, peer2ID)
-
-	require.NoError(t, am.MarkPeerConnected(ctx, proxyKey2, accountID, time.Now().UnixNano(), &types.NetworkMap{}),
-		"MarkPeerConnected for K2 must succeed")
-
-	// In production the agent's sync stream pulls a fresh NetworkMap as
-	// part of its normal reconcile cadence; in this isolated test
-	// MarkPeerConnected's affected-peer fan-out can race the channel-side
-	// buffer in a way that swallows the synth-DNS-bearing update before
-	// our await reads it. Trigger an explicit account-wide fan-out so the
-	// assertion below tests what production actually delivers, not the
-	// in-test buffer race.
-	am.UpdateAccountPeers(ctx, accountID, types.UpdateReason{Resource: types.UpdateResourcePeer, Operation: types.UpdateOperationUpdate})
-
-	account, err = am.Store.GetAccount(ctx, accountID)
-	require.NoError(t, err)
-	proxyIP2 := account.Peers[peer2ID].IP.String()
-	require.NotEmpty(t, proxyIP2, "K2 must have an assigned overlay IP")
-	require.NotEqual(t, proxyIP1, proxyIP2, "K2 must get a different overlay IP than K1 (sanity)")
-
-	// CRITICAL ASSERTION 1: K1 must no longer be in the store. The SqlStore
-	// returns ("", nil) for a missing key rather than NotFound, so assert
-	// on the returned ID being empty.
-	staleID, err := am.Store.GetPeerIDByKey(ctx, store.LockingStrengthNone, proxyKey1)
-	require.NoError(t, err, "GetPeerIDByKey for a missing peer must not error")
-	assert.Empty(t, staleID,
-		"stale embedded proxy peer K1 must be removed when a new embedded peer registers for the same (account, cluster); pre-fix this assertion fails because management never cleans up the prior peer record")
-
-	// CRITICAL ASSERTION 2: exactly one embedded proxy peer remains, and it
-	// is K2.
-	account, err = am.Store.GetAccount(ctx, accountID)
-	require.NoError(t, err)
-	embeddedKeys := []string{}
-	for _, p := range account.Peers {
-		if p.ProxyMeta.Embedded {
-			embeddedKeys = append(embeddedKeys, p.Key)
-		}
-	}
-	assert.Equal(t, []string{proxyKey2}, embeddedKeys,
-		"after a proxy restart exactly one embedded proxy peer should remain — the one with the new key K2")
-
-	// CRITICAL ASSERTION 3: the synth DNS record the client receives now
-	// points at K2's IP, not K1's.
-	rdata2 := awaitZoneRData(clientCh, clusterAddr, fqdn, true)
-	assert.Equal(t, proxyIP2, rdata2,
-		"after proxy restart, the client's synth DNS record must point at the NEW embedded peer's IP, not the stale K1 IP")
-}

management/server/http/handlers/accounts/accounts_handler.go

@@ -286,6 +286,21 @@ func (h *handler) updateAccountRequestSettings(req api.PutApiAccountsAccountIdJS
 	if req.Settings.MetricsPushEnabled != nil {
 		returnSettings.MetricsPushEnabled = *req.Settings.MetricsPushEnabled
 	}
+	if req.Settings.AgentNetworkOnly != nil {
+		returnSettings.AgentNetworkOnly = *req.Settings.AgentNetworkOnly
+	}
+	if req.Settings.DashboardFeatures != nil {
+		returnSettings.DashboardFeatures = &types.DashboardFeatures{
+			AgentNetwork: req.Settings.DashboardFeatures.AgentNetwork,
+		}
+	}
+
+	if returnSettings.AgentNetworkOnly &&
+		(returnSettings.DashboardFeatures == nil ||
+			returnSettings.DashboardFeatures.AgentNetwork == nil ||
+			!*returnSettings.DashboardFeatures.AgentNetwork) {
+		return nil, status.Errorf(status.InvalidArgument, "agent network only mode requires dashboard_features.agent_network to be enabled")
+	}
 
 	return returnSettings, nil
 }
@@ -417,6 +432,7 @@ func toAccountResponse(accountID string, settings *types.Settings, meta *types.A
 		AutoUpdateAlways:                &settings.AutoUpdateAlways,
 		Ipv6EnabledGroups:               &settings.IPv6EnabledGroups,
 		MetricsPushEnabled:              &settings.MetricsPushEnabled,
+		AgentNetworkOnly:                &settings.AgentNetworkOnly,
 		EmbeddedIdpEnabled:              &settings.EmbeddedIdpEnabled,
 		LocalAuthDisabled:               &settings.LocalAuthDisabled,
 		LocalMfaEnabled:                 &settings.LocalMfaEnabled,
@@ -430,6 +446,11 @@ func toAccountResponse(accountID string, settings *types.Settings, meta *types.A
 		networkRangeV6Str := settings.NetworkRangeV6.String()
 		apiSettings.NetworkRangeV6 = &networkRangeV6Str
 	}
+	if settings.DashboardFeatures != nil {
+		apiSettings.DashboardFeatures = &api.AccountDashboardFeatures{
+			AgentNetwork: settings.DashboardFeatures.AgentNetwork,
+		}
+	}
 
