[client] Sweep network-bound connections when the OS switches networks

On a network switch (e.g. cellular to WiFi) the management, signal and
relay sockets stay bound to the old network and look alive until the OS
tears them down — measured at 5 seconds of dead air on Android, while
the UI kept claiming Connected. The Android client papered over this
with a full engine restart, paying for it with a torn-down TUN device
and discarded peer state.

Introduce client/netsweep: connections register on dial and deregister
on close, and a sweep closes everything registered while aborting
in-flight dials through sweep-cancellable dial contexts. The aborted
dials matter: a relay dial started on the dying network would otherwise
hold the reconnect loop hostage for the QUIC handshake timeout. After a
sweep every failure surfaces as an ordinary read/write error and the
existing retry loops redial immediately on the new network.

The sweeper reaches the three long-lived connections through the same
options that carry the netstate gate: a gRPC dial option wraps the
management and signal transports (reconnects included), and the relay
client wraps its connection in one place for the picker, the guard and
foreign relays alike. Everything is nil-safe; platforms that inject no
sweeper are untouched.

Mobile clients expose the sweep as NotifyNetworkChange. Measured on
Android against the engine restart it replaces: recovery in 1.6s
instead of 3.2s, no Disconnected flash, and the TUN device, WireGuard
config and peer state survive.

client/android/client.go

@@ -25,6 +25,8 @@ 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"
@@ -32,11 +34,6 @@ import (
 	types "github.com/netbirdio/netbird/upload-server/types"
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // TunAdapter export internal TunAdapter for mobile
 type TunAdapter interface {
 	device.TunAdapter
@@ -77,6 +74,13 @@ 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
@@ -148,9 +152,28 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
 		recorder:              peer.NewRecorder(""),
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
+// 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)
+}
+
 // Run start the internal client. It is a blocker function
 func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroidTV bool, dns *DNSList, dnsReadyListener DnsReadyListener, envList *EnvList) error {
 	exportEnvList(envList)
@@ -188,7 +211,8 @@ 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
@@ -229,7 +253,8 @@ 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)
 }
@@ -513,7 +538,7 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	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/android/ssh_client.go

