[client] Fix lint issues in management and signal grpc clients

Rename ClientOption to Option in the management and signal client
packages so callers do not repeat the package name, and silence nilerr
on the offline-wait path where a cancelled context means shutdown
rather than a retryable failure.

.goreleaser_ui_gtk3.yaml

@@ -43,19 +43,17 @@ archives:
       - netbird-ui-gtk3
 
 nfpms:
-  # Same package_name as the GTK4 packages -- the two are mutually-exclusive
-  # alternatives served from separate repo paths (see uploads below); a given
-  # distro points at exactly one of them. The file names must still differ:
-  # the Debian pool is shared storage keyed by file name, so a default-named
-  # gtk3 .deb would overwrite the stable one.
+  # Mutually-exclusive alternative to the GTK4 netbird-ui package -- both
+  # ship the same /usr/bin/netbird-ui from the shared stable/yum repos, so
+  # this one carries its own name and conflicts with the GTK4 package.
   - maintainer: Netbird <dev@netbird.io>
     description: Netbird client UI.
     homepage: https://netbird.io/
     license: BSD-3-Clause
     vendor: NetBird
     id: netbird_ui_deb_gtk3
-    package_name: netbird-ui
-    file_name_template: "{{ .PackageName }}-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
+    package_name: netbird-ui-gtk3
+    file_name_template: "{{ .PackageName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
     builds:
       - netbird-ui-gtk3
     formats:
@@ -67,6 +65,10 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+    conflicts:
+      - netbird-ui
+    replaces:
+      - netbird-ui
     dependencies:
       - netbird (>= 0.75.0)
       - libgtk-3-0
@@ -79,8 +81,8 @@ nfpms:
     license: BSD-3-Clause
     vendor: NetBird
     id: netbird_ui_rpm_gtk3
-    package_name: netbird-ui
-    file_name_template: "{{ .PackageName }}-gtk3_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
+    package_name: netbird-ui-gtk3
+    file_name_template: "{{ .PackageName }}_{{ .Version }}_{{ .Os }}_{{ .Arch }}"
     builds:
       - netbird-ui-gtk3
     formats:
@@ -92,6 +94,10 @@ nfpms:
         dst: /usr/share/applications/org.wails.netbird.desktop
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
+    # No `replaces` here: nfpm maps it to rpm Obsoletes, which would make
+    # dnf swap installed GTK4 netbird-ui packages for this one on upgrade.
+    conflicts:
+      - netbird-ui
     dependencies:
       - netbird >= 0.75.0
       - (gtk3 or libgtk-3-0)
@@ -111,32 +117,20 @@ changelog:
   disable: true
 
 uploads:
-  # The gtk3 packages reuse the netbird-ui package name, so they live in
-  # dedicated repo paths (deb distribution `gtk3`, yum path `yum-gtk3`) that
-  # legacy distros point their repo config at.
-  #
-  # GoReleaser derives the credential env var from the upload name, so these
-  # would look for UPLOAD_DEBIAN-GTK3_SECRET / UPLOAD_YUM-GTK3_SECRET. The
-  # release workflow only exports UPLOAD_DEBIAN_SECRET / UPLOAD_YUM_SECRET, and
-  # a missing secret is a silent skip rather than a failure -- the packages
-  # reached the GitHub release but never the package repositories. Point
-  # `password` at the exported vars so both uploads authenticate.
-  - name: debian-gtk3
+  - name: debian
     skip: "{{ .Env.SKIP_PUBLISH }}"
     ids:
       - netbird_ui_deb_gtk3
     mode: archive
-    target: https://pkgs.wiretrustee.com/debian/pool/{{ .ArtifactName }};deb.distribution=gtk3;deb.component=main;deb.architecture={{ if .Arm }}armhf{{ else }}{{ .Arch }}{{ end }};deb.package=
+    target: https://pkgs.wiretrustee.com/debian/pool/{{ .ArtifactName }};deb.distribution=stable;deb.component=main;deb.architecture={{ if .Arm }}armhf{{ else }}{{ .Arch }}{{ end }};deb.package=
     username: dev@wiretrustee.com
-    password: "{{ .Env.UPLOAD_DEBIAN_SECRET }}"
     method: PUT
 
-  - name: yum-gtk3
+  - name: yum
     skip: "{{ .Env.SKIP_PUBLISH }}"
     ids:
       - netbird_ui_rpm_gtk3
     mode: archive
-    target: https://pkgs.wiretrustee.com/yum-gtk3/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }}
+    target: https://pkgs.wiretrustee.com/yum/{{ .Arch }}{{ if .Arm }}{{ .Arm }}{{ end }}
     username: dev@wiretrustee.com
-    password: "{{ .Env.UPLOAD_YUM_SECRET }}"
     method: PUT

client/android/client.go

@@ -26,6 +26,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/routemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -40,11 +42,6 @@ const (
 	AnonymizeLevelStrict  = nbAnonymize.LevelStrictString
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // TunAdapter export internal TunAdapter for mobile
 type TunAdapter interface {
 	device.TunAdapter
@@ -85,6 +82,13 @@ type Client struct {
 	deviceName            string
 	uiVersion             string
 	networkChangeListener listener.NetworkChangeListener
+	// netState outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run and RunWithoutLogin inject it into each new
+	// ConnectClient, which distributes it to every reconnection loop.
+	netState *netstate.State
+
+	// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
+	sweeper *netsweep.Sweeper
 
 	stateMu       sync.RWMutex
 	connectClient *internal.ConnectClient
@@ -156,6 +160,8 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
 		recorder:              peer.NewRecorder(""),
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
@@ -196,7 +202,8 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	}
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	// This path runs the interactive SSO flow, so reaching here means the peer
 	// is authenticated again — release the latch Status() reports from. Clear
@@ -237,7 +244,8 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
@@ -285,6 +293,23 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
 	}, nil
 }
 
+// SetNetworkAvailable feeds OS-reported network availability into the client.
+// While unavailable, the internal reconnect loops suspend their attempts and
+// the connection listener reports NoNetwork instead of Connecting; when
+// availability returns, the loops resume immediately with a fresh backoff.
+func (c *Client) SetNetworkAvailable(available bool) {
+	c.netState.Set(available)
+	c.recorder.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange cuts the management, signal and relay connections
+// after the OS switched networks, so the reconnect loops redial immediately
+// on the new one. The engine and the TUN device stay untouched.
+func (c *Client) NotifyNetworkChange() {
+	n := c.sweeper.Sweep()
+	log.Infof("network change: swept %d connections", n)
+}
+
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.
 // It works both with and without a running engine. anonymizeLevel is "default"
 // or "strict"; strict also anonymizes internal IP ranges, peer names, and
@@ -525,7 +550,11 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	if listener == nil {
+		c.recorder.RemoveConnectionListener()
+		return
+	}
+	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
 }
 
 // RemoveConnectionListener remove connection listener

client/android/connection_listener.go

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

client/grpc/dialer_generic.go

@@ -16,28 +16,47 @@ import (
 	"google.golang.org/grpc"
 
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netsweep"
 )
 
 func WithCustomDialer(_ bool, _ string) grpc.DialOption {
+	return grpc.WithContextDialer(dialContext)
+}
+
+// WithSweeper dials like WithCustomDialer but registers connections and
+// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
+// dial options in order, so the later context dialer wins.
+func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption {
 	return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
-		if runtime.GOOS == "linux" {
-			currentUser, err := user.Current()
-			if err != nil {
-				return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
-			}
+		dial := sweeper.StartDial(ctx)
+		defer dial.Release()
 
-			// the custom dialer requires root permissions which are not required for use cases run as non-root
-			if currentUser.Uid != "0" {
-				log.Debug("Not running as root, using standard dialer")
-				dialer := &net.Dialer{}
-				return dialer.DialContext(ctx, "tcp", addr)
-			}
-		}
-
-		conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+		conn, err := dialContext(dial.Ctx(), addr)
 		if err != nil {
-			return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+			return nil, err
 		}
-		return conn, nil
+		return dial.WrapConn(conn)
 	})
 }
+
+func dialContext(ctx context.Context, addr string) (net.Conn, error) {
+	if runtime.GOOS == "linux" {
+		currentUser, err := user.Current()
+		if err != nil {
+			return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
+		}
+
+		// the custom dialer requires root permissions which are not required for use cases run as non-root
+		if currentUser.Uid != "0" {
+			log.Debug("Not running as root, using standard dialer")
+			dialer := &net.Dialer{}
+			return dialer.DialContext(ctx, "tcp", addr)
+		}
+	}
+
+	conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+	}
+	return conn, nil
+}

client/grpc/dialer_js.go

@@ -3,6 +3,7 @@ package grpc
 import (
 	"google.golang.org/grpc"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/util/wsproxy/client"
 )
 
@@ -11,3 +12,8 @@ import (
 func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
 	return client.WithWebSocketDialer(tlsEnabled, component)
 }
+
+// WithSweeper is a no-op on WASM/JS: there is no network change signal.
+func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
+	return grpc.EmptyDialOption{}
+}

client/internal/connect.go

@@ -38,6 +38,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/ssh"
 	sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -70,18 +72,42 @@ type ConnectClient struct {
 	updateManager *updater.Manager
 
 	persistSyncResponse bool
+
+	// netState gates every reconnection loop on OS-reported network
+	// availability. Nil (the default) disables gating; mobile platforms
+	// inject it via WithNetworkState.
+	netState *netstate.State
+
+	// sweeper cuts the management, signal and relay connections on network
+	// change; nil disables it.
+	sweeper *netsweep.Sweeper
+}
+
+// ConnectClientOption configures optional ConnectClient behavior.
+type ConnectClientOption func(*ConnectClient)
+
+// WithNetworkState injects the OS network availability state that gates every
+// reconnection loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) ConnectClientOption {
+	return func(c *ConnectClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption {
+	return func(c *ConnectClient) { c.sweeper = sweeper }
 }
 
 func NewConnectClient(
 	ctx context.Context,
 	config *profilemanager.Config,
 	statusRecorder *peer.Status,
+	opts ...ConnectClientOption,
 ) *ConnectClient {
 	// Derive the run context here so Stop owns the cancel that unblocks the run
 	// loop. runCancel is set once at construction, so Stop can call it without
 	// racing the run loop's startup. Callers therefore need not cancel before Stop.
 	runCtx, runCancel := context.WithCancel(ctx)
-	return &ConnectClient{
+	c := &ConnectClient{
 		ctx:            runCtx,
 		runCancel:      runCancel,
 		runExited:      make(chan struct{}),
@@ -89,6 +115,10 @@ func NewConnectClient(
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
 	}
+	for _, opt := range opts {
+		opt(c)
+	}
+	return c
 }
 
 func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -274,6 +304,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			return nil
 		}
 
+		// suspend connection attempts while the OS reports no usable network
+		if waited, err := c.netState.Wait(c.ctx); err != nil {
+			return nil
+		} else if waited {
+			backOff.Reset()
+		}
+
 		state.Set(StatusConnecting)
 
 		engineCtx, cancel := context.WithCancel(c.ctx)
@@ -285,7 +322,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
-		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
+		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
+			mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
 		if err != nil {
 			// On daemon shutdown / Down() the parent context is cancelled
 			// and the dial fails with "context canceled". Wrapping that
@@ -360,7 +398,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
-		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
+		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -396,7 +434,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			engineConfig.StateDir = filepath.Dir(path)
 		}
 
-		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
+		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
+			relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
 		c.statusRecorder.SetRelayMgr(relayManager)
 		if len(relayURLs) > 0 {
 			if token != nil {
@@ -424,6 +463,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			UpdateManager:  c.updateManager,
 			ClientMetrics:  c.clientMetrics,
 			MetricsCtx:     c.ctx,
+			NetState:       c.netState,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine
@@ -480,6 +520,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	// status stream stuck at Connecting.
 	err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx))
 	if err != nil {
+		// Once the client context is cancelled backoff.WithContext surfaces the
+		// bare context error, and any attempt torn down mid-flight reports the
+		// same. That cancellation is the caller asking us to stop (Stop, Down or
+		// an engine restart), so exit cleanly instead of handing back a failure
+		// the caller would have to distinguish from a real one.
+		if c.ctx.Err() != nil && errors.Is(err, context.Canceled) {
+			log.Info("exiting client retry loop, context cancelled")
+			return nil
+		}
+
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 			state.Set(StatusNeedsLogin)
@@ -673,7 +723,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
 }
 
 // connectToSignal creates Signal Service client and established a connection
-func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
+func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
 	var sigTLSEnabled bool
 	if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
 		sigTLSEnabled = true
@@ -681,7 +731,8 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 		sigTLSEnabled = false
 	}
 
-	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
+	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
+		signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
 	if err != nil {
 		log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
 		return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)

client/internal/engine.go

@@ -59,6 +59,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/syncstore"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/jobexec"
+	"github.com/netbirdio/netbird/client/netstate"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -181,6 +182,9 @@ type EngineServices struct {
 	UpdateManager  *updater.Manager
 	ClientMetrics  *metrics.ClientMetrics
 	MetricsCtx     context.Context
+	// NetState gates the reconnection loops on OS-reported network
+	// availability; nil disables gating.
+	NetState *netstate.State
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -204,6 +208,10 @@ type Engine struct {
 	config    *EngineConfig
 	mobileDep MobileDependency
 
+	// netState gates the peer reconnection guards on OS-reported network
+	// availability; nil disables gating.
+	netState *netstate.State
+
 	// STUNs is a list of STUN servers used by ICE
 	STUNs []*stun.URI
 	// TURNs is a list of STUN servers used by ICE
@@ -337,6 +345,7 @@ func NewEngine(
 		syncMsgMux:         &sync.Mutex{},
 		config:             config,
 		mobileDep:          mobileDep,
+		netState:           services.NetState,
 		STUNs:              []*stun.URI{},
 		TURNs:              []*stun.URI{},
 		networkSerial:      0,
@@ -1893,7 +1902,8 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 			Addr:           e.getRosenpassAddr(),
 			PermissiveMode: e.config.RosenpassPermissive,
 		},
-		ICEConfig: e.createICEConfig(),
+		ICEConfig:    e.createICEConfig(),
+		NetworkState: e.netState,
 	}
 
 	serviceDependencies := peer.ServiceDependencies{

client/internal/peer/conn.go

@@ -26,6 +26,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/client/netstate"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
@@ -93,6 +94,10 @@ type ConnConfig struct {
 
 	// ICEConfig ICE protocol configuration
 	ICEConfig icemaker.Config
+
+	// NetworkState gates the reconnection guard on OS-reported network
+	// availability; nil disables gating.
+	NetworkState *netstate.State
 }
 
 type Conn struct {
@@ -254,7 +259,7 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error {
 		conn.handshaker.AddICEListener(conn.workerICE.OnNewOffer)
 	}
 
-	conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
+	conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher, conn.config.NetworkState)
 
 	conn.wg.Add(1)
 	go func() {

client/internal/peer/guard/guard.go

@@ -6,6 +6,8 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netstate"
 )
 
 // ConnStatus represents the connection state as seen by the guard.
@@ -31,20 +33,26 @@ type connStatusFunc func() ConnStatus
 // - Relayed connection disconnected
 // - ICE candidate changes
 type Guard struct {
-	log                     *log.Entry
-	isConnectedOnAllWay     connStatusFunc
-	timeout                 time.Duration
-	srWatcher               *SRWatcher
+	log                 *log.Entry
+	isConnectedOnAllWay connStatusFunc
+	timeout             time.Duration
+	srWatcher           *SRWatcher
+	// netState gates reconnect attempts on OS-reported network availability;
+	// nil disables gating.
+	netState                *netstate.State
 	relayedConnDisconnected chan struct{}
 	iCEConnDisconnected     chan struct{}
 }
 
-func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard {
+// NewGuard creates a reconnection guard for a peer connection. A nil netState
+// disables network availability gating.
+func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard {
 	return &Guard{
 		log:                     log,
 		isConnectedOnAllWay:     isConnectedFn,
 		timeout:                 timeout,
 		srWatcher:               srWatcher,
+		netState:                netState,
 		relayedConnDisconnected: make(chan struct{}, 1),
 		iCEConnDisconnected:     make(chan struct{}, 1),
 	}
@@ -96,9 +104,16 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	iceState := &iceRetryState{log: g.log}
 	defer iceState.reset()
 
