[client] Drop stale WG timeouts via the watcher context instead of a generation counter

Tag each WG timeout event with the watcher's context and discard it at
dispatch time when that context is cancelled. This replaces the earlier
generation counter and the mailbox-level epoch filter: cancelling the
watcher is now the single act that both stops it and retires its pending
timeouts, so the two can no longer diverge, and the staleness check moves
to dispatch time so a cancel performed by an earlier event in the same
drained batch already suppresses a superseded watcher's timeout.

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

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

.goreleaser_ui.yaml

@@ -93,7 +93,9 @@ nfpms:
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
     dependencies:
-      - netbird
+      - netbird (>= 0.75.0)
+      - libgtk-4-1 (>= 4.14)
+      - libwebkitgtk-6.0-4
 
   - maintainer: Netbird <dev@netbird.io>
     description: Netbird client UI.
@@ -114,7 +116,9 @@ nfpms:
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
     dependencies:
-      - netbird
+      - netbird >= 0.75.0
+      - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
+      - (webkitgtk6.0 or libwebkitgtk-6_0-4)
 
     rpm:
       signature:

client/android/client.go

@@ -57,6 +57,12 @@ type DnsReadyListener interface {
 	dns.ReadyListener
 }
 
+// TunSettings is a snapshot of the settings the TUN device is rebuilt with
+type TunSettings struct {
+	Routes        string
+	SearchDomains string
+}
+
 func init() {
 	formatter.SetLogcatFormatter(log.StandardLogger())
 }
@@ -76,6 +82,8 @@ type Client struct {
 	connectClient *internal.ConnectClient
 	config        *profilemanager.Config
 	cacheDir      string
+	// Identifies the running profile for the SSO login hint; see profile_state.go.
+	cfgPath string
 
 	stateChangeMu    sync.Mutex
 	stateChangeSubID string
@@ -96,11 +104,12 @@ type Client struct {
 	extendCancel context.CancelFunc
 }
 
-func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cc *internal.ConnectClient) {
+func (c *Client) setState(cfg *profilemanager.Config, cacheDir string, cfgPath string, cc *internal.ConnectClient) {
 	c.stateMu.Lock()
 	defer c.stateMu.Unlock()
 	c.config = cfg
 	c.cacheDir = cacheDir
+	c.cfgPath = cfgPath
 	c.connectClient = cc
 }
 
@@ -110,6 +119,16 @@ func (c *Client) stateSnapshot() (*profilemanager.Config, string, *internal.Conn
 	return c.config, c.cacheDir, c.connectClient
 }
 
+// authSnapshot returns the config together with the path it was loaded from, in
+// one lock: the path identifies the profile whose account email backs the login
+// hint, so reading it separately could pair one profile's config with another's
+// hint when a profile switch lands in between.
+func (c *Client) authSnapshot() (*profilemanager.Config, string, *internal.ConnectClient) {
+	c.stateMu.RLock()
+	defer c.stateMu.RUnlock()
+	return c.config, c.cfgPath, c.connectClient
+}
+
 func (c *Client) getConnectClient() *internal.ConnectClient {
 	c.stateMu.RLock()
 	defer c.stateMu.RUnlock()
@@ -162,7 +181,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	defer c.ctxCancel()
 	c.ctxCancelLock.Unlock()
 
-	auth := NewAuthWithConfig(ctx, cfg)
+	auth := NewAuthWithConfig(ctx, cfg, cfgFile)
 	err = auth.login(urlOpener, isAndroidTV)
 	if err != nil {
 		return err
@@ -170,7 +189,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
-	c.setState(cfg, cacheDir, connectClient)
+	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	// This path runs the interactive SSO flow, so reaching here means the peer
 	// is authenticated again — release the latch Status() reports from. Clear
 	// only once the fresh connect client is installed: until then Status()
@@ -211,7 +230,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
-	c.setState(cfg, cacheDir, connectClient)
+	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
@@ -240,6 +259,24 @@ func (c *Client) RenewTun(fd int) error {
 	return e.RenewTun(fd)
 }
 
+func (c *Client) GetTunSettings() (*TunSettings, error) {
+	cc := c.getConnectClient()
+	if cc == nil {
+		return nil, fmt.Errorf("engine not running")
+	}
+
+	e := cc.Engine()
+	if e == nil {
+		return nil, fmt.Errorf("engine not initialized")
+	}
+
+	routes, searchDomains := e.TunSettings()
+	return &TunSettings{
+		Routes:        strings.Join(routes, ";"),
+		SearchDomains: strings.Join(searchDomains, ";"),
+	}, nil
+}
+
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.
 // It works both with and without a running engine.
 func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (string, error) {

client/android/login.go

@@ -4,6 +4,8 @@ import (
 	"context"
 	"fmt"
 
+	log "github.com/sirupsen/logrus"
+
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/system"
@@ -36,12 +38,20 @@ type Auth struct {
 }
 
 // NewAuth instantiate Auth struct and validate the management URL
+//
+// The configuration at cfgPath is reused when one is already there, and only created when it is
+// not. Building a fresh in-memory config unconditionally gives the client a new WireGuard key on
+// every call: the peer registers under that key, the key is written out, and any peer registered by
+// an earlier call is orphaned on the server. It also breaks a client that enrols and then runs from
+// the persisted config, because the identity it registered is not the one it runs with — the
+// management stream rejects it with "no peer auth method provided".
 func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
 	inputCfg := profilemanager.ConfigInput{
+		ConfigPath:    cfgPath,
 		ManagementURL: mgmURL,
 	}
 
-	cfg, err := profilemanager.CreateInMemoryConfig(inputCfg)
+	cfg, err := profilemanager.UpdateOrCreateConfig(inputCfg)
 	if err != nil {
 		return nil, err
 	}
@@ -53,11 +63,14 @@ func NewAuth(cfgPath string, mgmURL string) (*Auth, error) {
 	}, nil
 }
 
-// NewAuthWithConfig instantiate Auth based on existing config
-func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config) *Auth {
+// NewAuthWithConfig instantiate Auth based on existing config. cfgPath is the
+// file the config was loaded from; it identifies the profile whose account email
+// backs the login_hint.
+func NewAuthWithConfig(ctx context.Context, config *profilemanager.Config, cfgPath string) *Auth {
 	return &Auth{
-		ctx:    ctx,
-		config: config,
+		ctx:     ctx,
+		config:  config,
+		cfgPath: cfgPath,
 	}
 }
 
@@ -150,12 +163,14 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 	}
 
 	jwtToken := ""
+	email := ""
 	if needsLogin {
 		tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
 		if err != nil {
 			return fmt.Errorf("interactive sso login failed: %v", err)
 		}
 		jwtToken = tokenInfo.GetTokenToUse()
+		email = tokenInfo.Email
 	}
 
 	err, _ = authClient.Login(a.ctx, "", jwtToken)
@@ -163,17 +178,42 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 		return fmt.Errorf("login failed: %v", err)
 	}
 
+	// Stored after Login, not before: a rejected token must not leave a hint
+	// pointing at an account that cannot be used.
+	if email != "" && a.cfgPath != "" {
+		if err := writeProfileEmail(a.cfgPath, email); err != nil {
+			log.Warnf("failed to store profile account email: %v", err)
+		}
+	}
+
 	go urlOpener.OnLoginSuccess()
 
 	return nil
 }
 
+// loginHintSetter is implemented by both concrete flows (PKCE and device code)
+// but absent from the OAuthFlow interface, hence the assertion below — the same
+// way internal/auth wires it in authenticateWithPKCEFlow.
+type loginHintSetter interface {
+	SetLoginHint(hint string)
+}
+
 func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, isAndroidTV bool) (*auth.TokenInfo, error) {
 	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV)
 	if err != nil {
 		return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
 	}
 
+	// An empty hint is deliberate, not a fallback: a fresh or logged-out profile
+	// leaves the choice to the IdP, which is how accounts get switched.
+	if a.cfgPath != "" {
+		if hint := readProfileEmail(a.cfgPath); hint != "" {
+			if setter, ok := oAuthFlow.(loginHintSetter); ok {
+				setter.SetLoginHint(hint)
+			}
+		}
+	}
+
 	flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO())
 	if err != nil {
 		return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err)

client/android/login_test.go

@@ -0,0 +1,51 @@
+package android
+
+import (
+	"path/filepath"
+	"testing"
+)
+
+// NewAuth must reuse the configuration already at cfgPath rather than building a fresh one.
+//
+// Creating a new in-memory config on every call gives the client a new WireGuard private key each
+// time. The peer registers under that key and the key is written out, so a peer registered by an
+// earlier call is orphaned on the server — a client that enrols twice leaves two entries and owns
+// neither. It also breaks enrol-then-run: RunWithoutLogin reloads the configuration from disk, so
+// the identity that registered is not the identity that runs, and the management stream rejects it
+// with "no peer auth method provided, please use a setup key or interactive SSO login".
+func TestNewAuth_ReusesPersistedIdentity(t *testing.T) {
+	cfgPath := filepath.Join(t.TempDir(), "config.json")
+
+	first, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("first NewAuth: %v", err)
+	}
+	if first.config.PrivateKey == "" {
+		t.Fatal("first NewAuth produced no private key")
+	}
+
+	second, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("second NewAuth: %v", err)
+	}
+
+	if second.config.PrivateKey != first.config.PrivateKey {
+		t.Errorf("private key changed between calls: a second enrolment would orphan the peer registered by the first")
+	}
+}
+
+// A missing configuration is still created, so a first enrolment works unchanged.
+func TestNewAuth_CreatesConfigWhenAbsent(t *testing.T) {
+	cfgPath := filepath.Join(t.TempDir(), "config.json")
+
+	auth, err := NewAuth(cfgPath, "https://api.example.com:443")
+	if err != nil {
+		t.Fatalf("NewAuth: %v", err)
+	}
+	if auth.config == nil || auth.config.PrivateKey == "" {
+		t.Fatal("NewAuth did not create a usable configuration")
+	}
+	if auth.cfgPath != cfgPath {
+		t.Errorf("cfgPath = %q, want %q", auth.cfgPath, cfgPath)
+	}
+}

client/android/profile_manager.go

@@ -13,18 +13,17 @@ import (
 )
 
 const (
-	// Android-specific config filename (different from desktop default.json)
-	defaultConfigFilename = "netbird.cfg"
-	// Subdirectory for non-default profiles (must match Java Preferences.java)
-	profilesSubdir = "profiles"
 	// Android uses a single user context per app (non-empty username required by ServiceManager)
 	androidUsername = "android"
 )
 
 // Profile represents a profile for gomobile
 type Profile struct {
-	ID       string
-	Name     string
+	ID   string
+	Name string
+	// Email is the account this profile last logged in with, "" if it never
+	// completed an SSO login or was logged out. See profile_state.go.
+	Email    string
 	IsActive bool
 }
 
@@ -101,6 +100,7 @@ func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
 		profiles = append(profiles, &Profile{
 			ID:       p.ID.String(),
 			Name:     p.Name,
+			Email:    pm.profileEmail(p.ID.String()),
 			IsActive: p.IsActive,
 		})
 	}
@@ -123,7 +123,22 @@ func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
 	if err != nil {
 		return nil, fmt.Errorf("failed to resolve active profile %q: %w", activeState.ID, err)
 	}
-	return &Profile{ID: prof.ID.String(), Name: prof.Name, IsActive: true}, nil
+	return &Profile{
+		ID:       prof.ID.String(),
+		Name:     prof.Name,
+		Email:    pm.profileEmail(prof.ID.String()),
+		IsActive: true,
+	}, nil
+}
+
+// profileEmail returns the account email recorded for a profile. Display-only, so
+// an unresolvable path degrades to "" rather than an error.
+func (pm *ProfileManager) profileEmail(id string) string {
+	configPath, err := pm.getProfileConfigPath(id)
+	if err != nil {
+		return ""
+	}
+	return readProfileEmail(configPath)
 }
 
 // SwitchProfile switches to a different profile
@@ -185,6 +200,11 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 		return fmt.Errorf("failed to save config: %w", err)
 	}
 
+	// Not fatal: a stale hint costs an account switch, not the logout itself.
+	if err := removeProfileEmail(configPath); err != nil {
+		log.Warnf("failed to clear stored account email for profile %s: %v", id, err)
+	}
+
 	log.Infof("logged out from profile: %s", id)
 	return nil
 }

client/android/profile_state.go

@@ -0,0 +1,108 @@
+package android
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"path/filepath"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/util"
+)
+
+const (
+	// Android-specific config filename (different from desktop default.json)
+	defaultConfigFilename = "netbird.cfg"
+	// Subdirectory for non-default profiles (must match Java Preferences.java)
+	profilesSubdir = "profiles"
+	// profileAccountSuffix names the file holding the profile's account email.
+	// Deliberately not ".state.json", which desktop uses for the same data:
+	// there the email and the engine's state manager live in different
+	// directories, but on Android both resolve under files/, so sharing the name
+	// would have the two overwrite each other — the state manager rewrites the
+	// whole file from its own keys (see statemanager.Manager.PersistState), and
+	// this package's writer does the same in reverse.
+	profileAccountSuffix = ".account.json"
+)
+
+// profileAccountPathFor derives the account file path from a profile's config
+// path: netbird.cfg -> netbird.account.json, <id>.json -> <id>.account.json.
+//
+// Deriving from the config path rather than resolving the active profile keeps
+// the write on the profile the login actually ran for: Auth.login runs in a
+// goroutine, so the active profile can change under a flow already in flight.
+func profileAccountPathFor(configPath string) (string, error) {
+	if configPath == "" {
+		return "", fmt.Errorf("empty config path")
+	}
+
+	base := filepath.Base(configPath)
+	stem := strings.TrimSuffix(base, filepath.Ext(base))
+	if stem == "" || stem == "." {
+		return "", fmt.Errorf("config path %q has no filename stem", configPath)
+	}
+
+	return filepath.Join(filepath.Dir(configPath), stem+profileAccountSuffix), nil
+}
+
+// readProfileEmail returns the account email stored for the profile whose config
+// lives at configPath. A missing or unreadable file yields "", which leaves the
+// account choice to the IdP.
+func readProfileEmail(configPath string) string {
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		log.Debugf("no profile account path for login hint: %v", err)
+		return ""
+	}
+
+	var state profilemanager.ProfileState
+	if _, err := util.ReadJson(accountPath, &state); err != nil {
+		if !os.IsNotExist(err) {
+			log.Debugf("failed to read profile account for login hint: %v", err)
+		}
+		return ""
+	}
+
+	return state.Email
+}
+
+// writeProfileEmail records the account email for the profile whose config lives
+// at configPath, so later logins can pass it as an OIDC login_hint. An empty
+// email is ignored rather than blanking what is already stored.
+func writeProfileEmail(configPath string, email string) error {
+	if email == "" {
+		return nil
+	}
+
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		return fmt.Errorf("resolve profile account path: %w", err)
+	}
+
+	state := profilemanager.ProfileState{Email: email}
+	if err := util.WriteJsonWithRestrictedPermission(context.Background(), accountPath, state); err != nil {
+		return fmt.Errorf("write profile account: %w", err)
+	}
+
+	return nil
+}
+
+// removeProfileEmail drops the stored account email. Called on logout: while the
+// email is on disk it goes out as a login_hint, which would steer the next login
+// straight back into the account just logged out of. Mirrors the desktop UI's
+// RemoveProfileState call.
+func removeProfileEmail(configPath string) error {
+	accountPath, err := profileAccountPathFor(configPath)
+	if err != nil {
+		return fmt.Errorf("resolve profile account path: %w", err)
+	}
+
+	if err := os.Remove(accountPath); err != nil && !os.IsNotExist(err) {
+		return fmt.Errorf("remove profile account: %w", err)
+	}
+
+	return nil
+}