@@ -1,521 +0,0 @@
-//go:build android
-
-package android
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"io"
-	"net"
-	"strconv"
-	"strings"
-	"sync"
-	"time"
-
-	log "github.com/sirupsen/logrus"
-	gossh "golang.org/x/crypto/ssh"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/auth"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	nbssh "github.com/netbirdio/netbird/client/ssh"
-	"github.com/netbirdio/netbird/client/ssh/detection"
-)
-
-const (
-	sshDialTimeout      = 30 * time.Second
-	sshDetectionTimeout = 5 * time.Second
-)
-
-// PasswordRequiredMarker tells Java to prompt for a password and retry. It is
-// a string because gomobile flattens errors to their message, so a sentinel
-// value would not survive the binding.
-const PasswordRequiredMarker = "netbird-ssh-password-required"
-
-var errPasswordRequired = errors.New(PasswordRequiredMarker)
-
-// SSHTerminalListener receives SSH session events. It is implemented in Java.
-//
-// All callbacks are invoked from goroutines and may run concurrently with each
-// other; the implementation must be safe to call from any thread.
-type SSHTerminalListener interface {
-	OnConnected()
-	OnData(data []byte)
-	OnClose(reason string)
-	OnError(message string)
-}
-
-// SSHClient is a NetBird-aware SSH client exposed to Java via gomobile.
-//
-// It dials through the running NetBird tunnel and runs a standard SSH session
-// on top with PTY enabled. Host-key verification uses the NetBird-provided
-// peer SSH host keys, identical to the desktop client.
-type SSHClient struct {
-	nb        *Client
-	mu        sync.Mutex
-	listener  SSHTerminalListener
-	urlOpener URLOpener
-
-	sshClient *gossh.Client
-	session   *gossh.Session
-	stdin     io.WriteCloser
-	closed    bool
-}
-
-// NewSSHClient creates a new SSH client bound to the running NetBird Client.
-func NewSSHClient(c *Client) *SSHClient {
-	return &SSHClient{nb: c}
-}
-
-// SetListener registers the Java listener. Must be called before Connect to
-// receive any events.
-func (s *SSHClient) SetListener(l SSHTerminalListener) {
-	s.mu.Lock()
-	s.listener = l
-	s.mu.Unlock()
-}
-
-// SetURLOpener registers the Java URL opener used to display the device-code
-// authorization page in a Custom Tabs window when the target peer requires
-// JWT authentication. Must be set before Connect to be effective.
-func (s *SSHClient) SetURLOpener(opener URLOpener) {
-	s.mu.Lock()
-	s.urlOpener = opener
-	s.mu.Unlock()
-}
-
-// Connect dials the SSH server through the NetBird tunnel and performs the
-// SSH handshake. It auto-detects the server type via SSH banner inspection
-// and selects the appropriate authentication path:
-//
-//   - NetBird-SSH server requiring JWT: launches the OAuth 2.0 device-code
-//     flow, opens the verification URL through the registered URLOpener, and
-//     uses the resulting token as the SSH password. Host-key verification
-//     uses the NetBird peer registry.
-//   - NetBird-SSH server without JWT: authenticates with the NetBird SSH
-//     private key. Host-key verification uses the NetBird peer registry.
-//   - Regular SSH server (e.g. OpenSSH): authenticates with the NetBird key
-//     first (so a user-installed NetBird public key works), then falls back
-//     to the supplied password if non-empty. Host-key verification is
-//     disabled (TOFU pending).
-//
-// The password parameter is only consulted for regular SSH servers.
-func (s *SSHClient) Connect(host string, port int, user, password string) error {
-	cfg, _, cc := s.nb.stateSnapshot()
-	if cc == nil {
-		return errors.New("netbird client not running")
-	}
-	if cfg == nil {
-		return errors.New("netbird config not loaded")
-	}
-	engine := cc.Engine()
-	if engine == nil {
-		return errors.New("netbird engine not available")
-	}
-
-	serverType := detectServerType(host, port)
-	log.Infof("SSH server type for %s:%d: %s", host, port, serverType)
-
-	authMethods, hostKeyCallback, err := s.buildAuth(cfg, engine, serverType, password)
-	if err != nil {
-		return err
-	}
-
-	clientConfig := &gossh.ClientConfig{
-		User:            user,
-		Auth:            authMethods,
-		HostKeyCallback: hostKeyCallback,
-		Timeout:         sshDialTimeout,
-	}
-	err = s.dialAndHandshake(host, port, clientConfig)
-
-	// A regular server may still accept a password, so let the caller ask for
-	// one instead of failing. NetBird servers never use a password, so a
-	// failure there is genuine.
-	if err != nil && serverType != detection.ServerTypeNetBirdJWT &&
-		serverType != detection.ServerTypeNetBirdNoJWT && isAuthFailure(err) {
-		return errPasswordRequired
-	}
-	if err != nil {
-		log.Infof("SSH: connect to %s:%d failed: %v", host, port, err)
-		return rootCause(err)
-	}
-	return nil
-}
-
-// isAuthFailure distinguishes credential rejection from dial, timeout and
-// host-key errors, which retrying with a password would not fix.
-func isAuthFailure(err error) bool {
-	if errors.Is(err, errPasswordRequired) {
-		return true
-	}
-	var partial *gossh.PartialSuccessError
-	if errors.As(err, &partial) {
-		return true
-	}