+	netChanged := g.netState.Changed()
+
 	for {
 		select {
 		case <-tickerChannel:
+			// skip attempts while the OS reports no usable network; the
+			// netChanged case below resumes the loop once it returns
+			if !g.netState.IsOnline() {
+				continue
+			}
 			switch g.isConnectedOnAllWay() {
 			case ConnStatusConnected:
 				// all good, nothing to do
@@ -135,6 +150,23 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 			tickerChannel = ticker.C
 			iceState.reset()
 
+		case <-netChanged:
+			// Re-arm for the next transition before acting on this one.
+			netChanged = g.netState.Changed()
+			if !g.netState.IsOnline() {
+				continue
+			}
+			// Ticks skipped while offline drove the backoff towards its
+			// maximum without ever attempting, and left the ICE budget
+			// frozen — possibly in hourly mode. Recover on our own so the
+			// peer does not depend on a signal or relay event that never
+			// comes when both stayed up across the outage.
+			g.log.Debugf("network is back, reset reconnection ticker")
+			ticker.Stop()
+			ticker = g.newReconnectTicker(ctx)
+			tickerChannel = ticker.C
+			iceState.reset()
+
 		case <-ctx.Done():
 			g.log.Debugf("context is done, stop reconnect loop")
 			return

client/internal/peer/guard/guard_leak_test.go

@@ -15,7 +15,7 @@ import (
 
 func newTestGuard(status connStatusFunc) *Guard {
 	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
-	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
+	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw, nil)
 }
 
 // countBackoffTickerGoroutines returns how many goroutines are currently sitting

client/internal/peer/guard/guard_netstate_test.go

@@ -0,0 +1,107 @@
+package guard
+
+import (
+	"context"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the
+// backoff must be able to grow well past the outage, as it does in production
+// where the timeout is seconds to minutes.
+func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard {
+	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
+	return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState)
+}
+
+// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected
+// across a network outage while neither signal nor relay reports an event —
+// both stayed up, as on a short airplane mode toggle over Wi-Fi.
+//
+// Every tick taken while offline is skipped, but it still advances the
+// exponential backoff, so by the time the network returns the next tick can be
+// tens of seconds away. Without an explicit reaction to the transition the
+// peer waits out that interval for a recovery that could start immediately.
+func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	// Start from the reconnect ticker (800ms initial interval), the state a
+	// peer is in after it loses its connection.
+	go g.Start(ctx, func() { attempts.Add(1) })
+	g.SetRelayedConnDisconnected()
+
+	// Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped
+	// while offline, but each one doubles the wait for the next.
+	netState.Set(false)
+	time.Sleep(8 * time.Second)
+
+	offlineAttempts := attempts.Load()
+	if offlineAttempts != 0 {
+		t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts)
+	}
+
+	netState.Set(true)
+
+	// The next organic tick is now several seconds out, so anything within
+	// this window can only come from reacting to the transition itself.
+	pollCtx, stopPolling := context.WithTimeout(ctx, 2*time.Second)
+	defer stopPolling()
+
+	select {
+	case <-pollCtx.Done():
+		t.Fatal("peer was not retried within 2s of the network coming back, " +
+			"with neither a signal nor a relay event to fall back on")
+	case <-pollUntil(pollCtx, func() bool { return attempts.Load() > 0 }):
+	}
+}
+
+// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going
+// offline must not itself trigger an attempt.
+func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go g.Start(ctx, func() { attempts.Add(1) })
+
+	netState.Set(false)
+	time.Sleep(5 * time.Second)
+
+	if got := attempts.Load(); got != 0 {
+		t.Fatalf("callback ran %d times after going offline, want 0", got)
+	}
+}
+
+// pollUntil closes the returned channel once cond holds. It gives up when ctx
+// is done, so the polling goroutine never outlives the test that started it.
+func pollUntil(ctx context.Context, cond func() bool) <-chan struct{} {
+	done := make(chan struct{})
+	go func() {
+		for {
+			if cond() {
+				close(done)
+				return
+			}
+			select {
+			case <-ctx.Done():
+				return
+			case <-time.After(10 * time.Millisecond):
+			}
+		}
+	}()
+	return done
+}

client/internal/peer/listener.go

@@ -1,11 +1,40 @@
 package peer
 
+// ClientState identifies the client connection state delivered via
+// Listener.OnStateChanged.
+type ClientState int
+
+// Client states. The numeric values cross the gomobile boundary (the mobile
+// bindings re-export them as integer constants), so they are a wire format:
+// append new states at the end, never reorder or insert.
+const (
+	ClientStateDisconnected ClientState = iota
+	ClientStateConnected
+	ClientStateConnecting
+	ClientStateDisconnecting
+	// ClientStateNoNetwork is an overlay state: it is never stored as the
+	// last notification, only derived from ClientStateConnecting while the
+	// OS reports no usable network (see notifier.effectiveState).
+	ClientStateNoNetwork
+)
+
 // Listener is a callback type about the NetBird network connection state
 type Listener interface {
+	// OnStateChanged reports every client state transition. New states are
+	// delivered only through this callback; the per-state callbacks below
+	// are kept for compatibility and will be removed once all consumers
+	// have migrated.
+	OnStateChanged(state ClientState)
+
+	// Deprecated: consume OnStateChanged instead.
 	OnConnected()
+	// Deprecated: consume OnStateChanged instead.
 	OnDisconnected()
+	// Deprecated: consume OnStateChanged instead.
 	OnConnecting()
+	// Deprecated: consume OnStateChanged instead.
 	OnDisconnecting()
+
 	OnAddressChanged(string, string)
 	OnPeersListChanged(int)
 }

client/internal/peer/notifier.go

@@ -4,31 +4,64 @@ import (
 	"sync"
 )
 
-const (
-	stateDisconnected = iota
-	stateConnected
-	stateConnecting
-	stateDisconnecting
-)
-
 type notifier struct {
+	// publishLock orders state publication: it is held across computing the
+	// effective state and handing it to the listener, so a transition cannot
+	// overtake a newer one and leave the listener on a stale state.
+	publishLock        sync.Mutex
 	serverStateLock    sync.Mutex
 	listenersLock      sync.Mutex
 	listener           Listener
 	currentClientState bool
-	lastNotification   int
+	lastNotification   ClientState
 	lastNumberOfPeers  int
 	lastFqdnAddress    string
 	lastIPAddress      string
+	networkAvailable   bool
 }
 
 func newNotifier() *notifier {
-	return &notifier{}
+	return &notifier{
+		networkAvailable: true,
+	}
+}
+
+// effectiveState maps the computed state to what listeners should see:
+// while the OS reports no usable network, "Connecting" would be a lie —
+// connection attempts are suspended — so it is reported as NoNetwork.
+// Caller must hold serverStateLock.
+func (n *notifier) effectiveState(state ClientState) ClientState {
+	if !n.networkAvailable && state == ClientStateConnecting {
+		return ClientStateNoNetwork
+	}
+	return state
+}
+
+// setNetworkAvailable records the OS network availability and re-notifies
+// the listener when the flag flips the effective state (Connecting <->
+// NoNetwork).
+func (n *notifier) setNetworkAvailable(available bool) {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
+	n.serverStateLock.Lock()
+	if n.networkAvailable == available {
+		n.serverStateLock.Unlock()
+		return
+	}
+	previous := n.effectiveState(n.lastNotification)
+	n.networkAvailable = available
+	current := n.effectiveState(n.lastNotification)
+	n.serverStateLock.Unlock()
+
+	if previous != current {
+		n.notify(current)
+	}
 }
 
 func (n *notifier) setListener(listener Listener) {
 	n.serverStateLock.Lock()
-	lastNotification := n.lastNotification
+	lastNotification := n.effectiveState(n.lastNotification)
 	numOfPeers := n.lastNumberOfPeers
 	fqdnAddress := n.lastFqdnAddress
 	address := n.lastIPAddress
@@ -52,6 +85,9 @@ func (n *notifier) removeListener() {
 }
 
 func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	calculatedState := n.calculateState(mgmState, signalState)
 
@@ -61,43 +97,54 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
 	}
 
 	n.lastNotification = calculatedState
+	effective := n.effectiveState(calculatedState)
 	n.serverStateLock.Unlock()
 
-	n.notify(calculatedState)
+	n.notify(effective)
 }
 
 func (n *notifier) clientStart() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = true
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
+	effective := n.effectiveState(ClientStateConnecting)
 	n.serverStateLock.Unlock()
 
-	n.notify(stateConnecting)
+	n.notify(effective)
 }
 
 func (n *notifier) clientStop() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = stateDisconnected
+	n.lastNotification = ClientStateDisconnected
 	n.serverStateLock.Unlock()
 
-	n.notify(stateDisconnected)
+	n.notify(ClientStateDisconnected)
 }
 
 func (n *notifier) clientTearDown() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = stateDisconnecting
+	n.lastNotification = ClientStateDisconnecting
 	n.serverStateLock.Unlock()
 
-	n.notify(stateDisconnecting)
+	n.notify(ClientStateDisconnecting)
 }
 
-func (n *notifier) isServerStateChanged(newState int) bool {
+func (n *notifier) isServerStateChanged(newState ClientState) bool {
 	return n.lastNotification != newState
 }
 
-func (n *notifier) notify(state int) {
+func (n *notifier) notify(state ClientState) {
 	n.listenersLock.Lock()
 	listener := n.listener
 	n.listenersLock.Unlock()
@@ -109,20 +156,20 @@ func (n *notifier) notify(state int) {
 	notifyListener(listener, state)
 }
 
-func (n *notifier) calculateState(managementConn, signalConn bool) int {
+func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
 	if managementConn && signalConn {
-		return stateConnected
+		return ClientStateConnected
 	}
 
 	if !managementConn && !signalConn && !n.currentClientState {
-		return stateDisconnected
+		return ClientStateDisconnected
 	}
 
-	if n.lastNotification == stateDisconnecting {
-		return stateDisconnecting
+	if n.lastNotification == ClientStateDisconnecting {
+		return ClientStateDisconnecting
 	}
 
-	return stateConnecting
+	return ClientStateConnecting
 }
 
 func (n *notifier) peerListChanged(numOfPeers int) {
@@ -159,15 +206,19 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
 	listener.OnAddressChanged(fqdn, address)
 }
 
-func notifyListener(l Listener, state int) {
+func notifyListener(l Listener, state ClientState) {
+	// legacy per-state callbacks; NoNetwork is delivered only via
+	// OnStateChanged below
 	switch state {
-	case stateDisconnected:
+	case ClientStateDisconnected:
 		l.OnDisconnected()
-	case stateConnected:
+	case ClientStateConnected:
 		l.OnConnected()
-	case stateConnecting:
+	case ClientStateConnecting:
 		l.OnConnecting()
-	case stateDisconnecting:
+	case ClientStateDisconnecting:
 		l.OnDisconnecting()
 	}
+
+	l.OnStateChanged(state)
 }

client/internal/peer/notifier_concurrent_test.go

@@ -0,0 +1,108 @@
+package peer
+
+import (
+	"sync"
+	"testing"
+	"time"
+)
+
+type recordingListener struct {
+	mu      sync.Mutex
+	states  []ClientState
+	onState func(ClientState)
+}
+
+func (l *recordingListener) OnStateChanged(state ClientState) {
+	l.mu.Lock()
+	l.states = append(l.states, state)
+	hook := l.onState
+	l.mu.Unlock()
+
+	if hook != nil {
+		hook(state)
+	}
+}
+
+func (l *recordingListener) last() (ClientState, bool) {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	if len(l.states) == 0 {
+		return 0, false
+	}
+	return l.states[len(l.states)-1], true
+}
+
+func (l *recordingListener) snapshot() []ClientState {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	return append([]ClientState(nil), l.states...)
+}
+
+func (l *recordingListener) OnConnected()                    {}
+func (l *recordingListener) OnDisconnected()                 {}
+func (l *recordingListener) OnConnecting()                   {}
+func (l *recordingListener) OnDisconnecting()                {}
+func (l *recordingListener) OnAddressChanged(string, string) {}
+func (l *recordingListener) OnPeersListChanged(int)          {}
+
+// TestNotifier_ConcurrentAvailabilityFlipOrdersPublication holds the first
+// transition inside the listener callback and flips availability again from
+// another goroutine while it is parked. The second flip must not publish
+// ahead of the one in flight, otherwise the listener ends up on a state the
+// notifier already superseded.
+func TestNotifier_ConcurrentAvailabilityFlipOrdersPublication(t *testing.T) {
+	n := newNotifier()
+	n.currentClientState = true
+	n.lastNotification = ClientStateConnecting
+
+	entered := make(chan struct{})
+	release := make(chan struct{})
+
+	l := &recordingListener{}
+	l.onState = func(state ClientState) {
+		if state != ClientStateNoNetwork {
+			return
+		}
+		l.mu.Lock()
+		l.onState = nil
+		l.mu.Unlock()
+		close(entered)
+		<-release
+	}
+	n.listener = l
+
+	var wg sync.WaitGroup
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		n.setNetworkAvailable(false)
+	}()
+
+	<-entered
+
+	flipped := make(chan struct{})
+	go func() {
+		defer close(flipped)
+		n.setNetworkAvailable(true)
+	}()
+
+	select {
+	case <-flipped:
+		t.Fatal("the online transition published while the offline one was " +
+			"still in flight; publication is not serialized")
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	close(release)
+	<-flipped
+	wg.Wait()
+
+	got, ok := l.last()
+	if !ok {
+		t.Fatal("listener never observed a state")
+	}
+	if got != ClientStateConnecting {
+		t.Fatalf("listener holds %v after the network came back, want Connecting; sequence: %v",
+			got, l.snapshot())
+	}
+}

client/internal/peer/notifier_test.go

@@ -6,29 +6,32 @@ import (
 )
 
 type mocListener struct {
-	lastState int
+	lastState ClientState
 	wg        sync.WaitGroup
 	peersWg   sync.WaitGroup
 	peers     int
 }
 
 func (l *mocListener) OnConnected() {
-	l.lastState = stateConnected
+	l.lastState = ClientStateConnected
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnected() {
-	l.lastState = stateDisconnected
+	l.lastState = ClientStateDisconnected
 	l.wg.Done()
 }
 func (l *mocListener) OnConnecting() {
-	l.lastState = stateConnecting
+	l.lastState = ClientStateConnecting
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnecting() {
-	l.lastState = stateDisconnecting
+	l.lastState = ClientStateDisconnecting
 	l.wg.Done()
 }
 
+func (l *mocListener) OnStateChanged(state ClientState) {
+
+}
 func (l *mocListener) OnAddressChanged(host, addr string) {
 
 }
@@ -57,15 +60,15 @@ func Test_notifier_serverState(t *testing.T) {
 
 	type scenario struct {
 		name        string
-		expected    int
+		expected    ClientState
 		mgmState    bool
 		signalState bool
 	}
 	scenarios := []scenario{
-		{"connected", stateConnected, true, true},
-		{"mgm down", stateConnecting, false, true},
-		{"signal down", stateConnecting, true, false},
-		{"disconnected", stateDisconnected, false, false},
+		{"connected", ClientStateConnected, true, true},
+		{"mgm down", ClientStateConnecting, false, true},
+		{"signal down", ClientStateConnecting, true, false},
+		{"disconnected", ClientStateDisconnected, false, false},
 	}
 
 	for _, tt := range scenarios {
@@ -85,7 +88,7 @@ func Test_notifier_SetListener(t *testing.T) {
 	listener.setPeersWaiter()
 
 	n := newNotifier()
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
 	n.setListener(listener)
 	listener.wait()
 	listener.waitPeers()
@@ -99,7 +102,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
 	listener.setWaiter()
 	listener.setPeersWaiter()
 	n := newNotifier()
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
 	n.setListener(listener)
 	// setListener replays cached state on a goroutine; wait for both the state
 	// and peers callbacks to finish so we don't race on listener.peers.

client/internal/peer/status.go

@@ -1211,6 +1211,12 @@ func (d *Status) ClientTeardown() {
 	d.notifyStateChange()
 }
 
