[client] Reset gRPC channel backoff when the network returns

Dials attempted by the gRPC channel while offline grow its internal
exponential backoff, so after the network came back the reconnect loop sat
in WaitForStateChange until that timer expired. Reset the channel backoff
alongside the retry backoff so the management and signal reconnects dial
immediately.

client/android/client.go

@@ -26,8 +26,7 @@ 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/netevents"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -82,13 +81,10 @@ 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
+	// netMgr outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run and RunWithoutLogin inject its state and
+	// sweeper into each new ConnectClient.
+	netMgr *netevents.Manager
 
 	stateMu       sync.RWMutex
 	connectClient *internal.ConnectClient
@@ -152,16 +148,17 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
 	execWorkaround(androidSDKVersion)
 
 	net.SetAndroidProtectSocketFn(tunAdapter.ProtectSocket)
+	system.SetIFaceDiscover(iFaceDiscover)
+	recorder := peer.NewRecorder("")
 	return &Client{
 		deviceName:            deviceName,
 		uiVersion:             uiVersion,
 		tunAdapter:            tunAdapter,
 		iFaceDiscover:         iFaceDiscover,
-		recorder:              peer.NewRecorder(""),
+		recorder:              recorder,
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
-		netState:              netstate.New(),
-		sweeper:               netsweep.New(),
+		netMgr:                netevents.NewManager(recorder),
 	}
 }
 
@@ -202,8 +199,9 @@ 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,
-		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
+		internal.WithNetEvents(c.netMgr))
 	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
@@ -245,7 +243,7 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
-		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
+		internal.WithNetEvents(c.netMgr))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
@@ -297,9 +295,12 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
 // 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.
+// Losing the last network also sweeps the registered connections: nothing can
+// redial while offline, so the stale sockets would otherwise stay silently
+// "connected" until their own timeouts and the client would keep reporting
+// Connected with no network at all.
 func (c *Client) SetNetworkAvailable(available bool) {
-	c.netState.Set(available)
-	c.recorder.SetNetworkAvailable(available)
+	c.netMgr.SetNetworkAvailable(available)
 }
 
 // NotifyNetworkChange marks the management, signal and relay connections
@@ -307,8 +308,7 @@ func (c *Client) SetNetworkAvailable(available bool) {
 // whatever has not redialed on the new network by then. The engine and the
 // TUN device stay untouched.
 func (c *Client) NotifyNetworkChange() {
-	c.sweeper.MarkNetworkChange()
-	log.Infof("network change: connections marked stale")
+	c.netMgr.NotifyNetworkChange()
 }
 
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.

client/grpc/dialer_generic.go

@@ -16,9 +16,14 @@ import (
 	"google.golang.org/grpc"
 
 	nbnet "github.com/netbirdio/netbird/client/net"
-	"github.com/netbirdio/netbird/client/netsweep"
+	"github.com/netbirdio/netbird/client/netevents/sweep"
 )
 
+// Sweeper registers in-flight dials for the network change sweep.
+type Sweeper interface {
+	StartDial(ctx context.Context) *sweep.Dial
+}
+
 func WithCustomDialer(_ bool, _ string) grpc.DialOption {
 	return grpc.WithContextDialer(dialContext)
 }
@@ -26,7 +31,7 @@ func WithCustomDialer(_ bool, _ string) grpc.DialOption {
 // 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 {
+func WithSweeper(sweeper Sweeper) grpc.DialOption {
 	return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
 		dial := sweeper.StartDial(ctx)
 		defer dial.Release()

client/grpc/dialer_js.go

@@ -1,12 +1,19 @@
 package grpc
 
 import (
+	"context"
+
 	"google.golang.org/grpc"
 
-	"github.com/netbirdio/netbird/client/netsweep"
+	"github.com/netbirdio/netbird/client/netevents/sweep"
 	"github.com/netbirdio/netbird/util/wsproxy/client"
 )
 
+// Sweeper registers in-flight dials for the network change sweep.
+type Sweeper interface {
+	StartDial(ctx context.Context) *sweep.Dial
+}
+
 // WithCustomDialer returns a gRPC dial option that uses WebSocket transport for WASM/JS environments.
 // The component parameter specifies the WebSocket proxy component path (e.g., "/management", "/signal").
 func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
@@ -14,6 +21,6 @@ func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
 }
 
 // WithSweeper is a no-op on WASM/JS: there is no network change signal.
-func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
+func WithSweeper(_ Sweeper) grpc.DialOption {
 	return grpc.EmptyDialOption{}
 }

client/grpc/retry.go

@@ -6,16 +6,19 @@ import (
 	"time"
 
 	"github.com/cenkalti/backoff/v4"
-
-	"github.com/netbirdio/netbird/client/netstate"
 )
 
+// ChangeWatcher exposes OS network availability transitions.
+type ChangeWatcher interface {
+	Changed() <-chan struct{}
+}
+
 // Retry mirrors backoff.Retry, but the sleep between attempts also wakes on
 // OS network availability transitions: an operation cut down by a network
 // change retries the moment the network settles instead of sleeping through
-// the recovery. A nil netState never fires, leaving plain backoff.Retry
+// the recovery. A nil watcher never fires, leaving plain backoff.Retry
 // behavior.
-func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, netState *netstate.State) error {
+func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, watcher ChangeWatcher) error {
 	bo.Reset()
 	for {
 		err := operation()
@@ -36,10 +39,14 @@ func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff,
 			return err
 		}
 
+		var changed <-chan struct{}
+		if watcher != nil {
+			changed = watcher.Changed()
+		}
 		timer := time.NewTimer(next)
 		select {
 		case <-timer.C:
-		case <-netState.Changed():
+		case <-changed:
 			timer.Stop()
 		case <-ctx.Done():
 			timer.Stop()

client/grpc/retry_test.go

@@ -10,7 +10,7 @@ import (
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
-	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netevents/netstate"
 )
 
 func TestRetryWakesOnNetworkChange(t *testing.T) {

client/internal/connect.go

@@ -38,8 +38,7 @@ 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"
+	"github.com/netbirdio/netbird/client/netevents"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/ssh"
 	sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -73,28 +72,17 @@ type ConnectClient struct {
 
 	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
+	// netEvents gates every reconnection loop on OS-reported network
+	// availability and sweeps connections on network change.
+	netEvents *netevents.Manager
 }
 
