Merge main branch into feature/client-metrics

client/Dockerfile

@@ -4,7 +4,7 @@
 #   sudo podman build -t localhost/netbird:latest -f client/Dockerfile --ignorefile .dockerignore-client .
 #   sudo podman run --rm -it --cap-add={BPF,NET_ADMIN,NET_RAW} localhost/netbird:latest
 
-FROM alpine:3.22.2
+FROM alpine:3.23.2
 # iproute2: busybox doesn't display ip rules properly
 RUN apk add --no-cache \
     bash \

client/cmd/debug.go

@@ -16,7 +16,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/server"
-	nbstatus "github.com/netbirdio/netbird/client/status"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/upload-server/types"
 )
@@ -98,7 +97,6 @@ func debugBundle(cmd *cobra.Command, _ []string) error {
 	client := proto.NewDaemonServiceClient(conn)
 	request := &proto.DebugBundleRequest{
 		Anonymize:    anonymizeFlag,
-		Status:       getStatusOutput(cmd, anonymizeFlag),
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
 	}
@@ -221,9 +219,6 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 
 	time.Sleep(3 * time.Second)
 
-	headerPostUp := fmt.Sprintf("----- NetBird post-up - Timestamp: %s", time.Now().Format(time.RFC3339))
-	statusOutput := fmt.Sprintf("%s\n%s", headerPostUp, getStatusOutput(cmd, anonymizeFlag))
-
 	if waitErr := waitForDurationOrCancel(cmd.Context(), duration, cmd); waitErr != nil {
 		return waitErr
 	}
@@ -231,11 +226,8 @@ func runForDuration(cmd *cobra.Command, args []string) error {
 
 	cmd.Println("Creating debug bundle...")
 
-	headerPreDown := fmt.Sprintf("----- NetBird pre-down - Timestamp: %s - Duration: %s", time.Now().Format(time.RFC3339), duration)
-	statusOutput = fmt.Sprintf("%s\n%s\n%s", statusOutput, headerPreDown, getStatusOutput(cmd, anonymizeFlag))
 	request := &proto.DebugBundleRequest{
 		Anonymize:    anonymizeFlag,
-		Status:       statusOutput,
 		SystemInfo:   systemInfoFlag,
 		LogFileCount: logFileCount,
 	}
@@ -302,25 +294,6 @@ func setSyncResponsePersistence(cmd *cobra.Command, args []string) error {
 	return nil
 }
 
-func getStatusOutput(cmd *cobra.Command, anon bool) string {
-	var statusOutputString string
-	statusResp, err := getStatus(cmd.Context(), true)
-	if err != nil {
-		cmd.PrintErrf("Failed to get status: %v\n", err)
-	} else {
-		pm := profilemanager.NewProfileManager()
-		var profName string
-		if activeProf, err := pm.GetActiveProfile(); err == nil {
-			profName = activeProf.Name
-		}
-
-		statusOutputString = nbstatus.ParseToFullDetailSummary(
-			nbstatus.ConvertToStatusOutputOverview(statusResp, anon, "", nil, nil, nil, "", profName),
-		)
-	}
-	return statusOutputString
-}
-
 func waitForDurationOrCancel(ctx context.Context, duration time.Duration, cmd *cobra.Command) error {
 	ticker := time.NewTicker(1 * time.Second)
 	defer ticker.Stop()
@@ -379,7 +352,7 @@ func generateDebugBundle(config *profilemanager.Config, recorder *peer.Status, c
 			InternalConfig: config,
 			StatusRecorder: recorder,
 			SyncResponse:   syncResponse,
-			LogFile:        logFilePath,
+			LogPath:        logFilePath,
 		},
 		debug.BundleConfig{
 			IncludeSystemInfo: true,

client/cmd/status.go

@@ -99,17 +99,17 @@ func statusFunc(cmd *cobra.Command, args []string) error {
 		profName = activeProf.Name
 	}
 
-	var outputInformationHolder = nbstatus.ConvertToStatusOutputOverview(resp, anonymizeFlag, statusFilter, prefixNamesFilter, prefixNamesFilterMap, ipsFilterMap, connectionTypeFilter, profName)
+	var outputInformationHolder = nbstatus.ConvertToStatusOutputOverview(resp.GetFullStatus(), anonymizeFlag, resp.GetDaemonVersion(), statusFilter, prefixNamesFilter, prefixNamesFilterMap, ipsFilterMap, connectionTypeFilter, profName)
 	var statusOutputString string
 	switch {
 	case detailFlag:
-		statusOutputString = nbstatus.ParseToFullDetailSummary(outputInformationHolder)
+		statusOutputString = outputInformationHolder.FullDetailSummary()
 	case jsonFlag:
-		statusOutputString, err = nbstatus.ParseToJSON(outputInformationHolder)
+		statusOutputString, err = outputInformationHolder.JSON()
 	case yamlFlag:
-		statusOutputString, err = nbstatus.ParseToYAML(outputInformationHolder)
+		statusOutputString, err = outputInformationHolder.YAML()
 	default:
-		statusOutputString = nbstatus.ParseGeneralSummary(outputInformationHolder, false, false, false, false)
+		statusOutputString = outputInformationHolder.GeneralSummary(false, false, false, false)
 	}
 
 	if err != nil {

client/cmd/testutil_test.go

@@ -18,6 +18,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral/manager"
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
+	"github.com/netbirdio/netbird/management/server/job"
 
 	clientProto "github.com/netbirdio/netbird/client/proto"
 	client "github.com/netbirdio/netbird/client/server"
@@ -97,6 +98,8 @@ func startManagement(t *testing.T, config *config.Config, testFile string) (*grp
 	peersmanager := peers.NewManager(store, permissionsManagerMock)
 	settingsManagerMock := settings.NewMockManager(ctrl)
 
+	jobManager := job.NewJobManager(nil, store, peersmanager)
+
 	iv, _ := integrations.NewIntegratedValidator(context.Background(), peersmanager, settingsManagerMock, eventStore)
 
 	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
@@ -115,7 +118,7 @@ func startManagement(t *testing.T, config *config.Config, testFile string) (*grp
 	requestBuffer := mgmt.NewAccountRequestBuffer(ctx, store)
 	networkMapController := controller.NewController(ctx, store, metrics, updateManager, requestBuffer, mgmt.MockIntegratedValidator{}, settingsMockManager, "netbird.cloud", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersmanager), config)
 
-	accountManager, err := mgmt.BuildManager(context.Background(), config, store, networkMapController, nil, "", eventStore, nil, false, iv, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManagerMock, false)
+	accountManager, err := mgmt.BuildManager(context.Background(), config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, iv, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManagerMock, false)
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -124,7 +127,7 @@ func startManagement(t *testing.T, config *config.Config, testFile string) (*grp
 	if err != nil {
 		t.Fatal(err)
 	}
-	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, secretsManager, nil, nil, &mgmt.MockIntegratedValidator{}, networkMapController, nil)
+	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &mgmt.MockIntegratedValidator{}, networkMapController, nil)
 	if err != nil {
 		t.Fatal(err)
 	}

client/cmd/up.go

@@ -200,7 +200,7 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
 	connectClient := internal.NewConnectClient(ctx, config, r, false)
 	SetupDebugHandler(ctx, config, r, connectClient, "")
 
-	return connectClient.Run(nil)
+	return connectClient.Run(nil, util.FindFirstLogPath(logFiles))
 }
 
 func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager.ProfileManager, activeProf *profilemanager.Profile, profileSwitched bool) error {

client/embed/embed.go

@@ -20,6 +20,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	sshcommon "github.com/netbirdio/netbird/client/ssh"
 	"github.com/netbirdio/netbird/client/system"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 var (
@@ -38,6 +39,7 @@ type Client struct {
 	setupKey   string
 	jwtToken   string
 	connect    *internal.ConnectClient
+	recorder   *peer.Status
 }
 
 // Options configures a new Client.
@@ -161,11 +163,17 @@ func New(opts Options) (*Client, error) {
 func (c *Client) Start(startCtx context.Context) error {
 	c.mu.Lock()
 	defer c.mu.Unlock()
-	if c.cancel != nil {
+	if c.connect != nil {
 		return ErrClientAlreadyStarted
 	}
 
-	ctx := internal.CtxInitState(context.Background())
+	ctx, cancel := context.WithCancel(internal.CtxInitState(context.Background()))
+	defer func() {
+		if c.connect == nil {
+			cancel()
+		}
+	}()
+
 	// nolint:staticcheck
 	ctx = context.WithValue(ctx, system.DeviceNameCtxKey, c.deviceName)
 	if err := internal.Login(ctx, c.config, c.setupKey, c.jwtToken); err != nil {
@@ -173,14 +181,16 @@ func (c *Client) Start(startCtx context.Context) error {
 	}
 
 	recorder := peer.NewRecorder(c.config.ManagementURL.String())
+	c.recorder = recorder
 	client := internal.NewConnectClient(ctx, c.config, recorder, false)
+	client.SetSyncResponsePersistence(true)
 
 	// either startup error (permanent backoff err) or nil err (successful engine up)
 	// TODO: make after-startup backoff err available
 	run := make(chan struct{})
 	clientErr := make(chan error, 1)
 	go func() {
-		if err := client.Run(run); err != nil {
+		if err := client.Run(run, ""); err != nil {
 			clientErr <- err
 		}
 	}()
@@ -197,6 +207,7 @@ func (c *Client) Start(startCtx context.Context) error {
 	}
 
 	c.connect = client
+	c.cancel = cancel
 
 	return nil
 }
@@ -211,17 +222,23 @@ func (c *Client) Stop(ctx context.Context) error {
 		return ErrClientNotStarted
 	}
 
+	if c.cancel != nil {
+		c.cancel()
+		c.cancel = nil
+	}
+
 	done := make(chan error, 1)
+	connect := c.connect
 	go func() {
-		done <- c.connect.Stop()
+		done <- connect.Stop()
 	}()
 
 	select {
 	case <-ctx.Done():
-		c.cancel = nil
+		c.connect = nil
 		return ctx.Err()
 	case err := <-done:
-		c.cancel = nil
+		c.connect = nil
 		if err != nil {
 			return fmt.Errorf("stop: %w", err)
 		}
@@ -315,6 +332,62 @@ func (c *Client) NewHTTPClient() *http.Client {
 	}
 }
 
+// Status returns the current status of the client.
+func (c *Client) Status() (peer.FullStatus, error) {
+	c.mu.Lock()
+	recorder := c.recorder
+	connect := c.connect
+	c.mu.Unlock()
+
+	if recorder == nil {
+		return peer.FullStatus{}, errors.New("client not started")
+	}
+
+	if connect != nil {
+		engine := connect.Engine()
+		if engine != nil {
+			_ = engine.RunHealthProbes(false)
+		}
+	}
+
+	return recorder.GetFullStatus(), nil
+}
+
+// GetLatestSyncResponse returns the latest sync response from the management server.
+func (c *Client) GetLatestSyncResponse() (*mgmProto.SyncResponse, error) {
+	engine, err := c.getEngine()
+	if err != nil {
+		return nil, err
+	}
+
+	syncResp, err := engine.GetLatestSyncResponse()
+	if err != nil {
+		return nil, fmt.Errorf("get sync response: %w", err)
+	}
+
+	return syncResp, nil
+}
+
+// SetLogLevel sets the logging level for the client and its components.
+func (c *Client) SetLogLevel(levelStr string) error {
+	level, err := logrus.ParseLevel(levelStr)
+	if err != nil {
+		return fmt.Errorf("parse log level: %w", err)
+	}
+
+	logrus.SetLevel(level)
+
+	c.mu.Lock()
+	connect := c.connect
+	c.mu.Unlock()
+
+	if connect != nil {
+		connect.SetLogLevel(level)
+	}
+
+	return nil
+}
+
 // VerifySSHHostKey verifies an SSH host key against stored peer keys.
 // Returns nil if the key matches, ErrPeerNotFound if peer is not in network,
 // ErrNoStoredKey if peer has no stored key, or an error for verification failures.

client/iface/configurer/common.go

@@ -3,8 +3,22 @@ package configurer
 import (
 	"net"
 	"net/netip"
+
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
 
+// buildPresharedKeyConfig creates a wgtypes.Config for setting a preshared key on a peer.
+// This is a shared helper used by both kernel and userspace configurers.
+func buildPresharedKeyConfig(peerKey wgtypes.Key, psk wgtypes.Key, updateOnly bool) wgtypes.Config {
+	return wgtypes.Config{
+		Peers: []wgtypes.PeerConfig{{
+			PublicKey:    peerKey,
+			PresharedKey: &psk,
+			UpdateOnly:   updateOnly,
+		}},
+	}
+}
+
 func prefixesToIPNets(prefixes []netip.Prefix) []net.IPNet {
 	ipNets := make([]net.IPNet, len(prefixes))
 	for i, prefix := range prefixes {

client/iface/configurer/kernel_unix.go

@@ -15,8 +15,6 @@ import (
 	"github.com/netbirdio/netbird/monotime"
 )
 
-var zeroKey wgtypes.Key
-
 type KernelConfigurer struct {
 	deviceName string
 }
@@ -48,6 +46,18 @@ func (c *KernelConfigurer) ConfigureInterface(privateKey string, port int) error
 	return nil
 }
 
+// SetPresharedKey sets the preshared key for a peer.
+// If updateOnly is true, only updates the existing peer; if false, creates or updates.
+func (c *KernelConfigurer) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
+	parsedPeerKey, err := wgtypes.ParseKey(peerKey)
+	if err != nil {
+		return err
+	}
+
+	cfg := buildPresharedKeyConfig(parsedPeerKey, psk, updateOnly)
+	return c.configure(cfg)
+}
+
 func (c *KernelConfigurer) UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error {
 	peerKeyParsed, err := wgtypes.ParseKey(peerKey)
 	if err != nil {
@@ -279,7 +289,7 @@ func (c *KernelConfigurer) FullStats() (*Stats, error) {
 			TxBytes:       p.TransmitBytes,
 			RxBytes:       p.ReceiveBytes,
 			LastHandshake: p.LastHandshakeTime,
-			PresharedKey:  p.PresharedKey != zeroKey,
+			PresharedKey:  [32]byte(p.PresharedKey),
 		}
 		if p.Endpoint != nil {
 			peer.Endpoint = *p.Endpoint

client/iface/configurer/usp.go

@@ -22,17 +22,16 @@ import (
 )
 
 const (
-	privateKey                  = "private_key"
-	ipcKeyLastHandshakeTimeSec  = "last_handshake_time_sec"
-	ipcKeyLastHandshakeTimeNsec = "last_handshake_time_nsec"
-	ipcKeyTxBytes               = "tx_bytes"
-	ipcKeyRxBytes               = "rx_bytes"
-	allowedIP                   = "allowed_ip"
-	endpoint                    = "endpoint"
-	fwmark                      = "fwmark"
-	listenPort                  = "listen_port"
-	publicKey                   = "public_key"
-	presharedKey                = "preshared_key"
+	privateKey                 = "private_key"
+	ipcKeyLastHandshakeTimeSec = "last_handshake_time_sec"
+	ipcKeyTxBytes              = "tx_bytes"
+	ipcKeyRxBytes              = "rx_bytes"
+	allowedIP                  = "allowed_ip"
+	endpoint                   = "endpoint"
+	fwmark                     = "fwmark"
+	listenPort                 = "listen_port"
+	publicKey                  = "public_key"
+	presharedKey               = "preshared_key"
 )
 
 var ErrAllowedIPNotFound = fmt.Errorf("allowed IP not found")
@@ -72,6 +71,18 @@ func (c *WGUSPConfigurer) ConfigureInterface(privateKey string, port int) error
 	return c.device.IpcSet(toWgUserspaceString(config))
 }
 
+// SetPresharedKey sets the preshared key for a peer.
+// If updateOnly is true, only updates the existing peer; if false, creates or updates.
+func (c *WGUSPConfigurer) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
+	parsedPeerKey, err := wgtypes.ParseKey(peerKey)
+	if err != nil {
+		return err
+	}
+
+	cfg := buildPresharedKeyConfig(parsedPeerKey, psk, updateOnly)
+	return c.device.IpcSet(toWgUserspaceString(cfg))
+}
+
 func (c *WGUSPConfigurer) UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error {
 	peerKeyParsed, err := wgtypes.ParseKey(peerKey)
 	if err != nil {
@@ -422,23 +433,19 @@ func toWgUserspaceString(wgCfg wgtypes.Config) string {
 		hexKey := hex.EncodeToString(p.PublicKey[:])
 		sb.WriteString(fmt.Sprintf("public_key=%s\n", hexKey))
 
+		if p.Remove {
+			sb.WriteString("remove=true\n")
+		}
+
+		if p.UpdateOnly {
+			sb.WriteString("update_only=true\n")
+		}
+
 		if p.PresharedKey != nil {
 			preSharedHexKey := hex.EncodeToString(p.PresharedKey[:])
 			sb.WriteString(fmt.Sprintf("preshared_key=%s\n", preSharedHexKey))
 		}
 
-		if p.Remove {
-			sb.WriteString("remove=true")
-		}
-
-		if p.ReplaceAllowedIPs {
-			sb.WriteString("replace_allowed_ips=true\n")
-		}
-
-		for _, aip := range p.AllowedIPs {
-			sb.WriteString(fmt.Sprintf("allowed_ip=%s\n", aip.String()))
-		}
-
 		if p.Endpoint != nil {
 			sb.WriteString(fmt.Sprintf("endpoint=%s\n", p.Endpoint.String()))
 		}
@@ -446,6 +453,14 @@ func toWgUserspaceString(wgCfg wgtypes.Config) string {
 		if p.PersistentKeepaliveInterval != nil {
 			sb.WriteString(fmt.Sprintf("persistent_keepalive_interval=%d\n", int(p.PersistentKeepaliveInterval.Seconds())))
 		}
+
+		if p.ReplaceAllowedIPs {
+			sb.WriteString("replace_allowed_ips=true\n")
+		}
+
+		for _, aip := range p.AllowedIPs {
+			sb.WriteString(fmt.Sprintf("allowed_ip=%s\n", aip.String()))
+		}
 	}
 	return sb.String()
 }
@@ -599,7 +614,9 @@ func parseStatus(deviceName, ipcStr string) (*Stats, error) {
 				continue
 			}
 			if val != "" && val != "0000000000000000000000000000000000000000000000000000000000000000" {
-				currentPeer.PresharedKey = true
+				if pskKey, err := hexToWireguardKey(val); err == nil {
+					currentPeer.PresharedKey = [32]byte(pskKey)
+				}
 			}
 		}
 	}

client/iface/configurer/wgshow.go

@@ -12,7 +12,7 @@ type Peer struct {
 	TxBytes       int64
 	RxBytes       int64
 	LastHandshake time.Time
-	PresharedKey  bool
+	PresharedKey  [32]byte
 }
 
 type Stats struct {

client/iface/device/interface.go

@@ -17,6 +17,7 @@ type WGConfigurer interface {
 	RemovePeer(peerKey string) error
 	AddAllowedIP(peerKey string, allowedIP netip.Prefix) error
 	RemoveAllowedIP(peerKey string, allowedIP netip.Prefix) error
+	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error
 	Close()
 	GetStats() (map[string]configurer.WGStats, error)
 	FullStats() (*configurer.Stats, error)

client/iface/iface.go

@@ -297,6 +297,19 @@ func (w *WGIface) FullStats() (*configurer.Stats, error) {
 	return w.configurer.FullStats()
 }
 
+// SetPresharedKey sets or updates the preshared key for a peer.
+// If updateOnly is true, only updates existing peer; if false, creates or updates.
+func (w *WGIface) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+
+	if w.configurer == nil {
+		return ErrIfaceNotFound
+	}
+
+	return w.configurer.SetPresharedKey(peerKey, psk, updateOnly)
+}
+
 func (w *WGIface) waitUntilRemoved() error {
 	maxWaitTime := 5 * time.Second
 	timeout := time.NewTimer(maxWaitTime)

client/internal/connect.go

@@ -70,8 +70,8 @@ func NewConnectClient(
 }
 
 // Run with main logic.
-func (c *ConnectClient) Run(runningChan chan struct{}) error {
-	return c.run(MobileDependency{}, runningChan)
+func (c *ConnectClient) Run(runningChan chan struct{}, logPath string) error {
+	return c.run(MobileDependency{}, runningChan, logPath)
 }
 
 // RunOnAndroid with main logic on mobile system
@@ -92,7 +92,7 @@ func (c *ConnectClient) RunOnAndroid(
 		DnsReadyListener:      dnsReadyListener,
 		StateFilePath:         stateFilePath,
 	}
-	return c.run(mobileDependency, nil)
+	return c.run(mobileDependency, nil, "")
 }
 
 func (c *ConnectClient) RunOniOS(
@@ -110,10 +110,10 @@ func (c *ConnectClient) RunOniOS(
 		DnsManager:            dnsManager,
 		StateFilePath:         stateFilePath,
 	}
-	return c.run(mobileDependency, nil)
+	return c.run(mobileDependency, nil, "")
 }
 
-func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan struct{}) error {
+func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan struct{}, logPath string) error {
 	defer func() {
 		if r := recover(); r != nil {
 			rec := c.statusRecorder
@@ -283,7 +283,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		relayURLs, token := parseRelayInfo(loginResp)
 		peerConfig := loginResp.GetPeerConfig()
 
-		engineConfig, err := createEngineConfig(myPrivateKey, c.config, peerConfig)
+		engineConfig, err := createEngineConfig(myPrivateKey, c.config, peerConfig, logPath)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -419,6 +419,19 @@ func (c *ConnectClient) GetLatestSyncResponse() (*mgmProto.SyncResponse, error)
 	return syncResponse, nil
 }
 
+// SetLogLevel sets the log level for the firewall manager if the engine is running.
+func (c *ConnectClient) SetLogLevel(level log.Level) {
+	engine := c.Engine()
+	if engine == nil {
+		return
+	}
+
+	fwManager := engine.GetFirewallManager()
+	if fwManager != nil {
+		fwManager.SetLogLevel(level)
+	}
+}
+
 // Status returns the current client status
 func (c *ConnectClient) Status() StatusType {
 	if c == nil {
@@ -458,7 +471,7 @@ func (c *ConnectClient) SetSyncResponsePersistence(enabled bool) {
 }
 
 // createEngineConfig converts configuration received from Management Service to EngineConfig
-func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConfig *mgmProto.PeerConfig) (*EngineConfig, error) {
+func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConfig *mgmProto.PeerConfig, logPath string) (*EngineConfig, error) {
 	nm := false
 	if config.NetworkMonitor != nil {
 		nm = *config.NetworkMonitor
@@ -493,7 +506,10 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 
 		LazyConnectionEnabled: config.LazyConnectionEnabled,
 
-		MTU: selectMTU(config.MTU, peerConfig.Mtu),
+		MTU:     selectMTU(config.MTU, peerConfig.Mtu),
+		LogPath: logPath,
+
+		ProfileConfig: config,
 	}
 
 	if config.PreSharedKey != "" {

client/internal/debug/debug.go

@@ -28,8 +28,10 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/updatemanager/installer"
+	nbstatus "github.com/netbirdio/netbird/client/status"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/util"
+	"github.com/netbirdio/netbird/version"
 )
 
 const readmeContent = `Netbird debug bundle
@@ -51,7 +53,6 @@ resolved_domains.txt: Anonymized resolved domain IP addresses from the status re
 config.txt: Anonymized configuration information of the NetBird client.
 network_map.json: Anonymized sync response containing peer configurations, routes, DNS settings, and firewall rules.
 state.json: Anonymized client state dump containing netbird states for the active profile.
-metrics.txt: Client metrics in Prometheus format including connection statistics, reliability metrics, and performance indicators.
 mutex.prof: Mutex profiling information.
 goroutine.prof: Goroutine profiling information.
 block.prof: Block profiling information.
@@ -229,11 +230,10 @@ type BundleGenerator struct {
 	internalConfig *profilemanager.Config
 	statusRecorder *peer.Status
 	syncResponse   *mgmProto.SyncResponse
-	logFile        string
+	logPath        string
 	clientMetrics  MetricsExporter
 
 	anonymize         bool
-	clientStatus      string
 	includeSystemInfo bool
 	logFileCount      uint32
 
@@ -242,7 +242,6 @@ type BundleGenerator struct {
 
 type BundleConfig struct {
 	Anonymize         bool
-	ClientStatus      string
 	IncludeSystemInfo bool
 	LogFileCount      uint32
 }
@@ -251,7 +250,7 @@ type GeneratorDependencies struct {
 	InternalConfig *profilemanager.Config
 	StatusRecorder *peer.Status
 	SyncResponse   *mgmProto.SyncResponse
-	LogFile        string
+	LogPath        string
 	ClientMetrics  MetricsExporter
 }
 
@@ -268,11 +267,10 @@ func NewBundleGenerator(deps GeneratorDependencies, cfg BundleConfig) *BundleGen
 		internalConfig: deps.InternalConfig,
 		statusRecorder: deps.StatusRecorder,
 		syncResponse:   deps.SyncResponse,
-		logFile:        deps.LogFile,
+		logPath:        deps.LogPath,
 		clientMetrics:  deps.ClientMetrics,
 
 		anonymize:         cfg.Anonymize,
-		clientStatus:      cfg.ClientStatus,
 		includeSystemInfo: cfg.IncludeSystemInfo,
 		logFileCount:      logFileCount,
 	}
@@ -318,13 +316,6 @@ func (g *BundleGenerator) createArchive() error {
 		return fmt.Errorf("add status: %w", err)
 	}
 
-	if g.statusRecorder != nil {
-		status := g.statusRecorder.GetFullStatus()
-		seedFromStatus(g.anonymizer, &status)
-	} else {
-		log.Debugf("no status recorder available for seeding")
-	}
-
 	if err := g.addConfig(); err != nil {
 		log.Errorf("failed to add config to debug bundle: %v", err)
 	}
@@ -365,7 +356,7 @@ func (g *BundleGenerator) createArchive() error {
 		log.Errorf("failed to add wg show output: %v", err)
 	}
 
-	if g.logFile != "" && !slices.Contains(util.SpecialLogs, g.logFile) {
+	if g.logPath != "" && !slices.Contains(util.SpecialLogs, g.logPath) {
 		if err := g.addLogfile(); err != nil {
 			log.Errorf("failed to add log file to debug bundle: %v", err)
 			if err := g.trySystemdLogFallback(); err != nil {
@@ -414,11 +405,26 @@ func (g *BundleGenerator) addReadme() error {
 }
 
 func (g *BundleGenerator) addStatus() error {
-	if status := g.clientStatus; status != "" {
-		statusReader := strings.NewReader(status)
+	if g.statusRecorder != nil {
+		pm := profilemanager.NewProfileManager()
+		var profName string
+		if activeProf, err := pm.GetActiveProfile(); err == nil {
+			profName = activeProf.Name
+		}
+
+		fullStatus := g.statusRecorder.GetFullStatus()
+		protoFullStatus := nbstatus.ToProtoFullStatus(fullStatus)
+		protoFullStatus.Events = g.statusRecorder.GetEventHistory()
+		overview := nbstatus.ConvertToStatusOutputOverview(protoFullStatus, g.anonymize, version.NetbirdVersion(), "", nil, nil, nil, "", profName)
+		statusOutput := overview.FullDetailSummary()
+
+		statusReader := strings.NewReader(statusOutput)
 		if err := g.addFileToZip(statusReader, "status.txt"); err != nil {
 			return fmt.Errorf("add status file to zip: %w", err)
 		}
+		seedFromStatus(g.anonymizer, &fullStatus)
+	} else {
+		log.Debugf("no status recorder available for seeding")
 	}
 	return nil
 }
@@ -668,25 +674,6 @@ func (g *BundleGenerator) addStateFile() error {
 	return nil
 }
 
-func (g *BundleGenerator) addMetrics() error {
-	if g.clientMetrics == nil {
-		log.Debugf("skipping metrics in debug bundle: no metrics collector")
-		return nil
-	}
-
-	var buf bytes.Buffer
-	if err := g.clientMetrics.Export(&buf); err != nil {
-		return fmt.Errorf("export metrics: %w", err)
-	}
-
-	if err := g.addFileToZip(&buf, "metrics.txt"); err != nil {
-		return fmt.Errorf("add metrics file to zip: %w", err)
-	}
-
-	log.Debugf("added metrics to debug bundle")
-	return nil
-}
-
 func (g *BundleGenerator) addUpdateLogs() error {
 	inst := installer.New()
 	logFiles := inst.LogFiles()
@@ -741,15 +728,34 @@ func (g *BundleGenerator) addCorruptedStateFiles() error {
 	return nil
 }
 
+func (g *BundleGenerator) addMetrics() error {
+	if g.clientMetrics == nil {
+		log.Debugf("skipping metrics in debug bundle: no metrics collector")
+		return nil
+	}
+
+	var buf bytes.Buffer
+	if err := g.clientMetrics.Export(&buf); err != nil {
+		return fmt.Errorf("export metrics: %w", err)
+	}
+
+	if err := g.addFileToZip(&buf, "metrics.txt"); err != nil {
+		return fmt.Errorf("add metrics file to zip: %w", err)
+	}
+
+	log.Debugf("added metrics to debug bundle")
+	return nil
+}
+
 func (g *BundleGenerator) addLogfile() error {
-	if g.logFile == "" {
+	if g.logPath == "" {
 		log.Debugf("skipping empty log file in debug bundle")
 		return nil
 	}
 
-	logDir := filepath.Dir(g.logFile)
+	logDir := filepath.Dir(g.logPath)
 
