address review feedback on cache and session store

Split the memory and Redis cache implementations into separate files and
provide backend-native atomic set-if-absent support.

client/android/client.go

@@ -25,8 +25,6 @@ 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"
@@ -34,6 +32,11 @@ 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
@@ -74,13 +77,6 @@ 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
@@ -152,28 +148,9 @@ 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)
@@ -211,8 +188,7 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	}
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
-		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
 	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
@@ -253,8 +229,7 @@ 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))
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
@@ -538,7 +513,7 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
+	c.recorder.SetConnectionListener(listener)
 }
 
 // RemoveConnectionListener remove connection listener

client/android/connection_listener.go

@@ -1,41 +0,0 @@
-//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/firewall/firewalld/firewalld.go

@@ -2,8 +2,8 @@
 // its wg interface into firewalld's "trusted" zone. This is required because
 // firewalld's nftables chains are created with NFT_CHAIN_OWNER on recent
 // versions, which returns EPERM to any other process that tries to insert
-// rules into them. Trusting the interface makes firewalld itself add the
-// accept rules to its own chains instead.
+// rules into them. The workaround mirrors what Tailscale does: let firewalld
+// itself add the accept rules to its own chains by trusting the interface.
 package firewalld
 
 // TrustedZone is the firewalld zone name used for interfaces whose traffic

client/grpc/dialer_generic.go

@@ -16,47 +16,28 @@ 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) {
-		dial := sweeper.StartDial(ctx)
-		defer dial.Release()
+		if runtime.GOOS == "linux" {
+			currentUser, err := user.Current()
+			if err != nil {
+				return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
+			}
 
-		conn, err := dialContext(dial.Ctx(), addr)
-		if err != nil {
-			return nil, 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)
+			}
 		}
-		return dial.WrapConn(conn)
+
+		conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+		if err != nil {
+			return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+		}
+		return 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

@@ -3,7 +3,6 @@ package grpc
 import (
 	"google.golang.org/grpc"
 
-	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/util/wsproxy/client"
 )
 
@@ -12,8 +11,3 @@ 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

@@ -38,8 +38,6 @@ 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"
@@ -72,42 +70,18 @@ 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)
-	c := &ConnectClient{
+	return &ConnectClient{
 		ctx:            runCtx,
 		runCancel:      runCancel,
 		runExited:      make(chan struct{}),
@@ -115,10 +89,6 @@ func NewConnectClient(
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
 	}
-	for _, opt := range opts {
-		opt(c)
-	}
-	return c
 }
 
 func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -304,13 +274,6 @@ 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)
@@ -322,8 +285,7 @@ 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))
+		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
 		if err != nil {
 			// On daemon shutdown / Down() the parent context is cancelled
 			// and the dial fails with "context canceled". Wrapping that
@@ -398,7 +360,7 @@ 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)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -434,8 +396,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			engineConfig.StateDir = filepath.Dir(path)
 		}
 
-		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
-			relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
+		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
 		c.statusRecorder.SetRelayMgr(relayManager)
 		if len(relayURLs) > 0 {
 			if token != nil {
@@ -463,7 +424,6 @@ 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
@@ -520,16 +480,6 @@ 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)
@@ -723,7 +673,7 @@ 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) (*signal.GrpcClient, error) {
 	var sigTLSEnabled bool
 	if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
 		sigTLSEnabled = true
@@ -731,8 +681,7 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 		sigTLSEnabled = false
 	}
 
-	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
-		signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
+	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
 	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

@@ -58,7 +58,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/syncstore"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/jobexec"
-	"github.com/netbirdio/netbird/client/netstate"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -181,9 +180,6 @@ 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.
@@ -207,10 +203,6 @@ 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
@@ -344,7 +336,6 @@ func NewEngine(
 		syncMsgMux:         &sync.Mutex{},
 		config:             config,
 		mobileDep:          mobileDep,
-		netState:           services.NetState,
 		STUNs:              []*stun.URI{},
 		TURNs:              []*stun.URI{},
 		networkSerial:      0,
@@ -1900,8 +1891,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 			Addr:           e.getRosenpassAddr(),
 			PermissiveMode: e.config.RosenpassPermissive,
 		},
-		ICEConfig:    e.createICEConfig(),
-		NetworkState: e.netState,
+		ICEConfig: e.createICEConfig(),
 	}
 
 	serviceDependencies := peer.ServiceDependencies{

client/internal/peer/conn.go

@@ -26,7 +26,6 @@ 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"
 )
@@ -94,10 +93,6 @@ 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 {
@@ -259,7 +254,7 @@ 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.config.NetworkState)
+	conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
 
 	conn.wg.Add(1)
 	go func() {

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.
@@ -33,26 +31,20 @@ type connStatusFunc func() ConnStatus
 // - Relayed connection disconnected
 // - ICE candidate changes
 type Guard struct {
-	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
+	log                     *log.Entry
+	isConnectedOnAllWay     connStatusFunc
+	timeout                 time.Duration
+	srWatcher               *SRWatcher
 	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) *Guard {
 	return &Guard{
 		log:                     log,
 		isConnectedOnAllWay:     isConnectedFn,
 		timeout:                 timeout,
 		srWatcher:               srWatcher,
-		netState:                netState,
 		relayedConnDisconnected: make(chan struct{}, 1),
 		iCEConnDisconnected:     make(chan struct{}, 1),
 	}
@@ -107,12 +99,6 @@ 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, nil)
+	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
 }
 
 // countBackoffTickerGoroutines returns how many goroutines are currently sitting

client/internal/peer/listener.go

@@ -1,40 +1,11 @@
 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

@@ -4,57 +4,31 @@ import (
 	"sync"
 )
 
+const (
+	stateDisconnected = iota
+	stateConnected
+	stateConnecting
+	stateDisconnecting
+)
+
 type notifier struct {
 	serverStateLock    sync.Mutex
 	listenersLock      sync.Mutex
 	listener           Listener
 	currentClientState bool
-	lastNotification   ClientState
+	lastNotification   int
 	lastNumberOfPeers  int
 	lastFqdnAddress    string
 	lastIPAddress      string
-	networkAvailable   bool
 }
 
 func newNotifier() *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)
-	}
+	return &notifier{}
 }
 
 func (n *notifier) setListener(listener Listener) {
 	n.serverStateLock.Lock()
-	lastNotification := n.effectiveState(n.lastNotification)
+	lastNotification := n.lastNotification
 	numOfPeers := n.lastNumberOfPeers
 	fqdnAddress := n.lastFqdnAddress
 	address := n.lastIPAddress
@@ -87,45 +61,43 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
 	}
 
 	n.lastNotification = calculatedState
-	effective := n.effectiveState(calculatedState)
 	n.serverStateLock.Unlock()
 
-	n.notify(effective)
+	n.notify(calculatedState)
 }
 
 func (n *notifier) clientStart() {
 	n.serverStateLock.Lock()
 	n.currentClientState = true
-	n.lastNotification = ClientStateConnecting
-	effective := n.effectiveState(ClientStateConnecting)
+	n.lastNotification = stateConnecting
 	n.serverStateLock.Unlock()
 
-	n.notify(effective)
+	n.notify(stateConnecting)
 }
 
 func (n *notifier) clientStop() {
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = ClientStateDisconnected
+	n.lastNotification = stateDisconnected
 	n.serverStateLock.Unlock()
 
-	n.notify(ClientStateDisconnected)
+	n.notify(stateDisconnected)
 }
 
 func (n *notifier) clientTearDown() {
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = ClientStateDisconnecting
+	n.lastNotification = stateDisconnecting
 	n.serverStateLock.Unlock()
 
