WIP

.github/workflows/agent-network-e2e.yml

@@ -5,13 +5,6 @@ on:
   schedule:
     - cron: "0 3 * * *"
   workflow_dispatch:
-    inputs:
-      bedrock_model:
-        description: >-
-          Bedrock inference-profile id to drive the matrix with, exactly as
-          AWS issues it. Leave empty for the Sonnet 4.6 default.
-        required: false
-        default: ""
 
 concurrency:
   group: ${{ github.workflow }}-${{ github.ref }}
@@ -58,9 +51,6 @@ jobs:
           # token (and URL, for gateways) is unset, so partial coverage is fine.
           OPENAI_TOKEN: ${{ secrets.E2E_OPENAI_TOKEN }}
           ANTHROPIC_TOKEN: ${{ secrets.E2E_ANTHROPIC_TOKEN }}
-          # Moonshot AI platform key (platform.kimi.ai); drives both Kimi wire
-          # shapes (OpenAI /v1 and Anthropic /anthropic) through kimi_api.
-          KIMI_TOKEN: ${{ secrets.E2E_KIMI_TOKEN }}
           VERCEL_URL: ${{ secrets.E2E_VERCEL_URL }}
           VERCEL_TOKEN: ${{ secrets.E2E_VERCEL_TOKEN }}
           OPENROUTER_URL: ${{ secrets.E2E_OPENROUTER_URL }}
@@ -69,8 +59,6 @@ jobs:
           CLOUDFLARE_TOKEN: ${{ secrets.E2E_CLOUDFLARE_TOKEN }}
           AWS_BEARER_TOKEN_BEDROCK: ${{ secrets.E2E_AWS_BEARER_TOKEN_BEDROCK }}
           AWS_REGION: ${{ secrets.E2E_AWS_REGION }}
-          # Bedrock model override: dispatch input wins, then the repo variable, else the test default.
-          AWS_BEDROCK_MODEL: ${{ inputs.bedrock_model || vars.E2E_AWS_BEDROCK_MODEL }}
           # Vertex (Anthropic-on-Vertex): SA + project required; region defaults
           # to "global", model to a pinned claude snapshot.
           GOOGLE_VERTEX_SA_BASE64: ${{ secrets.E2E_GOOGLE_VERTEX_SA_BASE64 }}

.github/workflows/frontend-ui.yml

@@ -86,7 +86,7 @@ jobs:
             ${{ runner.os }}-pnpm-
 
       - name: Install dependencies
-        run: pnpm install --frozen-lockfile --ignore-scripts
+        run: pnpm install --frozen-lockfile
 
       - name: Generate Wails bindings
         run: pnpm run bindings

.github/workflows/golangci-lint.yml

@@ -45,7 +45,7 @@ jobs:
             display_name: Linux
     name: ${{ matrix.display_name }}
     runs-on: ${{ matrix.os }}
-    timeout-minutes: 25
+    timeout-minutes: 15
     steps:
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
@@ -79,4 +79,4 @@ jobs:
           skip-cache: true
           skip-save-cache: true
           cache-invalidation-interval: 0
-          args: --timeout=20m
+          args: --timeout=12m

.github/workflows/test-infrastructure-files.yml

@@ -249,35 +249,78 @@ jobs:
           docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
           docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
 
-  test-legacy-getting-started-scripts:
+  test-getting-started-script:
     runs-on: ubuntu-latest
     steps:
+      - name: Install jq
+        run: sudo apt-get install -y jq
+
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
         with:
           persist-credentials: false
 
-      - name: Verify Dex retirement notice
-        run: |
-          if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Dex installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Dex support is not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/local" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+      - name: run script with Zitadel PostgreSQL
+        run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
 
-      - name: Verify Zitadel retirement notice
+      - name: test Caddy file gen postgres
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen postgres
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen postgres
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen postgres
         run: |
-          if bash infrastructure_files/getting-started-with-zitadel.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Zitadel installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Zitadel support and existing Zitadel deployments are not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/zitadel" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-guide" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen postgres
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen postgres
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen postgres
+        run: test -f relay.env
+
+      - name: test zdb.env file gen postgres
+        run: test -f zdb.env
+
+      - name: Postgres run cleanup
+        run: |
+          docker compose down --volumes --rmi all
+          rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
+
+      - name: run script with Zitadel CockroachDB
+        run: bash -x infrastructure_files/getting-started-with-zitadel.sh
+        env:
+          NETBIRD_DOMAIN: use-ip
+          ZITADEL_DATABASE: cockroach
+
+      - name: test Caddy file gen CockroachDB
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen CockroachDB
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen CockroachDB
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen CockroachDB
+        run: |
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen CockroachDB
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen CockroachDB
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen CockroachDB
+        run: test -f relay.env

.goreleaser.yaml

@@ -273,8 +273,8 @@ dockers_v2:
        - netbirdio/netbird
        - ghcr.io/netbirdio/netbird
      tags:
-       - "{{ .Version }}-rootless"
-       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}rootless-latest{{ end }}"
+       - "v{{ .Version }}-rootless"
+       - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: client/Dockerfile-rootless
      extra_files:
        - client/netbird-entrypoint.sh

.goreleaser_ui.yaml

@@ -24,8 +24,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-amd64
     dir: client/ui
@@ -41,8 +39,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-arm64
     dir: client/ui
@@ -59,8 +55,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 archives:
   - id: linux-arch

.goreleaser_ui_darwin.yaml

@@ -29,8 +29,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 universal_binaries:
   - id: netbird-ui-darwin

client/android/client.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"os"
 	"slices"
-	"strings"
 	"sync"
 	"time"
 
@@ -248,9 +247,6 @@ func (c *Client) DebugBundle(platformFiles PlatformFiles, anonymize bool) (strin
 		deps.SyncResponse = resp
 
 		if e := cc.Engine(); e != nil {
-			deps.RefreshStatus = func() {
-				e.RunHealthProbes(context.Background(), true)
-			}
 			if cm := e.GetClientMetrics(); cm != nil {
 				deps.ClientMetrics = cm
 			}
@@ -300,13 +296,6 @@ func (c *Client) SetInfoLogLevel() {
 // PeersList return with the list of the PeerInfos
 func (c *Client) PeersList() *PeerInfoArray {
 
-	// The recorder only caches transfer counters and handshake times; nothing
-	// refreshes them on its own, so without this they read as zero. The desktop
-	// daemon does the same before serving a full peer status.
-	if err := c.recorder.RefreshWireGuardStats(); err != nil {
-		log.Debugf("failed to refresh WireGuard stats: %v", err)
-	}
-
 	fullStatus := c.recorder.GetFullStatus()
 
 	peerInfos := make([]PeerInfo, len(fullStatus.Peers))
@@ -317,20 +306,6 @@ func (c *Client) PeersList() *PeerInfoArray {
 			FQDN:       p.FQDN,
 			ConnStatus: int(p.ConnStatus),
 			Routes:     PeerRoutes{routes: maps.Keys(p.GetRoutes())},
-
-			PubKey:                     p.PubKey,
-			Latency:                    formatDuration(p.Latency),
-			LatencyMs:                  p.Latency.Milliseconds(),
-			BytesRx:                    p.BytesRx,
-			BytesTx:                    p.BytesTx,
-			ConnStatusUpdate:           formatTime(p.ConnStatusUpdate),
-			Relayed:                    p.Relayed,
-			RosenpassEnabled:           p.RosenpassEnabled,
-			LastWireguardHandshake:     formatTime(p.LastWireguardHandshake),
-			LocalIceCandidateType:      p.LocalIceCandidateType,
-			RemoteIceCandidateType:     p.RemoteIceCandidateType,
-			LocalIceCandidateEndpoint:  p.LocalIceCandidateEndpoint,
-			RemoteIceCandidateEndpoint: p.RemoteIceCandidateEndpoint,
 		}
 		peerInfos[n] = pi
 	}
@@ -461,6 +436,10 @@ func (c *Client) RemoveConnectionListener() {
 	c.recorder.RemoveConnectionListener()
 }
 
+func (c *Client) toggleRoute(command routeCommand) error {
+	return command.toggleRoute()
+}
+
 func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	client := c.getConnectClient()
 	if client == nil {
@@ -480,22 +459,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	return manager, nil
 }
 
-func (c *Client) SelectRoute(id string) error {
+func (c *Client) SelectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true)
+	return c.toggleRoute(selectRouteCommand{route: route, manager: manager})
 }
 
-func (c *Client) DeselectRoute(id string) error {
+func (c *Client) DeselectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.DeselectRoutes([]route.NetID{route.NetID(id)})
+	return c.toggleRoute(deselectRouteCommand{route: route, manager: manager})
 }
 
 // getNetworkDomainsFromRoute extracts domains from a route and enriches each domain
@@ -530,28 +509,3 @@ func exportEnvList(list *EnvList) {
 		}
 	}
 }
-
-// formatDuration renders a duration for display, trimming the fractional part
-// to two digits so latencies read as "12.34ms" rather than "12.345678ms".
-func formatDuration(d time.Duration) string {
-	ds := d.String()
-	dotIndex := strings.Index(ds, ".")
-	if dotIndex == -1 {
-		return ds
-	}
-
-	endIndex := min(dotIndex+3, len(ds))
-
-	// Skip the remaining digits so only the unit suffix is appended back.
-	unitStart := endIndex
-	for unitStart < len(ds) && ds[unitStart] >= '0' && ds[unitStart] <= '9' {
-		unitStart++
-	}
-	return ds[:endIndex] + ds[unitStart:]
-}
-
-// formatTime renders a timestamp in UTC using a fixed layout. The zero time is
-// passed through as-is so the UI can recognise it and show "never" instead.
-func formatTime(t time.Time) string {
-	return t.UTC().Format("2006-01-02 15:04:05")
-}

client/android/peer_notifier.go

@@ -12,30 +12,12 @@ const (
 )
 
 // PeerInfo describe information about the peers. It designed for the UI usage
-//
-// The fields below ConnStatus back the peer detail screen. Durations and times
-// are pre-formatted into strings so the UI does not have to know Go's layouts;
-// Latency is additionally exposed as LatencyMs for colour coding.
 type PeerInfo struct {
 	IP         string
 	IPv6       string
 	FQDN       string
 	ConnStatus int
 	Routes     PeerRoutes
-
-	PubKey                     string
-	Latency                    string
-	LatencyMs                  int64
-	BytesRx                    int64
-	BytesTx                    int64
-	ConnStatusUpdate           string
-	Relayed                    bool
-	RosenpassEnabled           bool
-	LastWireguardHandshake     string
-	LocalIceCandidateType      string
-	RemoteIceCandidateType     string
-	LocalIceCandidateEndpoint  string
-	RemoteIceCandidateEndpoint string
 }
 
 func (p *PeerInfo) GetPeerRoutes() *PeerRoutes {

client/android/profile_manager.go

@@ -189,19 +189,6 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 	return nil
 }
 
-// RenameProfile changes a profile's display name. The profile ID, and therefore
-// its on-disk filename, is left untouched: only the "name" field of the config
-// is rewritten. This works for the default profile too, whose config lives in
-// netbird.cfg rather than under profiles/.
-func (pm *ProfileManager) RenameProfile(id string, newName string) error {
-	if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
-		return fmt.Errorf("failed to rename profile: %w", err)
-	}
-
-	log.Infof("renamed profile %s to: %s", id, newName)
-	return nil
-}
-
 // RemoveProfile deletes a profile
 func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)

client/android/route_command.go

@@ -0,0 +1,70 @@
+//go:build android
+
+package android
+
+import (
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
+
+	"github.com/netbirdio/netbird/client/internal/routemanager"
+	"github.com/netbirdio/netbird/route"
+)
+
+func executeRouteToggle(id string, manager routemanager.Manager,
+	operationName string,
+	routeOperation func(routes []route.NetID, allRoutes []route.NetID) error) error {
+	netID := route.NetID(id)
+	routes := []route.NetID{netID}
+
+	routesMap := manager.GetClientRoutesWithNetID()
+	routes = route.ExpandV6ExitPairs(routes, routesMap)
+
+	log.Debugf("%s with ids: %v", operationName, routes)
+
+	if err := routeOperation(routes, maps.Keys(routesMap)); err != nil {
+		log.Debugf("error when %s: %s", operationName, err)
+		return fmt.Errorf("error %s: %w", operationName, err)
+	}
+
+	manager.TriggerSelection(manager.GetClientRoutes())
+
+	return nil
+}
+
+type routeCommand interface {
+	toggleRoute() error
+}
+
+type selectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (s selectRouteCommand) toggleRoute() error {
+	routeSelector := s.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	routeOperation := func(routes []route.NetID, allRoutes []route.NetID) error {
+		return routeSelector.SelectRoutes(routes, true, allRoutes)
+	}
+
+	return executeRouteToggle(s.route, s.manager, "selecting route", routeOperation)
+}
+
+type deselectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (d deselectRouteCommand) toggleRoute() error {
+	routeSelector := d.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	return executeRouteToggle(d.route, d.manager, "deselecting route", routeSelector.DeselectRoutes)
+}

client/cmd/root.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
+	"net"
 	"os"
 	"os/signal"
 	"path"
@@ -79,6 +80,8 @@ var (
 	updateSettingsDisabled bool
 	captureEnabled         bool
 	networksDisabled       bool
+	socketOwner            string
+	strictSocketDisabled   bool
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -143,10 +146,12 @@ func init() {
 
 	defaultDaemonAddr := "unix:///var/run/netbird.sock"
 	if runtime.GOOS == "windows" {
-		defaultDaemonAddr = "tcp://127.0.0.1:41731"
+		// Named pipe (not loopback TCP): the pipe SDDL gates who may connect and
+		// the pipe client token carries the caller's SID for per-RPC authorization.
+		defaultDaemonAddr = "npipe://netbird"
 	}
 
-	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
+	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
 	rootCmd.PersistentFlags().StringVarP(&managementURL, "management-url", "m", "", fmt.Sprintf("Management Service URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultManagementURL))
 	rootCmd.PersistentFlags().StringVar(&adminURL, "admin-url", "", fmt.Sprintf("Admin Panel URL [http|https]://[host]:[port] (default \"%s\")", profilemanager.DefaultAdminURL))
 	rootCmd.PersistentFlags().StringVarP(&logLevel, "log-level", "l", "info", "sets NetBird log level")
@@ -265,16 +270,31 @@ func FlagNameToEnvVar(cmdFlag string, prefix string) string {
 }
 
 // DialClientGRPCServer returns client connection to the daemon server.
+//
+// The daemon reads the caller's kernel identity from the transport (SO_PEERCRED
+// on a Unix socket, the client token on a Windows named pipe), so the client
+// side uses insecure (plaintext) credentials — it needs no cooperation to be
+// identified. For npipe addresses we install a context dialer since gRPC's
+// resolver does not understand Windows named pipes.
 func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, error) {
 	ctx, cancel := context.WithTimeout(ctx, time.Second*10)
 	defer cancel()
 
-	return grpc.DialContext(
-		ctx,
-		strings.TrimPrefix(addr, "tcp://"),
+	opts := []grpc.DialOption{
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
 		grpc.WithBlock(),
-	)
+	}
+
+	target := strings.TrimPrefix(addr, "tcp://")
+	if strings.HasPrefix(addr, "npipe://") {
+		path := pipePath(strings.TrimPrefix(addr, "npipe://"))
+		opts = append(opts, grpc.WithContextDialer(func(dialCtx context.Context, _ string) (net.Conn, error) {
+			return dialNamedPipe(dialCtx, path)
+		}))
+		target = "passthrough:///netbird-daemon-pipe"
+	}
+
+	return grpc.DialContext(ctx, target, opts...)
 }
 
 // WithBackOff execute function in backoff cycle.

client/cmd/service.go

@@ -56,6 +56,9 @@ func init() {
 	serviceCmd.PersistentFlags().BoolVar(&enableJSONSocket, "enable-json-socket", false, "Enables the HTTP/JSON API socket served by grpc-gateway. To persist, use: netbird service install --enable-json-socket")
 	serviceCmd.PersistentFlags().StringVar(&jsonSocket, "json-socket", defaultJSONSocket, "HTTP/JSON API socket address [unix|tcp]://[path|host:port]. Requires --enable-json-socket to serve. To persist, use: netbird service install --enable-json-socket --json-socket")
 
+	serviceCmd.PersistentFlags().StringVar(&socketOwner, "socket-owner", "", "user to own the daemon control socket; restricts it to that user plus the netbird group (0660). If unset, the first client to connect claims ownership (trust-on-first-use). Persisted via: netbird service install --socket-owner")
+	serviceCmd.PersistentFlags().BoolVar(&strictSocketDisabled, "disable-strict-socket", false, "leave the daemon control socket world-writable (0666) instead of restricting it (root-only, discouraged). Persisted via: netbird service install --disable-strict-socket")
+
 	rootCmd.PersistentFlags().StringVarP(&serviceName, "service", "s", defaultServiceName, "Netbird system service name")
 	serviceEnvDesc := `Sets extra environment variables for the service. ` +
 		`You can specify a comma-separated list of KEY=VALUE pairs. ` +

client/cmd/service_controller.go

@@ -5,6 +5,7 @@ package cmd
 import (
 	"context"
 	"fmt"
+	"runtime"
 	"time"
 
 	"github.com/kardianos/service"
@@ -13,12 +14,31 @@ import (
 	"github.com/spf13/cobra"
 	"google.golang.org/grpc"
 
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/server"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/util"
 )
 
+// daemonServerOptions returns the gRPC server options that install peer-identity
+// transport credentials on the daemon control channel. Identity extraction is
+// only possible over a Unix socket (SO_PEERCRED) or Windows named pipe (client
+// token); over TCP, or on platforms without a peer-credential primitive, the
+// daemon runs without per-caller authorization and logs a warning.
+func daemonServerOptions(network string) []grpc.ServerOption {
+	creds := ipcauth.NewTransportCredentials()
+	if creds == nil {
+		log.Warnf("daemon control channel has no peer-identity primitive on %s; per-caller authorization is disabled", runtime.GOOS)
+		return nil
+	}
+	if network == "tcp" {
+		log.Warnf("daemon is listening on TCP (%s); peer identity cannot be authenticated over TCP, per-caller authorization is disabled", daemonAddr)
+		return nil
+	}
+	return []grpc.ServerOption{grpc.Creds(creds)}
+}
+
 func validateJSONSocketFlags() error {
 	if serviceCmd.PersistentFlags().Changed("json-socket") && !enableJSONSocket {
 		return fmt.Errorf("--json-socket requires --enable-json-socket to configure the daemon JSON gateway")
@@ -37,8 +57,13 @@ func (p *program) Start(svc service.Service) error {
 	// Collect static system and platform information
 	system.UpdateStaticInfoAsync()
 
-	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
-	p.serv = grpc.NewServer()
+	network, _, err := parseListenAddress(daemonAddr)
+	if err != nil {
+		return fmt.Errorf("parse daemon address: %w", err)
+	}
+
+	// in any case, even if configuration does not exist we run daemon to serve the CLI gRPC API.
+	p.serv = grpc.NewServer(daemonServerOptions(network)...)
 
 	daemonListener, err := listenOnAddress(daemonAddr)
 	if err != nil {
@@ -62,7 +87,8 @@ func (p *program) Start(svc service.Service) error {
 			defer jsonListener.Close()
 		}
 
-		if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
+		serveListener, err := secureDaemonListener(daemonListener)
+		if err != nil {
 			log.Error(err)
 			return
 		}
@@ -84,6 +110,7 @@ func (p *program) Start(svc service.Service) error {
 		p.serverInstanceMu.Unlock()
 
 		if jsonListener != nil {
+			log.Warnf("JSON gateway (--enable-json-socket) re-dials the daemon locally as the daemon's own identity and BYPASSES per-caller authorization; restrict access to %s separately", jsonSocket)
 			if err := p.startJSONGateway(jsonListener, daemonAddr); err != nil {
 				log.Fatalf("failed to start daemon JSON server: %v", err)
 			}
@@ -92,7 +119,7 @@ func (p *program) Start(svc service.Service) error {
 		}
 
 		log.Printf("started daemon server: %v", daemonListener.address)
-		if err := p.serv.Serve(daemonListener.Listener); err != nil {
+		if err := p.serv.Serve(serveListener); err != nil {
 			log.Errorf("failed to serve daemon requests: %v", err)
 		}
 	}()

client/cmd/service_installer.go

@@ -71,6 +71,14 @@ func buildServiceArguments() []string {
 		args = append(args, "--enable-json-socket", "--json-socket", jsonSocket)
 	}
 
+	if socketOwner != "" {
+		args = append(args, "--socket-owner", socketOwner)
+	}
+
+	if strictSocketDisabled {
+		args = append(args, "--disable-strict-socket")
+	}
+
 	return args
 }
 

client/cmd/service_params.go

@@ -32,6 +32,8 @@ type serviceParams struct {
 	EnableCapture         bool              `json:"enable_capture,omitempty"`
 	DisableNetworks       bool              `json:"disable_networks,omitempty"`
 	EnableJSONSocket      bool              `json:"enable_json_socket,omitempty"`
+	SocketOwner           string            `json:"socket_owner,omitempty"`
+	DisableStrictSocket   bool              `json:"disable_strict_socket,omitempty"`
 	ServiceEnvVars        map[string]string `json:"service_env_vars,omitempty"`
 }
 
@@ -86,6 +88,8 @@ func currentServiceParams() *serviceParams {
 		EnableCapture:         captureEnabled,
 		DisableNetworks:       networksDisabled,
 		EnableJSONSocket:      enableJSONSocket,
+		SocketOwner:           socketOwner,
+		DisableStrictSocket:   strictSocketDisabled,
 	}
 
 	if len(serviceEnvVars) > 0 {
@@ -165,6 +169,14 @@ func applyServiceParams(cmd *cobra.Command, params *serviceParams) {
 		networksDisabled = params.DisableNetworks
 	}
 
+	if !serviceCmd.PersistentFlags().Changed("socket-owner") {
+		socketOwner = params.SocketOwner
+	}
+
+	if !serviceCmd.PersistentFlags().Changed("disable-strict-socket") {
+		strictSocketDisabled = params.DisableStrictSocket
+	}
+
 	applyServiceEnvParams(cmd, params)
 }
 

client/cmd/service_pipe_other.go

@@ -0,0 +1,20 @@
+//go:build !windows
+
+package cmd
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"runtime"
+)
+
+// listenNamedPipe is unsupported off Windows; named pipes are a Windows-only transport.
+func listenNamedPipe(string) (net.Listener, error) {
+	return nil, fmt.Errorf("named pipe daemon socket is only supported on Windows, not %s", runtime.GOOS)
+}
+
+// dialNamedPipe is unsupported off Windows.
+func dialNamedPipe(context.Context, string) (net.Conn, error) {
+	return nil, fmt.Errorf("named pipe daemon socket is only supported on Windows, not %s", runtime.GOOS)
+}

client/cmd/service_pipe_windows.go

@@ -0,0 +1,32 @@
+//go:build windows
+
+package cmd
+
+import (
+	"context"
+	"net"
+	"time"
+
+	"github.com/Microsoft/go-winio"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+)
+
+// listenNamedPipe creates the daemon control named pipe with a tight SDDL
+// (SYSTEM + Administrators + interactive users). ListenPipe fails if the pipe
+// already exists (first-instance semantics), which prevents a squatting process
+// from pre-creating it — we surface that error loudly rather than falling back.
+func listenNamedPipe(path string) (net.Listener, error) {
+	return winio.ListenPipe(path, &winio.PipeConfig{
+		SecurityDescriptor: ipcauth.DefaultPipeSDDL(),
+	})
+}
+
+// dialNamedPipe connects to the daemon control named pipe.
+func dialNamedPipe(ctx context.Context, path string) (net.Conn, error) {
+	if deadline, ok := ctx.Deadline(); ok {
+		timeout := time.Until(deadline)
+		return winio.DialPipe(path, &timeout)
+	}
+	return winio.DialPipeContext(ctx, path)
+}

client/cmd/service_socket.go

@@ -26,6 +26,15 @@ func listenOnAddress(addr string) (*socketListener, error) {
 		return nil, err
 	}
 
+	if network == "npipe" {
+		path := pipePath(address)
+		listener, err := listenNamedPipe(path)
+		if err != nil {
+			return nil, err
+		}
+		return &socketListener{Listener: listener, network: network, address: path}, nil
+	}
+
 	if network == "unix" {
 		removeStaleUnixSocket(address)
 	}
@@ -45,13 +54,23 @@ func parseListenAddress(addr string) (string, string, error) {
 	}
 
 	switch network {
-	case "unix", "tcp":
+	case "unix", "tcp", "npipe":
 		return network, address, nil
 	default:
 		return "", "", fmt.Errorf("unsupported daemon address protocol: %v", network)
 	}
 }
 
+// pipePath maps a daemon-addr npipe name (e.g. "netbird" from "npipe://netbird")
+// to a Windows named-pipe path (\\.\pipe\netbird). A caller may also pass a full
+// \\.\pipe\ path, which is returned unchanged.
+func pipePath(name string) string {
+	if strings.HasPrefix(name, `\\`) {
+		return name
+	}
+	return `\\.\pipe\` + name
+}
+
 func removeStaleUnixSocket(path string) {
 	stat, err := os.Lstat(path)
 	if err != nil {

client/cmd/service_socket_perms_other.go

@@ -0,0 +1,11 @@
+//go:build windows
+
+package cmd
+
+import "net"
+
+// secureDaemonListener is a no-op on Windows: the named-pipe SDDL gates who may
+// connect (Layer 1), and the pipe client token supplies per-RPC identity.
+func secureDaemonListener(l *socketListener) (net.Listener, error) {
+	return l.Listener, nil
+}

client/cmd/service_socket_perms_unix.go

@@ -0,0 +1,225 @@
+//go:build !windows && !ios && !android
+
+package cmd
+
+import (
+	"errors"
+	"fmt"
+	"net"
+	"os"
+	"os/exec"
+	"os/user"
+	"strconv"
+	"sync"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/ipcauth"
+	"github.com/netbirdio/netbird/client/internal/shell"
+)
+
+// secureDaemonListener applies the Layer-1 access control to the daemon control
+// socket and returns the listener to serve on. For a Unix socket this restricts
+// the socket to an owner (plus the netbird group); for anything else it is a
+// no-op (TCP is legacy/unauthenticated; named pipes are gated by their SDDL).
+func secureDaemonListener(l *socketListener) (net.Listener, error) {
+	if l.network != "unix" {
+		return l.Listener, nil
+	}
+
+	owner := effectiveSocketOwner()
+	switch {
+	case strictSocketDisabled:
+		// Root-only opt-out (via service.json): leave it world-writable.
+		if err := os.Chmod(l.address, 0666); err != nil {
+			return nil, fmt.Errorf("set daemon socket permissions: %w", err)
+		}
+		log.Warnf("daemon control socket left world-writable (0666) by --disable-strict-socket")
+		return l.Listener, nil
+
+	case owner != "":
+		// Seeded owner (flag, MDM, or persisted TOFU result): restrict before
+		// serving so there is no open window.
+		uid, err := lookupUser(owner)
+		if err != nil {
+			return nil, fmt.Errorf("lookup socket owner %q: %w", owner, err)
+		}
+		if err := restrictSocket(l.address, uid); err != nil {
+			return nil, fmt.Errorf("restrict socket to %q: %w", owner, err)
+		}
+		return l.Listener, nil
+
+	default:
+		// Trust-on-first-use: open the socket now; tofuListener locks it to the
+		// first caller's uid on the first connection.
+		if err := os.Chmod(l.address, 0666); err != nil {
+			return nil, fmt.Errorf("set daemon socket permissions: %w", err)
+		}
+		return &tofuListener{Listener: l.Listener, path: l.address, owner: -1}, nil
+	}
+}
+
+func lookupUser(username string) (int, error) {
+	u, err := shell.LookupWithGetent(username)
+	if err != nil {
+		return -1, fmt.Errorf("lookup user %s: %w", username, err)
+	}
+	uid, err := strconv.Atoi(u.Uid)
+	if err != nil {
+		return -1, fmt.Errorf("parse uid %s: %w", u.Uid, err)
+	}
+	return uid, nil
+}
+
+// addGroup creates a system group if it doesn't already exist and returns the gid.
+// Must run as root.
+func addGroup(name string) (int, error) {
+	group, err := shell.LookupGroupWithGetent(name)
+	if err == nil {
+		gid, err := strconv.ParseInt(group.Gid, 10, 64)
+		return int(gid), err
+	}
+
+	groupadd, err := exec.LookPath("groupadd")
+	if err != nil {
+		// Fallback for Alpine/BusyBox systems.
+		if groupadd, err = exec.LookPath("addgroup"); err != nil {
+			return -1, errors.New("neither groupadd nor addgroup found")
+		}
+	}
+
+	// Use --system for a service/daemon group (no login, low GID).
+	out, err := exec.Command(groupadd, "--system", name).CombinedOutput()
+	if err != nil {
+		return -1, fmt.Errorf("create group %q: %w: %s", name, err, out)
+	}
+	if group, err := shell.LookupGroupWithGetent(name); err == nil {
+		gid, err := strconv.ParseInt(group.Gid, 10, 64)
+		return int(gid), err
+	}
+	return -1, fmt.Errorf("lookup group %q: %w", name, err)
+}
+
+// restrictSocket locks the unix socket down to the owner uid plus the netbird
+// group (0660). If the group cannot be created or applied, it fails closed to
+// owner-only 0600 — it never leaves the socket world-writable.
+func restrictSocket(path string, uid int) error {
+	gid, err := addGroup("netbird")
+	if err != nil {
+		log.Errorf("create netbird group, failing closed to owner-only 0600: %v", err)
+		return chownChmod(path, uid, -1, 0600)
+	}
+	if err := chownChmod(path, uid, gid, 0660); err != nil {
+		log.Errorf("apply netbird group to socket, failing closed to owner-only 0600: %v", err)
+		return chownChmod(path, uid, -1, 0600)
+	}
+	return nil
+}
+
+// chownChmod sets ownership and mode on the socket. A gid of -1 leaves the
+// group unchanged.
+func chownChmod(path string, uid, gid int, mode os.FileMode) error {
+	if err := os.Chown(path, uid, gid); err != nil {
+		return fmt.Errorf("chown socket %s: %w", path, err)
+	}
+	if err := os.Chmod(path, mode); err != nil {
+		return fmt.Errorf("chmod socket %s: %w", path, err)
+	}
+	return nil
+}
+
+// tofuListener implements trust-on-first-use for the daemon control socket.
+// The socket starts world-writable; the first caller's uid (read via SO_PEERCRED)
+// becomes the owner. On that first connection the socket is restricted and the
+// owner persisted so the open window never reopens on later starts. Connections
+// that raced in during the open window and are neither the owner nor root are
+// dropped. Changing the socket mode does not disturb the already-open
+// connection, so the first caller's request is served normally.
+type tofuListener struct {
+	net.Listener
+	path  string
+	mu    sync.Mutex
+	owner int // -1 until claimed
+}
+
+func (l *tofuListener) Accept() (net.Conn, error) {
+	for {
+		c, err := l.Listener.Accept()
+		if err != nil {
+			return nil, err
+		}
+
+		id, err := ipcauth.PeerIdentity(c)
+		if err != nil {
+			log.Errorf("read peer credentials, dropping connection: %v", err)
+			_ = c.Close()
+			continue
+		}
+		uid := int(id.UID)
+
+		l.mu.Lock()
+		if l.owner == -1 {
+			if err := restrictSocket(l.path, uid); err != nil {
+				l.mu.Unlock()
+				_ = c.Close()
+				// Refuse to serve on a socket we could not lock down.
+				return nil, fmt.Errorf("restrict socket on first connection: %w", err)
+			}
+			l.owner = uid
+			persistSocketOwner(uid)
+			log.Infof("control socket restricted to first caller (uid %d)", uid)
+			l.mu.Unlock()
+			return c, nil
+		}
+		owner := l.owner
+		l.mu.Unlock()
+
+		// New connects are already gated by the 0660 perms set above; this only
+		// drops anything that slipped in during the brief open window.
+		if uid != owner && uid != 0 {
+			log.Warnf("dropping non-owner connection (uid %d) during socket bootstrap", uid)
+			_ = c.Close()
+			continue
+		}
+		return c, nil
+	}
+}
+
+// effectiveSocketOwner returns the configured socket owner: the --socket-owner
+// flag when set, otherwise the owner persisted by a previous TOFU migration.
+func effectiveSocketOwner() string {
+	if socketOwner != "" {
+		return socketOwner
+	}
+	params, err := loadServiceParams()
+	if err != nil {
+		log.Errorf("load service params for socket owner: %v", err)
+		return ""
+	}
+	if params != nil {
+		return params.SocketOwner
+	}
+	return ""
+}
+
+// persistSocketOwner records the TOFU-selected owner (by username) so the next
+// daemon start restricts the socket immediately, with no open window.
+func persistSocketOwner(uid int) {
+	u, err := user.LookupId(strconv.Itoa(uid))
+	if err != nil {
+		log.Errorf("resolve uid %d to username for persistence: %v", uid, err)
+		return
+	}
+	params, err := loadServiceParams()
+	if err != nil {
+		log.Errorf("load service params to persist socket owner: %v", err)
+		return
+	}
+	if params == nil {
+		params = currentServiceParams()
+	}
+	params.SocketOwner = u.Username
+	if err := saveServiceParams(params); err != nil {
+		log.Errorf("persist socket owner: %v", err)
+	}
+}

client/iface/iface_test.go

@@ -464,8 +464,6 @@ func Test_RemovePeer(t *testing.T) {
 }
 
 func Test_ConnectPeers(t *testing.T) {
-	t.Setenv("NB_DISABLE_EBPF_WG_PROXY", "true")
-
 	peer1ifaceName := fmt.Sprintf("utun%d", WgIntNumber+400)
 	peer1wgIP := netip.MustParsePrefix("10.99.99.17/30")
 	peer1Key, _ := wgtypes.GeneratePrivateKey()
@@ -507,8 +505,12 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	localIP1 := "127.0.0.1"
-	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP1, peer1wgPort))
+	localIP, err := getLocalIP()
+	if err != nil {
+		t.Fatal(err)
+	}
+
+	peer1endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer1wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -544,8 +546,7 @@ func Test_ConnectPeers(t *testing.T) {
 		t.Fatal(err)
 	}
 