-	if err := g.addSingleLogfile(g.logFile, clientLogFile); err != nil {
+	if err := g.addSingleLogfile(g.logPath, clientLogFile); err != nil {
 		return fmt.Errorf("add client log file to zip: %w", err)
 	}
 

client/internal/debug/upload.go

@@ -0,0 +1,101 @@
+package debug
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/json"
+	"fmt"
+	"io"
+	"net/http"
+	"os"
+
+	"github.com/netbirdio/netbird/upload-server/types"
+)
+
+const maxBundleUploadSize = 50 * 1024 * 1024
+
+func UploadDebugBundle(ctx context.Context, url, managementURL, filePath string) (key string, err error) {
+	response, err := getUploadURL(ctx, url, managementURL)
+	if err != nil {
+		return "", err
+	}
+
+	err = upload(ctx, filePath, response)
+	if err != nil {
+		return "", err
+	}
+	return response.Key, nil
+}
+
+func upload(ctx context.Context, filePath string, response *types.GetURLResponse) error {
+	fileData, err := os.Open(filePath)
+	if err != nil {
+		return fmt.Errorf("open file: %w", err)
+	}
+
+	defer fileData.Close()
+
+	stat, err := fileData.Stat()
+	if err != nil {
+		return fmt.Errorf("stat file: %w", err)
+	}
+
+	if stat.Size() > maxBundleUploadSize {
+		return fmt.Errorf("file size exceeds maximum limit of %d bytes", maxBundleUploadSize)
+	}
+
+	req, err := http.NewRequestWithContext(ctx, "PUT", response.URL, fileData)
+	if err != nil {
+		return fmt.Errorf("create PUT request: %w", err)
+	}
+
+	req.ContentLength = stat.Size()
+	req.Header.Set("Content-Type", "application/octet-stream")
+
+	putResp, err := http.DefaultClient.Do(req)
+	if err != nil {
+		return fmt.Errorf("upload failed: %v", err)
+	}
+	defer putResp.Body.Close()
+
+	if putResp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(putResp.Body)
+		return fmt.Errorf("upload status %d: %s", putResp.StatusCode, string(body))
+	}
+	return nil
+}
+
+func getUploadURL(ctx context.Context, url string, managementURL string) (*types.GetURLResponse, error) {
+	id := getURLHash(managementURL)
+	getReq, err := http.NewRequestWithContext(ctx, "GET", url+"?id="+id, nil)
+	if err != nil {
+		return nil, fmt.Errorf("create GET request: %w", err)
+	}
+
+	getReq.Header.Set(types.ClientHeader, types.ClientHeaderValue)
+
+	resp, err := http.DefaultClient.Do(getReq)
+	if err != nil {
+		return nil, fmt.Errorf("get presigned URL: %w", err)
+	}
+	defer resp.Body.Close()
+
+	if resp.StatusCode != http.StatusOK {
+		body, _ := io.ReadAll(resp.Body)
+		return nil, fmt.Errorf("get presigned URL status %d: %s", resp.StatusCode, string(body))
+	}
+
+	urlBytes, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return nil, fmt.Errorf("read response body: %w", err)
+	}
+	var response types.GetURLResponse
+	if err := json.Unmarshal(urlBytes, &response); err != nil {
+		return nil, fmt.Errorf("unmarshal response: %w", err)
+	}
+	return &response, nil
+}
+
+func getURLHash(url string) string {
+	return fmt.Sprintf("%x", sha256.Sum256([]byte(url)))
+}

client/internal/debug/upload_test.go

@@ -1,4 +1,4 @@
-package server
+package debug
 
 import (
 	"context"
@@ -38,7 +38,7 @@ func TestUpload(t *testing.T) {
 	fileContent := []byte("test file content")
 	err := os.WriteFile(file, fileContent, 0640)
 	require.NoError(t, err)
-	key, err := uploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file)
+	key, err := UploadDebugBundle(context.Background(), testURL+types.GetURLPath, testURL, file)
 	require.NoError(t, err)
 	id := getURLHash(testURL)
 	require.Contains(t, key, id+"/")

client/internal/debug/wgshow.go

@@ -60,7 +60,7 @@ func (g *BundleGenerator) toWGShowFormat(s *configurer.Stats) string {
 		}
 		sb.WriteString(fmt.Sprintf("  latest handshake: %s\n", peer.LastHandshake.Format(time.RFC1123)))
 		sb.WriteString(fmt.Sprintf("  transfer: %d B received, %d B sent\n", peer.RxBytes, peer.TxBytes))
-		if peer.PresharedKey {
+		if peer.PresharedKey != [32]byte{} {
 			sb.WriteString("  preshared key: (hidden)\n")
 		}
 	}

client/internal/dns.go

@@ -76,7 +76,7 @@ func collectPTRRecords(config *nbdns.Config, prefix netip.Prefix) []nbdns.Simple
 	var records []nbdns.SimpleRecord
 
 	for _, zone := range config.CustomZones {
-		if zone.SkipPTRProcess {
+		if zone.NonAuthoritative {
 			continue
 		}
 		for _, record := range zone.Records {

client/internal/dns/handler_chain.go

@@ -3,17 +3,21 @@ package dns
 import (
 	"fmt"
 	"slices"
+	"strconv"
 	"strings"
 	"sync"
+	"time"
 
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 )
 
 const (
 	PriorityMgmtCache = 150
-	PriorityLocal     = 100
-	PriorityDNSRoute  = 75
+	PriorityDNSRoute  = 100
+	PriorityLocal     = 75
 	PriorityUpstream  = 50
 	PriorityDefault   = 1
 	PriorityFallback  = -100
@@ -43,7 +47,23 @@ type HandlerChain struct {
 type ResponseWriterChain struct {
 	dns.ResponseWriter
 	origPattern    string
+	requestID      string
 	shouldContinue bool
+	response       *dns.Msg
+	meta           map[string]string
+}
+
+// RequestID returns the request ID for tracing
+func (w *ResponseWriterChain) RequestID() string {
+	return w.requestID
+}
+
+// SetMeta sets a metadata key-value pair for logging
+func (w *ResponseWriterChain) SetMeta(key, value string) {
+	if w.meta == nil {
+		w.meta = make(map[string]string)
+	}
+	w.meta[key] = value
 }
 
 func (w *ResponseWriterChain) WriteMsg(m *dns.Msg) error {
@@ -52,6 +72,7 @@ func (w *ResponseWriterChain) WriteMsg(m *dns.Msg) error {
 		w.shouldContinue = true
 		return nil
 	}
+	w.response = m
 	return w.ResponseWriter.WriteMsg(m)
 }
 
@@ -101,6 +122,8 @@ func (c *HandlerChain) AddHandler(pattern string, handler dns.Handler, priority
 
 	pos := c.findHandlerPosition(entry)
 	c.handlers = append(c.handlers[:pos], append([]HandlerEntry{entry}, c.handlers[pos:]...)...)
+
+	c.logHandlers()
 }
 
 // findHandlerPosition determines where to insert a new handler based on priority and specificity
@@ -140,68 +163,109 @@ func (c *HandlerChain) removeEntry(pattern string, priority int) {
 	for i := len(c.handlers) - 1; i >= 0; i-- {
 		entry := c.handlers[i]
 		if strings.EqualFold(entry.OrigPattern, pattern) && entry.Priority == priority {
+			log.Debugf("removing handler pattern: domain=%s priority=%d", entry.OrigPattern, priority)
 			c.handlers = append(c.handlers[:i], c.handlers[i+1:]...)
+			c.logHandlers()
 			break
 		}
 	}
 }
 
+// logHandlers logs the current handler chain state. Caller must hold the lock.
+func (c *HandlerChain) logHandlers() {
+	if !log.IsLevelEnabled(log.TraceLevel) {
+		return
+	}
+
+	var b strings.Builder
+	b.WriteString("handler chain (" + strconv.Itoa(len(c.handlers)) + "):\n")
+	for _, h := range c.handlers {
+		b.WriteString("  - pattern: domain=" + h.Pattern + " original: domain=" + h.OrigPattern +
+			" wildcard=" + strconv.FormatBool(h.IsWildcard) +
+			" match_subdomain=" + strconv.FormatBool(h.MatchSubdomains) +
+			" priority=" + strconv.Itoa(h.Priority) + "\n")
+	}
+	log.Trace(strings.TrimSuffix(b.String(), "\n"))
+}
+
 func (c *HandlerChain) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	if len(r.Question) == 0 {
 		return
 	}
 
-	qname := strings.ToLower(r.Question[0].Name)
+	startTime := time.Now()
+	requestID := resutil.GenerateRequestID()
+	logger := log.WithFields(log.Fields{
+		"request_id": requestID,
+		"dns_id":     fmt.Sprintf("%04x", r.Id),
+	})
+
+	question := r.Question[0]
+	qname := strings.ToLower(question.Name)
 
 	c.mu.RLock()
 	handlers := slices.Clone(c.handlers)
 	c.mu.RUnlock()
 
-	if log.IsLevelEnabled(log.TraceLevel) {
-		var b strings.Builder
-		b.WriteString(fmt.Sprintf("DNS request domain=%s, handlers (%d):\n", qname, len(handlers)))
-		for _, h := range handlers {
-			b.WriteString(fmt.Sprintf("  - pattern: domain=%s original: domain=%s wildcard=%v match_subdomain=%v priority=%d\n",
-				h.Pattern, h.OrigPattern, h.IsWildcard, h.MatchSubdomains, h.Priority))
-		}
-		log.Trace(strings.TrimSuffix(b.String(), "\n"))
-	}
-
 	// Try handlers in priority order
 	for _, entry := range handlers {
-		matched := c.isHandlerMatch(qname, entry)
-
-		if matched {
-			log.Tracef("handler matched: domain=%s -> pattern=%s wildcard=%v match_subdomain=%v priority=%d",
-				qname, entry.OrigPattern, entry.IsWildcard, entry.MatchSubdomains, entry.Priority)
-
-			chainWriter := &ResponseWriterChain{
-				ResponseWriter: w,
-				origPattern:    entry.OrigPattern,
-			}
-			entry.Handler.ServeDNS(chainWriter, r)
-
-			// If handler wants to continue, try next handler
-			if chainWriter.shouldContinue {
-				// Only log continue for non-management cache handlers to reduce noise
-				if entry.Priority != PriorityMgmtCache {
-					log.Tracef("handler requested continue to next handler for domain=%s", qname)
-				}
-				continue
-			}
-			return
+		if !c.isHandlerMatch(qname, entry) {
+			continue
 		}
+
+		handlerName := entry.OrigPattern
+		if s, ok := entry.Handler.(interface{ String() string }); ok {
+			handlerName = s.String()
+		}
+
+		logger.Tracef("question: domain=%s type=%s class=%s -> handler=%s pattern=%s wildcard=%v match_subdomain=%v priority=%d",
+			qname, dns.TypeToString[question.Qtype], dns.ClassToString[question.Qclass],
+			handlerName, entry.OrigPattern, entry.IsWildcard, entry.MatchSubdomains, entry.Priority)
+
+		chainWriter := &ResponseWriterChain{
+			ResponseWriter: w,
+			origPattern:    entry.OrigPattern,
+			requestID:      requestID,
+		}
+		entry.Handler.ServeDNS(chainWriter, r)
+
+		// If handler wants to continue, try next handler
+		if chainWriter.shouldContinue {
+			if entry.Priority != PriorityMgmtCache {
+				logger.Tracef("handler requested continue for domain=%s", qname)
+			}
+			continue
+		}
+
+		c.logResponse(logger, chainWriter, qname, startTime)
+		return
 	}
 
 	// No handler matched or all handlers passed
-	log.Tracef("no handler found for domain=%s", qname)
+	logger.Tracef("no handler found for domain=%s type=%s class=%s",
+		qname, dns.TypeToString[question.Qtype], dns.ClassToString[question.Qclass])
 	resp := &dns.Msg{}
 	resp.SetRcode(r, dns.RcodeRefused)
 	if err := w.WriteMsg(resp); err != nil {
-		log.Errorf("failed to write DNS response: %v", err)
+		logger.Errorf("failed to write DNS response: %v", err)
 	}
 }
 
+func (c *HandlerChain) logResponse(logger *log.Entry, cw *ResponseWriterChain, qname string, startTime time.Time) {
+	if cw.response == nil {
+		return
+	}
+
+	var meta string
+	for k, v := range cw.meta {
+		meta += " " + k + "=" + v
+	}
+
+	logger.Tracef("response: domain=%s rcode=%s answers=%s%s took=%s",
+		qname, dns.RcodeToString[cw.response.Rcode], resutil.FormatAnswers(cw.response.Answer),
+		meta, time.Since(startTime))
+}
+
 func (c *HandlerChain) isHandlerMatch(qname string, entry HandlerEntry) bool {
 	switch {
 	case entry.Pattern == ".":

client/internal/dns/local/local.go

@@ -1,30 +1,52 @@
 package local
 
 import (
+	"context"
+	"errors"
 	"fmt"
+	"net"
+	"net/netip"
 	"slices"
 	"strings"
 	"sync"
+	"time"
 
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/exp/maps"
 
+	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/dns/types"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
+const externalResolutionTimeout = 4 * time.Second
+
+type resolver interface {
+	LookupNetIP(ctx context.Context, network, host string) ([]netip.Addr, error)
+}
+
 type Resolver struct {
 	mu      sync.RWMutex
 	records map[dns.Question][]dns.RR
 	domains map[domain.Domain]struct{}
+	// zones maps zone domain -> NonAuthoritative (true = non-authoritative, user-created zone)
+	zones    map[domain.Domain]bool
+	resolver resolver
+
+	ctx    context.Context
+	cancel context.CancelFunc
 }
 
 func NewResolver() *Resolver {
+	ctx, cancel := context.WithCancel(context.Background())
 	return &Resolver{
 		records: make(map[dns.Question][]dns.RR),
 		domains: make(map[domain.Domain]struct{}),
+		zones:   make(map[domain.Domain]bool),
+		ctx:     ctx,
+		cancel:  cancel,
 	}
 }
 
@@ -37,7 +59,18 @@ func (d *Resolver) String() string {
 	return fmt.Sprintf("LocalResolver [%d records]", len(d.records))
 }
 
-func (d *Resolver) Stop() {}
+func (d *Resolver) Stop() {
+	if d.cancel != nil {
+		d.cancel()
+	}
+
+	d.mu.Lock()
+	defer d.mu.Unlock()
+
+	maps.Clear(d.records)
+	maps.Clear(d.domains)
+	maps.Clear(d.zones)
+}
 
 // ID returns the unique handler ID
 func (d *Resolver) ID() types.HandlerID {
@@ -48,60 +81,147 @@ func (d *Resolver) ProbeAvailability() {}
 
 // ServeDNS handles a DNS request
 func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
+	logger := log.WithField("request_id", resutil.GetRequestID(w))
+
 	if len(r.Question) == 0 {
-		log.Debugf("received local resolver request with no question")
+		logger.Debug("received local resolver request with no question")
 		return
 	}
 	question := r.Question[0]
 	question.Name = strings.ToLower(dns.Fqdn(question.Name))
 
-	log.Tracef("received local question: domain=%s type=%v class=%v", r.Question[0].Name, question.Qtype, question.Qclass)
-
 	replyMessage := &dns.Msg{}
 	replyMessage.SetReply(r)
 	replyMessage.RecursionAvailable = true
 
-	// lookup all records matching the question
-	records := d.lookupRecords(question)
-	if len(records) > 0 {
-		replyMessage.Rcode = dns.RcodeSuccess
-		replyMessage.Answer = append(replyMessage.Answer, records...)
-	} else {
-		// Check if we have any records for this domain name with different types
-		if d.hasRecordsForDomain(domain.Domain(question.Name)) {
-			replyMessage.Rcode = dns.RcodeSuccess // NOERROR with 0 records
-		} else {
-			replyMessage.Rcode = dns.RcodeNameError // NXDOMAIN
-		}
+	result := d.lookupRecords(logger, question)
+	replyMessage.Authoritative = !result.hasExternalData
+	replyMessage.Answer = result.records
+	replyMessage.Rcode = d.determineRcode(question, result)
+
+	if replyMessage.Rcode == dns.RcodeNameError && d.shouldFallthrough(question.Name) {
+		d.continueToNext(logger, w, r)
+		return
 	}
 
 	if err := w.WriteMsg(replyMessage); err != nil {
-		log.Warnf("failed to write the local resolver response: %v", err)
+		logger.Warnf("failed to write the local resolver response: %v", err)
+	}
+}
+
+// determineRcode returns the appropriate DNS response code.
+// Per RFC 6604, CNAME chains should return the rcode of the final target resolution,
+// even if CNAME records are included in the answer.
+func (d *Resolver) determineRcode(question dns.Question, result lookupResult) int {
+	// Use the rcode from lookup - this properly handles CNAME chains where
+	// the target may be NXDOMAIN or SERVFAIL even though we have CNAME records
+	if result.rcode != 0 {
+		return result.rcode
+	}
+
+	// No records found, but domain exists with different record types (NODATA)
+	if d.hasRecordsForDomain(domain.Domain(question.Name), question.Qtype) {
+		return dns.RcodeSuccess
+	}
+
+	return dns.RcodeNameError
+}
+
+// findZone finds the matching zone for a query name using reverse suffix lookup.
+// Returns (nonAuthoritative, found). This is O(k) where k = number of labels in qname.
+func (d *Resolver) findZone(qname string) (nonAuthoritative bool, found bool) {
+	qname = strings.ToLower(dns.Fqdn(qname))
+	for {
+		if nonAuth, ok := d.zones[domain.Domain(qname)]; ok {
+			return nonAuth, true
+		}
+		// Move to parent domain
+		idx := strings.Index(qname, ".")
+		if idx == -1 || idx == len(qname)-1 {
+			return false, false
+		}
+		qname = qname[idx+1:]
+	}
+}
+
+// shouldFallthrough checks if the query should fallthrough to the next handler.
+// Returns true if the queried name belongs to a non-authoritative zone.
+func (d *Resolver) shouldFallthrough(qname string) bool {
+	d.mu.RLock()
+	defer d.mu.RUnlock()
+
+	nonAuth, found := d.findZone(qname)
+	return found && nonAuth
+}
+
+func (d *Resolver) continueToNext(logger *log.Entry, w dns.ResponseWriter, r *dns.Msg) {
+	resp := &dns.Msg{}
+	resp.SetRcode(r, dns.RcodeNameError)
+	resp.MsgHdr.Zero = true
+	if err := w.WriteMsg(resp); err != nil {
+		logger.Warnf("failed to write continue signal: %v", err)
 	}
 }
 
 // hasRecordsForDomain checks if any records exist for the given domain name regardless of type
-func (d *Resolver) hasRecordsForDomain(domainName domain.Domain) bool {
+func (d *Resolver) hasRecordsForDomain(domainName domain.Domain, qType uint16) bool {
 	d.mu.RLock()
 	defer d.mu.RUnlock()
 
 	_, exists := d.domains[domainName]
+	if !exists && supportsWildcard(qType) {
+		testWild := transformDomainToWildcard(string(domainName))
+		_, exists = d.domains[domain.Domain(testWild)]
+	}
 	return exists
 }
 
+// isInManagedZone checks if the given name falls within any of our managed zones.
+// This is used to avoid unnecessary external resolution for CNAME targets that
+// are within zones we manage - if we don't have a record for it, it doesn't exist.
+// Caller must NOT hold the lock.
+func (d *Resolver) isInManagedZone(name string) bool {
+	d.mu.RLock()
+	defer d.mu.RUnlock()
+
+	_, found := d.findZone(name)
+	return found
+}
+
+// lookupResult contains the result of a DNS lookup operation.
+type lookupResult struct {
+	records         []dns.RR
+	rcode           int
+	hasExternalData bool
+}
+
 // lookupRecords fetches *all* DNS records matching the first question in r.
-func (d *Resolver) lookupRecords(question dns.Question) []dns.RR {
+func (d *Resolver) lookupRecords(logger *log.Entry, question dns.Question) lookupResult {
 	d.mu.RLock()
 	records, found := d.records[question]
+	usingWildcard := false
+	wildQuestion := transformToWildcard(question)
+	// RFC 4592 section 2.2.1: wildcard only matches if the name does NOT exist in the zone.
+	// If the domain exists with any record type, return NODATA instead of wildcard match.
+	if !found && supportsWildcard(question.Qtype) {
+		if _, domainExists := d.domains[domain.Domain(question.Name)]; !domainExists {
+			records, found = d.records[wildQuestion]
+			usingWildcard = found
+		}
+	}
 
 	if !found {
 		d.mu.RUnlock()
 		// alternatively check if we have a cname
 		if question.Qtype != dns.TypeCNAME {
-			question.Qtype = dns.TypeCNAME
-			return d.lookupRecords(question)
+			cnameQuestion := dns.Question{
+				Name:   question.Name,
+				Qtype:  dns.TypeCNAME,
+				Qclass: question.Qclass,
+			}
+			return d.lookupCNAMEChain(logger, cnameQuestion, question.Qtype)
 		}
-		return nil
+		return lookupResult{rcode: dns.RcodeNameError}
 	}
 
 	recordsCopy := slices.Clone(records)
@@ -110,29 +230,229 @@ func (d *Resolver) lookupRecords(question dns.Question) []dns.RR {
 	// if there's more than one record, rotate them (round-robin)
 	if len(recordsCopy) > 1 {
 		d.mu.Lock()
-		records = d.records[question]
+		q := question
+		if usingWildcard {
+			q = wildQuestion
+		}
+		records = d.records[q]
 		if len(records) > 1 {
 			first := records[0]
 			records = append(records[1:], first)
-			d.records[question] = records
+			d.records[q] = records
 		}
 		d.mu.Unlock()
 	}
 
-	return recordsCopy
+	if usingWildcard {
+		return responseFromWildRecords(question.Name, wildQuestion.Name, recordsCopy)
+	}
+
+	return lookupResult{records: recordsCopy, rcode: dns.RcodeSuccess}
 }
 
-func (d *Resolver) Update(update []nbdns.SimpleRecord) {
+func transformToWildcard(question dns.Question) dns.Question {
+	wildQuestion := question
+	wildQuestion.Name = transformDomainToWildcard(wildQuestion.Name)
+	return wildQuestion
+}
+
+func transformDomainToWildcard(domain string) string {
+	s := strings.Split(domain, ".")
+	s[0] = "*"
+	return strings.Join(s, ".")
+}
+
+func supportsWildcard(queryType uint16) bool {
+	return queryType != dns.TypeNS && queryType != dns.TypeSOA
+}
+
+func responseFromWildRecords(originalName, wildName string, wildRecords []dns.RR) lookupResult {
+	records := make([]dns.RR, len(wildRecords))
+	for i, record := range wildRecords {
+		copiedRecord := dns.Copy(record)
+		copiedRecord.Header().Name = originalName
+		records[i] = copiedRecord
+	}
+
+	return lookupResult{records: records, rcode: dns.RcodeSuccess}
+}
+
+// lookupCNAMEChain follows a CNAME chain and returns the CNAME records along with
+// the final resolved record of the requested type. This is required for musl libc
+// compatibility, which expects the full answer chain rather than just the CNAME.
+func (d *Resolver) lookupCNAMEChain(logger *log.Entry, cnameQuestion dns.Question, targetType uint16) lookupResult {
+	const maxDepth = 8
+	var chain []dns.RR
+
+	for range maxDepth {
+		cnameRecords := d.getRecords(cnameQuestion)
+		if len(cnameRecords) == 0 && supportsWildcard(targetType) {
+			wildQuestion := transformToWildcard(cnameQuestion)
+			if wildRecords := d.getRecords(wildQuestion); len(wildRecords) > 0 {
+				cnameRecords = responseFromWildRecords(cnameQuestion.Name, wildQuestion.Name, wildRecords).records
+			}
+		}
+
+		if len(cnameRecords) == 0 {
+			break
+		}
+
+		chain = append(chain, cnameRecords...)
+
+		cname, ok := cnameRecords[0].(*dns.CNAME)
+		if !ok {
+			break
+		}
+
+		targetName := strings.ToLower(cname.Target)
+		targetResult := d.resolveCNAMETarget(logger, targetName, targetType, cnameQuestion.Qclass)
+
+		// keep following chain
+		if targetResult.rcode == -1 {
+			cnameQuestion = dns.Question{Name: targetName, Qtype: dns.TypeCNAME, Qclass: cnameQuestion.Qclass}
+			continue
+		}
+
+		return d.buildChainResult(chain, targetResult)
+	}
+
+	if len(chain) > 0 {
+		return lookupResult{records: chain, rcode: dns.RcodeSuccess}
+	}
+	return lookupResult{rcode: dns.RcodeSuccess}
+}
+
+// buildChainResult combines CNAME chain records with the target resolution result.
+// Per RFC 6604, the final rcode is propagated through the chain.
+func (d *Resolver) buildChainResult(chain []dns.RR, target lookupResult) lookupResult {
+	records := chain
+	if len(target.records) > 0 {
+		records = append(records, target.records...)
+	}
+
+	// preserve hasExternalData for SERVFAIL so caller knows the error came from upstream
+	if target.hasExternalData && target.rcode == dns.RcodeServerFailure {
+		return lookupResult{
+			records:         records,
+			rcode:           dns.RcodeServerFailure,
+			hasExternalData: true,
+		}
+	}
+
+	return lookupResult{
+		records:         records,
+		rcode:           target.rcode,
+		hasExternalData: target.hasExternalData,
+	}
+}
+
+// resolveCNAMETarget attempts to resolve a CNAME target name.
+// Returns rcode=-1 to signal "keep following the chain".
+func (d *Resolver) resolveCNAMETarget(logger *log.Entry, targetName string, targetType uint16, qclass uint16) lookupResult {
+	if records := d.getRecords(dns.Question{Name: targetName, Qtype: targetType, Qclass: qclass}); len(records) > 0 {
+		return lookupResult{records: records, rcode: dns.RcodeSuccess}
+	}
+
+	// another CNAME, keep following
+	if d.hasRecord(dns.Question{Name: targetName, Qtype: dns.TypeCNAME, Qclass: qclass}) {
+		return lookupResult{rcode: -1}
+	}
+
+	// domain exists locally but not this record type (NODATA)
+	if d.hasRecordsForDomain(domain.Domain(targetName), targetType) {
+		return lookupResult{rcode: dns.RcodeSuccess}
+	}
+
+	// in our zone but doesn't exist (NXDOMAIN)
+	if d.isInManagedZone(targetName) {
+		return lookupResult{rcode: dns.RcodeNameError}
+	}
+
+	return d.resolveExternal(logger, targetName, targetType)
+}
+
+func (d *Resolver) getRecords(q dns.Question) []dns.RR {
+	d.mu.RLock()
+	defer d.mu.RUnlock()
+	return d.records[q]
+}
+
+func (d *Resolver) hasRecord(q dns.Question) bool {
+	d.mu.RLock()
+	defer d.mu.RUnlock()
+	_, ok := d.records[q]
+	return ok
+}
+
+// resolveExternal resolves a domain name using the system resolver.
+// This is used to resolve CNAME targets that point outside our local zone,
+// which is required for musl libc compatibility (musl expects complete answers).
+func (d *Resolver) resolveExternal(logger *log.Entry, name string, qtype uint16) lookupResult {
+	network := resutil.NetworkForQtype(qtype)
+	if network == "" {
+		return lookupResult{rcode: dns.RcodeNotImplemented}
+	}
+
+	resolver := d.resolver
+	if resolver == nil {
+		resolver = net.DefaultResolver
+	}
+
+	ctx, cancel := context.WithTimeout(d.ctx, externalResolutionTimeout)
+	defer cancel()
+
+	result := resutil.LookupIP(ctx, resolver, network, name, qtype)
+	if result.Err != nil {
+		d.logDNSError(logger, name, qtype, result.Err)
+		return lookupResult{rcode: result.Rcode, hasExternalData: true}
+	}
+
+	return lookupResult{
+		records:         resutil.IPsToRRs(name, result.IPs, 60),
+		rcode:           dns.RcodeSuccess,
+		hasExternalData: true,
+	}
+}
+
+// logDNSError logs DNS resolution errors for debugging.
+func (d *Resolver) logDNSError(logger *log.Entry, hostname string, qtype uint16, err error) {
+	qtypeName := dns.TypeToString[qtype]
+
+	var dnsErr *net.DNSError
+	if !errors.As(err, &dnsErr) {
+		logger.Debugf("DNS resolution failed for %s type %s: %v", hostname, qtypeName, err)
+		return
+	}
+
+	if dnsErr.IsNotFound {
+		logger.Tracef("DNS target not found: %s type %s", hostname, qtypeName)
+		return
+	}
+
+	if dnsErr.Server != "" {
+		logger.Debugf("DNS resolution failed for %s type %s server=%s: %v", hostname, qtypeName, dnsErr.Server, err)
+	} else {
+		logger.Debugf("DNS resolution failed for %s type %s: %v", hostname, qtypeName, err)
+	}
+}
+
+// Update replaces all zones and their records
+func (d *Resolver) Update(customZones []nbdns.CustomZone) {
 	d.mu.Lock()
 	defer d.mu.Unlock()
 
 	maps.Clear(d.records)
 	maps.Clear(d.domains)
+	maps.Clear(d.zones)
 