 	apiOnboarding := api.AccountOnboarding{
 		OnboardingFlowPending: onboarding.OnboardingFlowPending,

management/server/http/handlers/accounts/accounts_handler_test.go

@@ -130,6 +130,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr(""),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),
@@ -158,6 +159,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr(""),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),
@@ -186,6 +188,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr("latest"),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),
@@ -214,6 +217,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr(""),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),
@@ -242,6 +246,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr(""),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),
@@ -270,6 +275,109 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateAlways:                br(false),
 				AutoUpdateVersion:               sr(""),
 				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
+				EmbeddedIdpEnabled:              br(false),
+				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
+			},
+			expectedArray: false,
+			expectedID:    accountID,
+		},
+		{
+			name:           "PutAccount OK enabling agent_network_only",
+			expectedBody:   true,
+			requestType:    http.MethodPut,
+			requestPath:    "/api/accounts/" + accountID,
+			requestBody:    bytes.NewBufferString("{\"settings\": {\"peer_login_expiration\": 15552000,\"peer_login_expiration_enabled\": true,\"agent_network_only\": true,\"dashboard_features\": {\"agent_network\": true}},\"onboarding\": {\"onboarding_flow_pending\": true,\"signup_form_pending\": true}}"),
+			expectedStatus: http.StatusOK,
+			expectedSettings: api.AccountSettings{
+				PeerLoginExpiration:             15552000,
+				PeerLoginExpirationEnabled:      true,
+				GroupsPropagationEnabled:        br(false),
+				JwtGroupsClaimName:              sr(""),
+				JwtGroupsEnabled:                br(false),
+				JwtAllowGroups:                  &[]string{},
+				RegularUsersViewBlocked:         false,
+				RoutingPeerDnsResolutionEnabled: br(false),
+				LazyConnectionEnabled:           br(false),
+				DnsDomain:                       sr(""),
+				AutoUpdateAlways:                br(false),
+				AutoUpdateVersion:               sr(""),
+				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(true),
+				DashboardFeatures: &api.AccountDashboardFeatures{
+					AgentNetwork: br(true),
+				},
+				EmbeddedIdpEnabled: br(false),
+				LocalAuthDisabled:  br(false),
+				LocalMfaEnabled:    br(false),
+			},
+			expectedArray: false,
+			expectedID:    accountID,
+		},
+		{
+			name:           "PutAccount fails enabling agent_network_only without dashboard_features",
+			expectedBody:   true,
+			requestType:    http.MethodPut,
+			requestPath:    "/api/accounts/" + accountID,
+			requestBody:    bytes.NewBufferString("{\"settings\": {\"peer_login_expiration\": 15552000,\"peer_login_expiration_enabled\": true,\"agent_network_only\": true},\"onboarding\": {\"onboarding_flow_pending\": true,\"signup_form_pending\": true}}"),
+			expectedStatus: http.StatusUnprocessableEntity,
+			expectedArray:  false,
+		},
+		{
+			name:           "PutAccount OK setting dashboard_features agent_network",
+			expectedBody:   true,
+			requestType:    http.MethodPut,
+			requestPath:    "/api/accounts/" + accountID,
+			requestBody:    bytes.NewBufferString("{\"settings\": {\"peer_login_expiration\": 15552000,\"peer_login_expiration_enabled\": true,\"dashboard_features\": {\"agent_network\": true}},\"onboarding\": {\"onboarding_flow_pending\": true,\"signup_form_pending\": true}}"),
+			expectedStatus: http.StatusOK,
+			expectedSettings: api.AccountSettings{
+				PeerLoginExpiration:             15552000,
+				PeerLoginExpirationEnabled:      true,
+				GroupsPropagationEnabled:        br(false),
+				JwtGroupsClaimName:              sr(""),
+				JwtGroupsEnabled:                br(false),
+				JwtAllowGroups:                  &[]string{},
+				RegularUsersViewBlocked:         false,
+				RoutingPeerDnsResolutionEnabled: br(false),
+				LazyConnectionEnabled:           br(false),
+				DnsDomain:                       sr(""),
+				AutoUpdateAlways:                br(false),
+				AutoUpdateVersion:               sr(""),
+				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
+				DashboardFeatures: &api.AccountDashboardFeatures{
+					AgentNetwork: br(true),
+				},
+				EmbeddedIdpEnabled: br(false),
+				LocalAuthDisabled:  br(false),
+				LocalMfaEnabled:    br(false),
+			},
+			expectedArray: false,
+			expectedID:    accountID,
+		},
+		{
+			name:           "PutAccount OK disabling agent_network_only again",
+			expectedBody:   true,
+			requestType:    http.MethodPut,
+			requestPath:    "/api/accounts/" + accountID,
+			requestBody:    bytes.NewBufferString("{\"settings\": {\"peer_login_expiration\": 15552000,\"peer_login_expiration_enabled\": true,\"agent_network_only\": false},\"onboarding\": {\"onboarding_flow_pending\": true,\"signup_form_pending\": true}}"),
+			expectedStatus: http.StatusOK,
+			expectedSettings: api.AccountSettings{
+				PeerLoginExpiration:             15552000,
+				PeerLoginExpirationEnabled:      true,
+				GroupsPropagationEnabled:        br(false),
+				JwtGroupsClaimName:              sr(""),
+				JwtGroupsEnabled:                br(false),
+				JwtAllowGroups:                  &[]string{},
+				RegularUsersViewBlocked:         false,
+				RoutingPeerDnsResolutionEnabled: br(false),
+				LazyConnectionEnabled:           br(false),
+				DnsDomain:                       sr(""),
+				AutoUpdateAlways:                br(false),
+				AutoUpdateVersion:               sr(""),
+				MetricsPushEnabled:              br(false),
+				AgentNetworkOnly:                br(false),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
 				LocalMfaEnabled:                 br(false),