-	n.notify(ClientStateDisconnecting)
+	n.notify(stateDisconnecting)
 }
 
-func (n *notifier) isServerStateChanged(newState ClientState) bool {
+func (n *notifier) isServerStateChanged(newState int) bool {
 	return n.lastNotification != newState
 }
 
-func (n *notifier) notify(state ClientState) {
+func (n *notifier) notify(state int) {
 	n.listenersLock.Lock()
 	listener := n.listener
 	n.listenersLock.Unlock()
@@ -137,20 +109,20 @@ func (n *notifier) notify(state ClientState) {
 	notifyListener(listener, state)
 }
 
-func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
+func (n *notifier) calculateState(managementConn, signalConn bool) int {
 	if managementConn && signalConn {
-		return ClientStateConnected
+		return stateConnected
 	}
 
 	if !managementConn && !signalConn && !n.currentClientState {
-		return ClientStateDisconnected
+		return stateDisconnected
 	}
 
-	if n.lastNotification == ClientStateDisconnecting {
-		return ClientStateDisconnecting
+	if n.lastNotification == stateDisconnecting {
+		return stateDisconnecting
 	}
 
-	return ClientStateConnecting
+	return stateConnecting
 }
 
 func (n *notifier) peerListChanged(numOfPeers int) {
@@ -187,19 +159,15 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
 	listener.OnAddressChanged(fqdn, address)
 }
 
-func notifyListener(l Listener, state ClientState) {
-	// legacy per-state callbacks; NoNetwork is delivered only via
-	// OnStateChanged below
+func notifyListener(l Listener, state int) {
 	switch state {
-	case ClientStateDisconnected:
+	case stateDisconnected:
 		l.OnDisconnected()
-	case ClientStateConnected:
+	case stateConnected:
 		l.OnConnected()
-	case ClientStateConnecting:
+	case stateConnecting:
 		l.OnConnecting()
-	case ClientStateDisconnecting:
+	case stateDisconnecting:
 		l.OnDisconnecting()
 	}
-
-	l.OnStateChanged(state)
 }

client/internal/peer/notifier_test.go

@@ -6,32 +6,29 @@ import (
 )
 
 type mocListener struct {
-	lastState ClientState
+	lastState int
 	wg        sync.WaitGroup
 	peersWg   sync.WaitGroup
 	peers     int
 }
 
 func (l *mocListener) OnConnected() {
-	l.lastState = ClientStateConnected
+	l.lastState = stateConnected
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnected() {
-	l.lastState = ClientStateDisconnected
+	l.lastState = stateDisconnected
 	l.wg.Done()
 }
 func (l *mocListener) OnConnecting() {
-	l.lastState = ClientStateConnecting
+	l.lastState = stateConnecting
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnecting() {
-	l.lastState = ClientStateDisconnecting
+	l.lastState = stateDisconnecting
 	l.wg.Done()
 }
 
-func (l *mocListener) OnStateChanged(state ClientState) {
-
-}
 func (l *mocListener) OnAddressChanged(host, addr string) {
 
 }
@@ -60,15 +57,15 @@ func Test_notifier_serverState(t *testing.T) {
 
 	type scenario struct {
 		name        string
-		expected    ClientState
+		expected    int
 		mgmState    bool
 		signalState bool
 	}
 	scenarios := []scenario{
-		{"connected", ClientStateConnected, true, true},
-		{"mgm down", ClientStateConnecting, false, true},
-		{"signal down", ClientStateConnecting, true, false},
-		{"disconnected", ClientStateDisconnected, false, false},
+		{"connected", stateConnected, true, true},
+		{"mgm down", stateConnecting, false, true},
+		{"signal down", stateConnecting, true, false},
+		{"disconnected", stateDisconnected, false, false},
 	}
 
 	for _, tt := range scenarios {
@@ -88,7 +85,7 @@ func Test_notifier_SetListener(t *testing.T) {
 	listener.setPeersWaiter()
 
 	n := newNotifier()
-	n.lastNotification = ClientStateConnecting
+	n.lastNotification = stateConnecting
 	n.setListener(listener)
 	listener.wait()
 	listener.waitPeers()
@@ -102,7 +99,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
 	listener.setWaiter()
 	listener.setPeersWaiter()
 	n := newNotifier()
-	n.lastNotification = ClientStateConnecting
+	n.lastNotification = stateConnecting
 	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

@@ -1211,12 +1211,6 @@ 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

@@ -21,8 +21,6 @@ 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"
@@ -30,6 +28,11 @@ 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
@@ -76,12 +79,6 @@ 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
 
@@ -104,8 +101,6 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
 		dnsManager:            dnsManager,
-		netState:              netstate.New(),
-		sweeper:               netsweep.New(),
 	}
 }
 
@@ -181,8 +176,7 @@ 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,
-		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
 	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
@@ -191,24 +185,6 @@ 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()
@@ -344,7 +320,7 @@ func (c *Client) GetStatusDetails() *StatusDetails {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
+	c.recorder.SetConnectionListener(listener)
 }
 
