[client] Move metrics saver into its own metricsstages package

Relocate MetricsStages (per-connection metric stage timestamps) out of
the peer package into client/internal/peer/metricsstages.

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/engine.go

@@ -48,6 +48,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/peer/guard"
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -182,7 +183,7 @@ type EngineServices struct {
 type Engine struct {
 	// signal is a Signal Service client
 	signal   signal.Client
-	signaler *peer.Signaler
+	signaler *signaling.Signaler
 	// mgmClient is a Management Service client
 	mgmClient mgm.Client
 	// peerConns is a map that holds all the peers that are known to this peer
@@ -318,7 +319,7 @@ func NewEngine(
 		ctx:                ctx,
 		cancel:             cancel,
 		signal:             services.SignalClient,
-		signaler:           peer.NewSignaler(services.SignalClient, config.WgPrivateKey),
+		signaler:           signaling.NewSignaler(services.SignalClient, config.WgPrivateKey),
 		mgmClient:          services.MgmClient,
 		relayManager:       services.RelayManager,
 		peerStore:          peerstore.NewConnStore(),
@@ -551,7 +552,7 @@ 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)
 		}
@@ -2747,7 +2748,7 @@ func createFile(path string) error {
 	return file.Close()
 }
 
-func convertToOfferAnswer(msg *sProto.Message) (*peer.OfferAnswer, error) {
+func convertToOfferAnswer(msg *sProto.Message) (*signaling.OfferAnswer, error) {
 	remoteCred, err := signal.UnMarshalCredential(msg)
 	if err != nil {
 		return nil, err
@@ -2763,9 +2764,9 @@ func convertToOfferAnswer(msg *sProto.Message) (*peer.OfferAnswer, error) {
 	}
 
 	// Handle optional SessionID
-	var sessionID *peer.ICESessionID
+	var sessionID *icemaker.SessionID
 	if sessionBytes := msg.GetBody().GetSessionId(); sessionBytes != nil {
-		if id, err := peer.ICESessionIDFromBytes(sessionBytes); err != nil {
+		if id, err := icemaker.SessionIDFromBytes(sessionBytes); err != nil {
 			log.Warnf("Invalid session ID in message: %v", err)
 			sessionID = nil // Set to nil if conversion fails
 		} else {
@@ -2775,8 +2776,8 @@ func convertToOfferAnswer(msg *sProto.Message) (*peer.OfferAnswer, error) {
 
 	relayIP := decodeRelayIP(msg.GetBody().GetRelayServerIP())
 
-	offerAnswer := peer.OfferAnswer{
-		IceCredentials: peer.IceCredentials{
+	offerAnswer := signaling.OfferAnswer{
+		IceCredentials: signaling.IceCredentials{
 			UFrag: remoteCred.UFrag,
 			Pwd:   remoteCred.Pwd,
 		},

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_status.go

@@ -1,18 +1,5 @@
 package peer
 
-import (
-	log "github.com/sirupsen/logrus"
-)
-
-const (
-	// StatusIdle indicate the peer is in disconnected state
-	StatusIdle ConnStatus = iota
-	// StatusConnecting indicate the peer is in connecting state
-	StatusConnecting
-	// StatusConnected indicate the peer is in connected state
-	StatusConnected
-)
-
 // connStatusInputs is the primitive-valued snapshot of the state that drives the
 // tri-state connection classification. Extracted so the decision logic can be unit-tested
 // without constructing full Worker/Handshaker objects.
@@ -21,24 +8,7 @@ type connStatusInputs struct {
 	peerUsesRelay       bool // remote peer advertises relay support AND local has relay
 	relayConnected      bool // statusRelay reports Connected (independent of whether peer uses relay)
 	remoteSupportsICE   bool // remote peer sent ICE credentials
-	iceWorkerCreated    bool // local WorkerICE exists (false in force-relay mode)
+	iceWorkerCreated    bool // local ICE worker exists (false in force-relay mode)
 	iceStatusConnecting bool // statusICE is anything other than Disconnected
 	iceInProgress       bool // a negotiation is currently in flight
 }
-
-// ConnStatus describe the status of a peer's connection
-type ConnStatus int32
-
-func (s ConnStatus) String() string {
-	switch s {
-	case StatusConnecting:
-		return "Connecting"
-	case StatusConnected:
-		return "Connected"
-	case StatusIdle:
-		return "Idle"
-	default:
-		log.Errorf("unknown status: %d", s)
-		return "INVALID_PEER_CONNECTION_STATUS"
-	}
-}

client/internal/peer/conn_test.go

@@ -3,27 +3,33 @@ package peer
 import (
 	"context"
 	"fmt"
+	"net/netip"
 	"os"
 	"testing"
 	"time"
 
+	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 
 	"github.com/netbirdio/netbird/client/iface"
-	"github.com/netbirdio/netbird/client/internal/peer/dispatcher"
 	"github.com/netbirdio/netbird/client/internal/peer/guard"
 	"github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/internal/peer/metricsstages"
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
+	"github.com/netbirdio/netbird/client/internal/peer/status"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/util"
 )
 
-var testDispatcher = dispatcher.NewConnectionDispatcher()
-
 var connConf = ConnConfig{
 	Key:         "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
 	LocalKey:    "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
 	Timeout:     time.Second,
 	LocalWgPort: 51820,
+	WgConfig: WgConfig{
+		AllowedIps: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
+	},
 	ICEConfig: ice.Config{
 		InterfaceBlackList: nil,
 	},
@@ -51,92 +57,37 @@ func TestConn_GetKey(t *testing.T) {
 	swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
 
 	sd := ServiceDependencies{
-		SrWatcher:          swWatcher,
-		PeerConnDispatcher: testDispatcher,
+		SrWatcher: swWatcher,
 	}
 	conn, err := NewConn(connConf, sd)
-	if err != nil {
-		return
-	}
+	require.NoError(t, err)
 
 	got := conn.GetKey()
 
 	assert.Equal(t, got, connConf.Key, "they should be equal")
 }
 
-func TestConn_OnRemoteOffer(t *testing.T) {
+// TestConn_DiscardMessagesWhenNotOpened: signal messages posted to a not yet
+// opened connection must be discarded without blocking or panicking.
+func TestConn_DiscardMessagesWhenNotOpened(t *testing.T) {
 	swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
 	sd := ServiceDependencies{
-		StatusRecorder:     NewRecorder("https://mgm"),
-		SrWatcher:          swWatcher,
-		PeerConnDispatcher: testDispatcher,
+		StatusRecorder: status.NewRecorder("https://mgm"),
+		SrWatcher:      swWatcher,
 	}
 	conn, err := NewConn(connConf, sd)
-	if err != nil {
-		return
-	}
+	require.NoError(t, err)
 
-	onNewOfferChan := make(chan struct{})
-
-	conn.handshaker.AddRelayListener(func(remoteOfferAnswer *OfferAnswer) {
-		onNewOfferChan <- struct{}{}
-	})
-
-	conn.OnRemoteOffer(OfferAnswer{
-		IceCredentials: IceCredentials{
+	offerAnswer := signaling.OfferAnswer{
+		IceCredentials: signaling.IceCredentials{
 			UFrag: "test",
 			Pwd:   "test",
 		},
-		WgListenPort: 0,
-		Version:      "",
-	})
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	select {
-	case <-onNewOfferChan:
-		// success
-	case <-ctx.Done():
-		t.Error("expected to receive a new offer notification, but timed out")
-	}
-}
-
-func TestConn_OnRemoteAnswer(t *testing.T) {
-	swWatcher := guard.NewSRWatcher(nil, nil, nil, connConf.ICEConfig)
-	sd := ServiceDependencies{
-		StatusRecorder:     NewRecorder("https://mgm"),
-		SrWatcher:          swWatcher,
-		PeerConnDispatcher: testDispatcher,
-	}
-	conn, err := NewConn(connConf, sd)
-	if err != nil {
-		return
-	}
-
-	onNewOfferChan := make(chan struct{})
-
-	conn.handshaker.AddRelayListener(func(remoteOfferAnswer *OfferAnswer) {
-		onNewOfferChan <- struct{}{}
-	})
-
-	conn.OnRemoteAnswer(OfferAnswer{
-		IceCredentials: IceCredentials{
-			UFrag: "test",
-			Pwd:   "test",
-		},
-		WgListenPort: 0,
-		Version:      "",
-	})
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	select {
-	case <-onNewOfferChan:
-		// success
-	case <-ctx.Done():
-		t.Error("expected to receive a new offer notification, but timed out")
 	}
+	conn.OnRemoteOffer(offerAnswer)
+	conn.OnRemoteAnswer(offerAnswer)
+	conn.OnRemoteCandidate(nil, nil)
+	conn.Close(false)
 }
 
 func TestConn_presharedKey(t *testing.T) {
@@ -304,3 +255,84 @@ 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.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.handleWGTimeout()
+	}
+	assert.Empty(t, disconnected, "escalation must not fire below the threshold")
+
+	conn.handleWGTimeout()
+	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.handleWGTimeout()
+	}
+	assert.Len(t, disconnected, 1, "escalation must restart counting after firing")
+
+	conn.handleWGTimeout()
+	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.handleWGTimeout()
+	}
+	conn.handleWGCheckSuccess()
+
+	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
+		conn.handleWGTimeout()
+	}
+	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.handleWGTimeout()
+	}
+	assert.Empty(t, disconnected, "escalation must be limited to rosenpass connections")
+}

client/internal/peer/dispatcher/dispatcher.go

@@ -1,52 +0,0 @@
-package dispatcher
-
-import (
-	"sync"
-
-	"github.com/netbirdio/netbird/client/internal/peer/id"
-)
-
-type ConnectionListener struct {
-	OnConnected    func(peerID id.ConnID)
-	OnDisconnected func(peerID id.ConnID)
-}
-
-type ConnectionDispatcher struct {
-	listeners map[*ConnectionListener]struct{}
-	mu        sync.Mutex
-}
-
-func NewConnectionDispatcher() *ConnectionDispatcher {
-	return &ConnectionDispatcher{
-		listeners: make(map[*ConnectionListener]struct{}),
-	}
-}
-
-func (e *ConnectionDispatcher) AddListener(listener *ConnectionListener) {
-	e.mu.Lock()
-	defer e.mu.Unlock()
-	e.listeners[listener] = struct{}{}
-}
-
-func (e *ConnectionDispatcher) RemoveListener(listener *ConnectionListener) {
-	e.mu.Lock()
-	defer e.mu.Unlock()
-
-	delete(e.listeners, listener)
-}
-
-func (e *ConnectionDispatcher) NotifyConnected(peerConnID id.ConnID) {
-	e.mu.Lock()
-	defer e.mu.Unlock()
-	for listener := range e.listeners {
-		listener.OnConnected(peerConnID)
-	}
-}
-
-func (e *ConnectionDispatcher) NotifyDisconnected(peerConnID id.ConnID) {
-	e.mu.Lock()
-	defer e.mu.Unlock()
-	for listener := range e.listeners {
-		listener.OnDisconnected(peerConnID)
-	}
-}