-	localIP2 := "127.0.0.1"
-	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP2, peer2wgPort))
+	peer2endpoint, err := net.ResolveUDPAddr("udp", fmt.Sprintf("%s:%d", localIP, peer2wgPort))
 	if err != nil {
 		t.Fatal(err)
 	}
@@ -568,17 +569,17 @@ func Test_ConnectPeers(t *testing.T) {
 	if err != nil {
 		t.Fatal(err)
 	}
-	// The peers use userspace WireGuard (stdnet transport). A tight busy-loop
-	// here starves the wireguard-go goroutines that process the handshake, so
-	// poll on a ticker instead and yield the CPU between checks. WireGuard also
-	// only retries a lost handshake initiation every REKEY_TIMEOUT (5s), which
-	// is why the overall wait can occasionally stretch to tens of seconds.
+	// todo: investigate why in some tests execution we need 30s
 	timeout := 30 * time.Second
 	timeoutChannel := time.After(timeout)
-	ticker := time.NewTicker(500 * time.Millisecond)
-	defer ticker.Stop()
 
 	for {
+		select {
+		case <-timeoutChannel:
+			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
+		default:
+		}
+
 		peer, gpErr := getPeer(peer1ifaceName, peer2Key.PublicKey().String())
 		if gpErr != nil {
 			t.Fatal(gpErr)
@@ -587,12 +588,6 @@ func Test_ConnectPeers(t *testing.T) {
 			t.Log("peers successfully handshake")
 			break
 		}
-
-		select {
-		case <-timeoutChannel:
-			t.Fatalf("waiting for peer handshake timeout after %s", timeout.String())
-		case <-ticker.C:
-		}
 	}
 
 }
@@ -620,3 +615,28 @@ func getPeer(ifaceName, peerPubKey string) (wgtypes.Peer, error) {
 	}
 	return wgtypes.Peer{}, fmt.Errorf("peer not found")
 }
+
+func getLocalIP() (string, error) {
+	// Get all interfaces
+	addrs, err := net.InterfaceAddrs()
+	if err != nil {
+		return "", err
+	}
+
+	for _, addr := range addrs {
+		ipNet, ok := addr.(*net.IPNet)
+		if !ok {
+			continue
+		}
+		if ipNet.IP.IsLoopback() {
+			continue
+		}
+
+		if ipNet.IP.To4() == nil {
+			continue
+		}
+		return ipNet.IP.String(), nil
+	}
+
+	return "", fmt.Errorf("no local IP found")
+}

client/internal/auth/auth.go

@@ -351,7 +351,6 @@ func (a *Auth) setSystemInfoFlags(info *system.Info) {
 		a.config.BlockLANAccess,
 		a.config.BlockInbound,
 		a.config.DisableIPv6,
-		a.config.SyncMessageVersion,
 		a.config.EnableSSHRoot,
 		a.config.EnableSSHSFTP,
 		a.config.EnableSSHLocalPortForwarding,

client/internal/auth/sessionwatch/watcher.go

@@ -24,7 +24,11 @@ import (
 )
 
 const (
-	maxPastHorizon = 30 * 24 * time.Hour
+	// Skew tolerates a small clock difference between the management
+	// server and this peer before treating a deadline as "in the past".
+	// Slightly above typical NTP drift; tight enough that the UI doesn't
+	// paint a stale expiry as if it were valid.
+	Skew = 30 * time.Second
 
 	// maxDeadlineHorizon caps how far in the future an accepted deadline
 	// can sit. A timestamp beyond this is almost certainly a protocol
@@ -53,7 +57,7 @@ var (
 	ErrDeadlineTooFarFuture = errors.New("session deadline too far in the future")
 
 	// ErrDeadlineInPast is returned by Update when the supplied deadline
-	// is more than maxPastHorizon in the past.
+	// is more than Skew in the past.
 	ErrDeadlineInPast = errors.New("session deadline in the past")
 )
 
@@ -62,14 +66,15 @@ var (
 // for deadline change/clear, PublishEvent for the two warnings); tests pass
 // a fake recorder so the same surface is observable without an engine.
 //
-// While the watcher runs, it owns the deadline propagated to the recorder:
-// every set, clear and sanity-check rejection routes the value through
-// SetSessionExpiresAt, so the SubscribeStatus snapshot the UI reads can
-// never drift from the watcher's timer state. (SetSessionExpiresAt fans
-// out its own state-change notification, so no separate notify is needed.)
-// The recorder is server-scoped and outlives this engine-scoped watcher;
-// Close deliberately leaves the recorder value in place so transient engine
-// restarts don't blank it — the client run loop clears it on real teardown.
+// The watcher is the single owner of the deadline propagated to the
+// recorder: every set, clear, sanity-check rejection and Close routes the
+// value through SetSessionExpiresAt, so the SubscribeStatus snapshot the UI
+// reads can never drift from the watcher's timer state. (SetSessionExpiresAt
+// fans out its own state-change notification, so no separate notify is
+// needed.) The recorder is server-scoped and outlives this engine-scoped
+// watcher — without the Close-time clear a teardown (Down, or the Down+Up of
+// a profile switch) would leave the next session showing the previous one's
+// stale "expires in" value.
 //
 // PublishEvent's signature mirrors peer.Status.PublishEvent: the watcher
 // composes the metadata internally so the wire format (MetaSession*) is
@@ -130,13 +135,10 @@ func NewWithLeads(lead, final time.Duration, recorder StatusRecorder) *Watcher {
 // was disabled).
 //
 // Same-value updates are no-ops. A different non-zero value cancels any
-// pending timer, resets the "already fired" guards, and — when the
-// deadline lies in the future — arms fresh warning timers. A deadline
-// already in the past (within maxPastHorizon) is recorded as-is with no
-// timers: the session has expired and consumers render it that way.
+// pending timer, resets the "already fired" guard, and arms a new one.
 //
 // Returns one of the sentinel Err* values when the deadline fails the
-// sanity checks (pre-epoch, far future, or past beyond maxPastHorizon).
+// sanity checks (pre-epoch, far future, or in the past beyond Skew).
 // In every error case the watcher first clears its state so it stays
 // consistent with what the caller will push into its other sinks (e.g.
 // applySessionDeadline forces a zero deadline into the status recorder
@@ -161,7 +163,7 @@ func (w *Watcher) Update(deadline time.Time) error {
 	case deadline.After(now.Add(maxDeadlineHorizon)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v", ErrDeadlineTooFarFuture, deadline)
-	case deadline.Before(now.Add(-maxPastHorizon)):
+	case deadline.Before(now.Add(-Skew)):
 		w.clearLocked()
 		return fmt.Errorf("%w: %v (now=%v)", ErrDeadlineInPast, deadline, now)
 	}
@@ -181,9 +183,7 @@ func (w *Watcher) Update(deadline time.Time) error {
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
 
-	if deadline.After(now) {
-		w.armTimerLocked(deadline)
-	}
+	w.armTimerLocked(deadline)
 	recorder := w.recorder
 	w.mu.Unlock()
 	if recorder != nil {
@@ -227,25 +227,30 @@ func (w *Watcher) Dismiss() {
 	log.Infof("auth session final-warning dismissed for deadline %s", w.current.Format(time.RFC3339))
 }
 
-// Close stops any pending timer. Update calls after Close are ignored.
-// The recorder keeps its deadline: the watcher is engine-scoped and closes
-// on every engine restart (network change, sleep/wake, stream errors)
-// while the SSO deadline stays valid across those, so clearing here would
-// blank the UI's "expires in" row on every transient reconnect. The
-// client run loop clears the server-scoped recorder when it exits for
-// real (Down, profile switch, permanent login failure).
+// Close stops any pending timer and drops the deadline on the status
+// recorder. Update calls after Close are ignored. Clearing the recorder
+// here is what keeps a teardown (Down, or the Down+Up of a profile switch)
+// from leaving the next session showing this one's stale "expires in"
+// value — the recorder is server-scoped and outlives this engine-scoped
+// watcher, so nothing else drops the anchor on teardown.
 func (w *Watcher) Close() {
 	w.mu.Lock()
-	defer w.mu.Unlock()
 	if w.closed {
+		w.mu.Unlock()
 		return
 	}
 	w.closed = true
 	w.stopTimerLocked()
+	hadDeadline := !w.current.IsZero()
 	w.current = time.Time{}
 	w.firedAt = time.Time{}
 	w.finalFiredAt = time.Time{}
 	w.dismissedAt = time.Time{}
+	recorder := w.recorder
+	w.mu.Unlock()
+	if recorder != nil && hadDeadline {
+		recorder.SetSessionExpiresAt(time.Time{})
+	}
 }
 
 // clearLocked drops the tracked deadline and notifies the recorder so

client/internal/auth/sessionwatch/watcher_test.go

@@ -224,13 +224,11 @@ func TestNewDeadlineCancelsPriorTimer(t *testing.T) {
 
 func TestRefreshAfterFireArmsNewWarning(t *testing.T) {
 	r := &fakeRecorder{}
-	lead := 150 * time.Millisecond
+	lead := 30 * time.Millisecond
 	w := newWatcher(lead, r)
 	defer w.Close()
 
-	// Warning fires ~20ms in; the deadline itself stays 150ms away so the
-	// replacement below lands well before it.
-	first := time.Now().Add(170 * time.Millisecond)
+	first := time.Now().Add(50 * time.Millisecond)
 	_ = w.Update(first)
 
 	// Wait for stateChange + warning of the first cycle.
@@ -308,29 +306,7 @@ func TestUpdateRejectsTooFarFuture(t *testing.T) {
 	}
 }
 
-func TestUpdateRecentPastRecordedAsExpired(t *testing.T) {
-	r := &fakeRecorder{}
-	w := newWatcher(50*time.Millisecond, r)
-	defer w.Close()
-
-	d := time.Now().Add(-1 * time.Hour)
-	if err := w.Update(d); err != nil {
-		t.Fatalf("recent-past Update should succeed, got %v", err)
-	}
-	if !w.Deadline().Equal(d) {
-		t.Fatalf("expected deadline to be recorded, got %v want %v", w.Deadline(), d)
-	}
-	if got := r.deadline(); !got.Equal(d) {
-		t.Fatalf("recorder deadline = %v, want %v", got, d)
-	}
-
-	time.Sleep(80 * time.Millisecond)
-	if n := countWhere(r.snapshot(), func(e event) bool { return e.kind == publish }); n != 0 {
-		t.Fatalf("no warning events may fire for an already-past deadline, got %+v", r.snapshot())
-	}
-}
-
-func TestUpdateAncientPastRejected(t *testing.T) {
+func TestUpdateInPastClearsDeadline(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	defer w.Close()
@@ -342,12 +318,12 @@ func TestUpdateAncientPastRejected(t *testing.T) {
 	// Drain the stateChange from the seed.
 	waitForEvents(t, r, 1)
 
-	err := w.Update(time.Now().Add(-31 * 24 * time.Hour))
+	err := w.Update(time.Now().Add(-1 * time.Hour))
 	if !errors.Is(err, ErrDeadlineInPast) {
 		t.Fatalf("want ErrDeadlineInPast, got %v", err)
 	}
 	if !w.Deadline().IsZero() {
-		t.Fatalf("rejected ancient-past update must clear the deadline, got %v", w.Deadline())
+		t.Fatalf("in-past update must clear the deadline, got %v", w.Deadline())
 	}
 	events := waitForEvents(t, r, 2)
 	if events[1].kind != stateChange {
@@ -355,25 +331,39 @@ func TestUpdateAncientPastRejected(t *testing.T) {
 	}
 }
 
+func TestUpdateWithinSkewAccepted(t *testing.T) {
+	r := &fakeRecorder{}
+	w := newWatcher(50*time.Millisecond, r)
+	defer w.Close()
+
+	// 5 seconds in the past is within the 30s Skew tolerance — accept it.
+	d := time.Now().Add(-5 * time.Second)
+	if err := w.Update(d); err != nil {
+		t.Fatalf("within-skew Update should succeed, got %v", err)
+	}
+	if !w.Deadline().Equal(d) {
+		t.Fatalf("expected deadline to be applied, got %v want %v", w.Deadline(), d)
+	}
+}
+
 func TestCloseSilencesUpdates(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(50*time.Millisecond, r)
 	w.Close()
 
-	if err := w.Update(time.Now().Add(time.Hour)); err != nil {
-		t.Fatalf("Update after Close: want nil, got %v", err)
-	}
+	_ = w.Update(time.Now().Add(time.Hour))
+
+	time.Sleep(20 * time.Millisecond)
 	if got := r.snapshot(); len(got) != 0 {
 		t.Fatalf("expected no events after Close, got %+v", got)
 	}
 }
 
-// TestCloseKeepsRecorderDeadline pins the reconnect-flap fix: the watcher
-// closes on every engine restart (network change, sleep/wake) while the
-// SSO deadline stays valid across those, so Close must leave the
-// server-scoped recorder's value in place. The client run loop clears the
-// recorder when it exits for real.
-func TestCloseKeepsRecorderDeadline(t *testing.T) {
+// TestCloseClearsRecorderDeadline pins the profile-switch fix: a watcher
+// holding a live deadline must zero the recorder on Close so the next
+// engine's watcher (and the UI reading the shared server-scoped recorder)
+// doesn't start out showing the previous session's stale "expires in".
+func TestCloseClearsRecorderDeadline(t *testing.T) {
 	r := &fakeRecorder{}
 	w := newWatcher(time.Hour, r)
 
@@ -387,8 +377,8 @@ func TestCloseKeepsRecorderDeadline(t *testing.T) {
 
 	w.Close()
 
-	if got := r.deadline(); !got.Equal(d) {
-		t.Fatalf("recorder deadline after Close = %v, want %v", got, d)
+	if got := r.deadline(); !got.IsZero() {
+		t.Fatalf("recorder deadline after Close = %v, want zero", got)
 	}
 }
 

client/internal/conn_mgr.go

@@ -34,8 +34,6 @@ const (
 // - Handling connection establishment based on peer signaling
 //
 // The implementation is not thread-safe; it is protected by engine.syncMsgMux.
-// The only exception is ActivatePeer, which is safe for concurrent use so the
-// DNS warm-up path can call it without contending on the engine mutex.
 type ConnMgr struct {
 	peerStore        *peerstore.Store
 	statusRecorder   *peer.Status
@@ -44,26 +42,12 @@ type ConnMgr struct {
 	rosenpassEnabled bool
 
 	lazyConnMgr *manager.Manager
-	// lazyConnMgrMu guards the lazyConnMgr pointer for readers outside the
-	// engine loop (ActivatePeer). Writers hold it in addition to
-	// engine.syncMsgMux; all other reads stay under engine.syncMsgMux only.
-	lazyConnMgrMu sync.RWMutex
-
-	// reconcileRoutedIPs re-applies a peer's routed allowed IPs after its lazy wake endpoint is
-	// (re)armed (Mode A at arm time). Injected by the engine; nil disables the reconcile.
-	reconcileRoutedIPs func(peerKey string) error
 
 	wg            sync.WaitGroup
 	lazyCtx       context.Context
 	lazyCtxCancel context.CancelFunc
 }
 
-// SetRoutedIPsReconciler injects the callback used to re-apply a peer's routed allowed IPs when
-// its lazy wake endpoint is (re)armed. Must be called before the lazy manager starts.
-func (e *ConnMgr) SetRoutedIPsReconciler(fn func(peerKey string) error) {
-	e.reconcileRoutedIPs = fn
-}
-
 func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
 	e := &ConnMgr{
 		peerStore:        peerStore,
@@ -254,20 +238,12 @@ func (e *ConnMgr) RemovePeerConn(peerKey string) {
 	conn.Log.Infof("removed peer from lazy conn manager")
 }
 
-// ActivatePeer wakes an idle lazy connection. Unlike the rest of ConnMgr it is
-// safe for concurrent use: the lazy manager pointer is read under lazyConnMgrMu
-// and the manager itself is internally synchronized, so callers outside the
-// engine loop (DNS warm-up) do not need engine.syncMsgMux.
 func (e *ConnMgr) ActivatePeer(ctx context.Context, conn *peer.Conn) {
-	e.lazyConnMgrMu.RLock()
-	lazyConnMgr := e.lazyConnMgr
-	started := lazyConnMgr != nil && e.lazyCtxCancel != nil
-	e.lazyConnMgrMu.RUnlock()
-	if !started {
+	if !e.isStartedWithLazyMgr() {
 		return
 	}
 
-	if found := lazyConnMgr.ActivatePeer(conn.GetKey()); found {
+	if found := e.lazyConnMgr.ActivatePeer(conn.GetKey()); found {
 		if err := conn.Open(ctx); err != nil {
 			conn.Log.Errorf("failed to open connection: %v", err)
 		}
@@ -292,22 +268,16 @@ func (e *ConnMgr) Close() {
 
 	e.lazyCtxCancel()
 	e.wg.Wait()
-
-	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
-	e.lazyConnMgrMu.Unlock()
 }
 
 func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	cfg := manager.Config{
 		InactivityThreshold: inactivityThresholdEnv(),
-		ReconcileAllowedIPs: e.reconcileRoutedIPs,
 	}
-
-	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
+
 	e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
-	e.lazyConnMgrMu.Unlock()
 
 	e.wg.Add(1)
 	go func() {
@@ -346,10 +316,7 @@ func (e *ConnMgr) closeManager(ctx context.Context) {
 
 	e.lazyCtxCancel()
 	e.wg.Wait()
-
-	e.lazyConnMgrMu.Lock()
 	e.lazyConnMgr = nil
-	e.lazyConnMgrMu.Unlock()
 
 	for _, peerID := range e.peerStore.PeersPubKey() {
 		e.peerStore.PeerConnOpen(ctx, peerID)
@@ -385,20 +352,11 @@ func inactivityThresholdEnv() *time.Duration {
 		return nil
 	}
 
-	// Documented format: a Go duration such as "30m" or "1h".
-	if d, err := time.ParseDuration(envValue); err == nil {
-		if d <= 0 {
-			return nil
-		}
-		return &d
+	parsedMinutes, err := strconv.Atoi(envValue)
+	if err != nil || parsedMinutes <= 0 {
+		return nil
 	}
 
-	// Backwards compatibility: a bare integer used to be interpreted as minutes.
-	if parsedMinutes, err := strconv.Atoi(envValue); err == nil && parsedMinutes > 0 {
-		d := time.Duration(parsedMinutes) * time.Minute
-		return &d
-	}
-
-	log.Warnf("invalid %s value %q: expected a Go duration such as 30m or 1h", lazyconn.EnvInactivityThreshold, envValue)
-	return nil
+	d := time.Duration(parsedMinutes) * time.Minute
+	return &d
 }

client/internal/conn_mgr_test.go

@@ -1,21 +1,10 @@
 package internal
 
 import (
-	"context"
-	"net"
-	"net/netip"
 	"os"
-	"sync"
 	"testing"
-	"time"
 
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
-
-	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-	"github.com/netbirdio/netbird/monotime"
 )
 
 func TestResolveLazyForce(t *testing.T) {
@@ -49,93 +38,3 @@ func TestResolveLazyForce(t *testing.T) {
 		})
 	}
 }
-
-type mockLazyWGIface struct{}
-
-func (mockLazyWGIface) RemovePeer(string) error { return nil }
-func (mockLazyWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
-	return nil
-}
-func (mockLazyWGIface) IsUserspaceBind() bool                    { return false }
-func (mockLazyWGIface) Address() wgaddr.Address                  { return wgaddr.Address{} }
-func (mockLazyWGIface) LastActivities() map[string]monotime.Time { return nil }
-func (mockLazyWGIface) MTU() uint16                              { return 1280 }
-
-// TestConnMgr_ActivatePeerConcurrentWithLifecycle exercises ActivatePeer from
-// non-engine goroutines (the DNS warm-up path) racing the manager lifecycle,
-// which stays on the engine loop. Run with -race: it fails if ActivatePeer
-// still requires engine.syncMsgMux for safety.
-func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
-	t.Setenv(lazyconn.EnvLazyConn, "on")
-
-	status := peer.NewRecorder("https://mgm")
-	store := peerstore.NewConnStore()
-	connMgr := NewConnMgr(&EngineConfig{}, status, store, mockLazyWGIface{})
-
-	conn := newTestPeerConn(t, "peerA")
-
-	ctx, cancel := context.WithCancel(context.Background())
-	defer cancel()
-	connMgr.Start(ctx)
-
-	done := make(chan struct{})
-	var wg sync.WaitGroup
-	for range 4 {
-		wg.Add(1)
-		go func() {
-			defer wg.Done()
-			for {
-				select {
-				case <-done:
-					return
-				default:
-					connMgr.ActivatePeer(ctx, conn)
-				}
-			}
-		}()
-	}
-
-	// Let the activators spin against the started manager, then tear it down
-	// underneath them and let them spin against the stopped manager.
-	time.Sleep(100 * time.Millisecond)
-	connMgr.Close()
-	time.Sleep(50 * time.Millisecond)
-
-	close(done)
-	wg.Wait()
-}
-
-func TestInactivityThresholdEnv(t *testing.T) {
-	tests := []struct {
-		name string
-		val  string
-		want *time.Duration
-	}{
-		{name: "unset", val: "", want: nil},
-		{name: "go duration minutes", val: "30m", want: durPtr(30 * time.Minute)},
-		{name: "go duration hours", val: "1h", want: durPtr(time.Hour)},
-		{name: "go duration seconds", val: "90s", want: durPtr(90 * time.Second)},
-		{name: "bare integer is minutes (backwards compat)", val: "5", want: durPtr(5 * time.Minute)},
-		{name: "zero duration", val: "0s", want: nil},
-		{name: "zero integer", val: "0", want: nil},
-		{name: "negative duration", val: "-5m", want: nil},
-		{name: "garbage", val: "abc", want: nil},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(lazyconn.EnvInactivityThreshold, tc.val)
-			got := inactivityThresholdEnv()
-			switch {
-			case tc.want == nil && got != nil:
-				t.Fatalf("want nil, got %v", *got)
-			case tc.want != nil && got == nil:
-				t.Fatalf("want %v, got nil", *tc.want)
-			case tc.want != nil && *got != *tc.want:
-				t.Fatalf("want %v, got %v", *tc.want, *got)
-			}
-		})
-	}
-}
-
-func durPtr(d time.Duration) *time.Duration { return &d }

client/internal/connect.go

@@ -34,7 +34,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
-	"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
@@ -137,13 +136,10 @@ func (c *ConnectClient) RunOniOS(
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
 	debug.SetGCPercent(5)
 
-	notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
-	defer notifier.Close()
-
 	mobileDependency := MobileDependency{
 		FileDescriptor:        fileDescriptor,
-		NetworkChangeListener: notifier,
-		DnsManager:            notifier,
+		NetworkChangeListener: networkChangeListener,
+		DnsManager:            dnsManager,
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}
@@ -261,10 +257,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Errorf("failed to clean up temporary installer file: %v", err)
 	}
 
-	defer func() {
-		c.statusRecorder.SetSessionExpiresAt(time.Time{})
-		c.statusRecorder.ClientStop()
-	}()
+	defer c.statusRecorder.ClientStop()
 	operation := func() error {
 		// if context cancelled we not start new backoff cycle
 		if c.ctx.Err() != nil {
@@ -625,7 +618,6 @@ func createEngineConfig(key wgtypes.Key, config *profilemanager.Config, peerConf
 		BlockLANAccess:      config.BlockLANAccess,
 		BlockInbound:        config.BlockInbound,
 		DisableIPv6:         config.DisableIPv6,
-		SyncMessageVersion:  config.SyncMessageVersion,
 