client/android/profile_state_test.go

@@ -0,0 +1,161 @@
+package android
+
+import (
+	"os"
+	"path/filepath"
+	"testing"
+)
+
+func TestProfileAccountPathFor(t *testing.T) {
+	tests := []struct {
+		name       string
+		configPath string
+		want       string
+		wantErr    bool
+	}{
+		{
+			name:       "default profile",
+			configPath: "/data/data/io.netbird.client/files/netbird.cfg",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/netbird.account.json"),
+		},
+		{
+			name:       "id profile",
+			configPath: "/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.json",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/profiles/4c5f5c8198c3989cffb5b5394f5a7ae0.account.json"),
+		},
+		{
+			name:       "legacy name-keyed profile is handled the same way",
+			configPath: "/data/data/io.netbird.client/files/profiles/work.json",
+			want:       filepath.FromSlash("/data/data/io.netbird.client/files/profiles/work.account.json"),
+		},
+		{
+			name:       "empty path is rejected",
+			configPath: "",
+			wantErr:    true,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			got, err := profileAccountPathFor(tt.configPath)
+			if tt.wantErr {
+				if err == nil {
+					t.Fatalf("expected an error, got path %q", got)
+				}
+				return
+			}
+			if err != nil {
+				t.Fatalf("unexpected error: %v", err)
+			}
+			if got != tt.want {
+				t.Errorf("got %q, want %q", got, tt.want)
+			}
+		})
+	}
+}
+
+func TestProfileAccountPathForDefaultDoesNotCollide(t *testing.T) {
+	root := "/data/data/io.netbird.client/files"
+
+	defaultAccount, err := profileAccountPathFor(filepath.Join(root, defaultConfigFilename))
+	if err != nil {
+		t.Fatalf("default profile: %v", err)
+	}
+
+	idAccount, err := profileAccountPathFor(filepath.Join(root, profilesSubdir, "abc123.json"))
+	if err != nil {
+		t.Fatalf("id profile: %v", err)
+	}
+
+	if defaultAccount == idAccount {
+		t.Fatalf("default and id profile share an account file: %q", defaultAccount)
+	}
+}
+
+// The account file must never land on the engine state file: on Android both
+// resolve under files/, and the state manager rewrites the whole file from its
+// own keys, so sharing a path would have the two overwrite each other. The
+// expected names here mirror ProfileManager.GetStateFilePath.
+func TestProfileAccountPathAvoidsEngineStateFile(t *testing.T) {
+	root := "/data/data/io.netbird.client/files"
+
+	cases := []struct {
+		configPath  string
+		engineState string
+	}{
+		{
+			configPath:  filepath.Join(root, defaultConfigFilename),
+			engineState: filepath.Join(root, "state.json"),
+		},
+		{
+			configPath:  filepath.Join(root, profilesSubdir, "abc123.json"),
+			engineState: filepath.Join(root, profilesSubdir, "abc123.state.json"),
+		},
+	}
+
+	for _, c := range cases {
+		account, err := profileAccountPathFor(c.configPath)
+		if err != nil {
+			t.Fatalf("%s: %v", c.configPath, err)
+		}
+		if account == c.engineState {
+			t.Errorf("account file collides with the engine state file: %q", account)
+		}
+	}
+}
+
+func TestWriteThenReadProfileEmail(t *testing.T) {
+	configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
+	if err := ensureDirFor(t, configPath); err != nil {
+		t.Fatalf("prepare dir: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != "" {
+		t.Errorf("expected no email before a login, got %q", got)
+	}
+
+	const email = "user@example.com"
+	if err := writeProfileEmail(configPath, email); err != nil {
+		t.Fatalf("write: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != email {
+		t.Errorf("got %q, want %q", got, email)
+	}
+
+	if err := removeProfileEmail(configPath); err != nil {
+		t.Fatalf("remove: %v", err)
+	}
+	if got := readProfileEmail(configPath); got != "" {
+		t.Errorf("expected no email after logout, got %q", got)
+	}
+
+	// Logout may run on a never-logged-in profile, so a second remove must pass.
+	if err := removeProfileEmail(configPath); err != nil {
+		t.Fatalf("second remove should be a no-op: %v", err)
+	}
+}
+
+func TestWriteProfileEmailIgnoresEmpty(t *testing.T) {
+	configPath := filepath.Join(t.TempDir(), "profiles", "abc123.json")
+	if err := ensureDirFor(t, configPath); err != nil {
+		t.Fatalf("prepare dir: %v", err)
+	}
+
+	const email = "user@example.com"
+	if err := writeProfileEmail(configPath, email); err != nil {
+		t.Fatalf("write: %v", err)
+	}
+	if err := writeProfileEmail(configPath, ""); err != nil {
+		t.Fatalf("write empty: %v", err)
+	}
+
+	if got := readProfileEmail(configPath); got != email {
+		t.Errorf("empty write clobbered the stored email: got %q, want %q", got, email)
+	}
+}
+
+func ensureDirFor(t *testing.T, path string) error {
+	t.Helper()
+	return os.MkdirAll(filepath.Dir(path), 0o700)
+}

client/android/session.go

@@ -278,7 +278,7 @@ func (c *Client) endExtend() {
 }
 
 func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isAndroidTV bool) error {
-	cfg, _, cc := c.stateSnapshot()
+	cfg, cfgPath, cc := c.authSnapshot()
 	if cfg == nil || cc == nil {
 		return fmt.Errorf("engine is not running")
 	}
@@ -293,7 +293,10 @@ func (c *Client) extendAuthSession(ctx context.Context, urlOpener URLOpener, isA
 	}
 	defer authClient.Close()
 
-	a := &Auth{ctx: ctx, config: cfg}
+	// Passing the config path makes the flow pick up the login_hint: an extend
+	// renews the session of the account already signed in, so it must not stop to
+	// offer a choice.
+	a := NewAuthWithConfig(ctx, cfg, cfgPath)
 	tokenInfo, err := a.foregroundGetTokenInfo(authClient, urlOpener, isAndroidTV)
 	if err != nil {
 		return fmt.Errorf("interactive sso login failed: %v", err)

client/internal/connect.go

@@ -113,11 +113,14 @@ func (c *ConnectClient) RunOnAndroid(
 	stateFilePath string,
 	cacheDir string,
 ) error {
+	notifier := tunnelnotifier.New(networkChangeListener, nil)
+	defer notifier.Close()
+
 	// in case of non Android os these variables will be nil
 	mobileDependency := MobileDependency{
 		TunAdapter:            tunAdapter,
 		IFaceDiscover:         iFaceDiscover,
-		NetworkChangeListener: networkChangeListener,
+		NetworkChangeListener: notifier,
 		HostDNSAddresses:      dnsAddresses,
 		DnsReadyListener:      dnsReadyListener,
 		StateFilePath:         stateFilePath,

client/internal/dns/notifier.go

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

client/internal/dns/server.go

@@ -252,7 +252,7 @@ func NewDefaultServerPermanentUpstream(
 	ds.hostsDNSHolder.set(hostsDnsList)
 	ds.permanent = true
 	ds.currentConfig = dnsConfigToHostDNSConfig(config, ds.service.RuntimeIP(), ds.service.RuntimePort())
-	ds.searchDomainNotifier = newNotifier(ds.SearchDomains())
+	ds.searchDomainNotifier = newNotifier(ds.searchDomains())
 	ds.searchDomainNotifier.setListener(listener)
 	setServerDns(ds)
 	return ds
@@ -602,6 +602,12 @@ func (s *DefaultServer) UpdateDNSServer(serial uint64, update nbdns.Config) erro
 }
 
 func (s *DefaultServer) SearchDomains() []string {
+	s.mux.Lock()
+	defer s.mux.Unlock()
+	return s.searchDomains()
+}
+
+func (s *DefaultServer) searchDomains() []string {
 	var searchDomains []string
 
 	for _, dConf := range s.currentConfig.Domains {
@@ -686,7 +692,7 @@ func (s *DefaultServer) applyConfiguration(update nbdns.Config) error {
 	}()
 
 	if s.searchDomainNotifier != nil {
-		s.searchDomainNotifier.onNewSearchDomains(s.SearchDomains())
+		s.searchDomainNotifier.onNewSearchDomains(s.searchDomains())
 	}
 
 	s.updateNSGroupStates(update.NameServerGroups)

client/internal/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"
@@ -186,7 +187,7 @@ 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
@@ -329,7 +330,7 @@ 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(),
@@ -572,12 +573,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	}
 	e.stateManager.Start()
 
-	initialRoutes, dnsConfig, dnsFeatureFlag, err := e.readInitialSettings()
-	if err != nil {
-		return fmt.Errorf("read initial settings: %w", err)
-	}
-
-	dnsServer, err := e.newDnsServer(dnsConfig)
+	dnsServer, err := e.newDnsServer()
 	if err != nil {
 		return fmt.Errorf("create dns server: %w", err)
 	}
@@ -595,10 +591,8 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		WGInterface:         e.wgInterface,
 		StatusRecorder:      e.statusRecorder,
 		RelayManager:        e.relayManager,
-		InitialRoutes:       initialRoutes,
 		StateManager:        e.stateManager,
 		DNSServer:           dnsServer,
-		DNSFeatureFlag:      dnsFeatureFlag,
 		PeerStore:           e.peerStore,
 		DisableClientRoutes: e.config.DisableClientRoutes,
 		DisableServerRoutes: e.config.DisableServerRoutes,
@@ -2102,42 +2096,6 @@ func (e *Engine) close() {
 	}
 }
 
-func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, error) {
-	if runtime.GOOS != "android" {
-		// nolint:nilnil
-		return nil, nil, false, nil
-	}
-
-	info := system.GetInfo(e.ctx)
-	info.SetFlags(
-		e.config.RosenpassEnabled,
-		e.config.RosenpassPermissive,
-		&e.config.ServerSSHAllowed,
-		e.config.DisableClientRoutes,
-		e.config.DisableServerRoutes,
-		e.config.DisableDNS,
-		e.config.DisableFirewall,
-		e.config.BlockLANAccess,
-		e.config.BlockInbound,
-		e.config.DisableIPv6,
-		e.config.SyncMessageVersion,
-		e.config.EnableSSHRoot,
-		e.config.EnableSSHSFTP,
-		e.config.EnableSSHLocalPortForwarding,
-		e.config.EnableSSHRemotePortForwarding,
-		e.config.DisableSSHAuth,
-	)
-
-	netMap, err := e.mgmClient.GetNetworkMap(info)
-	if err != nil {
-		return nil, nil, false, err
-	}
-	routes := toRoutes(netMap.GetRoutes())
-	dnsCfg := toDNSConfig(netMap.GetDNSConfig(), e.wgInterface.Address())
-	dnsFeatureFlag := toDNSFeatureFlag(netMap)
-	return routes, &dnsCfg, dnsFeatureFlag, nil
-}
-
 func (e *Engine) newWgIface() (*iface.WGIface, error) {
 	transportNet, err := e.newStdNet()
 	if err != nil {
@@ -2172,7 +2130,7 @@ func (e *Engine) newWgIface() (*iface.WGIface, error) {
 func (e *Engine) wgInterfaceCreate() (err error) {
 	switch runtime.GOOS {
 	case "android":
-		err = e.wgInterface.CreateOnAndroid(e.routeManager.InitialRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
+		err = e.wgInterface.CreateOnAndroid(e.routeManager.CurrentRouteRange(), e.dnsServer.DnsIP().String(), e.dnsServer.SearchDomains())
 	case "ios":
 		e.mobileDep.NetworkChangeListener.SetInterfaceIP(e.config.WgAddr.String())
 		if e.config.WgAddr.HasIPv6() {
@@ -2185,7 +2143,7 @@ func (e *Engine) wgInterfaceCreate() (err error) {
 	return err
 }
 
-func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
+func (e *Engine) newDnsServer() (dns.Server, error) {
 	// due to tests where we are using a mocked version of the DNS server
 	if e.dnsServer != nil {
 		return e.dnsServer, nil
@@ -2197,7 +2155,7 @@ func (e *Engine) newDnsServer(dnsConfig *nbdns.Config) (dns.Server, error) {
 			e.ctx,
 			e.wgInterface,
 			e.mobileDep.HostDNSAddresses,
-			*dnsConfig,
+			nbdns.Config{},
 			e.mobileDep.NetworkChangeListener,
 			e.statusRecorder,
 			e.config.DisableDNS,
@@ -2858,7 +2816,7 @@ 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
@@ -2874,9 +2832,9 @@ 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 {
@@ -2886,8 +2844,8 @@ 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/engine_tunsettings.go