client/internal/peer/event.go

@@ -0,0 +1,69 @@
+package peer
+
+import (
+	"time"
+
+	"github.com/pion/ice/v4"
+
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
+	"github.com/netbirdio/netbird/client/internal/peer/worker"
+	"github.com/netbirdio/netbird/route"
+)
+
+// event is a message processed by the Conn event loop. All mutable Conn state
+// is owned by that loop; producers deliver events through the mailbox and
+// never mutate Conn state directly.
+type event any
+
+// evClose asks the event loop to tear down the connection. done is closed
+// once the teardown finished.
+type evClose struct {
+	signalToRemote bool
+	done           chan struct{}
+}
+
+type evRemoteOffer struct {
+	offer signaling.OfferAnswer
+}
+
+type evRemoteAnswer struct {
+	answer signaling.OfferAnswer
+}
+
+type evRemoteCandidate struct {
+	candidate ice.Candidate
+	haRoutes  route.HAMap
+}
+
+type evICEReady struct {
+	priority worker.ConnPriority
+	info     worker.ICEConnInfo
+}
+
+type evICEDown struct {
+	sessionChanged bool
+}
+
+type evRelayReady struct {
+	info worker.RelayConnInfo
+}
+
+type evRelayDown struct{}
+
+// evRelayDialDone reports that the relay dial helper goroutine finished,
+// successfully or not, so the loop may dispatch a pending offer.
+type evRelayDialDone struct{}
+
+type evWGTimeout struct{}
+
+// evWGHandshake reports the first WireGuard handshake of the current watcher run.
+type evWGHandshake struct {
+	when time.Time
+}
+
+// evWGCheckOK reports a watcher check that observed a fresh handshake,
+// including handshakes of connections that were already up.
+type evWGCheckOK struct{}
+
+// evGuardTick asks the loop to send a new offer to restore connectivity.
+type evGuardTick struct{}

client/internal/peer/guard/ice_monitor.go

@@ -21,8 +21,6 @@ const (
 )
 
 type ICEMonitor struct {
-	ReconnectCh chan struct{}
-
 	iFaceDiscover stdnet.ExternalIFaceDiscover
 	iceConfig     icemaker.Config
 	tickerPeriod  time.Duration
@@ -34,7 +32,6 @@ type ICEMonitor struct {
 func NewICEMonitor(iFaceDiscover stdnet.ExternalIFaceDiscover, config icemaker.Config, period time.Duration) *ICEMonitor {
 	log.Debugf("prepare ICE monitor with period: %s", period)
 	cm := &ICEMonitor{
-		ReconnectCh:   make(chan struct{}, 1),
 		iFaceDiscover: iFaceDiscover,
 		iceConfig:     config,
 		tickerPeriod:  period,

client/internal/peer/handshaker.go

@@ -1,246 +0,0 @@
-package peer
-
-import (
-	"context"
-	"errors"
-	"net/netip"
-	"sync"
-	"sync/atomic"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/version"
-)
-
-var (
-	ErrSignalIsNotReady = errors.New("signal is not ready")
-)
-
-// IceCredentials ICE protocol credentials struct
-type IceCredentials struct {
-	UFrag string
-	Pwd   string
-}
-
-// OfferAnswer represents a session establishment offer or answer
-type OfferAnswer struct {
-	IceCredentials IceCredentials
-	// WgListenPort is a remote WireGuard listen port.
-	// This field is used when establishing a direct WireGuard connection without any proxy.
-	// We can set the remote peer's endpoint with this port.
-	WgListenPort int
-
-	// Version of NetBird Agent
-	Version string
-	// RosenpassPubKey is the Rosenpass public key of the remote peer when receiving this message
-	// This value is the local Rosenpass server public key when sending the message
-	RosenpassPubKey []byte
-	// RosenpassAddr is the Rosenpass server address (IP:port) of the remote peer when receiving this message
-	// This value is the local Rosenpass server address when sending the message
-	RosenpassAddr string
-
-	// relay server address
-	RelaySrvAddress string
-	// RelaySrvIP is the IP the remote peer is connected to on its
-	// relay server. Used as a dial target if DNS for RelaySrvAddress
-	// fails. Zero value if the peer did not advertise an IP.
-	RelaySrvIP netip.Addr
-	// SessionID is the unique identifier of the session, used to discard old messages
-	SessionID *ICESessionID
-}
-
-func (o *OfferAnswer) hasICECredentials() bool {
-	return o.IceCredentials.UFrag != "" && o.IceCredentials.Pwd != ""
-}
-
-type Handshaker struct {
-	mu            sync.Mutex
-	log           *log.Entry
-	config        ConnConfig
-	signaler      *Signaler
-	ice           *WorkerICE
-	relay         *WorkerRelay
-	metricsStages *MetricsStages
-	// relayListener is not blocking because the listener is using a goroutine to process the messages
-	// and it will only keep the latest message if multiple offers are received in a short time
-	// this is to avoid blocking the handshaker if the listener is doing some heavy processing
-	// and also to avoid processing old offers if multiple offers are received in a short time
-	// the listener will always process the latest offer
-	relayListener *AsyncOfferListener
-	iceListener   func(remoteOfferAnswer *OfferAnswer)
-
-	// remoteICESupported tracks whether the remote peer includes ICE credentials in its offers/answers.
-	// When false, the local side skips ICE listener dispatch and suppresses ICE credentials in responses.
-	remoteICESupported atomic.Bool
-
-	// remoteOffersCh is a channel used to wait for remote credentials to proceed with the connection
-	remoteOffersCh chan OfferAnswer
-	// remoteAnswerCh is a channel used to wait for remote credentials answer (confirmation of our offer) to proceed with the connection
-	remoteAnswerCh chan OfferAnswer
-}
-
-func NewHandshaker(log *log.Entry, config ConnConfig, signaler *Signaler, ice *WorkerICE, relay *WorkerRelay, metricsStages *MetricsStages) *Handshaker {
-	h := &Handshaker{
-		log:            log,
-		config:         config,
-		signaler:       signaler,
-		ice:            ice,
-		relay:          relay,
-		metricsStages:  metricsStages,
-		remoteOffersCh: make(chan OfferAnswer),
-		remoteAnswerCh: make(chan OfferAnswer),
-	}
-	// assume remote supports ICE until we learn otherwise from received offers
-	h.remoteICESupported.Store(ice != nil)
-	return h
-}
-
-func (h *Handshaker) RemoteICESupported() bool {
-	return h.remoteICESupported.Load()
-}
-
-func (h *Handshaker) AddRelayListener(offer func(remoteOfferAnswer *OfferAnswer)) {
-	h.relayListener = NewAsyncOfferListener(offer)
-}
-
-func (h *Handshaker) AddICEListener(offer func(remoteOfferAnswer *OfferAnswer)) {
-	h.iceListener = offer
-}
-
-func (h *Handshaker) Listen(ctx context.Context) {
-	for {
-		select {
-		case remoteOfferAnswer := <-h.remoteOffersCh:
-			h.log.Infof("received offer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials())
-
-			// Record signaling received for reconnection attempts
-			if h.metricsStages != nil {
-				h.metricsStages.RecordSignalingReceived()
-			}
-
-			h.updateRemoteICEState(&remoteOfferAnswer)
-
-			if h.relayListener != nil {
-				h.relayListener.Notify(&remoteOfferAnswer)
-			}
-
-			if h.iceListener != nil && h.RemoteICESupported() {
-				h.iceListener(&remoteOfferAnswer)
-			}
-
-			if err := h.sendAnswer(); err != nil {
-				h.log.Errorf("failed to send remote offer confirmation: %s", err)
-				continue
-			}
-		case remoteOfferAnswer := <-h.remoteAnswerCh:
-			h.log.Infof("received answer, running version %s, remote WireGuard listen port %d, session id: %s, remote ICE supported: %t", remoteOfferAnswer.Version, remoteOfferAnswer.WgListenPort, remoteOfferAnswer.SessionIDString(), remoteOfferAnswer.hasICECredentials())
-
-			// Record signaling received for reconnection attempts
-			if h.metricsStages != nil {
-				h.metricsStages.RecordSignalingReceived()
-			}
-
-			h.updateRemoteICEState(&remoteOfferAnswer)
-
-			if h.relayListener != nil {
-				h.relayListener.Notify(&remoteOfferAnswer)
-			}
-
-			if h.iceListener != nil && h.RemoteICESupported() {
-				h.iceListener(&remoteOfferAnswer)
-			}
-		case <-ctx.Done():
-			h.log.Infof("stop listening for remote offers and answers")
-			return
-		}
-	}
-}
-
-func (h *Handshaker) SendOffer() error {
-	h.mu.Lock()
-	defer h.mu.Unlock()
-	return h.sendOffer()
-}
-
-// OnRemoteOffer handles an offer from the remote peer and returns true if the message was accepted, false otherwise
-// doesn't block, discards the message if connection wasn't ready
-func (h *Handshaker) OnRemoteOffer(offer OfferAnswer) {
-	select {
-	case h.remoteOffersCh <- offer:
-		return
-	default:
-		h.log.Warnf("skipping remote offer message because receiver not ready")
-		// connection might not be ready yet to receive so we ignore the message
-		return
-	}
-}
-
-// OnRemoteAnswer handles an offer from the remote peer and returns true if the message was accepted, false otherwise
-// doesn't block, discards the message if connection wasn't ready
-func (h *Handshaker) OnRemoteAnswer(answer OfferAnswer) {
-	select {
-	case h.remoteAnswerCh <- answer:
-		return
-	default:
-		// connection might not be ready yet to receive so we ignore the message
-		h.log.Warnf("skipping remote answer message because receiver not ready")
-		return
-	}
-}
-
-// sendOffer prepares local user credentials and signals them to the remote peer
-func (h *Handshaker) sendOffer() error {
-	if !h.signaler.Ready() {
-		return ErrSignalIsNotReady
-	}
-
-	offer := h.buildOfferAnswer()
-	h.log.Debugf("sending offer with serial: %s", offer.SessionIDString())
-
-	return h.signaler.SignalOffer(offer, h.config.Key)
-}
-
-func (h *Handshaker) sendAnswer() error {
-	answer := h.buildOfferAnswer()
-	h.log.Debugf("sending answer with serial: %s", answer.SessionIDString())
-
-	return h.signaler.SignalAnswer(answer, h.config.Key)
-}
-
-func (h *Handshaker) buildOfferAnswer() OfferAnswer {
-	answer := OfferAnswer{
-		WgListenPort:    h.config.LocalWgPort,
-		Version:         version.NetbirdVersion(),
-		RosenpassPubKey: h.config.RosenpassConfig.PubKey,
-		RosenpassAddr:   h.config.RosenpassConfig.Addr,
-	}
-
-	if h.ice != nil && h.RemoteICESupported() {
-		uFrag, pwd := h.ice.GetLocalUserCredentials()
-		sid := h.ice.SessionID()
-		answer.IceCredentials = IceCredentials{uFrag, pwd}
-		answer.SessionID = &sid
-	}
-
-	if addr, ip, err := h.relay.RelayInstanceAddress(); err == nil {
-		answer.RelaySrvAddress = addr
-		answer.RelaySrvIP = ip
-	}
-
-	return answer
-}
-
-func (h *Handshaker) updateRemoteICEState(offer *OfferAnswer) {
-	hasICE := offer.hasICECredentials()
-	prev := h.remoteICESupported.Swap(hasICE)
-	if prev != hasICE {
-		if hasICE {
-			h.log.Infof("remote peer started sending ICE credentials")
-		} else {
-			h.log.Infof("remote peer stopped sending ICE credentials")
-			if h.ice != nil {
-				h.ice.Close()
-			}
-		}
-	}
-}