 		LazyConnection: lazyconn.ParseState(config.LazyConnection),
 
@@ -701,7 +693,6 @@ func loginToManagement(ctx context.Context, client mgm.Client, pubSSHKey []byte,
 		config.BlockLANAccess,
 		config.BlockInbound,
 		config.DisableIPv6,
-		config.SyncMessageVersion,
 		config.EnableSSHRoot,
 		config.EnableSSHSFTP,
 		config.EnableSSHLocalPortForwarding,

client/internal/debug/debug.go

@@ -676,7 +676,6 @@ func (g *BundleGenerator) addCommonConfigFields(configContent *strings.Builder)
 	configContent.WriteString(fmt.Sprintf("BlockLANAccess: %v\n", g.internalConfig.BlockLANAccess))
 	configContent.WriteString(fmt.Sprintf("BlockInbound: %v\n", g.internalConfig.BlockInbound))
 	configContent.WriteString(fmt.Sprintf("DisableIPv6: %v\n", g.internalConfig.DisableIPv6))
-	configContent.WriteString(fmt.Sprintf("SyncMessageVersion: %v\n", g.internalConfig.SyncMessageVersion))
 
 	if g.internalConfig.DisableNotifications != nil {
 		configContent.WriteString(fmt.Sprintf("DisableNotifications: %v\n", *g.internalConfig.DisableNotifications))

client/internal/debug/debug_test.go

@@ -887,8 +887,6 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		ClientCertKeyPath:             "/tmp/key",
 		LazyConnection:                "on",
 		MTU:                           1280,
-		DisableIPv6:                   true,
-		SyncMessageVersion:            func(v int) *int { return &v }(1),
 	}
 
 	for _, anonymize := range []bool{false, true} {

client/internal/dns/local/local.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
-	"os"
 	"slices"
 	"strings"
 	"sync"
@@ -37,43 +36,7 @@ type resolver interface {
 // record is left alone (it points at something outside our mesh, e.g.
 // a non-peer upstream).
 type PeerConnectivity interface {
-	IsConnectedByIP(ip netip.Addr) (known, connected bool)
-}
-
-// PeerActivator wakes lazy-connection peers on demand. The local resolver calls
-// it with the tunnel IPs an answer points at, so a peer that is idle (lazily
-// disconnected) starts connecting at DNS-resolution time rather than racing the
-// client's first request packet. nil disables warm-up.
-type PeerActivator interface {
-	// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and blocks
-	// until one is connected or ctx (a short per-query budget) expires. It is a
-	// fast no-op for unknown or already-connected addresses.
-	ActivatePeersByIP(ctx context.Context, addrs []netip.Addr)
-}
-
-const (
-	defaultLazyWarmupTimeout = 2 * time.Second
-	envLazyWarmupTimeout     = "NB_DNS_LAZY_WARMUP_TIMEOUT"
-)
-
-// lazyWarmupTimeoutFromEnv returns the per-query budget for waking a
-// lazy-connection peer a DNS answer points at. Tunable via
-// NB_DNS_LAZY_WARMUP_TIMEOUT (a Go duration). Parsed once at construction time.
-func lazyWarmupTimeoutFromEnv() time.Duration {
-	v := os.Getenv(envLazyWarmupTimeout)
-	if v == "" {
-		return defaultLazyWarmupTimeout
-	}
-	d, err := time.ParseDuration(v)
-	if err != nil {
-		log.Warnf("invalid %s value %q, using default %s: %v", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout, err)
-		return defaultLazyWarmupTimeout
-	}
-	if d <= 0 {
-		log.Warnf("non-positive %s value %q, using default %s", envLazyWarmupTimeout, v, defaultLazyWarmupTimeout)
-		return defaultLazyWarmupTimeout
-	}
-	return d
+	IsConnectedByIP(ip string) (known, connected bool)
 }
 
 type Resolver struct {
@@ -88,12 +51,6 @@ type Resolver struct {
 	// filter and preserves the legacy "return whatever is registered"
 	// behaviour for callers that never wire a status source.
 	peerConn PeerConnectivity
-	// peerActivator, when non-nil, is called at resolution time to warm the
-	// lazy connection to the peer(s) an answer points at. nil disables warm-up.
-	peerActivator PeerActivator
-	// warmupTimeout is the per-query budget for the lazy-connection warm-up
-	// wait, resolved from the environment once at construction time.
-	warmupTimeout time.Duration
 
 	ctx    context.Context
 	cancel context.CancelFunc
@@ -102,12 +59,11 @@ type Resolver struct {
 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),
-		warmupTimeout: lazyWarmupTimeoutFromEnv(),
-		ctx:           ctx,
-		cancel:        cancel,
+		records: make(map[dns.Question][]dns.RR),
+		domains: make(map[domain.Domain]struct{}),
+		zones:   make(map[domain.Domain]bool),
+		ctx:     ctx,
+		cancel:  cancel,
 	}
 }
 
@@ -120,14 +76,6 @@ func (d *Resolver) SetPeerConnectivity(p PeerConnectivity) {
 	d.peerConn = p
 }
 
-// SetPeerActivator wires the DNS-time lazy-connection warm-up. Pass nil to
-// disable. Safe to call multiple times; the latest value wins.
-func (d *Resolver) SetPeerActivator(a PeerActivator) {
-	d.mu.Lock()
-	defer d.mu.Unlock()
-	d.peerActivator = a
-}
-
 func (d *Resolver) MatchSubdomains() bool {
 	return true
 }
@@ -174,9 +122,6 @@ func (d *Resolver) ServeDNS(w dns.ResponseWriter, r *dns.Msg) {
 	replyMessage.RecursionAvailable = true
 
 	result := d.lookupRecords(logger, question)
-	// Warm before filtering: activation flips a lazily-idle target to connected,
-	// which then lets it survive the disconnected-peer filter below.
-	d.warmLazyPeers(question, result.records)
 	result.records = d.filterDisconnectedPeerAnswers(logger, question, result.records)
 	replyMessage.Authoritative = !result.hasExternalData
 	replyMessage.Answer = result.records
@@ -550,8 +495,8 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	kept := make([]dns.RR, 0, len(records))
 	var dropped int
 	for _, rr := range records {
-		ip, ok := extractRecordAddr(rr)
-		if !ok {
+		ip := extractRecordIP(rr)
+		if ip == "" {
 			kept = append(kept, rr)
 			continue
 		}
@@ -573,57 +518,22 @@ func (d *Resolver) filterDisconnectedPeerAnswers(logger *log.Entry, question dns
 	return kept
 }
 
-// warmLazyPeers triggers lazy-connection wake-up for the peers a resolved
-// answer points at and waits briefly for one to connect, so the caller's first
-// request doesn't race the connection establishment. Warm-up is scoped to
-// match-only (non-authoritative) zones — the synthesized private-service zones
-// and user-created zones whose records point at specific peers. The account's
-// peer zone is authoritative, so plain peer-name lookups never trigger warm-up;
-// otherwise resolving any peer's name would wake its idle connection, defeating
-// laziness mesh-wide. No-op when no activator is wired (lazy connections
-// disabled) or the answer carries no peer IPs.
-func (d *Resolver) warmLazyPeers(question dns.Question, records []dns.RR) {
-	if len(records) < 2 {
-		return
-	}
-	d.mu.RLock()
-	activator := d.peerActivator
-	var nonAuth, found bool
-	if activator != nil {
-		nonAuth, found = d.findZone(question.Name)
-	}
-	d.mu.RUnlock()
-	if activator == nil || !found || !nonAuth {
-		return
-	}
-
-	var addrs []netip.Addr
-	for _, rr := range records {
-		if addr, ok := extractRecordAddr(rr); ok {
-			addrs = append(addrs, addr)
-		}
-	}
-	if len(addrs) == 0 {
-		return
-	}
-
-	ctx, cancel := context.WithTimeout(d.ctx, d.warmupTimeout)
-	defer cancel()
-	activator.ActivatePeersByIP(ctx, addrs)
-}
-
-// extractRecordAddr returns the IP address carried by an A or AAAA record.
-// ok is false for any other record type or a record with no address.
-func extractRecordAddr(rr dns.RR) (netip.Addr, bool) {
+// extractRecordIP returns the dotted-decimal / colon-hex IP carried by
+// an A or AAAA record, or "" for any other record type.
+func extractRecordIP(rr dns.RR) string {
 	switch r := rr.(type) {
 	case *dns.A:
-		addr, ok := netip.AddrFromSlice(r.A)
-		return addr.Unmap(), ok
+		if r.A == nil {
+			return ""
+		}
+		return r.A.String()
 	case *dns.AAAA:
-		addr, ok := netip.AddrFromSlice(r.AAAA)
-		return addr.Unmap(), ok
+		if r.AAAA == nil {
+			return ""
+		}
+		return r.AAAA.String()
 	}
-	return netip.Addr{}, false
+	return ""
 }
 
 // Update replaces all zones and their records

client/internal/dns/local/local_test.go

@@ -37,8 +37,8 @@ type mockPeerConnectivity struct {
 	byIP map[string]struct{ known, connected bool }
 }
 
-func (m mockPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
-	v, ok := m.byIP[ip.String()]
+func (m mockPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
+	v, ok := m.byIP[ip]
 	if !ok {
 		return false, false
 	}

client/internal/dns/local/warmup_test.go

@@ -1,204 +0,0 @@
-package local
-
-import (
-	"context"
-	"net"
-	"net/netip"
-	"sync"
-	"testing"
-	"time"
-
-	"github.com/miekg/dns"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/dns/test"
-	nbdns "github.com/netbirdio/netbird/dns"
-)
-
-// recordingActivator records the addresses it was asked to warm and returns
-// immediately, so ServeDNS is not blocked by the test.
-type recordingActivator struct {
-	mu     sync.Mutex
-	called bool
-	addrs  []netip.Addr
-}
-
-func (r *recordingActivator) ActivatePeersByIP(_ context.Context, addrs []netip.Addr) {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	r.called = true
-	r.addrs = append(r.addrs, addrs...)
-}
-
-func serveA(t *testing.T, resolver *Resolver, name string) *dns.Msg {
-	t.Helper()
-	var resp *dns.Msg
-	w := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { resp = m; return nil }}
-	resolver.ServeDNS(w, new(dns.Msg).SetQuestion(name, dns.TypeA))
-	return resp
-}
-
-// serviceZone registers rec in a match-only (non-authoritative) zone, the shape
-// the synthesized private-service zones arrive in.
-func serviceZone(t *testing.T, resolver *Resolver, zone string, records ...nbdns.SimpleRecord) {
-	t.Helper()
-	resolver.Update([]nbdns.CustomZone{{
-		Domain:           zone,
-		Records:          records,
-		NonAuthoritative: true,
-	}})
-}
-
-func TestLocalResolver_WarmsLazyPeerOnResolve(t *testing.T) {
-	// Warm-up fires only for multi-record answers (the HA / round-robin shape of
-	// the synthesized private-service zones), so register two peer targets.
-	const name = "svc.proxy.netbird.cloud."
-	recs := []nbdns.SimpleRecord{
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"},
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.8"},
-	}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", recs...)
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.True(t, act.called, "activator must be invoked for a multi-record service-zone answer")
-	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.7"), "activator must receive the first peer IP")
-	assert.Contains(t, act.addrs, netip.MustParseAddr("100.64.0.8"), "activator must receive the second peer IP")
-}
-
-func TestLocalResolver_NoWarmupForSingleRecord(t *testing.T) {
-	// A single-record answer does not trigger warm-up; the resolver only warms
-	// multi-record answers.
-	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, rec.Name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked for a single-record answer")
-}
-
-func TestLocalResolver_NoActivatorNoWarmup(t *testing.T) {
-	// With no activator wired the resolver behaves exactly as before.
-	rec := nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"}
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud", rec)
-
-	resp := serveA(t, resolver, rec.Name)
-	require.NotNil(t, resp, "resolver must still answer without an activator")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A record")
-}
-
-func TestLocalResolver_NoWarmupForMissingRecord(t *testing.T) {
-	// A query that resolves to nothing must not invoke the activator (no IPs).
-	resolver := NewResolver()
-	serviceZone(t, resolver, "proxy.netbird.cloud",
-		nbdns.SimpleRecord{Name: "svc.proxy.netbird.cloud.", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.7"})
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	serveA(t, resolver, "absent.proxy.netbird.cloud.")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked when there is no answer")
-}
-
-func TestLocalResolver_NoWarmupInAuthoritativeZone(t *testing.T) {
-	// The account's peer zone is authoritative; resolving a peer's name there
-	// must not wake its lazy connection — warm-up is scoped to match-only
-	// (non-authoritative) zones such as the synthesized private-service zones.
-	// Use a multi-record answer so the authoritative-zone scoping is the only
-	// reason warm-up is skipped, not the single-record guard.
-	const name = "peer.netbird.cloud."
-	recs := []nbdns.SimpleRecord{
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.9"},
-		{Name: name, Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "100.64.0.10"},
-	}
-	resolver := NewResolver()
-	resolver.Update([]nbdns.CustomZone{{
-		Domain:  "netbird.cloud",
-		Records: recs,
-	}})
-
-	act := &recordingActivator{}
-	resolver.SetPeerActivator(act)
-
-	resp := serveA(t, resolver, name)
-	require.NotNil(t, resp, "resolver must answer")
-	require.NotEmpty(t, resp.Answer, "answer must carry the A records")
-
-	act.mu.Lock()
-	defer act.mu.Unlock()
-	assert.False(t, act.called, "activator must not be invoked for authoritative-zone answers")
-}
-
-func TestLazyWarmupTimeoutFromEnv(t *testing.T) {
-	tests := []struct {
-		name   string
-		value  string
-		envSet bool
-		want   time.Duration
-	}{
-		{name: "unset uses default", want: defaultLazyWarmupTimeout},
-		{name: "valid overrides", value: "5s", envSet: true, want: 5 * time.Second},
-		{name: "invalid falls back", value: "not-a-duration", envSet: true, want: defaultLazyWarmupTimeout},
-		{name: "negative falls back", value: "-1s", envSet: true, want: defaultLazyWarmupTimeout},
-		{name: "zero falls back", value: "0s", envSet: true, want: defaultLazyWarmupTimeout},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			if tt.envSet {
-				t.Setenv(envLazyWarmupTimeout, tt.value)
-			}
-			assert.Equal(t, tt.want, lazyWarmupTimeoutFromEnv())
-			assert.Equal(t, tt.want, NewResolver().warmupTimeout, "constructor must resolve the timeout once")
-		})
-	}
-}
-
-func TestExtractRecordAddr(t *testing.T) {
-	t.Run("A record yields unmapped v4", func(t *testing.T) {
-		// net.ParseIP returns the 16-byte v4-in-v6 form, the same shape
-		// miekg/dns stores after parsing an A record; the extracted address
-		// must compare equal to a plain v4 netip.Addr.
-		addr, ok := extractRecordAddr(&dns.A{A: net.ParseIP("100.64.0.7")})
-		require.True(t, ok)
-		assert.True(t, addr.Is4())
-		assert.Equal(t, netip.MustParseAddr("100.64.0.7"), addr)
-	})
-
-	t.Run("AAAA record yields v6", func(t *testing.T) {
-		addr, ok := extractRecordAddr(&dns.AAAA{AAAA: net.ParseIP("fd00::1")})
-		require.True(t, ok)
-		assert.Equal(t, netip.MustParseAddr("fd00::1"), addr)
-	})
-
-	t.Run("A record without address", func(t *testing.T) {
-		_, ok := extractRecordAddr(&dns.A{})
-		assert.False(t, ok)
-	})
-
-	t.Run("non-address record", func(t *testing.T) {
-		_, ok := extractRecordAddr(&dns.CNAME{Target: "target.netbird.cloud."})
-		assert.False(t, ok)
-	})
-}

client/internal/dns/mock_server.go

@@ -8,7 +8,6 @@ import (
 	"github.com/miekg/dns"
 
 	dnsconfig "github.com/netbirdio/netbird/client/internal/dns/config"
-	"github.com/netbirdio/netbird/client/internal/dns/local"
 	nbdns "github.com/netbirdio/netbird/dns"
 	"github.com/netbirdio/netbird/route"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -93,11 +92,6 @@ func (m *MockServer) SetFirewall(Firewall) {
 	// Mock implementation - no-op
 }
 
-// SetPeerActivator mock implementation of SetPeerActivator from Server interface
-func (m *MockServer) SetPeerActivator(local.PeerActivator) {
-	// Mock implementation - no-op
-}
-
 // BeginBatch mock implementation of BeginBatch from Server interface
 func (m *MockServer) BeginBatch() {
 	// Mock implementation - no-op

client/internal/dns/server.go

@@ -82,7 +82,6 @@ type Server interface {
 	PopulateManagementDomain(mgmtURL *url.URL) error
 	SetRouteSources(selected, active func() route.HAMap)
 	SetFirewall(Firewall)
-	SetPeerActivator(local.PeerActivator)
 }
 
 type nsGroupsByDomain struct {
@@ -492,13 +491,6 @@ func (s *DefaultServer) SetFirewall(fw Firewall) {
 	}
 }
 
-// SetPeerActivator wires the DNS-time lazy-connection warm-up on the local
-// resolver. Injected after the connection manager exists (it does not at
-// DNS-server construction time). Pass nil to disable.
-func (s *DefaultServer) SetPeerActivator(a local.PeerActivator) {
-	s.localResolver.SetPeerActivator(a)
-}
-
 // Stop stops the server
 func (s *DefaultServer) Stop() {
 	s.ctxCancel()
@@ -1443,11 +1435,11 @@ type localPeerConnectivity struct {
 
 // IsConnectedByIP looks the IP up in the peerstore and surfaces both
 // the known and connected bits. Used by Resolver.filterDisconnectedPeerAnswers.
-func (l localPeerConnectivity) IsConnectedByIP(ip netip.Addr) (known, connected bool) {
+func (l localPeerConnectivity) IsConnectedByIP(ip string) (known, connected bool) {
 	if l.status == nil {
 		return false, false
 	}
-	state, ok := l.status.PeerStateByIP(ip.String())
+	state, ok := l.status.PeerStateByIP(ip)
 	if !ok {
 		return false, false
 	}

client/internal/dns_peer_activator.go

@@ -1,76 +0,0 @@
-package internal
-
-import (
-	"context"
-	"net/netip"
-	"time"
-
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-)
-
-const dnsActivationPollInterval = 50 * time.Millisecond
-
-// dnsPeerActivator wakes lazy-connection peers from the DNS resolution path. It
-// implements dns/local.PeerActivator. DNS queries run on their own goroutines,
-// so it only touches state that is safe for concurrent use — ConnMgr.ActivatePeer,
-// peerstore.Store and peer.Status — and never takes the engine's syncMsgMux,
-// keeping DNS resolution from contending with network-map processing.
-type dnsPeerActivator struct {
-	connMgr   *ConnMgr
-	peerStore *peerstore.Store
-	status    *peer.Status
-	// ctx is the engine's long-lived context. The connection dial is tied to it
-	// (not the per-query DNS wait budget) so a handshake that outlasts the wait
-	// still completes in the background rather than being cancelled at the deadline.
-	ctx context.Context
-}
-
-// ActivatePeersByIP triggers wake-up for the peer(s) owning addrs and waits
-// until one is connected or ctx (the per-query DNS wait budget) expires.
-// Activation itself is tied to the engine's long-lived context so the dial
-// survives a wait that times out. Unknown or already-connected addresses are
-// skipped, so the steady-state (warm) path adds no latency.
-func (a *dnsPeerActivator) ActivatePeersByIP(ctx context.Context, addrs []netip.Addr) {
-	if a == nil || a.connMgr == nil {
-		return
-	}
-
-	var pending []string
-	for _, addr := range addrs {
-		ip := addr.String()
-		st, ok := a.status.PeerStateByIP(ip)
-		if !ok || st.ConnStatus == peer.StatusConnected {
-			continue
-		}
-		conn, ok := a.peerStore.PeerConn(st.PubKey)
-		if !ok {
-			continue
-		}
-		a.connMgr.ActivatePeer(a.ctx, conn)
-		pending = append(pending, ip)
-	}
-
-	if len(pending) == 0 {
-		return
-	}
-	a.waitConnected(ctx, pending)
-}
-
-// waitConnected blocks until any of ips reports a connected peer or ctx expires.
-func (a *dnsPeerActivator) waitConnected(ctx context.Context, ips []string) {
-	ticker := time.NewTicker(dnsActivationPollInterval)
-	defer ticker.Stop()
-	for {
-		for _, ip := range ips {
-			if st, ok := a.status.PeerStateByIP(ip); ok && st.ConnStatus == peer.StatusConnected {
-				return
-			}
-		}
-		select {
-		case <-ctx.Done():
-			return
-		case <-ticker.C:
-		}
-	}
-}

client/internal/dns_peer_activator_test.go

@@ -1,129 +0,0 @@
-package internal
-
-import (
-	"context"
-	"net/netip"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-)
-
-func newTestPeerConn(t *testing.T, key string) *peer.Conn {
-	t.Helper()
-	conn, err := peer.NewConn(peer.ConnConfig{
-		Key:      key,
-		LocalKey: "local",
-		WgConfig: peer.WgConfig{
-			AllowedIps: []netip.Prefix{netip.MustParsePrefix("100.64.0.1/32")},
-		},
-	}, peer.ServiceDependencies{})
-	require.NoError(t, err)
-	return conn
-}
-
-func newTestDNSPeerActivator(t *testing.T) (*dnsPeerActivator, *peer.Status, *peerstore.Store) {
-	t.Helper()
-	status := peer.NewRecorder("https://mgm")
-	store := peerstore.NewConnStore()
-	// ConnMgr without Start: the lazy manager is nil, so ActivatePeer is a
-	// no-op — these tests exercise the activator's skip/wait logic.
-	connMgr := NewConnMgr(&EngineConfig{}, status, store, nil)
-	return &dnsPeerActivator{
-		connMgr:   connMgr,
-		peerStore: store,
-		status:    status,
-		ctx:       context.Background(),
-	}, status, store
-}
-
-func TestDNSPeerActivator_NilSafe(t *testing.T) {
-	var a *dnsPeerActivator
-	a.ActivatePeersByIP(context.Background(), []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-}
-
-// TestDNSPeerActivator_SkipsUnknownAndConnectedPeers verifies the steady-state
-// (warm) path adds no latency: already-connected and unknown addresses never
-// enter the wait loop.
-func TestDNSPeerActivator_SkipsUnknownAndConnectedPeers(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", "fd00::1"))
-	require.NoError(t, status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected}))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{
-		netip.MustParseAddr("100.64.0.1"),  // known, connected -> skipped
-		netip.MustParseAddr("fd00::1"),     // known via IPv6, connected -> skipped
-		netip.MustParseAddr("100.64.0.99"), // unknown -> skipped
-	})
-	require.Less(t, time.Since(start), time.Second, "no pending peer must mean no wait")
-}
-
-// TestDNSPeerActivator_WaitsForPendingPeerToConnect verifies the wait loop
-// returns as soon as a pending peer reports connected, well before the
-// per-query budget expires.
-func TestDNSPeerActivator_WaitsForPendingPeerToConnect(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	go func() {
-		time.Sleep(150 * time.Millisecond)
-		_ = status.UpdatePeerState(peer.State{PubKey: "peerA", ConnStatus: peer.StatusConnected})
-	}()
-
-	ctx, cancel := context.WithTimeout(context.Background(), 10*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	elapsed := time.Since(start)
-
-	require.GreaterOrEqual(t, elapsed, 100*time.Millisecond, "must wait for the pending peer")
-	require.Less(t, elapsed, 5*time.Second, "must return on connect, not at the deadline")
-}
-
-// TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle verifies a peer that
-// never connects releases the DNS response at the per-query budget instead of
-// blocking it indefinitely.
-func TestDNSPeerActivator_ReturnsAtBudgetWhenPeerStaysIdle(t *testing.T) {
-	a, status, store := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-	store.AddPeerConn("peerA", newTestPeerConn(t, "peerA"))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 300*time.Millisecond)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	elapsed := time.Since(start)
-
-	require.GreaterOrEqual(t, elapsed, 250*time.Millisecond, "must wait out the budget for a pending peer")
-	require.Less(t, elapsed, 5*time.Second, "must not block past the budget")
-}
-
-// TestDNSPeerActivator_NoWaitWithoutPeerConn verifies a known-but-idle peer
-// with no connection object in the store is not waited on: there is nothing to
-// activate, so waiting could only ever time out.
-func TestDNSPeerActivator_NoWaitWithoutPeerConn(t *testing.T) {
-	a, status, _ := newTestDNSPeerActivator(t)
-
-	require.NoError(t, status.AddPeer("peerA", "a.netbird.cloud", "100.64.0.1", ""))
-
-	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
-	defer cancel()
-
-	start := time.Now()
-	a.ActivatePeersByIP(ctx, []netip.Addr{netip.MustParseAddr("100.64.0.1")})
-	require.Less(t, time.Since(start), time.Second, "peer without a conn must not be waited on")
-}

client/internal/ebpf/ebpf/src/dns_fwd.c

@@ -52,14 +52,11 @@ int xdp_dns_fwd(struct iphdr  *ip, struct udphdr *udp) {
 
     if (udp->dest == GENERAL_DNS_PORT && ip->daddr == dns_ip) {
         udp->dest = dns_port;
-        // Clear the now-stale checksum; zero means "not computed" for IPv4.
-        udp->check = 0;
         return XDP_PASS;
     }
 
     if (udp->source == dns_port && ip->saddr == dns_ip) {
         udp->source = GENERAL_DNS_PORT;
-        udp->check = 0;
         return XDP_PASS;
     }
 

client/internal/ebpf/ebpf/src/wg_proxy.c

@@ -50,11 +50,5 @@ int xdp_wg_proxy(struct iphdr  *ip, struct udphdr *udp) {
     __be16 new_dst_port = htons(proxy_port);
     udp->dest = new_dst_port;
     udp->source = new_src_port;
-
-    // The ports are covered by the UDP checksum. This is an IPv4 loopback hop
-    // and the payload is already integrity-protected, so clear the checksum (a
-    // zero UDP checksum means "not computed" for IPv4) rather than leave a
-    // stale value the kernel would drop as UDP_CSUM.
-    udp->check = 0;
 	return XDP_PASS;
 }

client/internal/engine.go

@@ -64,10 +64,7 @@ import (
 	"github.com/netbirdio/netbird/route"
 	mgm "github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/management/domain"
-	sharedgrpc "github.com/netbirdio/netbird/shared/management/grpc"
-	nbnetworkmap "github.com/netbirdio/netbird/shared/management/networkmap"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-	types "github.com/netbirdio/netbird/shared/management/types"
 	"github.com/netbirdio/netbird/shared/netiputil"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
@@ -150,7 +147,6 @@ type EngineConfig struct {
 	BlockLANAccess      bool
 	BlockInbound        bool
 	DisableIPv6         bool
-	SyncMessageVersion  *int
 
 	// LazyConnection is the MDM-sourced lazy-connection override; StateUnset defers to
 	// the env var and management feature flag.
@@ -224,13 +220,6 @@ type Engine struct {
 	// networkSerial is the latest CurrentSerial (state ID) of the network sent by the Management service
 	networkSerial uint64
 
-	// latestComponents is the most-recent NetworkMapComponents decoded from
-	// a NetworkMapEnvelope (capability=3 peers only). Held alongside the
-	// NetworkMap that Calculate() produced from it so future incremental
-	// updates have a base to apply changes against. nil for legacy-format
-	// peers. Guarded by syncMsgMux.
-	latestComponents *types.NetworkMapComponents
-
 	networkMonitor *networkmonitor.NetworkMonitor
 
 	sshServer sshServer
@@ -663,24 +652,8 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 	iceCfg := e.createICEConfig()
 
 	e.connMgr = NewConnMgr(e.config, e.statusRecorder, e.peerStore, wgIface)
-	e.connMgr.SetRoutedIPsReconciler(func(peerKey string) error {
-		if e.routeManager == nil {
-			return nil
-		}
-		return e.routeManager.ReconcilePeerAllowedIPs(peerKey)
-	})
 	e.connMgr.Start(e.ctx)
 
-	// Wire DNS-time lazy-connection warm-up now that the connection manager
-	// exists (it does not at DNS-server construction time). A DNS answer that
-	// points at an idle peer then wakes it before the client's first request.
-	e.dnsServer.SetPeerActivator(&dnsPeerActivator{
-		connMgr:   e.connMgr,
-		peerStore: e.peerStore,
-		status:    e.statusRecorder,
-		ctx:       e.ctx,
-	})
-
 	e.srWatcher = guard.NewSRWatcher(e.signal, e.relayManager, e.mobileDep.IFaceDiscover, iceCfg)
 	e.srWatcher.Start(peer.IsForceRelayed())
 
@@ -990,12 +963,8 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 
 	e.ApplySessionDeadline(update.GetSessionExpiresAt())
 
-	// Envelope sync responses carry PeerConfig at the top level; legacy
-	// NetworkMap syncs carry it under NetworkMap.PeerConfig.
-	if pc := update.GetPeerConfig(); pc != nil {
-		e.handleAutoUpdateVersion(pc.GetAutoUpdate())
-	} else if nm := update.GetNetworkMap(); nm != nil && nm.GetPeerConfig() != nil {
-		e.handleAutoUpdateVersion(nm.GetPeerConfig().GetAutoUpdate())
+	if update.NetworkMap != nil && update.NetworkMap.PeerConfig != nil {
+		e.handleAutoUpdateVersion(update.NetworkMap.PeerConfig.AutoUpdate)
 	}
 
 	done := e.phase("netbird_config")
@@ -1005,47 +974,12 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 		return err
 	}
 
-	// Decode the network map from either the components envelope or the
-	// legacy proto.NetworkMap before the posture-check gating below, so the
-	// "is there a network map" decision covers both wire shapes.
-	var (
-		nm         *mgmProto.NetworkMap
-		components *types.NetworkMapComponents
-	)
-	if version := update.GetVersion(); version == int32(sharedgrpc.ComponentNetworkMap) {
-		// Components-format peer: decode the envelope back to typed
-		// components, run Calculate() locally, and convert to the wire
-		// NetworkMap shape the rest of the engine consumes. Components are
-		// retained so future incremental updates can apply deltas instead
-		// of doing a full reconstruction.
-		envelope := update.GetNetworkMapEnvelope()
-		if envelope == nil {
-			return fmt.Errorf("received a SyncReponse indicating use of components network map, but components are missing")
-		}
-
-		localKey := e.config.WgPrivateKey.PublicKey().String()
-		dnsName := ""
-		if pc := update.GetPeerConfig(); pc != nil {
-			// PeerConfig.Fqdn = "<dns_label>.<dns_domain>" — extract the
-			// shared domain by stripping the peer's own label prefix. Falls
-			// back to empty if the FQDN doesn't have the expected shape.
-			dnsName = extractDNSDomainFromFQDN(pc.GetFqdn())
-		}
-		result, err := nbnetworkmap.EnvelopeToNetworkMap(e.ctx, envelope, localKey, dnsName)
-		if err != nil {
-			return fmt.Errorf("decode network map envelope: %w", err)
-		}
-		nm = result.NetworkMap
-		components = result.Components
-	} else {
-		nm = update.GetNetworkMap()
-	}
-
 	// Posture checks are bound to the network map presence:
 	//   NetworkMap != nil, checks present -> apply the received checks
 	//   NetworkMap != nil, checks nil     -> posture checks were removed, clear them
 	//   NetworkMap == nil                 -> config-only update (e.g. relay token rotation),
 	//                                        leave the previously applied checks untouched
+	nm := update.GetNetworkMap()
 	if nm == nil {
 		return nil
 	}
@@ -1058,14 +992,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	}
 
 	done = e.phase("persist")
-	// Only retain the components view when the server sent the envelope
-	// path. A legacy proto.NetworkMap means components == nil; writing it
-	// here would clobber a previously-cached snapshot, breaking the
-	// incremental-delta base on a future envelope sync.
-	if components != nil {
-		e.latestComponents = components
-	}
-
 	e.persistSyncResponse(update)
 	done()
 
@@ -1079,19 +1005,6 @@ func (e *Engine) handleSync(update *mgmProto.SyncResponse) error {
 	return nil
 }
 