-	for _, rec := range update {
-		if err := d.registerRecord(rec); err != nil {
-			log.Warnf("failed to register the record (%s): %v", rec, err)
-			continue
+	for _, zone := range customZones {
+		zoneDomain := domain.Domain(strings.ToLower(dns.Fqdn(zone.Domain)))
+		d.zones[zoneDomain] = zone.NonAuthoritative
+
+		for _, rec := range zone.Records {
+			if err := d.registerRecord(rec); err != nil {
+				log.Warnf("failed to register the record (%s): %v", rec, err)
+			}
 		}
 	}
 }

client/internal/dns/resutil/resolve.go

@@ -0,0 +1,197 @@
+// Package resutil provides shared DNS resolution utilities
+package resutil
+
+import (
+	"context"
+	"crypto/rand"
+	"encoding/hex"
+	"errors"
+	"net"
+	"net/netip"
+	"strings"
+
+	"github.com/miekg/dns"
+	log "github.com/sirupsen/logrus"
+)
+
+// GenerateRequestID creates a random 8-character hex string for request tracing.
+func GenerateRequestID() string {
+	bytes := make([]byte, 4)
+	if _, err := rand.Read(bytes); err != nil {
+		log.Errorf("generate request ID: %v", err)
+		return ""
+	}
+	return hex.EncodeToString(bytes)
+}
+
+// IPsToRRs converts a slice of IP addresses to DNS resource records.
+// IPv4 addresses become A records, IPv6 addresses become AAAA records.
+func IPsToRRs(name string, ips []netip.Addr, ttl uint32) []dns.RR {
+	var result []dns.RR
+
+	for _, ip := range ips {
+		if ip.Is6() {
+			result = append(result, &dns.AAAA{
+				Hdr: dns.RR_Header{
+					Name:   name,
+					Rrtype: dns.TypeAAAA,
+					Class:  dns.ClassINET,
+					Ttl:    ttl,
+				},
+				AAAA: ip.AsSlice(),
+			})
+		} else {
+			result = append(result, &dns.A{
+				Hdr: dns.RR_Header{
+					Name:   name,
+					Rrtype: dns.TypeA,
+					Class:  dns.ClassINET,
+					Ttl:    ttl,
+				},
+				A: ip.AsSlice(),
+			})
+		}
+	}
+
+	return result
+}
+
+// NetworkForQtype returns the network string ("ip4" or "ip6") for a DNS query type.
+// Returns empty string for unsupported types.
+func NetworkForQtype(qtype uint16) string {
+	switch qtype {
+	case dns.TypeA:
+		return "ip4"
+	case dns.TypeAAAA:
+		return "ip6"
+	default:
+		return ""
+	}
+}
+
+type resolver interface {
+	LookupNetIP(ctx context.Context, network, host string) ([]netip.Addr, error)
+}
+
+// chainedWriter is implemented by ResponseWriters that carry request metadata
+type chainedWriter interface {
+	RequestID() string
+	SetMeta(key, value string)
+}
+
+// GetRequestID extracts a request ID from the ResponseWriter if available,
+// otherwise generates a new one.
+func GetRequestID(w dns.ResponseWriter) string {
+	if cw, ok := w.(chainedWriter); ok {
+		if id := cw.RequestID(); id != "" {
+			return id
+		}
+	}
+	return GenerateRequestID()
+}
+
+// SetMeta sets metadata on the ResponseWriter if it supports it.
+func SetMeta(w dns.ResponseWriter, key, value string) {
+	if cw, ok := w.(chainedWriter); ok {
+		cw.SetMeta(key, value)
+	}
+}
+
+// LookupResult contains the result of an external DNS lookup
+type LookupResult struct {
+	IPs   []netip.Addr
+	Rcode int
+	Err   error // Original error for caller's logging needs
+}
+
+// LookupIP performs a DNS lookup and determines the appropriate rcode.
+func LookupIP(ctx context.Context, r resolver, network, host string, qtype uint16) LookupResult {
+	ips, err := r.LookupNetIP(ctx, network, host)
+	if err != nil {
+		return LookupResult{
+			Rcode: getRcodeForError(ctx, r, host, qtype, err),
+			Err:   err,
+		}
+	}
+
+	// Unmap IPv4-mapped IPv6 addresses that some resolvers may return
+	for i, ip := range ips {
+		ips[i] = ip.Unmap()
+	}
+
+	return LookupResult{
+		IPs:   ips,
+		Rcode: dns.RcodeSuccess,
+	}
+}
+
+func getRcodeForError(ctx context.Context, r resolver, host string, qtype uint16, err error) int {
+	var dnsErr *net.DNSError
+	if !errors.As(err, &dnsErr) {
+		return dns.RcodeServerFailure
+	}
+
+	if dnsErr.IsNotFound {
+		return getRcodeForNotFound(ctx, r, host, qtype)
+	}
+
+	return dns.RcodeServerFailure
+}
+
+// getRcodeForNotFound distinguishes between NXDOMAIN (domain doesn't exist) and NODATA
+// (domain exists but no records of requested type) by checking the opposite record type.
+//
+// musl libc (the reason we need this distinction) only queries A/AAAA pairs in getaddrinfo,
+// so checking the opposite A/AAAA type is sufficient. Other record types (MX, TXT, etc.)
+// are not queried by musl and don't need this handling.
+func getRcodeForNotFound(ctx context.Context, r resolver, domain string, originalQtype uint16) int {
+	// Try querying for a different record type to see if the domain exists
+	// If the original query was for AAAA, try A. If it was for A, try AAAA.
+	// This helps distinguish between NXDOMAIN and NODATA.
+	var alternativeNetwork string
+	switch originalQtype {
+	case dns.TypeAAAA:
+		alternativeNetwork = "ip4"
+	case dns.TypeA:
+		alternativeNetwork = "ip6"
+	default:
+		return dns.RcodeNameError
+	}
+
+	if _, err := r.LookupNetIP(ctx, alternativeNetwork, domain); err != nil {
+		var dnsErr *net.DNSError
+		if errors.As(err, &dnsErr) && dnsErr.IsNotFound {
+			// Alternative query also returned not found - domain truly doesn't exist
+			return dns.RcodeNameError
+		}
+		// Some other error (timeout, server failure, etc.) - can't determine, assume domain exists
+		return dns.RcodeSuccess
+	}
+
+	// Alternative query succeeded - domain exists but has no records of this type
+	return dns.RcodeSuccess
+}
+
+// FormatAnswers formats DNS resource records for logging.
+func FormatAnswers(answers []dns.RR) string {
+	if len(answers) == 0 {
+		return "[]"
+	}
+
+	parts := make([]string, 0, len(answers))
+	for _, rr := range answers {
+		switch r := rr.(type) {
+		case *dns.A:
+			parts = append(parts, r.A.String())
+		case *dns.AAAA:
+			parts = append(parts, r.AAAA.String())
+		case *dns.CNAME:
+			parts = append(parts, "CNAME:"+r.Target)
+		case *dns.PTR:
+			parts = append(parts, "PTR:"+r.Ptr)
+		default:
+			parts = append(parts, dns.TypeToString[rr.Header().Rrtype])
+		}
+	}
+	return "[" + strings.Join(parts, ", ") + "]"
+}

client/internal/dns/server.go

@@ -485,7 +485,7 @@ func (s *DefaultServer) applyConfiguration(update nbdns.Config) error {
 		}
 	}
 
-	localMuxUpdates, localRecords, err := s.buildLocalHandlerUpdate(update.CustomZones)
+	localMuxUpdates, localZones, err := s.buildLocalHandlerUpdate(update.CustomZones)
 	if err != nil {
 		return fmt.Errorf("local handler updater: %w", err)
 	}
@@ -498,8 +498,7 @@ func (s *DefaultServer) applyConfiguration(update nbdns.Config) error {
 
 	s.updateMux(muxUpdates)
 
-	// register local records
-	s.localResolver.Update(localRecords)
+	s.localResolver.Update(localZones)
 
 	s.currentConfig = dnsConfigToHostDNSConfig(update, s.service.RuntimeIP(), s.service.RuntimePort())
 
@@ -632,9 +631,7 @@ func (s *DefaultServer) registerFallback(config HostDNSConfig) {
 
 	handler, err := newUpstreamResolver(
 		s.ctx,
-		s.wgInterface.Name(),
-		s.wgInterface.Address().IP,
-		s.wgInterface.Address().Network,
+		s.wgInterface,
 		s.statusRecorder,
 		s.hostsDNSHolder,
 		nbdns.RootZone,
@@ -659,9 +656,9 @@ func (s *DefaultServer) registerFallback(config HostDNSConfig) {
 	s.registerHandler([]string{nbdns.RootZone}, handler, PriorityFallback)
 }
 
-func (s *DefaultServer) buildLocalHandlerUpdate(customZones []nbdns.CustomZone) ([]handlerWrapper, []nbdns.SimpleRecord, error) {
+func (s *DefaultServer) buildLocalHandlerUpdate(customZones []nbdns.CustomZone) ([]handlerWrapper, []nbdns.CustomZone, error) {
 	var muxUpdates []handlerWrapper
-	var localRecords []nbdns.SimpleRecord
+	var zones []nbdns.CustomZone
 
 	for _, customZone := range customZones {
 		if len(customZone.Records) == 0 {
@@ -675,17 +672,20 @@ func (s *DefaultServer) buildLocalHandlerUpdate(customZones []nbdns.CustomZone)
 			priority: PriorityLocal,
 		})
 
+		// zone records contain the fqdn, so we can just flatten them
+		var localRecords []nbdns.SimpleRecord
 		for _, record := range customZone.Records {
 			if record.Class != nbdns.DefaultClass {
 				log.Warnf("received an invalid class type: %s", record.Class)
 				continue
 			}
-			// zone records contain the fqdn, so we can just flatten them
 			localRecords = append(localRecords, record)
 		}
+		customZone.Records = localRecords
+		zones = append(zones, customZone)
 	}
 
-	return muxUpdates, localRecords, nil
+	return muxUpdates, zones, nil
 }
 
 func (s *DefaultServer) buildUpstreamHandlerUpdate(nameServerGroups []*nbdns.NameServerGroup) ([]handlerWrapper, error) {
@@ -741,9 +741,7 @@ func (s *DefaultServer) createHandlersForDomainGroup(domainGroup nsGroupsByDomai
 		log.Debugf("creating handler for domain=%s with priority=%d", domainGroup.domain, priority)
 		handler, err := newUpstreamResolver(
 			s.ctx,
-			s.wgInterface.Name(),
-			s.wgInterface.Address().IP,
-			s.wgInterface.Address().Network,
+			s.wgInterface,
 			s.statusRecorder,
 			s.hostsDNSHolder,
 			domainGroup.domain,
@@ -924,9 +922,7 @@ func (s *DefaultServer) addHostRootZone() {
 
 	handler, err := newUpstreamResolver(
 		s.ctx,
-		s.wgInterface.Name(),
-		s.wgInterface.Address().IP,
-		s.wgInterface.Address().Network,
+		s.wgInterface,
 		s.statusRecorder,
 		s.hostsDNSHolder,
 		nbdns.RootZone,

client/internal/dns/server_test.go

@@ -15,6 +15,7 @@ import (
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/mock"
+	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
 	"github.com/netbirdio/netbird/client/firewall/uspfilter"
@@ -81,6 +82,10 @@ func (w *mocWGIface) GetStats(_ string) (configurer.WGStats, error) {
 	return configurer.WGStats{}, nil
 }
 
+func (w *mocWGIface) GetNet() *netstack.Net {
+	return nil
+}
+
 var zoneRecords = []nbdns.SimpleRecord{
 	{
 		Name:  "peera.netbird.cloud",
@@ -128,7 +133,7 @@ func TestUpdateDNSServer(t *testing.T) {
 	testCases := []struct {
 		name                string
 		initUpstreamMap     registeredHandlerMap
-		initLocalRecords    []nbdns.SimpleRecord
+		initLocalZones      []nbdns.CustomZone
 		initSerial          uint64
 		inputSerial         uint64
 		inputUpdate         nbdns.Config
@@ -180,8 +185,8 @@ func TestUpdateDNSServer(t *testing.T) {
 			expectedLocalQs: []dns.Question{{Name: "peera.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}},
 		},
 		{
-			name:             "New Config Should Succeed",
-			initLocalRecords: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}},
+			name:           "New Config Should Succeed",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
 			initUpstreamMap: registeredHandlerMap{
 				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
 					domain:   "netbird.cloud",
@@ -221,19 +226,19 @@ func TestUpdateDNSServer(t *testing.T) {
 			expectedLocalQs: []dns.Question{{Name: zoneRecords[0].Name, Qtype: 1, Qclass: 1}},
 		},
 		{
-			name:             "Smaller Config Serial Should Be Skipped",
-			initLocalRecords: []nbdns.SimpleRecord{},
-			initUpstreamMap:  make(registeredHandlerMap),
-			initSerial:       2,
-			inputSerial:      1,
-			shouldFail:       true,
+			name:            "Smaller Config Serial Should Be Skipped",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      2,
+			inputSerial:     1,
+			shouldFail:      true,
 		},
 		{
-			name:             "Empty NS Group Domain Or Not Primary Element Should Fail",
-			initLocalRecords: []nbdns.SimpleRecord{},
-			initUpstreamMap:  make(registeredHandlerMap),
-			initSerial:       0,
-			inputSerial:      1,
+			name:            "Empty NS Group Domain Or Not Primary Element Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
 			inputUpdate: nbdns.Config{
 				ServiceEnable: true,
 				CustomZones: []nbdns.CustomZone{
@@ -251,11 +256,11 @@ func TestUpdateDNSServer(t *testing.T) {
 			shouldFail: true,
 		},
 		{
-			name:             "Invalid NS Group Nameservers list Should Fail",
-			initLocalRecords: []nbdns.SimpleRecord{},
-			initUpstreamMap:  make(registeredHandlerMap),
-			initSerial:       0,
-			inputSerial:      1,
+			name:            "Invalid NS Group Nameservers list Should Fail",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
 			inputUpdate: nbdns.Config{
 				ServiceEnable: true,
 				CustomZones: []nbdns.CustomZone{
@@ -273,11 +278,11 @@ func TestUpdateDNSServer(t *testing.T) {
 			shouldFail: true,
 		},
 		{
-			name:             "Invalid Custom Zone Records list Should Skip",
-			initLocalRecords: []nbdns.SimpleRecord{},
-			initUpstreamMap:  make(registeredHandlerMap),
-			initSerial:       0,
-			inputSerial:      1,
+			name:            "Invalid Custom Zone Records list Should Skip",
+			initLocalZones:  []nbdns.CustomZone{},
+			initUpstreamMap: make(registeredHandlerMap),
+			initSerial:      0,
+			inputSerial:     1,
 			inputUpdate: nbdns.Config{
 				ServiceEnable: true,
 				CustomZones: []nbdns.CustomZone{
@@ -299,8 +304,8 @@ func TestUpdateDNSServer(t *testing.T) {
 			}},
 		},
 		{
-			name:             "Empty Config Should Succeed and Clean Maps",
-			initLocalRecords: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}},
+			name:           "Empty Config Should Succeed and Clean Maps",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
 			initUpstreamMap: registeredHandlerMap{
 				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
 					domain:   zoneRecords[0].Name,
@@ -315,8 +320,8 @@ func TestUpdateDNSServer(t *testing.T) {
 			expectedLocalQs:     []dns.Question{},
 		},
 		{
-			name:             "Disabled Service Should clean map",
-			initLocalRecords: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}},
+			name:           "Disabled Service Should clean map",
+			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
 			initUpstreamMap: registeredHandlerMap{
 				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
 					domain:   zoneRecords[0].Name,
@@ -385,7 +390,7 @@ func TestUpdateDNSServer(t *testing.T) {
 			}()
 
 			dnsServer.dnsMuxMap = testCase.initUpstreamMap
-			dnsServer.localResolver.Update(testCase.initLocalRecords)
+			dnsServer.localResolver.Update(testCase.initLocalZones)
 			dnsServer.updateSerial = testCase.initSerial
 
 			err = dnsServer.UpdateDNSServer(testCase.inputSerial, testCase.inputUpdate)
@@ -510,8 +515,7 @@ func TestDNSFakeResolverHandleUpdates(t *testing.T) {
 			priority: PriorityUpstream,
 		},
 	}
-	//dnsServer.localResolver.RegisteredMap = local.RegistrationMap{local.BuildRecordKey("netbird.cloud", dns.ClassINET, dns.TypeA): struct{}{}}
-	dnsServer.localResolver.Update([]nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}})
+	dnsServer.localResolver.Update([]nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}})
 	dnsServer.updateSerial = 0
 
 	nameServers := []nbdns.NameServer{
@@ -2048,7 +2052,7 @@ func TestLocalResolverPriorityInServer(t *testing.T) {
 
 func TestLocalResolverPriorityConstants(t *testing.T) {
 	// Test that priority constants are ordered correctly
-	assert.Greater(t, PriorityLocal, PriorityDNSRoute, "Local priority should be higher than DNS route")
+	assert.Greater(t, PriorityDNSRoute, PriorityLocal, "DNS Route should be higher than Local priority")
 	assert.Greater(t, PriorityLocal, PriorityUpstream, "Local priority should be higher than upstream")
 	assert.Greater(t, PriorityUpstream, PriorityDefault, "Upstream priority should be higher than default")
 

client/internal/dns/upstream.go

@@ -2,7 +2,6 @@ package dns
 
 import (
 	"context"
-	"crypto/rand"
 	"crypto/sha256"
 	"encoding/hex"
 	"errors"
@@ -19,8 +18,10 @@ import (
 	"github.com/hashicorp/go-multierror"
 	"github.com/miekg/dns"
 	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/iface"
+	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/dns/types"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/proto"
@@ -113,10 +114,7 @@ func (u *upstreamResolverBase) Stop() {
 
 // ServeDNS handles a DNS request
 func (u *upstreamResolverBase) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
-	requestID := GenerateRequestID()
-	logger := log.WithField("request_id", requestID)
-
-	logger.Tracef("received upstream question: domain=%s type=%v class=%v", r.Question[0].Name, r.Question[0].Qtype, r.Question[0].Qclass)
+	logger := log.WithField("request_id", resutil.GetRequestID(w))
 
 	u.prepareRequest(r)
 
@@ -202,11 +200,18 @@ func (u *upstreamResolverBase) handleUpstreamError(err error, upstream netip.Add
 
 func (u *upstreamResolverBase) writeSuccessResponse(w dns.ResponseWriter, rm *dns.Msg, upstream netip.AddrPort, domain string, t time.Duration, logger *log.Entry) bool {
 	u.successCount.Add(1)
-	logger.Tracef("took %s to query the upstream %s for question domain=%s", t, upstream, domain)
+
+	resutil.SetMeta(w, "upstream", upstream.String())
+
+	// Clear Zero bit from external responses to prevent upstream servers from
+	// manipulating our internal fallthrough signaling mechanism
+	rm.MsgHdr.Zero = false
 
 	if err := w.WriteMsg(rm); err != nil {
 		logger.Errorf("failed to write DNS response for question domain=%s: %s", domain, err)
+		return true
 	}
+
 	return true
 }
 
@@ -414,16 +419,56 @@ func ExchangeWithFallback(ctx context.Context, client *dns.Client, r *dns.Msg, u
 	return rm, t, nil
 }
 
-func GenerateRequestID() string {
-	bytes := make([]byte, 4)
-	_, err := rand.Read(bytes)
+// ExchangeWithNetstack performs a DNS exchange using netstack for dialing.
+// This is needed when netstack is enabled to reach peer IPs through the tunnel.
+func ExchangeWithNetstack(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upstream string) (*dns.Msg, error) {
+	reply, err := netstackExchange(ctx, nsNet, r, upstream, "udp")
 	if err != nil {
-		log.Errorf("failed to generate request ID: %v", err)
-		return ""
+		return nil, err
 	}
-	return hex.EncodeToString(bytes)
+
+	// If response is truncated, retry with TCP
+	if reply != nil && reply.MsgHdr.Truncated {
+		log.Tracef("udp response for domain=%s type=%v class=%v is truncated, trying TCP",
+			r.Question[0].Name, r.Question[0].Qtype, r.Question[0].Qclass)
+		return netstackExchange(ctx, nsNet, r, upstream, "tcp")
+	}
+
+	return reply, nil
 }
 
+func netstackExchange(ctx context.Context, nsNet *netstack.Net, r *dns.Msg, upstream, network string) (*dns.Msg, error) {
+	conn, err := nsNet.DialContext(ctx, network, upstream)
+	if err != nil {
+		return nil, fmt.Errorf("with %s: %w", network, err)
+	}
+	defer func() {
+		if err := conn.Close(); err != nil {
+			log.Debugf("failed to close DNS connection: %v", err)
+		}
+	}()
+
+	if deadline, ok := ctx.Deadline(); ok {
+		if err := conn.SetDeadline(deadline); err != nil {
+			return nil, fmt.Errorf("set deadline: %w", err)
+		}
+	}
+
+	dnsConn := &dns.Conn{Conn: conn}
+
+	if err := dnsConn.WriteMsg(r); err != nil {
+		return nil, fmt.Errorf("write %s message: %w", network, err)
+	}
+
+	reply, err := dnsConn.ReadMsg()
+	if err != nil {
+		return nil, fmt.Errorf("read %s message: %w", network, err)
+	}
+
+	return reply, nil
+}
+
+
 // FormatPeerStatus formats peer connection status information for debugging DNS timeouts
 func FormatPeerStatus(peerState *peer.State) string {
 	isConnected := peerState.ConnStatus == peer.StatusConnected

client/internal/dns/upstream_android.go

@@ -23,9 +23,7 @@ type upstreamResolver struct {
 // first time, and we need to wait for a while to start to use again the proper DNS resolver.
 func newUpstreamResolver(
 	ctx context.Context,
-	_ string,
-	_ netip.Addr,
-	_ netip.Prefix,
+	_ WGIface,
 	statusRecorder *peer.Status,
 	hostsDNSHolder *hostsDNSHolder,
 	domain string,

client/internal/dns/upstream_general.go

@@ -5,22 +5,23 @@ package dns
 import (
 	"context"
 	"net/netip"
+	"runtime"
 	"time"
 
 	"github.com/miekg/dns"
+	"golang.zx2c4.com/wireguard/tun/netstack"
 
 	"github.com/netbirdio/netbird/client/internal/peer"
 )
 
 type upstreamResolver struct {
 	*upstreamResolverBase
+	nsNet *netstack.Net
 }
 
 func newUpstreamResolver(
 	ctx context.Context,
-	_ string,
-	_ netip.Addr,
-	_ netip.Prefix,
+	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
 	domain string,
@@ -28,12 +29,23 @@ func newUpstreamResolver(
 	upstreamResolverBase := newUpstreamResolverBase(ctx, statusRecorder, domain)
 	nonIOS := &upstreamResolver{
 		upstreamResolverBase: upstreamResolverBase,
+		nsNet:                wgIface.GetNet(),
 	}
 	upstreamResolverBase.upstreamClient = nonIOS
 	return nonIOS, nil
 }
 
 func (u *upstreamResolver) exchange(ctx context.Context, upstream string, r *dns.Msg) (rm *dns.Msg, t time.Duration, err error) {
+	// TODO: Check if upstream DNS server is routed through a peer before using netstack.
+	// Similar to iOS logic, we should determine if the DNS server is reachable directly
+	// or needs to go through the tunnel, and only use netstack when necessary.
+	// For now, only use netstack on JS platform where direct access is not possible.
+	if u.nsNet != nil && runtime.GOOS == "js" {
+		start := time.Now()
+		reply, err := ExchangeWithNetstack(ctx, u.nsNet, r, upstream)
+		return reply, time.Since(start), err
+	}
+
 	client := &dns.Client{
 		Timeout: ClientTimeout,
 	}

client/internal/dns/upstream_ios.go

@@ -26,9 +26,7 @@ type upstreamResolverIOS struct {
 
 func newUpstreamResolver(
 	ctx context.Context,
-	interfaceName string,
-	ip netip.Addr,
-	net netip.Prefix,
+	wgIface WGIface,
 	statusRecorder *peer.Status,
 	_ *hostsDNSHolder,
 	domain string,
@@ -37,9 +35,9 @@ func newUpstreamResolver(
 
 	ios := &upstreamResolverIOS{
 		upstreamResolverBase: upstreamResolverBase,
-		lIP:                  ip,
-		lNet:                 net,
-		interfaceName:        interfaceName,
+		lIP:                  wgIface.Address().IP,
+		lNet:                 wgIface.Address().Network,
+		interfaceName:        wgIface.Name(),
 	}
 	ios.upstreamClient = ios
 

client/internal/dns/upstream_test.go

@@ -2,13 +2,17 @@ package dns
 
 import (
 	"context"
+	"net"
 	"net/netip"
 	"strings"
 	"testing"
 	"time"
 
 	"github.com/miekg/dns"
+	"golang.zx2c4.com/wireguard/tun/netstack"
 
+	"github.com/netbirdio/netbird/client/iface/device"
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/dns/test"
 )
 
@@ -58,7 +62,7 @@ func TestUpstreamResolver_ServeDNS(t *testing.T) {
 	for _, testCase := range testCases {
 		t.Run(testCase.name, func(t *testing.T) {
 			ctx, cancel := context.WithCancel(context.TODO())
-			resolver, _ := newUpstreamResolver(ctx, "", netip.Addr{}, netip.Prefix{}, nil, nil, ".")
+			resolver, _ := newUpstreamResolver(ctx, &mockNetstackProvider{}, nil, nil, ".")
 			// Convert test servers to netip.AddrPort
 			var servers []netip.AddrPort
 			for _, server := range testCase.InputServers {
@@ -112,6 +116,19 @@ func TestUpstreamResolver_ServeDNS(t *testing.T) {
 	}
 }
 
+type mockNetstackProvider struct{}
+
+func (m *mockNetstackProvider) Name() string                      { return "mock" }
+func (m *mockNetstackProvider) Address() wgaddr.Address           { return wgaddr.Address{} }
+func (m *mockNetstackProvider) ToInterface() *net.Interface       { return nil }
+func (m *mockNetstackProvider) IsUserspaceBind() bool             { return false }
+func (m *mockNetstackProvider) GetFilter() device.PacketFilter    { return nil }
+func (m *mockNetstackProvider) GetDevice() *device.FilteredDevice { return nil }
+func (m *mockNetstackProvider) GetNet() *netstack.Net             { return nil }
+func (m *mockNetstackProvider) GetInterfaceGUIDString() (string, error) {
+	return "", nil
+}
+
 type mockUpstreamResolver struct {
 	r   *dns.Msg
 	rtt time.Duration

client/internal/dns/wgiface.go

@@ -5,6 +5,8 @@ package dns
 import (
 	"net"
 
+	"golang.zx2c4.com/wireguard/tun/netstack"
+
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 )
@@ -17,4 +19,5 @@ type WGIface interface {
 	IsUserspaceBind() bool
 	GetFilter() device.PacketFilter
 	GetDevice() *device.FilteredDevice
+	GetNet() *netstack.Net
 }

client/internal/dns/wgiface_windows.go

@@ -1,6 +1,8 @@
 package dns
 
 import (
+	"golang.zx2c4.com/wireguard/tun/netstack"
+
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 )
@@ -12,5 +14,6 @@ type WGIface interface {
 	IsUserspaceBind() bool
 	GetFilter() device.PacketFilter
 	GetDevice() *device.FilteredDevice
+	GetNet() *netstack.Net
 	GetInterfaceGUIDString() (string, error)
 }

client/internal/dnsfwd/forwarder.go

@@ -18,6 +18,7 @@ import (
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
 	firewall "github.com/netbirdio/netbird/client/firewall/manager"
+	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/route"
 )
@@ -189,29 +190,22 @@ func (f *DNSForwarder) Close(ctx context.Context) error {
 	return nberrors.FormatErrorOrNil(result)
 }
 
-func (f *DNSForwarder) handleDNSQuery(w dns.ResponseWriter, query *dns.Msg) *dns.Msg {
+func (f *DNSForwarder) handleDNSQuery(logger *log.Entry, w dns.ResponseWriter, query *dns.Msg) *dns.Msg {
 	if len(query.Question) == 0 {
 		return nil
 	}
 	question := query.Question[0]
-	log.Tracef("received DNS request for DNS forwarder: domain=%v type=%v class=%v",
-		question.Name, question.Qtype, question.Qclass)
+	logger.Tracef("received DNS request for DNS forwarder: domain=%s type=%s class=%s",
+		question.Name, dns.TypeToString[question.Qtype], dns.ClassToString[question.Qclass])
 
 	domain := strings.ToLower(question.Name)
 
 	resp := query.SetReply(query)
-	var network string
-	switch question.Qtype {
-	case dns.TypeA:
-		network = "ip4"
-	case dns.TypeAAAA:
-		network = "ip6"
-	default:
-		// TODO: Handle other types
-
+	network := resutil.NetworkForQtype(question.Qtype)
+	if network == "" {
 		resp.Rcode = dns.RcodeNotImplemented
 		if err := w.WriteMsg(resp); err != nil {
-			log.Errorf("failed to write DNS response: %v", err)
+			logger.Errorf("failed to write DNS response: %v", err)
 		}
 		return nil
 	}
@@ -221,33 +215,35 @@ func (f *DNSForwarder) handleDNSQuery(w dns.ResponseWriter, query *dns.Msg) *dns
 	if mostSpecificResId == "" {
 		resp.Rcode = dns.RcodeRefused
 		if err := w.WriteMsg(resp); err != nil {
-			log.Errorf("failed to write DNS response: %v", err)
+			logger.Errorf("failed to write DNS response: %v", err)
 		}
 		return nil
 	}
 
 	ctx, cancel := context.WithTimeout(context.Background(), upstreamTimeout)
 	defer cancel()
-	ips, err := f.resolver.LookupNetIP(ctx, network, domain)
-	if err != nil {
-		f.handleDNSError(ctx, w, question, resp, domain, err)
+
+	result := resutil.LookupIP(ctx, f.resolver, network, domain, question.Qtype)
+	if result.Err != nil {
+		f.handleDNSError(ctx, logger, w, question, resp, domain, result)
 		return nil
 	}
 
-	// Unmap IPv4-mapped IPv6 addresses that some resolvers may return
-	for i, ip := range ips {
-		ips[i] = ip.Unmap()
-	}
-
-	f.updateInternalState(ips, mostSpecificResId, matchingEntries)
-	f.addIPsToResponse(resp, domain, ips)
-	f.cache.set(domain, question.Qtype, ips)
+	f.updateInternalState(result.IPs, mostSpecificResId, matchingEntries)
+	resp.Answer = append(resp.Answer, resutil.IPsToRRs(domain, result.IPs, f.ttl)...)
+	f.cache.set(domain, question.Qtype, result.IPs)
 
 	return resp
 }
 
 func (f *DNSForwarder) handleDNSQueryUDP(w dns.ResponseWriter, query *dns.Msg) {
-	resp := f.handleDNSQuery(w, query)
+	startTime := time.Now()
+	logger := log.WithFields(log.Fields{
+		"request_id": resutil.GenerateRequestID(),
+		"dns_id":     fmt.Sprintf("%04x", query.Id),
+	})
+
+	resp := f.handleDNSQuery(logger, w, query)
 	if resp == nil {
 		return
 	}
@@ -265,19 +261,33 @@ func (f *DNSForwarder) handleDNSQueryUDP(w dns.ResponseWriter, query *dns.Msg) {
 	}
 
 	if err := w.WriteMsg(resp); err != nil {
-		log.Errorf("failed to write DNS response: %v", err)
+		logger.Errorf("failed to write DNS response: %v", err)
+		return
 	}
+
+	logger.Tracef("response: domain=%s rcode=%s answers=%s took=%s",
+		query.Question[0].Name, dns.RcodeToString[resp.Rcode], resutil.FormatAnswers(resp.Answer), time.Since(startTime))
 }
 
 func (f *DNSForwarder) handleDNSQueryTCP(w dns.ResponseWriter, query *dns.Msg) {
-	resp := f.handleDNSQuery(w, query)
+	startTime := time.Now()
+	logger := log.WithFields(log.Fields{
+		"request_id": resutil.GenerateRequestID(),
+		"dns_id":     fmt.Sprintf("%04x", query.Id),
+	})
+
+	resp := f.handleDNSQuery(logger, w, query)
 	if resp == nil {
 		return
 	}
 
 	if err := w.WriteMsg(resp); err != nil {
-		log.Errorf("failed to write DNS response: %v", err)
+		logger.Errorf("failed to write DNS response: %v", err)
+		return
 	}
+
+	logger.Tracef("response: domain=%s rcode=%s answers=%s took=%s",
+		query.Question[0].Name, dns.RcodeToString[resp.Rcode], resutil.FormatAnswers(resp.Answer), time.Since(startTime))
 }
 
 func (f *DNSForwarder) updateInternalState(ips []netip.Addr, mostSpecificResId route.ResID, matchingEntries []*ForwarderEntry) {
@@ -315,140 +325,64 @@ func (f *DNSForwarder) updateFirewall(matchingEntries []*ForwarderEntry, prefixe
 	}
 }
 
-// setResponseCodeForNotFound determines and sets the appropriate response code when IsNotFound is true
-// It distinguishes between NXDOMAIN (domain doesn't exist) and NODATA (domain exists but no records of requested type)
-//
-// LIMITATION: This function only checks A and AAAA record types to determine domain existence.
-// If a domain has only other record types (MX, TXT, CNAME, etc.) but no A/AAAA records,
-// it may incorrectly return NXDOMAIN instead of NODATA. This is acceptable since the forwarder
-// only handles A/AAAA queries and returns NOTIMP for other types.
-func (f *DNSForwarder) setResponseCodeForNotFound(ctx context.Context, resp *dns.Msg, domain string, originalQtype uint16) {
-	// Try querying for a different record type to see if the domain exists
-	// If the original query was for AAAA, try A. If it was for A, try AAAA.
-	// This helps distinguish between NXDOMAIN and NODATA.
-	var alternativeNetwork string
-	switch originalQtype {
-	case dns.TypeAAAA:
-		alternativeNetwork = "ip4"
-	case dns.TypeA:
-		alternativeNetwork = "ip6"
-	default:
-		resp.Rcode = dns.RcodeNameError
-		return
-	}
-
-	if _, err := f.resolver.LookupNetIP(ctx, alternativeNetwork, domain); err != nil {
-		var dnsErr *net.DNSError
-		if errors.As(err, &dnsErr) && dnsErr.IsNotFound {
-			// Alternative query also returned not found - domain truly doesn't exist
-			resp.Rcode = dns.RcodeNameError
-			return
-		}
-		// Some other error (timeout, server failure, etc.) - can't determine, assume domain exists
-		resp.Rcode = dns.RcodeSuccess
-		return
-	}
-
-	// Alternative query succeeded - domain exists but has no records of this type
-	resp.Rcode = dns.RcodeSuccess
-}
-
 // handleDNSError processes DNS lookup errors and sends an appropriate error response.
 func (f *DNSForwarder) handleDNSError(
 	ctx context.Context,
+	logger *log.Entry,
 	w dns.ResponseWriter,
 	question dns.Question,
 	resp *dns.Msg,
 	domain string,
-	err error,
+	result resutil.LookupResult,
 ) {
-	// Default to SERVFAIL; override below when appropriate.
-	resp.Rcode = dns.RcodeServerFailure
-
 	qType := question.Qtype
 	qTypeName := dns.TypeToString[qType]
 