client/internal/peer/handshaker_listener.go

@@ -1,62 +0,0 @@
-package peer
-
-import (
-	"sync"
-)
-
-type callbackFunc func(remoteOfferAnswer *OfferAnswer)
-
-func (oa *OfferAnswer) SessionIDString() string {
-	if oa.SessionID == nil {
-		return "unknown"
-	}
-	return oa.SessionID.String()
-}
-
-type AsyncOfferListener struct {
-	fn      callbackFunc
-	running bool
-	latest  *OfferAnswer
-	mu      sync.Mutex
-}
-
-func NewAsyncOfferListener(fn callbackFunc) *AsyncOfferListener {
-	return &AsyncOfferListener{
-		fn: fn,
-	}
-}
-
-func (o *AsyncOfferListener) Notify(remoteOfferAnswer *OfferAnswer) {
-	o.mu.Lock()
-	defer o.mu.Unlock()
-
-	// Store the latest offer
-	o.latest = remoteOfferAnswer
-
-	// If already running, the running goroutine will pick up this latest value
-	if o.running {
-		return
-	}
-
-	// Start processing
-	o.running = true
-
-	// Process in a goroutine to avoid blocking the caller
-	go func(remoteOfferAnswer *OfferAnswer) {
-		for {
-			o.fn(remoteOfferAnswer)
-
-			o.mu.Lock()
-			if o.latest == nil {
-				// No more work to do
-				o.running = false
-				o.mu.Unlock()
-				return
-			}
-			remoteOfferAnswer = o.latest
-			// Clear the latest to mark it as being processed
-			o.latest = nil
-			o.mu.Unlock()
-		}
-	}(remoteOfferAnswer)
-}

client/internal/peer/handshaker_listener_test.go

@@ -1,39 +0,0 @@
-package peer
-
-import (
-	"testing"
-	"time"
-)
-
-func Test_newOfferListener(t *testing.T) {
-	dummyOfferAnswer := &OfferAnswer{}
-	runChan := make(chan struct{}, 10)
-
-	longRunningFn := func(remoteOfferAnswer *OfferAnswer) {
-		time.Sleep(1 * time.Second)
-		runChan <- struct{}{}
-	}
-
-	hl := NewAsyncOfferListener(longRunningFn)
-
-	hl.Notify(dummyOfferAnswer)
-	hl.Notify(dummyOfferAnswer)
-	hl.Notify(dummyOfferAnswer)
-
-	// Wait for exactly 2 callbacks
-	for i := 0; i < 2; i++ {
-		select {
-		case <-runChan:
-		case <-time.After(3 * time.Second):
-			t.Fatal("Timeout waiting for callback")
-		}
-	}
-
-	// Verify no additional callbacks happen
-	select {
-	case <-runChan:
-		t.Fatal("Unexpected additional callback")
-	case <-time.After(100 * time.Millisecond):
-		t.Log("Correctly received exactly 2 callbacks")
-	}
-}

client/internal/peer/ice/session_id.go

@@ -1,4 +1,4 @@
-package peer
+package ice
 
 import (
 	"crypto/rand"
@@ -9,26 +9,26 @@ import (
 
 const sessionIDSize = 5
 
-type ICESessionID string
+type SessionID string
 
-// NewICESessionID generates a new session ID for distinguishing sessions
-func NewICESessionID() (ICESessionID, error) {
+// NewSessionID generates a new session ID for distinguishing sessions
+func NewSessionID() (SessionID, error) {
 	b := make([]byte, sessionIDSize)
 	if _, err := io.ReadFull(rand.Reader, b); err != nil {
 		return "", fmt.Errorf("failed to generate session ID: %w", err)
 	}
-	return ICESessionID(hex.EncodeToString(b)), nil
+	return SessionID(hex.EncodeToString(b)), nil
 }
 
-func ICESessionIDFromBytes(b []byte) (ICESessionID, error) {
+func SessionIDFromBytes(b []byte) (SessionID, error) {
 	if len(b) != sessionIDSize {
 		return "", fmt.Errorf("invalid session ID length: %d", len(b))
 	}
-	return ICESessionID(hex.EncodeToString(b)), nil
+	return SessionID(hex.EncodeToString(b)), nil
 }
 
 // Bytes returns the raw bytes of the session ID for protobuf serialization
-func (id ICESessionID) Bytes() ([]byte, error) {
+func (id SessionID) Bytes() ([]byte, error) {
 	if len(id) == 0 {
 		return nil, fmt.Errorf("ICE session ID is empty")
 	}
@@ -42,6 +42,6 @@ func (id ICESessionID) Bytes() ([]byte, error) {
 	return b, nil
 }
 
-func (id ICESessionID) String() string {
+func (id SessionID) String() string {
 	return string(id)
 }

client/internal/peer/iface.go

@@ -1,22 +0,0 @@
-package peer
-
-import (
-	"net"
-	"net/netip"
-	"time"
-
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-
-	"github.com/netbirdio/netbird/client/iface/configurer"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
-	"github.com/netbirdio/netbird/client/iface/wgproxy"
-)
-
-type WGIface interface {
-	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
-	RemovePeer(peerKey string) error
-	GetStats() (map[string]configurer.WGStats, error)
-	GetProxy() wgproxy.Proxy
-	Address() wgaddr.Address
-	RemoveEndpointAddress(key string) error
-}

client/internal/peer/listener.go

@@ -1,11 +0,0 @@
-package peer
-
-// Listener is a callback type about the NetBird network connection state
-type Listener interface {
-	OnConnected()
-	OnDisconnected()
-	OnConnecting()
-	OnDisconnecting()
-	OnAddressChanged(string, string)
-	OnPeersListChanged(int)
-}

client/internal/peer/mailbox.go

@@ -0,0 +1,116 @@
+package peer
+
+import (
+	"sync"
+)
+
+// maxQueuedCandidates bounds the remote candidate queue; on overflow the
+// oldest candidate is dropped. Lost candidates are recovered by the next
+// offer exchange triggered by the guard.
+const maxQueuedCandidates = 128
+
+// mailbox is the coalescing inbox of the Conn event loop. Posting never
+// blocks. Per message kind either the latest value wins (offer, answer,
+// guard tick), the values queue in bounded FIFO order (candidates) or in
+// unbounded FIFO order (lifecycle and transport state changes, which are
+// low-volume and must not be lost). A new offer flushes the queued
+// candidates because they belong to the superseded session.
+type mailbox struct {
+	mu     sync.Mutex
+	closed bool
+
+	lifecycle  []event
+	transport  []event
+	offer      *evRemoteOffer
+	answer     *evRemoteAnswer
+	candidates []evRemoteCandidate
+	guardTick  bool
+
+	wake chan struct{}
+}
+
+func newMailbox() *mailbox {
+	return &mailbox{
+		wake: make(chan struct{}, 1),
+	}
+}
+
+// post stores the event and wakes the loop. It reports false if the mailbox
+// is already closed and the event was not accepted.
+func (m *mailbox) post(ev event) bool {
+	m.mu.Lock()
+	if m.closed {
+		m.mu.Unlock()
+		return false
+	}
+
+	switch e := ev.(type) {
+	case evClose:
+		m.lifecycle = append(m.lifecycle, e)
+	case evRemoteOffer:
+		m.offer = &e
+		m.candidates = nil
+	case evRemoteAnswer:
+		m.answer = &e
+	case evRemoteCandidate:
+		if len(m.candidates) >= maxQueuedCandidates {
+			m.candidates = m.candidates[1:]
+		}
+		m.candidates = append(m.candidates, e)
+	case evGuardTick:
+		m.guardTick = true
+	default:
+		m.transport = append(m.transport, ev)
+	}
+	m.mu.Unlock()
+
+	select {
+	case m.wake <- struct{}{}:
+	default:
+	}
+	return true
+}
+
+// drain returns the pending events in processing order: lifecycle first,
+// then transport state changes, the coalesced offer and answer, the queued
+// candidates and finally the guard tick.
+func (m *mailbox) drain() []event {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	return m.drainLocked()
+}
+
+// closeAndDrain marks the mailbox closed so further posts are rejected and
+// returns the events that were still pending.
+func (m *mailbox) closeAndDrain() []event {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.closed = true
+	return m.drainLocked()
+}
+
+func (m *mailbox) drainLocked() []event {
+	evs := make([]event, 0, len(m.lifecycle)+len(m.transport)+len(m.candidates)+3)
+	evs = append(evs, m.lifecycle...)
+	evs = append(evs, m.transport...)
+	if m.offer != nil {
+		evs = append(evs, *m.offer)
+	}
+	if m.answer != nil {
+		evs = append(evs, *m.answer)
+	}
+	for _, c := range m.candidates {
+		evs = append(evs, c)
+	}
+	if m.guardTick {
+		evs = append(evs, evGuardTick{})
+	}
+
+	m.lifecycle = nil
+	m.transport = nil
+	m.offer = nil
+	m.answer = nil
+	m.candidates = nil
+	m.guardTick = false
+	return evs
+}

client/internal/peer/mailbox_test.go

@@ -0,0 +1,128 @@
+package peer
+
+import (
+	"testing"
+
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestMailbox_OfferCoalescing(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{WgListenPort: 1}}))
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{WgListenPort: 2}}))
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{WgListenPort: 3}}))
+
+	evs := mb.drain()
+	require.Len(t, evs, 1, "consecutive offers must coalesce to a single event")
+	offer, ok := evs[0].(evRemoteOffer)
+	require.True(t, ok, "coalesced event must be an offer")
+	assert.Equal(t, 3, offer.offer.WgListenPort, "the newest offer must win")
+}
+
+func TestMailbox_OfferFlushesCandidates(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evRemoteCandidate{}))
+	require.True(t, mb.post(evRemoteCandidate{}))
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{}}))
+
+	evs := mb.drain()
+	require.Len(t, evs, 1, "candidates of the superseded session must be flushed")
+	_, ok := evs[0].(evRemoteOffer)
+	assert.True(t, ok, "only the offer must remain after the flush")
+}
+
+func TestMailbox_CandidatesKeepOrderAfterOffer(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{}}))
+	require.True(t, mb.post(evRemoteCandidate{haRoutes: nil}))
+	require.True(t, mb.post(evRemoteCandidate{haRoutes: nil}))
+
+	evs := mb.drain()
+	require.Len(t, evs, 3)
+	_, ok := evs[0].(evRemoteOffer)
+	assert.True(t, ok, "offer must be processed before the candidates")
+	for _, ev := range evs[1:] {
+		_, ok := ev.(evRemoteCandidate)
+		assert.True(t, ok, "candidates posted after the offer must survive")
+	}
+}
+
+func TestMailbox_CandidateQueueBounded(t *testing.T) {
+	mb := newMailbox()
+
+	for i := 0; i < maxQueuedCandidates+10; i++ {
+		require.True(t, mb.post(evRemoteCandidate{}))
+	}
+
+	evs := mb.drain()
+	assert.Len(t, evs, maxQueuedCandidates, "candidate queue must stay bounded")
+}
+
+func TestMailbox_DrainOrder(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evGuardTick{}))
+	require.True(t, mb.post(evRemoteAnswer{answer: signaling.OfferAnswer{}}))
+	require.True(t, mb.post(evRemoteOffer{offer: signaling.OfferAnswer{}}))
+	require.True(t, mb.post(evRelayDown{}))
+	require.True(t, mb.post(evICEDown{sessionChanged: true}))
+	require.True(t, mb.post(evClose{}))
+
+	evs := mb.drain()
+	require.Len(t, evs, 6)
+
+	_, ok := evs[0].(evClose)
+	assert.True(t, ok, "lifecycle events must come first")
+	_, ok = evs[1].(evRelayDown)
+	assert.True(t, ok, "transport events must keep FIFO order")
+	_, ok = evs[2].(evICEDown)
+	assert.True(t, ok, "transport events must keep FIFO order")
+	_, ok = evs[3].(evRemoteOffer)
+	assert.True(t, ok, "offer must come after transport events")
+	_, ok = evs[4].(evRemoteAnswer)
+	assert.True(t, ok, "answer must come after the offer")
+	_, ok = evs[5].(evGuardTick)
+	assert.True(t, ok, "guard tick must come last")
+}
+
+func TestMailbox_GuardTickCoalesced(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evGuardTick{}))
+	require.True(t, mb.post(evGuardTick{}))
+	require.True(t, mb.post(evGuardTick{}))
+
+	evs := mb.drain()
+	assert.Len(t, evs, 1, "guard ticks must coalesce to a single event")
+}
+
+func TestMailbox_PostAfterCloseRejected(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evRelayDown{}))
+	leftovers := mb.closeAndDrain()
+	assert.Len(t, leftovers, 1, "pending events must be returned on close")
+
+	assert.False(t, mb.post(evRelayDown{}), "posts must be rejected after close")
+	assert.Empty(t, mb.drain(), "no events must remain after close")
+}
+
+func TestMailbox_WakeSignal(t *testing.T) {
+	mb := newMailbox()
+
+	require.True(t, mb.post(evRelayDown{}))
+	require.True(t, mb.post(evGuardTick{}))
+
+	select {
+	case <-mb.wake:
+	default:
+		t.Fatal("wake signal must be pending after posts")
+	}
+
+	assert.Len(t, mb.drain(), 2, "a single wake must deliver all pending events")
+}