@@ -0,0 +1,20 @@
+package internal
+
+func (e *Engine) TunSettings() ([]string, []string) {
+	e.syncMsgMux.Lock()
+	routeManager := e.routeManager
+	dnsServer := e.dnsServer
+	e.syncMsgMux.Unlock()
+
+	var routes []string
+	if routeManager != nil {
+		routes = routeManager.CurrentRouteRange()
+	}
+
+	var searchDomains []string
+	if dnsServer != nil {
+		searchDomains = dnsServer.SearchDomains()
+	}
+
+	return routes, searchDomains
+}

client/internal/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

@@ -3,28 +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,
 	},
@@ -52,92 +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) {
@@ -320,7 +270,7 @@ func newWGTimeoutTestConn(rosenpassEnabled bool, disconnected *[]string) *Conn {
 		ctx:           context.Background(),
 		config:        cfg,
 		Log:           log.WithField("peer", cfg.Key),
-		metricsStages: &MetricsStages{},
+		metricsStages: &metricsstages.MetricsStages{},
 	}
 	conn.SetOnDisconnected(func(remotePeer string) {
 		*disconnected = append(*disconnected, remotePeer)
@@ -339,20 +289,20 @@ func TestConn_onWGDisconnected_EscalatesToRosenpassReset(t *testing.T) {
 	conn := newWGTimeoutTestConn(true, &disconnected)
 
 	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
-		conn.onWGDisconnected(conn.ctx)
+		conn.handleWGTimeout()
 	}
 	assert.Empty(t, disconnected, "escalation must not fire below the threshold")
 
-	conn.onWGDisconnected(conn.ctx)
+	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.onWGDisconnected(conn.ctx)
+		conn.handleWGTimeout()
 	}
 	assert.Len(t, disconnected, 1, "escalation must restart counting after firing")
 
-	conn.onWGDisconnected(conn.ctx)
+	conn.handleWGTimeout()
 	assert.Len(t, disconnected, 2, "continued timeouts must escalate again")
 }
 
@@ -364,12 +314,12 @@ func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) {
 	conn := newWGTimeoutTestConn(true, &disconnected)
 
 	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
-		conn.onWGDisconnected(conn.ctx)
+		conn.handleWGTimeout()
 	}
-	conn.onWGCheckSuccess()
+	conn.handleWGCheckSuccess()
 
 	for i := 0; i < wgTimeoutEscalationThreshold-1; i++ {
-		conn.onWGDisconnected(conn.ctx)
+		conn.handleWGTimeout()
 	}
 	assert.Empty(t, disconnected, "handshake success must reset the timeout count")
 }
@@ -377,12 +327,30 @@ func TestConn_onWGDisconnected_CheckSuccessResetsEscalation(t *testing.T) {
 // TestConn_onWGDisconnected_NoEscalationWithoutRosenpass: without rosenpass
 // there is no per-peer key state to reset; repeated timeouts must not report
 // disconnects.
+func TestConn_handleEvent_DropsStaleWGTimeout(t *testing.T) {
+	var disconnected []string
+	conn := newWGTimeoutTestConn(true, &disconnected)
+
+	staleCtx, cancel := context.WithCancel(context.Background())
+	cancel()
+	for i := 0; i < wgTimeoutEscalationThreshold; i++ {
+		conn.handleEvent(evWGTimeout{ctx: staleCtx})
+	}
+	assert.Empty(t, disconnected, "timeouts from a cancelled watcher must be dropped")
+
+	liveCtx := context.Background()
+	for i := 0; i < wgTimeoutEscalationThreshold; i++ {
+		conn.handleEvent(evWGTimeout{ctx: liveCtx})
+	}
+	assert.Len(t, disconnected, 1, "timeouts from the live watcher must be dispatched")
+}
+
 func TestConn_onWGDisconnected_NoEscalationWithoutRosenpass(t *testing.T) {
 	var disconnected []string
 	conn := newWGTimeoutTestConn(false, &disconnected)
 
 	for i := 0; i < wgTimeoutEscalationThreshold*3; i++ {
-		conn.onWGDisconnected(conn.ctx)
+		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 +1,83 @@
+package peer
+
+import (
+	"context"
+	"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
+
+// staleableEvent is implemented by events tied to the lifetime of a transport
+// component (WG watcher, ICE agent, relay connection). Each such component runs
+// under its own context, cancelled when the component is superseded; an event
+// carrying a cancelled context is dropped at dispatch time. A cancel performed
+// by an earlier event in the same drained batch already suppresses it.
+type staleableEvent interface {
+	isStale() bool
+}
+
+// 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 {
+	ctx context.Context
+}
+
+func (e evWGTimeout) isStale() bool { return e.ctx.Err() != nil }
+
+// 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"
@@ -8,6 +8,7 @@ import (
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/iface/configurer"
+	"github.com/netbirdio/netbird/client/internal/peer/state_dump"
 )
 
 const (
@@ -29,7 +30,7 @@ type WGWatcher struct {
 	log           *log.Entry
 	wgIfaceStater WGInterfaceStater
 	peerKey       string
-	stateDump     *stateDump
+	stateDump     *state_dump.StateDump
 
 	// initialHandshake is not thread-safe; never call PrepareInitialHandshake and EnableWgWatcher concurrently.
 	initialHandshake time.Time
@@ -37,7 +38,7 @@ 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,

client/internal/peer/wg_watcher/wg_watcher_test.go

@@ -1,4 +1,4 @@
-package peer
+package wg_watcher
 
 import (
 	"context"
@@ -9,6 +9,8 @@ import (
 	log "github.com/sirupsen/logrus"
 
 	"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 {
@@ -56,7 +58,7 @@ func TestWGWatcher_CheckSuccessCallback(t *testing.T) {
 	// platforms with coarse clock resolution (Windows), where two time.Now() calls
 	// microseconds apart can return the same instant and read as a timed-out handshake.
 	stats := &mockHandshakeStats{handshake: time.Now().Add(-time.Hour)}
-	watcher := NewWGWatcher(mlog, stats, "", newStateDump("peer", mlog, &Status{}))
+	watcher := NewWGWatcher(mlog, stats, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
 
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
@@ -65,14 +67,18 @@ func TestWGWatcher_CheckSuccessCallback(t *testing.T) {
 
 	firstHandshake := make(chan struct{}, 1)
 	checkSuccess := make(chan struct{}, 1)
-	go watcher.EnableWgWatcher(ctx, time.Now(), func() {}, func(when time.Time) {
-		firstHandshake <- struct{}{}
-	}, func() {
-		select {
-		case checkSuccess <- struct{}{}:
-		default:
-		}
-	})
+	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()
 
@@ -87,6 +93,11 @@ func TestWGWatcher_CheckSuccessCallback(t *testing.T) {
 		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) {
@@ -95,7 +106,7 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
 
 	mlog := log.WithField("peer", "tet")
 	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
+	watcher := NewWGWatcher(mlog, mocWgIface, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
 
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
@@ -127,7 +138,7 @@ func TestWGWatcher_ReEnable(t *testing.T) {
 
 	mlog := log.WithField("peer", "tet")
 	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
+	watcher := NewWGWatcher(mlog, mocWgIface, "", state_dump.NewStateDump("peer", mlog, &status.Recorder{}))
 
 	ctx, cancel := context.WithCancel(context.Background())
 	watcher.PrepareInitialHandshake()

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/state.go

@@ -45,12 +45,35 @@ func (pm *ProfileManager) GetProfileState(id ID) (*ProfileState, error) {
 	return &state, nil
 }
 
-func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
+// SetProfileState writes the state file of the profile identified by id. Prefer
+// it over SetActiveProfileState whenever the caller knows which profile the data
+// belongs to: an SSO login spans seconds of user interaction, and the active
+// profile can change during it, which would file the account email under
+// whichever profile happened to be active when the flow returned.
+func (pm *ProfileManager) SetProfileState(id ID, state *ProfileState) error {
 	configDir, err := getConfigDir()
 	if err != nil {
 		return fmt.Errorf("get config directory: %w", err)
 	}
 
+	if id == "" {
+		return fmt.Errorf("empty profile ID")
+	}
+	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
+		return fmt.Errorf("invalid profile ID: %q", id)
+	}
+
+	stateFile := filepath.Join(configDir, id.String()+".state.json")
+	if err := util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state); err != nil {
+		return fmt.Errorf("write profile state: %w", err)
+	}
+
+	return nil
+}
+
+// SetActiveProfileState writes the state file of whichever profile is active at
+// call time. Use SetProfileState when the target profile is known.
+func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 	activeProf, err := pm.GetActiveProfile()
 	if err != nil {
 		if errors.Is(err, ErrNoActiveProfile) {
@@ -59,18 +82,7 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 		return fmt.Errorf("get active profile: %w", err)
 	}
 
-	id := activeProf.ID
-	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
-		return fmt.Errorf("invalid active profile ID: %q", id)
-	}
-
-	stateFile := filepath.Join(configDir, id.String()+".state.json")
-	err = util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state)
-	if err != nil {
-		return fmt.Errorf("write profile state: %w", err)
-	}
-
-	return nil
+	return pm.SetProfileState(activeProf.ID, state)
 }
 
 // RemoveProfileState deletes the per-profile state file (which holds the

client/internal/routemanager/dnsinterceptor/handler.go

@@ -479,7 +479,7 @@ func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix, logger
 
 // internalDnatFw checks if the firewall supports internal DNAT
 func (d *DnsInterceptor) internalDnatFw() (internalDNATer, bool) {
-	if d.firewall == nil || runtime.GOOS != "android" {
+	if d.firewall == nil || d.fakeIPManager == nil || runtime.GOOS != "android" {
 		return nil, false
 	}
 	fw, ok := d.firewall.(internalDNATer)

client/internal/routemanager/manager.go

@@ -8,14 +8,13 @@ import (
 	"net/netip"
 	"net/url"
 	"runtime"
-	"slices"
+	"sort"
 	"strings"
 	"sync"
 	"sync/atomic"
 	"syscall"
 	"time"
 
-	"github.com/google/uuid"
 	"github.com/hashicorp/go-multierror"
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/exp/maps"
@@ -62,7 +61,7 @@ type Manager interface {
 	GetActiveClientRoutes() route.HAMap
 	GetClientRoutesWithNetID() map[route.NetID][]*route.Route
 	SetRouteChangeListener(listener listener.NetworkChangeListener)
-	InitialRouteRange() []string
+	CurrentRouteRange() []string
 	SetFirewall(firewall.Manager) error
 	SetDNSForwarderPort(port uint16)
 	ReconcilePeerAllowedIPs(peerKey string) error
@@ -76,10 +75,8 @@ type ManagerConfig struct {
 	WGInterface         iface.WGIface
 	StatusRecorder      *peer.Status
 	RelayManager        *relayClient.Manager
-	InitialRoutes       []*route.Route
 	StateManager        *statemanager.Manager
 	DNSServer           dns.Server
-	DNSFeatureFlag      bool
 	PeerStore           *peerstore.Store
 	DisableClientRoutes bool
 	DisableServerRoutes bool
@@ -149,45 +146,12 @@ func NewManager(config ManagerConfig) *DefaultManager {
 	useNoop := netstack.IsEnabled() || config.DisableClientRoutes
 	dm.setupRefCounters(useNoop)
 
-	// don't proceed with client routes if it is disabled
-	if config.DisableClientRoutes {
-		return dm
-	}
-
-	if runtime.GOOS == "android" {
-		dm.setupAndroidRoutes(config)
-	}
 	return dm
 }
-func (m *DefaultManager) setupAndroidRoutes(config ManagerConfig) {
-	cr := m.initialClientRoutes(config.InitialRoutes)
 
-	routesForComparison := slices.Clone(cr)
-
-	if config.DNSFeatureFlag {
-		m.fakeIPManager = fakeip.NewManager()
-
-		v4ID := uuid.NewString()
-		fakeIPRoute := &route.Route{
-			ID:          route.ID(v4ID),
-			Network:     m.fakeIPManager.GetFakeIPBlock(),
-			NetID:       route.NetID(v4ID),
-			Peer:        m.pubKey,
-			NetworkType: route.IPv4Network,
-		}
-		v6ID := uuid.NewString()
-		fakeIPv6Route := &route.Route{
-			ID:          route.ID(v6ID),
-			Network:     m.fakeIPManager.GetFakeIPv6Block(),
-			NetID:       route.NetID(v6ID),
-			Peer:        m.pubKey,
-			NetworkType: route.IPv6Network,
-		}
-		cr = append(cr, fakeIPRoute, fakeIPv6Route)
-		m.notifier.SetFakeIPRoutes([]*route.Route{fakeIPRoute, fakeIPv6Route})
-	}
-
-	m.notifier.SetInitialClientRoutes(cr, routesForComparison)
+func (m *DefaultManager) enableFakeIPRoutes() {
+	m.fakeIPManager = fakeip.NewManager()
+	m.notifier.NotifyRouteChange()
 }
 
 func (m *DefaultManager) setupRefCounters(useNoop bool) {
@@ -464,6 +428,9 @@ func (m *DefaultManager) UpdateRoutes(
 
 	var merr *multierror.Error
 	if !m.disableClientRoutes {
+		if runtime.GOOS == "android" && useNewDNSRoute && m.fakeIPManager == nil {
+			m.enableFakeIPRoutes()
+		}
 
 		// Update route selector based on management server's isSelected status
 		m.updateRouteSelectorFromManagement(clientRoutes)
@@ -500,9 +467,32 @@ func (m *DefaultManager) SetRouteChangeListener(listener listener.NetworkChangeL
 	m.notifier.SetListener(listener)
 }
 
-// InitialRouteRange return the list of initial routes. It used by mobile systems
-func (m *DefaultManager) InitialRouteRange() []string {
-	return m.notifier.GetInitialRouteRanges()
+// CurrentRouteRange returns the current TUN route list. It is used by mobile systems
+func (m *DefaultManager) CurrentRouteRange() []string {
+	m.mux.Lock()
+	defer m.mux.Unlock()
+
+	if m.disableClientRoutes {
+		return nil
+	}
+
+	filtered := m.routeSelector.FilterSelectedExitNodes(m.clientRoutes)
+	var nets []string
+	for _, routes := range filtered {
+		for _, r := range routes {
+			if r.IsDynamic() {
+				continue
+			}
+			nets = append(nets, r.NetString())
+		}
+	}
+
+	if m.fakeIPManager != nil {
+		nets = append(nets, m.fakeIPManager.GetFakeIPBlock().String(), m.fakeIPManager.GetFakeIPv6Block().String())
+	}
+
+	sort.Strings(nets)
+	return nets
 }
 
 // GetRouteSelector returns the route selector
@@ -700,16 +690,6 @@ func (m *DefaultManager) ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]
 	return newServerRoutesMap, newClientRoutesIDMap
 }
 