-	// Prefer typed DNS errors; fall back to generic logging otherwise.
-	var dnsErr *net.DNSError
-	if !errors.As(err, &dnsErr) {
-		log.Warnf(errResolveFailed, domain, err)
-		if writeErr := w.WriteMsg(resp); writeErr != nil {
-			log.Errorf("failed to write failure DNS response: %v", writeErr)
-		}
-		return
-	}
+	resp.Rcode = result.Rcode
 
-	// NotFound: set NXDOMAIN / appropriate code via helper.
-	if dnsErr.IsNotFound {
-		f.setResponseCodeForNotFound(ctx, resp, domain, qType)
-		if writeErr := w.WriteMsg(resp); writeErr != nil {
-			log.Errorf("failed to write failure DNS response: %v", writeErr)
-		}
+	// NotFound: cache negative result and respond
+	if result.Rcode == dns.RcodeNameError || result.Rcode == dns.RcodeSuccess {
 		f.cache.set(domain, question.Qtype, nil)
+		if writeErr := w.WriteMsg(resp); writeErr != nil {
+			logger.Errorf("failed to write failure DNS response: %v", writeErr)
+		}
 		return
 	}
 
 	// Upstream failed but we might have a cached answer—serve it if present.
 	if ips, ok := f.cache.get(domain, qType); ok {
 		if len(ips) > 0 {
-			log.Debugf("serving cached DNS response after upstream failure: domain=%s type=%s", domain, qTypeName)
-			f.addIPsToResponse(resp, domain, ips)
+			logger.Debugf("serving cached DNS response after upstream failure: domain=%s type=%s", domain, qTypeName)
+			resp.Answer = append(resp.Answer, resutil.IPsToRRs(domain, ips, f.ttl)...)
 			resp.Rcode = dns.RcodeSuccess
 			if writeErr := w.WriteMsg(resp); writeErr != nil {
-				log.Errorf("failed to write cached DNS response: %v", writeErr)
-			}
-		} else { // send NXDOMAIN / appropriate code if cache is empty
-			f.setResponseCodeForNotFound(ctx, resp, domain, qType)
-			if writeErr := w.WriteMsg(resp); writeErr != nil {
-				log.Errorf("failed to write failure DNS response: %v", writeErr)
+				logger.Errorf("failed to write cached DNS response: %v", writeErr)
 			}
+			return
+		}
+
+		// Cached negative result - re-verify NXDOMAIN vs NODATA
+		verifyResult := resutil.LookupIP(ctx, f.resolver, resutil.NetworkForQtype(qType), domain, qType)
+		if verifyResult.Rcode == dns.RcodeNameError || verifyResult.Rcode == dns.RcodeSuccess {
+			resp.Rcode = verifyResult.Rcode
+			if writeErr := w.WriteMsg(resp); writeErr != nil {
+				logger.Errorf("failed to write failure DNS response: %v", writeErr)
+			}
+			return
 		}
-		return
 	}
 
-	// No cache. Log with or without the server field for more context.
-	if dnsErr.Server != "" {
-		log.Warnf("failed to resolve: type=%s domain=%s server=%s: %v", qTypeName, domain, dnsErr.Server, err)
+	// No cache or verification failed. Log with or without the server field for more context.
+	var dnsErr *net.DNSError
+	if errors.As(result.Err, &dnsErr) && dnsErr.Server != "" {
+		logger.Warnf("failed to resolve: type=%s domain=%s server=%s: %v", qTypeName, domain, dnsErr.Server, result.Err)
 	} else {
-		log.Warnf(errResolveFailed, domain, err)
+		logger.Warnf(errResolveFailed, domain, result.Err)
 	}
 
 	// Write final failure response.
 	if writeErr := w.WriteMsg(resp); writeErr != nil {
-		log.Errorf("failed to write failure DNS response: %v", writeErr)
-	}
-}
-
-// addIPsToResponse adds IP addresses to the DNS response as appropriate A or AAAA records
-func (f *DNSForwarder) addIPsToResponse(resp *dns.Msg, domain string, ips []netip.Addr) {
-	for _, ip := range ips {
-		var respRecord dns.RR
-		if ip.Is6() {
-			log.Tracef("resolved domain=%s to IPv6=%s", domain, ip)
-			rr := dns.AAAA{
-				AAAA: ip.AsSlice(),
-				Hdr: dns.RR_Header{
-					Name:   domain,
-					Rrtype: dns.TypeAAAA,
-					Class:  dns.ClassINET,
-					Ttl:    f.ttl,
-				},
-			}
-			respRecord = &rr
-		} else {
-			log.Tracef("resolved domain=%s to IPv4=%s", domain, ip)
-			rr := dns.A{
-				A: ip.AsSlice(),
-				Hdr: dns.RR_Header{
-					Name:   domain,
-					Rrtype: dns.TypeA,
-					Class:  dns.ClassINET,
-					Ttl:    f.ttl,
-				},
-			}
-			respRecord = &rr
-		}
-		resp.Answer = append(resp.Answer, respRecord)
+		logger.Errorf("failed to write failure DNS response: %v", writeErr)
 	}
 }
 

client/internal/dnsfwd/forwarder_test.go

@@ -10,6 +10,7 @@ import (
 	"time"
 
 	"github.com/miekg/dns"
+	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/mock"
 	"github.com/stretchr/testify/require"
@@ -317,7 +318,7 @@ func TestDNSForwarder_UnauthorizedDomainAccess(t *testing.T) {
 			query.SetQuestion(dns.Fqdn(tt.queryDomain), dns.TypeA)
 
 			mockWriter := &test.MockResponseWriter{}
-			resp := forwarder.handleDNSQuery(mockWriter, query)
+			resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 			if tt.shouldResolve {
 				require.NotNil(t, resp, "Expected response for authorized domain")
@@ -465,7 +466,7 @@ func TestDNSForwarder_FirewallSetUpdates(t *testing.T) {
 			dnsQuery.SetQuestion(dns.Fqdn(tt.query), dns.TypeA)
 
 			mockWriter := &test.MockResponseWriter{}
-			resp := forwarder.handleDNSQuery(mockWriter, dnsQuery)
+			resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, dnsQuery)
 
 			// Verify response
 			if tt.shouldResolve {
@@ -527,7 +528,7 @@ func TestDNSForwarder_MultipleIPsInSingleUpdate(t *testing.T) {
 	query.SetQuestion("example.com.", dns.TypeA)
 
 	mockWriter := &test.MockResponseWriter{}
-	resp := forwarder.handleDNSQuery(mockWriter, query)
+	resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 	// Verify response contains all IPs
 	require.NotNil(t, resp)
@@ -604,7 +605,7 @@ func TestDNSForwarder_ResponseCodes(t *testing.T) {
 				},
 			}
 
-			_ = forwarder.handleDNSQuery(mockWriter, query)
+			_ = forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 			// Check the response written to the writer
 			require.NotNil(t, writtenResp, "Expected response to be written")
@@ -674,7 +675,7 @@ func TestDNSForwarder_ServeFromCacheOnUpstreamFailure(t *testing.T) {
 	q1 := &dns.Msg{}
 	q1.SetQuestion(dns.Fqdn("example.com"), dns.TypeA)
 	w1 := &test.MockResponseWriter{}
-	resp1 := forwarder.handleDNSQuery(w1, q1)
+	resp1 := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), w1, q1)
 	require.NotNil(t, resp1)
 	require.Equal(t, dns.RcodeSuccess, resp1.Rcode)
 	require.Len(t, resp1.Answer, 1)
@@ -684,7 +685,7 @@ func TestDNSForwarder_ServeFromCacheOnUpstreamFailure(t *testing.T) {
 	q2.SetQuestion(dns.Fqdn("example.com"), dns.TypeA)
 	var writtenResp *dns.Msg
 	w2 := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { writtenResp = m; return nil }}
-	_ = forwarder.handleDNSQuery(w2, q2)
+	_ = forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), w2, q2)
 
 	require.NotNil(t, writtenResp, "expected response to be written")
 	require.Equal(t, dns.RcodeSuccess, writtenResp.Rcode)
@@ -714,7 +715,7 @@ func TestDNSForwarder_CacheNormalizationCasingAndDot(t *testing.T) {
 	q1 := &dns.Msg{}
 	q1.SetQuestion(mixedQuery+".", dns.TypeA)
 	w1 := &test.MockResponseWriter{}
-	resp1 := forwarder.handleDNSQuery(w1, q1)
+	resp1 := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), w1, q1)
 	require.NotNil(t, resp1)
 	require.Equal(t, dns.RcodeSuccess, resp1.Rcode)
 	require.Len(t, resp1.Answer, 1)
@@ -728,7 +729,7 @@ func TestDNSForwarder_CacheNormalizationCasingAndDot(t *testing.T) {
 	q2.SetQuestion("EXAMPLE.COM", dns.TypeA)
 	var writtenResp *dns.Msg
 	w2 := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { writtenResp = m; return nil }}
-	_ = forwarder.handleDNSQuery(w2, q2)
+	_ = forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), w2, q2)
 
 	require.NotNil(t, writtenResp)
 	require.Equal(t, dns.RcodeSuccess, writtenResp.Rcode)
@@ -783,7 +784,7 @@ func TestDNSForwarder_MultipleOverlappingPatterns(t *testing.T) {
 	query.SetQuestion("smtp.mail.example.com.", dns.TypeA)
 
 	mockWriter := &test.MockResponseWriter{}
-	resp := forwarder.handleDNSQuery(mockWriter, query)
+	resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 	require.NotNil(t, resp)
 	assert.Equal(t, dns.RcodeSuccess, resp.Rcode)
@@ -904,7 +905,7 @@ func TestDNSForwarder_NodataVsNxdomain(t *testing.T) {
 				},
 			}
 
-			resp := forwarder.handleDNSQuery(mockWriter, query)
+			resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 			// If a response was returned, it means it should be written (happens in wrapper functions)
 			if resp != nil && writtenResp == nil {
@@ -937,7 +938,7 @@ func TestDNSForwarder_EmptyQuery(t *testing.T) {
 			return nil
 		},
 	}
-	resp := forwarder.handleDNSQuery(mockWriter, query)
+	resp := forwarder.handleDNSQuery(log.NewEntry(log.StandardLogger()), mockWriter, query)
 
 	assert.Nil(t, resp, "Should return nil for empty query")
 	assert.False(t, writeCalled, "Should not write response for empty query")

client/internal/engine.go

@@ -31,6 +31,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/udpmux"
 	"github.com/netbirdio/netbird/client/internal/acl"
+	"github.com/netbirdio/netbird/client/internal/debug"
 	"github.com/netbirdio/netbird/client/internal/dns"
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
 	"github.com/netbirdio/netbird/client/internal/dnsfwd"
@@ -43,12 +44,14 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer/guard"
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/relay"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
 	"github.com/netbirdio/netbird/client/internal/routemanager"
 	"github.com/netbirdio/netbird/client/internal/routemanager/systemops"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/updatemanager"
+	"github.com/netbirdio/netbird/client/jobexec"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/shared/management/domain"
 	semaphoregroup "github.com/netbirdio/netbird/util/semaphore-group"
@@ -133,6 +136,11 @@ type EngineConfig struct {
 	LazyConnectionEnabled bool
 
 	MTU uint16
+
+	// for debug bundle generation
+	ProfileConfig *profilemanager.Config
+
+	LogPath string
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -196,7 +204,8 @@ type Engine struct {
 	stateManager *statemanager.Manager
 	srWatcher    *guard.SRWatcher
 
-	// Sync response persistence
+	// Sync response persistence (protected by syncRespMux)
+	syncRespMux         sync.RWMutex
 	persistSyncResponse bool
 	latestSyncResponse  *mgmProto.SyncResponse
 	connSemaphore       *semaphoregroup.SemaphoreGroup
@@ -215,6 +224,9 @@ type Engine struct {
 
 	// clientMetrics collects and pushes metrics
 	clientMetrics *metrics.ClientMetrics
+
+	jobExecutor   *jobexec.Executor
+	jobExecutorWG sync.WaitGroup
 }
 
 // Peer is an instance of the Connection Peer
@@ -228,7 +240,18 @@ type localIpUpdater interface {
 }
 
 // NewEngine creates a new Connection Engine with probes attached
-func NewEngine(clientCtx context.Context, clientCancel context.CancelFunc, signalClient signal.Client, mgmClient mgm.Client, relayManager *relayClient.Manager, config *EngineConfig, mobileDep MobileDependency, statusRecorder *peer.Status, checks []*mgmProto.Checks, stateManager *statemanager.Manager) *Engine {
+func NewEngine(
+	clientCtx context.Context,
+	clientCancel context.CancelFunc,
+	signalClient signal.Client,
+	mgmClient mgm.Client,
+	relayManager *relayClient.Manager,
+	config *EngineConfig,
+	mobileDep MobileDependency,
+	statusRecorder *peer.Status,
+	checks []*mgmProto.Checks,
+	stateManager *statemanager.Manager,
+) *Engine {
 	// Initialize metrics based on deployment type
 	var deploymentType metrics.DeploymentType
 	if mgmClient != nil {
@@ -254,6 +277,7 @@ func NewEngine(clientCtx context.Context, clientCancel context.CancelFunc, signa
 		checks:         checks,
 		connSemaphore:  semaphoregroup.NewSemaphoreGroup(connInitLimit),
 		probeStunTurn:  relay.NewStunTurnProbe(relay.DefaultCacheTTL),
+		jobExecutor:    jobexec.NewExecutor(),
 		clientMetrics:  metrics.NewClientMetrics(deploymentType, true),
 	}
 
@@ -323,6 +347,8 @@ func (e *Engine) Stop() error {
 		e.cancel()
 	}
 
+	e.jobExecutorWG.Wait() // block until job goroutines finish
+
 	e.close()
 
 	// stop flow manager after wg interface is gone
@@ -490,6 +516,11 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		return fmt.Errorf("up wg interface: %w", err)
 	}
 
+	// Set the WireGuard interface for rosenpass after interface is up
+	if e.rpManager != nil {
+		e.rpManager.SetInterface(e.wgInterface)
+	}
+
 	// if inbound conns are blocked there is no need to create the ACL manager
 	if e.firewall != nil && !e.config.BlockInbound {
 		e.acl = acl.NewDefaultManager(e.firewall)
@@ -511,6 +542,7 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 
 	e.receiveSignalEvents()
 	e.receiveManagementEvents()
+	e.receiveJobEvents()
 
 	// starting network monitor at the very last to avoid disruptions
 	e.startNetworkMonitor()
@@ -839,9 +871,18 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return nil
 	}
 
+	// Persist sync response under the dedicated lock (syncRespMux), not under syncMsgMux.
+	// Read the storage-enabled flag under the syncRespMux too.
+	e.syncRespMux.RLock()
+	enabled := e.persistSyncResponse
+	e.syncRespMux.RUnlock()
+
 	// Store sync response if persistence is enabled
-	if e.persistSyncResponse {
+	if enabled {
+		e.syncRespMux.Lock()
 		e.latestSyncResponse = update
+		e.syncRespMux.Unlock()
+
 		log.Debugf("sync response persisted with serial %d", nm.GetSerial())
 	}
 
@@ -971,6 +1012,78 @@ func (e *Engine) updateConfig(conf *mgmProto.PeerConfig) error {
 
 	return nil
 }
+func (e *Engine) receiveJobEvents() {
+	e.jobExecutorWG.Add(1)
+	go func() {
+		defer e.jobExecutorWG.Done()
+		err := e.mgmClient.Job(e.ctx, func(msg *mgmProto.JobRequest) *mgmProto.JobResponse {
+			resp := mgmProto.JobResponse{
+				ID:     msg.ID,
+				Status: mgmProto.JobStatus_failed,
+			}
+			switch params := msg.WorkloadParameters.(type) {
+			case *mgmProto.JobRequest_Bundle:
+				bundleResult, err := e.handleBundle(params.Bundle)
+				if err != nil {
+					log.Errorf("handling bundle: %v", err)
+					resp.Reason = []byte(err.Error())
+					return &resp
+				}
+				resp.Status = mgmProto.JobStatus_succeeded
+				resp.WorkloadResults = bundleResult
+				return &resp
+			default:
+				resp.Reason = []byte(jobexec.ErrJobNotImplemented.Error())
+				return &resp
+			}
+		})
+		if err != nil {
+			// happens if management is unavailable for a long time.
+			// We want to cancel the operation of the whole client
+			_ = CtxGetState(e.ctx).Wrap(ErrResetConnection)
+			e.clientCancel()
+			return
+		}
+		log.Info("stopped receiving jobs from Management Service")
+	}()
+	log.Info("connecting to Management Service jobs stream")
+}
+
+func (e *Engine) handleBundle(params *mgmProto.BundleParameters) (*mgmProto.JobResponse_Bundle, error) {
+	log.Infof("handle remote debug bundle request: %s", params.String())
+	syncResponse, err := e.GetLatestSyncResponse()
+	if err != nil {
+		log.Warnf("get latest sync response: %v", err)
+	}
+
+	bundleDeps := debug.GeneratorDependencies{
+		InternalConfig: e.config.ProfileConfig,
+		StatusRecorder: e.statusRecorder,
+		SyncResponse:   syncResponse,
+		LogPath:        e.config.LogPath,
+		ClientMetrics:  e.clientMetrics,
+	}
+
+	bundleJobParams := debug.BundleConfig{
+		Anonymize:         params.Anonymize,
+		IncludeSystemInfo: true,
+		LogFileCount:      uint32(params.LogFileCount),
+	}
+
+	waitFor := time.Duration(params.BundleForTime) * time.Minute
+
+	uploadKey, err := e.jobExecutor.BundleJob(e.ctx, bundleDeps, bundleJobParams, waitFor, e.config.ProfileConfig.ManagementURL.String())
+	if err != nil {
+		return nil, err
+	}
+
+	response := &mgmProto.JobResponse_Bundle{
+		Bundle: &mgmProto.BundleResult{
+			UploadKey: uploadKey,
+		},
+	}
+	return response, nil
+}
 
 // receiveManagementEvents connects to the Management Service event stream to receive updates from the management service
 // E.g. when a new peer has been registered and we are allowed to connect to it.
@@ -1262,11 +1375,16 @@ func toDNSConfig(protoDNSConfig *mgmProto.DNSConfig, network netip.Prefix) nbdns
 		ForwarderPort:    forwarderPort,
 	}
 
-	for _, zone := range protoDNSConfig.GetCustomZones() {
+	protoZones := protoDNSConfig.GetCustomZones()
+	// Treat single zone as authoritative for backward compatibility with old servers
+	// that only send the peer FQDN zone without setting field 4.
+	singleZoneCompat := len(protoZones) == 1
+
+	for _, zone := range protoZones {
 		dnsZone := nbdns.CustomZone{
 			Domain:               zone.GetDomain(),
 			SearchDomainDisabled: zone.GetSearchDomainDisabled(),
-			SkipPTRProcess:       zone.GetSkipPTRProcess(),
+			NonAuthoritative:     zone.GetNonAuthoritative() && !singleZoneCompat,
 		}
 		for _, record := range zone.Records {
 			dnsRecord := nbdns.SimpleRecord{
@@ -1412,6 +1530,7 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 	if e.rpManager != nil {
 		peerConn.SetOnConnected(e.rpManager.OnConnected)
 		peerConn.SetOnDisconnected(e.rpManager.OnDisconnected)
+		peerConn.SetRosenpassInitializedPresharedKeyValidator(e.rpManager.IsPresharedKeyInitialized)
 	}
 
 	return peerConn, nil
@@ -1760,22 +1879,26 @@ func (e *Engine) RunHealthProbes(waitForResult bool) bool {
 	}
 
 	e.syncMsgMux.Unlock()
-	var results []relay.ProbeResult
-	if waitForResult {
-		results = e.probeStunTurn.ProbeAllWaitResult(e.ctx, stuns, turns)
-	} else {
-		results = e.probeStunTurn.ProbeAll(e.ctx, stuns, turns)
-	}
-	e.statusRecorder.UpdateRelayStates(results)
 
+	// Skip STUN/TURN probing for JS/WASM as it's not available
 	relayHealthy := true
-	for _, res := range results {
-		if res.Err != nil {
-			relayHealthy = false
-			break
+	if runtime.GOOS != "js" {
+		var results []relay.ProbeResult
+		if waitForResult {
+			results = e.probeStunTurn.ProbeAllWaitResult(e.ctx, stuns, turns)
+		} else {
+			results = e.probeStunTurn.ProbeAll(e.ctx, stuns, turns)
 		}
+		e.statusRecorder.UpdateRelayStates(results)
+
+		for _, res := range results {
+			if res.Err != nil {
+				relayHealthy = false
+				break
+			}
+		}
+		log.Debugf("relay health check: healthy=%t", relayHealthy)
 	}
-	log.Debugf("relay health check: healthy=%t", relayHealthy)
 
 	allHealthy := signalHealthy && managementHealthy && relayHealthy
 	log.Debugf("all health checks completed: healthy=%t", allHealthy)
@@ -1856,8 +1979,8 @@ func (e *Engine) stopDNSServer() {
 
 // SetSyncResponsePersistence enables or disables sync response persistence
 func (e *Engine) SetSyncResponsePersistence(enabled bool) {
-	e.syncMsgMux.Lock()
-	defer e.syncMsgMux.Unlock()
+	e.syncRespMux.Lock()
+	defer e.syncRespMux.Unlock()
 
 	if enabled == e.persistSyncResponse {
 		return
@@ -1872,20 +1995,22 @@ func (e *Engine) SetSyncResponsePersistence(enabled bool) {
 
 // GetLatestSyncResponse returns the stored sync response if persistence is enabled
 func (e *Engine) GetLatestSyncResponse() (*mgmProto.SyncResponse, error) {
-	e.syncMsgMux.Lock()
-	defer e.syncMsgMux.Unlock()
+	e.syncRespMux.RLock()
+	enabled := e.persistSyncResponse
+	latest := e.latestSyncResponse
+	e.syncRespMux.RUnlock()
 
-	if !e.persistSyncResponse {
+	if !enabled {
 		return nil, errors.New("sync response persistence is disabled")
 	}
 
-	if e.latestSyncResponse == nil {
+	if latest == nil {
 		//nolint:nilnil
 		return nil, nil
 	}
 
-	log.Debugf("Retrieving latest sync response with size %d bytes", proto.Size(e.latestSyncResponse))
-	sr, ok := proto.Clone(e.latestSyncResponse).(*mgmProto.SyncResponse)
+	log.Debugf("Retrieving latest sync response with size %d bytes", proto.Size(latest))
+	sr, ok := proto.Clone(latest).(*mgmProto.SyncResponse)
 	if !ok {
 		return nil, fmt.Errorf("failed to clone sync response")
 	}

client/internal/engine_ssh.go

@@ -72,9 +72,16 @@ func (e *Engine) updateSSH(sshConf *mgmProto.SSHConfig) error {
 	}
 
 	if protoJWT := sshConf.GetJwtConfig(); protoJWT != nil {
+		audiences := protoJWT.GetAudiences()
+		if len(audiences) == 0 && protoJWT.GetAudience() != "" {
+			audiences = []string{protoJWT.GetAudience()}
+		}
+
+		log.Debugf("starting SSH server with JWT authentication: audiences=%v", audiences)
+
 		jwtConfig := &sshserver.JWTConfig{
 			Issuer:       protoJWT.GetIssuer(),
-			Audience:     protoJWT.GetAudience(),
+			Audiences:    audiences,
 			KeysLocation: protoJWT.GetKeysLocation(),
 			MaxTokenAge:  protoJWT.GetMaxTokenAge(),
 		}

client/internal/engine_test.go

@@ -25,6 +25,7 @@ import (
 	"google.golang.org/grpc/keepalive"
 
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/management/server/job"
 
 	"github.com/netbirdio/management-integrations/integrations"
 
@@ -213,6 +214,10 @@ func (m *MockWGIface) LastActivities() map[string]monotime.Time {
 	return nil
 }
 
+func (m *MockWGIface) SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error {
+	return nil
+}
+
 func TestMain(m *testing.M) {
 	_ = util.InitLog("debug", util.LogConsole)
 	code := m.Run()
@@ -1599,6 +1604,7 @@ func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, stri
 
 	permissionsManager := permissions.NewManager(store)
 	peersManager := peers.NewManager(store, permissionsManager)
+	jobManager := job.NewJobManager(nil, store, peersManager)
 
 	ia, _ := integrations.NewIntegratedValidator(context.Background(), peersManager, nil, eventStore)
 
@@ -1622,7 +1628,7 @@ func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, stri
 	updateManager := update_channel.NewPeersUpdateManager(metrics)
 	requestBuffer := server.NewAccountRequestBuffer(context.Background(), store)
 	networkMapController := controller.NewController(context.Background(), store, metrics, updateManager, requestBuffer, server.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersManager), config)
-	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false)
+	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManager, false)
 	if err != nil {
 		return nil, "", err
 	}
@@ -1631,7 +1637,7 @@ func startManagement(t *testing.T, dataDir, testFile string) (*grpc.Server, stri
 	if err != nil {
 		return nil, "", err
 	}
-	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil)
+	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil)
 	if err != nil {
 		return nil, "", err
 	}

client/internal/iface_common.go

@@ -42,4 +42,5 @@ type wgIfaceBase interface {
 	GetNet() *netstack.Net
 	FullStats() (*configurer.Stats, error)
 	LastActivities() map[string]monotime.Time
+	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error
 }

client/internal/metrics/metrics.go

@@ -41,7 +41,7 @@ func NewClientMetrics(deploymentType DeploymentType, enabled bool) *ClientMetric
 	if !enabled {
 		impl = &noopMetrics{}
 	} else {
-		impl = newOtelMetrics(deploymentType)
+		impl = newVictoriaMetrics(deploymentType)
 	}
 	return &ClientMetrics{impl: impl}
 }

client/internal/metrics/victoria.go

@@ -6,6 +6,7 @@ import (
 	"io"
 
 	"github.com/VictoriaMetrics/metrics"
+	log "github.com/sirupsen/logrus"
 )
 
 // victoriaMetrics is the VictoriaMetrics implementation of ClientMetrics
@@ -82,6 +83,11 @@ func (m *victoriaMetrics) RecordConnectionStages(
 	m.set.GetOrCreateHistogram(
 		m.getMetricName("netbird_peer_connection_total_creation_to_handshake", connTypeStr, attemptType),
 	).Update(totalDuration)
+
+	log.Infof("--- Peer connection metrics [%s, %s, %s]: creation→semaphore: %.3fs, semaphore→signaling: %.3fs, signaling→connection: %.3fs, connection→handshake: %.3fs, total: %.3fs",
+		m.deploymentType.String(), connTypeStr, attemptType,
+		creationToSemaphore, semaphoreToSignaling, signalingToConnection, connectionToHandshake,
+		totalDuration)
 }
 
 // getMetricName constructs a metric name with labels

client/internal/peer/conn.go

@@ -100,8 +100,9 @@ type Conn struct {
 	relayManager   *relayClient.Manager
 	srWatcher      *guard.SRWatcher
 
-	onConnected    func(remoteWireGuardKey string, remoteRosenpassPubKey []byte, wireGuardIP string, remoteRosenpassAddr string)
-	onDisconnected func(remotePeer string)
+	onConnected                               func(remoteWireGuardKey string, remoteRosenpassPubKey []byte, wireGuardIP string, remoteRosenpassAddr string)
+	onDisconnected                            func(remotePeer string)
+	rosenpassInitializedPresharedKeyValidator func(peerKey string) bool
 
 	statusRelay         *worker.AtomicWorkerStatus
 	statusICE           *worker.AtomicWorkerStatus
@@ -110,8 +111,10 @@ type Conn struct {
 
 	workerICE   *WorkerICE
 	workerRelay *WorkerRelay
-	wgWatcher   *WGWatcher
-	wgWatcherWg sync.WaitGroup
+
+	wgWatcher       *WGWatcher
+	wgWatcherWg     sync.WaitGroup
+	wgWatcherCancel context.CancelFunc
 
 	// used to store the remote Rosenpass key for Relayed connection in case of connection update from ice
 	rosenpassRemoteKey []byte
@@ -130,11 +133,8 @@ type Conn struct {
 	endpointUpdater *EndpointUpdater
 
 	// Connection stage timestamps for metrics
-	metricsRecorder       MetricsRecorder
-	hasBeenConnected      bool // Track if we've ever established a successful connection
-	isReconnectionAttempt bool // Track if current attempt is a reconnection
-	stageTimestamps       metrics.ConnectionStageTimestamps
-	stagesMutex           sync.Mutex
+	metricsRecorder MetricsRecorder
+	metricsStages   MetricsStages
 }
 
 // NewConn creates a new not opened Conn to the remote peer.
@@ -163,7 +163,7 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
 		metricsRecorder: services.MetricsRecorder,
 	}
 
-	conn.wgWatcher = NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState, conn.onWGHandshakeSuccess)
+	conn.wgWatcher = NewWGWatcher(connLog, config.WgConfig.WgInterface, config.Key, dumpState)
 
 	return conn, nil
 }
@@ -172,21 +172,24 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
 // It will try to establish a connection using ICE and in parallel with relay. The higher priority connection type will
 // be used.
 func (conn *Conn) Open(engineCtx context.Context) error {
+	conn.mu.Lock()
+	if conn.opened {
+		conn.mu.Unlock()
+		return nil
+	}
+
 	// Record the start time - beginning of connection attempt
-	conn.stagesMutex.Lock()
-	conn.stageTimestamps.Created = time.Now()
-	conn.stagesMutex.Unlock()
+	conn.metricsStages = MetricsStages{}
+	conn.metricsStages.RecordCreated()
+
+	conn.mu.Unlock()
 
 	// Semaphore.Add() blocks here until there's a free slot
+	// todo create common semaphor logic for reconnection and connections too that can remote seats from semaphor on the fly
 	if err := conn.semaphore.Add(engineCtx); err != nil {
 		return err
 	}
 