client/internal/peer/metricsstages/metrics_saver.go

@@ -1,4 +1,4 @@
-package peer
+package metricsstages
 
 import (
 	"sync"

client/internal/peer/metricsstages/metrics_saver_test.go

@@ -1,4 +1,4 @@
-package peer
+package metricsstages
 
 import (
 	"testing"

client/internal/peer/signaling/handshaker.go

@@ -0,0 +1,189 @@
+package signaling
+
+import (
+	"errors"
+	"net/netip"
+	"sync"
+	"sync/atomic"
+
+	log "github.com/sirupsen/logrus"
+
+	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
+	relayClient "github.com/netbirdio/netbird/shared/relay/client"
+	"github.com/netbirdio/netbird/version"
+)
+
+var (
+	ErrSignalIsNotReady = errors.New("signal is not ready")
+)
+
+// IceCredentials ICE protocol credentials struct
+type IceCredentials struct {
+	UFrag string
+	Pwd   string
+}
+
+// OfferAnswer represents a session establishment offer or answer
+type OfferAnswer struct {
+	IceCredentials IceCredentials
+	// WgListenPort is a remote WireGuard listen port.
+	// This field is used when establishing a direct WireGuard connection without any proxy.
+	// We can set the remote peer's endpoint with this port.
+	WgListenPort int
+
+	// Version of NetBird Agent
+	Version string
+	// RosenpassPubKey is the Rosenpass public key of the remote peer when receiving this message
+	// This value is the local Rosenpass server public key when sending the message
+	RosenpassPubKey []byte
+	// RosenpassAddr is the Rosenpass server address (IP:port) of the remote peer when receiving this message
+	// This value is the local Rosenpass server address when sending the message
+	RosenpassAddr string
+
+	// relay server address
+	RelaySrvAddress string
+	// RelaySrvIP is the IP the remote peer is connected to on its
+	// relay server. Used as a dial target if DNS for RelaySrvAddress
+	// fails. Zero value if the peer did not advertise an IP.
+	RelaySrvIP netip.Addr
+	// SessionID is the unique identifier of the session, used to discard old messages
+	SessionID *icemaker.SessionID
+}
+
+func (o *OfferAnswer) HasICECredentials() bool {
+	return o.IceCredentials.UFrag != "" && o.IceCredentials.Pwd != ""
+}
+
+func (o *OfferAnswer) SessionIDString() string {
+	if o.SessionID == nil {
+		return "unknown"
+	}
+	return o.SessionID.String()
+}
+
+// Config carries the peer-specific values the Handshaker embeds into offers
+// and answers.
+type Config struct {
+	Key             string
+	LocalWgPort     int
+	RosenpassPubKey []byte
+	RosenpassAddr   string
+}
+
+// Credentials are the local ICE credentials and session id the Handshaker embeds in offers.
+type Credentials struct {
+	UFrag     string
+	Pwd       string
+	SessionID icemaker.SessionID
+}
+
+// ICEWorker is the subset of the ICE worker the Handshaker needs to build offers.
+type ICEWorker interface {
+	Credentials() Credentials
+	Close()
+}
+
+// Handshaker keeps the signaling protocol logic: building and sending offers
+// and answers and tracking whether the remote peer supports ICE. Incoming
+// message processing is driven by the Conn event loop.
+type Handshaker struct {
+	mu           sync.Mutex
+	log          *log.Entry
+	config       Config
+	signaler     *Signaler
+	ice          ICEWorker
+	relayManager *relayClient.Manager
+
+	// remoteICESupported tracks whether the remote peer includes ICE credentials in its offers/answers.
+	// When false, the local side skips ICE dispatch and suppresses ICE credentials in responses.
+	remoteICESupported atomic.Bool
+}
+
+func NewHandshaker(log *log.Entry, config Config, signaler *Signaler, ice ICEWorker, relayManager *relayClient.Manager) *Handshaker {
+	h := &Handshaker{
+		log:          log,
+		config:       config,
+		signaler:     signaler,
+		ice:          ice,
+		relayManager: relayManager,
+	}
+	// assume remote supports ICE until we learn otherwise from received offers
+	h.remoteICESupported.Store(ice != nil)
+	return h
+}
+
+func (h *Handshaker) RemoteICESupported() bool {
+	return h.remoteICESupported.Load()
+}
+
+func (h *Handshaker) SendOffer() error {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	return h.sendOffer()
+}
+
+func (h *Handshaker) SendAnswer() error {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	return h.sendAnswer()
+}
+
+// sendOffer prepares local user credentials and signals them to the remote peer
+func (h *Handshaker) sendOffer() error {
+	if !h.signaler.Ready() {
+		return ErrSignalIsNotReady
+	}
+
+	offer := h.buildOfferAnswer()
+	h.log.Debugf("sending offer with serial: %s", offer.SessionIDString())
+
+	return h.signaler.SignalOffer(offer, h.config.Key)
+}
+
+func (h *Handshaker) sendAnswer() error {
+	answer := h.buildOfferAnswer()
+	h.log.Debugf("sending answer with serial: %s", answer.SessionIDString())
+
+	return h.signaler.SignalAnswer(answer, h.config.Key)
+}
+
+func (h *Handshaker) buildOfferAnswer() OfferAnswer {
+	answer := OfferAnswer{
+		WgListenPort:    h.config.LocalWgPort,
+		Version:         version.NetbirdVersion(),
+		RosenpassPubKey: h.config.RosenpassPubKey,
+		RosenpassAddr:   h.config.RosenpassAddr,
+	}
+
+	if h.ice != nil && h.RemoteICESupported() {
+		creds := h.ice.Credentials()
+		answer.IceCredentials = IceCredentials{creds.UFrag, creds.Pwd}
+		sid := creds.SessionID
+		answer.SessionID = &sid
+	}
+
+	if addr, ip, err := h.relayManager.RelayInstanceAddress(); err == nil {
+		answer.RelaySrvAddress = addr
+		answer.RelaySrvIP = ip
+	}
+
+	return answer
+}
+
+// UpdateRemoteICEState refreshes the remote ICE support flag from a received
+// offer or answer and closes the ICE worker when the remote peer stopped
+// sending ICE credentials. Runs on the Conn event loop.
+func (h *Handshaker) UpdateRemoteICEState(offer *OfferAnswer) {
+	hasICE := offer.HasICECredentials()
+	prev := h.remoteICESupported.Swap(hasICE)
+	if prev != hasICE {
+		if hasICE {
+			h.log.Infof("remote peer started sending ICE credentials")
+		} else {
+			h.log.Infof("remote peer stopped sending ICE credentials")
+			if h.ice != nil {
+				h.ice.Close()
+			}
+		}
+	}
+}

client/internal/peer/signaling/signaler.go

@@ -1,4 +1,4 @@
-package peer
+package signaling
 
 import (
 	"github.com/pion/ice/v4"

client/internal/peer/state_dump/state_dump.go

@@ -1,4 +1,4 @@
-package peer
+package state_dump
 
 import (
 	"context"
@@ -6,11 +6,13 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer/status"
 )
 
-type stateDump struct {
+type StateDump struct {
 	log    *log.Entry
-	status *Status
+	status *status.Recorder
 	key    string
 
 	sentOffer       int
@@ -26,15 +28,15 @@ type stateDump struct {
 	mu sync.Mutex
 }
 
-func newStateDump(key string, log *log.Entry, statusRecorder *Status) *stateDump {
-	return &stateDump{
+func NewStateDump(key string, log *log.Entry, statusRecorder *status.Recorder) *StateDump {
+	return &StateDump{
 		log:    log,
 		status: statusRecorder,
 		key:    key,
 	}
 }
 
-func (s *stateDump) Start(ctx context.Context) {
+func (s *StateDump) Start(ctx context.Context) {
 	ticker := time.NewTicker(10 * time.Minute)
 	defer ticker.Stop()
 
@@ -48,25 +50,25 @@ func (s *stateDump) Start(ctx context.Context) {
 	}
 }
 
-func (s *stateDump) RemoteOffer() {
+func (s *StateDump) RemoteOffer() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.remoteOffer++
 }
 
-func (s *stateDump) RemoteCandidate() {
+func (s *StateDump) RemoteCandidate() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.remoteCandidate++
 }
 
-func (s *stateDump) SendOffer() {
+func (s *StateDump) SendOffer() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.sentOffer++
 }
 
-func (s *stateDump) dumpState() {
+func (s *StateDump) dumpState() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 
@@ -80,41 +82,41 @@ func (s *stateDump) dumpState() {
 		status, s.sentOffer, s.remoteOffer, s.remoteAnswer, s.remoteCandidate, s.p2pConnected, s.switchToRelay, s.wgCheckSuccess, s.relayConnected, s.localProxies)
 }
 
-func (s *stateDump) RemoteAnswer() {
+func (s *StateDump) RemoteAnswer() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	s.remoteAnswer++
 }
 
-func (s *stateDump) P2PConnected() {
+func (s *StateDump) P2PConnected() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 
 	s.p2pConnected++
 }
 
-func (s *stateDump) SwitchToRelay() {
+func (s *StateDump) SwitchToRelay() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 
 	s.switchToRelay++
 }
 
-func (s *stateDump) WGcheckSuccess() {
+func (s *StateDump) WGcheckSuccess() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 
 	s.wgCheckSuccess++
 }
 
-func (s *stateDump) RelayConnected() {
+func (s *StateDump) RelayConnected() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 
 	s.relayConnected++
 }
 