 // RemoveConnectionListener remove connection listener

client/ios/NetBirdSDK/connection_listener.go

@@ -1,43 +0,0 @@
-//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

@@ -1,93 +0,0 @@
-// 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

@@ -1,170 +0,0 @@
-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

@@ -1,171 +0,0 @@
-// Package netsweep cuts network-bound activity when the OS switches networks:
-// a sweep closes the registered connections and aborts the in-flight dials, so
-// their owners redial immediately instead of waiting for the old sockets to
-// time out.
-//
-// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
-package netsweep
-
-import (
-	"context"
-	"errors"
-	"net"
-	"sync"
-
-	log "github.com/sirupsen/logrus"
-)
-
-// ErrSwept reports that a dial finished after a network change swept its
-// registration. The connection is already closed; the caller must treat it
-// as a failed dial and redial on the new network.
-var ErrSwept = errors.New("netsweep: connection swept by network change")
-
-// 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]*Dial
-	nextID uint64
-}
-
-// New creates an empty sweeper.
-func New() *Sweeper {
-	return &Sweeper{
-		conns: make(map[uint64]net.Conn),
-		dials: make(map[uint64]*Dial),
-	}
-}
-
-// Dial tracks one dial from start to connection registration. It hands the
-// dialed connection to the sweeper atomically, so a sweep can never fall
-// between the dial finishing and the connection being registered.
-type Dial struct {
-	sweeper *Sweeper
-	ctx     context.Context
-	cancel  context.CancelFunc
-	id      uint64
-	done    bool // set by Sweep, WrapConn or Release; guarded by sweeper.mu
-}
-
-// StartDial registers an in-flight dial. Dial with Ctx, hand the result to
-// WrapConn, and Release the dial when the attempt is over, typically deferred.
-func (s *Sweeper) StartDial(ctx context.Context) *Dial {
-	if s == nil {
-		return &Dial{ctx: ctx}
-	}
-
-	ctx, cancel := context.WithCancel(ctx)
-	d := &Dial{sweeper: s, ctx: ctx, cancel: cancel}
-
-	s.mu.Lock()
-	d.id = s.nextID
-	s.nextID++
-	s.dials[d.id] = d
-	s.mu.Unlock()
-
-	return d
-}
-
-// Ctx returns the dial's context. Sweep cancels it, so a dial started on the
-// old network aborts instead of waiting out its handshake timeout.
-func (d *Dial) Ctx() context.Context {
-	return d.ctx
-}
-
-// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial,
-// the connection belongs to the old network: it is closed and ErrSwept is
-// returned. Otherwise conn is registered against the next sweep and returned
-// wrapped, deregistering itself on Close. Call it once, before Release.
-func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) {
-	s := d.sweeper
-	if s == nil {
-		return conn, nil
-	}
-
-	s.mu.Lock()
-	if d.done {
-		s.mu.Unlock()
-		if err := conn.Close(); err != nil {
-			log.Debugf("swept dial close error: %v", err)
-		}
-		return nil, ErrSwept
-	}
-	d.done = true
-	delete(s.dials, d.id)
-	id := s.nextID
-	s.nextID++
-	s.conns[id] = conn
-	s.mu.Unlock()
-
-	return &sweptConn{Conn: conn, sweeper: s, id: id}, nil
-}
-
-// Release ends the dial's registration and cancels its context. It is
-// idempotent and safe after WrapConn, so callers can defer it.
-func (d *Dial) Release() {
-	s := d.sweeper
-	if s == nil {
-		return
-	}
-
-	s.mu.Lock()
-	d.done = true
-	delete(s.dials, d.id)
-	s.mu.Unlock()
-
-	d.cancel()
-}
-
-// Sweep closes every registered connection, aborts every in-flight dial, and
-// returns how many connections it closed. A dial whose connection was not
-// yet handed to WrapConn is marked, so the late WrapConn closes it instead
-// of registering it.
-func (s *Sweeper) Sweep() int {
-	if s == nil {
-		return 0
-	}
-
-	s.mu.Lock()
-	conns := s.conns
-	dials := s.dials
-	s.conns = make(map[uint64]net.Conn)
-	s.dials = make(map[uint64]*Dial)
-	for _, d := range dials {
-		d.done = true
-	}
-	s.mu.Unlock()
-
-	if len(dials) > 0 {
-		log.Debugf("aborting %d in-flight dials", len(dials))
-		for _, d := range dials {
-			d.cancel()
-		}
-	}
-
-	for _, conn := range conns {
-		log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr())
-		if err := conn.Close(); err != nil {
-			log.Debugf("swept connection close error: %v", err)
-		}
-	}
-	return len(conns)
-}
-
-func (s *Sweeper) deregister(id uint64) {
-	s.mu.Lock()
-	delete(s.conns, id)
-	s.mu.Unlock()
-}

client/netsweep/netsweep_test.go

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

go.mod

@@ -340,4 +340,4 @@ replace github.com/dexidp/dex/api/v2 => github.com/netbirdio/dex/api/v2 v2.0.0-2
 
 replace github.com/mailru/easyjson => github.com/netbirdio/easyjson v0.9.0
 
-replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701
+replace github.com/wailsapp/wails/v3 => github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4

go.sum

@@ -490,8 +490,8 @@ github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502 h1:3tHlFmhTdX9ax
 github.com/netbirdio/service v0.0.0-20240911161631-f62744f42502/go.mod h1:CIMRFEJVL+0DS1a3Nx06NaMn4Dz63Ng6O7dl0qH0zVM=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45 h1:ujgviVYmx243Ksy7NdSwrdGPSRNE3pb8kEDSpH0QuAQ=
 github.com/netbirdio/signal-dispatcher/dispatcher v0.0.0-20250805121659-6b4ac470ca45/go.mod h1:5/sjFmLb8O96B5737VCqhHyGRzNFIaN/Bu7ZodXc3qQ=
-github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701 h1:QL9nupfRom0L9jcY7N9l/Bc6QK2PtC6pHzC+ftpTqpw=
-github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260807055527-fc03f984d701/go.mod h1:BzATbK71VFikMMMCo434wAi0QcaI03P+xeaWgDvQvjw=
+github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4 h1:UKztc3QjWvzU5DZk+uYaOWN0x62NSe/pkxuPvzqZIy4=
+github.com/netbirdio/wails/v3 v3.0.0-beta.3.0.20260803205919-ad21e92381f4/go.mod h1:BzATbK71VFikMMMCo434wAi0QcaI03P+xeaWgDvQvjw=
 github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a h1:3CWK+yTvRKOcC0Q8VCTGy4l60TEb27CQVS7LkMxwjmw=
 github.com/netbirdio/wireguard-go v0.0.0-20260628102922-2834bebf6c1a/go.mod h1:rpwXGsirqLqN2L0JDJQlwOboGHmptD5ZD6T2VmcqhTw=
 github.com/nxadm/tail v1.4.4/go.mod h1:kenIhsEOeOJmVchQTgglprH7qJGnHDVpk1VPCcaMI8A=

management/internals/modules/reverseproxy/service/manager/manager_test.go

@@ -7,7 +7,6 @@ import (
 	"testing"
 	"time"
 
-	cachestore "github.com/eko/gocache/lib/v4/store"
 	"github.com/golang/mock/gomock"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -31,7 +30,7 @@ import (
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
-func testCacheStore(t *testing.T) cachestore.StoreInterface {
+func testCacheStore(t *testing.T) nbcache.Store {
 	t.Helper()
 	s, err := nbcache.NewStore(context.Background(), 30*time.Minute, 10*time.Minute, 100)
 	require.NoError(t, err)
@@ -295,6 +294,7 @@ func TestPersistNewService(t *testing.T) {
 		assert.Equal(t, status.AlreadyExists, sErr.Type())
 	})
 }
+
 func TestPreserveExistingAuthSecrets(t *testing.T) {
 	mgr := &Manager{}
 

management/internals/server/boot.go

@@ -20,8 +20,6 @@ import (
 	"google.golang.org/grpc/credentials"
 	"google.golang.org/grpc/keepalive"
 
-	cachestore "github.com/eko/gocache/lib/v4/store"
-
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/formatter/hook"
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
@@ -70,8 +68,8 @@ func (s *BaseServer) Metrics() telemetry.AppMetrics {
 
 // CacheStore returns a shared cache store backed by Redis or in-memory depending on the environment.
 // All consumers should reuse this store to avoid creating multiple Redis connections.
-func (s *BaseServer) CacheStore() cachestore.StoreInterface {
-	return Create(s, func() cachestore.StoreInterface {
+func (s *BaseServer) CacheStore() nbcache.Store {
+	return Create(s, func() nbcache.Store {
 		cs, err := nbcache.NewStore(context.Background(), nbcache.DefaultStoreMaxTimeout, nbcache.DefaultStoreCleanupInterval, nbcache.DefaultStoreMaxConn)
 		if err != nil {
 			log.Fatalf("failed to create shared cache store: %v", err)

management/internals/shared/grpc/pkce_verifier.go

@@ -5,22 +5,23 @@ import (
 	"fmt"
 	"time"
 
-	"github.com/eko/gocache/lib/v4/cache"
 	"github.com/eko/gocache/lib/v4/store"
 	log "github.com/sirupsen/logrus"
+
+	nbcache "github.com/netbirdio/netbird/management/server/cache"
 )
 
 // PKCEVerifierStore manages PKCE verifiers for OAuth flows.
 // Supports both in-memory and Redis storage via NB_IDP_CACHE_REDIS_ADDRESS env var.
 type PKCEVerifierStore struct {
-	cache *cache.Cache[string]
+	cache nbcache.Store
 	ctx   context.Context
 }
 