+// SetNetworkAvailable records the OS-reported network availability; while
+// unavailable, listeners see NoNetwork instead of Connecting.
+func (d *Status) SetNetworkAvailable(available bool) {
+	d.notifier.setNetworkAvailable(available)
+}
+
 // SetConnectionListener set a listener to the notifier
 func (d *Status) SetConnectionListener(listener Listener) {
 	d.notifier.setListener(listener)

client/ios/NetBirdSDK/client.go

@@ -22,6 +22,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/listener"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -36,11 +38,6 @@ const (
 	AnonymizeLevelStrict  = nbAnonymize.LevelStrictString
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // RouteListener export internal RouteListener for mobile
 type NetworkChangeListener interface {
 	listener.NetworkChangeListener
@@ -87,6 +84,12 @@ type Client struct {
 	onHostDnsFn           func([]string)
 	dnsManager            dns.IosDnsManager
 	loginComplete         bool
+	// netState outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run injects it into each new ConnectClient, which
+	// distributes it to every reconnection loop.
+	netState *netstate.State
+	// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
+	sweeper *netsweep.Sweeper
 	// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
 	preloadedConfig *profilemanager.Config
 
@@ -109,6 +112,8 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
 		dnsManager:            dnsManager,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
@@ -184,7 +189,8 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	c.onHostDnsFn = func([]string) {}
 	cfg.WgIface = interfaceName
 
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, connectClient)
 	// Persist the latest sync response so DebugBundle can include the network
 	// map. On iOS this is backed by disk to keep it out of the constrained
@@ -193,6 +199,24 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
 }
 
+// SetNetworkAvailable feeds OS-reported network availability into the client
+// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops
+// suspend their attempts and the connection listener reports NoNetwork
+// instead of Connecting; when availability returns, the loops resume
+// immediately with a fresh backoff.
+func (c *Client) SetNetworkAvailable(available bool) {
+	c.netState.Set(available)
+	c.recorder.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange cuts the management, signal and relay connections
+// after the OS switched networks, so the reconnect loops redial immediately
+// on the new one. The engine and the TUN device stay untouched.
+func (c *Client) NotifyNetworkChange() {
+	n := c.sweeper.Sweep()
+	log.Infof("network change: swept %d connections", n)
+}
+
 // Stop the internal client and free the resources
 func (c *Client) Stop() {
 	c.ctxCancelLock.Lock()
@@ -331,7 +355,11 @@ func (c *Client) GetStatusDetails() *StatusDetails {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	if listener == nil {
+		c.recorder.RemoveConnectionListener()
+		return
+	}
+	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
 }
 
 // RemoveConnectionListener remove connection listener

client/ios/NetBirdSDK/connection_listener.go

@@ -0,0 +1,43 @@
+//go:build ios
+
+package NetBirdSDK
+
+import (
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+// Client state values, re-exported as basic constants so gomobile emits them
+// into the generated bindings. They mirror peer.ClientState*: append-only,
+// never reorder.
+const (
+	ClientStateDisconnected  = int(peer.ClientStateDisconnected)
+	ClientStateConnected     = int(peer.ClientStateConnected)
+	ClientStateConnecting    = int(peer.ClientStateConnecting)
+	ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
+	ClientStateNoNetwork     = int(peer.ClientStateNoNetwork)
+)
+
+// ConnectionListener export internal Listener for mobile.
+//
+// It intentionally lacks OnStateChanged for now: adding a method to a gomobile
+// interface breaks every Swift implementation, so the iOS app keeps building
+// against the legacy per-state callbacks. A follow-up will extend it together
+// with the app.
+type ConnectionListener interface {
+	OnConnected()
+	OnDisconnected()
+	OnConnecting()
+	OnDisconnecting()
+	OnAddressChanged(string, string)
+	OnPeersListChanged(int)
+}
+
+// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
+// peer.Listener.
+type connectionListenerAdapter struct {
+	ConnectionListener
+}
+
+// OnStateChanged is dropped on iOS until the app adopts the state callback;
+// the legacy per-state callbacks continue to fire.
+func (a connectionListenerAdapter) OnStateChanged(peer.ClientState) {}

client/netstate/netstate.go

@@ -0,0 +1,107 @@
+// Package netstate tracks OS-reported network availability for the client.
+//
+// A State instance is owned by the platform integration (e.g. the Android or
+// iOS bindings, fed from ConnectivityManager callbacks or NWPathMonitor) and
+// is injected into the connection retry loops (management, signal, relay,
+// peer guards and the top-level connect loop), which consult it to avoid
+// burning CPU and battery on reconnect attempts while the device has no
+// network at all (e.g. airplane mode), and to reset their backoff as soon as
+// the network returns.
+//
+// Consumers hold a *State that may be nil — every non-mobile platform leaves
+// it unset. The read methods are safe on a nil receiver: they report online
+// and never block, so consumers behave as if this package did not exist.
+package netstate
+
+import (
+	"context"
+	"sync"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// State holds the OS-reported network availability. The zero value is not
+// usable; create instances with New.
+type State struct {
+	mu      sync.Mutex
+	online  bool
+	changed chan struct{}
+}
+
+// New creates a State that starts online.
+func New() *State {
+	return &State{
+		online:  true,
+		changed: make(chan struct{}),
+	}
+}
+
+// Set records whether the OS reports any usable network. Transitions wake up
+// all Wait callers immediately.
+func (s *State) Set(online bool) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	if s.online == online {
+		return
+	}
+	s.online = online
+	close(s.changed)
+	s.changed = make(chan struct{})
+	log.Infof("OS network availability changed: online=%t", online)
+}
+
+// IsOnline reports whether the OS reports at least one usable network. On a
+// nil receiver — no State injected — it reports online.
+func (s *State) IsOnline() bool {
+	if s == nil {
+		return true
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.online
+}
+
+// Changed returns a channel closed on the next availability transition, for
+// callers that already own a select loop and cannot block in Wait. Re-read it
+// after every fire: each transition installs a fresh channel. On a nil
+// receiver — no State injected — it returns nil, which blocks forever in a
+// select, so the caller simply never observes a transition.
+func (s *State) Changed() <-chan struct{} {
+	if s == nil {
+		return nil
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.changed
+}
+
+// Wait blocks while the network is offline. It reports whether it had to
+// wait, so callers can reset their backoff after an outage. It returns early
+// with the context error when ctx is done. On a nil receiver — no State
+// injected — it returns immediately.
+func (s *State) Wait(ctx context.Context) (bool, error) {
+	if s == nil {
+		return false, nil
+	}
+	waited := false
+	for {
+		s.mu.Lock()
+		if s.online {
+			s.mu.Unlock()
+			return waited, nil
+		}
+		ch := s.changed
+		s.mu.Unlock()
+
+		if !waited {
+			waited = true
+			log.Debugf("network is offline, pausing connection attempts")
+		}
+
+		select {
+		case <-ctx.Done():
+			return waited, ctx.Err()
+		case <-ch:
+		}
+	}
+}

client/netstate/netstate_test.go

@@ -0,0 +1,170 @@
+package netstate
+
+import (
+	"context"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestNewStateIsOnline(t *testing.T) {
+	assert.True(t, New().IsOnline(), "a fresh State should start online")
+}
+
+func TestSetTogglesOnlineState(t *testing.T) {
+	s := New()
+
+	s.Set(false)
+	assert.False(t, s.IsOnline(), "state should be offline after Set(false)")
+
+	s.Set(true)
+	assert.True(t, s.IsOnline(), "state should be online after Set(true)")
+}
+
+func TestWaitReturnsImmediatelyWhenOnline(t *testing.T) {
+	s := New()
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+
+	waited, err := s.Wait(ctx)
+	require.NoError(t, err)
+	assert.False(t, waited, "Wait should not block when the network is online")
+}
+
+func TestWaitBlocksUntilOnline(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	result := make(chan bool, 1)
+	go func() {
+		waited, err := s.Wait(ctx)
+		if err != nil {
+			result <- false
+			return
+		}
+		result <- waited
+	}()
+
+	// Verify Wait is actually blocking while offline
+	select {
+	case <-result:
+		t.Fatal("Wait should block while the network is offline")
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	s.Set(true)
+
+	select {
+	case waited := <-result:
+		assert.True(t, waited, "Wait should report that it had to wait for the network")
+	case <-time.After(2 * time.Second):
+		t.Fatal("Wait should return promptly after the network becomes available")
+	}
+}
+
+func TestWaitReturnsOnContextCancel(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithCancel(context.Background())
+
+	result := make(chan error, 1)
+	go func() {
+		_, err := s.Wait(ctx)
+		result <- err
+	}()
+
+	cancel()
+
+	select {
+	case err := <-result:
+		assert.ErrorIs(t, err, context.Canceled)
+	case <-time.After(2 * time.Second):
+		t.Fatal("Wait should return promptly after context cancellation")
+	}
+}
+
+func TestWaitWakesAllWaiters(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	const waiters = 10
+	var wg sync.WaitGroup
+	results := make(chan bool, waiters)
+	for i := 0; i < waiters; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			waited, err := s.Wait(ctx)
+			if err != nil {
+				results <- false
+				return
+			}
+			results <- waited
+		}()
+	}
+
+	time.Sleep(100 * time.Millisecond)
+	s.Set(true)
+	wg.Wait()
+
+	close(results)
+	count := 0
+	for waited := range results {
+		assert.True(t, waited, "every waiter should report that it waited")
+		count++
+	}
+	assert.Equal(t, waiters, count, "all waiters should have returned")
+}
+
+func TestNilStateReadsAreNoops(t *testing.T) {
+	var s *State
+
+	assert.True(t, s.IsOnline(), "nil State should report online")
+
+	waited, err := s.Wait(context.Background())
+	require.NoError(t, err)
+	assert.False(t, waited, "nil State's Wait should not block")
+}
+
+func TestConcurrentSetAndWait(t *testing.T) {
+	s := New()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	var wg sync.WaitGroup
+	for i := 0; i < 4; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			for j := 0; j < 100; j++ {
+				s.Set(j%2 == 0)
+				s.IsOnline()
+			}
+		}()
+	}
+	for i := 0; i < 4; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			for j := 0; j < 100; j++ {
+				if _, err := s.Wait(ctx); err != nil {
+					return
+				}
+			}
+		}()
+	}
+
+	wg.Wait()
+}

client/netsweep/netsweep.go

@@ -0,0 +1,175 @@
+// Package netsweep cuts network-bound activity when the OS switches networks:
+// a sweep closes the registered connections and aborts the in-flight dials, so
+// their owners redial immediately instead of waiting for the old sockets to
+// time out.
+//
+// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
+package netsweep
+
+import (
+	"context"
+	"errors"
+	"net"
+	"sync"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// ErrSwept reports that a dial finished after a network change swept its
+// registration. The connection is already closed; the caller must treat it
+// as a failed dial and redial on the new network.
+var ErrSwept = errors.New("netsweep: connection swept by network change")
+
+// sweepID identifies one registration in a sweeper. Connections and dials
+// draw from the same counter, so an id is unique across both registries.
+type sweepID uint64
+
+// Dial tracks one dial from start to connection registration. It hands the
+// dialed connection to the sweeper atomically, so a sweep can never fall
+// between the dial finishing and the connection being registered.
+type Dial struct {
+	sweeper *Sweeper
+	ctx     context.Context
+	cancel  context.CancelFunc
+	id      sweepID
+	done    bool // set by Sweep, WrapConn or Release; guarded by sweeper.mu
+}
+
+// Ctx returns the dial's context. Sweep cancels it, so a dial started on the
+// old network aborts instead of waiting out its handshake timeout.
+func (d *Dial) Ctx() context.Context {
+	return d.ctx
+}
+
+// Release ends the dial's registration and cancels its context. It is
+// idempotent and safe after WrapConn, so callers can defer it.
+func (d *Dial) Release() {
+	s := d.sweeper
+	if s == nil {
+		return
+	}
+
+	s.mu.Lock()
+	d.done = true
+	delete(s.dials, d.id)
+	s.mu.Unlock()
+
+	d.cancel()
+}
+
+// sweptConn deregisters itself from the sweeper when closed.
+type sweptConn struct {
+	net.Conn
+	sweeper *Sweeper
+	id      sweepID
+}
+
+func (c *sweptConn) Close() error {
+	c.sweeper.deregister(c.id)
+	return c.Conn.Close()
+}
+
+// Sweeper registers live connections and in-flight dials so Sweep can cut
+// everything that started before the network changed.
+type Sweeper struct {
+	mu     sync.Mutex
+	conns  map[sweepID]net.Conn
+	dials  map[sweepID]*Dial
+	nextID sweepID
+}
+
+// New creates an empty sweeper.
+func New() *Sweeper {
+	return &Sweeper{
+		conns: make(map[sweepID]net.Conn),
+		dials: make(map[sweepID]*Dial),
+	}
+}
+
+// StartDial registers an in-flight dial. Dial with Ctx, hand the result to
+// WrapConn, and Release the dial when the attempt is over, typically deferred.
+func (s *Sweeper) StartDial(ctx context.Context) *Dial {
+	if s == nil {
+		return &Dial{ctx: ctx}
+	}
+
+	ctx, cancel := context.WithCancel(ctx)
+	d := &Dial{sweeper: s, ctx: ctx, cancel: cancel}
+
+	s.mu.Lock()
+	d.id = s.nextID
+	s.nextID++
+	s.dials[d.id] = d
+	s.mu.Unlock()
+
+	return d
+}
+
+// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial,
+// the connection belongs to the old network: it is closed and ErrSwept is
+// returned. Otherwise conn is registered against the next sweep and returned
+// wrapped, deregistering itself on Close. Call it once, before Release.
+func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) {
+	s := d.sweeper
+	if s == nil {
+		return conn, nil
+	}
+
+	s.mu.Lock()
+	if d.done {
+		s.mu.Unlock()
+		if err := conn.Close(); err != nil {
+			log.Debugf("swept dial close error: %v", err)
+		}
+		return nil, ErrSwept
+	}
+	d.done = true
+	delete(s.dials, d.id)
+	id := s.nextID
+	s.nextID++
+	s.conns[id] = conn
+	s.mu.Unlock()
+
+	return &sweptConn{Conn: conn, sweeper: s, id: id}, nil
+}
+
+// Sweep closes every registered connection, aborts every in-flight dial, and
+// returns how many connections it closed. A dial whose connection was not
+// yet handed to WrapConn is marked, so the late WrapConn closes it instead
+// of registering it.
+func (s *Sweeper) Sweep() int {
+	if s == nil {
+		return 0
+	}
+
+	s.mu.Lock()
+	conns := s.conns
+	dials := s.dials
+	s.conns = make(map[sweepID]net.Conn)
+	s.dials = make(map[sweepID]*Dial)
+	for _, d := range dials {
+		d.done = true
+	}
+	s.mu.Unlock()
+
+	if len(dials) > 0 {
+		log.Debugf("aborting %d in-flight dials", len(dials))
+		for _, d := range dials {
+			d.cancel()
+		}
+	}
+
+	for _, conn := range conns {
+		log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr())
+		if err := conn.Close(); err != nil {
+			log.Debugf("swept connection close error: %v", err)
+		}
+	}
+	return len(conns)
+}
+
+func (s *Sweeper) deregister(id sweepID) {
+	s.mu.Lock()
+	delete(s.conns, id)
+	s.mu.Unlock()
+}