-func (s *stateDump) NewLocalProxy() {
+func (s *StateDump) NewLocalProxy() {
 	s.mu.Lock()
 	defer s.mu.Unlock()
 

client/internal/peer/status/conn_status.go

@@ -0,0 +1,31 @@
+package status
+
+import (
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	// StatusIdle indicate the peer is in disconnected state
+	StatusIdle ConnStatus = iota
+	// StatusConnecting indicate the peer is in connecting state
+	StatusConnecting
+	// StatusConnected indicate the peer is in connected state
+	StatusConnected
+)
+
+// ConnStatus describe the status of a peer's connection
+type ConnStatus int32
+
+func (s ConnStatus) String() string {
+	switch s {
+	case StatusConnecting:
+		return "Connecting"
+	case StatusConnected:
+		return "Connected"
+	case StatusIdle:
+		return "Idle"
+	default:
+		log.Errorf("unknown status: %d", s)
+		return "INVALID_PEER_CONNECTION_STATUS"
+	}
+}

client/internal/peer/status/conn_status_test.go

@@ -1,4 +1,4 @@
-package peer
+package status
 
 import (
 	"testing"

client/internal/peer/status/events.go

@@ -0,0 +1,48 @@
+package status
+
+import (
+	"slices"
+	"sync"
+
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+type EventQueue struct {
+	maxSize int
+	events  []*proto.SystemEvent
+	mutex   sync.RWMutex
+}
+
+func NewEventQueue(size int) *EventQueue {
+	return &EventQueue{
+		maxSize: size,
+		events:  make([]*proto.SystemEvent, 0, size),
+	}
+}
+
+func (q *EventQueue) Add(event *proto.SystemEvent) {
+	q.mutex.Lock()
+	defer q.mutex.Unlock()
+
+	q.events = append(q.events, event)
+
+	if len(q.events) > q.maxSize {
+		q.events = q.events[len(q.events)-q.maxSize:]
+	}
+}
+
+func (q *EventQueue) GetAll() []*proto.SystemEvent {
+	q.mutex.RLock()
+	defer q.mutex.RUnlock()
+
+	return slices.Clone(q.events)
+}
+
+type EventSubscription struct {
+	id     string
+	events chan *proto.SystemEvent
+}
+
+func (s *EventSubscription) Events() <-chan *proto.SystemEvent {
+	return s.events
+}

client/internal/peer/status/full_status.go

@@ -0,0 +1,122 @@
+package status
+
+import (
+	"golang.org/x/exp/maps"
+	"google.golang.org/protobuf/types/known/durationpb"
+	"google.golang.org/protobuf/types/known/timestamppb"
+
+	"github.com/netbirdio/netbird/client/internal/relay"
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+// FullStatus contains the full state held by the Recorder instance
+type FullStatus struct {
+	Peers                 []State
+	ManagementState       ManagementState
+	SignalState           SignalState
+	LocalPeerState        LocalPeerState
+	RosenpassState        RosenpassState
+	Relays                []relay.ProbeResult
+	NSGroupStates         []NSGroupState
+	NumOfForwardingRules  int
+	LazyConnectionEnabled bool
+	Events                []*proto.SystemEvent
+}
+
+// ToProto converts FullStatus to proto.FullStatus.
+func (fs FullStatus) ToProto() *proto.FullStatus {
+	pbFullStatus := proto.FullStatus{
+		ManagementState: &proto.ManagementState{},
+		SignalState:     &proto.SignalState{},
+		LocalPeerState:  &proto.LocalPeerState{},
+		Peers:           []*proto.PeerState{},
+	}
+
+	pbFullStatus.ManagementState.URL = fs.ManagementState.URL
+	pbFullStatus.ManagementState.Connected = fs.ManagementState.Connected
+	if err := fs.ManagementState.Error; err != nil {
+		pbFullStatus.ManagementState.Error = err.Error()
+	}
+
+	pbFullStatus.SignalState.URL = fs.SignalState.URL
+	pbFullStatus.SignalState.Connected = fs.SignalState.Connected
+	if err := fs.SignalState.Error; err != nil {
+		pbFullStatus.SignalState.Error = err.Error()
+	}
+
+	pbFullStatus.LocalPeerState.IP = fs.LocalPeerState.IP
+	pbFullStatus.LocalPeerState.Ipv6 = fs.LocalPeerState.IPv6
+	pbFullStatus.LocalPeerState.PubKey = fs.LocalPeerState.PubKey
+	pbFullStatus.LocalPeerState.KernelInterface = fs.LocalPeerState.KernelInterface
+	pbFullStatus.LocalPeerState.Fqdn = fs.LocalPeerState.FQDN
+	pbFullStatus.LocalPeerState.WgPort = int32(fs.LocalPeerState.WgPort)
+	pbFullStatus.LocalPeerState.RosenpassPermissive = fs.RosenpassState.Permissive
+	pbFullStatus.LocalPeerState.RosenpassEnabled = fs.RosenpassState.Enabled
+	pbFullStatus.NumberOfForwardingRules = int32(fs.NumOfForwardingRules)
+	pbFullStatus.LazyConnectionEnabled = fs.LazyConnectionEnabled
+
+	pbFullStatus.LocalPeerState.Networks = maps.Keys(fs.LocalPeerState.Routes)
+
+	for _, peerState := range fs.Peers {
+		networks := maps.Keys(peerState.GetRoutes())
+
+		pbPeerState := &proto.PeerState{
+			IP:                         peerState.IP,
+			Ipv6:                       peerState.IPv6,
+			PubKey:                     peerState.PubKey,
+			ConnStatus:                 peerState.ConnStatus.String(),
+			ConnStatusUpdate:           timestamppb.New(peerState.ConnStatusUpdate),
+			Relayed:                    peerState.Relayed,
+			LocalIceCandidateType:      peerState.LocalIceCandidateType,
+			RemoteIceCandidateType:     peerState.RemoteIceCandidateType,
+			LocalIceCandidateEndpoint:  peerState.LocalIceCandidateEndpoint,
+			RemoteIceCandidateEndpoint: peerState.RemoteIceCandidateEndpoint,
+			RelayAddress:               peerState.RelayServerAddress,
+			Fqdn:                       peerState.FQDN,
+			LastWireguardHandshake:     timestamppb.New(peerState.LastWireguardHandshake),
+			BytesRx:                    peerState.BytesRx,
+			BytesTx:                    peerState.BytesTx,
+			RosenpassEnabled:           peerState.RosenpassEnabled,
+			Networks:                   networks,
+			Latency:                    durationpb.New(peerState.Latency),
+			SshHostKey:                 peerState.SSHHostKey,
+		}
+		pbFullStatus.Peers = append(pbFullStatus.Peers, pbPeerState)
+	}
+
+	for _, relayState := range fs.Relays {
+		pbRelayState := &proto.RelayState{
+			URI:       relayState.URI,
+			Available: relayState.Err == nil,
+			Transport: relayState.Transport,
+		}
+		if err := relayState.Err; err != nil {
+			pbRelayState.Error = err.Error()
+		}
+		pbFullStatus.Relays = append(pbFullStatus.Relays, pbRelayState)
+	}
+
+	for _, dnsState := range fs.NSGroupStates {
+		var err string
+		if dnsState.Error != nil {
+			err = dnsState.Error.Error()
+		}
+
+		var servers []string
+		for _, server := range dnsState.Servers {
+			servers = append(servers, server.String())
+		}
+
+		pbDnsState := &proto.NSGroupState{
+			Servers: servers,
+			Domains: dnsState.Domains,
+			Enabled: dnsState.Enabled,
+			Error:   err,
+		}
+		pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
+	}
+
+	pbFullStatus.Events = fs.Events
+
+	return &pbFullStatus
+}

client/internal/peer/status/notifier.go

@@ -1,4 +1,4 @@
-package peer
+package status
 
 import (
 	"sync"
@@ -11,6 +11,16 @@ const (
 	stateDisconnecting
 )
 
+// Listener is a callback type about the NetBird network connection state
+type Listener interface {
+	OnConnected()
+	OnDisconnected()
+	OnConnecting()
+	OnDisconnecting()
+	OnAddressChanged(string, string)
+	OnPeersListChanged(int)
+}
+
 type notifier struct {
 	serverStateLock    sync.Mutex
 	listenersLock      sync.Mutex

client/internal/peer/status/notifier_test.go

@@ -1,4 +1,4 @@
-package peer
+package status
 
 import (
 	"sync"

client/internal/peer/status/peer_state.go

@@ -0,0 +1,63 @@
+package status
+
+import (
+	"sync"
+	"time"
+
+	"golang.org/x/exp/maps"
+)
+
+// State contains the latest state of a peer
+type State struct {
+	Mux                        *sync.RWMutex
+	IP                         string
+	IPv6                       string
+	PubKey                     string
+	FQDN                       string
+	ConnStatus                 ConnStatus
+	ConnStatusUpdate           time.Time
+	Relayed                    bool
+	LocalIceCandidateType      string
+	RemoteIceCandidateType     string
+	LocalIceCandidateEndpoint  string
+	RemoteIceCandidateEndpoint string
+	RelayServerAddress         string
+	LastWireguardHandshake     time.Time
+	BytesTx                    int64
+	BytesRx                    int64
+	Latency                    time.Duration
+	RosenpassEnabled           bool
+	SSHHostKey                 []byte
+	routes                     map[string]struct{}
+}
+
+// AddRoute add a single route to routes map
+func (s *State) AddRoute(network string) {
+	s.Mux.Lock()
+	defer s.Mux.Unlock()
+	if s.routes == nil {
+		s.routes = make(map[string]struct{})
+	}
+	s.routes[network] = struct{}{}
+}
+
+// SetRoutes set state routes
+func (s *State) SetRoutes(routes map[string]struct{}) {
+	s.Mux.Lock()
+	defer s.Mux.Unlock()
+	s.routes = routes
+}
+
+// DeleteRoute removes a route from the network amp
+func (s *State) DeleteRoute(network string) {
+	s.Mux.Lock()
+	defer s.Mux.Unlock()
+	delete(s.routes, network)
+}
+
+// GetRoutes return routes map
+func (s *State) GetRoutes() map[string]struct{} {
+	s.Mux.RLock()
+	defer s.Mux.RUnlock()
+	return maps.Clone(s.routes)
+}

client/internal/peer/status/recorder_test.go

@@ -1,4 +1,4 @@
-package peer
+package status
 
 import (
 	"context"

client/internal/peer/status/route.go

@@ -1,4 +1,4 @@
-package peer
+package status
 
 import (
 	"net/netip"

client/internal/peer/status_alias.go

@@ -0,0 +1,36 @@
+package peer
+
+import "github.com/netbirdio/netbird/client/internal/peer/status"
+
+// Transitional aliases re-exporting the peer status recorder from its own
+// package. Callers are being migrated to reference the status package
+// directly; these aliases will be removed once the migration completes.
+type (
+	Status                   = status.Recorder
+	State                    = status.State
+	ConnStatus               = status.ConnStatus
+	FullStatus               = status.FullStatus
+	RouterState              = status.RouterState
+	LocalPeerState           = status.LocalPeerState
+	SignalState              = status.SignalState
+	ManagementState          = status.ManagementState
+	RosenpassState           = status.RosenpassState
+	NSGroupState             = status.NSGroupState
+	ResolvedDomainInfo       = status.ResolvedDomainInfo
+	StatusChangeSubscription = status.StatusChangeSubscription
+	EventQueue               = status.EventQueue
+	EventSubscription        = status.EventSubscription
+	WGIfaceStatus            = status.WGIfaceStatus
+	Listener                 = status.Listener
+	EventListener            = status.EventListener
+)
+
+const (
+	StatusIdle       = status.StatusIdle
+	StatusConnecting = status.StatusConnecting
+	StatusConnected  = status.StatusConnected
+)
+
+var (
+	NewRecorder = status.NewRecorder
+)

client/internal/peer/wg_watcher/wg_watcher.go

@@ -1,4 +1,4 @@
-package peer
+package wg_watcher
 
 import (
 	"context"
@@ -9,6 +9,7 @@ import (
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/iface/configurer"
+	"github.com/netbirdio/netbird/client/internal/peer/state_dump"
 )
 
 const (
@@ -28,7 +29,7 @@ type WGWatcher struct {
 	log           *log.Entry
 	wgIfaceStater WGInterfaceStater
 	peerKey       string
-	stateDump     *stateDump
+	stateDump     *state_dump.StateDump
 
 	enabled   bool
 	muEnabled sync.Mutex
@@ -38,7 +39,7 @@ type WGWatcher struct {
 	resetCh chan struct{}
 }
 