 // NewPKCEVerifierStore creates a PKCE verifier store using the provided shared cache store.
-func NewPKCEVerifierStore(ctx context.Context, cacheStore store.StoreInterface) *PKCEVerifierStore {
+func NewPKCEVerifierStore(ctx context.Context, cacheStore nbcache.Store) *PKCEVerifierStore {
 	return &PKCEVerifierStore{
-		cache: cache.New[string](cacheStore),
+		cache: cacheStore,
 		ctx:   ctx,
 	}
 }
@@ -40,14 +41,14 @@ func (s *PKCEVerifierStore) Store(state, verifier string, ttl time.Duration) err
 // Returns the verifier and true if found, or empty string and false if not found.
 // This enforces single-use semantics for PKCE verifiers.
 func (s *PKCEVerifierStore) LoadAndDelete(state string) (string, bool) {
-	verifier, err := s.cache.Get(s.ctx, state)
+	verifier, found, err := s.cache.GetDel(s.ctx, state)
 	if err != nil {
-		log.Debugf("PKCE verifier not found for state")
+		log.Warnf("Failed to consume PKCE verifier: %v", err)
 		return "", false
 	}
-
-	if err := s.cache.Delete(s.ctx, state); err != nil {
-		log.Warnf("Failed to delete PKCE verifier for state: %v", err)
+	if !found {
+		log.Debug("PKCE verifier not found for state")
+		return "", false
 	}
 
 	return verifier, true

management/internals/shared/grpc/pkce_verifier_test.go

@@ -0,0 +1,85 @@
+package grpc
+
+import (
+	"context"
+	"testing"
+	"time"
+)
+
+func TestPKCEVerifierStoreLoadAndDelete(t *testing.T) {
+	const (
+		state    = "state"
+		verifier = "verifier"
+		attempts = 64
+	)
+
+	t.Run("exactly one concurrent caller consumes the verifier", func(t *testing.T) {
+		store := NewPKCEVerifierStore(context.Background(), testCacheStore(t))
+		if err := store.Store(state, verifier, time.Minute); err != nil {
+			t.Fatalf("couldn't store PKCE verifier: %s", err)
+		}
+
+		start := make(chan struct{})
+		type result struct {
+			verifier string
+			found    bool
+		}
+		results := make(chan result, attempts)
+		for range attempts {
+			go func() {
+				<-start
+				verifier, found := store.LoadAndDelete(state)
+				results <- result{verifier: verifier, found: found}
+			}()
+		}
+		close(start)
+
+		winners := 0
+		for range attempts {
+			result := <-results
+			if result.found {
+				winners++
+				if result.verifier != verifier {
+					t.Fatalf("unexpected verifier: got %q, expected %q", result.verifier, verifier)
+				}
+			}
+		}
+		if winners != 1 {
+			t.Fatalf("expected exactly one PKCE verifier consumer, got %d", winners)
+		}
+	})
+
+	t.Run("replayed state is rejected", func(t *testing.T) {
+		store := NewPKCEVerifierStore(context.Background(), testCacheStore(t))
+		if err := store.Store(state, verifier, time.Minute); err != nil {
+			t.Fatalf("couldn't store PKCE verifier: %s", err)
+		}
+
+		if got, found := store.LoadAndDelete(state); !found || got != verifier {
+			t.Fatalf("first load should return the verifier, got %q, found %t", got, found)
+		}
+		if got, found := store.LoadAndDelete(state); found {
+			t.Fatalf("replayed state should not resolve, got %q", got)
+		}
+	})
+
+	t.Run("unknown state is rejected", func(t *testing.T) {
+		store := NewPKCEVerifierStore(context.Background(), testCacheStore(t))
+
+		if got, found := store.LoadAndDelete("never-stored"); found {
+			t.Fatalf("unknown state should not resolve, got %q", got)
+		}
+	})
+
+	t.Run("expired verifier is rejected", func(t *testing.T) {
+		store := NewPKCEVerifierStore(context.Background(), testCacheStore(t))
+		if err := store.Store(state, verifier, 50*time.Millisecond); err != nil {
+			t.Fatalf("couldn't store PKCE verifier: %s", err)
+		}
+
+		time.Sleep(100 * time.Millisecond)
+		if got, found := store.LoadAndDelete(state); found {
+			t.Fatalf("expired verifier should not resolve, got %q", got)
+		}
+	})
+}

management/internals/shared/grpc/proxy_test.go

@@ -9,7 +9,6 @@ import (
 	"testing"
 	"time"
 
-	cachestore "github.com/eko/gocache/lib/v4/store"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 	"google.golang.org/grpc/codes"
@@ -21,7 +20,7 @@ import (
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
-func testCacheStore(t *testing.T) cachestore.StoreInterface {
+func testCacheStore(t *testing.T) nbcache.Store {
 	t.Helper()
 	s, err := nbcache.NewStore(context.Background(), 30*time.Minute, 10*time.Minute, 100)
 	require.NoError(t, err)

management/server/auth/session.go

@@ -7,9 +7,6 @@ import (
 	"errors"
 	"fmt"
 	"time"
-
-	"github.com/eko/gocache/lib/v4/cache"
-	"github.com/eko/gocache/lib/v4/store"
 )
 
 const (
@@ -22,12 +19,17 @@ var (
 	ErrTokenExpired     = errors.New("JWT expired")
 )
 
-type SessionStore struct {
-	cache *cache.Cache[string]
+// TokenCache atomically records used JWTs until their expiration.
+type TokenCache interface {
+	SetNX(ctx context.Context, key, value string, ttl time.Duration) (bool, error)
 }
 
-func NewSessionStore(cacheStore store.StoreInterface) *SessionStore {
-	return &SessionStore{cache: cache.New[string](cacheStore)}
+type SessionStore struct {
+	cache TokenCache
+}
+
+func NewSessionStore(cacheStore TokenCache) *SessionStore {
+	return &SessionStore{cache: cacheStore}
 }
 
 // RegisterToken records a JWT until its exp time and rejects reuse.
@@ -38,20 +40,14 @@ func (s *SessionStore) RegisterToken(ctx context.Context, token string, expiresA
 	}
 
 	key := usedTokenKeyPrefix + hashToken(token)
-	_, err := s.cache.Get(ctx, key)
-	if err == nil {
+	created, err := s.cache.SetNX(ctx, key, usedTokenMarker, ttl)
+	if err != nil {
+		return fmt.Errorf("store used token entry: %w", err)
+	}
+	if !created {
 		return ErrTokenAlreadyUsed
 	}
 
-	var notFound *store.NotFound
-	if !errors.As(err, &notFound) {
-		return fmt.Errorf("failed to lookup used token entry: %w", err)
-	}
-
-	if err := s.cache.Set(ctx, key, usedTokenMarker, store.WithExpiration(ttl)); err != nil {
-		return fmt.Errorf("failed to store used token entry: %w", err)
-	}
-
 	return nil
 }
 

management/server/auth/session_test.go

@@ -2,6 +2,7 @@ package auth
 
 import (
 	"context"
+	"errors"
 	"testing"
 	"time"
 
@@ -38,6 +39,39 @@ func TestSessionStore_RegisterSameTokenTwiceIsRejected(t *testing.T) {
 	assert.ErrorIs(t, err, ErrTokenAlreadyUsed)
 }
 