-// extractDNSDomainFromFQDN returns the trailing dotted domain part of the
-// receiving peer's FQDN — the same value the management server fills as
-// dnsName when it builds the legacy NetworkMap. "peer42.netbird.cloud" →
-// "netbird.cloud". An empty string is returned for unrecognized formats.
-func extractDNSDomainFromFQDN(fqdn string) string {
-	for i := 0; i < len(fqdn); i++ {
-		if fqdn[i] == '.' && i+1 < len(fqdn) {
-			return fqdn[i+1:]
-		}
-	}
-	return ""
-}
-
 // updateNetbirdConfig applies the management-provided NetBird configuration:
 // STUN/TURN and relay servers, flow logging and DNS settings. A nil config is a no-op,
 // which is the case for sync updates carrying only a network map.
@@ -1251,7 +1164,6 @@ func (e *Engine) applyInfoFlags(info *system.Info) {
 		e.config.BlockLANAccess,
 		e.config.BlockInbound,
 		e.config.DisableIPv6,
-		e.config.SyncMessageVersion,
 		e.config.EnableSSHRoot,
 		e.config.EnableSSHSFTP,
 		e.config.EnableSSHLocalPortForwarding,
@@ -2120,7 +2032,6 @@ func (e *Engine) readInitialSettings() ([]*route.Route, *nbdns.Config, bool, err
 		e.config.BlockLANAccess,
 		e.config.BlockInbound,
 		e.config.DisableIPv6,
-		e.config.SyncMessageVersion,
 		e.config.EnableSSHRoot,
 		e.config.EnableSSHSFTP,
 		e.config.EnableSSHLocalPortForwarding,

client/internal/engine_session_deadline_test.go

@@ -75,14 +75,4 @@ func TestApplySessionDeadline_ThreeState(t *testing.T) {
 		require.True(t, e.statusRecorder.GetSessionExpiresAt().IsZero(),
 			"invalid timestamp must clear the deadline")
 	})
-
-	t.Run("recently expired timestamp stays visible as expired", func(t *testing.T) {
-		e := newEngine()
-		expired := time.Now().Add(-5 * time.Minute).UTC().Truncate(time.Second)
-
-		e.ApplySessionDeadline(timestamppb.New(expired))
-
-		require.True(t, e.statusRecorder.GetSessionExpiresAt().Equal(expired),
-			"recently-expired deadline must stay on the recorder so consumers render it as expired")
-	})
 }

client/internal/ipcauth/creds_stub.go

@@ -0,0 +1,13 @@
+//go:build !linux && !darwin && !freebsd && !windows
+
+package ipcauth
+
+import "google.golang.org/grpc/credentials"
+
+// NewTransportCredentials returns nil on platforms without a peer-identity
+// primitive. The daemon falls back to insecure credentials and skips per-RPC
+// authorization (logging a warning), preserving pre-hardening behavior until
+// the transport gains an identity primitive.
+func NewTransportCredentials() credentials.TransportCredentials {
+	return nil
+}

client/internal/ipcauth/creds_unix.go

@@ -0,0 +1,48 @@
+//go:build linux || darwin || freebsd
+
+package ipcauth
+
+import (
+	"context"
+	"net"
+
+	"google.golang.org/grpc/credentials"
+)
+
+// NewTransportCredentials returns gRPC transport credentials that extract the
+// caller's kernel-authenticated identity from a Unix-socket connection and
+// expose it via IdentityFromContext. It is non-nil on platforms with a
+// peer-credential primitive.
+func NewTransportCredentials() credentials.TransportCredentials {
+	return unixCreds{}
+}
+
+// unixCreds implements credentials.TransportCredentials over a Unix socket.
+// The server side reads SO_PEERCRED/LOCAL_PEERCRED during the handshake; the
+// client side is a no-op (the kernel supplies the peer identity to the server
+// without any client cooperation).
+type unixCreds struct{}
+
+func (unixCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
+	return conn, AuthInfo{}, nil
+}
+
+// ServerHandshake extracts the peer identity and fails closed if it cannot be read.
+func (unixCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
+	id, err := PeerIdentity(conn)
+	if err != nil {
+		return nil, nil, err
+	}
+	return conn, AuthInfo{
+		CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
+		Identity:       id,
+	}, nil
+}
+
+func (unixCreds) Info() credentials.ProtocolInfo {
+	return credentials.ProtocolInfo{SecurityProtocol: "netbird-ipc-peercred"}
+}
+
+func (unixCreds) Clone() credentials.TransportCredentials { return unixCreds{} }
+
+func (unixCreds) OverrideServerName(string) error { return nil }

client/internal/ipcauth/creds_windows.go

@@ -0,0 +1,142 @@
+//go:build windows
+
+package ipcauth
+
+import (
+	"context"
+	"fmt"
+	"net"
+	"runtime"
+
+	"golang.org/x/sys/windows"
+	"google.golang.org/grpc/credentials"
+)
+
+var (
+	modadvapi32                    = windows.NewLazySystemDLL("advapi32.dll")
+	procImpersonateNamedPipeClient = modadvapi32.NewProc("ImpersonateNamedPipeClient")
+	procRevertToSelf               = modadvapi32.NewProc("RevertToSelf")
+)
+
+// Windows group-SID attribute flags (winnt.h): a group only counts toward
+// membership when it is enabled and not marked use-for-deny-only.
+const (
+	seGroupEnabled        = 0x00000004
+	seGroupUseForDenyOnly = 0x00000010
+)
+
+// DefaultPipeSDDL restricts the daemon control pipe to LocalSystem (SY), the
+// Administrators group (BA), and interactive logon users (IU). It deliberately
+// excludes Authenticated Users / Everyone so remote or arbitrary service
+// principals cannot connect. This is the Layer-1 channel gate; the interceptor
+// (Layer 2) further restricts by per-profile ownership.
+func DefaultPipeSDDL() string {
+	return "D:P(A;;GA;;;SY)(A;;GA;;;BA)(A;;GA;;;IU)"
+}
+
+// NewTransportCredentials returns gRPC transport credentials that derive the
+// caller's identity from the named-pipe client token, following Microsoft's
+// "Verifying Client Access with ACLs" pattern: ImpersonateNamedPipeClient ->
+// OpenThreadToken -> RevertToSelf. Per threat-model M-NOIMP, impersonation is
+// used only to read the client token for identity, never to perform privileged work.
+func NewTransportCredentials() credentials.TransportCredentials {
+	return winpipeCreds{}
+}
+
+type winpipeCreds struct{}
+
+func (winpipeCreds) ClientHandshake(_ context.Context, _ string, conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
+	return conn, AuthInfo{}, nil
+}
+
+// ServerHandshake extracts the connecting client's identity from the pipe token.
+// Fails closed if the handle or token cannot be read.
+func (winpipeCreds) ServerHandshake(conn net.Conn) (net.Conn, credentials.AuthInfo, error) {
+	// go-winio's pipe connection embeds *win32File, which exposes Fd().
+	fdConn, ok := conn.(interface{ Fd() uintptr })
+	if !ok {
+		return nil, nil, fmt.Errorf("connection %T does not expose a pipe handle", conn)
+	}
+	handle := windows.Handle(fdConn.Fd())
+
+	id, err := pipeClientIdentity(handle)
+	if err != nil {
+		return nil, nil, err
+	}
+	return conn, AuthInfo{
+		CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
+		Identity:       id,
+	}, nil
+}
+
+func (winpipeCreds) Info() credentials.ProtocolInfo {
+	return credentials.ProtocolInfo{SecurityProtocol: "netbird-ipc-peercred"}
+}
+
+func (winpipeCreds) Clone() credentials.TransportCredentials { return winpipeCreds{} }
+
+func (winpipeCreds) OverrideServerName(string) error { return nil }
+
+// pipeClientIdentity reads the connecting client's user SID and enabled group
+// SIDs from the named-pipe handle. The impersonation window is kept as small as
+// possible and pinned to the OS thread (impersonation is thread-local).
+func pipeClientIdentity(handle windows.Handle) (Identity, error) {
+	var pid uint32
+	hasPID := windows.GetNamedPipeClientProcessId(handle, &pid) == nil
+
+	runtime.LockOSThread()
+	defer runtime.UnlockOSThread()
+
+	if err := impersonateNamedPipeClient(handle); err != nil {
+		return Identity{}, fmt.Errorf("impersonate named pipe client: %w", err)
+	}
+	defer func() { _ = revertToSelf() }()
+
+	// openAsSelf=true: the token is opened using the daemon's process context
+	// (LocalSystem), not the impersonated client's, so the open always succeeds.
+	var token windows.Token
+	if err := windows.OpenThreadToken(windows.CurrentThread(), windows.TOKEN_QUERY, true, &token); err != nil {
+		return Identity{}, fmt.Errorf("open thread token: %w", err)
+	}
+	defer token.Close()
+
+	tu, err := token.GetTokenUser()
+	if err != nil {
+		return Identity{}, fmt.Errorf("get token user: %w", err)
+	}
+
+	tg, err := token.GetTokenGroups()
+	if err != nil {
+		return Identity{}, fmt.Errorf("get token groups: %w", err)
+	}
+	var groups []string
+	for _, g := range tg.AllGroups() {
+		if g.Attributes&seGroupEnabled == 0 || g.Attributes&seGroupUseForDenyOnly != 0 {
+			continue
+		}
+		groups = append(groups, g.Sid.String())
+	}
+
+	return Identity{
+		SID:    tu.User.Sid.String(),
+		Groups: groups,
+		PID:    int32(pid),
+		HasPID: hasPID,
+	}, nil
+}
+
+func impersonateNamedPipeClient(h windows.Handle) error {
+	r, _, e := procImpersonateNamedPipeClient.Call(uintptr(h))
+	if r == 0 {
+		return e
+	}
+	return nil
+}
+
+func revertToSelf() error {
+	r, _, e := procRevertToSelf.Call()
+	if r == 0 {
+		return e
+	}
+	return nil
+}

client/internal/ipcauth/identity.go

@@ -0,0 +1,93 @@
+// Package ipcauth provides kernel-authenticated caller identity for the daemon's
+// local IPC (gRPC) channel and the transport credentials that populate it.
+//
+// It is the identity foundation shared by two layers of the local-IPC hardening:
+//   - the socket-permission layer (Layer 1, client/cmd), which reads the peer
+//     identity to gate who may connect and to run trust-on-first-use; and
+//   - the per-RPC authorization interceptor (Layer 2), which reads the same
+//     identity from the gRPC context to enforce per-profile ownership.
+//
+// On Unix the identity is read from the kernel via SO_PEERCRED (Linux) or
+// LOCAL_PEERCRED (Darwin/FreeBSD). On Windows it is derived from the named-pipe
+// client token. Platforms without a peer-identity primitive get no credentials
+// and therefore no enforcement (the daemon logs a warning and stays open,
+// preserving today's behavior until the transport is hardened).
+package ipcauth
+
+import (
+	"context"
+	"fmt"
+
+	"google.golang.org/grpc/credentials"
+	"google.golang.org/grpc/peer"
+)
+
+// Identity is the kernel-authenticated identity of a local IPC caller.
+//
+// The zero value is not a valid identity; callers obtain one via
+// IdentityFromContext (which reports presence) or PeerIdentity.
+type Identity struct {
+	// UID and GID are the caller's Unix user ID and primary group ID.
+	// Zero on Windows, where SID is authoritative instead.
+	UID uint32
+	GID uint32
+
+	// PID is the caller's process ID, for audit only. HasPID is false when the
+	// platform cannot supply it (e.g. Darwin/FreeBSD xucred carries no PID).
+	PID    int32
+	HasPID bool
+
+	// SID is the caller's Windows security identifier (empty on Unix).
+	SID string
+
+	// Groups holds the caller's Windows group SIDs, captured from the client
+	// token at handshake time (empty on Unix, where supplementary group
+	// membership is resolved on demand via NSS/getent by the authorizer).
+	Groups []string
+}
+
+// IsWindows reports whether this identity is a Windows principal (SID-based)
+// rather than a Unix uid/gid principal.
+func (i Identity) IsWindows() bool {
+	return i.SID != ""
+}
+
+// String renders the identity for audit logs.
+func (i Identity) String() string {
+	if i.IsWindows() {
+		if i.HasPID {
+			return fmt.Sprintf("sid=%s pid=%d", i.SID, i.PID)
+		}
+		return fmt.Sprintf("sid=%s", i.SID)
+	}
+	if i.HasPID {
+		return fmt.Sprintf("uid=%d gid=%d pid=%d", i.UID, i.GID, i.PID)
+	}
+	return fmt.Sprintf("uid=%d gid=%d", i.UID, i.GID)
+}
+
+// AuthInfo carries the peer Identity as a gRPC credentials.AuthInfo so the
+// interceptor can retrieve it from the request context via IdentityFromContext.
+type AuthInfo struct {
+	credentials.CommonAuthInfo
+	Identity Identity
+}
+
+// AuthType identifies the authentication scheme.
+func (AuthInfo) AuthType() string { return "netbird-ipc-peercred" }
+
+// IdentityFromContext extracts the caller's kernel-authenticated identity from
+// the gRPC peer context. The second return value is false when no IPC transport
+// credentials were negotiated (e.g. an unsupported platform, or a caller that
+// did not come through the daemon socket) — callers MUST fail closed in that case.
+func IdentityFromContext(ctx context.Context) (Identity, bool) {
+	p, ok := peer.FromContext(ctx)
+	if !ok {
+		return Identity{}, false
+	}
+	info, ok := p.AuthInfo.(AuthInfo)
+	if !ok {
+		return Identity{}, false
+	}
+	return info.Identity, true
+}

client/internal/ipcauth/identity_test.go

@@ -0,0 +1,47 @@
+package ipcauth
+
+import (
+	"context"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"google.golang.org/grpc/credentials"
+	"google.golang.org/grpc/peer"
+)
+
+func TestIdentityFromContext_NoPeer(t *testing.T) {
+	_, ok := IdentityFromContext(context.Background())
+	assert.False(t, ok, "bare context must report no identity (fail closed)")
+}
+
+func TestIdentityFromContext_WrongAuthInfo(t *testing.T) {
+	ctx := peer.NewContext(context.Background(), &peer.Peer{})
+	_, ok := IdentityFromContext(ctx)
+	assert.False(t, ok, "peer without our AuthInfo must report no identity")
+}
+
+func TestIdentityFromContext_Present(t *testing.T) {
+	want := Identity{UID: 1000, GID: 1000, PID: 4242, HasPID: true}
+	ctx := peer.NewContext(context.Background(), &peer.Peer{
+		AuthInfo: AuthInfo{
+			CommonAuthInfo: credentials.CommonAuthInfo{SecurityLevel: credentials.NoSecurity},
+			Identity:       want,
+		},
+	})
+
+	got, ok := IdentityFromContext(ctx)
+	assert.True(t, ok)
+	assert.Equal(t, want, got)
+}
+
+func TestIdentity_String(t *testing.T) {
+	assert.Equal(t, "uid=1000 gid=1000 pid=42", Identity{UID: 1000, GID: 1000, PID: 42, HasPID: true}.String())
+	assert.Equal(t, "uid=1000 gid=1000", Identity{UID: 1000, GID: 1000}.String())
+	assert.Equal(t, "sid=S-1-5-21-1 pid=42", Identity{SID: "S-1-5-21-1", PID: 42, HasPID: true}.String())
+	assert.Equal(t, "sid=S-1-5-21-1", Identity{SID: "S-1-5-21-1"}.String())
+}
+
+func TestIdentity_IsWindows(t *testing.T) {
+	assert.True(t, Identity{SID: "S-1-5-18"}.IsWindows())
+	assert.False(t, Identity{UID: 0}.IsWindows())
+}

client/internal/ipcauth/peercred_bsd.go

@@ -0,0 +1,43 @@
+//go:build darwin || freebsd
+
+package ipcauth
+
+import (
+	"fmt"
+	"net"
+
+	"golang.org/x/sys/unix"
+)
+
+// PeerIdentity reads the kernel-authenticated identity of the process on the
+// other end of a Unix socket connection via LOCAL_PEERCRED (xucred). xucred
+// carries the uid and group list but no pid, so audit on these platforms is
+// uid/gid-based (HasPID is false); PID via LOCAL_PEERPID is a possible follow-up.
+func PeerIdentity(c net.Conn) (Identity, error) {
+	uc, ok := c.(*net.UnixConn)
+	if !ok {
+		return Identity{}, fmt.Errorf("connection is not a unix socket: %T", c)
+	}
+	raw, err := uc.SyscallConn()
+	if err != nil {
+		return Identity{}, fmt.Errorf("raw conn: %w", err)
+	}
+
+	var cred *unix.Xucred
+	var credErr error
+	if err := raw.Control(func(fd uintptr) {
+		cred, credErr = unix.GetsockoptXucred(int(fd), unix.SOL_LOCAL, unix.LOCAL_PEERCRED)
+	}); err != nil {
+		return Identity{}, fmt.Errorf("getsockopt control: %w", err)
+	}
+	if credErr != nil {
+		return Identity{}, fmt.Errorf("LOCAL_PEERCRED: %w", credErr)
+	}
+
+	id := Identity{UID: cred.Uid}
+	// Groups[0] is the effective (primary) GID; guard against an empty list.
+	if cred.Ngroups > 0 {
+		id.GID = cred.Groups[0]
+	}
+	return id, nil
+}

client/internal/ipcauth/peercred_linux.go

@@ -0,0 +1,43 @@
+//go:build linux
+
+package ipcauth
+
+import (
+	"fmt"
+	"net"
+
+	"golang.org/x/sys/unix"
+)
+
+// PeerIdentity reads the kernel-authenticated identity of the process on the
+// other end of a Unix socket connection via SO_PEERCRED. The credentials are
+// captured by the kernel at connect() time and cannot be spoofed or changed for
+// the life of the connection.
+func PeerIdentity(c net.Conn) (Identity, error) {
+	uc, ok := c.(*net.UnixConn)
+	if !ok {
+		return Identity{}, fmt.Errorf("connection is not a unix socket: %T", c)
+	}
+	raw, err := uc.SyscallConn()
+	if err != nil {
+		return Identity{}, fmt.Errorf("raw conn: %w", err)
+	}
+
+	var cred *unix.Ucred
+	var credErr error
+	if err := raw.Control(func(fd uintptr) {
+		cred, credErr = unix.GetsockoptUcred(int(fd), unix.SOL_SOCKET, unix.SO_PEERCRED)
+	}); err != nil {
+		return Identity{}, fmt.Errorf("getsockopt control: %w", err)
+	}
+	if credErr != nil {
+		return Identity{}, fmt.Errorf("SO_PEERCRED: %w", credErr)
+	}
+
+	return Identity{
+		UID:    cred.Uid,
+		GID:    cred.Gid,
+		PID:    cred.Pid,
+		HasPID: true,
+	}, nil
+}

client/internal/ipcauth/peercred_stub.go

@@ -0,0 +1,16 @@
+//go:build !linux && !darwin && !freebsd
+
+package ipcauth
+
+import (
+	"fmt"
+	"net"
+	"runtime"
+)
+
+// PeerIdentity is unimplemented on platforms without a Unix-socket peer-credential
+// primitive. Windows derives identity from the named-pipe client token instead
+// (see the Windows transport credentials), so it never calls this.
+func PeerIdentity(net.Conn) (Identity, error) {
+	return Identity{}, fmt.Errorf("peer credential check not supported on %s", runtime.GOOS)
+}

client/internal/ipcauth/peercred_unix_test.go

@@ -0,0 +1,113 @@
+//go:build linux || darwin || freebsd
+
+package ipcauth
+
+import (
+	"net"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// TestPeerIdentity_MatchesCurrentProcess connects to a real Unix socket and
+// verifies the extracted UID/GID match the running process (both ends are us).
+func TestPeerIdentity_MatchesCurrentProcess(t *testing.T) {
+	sock := filepath.Join(t.TempDir(), "peer.sock")
+	ln, err := net.Listen("unix", sock)
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = ln.Close() })
+
+	type result struct {
+		id  Identity
+		err error
+	}
+	done := make(chan result, 1)
+	go func() {
+		c, aerr := ln.Accept()
+		if aerr != nil {
+			done <- result{err: aerr}
+			return
+		}
+		defer func() { _ = c.Close() }()
+		id, ierr := PeerIdentity(c)
+		done <- result{id: id, err: ierr}
+	}()
+
+	client, err := net.Dial("unix", sock)
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	res := <-done
+	require.NoError(t, res.err)
+	assert.Equal(t, uint32(os.Getuid()), res.id.UID, "UID should match current process")
+	assert.Equal(t, uint32(os.Getgid()), res.id.GID, "primary GID should match current process")
+}
+
+// TestPeerIdentity_NonUnixConn rejects non-Unix connections (fail closed).
+func TestPeerIdentity_NonUnixConn(t *testing.T) {
+	ln, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = ln.Close() })
+
+	done := make(chan error, 1)
+	go func() {
+		c, aerr := ln.Accept()
+		if aerr != nil {
+			done <- aerr
+			return
+		}
+		defer func() { _ = c.Close() }()
+		_, ierr := PeerIdentity(c)
+		done <- ierr
+	}()
+
+	client, err := net.Dial("tcp", ln.Addr().String())
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	assert.Error(t, <-done, "PeerIdentity must reject a non-Unix connection")
+}
+
+// TestUnixCreds_ServerHandshake exercises the transport-credentials path end to end.
+func TestUnixCreds_ServerHandshake(t *testing.T) {
+	creds := NewTransportCredentials()
+	require.NotNil(t, creds)
+
+	sock := filepath.Join(t.TempDir(), "hs.sock")
+	ln, err := net.Listen("unix", sock)
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = ln.Close() })
+
+	type result struct {
+		info interface{ AuthType() string }
+		err  error
+	}
+	done := make(chan result, 1)
+	go func() {
+		c, aerr := ln.Accept()
+		if aerr != nil {
+			done <- result{err: aerr}
+			return
+		}
+		_, ai, herr := creds.ServerHandshake(c)
+		if herr != nil {
+			done <- result{err: herr}
+			return
+		}
+		done <- result{info: ai}
+	}()
+
+	client, err := net.Dial("unix", sock)
+	require.NoError(t, err)
+	t.Cleanup(func() { _ = client.Close() })
+
+	res := <-done
+	require.NoError(t, res.err)
+	ai, ok := res.info.(AuthInfo)
+	require.True(t, ok, "expected ipcauth.AuthInfo, got %T", res.info)
+	assert.Equal(t, uint32(os.Getuid()), ai.Identity.UID)
+	assert.Equal(t, "netbird-ipc-peercred", ai.AuthType())
+}

client/internal/lazyconn/manager/manager.go

@@ -29,11 +29,6 @@ type managedPeer struct {
 
 type Config struct {
 	InactivityThreshold *time.Duration
-	// ReconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is
-	// armed. The activity listener creates the wake peer with the overlay /32 only; without the
-	// routed prefixes WireGuard would not steer subnet-bound traffic to the wake endpoint, so an
-	// idle routing peer could never be woken by that traffic. Optional; nil disables the reconcile.
-	ReconcileAllowedIPs func(peerKey string) error
 }
 
 // Manager manages lazy connections
@@ -61,9 +56,6 @@ type Manager struct {
 	peerToHAGroups map[string][]route.HAUniqueID // peer ID -> HA groups they belong to
 	haGroupToPeers map[route.HAUniqueID][]string // HA group -> peer IDs in the group
 	routesMu       sync.RWMutex
-
-	// reconcileAllowedIPs re-applies a peer's routed allowed IPs after its wake endpoint is armed.
-	reconcileAllowedIPs func(peerKey string) error
 }
 
 // NewManager creates a new lazy connection manager
@@ -81,7 +73,6 @@ func NewManager(config Config, engineCtx context.Context, peerStore *peerstore.S
 		activityManager:      activity.NewManager(wgIface),
 		peerToHAGroups:       make(map[string][]route.HAUniqueID),
 		haGroupToPeers:       make(map[route.HAUniqueID][]string),
-		reconcileAllowedIPs:  config.ReconcileAllowedIPs,
 	}
 
 	if wgIface.IsUserspaceBind() {
@@ -210,7 +201,7 @@ func (m *Manager) AddPeer(peerCfg lazyconn.PeerConfig) (bool, error) {
 		return false, nil
 	}
 
-	if err := m.armActivityListener(peerCfg); err != nil {
+	if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
 		return false, err
 	}
 
@@ -297,7 +288,7 @@ func (m *Manager) DeactivatePeer(peerID peerid.ConnID) {
 
 	m.inactivityManager.RemovePeer(mp.peerCfg.PublicKey)
 
-	if err := m.armActivityListener(*mp.peerCfg); err != nil {
+	if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
 		mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
 		return
 	}
@@ -474,31 +465,6 @@ func (m *Manager) close() {
 }
 
 // shouldDeferIdleForHA checks if peer should stay connected due to HA group requirements
-// armRoutedAllowedIPs re-applies the peer's routed allowed IPs onto its freshly armed wake
-// endpoint. The activity listener creates the wake peer with the overlay /32 only, so without
-// this the routed prefixes would be missing and traffic to a routed subnet could not wake the
-// idle routing peer. It is a no-op when no reconciler is configured.
-// armActivityListener (re)arms the peer's wake endpoint via the activity manager and then
-// re-applies its routed allowed IPs, so traffic to a routed subnet can wake an idle routing
-// peer. The routed prefixes must be re-applied after the wake endpoint exists because the
-// listener creates it with the overlay /32 only.
-func (m *Manager) armActivityListener(peerCfg lazyconn.PeerConfig) error {
-	if err := m.activityManager.MonitorPeerActivity(peerCfg); err != nil {
-		return err
-	}
-	m.armRoutedAllowedIPs(&peerCfg)
-	return nil
-}
-
-func (m *Manager) armRoutedAllowedIPs(peerCfg *lazyconn.PeerConfig) {
-	if m.reconcileAllowedIPs == nil {
-		return
-	}
-	if err := m.reconcileAllowedIPs(peerCfg.PublicKey); err != nil {
-		peerCfg.Log.Errorf("failed to reconcile routed allowed IPs on wake endpoint: %v", err)
-	}
-}
-
 func (m *Manager) shouldDeferIdleForHA(inactivePeers map[string]struct{}, peerID string) bool {
 	m.routesMu.RLock()
 	defer m.routesMu.RUnlock()
@@ -611,7 +577,7 @@ func (m *Manager) onPeerInactivityTimedOut(peerIDs map[string]struct{}) {
 
 		mp.peerCfg.Log.Infof("start activity monitor")
 
-		if err := m.armActivityListener(*mp.peerCfg); err != nil {
+		if err := m.activityManager.MonitorPeerActivity(*mp.peerCfg); err != nil {
 			mp.peerCfg.Log.Errorf("failed to create activity monitor: %v", err)
 			continue
 		}

client/internal/mobile_dependency.go

@@ -11,14 +11,12 @@ import (
 
 // MobileDependency collect all dependencies for mobile platform
 type MobileDependency struct {
-	// Android and iOS
-	NetworkChangeListener listener.NetworkChangeListener
-
 	// Android only
-	TunAdapter       device.TunAdapter
-	IFaceDiscover    stdnet.ExternalIFaceDiscover
-	HostDNSAddresses []netip.AddrPort
-	DnsReadyListener dns.ReadyListener
+	TunAdapter            device.TunAdapter
+	IFaceDiscover         stdnet.ExternalIFaceDiscover
+	NetworkChangeListener listener.NetworkChangeListener
+	HostDNSAddresses      []netip.AddrPort
+	DnsReadyListener      dns.ReadyListener
 
 	//	iOS only
 	DnsManager     dns.IosDnsManager

client/internal/peer/status.go

@@ -813,14 +813,19 @@ func (d *Status) SetSessionExpiresAt(deadline time.Time) {
 }
 
 // GetSessionExpiresAt returns the most recently recorded SSO session deadline,
-// or the zero value when no deadline is tracked. A deadline in the past is
-// returned as-is: it means the session has expired, and consumers (tray row,
-// CLI status) render it as "expired" rather than hiding it — masking it as
-// "none" would blank the UI at the exact moment it should say the session
-// ended.
+// or the zero value when no deadline is tracked. A deadline that has already
+// slipped into the past reports as "none": once the session has expired it is
+// no longer a meaningful countdown, and the sessionwatch.Watcher does not
+// arm a timer at the deadline itself to clear it (only the two pre-expiry
+// warnings). Without this guard the UI would keep painting a stale
+// "expires in …" against a moment that has passed until the next login,
+// extend, or teardown rewrote the value.
 func (d *Status) GetSessionExpiresAt() time.Time {
 	d.mux.Lock()
 	defer d.mux.Unlock()
+	if !d.sessionExpiresAt.IsZero() && d.sessionExpiresAt.Before(time.Now()) {
+		return time.Time{}
+	}
 	return d.sessionExpiresAt
 }
 

client/internal/profilemanager/config.go

@@ -96,7 +96,6 @@ type ConfigInput struct {
 	BlockLANAccess      *bool
 	BlockInbound        *bool
 	DisableIPv6         *bool
-	SyncMessageVersion  *int
 
 	DisableNotifications *bool
 
@@ -138,7 +137,6 @@ type Config struct {
 	BlockLANAccess      bool
 	BlockInbound        bool
 	DisableIPv6         bool
-	SyncMessageVersion  *int
 
 	DisableNotifications *bool
 
@@ -589,12 +587,6 @@ func (config *Config) apply(input ConfigInput) (updated bool, err error) {
 		updated = true
 	}
 
-	if input.SyncMessageVersion != nil && *input.SyncMessageVersion != *config.SyncMessageVersion {
-		log.Infof("setting SyncMessageVersion to %v", *input.SyncMessageVersion)
-		*config.SyncMessageVersion = *input.SyncMessageVersion
-		updated = true
-	}
-
 	if input.DisableNotifications != nil && (config.DisableNotifications == nil || *input.DisableNotifications != *config.DisableNotifications) {
 		if *input.DisableNotifications {
 			log.Infof("disabling notifications")

client/internal/routemanager/dnsinterceptor/handler.go

@@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error {
 
 			// AllowedIPs should use real IPs
 			if d.currentPeerKey != "" {
-				if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+				if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 					merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 				}
 			}
@@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error {
 	}
 
 	// AllowedIPs use real IPs
-	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil {
+	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil {
 		return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err)
 	}
 