client/netsweep/netsweep_test.go

@@ -0,0 +1,168 @@
+package netsweep
+
+import (
+	"context"
+	"net"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestSweepClosesRegisteredConns(t *testing.T) {
+	sweeper := New()
+
+	c1 := wrap(t, sweeper, connPair(t))
+	c2 := wrap(t, sweeper, connPair(t))
+
+	assert.Equal(t, 2, sweeper.Sweep(), "both live connections should be closed")
+
+	// The wrappers must report closed now.
+	buf := make([]byte, 1)
+	_, err := c1.Read(buf)
+	assert.Error(t, err, "first connection should be unusable after the sweep")
+	_, err = c2.Read(buf)
+	assert.Error(t, err, "second connection should be unusable after the sweep")
+
+	assert.Equal(t, 0, sweeper.Sweep(), "second sweep should find nothing")
+}
+
+func TestCloseDeregisters(t *testing.T) {
+	sweeper := New()
+
+	conn := wrap(t, sweeper, connPair(t))
+	require.NoError(t, conn.Close())
+
+	assert.Equal(t, 0, sweeper.Sweep(), "closed connection must leave the registry")
+}
+
+func TestCloseIsIdempotent(t *testing.T) {
+	sweeper := New()
+
+	conn := wrap(t, sweeper, connPair(t))
+	require.NoError(t, conn.Close())
+	assert.Error(t, conn.Close(), "double close surfaces the underlying error but must not panic")
+}
+
+func TestSweepOnlyAffectsOlderConns(t *testing.T) {
+	sweeper := New()
+
+	_ = wrap(t, sweeper, connPair(t))
+	assert.Equal(t, 1, sweeper.Sweep())
+
+	// A connection dialed after the sweep must survive until the next one.
+	_ = wrap(t, sweeper, connPair(t))
+	assert.Equal(t, 1, sweeper.Sweep(), "post-sweep connection belongs to the next sweep")
+}
+
+func TestSweepAbortsInFlightDials(t *testing.T) {
+	sweeper := New()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	sweeper.Sweep()
+
+	assert.ErrorIs(t, dial.Ctx().Err(), context.Canceled, "sweep must cancel the in-flight dial context")
+}
+
+func TestReleasedDialIsNotAborted(t *testing.T) {
+	sweeper := New()
+
+	// Simulate a dial that finished before the sweep.
+	released := sweeper.StartDial(context.Background())
+	released.Release()
+
+	// A dial still in flight during the sweep.
+	pending := sweeper.StartDial(context.Background())
+	defer pending.Release()
+
+	sweeper.Sweep()
+	assert.ErrorIs(t, pending.Ctx().Err(), context.Canceled, "pending dial must be aborted")
+}
+
+func TestSweepBetweenDialAndHandoffClosesConn(t *testing.T) {
+	sweeper := New()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	// The dial succeeds on the old network, then the sweep lands before the
+	// connection is handed over.
+	conn := connPair(t)
+	assert.Equal(t, 0, sweeper.Sweep(), "the connection is not registered yet")
+
+	wrapped, err := dial.WrapConn(conn)
+	require.ErrorIs(t, err, ErrSwept)
+	require.Nil(t, wrapped)
+
+	buf := make([]byte, 1)
+	_, err = conn.Read(buf)
+	assert.Error(t, err, "the old-network connection must be closed, not leaked")
+
+	assert.Equal(t, 0, sweeper.Sweep(), "nothing may leak into the next sweep")
+}
+
+func TestNilSweeperIsNoop(t *testing.T) {
+	var sweeper *Sweeper
+
+	conn := connPair(t)
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	wrapped, err := dial.WrapConn(conn)
+	require.NoError(t, err)
+	assert.Equal(t, conn, wrapped, "nil sweeper must return the conn unchanged")
+	assert.NoError(t, dial.Ctx().Err(), "nil sweeper must not cancel the dial context")
+	assert.Equal(t, 0, sweeper.Sweep(), "nil sweeper closes nothing")
+}
+
+// wrap registers conn with the sweeper through a completed dial.
+func wrap(t *testing.T, sweeper *Sweeper, conn net.Conn) net.Conn {
+	t.Helper()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	wrapped, err := dial.WrapConn(conn)
+	require.NoError(t, err)
+	return wrapped
+}
+
+// connPair dials a loopback TCP connection and keeps the accepted peer open
+// until the test ends: a peer that closed early would make the connection
+// unreadable on its own, so a read error after the sweep would prove nothing.
+func connPair(t *testing.T) net.Conn {
+	t.Helper()
+
+	l, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+	t.Cleanup(func() {
+		if err := l.Close(); err != nil {
+			t.Logf("listener close error: %v", err)
+		}
+	})
+
+	accepted := make(chan net.Conn, 1)
+	go func() {
+		conn, err := l.Accept()
+		if err != nil {
+			close(accepted)
+			return
+		}
+		accepted <- conn
+	}()
+
+	conn, err := net.Dial("tcp", l.Addr().String())
+	require.NoError(t, err)
+
+	peer, ok := <-accepted
+	require.True(t, ok, "listener must accept the dialed connection")
+	t.Cleanup(func() {
+		if err := peer.Close(); err != nil {
+			t.Logf("peer close error: %v", err)
+		}
+	})
+
+	return conn
+}

client/ssh/server/command_execution_windows.go

@@ -243,7 +243,7 @@ func (s *Server) setUserEnvironmentVariables(envMap map[string]string, userProfi
 
 // prepareCommandEnv prepares environment variables for command execution on Windows
 func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, session ssh.Session) []string {
-	username, domain := s.parseUsername(localUser.Username)
+	username, domain := parseUsername(localUser.Username)
 	userEnv, err := s.getUserEnvironment(logger, username, domain)
 	if err != nil {
 		log.Debugf("failed to get user environment for %s\\%s, using fallback: %v", domain, username, err)
@@ -383,7 +383,7 @@ func (s *Server) executeCommandWithPty(logger *log.Entry, session ssh.Session, _
 		return false
 	}
 
-	username, domain := s.parseUsername(localUser.Username)
+	username, domain := parseUsername(localUser.Username)
 	shell := getUserShell(localUser.Uid)
 
 	req := PtyExecutionRequest{

client/ssh/server/port_forwarding.go

@@ -133,7 +133,12 @@ func (s *Server) checkPrivilegedPortAccess(forwardType string, port uint32, resu
 		return nil
 	}
 
-	if result.User != nil && isPrivilegedUsername(result.User.Username) {
+	// Only uid 0 may bind below the threshold, which is the kernel's own rule and
+	// is asked directly rather than through isPrivilegedOrUnknown: that helper
+	// reports an account it cannot evaluate as privileged, which is safe for a
+	// refusal and unsafe for a grant such as this one. Windows has returned
+	// above, so Uid here is a Unix uid and never a SID.
+	if result.User != nil && result.User.Uid == "0" {
 		return nil
 	}
 

client/ssh/server/privileges_other.go

@@ -0,0 +1,16 @@
+//go:build !windows
+
+package server
+
+// isProcessElevated is only meaningful on Windows; other platforms use the
+// effective UID check in isCurrentProcessPrivileged.
+func isProcessElevated() bool {
+	return false
+}
+
+// isWindowsAccountPrivilegedOrUnknown is only reachable on Windows. Report
+// privileged on other platforms so a caller refusing privileged accounts fails
+// closed.
+func isWindowsAccountPrivilegedOrUnknown(string) bool {
+	return true
+}

client/ssh/server/privileges_windows.go

@@ -0,0 +1,228 @@
+//go:build windows
+
+package server
+
+import (
+	"fmt"
+	"strings"
+	"unsafe"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sys/windows"
+)
+
+var (
+	netapi32                  = windows.NewLazySystemDLL("netapi32.dll")
+	procNetUserGetLocalGroups = netapi32.NewProc("NetUserGetLocalGroups")
+)
+
+const (
+	// lgIncludeIndirect makes NetUserGetLocalGroups also return local groups
+	// the user belongs to through a global group.
+	lgIncludeIndirect  = 0x1
+	maxPreferredLength = 0xFFFFFFFF
+)
+
+// localGroupUsersInfo0 mirrors LOCALGROUP_USERS_INFO_0.
+type localGroupUsersInfo0 struct {
+	name *uint16
+}
+
+// isProcessElevated reports whether the current process token is elevated
+// (TokenElevation): true for elevated administrators, the built-in
+// Administrator, administrators with UAC disabled, and SYSTEM; false for
+// standard users and administrators running with a UAC-filtered token.
+func isProcessElevated() bool {
+	return windows.GetCurrentProcessToken().IsElevated()
+}
+
+// isWindowsAccountPrivilegedOrUnknown reports whether the account is privileged
+// on this machine: a well-known service account, a built-in Administrator
+// (RID 500), or a member of the local Administrators group, directly or through
+// nested groups.
+//
+// An account whose privilege cannot be determined counts as privileged, which
+// is why the name says "or unknown". That is fail-closed for a caller that
+// refuses privileged accounts, and fail-open for a caller that grants something
+// to them, so only the former may use this.
+func isWindowsAccountPrivilegedOrUnknown(username string) bool {
+	sid, _, _, err := windows.LookupSID("", username)
+	if err != nil {
+		log.Warnf("privilege check: SID lookup for %q failed, treating as privileged: %v", username, err)
+		return true
+	}
+
+	if isPrivilegedUserSID(sid) {
+		return true
+	}
+
+	member, err := isLocalAdminsMember(username)
+	if err != nil {
+		log.Warnf("privilege check: cannot determine Administrators membership for %q, treating as privileged: %v", username, err)
+		return true
+	}
+	return member
+}
+
+// isPrivilegedUserSID reports whether the SID itself identifies a privileged
+// principal, without consulting group membership.
+func isPrivilegedUserSID(sid *windows.SID) bool {
+	wellKnown := []windows.WELL_KNOWN_SID_TYPE{
+		windows.WinLocalSystemSid,
+		windows.WinLocalServiceSid,
+		windows.WinNetworkServiceSid,
+		windows.WinBuiltinAdministratorsSid,
+	}
+	for _, sidType := range wellKnown {
+		if sid.IsWellKnown(sidType) {
+			return true
+		}
+	}
+	return isBuiltinAdministratorSID(sid)
+}
+
+// isBuiltinAdministratorSID reports whether the SID is a machine or domain
+// built-in Administrator account (S-1-5-21-...-500). RID 500 is reserved for
+// that account; it can be renamed but cannot be removed from the
+// Administrators group.
+func isBuiltinAdministratorSID(sid *windows.SID) bool {
+	if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY {
+		return false
+	}
+	count := sid.SubAuthorityCount()
+	if count < 2 || sid.SubAuthority(0) != 21 {
+		return false
+	}
+	return sid.SubAuthority(uint32(count-1)) == 500
+}
+
+// isLocalAdminsMember reports whether the account is a member of the local
+// Administrators group.
+//
+// Local accounts are checked against the local SAM, which is authoritative for
+// them and, unlike a token, cannot under-report: UAC filters the tokens of
+// local administrators, and a filtered token carries Administrators as
+// deny-only, which a membership check on the token would read as "not a
+// member". Domain accounts are exempt from that filtering, so for them an S4U
+// token is preferred because its group list is LSA's transitive expansion and
+// therefore covers nested and universal groups plus the machine's own local
+// groups. NetUserGetLocalGroups expands only one global-group hop but needs no
+// logon, so it serves as the fallback when no token can be obtained.
+func isLocalAdminsMember(username string) (bool, error) {
+	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	if err != nil {
+		return false, fmt.Errorf("create Administrators SID: %w", err)
+	}
+
+	account, domain := parseUsername(username)
+	if NewPrivilegeDropper().isLocalUser(domain) {
+		return localGroupsContainSID(account, adminSid)
+	}
+
+	member, s4uErr := s4uTokenIsMember(account, domain, adminSid)
+	if s4uErr == nil {
+		return member, nil
+	}
+	log.Debugf("privilege check: S4U membership check for %q failed, falling back to local group enumeration: %v", username, s4uErr)
+
+	member, err = localGroupsContainSID(buildUserCpn(account, domain), adminSid)
+	if err != nil {
+		return false, fmt.Errorf("S4U check: %w; local group enumeration: %w", s4uErr, err)
+	}
+	return member, nil
+}
+
+// s4uTokenIsMember obtains an S4U token for the account and checks whether the
+// given SID is enabled in it.
+func s4uTokenIsMember(account, domain string, sid *windows.SID) (bool, error) {
+	token, err := generateS4UUserToken(log.NewEntry(log.StandardLogger()), account, domain)
+	if err != nil {
+		return false, err
+	}
+	defer func() {
+		if err := windows.CloseHandle(token); err != nil {
+			log.Debugf("close S4U token: %v", err)
+		}
+	}()
+	return windows.Token(token).IsMember(sid)
+}
+
+// localGroupsContainSID reports whether the wanted group is among the local
+// groups the account belongs to, directly or through a global group.
+//
+// The wanted SID is resolved to its group name once and compared against the
+// enumerated names. Well-known SIDs resolve from a static table, so that lookup
+// needs no domain controller, and it keeps the comparison correct for a renamed
+// or localized group because both sides then carry the new name. Resolving each
+// enumerated name back to a SID instead would add a lookup per group that can
+// block until it times out while a domain controller is unreachable, and cannot
+// change the outcome: the names enumerated here are local groups of this
+// machine, whose names are unique, so a name match identifies the group.
+//
+// A failure to resolve the wanted SID is returned rather than reported as
+// "not a member", so a privilege check built on this fails closed.
+func localGroupsContainSID(username string, want *windows.SID) (bool, error) {
+	wantName, _, _, err := want.LookupAccount("")
+	if err != nil {
+		return false, fmt.Errorf("resolve group SID %s to a name: %w", want, err)
+	}
+
+	groups, err := netUserGetLocalGroups(username)
+	if err != nil {
+		return false, err
+	}
+
+	for _, group := range groups {
+		if strings.EqualFold(group, wantName) {
+			return true, nil
+		}
+	}
+	return false, nil
+}
+
+// netUserGetLocalGroups returns the names of the local groups the account is a
+// member of, including indirect membership through global groups.
+func netUserGetLocalGroups(username string) ([]string, error) {
+	name16, err := windows.UTF16PtrFromString(username)
+	if err != nil {
+		return nil, fmt.Errorf("convert username: %w", err)
+	}
+
+	var buf *byte
+	var entriesRead, totalEntries uint32
+	status, _, _ := procNetUserGetLocalGroups.Call(
+		0, // local server
+		uintptr(unsafe.Pointer(name16)),
+		0, // level 0: LOCALGROUP_USERS_INFO_0
+		lgIncludeIndirect,
+		uintptr(unsafe.Pointer(&buf)),
+		maxPreferredLength,
+		uintptr(unsafe.Pointer(&entriesRead)),
+		uintptr(unsafe.Pointer(&totalEntries)),
+	)
+	if status != 0 {
+		return nil, fmt.Errorf("NetUserGetLocalGroups for %q: status %d", username, status)
+	}
+	if buf == nil {
+		return nil, nil
+	}
+	defer func() {
+		if err := windows.NetApiBufferFree(buf); err != nil {
+			log.Debugf("free NetApi buffer: %v", err)
+		}
+	}()
+
+	// MAX_PREFERRED_LENGTH makes the API allocate as much as it needs, so a
+	// short read is not expected. Report it rather than silently returning a
+	// subset of the account's groups.
+	if entriesRead != totalEntries {
+		return nil, fmt.Errorf("NetUserGetLocalGroups for %q returned %d of %d groups", username, entriesRead, totalEntries)
+	}
+
+	entries := unsafe.Slice((*localGroupUsersInfo0)(unsafe.Pointer(buf)), entriesRead)
+	groups := make([]string, 0, entriesRead)
+	for _, entry := range entries {
+		groups = append(groups, windows.UTF16PtrToString(entry.name))
+	}
+	return groups, nil
+}