-	// Record when semaphore was acquired (after the wait)
-	conn.stagesMutex.Lock()
-	conn.stageTimestamps.SemaphoreAcquired = time.Now()
-	conn.stagesMutex.Unlock()
-
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
 
@@ -195,9 +198,12 @@ func (conn *Conn) Open(engineCtx context.Context) error {
 		return nil
 	}
 
+	// Record when semaphore was acquired (after the wait)
+	conn.metricsStages.RecordSemaphoreAcquired()
+
 	conn.ctx, conn.ctxCancel = context.WithCancel(engineCtx)
 
-	conn.workerRelay = NewWorkerRelay(conn.ctx, conn.Log, isController(conn.config), conn.config, conn, conn.relayManager, conn.dumpState)
+	conn.workerRelay = NewWorkerRelay(conn.ctx, conn.Log, isController(conn.config), conn.config, conn, conn.relayManager)
 
 	relayIsSupportedLocally := conn.workerRelay.RelayIsSupportedLocally()
 	workerICE, err := NewWorkerICE(conn.ctx, conn.Log, conn.config, conn, conn.signaler, conn.iFaceDiscover, conn.statusRecorder, relayIsSupportedLocally)
@@ -266,7 +272,9 @@ func (conn *Conn) Close(signalToRemote bool) {
 	conn.Log.Infof("close peer connection")
 	conn.ctxCancel()
 
-	conn.wgWatcher.DisableWgWatcher()
+	if conn.wgWatcherCancel != nil {
+		conn.wgWatcherCancel()
+	}
 	conn.workerRelay.CloseConn()
 	conn.workerICE.Close()
 
@@ -296,13 +304,6 @@ func (conn *Conn) Close(signalToRemote bool) {
 
 	conn.setStatusToDisconnected()
 
-	// Reset connection metrics state
-	conn.stagesMutex.Lock()
-	conn.hasBeenConnected = false
-	conn.isReconnectionAttempt = false
-	conn.stageTimestamps = metrics.ConnectionStageTimestamps{}
-	conn.stagesMutex.Unlock()
-
 	conn.opened = false
 	conn.wg.Wait()
 	conn.Log.Infof("peer connection closed")
@@ -332,25 +333,17 @@ func (conn *Conn) SetOnDisconnected(handler func(remotePeer string)) {
 	conn.onDisconnected = handler
 }
 
+// SetRosenpassInitializedPresharedKeyValidator sets a function to check if Rosenpass has taken over
+// PSK management for a peer. When this returns true, presharedKey() returns nil
+// to prevent UpdatePeer from overwriting the Rosenpass-managed PSK.
+func (conn *Conn) SetRosenpassInitializedPresharedKeyValidator(handler func(peerKey string) bool) {
+	conn.rosenpassInitializedPresharedKeyValidator = handler
+}
+
 func (conn *Conn) OnRemoteOffer(offer OfferAnswer) {
 	conn.dumpState.RemoteOffer()
 	conn.Log.Infof("OnRemoteOffer, on status ICE: %s, status Relay: %s", conn.statusICE, conn.statusRelay)
 
-	conn.stagesMutex.Lock()
-	// Detect reconnection: we had been connected before, but now both ICE and Relay are disconnected
-	if conn.hasBeenConnected && conn.evalStatus() != StatusConnected {
-		conn.isReconnectionAttempt = true
-		conn.stageTimestamps = metrics.ConnectionStageTimestamps{} // Reset for new reconnection attempt
-		now := time.Now()
-		conn.stageTimestamps.Created = now
-		conn.stageTimestamps.Signaling = now
-		conn.Log.Infof("Reconnection triggered by remote offer")
-	} else if conn.stageTimestamps.Signaling.IsZero() {
-		// First time receiving offer for this connection attempt (signaling start)
-		conn.stageTimestamps.Signaling = time.Now()
-	}
-	conn.stagesMutex.Unlock()
-
 	conn.handshaker.OnRemoteOffer(offer)
 }
 
@@ -425,9 +418,6 @@ func (conn *Conn) onICEConnectionIsReady(priority conntype.ConnPriority, iceConn
 		ep = directEp
 	}
 
-	conn.wgWatcher.DisableWgWatcher()
-	// todo consider to run conn.wgWatcherWg.Wait() here
-
 	if conn.wgProxyRelay != nil {
 		conn.wgProxyRelay.Pause()
 	}
@@ -438,6 +428,7 @@ func (conn *Conn) onICEConnectionIsReady(priority conntype.ConnPriority, iceConn
 
 	conn.Log.Infof("configure WireGuard endpoint to: %s", ep.String())
 	presharedKey := conn.presharedKey(iceConnInfo.RosenpassPubKey)
+	conn.enableWgWatcherIfNeeded()
 	if err = conn.endpointUpdater.ConfigureWGEndpoint(ep, presharedKey); err != nil {
 		conn.handleConfigurationFailure(err, wgProxy)
 		return
@@ -449,12 +440,6 @@ func (conn *Conn) onICEConnectionIsReady(priority conntype.ConnPriority, iceConn
 		conn.wgProxyRelay.RedirectAs(ep)
 	}
 
-	conn.wgWatcherWg.Add(1)
-	go func() {
-		defer conn.wgWatcherWg.Done()
-		conn.wgWatcher.EnableWgWatcher(conn.ctx, nil)
-	}()
-
 	conn.currentConnPriority = priority
 	conn.statusICE.SetConnected()
 	conn.updateIceState(iceConnInfo)
@@ -488,17 +473,10 @@ func (conn *Conn) onICEStateDisconnected() {
 			conn.Log.Errorf("failed to switch to relay conn: %v", err)
 		}
 
-		conn.wgWatcher.DisableWgWatcher()
-		conn.wgWatcherWg.Add(1)
-		go func() {
-			defer conn.wgWatcherWg.Done()
-			conn.wgWatcher.EnableWgWatcher(conn.ctx, conn.onWGDisconnected)
-		}()
 		conn.wgProxyRelay.Work()
 		conn.currentConnPriority = conntype.Relay
 	} else {
 		conn.Log.Infof("ICE disconnected, do not switch to Relay. Reset priority to: %s", conntype.None.String())
-		conn.wgWatcher.DisableWgWatcher()
 		conn.currentConnPriority = conntype.None
 		if err := conn.config.WgConfig.WgInterface.RemoveEndpointAddress(conn.config.WgConfig.RemoteKey); err != nil {
 			conn.Log.Errorf("failed to remove wg endpoint: %v", err)
@@ -511,15 +489,19 @@ func (conn *Conn) onICEStateDisconnected() {
 	}
 	conn.statusICE.SetDisconnected()
 
+	conn.disableWgWatcherIfNeeded()
+
+	if conn.currentConnPriority == conntype.None {
+		conn.metricsStages.Disconnected()
+	}
+
 	peerState := State{
 		PubKey:           conn.config.Key,
 		ConnStatus:       conn.evalStatus(),
 		Relayed:          conn.isRelayed(),
 		ConnStatusUpdate: time.Now(),
 	}
-
-	err := conn.statusRecorder.UpdatePeerICEStateToDisconnected(peerState)
-	if err != nil {
+	if err := conn.statusRecorder.UpdatePeerICEStateToDisconnected(peerState); err != nil {
 		conn.Log.Warnf("unable to set peer's state to disconnected ice, got error: %v", err)
 	}
 }
@@ -559,6 +541,7 @@ func (conn *Conn) onRelayConnectionIsReady(rci RelayConnInfo) {
 
 	wgProxy.Work()
 	presharedKey := conn.presharedKey(rci.rosenpassPubKey)
+	conn.enableWgWatcherIfNeeded()
 	if err := conn.endpointUpdater.ConfigureWGEndpoint(wgProxy.EndpointAddr(), presharedKey); err != nil {
 		if err := wgProxy.CloseConn(); err != nil {
 			conn.Log.Warnf("Failed to close relay connection: %v", err)
@@ -567,13 +550,6 @@ func (conn *Conn) onRelayConnectionIsReady(rci RelayConnInfo) {
 		return
 	}
 
-	conn.wgWatcher.DisableWgWatcher()
-	conn.wgWatcherWg.Add(1)
-	go func() {
-		defer conn.wgWatcherWg.Done()
-		conn.wgWatcher.EnableWgWatcher(conn.ctx, conn.onWGDisconnected)
-	}()
-
 	wgConfigWorkaround()
 	conn.rosenpassRemoteKey = rci.rosenpassPubKey
 	conn.currentConnPriority = conntype.Relay
@@ -587,7 +563,11 @@ func (conn *Conn) onRelayConnectionIsReady(rci RelayConnInfo) {
 func (conn *Conn) onRelayDisconnected() {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
+	conn.handleRelayDisconnectedLocked()
+}
 
+// handleRelayDisconnectedLocked handles relay disconnection. Caller must hold conn.mu.
+func (conn *Conn) handleRelayDisconnectedLocked() {
 	if conn.ctx.Err() != nil {
 		return
 	}
@@ -613,6 +593,12 @@ func (conn *Conn) onRelayDisconnected() {
 	}
 	conn.statusRelay.SetDisconnected()
 
+	conn.disableWgWatcherIfNeeded()
+
+	if conn.currentConnPriority == conntype.None {
+		conn.metricsStages.Disconnected()
+	}
+
 	peerState := State{
 		PubKey:           conn.config.Key,
 		ConnStatus:       conn.evalStatus(),
@@ -628,15 +614,30 @@ func (conn *Conn) onGuardEvent() {
 	conn.dumpState.SendOffer()
 	if err := conn.handshaker.SendOffer(); err != nil {
 		conn.Log.Errorf("failed to send offer: %v", err)
+	}
+	conn.metricsStages.RecordSignaling()
+}
+
+func (conn *Conn) onWGDisconnected() {
+	conn.mu.Lock()
+	defer conn.mu.Unlock()
+
+	if conn.ctx.Err() != nil {
 		return
 	}
 
-	// Record signaling start timestamp (first signal sent)
-	conn.stagesMutex.Lock()
-	if conn.stageTimestamps.Signaling.IsZero() {
-		conn.stageTimestamps.Signaling = time.Now()
+	conn.Log.Warnf("WireGuard handshake timeout detected, closing current connection")
+
+	// Close the active connection based on current priority
+	switch conn.currentConnPriority {
+	case conntype.Relay:
+		conn.workerRelay.CloseConn()
+		conn.handleRelayDisconnectedLocked()
+	case conntype.ICEP2P, conntype.ICETurn:
+		conn.workerICE.Close()
+	default:
+		conn.Log.Debugf("No active connection to close on WG timeout")
 	}
-	conn.stagesMutex.Unlock()
 }
 
 func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []byte) {
@@ -701,19 +702,7 @@ func (conn *Conn) doOnConnected(remoteRosenpassPubKey []byte, remoteRosenpassAdd
 		runtime.GC()
 	}
 
-	// Record connection ready timestamp and mark as connected
-	conn.stagesMutex.Lock()
-	if conn.stageTimestamps.ConnectionReady.IsZero() {
-		conn.stageTimestamps.ConnectionReady = time.Now()
-	}
-	// Mark that we've established a connection
-	conn.hasBeenConnected = true
-
-	// todo: remove this when fixed the wireguard watcher
-	conn.stageTimestamps.WgHandshakeSuccess = time.Now()
-	conn.recordConnectionMetrics()
-
-	conn.stagesMutex.Unlock()
+	conn.metricsStages.RecordConnectionReady()
 
 	if conn.onConnected != nil {
 		conn.onConnected(conn.config.Key, remoteRosenpassPubKey, conn.config.WgConfig.AllowedIps[0].Addr().String(), remoteRosenpassAddr)
@@ -759,10 +748,17 @@ func (conn *Conn) isConnectedOnAllWay() (connected bool) {
 		}
 	}()
 
-	if runtime.GOOS != "js" && conn.statusICE.Get() == worker.StatusDisconnected && !conn.workerICE.InProgress() {
+	// For JS platform: only relay connection is supported
+	if runtime.GOOS == "js" {
+		return conn.statusRelay.Get() == worker.StatusConnected
+	}
+
+	// For non-JS platforms: check ICE connection status
+	if conn.statusICE.Get() == worker.StatusDisconnected && !conn.workerICE.InProgress() {
 		return false
 	}
 
+	// If relay is supported with peer, it must also be connected
 	if conn.workerRelay.IsRelayConnectionSupportedWithPeer() {
 		if conn.statusRelay.Get() == worker.StatusDisconnected {
 			return false
@@ -772,6 +768,26 @@ func (conn *Conn) isConnectedOnAllWay() (connected bool) {
 	return true
 }
 
+func (conn *Conn) enableWgWatcherIfNeeded() {
+	if !conn.wgWatcher.IsEnabled() {
+		wgWatcherCtx, wgWatcherCancel := context.WithCancel(conn.ctx)
+		conn.wgWatcherCancel = wgWatcherCancel
+		conn.wgWatcherWg.Add(1)
+		now := time.Now()
+		go func() {
+			defer conn.wgWatcherWg.Done()
+			conn.wgWatcher.EnableWgWatcher(wgWatcherCtx, now, conn.onWGDisconnected, conn.onWGHandshakeSuccess)
+		}()
+	}
+}
+
+func (conn *Conn) disableWgWatcherIfNeeded() {
+	if conn.currentConnPriority == conntype.None && conn.wgWatcherCancel != nil {
+		conn.wgWatcherCancel()
+		conn.wgWatcherCancel = nil
+	}
+}
+
 func (conn *Conn) newProxy(remoteConn net.Conn) (wgproxy.Proxy, error) {
 	conn.Log.Debugf("setup proxied WireGuard connection")
 	udpAddr := &net.UDPAddr{
@@ -824,29 +840,17 @@ func (conn *Conn) setRelayedProxy(proxy wgproxy.Proxy) {
 	conn.wgProxyRelay = proxy
 }
 
-// onWGDisconnected is called when the WireGuard handshake times out
-func (conn *Conn) onWGDisconnected() {
-	conn.workerRelay.CloseConn()
-	conn.onRelayDisconnected()
-}
-
 // onWGHandshakeSuccess is called when the first WireGuard handshake is detected
-func (conn *Conn) onWGHandshakeSuccess() {
-	conn.stagesMutex.Lock()
-	defer conn.stagesMutex.Unlock()
-
-	/*
-		if conn.stageTimestamps.WgHandshakeSuccess.IsZero() {
-			conn.stageTimestamps.WgHandshakeSuccess = time.Now()
-			conn.recordConnectionMetrics()
-		}
-
-	*/
+func (conn *Conn) onWGHandshakeSuccess(when time.Time) {
+	conn.metricsStages.RecordWGHandshakeSuccess(when)
+	conn.recordConnectionMetrics()
 }
 
 // recordConnectionMetrics records connection stage timestamps as metrics
 func (conn *Conn) recordConnectionMetrics() {
+	log.Infof("--- record Metrics")
 	if conn.metricsRecorder == nil {
+		log.Infof("--- is nil")
 		return
 	}
 
@@ -859,12 +863,13 @@ func (conn *Conn) recordConnectionMetrics() {
 		connType = metrics.ConnectionTypeICE
 	}
 
+	log.Infof("-- record: connType: %v, %v, %v", connType, conn.metricsStages.IsReconnection(), conn.metricsStages.GetTimestamps())
 	// Record metrics with timestamps - duration calculation happens in metrics package
 	conn.metricsRecorder.RecordConnectionStages(
 		context.Background(),
 		connType,
-		conn.isReconnectionAttempt,
-		conn.stageTimestamps,
+		conn.metricsStages.IsReconnection(),
+		conn.metricsStages.GetTimestamps(),
 	)
 }
 
@@ -886,10 +891,24 @@ func (conn *Conn) presharedKey(remoteRosenpassKey []byte) *wgtypes.Key {
 		return conn.config.WgConfig.PreSharedKey
 	}
 
+	// If Rosenpass has already set a PSK for this peer, return nil to prevent
+	// UpdatePeer from overwriting the Rosenpass-managed key.
+	if conn.rosenpassInitializedPresharedKeyValidator != nil && conn.rosenpassInitializedPresharedKeyValidator(conn.config.Key) {
+		return nil
+	}
+
+	// Use NetBird PSK as the seed for Rosenpass. This same PSK is passed to
+	// Rosenpass as PeerConfig.PresharedKey, ensuring the derived post-quantum
+	// key is cryptographically bound to the original secret.
+	if conn.config.WgConfig.PreSharedKey != nil {
+		return conn.config.WgConfig.PreSharedKey
+	}
+
+	// Fallback to deterministic key if no NetBird PSK is configured
 	determKey, err := conn.rosenpassDetermKey()
 	if err != nil {
 		conn.Log.Errorf("failed to generate Rosenpass initial key: %v", err)
-		return conn.config.WgConfig.PreSharedKey
+		return nil
 	}
 
 	return determKey

client/internal/peer/conn_test.go

@@ -284,3 +284,27 @@ func TestConn_presharedKey(t *testing.T) {
 		})
 	}
 }
+
+func TestConn_presharedKey_RosenpassManaged(t *testing.T) {
+	conn := Conn{
+		config: ConnConfig{
+			Key:             "LLHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+			LocalKey:        "RRHf3Ma6z6mdLbriAJbqhX7+nM/B71lgw2+91q3LfhU=",
+			RosenpassConfig: RosenpassConfig{PubKey: []byte("dummykey")},
+		},
+	}
+
+	// When Rosenpass has already initialized the PSK for this peer,
+	// presharedKey must return nil to avoid UpdatePeer overwriting it.
+	conn.rosenpassInitializedPresharedKeyValidator = func(peerKey string) bool { return true }
+	if k := conn.presharedKey([]byte("remote")); k != nil {
+		t.Fatalf("expected nil presharedKey when Rosenpass manages PSK, got %v", k)
+	}
+
+	// When Rosenpass hasn't taken over yet, presharedKey should provide
+	// a non-nil initial key (deterministic or from NetBird PSK).
+	conn.rosenpassInitializedPresharedKeyValidator = func(peerKey string) bool { return false }
+	if k := conn.presharedKey([]byte("remote")); k == nil {
+		t.Fatalf("expected non-nil presharedKey before Rosenpass manages PSK")
+	}
+}

client/internal/peer/metrics_saver.go

@@ -0,0 +1,88 @@
+package peer
+
+import (
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/metrics"
+)
+
+type MetricsStages struct {
+	isReconnectionAttempt bool // Track if current attempt is a reconnection
+	stageTimestamps       metrics.ConnectionStageTimestamps
+	mu                    sync.Mutex
+}
+
+func (s *MetricsStages) RecordCreated() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	log.Infof("--- RecordCreated")
+	s.stageTimestamps.Created = time.Now()
+}
+
+func (s *MetricsStages) RecordSemaphoreAcquired() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	log.Infof("--- RecordSemaphoreAcquired")
+	s.stageTimestamps.SemaphoreAcquired = time.Now()
+}
+
+func (s *MetricsStages) RecordSignaling() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	log.Infof("--- RecordSignaling")
+
+	if s.stageTimestamps.Signaling.IsZero() {
+		log.Infof("--- Recorded Signaling")
+		s.stageTimestamps.Signaling = time.Now()
+	}
+}
+
+func (s *MetricsStages) RecordConnectionReady() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	log.Infof("--- RecordConnectionReady")
+	if s.stageTimestamps.ConnectionReady.IsZero() {
+		log.Infof("--- Recorded ConnectionReady")
+		s.stageTimestamps.ConnectionReady = time.Now()
+	}
+
+}
+
+func (s *MetricsStages) RecordWGHandshakeSuccess(elapsed time.Time) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	log.Infof("--- record: %v, %v", s.stageTimestamps.ConnectionReady, elapsed)
+	if !s.stageTimestamps.ConnectionReady.IsZero() {
+		// todo, check if it is earlier then ConnectionReady
+		s.stageTimestamps.WgHandshakeSuccess = elapsed
+	}
+}
+
+func (s *MetricsStages) Disconnected() {
+	log.Infof("--- Disconnected")
+	s.mu.Lock()
+	defer s.mu.Unlock()
+
+	now := time.Now()
+	s.stageTimestamps = metrics.ConnectionStageTimestamps{
+		Created:           now,
+		SemaphoreAcquired: now,
+	}
+	s.isReconnectionAttempt = true
+}
+
+func (s *MetricsStages) IsReconnection() bool {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.isReconnectionAttempt
+}
+
+func (s *MetricsStages) GetTimestamps() metrics.ConnectionStageTimestamps {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.stageTimestamps
+}

client/internal/peer/status.go

@@ -14,6 +14,7 @@ import (
 	"golang.org/x/exp/maps"
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
+	"google.golang.org/protobuf/types/known/durationpb"
 	"google.golang.org/protobuf/types/known/timestamppb"
 
 	firewall "github.com/netbirdio/netbird/client/firewall/manager"
@@ -158,6 +159,7 @@ type FullStatus struct {
 	NSGroupStates         []NSGroupState
 	NumOfForwardingRules  int
 	LazyConnectionEnabled bool
+	Events                []*proto.SystemEvent
 }
 
 type StatusChangeSubscription struct {
@@ -981,6 +983,7 @@ func (d *Status) GetFullStatus() FullStatus {
 	}
 
 	fullStatus.Peers = append(fullStatus.Peers, d.offlinePeers...)
+	fullStatus.Events = d.GetEventHistory()
 	return fullStatus
 }
 
@@ -1181,3 +1184,97 @@ type EventSubscription struct {
 func (s *EventSubscription) Events() <-chan *proto.SystemEvent {
 	return s.events
 }
+
+// ToProto converts FullStatus to proto.FullStatus.
+func (fs FullStatus) ToProto() *proto.FullStatus {
+	pbFullStatus := proto.FullStatus{
+		ManagementState: &proto.ManagementState{},
+		SignalState:     &proto.SignalState{},
+		LocalPeerState:  &proto.LocalPeerState{},
+		Peers:           []*proto.PeerState{},
+	}
+
+	pbFullStatus.ManagementState.URL = fs.ManagementState.URL
+	pbFullStatus.ManagementState.Connected = fs.ManagementState.Connected
+	if err := fs.ManagementState.Error; err != nil {
+		pbFullStatus.ManagementState.Error = err.Error()
+	}
+
+	pbFullStatus.SignalState.URL = fs.SignalState.URL
+	pbFullStatus.SignalState.Connected = fs.SignalState.Connected
+	if err := fs.SignalState.Error; err != nil {
+		pbFullStatus.SignalState.Error = err.Error()
+	}
+
+	pbFullStatus.LocalPeerState.IP = fs.LocalPeerState.IP
+	pbFullStatus.LocalPeerState.PubKey = fs.LocalPeerState.PubKey
+	pbFullStatus.LocalPeerState.KernelInterface = fs.LocalPeerState.KernelInterface
+	pbFullStatus.LocalPeerState.Fqdn = fs.LocalPeerState.FQDN
+	pbFullStatus.LocalPeerState.RosenpassPermissive = fs.RosenpassState.Permissive
+	pbFullStatus.LocalPeerState.RosenpassEnabled = fs.RosenpassState.Enabled
+	pbFullStatus.NumberOfForwardingRules = int32(fs.NumOfForwardingRules)
+	pbFullStatus.LazyConnectionEnabled = fs.LazyConnectionEnabled
+
+	pbFullStatus.LocalPeerState.Networks = maps.Keys(fs.LocalPeerState.Routes)
+
+	for _, peerState := range fs.Peers {
+		networks := maps.Keys(peerState.GetRoutes())
+
+		pbPeerState := &proto.PeerState{
+			IP:                         peerState.IP,
+			PubKey:                     peerState.PubKey,
+			ConnStatus:                 peerState.ConnStatus.String(),
+			ConnStatusUpdate:           timestamppb.New(peerState.ConnStatusUpdate),
+			Relayed:                    peerState.Relayed,
+			LocalIceCandidateType:      peerState.LocalIceCandidateType,
+			RemoteIceCandidateType:     peerState.RemoteIceCandidateType,
+			LocalIceCandidateEndpoint:  peerState.LocalIceCandidateEndpoint,
+			RemoteIceCandidateEndpoint: peerState.RemoteIceCandidateEndpoint,
+			RelayAddress:               peerState.RelayServerAddress,
+			Fqdn:                       peerState.FQDN,
+			LastWireguardHandshake:     timestamppb.New(peerState.LastWireguardHandshake),
+			BytesRx:                    peerState.BytesRx,
+			BytesTx:                    peerState.BytesTx,
+			RosenpassEnabled:           peerState.RosenpassEnabled,
+			Networks:                   networks,
+			Latency:                    durationpb.New(peerState.Latency),
+			SshHostKey:                 peerState.SSHHostKey,
+		}
+		pbFullStatus.Peers = append(pbFullStatus.Peers, pbPeerState)
+	}
+
+	for _, relayState := range fs.Relays {
+		pbRelayState := &proto.RelayState{
+			URI:       relayState.URI,
+			Available: relayState.Err == nil,
+		}
+		if err := relayState.Err; err != nil {
+			pbRelayState.Error = err.Error()
+		}
+		pbFullStatus.Relays = append(pbFullStatus.Relays, pbRelayState)
+	}
+
+	for _, dnsState := range fs.NSGroupStates {
+		var err string
+		if dnsState.Error != nil {
+			err = dnsState.Error.Error()
+		}
+
+		var servers []string
+		for _, server := range dnsState.Servers {
+			servers = append(servers, server.String())
+		}
+
+		pbDnsState := &proto.NSGroupState{
+			Servers: servers,
+			Domains: dnsState.Domains,
+			Enabled: dnsState.Enabled,
+			Error:   err,
+		}
+		pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
+	}
+
+	pbFullStatus.Events = fs.Events
+
+	return &pbFullStatus
+}

client/internal/peer/wg_watcher.go

@@ -30,71 +30,57 @@ type WGWatcher struct {
 	peerKey       string
 	stateDump     *stateDump
 
-	ctx         context.Context
-	ctxCancel   context.CancelFunc
-	ctxLock     sync.Mutex
-	enabledTime time.Time
-
-	onFirstHandshakeFn func()
+	enabled   bool
+	muEnabled sync.RWMutex
 }
 
-func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey string, stateDump *stateDump, onFirstHandshakeFn func()) *WGWatcher {
+func NewWGWatcher(log *log.Entry, wgIfaceStater WGInterfaceStater, peerKey string, stateDump *stateDump) *WGWatcher {
 	return &WGWatcher{
-		log:                log,
-		wgIfaceStater:      wgIfaceStater,
-		peerKey:            peerKey,
-		stateDump:          stateDump,
-		onFirstHandshakeFn: onFirstHandshakeFn,
+		log:           log,
+		wgIfaceStater: wgIfaceStater,
+		peerKey:       peerKey,
+		stateDump:     stateDump,
 	}
 }
 
 // EnableWgWatcher starts the WireGuard watcher. If it is already enabled, it will return immediately and do nothing.
-func (w *WGWatcher) EnableWgWatcher(parentCtx context.Context, onDisconnectedFn func()) {
-	w.log.Debugf("enable WireGuard watcher")
-	w.ctxLock.Lock()
-	w.enabledTime = time.Now()
-
-	if w.ctx != nil && w.ctx.Err() == nil {
-		w.log.Errorf("WireGuard watcher already enabled")
-		w.ctxLock.Unlock()
+// The watcher runs until ctx is cancelled. Caller is responsible for context lifecycle management.
+func (w *WGWatcher) EnableWgWatcher(ctx context.Context, enabledTime time.Time, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time)) {
+	w.muEnabled.Lock()
+	if w.enabled {
+		w.muEnabled.Unlock()
 		return
 	}
 
-	ctx, ctxCancel := context.WithCancel(parentCtx)
-	w.ctx = ctx
-	w.ctxCancel = ctxCancel
-	w.ctxLock.Unlock()
+	w.log.Debugf("enable WireGuard watcher")
+	w.enabled = true
+	w.muEnabled.Unlock()
 
 	initialHandshake, err := w.wgState()
 	if err != nil {
 		w.log.Warnf("failed to read initial wg stats: %v", err)
 	}
 
-	w.periodicHandshakeCheck(ctx, ctxCancel, onDisconnectedFn, initialHandshake)
+	w.periodicHandshakeCheck(ctx, onDisconnectedFn, onHandshakeSuccessFn, enabledTime, initialHandshake)
+
+	w.muEnabled.Lock()
+	w.enabled = false
+	w.muEnabled.Unlock()
 }
 
-// DisableWgWatcher stops the WireGuard watcher and wait for the watcher to exit
-func (w *WGWatcher) DisableWgWatcher() {
-	w.ctxLock.Lock()
-	defer w.ctxLock.Unlock()
-
-	if w.ctxCancel == nil {
-		return
-	}
-
-	w.log.Debugf("disable WireGuard watcher")
-
-	w.ctxCancel()
-	w.ctxCancel = nil
+// IsEnabled returns true if the WireGuard watcher is currently enabled
+func (w *WGWatcher) IsEnabled() bool {
+	w.muEnabled.RLock()
+	defer w.muEnabled.RUnlock()
+	return w.enabled
 }
 
 // wgStateCheck help to check the state of the WireGuard handshake and relay connection
-func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, ctxCancel context.CancelFunc, onDisconnectedFn func(), initialHandshake time.Time) {
+func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, onDisconnectedFn func(), onHandshakeSuccessFn func(when time.Time), enabledTime time.Time, initialHandshake time.Time) {
 	w.log.Infof("WireGuard watcher started")
 
 	timer := time.NewTimer(wgHandshakeOvertime)
 	defer timer.Stop()
-	defer ctxCancel()
 
 	lastHandshake := initialHandshake
 
@@ -103,17 +89,13 @@ func (w *WGWatcher) periodicHandshakeCheck(ctx context.Context, ctxCancel contex
 		case <-timer.C:
 			handshake, ok := w.handshakeCheck(lastHandshake)
 			if !ok {
-				if onDisconnectedFn != nil {
-					onDisconnectedFn()
-				}
+				onDisconnectedFn()
 				return
 			}
 			if lastHandshake.IsZero() {
-				elapsed := w.calcElapsed(handshake)
-				w.log.Infof("first wg handshake detected within: %.2fsec, (%s)", elapsed, handshake)
-				if w.onFirstHandshakeFn != nil {
-					w.onFirstHandshakeFn()
-				}
+				elapsed := calcElapsed(enabledTime, *handshake)
+				w.log.Infof("--- first wg handshake detected within: %.2fsec, (%s - %s)", elapsed, enabledTime, handshake)
+				onHandshakeSuccessFn(*handshake)
 			}
 
 			lastHandshake = *handshake
@@ -175,8 +157,8 @@ func (w *WGWatcher) wgState() (time.Time, error) {
 
 // calcElapsed calculates elapsed time since watcher was enabled.
 // The watcher started after the wg configuration happens, because of this need to normalise the negative value
-func (w *WGWatcher) calcElapsed(handshake *time.Time) float64 {
-	elapsed := handshake.Sub(w.enabledTime).Seconds()
+func calcElapsed(enabledTime, handshake time.Time) float64 {
+	elapsed := handshake.Sub(enabledTime).Seconds()
 	if elapsed < 0 {
 		elapsed = 0
 	}

client/internal/peer/wg_watcher_test.go

@@ -2,6 +2,7 @@ package peer
 
 import (
 	"context"
+	"sync"
 	"testing"
 	"time"
 