management/server/peer.go

@@ -106,11 +106,13 @@ func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubK
 	}
 	if !updated {
 		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusStale)
-		log.WithContext(ctx).Tracef("peer %s already has a newer session in store, skipping connect", peer.ID)
+		log.WithContext(ctx).Debugf("peer %s already has a newer session in store, skipping connect", peer.ID)
 		return nil
 	}
 	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusApplied)
 
+	log.WithContext(ctx).Debugf("mark peer %s connected", peer.ID)
+
 	if err = am.schedulePeerExpirations(ctx, accountID, peer); err != nil {
 		return err
 	}
@@ -180,12 +182,14 @@ func (am *DefaultAccountManager) MarkPeerDisconnected(ctx context.Context, peerP
 	}
 	if !updated {
 		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusStale)
-		log.WithContext(ctx).Tracef("peer %s session token mismatch on disconnect (token=%d), skipping",
+		log.WithContext(ctx).Debugf("peer %s session token mismatch on disconnect (token=%d), skipping",
 			peer.ID, sessionStartedAt)
 		return nil
 	}
 	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusApplied)
 
+	log.WithContext(ctx).Debugf("mark peer %s disconnected", peer.ID)
+
 	// Symmetric with MarkPeerConnected: when an embedded proxy peer goes
 	// offline, refresh the peers that had synthesized records pointing at
 	// it so they pull the stale entries instead of waiting out TTL.

management/server/store/sql_store.go

@@ -1605,7 +1605,8 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 			settings_jwt_groups_enabled, settings_jwt_groups_claim_name, settings_jwt_allow_groups,
 			settings_routing_peer_dns_resolution_enabled, settings_dns_domain, settings_network_range,
 			settings_network_range_v6, settings_ipv6_enabled_groups, settings_lazy_connection_enabled,
-			settings_local_mfa_enabled, settings_metrics_push_enabled,
+			settings_local_mfa_enabled, settings_metrics_push_enabled, settings_agent_network_only,
+			settings_dashboard_features,
 			-- Embedded ExtraSettings
 			settings_extra_peer_approval_enabled, settings_extra_user_approval_required,
 			settings_extra_integrated_validator, settings_extra_integrated_validator_groups
@@ -1629,6 +1630,8 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 		sLazyConnectionEnabled           sql.NullBool
 		sLocalMFAEnabled                 sql.NullBool
 		sMetricsPushEnabled              sql.NullBool
+		sAgentNetworkOnly                sql.NullBool
+		sDashboardFeatures               sql.NullString
 		sExtraPeerApprovalEnabled        sql.NullBool
 		sExtraUserApprovalRequired       sql.NullBool
 		sExtraIntegratedValidator        sql.NullString
@@ -1651,7 +1654,8 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 		&sJWTGroupsEnabled, &sJWTGroupsClaimName, &sJWTAllowGroups,
 		&sRoutingPeerDNSResolutionEnabled, &sDNSDomain, &sNetworkRange,
 		&sNetworkRangeV6, &sIPv6EnabledGroups, &sLazyConnectionEnabled,
-		&sLocalMFAEnabled, &sMetricsPushEnabled,
+		&sLocalMFAEnabled, &sMetricsPushEnabled, &sAgentNetworkOnly,
+		&sDashboardFeatures,
 		&sExtraPeerApprovalEnabled, &sExtraUserApprovalRequired,
 		&sExtraIntegratedValidator, &sExtraIntegratedValidatorGroups,
 	)
@@ -1720,6 +1724,14 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 	if sMetricsPushEnabled.Valid {
 		account.Settings.MetricsPushEnabled = sMetricsPushEnabled.Bool
 	}
+	if sAgentNetworkOnly.Valid {
+		account.Settings.AgentNetworkOnly = sAgentNetworkOnly.Bool
+	}
+	if sDashboardFeatures.Valid && sDashboardFeatures.String != "" {
+		if err := json.Unmarshal([]byte(sDashboardFeatures.String), &account.Settings.DashboardFeatures); err != nil {
+			log.WithContext(ctx).Warnf("failed to unmarshal dashboard features for account %s: %v", accountID, err)
+		}
+	}
 	if sJWTAllowGroups.Valid {
 		_ = json.Unmarshal([]byte(sJWTAllowGroups.String), &account.Settings.JWTAllowGroups)
 	}