-func (m *DefaultManager) initialClientRoutes(initialRoutes []*route.Route) []*route.Route {
-	_, crMap := m.ClassifyRoutes(initialRoutes)
-	rs := make([]*route.Route, 0, len(crMap))
-	for _, routes := range crMap {
-		rs = append(rs, routes...)
-	}
-
-	return rs
-}
-
 func isRouteSupported(route *route.Route) bool {
 	if netstack.IsEnabled() || !nbnet.CustomRoutingDisabled() || route.IsDynamic() {
 		return true

client/internal/routemanager/mock.go

@@ -30,8 +30,8 @@ func (m *MockManager) Init() error {
 	return nil
 }
 
-// InitialRouteRange mock implementation of InitialRouteRange from Manager interface
-func (m *MockManager) InitialRouteRange() []string {
+// CurrentRouteRange mock implementation of CurrentRouteRange from Manager interface
+func (m *MockManager) CurrentRouteRange() []string {
 	return nil
 }
 

client/internal/routemanager/notifier/notifier_android.go

@@ -6,7 +6,6 @@ import (
 	"net/netip"
 	"slices"
 	"sort"
-	"strings"
 	"sync"
 
 	"github.com/netbirdio/netbird/client/internal/listener"
@@ -14,12 +13,15 @@ import (
 )
 
 type Notifier struct {
-	initialRoutes []*route.Route
-	currentRoutes []*route.Route
-	fakeIPRoutes  []*route.Route
+	mu sync.Mutex
 
-	listener    listener.NetworkChangeListener
-	listenerMux sync.Mutex
+	// currentRoutes is the last announced route set. It exists only to
+	// suppress noise: without it every network map sync would trigger the
+	// Java side, even when the routes did not change. The actual TUN route
+	// state is owned by the route manager and pulled from there.
+	currentRoutes []*route.Route
+
+	listener listener.NetworkChangeListener
 }
 
 func NewNotifier() *Notifier {
@@ -27,20 +29,15 @@ func NewNotifier() *Notifier {
 }
 
 func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
-	n.listenerMux.Lock()
-	defer n.listenerMux.Unlock()
+	n.mu.Lock()
+	defer n.mu.Unlock()
 	n.listener = listener
 }
 
-// SetInitialClientRoutes stores the initial route sets for TUN configuration.
-func (n *Notifier) SetInitialClientRoutes(initialRoutes []*route.Route, routesForComparison []*route.Route) {
-	n.initialRoutes = filterStatic(initialRoutes)
-	n.currentRoutes = filterStatic(routesForComparison)
-}
-
-// SetFakeIPRoutes stores the fake IP routes to be included in every TUN rebuild.
-func (n *Notifier) SetFakeIPRoutes(routes []*route.Route) {
-	n.fakeIPRoutes = routes
+func (n *Notifier) NotifyRouteChange() {
+	n.mu.Lock()
+	defer n.mu.Unlock()
+	n.notifyLocked()
 }
 
 func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
@@ -54,46 +51,32 @@ func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
 		}
 	}
 
-	if !n.hasRouteDiff(n.currentRoutes, newRoutes) {
+	n.mu.Lock()
+	defer n.mu.Unlock()
+	if !hasRouteDiff(n.currentRoutes, newRoutes) {
 		return
 	}
 
 	n.currentRoutes = newRoutes
-	n.notify()
+	n.notifyLocked()
 }
 
 func (n *Notifier) OnNewPrefixes([]netip.Prefix) {
 	// Not used on Android
 }
 
-func (n *Notifier) notify() {
-	n.listenerMux.Lock()
-	defer n.listenerMux.Unlock()
+func (n *Notifier) notifyLocked() {
 	if n.listener == nil {
 		return
 	}
-
-	allRoutes := slices.Clone(n.currentRoutes)
-	allRoutes = append(allRoutes, n.fakeIPRoutes...)
-
-	routeStrings := n.routesToStrings(allRoutes)
-	sort.Strings(routeStrings)
-	go func(l listener.NetworkChangeListener) {
-		l.OnNetworkChanged(strings.Join(routeStrings, ","))
-	}(n.listener)
+	n.listener.OnNetworkChanged("")
 }
 
-func filterStatic(routes []*route.Route) []*route.Route {
-	out := make([]*route.Route, 0, len(routes))
-	for _, r := range routes {
-		if !r.IsDynamic() {
-			out = append(out, r)
-		}
-	}
-	return out
+func (n *Notifier) Close() {
+	// unused
 }
 
-func (n *Notifier) routesToStrings(routes []*route.Route) []string {
+func routesToStrings(routes []*route.Route) []string {
 	nets := make([]string, 0, len(routes))
 	for _, r := range routes {
 		nets = append(nets, r.NetString())
@@ -101,25 +84,10 @@ func (n *Notifier) routesToStrings(routes []*route.Route) []string {
 	return nets
 }
 
-func (n *Notifier) hasRouteDiff(a []*route.Route, b []*route.Route) bool {
-	slices.SortFunc(a, func(x, y *route.Route) int {
-		return strings.Compare(x.NetString(), y.NetString())
-	})
-	slices.SortFunc(b, func(x, y *route.Route) int {
-		return strings.Compare(x.NetString(), y.NetString())
-	})
-
-	return !slices.EqualFunc(a, b, func(x, y *route.Route) bool {
-		return x.NetString() == y.NetString()
-	})
-}
-
-func (n *Notifier) GetInitialRouteRanges() []string {
-	initialStrings := n.routesToStrings(n.initialRoutes)
-	sort.Strings(initialStrings)
-	return initialStrings
-}
-
-func (n *Notifier) Close() {
-	// unused
+func hasRouteDiff(a []*route.Route, b []*route.Route) bool {
+	as := routesToStrings(a)
+	bs := routesToStrings(b)
+	sort.Strings(as)
+	sort.Strings(bs)
+	return !slices.Equal(as, bs)
 }

client/internal/routemanager/notifier/notifier_ios.go

@@ -29,11 +29,7 @@ func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
 	n.listener = listener
 }
 
-func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
-	// iOS doesn't care about initial routes
-}
-
-func (n *Notifier) SetFakeIPRoutes([]*route.Route) {
+func (n *Notifier) NotifyRouteChange() {
 	// Not used on iOS
 }
 

client/internal/routemanager/notifier/notifier_other.go

@@ -19,11 +19,7 @@ func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
 	// Not used on non-mobile platforms
 }
 
-func (n *Notifier) SetInitialClientRoutes([]*route.Route, []*route.Route) {
-	// Not used on non-mobile platforms
-}
-
-func (n *Notifier) SetFakeIPRoutes([]*route.Route) {
+func (n *Notifier) NotifyRouteChange() {
 	// Not used on non-mobile platforms
 }
 
@@ -35,10 +31,6 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
 	// Not used on non-mobile platforms
 }
 
-func (n *Notifier) GetInitialRouteRanges() []string {
-	return []string{}
-}
-
 func (n *Notifier) Close() {
 	// unused
 }

client/internal/updater/installer/installer_run_darwin.go

@@ -98,47 +98,44 @@ func (u *Installer) startDaemon(daemonFolder string) error {
 func (u *Installer) startUIAsUser() error {
 	log.Infof("starting netbird-ui: %s", uiBinary)
 
-	// Get the current console user
-	cmd := exec.Command("stat", "-f", "%Su", "/dev/console")
-	output, err := cmd.Output()
+	username, err := consoleUser()
 	if err != nil {
-		return fmt.Errorf("failed to get console user: %w", err)
+		return err
 	}
 
-	username := strings.TrimSpace(string(output))
-	if username == "" || username == "root" {
-		return fmt.Errorf("no active user session found")
-	}
-
-	log.Infof("starting UI for user: %s", username)
-
-	// Get user's UID
 	userInfo, err := user.Lookup(username)
 	if err != nil {
-		return fmt.Errorf("failed to lookup user %s: %w", username, err)
+		return fmt.Errorf("lookup user %s: %w", username, err)
 	}
 
-	// Start the UI process as the console user using launchctl
-	// This ensures the app runs in the user's context with proper GUI access
-	launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "open", "-a", uiBinary)
+	log.Infof("starting UI for user: %s (uid %s)", username, userInfo.Uid)
+
+	launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "sudo", "-u", username, "-H", "open", "-a", uiBinary)
 	log.Infof("launchCmd: %s", launchCmd.String())
-	// Set the user's home directory for proper macOS app behavior
-	launchCmd.Env = append(os.Environ(), "HOME="+userInfo.HomeDir)
-	log.Infof("set HOME environment variable: %s", userInfo.HomeDir)
 
-	if err := launchCmd.Start(); err != nil {
-		return fmt.Errorf("failed to start UI process: %w", err)
-	}
-
-	// Release the process so it can run independently
-	if err := launchCmd.Process.Release(); err != nil {
-		log.Warnf("failed to release UI process: %v", err)
+	if err := launchCmd.Run(); err != nil {
+		return fmt.Errorf("run UI launch: %w", err)
 	}
 
 	log.Infof("netbird-ui started successfully for user %s", username)
 	return nil
 }
 
+func consoleUser() (string, error) {
+	output, err := exec.Command("stat", "-f", "%Su", "/dev/console").Output()
+	if err != nil {
+		return "", fmt.Errorf("get console user: %w", err)
+	}
+
+	username := strings.TrimSpace(string(output))
+	switch username {
+	case "", "root", "loginwindow", "_mbsetupuser":
+		return "", fmt.Errorf("no active GUI user session, console user: %q", username)
+	}
+
+	return username, nil
+}
+
 func (u *Installer) installPkgFile(ctx context.Context, path string) error {
 	log.Infof("installing pkg file: %s", path)
 

client/server/login_outcome_test.go

@@ -0,0 +1,110 @@
+package server
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+// A login that never reached Management is not a decision about the peer's
+// credentials, so it must come back as a retryable error rather than an SSO
+// prompt: the user cannot finish a browser login while Management is down, and
+// the CLI's own backoff resolves the outage on its own once the daemon reports
+// the failure. Reproduces `netbird down; netbird up` printing a device-code URL
+// because Management happened to be restarting when the daemon dialed it.
+func TestLogin_ManagementUnreachableIsReturnedInsteadOfDemandingSSO(t *testing.T) {
+	s, _, _, username, _ := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+
+	unreachable := errors.New("create connection: dial context: context deadline exceeded")
+	attempts := 0
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		attempts++
+		return false, unreachable
+	}
+
+	resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
+	require.Error(t, err)
+	require.ErrorIs(t, err, unreachable, "the transport failure was replaced by something else")
+	require.Nil(t, resp, "a failed login must not answer with a login response")
+	require.Equal(t, 1, attempts)
+	require.Nil(t, s.oauthAuthFlow.flow, "the daemon started an SSO flow for a peer whose login was never decided")
+
+	status, err := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, err)
+	require.Equal(t, internal.StatusLoginFailed, status,
+		"a peer that could not reach Management is not waiting on a login")
+}
+
+// The counterpart: Management refusing the peer's credentials is a decision, and
+// the SSO flow still has to start for it. The profile carries an unusable
+// private key so the flow setup fails immediately instead of dialing, which is
+// enough to show the branch was entered — the refusal itself is never what comes
+// back out.
+func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
+	s, _, _, username, cfgPath := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+	breakProfilePrivateKey(t, cfgPath)
+
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		return true, nil
+	}
+
+	_, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
+	require.Error(t, err)
+
+	status, stateErr := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, stateErr)
+	require.Equal(t, internal.StatusLoginFailed, status,
+		"the SSO flow setup was never reached with the broken key")
+}
+
+func TestLogin_SetupKeyStillRunsWhenPeerNeedsLogin(t *testing.T) {
+	s, _, _, username, _ := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		return true, nil
+	}
+
+	var keysTried []string
+	s.loginAttemptFn = func(_ context.Context, setupKey, _ string) (internal.StatusType, error) {
+		keysTried = append(keysTried, setupKey)
+		return "", nil
+	}
+
+	setupKey := "A2C8E32F-AEB2-4B45-8FD3-8A0C1B2D3E4F"
+	resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username, SetupKey: setupKey})
+	require.NoError(t, err, "the probe's outcome leaked out as the login result")
+	require.NotNil(t, resp)
+	require.Equal(t, []string{setupKey}, keysTried, "the setup key never reached the login attempt")
+	require.Nil(t, s.oauthAuthFlow.flow, "a setup-key login started an SSO flow")
+
+	status, err := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, err)
+	require.Equal(t, internal.StatusIdle, status)
+}
+
+// breakProfilePrivateKey replaces the profile's private key with an unparseable
+// one, which makes any attempt to build a Management client fail on the spot.
+func breakProfilePrivateKey(t *testing.T, cfgPath string) {
+	t.Helper()
+
+	raw, err := os.ReadFile(cfgPath)
+	require.NoError(t, err)
+
+	var cfg map[string]any
+	require.NoError(t, json.Unmarshal(raw, &cfg))
+	cfg["PrivateKey"] = "not-a-key"
+
+	patched, err := json.Marshal(cfg)
+	require.NoError(t, err)
+	require.NoError(t, os.WriteFile(cfgPath, patched, 0o600))
+}

client/server/server.go

@@ -135,6 +135,13 @@ type Server struct {
 	updateManager *updater.Manager
 
 	jwtCache *jwtCache
+
+	// loginAttemptFn stands in for the Management login round trip. Tests set
+	// it to drive the login outcomes that need a server on the other end;
+	// production leaves it nil, and every login goes through loginAttempt.
+	loginAttemptFn func(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error)
+
+	isLoginRequiredFn func(ctx context.Context) (bool, error)
 }
 
 type oauthAuthFlow struct {
@@ -370,7 +377,34 @@ func (s *Server) connectionGoroutineRunning() bool {
 	}
 }
 
-// loginAttempt attempts to login using the provided information. it returns a status in case something fails
+// attemptLogin runs a login round trip against Management, or the stand-in a
+// test installed in place of it.
+func (s *Server) attemptLogin(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
+	if s.loginAttemptFn != nil {
+		return s.loginAttemptFn(ctx, setupKey, jwtToken)
+	}
+	return s.loginAttempt(ctx, setupKey, jwtToken)
+}
+
+func (s *Server) isLoginRequired(ctx context.Context) (bool, error) {
+	if s.isLoginRequiredFn != nil {
+		return s.isLoginRequiredFn(ctx)
+	}
+
+	authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
+	if err != nil {
+		log.Errorf("failed to create auth client: %v", err)
+		return false, err
+	}
+	defer authClient.Close()
+
+	return authClient.IsLoginRequired(ctx)
+}
+
+// loginAttempt attempts to login using the provided information. It returns
+// StatusNeedsLogin when Management refused the peer's credentials and
+// StatusLoginFailed for every other failure, so callers can tell an
+// authentication decision apart from a login that never got made.
 func (s *Server) loginAttempt(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
 	authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
 	if err != nil {
@@ -623,7 +657,19 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	s.config = config
 	s.mutex.Unlock()
 