 // 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 }
+// WithNetEvents injects the OS network event handling.
+func WithNetEvents(events *netevents.Manager) ConnectClientOption {
+	return func(c *ConnectClient) { c.netEvents = events }
 }
 
 func NewConnectClient(
@@ -305,7 +293,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}
 
 		// suspend connection attempts while the OS reports no usable network
-		if waited, err := c.netState.Wait(c.ctx); err != nil {
+		if waited, err := c.netEvents.Wait(c.ctx); err != nil {
 			return nil
 		} else if waited {
 			backOff.Reset()
@@ -323,7 +311,7 @@ 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,
-			mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
+			mgm.WithNetEvents(c.netEvents))
 		if err != nil {
 			// On daemon shutdown / Down() the parent context is cancelled
 			// and the dial fails with "context canceled". Wrapping that
@@ -398,7 +386,7 @@ 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, c.netState, c.sweeper)
+		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netEvents)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -435,7 +423,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}
 
 		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
-			relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
+			relayClient.WithNetEvents(c.netEvents))
 		c.statusRecorder.SetRelayMgr(relayManager)
 		if len(relayURLs) > 0 {
 			if token != nil {
@@ -463,7 +451,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			UpdateManager:  c.updateManager,
 			ClientMetrics:  c.clientMetrics,
 			MetricsCtx:     c.ctx,
-			NetState:       c.netState,
+			NetState:       c.netEvents,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine
@@ -723,7 +711,7 @@ 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, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
+func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netEvents *netevents.Manager) (*signal.GrpcClient, error) {
 	var sigTLSEnabled bool
 	if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
 		sigTLSEnabled = true
@@ -732,7 +720,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 	}
 
 	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
-		signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
+		signal.WithNetEvents(netEvents))
 	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

@@ -59,7 +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"
+	"github.com/netbirdio/netbird/client/netevents"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -184,7 +184,7 @@ type EngineServices struct {
 	MetricsCtx     context.Context
 	// NetState gates the reconnection loops on OS-reported network
 	// availability; nil disables gating.
-	NetState *netstate.State
+	NetState *netevents.Manager
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -210,7 +210,7 @@ type Engine struct {
 
 	// netState gates the peer reconnection guards on OS-reported network
 	// availability; nil disables gating.
-	netState *netstate.State
+	netState *netevents.Manager
 
 	// STUNs is a list of STUN servers used by ICE
 	STUNs []*stun.URI

client/internal/peer/conn.go

@@ -26,7 +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/client/netevents"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
@@ -97,7 +97,7 @@ type ConnConfig struct {
 
 	// NetworkState gates the reconnection guard on OS-reported network
 	// availability; nil disables gating.
-	NetworkState *netstate.State
+	NetworkState *netevents.Manager
 }
 
 type Conn struct {

client/internal/peer/guard/guard.go

@@ -6,8 +6,6 @@ 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.
@@ -24,6 +22,12 @@ const (
 
 type connStatusFunc func() ConnStatus
 
+// NetworkWatcher is the availability view the guard gates reconnects on.
+type NetworkWatcher interface {
+	IsOnline() bool
+	Changed() <-chan struct{}
+}
+
 // Guard is responsible for the reconnection logic.
 // It will trigger to send an offer to the peer then has connection issues.
 // Watch these events:
@@ -39,14 +43,14 @@ type Guard struct {
 	srWatcher           *SRWatcher
 	// netState gates reconnect attempts on OS-reported network availability;
 	// nil disables gating.
-	netState                *netstate.State
+	netState                NetworkWatcher
 	relayedConnDisconnected chan struct{}
 	iCEConnDisconnected     chan struct{}
 }
 
 // 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 {
+func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState NetworkWatcher) *Guard {
 	return &Guard{
 		log:                     log,
 		isConnectedOnAllWay:     isConnectedFn,
@@ -104,14 +108,17 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	iceState := &iceRetryState{log: g.log}
 	defer iceState.reset()
 
-	netChanged := g.netState.Changed()
+	var netChanged <-chan struct{}
+	if g.netState != nil {
+		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() {
+			if g.netState != nil && !g.netState.IsOnline() {
 				continue
 			}
 			switch g.isConnectedOnAllWay() {

client/internal/peer/guard/guard_netstate_test.go

@@ -9,7 +9,7 @@ import (
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/internal/peer/ice"
-	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netevents/netstate"
 )
 
 // newTestGuardWithNetState builds a guard with a realistic MaxInterval: the

client/internal/updater/installer/doc.go

@@ -37,23 +37,32 @@
 // Updater Process (Setup):
 //
 //  1. Receives parameters from service via command-line arguments
-//  2. Runs installer with appropriate silent/quiet flags:
+//  2. Terminates the UI so the installer does not have to replace a locked image
+//     file, which would otherwise leave the install needing a reboot
+//  3. Runs installer with appropriate silent/quiet flags:
 //     - Windows EXE: installer.exe /S
-//     - Windows MSI: msiexec.exe /i installer.msi /quiet /qn /l*v msi.log
+//     - Windows MSI: msiexec.exe /i installer.msi /qn /norestart REBOOT=ReallySuppress /l*v msi.log
 //     - macOS PKG: installer -pkg installer.pkg -target /
 //     - macOS Homebrew: brew upgrade netbirdio/tap/netbird
-//  3. Installer terminates daemon and UI processes
-//  4. Installer replaces binaries with new version
-//  5. Updater waits for installer to complete
-//  6. Updater restarts daemon:
+//  4. Installer terminates the daemon
+//  5. Installer replaces binaries with new version
+//  6. Updater waits for installer to complete. On Windows, MSI exit codes 3010
+//     (ERROR_SUCCESS_REBOOT_REQUIRED) and 1641 (ERROR_SUCCESS_REBOOT_INITIATED)
+//     are a pending-reboot outcome, not a failure: the install succeeded, but
+//     some files are only replaced on the next restart (the reboot itself is
+//     suppressed via /norestart and REBOOT=ReallySuppress), and the flow
+//     continues as on success
+//  7. Updater restarts daemon:
 //     - Windows: netbird.exe service start
 //     - macOS/Linux: netbird service start
-//  7. Updater restarts UI:
-//     - Windows: Launches netbird-ui.exe as active console user using CreateProcessAsUser
+//  8. Updater restarts UI:
+//     - Windows: Launches netbird-ui.exe using CreateProcessAsUser in every
+//     session it was terminated in, falling back to the active console session
 //     - macOS: Uses launchctl asuser to launch NetBird.app for console user
 //     - Linux: Not implemented (UI typically auto-starts)
-//  8. Updater writes result.json with success/error status
-//  9. Updater process exits
+//  9. Updater writes result.json with success/error status (a pending reboot is
+//     recorded as success)
+//  10. Updater process exits
 //
 // # Result Communication
 //

client/internal/updater/installer/installer_run_windows.go

@@ -2,6 +2,7 @@ package installer
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"os"
 	"os/exec"
@@ -22,6 +23,12 @@ const (
 
 	msiLogFile = "msi.log"
 