-func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey string, stateDump *stateDump) *WGWatcher {
+func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey string, stateDump *state_dump.StateDump) *WGWatcher {
 	return &WGWatcher{
 		log:           log,
 		wgIfaceStater: wgIfaceStater,
@@ -71,9 +72,11 @@ 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 +93,7 @@ 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 +120,10 @@ 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/wg_watcher_test.go

@@ -0,0 +1,179 @@
+package wg_watcher
+
+import (
+	"context"
+	"sync"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/iface/configurer"
+	"github.com/netbirdio/netbird/client/internal/peer/state_dump"
+	"github.com/netbirdio/netbird/client/internal/peer/status"
+)
+
+type MocWgIface struct {
+	stop bool
+}
+
+func (m *MocWgIface) GetStats() (map[string]configurer.WGStats, error) {
+	return map[string]configurer.WGStats{}, nil
+}
+
+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, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	require.True(t, watcher.PrepareInitialHandshake())
+
+	firstHandshake := make(chan struct{}, 1)
+	checkSuccess := make(chan struct{}, 1)
+	watcherDone := make(chan struct{})
+	go func() {
+		defer close(watcherDone)
+		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:
+	}
+
+	// Wait for the watcher goroutine to exit so it cannot race with other
+	// tests mutating the package-level check timing variables.
+	cancel()
+	<-watcherDone
+}
+
+func TestWGWatcher_EnableWgWatcher(t *testing.T) {
+	checkPeriod = 5 * time.Second
+	wgHandshakeOvertime = 1 * time.Second
+
+	mlog := log.WithField("peer", "tet")
+	mocWgIface := &MocWgIface{}
+	watcher := NewWGWatcher(mlog, mocWgIface, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+
+	ok := watcher.PrepareInitialHandshake()
+	require.True(t, ok, "watcher should not be enabled yet")
+
+	onDisconnected := make(chan struct{}, 1)
+	go watcher.EnableWgWatcher(ctx, time.Now(), func() {
+		mlog.Infof("onDisconnectedFn")
+		onDisconnected <- struct{}{}
+	}, func(when time.Time) {
+		mlog.Infof("onHandshakeSuccess: %v", when)
+	}, nil)
+
+	// wait for initial reading
+	time.Sleep(2 * time.Second)
+	mocWgIface.disconnect()
+
+	select {
+	case <-onDisconnected:
+	case <-time.After(10 * time.Second):
+		t.Errorf("timeout")
+	}
+}
+
+func TestWGWatcher_ReEnable(t *testing.T) {
+	checkPeriod = 5 * time.Second
+	wgHandshakeOvertime = 1 * time.Second
+
+	mlog := log.WithField("peer", "tet")
+	mocWgIface := &MocWgIface{}
+	watcher := NewWGWatcher(mlog, mocWgIface, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
+
+	ctx, cancel := context.WithCancel(context.Background())
+	ok := watcher.PrepareInitialHandshake()
+	require.True(t, ok, "watcher should not be enabled yet")
+
+	wg := &sync.WaitGroup{}
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {}, nil)
+	}()
+	cancel()
+
+	wg.Wait()
+
+	// Re-enable with a new context
+	ctx, cancel = context.WithCancel(context.Background())
+	defer cancel()
+
+	ok = watcher.PrepareInitialHandshake()
+	require.True(t, ok, "watcher should be re-enabled after the previous run stopped")
+
+	onDisconnected := make(chan struct{}, 1)
+	go watcher.EnableWgWatcher(ctx, time.Now(), func() {
+		onDisconnected <- struct{}{}
+	}, func(when time.Time) {}, nil)
+
+	time.Sleep(2 * time.Second)
+	mocWgIface.disconnect()
+
+	select {
+	case <-onDisconnected:
+	case <-time.After(10 * time.Second):
+		t.Errorf("timeout")
+	}
+}

client/internal/peer/wg_watcher_test.go

@@ -1,102 +0,0 @@
-package peer
-
-import (
-	"context"
-	"sync"
-	"testing"
-	"time"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/iface/configurer"
-)
-
-type MocWgIface struct {
-	stop bool
-}
-
-func (m *MocWgIface) GetStats() (map[string]configurer.WGStats, error) {
-	return map[string]configurer.WGStats{}, nil
-}
-
-func (m *MocWgIface) disconnect() {
-	m.stop = true
-}
-
-func TestWGWatcher_EnableWgWatcher(t *testing.T) {
-	checkPeriod = 5 * time.Second
-	wgHandshakeOvertime = 1 * time.Second
-
-	mlog := log.WithField("peer", "tet")
-	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-
-	ok := watcher.PrepareInitialHandshake()
-	require.True(t, ok, "watcher should not be enabled yet")
-
-	onDisconnected := make(chan struct{}, 1)
-	go watcher.EnableWgWatcher(ctx, time.Now(), func() {
-		mlog.Infof("onDisconnectedFn")
-		onDisconnected <- struct{}{}
-	}, func(when time.Time) {
-		mlog.Infof("onHandshakeSuccess: %v", when)
-	})
-
-	// wait for initial reading
-	time.Sleep(2 * time.Second)
-	mocWgIface.disconnect()
-
-	select {
-	case <-onDisconnected:
-	case <-time.After(10 * time.Second):
-		t.Errorf("timeout")
-	}
-}
-
-func TestWGWatcher_ReEnable(t *testing.T) {
-	checkPeriod = 5 * time.Second
-	wgHandshakeOvertime = 1 * time.Second
-
-	mlog := log.WithField("peer", "tet")
-	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
-
-	ctx, cancel := context.WithCancel(context.Background())
-	ok := watcher.PrepareInitialHandshake()
-	require.True(t, ok, "watcher should not be enabled yet")
-
-	wg := &sync.WaitGroup{}
-	wg.Add(1)
-	go func() {
-		defer wg.Done()
-		watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {})
-	}()
-	cancel()
-
-	wg.Wait()
-
-	// Re-enable with a new context
-	ctx, cancel = context.WithCancel(context.Background())
-	defer cancel()
-
-	ok = watcher.PrepareInitialHandshake()
-	require.True(t, ok, "watcher should be re-enabled after the previous run stopped")
-
-	onDisconnected := make(chan struct{}, 1)
-	go watcher.EnableWgWatcher(ctx, time.Now(), func() {
-		onDisconnected <- struct{}{}
-	}, func(when time.Time) {})
-
-	time.Sleep(2 * time.Second)
-	mocWgIface.disconnect()
-
-	select {
-	case <-onDisconnected:
-	case <-time.After(10 * time.Second):
-		t.Errorf("timeout")
-	}
-}

client/internal/peer/worker/priority.go

@@ -1,4 +1,4 @@
-package conntype
+package worker
 
 import (
 	"fmt"

client/internal/peer/worker/worker_ice.go

@@ -1,4 +1,4 @@
-package peer
+package worker
 
 import (
 	"context"
@@ -13,8 +13,9 @@ import (
 
 	"github.com/netbirdio/netbird/client/iface"
 	"github.com/netbirdio/netbird/client/iface/udpmux"
-	"github.com/netbirdio/netbird/client/internal/peer/conntype"
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
+	"github.com/netbirdio/netbird/client/internal/peer/status"
 	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/route"
@@ -32,57 +33,68 @@ type ICEConnInfo struct {
 	RelayedOnLocal             bool
 }
 
-type WorkerICE struct {
-	ctx               context.Context
-	log               *log.Entry
-	config            ConnConfig
-	conn              *Conn
-	signaler          *Signaler
-	iFaceDiscover     stdnet.ExternalIFaceDiscover
-	statusRecorder    *Status
-	hasRelayOnLocally bool
+type ICEDependencies struct {
+	Signaler           *signaling.Signaler
+	IFaceDiscover      stdnet.ExternalIFaceDiscover
+	StatusRecorder     *status.Recorder
+	PortForwardManager *portforward.Manager
+}
+
+type ICE struct {
+	log                *log.Entry
+	key                string
+	iceConfig          icemaker.Config
+	isController       bool
+	onConnReady        func(priority ConnPriority, iceConnInfo ICEConnInfo)
+	onStatusDisconnect func(sessionChanged bool)
+	signaler           *signaling.Signaler
+	iFaceDiscover      stdnet.ExternalIFaceDiscover
+	statusRecorder     *status.Recorder
+	portForwardManager *portforward.Manager
+	hasRelayOnLocally  bool
 
 	agent             *icemaker.ThreadSafeAgent
 	agentDialerCancel context.CancelFunc
 	agentConnecting   bool      // while it is true, drop all incoming offers
 	lastSuccess       time.Time // with this avoid the too frequent ICE agent recreation
+	// connectedAgent is the agent whose connection was last reported ready; guarded by muxAgent
+	connectedAgent *icemaker.ThreadSafeAgent
 	// remoteSessionID represents the peer's session identifier from the latest remote offer.
-	remoteSessionID ICESessionID
+	remoteSessionID icemaker.SessionID
 	// sessionID is used to track the current session ID of the ICE agent
 	// increase by one when disconnecting the agent
 	// with it the remote peer can discard the already deprecated offer/answer
 	// Without it the remote peer may recreate a workable ICE connection
-	sessionID            ICESessionID
+	sessionID            icemaker.SessionID
 	remoteSessionChanged bool
 	muxAgent             sync.Mutex
 
 	localUfrag string
 	localPwd   string
 
-	// we record the last known state of the ICE agent to avoid duplicate on disconnected events
-	lastKnownState ice.ConnectionState
-
 	// portForwardAttempted tracks if we've already tried port forwarding this session
 	portForwardAttempted bool
 }
 
-func NewWorkerICE(ctx context.Context, log *log.Entry, config ConnConfig, conn *Conn, signaler *Signaler, ifaceDiscover stdnet.ExternalIFaceDiscover, statusRecorder *Status, hasRelayOnLocally bool) (*WorkerICE, error) {
-	sessionID, err := NewICESessionID()
+func NewICE(log *log.Entry, key string, iceConfig icemaker.Config, isController bool, onConnReady func(ConnPriority, ICEConnInfo), onStatusDisconnect func(bool), services ICEDependencies, hasRelayOnLocally bool) (*ICE, error) {
+	sessionID, err := icemaker.NewSessionID()
 	if err != nil {
 		return nil, err
 	}
 
-	w := &WorkerICE{
-		ctx:               ctx,
-		log:               log,
-		config:            config,
-		conn:              conn,
-		signaler:          signaler,
-		iFaceDiscover:     ifaceDiscover,
-		statusRecorder:    statusRecorder,
-		hasRelayOnLocally: hasRelayOnLocally,
-		lastKnownState:    ice.ConnectionStateDisconnected,
-		sessionID:         sessionID,
+	w := &ICE{
+		log:                log,
+		key:                key,
+		iceConfig:          iceConfig,
+		isController:       isController,
+		onConnReady:        onConnReady,
+		onStatusDisconnect: onStatusDisconnect,
+		signaler:           services.Signaler,
+		iFaceDiscover:      services.IFaceDiscover,
+		statusRecorder:     services.StatusRecorder,
+		portForwardManager: services.PortForwardManager,
+		hasRelayOnLocally:  hasRelayOnLocally,
+		sessionID:          sessionID,
 	}
 
 	localUfrag, localPwd, err := icemaker.GenerateICECredentials()
@@ -94,7 +106,7 @@ func NewWorkerICE(ctx context.Context, log *log.Entry, config ConnConfig, conn *
 	return w, nil
 }
 