management/server/store/sql_store_test.go

@@ -1245,6 +1245,61 @@ func TestSqlite_CreateAndGetObjectInTransaction(t *testing.T) {
 	assert.NoError(t, err)
 }
 
+func TestSqlStore_SaveAccountPersistsAgentNetworkOnly(t *testing.T) {
+	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", t.TempDir())
+	t.Cleanup(cleanup)
+	require.NoError(t, err)
+
+	accountID := "bf1c8084-ba50-4ce7-9439-34653001fc3b"
+	account, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.False(t, account.Settings.AgentNetworkOnly, "setting should default to false")
+
+	account.Settings.AgentNetworkOnly = true
+	require.NoError(t, store.SaveAccount(context.Background(), account))
+
+	reloaded, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.True(t, reloaded.Settings.AgentNetworkOnly, "setting should survive a save/load round-trip")
+
+	reloaded.Settings.AgentNetworkOnly = false
+	require.NoError(t, store.SaveAccount(context.Background(), reloaded))
+
+	disabled, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.False(t, disabled.Settings.AgentNetworkOnly, "disabling should persist")
+}
+
+func TestSqlStore_SaveAccountPersistsDashboardFeatures(t *testing.T) {
+	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", t.TempDir())
+	t.Cleanup(cleanup)
+	require.NoError(t, err)
+
+	accountID := "bf1c8084-ba50-4ce7-9439-34653001fc3b"
+	account, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.Nil(t, account.Settings.DashboardFeatures, "dashboard features should default to unset")
+
+	agentNetwork := true
+	account.Settings.DashboardFeatures = &types.DashboardFeatures{AgentNetwork: &agentNetwork}
+	require.NoError(t, store.SaveAccount(context.Background(), account))
+
+	reloaded, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.NotNil(t, reloaded.Settings.DashboardFeatures, "dashboard features should survive a save/load round-trip")
+	require.NotNil(t, reloaded.Settings.DashboardFeatures.AgentNetwork, "agent network flag should be set")
+	require.True(t, *reloaded.Settings.DashboardFeatures.AgentNetwork, "agent network flag should persist as true")
+
+	disabled := false
+	reloaded.Settings.DashboardFeatures = &types.DashboardFeatures{AgentNetwork: &disabled}
+	require.NoError(t, store.SaveAccount(context.Background(), reloaded))
+
+	reloadedDisabled, err := store.GetAccount(context.Background(), accountID)
+	require.NoError(t, err)
+	require.NotNil(t, reloadedDisabled.Settings.DashboardFeatures.AgentNetwork, "agent network flag should remain set")
+	require.False(t, *reloadedDisabled.Settings.DashboardFeatures.AgentNetwork, "explicit false should persist")
+}
+
 func TestSqlStore_GetAccountUsers(t *testing.T) {
 	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/extended-store.sql", t.TempDir())
 	t.Cleanup(cleanup)

management/server/types/account.go

@@ -305,7 +305,8 @@ func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZon
 			zone = &nbdns.CustomZone{
 				Domain:           dns.Fqdn(serviceDomainZone),
 				Records:          []nbdns.SimpleRecord{},
-				NonAuthoritative: true,
+				NonAuthoritative:     true,
+				SearchDomainDisabled: true,
 			}
 			zonesByApex[serviceDomainZone] = zone
 		}

management/server/types/settings.go

@@ -76,6 +76,15 @@ type Settings struct {
 	// MetricsPushEnabled globally enables or disables client metrics push for the account
 	MetricsPushEnabled bool `gorm:"default:false"`
 