+	// ERROR_SUCCESS_REBOOT_REQUIRED and ERROR_SUCCESS_REBOOT_INITIATED
+	msiRebootRequired  = 3010
+	msiRebootInitiated = 1641
+
+	processExitWait = 10 * time.Second
+
 	msiDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.msi"
 	exeDownloadURL = "https://github.com/netbirdio/netbird/releases/download/v%version/netbird_installer_%version_windows_%arch.exe"
 )
@@ -38,6 +45,8 @@ var (
 func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string, daemonFolder string) (resultErr error) {
 	resultHandler := NewResultHandler(u.tempDir)
 
+	var uiSessions []uint32
+
 	// Always ensure daemon and UI are restarted after setup
 	defer func() {
 		log.Infof("starting daemon back")
@@ -46,7 +55,7 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 		}
 
 		log.Infof("starting UI back")
-		if err := u.startUIAsUser(daemonFolder); err != nil {
+		if err := u.startUI(daemonFolder, uiSessions); err != nil {
 			log.Errorf("failed to start UI: %v", err)
 		}
 
@@ -75,6 +84,14 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 		return
 	}
 
+	// The UI holds an open handle on its own image. Left running, Restart Manager
+	// cannot shut it down (msiexec runs as LocalSystem here, the UI as the
+	// interactive user), so the MSI falls back to replacing the file on reboot and
+	// marks the install as restart-required. The deferred close-application action
+	// in the package runs too late to prevent that, it happens after
+	// InstallValidate has already registered the file as in use.
+	uiSessions = killUI()
+
 	var cmd *exec.Cmd
 	switch installerType {
 	case TypeExe:
@@ -84,7 +101,9 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 		installerDir := filepath.Dir(installerFile)
 		logPath := filepath.Join(installerDir, msiLogFile)
 		log.Infof("run msi installer: %s", installerFile)
-		cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/quiet", "/qn", "/l*v", logPath)
+		// REBOOT=ReallySuppress: a silent install has no way to ask, so without it
+		// msiexec reboots the machine on its own if it decides one is needed.
+		cmd = exec.CommandContext(ctx, "msiexec.exe", "/i", filepath.Base(installerFile), "/qn", "/norestart", "REBOOT=ReallySuppress", "/l*v", logPath)
 	}
 
 	cmd.Dir = filepath.Dir(installerFile)
@@ -95,9 +114,13 @@ func (u *Installer) Setup(ctx context.Context, dryRun bool, installerFile string
 	}
 
 	log.Infof("installer started with PID %d", cmd.Process.Pid)
-	if resultErr = cmd.Wait(); resultErr != nil {
-		log.Errorf("installer process finished with error: %v", resultErr)
-		return
+	if err := cmd.Wait(); err != nil {
+		if !isRebootPending(err) {
+			resultErr = err
+			log.Errorf("installer process finished with error: %v", err)
+			return
+		}
+		log.Warnf("installer completed but reported a pending reboot, some files will be replaced on the next restart")
 	}
 
 	return nil
@@ -117,16 +140,142 @@ func (u *Installer) startDaemon(daemonFolder string) error {
 	return nil
 }
 
-func (u *Installer) startUIAsUser(daemonFolder string) error {
+func (u *Installer) startUI(daemonFolder string, sessionIDs []uint32) error {
 	uiPath := filepath.Join(daemonFolder, uiName)
 	log.Infof("starting netbird-ui: %s", uiPath)
 
-	// Get the active console session ID
-	sessionID := windows.WTSGetActiveConsoleSessionId()
-	if sessionID == 0xFFFFFFFF {
-		return fmt.Errorf("no active user session found")
+	if len(sessionIDs) == 0 {
+		sessionID := windows.WTSGetActiveConsoleSessionId()
+		if sessionID == 0xFFFFFFFF {
+			return fmt.Errorf("no active user session found")
+		}
+		sessionIDs = []uint32{sessionID}
 	}
 