client/ssh/server/privileges_windows_test.go

@@ -0,0 +1,293 @@
+//go:build windows
+
+package server
+
+import (
+	"os/user"
+	"testing"
+	"unsafe"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"golang.org/x/sys/windows"
+)
+
+// filterNormalAccount limits NetUserEnum to normal user accounts.
+const filterNormalAccount = 0x2
+
+// TOKEN_ELEVATION_TYPE values.
+const (
+	tokenElevationTypeDefault = 1
+	tokenElevationTypeFull    = 2
+	tokenElevationTypeLimited = 3
+)
+
+// tokenElevationType reads TokenElevationType from a token.
+func tokenElevationType(token windows.Token) (uint32, error) {
+	var elevationType, returnedLen uint32
+	err := windows.GetTokenInformation(token, windows.TokenElevationType,
+		(*byte)(unsafe.Pointer(&elevationType)), uint32(unsafe.Sizeof(elevationType)), &returnedLen)
+	if err != nil {
+		return 0, err
+	}
+	return elevationType, nil
+}
+
+// userInfo0 mirrors USER_INFO_0.
+type userInfo0 struct {
+	name *uint16
+}
+
+func mustParseSID(t *testing.T, s string) *windows.SID {
+	t.Helper()
+	sid, err := windows.StringToSid(s)
+	require.NoError(t, err, "parse SID %s", s)
+	return sid
+}
+
+// localAccountNames returns the names of the local user accounts.
+func localAccountNames(t *testing.T) []string {
+	t.Helper()
+
+	var buf *byte
+	var entriesRead, totalEntries, resume uint32
+	err := windows.NetUserEnum(nil, 0, filterNormalAccount, &buf, maxPreferredLength,
+		&entriesRead, &totalEntries, &resume)
+	require.NoError(t, err, "enumerate local users")
+	t.Cleanup(func() {
+		require.NoError(t, windows.NetApiBufferFree(buf), "free NetApi buffer")
+	})
+
+	entries := unsafe.Slice((*userInfo0)(unsafe.Pointer(buf)), entriesRead)
+	names := make([]string, 0, entriesRead)
+	for _, entry := range entries {
+		names = append(names, windows.UTF16PtrToString(entry.name))
+	}
+	return names
+}
+
+// localAccountNameByRID returns the name of the local account carrying the
+// given RID. Accounts such as Administrator and Guest can be renamed and are
+// localized, so tests must not name them literally.
+func localAccountNameByRID(t *testing.T, rid uint32) string {
+	t.Helper()
+
+	for _, name := range localAccountNames(t) {
+		sid, _, _, err := windows.LookupSID("", name)
+		if err != nil {
+			continue
+		}
+		if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY {
+			continue
+		}
+		count := sid.SubAuthorityCount()
+		if count < 2 || sid.SubAuthority(0) != 21 {
+			continue
+		}
+		if sid.SubAuthority(uint32(count-1)) == rid {
+			return name
+		}
+	}
+
+	t.Fatalf("no local account with RID %d", rid)
+	return ""
+}
+
+// wellKnownAccountName resolves a well-known SID to the qualified account name
+// the local system uses for it, which is localized.
+func wellKnownAccountName(t *testing.T, sidType windows.WELL_KNOWN_SID_TYPE) string {
+	t.Helper()
+
+	sid, err := windows.CreateWellKnownSid(sidType)
+	require.NoError(t, err, "create well-known SID")
+	name, domain, _, err := sid.LookupAccount("")
+	require.NoError(t, err, "resolve %s to an account name", sid)
+	if domain == "" {
+		return name
+	}
+	return domain + `\` + name
+}
+
+func TestIsBuiltinAdministratorSID(t *testing.T) {
+	tests := []struct {
+		name string
+		sid  string
+		want bool
+	}{
+		{"machine_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true},
+		{"domain_administrator", "S-1-5-21-3390233681-4087452608-412898826-500", true},
+		{"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false},
+		{"guest_account", "S-1-5-21-1111111111-2222222222-3333333333-501", false},
+		{"domain_admins_group", "S-1-5-21-1111111111-2222222222-3333333333-512", false},
+		{"system", "S-1-5-18", false},
+		{"administrators_group", "S-1-5-32-544", false},
+		{"non_nt_authority", "S-1-1-0", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := isBuiltinAdministratorSID(mustParseSID(t, tt.sid))
+			assert.Equal(t, tt.want, result, "RID 500 detection for %s", tt.sid)
+		})
+	}
+}
+
+func TestIsPrivilegedUserSID(t *testing.T) {
+	tests := []struct {
+		name string
+		sid  string
+		want bool
+	}{
+		{"local_system", "S-1-5-18", true},
+		{"local_service", "S-1-5-19", true},
+		{"network_service", "S-1-5-20", true},
+		{"administrators_group", "S-1-5-32-544", true},
+		{"builtin_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true},
+		{"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false},
+		{"users_group", "S-1-5-32-545", false},
+		{"everyone", "S-1-1-0", false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := isPrivilegedUserSID(mustParseSID(t, tt.sid))
+			assert.Equal(t, tt.want, result, "SID privilege classification for %s", tt.sid)
+		})
+	}
+}
+
+func TestIsWindowsAccountPrivilegedOrUnknown(t *testing.T) {
+	tests := []struct {
+		name     string
+		username string
+		want     bool
+	}{
+		{"system", wellKnownAccountName(t, windows.WinLocalSystemSid), true},
+		{"local_service", wellKnownAccountName(t, windows.WinLocalServiceSid), true},
+		{"network_service", wellKnownAccountName(t, windows.WinNetworkServiceSid), true},
+		{"administrators_group", wellKnownAccountName(t, windows.WinBuiltinAdministratorsSid), true},
+		// The built-in Administrator (RID 500) and Guest (RID 501) accounts
+		// exist on every Windows installation, though they may be disabled.
+		{"builtin_administrator", localAccountNameByRID(t, 500), true},
+		{"guest", localAccountNameByRID(t, 501), false},
+		// Unresolvable accounts fail closed.
+		{"nonexistent_user", "netbird-no-such-user", true},
+		{"empty_username", "", true},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := isWindowsAccountPrivilegedOrUnknown(tt.username)
+			assert.Equal(t, tt.want, result, "account privilege classification for %q", tt.username)
+		})
+	}
+}
+
+func TestIsProcessElevated(t *testing.T) {
+	elevated := isProcessElevated()
+
+	// TokenElevationType is a second, independent view of the same token:
+	// Full means elevated and Limited means a filtered administrator, while
+	// Default covers both a standard user and an administrator with no linked
+	// token (UAC off, the built-in Administrator, SYSTEM), so it implies nothing.
+	elevationType, err := tokenElevationType(windows.GetCurrentProcessToken())
+	require.NoError(t, err, "read token elevation type")
+
+	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	require.NoError(t, err, "create Administrators SID")
+
+	// Token(0) makes CheckTokenMembership evaluate the caller's own token. It
+	// counts only enabled SIDs, so a filtered administrator reports false here.
+	member, err := windows.Token(0).IsMember(adminSid)
+	require.NoError(t, err, "check own Administrators membership")
+
+	t.Logf("elevated=%v elevationType=%d memberOfAdministrators=%v", elevated, elevationType, member)
+
+	switch elevationType {
+	case tokenElevationTypeFull:
+		assert.True(t, elevated, "a token of elevation type Full must report elevated")
+	case tokenElevationTypeLimited:
+		assert.False(t, elevated, "a filtered administrator token must not report elevated")
+	}
+
+	// Administrators enabled in the token means the token wields administrative
+	// rights, which is what elevation reports.
+	if member {
+		assert.True(t, elevated, "token with enabled Administrators membership must report elevated")
+	}
+}
+
+// TestS4UMembershipAgreesWithLocalGroups exercises the S4U token path used
+// for domain accounts. S4U logons need the TCB privilege, so the test runs
+// only as SYSTEM (which is how CI executes the suite). For local accounts the
+// token's Administrators membership must agree with the SAM enumeration.
+func TestS4UMembershipAgreesWithLocalGroups(t *testing.T) {
+	system, err := windows.CreateWellKnownSid(windows.WinLocalSystemSid)
+	require.NoError(t, err, "create SYSTEM SID")
+	current, err := user.Current()
+	require.NoError(t, err, "get current user")
+	if current.Uid != system.String() {
+		t.Skipf("S4U logon requires SYSTEM (running as %s)", current.Username)
+	}
+
+	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	require.NoError(t, err, "create Administrators SID")
+
+	checked := 0
+	for _, name := range localAccountNames(t) {
+		viaToken, err := s4uTokenIsMember(name, ".", adminSid)
+		if err != nil {
+			// Disabled or logon-restricted accounts cannot get an S4U logon.
+			t.Logf("skipping %s: %v", name, err)
+			continue
+		}
+		viaSAM, err := localGroupsContainSID(name, adminSid)
+		require.NoError(t, err, "enumerate local groups for %s", name)
+
+		assert.Equal(t, viaSAM, viaToken, "S4U token and SAM enumeration must agree on Administrators membership for %s", name)
+		checked++
+	}
+	// Ineligible accounts are skipped, so without this the test could report
+	// success while comparing nothing at all.
+	require.Positive(t, checked, "no local account completed an S4U logon, so nothing was compared")
+	t.Logf("checked %d local accounts via S4U", checked)
+}
+
+// TestLocalGroupsContainSID_Administrator checks the positive case against the
+// built-in Administrator, a member of Administrators on every installation.
+func TestLocalGroupsContainSID_Administrator(t *testing.T) {
+	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	require.NoError(t, err, "create Administrators SID")
+
+	administrator := localAccountNameByRID(t, 500)
+	member, err := localGroupsContainSID(administrator, adminSid)
+	require.NoError(t, err, "enumerate local groups for %s", administrator)
+	assert.True(t, member, "%s is a member of the Administrators group", administrator)
+}
+
+// TestLocalGroupsContainSID_UnresolvableGroupFailsClosed covers a wanted SID
+// that resolves to no group: the error must surface rather than being reported
+// as "not a member", so the privilege check treats the account as privileged.
+func TestLocalGroupsContainSID_UnresolvableGroupFailsClosed(t *testing.T) {
+	unknown := mustParseSID(t, "S-1-5-21-1111111111-2222222222-3333333333-4444")
+
+	_, err := localGroupsContainSID(localAccountNameByRID(t, 500), unknown)
+	require.Error(t, err, "must report an error when the wanted group cannot be identified")
+}
+
+func TestLocalGroupsContainSID_Guest(t *testing.T) {
+	guestsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinGuestsSid)
+	require.NoError(t, err, "create Guests SID")
+	adminsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
+	require.NoError(t, err, "create Administrators SID")
+
+	guest := localAccountNameByRID(t, 501)
+
+	inGuests, err := localGroupsContainSID(guest, guestsSid)
+	require.NoError(t, err, "enumerate local groups for %s", guest)
+	assert.True(t, inGuests, "%s is a member of the Guests group", guest)
+
+	inAdmins, err := localGroupsContainSID(guest, adminsSid)
+	require.NoError(t, err, "enumerate local groups for %s", guest)
+	assert.False(t, inAdmins, "%s is not a member of the Administrators group", guest)
+}

client/ssh/server/server_config_test.go

@@ -239,6 +239,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 		forwardType   string
 		port          uint32
 		username      string
+		uid           string
 		expectError   bool
 		errorMsg      string
 		skipOnWindows bool
@@ -248,6 +249,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 			forwardType:   "remote",
 			port:          80,
 			username:      "testuser",
+			uid:           "1000",
 			expectError:   true,
 			errorMsg:      "cannot bind to privileged port",
 			skipOnWindows: true,
@@ -257,6 +259,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 			forwardType:   "tcpip-forward",
 			port:          443,
 			username:      "testuser",
+			uid:           "1000",
 			expectError:   true,
 			errorMsg:      "cannot bind to privileged port",
 			skipOnWindows: true,
@@ -266,6 +269,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 			forwardType: "remote",
 			port:        8080,
 			username:    "testuser",
+			uid:         "1000",
 			expectError: false,
 		},
 		{
@@ -273,6 +277,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 			forwardType: "remote",
 			port:        0,
 			username:    "testuser",
+			uid:         "1000",
 			expectError: false,
 		},
 		{
@@ -280,13 +285,35 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 			forwardType: "remote",
 			port:        22,
 			username:    "root",
+			uid:         "0",
 			expectError: false,
 		},
+		{
+			// Only uid 0 is privileged, whatever the account is called.
+			name:          "uid 0 under another name may bind a privileged port",
+			forwardType:   "remote",
+			port:          22,
+			username:      "toor",
+			uid:           "0",
+			expectError:   false,
+			skipOnWindows: true,
+		},
+		{
+			name:          "account named root without uid 0 may not",
+			forwardType:   "remote",
+			port:          22,
+			username:      "root",
+			uid:           "1000",
+			expectError:   true,
+			errorMsg:      "cannot bind to privileged port",
+			skipOnWindows: true,
+		},
 		{
 			name:        "local forward privileged port allowed for non-root",
 			forwardType: "local",
 			port:        80,
 			username:    "testuser",
+			uid:         "1000",
 			expectError: false,
 		},
 	}
@@ -299,7 +326,7 @@ func TestServer_PrivilegedPortAccess(t *testing.T) {
 
 			result := PrivilegeCheckResult{
 				Allowed: true,
-				User:    &user.User{Username: tt.username},
+				User:    &user.User{Username: tt.username, Uid: tt.uid},
 			}
 
 			err := server.checkPrivilegedPortAccess(tt.forwardType, tt.port, result)
@@ -420,6 +447,13 @@ func TestServer_PortConflictHandling(t *testing.T) {
 
 func TestServer_IsPrivilegedUser(t *testing.T) {
 
+	// Windows classification depends on account SIDs and group membership, and
+	// the accounts involved carry localized, renameable names. It is covered by
+	// TestIsWindowsAccountPrivileged, which resolves them from well-known SIDs.
+	if runtime.GOOS == "windows" {
+		t.Skip("covered by TestIsWindowsAccountPrivileged")
+	}
+
 	tests := []struct {
 		username    string
 		expected    bool
@@ -440,44 +474,16 @@ func TestServer_IsPrivilegedUser(t *testing.T) {
 			expected:    false,
 			description: "empty username should not be privileged",
 		},
-	}
-
-	// Add Windows-specific tests
-	if runtime.GOOS == "windows" {
-		tests = append(tests, []struct {
-			username    string
-			expected    bool
-			description string
-		}{
-			{
-				username:    "Administrator",
-				expected:    true,
-				description: "Administrator should be considered privileged on Windows",
-			},
-			{
-				username:    "administrator",
-				expected:    true,
-				description: "administrator should be considered privileged on Windows (case insensitive)",
-			},
-		}...)
-	} else {
-		// On non-Windows systems, Administrator should not be privileged
-		tests = append(tests, []struct {
-			username    string
-			expected    bool
-			description string
-		}{
-			{
-				username:    "Administrator",
-				expected:    false,
-				description: "Administrator should not be privileged on non-Windows systems",
-			},
-		}...)
+		{
+			username:    "Administrator",
+			expected:    false,
+			description: "Administrator should not be privileged on non-Windows systems",
+		},
 	}
 
 	for _, tt := range tests {
 		t.Run(tt.description, func(t *testing.T) {
-			result := isPrivilegedUsername(tt.username)
+			result := isPrivilegedOrUnknown(tt.username)
 			assert.Equal(t, tt.expected, result, tt.description)
 		})
 	}

client/ssh/server/sftp_windows.go

@@ -17,7 +17,7 @@ import (
 // createSftpCommand creates a Windows SFTP command with user switching.
 // The caller must close the returned token handle after starting the process.
 func (s *Server) createSftpCommand(targetUser *user.User, sess ssh.Session) (*exec.Cmd, windows.Token, error) {
-	username, domain := s.parseUsername(targetUser.Username)
+	username, domain := parseUsername(targetUser.Username)
 
 	netbirdPath, err := os.Executable()
 	if err != nil {

client/ssh/server/user_utils.go

@@ -16,11 +16,6 @@ var (
 	ErrPrivilegedUserSwitch = errors.New("cannot switch to privileged user - current user lacks required privileges")
 )
 
-// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.)
-func isPlatformUnix() bool {
-	return getCurrentOS() != "windows"
-}
-
 // Dependency injection variables for testing - allows mocking dynamic runtime checks
 var (
 	getCurrentUser         = currentUserWithGetent
@@ -29,6 +24,9 @@ var (
 	getIsProcessPrivileged = isCurrentProcessPrivileged
 
 	getEuid = os.Geteuid
+
+	getProcessElevated                   = isProcessElevated
+	getWindowsAccountPrivilegedOrUnknown = isWindowsAccountPrivilegedOrUnknown
 )
 
 const (
@@ -65,6 +63,13 @@ type PrivilegeCheckResult struct {
 	RequiresUserSwitching bool
 }
 
+// privilegeCheckContext holds all context needed for privilege checking
+type privilegeCheckContext struct {
+	currentUser           *user.User
+	currentUserPrivileged bool
+	allowRoot             bool
+}
+
 // CheckPrivileges performs comprehensive privilege checking for all SSH features.
 // This is the single source of truth for privilege decisions across the SSH server.
 func (s *Server) CheckPrivileges(req PrivilegeCheckRequest) PrivilegeCheckResult {
@@ -75,7 +80,7 @@ func (s *Server) CheckPrivileges(req PrivilegeCheckRequest) PrivilegeCheckResult
 
 	// Handle empty username case - but still check root access controls
 	if req.RequestedUsername == "" {
-		if isPrivilegedUsername(context.currentUser.Username) && !context.allowRoot {
+		if isPrivilegedOrUnknown(context.currentUser.Username) && !context.allowRoot {
 			return PrivilegeCheckResult{
 				Allowed: false,
 				Error:   &PrivilegedUserError{Username: context.currentUser.Username},
@@ -135,7 +140,7 @@ func (s *Server) checkUserRequest(ctx *privilegeCheckContext, req PrivilegeCheck
 
 	needsUserSwitching := !isSameResolvedUser(resolvedUser, ctx.currentUser)
 