@@ -28,15 +29,17 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
 
 	mlog := log.WithField("peer", "tet")
 	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}), nil)
+	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
 
 	ctx, cancel := context.WithCancel(context.Background())
 	defer cancel()
 
 	onDisconnected := make(chan struct{}, 1)
-	go watcher.EnableWgWatcher(ctx, func() {
+	go watcher.EnableWgWatcher(ctx,, func() {
 		mlog.Infof("onDisconnectedFn")
 		onDisconnected <- struct{}{}
+	}, func(elapsed float64) {
+		mlog.Infof("onHandshakeSuccess: %.3fs", elapsed)
 	})
 
 	// wait for initial reading
@@ -48,7 +51,6 @@ func TestWGWatcher_EnableWgWatcher(t *testing.T) {
 	case <-time.After(10 * time.Second):
 		t.Errorf("timeout")
 	}
-	watcher.DisableWgWatcher()
 }
 
 func TestWGWatcher_ReEnable(t *testing.T) {
@@ -57,20 +59,27 @@ func TestWGWatcher_ReEnable(t *testing.T) {
 
 	mlog := log.WithField("peer", "tet")
 	mocWgIface := &MocWgIface{}
-	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}), nil)
+	watcher := NewWGWatcher(mlog, mocWgIface, "", newStateDump("peer", mlog, &Status{}))
 
 	ctx, cancel := context.WithCancel(context.Background())
+	wg := &sync.WaitGroup{}
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		watcher.EnableWgWatcher(ctx, func() {}, func(elapsed float64) {})
+	}()
+	cancel()
+
+	wg.Wait()
+
+	// Re-enable with a new context
+	ctx, cancel = context.WithCancel(context.Background())
 	defer cancel()
 
 	onDisconnected := make(chan struct{}, 1)
-
-	go watcher.EnableWgWatcher(ctx, func() {})
-	time.Sleep(1 * time.Second)
-	watcher.DisableWgWatcher()
-
-	go watcher.EnableWgWatcher(ctx, func() {
+	go watcher.EnableWgWatcher(ctx,, func() {
 		onDisconnected <- struct{}{}
-	})
+	}, func(elapsed float64) {})
 
 	time.Sleep(2 * time.Second)
 	mocWgIface.disconnect()
@@ -80,5 +89,4 @@ func TestWGWatcher_ReEnable(t *testing.T) {
 	case <-time.After(10 * time.Second):
 		t.Errorf("timeout")
 	}
-	watcher.DisableWgWatcher()
 }

client/internal/peer/worker_relay.go

@@ -32,7 +32,7 @@ type WorkerRelay struct {
 	relaySupportedOnRemotePeer atomic.Bool
 }
 
-func NewWorkerRelay(ctx context.Context, log *log.Entry, ctrl bool, config ConnConfig, conn *Conn, relayManager *relayClient.Manager, stateDump *stateDump) *WorkerRelay {
+func NewWorkerRelay(ctx context.Context, log *log.Entry, ctrl bool, config ConnConfig, conn *Conn, relayManager *relayClient.Manager) *WorkerRelay {
 	r := &WorkerRelay{
 		peerCtx:      ctx,
 		log:          log,

client/internal/rosenpass/manager.go

@@ -34,6 +34,7 @@ type Manager struct {
 	server       *rp.Server
 	lock         sync.Mutex
 	port         int
+	wgIface      PresharedKeySetter
 }
 
 // NewManager creates a new Rosenpass manager
@@ -109,7 +110,13 @@ func (m *Manager) generateConfig() (rp.Config, error) {
 	cfg.SecretKey = m.ssk
 
 	cfg.Peers = []rp.PeerConfig{}
-	m.rpWgHandler, _ = NewNetbirdHandler(m.preSharedKey, m.ifaceName)
+
+	m.lock.Lock()
+	m.rpWgHandler = NewNetbirdHandler()
+	if m.wgIface != nil {
+		m.rpWgHandler.SetInterface(m.wgIface)
+	}
+	m.lock.Unlock()
 
 	cfg.Handlers = []rp.Handler{m.rpWgHandler}
 
@@ -172,6 +179,20 @@ func (m *Manager) Close() error {
 	return nil
 }
 
+// SetInterface sets the WireGuard interface for the rosenpass handler.
+// This can be called before or after Run() - the interface will be stored
+// and passed to the handler when it's created or updated immediately if
+// already running.
+func (m *Manager) SetInterface(iface PresharedKeySetter) {
+	m.lock.Lock()
+	defer m.lock.Unlock()
+
+	m.wgIface = iface
+	if m.rpWgHandler != nil {
+		m.rpWgHandler.SetInterface(iface)
+	}
+}
+
 // OnConnected is a handler function that is triggered when a connection to a remote peer establishes
 func (m *Manager) OnConnected(remoteWireGuardKey string, remoteRosenpassPubKey []byte, wireGuardIP string, remoteRosenpassAddr string) {
 	m.lock.Lock()
@@ -192,6 +213,20 @@ func (m *Manager) OnConnected(remoteWireGuardKey string, remoteRosenpassPubKey [
 	}
 }
 
+// IsPresharedKeyInitialized returns true if Rosenpass has completed a handshake
+// and set a PSK for the given WireGuard peer.
+func (m *Manager) IsPresharedKeyInitialized(wireGuardPubKey string) bool {
+	m.lock.Lock()
+	defer m.lock.Unlock()
+
+	peerID, ok := m.rpPeerIDs[wireGuardPubKey]
+	if !ok || peerID == nil {
+		return false
+	}
+
+	return m.rpWgHandler.IsPeerInitialized(*peerID)
+}
+
 func findRandomAvailableUDPPort() (int, error) {
 	conn, err := net.ListenUDP("udp", &net.UDPAddr{IP: net.IPv4zero, Port: 0})
 	if err != nil {

client/internal/rosenpass/netbird_handler.go

@@ -1,46 +1,50 @@
 package rosenpass
 
 import (
-	"fmt"
-	"log/slog"
+	"sync"
 
 	rp "cunicu.li/go-rosenpass"
 	log "github.com/sirupsen/logrus"
 
-	"golang.zx2c4.com/wireguard/wgctrl"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
 
+// PresharedKeySetter is the interface for setting preshared keys on WireGuard peers.
+// This minimal interface allows rosenpass to update PSKs without depending on the full WGIface.
+type PresharedKeySetter interface {
+	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error
+}
+
 type wireGuardPeer struct {
 	Interface string
 	PublicKey rp.Key
 }
 
 type NetbirdHandler struct {
-	ifaceName    string
-	client       *wgctrl.Client
-	peers        map[rp.PeerID]wireGuardPeer
-	presharedKey [32]byte
+	mu               sync.Mutex
+	iface            PresharedKeySetter
+	peers            map[rp.PeerID]wireGuardPeer
+	initializedPeers map[rp.PeerID]bool
 }
 
-func NewNetbirdHandler(preSharedKey *[32]byte, wgIfaceName string) (hdlr *NetbirdHandler, err error) {
-	hdlr = &NetbirdHandler{
-		ifaceName: wgIfaceName,
-		peers:     map[rp.PeerID]wireGuardPeer{},
+func NewNetbirdHandler() *NetbirdHandler {
+	return &NetbirdHandler{
+		peers:            map[rp.PeerID]wireGuardPeer{},
+		initializedPeers: map[rp.PeerID]bool{},
 	}
+}
 
-	if preSharedKey != nil {
-		hdlr.presharedKey = *preSharedKey
-	}
-
-	if hdlr.client, err = wgctrl.New(); err != nil {
-		return nil, fmt.Errorf("failed to creat WireGuard client: %w", err)
-	}
-
-	return hdlr, nil
+// SetInterface sets the WireGuard interface for the handler.
+// This must be called after the WireGuard interface is created.
+func (h *NetbirdHandler) SetInterface(iface PresharedKeySetter) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	h.iface = iface
 }
 
 func (h *NetbirdHandler) AddPeer(pid rp.PeerID, intf string, pk rp.Key) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
 	h.peers[pid] = wireGuardPeer{
 		Interface: intf,
 		PublicKey: pk,
@@ -48,79 +52,61 @@ func (h *NetbirdHandler) AddPeer(pid rp.PeerID, intf string, pk rp.Key) {
 }
 
 func (h *NetbirdHandler) RemovePeer(pid rp.PeerID) {
+	h.mu.Lock()
+	defer h.mu.Unlock()
 	delete(h.peers, pid)
+	delete(h.initializedPeers, pid)
+}
+
+// IsPeerInitialized returns true if Rosenpass has completed a handshake
+// and set a PSK for this peer.
+func (h *NetbirdHandler) IsPeerInitialized(pid rp.PeerID) bool {
+	h.mu.Lock()
+	defer h.mu.Unlock()
+	return h.initializedPeers[pid]
 }
 
 func (h *NetbirdHandler) HandshakeCompleted(pid rp.PeerID, key rp.Key) {
-	log.Debug("Handshake complete")
 	h.outputKey(rp.KeyOutputReasonStale, pid, key)
 }
 
 func (h *NetbirdHandler) HandshakeExpired(pid rp.PeerID) {
 	key, _ := rp.GeneratePresharedKey()
-	log.Debug("Handshake expired")
 	h.outputKey(rp.KeyOutputReasonStale, pid, key)
 }
 
 func (h *NetbirdHandler) outputKey(_ rp.KeyOutputReason, pid rp.PeerID, psk rp.Key) {
+	h.mu.Lock()
+	iface := h.iface
 	wg, ok := h.peers[pid]
+	isInitialized := h.initializedPeers[pid]
+	h.mu.Unlock()
+
+	if iface == nil {
+		log.Warn("rosenpass: interface not set, cannot update preshared key")
+		return
+	}
+
 	if !ok {
 		return
 	}
 
-	device, err := h.client.Device(h.ifaceName)
-	if err != nil {
-		log.Errorf("Failed to get WireGuard device: %v", err)
+	peerKey := wgtypes.Key(wg.PublicKey).String()
+	pskKey := wgtypes.Key(psk)
+
+	// Use updateOnly=true for later rotations (peer already has Rosenpass PSK)
+	// Use updateOnly=false for first rotation (peer has original/empty PSK)
+	if err := iface.SetPresharedKey(peerKey, pskKey, isInitialized); err != nil {
+		log.Errorf("Failed to apply rosenpass key: %v", err)
 		return
 	}
-	config := []wgtypes.PeerConfig{
-		{
-			UpdateOnly:   true,
-			PublicKey:    wgtypes.Key(wg.PublicKey),
-			PresharedKey: (*wgtypes.Key)(&psk),
-		},
-	}
-	for _, peer := range device.Peers {
-		if peer.PublicKey == wgtypes.Key(wg.PublicKey) {
-			if publicKeyEmpty(peer.PresharedKey) || peer.PresharedKey == h.presharedKey {
-				log.Debugf("Restart wireguard connection to peer %s", peer.PublicKey)
-				config = []wgtypes.PeerConfig{
-					{
-						PublicKey:    wgtypes.Key(wg.PublicKey),
-						PresharedKey: (*wgtypes.Key)(&psk),
-						Endpoint:     peer.Endpoint,
-						AllowedIPs:   peer.AllowedIPs,
-					},
-				}
-				err = h.client.ConfigureDevice(wg.Interface, wgtypes.Config{
-					Peers: []wgtypes.PeerConfig{
-						{
-							Remove:    true,
-							PublicKey: wgtypes.Key(wg.PublicKey),
-						},
-					},
-				})
-				if err != nil {
-					slog.Debug("Failed to remove peer")
-					return
-				}
-			}
 
+	// Mark peer as isInitialized after the successful first rotation
+	if !isInitialized {
+		h.mu.Lock()
+		if _, exists := h.peers[pid]; exists {
+			h.initializedPeers[pid] = true
 		}
-	}
-
-	if err = h.client.ConfigureDevice(wg.Interface, wgtypes.Config{
-		Peers: config,
-	}); err != nil {
-		log.Errorf("Failed to apply rosenpass key: %v", err)
+		h.mu.Unlock()
 	}
 }
-
-func publicKeyEmpty(key wgtypes.Key) bool {
-	for _, b := range key {
-		if b != 0 {
-			return false
-		}
-	}
-	return true
-}

client/internal/routemanager/dnsinterceptor/handler.go

@@ -17,12 +17,13 @@ import (
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
 	firewall "github.com/netbirdio/netbird/client/firewall/manager"
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	nbdns "github.com/netbirdio/netbird/client/internal/dns"
+	"github.com/netbirdio/netbird/client/internal/dns/resutil"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/client/internal/routemanager/common"
 	"github.com/netbirdio/netbird/client/internal/routemanager/fakeip"
+	iface "github.com/netbirdio/netbird/client/internal/routemanager/iface"
 	"github.com/netbirdio/netbird/client/internal/routemanager/refcounter"
 	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -37,11 +38,6 @@ type internalDNATer interface {
 	AddInternalDNATMapping(netip.Addr, netip.Addr) error
 }
 
-type wgInterface interface {
-	Name() string
-	Address() wgaddr.Address
-}
-
 type DnsInterceptor struct {
 	mu                   sync.RWMutex
 	route                *route.Route
@@ -51,7 +47,7 @@ type DnsInterceptor struct {
 	dnsServer            nbdns.Server
 	currentPeerKey       string
 	interceptedDomains   domainMap
-	wgInterface          wgInterface
+	wgInterface          iface.WGIface
 	peerStore            *peerstore.Store
 	firewall             firewall.Manager
 	fakeIPManager        *fakeip.Manager
@@ -219,14 +215,14 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
 
 // ServeDNS implements the dns.Handler interface
 func (d *DnsInterceptor) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
-	requestID := nbdns.GenerateRequestID()
-	logger := log.WithField("request_id", requestID)
+	logger := log.WithFields(log.Fields{
+		"request_id": resutil.GetRequestID(w),
+		"dns_id":     fmt.Sprintf("%04x", r.Id),
+	})
 
 	if len(r.Question) == 0 {
 		return
 	}
-	logger.Tracef("received DNS request for domain=%s type=%v class=%v",
-		r.Question[0].Name, r.Question[0].Qtype, r.Question[0].Qclass)
 
 	// pass if non A/AAAA query
 	if r.Question[0].Qtype != dns.TypeA && r.Question[0].Qtype != dns.TypeAAAA {
@@ -249,12 +245,6 @@ func (d *DnsInterceptor) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 		return
 	}
 
-	client, err := nbdns.GetClientPrivate(d.wgInterface.Address().IP, d.wgInterface.Name(), dnsTimeout)
-	if err != nil {
-		d.writeDNSError(w, r, logger, fmt.Sprintf("create DNS client: %v", err))
-		return
-	}
-
 	if r.Extra == nil {
 		r.MsgHdr.AuthenticatedData = true
 	}
@@ -263,32 +253,15 @@ func (d *DnsInterceptor) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	ctx, cancel := context.WithTimeout(context.Background(), dnsTimeout)
 	defer cancel()
 
-	startTime := time.Now()
-	reply, _, err := nbdns.ExchangeWithFallback(ctx, client, r, upstream)
-	if err != nil {
-		if errors.Is(err, context.DeadlineExceeded) {
-			elapsed := time.Since(startTime)
-			peerInfo := d.debugPeerTimeout(upstreamIP, peerKey)
-			logger.Errorf("peer DNS timeout after %v (timeout=%v) for domain=%s to peer %s (%s)%s - error: %v",
-				elapsed.Truncate(time.Millisecond), dnsTimeout, r.Question[0].Name, upstreamIP.String(), peerKey, peerInfo, err)
-		} else {
-			logger.Errorf("failed to exchange DNS request with %s (%s) for domain=%s: %v", upstreamIP.String(), peerKey, r.Question[0].Name, err)
-		}
-		if err := w.WriteMsg(&dns.Msg{MsgHdr: dns.MsgHdr{Rcode: dns.RcodeServerFailure, Id: r.Id}}); err != nil {
-			logger.Errorf("failed writing DNS response: %v", err)
-		}
+	reply := d.queryUpstreamDNS(ctx, w, r, upstream, upstreamIP, peerKey, logger)
+	if reply == nil {
 		return
 	}
 
-	var answer []dns.RR
-	if reply != nil {
-		answer = reply.Answer
-	}
-
-	logger.Tracef("upstream %s (%s) DNS response for domain=%s answers=%v", upstreamIP.String(), peerKey, r.Question[0].Name, answer)
+	resutil.SetMeta(w, "peer", peerKey)
 
 	reply.Id = r.Id
-	if err := d.writeMsg(w, reply); err != nil {
+	if err := d.writeMsg(w, reply, logger); err != nil {
 		logger.Errorf("failed writing DNS response: %v", err)
 	}
 }
@@ -324,11 +297,15 @@ func (d *DnsInterceptor) getUpstreamIP(peerKey string) (netip.Addr, error) {
 	return peerAllowedIP, nil
 }
 
-func (d *DnsInterceptor) writeMsg(w dns.ResponseWriter, r *dns.Msg) error {
+func (d *DnsInterceptor) writeMsg(w dns.ResponseWriter, r *dns.Msg, logger *log.Entry) error {
 	if r == nil {
 		return fmt.Errorf("received nil DNS message")
 	}
 
+	// Clear Zero bit from peer responses to prevent external sources from
+	// manipulating our internal fallthrough signaling mechanism
+	r.MsgHdr.Zero = false
+
 	if len(r.Answer) > 0 && len(r.Question) > 0 {
 		origPattern := ""
 		if writer, ok := w.(*nbdns.ResponseWriterChain); ok {
@@ -350,14 +327,14 @@ func (d *DnsInterceptor) writeMsg(w dns.ResponseWriter, r *dns.Msg) error {
 			case *dns.A:
 				addr, ok := netip.AddrFromSlice(rr.A)
 				if !ok {
-					log.Tracef("failed to convert A record for domain=%s ip=%v", resolvedDomain, rr.A)
+					logger.Tracef("failed to convert A record for domain=%s ip=%v", resolvedDomain, rr.A)
 					continue
 				}
 				ip = addr
 			case *dns.AAAA:
 				addr, ok := netip.AddrFromSlice(rr.AAAA)
 				if !ok {
-					log.Tracef("failed to convert AAAA record for domain=%s ip=%v", resolvedDomain, rr.AAAA)
+					logger.Tracef("failed to convert AAAA record for domain=%s ip=%v", resolvedDomain, rr.AAAA)
 					continue
 				}
 				ip = addr
@@ -370,11 +347,11 @@ func (d *DnsInterceptor) writeMsg(w dns.ResponseWriter, r *dns.Msg) error {
 		}
 
 		if len(newPrefixes) > 0 {
-			if err := d.updateDomainPrefixes(resolvedDomain, originalDomain, newPrefixes); err != nil {
-				log.Errorf("failed to update domain prefixes: %v", err)
+			if err := d.updateDomainPrefixes(resolvedDomain, originalDomain, newPrefixes, logger); err != nil {
+				logger.Errorf("failed to update domain prefixes: %v", err)
 			}
 
-			d.replaceIPsInDNSResponse(r, newPrefixes)
+			d.replaceIPsInDNSResponse(r, newPrefixes, logger)
 		}
 	}
 
@@ -386,22 +363,22 @@ func (d *DnsInterceptor) writeMsg(w dns.ResponseWriter, r *dns.Msg) error {
 }
 
 // logPrefixChanges handles the logging for prefix changes
-func (d *DnsInterceptor) logPrefixChanges(resolvedDomain, originalDomain domain.Domain, toAdd, toRemove []netip.Prefix) {
+func (d *DnsInterceptor) logPrefixChanges(resolvedDomain, originalDomain domain.Domain, toAdd, toRemove []netip.Prefix, logger *log.Entry) {
 	if len(toAdd) > 0 {
-		log.Debugf("added dynamic route(s) for domain=%s (pattern: domain=%s): %s",
+		logger.Debugf("added dynamic route(s) for domain=%s (pattern: domain=%s): %s",
 			resolvedDomain.SafeString(),
 			originalDomain.SafeString(),
 			toAdd)
 	}
 	if len(toRemove) > 0 && !d.route.KeepRoute {
-		log.Debugf("removed dynamic route(s) for domain=%s (pattern: domain=%s): %s",
+		logger.Debugf("removed dynamic route(s) for domain=%s (pattern: domain=%s): %s",
 			resolvedDomain.SafeString(),
 			originalDomain.SafeString(),
 			toRemove)
 	}
 }
 
-func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain domain.Domain, newPrefixes []netip.Prefix) error {
+func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain domain.Domain, newPrefixes []netip.Prefix, logger *log.Entry) error {
 	d.mu.Lock()
 	defer d.mu.Unlock()
 
@@ -418,9 +395,9 @@ func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain dom
 			realIP := prefix.Addr()
 			if fakeIP, err := d.fakeIPManager.AllocateFakeIP(realIP); err == nil {
 				dnatMappings[fakeIP] = realIP
-				log.Tracef("allocated fake IP %s for real IP %s", fakeIP, realIP)
+				logger.Tracef("allocated fake IP %s for real IP %s", fakeIP, realIP)
 			} else {
-				log.Errorf("Failed to allocate fake IP for %s: %v", realIP, err)
+				logger.Errorf("failed to allocate fake IP for %s: %v", realIP, err)
 			}
 		}
 	}
@@ -432,7 +409,7 @@ func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain dom
 		}
 	}
 
-	d.addDNATMappings(dnatMappings)
+	d.addDNATMappings(dnatMappings, logger)
 
 	if !d.route.KeepRoute {
 		// Remove old prefixes
@@ -448,7 +425,7 @@ func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain dom
 			}
 		}
 
-		d.removeDNATMappings(toRemove)
+		d.removeDNATMappings(toRemove, logger)
 	}
 
 	// Update domain prefixes using resolved domain as key - store real IPs
@@ -463,14 +440,14 @@ func (d *DnsInterceptor) updateDomainPrefixes(resolvedDomain, originalDomain dom
 		// Store real IPs for status (user-facing), not fake IPs
 		d.statusRecorder.UpdateResolvedDomainsStates(originalDomain, resolvedDomain, newPrefixes, d.route.GetResourceID())
 
-		d.logPrefixChanges(resolvedDomain, originalDomain, toAdd, toRemove)
+		d.logPrefixChanges(resolvedDomain, originalDomain, toAdd, toRemove, logger)
 	}
 
 	return nberrors.FormatErrorOrNil(merr)
 }
 
 // removeDNATMappings removes DNAT mappings from the firewall for real IP prefixes
-func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix) {
+func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix, logger *log.Entry) {
 	if len(realPrefixes) == 0 {
 		return
 	}
@@ -484,9 +461,9 @@ func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix) {
 		realIP := prefix.Addr()
 		if fakeIP, exists := d.fakeIPManager.GetFakeIP(realIP); exists {
 			if err := dnatFirewall.RemoveInternalDNATMapping(fakeIP); err != nil {
-				log.Errorf("Failed to remove DNAT mapping for %s: %v", fakeIP, err)
+				logger.Errorf("failed to remove DNAT mapping for %s: %v", fakeIP, err)
 			} else {
-				log.Debugf("Removed DNAT mapping for: %s -> %s", fakeIP, realIP)
+				logger.Debugf("removed DNAT mapping: %s -> %s", fakeIP, realIP)
 			}
 		}
 	}
@@ -502,7 +479,7 @@ func (d *DnsInterceptor) internalDnatFw() (internalDNATer, bool) {
 }
 
 // addDNATMappings adds DNAT mappings to the firewall
-func (d *DnsInterceptor) addDNATMappings(mappings map[netip.Addr]netip.Addr) {
+func (d *DnsInterceptor) addDNATMappings(mappings map[netip.Addr]netip.Addr, logger *log.Entry) {
 	if len(mappings) == 0 {
 		return
 	}
@@ -514,9 +491,9 @@ func (d *DnsInterceptor) addDNATMappings(mappings map[netip.Addr]netip.Addr) {
 
 	for fakeIP, realIP := range mappings {
 		if err := dnatFirewall.AddInternalDNATMapping(fakeIP, realIP); err != nil {
-			log.Errorf("Failed to add DNAT mapping %s -> %s: %v", fakeIP, realIP, err)
+			logger.Errorf("failed to add DNAT mapping %s -> %s: %v", fakeIP, realIP, err)
 		} else {
-			log.Debugf("Added DNAT mapping: %s -> %s", fakeIP, realIP)
+			logger.Debugf("added DNAT mapping: %s -> %s", fakeIP, realIP)
 		}
 	}
 }
@@ -528,12 +505,12 @@ func (d *DnsInterceptor) cleanupDNATMappings() {
 	}
 
 	for _, prefixes := range d.interceptedDomains {
-		d.removeDNATMappings(prefixes)
+		d.removeDNATMappings(prefixes, log.NewEntry(log.StandardLogger()))
 	}
 }
 
 // replaceIPsInDNSResponse replaces real IPs with fake IPs in the DNS response
-func (d *DnsInterceptor) replaceIPsInDNSResponse(reply *dns.Msg, realPrefixes []netip.Prefix) {
+func (d *DnsInterceptor) replaceIPsInDNSResponse(reply *dns.Msg, realPrefixes []netip.Prefix, logger *log.Entry) {
 	if _, ok := d.internalDnatFw(); !ok {
 		return
 	}
@@ -549,7 +526,7 @@ func (d *DnsInterceptor) replaceIPsInDNSResponse(reply *dns.Msg, realPrefixes []
 
 			if fakeIP, exists := d.fakeIPManager.GetFakeIP(realIP); exists {
 				rr.A = fakeIP.AsSlice()
-				log.Tracef("Replaced real IP %s with fake IP %s in DNS response", realIP, fakeIP)
+				logger.Tracef("replaced real IP %s with fake IP %s in DNS response", realIP, fakeIP)
 			}
 
 		case *dns.AAAA:
@@ -560,7 +537,7 @@ func (d *DnsInterceptor) replaceIPsInDNSResponse(reply *dns.Msg, realPrefixes []
 
 			if fakeIP, exists := d.fakeIPManager.GetFakeIP(realIP); exists {
 				rr.AAAA = fakeIP.AsSlice()
-				log.Tracef("Replaced real IP %s with fake IP %s in DNS response", realIP, fakeIP)
+				logger.Tracef("replaced real IP %s with fake IP %s in DNS response", realIP, fakeIP)
 			}
 		}
 	}
@@ -586,6 +563,44 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR
 	return
 }
 
+// queryUpstreamDNS queries the upstream DNS server using netstack if available, otherwise uses regular client.
+// Returns the DNS reply on success, or nil on error (error responses are written internally).
+func (d *DnsInterceptor) queryUpstreamDNS(ctx context.Context, w dns.ResponseWriter, r *dns.Msg, upstream string, upstreamIP netip.Addr, peerKey string, logger *log.Entry) *dns.Msg {
+	startTime := time.Now()
+
+	nsNet := d.wgInterface.GetNet()
+	var reply *dns.Msg
+	var err error
+
+	if nsNet != nil {
+		reply, err = nbdns.ExchangeWithNetstack(ctx, nsNet, r, upstream)
+	} else {
+		client, clientErr := nbdns.GetClientPrivate(d.wgInterface.Address().IP, d.wgInterface.Name(), dnsTimeout)
+		if clientErr != nil {
+			d.writeDNSError(w, r, logger, fmt.Sprintf("create DNS client: %v", clientErr))
+			return nil
+		}
+		reply, _, err = nbdns.ExchangeWithFallback(ctx, client, r, upstream)
+	}
+
+	if err == nil {
+		return reply
+	}
+
+	if errors.Is(err, context.DeadlineExceeded) {
+		elapsed := time.Since(startTime)
+		peerInfo := d.debugPeerTimeout(upstreamIP, peerKey)
+		logger.Errorf("peer DNS timeout after %v (timeout=%v) for domain=%s to peer %s (%s)%s - error: %v",
+			elapsed.Truncate(time.Millisecond), dnsTimeout, r.Question[0].Name, upstreamIP.String(), peerKey, peerInfo, err)
+	} else {
+		logger.Errorf("failed to exchange DNS request with %s (%s) for domain=%s: %v", upstreamIP.String(), peerKey, r.Question[0].Name, err)
+	}
+	if err := w.WriteMsg(&dns.Msg{MsgHdr: dns.MsgHdr{Rcode: dns.RcodeServerFailure, Id: r.Id}}); err != nil {
+		logger.Errorf("failed writing DNS response: %v", err)
+	}
+	return nil
+}
+
 func (d *DnsInterceptor) debugPeerTimeout(peerIP netip.Addr, peerKey string) string {
 	if d.statusRecorder == nil {
 		return ""

client/internal/routemanager/iface/iface_common.go

@@ -4,6 +4,8 @@ import (
 	"net"
 	"net/netip"
 
+	"golang.zx2c4.com/wireguard/tun/netstack"
+
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 )
@@ -18,4 +20,5 @@ type wgIfaceBase interface {
 	IsUserspaceBind() bool
 	GetFilter() device.PacketFilter
 	GetDevice() *device.FilteredDevice
+	GetNet() *netstack.Net
 }

client/jobexec/executor.go

@@ -0,0 +1,76 @@
+package jobexec
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"os"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/debug"
+	"github.com/netbirdio/netbird/upload-server/types"
+)
+
+const (
+	MaxBundleWaitTime = 60 * time.Minute // maximum wait time for bundle generation (1 hour)
+)
+
+var (
+	ErrJobNotImplemented = errors.New("job not implemented")
+)
+
+type Executor struct {
+}
+
+func NewExecutor() *Executor {
+	return &Executor{}
+}
+
+func (e *Executor) BundleJob(ctx context.Context, debugBundleDependencies debug.GeneratorDependencies, params debug.BundleConfig, waitForDuration time.Duration, mgmURL string) (string, error) {
+	if waitForDuration > MaxBundleWaitTime {
+		log.Warnf("bundle wait time %v exceeds maximum %v, capping to maximum", waitForDuration, MaxBundleWaitTime)
+		waitForDuration = MaxBundleWaitTime
+	}
+
+	if waitForDuration > 0 {
+		if err := waitFor(ctx, waitForDuration); err != nil {
+			return "", err
+		}
+	}
+
+	log.Infof("execute debug bundle generation")
+
+	bundleGenerator := debug.NewBundleGenerator(debugBundleDependencies, params)
+
+	path, err := bundleGenerator.Generate()
+	if err != nil {
+		return "", fmt.Errorf("generate debug bundle: %w", err)
+	}
+	defer func() {
+		if err := os.Remove(path); err != nil {
+			log.Errorf("failed to remove debug bundle file: %v", err)
+		}
+	}()
+
+	key, err := debug.UploadDebugBundle(ctx, types.DefaultBundleURL, mgmURL, path)
+	if err != nil {
+		log.Errorf("failed to upload debug bundle: %v", err)
+		return "", fmt.Errorf("upload debug bundle: %w", err)
+	}
+
+	log.Infof("debug bundle has been generated successfully")
+	return key, nil
+}
+
+func waitFor(ctx context.Context, duration time.Duration) error {
+	log.Infof("wait for %v minutes before executing debug bundle", duration.Minutes())
+	select {
+	case <-time.After(duration):
+		return nil
+	case <-ctx.Done():
+		log.Infof("wait cancelled: %v", ctx.Err())
+		return ctx.Err()
+	}
+}

client/proto/daemon.pb.go

@@ -1,7 +1,7 @@
 // Code generated by protoc-gen-go. DO NOT EDIT.
 // versions:
 // 	protoc-gen-go v1.36.6
-// 	protoc        v3.21.12
+// 	protoc        v6.33.1
 // source: daemon.proto
 
 package proto
@@ -2757,7 +2757,6 @@ func (x *ForwardingRulesResponse) GetRules() []*ForwardingRule {
 type DebugBundleRequest struct {
 	state         protoimpl.MessageState `protogen:"open.v1"`
 	Anonymize     bool                   `protobuf:"varint,1,opt,name=anonymize,proto3" json:"anonymize,omitempty"`
-	Status        string                 `protobuf:"bytes,2,opt,name=status,proto3" json:"status,omitempty"`
 	SystemInfo    bool                   `protobuf:"varint,3,opt,name=systemInfo,proto3" json:"systemInfo,omitempty"`
 	UploadURL     string                 `protobuf:"bytes,4,opt,name=uploadURL,proto3" json:"uploadURL,omitempty"`
 	LogFileCount  uint32                 `protobuf:"varint,5,opt,name=logFileCount,proto3" json:"logFileCount,omitempty"`
@@ -2802,13 +2801,6 @@ func (x *DebugBundleRequest) GetAnonymize() bool {
 	return false
 }
 