-	if _, err := s.loginAttempt(ctx, "", ""); err == nil {
+	// A probe that errors leaves the login undecided: Management unreachable, a
+	// restart mid-request, an internal error. Those are returned for the caller
+	// to retry, because turning them into an SSO prompt asks the user to solve
+	// something that is not theirs to solve, and a browser login cannot succeed
+	// while Management is unreachable anyway. Only Management refusing the
+	// peer's key is a decision, and IsLoginRequired reports that as
+	// needsLogin=true rather than an error.
+	needsLogin, err := s.isLoginRequired(ctx)
+	if err != nil {
+		state.Set(internal.StatusLoginFailed)
+		return nil, err
+	}
+	if !needsLogin {
 		state.Set(internal.StatusIdle)
 		return &proto.LoginResponse{}, nil
 	}
@@ -684,7 +730,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	// which returns NeedsLogin and parks on the browser leg.
 	state.Set(internal.StatusConnecting)
 
-	if loginStatus, err := s.loginAttempt(ctx, msg.SetupKey, ""); err != nil {
+	if loginStatus, err := s.attemptLogin(ctx, msg.SetupKey, ""); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}
@@ -839,7 +885,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 	s.oauthAuthFlow.expiresAt = time.Now()
 	s.mutex.Unlock()
 
-	if loginStatus, err := s.loginAttempt(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
+	if loginStatus, err := s.attemptLogin(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}
@@ -1769,6 +1815,9 @@ func (s *Server) RequestExtendAuthSession(
 	if connectClient == nil {
 		return nil, gstatus.Errorf(codes.FailedPrecondition, "client is not running")
 	}
+	if connectClient.Engine() == nil {
+		return nil, gstatus.Errorf(codes.FailedPrecondition, "session can no longer be extended, log in again to reconnect")
+	}
 
 	hint := ""
 	if msg.Hint != nil {

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

@@ -26,17 +26,17 @@ contents:
 
 # Default dependencies for the GTK4 + WebKitGTK 6.0 stack (Ubuntu 24.04+ / Debian 13+)
 depends:
-  - libgtk-4-1
+  - libgtk-4-1 (>= 4.14)
   - libwebkitgtk-6.0-4
   - xdg-utils
 
 # Distribution-specific overrides for different package formats
 overrides:
-  # RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux
+  # RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux / openSUSE
   rpm:
     depends:
-      - gtk4
-      - webkitgtk6.0
+      - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
+      - (webkitgtk6.0 or libwebkitgtk-6_0-4)
       - xdg-utils
 
   # Arch Linux packages

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

@@ -43,7 +43,12 @@ function buildSsoCancelPromise(state: SsoState, signal?: AbortSignal): Promise<v
 }
 
 async function runSsoLogin(
-    result: { verificationUri: string; verificationUriComplete: string; userCode: string },
+    result: {
+        verificationUri: string;
+        verificationUriComplete: string;
+        userCode: string;
+        profileId: string;
+    },
     state: SsoState,
     signal?: AbortSignal,
 ): Promise<void> {
@@ -56,7 +61,7 @@ async function runSsoLogin(
     // suspended, so a frontend-driven Up (a promise continuation) would not
     // fire until the user woke the window (e.g. hovering the tray icon).
     const waitPromise = Connection.WaitSSOLoginAndUp(
-        { userCode: result.userCode, hostname: "" },
+        { userCode: result.userCode, hostname: "", profileId: result.profileId },
         { profileName: "", username: "" },
     );
 

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

@@ -11,7 +11,7 @@ import { DialogHeading } from "@/components/dialog/DialogHeading";
 import { SquareIcon } from "@/components/SquareIcon";
 import { Connection, Profiles as ProfilesSvc, Session, WindowManager } from "@bindings/services";
 import { useAutoSizeWindow } from "@/hooks/useAutoSizeWindow";
-import { EVENT_BROWSER_LOGIN_CANCEL } from "@/lib/connection";
+import { EVENT_BROWSER_LOGIN_CANCEL, EVENT_TRIGGER_LOGIN } from "@/lib/connection";
 import { errorDialog, formatErrorMessage } from "@/lib/errors.ts";
 import { formatRemaining } from "@/lib/formatters";
 
@@ -131,6 +131,21 @@ export default function SessionExpirationDialog() {
         }
     }, [busy, t]);
 
+    const authenticate = useCallback(async () => {
+        if (busy) return;
+        setBusy(true);
+        try {
+            await Events.Emit(EVENT_TRIGGER_LOGIN);
+            await WindowManager.CloseSessionExpiration();
+        } catch (e) {
+            setBusy(false);
+            await errorDialog({
+                Title: t("connect.error.loginTitle"),
+                Message: formatErrorMessage(e),
+            });
+        }
+    }, [busy, t]);
+
     const logout = useCallback(async () => {
         if (busy) return;
         setBusy(true);
@@ -185,7 +200,7 @@ export default function SessionExpirationDialog() {
                     variant={"primary"}
                     size={"md"}
                     className={"w-full"}
-                    onClick={stay}
+                    onClick={expired ? authenticate : stay}
                     disabled={busy}
                 >
                     {expired ? t("sessionExpiration.authenticate") : t("sessionExpiration.stay")}

client/ui/main.go

@@ -14,7 +14,6 @@ import (
 	"github.com/sirupsen/logrus"
 	"github.com/wailsapp/wails/v3/pkg/application"
 	"github.com/wailsapp/wails/v3/pkg/events"
-	"github.com/wailsapp/wails/v3/pkg/services/notifications"
 
 	"github.com/netbirdio/netbird/client/ui/authsession"
 	"github.com/netbirdio/netbird/client/ui/i18n"
@@ -63,7 +62,7 @@ type registeredServices struct {
 	profiles        *services.Profiles
 	update          *services.Update
 	daemonFeed      *services.DaemonFeed
-	notifier        *notifications.NotificationService
+	notifier        *Notifier
 	compat          *services.Compat
 	profileSwitcher *services.ProfileSwitcher
 	bundle          *i18n.Bundle
@@ -102,7 +101,7 @@ func main() {
 	updaterHolder := updater.NewHolder(app.Event)
 	update := services.NewUpdate(conn, updaterHolder)
 	daemonFeed := services.NewDaemonFeed(conn, app.Event, updaterHolder, debugLog)
-	notifier := notifications.New()
+	notifier := newNotifier()
 	compat := services.NewCompat(conn)
 	// macOS shows no toast until permission is requested. Run it after
 	// ApplicationStarted so the notifier's Startup has initialised the
@@ -210,7 +209,7 @@ func main() {
 // requestNotificationAuthorization prompts for macOS notification permission.
 // The request blocks until the user responds (up to 3 minutes), so callers run
 // it in a goroutine. No-op on Linux/Windows.
-func requestNotificationAuthorization(notifier *notifications.NotificationService) {
+func requestNotificationAuthorization(notifier *Notifier) {
 	authorized, err := notifier.CheckNotificationAuthorization()
 	if err != nil {
 		logrus.Debugf("check notification authorization: %v", err)

client/ui/notifier.go

@@ -0,0 +1,101 @@
+//go:build !android && !ios && !freebsd && !js
+
+package main
+
+import (
+	"context"
+	"errors"
+	"sync/atomic"
+
+	log "github.com/sirupsen/logrus"
+	"github.com/wailsapp/wails/v3/pkg/application"
+	"github.com/wailsapp/wails/v3/pkg/services/notifications"
+)
+
+var errNotificationsUnavailable = errors.New("notifications unavailable")
+
+// Notifier wraps the Wails notification service so an unavailable backend
+// disables notifications instead of aborting the app. Startup fails for
+// environment reasons (a bare unbundled binary on macOS has no bundle
+// identifier, a headless Linux session has no D-Bus session bus), and Wails
+// treats a service startup error as fatal. After a failed startup every call
+// is a no-op: on macOS, touching UNUserNotificationCenter without a bundle
+// identifier raises an Objective-C exception that recover() cannot catch.
+type Notifier struct {
+	inner     *notifications.NotificationService
+	available atomic.Bool
+}
+
+func newNotifier() *Notifier {
+	return &Notifier{inner: notifications.New()}
+}
+
+// ServiceName implements the Wails service-name hook for startup logs.
+func (n *Notifier) ServiceName() string {
+	return n.inner.ServiceName()
+}
+
+// ServiceStartup starts the platform notifier, downgrading failure to a
+// warning so the app keeps running without notifications.
+func (n *Notifier) ServiceStartup(ctx context.Context, options application.ServiceOptions) error {
+	if err := n.inner.ServiceStartup(ctx, options); err != nil {
+		log.Warnf("notifications disabled: %v", err)
+		return nil
+	}
+	n.available.Store(true)
+	return nil
+}
+
+func (n *Notifier) ServiceShutdown() error {
+	if !n.available.Load() {
+		return nil
+	}
+	return n.inner.ServiceShutdown()
+}
+
+func (n *Notifier) CheckNotificationAuthorization() (bool, error) {
+	if !n.available.Load() {
+		return false, errNotificationsUnavailable
+	}
+	return n.inner.CheckNotificationAuthorization()
+}
+
+func (n *Notifier) RequestNotificationAuthorization() (bool, error) {
+	if !n.available.Load() {
+		return false, errNotificationsUnavailable
+	}
+	return n.inner.RequestNotificationAuthorization()
+}
+
+// SendNotification delivers a notification, silently dropping it when the
+// backend never started (notifications are best-effort everywhere).
+func (n *Notifier) SendNotification(options notifications.NotificationOptions) error {
+	if !n.available.Load() {
+		log.Debugf("notifications disabled, dropping %q", options.ID)
+		return nil
+	}
+	return n.inner.SendNotification(options)
+}
+
+func (n *Notifier) SendNotificationWithActions(options notifications.NotificationOptions) error {
+	if !n.available.Load() {
+		log.Debugf("notifications disabled, dropping %q", options.ID)
+		return nil
+	}
+	return n.inner.SendNotificationWithActions(options)
+}
+
+func (n *Notifier) RegisterNotificationCategory(category notifications.NotificationCategory) error {
+	if !n.available.Load() {
+		return nil
+	}
+	return n.inner.RegisterNotificationCategory(category)
+}
+
+// OnNotificationResponse registers the response callback. Pure Go state, so
+// it is safe (and simply inert) when the backend never started.
+//
+//wails:ignore
+func (n *Notifier) OnNotificationResponse(callback func(result notifications.NotificationResult)) {
+	n.inner.OnNotificationResponse(callback)
+}

client/ui/preferences/store.go

@@ -246,6 +246,7 @@ func (s *Store) ExistedAtLoad() bool {
 func (s *Store) load() error {
 	if _, err := os.Stat(s.path); err != nil {
 		if errors.Is(err, os.ErrNotExist) {
+			log.Infof("no ui preferences file at %s; using defaults", s.path)
 			return nil
 		}
 		return fmt.Errorf("stat preferences: %w", err)

client/ui/services/connection.go

@@ -33,12 +33,21 @@ type LoginResult struct {
 	UserCode                string `json:"userCode"`
 	VerificationURI         string `json:"verificationUri"`
 	VerificationURIComplete string `json:"verificationUriComplete"`
+	// ProfileID is the ID of the profile this login ran against, or "" when the
+	// caller named the profile itself and no ID was resolved. Pass it back in
+	// WaitSSOParams so the account email lands on this profile even if the
+	// active one changes during SSO.
+	ProfileID string `json:"profileId"`
 }
 
 // WaitSSOParams are the inputs to waitSSOLogin.
 type WaitSSOParams struct {
 	UserCode string `json:"userCode"`
 	Hostname string `json:"hostname"`
+	// ProfileID is the profile the login was started for, used to file the
+	// account email against it rather than against whichever profile is active
+	// when the flow returns. Optional: empty falls back to the active profile.
+	ProfileID string `json:"profileId"`
 }
 
 // UpParams selects the profile to bring up.
@@ -77,11 +86,16 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 	// Fall back to the daemon's active profile and the current OS user.
 	profileName := p.ProfileName
 	username := p.Username
+	// Only set when the daemon told us the ID. A caller-supplied ProfileName is
+	// a handle — a display name or an ID prefix resolve too — and the state file
+	// is named after the ID, so passing a handle on would name the wrong file.
+	profileID := ""
 	if profileName == "" {
 		if active, aerr := cli.GetActiveProfile(ctx, &proto.GetActiveProfileRequest{}); aerr == nil {
 			// Address the active profile by ID (the daemon resolves it as a
 			// handle); names can collide, the ID cannot.
 			profileName = active.GetId()
+			profileID = profileName
 			if username == "" {
 				username = active.GetUsername()
 			}
@@ -122,6 +136,7 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 		UserCode:                resp.GetUserCode(),
 		VerificationURI:         resp.GetVerificationURI(),
 		VerificationURIComplete: resp.GetVerificationURIComplete(),
+		ProfileID:               profileID,
 	}, nil
 }
 
@@ -242,6 +257,31 @@ func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
 		return "", s.classifyDaemonError(err)
 	}
 	log.Infof("SSO login completed, daemon reported success")
+
+	// Persist the account email the same way the CLI does after its own
+	// WaitSSOLogin: the daemon returns it but cannot store it, since it runs as
+	// root and the per-profile state file is user-owned (see Logout below).
+	// Without this the profile has no email, so Profiles.List shows no account
+	// and later logins and session extends go out without a login_hint —
+	// leaving the IdP to guess which account was meant.
+	if email := resp.GetEmail(); email != "" {
+		state := &profilemanager.ProfileState{Email: email}
+		pm := profilemanager.NewProfileManager()
+
+		// Against the profile the login was started for: SSO spans seconds of
+		// user interaction, and a profile switch in that window would otherwise
+		// file the email under the wrong profile.
+		if p.ProfileID != "" {
+			err = pm.SetProfileState(profilemanager.ID(p.ProfileID), state)
+		} else {
+			err = pm.SetActiveProfileState(state)
+		}
+		if err != nil {
+			// Non-fatal: the login itself succeeded.
+			log.Warnf("failed to store account email: %v", err)
+		}
+	}
+
 	return resp.GetEmail(), nil
 }
 

client/ui/services/profile.go

@@ -6,6 +6,8 @@ import (
 	"context"
 	"os/user"
 