-func (w *WorkerICE) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
+func (w *ICE) OnNewOffer(ctx context.Context, remoteOfferAnswer *signaling.OfferAnswer) {
 	w.log.Debugf("OnNewOffer for ICE, serial: %s", remoteOfferAnswer.SessionIDString())
 	w.muxAgent.Lock()
 	defer w.muxAgent.Unlock()
@@ -118,7 +130,7 @@ func (w *WorkerICE) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 			}
 		}
 
-		sessionID, err := NewICESessionID()
+		sessionID, err := icemaker.NewSessionID()
 		if err != nil {
 			w.log.Errorf("failed to create new session ID: %s", err)
 		}
@@ -136,8 +148,8 @@ func (w *WorkerICE) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	if remoteOfferAnswer.SessionID != nil {
 		w.log.Debugf("recreate ICE agent: %s / %s", w.sessionID, *remoteOfferAnswer.SessionID)
 	}
-	dialerCtx, dialerCancel := context.WithCancel(w.ctx)
-	agent, err := w.reCreateAgent(dialerCancel, preferredCandidateTypes)
+	dialerCtx, dialerCancel := context.WithCancel(ctx)
+	agent, err := w.reCreateAgent(ctx, dialerCancel, preferredCandidateTypes)
 	if err != nil {
 		w.log.Errorf("failed to recreate ICE Agent: %s", err)
 		return
@@ -151,14 +163,14 @@ func (w *WorkerICE) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 		w.remoteSessionID = ""
 	}
 
-	go w.connect(dialerCtx, agent, remoteOfferAnswer)
+	go w.connect(dialerCtx, dialerCancel, agent, remoteOfferAnswer)
 }
 
 // OnRemoteCandidate Handles ICE connection Candidate provided by the remote peer.
-func (w *WorkerICE) OnRemoteCandidate(candidate ice.Candidate, haRoutes route.HAMap) {
+func (w *ICE) OnRemoteCandidate(candidate ice.Candidate, haRoutes route.HAMap) {
 	w.muxAgent.Lock()
 	defer w.muxAgent.Unlock()
-	w.log.Debugf("OnRemoteCandidate from peer %s -> %s", w.config.Key, candidate.String())
+	w.log.Debugf("OnRemoteCandidate from peer %s -> %s", w.key, candidate.String())
 	if w.agent == nil {
 		w.log.Warnf("ICE Agent is not initialized yet")
 		return
@@ -185,18 +197,24 @@ func (w *WorkerICE) OnRemoteCandidate(candidate ice.Candidate, haRoutes route.HA
 	}
 }
 
-func (w *WorkerICE) GetLocalUserCredentials() (frag string, pwd string) {
-	return w.localUfrag, w.localPwd
+func (w *ICE) Credentials() signaling.Credentials {
+	w.muxAgent.Lock()
+	defer w.muxAgent.Unlock()
+	return signaling.Credentials{
+		UFrag:     w.localUfrag,
+		Pwd:       w.localPwd,
+		SessionID: w.sessionID,
+	}
 }
 
-func (w *WorkerICE) InProgress() bool {
+func (w *ICE) InProgress() bool {
 	w.muxAgent.Lock()
 	defer w.muxAgent.Unlock()
 
 	return w.agentConnecting
 }
 
-func (w *WorkerICE) Close() {
+func (w *ICE) Close() {
 	w.muxAgent.Lock()
 	defer w.muxAgent.Unlock()
 
@@ -212,10 +230,10 @@ func (w *WorkerICE) Close() {
 	w.agent = nil
 }
 
-func (w *WorkerICE) reCreateAgent(dialerCancel context.CancelFunc, candidates []ice.CandidateType) (*icemaker.ThreadSafeAgent, error) {
+func (w *ICE) reCreateAgent(ctx context.Context, dialerCancel context.CancelFunc, candidates []ice.CandidateType) (*icemaker.ThreadSafeAgent, error) {
 	w.portForwardAttempted = false
 
-	agent, err := icemaker.NewAgent(w.ctx, w.iFaceDiscover, w.config.ICEConfig, candidates, w.localUfrag, w.localPwd)
+	agent, err := icemaker.NewAgent(ctx, w.iFaceDiscover, w.iceConfig, candidates, w.localUfrag, w.localPwd)
 	if err != nil {
 		return nil, fmt.Errorf("create agent: %w", err)
 	}
@@ -237,7 +255,7 @@ func (w *WorkerICE) reCreateAgent(dialerCancel context.CancelFunc, candidates []
 	return agent, nil
 }
 
-func (w *WorkerICE) SessionID() ICESessionID {
+func (w *ICE) getSessionID() icemaker.SessionID {
 	w.muxAgent.Lock()
 	defer w.muxAgent.Unlock()
 
@@ -247,11 +265,11 @@ func (w *WorkerICE) SessionID() ICESessionID {
 // will block until connection succeeded
 // but it won't release if ICE Agent went into Disconnected or Failed state,
 // so we have to cancel it with the provided context once agent detected a broken connection
-func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) {
+func (w *ICE) connect(ctx context.Context, dialerCancel context.CancelFunc, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *signaling.OfferAnswer) {
 	w.log.Debugf("gather candidates")
 	if err := agent.GatherCandidates(); err != nil {
 		w.log.Warnf("failed to gather candidates: %s", err)
-		w.closeAgent(agent, w.agentDialerCancel)
+		w.closeAgent(agent, dialerCancel)
 		return
 	}
 
@@ -259,19 +277,19 @@ func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent
 	remoteConn, err := w.turnAgentDial(ctx, agent, remoteOfferAnswer)
 	if err != nil {
 		w.log.Debugf("failed to dial the remote peer: %s", err)
-		w.closeAgent(agent, w.agentDialerCancel)
+		w.closeAgent(agent, dialerCancel)
 		return
 	}
 	w.log.Debugf("agent dial succeeded")
 
 	pair, err := agent.GetSelectedCandidatePair()
 	if err != nil {
-		w.closeAgent(agent, w.agentDialerCancel)
+		w.closeAgent(agent, dialerCancel)
 		return
 	}
 	if pair == nil {
 		w.log.Warnf("selected candidate pair is nil, cannot proceed")
-		w.closeAgent(agent, w.agentDialerCancel)
+		w.closeAgent(agent, dialerCancel)
 		return
 	}
 
@@ -299,17 +317,22 @@ func (w *WorkerICE) connect(ctx context.Context, agent *icemaker.ThreadSafeAgent
 	}
 	w.log.Debugf("on ICE conn is ready to use")
 
-	w.log.Infof("connection succeeded with offer session: %s", remoteOfferAnswer.SessionIDString())
 	w.muxAgent.Lock()
+	if w.agent != agent {
+		w.muxAgent.Unlock()
+		w.log.Debugf("agent has been replaced during connect, dropping obsolete connection")
+		return
+	}
 	w.agentConnecting = false
 	w.lastSuccess = time.Now()
+	w.connectedAgent = agent
 	w.muxAgent.Unlock()
 
-	// todo: the potential problem is a race between the onConnectionStateChange
-	w.conn.onICEConnectionIsReady(selectedPriority(pair), ci)
+	w.log.Infof("connection succeeded with offer session: %s", remoteOfferAnswer.SessionIDString())
+	w.onConnReady(selectedPriority(pair), ci)
 }
 
-func (w *WorkerICE) closeAgent(agent *icemaker.ThreadSafeAgent, cancel context.CancelFunc) bool {
+func (w *ICE) closeAgent(agent *icemaker.ThreadSafeAgent, cancel context.CancelFunc) bool {
 	cancel()
 	if err := agent.Close(); err != nil {
 		w.log.Warnf("failed to close ICE agent: %s", err)
@@ -323,7 +346,7 @@ func (w *WorkerICE) closeAgent(agent *icemaker.ThreadSafeAgent, cancel context.C
 
 	if w.agent == agent {
 		// consider to remove from here and move to the OnNewOffer
-		sessionID, err := NewICESessionID()
+		sessionID, err := icemaker.NewSessionID()
 		if err != nil {
 			w.log.Errorf("failed to create new session ID: %s", err)
 		}
@@ -335,7 +358,7 @@ func (w *WorkerICE) closeAgent(agent *icemaker.ThreadSafeAgent, cancel context.C
 	return sessionChanged
 }
 
-func (w *WorkerICE) punchRemoteWGPort(pair *ice.CandidatePair, remoteWgPort int) {
+func (w *ICE) punchRemoteWGPort(pair *ice.CandidatePair, remoteWgPort int) {
 	// wait local endpoint configuration
 	time.Sleep(time.Second)
 	addr, err := net.ResolveUDPAddr("udp", net.JoinHostPort(pair.Remote.Address(), strconv.Itoa(remoteWgPort)))
@@ -344,7 +367,7 @@ func (w *WorkerICE) punchRemoteWGPort(pair *ice.CandidatePair, remoteWgPort int)
 		return
 	}
 
-	mux, ok := w.config.ICEConfig.UDPMuxSrflx.(*udpmux.UniversalUDPMuxDefault)
+	mux, ok := w.iceConfig.UDPMuxSrflx.(*udpmux.UniversalUDPMuxDefault)
 	if !ok {
 		w.log.Warn("invalid udp mux conversion")
 		return
@@ -357,7 +380,7 @@ func (w *WorkerICE) punchRemoteWGPort(pair *ice.CandidatePair, remoteWgPort int)
 
 // onICECandidate is a callback attached to an ICE Agent to receive new local connection candidates
 // and then signals them to the remote peer
-func (w *WorkerICE) onICECandidate(candidate ice.Candidate) {
+func (w *ICE) onICECandidate(candidate ice.Candidate) {
 	// nil means candidate gathering has been ended
 	if candidate == nil {
 		return
@@ -366,9 +389,9 @@ func (w *WorkerICE) onICECandidate(candidate ice.Candidate) {
 	// TODO: reported port is incorrect for CandidateTypeHost, makes understanding ICE use via logs confusing as port is ignored
 	w.log.Debugf("discovered local candidate %s", candidate.String())
 	go func() {
-		err := w.signaler.SignalICECandidate(candidate, w.config.Key)
+		err := w.signaler.SignalICECandidate(candidate, w.key)
 		if err != nil {
-			w.log.Errorf("failed signaling candidate to the remote peer %s %s", w.config.Key, err)
+			w.log.Errorf("failed signaling candidate to the remote peer %s %s", w.key, err)
 		}
 	}()
 
@@ -378,8 +401,8 @@ func (w *WorkerICE) onICECandidate(candidate ice.Candidate) {
 }
 
 // injectPortForwardedCandidate signals an additional candidate using the pre-created port mapping.
-func (w *WorkerICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) {
-	pfManager := w.conn.portForwardManager
+func (w *ICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) {
+	pfManager := w.portForwardManager
 	if pfManager == nil {
 		return
 	}
@@ -407,7 +430,7 @@ func (w *WorkerICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) {
 		forwardedCandidate.String(), mapping.InternalPort, mapping.ExternalPort, mapping.NATType, forwardedCandidate.Priority())
 
 	go func() {
-		if err := w.signaler.SignalICECandidate(forwardedCandidate, w.config.Key); err != nil {
+		if err := w.signaler.SignalICECandidate(forwardedCandidate, w.key); err != nil {
 			w.log.Errorf("signal port-forwarded candidate: %v", err)
 		}
 	}()
@@ -415,7 +438,7 @@ func (w *WorkerICE) injectPortForwardedCandidate(srflxCandidate ice.Candidate) {
 