-func (x *DebugBundleRequest) GetStatus() string {
-	if x != nil {
-		return x.Status
-	}
-	return ""
-}
-
 func (x *DebugBundleRequest) GetSystemInfo() bool {
 	if x != nil {
 		return x.SystemInfo
@@ -5773,10 +5765,9 @@ const file_daemon_proto_rawDesc = "" +
 	"\x12translatedHostname\x18\x04 \x01(\tR\x12translatedHostname\x128\n" +
 	"\x0etranslatedPort\x18\x05 \x01(\v2\x10.daemon.PortInfoR\x0etranslatedPort\"G\n" +
 	"\x17ForwardingRulesResponse\x12,\n" +
-	"\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\xac\x01\n" +
+	"\x05rules\x18\x01 \x03(\v2\x16.daemon.ForwardingRuleR\x05rules\"\x94\x01\n" +
 	"\x12DebugBundleRequest\x12\x1c\n" +
-	"\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x16\n" +
-	"\x06status\x18\x02 \x01(\tR\x06status\x12\x1e\n" +
+	"\tanonymize\x18\x01 \x01(\bR\tanonymize\x12\x1e\n" +
 	"\n" +
 	"systemInfo\x18\x03 \x01(\bR\n" +
 	"systemInfo\x12\x1c\n" +

client/proto/daemon.proto

@@ -455,7 +455,6 @@ message ForwardingRulesResponse {
 // DebugBundler
 message DebugBundleRequest {
   bool anonymize = 1;
-  string status = 2;
   bool systemInfo = 3;
   string uploadURL = 4;
   uint32 logFileCount = 5;

client/server/debug.go

@@ -4,24 +4,16 @@ package server
 
 import (
 	"context"
-	"crypto/sha256"
-	"encoding/json"
 	"errors"
 	"fmt"
-	"io"
-	"net/http"
-	"os"
 
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/internal/debug"
 	"github.com/netbirdio/netbird/client/proto"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-	"github.com/netbirdio/netbird/upload-server/types"
 )
 
-const maxBundleUploadSize = 50 * 1024 * 1024
-
 // DebugBundle creates a debug bundle and returns the location.
 func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (resp *proto.DebugBundleResponse, err error) {
 	s.mutex.Lock()
@@ -44,12 +36,11 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 			InternalConfig: s.config,
 			StatusRecorder: s.statusRecorder,
 			SyncResponse:   syncResponse,
-			LogFile:        s.logFile,
+			LogPath:        s.logFile,
 			ClientMetrics:  clientMetrics,
 		},
 		debug.BundleConfig{
 			Anonymize:         req.GetAnonymize(),
-			ClientStatus:      req.GetStatus(),
 			IncludeSystemInfo: req.GetSystemInfo(),
 			LogFileCount:      req.GetLogFileCount(),
 		},
@@ -63,7 +54,7 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 	if req.GetUploadURL() == "" {
 		return &proto.DebugBundleResponse{Path: path}, nil
 	}
-	key, err := uploadDebugBundle(context.Background(), req.GetUploadURL(), s.config.ManagementURL.String(), path)
+	key, err := debug.UploadDebugBundle(context.Background(), req.GetUploadURL(), s.config.ManagementURL.String(), path)
 	if err != nil {
 		log.Errorf("failed to upload debug bundle to %s: %v", req.GetUploadURL(), err)
 		return &proto.DebugBundleResponse{Path: path, UploadFailureReason: err.Error()}, nil
@@ -74,92 +65,6 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 	return &proto.DebugBundleResponse{Path: path, UploadedKey: key}, nil
 }
 
-func uploadDebugBundle(ctx context.Context, url, managementURL, filePath string) (key string, err error) {
-	response, err := getUploadURL(ctx, url, managementURL)
-	if err != nil {
-		return "", err
-	}
-
-	err = upload(ctx, filePath, response)
-	if err != nil {
-		return "", err
-	}
-	return response.Key, nil
-}
-
-func upload(ctx context.Context, filePath string, response *types.GetURLResponse) error {
-	fileData, err := os.Open(filePath)
-	if err != nil {
-		return fmt.Errorf("open file: %w", err)
-	}
-
-	defer fileData.Close()
-
-	stat, err := fileData.Stat()
-	if err != nil {
-		return fmt.Errorf("stat file: %w", err)
-	}
-
-	if stat.Size() > maxBundleUploadSize {
-		return fmt.Errorf("file size exceeds maximum limit of %d bytes", maxBundleUploadSize)
-	}
-
-	req, err := http.NewRequestWithContext(ctx, "PUT", response.URL, fileData)
-	if err != nil {
-		return fmt.Errorf("create PUT request: %w", err)
-	}
-
-	req.ContentLength = stat.Size()
-	req.Header.Set("Content-Type", "application/octet-stream")
-
-	putResp, err := http.DefaultClient.Do(req)
-	if err != nil {
-		return fmt.Errorf("upload failed: %v", err)
-	}
-	defer putResp.Body.Close()
-
-	if putResp.StatusCode != http.StatusOK {
-		body, _ := io.ReadAll(putResp.Body)
-		return fmt.Errorf("upload status %d: %s", putResp.StatusCode, string(body))
-	}
-	return nil
-}
-
-func getUploadURL(ctx context.Context, url string, managementURL string) (*types.GetURLResponse, error) {
-	id := getURLHash(managementURL)
-	getReq, err := http.NewRequestWithContext(ctx, "GET", url+"?id="+id, nil)
-	if err != nil {
-		return nil, fmt.Errorf("create GET request: %w", err)
-	}
-
-	getReq.Header.Set(types.ClientHeader, types.ClientHeaderValue)
-
-	resp, err := http.DefaultClient.Do(getReq)
-	if err != nil {
-		return nil, fmt.Errorf("get presigned URL: %w", err)
-	}
-	defer resp.Body.Close()
-
-	if resp.StatusCode != http.StatusOK {
-		body, _ := io.ReadAll(resp.Body)
-		return nil, fmt.Errorf("get presigned URL status %d: %s", resp.StatusCode, string(body))
-	}
-
-	urlBytes, err := io.ReadAll(resp.Body)
-	if err != nil {
-		return nil, fmt.Errorf("read response body: %w", err)
-	}
-	var response types.GetURLResponse
-	if err := json.Unmarshal(urlBytes, &response); err != nil {
-		return nil, fmt.Errorf("unmarshal response: %w", err)
-	}
-	return &response, nil
-}
-
-func getURLHash(url string) string {
-	return fmt.Sprintf("%x", sha256.Sum256([]byte(url)))
-}
-
 // GetLogLevel gets the current logging level for the server.
 func (s *Server) GetLogLevel(_ context.Context, _ *proto.GetLogLevelRequest) (*proto.GetLogLevelResponse, error) {
 	s.mutex.Lock()
@@ -181,20 +86,9 @@ func (s *Server) SetLogLevel(_ context.Context, req *proto.SetLogLevelRequest) (
 
 	log.SetLevel(level)
 
-	if s.connectClient == nil {
-		return nil, fmt.Errorf("connect client not initialized")
+	if s.connectClient != nil {
+		s.connectClient.SetLogLevel(level)
 	}
-	engine := s.connectClient.Engine()
-	if engine == nil {
-		return nil, fmt.Errorf("engine not initialized")
-	}
-
-	fwManager := engine.GetFirewallManager()
-	if fwManager == nil {
-		return nil, fmt.Errorf("firewall manager not initialized")
-	}
-
-	fwManager.SetLogLevel(level)
 
 	log.Infof("Log level set to %s", level.String())
 

client/server/event.go

@@ -1,8 +1,6 @@
 package server
 
 import (
-	"context"
-
 	log "github.com/sirupsen/logrus"
 
 	"github.com/netbirdio/netbird/client/proto"
@@ -29,8 +27,3 @@ func (s *Server) SubscribeEvents(req *proto.SubscribeRequest, stream proto.Daemo
 		}
 	}
 }
-
-func (s *Server) GetEvents(context.Context, *proto.GetEventsRequest) (*proto.GetEventsResponse, error) {
-	events := s.statusRecorder.GetEventHistory()
-	return &proto.GetEventsResponse{Events: events}, nil
-}

client/server/server.go

@@ -13,15 +13,11 @@ import (
 	"time"
 
 	"github.com/cenkalti/backoff/v4"
-	"golang.org/x/exp/maps"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-	"google.golang.org/protobuf/types/known/durationpb"
-
 	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 	"google.golang.org/grpc/codes"
 	"google.golang.org/grpc/metadata"
 	gstatus "google.golang.org/grpc/status"
-	"google.golang.org/protobuf/types/known/timestamppb"
 
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -70,7 +66,7 @@ type Server struct {
 	proto.UnimplementedDaemonServiceServer
 	clientRunning     bool // protected by mutex
 	clientRunningChan chan struct{}
-	clientGiveUpChan  chan struct{}
+	clientGiveUpChan  chan struct{} // closed when connectWithRetryRuns goroutine exits
 
 	connectClient *internal.ConnectClient
 
@@ -796,9 +792,11 @@ func (s *Server) SwitchProfile(callerCtx context.Context, msg *proto.SwitchProfi
 // Down engine work in the daemon.
 func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownResponse, error) {
 	s.mutex.Lock()
-	defer s.mutex.Unlock()
+
+	giveUpChan := s.clientGiveUpChan
 
 	if err := s.cleanupConnection(); err != nil {
+		s.mutex.Unlock()
 		// todo review to update the status in case any type of error
 		log.Errorf("failed to shut down properly: %v", err)
 		return nil, err
@@ -807,6 +805,20 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
 	state := internal.CtxGetState(s.rootCtx)
 	state.Set(internal.StatusIdle)
 
+	s.mutex.Unlock()
+
+	// Wait for the connectWithRetryRuns goroutine to finish with a short timeout.
+	// This prevents the goroutine from setting ErrResetConnection after Down() returns.
+	// The giveUpChan is closed at the end of connectWithRetryRuns.
+	if giveUpChan != nil {
+		select {
+		case <-giveUpChan:
+			log.Debugf("client goroutine finished successfully")
+		case <-time.After(5 * time.Second):
+			log.Warnf("timeout waiting for client goroutine to finish, proceeding anyway")
+		}
+	}
+
 	return &proto.DownResponse{}, nil
 }
 
@@ -1067,11 +1079,9 @@ func (s *Server) Status(
 	if msg.GetFullPeerStatus {
 		s.runProbes(msg.ShouldRunProbes)
 		fullStatus := s.statusRecorder.GetFullStatus()
-		pbFullStatus := toProtoFullStatus(fullStatus)
+		pbFullStatus := fullStatus.ToProto()
 		pbFullStatus.Events = s.statusRecorder.GetEventHistory()
-
 		pbFullStatus.SshServerState = s.getSSHServerState()
-
 		statusResponse.FullStatus = pbFullStatus
 	}
 
@@ -1526,7 +1536,7 @@ func (s *Server) connect(ctx context.Context, config *profilemanager.Config, sta
 	log.Tracef("running client connection")
 	s.connectClient = internal.NewConnectClient(ctx, config, statusRecorder, doInitialAutoUpdate)
 	s.connectClient.SetSyncResponsePersistence(s.persistSyncResponse)
-	if err := s.connectClient.Run(runningChan); err != nil {
+	if err := s.connectClient.Run(runningChan, s.logFile); err != nil {
 		return err
 	}
 	return nil
@@ -1600,94 +1610,6 @@ func parseEnvDuration(envVar string, defaultDuration time.Duration) time.Duratio
 	return defaultDuration
 }
 
-func toProtoFullStatus(fullStatus peer.FullStatus) *proto.FullStatus {
-	pbFullStatus := proto.FullStatus{
-		ManagementState: &proto.ManagementState{},
-		SignalState:     &proto.SignalState{},
-		LocalPeerState:  &proto.LocalPeerState{},
-		Peers:           []*proto.PeerState{},
-	}
-
-	pbFullStatus.ManagementState.URL = fullStatus.ManagementState.URL
-	pbFullStatus.ManagementState.Connected = fullStatus.ManagementState.Connected
-	if err := fullStatus.ManagementState.Error; err != nil {
-		pbFullStatus.ManagementState.Error = err.Error()
-	}
-
-	pbFullStatus.SignalState.URL = fullStatus.SignalState.URL
-	pbFullStatus.SignalState.Connected = fullStatus.SignalState.Connected
-	if err := fullStatus.SignalState.Error; err != nil {
-		pbFullStatus.SignalState.Error = err.Error()
-	}
-
-	pbFullStatus.LocalPeerState.IP = fullStatus.LocalPeerState.IP
-	pbFullStatus.LocalPeerState.PubKey = fullStatus.LocalPeerState.PubKey
-	pbFullStatus.LocalPeerState.KernelInterface = fullStatus.LocalPeerState.KernelInterface
-	pbFullStatus.LocalPeerState.Fqdn = fullStatus.LocalPeerState.FQDN
-	pbFullStatus.LocalPeerState.RosenpassPermissive = fullStatus.RosenpassState.Permissive
-	pbFullStatus.LocalPeerState.RosenpassEnabled = fullStatus.RosenpassState.Enabled
-	pbFullStatus.LocalPeerState.Networks = maps.Keys(fullStatus.LocalPeerState.Routes)
-	pbFullStatus.NumberOfForwardingRules = int32(fullStatus.NumOfForwardingRules)
-	pbFullStatus.LazyConnectionEnabled = fullStatus.LazyConnectionEnabled
-
-	for _, peerState := range fullStatus.Peers {
-		pbPeerState := &proto.PeerState{
-			IP:                         peerState.IP,
-			PubKey:                     peerState.PubKey,
-			ConnStatus:                 peerState.ConnStatus.String(),
-			ConnStatusUpdate:           timestamppb.New(peerState.ConnStatusUpdate),
-			Relayed:                    peerState.Relayed,
-			LocalIceCandidateType:      peerState.LocalIceCandidateType,
-			RemoteIceCandidateType:     peerState.RemoteIceCandidateType,
-			LocalIceCandidateEndpoint:  peerState.LocalIceCandidateEndpoint,
-			RemoteIceCandidateEndpoint: peerState.RemoteIceCandidateEndpoint,
-			RelayAddress:               peerState.RelayServerAddress,
-			Fqdn:                       peerState.FQDN,
-			LastWireguardHandshake:     timestamppb.New(peerState.LastWireguardHandshake),
-			BytesRx:                    peerState.BytesRx,
-			BytesTx:                    peerState.BytesTx,
-			RosenpassEnabled:           peerState.RosenpassEnabled,
-			Networks:                   maps.Keys(peerState.GetRoutes()),
-			Latency:                    durationpb.New(peerState.Latency),
-			SshHostKey:                 peerState.SSHHostKey,
-		}
-		pbFullStatus.Peers = append(pbFullStatus.Peers, pbPeerState)
-	}
-
-	for _, relayState := range fullStatus.Relays {
-		pbRelayState := &proto.RelayState{
-			URI:       relayState.URI,
-			Available: relayState.Err == nil,
-		}
-		if err := relayState.Err; err != nil {
-			pbRelayState.Error = err.Error()
-		}
-		pbFullStatus.Relays = append(pbFullStatus.Relays, pbRelayState)
-	}
-
-	for _, dnsState := range fullStatus.NSGroupStates {
-		var err string
-		if dnsState.Error != nil {
-			err = dnsState.Error.Error()
-		}
-
-		var servers []string
-		for _, server := range dnsState.Servers {
-			servers = append(servers, server.String())
-		}
-
-		pbDnsState := &proto.NSGroupState{
-			Servers: servers,
-			Domains: dnsState.Domains,
-			Enabled: dnsState.Enabled,
-			Error:   err,
-		}
-		pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
-	}
-
-	return &pbFullStatus
-}
-
 // sendTerminalNotification sends a terminal notification message
 // to inform the user that the NetBird connection session has expired.
 func sendTerminalNotification() error {

client/server/server_test.go

@@ -20,6 +20,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral/manager"
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
+	"github.com/netbirdio/netbird/management/server/job"
 
 	"github.com/netbirdio/netbird/management/internals/server/config"
 	"github.com/netbirdio/netbird/management/server/groups"
@@ -306,6 +307,8 @@ func startManagement(t *testing.T, signalAddr string, counter *int) (*grpc.Serve
 	peersManager := peers.NewManager(store, permissionsManagerMock)
 	settingsManagerMock := settings.NewMockManager(ctrl)
 
+	jobManager := job.NewJobManager(nil, store, peersManager)
+
 	ia, _ := integrations.NewIntegratedValidator(context.Background(), peersManager, settingsManagerMock, eventStore)
 
 	metrics, err := telemetry.NewDefaultAppMetrics(context.Background())
@@ -317,7 +320,7 @@ func startManagement(t *testing.T, signalAddr string, counter *int) (*grpc.Serve
 	requestBuffer := server.NewAccountRequestBuffer(context.Background(), store)
 	peersUpdateManager := update_channel.NewPeersUpdateManager(metrics)
 	networkMapController := controller.NewController(context.Background(), store, metrics, peersUpdateManager, requestBuffer, server.MockIntegratedValidator{}, settingsMockManager, "netbird.selfhosted", port_forwarding.NewControllerMock(), manager.NewEphemeralManager(store, peersManager), config)
-	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManagerMock, false)
+	accountManager, err := server.BuildManager(context.Background(), config, store, networkMapController, jobManager, nil, "", eventStore, nil, false, ia, metrics, port_forwarding.NewControllerMock(), settingsMockManager, permissionsManagerMock, false)
 	if err != nil {
 		return nil, "", err
 	}
@@ -326,7 +329,7 @@ func startManagement(t *testing.T, signalAddr string, counter *int) (*grpc.Serve
 	if err != nil {
 		return nil, "", err
 	}
-	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil)
+	mgmtServer, err := nbgrpc.NewServer(config, accountManager, settingsMockManager, jobManager, secretsManager, nil, nil, &server.MockIntegratedValidator{}, networkMapController, nil)
 	if err != nil {
 		return nil, "", err
 	}

client/ssh/proxy/proxy_test.go

@@ -132,7 +132,7 @@ func TestSSHProxy_Connect(t *testing.T) {
 		HostKeyPEM: hostKey,
 		JWT: &server.JWTConfig{
 			Issuer:       issuer,
-			Audience:     audience,
+			Audiences:    []string{audience},
 			KeysLocation: jwksURL,
 		},
 	}

client/ssh/server/jwt_test.go

@@ -43,7 +43,7 @@ func TestJWTEnforcement(t *testing.T) {
 	t.Run("blocks_without_jwt", func(t *testing.T) {
 		jwtConfig := &JWTConfig{
 			Issuer:       "test-issuer",
-			Audience:     "test-audience",
+			Audiences:    []string{"test-audience"},
 			KeysLocation: "test-keys",
 		}
 		serverConfig := &Config{
@@ -202,7 +202,7 @@ func TestJWTDetection(t *testing.T) {
 
 	jwtConfig := &JWTConfig{
 		Issuer:       issuer,
-		Audience:     audience,
+		Audiences:    []string{audience},
 		KeysLocation: jwksURL,
 	}
 	serverConfig := &Config{
@@ -329,7 +329,7 @@ func TestJWTFailClose(t *testing.T) {
 		t.Run(tc.name, func(t *testing.T) {
 			jwtConfig := &JWTConfig{
 				Issuer:       issuer,
-				Audience:     audience,
+				Audiences:    []string{audience},
 				KeysLocation: jwksURL,
 				MaxTokenAge:  3600,
 			}
@@ -567,7 +567,7 @@ func TestJWTAuthentication(t *testing.T) {
 
 			jwtConfig := &JWTConfig{
 				Issuer:       issuer,
-				Audience:     audience,
+				Audiences:    []string{audience},
 				KeysLocation: jwksURL,
 			}
 			serverConfig := &Config{
@@ -646,3 +646,108 @@ func TestJWTAuthentication(t *testing.T) {
 		})
 	}
 }
+
+// TestJWTMultipleAudiences tests JWT validation with multiple audiences (dashboard and CLI).
+func TestJWTMultipleAudiences(t *testing.T) {
+	if testing.Short() {
+		t.Skip("Skipping JWT multiple audiences tests in short mode")
+	}
+
+	jwksServer, privateKey, jwksURL := setupJWKSServer(t)
+	defer jwksServer.Close()
+
+	const (
+		issuer            = "https://test-issuer.example.com"
+		dashboardAudience = "dashboard-audience"
+		cliAudience       = "cli-audience"
+	)
+
+	hostKey, err := nbssh.GeneratePrivateKey(nbssh.ED25519)
+	require.NoError(t, err)
+
+	testCases := []struct {
+		name       string
+		audience   string
+		wantAuthOK bool
+	}{
+		{
+			name:       "accepts_dashboard_audience",
+			audience:   dashboardAudience,
+			wantAuthOK: true,
+		},
+		{
+			name:       "accepts_cli_audience",
+			audience:   cliAudience,
+			wantAuthOK: true,
+		},
+		{
+			name:       "rejects_unknown_audience",
+			audience:   "unknown-audience",
+			wantAuthOK: false,
+		},
+	}
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			jwtConfig := &JWTConfig{
+				Issuer:       issuer,
+				Audiences:    []string{dashboardAudience, cliAudience},
+				KeysLocation: jwksURL,
+			}
+			serverConfig := &Config{
+				HostKeyPEM: hostKey,
+				JWT:        jwtConfig,
+			}
+			server := New(serverConfig)
+			server.SetAllowRootLogin(true)
+
+			testUserHash, err := sshuserhash.HashUserID("test-user")
+			require.NoError(t, err)
+
+			currentUser := testutil.GetTestUsername(t)
+			authConfig := &sshauth.Config{
+				UserIDClaim:     sshauth.DefaultUserIDClaim,
+				AuthorizedUsers: []sshuserhash.UserIDHash{testUserHash},
+				MachineUsers: map[string][]uint32{
+					currentUser: {0},
+				},
+			}
+			server.UpdateSSHAuth(authConfig)
+
+			serverAddr := StartTestServer(t, server)
+			defer require.NoError(t, server.Stop())
+
+			host, portStr, err := net.SplitHostPort(serverAddr)
+			require.NoError(t, err)
+
+			token := generateValidJWT(t, privateKey, issuer, tc.audience)
+			config := &cryptossh.ClientConfig{
+				User: testutil.GetTestUsername(t),
+				Auth: []cryptossh.AuthMethod{
+					cryptossh.Password(token),
+				},
+				HostKeyCallback: cryptossh.InsecureIgnoreHostKey(),
+				Timeout:         2 * time.Second,
+			}
+
+			conn, err := cryptossh.Dial("tcp", net.JoinHostPort(host, portStr), config)
+			if tc.wantAuthOK {
+				require.NoError(t, err, "JWT authentication should succeed for audience %s", tc.audience)
+				defer func() {
+					if err := conn.Close(); err != nil {
+						t.Logf("close connection: %v", err)
+					}
+				}()
+
+				session, err := conn.NewSession()
+				require.NoError(t, err)
+				defer session.Close()
+
+				err = session.Shell()
+				require.NoError(t, err, "Shell should work with valid audience")
+			} else {
+				assert.Error(t, err, "JWT authentication should fail for unknown audience")
+			}
+		})
+	}
+}

client/ssh/server/server.go

@@ -176,9 +176,9 @@ type Server struct {
 
 type JWTConfig struct {
 	Issuer       string
-	Audience     string
 	KeysLocation string
 	MaxTokenAge  int64
+	Audiences    []string
 }
 
 // Config contains all SSH server configuration options
@@ -427,18 +427,21 @@ func (s *Server) ensureJWTValidator() error {
 		return fmt.Errorf("JWT config not set")
 	}
 
-	log.Debugf("Initializing JWT validator (issuer: %s, audience: %s)", config.Issuer, config.Audience)
+	if len(config.Audiences) == 0 {
+		return fmt.Errorf("JWT config has no audiences configured")
+	}
 
+	log.Debugf("Initializing JWT validator (issuer: %s, audiences: %v)", config.Issuer, config.Audiences)
 	validator := jwt.NewValidator(
 		config.Issuer,
-		[]string{config.Audience},
+		config.Audiences,
 		config.KeysLocation,
 		true,
 	)
 
 	// Use custom userIDClaim from authorizer if available
 	extractorOptions := []jwt.ClaimsExtractorOption{
-		jwt.WithAudience(config.Audience),
+		jwt.WithAudience(config.Audiences[0]),
 	}
 	if authorizer.GetUserIDClaim() != "" {
 		extractorOptions = append(extractorOptions, jwt.WithUserIDClaim(authorizer.GetUserIDClaim()))
@@ -475,8 +478,8 @@ func (s *Server) validateJWTToken(tokenString string) (*gojwt.Token, error) {
 	if err != nil {
 		if jwtConfig != nil {
 			if claims, parseErr := s.parseTokenWithoutValidation(tokenString); parseErr == nil {
-				return nil, fmt.Errorf("validate token (expected issuer=%s, audience=%s, actual issuer=%v, audience=%v): %w",
-					jwtConfig.Issuer, jwtConfig.Audience, claims["iss"], claims["aud"], err)
+				return nil, fmt.Errorf("validate token (expected issuer=%s, audiences=%v, actual issuer=%v, audience=%v): %w",
+					jwtConfig.Issuer, jwtConfig.Audiences, claims["iss"], claims["aud"], err)
 			}
 		}
 		return nil, fmt.Errorf("validate token: %w", err)

client/status/status.go

@@ -11,8 +11,12 @@ import (
 	"strings"
 	"time"
 
+	"google.golang.org/protobuf/types/known/durationpb"
+	"google.golang.org/protobuf/types/known/timestamppb"
 	"gopkg.in/yaml.v3"
 
+	"golang.org/x/exp/maps"
+
 	"github.com/netbirdio/netbird/client/anonymize"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	probeRelay "github.com/netbirdio/netbird/client/internal/relay"
@@ -116,9 +120,7 @@ type OutputOverview struct {
 	SSHServerState          SSHServerStateOutput       `json:"sshServer" yaml:"sshServer"`
 }
 
-func ConvertToStatusOutputOverview(resp *proto.StatusResponse, anon bool, statusFilter string, prefixNamesFilter []string, prefixNamesFilterMap map[string]struct{}, ipsFilter map[string]struct{}, connectionTypeFilter string, profName string) OutputOverview {
-	pbFullStatus := resp.GetFullStatus()
-
+func ConvertToStatusOutputOverview(pbFullStatus *proto.FullStatus, anon bool, daemonVersion string, statusFilter string, prefixNamesFilter []string, prefixNamesFilterMap map[string]struct{}, ipsFilter map[string]struct{}, connectionTypeFilter string, profName string) OutputOverview {
 	managementState := pbFullStatus.GetManagementState()
 	managementOverview := ManagementStateOutput{
 		URL:       managementState.GetURL(),
@@ -134,13 +136,13 @@ func ConvertToStatusOutputOverview(resp *proto.StatusResponse, anon bool, status
 	}
 
 	relayOverview := mapRelays(pbFullStatus.GetRelays())
-	peersOverview := mapPeers(resp.GetFullStatus().GetPeers(), statusFilter, prefixNamesFilter, prefixNamesFilterMap, ipsFilter, connectionTypeFilter)
 	sshServerOverview := mapSSHServer(pbFullStatus.GetSshServerState())
+	peersOverview := mapPeers(pbFullStatus.GetPeers(), statusFilter, prefixNamesFilter, prefixNamesFilterMap, ipsFilter, connectionTypeFilter)
 
 	overview := OutputOverview{
 		Peers:                   peersOverview,
 		CliVersion:              version.NetbirdVersion(),
-		DaemonVersion:           resp.GetDaemonVersion(),
+		DaemonVersion:           daemonVersion,
 		ManagementState:         managementOverview,
 		SignalState:             signalOverview,
 		Relays:                  relayOverview,
@@ -325,61 +327,64 @@ func sortPeersByIP(peersStateDetail []PeerStateDetailOutput) {
 	}
 }
 
-func ParseToJSON(overview OutputOverview) (string, error) {
-	jsonBytes, err := json.Marshal(overview)
+// JSON returns the status overview as a JSON string.
+func (o *OutputOverview) JSON() (string, error) {
+	jsonBytes, err := json.Marshal(o)
 	if err != nil {
 		return "", fmt.Errorf("json marshal failed")
 	}
 	return string(jsonBytes), err
 }
 
-func ParseToYAML(overview OutputOverview) (string, error) {
-	yamlBytes, err := yaml.Marshal(overview)
+// YAML returns the status overview as a YAML string.
+func (o *OutputOverview) YAML() (string, error) {
+	yamlBytes, err := yaml.Marshal(o)
 	if err != nil {
 		return "", fmt.Errorf("yaml marshal failed")
 	}
 	return string(yamlBytes), nil
 }
 