+	log "github.com/sirupsen/logrus"
+
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 )
@@ -151,11 +153,31 @@ func (s *Profiles) Remove(ctx context.Context, p ProfileRef) error {
 	if err != nil {
 		return err
 	}
-	_, err = cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
+	resp, err := cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
 		ProfileName: p.ProfileName,
 		Username:    p.Username,
 	})
-	return err
+	if err != nil {
+		return err
+	}
+
+	// The daemon deletes what it owns but runs as root, so it leaves the
+	// user-owned state file holding the account email behind (same split as
+	// Connection.Logout). Legacy profiles are keyed by name rather than by a
+	// generated ID, so a recreated profile of the same name would inherit the
+	// deleted one's email and offer it as the login_hint.
+	//
+	// Keyed on the ID the daemon resolved, not on the request handle: that may
+	// have been a display name or an ID prefix, which would name a different
+	// file (or none).
+	if id := resp.GetId(); id != "" {
+		if err := profilemanager.NewProfileManager().RemoveProfileState(id); err != nil {
+			// Non-fatal: the profile itself is gone.
+			log.Warnf("failed to remove profile state for %s: %v", id, err)
+		}
+	}
+
+	return nil
 }
 
 // Rename changes a profile's display name. The on-disk ID is unaffected, so

client/ui/tray.go

@@ -44,7 +44,7 @@ type TrayServices struct {
 	Profiles        *services.Profiles
 	Networks        *services.Networks
 	DaemonFeed      *services.DaemonFeed
-	Notifier        *notifications.NotificationService
+	Notifier        *Notifier
 	Update          *services.Update
 	ProfileSwitcher *services.ProfileSwitcher
 	WindowManager   *services.WindowManager

client/ui/tray_click_linux.go

@@ -4,17 +4,26 @@ package main
 
 // bindTrayClick wires the tray icon's left-click handler on Linux.
 //
-// Both Linux click paths converge on Wails' linuxSystemTray.Activate, which
-// fires the registered clickHandler:
-//   - Real SNI hosts (KDE Plasma, Waybar, GNOME Shell + AppIndicator) invoke
-//     org.kde.StatusNotifierItem.Activate over D-Bus on left-click.
-//   - The in-process StatusNotifierWatcher + XEmbed host used on minimal WMs
-//     (Fluxbox, i3, dwm, OpenBox) maps a Button1 press to that same Activate
-//     call itself (xembed_host_linux.go), so it routes through the same hook.
-// Registering OnClick here therefore covers both paths with one handler — no
-// changes to the watcher or XEmbed C code are needed. Left-click now opens the
-// main window; right-click still opens the menu via Wails' default
-// SecondaryActivate→OpenMenu handler (and the XEmbed GTK popup on minimal WMs).
+// Expected behaviour per tray host:
+//
+//	Host                           Left click              Right click
+//	KDE Plasma, Waybar             main window (Activate)  menu (host-rendered)
+//	GNOME Shell + AppIndicator     menu only               menu only
+//	Minimal WMs via XEmbed host    main window (Activate)  XEmbed GTK popup
+//
+// OnClick fires only on org.kde.StatusNotifierItem.Activate — a real left
+// click. KDE/Waybar send it over D-Bus; the in-process XEmbed host
+// (xembed_host_linux.go) maps a Button1 press to the same Activate call.
+//
+// GNOME Shell + AppIndicator never sends Activate: it renders the dbusmenu
+// on ANY click and only reports the menu opening via dbusmenu
+// Event("opened"). Upstream Wails treated that event as a click, so on GNOME
+// both buttons raised the main window on top of the menu, and on KDE/Waybar
+// a right click raised it over the freshly opened menu. The netbirdio/wails
+// fork (go.mod replace) drops that heuristic: a menu open never fires
+// OnClick. On GNOME the main window is reached via the "Open NetBird" menu
+// entry; left-click-opens-window is not achievable there anyway, since the
+// host always opens the menu itself.
 //
 // We do NOT register OnDoubleClick: Wails' Linux SNI backend never fires it
 // (unlike Windows). And we deliberately skip AttachWindow — it plus Wails3's

client/ui/tray_notify.go

@@ -44,7 +44,7 @@ func safeSendNotification(send sendFn, what string, opts notifications.Notificat
 // notifyIfDaemonOutdated probes the daemon once and fires an OS toast when it
 // is reachable but too old for this UI. A probe error means the daemon isn't
 // reachable (not outdated), so it is left to the normal connection flow.
-func notifyIfDaemonOutdated(compat *services.Compat, notifier *notifications.NotificationService, loc *Localizer) {
+func notifyIfDaemonOutdated(compat *services.Compat, notifier *Notifier, loc *Localizer) {
 	ready, err := compat.DaemonReady(context.Background())
 	if err != nil {
 		log.Debugf("daemon compatibility probe: %v", err)

client/ui/tray_session.go

@@ -27,11 +27,10 @@ const (
 	finalWarningCountdownSeconds = 120
 )
 
-// handleSessionExpired notifies and brings the window forward so the frontend's /login route drives renewal.
+// handleSessionExpired notifies and brings the window forward so the user can reconnect.
 func (t *Tray) handleSessionExpired() {
 	t.notify(t.loc.T("notify.sessionExpired.title"), t.loc.T("notify.sessionExpired.body"), notifyIDSessionExpired)
 	if t.window != nil {
-		t.window.SetURL("/#/login")
 		t.window.Show()
 		t.window.Focus()
 	}
@@ -308,11 +307,7 @@ func (t *Tray) openSessionExtendFlow() {
 	}
 	seconds := int(time.Until(deadline).Seconds())
 	if seconds <= 0 {
-		if t.window != nil {
-			t.window.SetURL("/#/login")
-			t.window.Show()
-			t.window.Focus()
-		}
+		t.app.Event.Emit(services.EventTriggerLogin)
 		return
 	}
 	if t.svc.WindowManager == nil {

client/ui/tray_update.go

@@ -21,7 +21,7 @@ type trayUpdater struct {
 	app          *application.App
 	window       *application.WebviewWindow
 	update       *services.Update
-	notifier     *notifications.NotificationService
+	notifier     *Notifier
 	loc          *Localizer
 	onIconChange func()
 	// onMenuChange drives a full tray relayout: the update row lives in the
@@ -36,7 +36,7 @@ type trayUpdater struct {
 	progressWindowOpen bool
 }
 
-func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *notifications.NotificationService, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
+func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
 	u := &trayUpdater{
 		app:          app,
 		window:       window,

e2e/agentnetwork/management_test.go

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

e2e/agentnetwork/settings_bootstrap_test.go

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

go.mod

@@ -114,7 +114,7 @@ require (
 	github.com/ti-mo/conntrack v0.5.1
 	github.com/ti-mo/netfilter v0.5.2
 	github.com/vmihailenco/msgpack/v5 v5.4.1
-	github.com/wailsapp/wails/v3 v3.0.0-alpha2.117
+	github.com/wailsapp/wails/v3 v3.0.0-beta.3
 	github.com/yusufpapurcu/wmi v1.2.4
 	github.com/zcalusic/sysinfo v1.1.3
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.67.0
@@ -339,3 +339,5 @@ replace github.com/dexidp/dex => github.com/netbirdio/dex v0.244.1-0.20260716205
 replace github.com/dexidp/dex/api/v2 => github.com/netbirdio/dex/api/v2 v2.0.0-20260512110716-8d70ad8647c1
 
 replace github.com/mailru/easyjson => github.com/netbirdio/easyjson v0.9.0
+
+replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4

go.sum

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

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

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

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

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

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

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

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

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

management/internals/modules/agentnetwork/manager.go

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

management/internals/modules/agentnetwork/provider_bootstrap_test.go

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

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

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

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

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

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

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

management/internals/server/boot.go

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

management/internals/server/grpc_extension.go

@@ -0,0 +1,74 @@
+package server
+
+import (
+	"context"
+
+	"google.golang.org/grpc"
+)
+
+// GRPCExtension bundles an external module's contribution to the management
+// gRPC server: the registration of one or more services onto the shared
+// grpc.Server, any server-wide interceptors those services require, and an
+// optional shutdown hook. It is a generic extension point with no knowledge of
+// any specific service.
+type GRPCExtension struct {
+	// Register is invoked with the shared grpc.Server (as a ServiceRegistrar)
+	// after the built-in services are registered. It may register any number of
+	// services. May be nil.
+	Register func(grpc.ServiceRegistrar)
+	// UnaryInterceptors are appended to the server's unary interceptor chain,
+	// running after the built-in interceptors. May be empty.
+	UnaryInterceptors []grpc.UnaryServerInterceptor
+	// StreamInterceptors are appended to the server's stream interceptor chain,
+	// running after the built-in interceptors. May be empty.
+	StreamInterceptors []grpc.StreamServerInterceptor
+	// Shutdown, if non-nil, is called once during Stop() with the context
+	// governing server shutdown, which carries a deadline. The hook MUST
+	// return promptly and MUST abandon its work once that context is
+	// cancelled or expires: it runs before the rest of Stop()'s cleanup
+	// (store, event store, embedded IdP) and before Stop() itself checks the
+	// context's deadline, so a hook that ignores the context will delay all
+	// of that cleanup and prevent Stop() from returning on time. May be nil.
+	Shutdown func(ctx context.Context)
+}
+
+// RegisterGRPCExtension registers a gRPC extension. Call before the gRPC server
+// is first built (i.e. before Start); registrations after that have no effect.
+func (s *BaseServer) RegisterGRPCExtension(ext GRPCExtension) {
+	s.grpcExtensions = append(s.grpcExtensions, ext)
+}
+
+// appendExtensionInterceptors appends each extension's interceptors to the gRPC
+// server options as additional chained interceptors. grpc.ChainUnaryInterceptor
+// and grpc.ChainStreamInterceptor are additive, so the returned options run the
+// extension interceptors after any interceptors already present in opts.
+func appendExtensionInterceptors(opts []grpc.ServerOption, exts []GRPCExtension) []grpc.ServerOption {
+	for _, ext := range exts {
+		if len(ext.UnaryInterceptors) > 0 {
+			opts = append(opts, grpc.ChainUnaryInterceptor(ext.UnaryInterceptors...))
+		}
+		if len(ext.StreamInterceptors) > 0 {
+			opts = append(opts, grpc.ChainStreamInterceptor(ext.StreamInterceptors...))
+		}
+	}
+	return opts
+}
+
+// registerExtensions registers each extension's services onto reg.
+func registerExtensions(reg grpc.ServiceRegistrar, exts []GRPCExtension) {
+	for _, ext := range exts {
+		if ext.Register != nil {
+			ext.Register(reg)
+		}
+	}
+}
+
+// runExtensionShutdownHooks calls each extension's shutdown hook, if set,
+// passing ctx through so hooks can honor its deadline/cancellation.
+func runExtensionShutdownHooks(ctx context.Context, exts []GRPCExtension) {
+	for _, ext := range exts {
+		if ext.Shutdown != nil {
+			ext.Shutdown(ctx)
+		}
+	}
+}

management/internals/server/grpc_extension_test.go

@@ -0,0 +1,160 @@
+package server
+
+import (
+	"context"
+	"net"
+	"sync/atomic"
+	"testing"
+
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/credentials/insecure"
+	"google.golang.org/grpc/health"
+	healthgrpc "google.golang.org/grpc/health/grpc_health_v1"
+	"google.golang.org/grpc/test/bufconn"
+)
+
+// Test that an extension's interceptors and service registration are actually
+// wired onto a real in-process gRPC server via the helpers, and that shutdown
+// hooks run. This validates the load-bearing assumption that
+// grpc.ChainUnaryInterceptor is additive (extension interceptors run in
+// addition to any base chain).
+func TestGRPCExtensionAppliedToServer(t *testing.T) {
+	var unaryCalls atomic.Int32
+	var streamShutdownCalled atomic.Bool
+
+	ext := GRPCExtension{
+		Register: func(reg grpc.ServiceRegistrar) {
+			healthgrpc.RegisterHealthServer(reg, health.NewServer())
+		},
+		UnaryInterceptors: []grpc.UnaryServerInterceptor{
+			func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
+				unaryCalls.Add(1)
+				return handler(ctx, req)
+			},
+		},
+		Shutdown: func(ctx context.Context) { streamShutdownCalled.Store(true) },
+	}
+	exts := []GRPCExtension{ext}
+
+	// Base options mimic GRPCServer(): a pre-existing chain the extension appends to.
+	var baseUnaryCalls atomic.Int32
+	opts := []grpc.ServerOption{
+		grpc.ChainUnaryInterceptor(func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
+			baseUnaryCalls.Add(1)
+			return handler(ctx, req)
+		}),
+	}
+	opts = appendExtensionInterceptors(opts, exts)
+
+	srv := grpc.NewServer(opts...)
+	registerExtensions(srv, exts)
+
+	lis := bufconn.Listen(1024 * 1024)
+	go func() { _ = srv.Serve(lis) }()
+	t.Cleanup(srv.Stop)
+
+	conn, err := grpc.NewClient("passthrough:///bufnet",
+		grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) { return lis.DialContext(ctx) }),
+		grpc.WithTransportCredentials(insecure.NewCredentials()))
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(func() { _ = conn.Close() })
+
+	_, err = healthgrpc.NewHealthClient(conn).Check(context.Background(), &healthgrpc.HealthCheckRequest{})
+	if err != nil {
+		t.Fatalf("health check via extension-registered service failed: %v", err)
+	}
+	if baseUnaryCalls.Load() != 1 {
+		t.Errorf("base interceptor calls = %d, want 1 (base chain must be preserved)", baseUnaryCalls.Load())
+	}
+	if unaryCalls.Load() != 1 {
+		t.Errorf("extension interceptor calls = %d, want 1", unaryCalls.Load())
+	}
+
+	runExtensionShutdownHooks(context.Background(), exts)
+	if !streamShutdownCalled.Load() {
+		t.Error("extension shutdown hook was not called")
+	}
+}
+
+// TestGRPCExtensionShutdownHookReceivesCallerContext asserts that each hook receives
+// a non-nil context and that it is the very same context the caller passed
+// in, so hooks can rely on values/deadlines placed on it by Stop().
+func TestGRPCExtensionShutdownHookReceivesCallerContext(t *testing.T) {
+	type sentinelKey struct{}
+	want := "shutdown-ctx-sentinel"
+	ctx := context.WithValue(context.Background(), sentinelKey{}, want)
+
+	var called bool
+	ext := GRPCExtension{
+		Shutdown: func(hookCtx context.Context) {
+			called = true
+			if hookCtx == nil {
+				t.Fatal("hook received a nil context")
+			}
+			got, _ := hookCtx.Value(sentinelKey{}).(string)
+			if got != want {
+				t.Errorf("hook context sentinel = %q, want %q (not the caller's context)", got, want)
+			}
+		},
+	}
+
+	runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
+	if !called {
+		t.Fatal("shutdown hook was not called")
+	}
+}
+
+// TestGRPCExtensionShutdownHookObservesCancellation documents, by test, that
+// hooks can honor cancellation/deadlines: a hook given an already-cancelled
+// context must see ctx.Err() != nil and a closed Done() channel.
+func TestGRPCExtensionShutdownHookObservesCancellation(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	var called bool
+	ext := GRPCExtension{
+		Shutdown: func(hookCtx context.Context) {
+			called = true
+			if hookCtx.Err() == nil {
+				t.Error("hook context Err() = nil, want non-nil for a cancelled context")
+			}
+			select {
+			case <-hookCtx.Done():
+			default:
+				t.Error("hook context Done() channel is not closed for a cancelled context")
+			}
+		},
+	}
+
+	runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
+	if !called {
+		t.Fatal("shutdown hook was not called")
+	}
+}
+
+// TestGRPCExtensionShutdownHookNilSkipped asserts that an extension
+// with a nil Shutdown hook is skipped without panicking, and that hooks for
+// other extensions still run.
+func TestGRPCExtensionShutdownHookNilSkipped(t *testing.T) {
+	var called atomic.Bool
+	exts := []GRPCExtension{
+		{Shutdown: nil},
+		{Shutdown: func(context.Context) { called.Store(true) }},
+	}
+
+	runExtensionShutdownHooks(context.Background(), exts)
+	if !called.Load() {
+		t.Error("shutdown hook for non-nil extension was not called")
+	}
+}
+
+func TestRegisterGRPCExtensionAccumulates(t *testing.T) {
+	s := &BaseServer{}
+	s.RegisterGRPCExtension(GRPCExtension{})
+	s.RegisterGRPCExtension(GRPCExtension{})
+	if len(s.grpcExtensions) != 2 {
+		t.Fatalf("grpcExtensions len = %d, want 2", len(s.grpcExtensions))
+	}
+}