-	return strings.Contains(err.Error(), "unable to authenticate")
-}
-
-// StartSession requests a PTY and starts an interactive shell. Output from
-// the session is forwarded to the listener via OnData.
-func (s *SSHClient) StartSession(cols, rows int) error {
-	err := s.startSession(cols, rows)
-	if err != nil {
-		log.Infof("SSH: start session failed: %v", err)
-		return rootCause(err)
-	}
-	return nil
-}
-
-func (s *SSHClient) startSession(cols, rows int) error {
-	log.Debugf("SSH: starting session %dx%d", cols, rows)
-	s.mu.Lock()
-	sshClient := s.sshClient
-	s.mu.Unlock()
-
-	if sshClient == nil {
-		return errors.New("ssh client not connected")
-	}
-
-	session, err := sshClient.NewSession()
-	if err != nil {
-		return fmt.Errorf("new session: %w", err)
-	}
-
-	modes := gossh.TerminalModes{
-		gossh.ECHO:          1,
-		gossh.TTY_OP_ISPEED: 14400,
-		gossh.TTY_OP_OSPEED: 14400,
-		gossh.VINTR:         3,
-		gossh.VQUIT:         28,
-		gossh.VERASE:        127,
-	}
-	if err := session.RequestPty("xterm-256color", rows, cols, modes); err != nil {
-		closeQuiet(session, "session after pty error")
-		return fmt.Errorf("request pty: %w", err)
-	}
-
-	stdin, err := session.StdinPipe()
-	if err != nil {
-		closeQuiet(session, "session after stdin error")
-		return fmt.Errorf("stdin pipe: %w", err)
-	}
-	stdout, err := session.StdoutPipe()
-	if err != nil {
-		closeQuiet(session, "session after stdout error")
-		return fmt.Errorf("stdout pipe: %w", err)
-	}
-	stderr, err := session.StderrPipe()
-	if err != nil {
-		closeQuiet(session, "session after stderr error")
-		return fmt.Errorf("stderr pipe: %w", err)
-	}
-
-	if err := session.Shell(); err != nil {
-		closeQuiet(session, "session after shell error")
-		return fmt.Errorf("start shell: %w", err)
-	}
-
-	s.mu.Lock()
-	s.session = session
-	s.stdin = stdin
-	s.mu.Unlock()
-
-	go s.readLoop(stdout, "stdout")
-	go s.readLoop(stderr, "stderr")
-	log.Debug("SSH: session started, shell running")
-	return nil
-}
-
-// Write sends data to the SSH session stdin.
-func (s *SSHClient) Write(data []byte) error {
-	s.mu.Lock()
-	stdin := s.stdin
-	s.mu.Unlock()
-	if stdin == nil {
-		return errors.New("ssh session not started")
-	}
-	if _, err := stdin.Write(data); err != nil {
-		return fmt.Errorf("write stdin: %w", err)
-	}
-	return nil
-}
-
-// Resize updates the PTY window size.
-func (s *SSHClient) Resize(cols, rows int) error {
-	s.mu.Lock()
-	session := s.session
-	s.mu.Unlock()
-	if session == nil {
-		return errors.New("ssh session not started")
-	}
-	return session.WindowChange(rows, cols)
-}
-
-// Close terminates the SSH session and underlying connection. Safe to call
-// multiple times.
-func (s *SSHClient) Close() error {
-	s.mu.Lock()
-	sshClient := s.sshClient
-	session := s.session
-	stdin := s.stdin
-	s.sshClient = nil
-	s.session = nil
-	s.stdin = nil
-	s.mu.Unlock()
-
-	if stdin != nil {
-		if err := stdin.Close(); err != nil {
-			log.Debugf("ssh: stdin close: %v", err)
-		}
-	}
-	if session != nil {
-		if err := session.Close(); err != nil && !errors.Is(err, io.EOF) {
-			log.Debugf("ssh: session close: %v", err)
-		}
-	}
-	var firstErr error
-	if sshClient != nil {
-		if err := sshClient.Close(); err != nil {
-			firstErr = err
-		}
-	}
-	s.notifyClose("closed by client")
-	return firstErr
-}
-
-func (s *SSHClient) buildAuth(cfg *profilemanager.Config, engine *internal.Engine,
-	serverType detection.ServerType, password string) ([]gossh.AuthMethod, gossh.HostKeyCallback, error) {
-
-	switch serverType {
-	case detection.ServerTypeNetBirdJWT:
-		token, err := s.requestJWTToken(cfg)
-		if err != nil {
-			return nil, nil, fmt.Errorf("jwt: %w", err)
-		}
-		auths := []gossh.AuthMethod{gossh.Password(token)}
-		return auths, nbssh.CreateHostKeyCallback(&engineHostKeyVerifier{engine: engine}), nil
-
-	case detection.ServerTypeNetBirdNoJWT:
-		if cfg.SSHKey == "" {
-			return nil, nil, errors.New("no NetBird SSH key available")
-		}
-		signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey))
-		if err != nil {
-			return nil, nil, fmt.Errorf("parse netbird ssh key: %w", err)
-		}
-		auths := []gossh.AuthMethod{gossh.PublicKeys(signer)}
-		return auths, nbssh.CreateHostKeyCallback(&engineHostKeyVerifier{engine: engine}), nil
-
-	default: // regular SSH
-		var auths []gossh.AuthMethod
-		if cfg.SSHKey != "" {
-			if signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey)); err == nil {
-				auths = append(auths, gossh.PublicKeys(signer))
-			} else {
-				log.Debugf("ssh: parse netbird key for regular auth: %v", err)
-			}
-		}
-		if password != "" {
-			pw := password
-			auths = append(auths, gossh.Password(pw))
-			auths = append(auths, gossh.KeyboardInteractive(func(_, _ string, questions []string, _ []bool) ([]string, error) {
-				answers := make([]string, len(questions))
-				for i := range questions {
-					answers[i] = pw
-				}
-				return answers, nil
-			}))
-		}
-		if len(auths) == 0 {
-			// Nothing to offer at all: ask for a password rather than failing,
-			// so the caller can retry once the user supplies one.