-func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool, showNameServers bool, showSSHSessions bool) string {
+// GeneralSummary returns a general summary of the status overview.
+func (o *OutputOverview) GeneralSummary(showURL bool, showRelays bool, showNameServers bool, showSSHSessions bool) string {
 	var managementConnString string
-	if overview.ManagementState.Connected {
+	if o.ManagementState.Connected {
 		managementConnString = "Connected"
 		if showURL {
-			managementConnString = fmt.Sprintf("%s to %s", managementConnString, overview.ManagementState.URL)
+			managementConnString = fmt.Sprintf("%s to %s", managementConnString, o.ManagementState.URL)
 		}
 	} else {
 		managementConnString = "Disconnected"
-		if overview.ManagementState.Error != "" {
-			managementConnString = fmt.Sprintf("%s, reason: %s", managementConnString, overview.ManagementState.Error)
+		if o.ManagementState.Error != "" {
+			managementConnString = fmt.Sprintf("%s, reason: %s", managementConnString, o.ManagementState.Error)
 		}
 	}
 
 	var signalConnString string
-	if overview.SignalState.Connected {
+	if o.SignalState.Connected {
 		signalConnString = "Connected"
 		if showURL {
-			signalConnString = fmt.Sprintf("%s to %s", signalConnString, overview.SignalState.URL)
+			signalConnString = fmt.Sprintf("%s to %s", signalConnString, o.SignalState.URL)
 		}
 	} else {
 		signalConnString = "Disconnected"
-		if overview.SignalState.Error != "" {
-			signalConnString = fmt.Sprintf("%s, reason: %s", signalConnString, overview.SignalState.Error)
+		if o.SignalState.Error != "" {
+			signalConnString = fmt.Sprintf("%s, reason: %s", signalConnString, o.SignalState.Error)
 		}
 	}
 
 	interfaceTypeString := "Userspace"
-	interfaceIP := overview.IP
-	if overview.KernelInterface {
+	interfaceIP := o.IP
+	if o.KernelInterface {
 		interfaceTypeString = "Kernel"
-	} else if overview.IP == "" {
+	} else if o.IP == "" {
 		interfaceTypeString = "N/A"
 		interfaceIP = "N/A"
 	}
 
 	var relaysString string
 	if showRelays {
-		for _, relay := range overview.Relays.Details {
+		for _, relay := range o.Relays.Details {
 			available := "Available"
 			reason := ""
 
@@ -395,18 +400,18 @@ func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool,
 			relaysString += fmt.Sprintf("\n  [%s] is %s%s", relay.URI, available, reason)
 		}
 	} else {
-		relaysString = fmt.Sprintf("%d/%d Available", overview.Relays.Available, overview.Relays.Total)
+		relaysString = fmt.Sprintf("%d/%d Available", o.Relays.Available, o.Relays.Total)
 	}
 
 	networks := "-"
-	if len(overview.Networks) > 0 {
-		sort.Strings(overview.Networks)
-		networks = strings.Join(overview.Networks, ", ")
+	if len(o.Networks) > 0 {
+		sort.Strings(o.Networks)
+		networks = strings.Join(o.Networks, ", ")
 	}
 
 	var dnsServersString string
 	if showNameServers {
-		for _, nsServerGroup := range overview.NSServerGroups {
+		for _, nsServerGroup := range o.NSServerGroups {
 			enabled := "Available"
 			if !nsServerGroup.Enabled {
 				enabled = "Unavailable"
@@ -430,25 +435,25 @@ func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool,
 			)
 		}
 	} else {
-		dnsServersString = fmt.Sprintf("%d/%d Available", countEnabled(overview.NSServerGroups), len(overview.NSServerGroups))
+		dnsServersString = fmt.Sprintf("%d/%d Available", countEnabled(o.NSServerGroups), len(o.NSServerGroups))
 	}
 
 	rosenpassEnabledStatus := "false"
-	if overview.RosenpassEnabled {
+	if o.RosenpassEnabled {
 		rosenpassEnabledStatus = "true"
-		if overview.RosenpassPermissive {
+		if o.RosenpassPermissive {
 			rosenpassEnabledStatus = "true (permissive)" //nolint:gosec
 		}
 	}
 
 	lazyConnectionEnabledStatus := "false"
-	if overview.LazyConnectionEnabled {
+	if o.LazyConnectionEnabled {
 		lazyConnectionEnabledStatus = "true"
 	}
 
 	sshServerStatus := "Disabled"
-	if overview.SSHServerState.Enabled {
-		sessionCount := len(overview.SSHServerState.Sessions)
+	if o.SSHServerState.Enabled {
+		sessionCount := len(o.SSHServerState.Sessions)
 		if sessionCount > 0 {
 			sessionWord := "session"
 			if sessionCount > 1 {
@@ -460,7 +465,7 @@ func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool,
 		}
 
 		if showSSHSessions && sessionCount > 0 {
-			for _, session := range overview.SSHServerState.Sessions {
+			for _, session := range o.SSHServerState.Sessions {
 				var sessionDisplay string
 				if session.JWTUsername != "" {
 					sessionDisplay = fmt.Sprintf("[%s@%s -> %s] %s",
@@ -484,7 +489,7 @@ func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool,
 		}
 	}
 
-	peersCountString := fmt.Sprintf("%d/%d Connected", overview.Peers.Connected, overview.Peers.Total)
+	peersCountString := fmt.Sprintf("%d/%d Connected", o.Peers.Connected, o.Peers.Total)
 
 	goos := runtime.GOOS
 	goarch := runtime.GOARCH
@@ -512,30 +517,31 @@ func ParseGeneralSummary(overview OutputOverview, showURL bool, showRelays bool,
 			"Forwarding rules: %d\n"+
 			"Peers count: %s\n",
 		fmt.Sprintf("%s/%s%s", goos, goarch, goarm),
-		overview.DaemonVersion,
+		o.DaemonVersion,
 		version.NetbirdVersion(),
-		overview.ProfileName,
+		o.ProfileName,
 		managementConnString,
 		signalConnString,
 		relaysString,
 		dnsServersString,
-		domain.Domain(overview.FQDN).SafeString(),
+		domain.Domain(o.FQDN).SafeString(),
 		interfaceIP,
 		interfaceTypeString,
 		rosenpassEnabledStatus,
 		lazyConnectionEnabledStatus,
 		sshServerStatus,
 		networks,
-		overview.NumberOfForwardingRules,
+		o.NumberOfForwardingRules,
 		peersCountString,
 	)
 	return summary
 }
 
-func ParseToFullDetailSummary(overview OutputOverview) string {
-	parsedPeersString := parsePeers(overview.Peers, overview.RosenpassEnabled, overview.RosenpassPermissive)
-	parsedEventsString := parseEvents(overview.Events)
-	summary := ParseGeneralSummary(overview, true, true, true, true)
+// FullDetailSummary returns a full detailed summary with peer details and events.
+func (o *OutputOverview) FullDetailSummary() string {
+	parsedPeersString := parsePeers(o.Peers, o.RosenpassEnabled, o.RosenpassPermissive)
+	parsedEventsString := parseEvents(o.Events)
+	summary := o.GeneralSummary(true, true, true, true)
 
 	return fmt.Sprintf(
 		"Peers detail:"+
@@ -549,6 +555,94 @@ func ParseToFullDetailSummary(overview OutputOverview) string {
 	)
 }
 
+func ToProtoFullStatus(fullStatus peer.FullStatus) *proto.FullStatus {
+	pbFullStatus := proto.FullStatus{
+		ManagementState: &proto.ManagementState{},
+		SignalState:     &proto.SignalState{},
+		LocalPeerState:  &proto.LocalPeerState{},
+		Peers:           []*proto.PeerState{},
+	}
+
+	pbFullStatus.ManagementState.URL = fullStatus.ManagementState.URL
+	pbFullStatus.ManagementState.Connected = fullStatus.ManagementState.Connected
+	if err := fullStatus.ManagementState.Error; err != nil {
+		pbFullStatus.ManagementState.Error = err.Error()
+	}
+
+	pbFullStatus.SignalState.URL = fullStatus.SignalState.URL
+	pbFullStatus.SignalState.Connected = fullStatus.SignalState.Connected
+	if err := fullStatus.SignalState.Error; err != nil {
+		pbFullStatus.SignalState.Error = err.Error()
+	}
+
+	pbFullStatus.LocalPeerState.IP = fullStatus.LocalPeerState.IP
+	pbFullStatus.LocalPeerState.PubKey = fullStatus.LocalPeerState.PubKey
+	pbFullStatus.LocalPeerState.KernelInterface = fullStatus.LocalPeerState.KernelInterface
+	pbFullStatus.LocalPeerState.Fqdn = fullStatus.LocalPeerState.FQDN
+	pbFullStatus.LocalPeerState.RosenpassPermissive = fullStatus.RosenpassState.Permissive
+	pbFullStatus.LocalPeerState.RosenpassEnabled = fullStatus.RosenpassState.Enabled
+	pbFullStatus.LocalPeerState.Networks = maps.Keys(fullStatus.LocalPeerState.Routes)
+	pbFullStatus.NumberOfForwardingRules = int32(fullStatus.NumOfForwardingRules)
+	pbFullStatus.LazyConnectionEnabled = fullStatus.LazyConnectionEnabled
+
+	for _, peerState := range fullStatus.Peers {
+		pbPeerState := &proto.PeerState{
+			IP:                         peerState.IP,
+			PubKey:                     peerState.PubKey,
+			ConnStatus:                 peerState.ConnStatus.String(),
+			ConnStatusUpdate:           timestamppb.New(peerState.ConnStatusUpdate),
+			Relayed:                    peerState.Relayed,
+			LocalIceCandidateType:      peerState.LocalIceCandidateType,
+			RemoteIceCandidateType:     peerState.RemoteIceCandidateType,
+			LocalIceCandidateEndpoint:  peerState.LocalIceCandidateEndpoint,
+			RemoteIceCandidateEndpoint: peerState.RemoteIceCandidateEndpoint,
+			RelayAddress:               peerState.RelayServerAddress,
+			Fqdn:                       peerState.FQDN,
+			LastWireguardHandshake:     timestamppb.New(peerState.LastWireguardHandshake),
+			BytesRx:                    peerState.BytesRx,
+			BytesTx:                    peerState.BytesTx,
+			RosenpassEnabled:           peerState.RosenpassEnabled,
+			Networks:                   maps.Keys(peerState.GetRoutes()),
+			Latency:                    durationpb.New(peerState.Latency),
+			SshHostKey:                 peerState.SSHHostKey,
+		}
+		pbFullStatus.Peers = append(pbFullStatus.Peers, pbPeerState)
+	}
+
+	for _, relayState := range fullStatus.Relays {
+		pbRelayState := &proto.RelayState{
+			URI:       relayState.URI,
+			Available: relayState.Err == nil,
+		}
+		if err := relayState.Err; err != nil {
+			pbRelayState.Error = err.Error()
+		}
+		pbFullStatus.Relays = append(pbFullStatus.Relays, pbRelayState)
+	}
+
+	for _, dnsState := range fullStatus.NSGroupStates {
+		var err string
+		if dnsState.Error != nil {
+			err = dnsState.Error.Error()
+		}
+
+		var servers []string
+		for _, server := range dnsState.Servers {
+			servers = append(servers, server.String())
+		}
+
+		pbDnsState := &proto.NSGroupState{
+			Servers: servers,
+			Domains: dnsState.Domains,
+			Enabled: dnsState.Enabled,
+			Error:   err,
+		}
+		pbFullStatus.DnsServers = append(pbFullStatus.DnsServers, pbDnsState)
+	}
+
+	return &pbFullStatus
+}
+
 func parsePeers(peers PeersStateOutput, rosenpassEnabled, rosenpassPermissive bool) string {
 	var (
 		peersString = ""

client/status/status_test.go

@@ -238,7 +238,7 @@ var overview = OutputOverview{
 }
 
 func TestConversionFromFullStatusToOutputOverview(t *testing.T) {
-	convertedResult := ConvertToStatusOutputOverview(resp, false, "", nil, nil, nil, "", "")
+	convertedResult := ConvertToStatusOutputOverview(resp.GetFullStatus(), false, resp.GetDaemonVersion(), "", nil, nil, nil, "", "")
 
 	assert.Equal(t, overview, convertedResult)
 }
@@ -268,7 +268,7 @@ func TestSortingOfPeers(t *testing.T) {
 }
 
 func TestParsingToJSON(t *testing.T) {
-	jsonString, _ := ParseToJSON(overview)
+	jsonString, _ := overview.JSON()
 
 	//@formatter:off
 	expectedJSONString := `
@@ -404,7 +404,7 @@ func TestParsingToJSON(t *testing.T) {
 }
 
 func TestParsingToYAML(t *testing.T) {
-	yaml, _ := ParseToYAML(overview)
+	yaml, _ := overview.YAML()
 
 	expectedYAML :=
 		`peers:
@@ -511,7 +511,7 @@ func TestParsingToDetail(t *testing.T) {
 	lastConnectionUpdate2 := timeAgo(overview.Peers.Details[1].LastStatusUpdate)
 	lastHandshake2 := timeAgo(overview.Peers.Details[1].LastWireguardHandshake)
 
-	detail := ParseToFullDetailSummary(overview)
+	detail := overview.FullDetailSummary()
 
 	expectedDetail := fmt.Sprintf(
 		`Peers detail:
@@ -575,7 +575,7 @@ Peers count: 2/2 Connected
 }
 
 func TestParsingToShortVersion(t *testing.T) {
-	shortVersion := ParseGeneralSummary(overview, false, false, false, false)
+	shortVersion := overview.GeneralSummary(false, false, false, false)
 
 	expectedString := fmt.Sprintf("OS: %s/%s", runtime.GOOS, runtime.GOARCH) + `
 Daemon version: 0.14.1

client/ui/debug.go

@@ -18,9 +18,7 @@ import (
 	"github.com/skratchdot/open-golang/open"
 
 	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
-	nbstatus "github.com/netbirdio/netbird/client/status"
 	uptypes "github.com/netbirdio/netbird/upload-server/types"
 )
 
@@ -291,19 +289,18 @@ func (s *serviceClient) handleRunForDuration(
 		return
 	}
 
-	statusOutput, err := s.collectDebugData(conn, initialState, params, progressUI)
-	if err != nil {
+	defer s.restoreServiceState(conn, initialState)
+
+	if err := s.collectDebugData(conn, initialState, params, progressUI); err != nil {
 		handleError(progressUI, err.Error())
 		return
 	}
 
-	if err := s.createDebugBundleFromCollection(conn, params, statusOutput, progressUI); err != nil {
+	if err := s.createDebugBundleFromCollection(conn, params, progressUI); err != nil {
 		handleError(progressUI, err.Error())
 		return
 	}
 
-	s.restoreServiceState(conn, initialState)
-
 	progressUI.statusLabel.SetText("Bundle created successfully")
 }
 
@@ -417,68 +414,33 @@ func (s *serviceClient) collectDebugData(
 	state *debugInitialState,
 	params *debugCollectionParams,
 	progress *progressUI,
-) (string, error) {
+) error {
 	ctx, cancel := context.WithTimeout(s.ctx, params.duration)
 	defer cancel()
 	var wg sync.WaitGroup
 	startProgressTracker(ctx, &wg, params.duration, progress)
 
 	if err := s.configureServiceForDebug(conn, state, params.enablePersistence); err != nil {
-		return "", err
+		return err
 	}
 
-	pm := profilemanager.NewProfileManager()
-	var profName string
-	if activeProf, err := pm.GetActiveProfile(); err == nil {
-		profName = activeProf.Name
-	}
-
-	postUpStatus, err := conn.Status(s.ctx, &proto.StatusRequest{GetFullPeerStatus: true})
-	if err != nil {
-		log.Warnf("Failed to get post-up status: %v", err)
-	}
-
-	var postUpStatusOutput string
-	if postUpStatus != nil {
-		overview := nbstatus.ConvertToStatusOutputOverview(postUpStatus, params.anonymize, "", nil, nil, nil, "", profName)
-		postUpStatusOutput = nbstatus.ParseToFullDetailSummary(overview)
-	}
-	headerPostUp := fmt.Sprintf("----- NetBird post-up - Timestamp: %s", time.Now().Format(time.RFC3339))
-	statusOutput := fmt.Sprintf("%s\n%s", headerPostUp, postUpStatusOutput)
-
 	wg.Wait()
 	progress.progressBar.Hide()
 	progress.statusLabel.SetText("Collecting debug data...")
 
-	preDownStatus, err := conn.Status(s.ctx, &proto.StatusRequest{GetFullPeerStatus: true})
-	if err != nil {
-		log.Warnf("Failed to get pre-down status: %v", err)
-	}
-
-	var preDownStatusOutput string
-	if preDownStatus != nil {
-		overview := nbstatus.ConvertToStatusOutputOverview(preDownStatus, params.anonymize, "", nil, nil, nil, "", profName)
-		preDownStatusOutput = nbstatus.ParseToFullDetailSummary(overview)
-	}
-	headerPreDown := fmt.Sprintf("----- NetBird pre-down - Timestamp: %s - Duration: %s",
-		time.Now().Format(time.RFC3339), params.duration)
-	statusOutput = fmt.Sprintf("%s\n%s\n%s", statusOutput, headerPreDown, preDownStatusOutput)
-
-	return statusOutput, nil
+	return nil
 }
 
 // Create the debug bundle with collected data
 func (s *serviceClient) createDebugBundleFromCollection(
 	conn proto.DaemonServiceClient,
 	params *debugCollectionParams,
-	statusOutput string,
 	progress *progressUI,
 ) error {
 	progress.statusLabel.SetText("Creating debug bundle with collected logs...")
 
 	request := &proto.DebugBundleRequest{
 		Anonymize:  params.anonymize,
-		Status:     statusOutput,
 		SystemInfo: params.systemInfo,
 	}
 
@@ -581,26 +543,8 @@ func (s *serviceClient) createDebugBundle(anonymize bool, systemInfo bool, uploa
 		return nil, fmt.Errorf("get client: %v", err)
 	}
 
-	pm := profilemanager.NewProfileManager()
-	var profName string
-	if activeProf, err := pm.GetActiveProfile(); err == nil {
-		profName = activeProf.Name
-	}
-
-	statusResp, err := conn.Status(s.ctx, &proto.StatusRequest{GetFullPeerStatus: true})
-	if err != nil {
-		log.Warnf("failed to get status for debug bundle: %v", err)
-	}
-
-	var statusOutput string
-	if statusResp != nil {
-		overview := nbstatus.ConvertToStatusOutputOverview(statusResp, anonymize, "", nil, nil, nil, "", profName)
-		statusOutput = nbstatus.ParseToFullDetailSummary(overview)
-	}
-
 	request := &proto.DebugBundleRequest{
 		Anonymize:  anonymize,
-		Status:     statusOutput,
 		SystemInfo: systemInfo,
 	}
 

client/wasm/cmd/main.go

@@ -9,20 +9,28 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
+	"google.golang.org/protobuf/encoding/protojson"
 
 	netbird "github.com/netbirdio/netbird/client/embed"
 	sshdetection "github.com/netbirdio/netbird/client/ssh/detection"
+	nbstatus "github.com/netbirdio/netbird/client/status"
 	"github.com/netbirdio/netbird/client/wasm/internal/http"
 	"github.com/netbirdio/netbird/client/wasm/internal/rdp"
 	"github.com/netbirdio/netbird/client/wasm/internal/ssh"
 	"github.com/netbirdio/netbird/util"
+	"github.com/netbirdio/netbird/version"
 )
 
 const (
 	clientStartTimeout         = 30 * time.Second
 	clientStopTimeout          = 10 * time.Second
+	pingTimeout                = 10 * time.Second
 	defaultLogLevel            = "warn"
 	defaultSSHDetectionTimeout = 20 * time.Second
+
+	icmpEchoRequest = 8
+	icmpCodeEcho    = 0
+	pingBufferSize  = 1500
 )
 
 func main() {
@@ -113,18 +121,45 @@ func createStopMethod(client *netbird.Client) js.Func {
 	})
 }
 
+// validateSSHArgs validates SSH connection arguments
+func validateSSHArgs(args []js.Value) (host string, port int, username string, err js.Value) {
+	if len(args) < 2 {
+		return "", 0, "", js.ValueOf("error: requires host and port")
+	}
+
+	if args[0].Type() != js.TypeString {
+		return "", 0, "", js.ValueOf("host parameter must be a string")
+	}
+	if args[1].Type() != js.TypeNumber {
+		return "", 0, "", js.ValueOf("port parameter must be a number")
+	}
+
+	host = args[0].String()
+	port = args[1].Int()
+	username = "root"
+
+	if len(args) > 2 {
+		if args[2].Type() == js.TypeString && args[2].String() != "" {
+			username = args[2].String()
+		} else if args[2].Type() != js.TypeString {
+			return "", 0, "", js.ValueOf("username parameter must be a string")
+		}
+	}
+
+	return host, port, username, js.Undefined()
+}
+
 // createSSHMethod creates the SSH connection method
 func createSSHMethod(client *netbird.Client) js.Func {
 	return js.FuncOf(func(this js.Value, args []js.Value) any {
-		if len(args) < 2 {
-			return js.ValueOf("error: requires host and port")
-		}
-
-		host := args[0].String()
-		port := args[1].Int()
-		username := "root"
-		if len(args) > 2 && args[2].String() != "" {
-			username = args[2].String()
+		host, port, username, validationErr := validateSSHArgs(args)
+		if !validationErr.IsUndefined() {
+			if validationErr.Type() == js.TypeString && validationErr.String() == "error: requires host and port" {
+				return validationErr
+			}
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(validationErr)
+			})
 		}
 
 		var jwtToken string
@@ -154,6 +189,110 @@ func createSSHMethod(client *netbird.Client) js.Func {
 	})
 }
 
+func performPing(client *netbird.Client, hostname string) {
+	ctx, cancel := context.WithTimeout(context.Background(), pingTimeout)
+	defer cancel()
+
+	start := time.Now()
+	conn, err := client.Dial(ctx, "ping", hostname)
+	if err != nil {
+		js.Global().Get("console").Call("log", fmt.Sprintf("Ping to %s failed: %v", hostname, err))
+		return
+	}
+	defer func() {
+		if err := conn.Close(); err != nil {
+			log.Debugf("failed to close ping connection: %v", err)
+		}
+	}()
+
+	icmpData := make([]byte, 8)
+	icmpData[0] = icmpEchoRequest
+	icmpData[1] = icmpCodeEcho
+
+	if _, err := conn.Write(icmpData); err != nil {
+		js.Global().Get("console").Call("log", fmt.Sprintf("Ping to %s write failed: %v", hostname, err))
+		return
+	}
+
+	buf := make([]byte, pingBufferSize)
+	if _, err := conn.Read(buf); err != nil {
+		js.Global().Get("console").Call("log", fmt.Sprintf("Ping to %s read failed: %v", hostname, err))
+		return
+	}
+
+	latency := time.Since(start)
+	js.Global().Get("console").Call("log", fmt.Sprintf("Ping to %s: %dms", hostname, latency.Milliseconds()))
+}
+
+func performPingTCP(client *netbird.Client, hostname string, port int) {
+	ctx, cancel := context.WithTimeout(context.Background(), pingTimeout)
+	defer cancel()
+
+	address := fmt.Sprintf("%s:%d", hostname, port)
+	start := time.Now()
+	conn, err := client.Dial(ctx, "tcp", address)
+	if err != nil {
+		js.Global().Get("console").Call("log", fmt.Sprintf("TCP ping to %s failed: %v", address, err))
+		return
+	}
+	latency := time.Since(start)
+
+	if err := conn.Close(); err != nil {
+		log.Debugf("failed to close TCP connection: %v", err)
+	}
+
+	js.Global().Get("console").Call("log", fmt.Sprintf("TCP ping to %s succeeded: %dms", address, latency.Milliseconds()))
+}
+
+// createPingMethod creates the ping method
+func createPingMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(this js.Value, args []js.Value) any {
+		if len(args) < 1 {
+			return js.ValueOf("error: hostname required")
+		}
+
+		if args[0].Type() != js.TypeString {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("hostname parameter must be a string"))
+			})
+		}
+
+		hostname := args[0].String()
+		return createPromise(func(resolve, reject js.Value) {
+			performPing(client, hostname)
+			resolve.Invoke(js.Undefined())
+		})
+	})
+}
+
+// createPingTCPMethod creates the pingtcp method
+func createPingTCPMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(this js.Value, args []js.Value) any {
+		if len(args) < 2 {
+			return js.ValueOf("error: hostname and port required")
+		}
+
+		if args[0].Type() != js.TypeString {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("hostname parameter must be a string"))
+			})
+		}
+
+		if args[1].Type() != js.TypeNumber {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("port parameter must be a number"))
+			})
+		}
+
+		hostname := args[0].String()
+		port := args[1].Int()
+		return createPromise(func(resolve, reject js.Value) {
+			performPingTCP(client, hostname, port)
+			resolve.Invoke(js.Undefined())
+		})
+	})
+}
+
 // createProxyRequestMethod creates the proxyRequest method
 func createProxyRequestMethod(client *netbird.Client) js.Func {
 	return js.FuncOf(func(this js.Value, args []js.Value) any {
@@ -162,6 +301,11 @@ func createProxyRequestMethod(client *netbird.Client) js.Func {
 		}
 
 		request := args[0]
+		if request.Type() != js.TypeObject {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("request parameter must be an object"))
+			})
+		}
 
 		return createPromise(func(resolve, reject js.Value) {
 			response, err := http.ProxyRequest(client, request)
@@ -181,11 +325,141 @@ func createRDPProxyMethod(client *netbird.Client) js.Func {
 			return js.ValueOf("error: hostname and port required")
 		}
 
+		if args[0].Type() != js.TypeString {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("hostname parameter must be a string"))
+			})
+		}
+		if args[1].Type() != js.TypeString {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("port parameter must be a string"))
+			})
+		}
+
 		proxy := rdp.NewRDCleanPathProxy(client)
 		return proxy.CreateProxy(args[0].String(), args[1].String())
 	})
 }
 
+// getStatusOverview is a helper to get the status overview
+func getStatusOverview(client *netbird.Client) (nbstatus.OutputOverview, error) {
+	fullStatus, err := client.Status()
+	if err != nil {
+		return nbstatus.OutputOverview{}, err
+	}
+
+	pbFullStatus := fullStatus.ToProto()
+
+	return nbstatus.ConvertToStatusOutputOverview(pbFullStatus, false, version.NetbirdVersion(), "", nil, nil, nil, "", ""), nil
+}
+
+// createStatusMethod creates the status method that returns JSON
+func createStatusMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(_ js.Value, args []js.Value) any {
+		return createPromise(func(resolve, reject js.Value) {
+			overview, err := getStatusOverview(client)
+			if err != nil {
+				reject.Invoke(js.ValueOf(err.Error()))
+				return
+			}
+
+			jsonStr, err := overview.JSON()
+			if err != nil {
+				reject.Invoke(js.ValueOf(err.Error()))
+				return
+			}
+			jsonObj := js.Global().Get("JSON").Call("parse", jsonStr)
+			resolve.Invoke(jsonObj)
+		})
+	})
+}
+
+// createStatusSummaryMethod creates the statusSummary method
+func createStatusSummaryMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(_ js.Value, args []js.Value) any {
+		return createPromise(func(resolve, reject js.Value) {
+			overview, err := getStatusOverview(client)
+			if err != nil {
+				reject.Invoke(js.ValueOf(err.Error()))
+				return
+			}
+
+			summary := overview.GeneralSummary(false, false, false, false)
+			js.Global().Get("console").Call("log", summary)
+			resolve.Invoke(js.Undefined())
+		})
+	})
+}
+
+// createStatusDetailMethod creates the statusDetail method
+func createStatusDetailMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(_ js.Value, args []js.Value) any {
+		return createPromise(func(resolve, reject js.Value) {
+			overview, err := getStatusOverview(client)
+			if err != nil {
+				reject.Invoke(js.ValueOf(err.Error()))
+				return
+			}
+
+			detail := overview.FullDetailSummary()
+			js.Global().Get("console").Call("log", detail)
+			resolve.Invoke(js.Undefined())
+		})
+	})
+}
+
+// createGetSyncResponseMethod creates the getSyncResponse method that returns the latest sync response as JSON
+func createGetSyncResponseMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(_ js.Value, args []js.Value) any {
+		return createPromise(func(resolve, reject js.Value) {
+			syncResp, err := client.GetLatestSyncResponse()
+			if err != nil {
+				reject.Invoke(js.ValueOf(err.Error()))
+				return
+			}
+
+			options := protojson.MarshalOptions{
+				EmitUnpopulated: true,
+				UseProtoNames:   true,
+				AllowPartial:    true,
+			}
+			jsonBytes, err := options.Marshal(syncResp)
+			if err != nil {
+				reject.Invoke(js.ValueOf(fmt.Sprintf("marshal sync response: %v", err)))
+				return
+			}
+
+			jsonObj := js.Global().Get("JSON").Call("parse", string(jsonBytes))
+			resolve.Invoke(jsonObj)
+		})
+	})
+}
+
+// createSetLogLevelMethod creates the setLogLevel method to dynamically change logging level
+func createSetLogLevelMethod(client *netbird.Client) js.Func {
+	return js.FuncOf(func(_ js.Value, args []js.Value) any {
+		if len(args) < 1 {
+			return js.ValueOf("error: log level required")
+		}
+
+		if args[0].Type() != js.TypeString {
+			return createPromise(func(resolve, reject js.Value) {
+				reject.Invoke(js.ValueOf("log level parameter must be a string"))
+			})
+		}
+
+		logLevel := args[0].String()
+		return createPromise(func(resolve, reject js.Value) {
+			if err := client.SetLogLevel(logLevel); err != nil {
+				reject.Invoke(js.ValueOf(fmt.Sprintf("set log level: %v", err)))
+				return
+			}
+			log.Infof("Log level set to: %s", logLevel)
+			resolve.Invoke(js.ValueOf(true))
+		})
+	})
+}
+
 // createPromise is a helper to create JavaScript promises
 func createPromise(handler func(resolve, reject js.Value)) js.Value {
 	return js.Global().Get("Promise").New(js.FuncOf(func(_ js.Value, promiseArgs []js.Value) any {
@@ -237,17 +511,24 @@ func createClientObject(client *netbird.Client) js.Value {
 
 	obj["start"] = createStartMethod(client)
 	obj["stop"] = createStopMethod(client)
+	obj["ping"] = createPingMethod(client)
+	obj["pingtcp"] = createPingTCPMethod(client)
 	obj["detectSSHServerType"] = createDetectSSHServerMethod(client)
 	obj["createSSHConnection"] = createSSHMethod(client)
 	obj["proxyRequest"] = createProxyRequestMethod(client)
 	obj["createRDPProxy"] = createRDPProxyMethod(client)
+	obj["status"] = createStatusMethod(client)
+	obj["statusSummary"] = createStatusSummaryMethod(client)
+	obj["statusDetail"] = createStatusDetailMethod(client)
+	obj["getSyncResponse"] = createGetSyncResponseMethod(client)
+	obj["setLogLevel"] = createSetLogLevelMethod(client)
 
 	return js.ValueOf(obj)
 }
 
 // netBirdClientConstructor acts as a JavaScript constructor function
-func netBirdClientConstructor(this js.Value, args []js.Value) any {
-	return js.Global().Get("Promise").New(js.FuncOf(func(this js.Value, promiseArgs []js.Value) any {
+func netBirdClientConstructor(_ js.Value, args []js.Value) any {
+	return js.Global().Get("Promise").New(js.FuncOf(func(_ js.Value, promiseArgs []js.Value) any {
 		resolve := promiseArgs[0]
 		reject := promiseArgs[1]