-	if isPrivilegedUsername(resolvedUser.Username) && !ctx.allowRoot {
+	if isPrivilegedOrUnknown(resolvedUser.Username) && !ctx.allowRoot {
 		return PrivilegeCheckResult{
 			Allowed:               false,
 			Error:                 &PrivilegedUserError{Username: resolvedUser.Username},
@@ -175,6 +180,42 @@ func (s *Server) resolveRequestedUser(requestedUsername string) (*user.User, err
 	return u, nil
 }
 
+// SetAllowRootLogin configures root login access
+func (s *Server) SetAllowRootLogin(allow bool) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.allowRootLogin = allow
+}
+
+// userNameLookup performs user lookup with root login permission check
+func (s *Server) userNameLookup(username string) (*user.User, error) {
+	result, err := s.userPrivilegeCheck(username)
+	if err != nil {
+		return nil, err
+	}
+	return result.User, nil
+}
+
+// userPrivilegeCheck performs user lookup with full privilege check result
+func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) {
+	result := s.CheckPrivileges(PrivilegeCheckRequest{
+		RequestedUsername:         username,
+		FeatureSupportsUserSwitch: true,
+		FeatureName:               FeatureSSHLogin,
+	})
+
+	if !result.Allowed {
+		return result, result.Error
+	}
+
+	return result, nil
+}
+
+// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.)
+func isPlatformUnix() bool {
+	return getCurrentOS() != "windows"
+}
+
 // isSameResolvedUser compares two resolved user identities
 func isSameResolvedUser(user1, user2 *user.User) bool {
 	if user1 == nil || user2 == nil {
@@ -183,13 +224,6 @@ func isSameResolvedUser(user1, user2 *user.User) bool {
 	return user1.Uid == user2.Uid
 }
 
-// privilegeCheckContext holds all context needed for privilege checking
-type privilegeCheckContext struct {
-	currentUser           *user.User
-	currentUserPrivileged bool
-	allowRoot             bool
-}
-
 // isSameUser checks if two usernames refer to the same user
 // SECURITY: This function must be conservative - it should only return true
 // when we're certain both usernames refer to the exact same user identity
@@ -253,159 +287,30 @@ func isWindowsSameUser(requestedUsername, currentUsername string) bool {
 	return strings.EqualFold(reqDomain, curDomain)
 }
 
-// SetAllowRootLogin configures root login access
-func (s *Server) SetAllowRootLogin(allow bool) {
-	s.mu.Lock()
-	defer s.mu.Unlock()
-	s.allowRootLogin = allow
-}
-
-// userNameLookup performs user lookup with root login permission check
-func (s *Server) userNameLookup(username string) (*user.User, error) {
-	result := s.CheckPrivileges(PrivilegeCheckRequest{
-		RequestedUsername:         username,
-		FeatureSupportsUserSwitch: true,
-		FeatureName:               FeatureSSHLogin,
-	})
-
-	if !result.Allowed {
-		return nil, result.Error
-	}
-
-	return result.User, nil
-}
-
-// userPrivilegeCheck performs user lookup with full privilege check result
-func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) {
-	result := s.CheckPrivileges(PrivilegeCheckRequest{
-		RequestedUsername:         username,
-		FeatureSupportsUserSwitch: true,
-		FeatureName:               FeatureSSHLogin,
-	})
-
-	if !result.Allowed {
-		return result, result.Error
-	}
-
-	return result, nil
-}
-
-// isPrivilegedUsername checks if the given username represents a privileged user across platforms.
-// On Unix: root
-// On Windows: Administrator, SYSTEM (case-insensitive)
-// Handles domain-qualified usernames like "DOMAIN\Administrator" or "user@domain.com"
-func isPrivilegedUsername(username string) bool {
+// isPrivilegedOrUnknown reports whether the given username represents a
+// privileged user, or on Windows an account whose privilege could not be
+// determined.
+// On Unix: root.
+// On Windows: well-known service accounts, built-in Administrator accounts,
+// and members of the local Administrators group; handles domain-qualified
+// usernames like "DOMAIN\user" or "user@domain.com". An account that cannot be
+// resolved or evaluated is reported as privileged.
+//
+// Use this to refuse privileged accounts, never to grant them anything: the
+// undetermined case is safe for a refusal and unsafe for a grant.
+func isPrivilegedOrUnknown(username string) bool {
 	if getCurrentOS() != "windows" {
 		return username == "root"
 	}
-
-	bareUsername := username
-	// Handle Windows domain format: DOMAIN\username
-	if idx := strings.LastIndex(username, `\`); idx != -1 {
-		bareUsername = username[idx+1:]
-	}
-	// Handle email-style format: username@domain.com
-	if idx := strings.Index(bareUsername, "@"); idx != -1 {
-		bareUsername = bareUsername[:idx]
-	}
-
-	return isWindowsPrivilegedUser(bareUsername)
-}
-
-// isWindowsPrivilegedUser checks if a bare username (domain already stripped) represents a Windows privileged account
-func isWindowsPrivilegedUser(bareUsername string) bool {
-	// common privileged usernames (case insensitive)
-	privilegedNames := []string{
-		"administrator",
-		"admin",
-		"root",
-		"system",
-		"localsystem",
-		"networkservice",
-		"localservice",
-	}
-
-	usernameLower := strings.ToLower(bareUsername)
-	for _, privilegedName := range privilegedNames {
-		if usernameLower == privilegedName {
-			return true
-		}
-	}
-
-	// computer accounts (ending with $) are not privileged by themselves
-	// They only gain privileges through group membership or specific SIDs
-
-	if targetUser, err := lookupUser(bareUsername); err == nil {
-		return isWindowsPrivilegedSID(targetUser.Uid)
-	}
-
-	return false
-}
-
-// isWindowsPrivilegedSID checks if a Windows SID represents a privileged account
-func isWindowsPrivilegedSID(sid string) bool {
-	privilegedSIDs := []string{
-		"S-1-5-18",     // Local System (SYSTEM)
-		"S-1-5-19",     // Local Service (NT AUTHORITY\LOCAL SERVICE)
-		"S-1-5-20",     // Network Service (NT AUTHORITY\NETWORK SERVICE)
-		"S-1-5-32-544", // Administrators group (BUILTIN\Administrators)
-		"S-1-5-500",    // Built-in Administrator account (local machine RID 500)
-	}
-
-	for _, privilegedSID := range privilegedSIDs {
-		if sid == privilegedSID {
-			return true
-		}
-	}
-
-	// Check for domain administrator accounts (RID 500 in any domain)
-	// Format: S-1-5-21-domain-domain-domain-500
-	// This is reliable as RID 500 is reserved for the domain Administrator account
-	if strings.HasPrefix(sid, "S-1-5-21-") && strings.HasSuffix(sid, "-500") {
-		return true
-	}
-
-	// Check for other well-known privileged RIDs in domain contexts
-	// RID 512 = Domain Admins group, RID 516 = Domain Controllers group
-	if strings.HasPrefix(sid, "S-1-5-21-") {
-		if strings.HasSuffix(sid, "-512") || // Domain Admins group
-			strings.HasSuffix(sid, "-516") || // Domain Controllers group
-			strings.HasSuffix(sid, "-519") { // Enterprise Admins group
-			return true
-		}
-	}
-
-	return false
+	return getWindowsAccountPrivilegedOrUnknown(username)
 }
 
 // isCurrentProcessPrivileged checks if the current process is running with elevated privileges.
 // On Unix systems, this means running as root (UID 0).
-// On Windows, this means running as Administrator or SYSTEM.
+// On Windows, this means the process token is elevated (administrators, SYSTEM).
 func isCurrentProcessPrivileged() bool {
 	if getCurrentOS() == "windows" {
-		return isWindowsElevated()
+		return getProcessElevated()
 	}
 	return getEuid() == 0
 }
-
-// isWindowsElevated checks if the current process is running with elevated privileges on Windows
-func isWindowsElevated() bool {
-	currentUser, err := getCurrentUser()
-	if err != nil {
-		log.Errorf("failed to get current user for privilege check, assuming non-privileged: %v", err)
-		return false
-	}
-
-	if isWindowsPrivilegedSID(currentUser.Uid) {
-		log.Debugf("Windows user switching supported: running as privileged SID %s", currentUser.Uid)
-		return true
-	}
-
-	if isPrivilegedUsername(currentUser.Username) {
-		log.Debugf("Windows user switching supported: running as privileged username %s", currentUser.Username)
-		return true
-	}
-
-	log.Debugf("Windows user switching not supported: not running as privileged user (current: %s)", currentUser.Uid)
-	return false
-}

client/ssh/server/user_utils_test.go

@@ -4,6 +4,7 @@ import (
 	"errors"
 	"os/user"
 	"runtime"
+	"strings"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -27,8 +28,8 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 	originalLookupUser := lookupUser
 	originalGetCurrentOS := getCurrentOS
 	originalGetEuid := getEuid
-
-	// Reset caches to ensure clean test state
+	originalGetProcessElevated := getProcessElevated
+	originalGetWindowsAccountPrivilegedOrUnknown := getWindowsAccountPrivilegedOrUnknown
 
 	// Set test values - inject platform dependencies
 	getCurrentUser = func() (*user.User, error) {
@@ -53,16 +54,31 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 		return euid
 	}
 
-	// Mock privilege detection based on the test user
-	getIsProcessPrivileged = func() bool {
+	// Simulate the Windows token elevation check based on the fixture user:
+	// the built-in Administrator (RID 500) and SYSTEM run elevated.
+	getProcessElevated = func() bool {
 		if currentUser == nil {
 			return false
 		}
-		// Check both username and SID for Windows systems
-		if os == "windows" && isWindowsPrivilegedSID(currentUser.Uid) {
+		return currentUser.Uid == "S-1-5-18" || strings.HasSuffix(currentUser.Uid, "-500")
+	}
+
+	// Simulate the Windows account classifier for the fixture accounts.
+	// "root" does not exist on Windows; the real classifier fails closed on
+	// unresolvable accounts, so it counts as privileged here too.
+	getWindowsAccountPrivilegedOrUnknown = func(username string) bool {
+		bare := username
+		if idx := strings.LastIndex(bare, `\`); idx != -1 {
+			bare = bare[idx+1:]
+		}
+		if idx := strings.Index(bare, "@"); idx != -1 {
+			bare = bare[:idx]
+		}
+		switch strings.ToLower(bare) {
+		case "administrator", "system", "root":
 			return true
 		}
-		return isPrivilegedUsername(currentUser.Username)
+		return false
 	}
 
 	// Return cleanup function
@@ -71,10 +87,8 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 		lookupUser = originalLookupUser
 		getCurrentOS = originalGetCurrentOS
 		getEuid = originalGetEuid
-
-		getIsProcessPrivileged = isCurrentProcessPrivileged
-
-		// Reset caches after test
+		getProcessElevated = originalGetProcessElevated
+		getWindowsAccountPrivilegedOrUnknown = originalGetWindowsAccountPrivilegedOrUnknown
 	}
 }
 
@@ -421,6 +435,9 @@ func TestUsedFallback_MeansNoPrivilegeDropping(t *testing.T) {
 }
 
 func TestPrivilegedUsernameDetection(t *testing.T) {
+	// Windows classification is syscall-backed (SID resolution, group
+	// membership) and is covered by privileges_windows_test.go; here only the
+	// Unix logic and the platform dispatch are exercised.
 	tests := []struct {
 		name       string
 		username   string
@@ -432,25 +449,9 @@ func TestPrivilegedUsernameDetection(t *testing.T) {
 		{"unix_regular_user", "alice", "linux", false},
 		{"unix_root_capital", "Root", "linux", false}, // Case-sensitive
 
-		// Windows tests
+		// Windows dispatch to the (mocked) account classifier
 		{"windows_administrator", "Administrator", "windows", true},
-		{"windows_system", "SYSTEM", "windows", true},
-		{"windows_admin", "admin", "windows", true},
-		{"windows_admin_lowercase", "administrator", "windows", true}, // Case-insensitive
-		{"windows_domain_admin", "DOMAIN\\Administrator", "windows", true},
-		{"windows_email_admin", "admin@domain.com", "windows", true},
 		{"windows_regular_user", "alice", "windows", false},
-		{"windows_domain_user", "DOMAIN\\alice", "windows", false},
-		{"windows_localsystem", "localsystem", "windows", true},
-		{"windows_networkservice", "networkservice", "windows", true},
-		{"windows_localservice", "localservice", "windows", true},
-
-		// Computer accounts (these depend on current user context in real implementation)
-		{"windows_computer_account", "WIN2K19-C2$", "windows", false},      // Computer account by itself not privileged
-		{"windows_domain_computer", "DOMAIN\\COMPUTER$", "windows", false}, // Domain computer account
-
-		// Cross-platform
-		{"root_on_windows", "root", "windows", true}, // Root should be privileged everywhere
 	}
 
 	for _, tt := range tests {
@@ -459,50 +460,8 @@ func TestPrivilegedUsernameDetection(t *testing.T) {
 			cleanup := setupTestDependencies(nil, nil, tt.platform, 1000, nil, nil)
 			defer cleanup()
 
-			result := isPrivilegedUsername(tt.username)
-			assert.Equal(t, tt.privileged, result)
-		})
-	}
-}
-
-func TestWindowsPrivilegedSIDDetection(t *testing.T) {
-	tests := []struct {
-		name        string
-		sid         string
-		privileged  bool
-		description string
-	}{
-		// Well-known system accounts
-		{"system_account", "S-1-5-18", true, "Local System (SYSTEM)"},
-		{"local_service", "S-1-5-19", true, "Local Service"},
-		{"network_service", "S-1-5-20", true, "Network Service"},
-		{"administrators_group", "S-1-5-32-544", true, "Administrators group"},
-		{"builtin_administrator", "S-1-5-500", true, "Built-in Administrator"},
-
-		// Domain accounts
-		{"domain_administrator", "S-1-5-21-1234567890-1234567890-1234567890-500", true, "Domain Administrator (RID 500)"},
-		{"domain_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-512", true, "Domain Admins group"},
-		{"domain_controllers_group", "S-1-5-21-1234567890-1234567890-1234567890-516", true, "Domain Controllers group"},
-		{"enterprise_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-519", true, "Enterprise Admins group"},
-
-		// Regular users
-		{"regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1001", false, "Regular domain user"},
-		{"another_regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1234", false, "Another regular user"},
-		{"local_user", "S-1-5-21-1234567890-1234567890-1234567890-1000", false, "Local regular user"},
-
-		// Groups that are not privileged
-		{"domain_users", "S-1-5-21-1234567890-1234567890-1234567890-513", false, "Domain Users group"},
-		{"power_users", "S-1-5-32-547", false, "Power Users group"},
-
-		// Invalid SIDs
-		{"malformed_sid", "S-1-5-invalid", false, "Malformed SID"},
-		{"empty_sid", "", false, "Empty SID"},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			result := isWindowsPrivilegedSID(tt.sid)
-			assert.Equal(t, tt.privileged, result, "Failed for %s: %s", tt.description, tt.sid)
+			result := isPrivilegedOrUnknown(tt.username)
+			assert.Equal(t, tt.privileged, result, "privilege classification for %s on %s", tt.username, tt.platform)
 		})
 	}
 }

client/ssh/server/userswitching_windows.go

@@ -91,7 +91,7 @@ func validateUsernameFormat(username string) error {
 func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, localUser *user.User, hasPty bool) (*exec.Cmd, func(), error) {
 	logger.Debugf("creating Windows executor command for user %s (Pty: %v)", localUser.Username, hasPty)
 
-	username, _ := s.parseUsername(localUser.Username)
+	username, _ := parseUsername(localUser.Username)
 	if err := validateUsername(username); err != nil {
 		return nil, nil, fmt.Errorf("invalid username %q: %w", username, err)
 	}
@@ -102,7 +102,7 @@ func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, l
 // createUserSwitchCommand creates a command with Windows user switching.
 // Returns the command and a cleanup function that must be called after starting the process.
 func (s *Server) createUserSwitchCommand(logger *log.Entry, session ssh.Session, localUser *user.User) (*exec.Cmd, func(), error) {
-	username, domain := s.parseUsername(localUser.Username)
+	username, domain := parseUsername(localUser.Username)
 
 	shell := getUserShell(localUser.Uid)
 
@@ -138,7 +138,7 @@ func (s *Server) createUserSwitchCommand(logger *log.Entry, session ssh.Session,
 }
 