+	// AgentNetworkOnly limits the dashboard to the Agent Network surface for this account.
+	// Set for accounts created via netbird.ai signups; users can disable it later.
+	AgentNetworkOnly bool `gorm:"default:false"`
+
+	// DashboardFeatures holds per-account dashboard section visibility overrides.
+	// It serializes to a single JSON column so new sections can be added without
+	// a schema change.
+	DashboardFeatures *DashboardFeatures `gorm:"serializer:json"`
+
 	// EmbeddedIdpEnabled indicates if the embedded identity provider is enabled.
 	// This is a runtime-only field, not stored in the database.
 	EmbeddedIdpEnabled bool `gorm:"-"`
@@ -114,6 +123,7 @@ func (s *Settings) Copy() *Settings {
 		AutoUpdateAlways:                s.AutoUpdateAlways,
 		IPv6EnabledGroups:               slices.Clone(s.IPv6EnabledGroups),
 		MetricsPushEnabled:              s.MetricsPushEnabled,
+		AgentNetworkOnly:                s.AgentNetworkOnly,
 		EmbeddedIdpEnabled:              s.EmbeddedIdpEnabled,
 		LocalAuthDisabled:               s.LocalAuthDisabled,
 		LocalMfaEnabled:                 s.LocalMfaEnabled,
@@ -121,9 +131,31 @@ func (s *Settings) Copy() *Settings {
 	if s.Extra != nil {
 		settings.Extra = s.Extra.Copy()
 	}
+	if s.DashboardFeatures != nil {
+		settings.DashboardFeatures = s.DashboardFeatures.Copy()
+	}
 	return settings
 }
 
+// DashboardFeatures holds per-account dashboard section visibility overrides.
+// Nil fields are unset and follow the default dashboard behavior; an explicit
+// value forces that section shown or hidden for the account.
+type DashboardFeatures struct {
+	// AgentNetwork, when set, forces the Agent Network menu shown (true) or
+	// hidden (false) regardless of the deployment feature flag.
+	AgentNetwork *bool `json:"agent_network,omitempty"`
+}
+
+// Copy returns a deep copy of the DashboardFeatures struct.
+func (d *DashboardFeatures) Copy() *DashboardFeatures {
+	c := &DashboardFeatures{}
+	if d.AgentNetwork != nil {
+		v := *d.AgentNetwork
+		c.AgentNetwork = &v
+	}
+	return c
+}
+
 type ExtraSettings struct {
 	// PeerApprovalEnabled enables or disables the need for peers bo be approved by an administrator
 	PeerApprovalEnabled bool

shared/management/http/api/openapi.yml

@@ -375,6 +375,12 @@ components:
           description: Enables or disables client metrics push for all peers in the account
           type: boolean
           example: false
+        agent_network_only:
+          description: Limits the dashboard to the Agent Network surface for this account. Set for accounts created via netbird.ai signups and can be disabled later. Enabling this requires dashboard_features.agent_network to be true in the same request.
+          type: boolean
+          example: false
+        dashboard_features:
+          $ref: '#/components/schemas/AccountDashboardFeatures'
         embedded_idp_enabled:
           description: Indicates whether the embedded identity provider (Dex) is enabled for this account. This is a read-only field.
           type: boolean
@@ -403,6 +409,14 @@ components:
         - regular_users_view_blocked
         - peer_expose_enabled
         - peer_expose_groups
+    AccountDashboardFeatures:
+      description: Per-account dashboard section visibility overrides. Omitted keys follow the default dashboard behavior.
+      type: object
+      properties:
+        agent_network:
+          description: Controls the Agent Network menu for the account regardless of the deployment feature flag. When true the menu is shown, when false it is hidden, and when omitted the default behavior applies. Must be true when agent_network_only is enabled.
+          type: boolean
+          example: true
     AccountExtraSettings:
       type: object
       properties:
@@ -9327,6 +9341,18 @@ paths:
           required: false
           schema:
             type: string
+        - name: source_id
+          in: query
+          description: Filter by source endpoint ID
+          required: false
+          schema:
+            type: string
+        - name: destination_id
+          in: query
+          description: Filter by destination endpoint ID
+          required: false
+          schema:
+            type: string
         - name: protocol
           in: query
           description: Filter by protocol
@@ -10478,7 +10504,7 @@ paths:
         - EDR Intune Integrations
       summary: Delete EDR Intune Integration
       description: Deletes an EDR Intune Integration by its ID.
-      operationId: deleteIntegration
+      operationId: deleteEDRIntuneIntegration
       responses:
         '200':
           description: Integration deleted successfully. Returns an empty object.
@@ -12562,7 +12588,7 @@ paths:
         - Event Streaming Integrations
       summary: Delete Event Streaming Integration
       description: Deletes an event streaming integration by its ID.
-      operationId: deleteIntegration
+      operationId: deleteEventStreamingIntegration
       responses:
         '200':
           description: Integration deleted successfully. Returns an empty object.