+func TestSessionStore_ConcurrentRegistrationAllowsOneCaller(t *testing.T) {
+	s := newTestSessionStore(t)
+	ctx := context.Background()
+	const attempts = 100
+
+	start := make(chan struct{})
+	results := make(chan error, attempts)
+	for range attempts {
+		go func() {
+			<-start
+			results <- s.RegisterToken(ctx, "token", time.Now().Add(time.Hour))
+		}()
+	}
+	close(start)
+
+	succeeded := 0
+	alreadyUsed := 0
+	for range attempts {
+		err := <-results
+		switch {
+		case err == nil:
+			succeeded++
+		case errors.Is(err, ErrTokenAlreadyUsed):
+			alreadyUsed++
+		default:
+			require.NoError(t, err, "concurrent registration returned an unexpected error")
+		}
+	}
+
+	assert.Equal(t, 1, succeeded, "exactly one concurrent caller should register the token")
+	assert.Equal(t, attempts-1, alreadyUsed, "every other caller should be rejected as already used")
+}
+
 func TestSessionStore_RegisterDifferentTokensAreIndependent(t *testing.T) {
 	s := newTestSessionStore(t)
 	ctx := context.Background()
@@ -72,6 +106,23 @@ func TestSessionStore_EntryEvictsAtTTLAndAllowsReRegistration(t *testing.T) {
 	require.NoError(t, s.RegisterToken(ctx, token, time.Now().Add(time.Hour)))
 }
 
+type failingTokenCache struct {
+	err error
+}
+
+func (f failingTokenCache) SetNX(context.Context, string, string, time.Duration) (bool, error) {
+	return false, f.err
+}
+
+func TestSessionStore_CacheErrorIsReturned(t *testing.T) {
+	cacheErr := errors.New("cache unavailable")
+	s := NewSessionStore(failingTokenCache{err: cacheErr})
+
+	err := s.RegisterToken(context.Background(), "token", time.Now().Add(time.Hour))
+	require.Error(t, err, "cache failure should be surfaced to the caller")
+	assert.ErrorIs(t, err, cacheErr, "cache error should be wrapped, not replaced")
+}
+
 func TestHashToken_StableAndDoesNotLeak(t *testing.T) {
 	a := hashToken("tokenA")
 	b := hashToken("tokenB")

management/server/cache/memory.go

@@ -0,0 +1,57 @@
+package cache
+
+import (
+	"context"
+	"fmt"
+	"sync"
+	"time"
+
+	"github.com/eko/gocache/lib/v4/store"
+	gocachestore "github.com/eko/gocache/store/go_cache/v4"
+	gocache "github.com/patrickmn/go-cache"
+)
+
+type goCacheStore struct {
+	store.StoreInterface
+	client *gocache.Cache
+	mu     sync.Mutex
+}
+
+func newMemoryStore(maxTimeout, cleanupInterval time.Duration) Store {
+	client := gocache.New(maxTimeout, cleanupInterval)
+	return &goCacheStore{
+		StoreInterface: gocachestore.NewGoCache(client),
+		client:         client,
+	}
+}
+
+func (s *goCacheStore) SetNX(_ context.Context, key, value string, ttl time.Duration) (bool, error) {
+	// Add only returns an error when a non-expired entry already exists.
+	if err := s.client.Add(key, value, ttl); err != nil {
+		return false, nil //nolint:nilerr
+	}
+	return true, nil
+}
+
+// GetDel reads the value under key and removes it. go-cache has no native read-and-delete
+// and releases its own lock between the two calls, so mu holds the pair together and no
+// value is consumed twice.
+//
+// Writes do not take mu: a Set landing mid-pair is lost, since GetDel returns the prior
+// value and deletes the new one. Callers must write a consumed key only once.
+func (s *goCacheStore) GetDel(_ context.Context, key string) (string, bool, error) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	value, found := s.client.Get(key)
+	if !found {
+		return "", false, nil
+	}
+	s.client.Delete(key)
+
+	str, ok := value.(string)
+	if !ok {
+		return "", false, fmt.Errorf("cached value is %T, not a string", value)
+	}
+	return str, true, nil
+}

management/server/cache/memory_test.go

@@ -0,0 +1,76 @@
+package cache_test
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/management/server/cache"
+)
+
+func TestMemoryStore(t *testing.T) {
+	memStore, err := cache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
+	require.NoError(t, err, "couldn't create memory store")
+
+	ctx := context.Background()
+	key, value := "testing", "tested"
+	err = memStore.Set(ctx, key, value)
+	assert.NoError(t, err, "couldn't set testing data")
+
+	result, err := memStore.Get(ctx, key)
+	assert.NoError(t, err, "couldn't get testing data")
+	assert.Equal(t, value, result, "value returned doesn't match testing data")
+
+	created, err := memStore.SetNX(ctx, "conditional", value, 100*time.Millisecond)
+	require.NoError(t, err, "couldn't conditionally set testing data")
+	require.True(t, created, "first conditional set should create the entry")
+
+	created, err = memStore.SetNX(ctx, "conditional", value, 100*time.Millisecond)
+	require.NoError(t, err, "couldn't conditionally check testing data")
+	require.False(t, created, "second conditional set should not replace the entry")
+
+	// test expiration
+	time.Sleep(300 * time.Millisecond)
+	_, err = memStore.Get(ctx, key)
+	assert.Error(t, err, "value should not be found")
+}
+
+func TestMemoryStoreGetDel(t *testing.T) {
+	ctx := context.Background()
+	newStore := func(t *testing.T) cache.Store {
+		t.Helper()
+		memStore, err := cache.NewStore(ctx, time.Minute, time.Minute, 100)
+		require.NoError(t, err, "couldn't create memory store")
+
+		return memStore
+	}
+
+	const (
+		key   = "consume"
+		value = "verifier"
+	)
+
+	t.Run("exactly one concurrent caller consumes the key", func(t *testing.T) {
+		memStore := newStore(t)
+		require.NoError(t, memStore.Set(ctx, key, value), "couldn't set testing data")
+
+		assertGetDelConsumedOnce(ctx, t, []cache.Store{memStore}, key, value)
+		assertGetDelMisses(ctx, t, memStore, key)
+	})
+
+	t.Run("missing key is not an error", func(t *testing.T) {
+		assertGetDelMisses(ctx, t, newStore(t), "never-set")
+	})
+
+	t.Run("expired key is not found", func(t *testing.T) {
+		memStore := newStore(t)
+		_, err := memStore.SetNX(ctx, key, value, 50*time.Millisecond)
+		require.NoError(t, err, "couldn't set testing data")
+
+		time.Sleep(100 * time.Millisecond)
+		assertGetDelMisses(ctx, t, memStore, key)
+	})
+}

management/server/cache/redis.go

@@ -0,0 +1,63 @@
+package cache
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"math"
+	"time"
+
+	"github.com/eko/gocache/lib/v4/store"
+	redisstore "github.com/eko/gocache/store/redis/v4"
+	"github.com/redis/go-redis/v9"
+	log "github.com/sirupsen/logrus"
+)
+
+type redisStore struct {
+	store.StoreInterface
+	client *redis.Client
+}
+
+func getRedisStore(ctx context.Context, redisEnvAddr string, maxConn int) (Store, error) {
+	options, err := redis.ParseURL(redisEnvAddr)
+	if err != nil {
+		return nil, fmt.Errorf("parsing redis cache url: %s", err)
+	}
+
+	options.MaxIdleConns = int(math.Ceil(float64(maxConn) * 0.5)) // 50% of max conns
+	options.MinIdleConns = int(math.Ceil(float64(maxConn) * 0.1)) // 10% of max conns
+	options.MaxActiveConns = maxConn
+	options.ConnMaxIdleTime = 30 * time.Minute
+	options.ConnMaxLifetime = 0
+	options.PoolTimeout = 10 * time.Second
+	redisClient := redis.NewClient(options)
+	subCtx, cancel := context.WithTimeout(ctx, 2*time.Second)
+	defer cancel()
+
+	_, err = redisClient.Ping(subCtx).Result()
+	if err != nil {
+		return nil, err
+	}
+
+	log.WithContext(subCtx).Infof("using redis cache at %s", redisEnvAddr)
+
+	return &redisStore{
+		StoreInterface: redisstore.NewRedis(redisClient),
+		client:         redisClient,
+	}, nil
+}
+
+func (s *redisStore) SetNX(ctx context.Context, key, value string, ttl time.Duration) (bool, error) {
+	return s.client.SetNX(ctx, key, value, ttl).Result()
+}
+
+func (s *redisStore) GetDel(ctx context.Context, key string) (string, bool, error) {
+	value, err := s.client.GetDel(ctx, key).Result()
+	if errors.Is(err, redis.Nil) {
+		return "", false, nil
+	}
+	if err != nil {
+		return "", false, err
+	}
+	return value, true, nil
+}