-			return nil, nil, errPasswordRequired
-		}
-		return auths, gossh.InsecureIgnoreHostKey(), nil // nolint:gosec // TOFU not yet implemented
-	}
-}
-
-func (s *SSHClient) requestJWTToken(cfg *profilemanager.Config) (string, error) {
-	s.mu.Lock()
-	urlOpener := s.urlOpener
-	s.mu.Unlock()
-	if urlOpener == nil {
-		return "", errors.New("URL opener not configured for JWT auth")
-	}
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
-	defer cancel()
-
-	flow, err := auth.NewOAuthFlow(ctx, cfg, false, true, profilemanager.GetLoginHint())
-	if err != nil {
-		return "", fmt.Errorf("create oauth flow: %w", err)
-	}
-
-	flowInfo, err := flow.RequestAuthInfo(ctx)
-	if err != nil {
-		return "", fmt.Errorf("request auth info: %w", err)
-	}
-
-	go urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode)
-
-	// WaitToken blocks for as long as the browser round-trip takes, so say so
-	// rather than leaving the terminal blank.
-	s.notifyStatus("Waiting for browser authentication...")
-
-	tokenInfo, err := flow.WaitToken(ctx, flowInfo)
-	if err != nil {
-		return "", fmt.Errorf("wait for token: %w", err)
-	}
-
-	token := tokenInfo.GetTokenToUse()
-	if token == "" {
-		return "", errors.New("empty token returned by IdP")
-	}
-	return token, nil
-}
-
-func (s *SSHClient) dialAndHandshake(host string, port int, clientConfig *gossh.ClientConfig) error {
-	addr := net.JoinHostPort(host, strconv.Itoa(port))
-	log.Infof("SSH: connecting to %s as %s", addr, clientConfig.User)
-
-	ctx, cancel := context.WithTimeout(context.Background(), sshDialTimeout)
-	defer cancel()
-
-	var dialer net.Dialer
-	conn, err := dialer.DialContext(ctx, "tcp", addr)
-	if err != nil {
-		return fmt.Errorf("dial %s: %w", addr, err)
-	}
-
-	sshConn, chans, reqs, err := gossh.NewClientConn(conn, addr, clientConfig)
-	if err != nil {
-		if cerr := conn.Close(); cerr != nil {
-			log.Debugf("ssh: close after handshake error: %v", cerr)
-		}
-		return fmt.Errorf("ssh handshake: %w", err)
-	}
-
-	s.mu.Lock()
-	s.sshClient = gossh.NewClient(sshConn, chans, reqs)
-	listener := s.listener
-	s.mu.Unlock()
-
-	log.Infof("SSH: connected to %s", addr)
-	if listener != nil {
-		listener.OnConnected()
-	}
-	return nil
-}
-
-func (s *SSHClient) readLoop(r io.Reader, name string) {
-	buf := make([]byte, 4096)
-	for {
-		n, err := r.Read(buf)
-		if n > 0 {
-			s.mu.Lock()
-			listener := s.listener
-			s.mu.Unlock()
-			if listener != nil {
-				chunk := make([]byte, n)
-				copy(chunk, buf[:n])
-				listener.OnData(chunk)
-			}
-		}
-		if err != nil {
-			// EOF is a normal shell exit, so report it without a reason.
-			if errors.Is(err, io.EOF) {
-				s.notifyClose("")
-				return
-			}
-			log.Debugf("ssh %s read: %v", name, err)
-			s.notifyClose(rootCause(err).Error())
-			return
-		}
-	}
-}
-
-// rootCause returns the innermost error of a %w chain, so the terminal shows
-// "i/o timeout" rather than every layer that added context on the way up.
-func rootCause(err error) error {
-	for {
-		// A joined error has no single root, so keep it as-is.
-		if _, ok := err.(interface{ Unwrap() []error }); ok {
-			return err
-		}
-		next := errors.Unwrap(err)
-		if next == nil {
-			return err
-		}
-		err = next
-	}
-}
-
-// Reset makes a closed client usable for another Connect: Close leaves the
-// one-shot guard set, and clearing it lets the same client back a reconnect.
-func (s *SSHClient) Reset() {
-	s.mu.Lock()
-	defer s.mu.Unlock()
-	s.closed = false
-}
-
-// notifyStatus writes a progress line to the terminal through the normal
-// output path, so long steps are visible while nothing else is arriving.
-func (s *SSHClient) notifyStatus(text string) {
-	s.mu.Lock()
-	listener := s.listener
-	s.mu.Unlock()
-	if listener != nil {
-		listener.OnData([]byte("\r\n\x1b[33m" + text + "\x1b[0m\r\n"))
-	}
-}
-
-func (s *SSHClient) notifyClose(reason string) {
-	s.mu.Lock()
-	if s.closed {
-		s.mu.Unlock()
-		return
-	}
-	s.closed = true
-	listener := s.listener
-	s.mu.Unlock()
-	if listener != nil {
-		listener.OnClose(reason)
-	}
-}
-
-// engineHostKeyVerifier adapts *internal.Engine to nbssh.HostKeyVerifier.
-type engineHostKeyVerifier struct {
-	engine *internal.Engine
-}
-
-func (v *engineHostKeyVerifier) VerifySSHHostKey(peerAddress string, presented []byte) error {
-	storedKey, found := v.engine.GetPeerSSHKey(peerAddress)
-	if !found {
-		return nbssh.ErrPeerNotFound
-	}
-	return nbssh.VerifyHostKey(storedKey, presented, peerAddress)
-}
-
-func closeQuiet(c io.Closer, label string) {
-	if c == nil {
-		return
-	}
-	if err := c.Close(); err != nil && !errors.Is(err, io.EOF) {
-		log.Debugf("ssh: close %s: %v", label, err)
-	}
-}
-
-func detectServerType(host string, port int) detection.ServerType {
-	ctx, cancel := context.WithTimeout(context.Background(), sshDetectionTimeout)
-	defer cancel()
-
-	dialer := &net.Dialer{}
-	serverType, err := detection.DetectSSHServerType(ctx, dialer, host, port)
-	if err != nil {
-		log.Debugf("ssh: server detection for %s:%d failed: %v (assuming regular SSH)", host, port, err)
-		return detection.ServerTypeRegular
-	}
-	return serverType
-}