+	var errs []error
+	for _, sessionID := range sessionIDs {
+		if err := startUIInSession(uiPath, sessionID); err != nil {
+			errs = append(errs, fmt.Errorf("session %d: %w", sessionID, err))
+			continue
+		}
+		log.Infof("netbird-ui started successfully in session %d", sessionID)
+	}
+	return errors.Join(errs...)
+}
+
+// isRebootPending reports whether the installer exit code means it succeeded but
+// left work for the next restart. The reboot itself is suppressed, so this is not
+// a failure.
+func isRebootPending(err error) bool {
+	var exitErr *exec.ExitError
+	if !errors.As(err, &exitErr) {
+		return false
+	}
+
+	switch exitErr.ExitCode() {
+	case msiRebootRequired, msiRebootInitiated:
+		return true
+	default:
+		return false
+	}
+}
+
+// killUI terminates any running netbird-ui process and returns the IDs of the
+// interactive sessions the terminated processes belonged to. Setup starts the
+// UI again in those sessions once the installer is done.
+func killUI() []uint32 {
+	pids, err := processIDsByName(uiName)
+	if err != nil {
+		log.Warnf("failed to look up %s processes: %v", uiName, err)
+		return nil
+	}
+
+	sessions := make(map[uint32]struct{})
+	for _, pid := range pids {
+		var sessionID uint32
+		if err := windows.ProcessIdToSessionId(pid, &sessionID); err != nil {
+			log.Warnf("failed to look up session of %s (PID %d): %v", uiName, pid, err)
+		}
+
+		if err := terminateProcess(pid); err != nil {
+			log.Warnf("failed to terminate %s (PID %d): %v", uiName, pid, err)
+			continue
+		}
+		log.Infof("terminated %s (PID %d) in session %d", uiName, pid, sessionID)
+
+		if sessionID != 0 {
+			sessions[sessionID] = struct{}{}
+		}
+	}
+
+	sessionIDs := make([]uint32, 0, len(sessions))
+	for sessionID := range sessions {
+		sessionIDs = append(sessionIDs, sessionID)
+	}
+	return sessionIDs
+}
+
+func processIDsByName(name string) ([]uint32, error) {
+	snapshot, err := windows.CreateToolhelp32Snapshot(windows.TH32CS_SNAPPROCESS, 0)
+	if err != nil {
+		return nil, fmt.Errorf("create process snapshot: %w", err)
+	}
+	defer func() {
+		if err := windows.CloseHandle(snapshot); err != nil {
+			log.Warnf("failed to close process snapshot: %v", err)
+		}
+	}()
+
+	var entry windows.ProcessEntry32
+	entry.Size = uint32(unsafe.Sizeof(entry))
+
+	var pids []uint32
+	for err = windows.Process32First(snapshot, &entry); err == nil; err = windows.Process32Next(snapshot, &entry) {
+		if strings.EqualFold(windows.UTF16ToString(entry.ExeFile[:]), name) {
+			pids = append(pids, entry.ProcessID)
+		}
+	}
+	if !errors.Is(err, windows.ERROR_NO_MORE_FILES) {
+		return nil, fmt.Errorf("enumerate processes: %w", err)
+	}
+
+	return pids, nil
+}
+
+func terminateProcess(pid uint32) error {
+	handle, err := windows.OpenProcess(windows.PROCESS_TERMINATE|windows.SYNCHRONIZE, false, pid)
+	if err != nil {
+		// The process may have exited between enumeration and now.
+		if errors.Is(err, windows.ERROR_INVALID_PARAMETER) {
+			return nil
+		}
+		return fmt.Errorf("open process: %w", err)
+	}
+	defer func() {
+		if err := windows.CloseHandle(handle); err != nil {
+			log.Warnf("failed to close process handle: %v", err)
+		}
+	}()
+
+	if err := windows.TerminateProcess(handle, 0); err != nil {
+		return fmt.Errorf("terminate process: %w", err)
+	}
+
+	// Wait for the handle to signal so the image file is released before the
+	// installer tries to overwrite it. A timeout is reported through the returned
+	// event, not through err, which stays nil unless the wait itself failed.
+	event, err := windows.WaitForSingleObject(handle, uint32(processExitWait.Milliseconds()))
+	if err != nil {
+		return fmt.Errorf("wait for process exit: %w", err)
+	}
+	if event != windows.WAIT_OBJECT_0 {
+		return fmt.Errorf("wait for process exit: unexpected wait result %#x", event)
+	}
+
+	return nil
+}
+
+func startUIInSession(uiPath string, sessionID uint32) error {
 	// Get the user token for that session
 	var userToken windows.Token
 	err := windows.WTSQueryUserToken(sessionID, &userToken)
@@ -197,7 +346,6 @@ func (u *Installer) startUIAsUser(daemonFolder string) error {
 		log.Warnf("failed to close thread handle: %v", err)
 	}
 
-	log.Infof("netbird-ui started successfully in session %d", sessionID)
 	return nil
 }
 

client/internal/updater/installer/installer_run_windows_test.go

@@ -0,0 +1,108 @@
+package installer
+
+import (
+	"errors"
+	"os/exec"
+	"slices"
+	"strconv"
+	"testing"
+)
+
+// exitErrorWithCode returns a real *exec.ExitError carrying the given exit code.
+func exitErrorWithCode(t *testing.T, code int) error {
+	t.Helper()
+
+	err := exec.Command("cmd.exe", "/c", "exit "+strconv.Itoa(code)).Run()
+	if err == nil {
+		t.Fatalf("expected a non-zero exit for code %d", code)
+	}
+	return err
+}
+
+func TestIsRebootPending(t *testing.T) {
+	tests := []struct {
+		name string
+		code int
+		want bool
+	}{
+		{name: "reboot required", code: msiRebootRequired, want: true},
+		{name: "reboot initiated", code: msiRebootInitiated, want: true},
+		{name: "generic failure", code: 1603, want: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			if got := isRebootPending(exitErrorWithCode(t, tt.code)); got != tt.want {
+				t.Errorf("isRebootPending(exit %d) = %v, want %v", tt.code, got, tt.want)
+			}
+		})
+	}
+}
+
+// TestProcessIDsByNameAndTerminate spawns a long-running system process, finds it
+// by name and terminates it, covering the path the updater uses to release the UI
+// image file before the installer replaces it.
+func TestProcessIDsByNameAndTerminate(t *testing.T) {
+	cmd := exec.Command("ping.exe", "-n", "60", "127.0.0.1")
+	if err := cmd.Start(); err != nil {
+		t.Fatalf("start ping: %v", err)
+	}
+
+	pid := uint32(cmd.Process.Pid)
+	killed := false
+	t.Cleanup(func() {
+		if !killed {
+			_ = cmd.Process.Kill()
+		}
+		_ = cmd.Wait()
+	})
+
+	// Name matching must be case-insensitive: the snapshot reports PING.EXE.
+	pids, err := processIDsByName("ping.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName: %v", err)
+	}
+
+	if !slices.Contains(pids, pid) {
+		t.Fatalf("PID %d not among the ping.exe processes found: %v", pid, pids)
+	}
+
+	if err := terminateProcess(pid); err != nil {
+		t.Fatalf("terminateProcess: %v", err)
+	}
+	killed = true
+
+	// terminateProcess only returns once the handle has signalled, so the process
+	// is already gone and Wait must not block. It exits with the code passed to
+	// TerminateProcess, which is 0, so Wait reports no error.
+	if err := cmd.Wait(); err != nil {
+		t.Fatalf("wait for terminated ping: %v", err)
+	}
+	if !cmd.ProcessState.Exited() {
+		t.Error("process did not exit after terminateProcess")
+	}
+
+	remaining, err := processIDsByName("ping.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName after terminate: %v", err)
+	}
+	if slices.Contains(remaining, pid) {
+		t.Errorf("PID %d still listed after terminateProcess", pid)
+	}
+}
+
+func TestProcessIDsByNameNoMatch(t *testing.T) {
+	pids, err := processIDsByName("netbird-nonexistent-process.exe")
+	if err != nil {
+		t.Fatalf("processIDsByName: %v", err)
+	}
+	if len(pids) != 0 {
+		t.Errorf("expected no matches, got %v", pids)
+	}
+}
+
+func TestIsRebootPendingNonExitError(t *testing.T) {
+	if isRebootPending(errors.New("start installer: file not found")) {
+		t.Error("a non-exit error must not be treated as a pending reboot")
+	}
+}

client/ios/NetBirdSDK/client.go

@@ -22,8 +22,7 @@ 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/netevents"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -84,12 +83,10 @@ 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
+	// netMgr outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run injects its state and sweeper into each new
+	// ConnectClient.
+	netMgr *netevents.Manager
 	// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
 	preloadedConfig *profilemanager.Config
 