shared/management/http/api/types.gen.go

@@ -1612,6 +1612,12 @@ type Account struct {
 	Settings   AccountSettings   `json:"settings"`
 }
 
+// AccountDashboardFeatures Per-account dashboard section visibility overrides. Omitted keys follow the default dashboard behavior.
+type AccountDashboardFeatures struct {
+	// AgentNetwork Controls the Agent Network menu for the account regardless of the deployment feature flag. When true the menu is shown, when false it is hidden, and when omitted the default behavior applies. Must be true when agent_network_only is enabled.
+	AgentNetwork *bool `json:"agent_network,omitempty"`
+}
+
 // AccountExtraSettings defines model for AccountExtraSettings.
 type AccountExtraSettings struct {
 	// NetworkTrafficLogsEnabled Enables or disables network traffic logging. If enabled, all network traffic events from peers will be stored.
@@ -1647,12 +1653,18 @@ type AccountRequest struct {
 
 // AccountSettings defines model for AccountSettings.
 type AccountSettings struct {
+	// AgentNetworkOnly Limits the dashboard to the Agent Network surface for this account. Set for accounts created via netbird.ai signups and can be disabled later. Enabling this requires dashboard_features.agent_network to be true in the same request.
+	AgentNetworkOnly *bool `json:"agent_network_only,omitempty"`
+
 	// AutoUpdateAlways When true, updates are installed automatically in the background. When false, updates require user interaction from the UI.
 	AutoUpdateAlways *bool `json:"auto_update_always,omitempty"`
 
 	// AutoUpdateVersion Set Clients auto-update version. "latest", "disabled", or a specific version (e.g "0.50.1")
 	AutoUpdateVersion *string `json:"auto_update_version,omitempty"`
 
+	// DashboardFeatures Per-account dashboard section visibility overrides. Omitted keys follow the default dashboard behavior.
+	DashboardFeatures *AccountDashboardFeatures `json:"dashboard_features,omitempty"`
+
 	// DnsDomain Allows to define a custom dns domain for the account
 	DnsDomain *string `json:"dns_domain,omitempty"`
 
@@ -5857,6 +5869,12 @@ type GetApiEventsNetworkTrafficParams struct {
 	// ReporterId Filter by reporter ID
 	ReporterId *string `form:"reporter_id,omitempty" json:"reporter_id,omitempty"`
 
+	// SourceId Filter by source endpoint ID
+	SourceId *string `form:"source_id,omitempty" json:"source_id,omitempty"`
+
+	// DestinationId Filter by destination endpoint ID
+	DestinationId *string `form:"destination_id,omitempty" json:"destination_id,omitempty"`
+
 	// Protocol Filter by protocol
 	Protocol *int `form:"protocol,omitempty" json:"protocol,omitempty"`
 

shared/relay/client/dialer/ws/close_generic.go

@@ -0,0 +1,9 @@
+//go:build !js
+
+package ws
+
+// closeConn closes the underlying WebSocket immediately, skipping the close
+// handshake.
+func (c *Conn) closeConn() error {
+	return c.Conn.CloseNow()
+}

shared/relay/client/dialer/ws/close_js.go

@@ -0,0 +1,25 @@
+//go:build js
+
+package ws
+
+import (
+	"github.com/coder/websocket"
+	log "github.com/sirupsen/logrus"
+)
+
+// closeConn closes the browser WebSocket without blocking the caller.
+//
+// The browser close API only accepts codes 1000 and 3000-4999, so CloseNow's
+// 1001 (going away) throws an InvalidAccessError. Close with a valid code
+// waits for the browser close event before returning, which can park the
+// calling goroutine (the relay teardown path holds its mutexes while closing)
+// until the close handshake finishes. Run the close in the background and
+// report success; a teardown close error is not actionable.
+func (c *Conn) closeConn() error {
+	go func() {
+		if err := c.Conn.Close(websocket.StatusNormalClosure, ""); err != nil {
+			log.Debugf("failed to close relay websocket: %v", err)
+		}
+	}()
+	return nil
+}

shared/relay/client/dialer/ws/conn.go

@@ -77,5 +77,5 @@ func (c *Conn) SetDeadline(t time.Time) error {
 }
 
 func (c *Conn) Close() error {
-	return c.Conn.CloseNow()
+	return c.closeConn()
 }

shared/relay/client/early_msg_buffer.go

@@ -10,7 +10,7 @@ import (
 
 const (
 	earlyMsgTTL      = 5 * time.Second
-	earlyMsgCapacity = 1000
+	earlyMsgCapacity = 10000
 )
 