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)
-			}
+		ctx, releaseDial := sweeper.WrapDialContext(ctx)
+		defer releaseDial()
 
-			// 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(ctx, addr)
 		if err != nil {
-			return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+			return nil, err
 		}
-		return conn, nil
+		return sweeper.WrapConn(conn), nil
 	})
 }
+
+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

@@ -58,6 +58,7 @@ 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"
@@ -180,6 +181,9 @@ 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.
@@ -203,6 +207,10 @@ 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
@@ -336,6 +344,7 @@ func NewEngine(
 		syncMsgMux:         &sync.Mutex{},
 		config:             config,
 		mobileDep:          mobileDep,
+		netState:           services.NetState,
 		STUNs:              []*stun.URI{},
 		TURNs:              []*stun.URI{},
 		networkSerial:      0,
@@ -1891,7 +1900,8 @@ 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),
 	}
@@ -99,6 +107,12 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	for {
 		select {
 		case <-tickerChannel:
+			// skip attempts while the OS reports no usable network; the ticker
+			// keeps running so other events remain responsive, and the guard
+			// resumes via the signal/relay reconnect events once network returns
+			if !g.netState.IsOnline() {
+				continue
+			}
 			switch g.isConnectedOnAllWay() {
 			case ConnStatusConnected:
 				// all good, nothing to do