@@ -100,6 +97,7 @@ type Client struct {
 
 // NewClient instantiate a new Client
 func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osVersion string, osName string, networkChangeListener NetworkChangeListener, dnsManager DnsManager) *Client {
+	recorder := peer.NewRecorder("")
 	return &Client{
 		cfgFile:               cfgFile,
 		stateFile:             stateFile,
@@ -108,12 +106,11 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
 		deviceName:            deviceName,
 		osName:                osName,
 		osVersion:             osVersion,
-		recorder:              peer.NewRecorder(""),
+		recorder:              recorder,
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
 		dnsManager:            dnsManager,
-		netState:              netstate.New(),
-		sweeper:               netsweep.New(),
+		netMgr:                netevents.NewManager(recorder),
 	}
 }
 
@@ -190,7 +187,7 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	cfg.WgIface = interfaceName
 
 	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
-		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
+		internal.WithNetEvents(c.netMgr))
 	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
@@ -203,10 +200,11 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 // (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.
+// immediately with a fresh backoff. Losing the last network also sweeps the
+// registered connections, so the client does not keep reporting Connected
+// over stale sockets with no network at all.
 func (c *Client) SetNetworkAvailable(available bool) {
-	c.netState.Set(available)
-	c.recorder.SetNetworkAvailable(available)
+	c.netMgr.SetNetworkAvailable(available)
 }
 
 // NotifyNetworkChange marks the management, signal and relay connections
@@ -214,8 +212,7 @@ func (c *Client) SetNetworkAvailable(available bool) {
 // whatever has not redialed on the new network by then. The engine and the
 // TUN device stay untouched.
 func (c *Client) NotifyNetworkChange() {
-	c.sweeper.MarkNetworkChange()
-	log.Infof("network change: connections marked stale")
+	c.netMgr.NotifyNetworkChange()
 }
 
 // Stop the internal client and free the resources

client/netevents/netevents.go

@@ -0,0 +1,158 @@
+// Package netevents owns the OS network event handling shared by the mobile
+// bindings: availability changes park or wake the reconnection loops and drive
+// the NoNetwork listener state, and both losing the last network and switching
+// networks sweep the stale connections so their owners redial immediately.
+package netevents
+
+import (
+	"context"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netevents/netstate"
+	"github.com/netbirdio/netbird/client/netevents/sweep"
+)
+
+// Recorder receives the availability changes for listener state reporting.
+type Recorder interface {
+	SetNetworkAvailable(available bool)
+}
+
+// Manager ties the network availability state, the connection sweeper and the
+// status recorder together; it outlives engine restarts. A nil *Manager is
+// the valid no-events value: the read methods report always-online and never
+// sweep.
+type Manager struct {
+	netState *netstate.State
+	sweeper  *sweep.Sweeper
+	recorder Recorder
+}
+
+// NewManager creates a Manager reporting into recorder, starting online.
+func NewManager(recorder Recorder) *Manager {
+	return &Manager{
+		netState: netstate.New(),
+		sweeper:  sweep.New(),
+		recorder: recorder,
+	}
+}
+
+// SetNetworkAvailable records OS-reported network availability. While
+// unavailable, the reconnection loops suspend their attempts and the
+// connection listener reports NoNetwork instead of Connecting; when
+// availability returns, the loops resume immediately with a fresh backoff.
+// Losing the last network also sweeps the registered connections: nothing can
+// redial while offline, so the stale sockets would otherwise stay silently
+// "connected" until their own timeouts and the client would keep reporting
+// Connected with no network at all.
+func (m *Manager) SetNetworkAvailable(available bool) {
+	if !available && m.netState.IsOnline() {
+		m.sweeper.MarkNetworkChange()
+	}
+	m.netState.Set(available)
+	m.recorder.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange marks the management, signal and relay connections
+// stale after the OS switched networks and schedules a sweep that cuts
+// whatever has not redialed on the new network by then. The engine and the
+// TUN device stay untouched.
+func (m *Manager) NotifyNetworkChange() {
+	m.sweeper.MarkNetworkChange()
+	log.Infof("network change: connections marked stale")
+}
+
+// IsOnline reports whether the OS reports at least one usable network.
+func (m *Manager) IsOnline() bool {
+	if m == nil {
+		return true
+	}
+	return m.netState.IsOnline()
+}
+
+// Changed returns a channel closed on the next availability transition.
+func (m *Manager) Changed() <-chan struct{} {
+	if m == nil {
+		return nil
+	}
+	return m.netState.Changed()
+}
+
+// Wait blocks while the network is offline; see netstate.State.Wait.
+func (m *Manager) Wait(ctx context.Context) (bool, error) {
+	if m == nil {
+		return false, nil
+	}
+	return m.netState.Wait(ctx)
+}
+
+// WaitSettled waits until an online verdict holds for a full settleWindow, or
+// while offline until the budget runs out. Returns false when ctx is
+// cancelled. The settle window exists because a disconnect often precedes the
+// OS offline flag by a few milliseconds, so a fresh online verdict cannot be
+// trusted immediately. A nil Manager has no events to watch: it degrades to a
+// fixed budget-long sleep.
+func (m *Manager) WaitSettled(ctx context.Context, budget, settleWindow time.Duration) bool {
+	if m == nil {
+		select {
+		case <-time.After(budget):
+			return true
+		case <-ctx.Done():
+			return false
+		}
+	}
+
+	budgetTimer := time.NewTimer(budget)
+	defer budgetTimer.Stop()
+
+	settle := time.NewTimer(settleWindow)
+	defer settle.Stop()
+
+	for {
+		// Channel first, flag second: a flip in between still fires the channel.
+		changedCh := m.netState.Changed()
+		if m.netState.IsOnline() {
+			select {
+			case <-settle.C:
+				return true
+			case <-changedCh:
+			case <-ctx.Done():
+				return false
+			}
+		} else {
+			select {
+			case <-budgetTimer.C:
+				return true
+			case <-changedCh:
+			case <-ctx.Done():
+				return false
+			}
+		}
+		if !settle.Stop() {
+			select {
+			case <-settle.C:
+			default:
+			}
+		}
+		settle.Reset(settleWindow)
+	}
+}
+
+// StartDial registers an in-flight dial with the sweeper; see sweep.Sweeper.StartDial.
+func (m *Manager) StartDial(ctx context.Context) *sweep.Dial {
+	if m == nil {
+		return (*sweep.Sweeper)(nil).StartDial(ctx)
+	}
+	return m.sweeper.StartDial(ctx)
+}
+
+// QuickRetryBackoff wraps bo for a quick retry after a network change; see
+// sweep.Sweeper.QuickRetryBackoff.
+func (m *Manager) QuickRetryBackoff(ctx context.Context, bo backoff.BackOff) backoff.BackOff {
+	if m == nil {
+		return bo
+	}
+	return m.sweeper.QuickRetryBackoff(ctx, bo, m.netState)
+}