 // earlyMsgBuffer buffers transport messages that arrive before the corresponding

shared/relay/client/manager.go

@@ -30,11 +30,16 @@ type RelayTrack struct {
 	relayClient *Client
 	err         error
 	created     time.Time
+	// ready is closed once the dial started by openConnVia finishes (relayClient
+	// or err is set). Callers reusing a track wait on this instead of the track
+	// lock, so the dial never runs under rt.Lock.
+	ready chan struct{}
 }
 
 func NewRelayTrack() *RelayTrack {
 	return &RelayTrack{
 		created: time.Now(),
+		ready:   make(chan struct{}),
 	}
 }
 
@@ -326,34 +331,24 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
 	// check if already has a connection to the desired relay server
 	m.relayClientsMutex.RLock()
 	rt, ok := m.relayClients[serverAddress]
-	if ok {
-		rt.RLock()
-		m.relayClientsMutex.RUnlock()
-		defer rt.RUnlock()
-		if rt.err != nil {
-			return nil, rt.err
-		}
-		return rt.relayClient.OpenConn(ctx, peerKey)
-	}
 	m.relayClientsMutex.RUnlock()
+	if ok {
+		return m.openConnOnTrack(ctx, rt, peerKey)
+	}
 
 	// if not, establish a new connection but check it again (because changed the lock type) before starting the
 	// connection
 	m.relayClientsMutex.Lock()
 	rt, ok = m.relayClients[serverAddress]
 	if ok {
-		rt.RLock()
 		m.relayClientsMutex.Unlock()
-		defer rt.RUnlock()
-		if rt.err != nil {
-			return nil, rt.err
-		}
-		return rt.relayClient.OpenConn(ctx, peerKey)
+		return m.openConnOnTrack(ctx, rt, peerKey)
 	}
 
-	// create a new relay client and store it in the relayClients map
+	// Publish the track and release the map lock BEFORE dialing, so the dial does
+	// not run under rt.Lock (which would block RelayStates and the cleanup loop
+	// for the full dial). Concurrent callers find this track and wait on rt.ready.
 	rt = NewRelayTrack()
-	rt.Lock()
 	m.relayClients[serverAddress] = rt
 	m.relayClientsMutex.Unlock()
 
@@ -361,8 +356,10 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
 	relayClient.SetTransportFallback(m.transportFallback)
 	err := relayClient.Connect(m.ctx)
 	if err != nil {
+		rt.Lock()
 		rt.err = err
 		rt.Unlock()
+		close(rt.ready)
 		m.relayClientsMutex.Lock()
 		delete(m.relayClients, serverAddress)
 		m.relayClientsMutex.Unlock()
@@ -370,14 +367,34 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
 	}
 	// if connection closed then delete the relay client from the list
 	relayClient.SetOnDisconnectListener(m.onServerDisconnected)
+	rt.Lock()
 	rt.relayClient = relayClient
 	rt.Unlock()
+	close(rt.ready)
 
-	conn, err := relayClient.OpenConn(ctx, peerKey)
-	if err != nil {
-		return nil, err
+	return relayClient.OpenConn(ctx, peerKey)
+}
+
+// openConnOnTrack opens a peer connection through an existing relay track,
+// waiting for the dial started by another openConnVia call to finish. It waits
+// on rt.ready rather than the track lock, so it neither holds nor contends the
+// track lock across the dial.
+func (m *Manager) openConnOnTrack(ctx context.Context, rt *RelayTrack, peerKey string) (net.Conn, error) {
+	select {
+	case <-rt.ready:
+	case <-ctx.Done():
+		return nil, ctx.Err()
 	}
-	return conn, nil
+
+	rt.RLock()
+	defer rt.RUnlock()
+	if rt.err != nil {
+		return nil, rt.err
+	}
+	if rt.relayClient == nil {
+		return nil, ErrRelayClientNotConnected
+	}
+	return rt.relayClient.OpenConn(ctx, peerKey)
 }
 
 func (m *Manager) onServerConnected() {
@@ -476,6 +493,13 @@ func (m *Manager) cleanUpUnusedRelays() {
 			continue
 		}
 
+		// dial still in progress (openConnVia publishes the track before Connect
+		// completes and no longer holds rt.Lock during it), nothing to clean up.
+		if rt.relayClient == nil {
+			rt.Unlock()
+			continue
+		}
+
 		if time.Since(rt.created) <= m.keepUnusedServerTime {
 			rt.Unlock()
 			continue