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/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 +4,57 @@ import (
 	"sync"
 )
 
-const (
-	stateDisconnected = iota
-	stateConnected
-	stateConnecting
-	stateDisconnecting
-)
-
 type notifier struct {
 	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.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
@@ -61,43 +87,45 @@ 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.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.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.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 +137,20 @@ 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 +187,19 @@ 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_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

@@ -21,6 +21,8 @@ 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"
@@ -28,11 +30,6 @@ import (
 	types "github.com/netbirdio/netbird/upload-server/types"
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // RouteListener export internal RouteListener for mobile
 type NetworkChangeListener interface {
 	listener.NetworkChangeListener
@@ -79,6 +76,12 @@ 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
 
@@ -101,6 +104,8 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
 		dnsManager:            dnsManager,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
@@ -176,7 +181,8 @@ 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
@@ -185,6 +191,24 @@ 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()
@@ -320,7 +344,7 @@ func (c *Client) GetStatusDetails() *StatusDetails {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	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 +1,93 @@
+// 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
+}
+
+// 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 +1,119 @@
+// 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"
+	"net"
+	"sync"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// sweptConn deregisters itself from the sweeper when closed.
+type sweptConn struct {
+	net.Conn
+	sweeper *Sweeper
+	id      uint64
+}
+
+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[uint64]net.Conn
+	dials  map[uint64]context.CancelFunc
+	nextID uint64
+}
+
+// New creates an empty sweeper.
+func New() *Sweeper {
+	return &Sweeper{
+		conns: make(map[uint64]net.Conn),
+		dials: make(map[uint64]context.CancelFunc),
+	}
+}
+
+// WrapConn registers conn and returns a wrapper that deregisters it on Close.
+func (s *Sweeper) WrapConn(conn net.Conn) net.Conn {
+	if s == nil {
+		return conn
+	}
+
+	s.mu.Lock()
+	id := s.nextID
+	s.nextID++
+	s.conns[id] = conn
+	s.mu.Unlock()
+
+	return &sweptConn{Conn: conn, sweeper: s, id: id}
+}
+
+// WrapDialContext derives a context that Sweep cancels. The returned release
+// must be called when the dial finishes, typically deferred.
+func (s *Sweeper) WrapDialContext(ctx context.Context) (context.Context, context.CancelFunc) {
+	if s == nil {
+		return ctx, func() {}
+	}
+
+	ctx, cancel := context.WithCancel(ctx)
+
+	s.mu.Lock()
+	id := s.nextID
+	s.nextID++
+	s.dials[id] = cancel
+	s.mu.Unlock()
+
+	release := func() {
+		s.mu.Lock()
+		delete(s.dials, id)
+		s.mu.Unlock()
+		cancel()
+	}
+	return ctx, release
+}
+
+// Sweep closes every registered connection, aborts every in-flight dial, and
+// returns how many connections it closed.
+func (s *Sweeper) Sweep() int {
+	if s == nil {
+		return 0
+	}
+
+	s.mu.Lock()
+	conns := s.conns
+	dials := s.dials
+	s.conns = make(map[uint64]net.Conn)
+	s.dials = make(map[uint64]context.CancelFunc)
+	s.mu.Unlock()
+
+	if len(dials) > 0 {
+		log.Debugf("aborting %d in-flight dials", len(dials))
+		for _, cancel := range dials {
+			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 uint64) {
+	s.mu.Lock()
+	delete(s.conns, id)
+	s.mu.Unlock()
+}