management/internals/server/server.go

@@ -68,6 +68,11 @@ type BaseServer struct {
 
 	proxyAuthClose func()
 
+	// grpcExtensions holds additional gRPC services, interceptors, and shutdown
+	// hooks registered by external modules via RegisterGRPCExtension. Populated
+	// during boot (single-threaded), consumed by GRPCServer() and Stop().
+	grpcExtensions []GRPCExtension
+
 	listener    net.Listener
 	certManager *autocert.Manager
 	update      *version.Update
@@ -257,6 +262,7 @@ func (s *BaseServer) Stop() error {
 		s.proxyAuthClose()
 		s.proxyAuthClose = nil
 	}
+	runExtensionShutdownHooks(ctx, s.grpcExtensions)
 	_ = s.Store().Close(ctx)
 	_ = s.EventStore().Close(ctx)
 	if s.update != nil {

management/internals/shared/grpc/components_encoder.go

@@ -61,6 +61,8 @@ func EncodeNetworkMapEnvelope(in ComponentsEnvelopeInput) *proto.NetworkMapEnvel
 		return &proto.NetworkMapEnvelope{
 			Payload: &proto.NetworkMapEnvelope_Full{
 				Full: &proto.NetworkMapComponentsFull{
+					Serial:     networkSerial(c.Network),
+					Network:    toAccountNetwork(c.Network),
 					PeerConfig: in.PeerConfig,
 					// components.Peers always contains the target peer
 					Peers:            []*proto.PeerCompact{toPeerCompact(c.Peers[c.PeerID])},

management/internals/shared/grpc/components_encoder_test.go

@@ -758,6 +758,9 @@ func TestEncodeNetworkMapEnvelope_NilComponentsGracefulDegrade(t *testing.T) {
 	assert.Equal(t, "netbird.cloud", full.DnsDomain)
 	assert.Len(t, full.Peers, 1)
 	assert.Empty(t, full.Policies)
+	require.NotNil(t, full.Network, "client runs Calculate() over the envelope and dereferences Network unconditionally; a nil here would crash the receiver")
+	assert.Equal(t, "net-empty", full.Network.Identifier)
+	assert.Equal(t, uint64(9), full.Serial)
 }
 
 func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
@@ -776,6 +779,12 @@ func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
 func emptyNetworkMapComponents() *types.NetworkMapComponents {
 	return types.EmptyNetworkMapComponents(
 		&types.NetworkMapComponents{
-			PeerID: "peer-id", Peers: map[string]*types.ComponentPeer{"peer-id": {}}},
+			PeerID: "peer-id", Peers: map[string]*types.ComponentPeer{"peer-id": {}},
+			Network: &types.Network{
+				Identifier: "net-empty",
+				Net:        net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)},
+				Serial:     9,
+			},
+		},
 	)
 }

management/server/agentnetwork_budgetrule_realstack_test.go

@@ -102,11 +102,20 @@ func TestAgentNetwork_UpdateSettings_PreservesImmutableAndTogglesCollection(t *t
 	require.NotEmpty(t, before.Subdomain, "subdomain pinned at bootstrap")
 	assert.False(t, before.EnablePromptCollection, "prompt collection defaults off")
 
-	// Attempt to flip toggles AND smuggle a different cluster/subdomain — the
-	// immutable fields must be ignored.
+	// A cluster different from the one pinned at bootstrap must be rejected
+	// outright — never silently swapped or ignored.
+	_, err = mgr.UpdateSettings(ctx, adminUserID, &agenttypes.Settings{
+		AccountID:           accountID,
+		Cluster:             "attacker.cluster",
+		EnableLogCollection: true,
+	})
+	require.Error(t, err, "UpdateSettings with a mismatched cluster must fail")
+
+	// Flipping the toggles works with the pinned cluster echoed back (and
+	// with it omitted); the subdomain is never taken from the request.
 	updated, err := mgr.UpdateSettings(ctx, adminUserID, &agenttypes.Settings{
 		AccountID:              accountID,
-		Cluster:                "attacker.cluster",
+		Cluster:                clusterAddr,
 		Subdomain:              "evil",
 		EnableLogCollection:    true,
 		EnablePromptCollection: true,

management/server/group.go

@@ -6,6 +6,8 @@ import (
 	"fmt"
 	"slices"
 
+	agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/rs/xid"
 	log "github.com/sirupsen/logrus"
 
@@ -744,6 +746,14 @@ func validateDeleteGroup(ctx context.Context, transaction store.Store, group *ty
 		return &GroupLinkError{"network router", linkedRouter.ID}
 	}
 
+	if isLinked, linkedService := isGroupLinkedToReverseProxyService(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"reverse proxy service", linkedService.Domain}
+	}
+
+	if isLinked, linkedPolicy := isGroupLinkedToAgentNetworkPolicy(ctx, transaction, group.AccountID, group.ID); isLinked {
+		return &GroupLinkError{"agent network policy", linkedPolicy.Name}
+	}
+
 	return checkGroupLinkedToSettings(ctx, transaction, group)
 }
 
@@ -875,6 +885,46 @@ func isGroupLinkedToNetworkRouter(ctx context.Context, transaction store.Store,
 	return false, nil
 }
 
+// isGroupLinkedToReverseProxyService checks if a group is used as an access group
+// of a private reverse proxy service or as a bearer-auth distribution group.
+func isGroupLinkedToReverseProxyService(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *service.Service) {
+	services, err := transaction.GetAccountServices(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving reverse proxy services while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, svc := range services {
+		if svc.Private && slices.Contains(svc.AccessGroups, groupID) {
+			return true, svc
+		}
+		if svc.Auth.BearerAuth != nil && svc.Auth.BearerAuth.Enabled && slices.Contains(svc.Auth.BearerAuth.DistributionGroups, groupID) {
+			return true, svc
+		}
+	}
+	return false, nil
+}
+
+// isGroupLinkedToAgentNetworkPolicy checks if a group is used as a source group by any
+// agent network policy in the account.
+func isGroupLinkedToAgentNetworkPolicy(ctx context.Context, transaction store.Store, accountID string, groupID string) (bool, *agentNetworkTypes.Policy) {
+	policies, err := transaction.GetAccountAgentNetworkPolicies(ctx, store.LockingStrengthNone, accountID)
+	if err != nil {
+		log.WithContext(ctx).Errorf("error retrieving agent network policies while checking group linkage: %v", err)
+		return false, nil
+	}
+
+	for _, policy := range policies {
+		if policy == nil {
+			continue
+		}
+		if slices.Contains(policy.SourceGroups, groupID) {
+			return true, policy
+		}
+	}
+	return false, nil
+}
+
 // areGroupChangesAffectPeers checks if any changes to the specified groups will affect peers.
 // It fetches each collection once and checks all groupIDs against them in memory.
 func areGroupChangesAffectPeers(ctx context.Context, transaction store.Store, accountID string, groupIDs []string) (bool, error) {

management/server/group_test.go

@@ -18,6 +18,8 @@ import (
 	"golang.org/x/exp/maps"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/server/groups"
 	"github.com/netbirdio/netbird/management/server/networks"
 	"github.com/netbirdio/netbird/management/server/networks/resources"
@@ -125,6 +127,21 @@ func TestDefaultAccountManager_DeleteGroup(t *testing.T) {
 			"grp-for-integration",
 			"only service users with admin power can delete integration group",
 		},
+		{
+			"agent network policy",
+			"grp-for-agent-network-policy",
+			"agent network policy",
+		},
+		{
+			"reverse proxy private service access group",
+			"grp-for-rp-private",
+			"reverse proxy service",
+		},
+		{
+			"reverse proxy bearer distribution group",
+			"grp-for-rp-bearer",
+			"reverse proxy service",
+		},
 	}
 
 	for _, testCase := range testCases {
@@ -218,6 +235,17 @@ func TestDefaultAccountManager_DeleteGroups(t *testing.T) {
 			groupIDs:        []string{"grp-for-integration"},
 			expectedReasons: []string{"only service users with admin power can delete integration group"},
 		},
+		{
+			name:            "agent network policy",
+			groupIDs:        []string{"grp-for-agent-network-policy"},
+			expectedReasons: []string{"agent network policy"},
+		},
+		{
+			name:               "reverse proxy services",
+			groupIDs:           []string{"grp-for-rp-private", "grp-for-rp-bearer"},
+			expectedReasons:    []string{"reverse proxy service", "reverse proxy service"},
+			expectedNotDeleted: []string{"grp-for-rp-private", "grp-for-rp-bearer"},
+		},
 		{
 			name:            "successfully delete multiple groups",
 			groupIDs:        []string{"group-1", "group-2"},
@@ -285,6 +313,65 @@ func TestDefaultAccountManager_DeleteGroups(t *testing.T) {
 	}
 }
 
+func TestDefaultAccountManager_DeleteGroupUnlinkedFromReverseProxyService(t *testing.T) {
+	am, _, err := createManager(t)
+	require.NoError(t, err, "Failed to create account manager")
+
+	_, account, err := initTestGroupAccount(am)
+	require.NoError(t, err, "Failed to init testing account")
+
+	deletableGroups := []*types.Group{
+		{
+			ID:        "grp-rp-bearer-disabled",
+			AccountID: account.Id,
+			Name:      "Group only in a disabled bearer auth",
+			Issued:    types.GroupIssuedAPI,
+			Peers:     make([]string, 0),
+		},
+		{
+			ID:        "grp-rp-nonprivate-access",
+			AccountID: account.Id,
+			Name:      "Group only in a non-private service's access groups",
+			Issued:    types.GroupIssuedAPI,
+			Peers:     make([]string, 0),
+		},
+	}
+	for _, group := range deletableGroups {
+		require.NoError(t, am.CreateGroup(context.Background(), account.Id, groupAdminUserID, group))
+	}
+
+	// Disabled bearer auth and stale access groups on a non-private service
+	// are inert configuration and must not block group deletion.
+	services := []*rpservice.Service{
+		{
+			ID:        "rp-svc-bearer-disabled",
+			AccountID: account.Id,
+			Domain:    "bearer-disabled.services.example.com",
+			Auth: rpservice.AuthConfig{
+				BearerAuth: &rpservice.BearerAuthConfig{
+					Enabled:            false,
+					DistributionGroups: []string{"grp-rp-bearer-disabled"},
+				},
+			},
+		},
+		{
+			ID:           "rp-svc-nonprivate-access",
+			AccountID:    account.Id,
+			Domain:       "nonprivate.services.example.com",
+			Private:      false,
+			AccessGroups: []string{"grp-rp-nonprivate-access"},
+		},
+	}
+	for _, svc := range services {
+		require.NoError(t, am.Store.CreateService(context.Background(), svc))
+	}
+
+	for _, group := range deletableGroups {
+		err = am.DeleteGroup(context.Background(), account.Id, groupAdminUserID, group.ID)
+		assert.NoError(t, err, "group %s is not referenced by an active reverse proxy gate and should be deletable", group.ID)
+	}
+}
+
 func TestDefaultAccountManager_DeleteGroupLinkedToFlowGroup(t *testing.T) {
 	am, _, err := createManager(t)
 	require.NoError(t, err)
@@ -406,6 +493,30 @@ func initTestGroupAccount(am *DefaultAccountManager) (*DefaultAccountManager, *t
 		Peers:     make([]string, 0),
 	}
 