@@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
 	for _, prefixes := range d.interceptedDomains {
 		for _, prefix := range prefixes {
 			// AllowedIPs use real IPs
-			if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+			if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 			}
 		}

client/internal/routemanager/dynamic/route.go

@@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error {
 	var merr *multierror.Error
 	for _, domainPrefixes := range r.dynamicDomains {
 		for _, prefix := range domainPrefixes {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -185,7 +185,7 @@ func (r *Route) startResolver(ctx context.Context) {
 }
 
 func (r *Route) update(ctx context.Context) error {
-	resolved, err := r.resolveDomains(ctx)
+	resolved, err := r.resolveDomains()
 	if err != nil {
 		if len(resolved) == 0 {
 			return fmt.Errorf("resolve domains: %w", err)
@@ -199,9 +199,9 @@ func (r *Route) update(ctx context.Context) error {
 	return nil
 }
 
-func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
+func (r *Route) resolveDomains() (domainMap, error) {
 	results := make(chan resolveResult)
-	go r.resolve(ctx, results)
+	go r.resolve(results)
 
 	resolved := domainMap{}
 	var merr *multierror.Error
@@ -217,7 +217,7 @@ func (r *Route) resolveDomains(ctx context.Context) (domainMap, error) {
 	return resolved, nberrors.FormatErrorOrNil(merr)
 }
 
-func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
+func (r *Route) resolve(results chan resolveResult) {
 	var wg sync.WaitGroup
 
 	for _, d := range r.route.Domains {
@@ -225,10 +225,10 @@ func (r *Route) resolve(ctx context.Context, results chan resolveResult) {
 		go func(domain domain.Domain) {
 			defer wg.Done()
 
-			ips, err := r.getIPsFromResolver(ctx, domain)
+			ips, err := r.getIPsFromResolver(domain)
 			if err != nil {
 				log.Tracef("Failed to resolve domain %s with private resolver: %v", domain.SafeString(), err)
-				ips, err = lookupHostIPs(ctx, domain)
+				ips, err = net.LookupIP(domain.PunycodeString())
 				if err != nil {
 					results <- resolveResult{domain: domain, err: fmt.Errorf("resolve d %s: %w", domain.SafeString(), err)}
 					return
@@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) {
 			merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err))
 		}
 		if r.currentPeerKey != "" {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -364,20 +364,6 @@ func determinePrefixChanges(oldPrefixes, newPrefixes []netip.Prefix) (toAdd, toR
 	return
 }
 
-// lookupHostIPs resolves d via the system resolver, honoring ctx cancellation.
-func lookupHostIPs(ctx context.Context, d domain.Domain) ([]net.IP, error) {
-	addrs, err := net.DefaultResolver.LookupIPAddr(ctx, d.PunycodeString())
-	if err != nil {
-		return nil, err
-	}
-
-	ips := make([]net.IP, 0, len(addrs))
-	for _, addr := range addrs {
-		ips = append(ips, addr.IP)
-	}
-	return ips, nil
-}
-
 func combinePrefixes(oldPrefixes, removedPrefixes, addedPrefixes []netip.Prefix) []netip.Prefix {
 	prefixSet := make(map[netip.Prefix]struct{})
 	for _, prefix := range oldPrefixes {

client/internal/routemanager/dynamic/route_generic.go

@@ -3,12 +3,11 @@
 package dynamic
 
 import (
-	"context"
 	"net"
 
 	"github.com/netbirdio/netbird/shared/management/domain"
 )
 
-func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
-	return lookupHostIPs(ctx, domain)
+func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
+	return net.LookupIP(domain.PunycodeString())
 }

client/internal/routemanager/dynamic/route_ios.go

@@ -3,7 +3,6 @@
 package dynamic
 
 import (
-	"context"
 	"fmt"
 	"net"
 	"time"
@@ -17,7 +16,7 @@ import (
 
 const dialTimeout = 10 * time.Second
 
-func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([]net.IP, error) {
+func (r *Route) getIPsFromResolver(domain domain.Domain) ([]net.IP, error) {
 	privateClient, err := nbdns.GetClientPrivate(r.wgInterface, r.resolverAddr.Addr(), dialTimeout)
 	if err != nil {
 		return nil, fmt.Errorf("error while creating private client: %s", err)
@@ -33,7 +32,7 @@ func (r *Route) getIPsFromResolver(ctx context.Context, domain domain.Domain) ([
 		msg := new(dns.Msg)
 		msg.SetQuestion(fqdn, qtype)
 
-		response, _, err := nbdns.ExchangeWithFallback(ctx, privateClient, msg, r.resolverAddr.String())
+		response, _, err := nbdns.ExchangeWithFallback(nil, privateClient, msg, r.resolverAddr.String())
 		if err != nil {
 			if queryErr == nil {
 				queryErr = fmt.Errorf("DNS query for %s (type %d) after %s: %w", domain.SafeString(), qtype, time.Since(startTime), err)

client/internal/routemanager/manager.go

@@ -52,10 +52,6 @@ type Manager interface {
 	UpdateRoutes(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	TriggerSelection(route.HAMap)
-	SelectRoutes(ids []route.NetID, appendRoute bool) error
-	DeselectRoutes(ids []route.NetID) error
-	SelectAllRoutes()
-	DeselectAllRoutes()
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
@@ -65,7 +61,6 @@ type Manager interface {
 	InitialRouteRange() []string
 	SetFirewall(firewall.Manager) error
 	SetDNSForwarderPort(port uint16)
-	ReconcilePeerAllowedIPs(peerKey string) error
 	Stop(stateManager *statemanager.Manager)
 }
 
@@ -220,7 +215,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 		)
 	}
 
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New(
 		func(prefix netip.Prefix, peerKey string) (string, error) {
 			// save peerKey to use it in the remove function
 			return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix)
@@ -237,30 +232,6 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 	)
 }
 
-// ReconcilePeerAllowedIPs re-applies every routed allowed IP currently tracked for the peer
-// onto the WireGuard device. The allowed-IP refcounter only calls its AddFunc (which pushes to
-// the device) on a prefix's 0->1 transition, so a peer whose device entry was rebuilt without a
-// matching refcounter change — e.g. a lazy connection cycling through idle->wake, which recreates
-// the WireGuard peer with the overlay /32 only — ends up missing routed prefixes the refcounter
-// still considers installed, and nothing retries. Calling this when the peer's WireGuard entry is
-// (re)created restores convergence. It is add-only and idempotent: AddAllowedIP is update-only, so
-// prefixes are re-added to an existing peer and an absent peer is left untouched.
-func (m *DefaultManager) ReconcilePeerAllowedIPs(peerKey string) error {
-	if m.allowedIPsRefCounter == nil {
-		return nil
-	}
-
-	return m.allowedIPsRefCounter.ReapplyMatching(
-		func(out string) bool { return out == peerKey },
-		func(prefix netip.Prefix) error {
-			if err := m.wgInterface.AddAllowedIP(peerKey, prefix); err != nil {
-				return fmt.Errorf("add allowed IP %s for peer %s: %w", prefix, peerKey, err)
-			}
-			return nil
-		},
-	)
-}
-
 // Init sets up the routing
 func (m *DefaultManager) Init() error {
 	m.routeSelector = m.initSelector()
@@ -804,7 +775,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	var info exitNodeInfo
 
 	for haID, routes := range clientRoutes {
-		if !isExitNodeRoutes(routes) {
+		if !m.isExitNodeRoute(routes) {
 			continue
 		}
 
@@ -824,6 +795,13 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	return info
 }
 
+func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
+}
+
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {
 	if m.routeSelector.IsSelected(netID) {
 		info.userSelected = append(info.userSelected, netID)

client/internal/routemanager/mock.go

@@ -16,8 +16,6 @@ type MockManager struct {
 	ClassifyRoutesFunc           func(routes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	UpdateRoutesFunc             func(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	TriggerSelectionFunc         func(haMap route.HAMap)
-	SelectRoutesFunc             func(ids []route.NetID, appendRoute bool) error
-	DeselectRoutesFunc           func(ids []route.NetID) error
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
 	GetSelectedClientRoutesFunc  func() route.HAMap
@@ -57,30 +55,6 @@ func (m *MockManager) TriggerSelection(networks route.HAMap) {
 	}
 }
 
-// SelectRoutes mock implementation of SelectRoutes from Manager interface
-func (m *MockManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if m.SelectRoutesFunc != nil {
-		return m.SelectRoutesFunc(ids, appendRoute)
-	}
-	return nil
-}
-
-// DeselectRoutes mock implementation of DeselectRoutes from Manager interface
-func (m *MockManager) DeselectRoutes(ids []route.NetID) error {
-	if m.DeselectRoutesFunc != nil {
-		return m.DeselectRoutesFunc(ids)
-	}
-	return nil
-}
-
-// SelectAllRoutes mock implementation of SelectAllRoutes from Manager interface
-func (m *MockManager) SelectAllRoutes() {
-}
-
-// DeselectAllRoutes mock implementation of DeselectAllRoutes from Manager interface
-func (m *MockManager) DeselectAllRoutes() {
-}
-
 // GetRouteSelector mock implementation of GetRouteSelector from Manager interface
 func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector {
 	if m.GetRouteSelectorFunc != nil {
@@ -138,11 +112,6 @@ func (m *MockManager) SetFirewall(firewall.Manager) error {
 func (m *MockManager) SetDNSForwarderPort(port uint16) {
 }
 
-// ReconcilePeerAllowedIPs mock implementation of ReconcilePeerAllowedIPs from Manager interface
-func (m *MockManager) ReconcilePeerAllowedIPs(peerKey string) error {
-	return nil
-}
-
 // Stop mock implementation of Stop from Manager interface
 func (m *MockManager) Stop(stateManager *statemanager.Manager) {
 	if m.StopFunc != nil {

client/internal/routemanager/notifier/notifier_ios.go

@@ -3,6 +3,7 @@
 package notifier
 
 import (
+	"container/list"
 	"net/netip"
 	"slices"
 	"sort"
@@ -15,12 +16,20 @@ import (
 
 type Notifier struct {
 	mu              sync.Mutex
+	cond            *sync.Cond
 	currentPrefixes []string
 	listener        listener.NetworkChangeListener
+	queue           *list.List
+	closed          bool
 }
 
 func NewNotifier() *Notifier {
-	return &Notifier{}
+	n := &Notifier{
+		queue: list.New(),
+	}
+	n.cond = sync.NewCond(&n.mu)
+	go n.deliverLoop()
+	return n
 }
 
 func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
@@ -50,19 +59,44 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
 	sort.Strings(newNets)
 
 	n.mu.Lock()
-	defer n.mu.Unlock()
 	if slices.Equal(n.currentPrefixes, newNets) {
+		n.mu.Unlock()
 		return
 	}
 	n.currentPrefixes = newNets
-	if n.listener != nil {
-		n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ","))
-	}
+	routes := strings.Join(n.currentPrefixes, ",")
+	n.queue.PushBack(routes)
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) Close() {
+	n.mu.Lock()
+	n.closed = true
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) GetInitialRouteRanges() []string {
 	return nil
 }
+
+func (n *Notifier) deliverLoop() {
+	for {
+		n.mu.Lock()
+		for n.queue.Len() == 0 && !n.closed {
+			n.cond.Wait()
+		}
+		if n.closed && n.queue.Len() == 0 {
+			n.mu.Unlock()
+			return
+		}
+		routes := n.queue.Remove(n.queue.Front()).(string)
+		l := n.listener
+		n.mu.Unlock()
+
+		if l != nil {
+			l.OnNetworkChanged(routes)
+		}
+	}
+}

client/internal/routemanager/reconcile_test.go

@@ -1,90 +0,0 @@
-//go:build !windows
-
-package routemanager
-
-import (
-	"net"
-	"net/netip"
-	"sync"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"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/routemanager/refcounter"
-)
-
-// reconcileWGMock is a minimal iface.WGIface that only records AddAllowedIP calls; every other
-// method is an inert stub because ReconcilePeerAllowedIPs exercises none of them.
-type reconcileWGMock struct {
-	mu   sync.Mutex
-	adds map[string][]netip.Prefix
-}
-
-func (m *reconcileWGMock) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
-	m.mu.Lock()
-	defer m.mu.Unlock()
-	if m.adds == nil {
-		m.adds = map[string][]netip.Prefix{}
-	}
-	m.adds[peerKey] = append(m.adds[peerKey], allowedIP)
-	return nil
-}
-
-func (m *reconcileWGMock) added(peerKey string) []netip.Prefix {
-	m.mu.Lock()
-	defer m.mu.Unlock()
-	return m.adds[peerKey]
-}
-
-func (m *reconcileWGMock) RemoveAllowedIP(string, netip.Prefix) error { return nil }
-func (m *reconcileWGMock) Name() string                               { return "utun-test" }
-func (m *reconcileWGMock) Address() wgaddr.Address                    { return wgaddr.Address{} }
-func (m *reconcileWGMock) ToInterface() *net.Interface                { return nil }
-func (m *reconcileWGMock) IsUserspaceBind() bool                      { return false }
-func (m *reconcileWGMock) GetFilter() device.PacketFilter             { return nil }
-func (m *reconcileWGMock) GetDevice() *device.FilteredDevice          { return nil }
-func (m *reconcileWGMock) GetNet() *netstack.Net                      { return nil }
-
-// TestReconcilePeerAllowedIPs verifies the declarative reconcile re-applies every routed prefix
-// tracked for the peer (self-heal, independent of refcount level) and stays scoped to that peer.
-func TestReconcilePeerAllowedIPs(t *testing.T) {
-	wg := &reconcileWGMock{}
-	m := &DefaultManager{wgInterface: wg}
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
-		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
-		func(netip.Prefix, string) error { return nil },
-	)
-
-	peerA1 := netip.MustParsePrefix("10.0.0.0/24")
-	peerA2 := netip.MustParsePrefix("10.1.0.0/24")
-	peerB1 := netip.MustParsePrefix("10.2.0.0/24")
-
-	for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
-		_, err := m.allowedIPsRefCounter.Increment(prefix, peer)
-		require.NoError(t, err)
-	}
-	// Extra reference: reconcile must still re-apply the prefix even though its refcount never
-	// hit 0 again (the exact case the plain incremental path skips).
-	_, err := m.allowedIPsRefCounter.Increment(peerA1, "peerA")
-	require.NoError(t, err)
-
-	require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
-
-	assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, wg.added("peerA"),
-		"reconcile must re-apply all routed prefixes of the peer")
-	assert.Empty(t, wg.added("peerB"), "reconcile must not touch another peer's prefixes")
-}
-
-// TestReconcilePeerAllowedIPsNoCounter verifies reconcile is a safe no-op before the refcounter is
-// set up.
-func TestReconcilePeerAllowedIPsNoCounter(t *testing.T) {
-	wg := &reconcileWGMock{}
-	m := &DefaultManager{wgInterface: wg}
-
-	require.NoError(t, m.ReconcilePeerAllowedIPs("peerA"))
-	assert.Empty(t, wg.added("peerA"))
-}

client/internal/routemanager/refcounter/allowedips.go

@@ -1,206 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"fmt"
-	"net/netip"
-	"sort"
-	"sync"
-
-	"github.com/hashicorp/go-multierror"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-)
-
-// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is
-// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most
-// one peer is active at a time even when several peers reference the prefix.
-type allowedIPsEntry struct {
-	// peers maps a peerKey to the number of references holding the prefix for that peer.
-	peers map[string]int
-	// active is the peerKey currently installed in WireGuard for this prefix ("" if none).
-	active string
-	// total is the sum of all per-peer reference counts (kept in sync with peers).
-	total int
-}
-
-// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs.
-//
-// The generic Counter keys only by prefix and remembers a single Out value set by the first
-// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or
-// multiple resolved domains) can reference the same prefix through different peers, and when the
-// peer currently installed in WireGuard releases its last reference the prefix must be handed over
-// to a surviving peer instead of being left pointing at the released one.
-//
-// It calls add/remove (which program WireGuard) only on the transitions that matter:
-//   - add on the first reference for a prefix, or when swapping the active peer;
-//   - remove on the last reference for a prefix, or on the old peer during a swap.
-type AllowedIPsRefCounter struct {
-	mu      sync.Mutex
-	entries map[netip.Prefix]*allowedIPsEntry
-	add     AddFunc[netip.Prefix, string, string]
-	remove  RemoveFunc[netip.Prefix, string]
-}
-
-// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter.
-// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer.
-// remove unprograms the prefix from the given peer.
-func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter {
-	return &AllowedIPsRefCounter{
-		entries: map[netip.Prefix]*allowedIPsEntry{},
-		add:     add,
-		remove:  remove,
-	}
-}
-
-// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first
-// reference to a prefix; while a different peer is already installed the prefix is left with it
-// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept.
-func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		e = &allowedIPsEntry{peers: map[string]int{}}
-		rm.entries[prefix] = e
-	}
-
-	logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-		prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active)
-
-	// Program WireGuard only when nothing is installed yet for this prefix.
-	if e.active == "" {
-		out, err := rm.add(prefix, peerKey)
-		if errors.Is(err, ErrIgnore) {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{Count: e.total, Out: e.active}, nil
-		}
-		if err != nil {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err)
-		}
-		e.active = out
-	}
-
-	e.peers[peerKey]++
-	e.total++
-
-	return Ref[string]{Count: e.total, Out: e.active}, nil
-}
-
-// Decrement removes a reference to prefix for peerKey. When the peer currently installed in
-// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists,
-// otherwise it is removed from WireGuard.
-func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		logCallerF("No allowed IP reference found for prefix %v", prefix)
-		return Ref[string]{}, nil
-	}
-
-	if e.peers[peerKey] > 0 {
-		logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-			prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active)
-		e.peers[peerKey]--
-		e.total--
-		if e.peers[peerKey] == 0 {
-			delete(e.peers, peerKey)
-		}
-	} else {
-		logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey)
-	}
-
-	// If the peer currently installed in WireGuard still holds references, nothing to reprogram.
-	// Keying the check on the active peer (not the one just released) makes this self-healing:
-	// a prior swap whose remove/add failed leaves e.active pointing at a peer with no references,
-	// and this retries the hand-off on the next Decrement instead of getting stuck.
-	if e.active != "" && e.peers[e.active] > 0 {
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	// Detach the stale/gone active peer from WireGuard before reprogramming.
-	if e.active != "" {
-		if err := rm.remove(prefix, e.active); err != nil {
-			return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)
-		}
-		e.active = ""
-	}
-
-	// Hand the prefix over to a surviving peer, or drop the entry when none remain.
-	if survivor, ok := pickSurvivor(e.peers); ok {
-		out, err := rm.add(prefix, survivor)
-		if err != nil {
-			return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err)
-		}
-		e.active = out
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	delete(rm.entries, prefix)
-	return Ref[string]{Count: 0, Out: ""}, nil
-}
-
-// Flush removes all prefixes from WireGuard and clears the counter.
-func (rm *AllowedIPsRefCounter) Flush() error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active == "" {
-			continue
-		}
-		logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active)
-		if err := rm.remove(prefix, e.active); err != nil {
-			merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err))
-		}
-	}
-
-	clear(rm.entries)
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies
-// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose
-// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching
-// refcounter change, which would otherwise leave the prefix installed in the counter but missing
-// on the device. Only the active peer is considered — a prefix that lost its installed peer to a
-// failed swap is skipped here and reconciled by the next Increment/Decrement.
-func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active != "" && pred(e.active) {
-			if err := apply(prefix); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do
-// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable
-// (lowest peerKey) for predictable behavior and testability.
-func pickSurvivor(peers map[string]int) (string, bool) {
-	if len(peers) == 0 {
-		return "", false
-	}
-	keys := make([]string, 0, len(peers))
-	for k := range peers {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	return keys[0], true
-}

client/internal/routemanager/refcounter/allowedips_test.go

@@ -1,241 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"net/netip"
-	"testing"
-)
-
-// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer.
-// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths.
-type fakeWG struct {
-	installed  map[netip.Prefix]string
-	adds       int
-	removes    int
-	failAdd    bool
-	failRemove bool
-}
-
-func newFakeWG() *fakeWG {
-	return &fakeWG{installed: map[netip.Prefix]string{}}
-}
-
-func (f *fakeWG) counter() *AllowedIPsRefCounter {
-	return NewAllowedIPs(
-		func(prefix netip.Prefix, peerKey string) (string, error) {
-			if f.failAdd {
-				f.failAdd = false
-				return "", errors.New("add failed")
-			}
-			f.adds++
-			f.installed[prefix] = peerKey
-			return peerKey, nil
-		},
-		func(prefix netip.Prefix, peerKey string) error {
-			if f.failRemove {
-				f.failRemove = false
-				return errors.New("remove failed")
-			}
-			f.removes++
-			// only clear if this peer is the one installed, mirroring wg semantics
-			if f.installed[prefix] == peerKey {
-				delete(f.installed, prefix)
-			}
-			return nil
-		},
-	)
-}
-
-func mustPrefix(t *testing.T, s string) netip.Prefix {
-	t.Helper()
-	p, err := netip.ParsePrefix(s)
-	if err != nil {
-		t.Fatalf("parse prefix %q: %v", s, err)
-	}
-	return p
-}
-
-func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Increment(p, peer)
-	if err != nil {
-		t.Fatalf("Increment(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Decrement(p, peer)
-	if err != nil {
-		t.Fatalf("Decrement(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same
-// prefix routed by different peers. Removing the network whose peer is installed must hand the
-// prefix over to the surviving peer instead of leaving it on the removed one.
-func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	// First peer wins while both are present.
-	if got := f.installed[p]; got != "peerA" {
-		t.Fatalf("expected peerA installed, got %q", got)
-	}
-
-	// Remove the active peer's network -> must swap to peerB.
-	mustDecrement(t, c, p, "peerA")
-	if got := f.installed[p]; got != "peerB" {
-		t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got)
-	}
-
-	// Remove the last one -> prefix gone.
-	mustDecrement(t, c, p, "peerB")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix removed, still installed on %q", f.installed[p])
-	}
-}
-
-// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard.
-func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	removesBefore := f.removes
-
-	mustDecrement(t, c, p, "peerB")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("active peer must stay peerA, got %q", f.installed[p])
-	}
-	if f.removes != removesBefore {
-		t.Fatalf("removing a non-active peer must not call wg remove")
-	}
-}
-
-// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until
-// the last reference is released (the reason the per-peer count must be an int, not a set).
-func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerA")
-	if f.adds != 1 {
-		t.Fatalf("expected a single wg add for the same peer, got %d", f.adds)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p])
-	}
-	if f.removes != 0 {
-		t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("prefix must be removed after last reference")
-	}
-}
-
-// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log).
-func TestAllowedIPs_RefCountAndActive(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	ref := mustIncrement(t, c, p, "peerA")
-	if ref.Count != 1 || ref.Out != "peerA" {
-		t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-	ref = mustIncrement(t, c, p, "peerB")
-	if ref.Count != 2 || ref.Out != "peerA" {
-		t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-}
-
-// TestAllowedIPs_Flush removes everything installed and clears the counter.
-func TestAllowedIPs_Flush(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p1 := mustPrefix(t, "10.44.8.0/24")
-	p2 := mustPrefix(t, "10.44.9.0/24")
-
-	mustIncrement(t, c, p1, "peerA")
-	mustIncrement(t, c, p2, "peerB")
-
-	if err := c.Flush(); err != nil {
-		t.Fatal(err)
-	}
-	if len(f.installed) != 0 {
-		t.Fatalf("expected all prefixes removed, got %v", f.installed)
-	}
-	// After flush, a fresh increment must add again.
-	mustIncrement(t, c, p1, "peerC")
-	if f.installed[p1] != "peerC" {
-		t.Fatalf("counter not reset after flush")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently
-// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer.
-func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	mustIncrement(t, c, p, "peerC")
-
-	// Removing the active peerA triggers a swap to a survivor; make the add fail once.
-	f.failAdd = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed swap add")
-	}
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p])
-	}
-
-	// A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck.
-	ref := mustDecrement(t, c, p, "peerC")
-	if got := f.installed[p]; got == "" {
-		t.Fatalf("self-heal failed: prefix left unrouted after add recovered")
-	}
-	if ref.Out == "" {
-		t.Fatalf("expected an active peer after self-heal, got empty")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead
-// of leaving e.active stuck on a peer that no longer holds references.
-func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-
-	// Releasing active peerA must detach it (remove) then add peerB; fail the remove once.
-	f.failRemove = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed remove")
-	}
-
-	// Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB.
-	mustDecrement(t, c, p, "peerB")
-	// peerB had only one ref, so after retry the prefix is fully released.
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p])
-	}
-}

client/internal/routemanager/refcounter/refcounter.go

@@ -94,26 +94,6 @@ func (rm *Counter[Key, I, O]) Get(key Key) (Ref[O], bool) {
 	return ref, ok
 }
 
-// ReapplyMatching calls apply for every key whose stored Out satisfies pred, holding the
-// counter lock for the whole pass. Running apply under the lock keeps it atomic with respect
-// to Increment/Decrement: a prefix dropped to zero is removed from the map (and had its
-// RemoveFunc called) before this pass observes it, so a stale key can never be re-applied.
-// pred and apply are invoked under the lock, so they must not call back into the counter.
-func (rm *Counter[Key, I, O]) ReapplyMatching(pred func(out O) bool, apply func(key Key) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for key, ref := range rm.refCountMap {
-		if pred(ref.Out) {
-			if err := apply(key); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
 // Increment increments the reference count for the given key.
 // If this is the first reference to the key, the AddFunc is called.
 func (rm *Counter[Key, I, O]) Increment(key Key, in I) (Ref[O], error) {

client/internal/routemanager/refcounter/refcounter_test.go

@@ -1,47 +0,0 @@
-package refcounter
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-// TestReapplyMatching verifies ReapplyMatching invokes apply for exactly the keys whose stored
-// Out satisfies the predicate (no duplicates for multiply-referenced keys) — the primitive
-// ReconcilePeerAllowedIPs relies on to re-apply a single peer's routed prefixes.
-func TestReapplyMatching(t *testing.T) {
-	rc := New[netip.Prefix, string, string](
-		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
-		func(netip.Prefix, string) error { return nil },
-	)
-
-	peerA1 := netip.MustParsePrefix("10.0.0.0/24")
-	peerA2 := netip.MustParsePrefix("10.1.0.0/24")
-	peerB1 := netip.MustParsePrefix("10.2.0.0/24")
-
-	for prefix, peer := range map[netip.Prefix]string{peerA1: "peerA", peerA2: "peerA", peerB1: "peerB"} {
-		_, err := rc.Increment(prefix, peer)
-		require.NoError(t, err)
-	}
-	// a second reference must not make the key applied twice
-	_, err := rc.Increment(peerA1, "peerA")
-	require.NoError(t, err)
-
-	var applied []netip.Prefix
-	err = rc.ReapplyMatching(
-		func(out string) bool { return out == "peerA" },
-		func(key netip.Prefix) error { applied = append(applied, key); return nil },
-	)
-	require.NoError(t, err)
-	assert.ElementsMatch(t, []netip.Prefix{peerA1, peerA2}, applied)
-
-	var none []netip.Prefix
-	err = rc.ReapplyMatching(
-		func(out string) bool { return out == "missing" },
-		func(key netip.Prefix) error { none = append(none, key); return nil },
-	)
-	require.NoError(t, err)
-	assert.Empty(t, none)
-}

client/internal/routemanager/refcounter/types.go

@@ -5,7 +5,5 @@ import "net/netip"
 // RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement
 type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}]
 
-// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware:
-// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer,
-// so the counter records the per-peer reference count and swaps the installed peer when the active one is released.
-// See allowedips.go.
+// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement
+type AllowedIPsRefCounter = Counter[netip.Prefix, string, string]

client/internal/routemanager/selection.go

@@ -1,138 +0,0 @@
-package routemanager
-
-import (
-	"fmt"
-	"slices"
-
-	"github.com/hashicorp/go-multierror"
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/exp/maps"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-	"github.com/netbirdio/netbird/route"
-)
-
-// SelectRoutes selects the routes with the given network IDs and applies the
-// new selection. V4/v6 exit-node pairs are expanded automatically. Exit nodes
-// are mutually exclusive: if the selection activates an exit node, every other
-// available exit node is deselected so two can't be active at once. With
-// appendRoute=false the previous selection is replaced instead of extended.
-func (m *DefaultManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if err := m.selectRoutes(ids, appendRoute); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-// DeselectRoutes removes the routes with the given network IDs from the
-// selection and applies the change. V4/v6 exit-node pairs are expanded
-// automatically.
-func (m *DefaultManager) DeselectRoutes(ids []route.NetID) error {
-	if err := m.deselectRoutes(ids); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-func (m *DefaultManager) deselectRoutes(ids []route.NetID) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-
-	log.Debugf("deselecting routes with ids: %v", routes)
-
-	if err := m.routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
-		return fmt.Errorf("deselect routes: %w", err)
-	}
-
-	return nil
-}
-
-// SelectAllRoutes selects every available route and applies the selection.
-// Exit nodes stay mutually exclusive: at most one remains active.
-func (m *DefaultManager) SelectAllRoutes() {
-	m.selectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectAllRoutes() {
-	m.routeSelector.SelectAllRoutes()
-
-	// Select-all wipes every explicit selection, so exit nodes fall back to
-	// management's auto-apply flags — which may mark several at once.
-	// Reconcile immediately so at most one exit node stays active instead of
-	// waiting for the next network map to enforce it.
-	m.mux.Lock()
-	defer m.mux.Unlock()
-	m.updateRouteSelectorFromManagement(m.clientRoutes)
-}
-
-// DeselectAllRoutes deselects every route and applies the change.
-func (m *DefaultManager) DeselectAllRoutes() {
-	m.routeSelector.DeselectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectRoutes(ids []route.NetID, appendRoute bool) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-	allIDs := maps.Keys(routesMap)
-
-	log.Debugf("selecting routes with ids: %v", routes)
-
-	// A partial failure (e.g. an unknown ID in the request) still selects the
-	// valid routes, so exclusivity below must run regardless of the error.
-	var merr *multierror.Error
-	if err := m.routeSelector.SelectRoutes(routes, appendRoute, allIDs); err != nil {
-		merr = multierror.Append(merr, fmt.Errorf("select routes: %w", err))
-	}
-
-	// Exit nodes are mutually exclusive: if this selection activates an
-	// exit node, deselect every other available exit node so two can't be
-	// selected at once. Non-exit route selections are left untouched.
-	if requestActivatesExitNode(routes, routesMap) {
-		if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
-			if err := m.routeSelector.DeselectRoutes(others, allIDs); err != nil {
-				merr = multierror.Append(merr, fmt.Errorf("deselect sibling exit nodes: %w", err))
-			}
-		}
-	}
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-func isExitNodeRoutes(routes []*route.Route) bool {
-	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
-}
-
-// requestActivatesExitNode reports whether any requested NetID maps to an exit
-// node (default route) in the current route table.
-func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
-	for _, id := range requested {
-		if isExitNodeRoutes(routesMap[id]) {
-			return true
-		}
-	}
-	return false
-}
-
-// otherExitNodeIDs returns every available exit-node NetID that is not in the
-// requested set — the siblings to deselect so a single exit node stays active.
-func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
-	keep := make(map[route.NetID]struct{}, len(requested))
-	for _, id := range requested {
-		keep[id] = struct{}{}
-	}
-	var others []route.NetID
-	for id, routes := range routesMap {
-		if !isExitNodeRoutes(routes) {
-			continue
-		}
-		if _, ok := keep[id]; ok {
-			continue
-		}
-		others = append(others, id)
-	}
-	return others
-}

client/internal/routemanager/selection_test.go

@@ -1,129 +0,0 @@
-package routemanager
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/routeselector"
-	"github.com/netbirdio/netbird/route"
-)
-
-func v6ExitRoute(netID, peer string) *route.Route {
-	return &route.Route{
-		NetID:   route.NetID(netID),
-		Network: netip.MustParsePrefix("::/0"),
-		Peer:    peer,
-	}
-}
-
-func newSelectionTestManager() *DefaultManager {
-	return &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", true)},
-			"exitA-v6|::/0":      {v6ExitRoute("exitA-v6", "p1")},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", true)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-}
-
-func TestSelectRoutes_ExitNodeExclusivity(t *testing.T) {
-	m := newSelectionTestManager()
-
-	// Selecting an exit node selects its v6 pair and deselects the sibling.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "exitA should be selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA-v6"), "the v6 pair follows its v4 base")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "the sibling exit node must be deselected")
-
-	// Switching to the sibling deselects the previous exit node and its v6 pair.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "exitB should now be selected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "the previous exit node must be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "the previous exit node's v6 pair must be deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-
-	// Selecting a non-exit route leaves the active exit node alone.
-	require.NoError(t, m.selectRoutes([]route.NetID{"lan"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "selecting a non-exit route keeps the exit node")
-
-	// Deselecting the active exit node turns every exit node off.
-	require.NoError(t, m.deselectRoutes([]route.NetID{"exitB"}))
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "exitB should be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "exitA stays deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-}
-
-func TestSelectRoutes_PartialErrorStillEnforcesExclusivity(t *testing.T) {
-	// The unknown ID must be reported, but the valid exit node in the same
-	// request is still selected — so its sibling must still be deselected.
-	// Both orderings are covered: processing must continue past the invalid
-	// ID wherever it sits in the request.
-	requests := map[string][]route.NetID{
-		"invalid id first": {"missing", "exitB"},
-		"invalid id last":  {"exitB", "missing"},
-	}
-
-	for name, ids := range requests {
-		t.Run(name, func(t *testing.T) {
-			m := newSelectionTestManager()
-
-			require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-
-			err := m.selectRoutes(ids, true)
-			assert.Error(t, err, "unknown id must be reported")
-			assert.True(t, m.routeSelector.IsSelected("exitB"), "valid exit node from the request is selected")
-			assert.False(t, m.routeSelector.IsSelected("exitA"), "sibling exit node must be deselected despite the error")
-			assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "sibling's v6 pair must be deselected too")
-		})
-	}
-}
-
-func TestSelectAllRoutes_KeepsSingleExitNode(t *testing.T) {
-	// Both exit nodes are marked for auto-apply by management
-	// (SkipAutoApply=false), the state where select-all could turn on two at
-	// once without the immediate reconciliation.
-	m := &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", false)},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", false)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-
-	m.selectAllRoutes()
-
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit routes are all selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "the deterministic management pick stays active")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "select-all must not leave a second exit node active")
-}
-
-func TestSelectRoutes_UnknownRoute(t *testing.T) {
-	m := newSelectionTestManager()
-
-	assert.Error(t, m.selectRoutes([]route.NetID{"missing"}, true), "selecting an unavailable route must fail")
-	assert.Error(t, m.deselectRoutes([]route.NetID{"missing"}), "deselecting an unavailable route must fail")
-}
-
-func TestExitNodeSelectionHelpers(t *testing.T) {
-	routesMap := map[route.NetID][]*route.Route{
-		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
-		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
-		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
-	}
-
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
-
-	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
-	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
-}

client/internal/routemanager/static/route.go

@@ -15,11 +15,6 @@ type Route struct {
 	route                *route.Route
 	routeRefCounter      *refcounter.RouteRefCounter
 	allowedIPsRefcounter *refcounter.AllowedIPsRefCounter
-	// currentPeerKey is the routing peer this watcher currently has the prefix installed on
-	// (the HA winner elected by the watcher). It can differ from route.Peer and change on
-	// failover, so it is recorded on AddAllowedIPs and used on RemoveAllowedIPs to decrement
-	// the exact peer that was incremented.
-	currentPeerKey string
 }
 
 func NewRoute(params common.HandlerParams) *Route {
@@ -57,15 +52,12 @@ func (r *Route) AddAllowedIPs(peerKey string) error {
 			ref.Out,
 		)
 	}
-	r.currentPeerKey = peerKey
 	return nil
 }
 
 func (r *Route) RemoveAllowedIPs() error {
-	var err error
-	if _, decErr := r.allowedIPsRefcounter.Decrement(r.route.Network, r.currentPeerKey); decErr != nil {
-		err = fmt.Errorf("remove allowed IP %s: %w", r.route.Network, decErr)
+	if _, err := r.allowedIPsRefcounter.Decrement(r.route.Network); err != nil {
+		return err
 	}
-	r.currentPeerKey = ""
-	return err
+	return nil
 }

client/internal/routemanager/sysctl/sysctl_linux.go

@@ -20,8 +20,6 @@ const (
 	rpFilterPath          = "net.ipv4.conf.all.rp_filter"
 	rpFilterInterfacePath = "net.ipv4.conf.%s.rp_filter"
 	srcValidMarkPath      = "net.ipv4.conf.all.src_valid_mark"
-	percentEscape         = "%25"
-	dotEscape             = "%2E"
 )
 
 type iface interface {
@@ -58,11 +56,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 			continue
 		}
 
-		// Escape '%' and '.' so they survive the dot-to-slash conversion in Set()
-		safeName := strings.ReplaceAll(intf.Name, "%", percentEscape)
-		safeName = strings.ReplaceAll(safeName, ".", dotEscape)
-
-		i := fmt.Sprintf(rpFilterInterfacePath, safeName)
+		i := fmt.Sprintf(rpFilterInterfacePath, intf.Name)
 		oldVal, err := Set(i, 2, true)
 		if err != nil {
 			result = multierror.Append(result, err)
@@ -76,11 +70,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 
 // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1
 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) {
-	path := strings.ReplaceAll(key, ".", "/")
-	// Unescape interface dots and percent signs
-	path = strings.ReplaceAll(path, dotEscape, ".")
-	path = strings.ReplaceAll(path, percentEscape, "%")
-	path = fmt.Sprintf("/proc/sys/%s", path)
+	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
 	currentValue, err := os.ReadFile(path)
 	if err != nil {
 		return -1, fmt.Errorf("read sysctl %s: %w", key, err)

client/internal/shell/getent_cgo_unix.go

@@ -0,0 +1,29 @@
+//go:build cgo && !osusergo && !windows
+
+package shell
+
+import "os/user"
+
+// LookupWithGetent with CGO delegates directly to os/user.Lookup.
+// When CGO is enabled, os/user uses libc (getpwnam_r) which goes through
+// the NSS stack natively. If it fails, the user truly doesn't exist and
+// getent would also fail.
+func LookupWithGetent(username string) (*user.User, error) {
+	return user.Lookup(username)
+}
+
+// CurrentUserWithGetent with CGO delegates directly to os/user.Current.
+func CurrentUserWithGetent() (*user.User, error) {
+	return user.Current()
+}
+
+// LookupGroupWithGetent returns the resolved group from either a gid or groupname.
+func LookupGroupWithGetent(name string) (*user.Group, error) {
+	return user.LookupGroup(name)
+}
+
+// GroupIdsWithFallback with CGO delegates directly to user.GroupIds.
+// libc's getgrouplist handles NSS groups natively.
+func GroupIdsWithFallback(u *user.User) ([]string, error) {
+	return u.GroupIds()
+}

client/internal/shell/getent_nocgo_unix.go

@@ -1,6 +1,6 @@
 //go:build (!cgo || osusergo) && !windows
 
-package server
+package shell
 
 import (
 	"os"
@@ -10,10 +10,10 @@ import (
 	log "github.com/sirupsen/logrus"
 )
 
-// lookupWithGetent looks up a user by name, falling back to getent if os/user fails.
+// LookupWithGetent looks up a user by name, falling back to getent if os/user fails.
 // Without CGO, os/user only reads /etc/passwd and misses NSS-provided users.
 // getent goes through the host's NSS stack.
-func lookupWithGetent(username string) (*user.User, error) {
+func LookupWithGetent(username string) (*user.User, error) {
 	u, err := user.Lookup(username)
 	if err == nil {
 		return u, nil
@@ -22,7 +22,7 @@ func lookupWithGetent(username string) (*user.User, error) {
 	stdErr := err
 	log.Debugf("os/user.Lookup(%q) failed, trying getent: %v", username, err)
 
-	u, _, getentErr := runGetent(username)
+	u, _, getentErr := runGetentPasswd(username)
 	if getentErr != nil {
 		log.Debugf("getent fallback for %q also failed: %v", username, getentErr)
 		return nil, stdErr
@@ -31,8 +31,26 @@ func lookupWithGetent(username string) (*user.User, error) {
 	return u, nil
 }
 
-// currentUserWithGetent gets the current user, falling back to getent if os/user fails.
-func currentUserWithGetent() (*user.User, error) {
+// LookupGroupWithGetent returns the resolved group from either a gid or groupname,
+// falling back to getent if os/user fails (NSS groups under nocgo).
+func LookupGroupWithGetent(name string) (*user.Group, error) {
+	g, err := user.LookupGroup(name)
+	if err == nil {
+		return g, nil
+	}
+
+	stdErr := err
+	log.Debugf("os/user.LookupGroup(%q) failed, trying getent: %v", name, err)
+	g, getentErr := runGetentGroup(name)
+	if getentErr != nil {
+		log.Debugf("getent fallback for %q also failed: %v", name, getentErr)
+		return nil, stdErr
+	}
+	return g, nil
+}
+
+// CurrentUserWithGetent gets the current user, falling back to getent if os/user fails.
+func CurrentUserWithGetent() (*user.User, error) {
 	u, err := user.Current()
 	if err == nil {
 		return u, nil
@@ -42,7 +60,7 @@ func currentUserWithGetent() (*user.User, error) {
 	uid := strconv.Itoa(os.Getuid())
 	log.Debugf("os/user.Current() failed, trying getent with UID %s: %v", uid, err)
 
-	u, _, getentErr := runGetent(uid)
+	u, _, getentErr := runGetentPasswd(uid)
 	if getentErr != nil {
 		return nil, stdErr
 	}
@@ -50,14 +68,14 @@ func currentUserWithGetent() (*user.User, error) {
 	return u, nil
 }
 
-// groupIdsWithFallback gets group IDs for a user via the id command first,
+// GroupIdsWithFallback gets group IDs for a user via the id command first,
 // falling back to user.GroupIds().
-// NOTE: unlike lookupWithGetent/currentUserWithGetent which try stdlib first,
+// NOTE: unlike LookupWithGetent/CurrentUserWithGetent which try stdlib first,
 // this intentionally tries `id -G` first because without CGO, user.GroupIds()
 // only reads /etc/group and silently returns incomplete results for NSS users
 // (no error, just missing groups). The id command goes through NSS and returns
 // the full set.
-func groupIdsWithFallback(u *user.User) ([]string, error) {
+func GroupIdsWithFallback(u *user.User) ([]string, error) {
 	ids, err := runIdGroups(u.Username)
 	if err == nil {
 		return ids, nil

client/internal/shell/getent_test.go

@@ -1,4 +1,4 @@
-package server
+package shell
 
 import (
 	"os/user"
@@ -15,7 +15,7 @@ func TestLookupWithGetent_CurrentUser(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
-	u, err := lookupWithGetent(current.Username)
+	u, err := LookupWithGetent(current.Username)
 	require.NoError(t, err)
 	assert.Equal(t, current.Username, u.Username)
 	assert.Equal(t, current.Uid, u.Uid)
@@ -23,7 +23,7 @@ func TestLookupWithGetent_CurrentUser(t *testing.T) {
 }
 
 func TestLookupWithGetent_NonexistentUser(t *testing.T) {
-	_, err := lookupWithGetent("nonexistent_user_xyzzy_12345")
+	_, err := LookupWithGetent("nonexistent_user_xyzzy_12345")
 	require.Error(t, err, "should fail for nonexistent user")
 }
 
@@ -31,7 +31,7 @@ func TestCurrentUserWithGetent(t *testing.T) {
 	stdUser, err := user.Current()
 	require.NoError(t, err)
 
-	u, err := currentUserWithGetent()
+	u, err := CurrentUserWithGetent()
 	require.NoError(t, err)
 	assert.Equal(t, stdUser.Uid, u.Uid)
 	assert.Equal(t, stdUser.Username, u.Username)
@@ -41,7 +41,7 @@ func TestGroupIdsWithFallback_CurrentUser(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
-	groups, err := groupIdsWithFallback(current)
+	groups, err := GroupIdsWithFallback(current)
 	require.NoError(t, err)
 	require.NotEmpty(t, groups, "current user should have at least one group")
 
@@ -56,7 +56,7 @@ func TestGroupIdsWithFallback_CurrentUser(t *testing.T) {
 func TestGetShellFromGetent_CurrentUser(t *testing.T) {
 	if runtime.GOOS == "windows" {
 		// Windows stub always returns empty, which is correct
-		shell := getShellFromGetent("1000")
+		shell := GetShellFromGetent("1000")
 		assert.Empty(t, shell, "Windows stub should return empty")
 		return
 	}
@@ -65,9 +65,9 @@ func TestGetShellFromGetent_CurrentUser(t *testing.T) {
 	require.NoError(t, err)
 
 	// getent may not be available on all systems (e.g., macOS without Homebrew getent)
-	shell := getShellFromGetent(current.Uid)
+	shell := GetShellFromGetent(current.Uid)
 	if shell == "" {
-		t.Log("getShellFromGetent returned empty, getent may not be available")
+		t.Log("GetShellFromGetent returned empty, getent may not be available")
 		return
 	}
 	assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
@@ -78,7 +78,7 @@ func TestLookupWithGetent_RootUser(t *testing.T) {
 		t.Skip("no root user on Windows")
 	}
 
-	u, err := lookupWithGetent("root")
+	u, err := LookupWithGetent("root")
 	if err != nil {
 		t.Skip("root user not available on this system")
 	}
@@ -86,25 +86,25 @@ func TestLookupWithGetent_RootUser(t *testing.T) {
 }
 
 // TestIntegration_FullLookupChain exercises the complete user lookup chain
-// against the real system, testing that all wrappers (lookupWithGetent,
-// currentUserWithGetent, groupIdsWithFallback, getShellFromGetent) produce
+// against the real system, testing that all wrappers (LookupWithGetent,
+// CurrentUserWithGetent, GroupIdsWithFallback, GetShellFromGetent) produce
 // consistent and correct results when composed together.
 func TestIntegration_FullLookupChain(t *testing.T) {
-	// Step 1: currentUserWithGetent must resolve the running user.
-	current, err := currentUserWithGetent()
-	require.NoError(t, err, "currentUserWithGetent must resolve the running user")
+	// Step 1: CurrentUserWithGetent must resolve the running user.
+	current, err := CurrentUserWithGetent()
+	require.NoError(t, err, "CurrentUserWithGetent must resolve the running user")
 	require.NotEmpty(t, current.Uid)
 	require.NotEmpty(t, current.Username)
 
-	// Step 2: lookupWithGetent by the same username must return matching identity.
-	byName, err := lookupWithGetent(current.Username)
+	// Step 2: LookupWithGetent by the same username must return matching identity.
+	byName, err := LookupWithGetent(current.Username)
 	require.NoError(t, err)
 	assert.Equal(t, current.Uid, byName.Uid, "lookup by name should return same UID")
 	assert.Equal(t, current.Gid, byName.Gid, "lookup by name should return same GID")
 	assert.Equal(t, current.HomeDir, byName.HomeDir, "lookup by name should return same home")
 
-	// Step 3: groupIdsWithFallback must return at least the primary GID.
-	groups, err := groupIdsWithFallback(current)
+	// Step 3: GroupIdsWithFallback must return at least the primary GID.
+	groups, err := GroupIdsWithFallback(current)
 	require.NoError(t, err)
 	require.NotEmpty(t, groups, "user must have at least one group")
 
@@ -120,10 +120,10 @@ func TestIntegration_FullLookupChain(t *testing.T) {
 	}
 	assert.True(t, foundPrimary, "primary GID %s should appear in supplementary groups", current.Gid)
 
-	// Step 4: getShellFromGetent should either return a valid shell path or empty
+	// Step 4: GetShellFromGetent should either return a valid shell path or empty
 	// (empty is OK when getent is not available, e.g. macOS without Homebrew getent).
 	if runtime.GOOS != "windows" {
-		shell := getShellFromGetent(current.Uid)
+		shell := GetShellFromGetent(current.Uid)
 		if shell != "" {
 			assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
 		}
@@ -131,17 +131,17 @@ func TestIntegration_FullLookupChain(t *testing.T) {
 }
 
 // TestIntegration_LookupAndGroupsConsistency verifies that a user resolved via
-// lookupWithGetent can have their groups resolved via groupIdsWithFallback,
+// LookupWithGetent can have their groups resolved via GroupIdsWithFallback,
 // testing the handoff between the two functions as used by the SSH server.
 func TestIntegration_LookupAndGroupsConsistency(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
 	// Simulate the SSH server flow: lookup user, then get their groups.
-	resolved, err := lookupWithGetent(current.Username)
+	resolved, err := LookupWithGetent(current.Username)
 	require.NoError(t, err)
 
-	groups, err := groupIdsWithFallback(resolved)
+	groups, err := GroupIdsWithFallback(resolved)
 	require.NoError(t, err)
 	require.NotEmpty(t, groups, "resolved user must have groups")
 
@@ -156,7 +156,7 @@ func TestIntegration_LookupAndGroupsConsistency(t *testing.T) {
 }
 
 // TestIntegration_ShellLookupChain tests the full shell resolution chain
-// (getShellFromPasswd -> getShellFromGetent -> $SHELL -> default) on Unix.
+// (getShellFromPasswd -> GetShellFromGetent -> $SHELL -> default) on Unix.
 func TestIntegration_ShellLookupChain(t *testing.T) {
 	if runtime.GOOS == "windows" {
 		t.Skip("Unix shell lookup not applicable on Windows")
@@ -165,8 +165,8 @@ func TestIntegration_ShellLookupChain(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
-	// getUserShell is the top-level function used by the SSH server.
-	shell := getUserShell(current.Uid)
-	require.NotEmpty(t, shell, "getUserShell must always return a shell")
+	// GetUserShell is the top-level function used by the SSH server.
+	shell := GetUserShell(current.Uid)
+	require.NotEmpty(t, shell, "GetUserShell must always return a shell")
 	assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
 }

client/internal/shell/getent_unix.go

@@ -1,6 +1,6 @@
 //go:build !windows
 
-package server
+package shell
 
 import (
 	"context"
@@ -14,19 +14,26 @@ import (
 
 const getentTimeout = 5 * time.Second
 
-// getShellFromGetent gets a user's login shell via getent by UID.
+// GetShellFromGetent gets a user's login shell via getent by UID.
 // This is needed even with CGO because getShellFromPasswd reads /etc/passwd
 // directly and won't find NSS-provided users there.
-func getShellFromGetent(userID string) string {
-	_, shell, err := runGetent(userID)
+func GetShellFromGetent(userID string) string {
+	_, shell, err := runGetentPasswd(userID)
 	if err != nil {
 		return ""
 	}
 	return shell
 }
 
-// runGetent executes `getent passwd <query>` and returns the user and login shell.
-func runGetent(query string) (*user.User, string, error) {
+// GetUserFromGetent returns the resolved user from either a uid or username,
+// going through the host's NSS stack.
+func GetUserFromGetent(query string) (*user.User, error) {
+	u, _, err := runGetentPasswd(query)
+	return u, err
+}
+
+// runGetentPasswd executes `getent passwd <query>` and returns the user and login shell.
+func runGetentPasswd(query string) (*user.User, string, error) {
 	if !validateGetentInput(query) {
 		return nil, "", fmt.Errorf("invalid getent input: %q", query)
 	}
@@ -42,7 +49,24 @@ func runGetent(query string) (*user.User, string, error) {
 	return parseGetentPasswd(string(out))
 }
 
-// parseGetentPasswd parses getent passwd output: "name:x:uid:gid:gecos:home:shell"
+// runGetentGroup executes `getent group <query>` and returns the group.
+func runGetentGroup(query string) (*user.Group, error) {
+	if !validateGetentInput(query) {
+		return nil, fmt.Errorf("invalid getent input: %q", query)
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), getentTimeout)
+	defer cancel()
+
+	out, err := exec.CommandContext(ctx, "getent", "group", query).Output()
+	if err != nil {
+		return nil, fmt.Errorf("getent group %s: %w", query, err)
+	}
+
+	return parseGetentGroup(string(out))
+}
+
+// parseGetentPasswd parses getent passwd output: "name:x:uid:gid:gecos:home:shell".
 func parseGetentPasswd(output string) (*user.User, string, error) {
 	fields := strings.SplitN(strings.TrimSpace(output), ":", 8)
 	if len(fields) < 6 {
@@ -67,6 +91,20 @@ func parseGetentPasswd(output string) (*user.User, string, error) {
 	}, shell, nil
 }
 
+// parseGetentGroup parses getent group output: "group:x:gid:members".
+func parseGetentGroup(output string) (*user.Group, error) {
+	fields := strings.SplitN(strings.TrimSpace(output), ":", 8)
+	if len(fields) < 4 {
+		return nil, fmt.Errorf("unexpected getent output (need 4+ fields): %q", output)
+	}
+
+	if fields[0] == "" || fields[2] == "" {
+		return nil, fmt.Errorf("missing required fields in getent output: %q", output)
+	}
+
+	return &user.Group{Gid: fields[2], Name: fields[0]}, nil
+}
+
 // validateGetentInput checks that the input is safe to pass to getent or id.
 // Allows POSIX usernames, numeric UIDs, and common NSS extensions
 // (@ for Kerberos, $ for Samba, + for NIS compat). A leading hyphen is

client/internal/shell/getent_unix_test.go

@@ -1,6 +1,6 @@
 //go:build !windows
 
-package server
+package shell
 
 import (
 	"os/exec"
@@ -198,7 +198,7 @@ func TestRunGetent_RootUser(t *testing.T) {
 		t.Skip("getent not available on this system")
 	}
 
-	u, shell, err := runGetent("root")
+	u, shell, err := runGetentPasswd("root")
 	require.NoError(t, err)
 	assert.Equal(t, "root", u.Username)
 	assert.Equal(t, "0", u.Uid)
@@ -211,7 +211,7 @@ func TestRunGetent_ByUID(t *testing.T) {
 		t.Skip("getent not available on this system")
 	}
 
-	u, _, err := runGetent("0")
+	u, _, err := runGetentPasswd("0")
 	require.NoError(t, err)
 	assert.Equal(t, "root", u.Username)
 	assert.Equal(t, "0", u.Uid)
@@ -222,15 +222,15 @@ func TestRunGetent_NonexistentUser(t *testing.T) {
 		t.Skip("getent not available on this system")
 	}
 
-	_, _, err := runGetent("nonexistent_user_xyzzy_12345")
+	_, _, err := runGetentPasswd("nonexistent_user_xyzzy_12345")
 	assert.Error(t, err)
 }
 
 func TestRunGetent_InvalidInput(t *testing.T) {
-	_, _, err := runGetent("")
+	_, _, err := runGetentPasswd("")
 	assert.Error(t, err)
 
-	_, _, err = runGetent("user\x00name")
+	_, _, err = runGetentPasswd("user\x00name")
 	assert.Error(t, err)
 }
 
@@ -239,7 +239,7 @@ func TestRunGetent_NotAvailable(t *testing.T) {
 		t.Skip("getent is available, can't test missing case")
 	}
 
-	_, _, err := runGetent("root")
+	_, _, err := runGetentPasswd("root")
 	assert.Error(t, err, "should fail when getent is not installed")
 }
 
@@ -286,7 +286,7 @@ func TestGetentResultsMatchStdlib(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
-	getentUser, _, err := runGetent(current.Username)
+	getentUser, _, err := runGetentPasswd(current.Username)
 	require.NoError(t, err)
 
 	assert.Equal(t, current.Username, getentUser.Username, "username should match")
@@ -303,7 +303,7 @@ func TestGetentResultsMatchStdlib_ByUID(t *testing.T) {
 	current, err := user.Current()
 	require.NoError(t, err)
 
-	getentUser, _, err := runGetent(current.Uid)
+	getentUser, _, err := runGetentPasswd(current.Uid)
 	require.NoError(t, err)
 
 	assert.Equal(t, current.Username, getentUser.Username, "username should match when looked up by UID")
@@ -359,7 +359,7 @@ func TestGetShellFromPasswd_CurrentUser(t *testing.T) {
 	assert.True(t, shell[0] == '/', "shell should be an absolute path, got %q", shell)
 
 	if _, err := exec.LookPath("getent"); err == nil {
-		_, getentShell, getentErr := runGetent(current.Uid)
+		_, getentShell, getentErr := runGetentPasswd(current.Uid)
 		if getentErr == nil && getentShell != "" {
 			assert.Equal(t, getentShell, shell, "shell from /etc/passwd should match getent")
 		}
@@ -403,7 +403,7 @@ func TestGetShellFromPasswd_MatchesGetentForKnownUsers(t *testing.T) {
 			continue
 		}
 
-		_, getentShell, err := runGetent(uid)
+		_, getentShell, err := runGetentPasswd(uid)
 		if err != nil {
 			continue
 		}

client/internal/shell/getent_windows.go

@@ -0,0 +1,31 @@
+//go:build windows
+
+package shell
+
+import "os/user"
+
+// LookupWithGetent on Windows just delegates to os/user.Lookup.
+// Windows does not use NSS/getent; its user lookup works without CGO.
+func LookupWithGetent(username string) (*user.User, error) {
+	return user.Lookup(username)
+}
+
+// CurrentUserWithGetent on Windows just delegates to os/user.Current.
+func CurrentUserWithGetent() (*user.User, error) {
+	return user.Current()
+}
+
+// LookupGroupWithGetent on Windows just delegates to os/user.LookupGroup.
+func LookupGroupWithGetent(name string) (*user.Group, error) {
+	return user.LookupGroup(name)
+}
+
+// GetShellFromGetent is a no-op on Windows; shell resolution uses PowerShell detection.
+func GetShellFromGetent(_ string) string {
+	return ""
+}
+
+// GroupIdsWithFallback on Windows just delegates to u.GroupIds().
+func GroupIdsWithFallback(u *user.User) ([]string, error) {
+	return u.GroupIds()
+}

client/internal/shell/shell.go

@@ -1,17 +1,14 @@
-package server
+package shell
 
 import (
 	"bufio"
 	"fmt"
-	"net"
 	"os"
 	"os/exec"
 	"os/user"
 	"runtime"
-	"strconv"
 	"strings"
 
-	"github.com/gliderlabs/ssh"
 	log "github.com/sirupsen/logrus"
 )
 
@@ -22,9 +19,9 @@ const (
 	powershellExe = "powershell.exe"
 )
 
-// getUserShell returns the appropriate shell for the given user ID
-// Handles all platform-specific logic and fallbacks consistently
-func getUserShell(userID string) string {
+// GetUserShell returns the appropriate shell for the given user ID.
+// Handles all platform-specific logic and fallbacks consistently.
+func GetUserShell(userID string) string {
 	switch runtime.GOOS {
 	case "windows":
 		return getWindowsUserShell()
@@ -56,7 +53,7 @@ func getUnixUserShell(userID string) string {
 		return shell
 	}
 
-	if shell := getShellFromGetent(userID); shell != "" {
+	if shell := GetShellFromGetent(userID); shell != "" {
 		return shell
 	}
 
@@ -67,7 +64,7 @@ func getUnixUserShell(userID string) string {
 	return defaultUnixShell
 }
 
-// getShellFromPasswd reads the shell from /etc/passwd for the given user ID
+// getShellFromPasswd reads the shell from /etc/passwd for the given user ID.
 func getShellFromPasswd(userID string) string {
 	file, err := os.Open("/etc/passwd")
 	if err != nil {
@@ -101,8 +98,8 @@ func getShellFromPasswd(userID string) string {
 	return ""
 }
 
-// prepareUserEnv prepares environment variables for user execution
-func prepareUserEnv(user *user.User, shell string) []string {
+// PrepareUserEnv prepares environment variables for user execution.
+func PrepareUserEnv(user *user.User, shell string) []string {
 	pathValue := "/usr/local/bin:/usr/bin:/bin:/usr/local/games:/usr/games"
 	if runtime.GOOS == "windows" {
 		pathValue = `C:\Windows\System32;C:\Windows;C:\Windows\System32\Wbem;C:\Windows\System32\WindowsPowerShell\v1.0`
@@ -117,9 +114,9 @@ func prepareUserEnv(user *user.User, shell string) []string {
 	}
 }
 