 // createForwardedCandidate creates a new server reflexive candidate with the forwarded port.
 // It uses the NAT gateway's external IP with the forwarded port.
-func (w *WorkerICE) createForwardedCandidate(srflxCandidate ice.Candidate, mapping *portforward.Mapping) (ice.Candidate, error) {
+func (w *ICE) createForwardedCandidate(srflxCandidate ice.Candidate, mapping *portforward.Mapping) (ice.Candidate, error) {
 	var externalIP string
 	if mapping.ExternalIP != nil && !mapping.ExternalIP.IsUnspecified() {
 		externalIP = mapping.ExternalIP.String()
@@ -460,9 +483,9 @@ func (w *WorkerICE) createForwardedCandidate(srflxCandidate ice.Candidate, mappi
 	return candidate, nil
 }
 
-func (w *WorkerICE) onICESelectedCandidatePair(agent *icemaker.ThreadSafeAgent, c1, c2 ice.Candidate) {
+func (w *ICE) onICESelectedCandidatePair(agent *icemaker.ThreadSafeAgent, c1, c2 ice.Candidate) {
 	w.log.Debugf("selected candidate pair [local <-> remote] -> [%s <-> %s], peer %s", c1.String(), c2.String(),
-		w.config.Key)
+		w.key)
 
 	pairStat, ok := agent.GetSelectedCandidatePairStats()
 	if !ok {
@@ -471,14 +494,14 @@ func (w *WorkerICE) onICESelectedCandidatePair(agent *icemaker.ThreadSafeAgent,
 	}
 
 	duration := time.Duration(pairStat.CurrentRoundTripTime * float64(time.Second))
-	if err := w.statusRecorder.UpdateLatency(w.config.Key, duration); err != nil {
+	if err := w.statusRecorder.UpdateLatency(w.key, duration); err != nil {
 		w.log.Debugf("failed to update latency for peer: %s", err)
 		return
 	}
 }
 
-func (w *WorkerICE) logSuccessfulPaths(agent *icemaker.ThreadSafeAgent) {
-	sessionID := w.SessionID()
+func (w *ICE) logSuccessfulPaths(agent *icemaker.ThreadSafeAgent) {
+	sessionID := w.getSessionID()
 	stats := agent.GetCandidatePairsStats()
 	localCandidates, _ := agent.GetLocalCandidates()
 	remoteCandidates, _ := agent.GetRemoteCandidates()
@@ -508,32 +531,44 @@ func (w *WorkerICE) logSuccessfulPaths(agent *icemaker.ThreadSafeAgent) {
 	}
 }
 
-func (w *WorkerICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dialerCancel context.CancelFunc) func(ice.ConnectionState) {
+func (w *ICE) onConnectionStateChange(agent *icemaker.ThreadSafeAgent, dialerCancel context.CancelFunc) func(ice.ConnectionState) {
+	// per-agent state; pion delivers callbacks of one agent sequentially
+	var connected bool
 	return func(state ice.ConnectionState) {
 		w.log.Debugf("ICE ConnectionState has changed to %s", state.String())
 		switch state {
 		case ice.ConnectionStateConnected:
-			w.lastKnownState = ice.ConnectionStateConnected
+			connected = true
 			w.logSuccessfulPaths(agent)
-			return
 		case ice.ConnectionStateFailed, ice.ConnectionStateDisconnected, ice.ConnectionStateClosed:
 			// ice.ConnectionStateClosed happens when we recreate the agent. For the P2P to TURN switch important to
 			// notify the conn.onICEStateDisconnected changes to update the current used priority
 
 			sessionChanged := w.closeAgent(agent, dialerCancel)
 
-			if w.lastKnownState == ice.ConnectionStateConnected {
-				w.lastKnownState = ice.ConnectionStateDisconnected
-				w.conn.onICEStateDisconnected(sessionChanged)
+			if !connected {
+				return
 			}
-		default:
-			return
+			connected = false
+
+			w.muxAgent.Lock()
+			stale := w.connectedAgent != agent
+			if !stale {
+				w.connectedAgent = nil
+			}
+			w.muxAgent.Unlock()
+
+			if stale {
+				w.log.Debugf("suppress disconnected event of replaced ICE agent")
+				return
+			}
+			w.onStatusDisconnect(sessionChanged)
 		}
 	}
 }
 
-func (w *WorkerICE) turnAgentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *OfferAnswer) (*ice.Conn, error) {
-	if isController(w.config) {
+func (w *ICE) turnAgentDial(ctx context.Context, agent *icemaker.ThreadSafeAgent, remoteOfferAnswer *signaling.OfferAnswer) (*ice.Conn, error) {
+	if w.isController {
 		return agent.Dial(ctx, remoteOfferAnswer.IceCredentials.UFrag, remoteOfferAnswer.IceCredentials.Pwd)
 	} else {
 		return agent.Accept(ctx, remoteOfferAnswer.IceCredentials.UFrag, remoteOfferAnswer.IceCredentials.Pwd)
@@ -595,10 +630,10 @@ func isRelayed(pair *ice.CandidatePair) bool {
 	return false
 }
 
-func selectedPriority(pair *ice.CandidatePair) conntype.ConnPriority {
+func selectedPriority(pair *ice.CandidatePair) ConnPriority {
 	if isRelayed(pair) {
-		return conntype.ICETurn
+		return ICETurn
 	} else {
-		return conntype.ICEP2P
+		return ICEP2P
 	}
 }

client/internal/peer/worker/worker_relay.go

@@ -1,4 +1,4 @@
-package peer
+package worker
 
 import (
 	"context"
@@ -10,22 +10,23 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/internal/peer/signaling"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
 
 type RelayConnInfo struct {
-	relayedConn     net.Conn
-	rosenpassPubKey []byte
-	rosenpassAddr   string
+	RelayedConn     net.Conn
+	RosenpassPubKey []byte
+	RosenpassAddr   string
 }
 
 type WorkerRelay struct {
-	peerCtx      context.Context
-	log          *log.Entry
-	isController bool
-	config       ConnConfig
-	conn         *Conn
-	relayManager *relayClient.Manager
+	log            *log.Entry
+	key            string
+	isController   bool
+	onConnReady    func(RelayConnInfo)
+	onDisconnected func()
+	relayManager   *relayClient.Manager
 
 	relayedConn net.Conn
 	relayLock   sync.Mutex
@@ -33,19 +34,19 @@ type WorkerRelay struct {
 	relaySupportedOnRemotePeer atomic.Bool
 }
 
-func NewWorkerRelay(ctx context.Context, log *log.Entry, ctrl bool, config ConnConfig, conn *Conn, relayManager *relayClient.Manager) *WorkerRelay {
+func NewWorkerRelay(log *log.Entry, key string, isController bool, onConnReady func(RelayConnInfo), onDisconnected func(), relayManager *relayClient.Manager) *WorkerRelay {
 	r := &WorkerRelay{
-		peerCtx:      ctx,
-		log:          log,
-		isController: ctrl,
-		config:       config,
-		conn:         conn,
-		relayManager: relayManager,
+		log:            log,
+		key:            key,
+		isController:   isController,
+		onConnReady:    onConnReady,
+		onDisconnected: onDisconnected,
+		relayManager:   relayManager,
 	}
 	return r
 }
 
-func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
+func (w *WorkerRelay) OnNewOffer(ctx context.Context, remoteOfferAnswer *signaling.OfferAnswer) {
 	if !w.isRelaySupported(remoteOfferAnswer) {
 		w.log.Infof("Relay is not supported by remote peer")
 		w.relaySupportedOnRemotePeer.Store(false)
@@ -66,7 +67,7 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 		serverIP = remoteOfferAnswer.RelaySrvIP
 	}
 
-	relayedConn, err := w.relayManager.OpenConn(w.peerCtx, srv, w.config.Key, serverIP)
+	relayedConn, err := w.relayManager.OpenConn(ctx, srv, w.key, serverIP)
 	if err != nil {
 		if errors.Is(err, relayClient.ErrConnAlreadyExists) {
 			w.log.Debugf("handled offer by reusing existing relay connection")
@@ -88,10 +89,10 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	}
 
 	w.log.Debugf("peer conn opened via Relay: %s", srv)
-	go w.conn.onRelayConnectionIsReady(RelayConnInfo{
-		relayedConn:     relayedConn,
-		rosenpassPubKey: remoteOfferAnswer.RosenpassPubKey,
-		rosenpassAddr:   remoteOfferAnswer.RosenpassAddr,
+	w.onConnReady(RelayConnInfo{
+		RelayedConn:     relayedConn,
+		RosenpassPubKey: remoteOfferAnswer.RosenpassPubKey,
+		RosenpassAddr:   remoteOfferAnswer.RosenpassAddr,
 	})
 }
 
@@ -119,7 +120,7 @@ func (w *WorkerRelay) CloseConn() {
 	}
 }
 
-func (w *WorkerRelay) isRelaySupported(answer *OfferAnswer) bool {
+func (w *WorkerRelay) isRelaySupported(answer *signaling.OfferAnswer) bool {
 	if !w.relayManager.HasRelayAddress() {
 		return false
 	}
@@ -134,5 +135,5 @@ func (w *WorkerRelay) preferredRelayServer(myRelayAddress, remoteRelayAddress st
 }
 
 func (w *WorkerRelay) onRelayClientDisconnected() {
-	go w.conn.onRelayDisconnected()
+	w.onDisconnected()
 }

client/internal/peer/worker_status.go

@@ -1,4 +1,4 @@
-package worker
+package peer
 
 import (
 	"sync/atomic"
@@ -7,17 +7,17 @@ import (
 )
 
 const (
-	StatusDisconnected Status = iota
-	StatusConnected
+	WorkerStatusDisconnected WorkerStatus = iota
+	WorkerStatusConnected
 )
 
-type Status int32
+type WorkerStatus int32
 
-func (s Status) String() string {
+func (s WorkerStatus) String() string {
 	switch s {
-	case StatusDisconnected:
+	case WorkerStatusDisconnected:
 		return "Disconnected"
-	case StatusConnected:
+	case WorkerStatusConnected:
 		return "Connected"
 	default:
 		log.Errorf("unknown status: %d", s)
@@ -37,16 +37,16 @@ func NewAtomicStatus() *AtomicWorkerStatus {
 }
 
 // Get returns the current connection status
-func (acs *AtomicWorkerStatus) Get() Status {
-	return Status(acs.status.Load())
+func (acs *AtomicWorkerStatus) Get() WorkerStatus {
+	return WorkerStatus(acs.status.Load())
 }
 
 func (acs *AtomicWorkerStatus) SetConnected() {
-	acs.status.Store(int32(StatusConnected))
+	acs.status.Store(int32(WorkerStatusConnected))
 }
 
 func (acs *AtomicWorkerStatus) SetDisconnected() {
-	acs.status.Store(int32(StatusDisconnected))
+	acs.status.Store(int32(WorkerStatusDisconnected))
 }
 
 // String returns the string representation of the current status

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/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/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/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/services/connection.go

@@ -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(),
@@ -129,6 +130,7 @@ func (s *Connection) WaitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
 	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,
@@ -136,6 +138,7 @@ func (s *Connection) WaitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
 	if err != nil {
 		return "", s.classifyDaemonError(err)
 	}
+	log.Infof("SSO login completed, daemon reported success")
 	return resp.GetEmail(), nil
 }
 
@@ -144,6 +147,7 @@ func (s *Connection) Up(ctx context.Context, p UpParams) error {
 	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 != "" {

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
@@ -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
@@ -314,8 +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

@@ -732,8 +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=
@@ -748,8 +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=
@@ -768,8 +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=
@@ -784,8 +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=
@@ -821,8 +821,8 @@ 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 v0.20.0/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=
@@ -835,8 +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=
@@ -848,8 +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=
@@ -863,8 +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/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/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
 		}

shared/management/http/api/openapi.yml

@@ -9327,6 +9327,18 @@ 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

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

@@ -5857,6 +5857,12 @@ 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/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)