+	groupForAgentNetworkPolicy := &types.Group{
+		ID:        "grp-for-agent-network-policy",
+		AccountID: "account-id",
+		Name:      "Group for agent network policies",
+		Issued:    types.GroupIssuedAPI,
+		Peers:     make([]string, 0),
+	}
+
+	groupForRPPrivate := &types.Group{
+		ID:        "grp-for-rp-private",
+		AccountID: "account-id",
+		Name:      "Group for private reverse proxy service",
+		Issued:    types.GroupIssuedAPI,
+		Peers:     make([]string, 0),
+	}
+
+	groupForRPBearer := &types.Group{
+		ID:        "grp-for-rp-bearer",
+		AccountID: "account-id",
+		Name:      "Group for bearer reverse proxy service",
+		Issued:    types.GroupIssuedAPI,
+		Peers:     make([]string, 0),
+	}
+
 	routeResource := &route.Route{
 		ID:     "example route",
 		Groups: []string{groupForRoute.ID},
@@ -461,6 +572,66 @@ func initTestGroupAccount(am *DefaultAccountManager) (*DefaultAccountManager, *t
 	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForSetupKeys)
 	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForUsers)
 	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForIntegration)
+	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForAgentNetworkPolicy)
+	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForRPPrivate)
+	_ = am.CreateGroup(context.Background(), accountID, groupAdminUserID, groupForRPBearer)
+
+	agentNetworkPolicy := &agentNetworkTypes.Policy{
+		ID:           "example agent network policy",
+		AccountID:    accountID,
+		Name:         "Example agent network policy",
+		Enabled:      true,
+		SourceGroups: []string{groupForAgentNetworkPolicy.ID},
+	}
+	if err := am.Store.SaveAgentNetworkPolicy(context.Background(), agentNetworkPolicy); err != nil {
+		return nil, nil, err
+	}
+
+	// The decoy services are created first so the linkage check has to scan
+	// past services that do not reference the groups under test.
+	rpServices := []*rpservice.Service{
+		{
+			ID:           "rp-svc-private-decoy",
+			AccountID:    accountID,
+			Domain:       "private-decoy.services.example.com",
+			Private:      true,
+			AccessGroups: []string{"unrelated-group"},
+		},
+		{
+			ID:        "rp-svc-bearer-decoy",
+			AccountID: accountID,
+			Domain:    "bearer-decoy.services.example.com",
+			Auth: rpservice.AuthConfig{
+				BearerAuth: &rpservice.BearerAuthConfig{
+					Enabled:            true,
+					DistributionGroups: []string{"unrelated-group"},
+				},
+			},
+		},
+		{
+			ID:           "rp-svc-private",
+			AccountID:    accountID,
+			Domain:       "private.services.example.com",
+			Private:      true,
+			AccessGroups: []string{groupForRPPrivate.ID},
+		},
+		{
+			ID:        "rp-svc-bearer",
+			AccountID: accountID,
+			Domain:    "bearer.services.example.com",
+			Auth: rpservice.AuthConfig{
+				BearerAuth: &rpservice.BearerAuthConfig{
+					Enabled:            true,
+					DistributionGroups: []string{groupForRPBearer.ID},
+				},
+			},
+		},
+	}
+	for _, svc := range rpServices {
+		if err := am.Store.CreateService(context.Background(), svc); err != nil {
+			return nil, nil, err
+		}
+	}
 
 	acc, err := am.Store.GetAccount(context.Background(), account.Id)
 	if err != nil {

management/server/permissions/manager.go

@@ -82,6 +82,9 @@ func (m *managerImpl) ValidateUserPermissions(
 	return m.ValidateRoleModuleAccess(ctx, accountID, role, module, operation), ctxEnriched, nil
 }
 
+// ValidateRoleModuleAccess resolves an operation against the role's explicit
+// grant for the module, then the grant for its parent module when the module
+// is a dotted submodule, and finally the role's AutoAllowNew default.
 func (m *managerImpl) ValidateRoleModuleAccess(
 	ctx context.Context,
 	accountID string,
@@ -89,7 +92,7 @@ func (m *managerImpl) ValidateRoleModuleAccess(
 	module modules.Module,
 	operation operations.Operation,
 ) bool {
-	if permissions, ok := role.Permissions[module]; ok {
+	if permissions, ok := lookupModulePermissions(role, module); ok {
 		if allowed, exists := permissions[operation]; exists {
 			return allowed
 		}
@@ -100,6 +103,21 @@ func (m *managerImpl) ValidateRoleModuleAccess(
 	return role.AutoAllowNew[operation]
 }
 
+// lookupModulePermissions returns the role's explicit permission set for the
+// module, falling back to the parent module's set for dotted submodules. The
+// second return reports whether any explicit set was found.
+func lookupModulePermissions(role roles.RolePermissions, module modules.Module) (map[operations.Operation]bool, bool) {
+	if permissions, ok := role.Permissions[module]; ok {
+		return permissions, true
+	}
+	if parent, hasParent := module.Parent(); hasParent {
+		if permissions, ok := role.Permissions[parent]; ok {
+			return permissions, true
+		}
+	}
+	return nil, false
+}
+
 func (m *managerImpl) ValidateAccountAccess(ctx context.Context, accountID string, user *types.User, allowOwnerAndAdmin bool) (context.Context, error) {
 	if user.AccountID != accountID {
 		return ctx, status.NewUserNotPartOfAccountError()
@@ -119,7 +137,7 @@ func (m *managerImpl) GetPermissionsByRole(ctx context.Context, role types.UserR
 	permissions := roles.Permissions{}
 
 	for k := range modules.All {
-		if rolePermissions, ok := roleMap.Permissions[k]; ok {
+		if rolePermissions, ok := lookupModulePermissions(roleMap, k); ok {
 			permissions[k] = rolePermissions
 			continue
 		}

management/server/permissions/manager_test.go

@@ -0,0 +1,139 @@
+package permissions
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/management/server/permissions/modules"
+	"github.com/netbirdio/netbird/management/server/permissions/operations"
+	"github.com/netbirdio/netbird/management/server/permissions/roles"
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+func TestValidateRoleModuleAccessSubmoduleCascade(t *testing.T) {
+	manager := NewManager(nil)
+	ctx := context.Background()
+
+	fullAccess := map[operations.Operation]bool{
+		operations.Read:   true,
+		operations.Create: true,
+		operations.Update: true,
+		operations.Delete: true,
+	}
+	readOnly := map[operations.Operation]bool{
+		operations.Read:   true,
+		operations.Create: false,
+		operations.Update: false,
+		operations.Delete: false,
+	}
+	denyAll := map[operations.Operation]bool{
+		operations.Read:   false,
+		operations.Create: false,
+		operations.Update: false,
+		operations.Delete: false,
+	}
+
+	t.Run("parent grant covers submodules", func(t *testing.T) {
+		role := roles.RolePermissions{
+			AutoAllowNew: denyAll,
+			Permissions:  roles.Permissions{modules.AgentNetwork: fullAccess},
+		}
+		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Create),
+			"parent full grant should allow create on a submodule")
+		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
+			"parent full grant should allow read on a submodule")
+	})
+
+	t.Run("submodule grant does not leak to parent or siblings", func(t *testing.T) {
+		role := roles.RolePermissions{
+			AutoAllowNew: denyAll,
+			Permissions:  roles.Permissions{modules.AgentNetworkUsage: readOnly},
+		}
+		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
+			"explicit submodule read should be allowed")
+		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Create),
+			"read-only submodule grant should not allow create")
+		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetwork, operations.Read),
+			"submodule grant should not grant the parent module")
+		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
+			"submodule grant should not grant a sibling submodule")
+	})
+
+	t.Run("explicit submodule entry wins over parent grant", func(t *testing.T) {
+		role := roles.RolePermissions{
+			AutoAllowNew: denyAll,
+			Permissions: roles.Permissions{
+				modules.AgentNetwork:     fullAccess,
+				modules.AgentNetworkLogs: denyAll,
+			},
+		}
+		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
+			"explicit submodule deny should override the parent grant")
+		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
+			"sibling submodules should still resolve through the parent grant")
+	})
+
+	t.Run("auto allow applies when neither submodule nor parent is granted", func(t *testing.T) {
+		role := roles.RolePermissions{
+			AutoAllowNew: readOnly,
+		}
+		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
+			"auto-allow read should apply to submodules")
+		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Delete),
+			"auto-allow should not grant unlisted operations")
+	})
+}
+
+// TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules pins the behavior the
+// submodule split must not change: every built-in role resolves the new
+// submodules exactly as it resolved the agent_network module before.
+func TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules(t *testing.T) {
+	manager := NewManager(nil)
+	ctx := context.Background()
+
+	submodules := []modules.Module{
+		modules.AgentNetworkProviders,
+		modules.AgentNetworkPolicies,
+		modules.AgentNetworkGuardrails,
+		modules.AgentNetworkBudgets,
+		modules.AgentNetworkUsage,
+		modules.AgentNetworkLogs,
+		modules.AgentNetworkSettings,
+	}
+	allOperations := []operations.Operation{operations.Read, operations.Create, operations.Update, operations.Delete}
+
+	for _, role := range []types.UserRole{types.UserRoleOwner, types.UserRoleAdmin, types.UserRoleAuditor, types.UserRoleNetworkAdmin, types.UserRoleUser} {
+		rolePermissions, ok := roles.RolesMap[role]
+		require.True(t, ok, "role %s must exist in RolesMap", role)
+
+		for _, sub := range submodules {
+			for _, op := range allOperations {
+				expected := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, modules.AgentNetwork, op)
+				actual := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, sub, op)
+				assert.Equal(t, expected, actual, "role %s: %s on %s should match the agent_network module", role, op, sub)
+			}
+		}
+	}
+}
+
+func TestGetPermissionsByRoleIncludesSubmodules(t *testing.T) {
+	manager := NewManager(nil)
+	ctx := context.Background()
+
+	permissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAuditor)
+	require.NoError(t, err, "auditor role must resolve")
+
+	usage, ok := permissions[modules.AgentNetworkUsage]
+	require.True(t, ok, "permissions map should contain the usage submodule")
+	assert.True(t, usage[operations.Read], "auditor should read the usage submodule")
+	assert.False(t, usage[operations.Update], "auditor should not update the usage submodule")
+
+	adminPermissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAdmin)
+	require.NoError(t, err, "admin role must resolve")
+	providers, ok := adminPermissions[modules.AgentNetworkProviders]
+	require.True(t, ok, "permissions map should contain the providers submodule")
+	assert.True(t, providers[operations.Delete], "admin should delete on the providers submodule")
+}

management/server/permissions/modules/module.go

@@ -1,5 +1,7 @@
 package modules
 
+import "strings"
+
 type Module string
 
 const (
@@ -20,6 +22,17 @@ const (
 	IdentityProviders Module = "identity_providers"
 	Services          Module = "services"
 	AgentNetwork      Module = "agent_network"
+
+	// Agent Network submodules. A role may grant one of these directly
+	// or grant the AgentNetwork parent, which covers all of them (see
+	// permissions.Manager cascade resolution).
+	AgentNetworkProviders  Module = "agent_network.providers"
+	AgentNetworkPolicies   Module = "agent_network.policies"
+	AgentNetworkGuardrails Module = "agent_network.guardrails"
+	AgentNetworkBudgets    Module = "agent_network.budgets"
+	AgentNetworkUsage      Module = "agent_network.usage"
+	AgentNetworkLogs       Module = "agent_network.logs"
+	AgentNetworkSettings   Module = "agent_network.settings"
 )
 
 var All = map[Module]struct{}{
@@ -40,4 +53,21 @@ var All = map[Module]struct{}{
 	IdentityProviders: {},
 	Services:          {},
 	AgentNetwork:      {},
+
+	AgentNetworkProviders:  {},
+	AgentNetworkPolicies:   {},
+	AgentNetworkGuardrails: {},
+	AgentNetworkBudgets:    {},
+	AgentNetworkUsage:      {},
+	AgentNetworkLogs:       {},
+	AgentNetworkSettings:   {},
+}
+
+// Parent returns the module owning a dotted submodule name and true, or the
+// module itself and false when it has no parent.
+func (m Module) Parent() (Module, bool) {
+	if i := strings.IndexByte(string(m), '.'); i > 0 {
+		return Module(string(m)[:i]), true
+	}
+	return m, false
 }

management/server/types/account.go

@@ -1707,14 +1707,34 @@ func (a *Account) injectPrivateServicePolicies(svc *service.Service, proxyPeers
 	if len(proxyPeers) == 0 {
 		return
 	}
+	// A service's AccessGroups can name groups that no longer exist — persisted
+	// services and the agent-network synthesiser both carry the ids verbatim from
+	// their own state. An unresolvable source authorises nothing, so drop it here
+	// rather than let the network-map assembly resolve it to a nil group.
+	sources := a.existingGroupIDs(svc.AccessGroups)
+	if len(sources) == 0 {
+		return
+	}
 	for _, proxyPeer := range proxyPeers {
-		a.Policies = append(a.Policies, a.createPrivateServicePolicy(svc, proxyPeer))
+		a.Policies = append(a.Policies, a.createPrivateServicePolicy(svc, proxyPeer, sources))
 	}
 }
 
-func (a *Account) createPrivateServicePolicy(svc *service.Service, proxyPeer *nbpeer.Peer) *Policy {
+// existingGroupIDs returns the subset of groupIDs that resolve to a group in the account,
+// preserving the input order.
+func (a *Account) existingGroupIDs(groupIDs []string) []string {
+	out := make([]string, 0, len(groupIDs))
+	for _, groupID := range groupIDs {
+		if _, ok := a.Groups[groupID]; ok {
+			out = append(out, groupID)
+		}
+	}
+	return out
+}
+
+func (a *Account) createPrivateServicePolicy(svc *service.Service, proxyPeer *nbpeer.Peer, accessGroups []string) *Policy {
 	policyID := fmt.Sprintf("private-access-%s-%s", svc.ID, proxyPeer.ID)
-	sources := append([]string(nil), svc.AccessGroups...)
+	sources := append([]string(nil), accessGroups...)
 	return &Policy{
 		ID:      policyID,
 		Name:    fmt.Sprintf("Private Access to %s", svc.Name),

management/server/types/proxy_access_token.go

@@ -68,7 +68,7 @@ type ProxyAccessTokenGenerated struct {
 // CreateNewProxyAccessToken generates a new proxy access token.
 // Returns the token with hashed value stored and plain token for one-time display.
 func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *string, createdBy string) (*ProxyAccessTokenGenerated, error) {
-	hashedToken, plainToken, err := generateProxyToken()
+	hashedToken, plainToken, err := GenerateProxyToken()
 	if err != nil {
 		return nil, err
 	}
@@ -94,7 +94,10 @@ func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *
 	}, nil
 }
 
-func generateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
+// GenerateProxyToken generates a new random proxy token, returning its SHA-256
+// hash (for storage) and the one-time plaintext. Exported so external modules
+// can mint tokens in the canonical proxy-token format.
+func GenerateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
 	secret, err := b.Random(ProxyTokenSecretLength)
 	if err != nil {
 		return "", "", err