-// acceptEnv checks if environment variable from SSH client should be accepted
-// This is a whitelist of variables that SSH clients can send to the server
-func acceptEnv(envVar string) bool {
+// AcceptEnv checks if an environment variable from an SSH client should be accepted.
+// This is a whitelist of variables that SSH clients can send to the server.
+func AcceptEnv(envVar string) bool {
 	varName := envVar
 	if idx := strings.Index(envVar, "="); idx != -1 {
 		varName = envVar[:idx]
@@ -156,29 +153,3 @@ func acceptEnv(envVar string) bool {
 
 	return false
 }
-
-// prepareSSHEnv prepares SSH protocol-specific environment variables
-// These variables provide information about the SSH connection itself
-func prepareSSHEnv(session ssh.Session) []string {
-	remoteAddr := session.RemoteAddr()
-	localAddr := session.LocalAddr()
-
-	remoteHost, remotePort, err := net.SplitHostPort(remoteAddr.String())
-	if err != nil {
-		remoteHost = remoteAddr.String()
-		remotePort = "0"
-	}
-
-	localHost, localPort, err := net.SplitHostPort(localAddr.String())
-	if err != nil {
-		localHost = localAddr.String()
-		localPort = strconv.Itoa(InternalSSHPort)
-	}
-
-	return []string{
-		// SSH_CLIENT format: "client_ip client_port server_port"
-		fmt.Sprintf("SSH_CLIENT=%s %s %s", remoteHost, remotePort, localPort),
-		// SSH_CONNECTION format: "client_ip client_port server_ip server_port"
-		fmt.Sprintf("SSH_CONNECTION=%s %s %s %s", remoteHost, remotePort, localHost, localPort),
-	}
-}

client/internal/tunnelnotifier/notifier.go

@@ -1,124 +0,0 @@
-package tunnelnotifier
-
-import (
-	"container/list"
-	"sync"
-
-	"github.com/netbirdio/netbird/client/internal/dns"
-	"github.com/netbirdio/netbird/client/internal/listener"
-)
-
-type eventKind int
-
-const (
-	eventRoutes eventKind = iota
-	eventIfaceIP
-	eventIfaceIPv6
-	eventDNS
-)
-
-var (
-	_ listener.NetworkChangeListener = (*Notifier)(nil)
-	_ dns.IosDnsManager              = (*Notifier)(nil)
-)
-
-type event struct {
-	kind    eventKind
-	payload string
-}
-
-type Notifier struct {
-	mu     sync.Mutex
-	cond   *sync.Cond
-	queue  *list.List
-	closed bool
-	done   chan struct{}
-
-	listener   listener.NetworkChangeListener
-	dnsManager dns.IosDnsManager
-}
-
-func New(l listener.NetworkChangeListener, dm dns.IosDnsManager) *Notifier {
-	n := &Notifier{
-		queue:      list.New(),
-		done:       make(chan struct{}),
-		listener:   l,
-		dnsManager: dm,
-	}
-	n.cond = sync.NewCond(&n.mu)
-	go n.deliverLoop()
-	return n
-}
-
-func (n *Notifier) OnNetworkChanged(routes string) {
-	n.enqueue(event{kind: eventRoutes, payload: routes})
-}
-
-func (n *Notifier) SetInterfaceIP(ip string) {
-	n.enqueue(event{kind: eventIfaceIP, payload: ip})
-}
-
-func (n *Notifier) SetInterfaceIPv6(ip string) {
-	n.enqueue(event{kind: eventIfaceIPv6, payload: ip})
-}
-
-func (n *Notifier) ApplyDns(config string) {
-	n.enqueue(event{kind: eventDNS, payload: config})
-}
-
-// Close stops accepting new events and blocks until the delivery loop has
-// drained all queued events and exited.
-func (n *Notifier) Close() {
-	n.mu.Lock()
-	n.closed = true
-	n.cond.Signal()
-	n.mu.Unlock()
-	<-n.done
-}
-
-func (n *Notifier) enqueue(ev event) {
-	n.mu.Lock()
-	defer n.mu.Unlock()
-	if n.closed {
-		return
-	}
-	n.queue.PushBack(ev)
-	n.cond.Signal()
-}
-
-func (n *Notifier) deliverLoop() {
-	defer close(n.done)
-	for {
-		n.mu.Lock()
-		for n.queue.Len() == 0 && !n.closed {
-			n.cond.Wait()
-		}
-		if n.closed && n.queue.Len() == 0 {
-			n.mu.Unlock()
-			return
-		}
-		ev := n.queue.Remove(n.queue.Front()).(event)
-		l := n.listener
-		dm := n.dnsManager
-		n.mu.Unlock()
-
-		switch ev.kind {
-		case eventRoutes:
-			if l != nil {
-				l.OnNetworkChanged(ev.payload)
-			}
-		case eventIfaceIP:
-			if l != nil {
-				l.SetInterfaceIP(ev.payload)
-			}
-		case eventIfaceIPv6:
-			if l != nil {
-				l.SetInterfaceIPv6(ev.payload)
-			}
-		case eventDNS:
-			if dm != nil {
-				dm.ApplyDns(ev.payload)
-			}
-		}
-	}
-}

client/internal/tunnelnotifier/notifier_test.go

@@ -1,192 +0,0 @@
-package tunnelnotifier
-
-import (
-	"fmt"
-	"sync"
-	"sync/atomic"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-type call struct {
-	kind    string
-	payload string
-}
-
-type recorder struct {
-	mu       sync.Mutex
-	calls    []call
-	inFlight atomic.Int32
-	overlap  atomic.Bool
-	delay    time.Duration
-}
-
-func (r *recorder) record(kind, payload string) {
-	if r.inFlight.Add(1) != 1 {
-		r.overlap.Store(true)
-	}
-	if r.delay > 0 {
-		time.Sleep(r.delay)
-	}
-	r.mu.Lock()
-	r.calls = append(r.calls, call{kind: kind, payload: payload})
-	r.mu.Unlock()
-	r.inFlight.Add(-1)
-}
-
-func (r *recorder) count() int {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	return len(r.calls)
-}
-
-func (r *recorder) snapshot() []call {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	out := make([]call, len(r.calls))
-	copy(out, r.calls)
-	return out
-}
-
-type fakeListener struct {
-	rec *recorder
-}
-
-func (f *fakeListener) OnNetworkChanged(routes string) {
-	f.rec.record("routes", routes)
-}
-
-func (f *fakeListener) SetInterfaceIP(ip string) {
-	f.rec.record("ip", ip)
-}
-
-func (f *fakeListener) SetInterfaceIPv6(ip string) {
-	f.rec.record("ipv6", ip)
-}
-
-type fakeDNSManager struct {
-	rec *recorder
-}
-
-func (f *fakeDNSManager) ApplyDns(config string) {
-	f.rec.record("dns", config)
-}
-
-func TestFIFOOrder(t *testing.T) {
-	rec := &recorder{}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	n.SetInterfaceIP("10.0.0.1")
-	n.SetInterfaceIPv6("fd00::1")
-	n.ApplyDns(`{"domains":[]}`)
-	n.OnNetworkChanged("10.0.0.0/8,192.168.0.0/16")
-	n.ApplyDns(`{"domains":["example.com"]}`)
-
-	require.Eventually(t, func() bool { return rec.count() == 5 }, time.Second, time.Millisecond)
-
-	expected := []call{
-		{kind: "ip", payload: "10.0.0.1"},
-		{kind: "ipv6", payload: "fd00::1"},
-		{kind: "dns", payload: `{"domains":[]}`},
-		{kind: "routes", payload: "10.0.0.0/8,192.168.0.0/16"},
-		{kind: "dns", payload: `{"domains":["example.com"]}`},
-	}
-	assert.Equal(t, expected, rec.snapshot())
-}
-
-func TestNoOverlappingCalls(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const producers = 8
-	const perProducer = 25
-
-	var wg sync.WaitGroup
-	for i := 0; i < producers; i++ {
-		wg.Add(1)
-		go func(id int) {
-			defer wg.Done()
-			for j := 0; j < perProducer; j++ {
-				payload := fmt.Sprintf("%d-%d", id, j)
-				switch j % 4 {
-				case 0:
-					n.OnNetworkChanged(payload)
-				case 1:
-					n.SetInterfaceIP(payload)
-				case 2:
-					n.SetInterfaceIPv6(payload)
-				case 3:
-					n.ApplyDns(payload)
-				}
-			}
-		}(i)
-	}
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == producers*perProducer }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-}
-
-func TestDNSAndRoutesInterleaved(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const events = 50
-
-	var wg sync.WaitGroup
-	wg.Add(2)
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.ApplyDns(fmt.Sprintf("dns-%d", i))
-		}
-	}()
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-		}
-	}()
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == 2*events }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-
-	var dnsSeen, routesSeen int
-	for _, c := range rec.snapshot() {
-		switch c.kind {
-		case "dns":
-			assert.Equal(t, fmt.Sprintf("dns-%d", dnsSeen), c.payload)
-			dnsSeen++
-		case "routes":
-			assert.Equal(t, fmt.Sprintf("routes-%d", routesSeen), c.payload)
-			routesSeen++
-		}
-	}
-	assert.Equal(t, events, dnsSeen)
-	assert.Equal(t, events, routesSeen)
-}
-
-func TestCloseDrainsQueue(t *testing.T) {
-	rec := &recorder{delay: time.Millisecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-
-	const events = 20
-	for i := 0; i < events; i++ {
-		n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-	}
-	n.Close()
-
-	require.Equal(t, events, rec.count(), "Close must not return before all queued events are delivered")
-
-	n.OnNetworkChanged("after-close")
-	n.ApplyDns("after-close")
-	time.Sleep(50 * time.Millisecond)
-	assert.Equal(t, events, rec.count())
-}

client/ios/NetBirdSDK/client.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
 
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/auth"
@@ -232,9 +233,6 @@ func (c *Client) DebugBundle(anonymize bool) (string, error) {
 		deps.SyncResponse = resp
 
 		if e := cc.Engine(); e != nil {
-			deps.RefreshStatus = func() {
-				e.RunHealthProbes(context.Background(), true)
-			}
 			if cm := e.GetClientMetrics(); cm != nil {
 				deps.ClientMetrics = cm
 			}
@@ -636,18 +634,23 @@ func (c *Client) SelectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("select all routes")
-		routeManager.SelectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("select route with id: %s", id)
-	if err := routeManager.SelectRoutes(toNetIDs([]string{id}), true); err != nil {
-		log.Debugf("error when selecting routes: %s", err)
-		return err
+		routeSelector.SelectAllRoutes()
+	} else {
+		log.Debugf("select route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.SelectRoutes(routes, true, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when selecting routes: %s", err)
+			return fmt.Errorf("select routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
+
 }
 
 func (c *Client) DeselectRoute(id string) error {
@@ -661,17 +664,21 @@ func (c *Client) DeselectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("deselect all routes")
-		routeManager.DeselectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("deselect route with id: %s", id)
-	if err := routeManager.DeselectRoutes(toNetIDs([]string{id})); err != nil {
-		log.Debugf("error when deselecting routes: %s", err)
-		return err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		log.Debugf("deselect route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when deselecting routes: %s", err)
+			return fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
 }
 

client/ios/NetBirdSDK/version.go

@@ -1,12 +0,0 @@
-//go:build ios
-
-package NetBirdSDK
-
-import "github.com/netbirdio/netbird/version"
-
-// GoClientVersion returns the NetBird Go client version that was baked into
-// the framework at compile time via
-// -ldflags "-X github.com/netbirdio/netbird/version.version=<version>".
-func GoClientVersion() string {
-	return version.NetbirdVersion()
-}

client/server/network.go

@@ -8,6 +8,7 @@ import (
 	"sort"
 	"strings"
 
+	"golang.org/x/exp/maps"
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
 
@@ -160,11 +161,30 @@ func (s *Server) SelectNetworks(_ context.Context, req *proto.SelectNetworksRequ
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.SelectAllRoutes()
-	} else if err := routeManager.SelectRoutes(toNetIDs(req.GetNetworkIDs()), req.GetAppend()); err != nil {
-		return nil, err
+		routeSelector.SelectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.SelectRoutes(routes, req.GetAppend(), netIdRoutes); err != nil {
+			return nil, fmt.Errorf("select routes: %w", err)
+		}
+
+		// Exit nodes are mutually exclusive: if this selection activates an
+		// exit node, deselect every other available exit node so two can't be
+		// selected at once. Non-exit route selections are left untouched.
+		if requestActivatesExitNode(routes, routesMap) {
+			if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
+				if err := routeSelector.DeselectRoutes(others, netIdRoutes); err != nil {
+					return nil, fmt.Errorf("deselect sibling exit nodes: %w", err)
+				}
+			}
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -204,11 +224,19 @@ func (s *Server) DeselectNetworks(_ context.Context, req *proto.SelectNetworksRe
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.DeselectAllRoutes()
-	} else if err := routeManager.DeselectRoutes(toNetIDs(req.GetNetworkIDs())); err != nil {
-		return nil, err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.DeselectRoutes(routes, netIdRoutes); err != nil {
+			return nil, fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -233,3 +261,37 @@ func toNetIDs(routes []string) []route.NetID {
 	return netIDs
 }
 
+func isExitNodeRoutes(routes []*route.Route) bool {
+	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
+}
+
+// requestActivatesExitNode reports whether any requested NetID maps to an exit
+// node (default route) in the current route table.
+func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
+	for _, id := range requested {
+		if isExitNodeRoutes(routesMap[id]) {
+			return true
+		}
+	}
+	return false
+}
+
+// otherExitNodeIDs returns every available exit-node NetID that is not in the
+// requested set — the siblings to deselect so a single exit node stays active.
+func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
+	keep := make(map[route.NetID]struct{}, len(requested))
+	for _, id := range requested {
+		keep[id] = struct{}{}
+	}
+	var others []route.NetID
+	for id, routes := range routesMap {
+		if !isExitNodeRoutes(routes) {
+			continue
+		}
+		if _, ok := keep[id]; ok {
+			continue
+		}
+		others = append(others, id)
+	}
+	return others
+}

client/server/network_exitnode_test.go

@@ -0,0 +1,26 @@
+package server
+
+import (
+	"net/netip"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/netbirdio/netbird/route"
+)
+
+func TestExitNodeSelectionHelpers(t *testing.T) {
+	routesMap := map[route.NetID][]*route.Route{
+		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
+		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
+		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
+	}
+
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
+
+	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
+	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
+}

client/server/server.go

@@ -1081,10 +1081,7 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
 
 	if err := s.cleanupConnection(); err != nil {
 		s.mutex.Unlock()
-		if errors.Is(err, ErrServiceNotUp) {
-			log.Debugf("Down called while service not up: %v", err)
-			return nil, err
-		}
+		// todo review to update the status in case any type of error
 		log.Errorf("failed to shut down properly: %v", err)
 		return nil, err
 	}
@@ -1157,7 +1154,7 @@ func (s *Server) cleanupConnection() error {
 	// making the run loop the sole owner of engine shutdown.
 	if engine != nil {
 		if err := engine.Stop(); err != nil {
-			log.Errorf("failed to stop engine during cleanup: %v", err)
+			return err
 		}
 	}
 

client/ssh/server/command_execution_unix.go

@@ -20,6 +20,8 @@ import (
 	"github.com/creack/pty"
 	"github.com/gliderlabs/ssh"
 	log "github.com/sirupsen/logrus"
+
+	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 )
 
 // ptyManager manages Pty file operations with thread safety
@@ -146,10 +148,10 @@ func (s *Server) createShellCommand(ctx context.Context, shell string, args []st
 
 // prepareCommandEnv prepares environment variables for command execution on Unix
 func (s *Server) prepareCommandEnv(_ *log.Entry, localUser *user.User, session ssh.Session) []string {
-	env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
+	env := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
 	env = append(env, prepareSSHEnv(session)...)
 	for _, v := range session.Environ() {
-		if acceptEnv(v) {
+		if shellutil.AcceptEnv(v) {
 			env = append(env, v)
 		}
 	}

client/ssh/server/command_execution_windows.go

@@ -15,6 +15,7 @@ import (
 	"golang.org/x/sys/windows"
 	"golang.org/x/sys/windows/registry"
 
+	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 	"github.com/netbirdio/netbird/client/ssh/server/winpty"
 )
 
@@ -243,14 +244,14 @@ func (s *Server) setUserEnvironmentVariables(envMap map[string]string, userProfi
 
 // prepareCommandEnv prepares environment variables for command execution on Windows
 func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, session ssh.Session) []string {
-	username, domain := parseUsername(localUser.Username)
+	username, domain := s.parseUsername(localUser.Username)
 	userEnv, err := s.getUserEnvironment(logger, username, domain)
 	if err != nil {
 		log.Debugf("failed to get user environment for %s\\%s, using fallback: %v", domain, username, err)
-		env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
+		env := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
 		env = append(env, prepareSSHEnv(session)...)
 		for _, v := range session.Environ() {
-			if acceptEnv(v) {
+			if shellutil.AcceptEnv(v) {
 				env = append(env, v)
 			}
 		}
@@ -260,7 +261,7 @@ func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, sess
 	env := userEnv
 	env = append(env, prepareSSHEnv(session)...)
 	for _, v := range session.Environ() {
-		if acceptEnv(v) {
+		if shellutil.AcceptEnv(v) {
 			env = append(env, v)
 		}
 	}
@@ -273,7 +274,7 @@ func (s *Server) handlePtyLogin(logger *log.Entry, session ssh.Session, privileg
 		return false
 	}
 
-	shell := getUserShell(privilegeResult.User.Uid)
+	shell := shellutil.GetUserShell(privilegeResult.User.Uid)
 	logger.Infof("starting interactive shell: %s", shell)
 
 	s.executeCommandWithPty(logger, session, nil, privilegeResult, ptyReq, nil)
@@ -383,8 +384,8 @@ func (s *Server) executeCommandWithPty(logger *log.Entry, session ssh.Session, _
 		return false
 	}
 
-	username, domain := parseUsername(localUser.Username)
-	shell := getUserShell(localUser.Uid)
+	username, domain := s.parseUsername(localUser.Username)
+	shell := shellutil.GetUserShell(localUser.Uid)
 
 	req := PtyExecutionRequest{
 		Shell:    shell,

client/ssh/server/getent_cgo_unix.go

@@ -1,24 +0,0 @@
-//go:build cgo && !osusergo && !windows
-
-package server
-
-import "os/user"
-
-// lookupWithGetent with CGO delegates directly to os/user.Lookup.
-// When CGO is enabled, os/user uses libc (getpwnam_r) which goes through
-// the NSS stack natively. If it fails, the user truly doesn't exist and
-// getent would also fail.
-func lookupWithGetent(username string) (*user.User, error) {
-	return user.Lookup(username)
-}
-
-// currentUserWithGetent with CGO delegates directly to os/user.Current.
-func currentUserWithGetent() (*user.User, error) {
-	return user.Current()
-}
-
-// groupIdsWithFallback with CGO delegates directly to user.GroupIds.
-// libc's getgrouplist handles NSS groups natively.
-func groupIdsWithFallback(u *user.User) ([]string, error) {
-	return u.GroupIds()
-}

client/ssh/server/getent_windows.go

@@ -1,26 +0,0 @@
-//go:build windows
-
-package server
-
-import "os/user"
-
-// lookupWithGetent on Windows just delegates to os/user.Lookup.
-// Windows does not use NSS/getent; its user lookup works without CGO.
-func lookupWithGetent(username string) (*user.User, error) {
-	return user.Lookup(username)
-}
-
-// currentUserWithGetent on Windows just delegates to os/user.Current.
-func currentUserWithGetent() (*user.User, error) {
-	return user.Current()
-}
-
-// getShellFromGetent is a no-op on Windows; shell resolution uses PowerShell detection.
-func getShellFromGetent(_ string) string {
-	return ""
-}
-
-// groupIdsWithFallback on Windows just delegates to u.GroupIds().
-func groupIdsWithFallback(u *user.User) ([]string, error) {
-	return u.GroupIds()
-}

client/ssh/server/privileges_other.go

@@ -1,15 +0,0 @@
-//go:build !windows
-
-package server
-
-// isProcessElevated is only meaningful on Windows; other platforms use the
-// effective UID check in isCurrentProcessPrivileged.
-func isProcessElevated() bool {
-	return false
-}
-
-// isWindowsAccountPrivileged is only reachable on Windows. Fail closed if it
-// is ever called on another platform.
-func isWindowsAccountPrivileged(string) bool {
-	return true
-}

client/ssh/server/privileges_windows.go

@@ -1,223 +0,0 @@
-//go:build windows
-
-package server
-
-import (
-	"fmt"
-	"strings"
-	"unsafe"
-
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/sys/windows"
-)
-
-var (
-	netapi32                  = windows.NewLazySystemDLL("netapi32.dll")
-	procNetUserGetLocalGroups = netapi32.NewProc("NetUserGetLocalGroups")
-)
-
-const (
-	// lgIncludeIndirect makes NetUserGetLocalGroups also return local groups
-	// the user belongs to through a global group.
-	lgIncludeIndirect  = 0x1
-	maxPreferredLength = 0xFFFFFFFF
-)
-
-// localGroupUsersInfo0 mirrors LOCALGROUP_USERS_INFO_0.
-type localGroupUsersInfo0 struct {
-	name *uint16
-}
-
-// isProcessElevated reports whether the current process token is elevated
-// (TokenElevation): true for elevated administrators, the built-in
-// Administrator, administrators with UAC disabled, and SYSTEM; false for
-// standard users and administrators running with a UAC-filtered token.
-func isProcessElevated() bool {
-	return windows.GetCurrentProcessToken().IsElevated()
-}
-
-// isWindowsAccountPrivileged reports whether the account is privileged on this
-// machine: a well-known service account, a built-in Administrator (RID 500),
-// or a member of the local Administrators group, directly or through nested
-// groups. Evaluation errors count as privileged so policy checks fail closed.
-func isWindowsAccountPrivileged(username string) bool {
-	sid, _, _, err := windows.LookupSID("", username)
-	if err != nil {
-		log.Warnf("privilege check: SID lookup for %q failed, treating as privileged: %v", username, err)
-		return true
-	}
-
-	if isPrivilegedUserSID(sid) {
-		return true
-	}
-
-	member, err := isLocalAdminsMember(username)
-	if err != nil {
-		log.Warnf("privilege check: cannot determine Administrators membership for %q, treating as privileged: %v", username, err)
-		return true
-	}
-	return member
-}
-
-// isPrivilegedUserSID reports whether the SID itself identifies a privileged
-// principal, without consulting group membership.
-func isPrivilegedUserSID(sid *windows.SID) bool {
-	wellKnown := []windows.WELL_KNOWN_SID_TYPE{
-		windows.WinLocalSystemSid,
-		windows.WinLocalServiceSid,
-		windows.WinNetworkServiceSid,
-		windows.WinBuiltinAdministratorsSid,
-	}
-	for _, sidType := range wellKnown {
-		if sid.IsWellKnown(sidType) {
-			return true
-		}
-	}
-	return isBuiltinAdministratorSID(sid)
-}
-
-// isBuiltinAdministratorSID reports whether the SID is a machine or domain
-// built-in Administrator account (S-1-5-21-...-500). RID 500 is reserved for
-// that account; it can be renamed but cannot be removed from the
-// Administrators group.
-func isBuiltinAdministratorSID(sid *windows.SID) bool {
-	if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY {
-		return false
-	}
-	count := sid.SubAuthorityCount()
-	if count < 2 || sid.SubAuthority(0) != 21 {
-		return false
-	}
-	return sid.SubAuthority(uint32(count-1)) == 500
-}
-
-// isLocalAdminsMember reports whether the account is a member of the local
-// Administrators group.
-//
-// Local accounts are checked against the local SAM, which is authoritative for
-// them and, unlike a token, cannot under-report: UAC filters the tokens of
-// local administrators, and a filtered token carries Administrators as
-// deny-only, which a membership check on the token would read as "not a
-// member". Domain accounts are exempt from that filtering, so for them an S4U
-// token is preferred because its group list is LSA's transitive expansion and
-// therefore covers nested and universal groups plus the machine's own local
-// groups. NetUserGetLocalGroups expands only one global-group hop but needs no
-// logon, so it serves as the fallback when no token can be obtained.
-func isLocalAdminsMember(username string) (bool, error) {
-	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
-	if err != nil {
-		return false, fmt.Errorf("create Administrators SID: %w", err)
-	}
-
-	account, domain := parseUsername(username)
-	if NewPrivilegeDropper().isLocalUser(domain) {
-		return localGroupsContainSID(account, adminSid)
-	}
-
-	member, s4uErr := s4uTokenIsMember(account, domain, adminSid)
-	if s4uErr == nil {
-		return member, nil
-	}
-	log.Debugf("privilege check: S4U membership check for %q failed, falling back to local group enumeration: %v", username, s4uErr)
-
-	member, err = localGroupsContainSID(buildUserCpn(account, domain), adminSid)
-	if err != nil {
-		return false, fmt.Errorf("S4U check: %w; local group enumeration: %w", s4uErr, err)
-	}
-	return member, nil
-}
-
-// s4uTokenIsMember obtains an S4U token for the account and checks whether the
-// given SID is enabled in it.
-func s4uTokenIsMember(account, domain string, sid *windows.SID) (bool, error) {
-	token, err := generateS4UUserToken(log.NewEntry(log.StandardLogger()), account, domain)
-	if err != nil {
-		return false, err
-	}
-	defer func() {
-		if err := windows.CloseHandle(token); err != nil {
-			log.Debugf("close S4U token: %v", err)
-		}
-	}()
-	return windows.Token(token).IsMember(sid)
-}
-
-// localGroupsContainSID reports whether the wanted group is among the local
-// groups the account belongs to, directly or through a global group.
-//
-// The wanted SID is resolved to its group name once and compared against the
-// enumerated names. Well-known SIDs resolve from a static table, so that lookup
-// needs no domain controller, and it keeps the comparison correct for a renamed
-// or localized group because both sides then carry the new name. Resolving each
-// enumerated name back to a SID instead would add a lookup per group that can
-// block until it times out while a domain controller is unreachable, and cannot
-// change the outcome: the names enumerated here are local groups of this
-// machine, whose names are unique, so a name match identifies the group.
-//
-// A failure to resolve the wanted SID is returned rather than reported as
-// "not a member", so a privilege check built on this fails closed.
-func localGroupsContainSID(username string, want *windows.SID) (bool, error) {
-	wantName, _, _, err := want.LookupAccount("")
-	if err != nil {
-		return false, fmt.Errorf("resolve group SID %s to a name: %w", want, err)
-	}
-
-	groups, err := netUserGetLocalGroups(username)
-	if err != nil {
-		return false, err
-	}
-
-	for _, group := range groups {
-		if strings.EqualFold(group, wantName) {
-			return true, nil
-		}
-	}
-	return false, nil
-}
-
-// netUserGetLocalGroups returns the names of the local groups the account is a
-// member of, including indirect membership through global groups.
-func netUserGetLocalGroups(username string) ([]string, error) {
-	name16, err := windows.UTF16PtrFromString(username)
-	if err != nil {
-		return nil, fmt.Errorf("convert username: %w", err)
-	}
-
-	var buf *byte
-	var entriesRead, totalEntries uint32
-	status, _, _ := procNetUserGetLocalGroups.Call(
-		0, // local server
-		uintptr(unsafe.Pointer(name16)),
-		0, // level 0: LOCALGROUP_USERS_INFO_0
-		lgIncludeIndirect,
-		uintptr(unsafe.Pointer(&buf)),
-		maxPreferredLength,
-		uintptr(unsafe.Pointer(&entriesRead)),
-		uintptr(unsafe.Pointer(&totalEntries)),
-	)
-	if status != 0 {
-		return nil, fmt.Errorf("NetUserGetLocalGroups for %q: status %d", username, status)
-	}
-	if buf == nil {
-		return nil, nil
-	}
-	defer func() {
-		if err := windows.NetApiBufferFree(buf); err != nil {
-			log.Debugf("free NetApi buffer: %v", err)
-		}
-	}()
-
-	// MAX_PREFERRED_LENGTH makes the API allocate as much as it needs, so a
-	// short read is not expected. Report it rather than silently returning a
-	// subset of the account's groups.
-	if entriesRead != totalEntries {
-		return nil, fmt.Errorf("NetUserGetLocalGroups for %q returned %d of %d groups", username, entriesRead, totalEntries)
-	}
-
-	entries := unsafe.Slice((*localGroupUsersInfo0)(unsafe.Pointer(buf)), entriesRead)
-	groups := make([]string, 0, entriesRead)
-	for _, entry := range entries {
-		groups = append(groups, windows.UTF16PtrToString(entry.name))
-	}
-	return groups, nil
-}