client/netevents/netevents_test.go

@@ -0,0 +1,34 @@
+package netevents
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+)
+
+type recorderStub struct{}
+
+func (recorderStub) SetNetworkAvailable(bool) {}
+
+func TestWaitSettledAfterOutage(t *testing.T) {
+	const budget = 1500 * time.Millisecond
+	const settleWindow = 200 * time.Millisecond
+	const outage = 2 * settleWindow
+
+	m := NewManager(recorderStub{})
+	m.SetNetworkAvailable(false)
+
+	start := time.Now()
+	go func() {
+		time.Sleep(outage)
+		m.SetNetworkAvailable(true)
+	}()
+
+	ok := m.WaitSettled(context.Background(), budget, settleWindow)
+	elapsed := time.Since(start)
+
+	assert.True(t, ok, "recovered network must let the caller proceed")
+	assert.GreaterOrEqual(t, elapsed, outage+settleWindow, "an online verdict must hold a full settle window before it is trusted")
+}

client/netevents/sweep/quick_retry.go

@@ -1,11 +1,11 @@
-package netsweep
+package sweep
 
 import (
 	"time"
 
 	"github.com/cenkalti/backoff/v4"
 
-	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netevents/netstate"
 )
 
 const quickRetryDelay = 200 * time.Millisecond

client/netevents/sweep/quick_retry_test.go

@@ -1,4 +1,4 @@
-package netsweep
+package sweep
 
 import (
 	"context"

client/netevents/sweep/sweep.go

@@ -1,10 +1,10 @@
-// Package netsweep cuts network-bound activity when the OS switches networks:
+// Package sweep 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
+package sweep
 
 import (
 	"context"
@@ -16,7 +16,7 @@ import (
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
 
-	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netevents/netstate"
 )
 
 // DefaultSweepDelay absorbs network flapping while the OS settles on a
@@ -34,7 +34,7 @@ type Config struct {
 // 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")
+var ErrSwept = errors.New("sweep: 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.

client/netevents/sweep/sweep_test.go

@@ -1,4 +1,4 @@
-package netsweep
+package sweep
 
 import (
 	"context"

client/system/info_android.go

@@ -30,6 +30,11 @@ func GetInfo(ctx context.Context) *Info {
 		kernelVersion = osInfo[2]
 	}
 
+	addrs, err := networkAddresses()
+	if err != nil {
+		log.Warnf("discover network addresses: %s", err)
+	}
+
 	gio := &Info{
 		GoOS:               runtime.GOOS,
 		Kernel:             kernel,
@@ -41,6 +46,7 @@ func GetInfo(ctx context.Context) *Info {
 		NetbirdVersion:     version.NetbirdVersion(),
 		UIVersion:          extractUIVersion(ctx),
 		KernelVersion:      kernelVersion,
+		NetworkAddresses:   addrs,
 		SystemSerialNumber: serial(),
 		SystemProductName:  productModel(),
 		SystemManufacturer: productManufacturer(),

client/system/network_addr.go

@@ -1,4 +1,4 @@
-//go:build !ios
+//go:build !ios && !android
 
 package system
 

client/system/network_addr_android.go

@@ -0,0 +1,89 @@
+package system
+
+import (
+	"net/netip"
+	"strings"
+)
+
+var iFaceDiscover IFaceDiscover
+
+type IFaceDiscover interface {
+	IFaces() (string, error)
+}
+
+// SetIFaceDiscover configures the Android interface discovery provider.
+func SetIFaceDiscover(discover IFaceDiscover) {
+	iFaceDiscover = discover
+}
+
+func networkAddresses() ([]NetworkAddress, error) {
+	if iFaceDiscover == nil {
+		return nil, nil
+	}
+	ifaces, err := iFaceDiscover.IFaces()
+	if err != nil {
+		return nil, err
+	}
+
+	var netAddresses []NetworkAddress
+	for _, line := range strings.Split(ifaces, "\n") {
+		addresses, ok := interfaceAddresses(line)
+		if !ok {
+			continue
+		}
+		for _, address := range addresses {
+			netAddr, ok := toNetworkAddress(address)
+			if !ok {
+				continue
+			}
+			if isDuplicated(netAddresses, netAddr) {
+				continue
+			}
+			netAddresses = append(netAddresses, netAddr)
+		}
+	}
+	return netAddresses, nil
+}
+
+func interfaceAddresses(line string) ([]string, bool) {
+	parts := strings.Split(line, "|")
+	if len(parts) != 2 {
+		return nil, false
+	}
+	flags := strings.Fields(parts[0])
+	if len(flags) != 8 {
+		return nil, false
+	}
+	up, loopback := flags[3], flags[5]
+	if up != "true" || loopback == "true" {
+		return nil, false
+	}
+	return strings.Fields(parts[1]), true
+}
+
+func toNetworkAddress(address string) (NetworkAddress, bool) {
+	prefix, err := netip.ParsePrefix(address)
+	if err != nil {
+		return NetworkAddress{}, false
+	}
+	if prefix.Addr().Is4In6() {
+		if prefix.Bits() < 96 {
+			return NetworkAddress{}, false
+		}
+		prefix = netip.PrefixFrom(prefix.Addr().Unmap(), prefix.Bits()-96)
+	}
+	ip := prefix.Addr()
+	if ip.IsLoopback() || ip.IsLinkLocalUnicast() || ip.IsMulticast() {
+		return NetworkAddress{}, false
+	}
+	return NetworkAddress{NetIP: prefix}, true
+}
+
+func isDuplicated(addresses []NetworkAddress, addr NetworkAddress) bool {
+	for _, duplicated := range addresses {
+		if duplicated.NetIP == addr.NetIP {
+			return true
+		}
+	}
+	return false
+}

client/system/network_addr_test.go

@@ -1,4 +1,4 @@
-//go:build !ios
+//go:build !ios && !android
 
 package system
 

shared/management/client/grpc.go

@@ -21,8 +21,7 @@ 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/netevents"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -64,12 +63,9 @@ 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
+	// netEvents gates the stream retry loop on OS-reported network
+	// availability and sweeps the transport on network change.
+	netEvents *netevents.Manager
 