shared/relay/client/manager_cleanup_test.go

@@ -0,0 +1,60 @@
+package client
+
+import (
+	"context"
+	"net/netip"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+// TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial drives a real, hanging foreign
+// relay dial and asserts cleanUpUnusedRelays does not stall behind it.
+func TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial(t *testing.T) {
+	serverAddr := stallingRelayListener(t)
+
+	mCtx, mCancel := context.WithCancel(context.Background())
+	t.Cleanup(mCancel)
+
+	m := NewManager(mCtx, nil, "alice", 1280)
+
+	dialDone := make(chan struct{})
+	go func() {
+		defer close(dialDone)
+		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+	}()
+
+	// The track appears in the map once the dial is in flight.
+	require.Eventually(t, func() bool {
+		m.relayClientsMutex.RLock()
+		defer m.relayClientsMutex.RUnlock()
+		_, ok := m.relayClients[serverAddr]
+		return ok
+	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+
+	cleanupDone := make(chan struct{})
+	go func() {
+		defer close(cleanupDone)
+		m.cleanUpUnusedRelays()
+	}()
+
+	select {
+	case <-cleanupDone:
+	case <-time.After(2 * time.Second):
+		t.Fatal("cleanUpUnusedRelays blocked on an in-progress relay dial while holding the relay map lock")
+	}
+
+	m.relayClientsMutex.RLock()
+	_, stillTracked := m.relayClients[serverAddr]
+	m.relayClientsMutex.RUnlock()
+	require.True(t, stillTracked, "an in-progress relay dial must not be evicted by cleanup")
+
+	// Release the hanging dial so the goroutine can exit cleanly.
+	mCancel()
+	select {
+	case <-dialDone:
+	case <-time.After(5 * time.Second):
+		t.Fatal("openConnVia did not return after context cancellation")
+	}
+}

shared/relay/client/manager_relaystates_test.go

@@ -0,0 +1,91 @@
+package client
+
+import (
+	"context"
+	"net"
+	"net/netip"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+// stallingRelayListener accepts TCP connections and holds them open without ever
+// responding, so a relay handshake dialed against it blocks until its context is
+// cancelled. It returns the "rel://host:port" URL to dial.
+func stallingRelayListener(t *testing.T) string {
+	t.Helper()
+
+	ln, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+
+	var mu sync.Mutex
+	var conns []net.Conn
+	go func() {
+		for {
+			c, err := ln.Accept()
+			if err != nil {
+				return
+			}
+			mu.Lock()
+			conns = append(conns, c)
+			mu.Unlock()
+		}
+	}()
+	t.Cleanup(func() {
+		_ = ln.Close()
+		mu.Lock()
+		for _, c := range conns {
+			_ = c.Close()
+		}
+		mu.Unlock()
+	})
+
+	return "rel://" + ln.Addr().String()
+}
+
+// TestRelayStates_DoesNotBlockOnRealHangingDial is a regression test for
+// RelayStates() called by a "status -d command" hanging behind an in-progress
+// relay dial.
+func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
+	serverAddr := stallingRelayListener(t)
+
+	mCtx, mCancel := context.WithCancel(context.Background())
+	t.Cleanup(mCancel)
+
+	m := NewManager(mCtx, nil, "alice", 1280)
+
+	dialDone := make(chan struct{})
+	go func() {
+		defer close(dialDone)
+		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+	}()
+
+	require.Eventually(t, func() bool {
+		m.relayClientsMutex.RLock()
+		defer m.relayClientsMutex.RUnlock()
+		_, ok := m.relayClients[serverAddr]
+		return ok
+	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+
+	done := make(chan []RelayConnState, 1)
+	go func() {
+		done <- m.RelayStates()
+	}()
+
+	select {
+	case states := <-done:
+		require.Empty(t, states, "a relay still being dialed carries no state and must be omitted")
+	case <-time.After(2 * time.Second):
+		t.Fatal("RelayStates blocked on a foreign relay whose Connect() is in progress")
+	}
+
+	// Release the hanging dial so the goroutine can exit cleanly.
+	mCancel()
+	select {
+	case <-dialDone:
+	case <-time.After(5 * time.Second):
+		t.Fatal("openConnVia did not return after context cancellation")
+	}
+}

signal/cmd/run.go

@@ -16,7 +16,7 @@ import (
 	"go.opentelemetry.io/otel/metric"
 	"golang.org/x/crypto/acme/autocert"
 	"golang.org/x/net/http2"
-	"golang.org/x/net/http2/h2c"
+	"golang.org/x/net/http2/h2c" //nolint:staticcheck
 
 	"github.com/netbirdio/netbird/shared/metrics"
 
@@ -281,6 +281,7 @@ func serveHTTP(httpListener net.Listener, handler http.Handler) {
 	go func() {
 		// Use h2c to support HTTP/2 without TLS (needed for gRPC)
 		h1s := &http.Server{
+			//nolint:staticcheck // h2c also handles the HTTP/1 Upgrade mechanism, which http.Server's UnencryptedHTTP2 does not
 			Handler: h2c.NewHandler(handler, &http2.Server{}),
 		}
 		err := h1s.Serve(httpListener)