management/server/cache/redis_test.go

@@ -0,0 +1,153 @@
+package cache_test
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/eko/gocache/lib/v4/store"
+	"github.com/redis/go-redis/v9"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	testcontainersredis "github.com/testcontainers/testcontainers-go/modules/redis"
+
+	"github.com/netbirdio/netbird/management/server/cache"
+)
+
+func startRedis(t *testing.T) string {
+	t.Helper()
+
+	ctx := context.Background()
+	redisContainer, err := testcontainersredis.Run(ctx, "redis:7")
+	require.NoError(t, err, "couldn't start redis container")
+
+	t.Cleanup(func() {
+		if err := redisContainer.Terminate(ctx); err != nil {
+			t.Logf("failed to terminate container: %s", err)
+		}
+	})
+
+	redisURL, err := redisContainer.ConnectionString(ctx)
+	require.NoError(t, err, "couldn't get connection string")
+
+	t.Setenv(cache.RedisStoreEnvVar, redisURL)
+	return redisURL
+}
+
+func newRedisStore(t *testing.T) cache.Store {
+	t.Helper()
+
+	redisStore, err := cache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
+	require.NoError(t, err)
+
+	return redisStore
+}
+
+func TestRedisStoreConnectionFailure(t *testing.T) {
+	t.Setenv(cache.RedisStoreEnvVar, "redis://127.0.0.1:6379")
+	_, err := cache.NewStore(context.Background(), 10*time.Millisecond, 30*time.Millisecond, 100)
+	require.Error(t, err, "getting redis cache store should return error")
+}
+
+func TestRedisStoreConnectionSuccess(t *testing.T) {
+	ctx := context.Background()
+	redisURL := startRedis(t)
+	redisStore := newRedisStore(t)
+
+	key, value := "testing", "tested"
+	err := redisStore.Set(ctx, key, value, store.WithExpiration(100*time.Millisecond))
+	assert.NoError(t, err, "couldn't set testing data")
+
+	result, err := redisStore.Get(ctx, key)
+	assert.NoError(t, err, "couldn't get testing data")
+	assert.Equal(t, value, result, "value returned doesn't match testing data")
+
+	options, err := redis.ParseURL(redisURL)
+	require.NoError(t, err, "parsing redis cache url")
+
+	redisClient := redis.NewClient(options)
+	r, err := redisClient.Get(ctx, key).Result()
+	assert.NoError(t, err, "couldn't get testing data from redis")
+	assert.Equal(t, value, r, "value returned from redis doesn't match testing data")
+
+	// test expiration
+	time.Sleep(300 * time.Millisecond)
+	_, err = redisStore.Get(ctx, key)
+	assert.Error(t, err, "value should not be found")
+}
+
+func TestRedisStoreSetNX(t *testing.T) {
+	ctx := context.Background()
+	redisURL := startRedis(t)
+	redisStore, secondRedisStore := newRedisStore(t), newRedisStore(t)
+
+	const (
+		key   = "conditional"
+		value = "tested"
+	)
+
+	start := make(chan struct{})
+	type setResult struct {
+		created bool
+		err     error
+	}
+	results := make(chan setResult, 2)
+	for _, cacheStore := range []cache.Store{redisStore, secondRedisStore} {
+		go func() {
+			<-start
+			created, err := cacheStore.SetNX(ctx, key, value, time.Minute)
+			results <- setResult{created: created, err: err}
+		}()
+	}
+	close(start)
+
+	created := 0
+	for range 2 {
+		result := <-results
+		require.NoError(t, result.err, "conditional redis set failed")
+		if result.created {
+			created++
+		}
+	}
+	require.Equal(t, 1, created, "expected exactly one redis client to create the entry")
+
+	options, err := redis.ParseURL(redisURL)
+	require.NoError(t, err, "parsing redis cache url")
+
+	ttl, err := redis.NewClient(options).PTTL(ctx, key).Result()
+	require.NoError(t, err, "couldn't read entry TTL")
+	require.Positive(t, ttl, "created entry should have a positive TTL")
+}
+
+func TestRedisStoreGetDel(t *testing.T) {
+	ctx := context.Background()
+	startRedis(t)
+	redisStore, secondRedisStore := newRedisStore(t), newRedisStore(t)
+
+	const (
+		key   = "consume"
+		value = "verifier"
+	)
+
+	t.Run("exactly one caller across independent clients consumes the key", func(t *testing.T) {
+		// A generous TTL: the key is consumed explicitly, so expiry racing the
+		// concurrent callers would only make the test flaky on a loaded runner.
+		err := redisStore.Set(ctx, key, value, store.WithExpiration(time.Minute))
+		require.NoError(t, err, "couldn't set value to consume")
+
+		assertGetDelConsumedOnce(ctx, t, []cache.Store{redisStore, secondRedisStore}, key, value)
+		assertGetDelMisses(ctx, t, secondRedisStore, key)
+	})
+
+	t.Run("missing key is not an error", func(t *testing.T) {
+		assertGetDelMisses(ctx, t, redisStore, "never-set")
+	})
+
+	t.Run("expired key is not found", func(t *testing.T) {
+		err := redisStore.Set(ctx, key, value, store.WithExpiration(50*time.Millisecond))
+		require.NoError(t, err, "couldn't set value to consume")
+
+		time.Sleep(100 * time.Millisecond)
+		assertGetDelMisses(ctx, t, redisStore, key)
+	})
+}

management/server/cache/store.go

@@ -2,17 +2,10 @@ package cache
 
 import (
 	"context"
-	"fmt"
-	"math"
 	"os"
 	"time"
 
 	"github.com/eko/gocache/lib/v4/store"
-	gocache_store "github.com/eko/gocache/store/go_cache/v4"
-	redis_store "github.com/eko/gocache/store/redis/v4"
-	gocache "github.com/patrickmn/go-cache"
-	"github.com/redis/go-redis/v9"
-	log "github.com/sirupsen/logrus"
 )
 
 // RedisStoreEnvVar is the environment variable that determines if a redis store should be used.
@@ -31,15 +24,23 @@ const (
 	DefaultStoreMaxConn = 1000
 )
 
+// Store extends the shared cache interface with conditional and consuming operations.
+type Store interface {
+	store.StoreInterface
+	// SetNX stores a value with a TTL only when the key does not exist.
+	SetNX(ctx context.Context, key, value string, ttl time.Duration) (bool, error)
+	// GetDel reads a value and removes it, so only one caller can consume a key.
+	GetDel(ctx context.Context, key string) (value string, found bool, err error)
+}
+
 // NewStore creates a new cache store with the given max timeout and cleanup interval. It checks for the environment Variable RedisStoreEnvVar
 // to determine if a redis store should be used. If the environment variable is set, it will attempt to connect to the redis store.
-func NewStore(ctx context.Context, maxTimeout, cleanupInterval time.Duration, maxConn int) (store.StoreInterface, error) {
+func NewStore(ctx context.Context, maxTimeout, cleanupInterval time.Duration, maxConn int) (Store, error) {
 	redisAddr := GetAddrFromEnv()
 	if redisAddr != "" {
 		return getRedisStore(ctx, redisAddr, maxConn)
 	}
-	goc := gocache.New(maxTimeout, cleanupInterval)
-	return gocache_store.NewGoCache(goc), nil
+	return newMemoryStore(maxTimeout, cleanupInterval), nil
 }
 