 	// syncStreamErr holds the last Sync stream error, or nil while the stream
 	// is established and healthy. GetServerKey succeeds even when the peer
@@ -123,15 +119,9 @@ func MaxRecvMsgSize() int {
 // 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 }
+// WithNetEvents injects the OS network event handling.
+func WithNetEvents(events *netevents.Manager) Option {
+	return func(c *GrpcClient) { c.netEvents = events }
 }
 
 // NewClient creates a new client to Management service
@@ -152,9 +142,7 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
 		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))
-	}
+	extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.netEvents))
 
 	var conn *grpc.ClientConn
 	operation := func() error {
@@ -235,16 +223,19 @@ func (c *GrpcClient) withMgmtStream(
 	ctx context.Context,
 	handler func(ctx context.Context, serverPubKey wgtypes.Key, backOff backoff.BackOff) error,
 ) error {
-	backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
+	backOff := c.netEvents.QuickRetryBackoff(ctx, 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 {
+		if waited, err := c.netEvents.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()
+			// dials attempted while offline grew the channel's internal backoff;
+			// reset it too, or the reconnect waits out that timer first
+			c.conn.ResetConnectBackoff()
 		}
 
 		connState := c.conn.GetState()
@@ -273,7 +264,7 @@ func (c *GrpcClient) withMgmtStream(
 		return handler(ctx, *serverPubKey, backOff)
 	}
 
-	err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
+	err := nbgrpc.Retry(ctx, operation, backOff, c.netEvents)
 	if err != nil {
 		log.Warnf("exiting the Management service connection retry loop due to the unrecoverable error: %s", err)
 	}

shared/relay/client/client.go

@@ -14,7 +14,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
-	"github.com/netbirdio/netbird/client/netsweep"
+	"github.com/netbirdio/netbird/client/netevents/sweep"
 	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"
@@ -151,6 +151,14 @@ type transportConn interface {
 	Protocol() string
 }
 
+// NetEvents is the OS network event view the relay consumes: availability
+// gating for the reconnect guard and dial registration for the network change
+// sweep.
+type NetEvents interface {
+	NetworkWatcher
+	StartDial(ctx context.Context) *sweep.Dial
+}
+
 // Client is a client for the relay server. It is responsible for establishing a connection to the relay server and
 // managing connections to other peers. All exported functions are safe to call concurrently. After close the connection,
 // the client can be reused by calling Connect again. When the client is closed, all connections are closed too.
@@ -186,9 +194,10 @@ type Client struct {
 	// 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
+	// netEvents registers the relay dial for the network change sweep; the
+	// read loop reports the disconnect and the guard reconnects. Shared via
+	// the manager.
+	netEvents NetEvents
 	// datagramFallbackTriggered guards a single fallback per connection so a
 	// burst of oversized datagrams triggers one reconnect, not many.
 	datagramFallbackTriggered atomic.Bool
@@ -400,7 +409,12 @@ 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)
+	var dial *sweep.Dial
+	if c.netEvents != nil {
+		dial = c.netEvents.StartDial(ctx)
+	} else {
+		dial = (*sweep.Sweeper)(nil).StartDial(ctx)
+	}
 	defer dial.Release()
 	ctx = dial.Ctx()
 

shared/relay/client/guard.go

@@ -7,8 +7,6 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/netstate"
 )
 
 const (
@@ -24,6 +22,13 @@ const (
 	verdictSettleWindow = 200 * time.Millisecond
 )
 
+// NetworkWatcher is the availability view the guard gates reconnects on.
+type NetworkWatcher interface {
+	Wait(ctx context.Context) (bool, error)
+	IsOnline() bool
+	WaitSettled(ctx context.Context, budget, settleWindow time.Duration) bool
+}
+
 // Guard manage the reconnection tries to the Relay server in case of disconnection event.
 type Guard struct {
 	// OnNewRelayClient is a channel that is used to notify the relay manager about a new relay client instance.
@@ -35,9 +40,8 @@ type Guard struct {
 	// attempts.
 	maxBackoffInterval time.Duration
 
-	// netState gates reconnect attempts on OS-reported network availability;
-	// nil disables gating.
-	netState *netstate.State
+	// netState gates reconnect attempts on OS-reported network availability.
+	netState NetworkWatcher
 
 	// lastErr is the error from the most recent failed reconnect attempt,
 	// surfaced as the home relay status while disconnected.
@@ -45,9 +49,8 @@ type Guard struct {
 }
 
 // NewGuard creates a new guard for the relay client. A non-positive
-// maxBackoffInterval falls back to defaultMaxBackoffInterval. A nil netState
-// disables network availability gating.
-func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *netstate.State) *Guard {
+// maxBackoffInterval falls back to defaultMaxBackoffInterval.
+func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState NetworkWatcher) *Guard {
 	if maxBackoffInterval <= 0 {
 		maxBackoffInterval = defaultMaxBackoffInterval
 	}
@@ -97,12 +100,14 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
 		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 g.netState != nil {
+				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)
@@ -129,13 +134,18 @@ func (g *Guard) tryToQuickReconnect(parentCtx context.Context, rc *Client) bool
 		return false
 	}
 
-	if ok := g.waitForNetwork(parentCtx); !ok {
-		return false
-	}
-
-	// Still offline after the budget: leave the retry to the ticker.
-	if !g.netState.IsOnline() {
-		return false
+	if g.netState != nil {
+		if ok := g.netState.WaitSettled(parentCtx, quickReconnectBudget, verdictSettleWindow); !ok {
+			return false
+		}
+		// Still offline after the budget: leave the retry to the ticker.
+		if !g.netState.IsOnline() {
+			return false
+		}
+	} else {
+		if cancelled := waiteBeforeRetry(parentCtx); !cancelled {
+			return false
+		}
 	}
 
 	log.Infof("try to reconnect to Relay server: %s", rc.connectionURL)
@@ -200,47 +210,14 @@ func (g *Guard) exponentTicker(ctx context.Context) *backoff.Ticker {
 	return backoff.NewTicker(bo)
 }
 