client/ssh/server/privileges_windows_test.go

@@ -1,256 +0,0 @@
-//go:build windows
-
-package server
-
-import (
-	"os/user"
-	"testing"
-	"unsafe"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"golang.org/x/sys/windows"
-)
-
-// filterNormalAccount limits NetUserEnum to normal user accounts.
-const filterNormalAccount = 0x2
-
-// userInfo0 mirrors USER_INFO_0.
-type userInfo0 struct {
-	name *uint16
-}
-
-func mustParseSID(t *testing.T, s string) *windows.SID {
-	t.Helper()
-	sid, err := windows.StringToSid(s)
-	require.NoError(t, err, "parse SID %s", s)
-	return sid
-}
-
-// localAccountNames returns the names of the local user accounts.
-func localAccountNames(t *testing.T) []string {
-	t.Helper()
-
-	var buf *byte
-	var entriesRead, totalEntries, resume uint32
-	err := windows.NetUserEnum(nil, 0, filterNormalAccount, &buf, maxPreferredLength,
-		&entriesRead, &totalEntries, &resume)
-	require.NoError(t, err, "enumerate local users")
-	t.Cleanup(func() {
-		require.NoError(t, windows.NetApiBufferFree(buf), "free NetApi buffer")
-	})
-
-	entries := unsafe.Slice((*userInfo0)(unsafe.Pointer(buf)), entriesRead)
-	names := make([]string, 0, entriesRead)
-	for _, entry := range entries {
-		names = append(names, windows.UTF16PtrToString(entry.name))
-	}
-	return names
-}
-
-// localAccountNameByRID returns the name of the local account carrying the
-// given RID. Accounts such as Administrator and Guest can be renamed and are
-// localized, so tests must not name them literally.
-func localAccountNameByRID(t *testing.T, rid uint32) string {
-	t.Helper()
-
-	for _, name := range localAccountNames(t) {
-		sid, _, _, err := windows.LookupSID("", name)
-		if err != nil {
-			continue
-		}
-		if sid.IdentifierAuthority() != windows.SECURITY_NT_AUTHORITY {
-			continue
-		}
-		count := sid.SubAuthorityCount()
-		if count < 2 || sid.SubAuthority(0) != 21 {
-			continue
-		}
-		if sid.SubAuthority(uint32(count-1)) == rid {
-			return name
-		}
-	}
-
-	t.Fatalf("no local account with RID %d", rid)
-	return ""
-}
-
-// wellKnownAccountName resolves a well-known SID to the qualified account name
-// the local system uses for it, which is localized.
-func wellKnownAccountName(t *testing.T, sidType windows.WELL_KNOWN_SID_TYPE) string {
-	t.Helper()
-
-	sid, err := windows.CreateWellKnownSid(sidType)
-	require.NoError(t, err, "create well-known SID")
-	name, domain, _, err := sid.LookupAccount("")
-	require.NoError(t, err, "resolve %s to an account name", sid)
-	if domain == "" {
-		return name
-	}
-	return domain + `\` + name
-}
-
-func TestIsBuiltinAdministratorSID(t *testing.T) {
-	tests := []struct {
-		name string
-		sid  string
-		want bool
-	}{
-		{"machine_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true},
-		{"domain_administrator", "S-1-5-21-3390233681-4087452608-412898826-500", true},
-		{"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false},
-		{"guest_account", "S-1-5-21-1111111111-2222222222-3333333333-501", false},
-		{"domain_admins_group", "S-1-5-21-1111111111-2222222222-3333333333-512", false},
-		{"system", "S-1-5-18", false},
-		{"administrators_group", "S-1-5-32-544", false},
-		{"non_nt_authority", "S-1-1-0", false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			result := isBuiltinAdministratorSID(mustParseSID(t, tt.sid))
-			assert.Equal(t, tt.want, result, "RID 500 detection for %s", tt.sid)
-		})
-	}
-}
-
-func TestIsPrivilegedUserSID(t *testing.T) {
-	tests := []struct {
-		name string
-		sid  string
-		want bool
-	}{
-		{"local_system", "S-1-5-18", true},
-		{"local_service", "S-1-5-19", true},
-		{"network_service", "S-1-5-20", true},
-		{"administrators_group", "S-1-5-32-544", true},
-		{"builtin_administrator", "S-1-5-21-1111111111-2222222222-3333333333-500", true},
-		{"regular_user", "S-1-5-21-1111111111-2222222222-3333333333-1001", false},
-		{"users_group", "S-1-5-32-545", false},
-		{"everyone", "S-1-1-0", false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			result := isPrivilegedUserSID(mustParseSID(t, tt.sid))
-			assert.Equal(t, tt.want, result, "SID privilege classification for %s", tt.sid)
-		})
-	}
-}
-
-func TestIsWindowsAccountPrivileged(t *testing.T) {
-	tests := []struct {
-		name     string
-		username string
-		want     bool
-	}{
-		{"system", wellKnownAccountName(t, windows.WinLocalSystemSid), true},
-		{"local_service", wellKnownAccountName(t, windows.WinLocalServiceSid), true},
-		{"network_service", wellKnownAccountName(t, windows.WinNetworkServiceSid), true},
-		{"administrators_group", wellKnownAccountName(t, windows.WinBuiltinAdministratorsSid), true},
-		// The built-in Administrator (RID 500) and Guest (RID 501) accounts
-		// exist on every Windows installation, though they may be disabled.
-		{"builtin_administrator", localAccountNameByRID(t, 500), true},
-		{"guest", localAccountNameByRID(t, 501), false},
-		// Unresolvable accounts fail closed.
-		{"nonexistent_user", "netbird-no-such-user", true},
-		{"empty_username", "", true},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			result := isWindowsAccountPrivileged(tt.username)
-			assert.Equal(t, tt.want, result, "account privilege classification for %q", tt.username)
-		})
-	}
-}
-
-func TestIsProcessElevated(t *testing.T) {
-	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
-	require.NoError(t, err, "create Administrators SID")
-
-	// Token(0) makes CheckTokenMembership evaluate the caller's own token.
-	member, err := windows.Token(0).IsMember(adminSid)
-	require.NoError(t, err, "check own Administrators membership")
-
-	elevated := isProcessElevated()
-	t.Logf("member of Administrators: %v, token elevated: %v", member, elevated)
-
-	// An enabled Administrators SID in the token implies an elevated token.
-	// CI runs this test as SYSTEM, which satisfies both.
-	if member {
-		assert.True(t, elevated, "token with enabled Administrators membership must report elevated")
-	}
-}
-
-// TestS4UMembershipAgreesWithLocalGroups exercises the S4U token path used
-// for domain accounts. S4U logons need the TCB privilege, so the test runs
-// only as SYSTEM (which is how CI executes the suite). For local accounts the
-// token's Administrators membership must agree with the SAM enumeration.
-func TestS4UMembershipAgreesWithLocalGroups(t *testing.T) {
-	system, err := windows.CreateWellKnownSid(windows.WinLocalSystemSid)
-	require.NoError(t, err, "create SYSTEM SID")
-	current, err := user.Current()
-	require.NoError(t, err, "get current user")
-	if current.Uid != system.String() {
-		t.Skipf("S4U logon requires SYSTEM (running as %s)", current.Username)
-	}
-
-	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
-	require.NoError(t, err, "create Administrators SID")
-
-	checked := 0
-	for _, name := range localAccountNames(t) {
-		viaToken, err := s4uTokenIsMember(name, ".", adminSid)
-		if err != nil {
-			// Disabled or logon-restricted accounts cannot get an S4U logon.
-			t.Logf("skipping %s: %v", name, err)
-			continue
-		}
-		viaSAM, err := localGroupsContainSID(name, adminSid)
-		require.NoError(t, err, "enumerate local groups for %s", name)
-
-		assert.Equal(t, viaSAM, viaToken, "S4U token and SAM enumeration must agree on Administrators membership for %s", name)
-		checked++
-	}
-	t.Logf("checked %d local accounts via S4U", checked)
-}
-
-// TestLocalGroupsContainSID_Administrator checks the positive case against the
-// built-in Administrator, a member of Administrators on every installation.
-func TestLocalGroupsContainSID_Administrator(t *testing.T) {
-	adminSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
-	require.NoError(t, err, "create Administrators SID")
-
-	administrator := localAccountNameByRID(t, 500)
-	member, err := localGroupsContainSID(administrator, adminSid)
-	require.NoError(t, err, "enumerate local groups for %s", administrator)
-	assert.True(t, member, "%s is a member of the Administrators group", administrator)
-}
-
-// TestLocalGroupsContainSID_UnresolvableGroupFailsClosed covers a wanted SID
-// that resolves to no group: the error must surface rather than being reported
-// as "not a member", so the privilege check treats the account as privileged.
-func TestLocalGroupsContainSID_UnresolvableGroupFailsClosed(t *testing.T) {
-	unknown := mustParseSID(t, "S-1-5-21-1111111111-2222222222-3333333333-4444")
-
-	_, err := localGroupsContainSID(localAccountNameByRID(t, 500), unknown)
-	require.Error(t, err, "must report an error when the wanted group cannot be identified")
-}
-
-func TestLocalGroupsContainSID_Guest(t *testing.T) {
-	guestsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinGuestsSid)
-	require.NoError(t, err, "create Guests SID")
-	adminsSid, err := windows.CreateWellKnownSid(windows.WinBuiltinAdministratorsSid)
-	require.NoError(t, err, "create Administrators SID")
-
-	guest := localAccountNameByRID(t, 501)
-
-	inGuests, err := localGroupsContainSID(guest, guestsSid)
-	require.NoError(t, err, "enumerate local groups for %s", guest)
-	assert.True(t, inGuests, "%s is a member of the Guests group", guest)
-
-	inAdmins, err := localGroupsContainSID(guest, adminsSid)
-	require.NoError(t, err, "enumerate local groups for %s", guest)
-	assert.False(t, inAdmins, "%s is not a member of the Administrators group", guest)
-}

client/ssh/server/server_config_test.go

@@ -420,13 +420,6 @@ func TestServer_PortConflictHandling(t *testing.T) {
 
 func TestServer_IsPrivilegedUser(t *testing.T) {
 
-	// Windows classification depends on account SIDs and group membership, and
-	// the accounts involved carry localized, renameable names. It is covered by
-	// TestIsWindowsAccountPrivileged, which resolves them from well-known SIDs.
-	if runtime.GOOS == "windows" {
-		t.Skip("covered by TestIsWindowsAccountPrivileged")
-	}
-
 	tests := []struct {
 		username    string
 		expected    bool
@@ -447,11 +440,39 @@ func TestServer_IsPrivilegedUser(t *testing.T) {
 			expected:    false,
 			description: "empty username should not be privileged",
 		},
-		{
-			username:    "Administrator",
-			expected:    false,
-			description: "Administrator should not be privileged on non-Windows systems",
-		},
+	}
+
+	// Add Windows-specific tests
+	if runtime.GOOS == "windows" {
+		tests = append(tests, []struct {
+			username    string
+			expected    bool
+			description string
+		}{
+			{
+				username:    "Administrator",
+				expected:    true,
+				description: "Administrator should be considered privileged on Windows",
+			},
+			{
+				username:    "administrator",
+				expected:    true,
+				description: "administrator should be considered privileged on Windows (case insensitive)",
+			},
+		}...)
+	} else {
+		// On non-Windows systems, Administrator should not be privileged
+		tests = append(tests, []struct {
+			username    string
+			expected    bool
+			description string
+		}{
+			{
+				username:    "Administrator",
+				expected:    false,
+				description: "Administrator should not be privileged on non-Windows systems",
+			},
+		}...)
 	}
 
 	for _, tt := range tests {

client/ssh/server/sftp_windows.go

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

client/ssh/server/ssh_env.go

@@ -0,0 +1,35 @@
+package server
+
+import (
+	"fmt"
+	"net"
+	"strconv"
+
+	"github.com/gliderlabs/ssh"
+)
+
+// prepareSSHEnv prepares SSH protocol-specific environment variables
+// These variables provide information about the SSH connection itself
+func prepareSSHEnv(session ssh.Session) []string {
+	remoteAddr := session.RemoteAddr()
+	localAddr := session.LocalAddr()
+
+	remoteHost, remotePort, err := net.SplitHostPort(remoteAddr.String())
+	if err != nil {
+		remoteHost = remoteAddr.String()
+		remotePort = "0"
+	}
+
+	localHost, localPort, err := net.SplitHostPort(localAddr.String())
+	if err != nil {
+		localHost = localAddr.String()
+		localPort = strconv.Itoa(InternalSSHPort)
+	}
+
+	return []string{
+		// SSH_CLIENT format: "client_ip client_port server_port"
+		fmt.Sprintf("SSH_CLIENT=%s %s %s", remoteHost, remotePort, localPort),
+		// SSH_CONNECTION format: "client_ip client_port server_ip server_port"
+		fmt.Sprintf("SSH_CONNECTION=%s %s %s %s", remoteHost, remotePort, localHost, localPort),
+	}
+}

client/ssh/server/user_utils.go

@@ -9,6 +9,8 @@ import (
 	"strings"
 
 	log "github.com/sirupsen/logrus"
+
+	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 )
 
 var (
@@ -16,17 +18,19 @@ var (
 	ErrPrivilegedUserSwitch = errors.New("cannot switch to privileged user - current user lacks required privileges")
 )
 
+// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.)
+func isPlatformUnix() bool {
+	return getCurrentOS() != "windows"
+}
+
 // Dependency injection variables for testing - allows mocking dynamic runtime checks
 var (
-	getCurrentUser         = currentUserWithGetent
-	lookupUser             = lookupWithGetent
+	getCurrentUser         = shellutil.CurrentUserWithGetent
+	lookupUser             = shellutil.LookupWithGetent
 	getCurrentOS           = func() string { return runtime.GOOS }
 	getIsProcessPrivileged = isCurrentProcessPrivileged
 
 	getEuid = os.Geteuid
-
-	getProcessElevated          = isProcessElevated
-	getWindowsAccountPrivileged = isWindowsAccountPrivileged
 )
 
 const (
@@ -63,13 +67,6 @@ type PrivilegeCheckResult struct {
 	RequiresUserSwitching bool
 }
 
-// privilegeCheckContext holds all context needed for privilege checking
-type privilegeCheckContext struct {
-	currentUser           *user.User
-	currentUserPrivileged bool
-	allowRoot             bool
-}
-
 // CheckPrivileges performs comprehensive privilege checking for all SSH features.
 // This is the single source of truth for privilege decisions across the SSH server.
 func (s *Server) CheckPrivileges(req PrivilegeCheckRequest) PrivilegeCheckResult {
@@ -180,42 +177,6 @@ func (s *Server) resolveRequestedUser(requestedUsername string) (*user.User, err
 	return u, nil
 }
 
-// SetAllowRootLogin configures root login access
-func (s *Server) SetAllowRootLogin(allow bool) {
-	s.mu.Lock()
-	defer s.mu.Unlock()
-	s.allowRootLogin = allow
-}
-
-// userNameLookup performs user lookup with root login permission check
-func (s *Server) userNameLookup(username string) (*user.User, error) {
-	result, err := s.userPrivilegeCheck(username)
-	if err != nil {
-		return nil, err
-	}
-	return result.User, nil
-}
-
-// userPrivilegeCheck performs user lookup with full privilege check result
-func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) {
-	result := s.CheckPrivileges(PrivilegeCheckRequest{
-		RequestedUsername:         username,
-		FeatureSupportsUserSwitch: true,
-		FeatureName:               FeatureSSHLogin,
-	})
-
-	if !result.Allowed {
-		return result, result.Error
-	}
-
-	return result, nil
-}
-
-// isPlatformUnix returns true for Unix-like platforms (Linux, macOS, etc.)
-func isPlatformUnix() bool {
-	return getCurrentOS() != "windows"
-}
-
 // isSameResolvedUser compares two resolved user identities
 func isSameResolvedUser(user1, user2 *user.User) bool {
 	if user1 == nil || user2 == nil {
@@ -224,6 +185,13 @@ func isSameResolvedUser(user1, user2 *user.User) bool {
 	return user1.Uid == user2.Uid
 }
 
+// privilegeCheckContext holds all context needed for privilege checking
+type privilegeCheckContext struct {
+	currentUser           *user.User
+	currentUserPrivileged bool
+	allowRoot             bool
+}
+
 // isSameUser checks if two usernames refer to the same user
 // SECURITY: This function must be conservative - it should only return true
 // when we're certain both usernames refer to the exact same user identity
@@ -287,24 +255,159 @@ func isWindowsSameUser(requestedUsername, currentUsername string) bool {
 	return strings.EqualFold(reqDomain, curDomain)
 }
 
+// SetAllowRootLogin configures root login access
+func (s *Server) SetAllowRootLogin(allow bool) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.allowRootLogin = allow
+}
+
+// userNameLookup performs user lookup with root login permission check
+func (s *Server) userNameLookup(username string) (*user.User, error) {
+	result := s.CheckPrivileges(PrivilegeCheckRequest{
+		RequestedUsername:         username,
+		FeatureSupportsUserSwitch: true,
+		FeatureName:               FeatureSSHLogin,
+	})
+
+	if !result.Allowed {
+		return nil, result.Error
+	}
+
+	return result.User, nil
+}
+
+// userPrivilegeCheck performs user lookup with full privilege check result
+func (s *Server) userPrivilegeCheck(username string) (PrivilegeCheckResult, error) {
+	result := s.CheckPrivileges(PrivilegeCheckRequest{
+		RequestedUsername:         username,
+		FeatureSupportsUserSwitch: true,
+		FeatureName:               FeatureSSHLogin,
+	})
+
+	if !result.Allowed {
+		return result, result.Error
+	}
+
+	return result, nil
+}
+
 // isPrivilegedUsername checks if the given username represents a privileged user across platforms.
-// On Unix: root.
-// On Windows: well-known service accounts, built-in Administrator accounts,
-// and members of the local Administrators group; handles domain-qualified
-// usernames like "DOMAIN\user" or "user@domain.com".
+// On Unix: root
+// On Windows: Administrator, SYSTEM (case-insensitive)
+// Handles domain-qualified usernames like "DOMAIN\Administrator" or "user@domain.com"
 func isPrivilegedUsername(username string) bool {
 	if getCurrentOS() != "windows" {
 		return username == "root"
 	}
-	return getWindowsAccountPrivileged(username)
+
+	bareUsername := username
+	// Handle Windows domain format: DOMAIN\username
+	if idx := strings.LastIndex(username, `\`); idx != -1 {
+		bareUsername = username[idx+1:]
+	}
+	// Handle email-style format: username@domain.com
+	if idx := strings.Index(bareUsername, "@"); idx != -1 {
+		bareUsername = bareUsername[:idx]
+	}
+
+	return isWindowsPrivilegedUser(bareUsername)
+}
+
+// isWindowsPrivilegedUser checks if a bare username (domain already stripped) represents a Windows privileged account
+func isWindowsPrivilegedUser(bareUsername string) bool {
+	// common privileged usernames (case insensitive)
+	privilegedNames := []string{
+		"administrator",
+		"admin",
+		"root",
+		"system",
+		"localsystem",
+		"networkservice",
+		"localservice",
+	}
+
+	usernameLower := strings.ToLower(bareUsername)
+	for _, privilegedName := range privilegedNames {
+		if usernameLower == privilegedName {
+			return true
+		}
+	}
+
+	// computer accounts (ending with $) are not privileged by themselves
+	// They only gain privileges through group membership or specific SIDs
+
+	if targetUser, err := lookupUser(bareUsername); err == nil {
+		return isWindowsPrivilegedSID(targetUser.Uid)
+	}
+
+	return false
+}
+
+// isWindowsPrivilegedSID checks if a Windows SID represents a privileged account
+func isWindowsPrivilegedSID(sid string) bool {
+	privilegedSIDs := []string{
+		"S-1-5-18",     // Local System (SYSTEM)
+		"S-1-5-19",     // Local Service (NT AUTHORITY\LOCAL SERVICE)
+		"S-1-5-20",     // Network Service (NT AUTHORITY\NETWORK SERVICE)
+		"S-1-5-32-544", // Administrators group (BUILTIN\Administrators)
+		"S-1-5-500",    // Built-in Administrator account (local machine RID 500)
+	}
+
+	for _, privilegedSID := range privilegedSIDs {
+		if sid == privilegedSID {
+			return true
+		}
+	}
+
+	// Check for domain administrator accounts (RID 500 in any domain)
+	// Format: S-1-5-21-domain-domain-domain-500
+	// This is reliable as RID 500 is reserved for the domain Administrator account
+	if strings.HasPrefix(sid, "S-1-5-21-") && strings.HasSuffix(sid, "-500") {
+		return true
+	}
+
+	// Check for other well-known privileged RIDs in domain contexts
+	// RID 512 = Domain Admins group, RID 516 = Domain Controllers group
+	if strings.HasPrefix(sid, "S-1-5-21-") {
+		if strings.HasSuffix(sid, "-512") || // Domain Admins group
+			strings.HasSuffix(sid, "-516") || // Domain Controllers group
+			strings.HasSuffix(sid, "-519") { // Enterprise Admins group
+			return true
+		}
+	}
+
+	return false
 }
 
 // isCurrentProcessPrivileged checks if the current process is running with elevated privileges.
 // On Unix systems, this means running as root (UID 0).
-// On Windows, this means the process token is elevated (administrators, SYSTEM).
+// On Windows, this means running as Administrator or SYSTEM.
 func isCurrentProcessPrivileged() bool {
 	if getCurrentOS() == "windows" {
-		return getProcessElevated()
+		return isWindowsElevated()
 	}
 	return getEuid() == 0
 }
+
+// isWindowsElevated checks if the current process is running with elevated privileges on Windows
+func isWindowsElevated() bool {
+	currentUser, err := getCurrentUser()
+	if err != nil {
+		log.Errorf("failed to get current user for privilege check, assuming non-privileged: %v", err)
+		return false
+	}
+
+	if isWindowsPrivilegedSID(currentUser.Uid) {
+		log.Debugf("Windows user switching supported: running as privileged SID %s", currentUser.Uid)
+		return true
+	}
+
+	if isPrivilegedUsername(currentUser.Username) {
+		log.Debugf("Windows user switching supported: running as privileged username %s", currentUser.Username)
+		return true
+	}
+
+	log.Debugf("Windows user switching not supported: not running as privileged user (current: %s)", currentUser.Uid)
+	return false
+}

client/ssh/server/user_utils_test.go

@@ -4,7 +4,6 @@ import (
 	"errors"
 	"os/user"
 	"runtime"
-	"strings"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
@@ -28,8 +27,8 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 	originalLookupUser := lookupUser
 	originalGetCurrentOS := getCurrentOS
 	originalGetEuid := getEuid
-	originalGetProcessElevated := getProcessElevated
-	originalGetWindowsAccountPrivileged := getWindowsAccountPrivileged
+
+	// Reset caches to ensure clean test state
 
 	// Set test values - inject platform dependencies
 	getCurrentUser = func() (*user.User, error) {
@@ -54,31 +53,16 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 		return euid
 	}
 
-	// Simulate the Windows token elevation check based on the fixture user:
-	// the built-in Administrator (RID 500) and SYSTEM run elevated.
-	getProcessElevated = func() bool {
+	// Mock privilege detection based on the test user
+	getIsProcessPrivileged = func() bool {
 		if currentUser == nil {
 			return false
 		}
-		return currentUser.Uid == "S-1-5-18" || strings.HasSuffix(currentUser.Uid, "-500")
-	}
-
-	// Simulate the Windows account classifier for the fixture accounts.
-	// "root" does not exist on Windows; the real classifier fails closed on
-	// unresolvable accounts, so it counts as privileged here too.
-	getWindowsAccountPrivileged = func(username string) bool {
-		bare := username
-		if idx := strings.LastIndex(bare, `\`); idx != -1 {
-			bare = bare[idx+1:]
-		}
-		if idx := strings.Index(bare, "@"); idx != -1 {
-			bare = bare[:idx]
-		}
-		switch strings.ToLower(bare) {
-		case "administrator", "system", "root":
+		// Check both username and SID for Windows systems
+		if os == "windows" && isWindowsPrivilegedSID(currentUser.Uid) {
 			return true
 		}
-		return false
+		return isPrivilegedUsername(currentUser.Username)
 	}
 
 	// Return cleanup function
@@ -87,8 +71,10 @@ func setupTestDependencies(currentUser *user.User, currentUserErr error, os stri
 		lookupUser = originalLookupUser
 		getCurrentOS = originalGetCurrentOS
 		getEuid = originalGetEuid
-		getProcessElevated = originalGetProcessElevated
-		getWindowsAccountPrivileged = originalGetWindowsAccountPrivileged
+
+		getIsProcessPrivileged = isCurrentProcessPrivileged
+
+		// Reset caches after test
 	}
 }
 
@@ -435,9 +421,6 @@ func TestUsedFallback_MeansNoPrivilegeDropping(t *testing.T) {
 }
 
 func TestPrivilegedUsernameDetection(t *testing.T) {
-	// Windows classification is syscall-backed (SID resolution, group
-	// membership) and is covered by privileges_windows_test.go; here only the
-	// Unix logic and the platform dispatch are exercised.
 	tests := []struct {
 		name       string
 		username   string
@@ -449,9 +432,25 @@ func TestPrivilegedUsernameDetection(t *testing.T) {
 		{"unix_regular_user", "alice", "linux", false},
 		{"unix_root_capital", "Root", "linux", false}, // Case-sensitive
 
-		// Windows dispatch to the (mocked) account classifier
+		// Windows tests
 		{"windows_administrator", "Administrator", "windows", true},
+		{"windows_system", "SYSTEM", "windows", true},
+		{"windows_admin", "admin", "windows", true},
+		{"windows_admin_lowercase", "administrator", "windows", true}, // Case-insensitive
+		{"windows_domain_admin", "DOMAIN\\Administrator", "windows", true},
+		{"windows_email_admin", "admin@domain.com", "windows", true},
 		{"windows_regular_user", "alice", "windows", false},
+		{"windows_domain_user", "DOMAIN\\alice", "windows", false},
+		{"windows_localsystem", "localsystem", "windows", true},
+		{"windows_networkservice", "networkservice", "windows", true},
+		{"windows_localservice", "localservice", "windows", true},
+
+		// Computer accounts (these depend on current user context in real implementation)
+		{"windows_computer_account", "WIN2K19-C2$", "windows", false},      // Computer account by itself not privileged
+		{"windows_domain_computer", "DOMAIN\\COMPUTER$", "windows", false}, // Domain computer account
+
+		// Cross-platform
+		{"root_on_windows", "root", "windows", true}, // Root should be privileged everywhere
 	}
 
 	for _, tt := range tests {
@@ -461,7 +460,49 @@ func TestPrivilegedUsernameDetection(t *testing.T) {
 			defer cleanup()
 
 			result := isPrivilegedUsername(tt.username)
-			assert.Equal(t, tt.privileged, result, "privilege classification for %s on %s", tt.username, tt.platform)
+			assert.Equal(t, tt.privileged, result)
+		})
+	}
+}
+
+func TestWindowsPrivilegedSIDDetection(t *testing.T) {
+	tests := []struct {
+		name        string
+		sid         string
+		privileged  bool
+		description string
+	}{
+		// Well-known system accounts
+		{"system_account", "S-1-5-18", true, "Local System (SYSTEM)"},
+		{"local_service", "S-1-5-19", true, "Local Service"},
+		{"network_service", "S-1-5-20", true, "Network Service"},
+		{"administrators_group", "S-1-5-32-544", true, "Administrators group"},
+		{"builtin_administrator", "S-1-5-500", true, "Built-in Administrator"},
+
+		// Domain accounts
+		{"domain_administrator", "S-1-5-21-1234567890-1234567890-1234567890-500", true, "Domain Administrator (RID 500)"},
+		{"domain_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-512", true, "Domain Admins group"},
+		{"domain_controllers_group", "S-1-5-21-1234567890-1234567890-1234567890-516", true, "Domain Controllers group"},
+		{"enterprise_admins_group", "S-1-5-21-1234567890-1234567890-1234567890-519", true, "Enterprise Admins group"},
+
+		// Regular users
+		{"regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1001", false, "Regular domain user"},
+		{"another_regular_user", "S-1-5-21-1234567890-1234567890-1234567890-1234", false, "Another regular user"},
+		{"local_user", "S-1-5-21-1234567890-1234567890-1234567890-1000", false, "Local regular user"},
+
+		// Groups that are not privileged
+		{"domain_users", "S-1-5-21-1234567890-1234567890-1234567890-513", false, "Domain Users group"},
+		{"power_users", "S-1-5-32-547", false, "Power Users group"},
+
+		// Invalid SIDs
+		{"malformed_sid", "S-1-5-invalid", false, "Malformed SID"},
+		{"empty_sid", "", false, "Empty SID"},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			result := isWindowsPrivilegedSID(tt.sid)
+			assert.Equal(t, tt.privileged, result, "Failed for %s: %s", tt.description, tt.sid)
 		})
 	}
 }

client/ssh/server/userswitching_unix.go

@@ -16,6 +16,8 @@ import (
 
 	"github.com/gliderlabs/ssh"
 	log "github.com/sirupsen/logrus"
+
+	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 )
 
 // POSIX portable filename character set regex: [a-zA-Z0-9._-]
@@ -160,7 +162,7 @@ func (s *Server) parseUserCredentials(localUser *user.User) (uint32, uint32, []u
 // getSupplementaryGroups retrieves supplementary group IDs for a user.
 // Uses id/getent fallback for NSS users in CGO_ENABLED=0 builds.
 func (s *Server) getSupplementaryGroups(u *user.User) ([]uint32, error) {
-	groupIDStrings, err := groupIdsWithFallback(u)
+	groupIDStrings, err := shellutil.GroupIdsWithFallback(u)
 	if err != nil {
 		return nil, fmt.Errorf("get group IDs for user %s: %w", u.Username, err)
 	}
@@ -196,7 +198,7 @@ func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, l
 		GID:        gid,
 		Groups:     groups,
 		WorkingDir: localUser.HomeDir,
-		Shell:      getUserShell(localUser.Uid),
+		Shell:      shellutil.GetUserShell(localUser.Uid),
 		Command:    session.RawCommand(),
 		PTY:        hasPty,
 	}
@@ -228,7 +230,7 @@ func (s *Server) createPtyCommand(privilegeResult PrivilegeCheckResult, ptyReq s
 func (s *Server) createDirectPtyCommand(session ssh.Session, localUser *user.User, ptyReq ssh.Pty) *exec.Cmd {
 	log.Debugf("creating direct Pty command for user %s (no user switching needed)", localUser.Username)
 
-	shell := getUserShell(localUser.Uid)
+	shell := shellutil.GetUserShell(localUser.Uid)
 	args := s.getShellCommandArgs(shell, session.RawCommand())
 
 	cmd := s.createShellCommand(session.Context(), shell, args)
@@ -245,12 +247,12 @@ func (s *Server) preparePtyEnv(localUser *user.User, ptyReq ssh.Pty, session ssh
 		termType = "xterm-256color"
 	}
 
-	env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
+	env := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
 	env = append(env, prepareSSHEnv(session)...)
 	env = append(env, fmt.Sprintf("TERM=%s", termType))
 
 	for _, v := range session.Environ() {
-		if acceptEnv(v) {
+		if shellutil.AcceptEnv(v) {
 			env = append(env, v)
 		}
 	}