 // GetAddrFromEnv returns the redis address from the environment variable RedisStoreEnvVar or its legacy counterpart.
@@ -50,29 +51,3 @@ func GetAddrFromEnv() string {
 	}
 	return addr
 }
-
-func getRedisStore(ctx context.Context, redisEnvAddr string, maxConn int) (store.StoreInterface, error) {
-	options, err := redis.ParseURL(redisEnvAddr)
-	if err != nil {
-		return nil, fmt.Errorf("parsing redis cache url: %s", err)
-	}
-
-	options.MaxIdleConns = int(math.Ceil(float64(maxConn) * 0.5)) // 50% of max conns
-	options.MinIdleConns = int(math.Ceil(float64(maxConn) * 0.1)) // 10% of max conns
-	options.MaxActiveConns = maxConn
-	options.ConnMaxIdleTime = 30 * time.Minute
-	options.ConnMaxLifetime = 0
-	options.PoolTimeout = 10 * time.Second
-	redisClient := redis.NewClient(options)
-	subCtx, cancel := context.WithTimeout(ctx, 2*time.Second)
-	defer cancel()
-
-	_, err = redisClient.Ping(subCtx).Result()
-	if err != nil {
-		return nil, err
-	}
-
-	log.WithContext(subCtx).Infof("using redis cache at %s", redisEnvAddr)
-
-	return redis_store.NewRedis(redisClient), nil
-}

management/server/cache/store_test.go

@@ -3,101 +3,53 @@ package cache_test
 import (
 	"context"
 	"testing"
-	"time"
 
-	"github.com/eko/gocache/lib/v4/store"
-	"github.com/redis/go-redis/v9"
-	testcontainersredis "github.com/testcontainers/testcontainers-go/modules/redis"
+	"github.com/stretchr/testify/require"
 
 	"github.com/netbirdio/netbird/management/server/cache"
 )
 
-func TestMemoryStore(t *testing.T) {
-	memStore, err := cache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
-	if err != nil {
-		t.Fatalf("couldn't create memory store: %s", err)
-	}
-	ctx := context.Background()
-	key, value := "testing", "tested"
-	err = memStore.Set(ctx, key, value)
-	if err != nil {
-		t.Errorf("couldn't set testing data: %s", err)
-	}
-	result, err := memStore.Get(ctx, key)
-	if err != nil {
-		t.Errorf("couldn't get testing data: %s", err)
-	}
-	if value != result.(string) {
-		t.Errorf("value returned doesn't match testing data, got %s, expected %s", result, value)
-	}
-	// test expiration
-	time.Sleep(300 * time.Millisecond)
-	_, err = memStore.Get(ctx, key)
-	if err == nil {
-		t.Error("value should not be found")
-	}
-}
+func assertGetDelConsumedOnce(ctx context.Context, t *testing.T, stores []cache.Store, key, value string) {
+	t.Helper()
 
-func TestRedisStoreConnectionFailure(t *testing.T) {
-	t.Setenv(cache.RedisStoreEnvVar, "redis://127.0.0.1:6379")
-	_, err := cache.NewStore(context.Background(), 10*time.Millisecond, 30*time.Millisecond, 100)
-	if err == nil {
-		t.Fatal("getting redis cache store should return error")
-	}
-}
+	const getDelAttempts = 64
 
-func TestRedisStoreConnectionSuccess(t *testing.T) {
-	ctx := context.Background()
-	redisContainer, err := testcontainersredis.Run(ctx, "redis:7")
-	if err != nil {
-		t.Fatalf("couldn't start redis container: %s", err)
+	type getDelResult struct {
+		value string
+		found bool
+		err   error
 	}
-	defer func() {
-		if err := redisContainer.Terminate(ctx); err != nil {
-			t.Logf("failed to terminate container: %s", err)
+
+	start := make(chan struct{})
+	results := make(chan getDelResult, getDelAttempts)
+	for i := range getDelAttempts {
+		cacheStore := stores[i%len(stores)]
+		go func() {
+			<-start
+			value, found, err := cacheStore.GetDel(ctx, key)
+			results <- getDelResult{value: value, found: found, err: err}
+		}()
+	}
+	close(start)
+
+	consumers := 0
+	for range getDelAttempts {
+		result := <-results
+		require.NoError(t, result.err, "concurrent GetDel failed")
+		if !result.found {
+			continue
 		}
-	}()
-	redisURL, err := redisContainer.ConnectionString(ctx)
-	if err != nil {
-		t.Fatalf("couldn't get connection string: %s", err)
-	}
-
-	t.Setenv(cache.RedisStoreEnvVar, redisURL)
-	redisStore, err := cache.NewStore(context.Background(), 100*time.Millisecond, 300*time.Millisecond, 100)
-	if err != nil {
-		t.Fatalf("couldn't create redis store: %s", err)
-	}
-
-	key, value := "testing", "tested"
-	err = redisStore.Set(ctx, key, value, store.WithExpiration(100*time.Millisecond))
-	if err != nil {
-		t.Errorf("couldn't set testing data: %s", err)
-	}
-	result, err := redisStore.Get(ctx, key)
-	if err != nil {
-		t.Errorf("couldn't get testing data: %s", err)
-	}
-	if value != result.(string) {
-		t.Errorf("value returned doesn't match testing data, got %s, expected %s", result, value)
-	}
-
-	options, err := redis.ParseURL(redisURL)
-	if err != nil {
-		t.Errorf("parsing redis cache url: %s", err)
-	}
-
-	redisClient := redis.NewClient(options)
-	r, e := redisClient.Get(ctx, key).Result()
-	if e != nil {
-		t.Errorf("couldn't get testing data from redis: %s", e)
-	}
-	if value != r {
-		t.Errorf("value returned from redis doesn't match testing data, got %s, expected %s", r, value)
-	}
-	// test expiration
-	time.Sleep(300 * time.Millisecond)
-	_, err = redisStore.Get(ctx, key)
-	if err == nil {
-		t.Error("value should not be found")
+		consumers++
+		require.Equal(t, value, result.value, "consumed value doesn't match testing data")
 	}
+	require.Equal(t, 1, consumers, "expected exactly one consumer")
+}
+
+func assertGetDelMisses(ctx context.Context, t *testing.T, cacheStore cache.Store, key string) {
+	t.Helper()
+
+	value, found, err := cacheStore.GetDel(ctx, key)
+	require.NoError(t, err, "GetDel on a missing key should not error")
+	require.False(t, found, "GetDel should not find key %q, got value %q", key, value)
+	require.Empty(t, value, "GetDel should return an empty value when not found")
 }

release_files/darwin_pkg/preinstall

@@ -4,67 +4,9 @@ set -x
 
 LOG_FILE=/var/log/netbird/client_pre_install.log
 AGENT=/usr/local/bin/netbird
-UI_PROCESS=netbird-ui
 