-// waitForNetwork waits out the settle window while online, or waits for the
-// network to return while offline, within the budget. Returns false when ctx
-// is cancelled. Without an injected netState it degrades to a fixed
-// budget-long sleep, the pre-netstate behavior.
-func (g *Guard) waitForNetwork(ctx context.Context) bool {
-	budget := time.NewTimer(quickReconnectBudget)
-	defer budget.Stop()
+func waiteBeforeRetry(ctx context.Context) bool {
+	timer := time.NewTimer(quickReconnectBudget)
+	defer timer.Stop()
 
-	settleWindow := verdictSettleWindow
-	if g.netState == nil {
-		settleWindow = quickReconnectBudget
-	}
-	settle := time.NewTimer(settleWindow)
-	defer settle.Stop()
-
-	for {
-		// Channel first, flag second: a flip in between still fires the channel.
-		changedCh := g.netState.Changed()
-		if g.netState.IsOnline() {
-			select {
-			case <-settle.C:
-				return true
-			case <-changedCh:
-			case <-ctx.Done():
-				return false
-			}
-		} else {
-			select {
-			case <-budget.C:
-				return true
-			case <-changedCh:
-			case <-ctx.Done():
-				return false
-			}
-		}
-		if !settle.Stop() {
-			select {
-			case <-settle.C:
-			default:
-			}
-		}
-		settle.Reset(settleWindow)
+	select {
+	case <-timer.C:
+		return true
+	case <-ctx.Done():
+		return false
 	}
 }

shared/relay/client/guard_test.go

@@ -1,30 +0,0 @@
-package client
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/netbirdio/netbird/client/netstate"
-)
-
-func TestWaitForNetworkSettlesAfterOutage(t *testing.T) {
-	ns := netstate.New()
-	ns.Set(false)
-	g := NewGuard(nil, 0, ns)
-
-	const outage = 2 * verdictSettleWindow
-	start := time.Now()
-	go func() {
-		time.Sleep(outage)
-		ns.Set(true)
-	}()
-
-	ok := g.waitForNetwork(context.Background())
-	elapsed := time.Since(start)
-
-	assert.True(t, ok, "recovered network must let the quick reconnect proceed")
-	assert.GreaterOrEqual(t, elapsed, outage+verdictSettleWindow, "reconnect must wait a full settle window after the network returns")
-}

shared/relay/client/manager.go

@@ -12,8 +12,6 @@ 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"
 )
 
@@ -67,15 +65,9 @@ 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 }
+// WithNetEvents injects the OS network event handling.
+func WithNetEvents(events NetEvents) ManagerOption {
+	return func(m *Manager) { m.netEvents = events }
 }
 
 // Manager is a manager for the relay client instances. It establishes one persistent connection to the given relay URL
@@ -105,8 +97,7 @@ type Manager struct {
 
 	mtu                uint16
 	maxBackoffInterval time.Duration
-	netState           *netstate.State
-	sweeper            *netsweep.Sweeper
+	netEvents          NetEvents
 
 	cleanupInterval      time.Duration
 	keepUnusedServerTime time.Duration
@@ -143,9 +134,9 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 	for _, opt := range opts {
 		opt(m)
 	}
-	m.serverPicker.Sweeper = m.sweeper
+	m.serverPicker.NetEvents = m.netEvents
 	m.serverPicker.ServerURLs.Store(serverURLs)
-	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netState)
+	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netEvents)
 	return m
 }
 
@@ -370,7 +361,7 @@ 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
+	relayClient.netEvents = m.netEvents
 	err := relayClient.Connect(m.ctx)
 	if err != nil {
 		rt.Lock()

shared/relay/client/picker.go

@@ -9,7 +9,6 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
-	"github.com/netbirdio/netbird/client/netsweep"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 )
 
@@ -31,7 +30,7 @@ type ServerPicker struct {
 	MTU               uint16
 	ConnectionTimeout time.Duration
 	TransportFallback *transportFallback
-	Sweeper           *netsweep.Sweeper
+	NetEvents         NetEvents
 }
 
 func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -75,7 +74,7 @@ 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
+	relayClient.netEvents = sp.NetEvents
 	err := relayClient.Connect(ctx)
 	resultChan <- connResult{
 		RelayClient: relayClient,

shared/signal/client/grpc.go

@@ -19,8 +19,7 @@ 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/client/netevents"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/signal/proto"
@@ -67,12 +66,9 @@ 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
+	// netEvents gates the Receive retry loop on OS-reported network
+	// availability and sweeps the transport on network change.
+	netEvents *netevents.Manager
 
 	onReconnectedListenerFn func()
 
@@ -100,15 +96,9 @@ type GrpcClient struct {
 // 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 }
+// WithNetEvents injects the OS network event handling.
+func WithNetEvents(events *netevents.Manager) Option {
+	return func(c *GrpcClient) { c.netEvents = events }
 }
 
 // NewClient creates a new Signal client
@@ -126,9 +116,7 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
 	}
 
 	var extraOpts []grpc.DialOption
-	if c.sweeper != nil {
-		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
-	}
+	extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.netEvents))
 
 	var conn *grpc.ClientConn
 	operation := func() error {
@@ -198,17 +186,20 @@ func defaultBackoff(ctx context.Context) backoff.BackOff {
 // The connection retry logic will try to reconnect for 30 min and if wasn't successful will propagate the error to the function caller.
 func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Message) error) error {
 
-	backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
+	backOff := c.netEvents.QuickRetryBackoff(ctx, 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 {
+		if waited, err := c.netEvents.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()
+			// dials attempted while offline grew the channel's internal backoff;
+			// reset it too, or the reconnect waits out that timer first
+			c.signalConn.ResetConnectBackoff()
 		}
 
 		c.notifyStreamDisconnected()
@@ -281,7 +272,7 @@ func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Mes
 		return nil
 	}
 
-	err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
+	err := nbgrpc.Retry(ctx, operation, backOff, c.netEvents)
 	if err != nil {
 		log.Errorf("exiting the Signal service connection retry loop due to the unrecoverable error: %v", err)
 		return err