 // parseUsername extracts username and domain from a Windows username
-func (s *Server) parseUsername(fullUsername string) (username, domain string) {
+func parseUsername(fullUsername string) (username, domain string) {
 	// Handle DOMAIN\username format
 	if idx := strings.LastIndex(fullUsername, `\`); idx != -1 {
 		domain = fullUsername[:idx]

e2e/harness/Dockerfile.client

@@ -20,5 +20,9 @@ ENV NETBIRD_BIN="/usr/local/bin/netbird" \
     NB_ENABLE_CAPTURE="false" \
     NB_ENTRYPOINT_SERVICE_TIMEOUT="30"
 ENTRYPOINT [ "/usr/local/bin/netbird-entrypoint.sh" ]
-COPY client/netbird-entrypoint.sh /usr/local/bin/netbird-entrypoint.sh
+# --chmod because the build context is not always a git checkout. A suite in
+# another module builds from this module's extracted copy in the module cache,
+# where every file is 0444 — the cache drops the executable bit git records — and
+# a bare COPY then produces an entrypoint the runtime cannot exec.
+COPY --chmod=0755 client/netbird-entrypoint.sh /usr/local/bin/netbird-entrypoint.sh
 COPY --from=builder /out/netbird /usr/local/bin/netbird

e2e/harness/client.go

@@ -32,12 +32,36 @@ type Client struct {
 	container testcontainers.Container
 }
 
+// clientOptions is what the ClientOption values assemble.
+type clientOptions struct {
+	name string
+}
+
+// ClientOption adjusts how StartClient runs the agent.
+type ClientOption func(*clientOptions)
+
+// WithClientName names the agent, which sets both its network alias and its
+// container hostname. The hostname matters beyond addressing: the agent reports
+// it to management at registration, so it is the name the peer appears under in
+// the API.
+//
+// Required to run more than one agent against the same server — the default name
+// is shared, and two containers cannot hold the same alias on one network.
+func WithClientName(name string) ClientOption {
+	return func(o *clientOptions) { o.name = name }
+}
+
 // StartClient builds the client image and runs it on the combined server's
 // network, joining via the given setup key. The image entrypoint brings the
 // daemon up automatically; callers wait for connectivity with WaitConnected /
 // WaitProxyPeer.
-func StartClient(ctx context.Context, c *Combined, setupKey string) (*Client, error) {
-	root, err := repoRoot()
+func StartClient(ctx context.Context, c *Combined, setupKey string, opts ...ClientOption) (*Client, error) {
+	o := clientOptions{name: clientAlias}
+	for _, opt := range opts {
+		opt(&o)
+	}
+
+	root, err := repoRoot(ctx)
 	if err != nil {
 		return nil, err
 	}
@@ -47,9 +71,13 @@ func StartClient(ctx context.Context, c *Combined, setupKey string) (*Client, er
 	}
 
 	req := testcontainers.ContainerRequest{
-		Image:          clientImage,
+		Image: clientImage,
+		// The agent reports the container's hostname to management, so this is
+		// the name the peer is addressable by in the API as well as on the
+		// network. The entrypoint takes no hostname flag of its own.
+		Hostname:       o.name,
 		Networks:       []string{c.network.Name},
-		NetworkAliases: map[string][]string{c.network.Name: {clientAlias}},
+		NetworkAliases: map[string][]string{c.network.Name: {o.name}},
 		Env: map[string]string{
 			"NB_MANAGEMENT_URL": combinedExposedURL,
 			"NB_SETUP_KEY":      setupKey,

e2e/harness/combined.go

@@ -61,11 +61,68 @@ type Combined struct {
 	workDir string
 }
 
+// combinedOptions is what the CombinedOption values assemble.
+type combinedOptions struct {
+	geolocation bool
+	env         map[string]string
+}
+
+// CombinedOption adjusts how StartCombined boots the server. The defaults suit a
+// suite that only drives the API; the options exist for the ones that need more
+// of the product than that.
+type CombinedOption func(*combinedOptions)
+
+// WithGeolocation leaves the GeoLite database download enabled. It is off by
+// default because the download adds startup latency that most suites get nothing
+// for. A suite asserting on location-based posture checks needs it: management
+// evaluates those rules against the database, and without it the rule fails
+// instead of passing without having been checked.
+func WithGeolocation() CombinedOption {
+	return func(o *combinedOptions) { o.geolocation = true }
+}
+
+// WithServerEnv adds environment variables to the combined container, overriding
+// the defaults on a key collision. For settings this harness does not model
+// directly, so a suite needing one does not have to fork the harness to get it.
+func WithServerEnv(env map[string]string) CombinedOption {
+	return func(o *combinedOptions) {
+		if o.env == nil {
+			o.env = map[string]string{}
+		}
+		for k, v := range env {
+			o.env[k] = v
+		}
+	}
+}
+
+// combinedEnv is the combined container's environment: setup-PAT enabled so the
+// caller can mint an admin token through /api/setup, geolocation off unless the
+// suite asked for it, and whatever the suite added on top.
+func combinedEnv(o combinedOptions) map[string]string {
+	env := map[string]string{
+		"NB_SETUP_PAT_ENABLED": "true",
+	}
+	if !o.geolocation {
+		// Skip the GeoLite DB download — it blocks startup and agent-network
+		// ingest doesn't use geolocation.
+		env["NB_DISABLE_GEOLOCATION"] = "true"
+	}
+	for k, v := range o.env {
+		env[k] = v
+	}
+	return env
+}
+
 // StartCombined builds the combined server from its multistage Dockerfile and
 // boots it with setup-PAT enabled on a fresh shared network, returning once the
 // API is serving. The caller still owns minting the admin PAT via Bootstrap.
-func StartCombined(ctx context.Context) (*Combined, error) {
-	root, err := repoRoot()
+func StartCombined(ctx context.Context, opts ...CombinedOption) (*Combined, error) {
+	var o combinedOptions
+	for _, opt := range opts {
+		opt(&o)
+	}
+
+	root, err := repoRoot(ctx)
 	if err != nil {
 		return nil, err
 	}
@@ -88,7 +145,7 @@ func StartCombined(ctx context.Context) (*Combined, error) {
 		return nil, fmt.Errorf("create work dir: %w", err)
 	}
 
-	cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, containerIssuer)
+	cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, !o.geolocation, containerIssuer)
 	if err := os.WriteFile(filepath.Join(workDir, "config.yaml"), []byte(cfg), 0o644); err != nil { //nolint:gosec // non-secret config, bind-mounted and read by the container
 		_ = net.Remove(ctx)
 		return nil, fmt.Errorf("write combined config: %w", err)
@@ -112,13 +169,8 @@ func StartCombined(ctx context.Context) (*Combined, error) {
 		ExposedPorts:   []string{combinedHTTPPort},
 		Networks:       []string{net.Name},
 		NetworkAliases: map[string][]string{net.Name: {combinedAlias}},
-		Env: map[string]string{
-			"NB_SETUP_PAT_ENABLED": "true",
-			// Skip the GeoLite DB download — it blocks startup and agent-network
-			// ingest doesn't use geolocation.
-			"NB_DISABLE_GEOLOCATION": "true",
-		},
-		Cmd: []string{"--config", "/nb/config.yaml"},
+		Env:            combinedEnv(o),
+		Cmd:            []string{"--config", "/nb/config.yaml"},
 		HostConfigModifier: func(hc *container.HostConfig) {
 			hc.Binds = append(hc.Binds, workDir+":/nb")
 		},

e2e/harness/config.go

@@ -15,6 +15,11 @@ package harness
 // server is required to load it — a broken path or malformed file fails startup
 // rather than silently falling back to the compiled-in rates, and TestMain then
 // fails with the container logs.
+//
+// disableGeoliteUpdate is a parameter rather than a fixed true because a suite
+// that exercises geolocation needs the database: management can only evaluate a
+// location rule with GeoLite loaded, and a rule it cannot evaluate fails rather
+// than passing vacuously. See WithGeolocation.
 const combinedConfigYAML = `server:
   listenAddress: ":8080"
   exposedAddress: "%s"
@@ -25,7 +30,7 @@ const combinedConfigYAML = `server:
   authSecret: "e2e-relay-secret"
   dataDir: "/nb/data"
   disableAnonymousMetrics: true
-  disableGeoliteUpdate: true
+  disableGeoliteUpdate: %t
   auth:
     issuer: "%s"
   store:

e2e/harness/options_test.go

@@ -0,0 +1,161 @@
+//go:build e2e
+
+package harness
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"os/exec"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The options exist so a suite can ask for a deployment this harness would not
+// otherwise give it. What they configure is a container environment and a config
+// file, both assembled before anything is started, so they are checkable without
+// Docker — which is the point: a wiring mistake here would otherwise only show up
+// as a puzzling failure minutes into a container run.
+
+func TestCombinedEnvGeolocation(t *testing.T) {
+	var off combinedOptions
+	assert.Equal(t, "true", combinedEnv(off)["NB_DISABLE_GEOLOCATION"],
+		"geolocation should be off by default")
+
+	var on combinedOptions
+	WithGeolocation()(&on)
+	assert.NotContains(t, combinedEnv(on), "NB_DISABLE_GEOLOCATION",
+		"WithGeolocation must leave NB_DISABLE_GEOLOCATION unset, so the server downloads the database")
+	assert.Equal(t, "true", combinedEnv(on)["NB_SETUP_PAT_ENABLED"],
+		"the setup PAT must stay enabled whatever else is configured; Bootstrap depends on it")
+}
+
+// The config file carries the same decision as the environment variable, and the
+// server needs both to agree: disableGeoliteUpdate suppresses the download even
+// when geolocation itself is enabled.
+func TestCombinedConfigGeolocation(t *testing.T) {
+	for _, tc := range []struct {
+		name string
+		opts []CombinedOption
+		want string
+	}{
+		{name: "default", want: "disableGeoliteUpdate: true"},
+		{name: "with geolocation", opts: []CombinedOption{WithGeolocation()}, want: "disableGeoliteUpdate: false"},
+	} {
+		t.Run(tc.name, func(t *testing.T) {
+			var o combinedOptions
+			for _, opt := range tc.opts {
+				opt(&o)
+			}
+			cfg := fmt.Sprintf(combinedConfigYAML, combinedExposedURL, !o.geolocation, containerIssuer)
+			assert.Contains(t, cfg, tc.want, "geolocation not rendered as expected")
+			// The issuer is the last verb; a mis-ordered argument list would put
+			// the boolean here instead and the server would fail to start.
+			assert.Contains(t, cfg, `issuer: "`+containerIssuer+`"`, "issuer not rendered")
+		})
+	}
+}
+
+func TestWithServerEnvOverrides(t *testing.T) {
+	var o combinedOptions
+	WithServerEnv(map[string]string{"NB_LOG_LEVEL": "debug"})(&o)
+	WithServerEnv(map[string]string{"NB_SETUP_PAT_ENABLED": "false"})(&o)
+
+	env := combinedEnv(o)
+	assert.Equal(t, "debug", env["NB_LOG_LEVEL"], "added variable missing")
+	assert.Equal(t, "false", env["NB_SETUP_PAT_ENABLED"], "a suite must be able to override a default")
+}
+
+// Two agents on one network cannot share an alias, so the name has to reach both
+// the alias and the hostname. The hostname is the one management records, so it is
+// also what the peer is addressable by through the API.
+func TestWithClientName(t *testing.T) {
+	o := clientOptions{name: clientAlias}
+	require.Equal(t, "client", o.name, "unexpected default client name")
+
+	WithClientName("peer2")(&o)
+	assert.Equal(t, "peer2", o.name, "WithClientName did not take")
+}
+
+// repoRoot has to recognise this module rather than merely finding a go.mod, or a
+// suite in another module gets its own root and a build context without the
+// component Dockerfiles in it.
+func TestIsModule(t *testing.T) {
+	dir := t.TempDir()
+
+	other := filepath.Join(dir, "go.mod")
+	require.NoError(t, os.WriteFile(other, []byte("module example.com/other\n\ngo 1.25\n"), 0o600))
+	assert.False(t, isModule(other, modulePath), "another module's go.mod must not be taken for this repo")
+
+	ours := filepath.Join(dir, "ours.mod")
+	require.NoError(t, os.WriteFile(ours, []byte("// a comment\n\nmodule "+modulePath+"\n\ngo 1.25\n"), 0o600))
+	assert.True(t, isModule(ours, modulePath), "this repo's go.mod was not recognised")
+
+	assert.False(t, isModule(filepath.Join(dir, "absent.mod"), modulePath),
+		"a missing go.mod must not report a match")
+}
+
+// Running from inside the repo, repoRoot finds it by walking up — the module
+// lookup is only the fallback, and this asserts the walk still wins so an in-repo
+// run never depends on the module cache.
+func TestRepoRootFindsThisRepo(t *testing.T) {
+	root, err := repoRoot(context.Background())
+	require.NoError(t, err)
+	assert.True(t, isModule(filepath.Join(root, "go.mod"), modulePath),
+		"repoRoot returned %s, which is not this module", root)
+
+	for _, f := range []string{combinedDockerfile, clientDockerfile} {
+		_, err := os.Stat(filepath.Join(root, f))
+		assert.NoError(t, err, "%s is not present under the reported root %s", f, root)
+	}
+}
+
+// A caller that vendors its dependencies puts the go command in automatic vendor
+// mode, where `go list -m -f {{.Dir}}` succeeds and reports an EMPTY directory:
+// vendor/ holds packages, not module source. Without -mod=readonly the lookup
+// would come back empty and the harness would report a missing module for a
+// dependency that is present.
+func TestModuleDirResolvesUnderVendorMode(t *testing.T) {
+	if _, err := exec.LookPath("go"); err != nil {
+		t.Skip("no go tool on PATH")
+	}
+	ctx := context.Background()
+
+	base := t.TempDir()
+	dep := filepath.Join(base, "dep")
+	main := filepath.Join(base, "main")
+	require.NoError(t, os.MkdirAll(dep, 0o750))
+	require.NoError(t, os.MkdirAll(main, 0o750))
+
+	// A local replacement rather than a real dependency, so this needs no network.
+	require.NoError(t, os.WriteFile(filepath.Join(dep, "go.mod"),
+		[]byte("module example.com/dep\n\ngo 1.25\n"), 0o600))
+	require.NoError(t, os.WriteFile(filepath.Join(dep, "dep.go"),
+		[]byte("package dep\n"), 0o600))
+	require.NoError(t, os.WriteFile(filepath.Join(main, "go.mod"),
+		[]byte("module example.com/main\n\ngo 1.25\n\nrequire example.com/dep v0.0.0\n\nreplace example.com/dep v0.0.0 => ../dep\n"), 0o600))
+	require.NoError(t, os.WriteFile(filepath.Join(main, "main.go"),
+		[]byte("package main\n\nimport _ \"example.com/dep\"\n\nfunc main() {}\n"), 0o600))
+
+	t.Chdir(main)
+	vendor := exec.CommandContext(ctx, "go", "mod", "vendor")
+	out, err := vendor.CombinedOutput()
+	require.NoError(t, err, "go mod vendor: %s", out)
+
+	dir, err := moduleDir(ctx, "example.com/dep")
+	require.NoError(t, err, "the module must still resolve with a vendor directory present")
+	assert.Equal(t, dep, dir, "resolved the wrong directory")
+}
+
+// A cancelled context has to stop the lookup rather than leaving the caller
+// waiting on a subprocess it has already given up on.
+func TestModuleDirHonoursContext(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+
+	_, err := moduleDir(ctx, modulePath)
+	assert.ErrorIs(t, err, context.Canceled, "a cancelled context must stop the lookup")
+}

e2e/harness/paths.go

@@ -3,27 +3,82 @@
 package harness
 
 import (
+	"context"
 	"fmt"
 	"os"
+	"os/exec"
 	"path/filepath"
+	"strings"
 )
 