 mkdir -p /var/log/netbird/
 
-# wait_for_ui_exit polls for up to $1 seconds, returning 0 as soon as no UI
-# process is left and 1 if one is still running when the time is up.
-wait_for_ui_exit() {
-    waited=0
-    while [ "$waited" -lt "$1" ]; do
-        pgrep -x "$UI_PROCESS" > /dev/null 2>&1 || return 0
-        sleep 1
-        waited=$((waited + 1))
-    done
-    return 1
-}
-
-# request_ui_quit asks the UI to quit from inside the console user's session and
-# reports whether the request could be sent at all. The installer runs as root
-# outside that session, so a quit Apple event sent straight from here always
-# fails with -600.
-request_ui_quit() {
-    console_user=$(stat -f%Su /dev/console 2>/dev/null)
-    case "$console_user" in
-        ""|root|loginwindow|_mbsetupuser)
-            echo "No active GUI user session (console user: '${console_user:-none}'); skipping the quit request."
-            return 1
-            ;;
-    esac
-
-    uid=$(id -u "$console_user" 2>/dev/null)
-    if [ -z "$uid" ]; then
-        echo "Could not resolve uid for console user '$console_user'; skipping the quit request."
-        return 1
-    fi
-
-    echo "Asking the NetBird UI to quit as console user $console_user (uid $uid)."
-    launchctl asuser "$uid" sudo -u "$console_user" -H osascript -e 'quit app "NetBird"' || true
-}
-
-# quit_ui stops a running UI so the app bundle can be replaced underneath it. A
-# UI process that survives the install keeps serving the old binary until it is
-# quit by hand, so anything still running once the quit request is out of the
-# way is signalled. Waiting for a graceful exit only makes sense when a quit
-# request was actually sent.
-quit_ui() {
-    if request_ui_quit && wait_for_ui_exit 10; then
-        return 0
-    fi
-
-    pgrep -x "$UI_PROCESS" > /dev/null 2>&1 || return 0
-
-    echo "NetBird UI still running; terminating it."
-    pkill -x "$UI_PROCESS" || true
-    if wait_for_ui_exit 3; then
-        return 0
-    fi
-
-    echo "NetBird UI ignored SIGTERM; killing it."
-    pkill -KILL -x "$UI_PROCESS" || true
-}
-
 {
     # check if it was installed with brew
     brew list --formula | grep netbird
@@ -73,9 +15,10 @@ quit_ui() {
         echo "NetBird has been installed with Brew. Please use Brew to update the package."
         exit 1
     fi
-    quit_ui
+    osascript -e 'quit app "Netbird"' || true
     $AGENT service stop || true
 
     echo "Preinstall complete"
     exit 0 # all good
 } &> $LOG_FILE
+

shared/management/client/grpc.go

@@ -21,8 +21,6 @@ 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"
@@ -64,13 +62,6 @@ 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
@@ -120,43 +111,16 @@ 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, 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)
-	}
+func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
+	var conn *grpc.ClientConn
 
 	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...)
@@ -172,9 +136,16 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
 		return nil, err
 	}
 
-	c.conn = conn
-	c.realClient = proto.NewManagementServiceClient(conn)
-	return c, nil
+	realClient := proto.NewManagementServiceClient(conn)
+
+	return &GrpcClient{
+		key:                   ourPrivateKey,
+		realClient:            realClient,
+		ctx:                   ctx,
+		conn:                  conn,
+		connStateCallbackLock: sync.RWMutex{},
+		serverURL:             addr,
+	}, nil
 }
 
 // GetServerURL returns the management server URL
@@ -237,16 +208,6 @@ 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

@@ -14,7 +14,6 @@ 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"
@@ -185,10 +184,6 @@ 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
@@ -398,12 +393,6 @@ func (c *Client) Close() error {
 }
 
 func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
-	// A sweep cancels this context, so a dial started on the old network
-	// aborts instead of waiting out its handshake timeout.
-	dial := c.sweeper.StartDial(ctx)
-	defer dial.Release()
-	ctx = dial.Ctx()
-
 	mode := transportModeFromEnv()
 	dialers := c.getDialers(mode)
 
@@ -428,19 +417,12 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
 			return nil, fmt.Errorf("dial via FQDN: %w", err)
 		}
 	}
-	// Read the transport off the concrete connection: the sweeper's wrapper
-	// embeds net.Conn only, so it does not promote Protocol().
+	c.relayConn = conn
+	c.datagramFallbackTriggered.Store(false)
 	if tc, ok := conn.(transportConn); ok {
 		c.transport = tc.Protocol()
 	}
 
-	conn, err := dial.WrapConn(conn)
-	if err != nil {
-		return nil, fmt.Errorf("register connection: %w", err)
-	}
-	c.relayConn = conn
-	c.datagramFallbackTriggered.Store(false)
-
 	instanceURL, err := c.handShake(ctx)
 	if err != nil {
 		cErr := conn.Close()

shared/relay/client/guard.go

@@ -7,8 +7,6 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/netstate"
 )
 
 const defaultMaxBackoffInterval = 60 * time.Second
@@ -24,19 +22,14 @@ 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. 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) *Guard {
 	if maxBackoffInterval <= 0 {
 		maxBackoffInterval = defaultMaxBackoffInterval
 	}
@@ -45,7 +38,6 @@ func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *nets
 		OnReconnected:      make(chan struct{}, 1),
 		serverPicker:       sp,
 		maxBackoffInterval: maxBackoffInterval,
-		netState:           netState,
 	}
 	return g
 }
@@ -78,21 +70,11 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
 
 	// start a ticker to pick a new server
 	ticker := g.exponentTicker(ctx)
-	defer func() {
-		ticker.Stop()
-	}()
+	defer 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)
@@ -122,13 +104,6 @@ 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

@@ -12,8 +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"
 )
 
@@ -67,17 +65,6 @@ 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
@@ -105,8 +92,6 @@ type Manager struct {
 
 	mtu                uint16
 	maxBackoffInterval time.Duration
-	netState           *netstate.State
-	sweeper            *netsweep.Sweeper
 
 	cleanupInterval      time.Duration
 	keepUnusedServerTime time.Duration
@@ -143,9 +128,8 @@ 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.netState)
+	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
 	return m
 }
 
@@ -370,7 +354,6 @@ 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

@@ -9,7 +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 +30,6 @@ type ServerPicker struct {
 	MTU               uint16
 	ConnectionTimeout time.Duration
 	TransportFallback *transportFallback
-	Sweeper           *netsweep.Sweeper
 }
 
 func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -75,7 +73,6 @@ 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

@@ -19,8 +19,6 @@ 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"
@@ -67,13 +65,6 @@ 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
@@ -97,43 +88,13 @@ type GrpcClient struct {
 	watchdogWg            sync.WaitGroup
 }
 
-// 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))
-	}
-
+func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
 	var conn *grpc.ClientConn
+
 	operation := func() error {
 		var err error
-		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent, extraOpts...)
+		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent)
 		if err != nil {
 			return fmt.Errorf("create connection: %w", err)
 		}
@@ -148,9 +109,15 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
 
 	log.Debugf("connected to Signal Service: %v", conn.Target())
 
-	c.signalConn = conn
-	c.realClient = proto.NewSignalExchangeClient(conn)
-	return c, nil
+	return &GrpcClient{
+		realClient:            proto.NewSignalExchangeClient(conn),
+		ctx:                   ctx,
+		signalConn:            conn,
+		key:                   key,
+		mux:                   sync.Mutex{},
+		status:                StreamDisconnected,
+		connStateCallbackLock: sync.RWMutex{},
+	}, nil
 }
 
 func (c *GrpcClient) StreamConnected() bool {
@@ -201,15 +168,6 @@ 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()