client/netsweep/netsweep_test.go

@@ -0,0 +1,119 @@
+package netsweep
+
+import (
+	"context"
+	"net"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestSweepClosesRegisteredConns(t *testing.T) {
+	sweeper := New()
+
+	c1 := sweeper.WrapConn(connPair(t))
+	c2 := sweeper.WrapConn(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 := sweeper.WrapConn(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 := sweeper.WrapConn(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()
+
+	_ = sweeper.WrapConn(connPair(t))
+	assert.Equal(t, 1, sweeper.Sweep())
+
+	// A connection dialed after the sweep must survive until the next one.
+	_ = sweeper.WrapConn(connPair(t))
+	assert.Equal(t, 1, sweeper.Sweep(), "post-sweep connection belongs to the next sweep")
+}
+
+func TestSweepAbortsInFlightDials(t *testing.T) {
+	sweeper := New()
+
+	dialCtx, release := sweeper.WrapDialContext(context.Background())
+	defer release()
+
+	sweeper.Sweep()
+
+	assert.ErrorIs(t, dialCtx.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.
+	_, release := sweeper.WrapDialContext(context.Background())
+	release()
+
+	// A dial still in flight during the sweep.
+	pendingCtx, pendingRelease := sweeper.WrapDialContext(context.Background())
+	defer pendingRelease()
+
+	sweeper.Sweep()
+	assert.ErrorIs(t, pendingCtx.Err(), context.Canceled, "pending dial must be aborted")
+}
+
+func TestNilSweeperIsNoop(t *testing.T) {
+	var sweeper *Sweeper
+
+	conn := connPair(t)
+	assert.Equal(t, conn, sweeper.WrapConn(conn), "nil sweeper must return the conn unchanged")
+	assert.Equal(t, 0, sweeper.Sweep(), "nil sweeper closes nothing")
+
+	ctx, release := sweeper.WrapDialContext(context.Background())
+	release()
+	assert.NoError(t, ctx.Err(), "nil sweeper must not cancel the dial context")
+}
+
+// connPair dials a loopback TCP connection against a throwaway listener.
+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)
+		}
+	})
+
+	go func() {
+		conn, err := l.Accept()
+		if err != nil {
+			return
+		}
+		_ = conn.Close()
+	}()
+
+	conn, err := net.Dial("tcp", l.Addr().String())
+	require.NoError(t, err)
+	return conn
+}

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
 }
 
+// ClientOption configures optional GrpcClient behavior.
+type ClientOption 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) ClientOption {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ClientOption {
+	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 ...ClientOption) (*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
+		} 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 +398,11 @@ 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.
+	ctx, releaseDial := c.sweeper.WrapDialContext(ctx)
+	defer releaseDial()
+
 	mode := transportModeFromEnv()
 	dialers := c.getDialers(mode)
 
@@ -417,6 +427,7 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
 			return nil, fmt.Errorf("dial via FQDN: %w", err)
 		}
 	}
+	conn = c.sweeper.WrapConn(conn)
 	c.relayConn = conn
 	c.datagramFallbackTriggered.Store(false)
 	if tc, ok := conn.(transportConn); ok {

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
+// ClientOption configures optional GrpcClient behavior.
+type ClientOption 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) ClientOption {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ClientOption {
+	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 ...ClientOption) (*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()