-// repoRoot walks up from the working directory to the module root (the
-// directory holding go.mod), so the Docker build context is correct no matter
-// which package the test runs from.
-func repoRoot() (string, error) {
+// modulePath is this module, used both to recognise the repo when walking up
+// from the working directory and to locate it when the suite lives elsewhere.
+const modulePath = "github.com/netbirdio/netbird"
+
+// repoRoot returns the directory the component Dockerfiles are built from.
+//
+// Walking up from the working directory finds it for any test inside this repo,
+// no matter which package it runs from. A suite in another module gets a
+// different answer that way — its own module root, where combined/Dockerfile
+// does not exist — so the ancestor has to be this module and not merely some
+// module. When it is not, the build context is the extracted module directory of
+// whichever version that suite depends on, which is the right one: the server it
+// tests against is then built from the same revision as the client library it
+// was compiled with.
+func repoRoot(ctx context.Context) (string, error) {
 	dir, err := os.Getwd()
 	if err != nil {
 		return "", err
 	}
 	for {
-		if _, statErr := os.Stat(filepath.Join(dir, "go.mod")); statErr == nil {
+		if isModule(filepath.Join(dir, "go.mod"), modulePath) {
 			return dir, nil
 		}
 		parent := filepath.Dir(dir)
 		if parent == dir {
-			return "", fmt.Errorf("go.mod not found above %s", dir)
+			break
 		}
 		dir = parent
 	}
+	return moduleDir(ctx, modulePath)
+}
+
+// isModule reports whether the go.mod at path declares the given module.
+func isModule(path, want string) bool {
+	b, err := os.ReadFile(path)
+	if err != nil {
+		return false
+	}
+	for _, line := range strings.Split(string(b), "\n") {
+		if rest, ok := strings.CutPrefix(strings.TrimSpace(line), "module "); ok {
+			return strings.TrimSpace(rest) == want
+		}
+	}
+	return false
+}
+
+// moduleDir asks the go tool where a module's source is, which for a dependent
+// module is its extracted copy in the module cache. The cache is read-only, and
+// a Docker build context is only ever read.
+//
+// -mod=readonly is required rather than cosmetic. A caller that vendors its
+// dependencies puts the go command in automatic vendor mode, where this lookup
+// succeeds with an EMPTY directory — vendor/ holds packages, not module source,
+// so there is nothing to report. Asking in readonly mode resolves against the
+// module graph instead, which answers for both a cached module and a local
+// replacement, and neither writes to go.mod.
+func moduleDir(ctx context.Context, module string) (string, error) {
+	cmd := exec.CommandContext(ctx, "go", "list", "-mod=readonly", "-m", "-f", "{{.Dir}}", module)
+	out, err := cmd.Output()
+	if err != nil {
+		return "", fmt.Errorf("locate %s: %w", module, err)
+	}
+	dir := strings.TrimSpace(string(out))
+	if dir == "" {
+		return "", fmt.Errorf("locate %s: the go tool reported no directory; run `go mod download %s`", module, module)
+	}
+	if _, err := os.Stat(dir); err != nil {
+		return "", fmt.Errorf("locate %s: %w", module, err)
+	}
+	return dir, nil
 }

e2e/harness/proxy.go

@@ -43,7 +43,7 @@ type Proxy struct {
 // or override any NB_PROXY_* var (e.g. NB_PROXY_TUNNEL_CACHE_TTL for tests that
 // need a short authorization-cache window).
 func StartProxy(ctx context.Context, c *Combined, proxyToken string, envOverrides ...map[string]string) (*Proxy, error) {
-	root, err := repoRoot()
+	root, err := repoRoot(ctx)
 	if err != nil {
 		return nil, err
 	}

shared/management/client/grpc.go

@@ -21,6 +21,8 @@ import (
 	"google.golang.org/grpc/connectivity"
 
 	nbgrpc "github.com/netbirdio/netbird/client/grpc"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -62,6 +64,13 @@ type GrpcClient struct {
 	connStateCallbackLock sync.RWMutex
 	serverURL             string
 
+	// netState gates the stream retry loop on OS-reported network
+	// availability; nil (the default) disables gating.
+	netState *netstate.State
+
+	// sweeper cuts the transport connections on network change; nil disables it.
+	sweeper *netsweep.Sweeper
+
 	// syncStreamErr holds the last Sync stream error, or nil while the stream
 	// is established and healthy. GetServerKey succeeds even when the peer
 	// cannot sync (e.g. the server returns "settings not found"), so the
@@ -111,16 +120,43 @@ func MaxRecvMsgSize() int {
 	return size
 }
 
+// Option configures optional GrpcClient behavior.
+type Option func(*GrpcClient)
+
+// WithNetworkState injects the OS network availability state that gates the
+// stream retry loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) Option {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) Option {
+	return func(c *GrpcClient) { c.sweeper = sweeper }
+}
+
 // NewClient creates a new client to Management service
-func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
-	var conn *grpc.ClientConn
+func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool, opts ...Option) (*GrpcClient, error) {
+	// Options apply before dialing: the sweeper must wrap the first connection too.
+	c := &GrpcClient{
+		key:                   ourPrivateKey,
+		ctx:                   ctx,
+		connStateCallbackLock: sync.RWMutex{},
+		serverURL:             addr,
+	}
+	for _, opt := range opts {
+		opt(c)
+	}
 
 	var extraOpts []grpc.DialOption
 	if maxSize := MaxRecvMsgSize(); maxSize > 0 {
 		extraOpts = append(extraOpts, grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(maxSize)))
 		log.Infof("management gRPC max receive message size set to %d bytes", maxSize)
 	}
+	if c.sweeper != nil {
+		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
+	}
 
+	var conn *grpc.ClientConn
 	operation := func() error {
 		var err error
 		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.ManagementComponent, extraOpts...)
@@ -136,16 +172,9 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
 		return nil, err
 	}
 
-	realClient := proto.NewManagementServiceClient(conn)
-
-	return &GrpcClient{
-		key:                   ourPrivateKey,
-		realClient:            realClient,
-		ctx:                   ctx,
-		conn:                  conn,
-		connStateCallbackLock: sync.RWMutex{},
-		serverURL:             addr,
-	}, nil
+	c.conn = conn
+	c.realClient = proto.NewManagementServiceClient(conn)
+	return c, nil
 }
 
 // GetServerURL returns the management server URL
@@ -208,6 +237,16 @@ func (c *GrpcClient) withMgmtStream(
 ) error {
 	backOff := defaultBackoff(ctx)
 	operation := func() error {
+		// suspend reconnect attempts while the OS reports no usable network.
+		// Wait only errors on a cancelled context, which means shutdown, so
+		// stop the loop without reporting a failure.
+		if waited, err := c.netState.Wait(ctx); err != nil {
+			log.Debugf("management connection context has been canceled while offline, this usually indicates shutdown")
+			return nil //nolint:nilerr // a cancelled context means shutdown, not a retryable failure
+		} else if waited {
+			backOff.Reset()
+		}
+
 		log.Debugf("management connection state %v", c.conn.GetState())
 		connState := c.conn.GetState()
 

shared/relay/client/client.go

@@ -14,6 +14,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	"github.com/netbirdio/netbird/shared/relay/client/dialer"
 	netErr "github.com/netbirdio/netbird/shared/relay/client/dialer/net"
@@ -184,6 +185,10 @@ type Client struct {
 	// datagram-sized transport is avoided on subsequent connects. Shared via
 	// the manager.
 	transportFallback *transportFallback
+
+	// sweeper cuts the relay connection on network change; the read loop
+	// reports the disconnect and the guard reconnects. Shared via the manager.
+	sweeper *netsweep.Sweeper
 	// datagramFallbackTriggered guards a single fallback per connection so a
 	// burst of oversized datagrams triggers one reconnect, not many.
 	datagramFallbackTriggered atomic.Bool
@@ -393,6 +398,12 @@ func (c *Client) Close() error {
 }
 
 func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
+	// A sweep cancels this context, so a dial started on the old network
+	// aborts instead of waiting out its handshake timeout.
+	dial := c.sweeper.StartDial(ctx)
+	defer dial.Release()
+	ctx = dial.Ctx()
+
 	mode := transportModeFromEnv()
 	dialers := c.getDialers(mode)
 
@@ -417,12 +428,19 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
 			return nil, fmt.Errorf("dial via FQDN: %w", err)
 		}
 	}
-	c.relayConn = conn
-	c.datagramFallbackTriggered.Store(false)
+	// Read the transport off the concrete connection: the sweeper's wrapper
+	// embeds net.Conn only, so it does not promote Protocol().
 	if tc, ok := conn.(transportConn); ok {
 		c.transport = tc.Protocol()
 	}
 
+	conn, err := dial.WrapConn(conn)
+	if err != nil {
+		return nil, fmt.Errorf("register connection: %w", err)
+	}
+	c.relayConn = conn
+	c.datagramFallbackTriggered.Store(false)
+
 	instanceURL, err := c.handShake(ctx)
 	if err != nil {
 		cErr := conn.Close()

shared/relay/client/guard.go

@@ -7,6 +7,8 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netstate"
 )
 
 const defaultMaxBackoffInterval = 60 * time.Second
@@ -22,14 +24,19 @@ type Guard struct {
 	// attempts.
 	maxBackoffInterval time.Duration
 
+	// netState gates reconnect attempts on OS-reported network availability;
+	// nil disables gating.
+	netState *netstate.State
+
 	// lastErr is the error from the most recent failed reconnect attempt,
 	// surfaced as the home relay status while disconnected.
 	lastErr atomic.Pointer[error]
 }
 
 // NewGuard creates a new guard for the relay client. A non-positive
-// maxBackoffInterval falls back to defaultMaxBackoffInterval.
-func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration) *Guard {
+// maxBackoffInterval falls back to defaultMaxBackoffInterval. A nil netState
+// disables network availability gating.
+func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *netstate.State) *Guard {
 	if maxBackoffInterval <= 0 {
 		maxBackoffInterval = defaultMaxBackoffInterval
 	}
@@ -38,6 +45,7 @@ func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration) *Guard {
 		OnReconnected:      make(chan struct{}, 1),
 		serverPicker:       sp,
 		maxBackoffInterval: maxBackoffInterval,
+		netState:           netState,
 	}
 	return g
 }
@@ -70,11 +78,21 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
 
 	// start a ticker to pick a new server
 	ticker := g.exponentTicker(ctx)
-	defer ticker.Stop()
+	defer func() {
+		ticker.Stop()
+	}()
 
 	for {
 		select {
 		case <-ticker.C:
+			// suspend reconnect attempts while the OS reports no usable network
+			if waited, err := g.netState.Wait(ctx); err != nil {
+				return
+			} else if waited {
+				ticker.Stop()
+				ticker = g.exponentTicker(ctx)
+				continue
+			}
 			if err := g.retry(ctx); err != nil {
 				log.Errorf("failed to pick new Relay server: %s", err)
 				g.setLastError(err)
@@ -104,6 +122,13 @@ func (g *Guard) tryToQuickReconnect(parentCtx context.Context, rc *Client) bool
 		return false
 	}
 
+	// Re-check after the wait: the disconnect that triggered this reconnect
+	// is often the first symptom of the network going away, so the
+	// availability flag typically arrives while we sleep here.
+	if !g.netState.IsOnline() {
+		return false
+	}
+
 	log.Infof("try to reconnect to Relay server: %s", rc.connectionURL)
 
 	if err := rc.Connect(parentCtx); err != nil {

shared/relay/client/manager.go

@@ -12,6 +12,8 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 )
 
@@ -65,6 +67,17 @@ func WithMaxBackoffInterval(d time.Duration) ManagerOption {
 	return func(m *Manager) { m.maxBackoffInterval = d }
 }
 
+// WithNetworkState injects the OS network availability state that gates the
+// reconnect guard; without it reconnect attempts are not gated.
+func WithNetworkState(netState *netstate.State) ManagerOption {
+	return func(m *Manager) { m.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ManagerOption {
+	return func(m *Manager) { m.sweeper = sweeper }
+}
+
 // Manager is a manager for the relay client instances. It establishes one persistent connection to the given relay URL
 // and automatically reconnect to them in case disconnection.
 // The manager also manage temporary relay connection. If a client wants to communicate with a client on a
@@ -92,6 +105,8 @@ type Manager struct {
 
 	mtu                uint16
 	maxBackoffInterval time.Duration
+	netState           *netstate.State
+	sweeper            *netsweep.Sweeper
 
 	cleanupInterval      time.Duration
 	keepUnusedServerTime time.Duration
@@ -128,8 +143,9 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 	for _, opt := range opts {
 		opt(m)
 	}
+	m.serverPicker.Sweeper = m.sweeper
 	m.serverPicker.ServerURLs.Store(serverURLs)
-	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
+	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netState)
 	return m
 }
 
@@ -354,6 +370,7 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
 
 	relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
 	relayClient.SetTransportFallback(m.transportFallback)
+	relayClient.sweeper = m.sweeper
 	err := relayClient.Connect(m.ctx)
 	if err != nil {
 		rt.Lock()

shared/relay/client/picker.go

@@ -9,6 +9,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 )
 
@@ -30,6 +31,7 @@ type ServerPicker struct {
 	MTU               uint16
 	ConnectionTimeout time.Duration
 	TransportFallback *transportFallback
+	Sweeper           *netsweep.Sweeper
 }
 
 func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -73,6 +75,7 @@ func (sp *ServerPicker) startConnection(ctx context.Context, resultChan chan con
 	log.Infof("try to connecting to relay server: %s", url)
 	relayClient := NewClient(url, sp.TokenStore, sp.PeerID, sp.MTU)
 	relayClient.SetTransportFallback(sp.TransportFallback)
+	relayClient.sweeper = sp.Sweeper
 	err := relayClient.Connect(ctx)
 	resultChan <- connResult{
 		RelayClient: relayClient,

shared/signal/client/grpc.go

@@ -19,6 +19,8 @@ import (
 	"google.golang.org/grpc/status"
 
 	nbgrpc "github.com/netbirdio/netbird/client/grpc"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/signal/proto"
@@ -65,6 +67,13 @@ type GrpcClient struct {
 	connStateCallback     ConnStateNotifier
 	connStateCallbackLock sync.RWMutex
 
+	// netState gates the Receive retry loop on OS-reported network
+	// availability; nil (the default) disables gating.
+	netState *netstate.State
+
+	// sweeper cuts the transport connections on network change; nil disables it.
+	sweeper *netsweep.Sweeper
+
 	onReconnectedListenerFn func()
 
 	decryptionWorker       *Worker
@@ -88,13 +97,43 @@ type GrpcClient struct {
 	watchdogWg            sync.WaitGroup
 }
 
-// NewClient creates a new Signal client
-func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
-	var conn *grpc.ClientConn
+// Option configures optional GrpcClient behavior.
+type Option func(*GrpcClient)
 
+// WithNetworkState injects the OS network availability state that gates the
+// Receive retry loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) Option {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) Option {
+	return func(c *GrpcClient) { c.sweeper = sweeper }
+}
+
+// NewClient creates a new Signal client
+func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool, opts ...Option) (*GrpcClient, error) {
+	// Options apply before dialing: the sweeper must wrap the first connection too.
+	c := &GrpcClient{
+		ctx:                   ctx,
+		key:                   key,
+		mux:                   sync.Mutex{},
+		status:                StreamDisconnected,
+		connStateCallbackLock: sync.RWMutex{},
+	}
+	for _, opt := range opts {
+		opt(c)
+	}
+
+	var extraOpts []grpc.DialOption
+	if c.sweeper != nil {
+		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
+	}
+
+	var conn *grpc.ClientConn
 	operation := func() error {
 		var err error
-		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent)
+		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent, extraOpts...)
 		if err != nil {
 			return fmt.Errorf("create connection: %w", err)
 		}
@@ -109,15 +148,9 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
 
 	log.Debugf("connected to Signal Service: %v", conn.Target())
 
-	return &GrpcClient{
-		realClient:            proto.NewSignalExchangeClient(conn),
-		ctx:                   ctx,
-		signalConn:            conn,
-		key:                   key,
-		mux:                   sync.Mutex{},
-		status:                StreamDisconnected,
-		connStateCallbackLock: sync.RWMutex{},
-	}, nil
+	c.signalConn = conn
+	c.realClient = proto.NewSignalExchangeClient(conn)
+	return c, nil
 }
 
 func (c *GrpcClient) StreamConnected() bool {
@@ -168,6 +201,15 @@ func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Mes
 	var backOff = defaultBackoff(ctx)
 
 	operation := func() error {
+		// suspend reconnect attempts while the OS reports no usable network.
+		// Wait only errors on a cancelled context, which means shutdown, so
+		// stop the loop without reporting a failure.
+		if waited, err := c.netState.Wait(ctx); err != nil {
+			log.Debugf("signal connection context has been canceled while offline, this usually indicates shutdown")
+			return nil
+		} else if waited {
+			backOff.Reset()
+		}
 
 		c.notifyStreamDisconnected()