Add tests

# Conflicts:
#	shared/relay/client/manager.go

client/android/client.go

@@ -247,6 +247,9 @@ 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
 			}

client/cmd/root.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"io"
 	"io/fs"
-	"net"
 	"os"
 	"os/signal"
 	"path"
@@ -80,8 +79,6 @@ var (
 	updateSettingsDisabled bool
 	captureEnabled         bool
 	networksDisabled       bool
-	socketOwner            string
-	strictSocketDisabled   bool
 
 	rootCmd = &cobra.Command{
 		Use:          "netbird",
@@ -146,12 +143,10 @@ func init() {
 
 	defaultDaemonAddr := "unix:///var/run/netbird.sock"
 	if runtime.GOOS == "windows" {
-		// 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"
+		defaultDaemonAddr = "tcp://127.0.0.1:41731"
 	}
 
-	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp|npipe]://[path|host:port|name]")
+	rootCmd.PersistentFlags().StringVar(&daemonAddr, "daemon-addr", defaultDaemonAddr, "Daemon service address to serve CLI requests [unix|tcp]://[path|host:port]")
 	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")
@@ -270,31 +265,16 @@ 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()
 
-	opts := []grpc.DialOption{
+	return grpc.DialContext(
+		ctx,
+		strings.TrimPrefix(addr, "tcp://"),
 		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

@@ -56,9 +56,6 @@ 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

@@ -5,7 +5,6 @@ package cmd
 import (
 	"context"
 	"fmt"
-	"runtime"
 	"time"
 
 	"github.com/kardianos/service"
@@ -14,31 +13,12 @@ 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")
@@ -57,13 +37,8 @@ func (p *program) Start(svc service.Service) error {
 	// Collect static system and platform information
 	system.UpdateStaticInfoAsync()
 
-	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)...)
+	// in any case, even if configuration does not exists we run daemon to serve CLI gRPC API.
+	p.serv = grpc.NewServer()
 
 	daemonListener, err := listenOnAddress(daemonAddr)
 	if err != nil {
@@ -87,8 +62,7 @@ func (p *program) Start(svc service.Service) error {
 			defer jsonListener.Close()
 		}
 
-		serveListener, err := secureDaemonListener(daemonListener)
-		if err != nil {
+		if err := daemonListener.chmodUnixSocket("daemon"); err != nil {
 			log.Error(err)
 			return
 		}
@@ -110,7 +84,6 @@ 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)
 			}
@@ -119,7 +92,7 @@ func (p *program) Start(svc service.Service) error {
 		}
 
 		log.Printf("started daemon server: %v", daemonListener.address)
-		if err := p.serv.Serve(serveListener); err != nil {
+		if err := p.serv.Serve(daemonListener.Listener); err != nil {
 			log.Errorf("failed to serve daemon requests: %v", err)
 		}
 	}()

client/cmd/service_installer.go

@@ -71,14 +71,6 @@ 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

@@ -32,8 +32,6 @@ 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"`
 }
 
@@ -88,8 +86,6 @@ func currentServiceParams() *serviceParams {
 		EnableCapture:         captureEnabled,
 		DisableNetworks:       networksDisabled,
 		EnableJSONSocket:      enableJSONSocket,
-		SocketOwner:           socketOwner,
-		DisableStrictSocket:   strictSocketDisabled,
 	}
 
 	if len(serviceEnvVars) > 0 {
@@ -169,14 +165,6 @@ 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

@@ -1,20 +0,0 @@
-//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

@@ -1,32 +0,0 @@
-//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

@@ -26,15 +26,6 @@ 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)
 	}
@@ -54,23 +45,13 @@ func parseListenAddress(addr string) (string, string, error) {
 	}
 
 	switch network {
-	case "unix", "tcp", "npipe":
+	case "unix", "tcp":
 		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

@@ -1,11 +0,0 @@
-//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

@@ -1,225 +0,0 @@
-//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/internal/ipcauth/creds_stub.go

@@ -1,13 +0,0 @@
-//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

@@ -1,48 +0,0 @@
-//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

@@ -1,142 +0,0 @@
-//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

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

@@ -1,47 +0,0 @@
-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

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

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

@@ -1,16 +0,0 @@
-//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

@@ -1,113 +0,0 @@
-//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/peer/worker_relay.go

@@ -54,19 +54,15 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	w.relaySupportedOnRemotePeer.Store(true)
 
 	// the relayManager will return with error in case if the connection has lost with relay server
-	currentRelayAddress, _, err := w.relayManager.RelayInstanceAddress()
+	_, _, err := w.relayManager.RelayInstanceAddress()
 	if err != nil {
 		w.log.Errorf("failed to handle new offer: %s", err)
 		return
 	}
 
-	srv := w.preferredRelayServer(currentRelayAddress, remoteOfferAnswer.RelaySrvAddress)
-	var serverIP netip.Addr
-	if srv == remoteOfferAnswer.RelaySrvAddress {
-		serverIP = remoteOfferAnswer.RelaySrvIP
-	}
-
-	relayedConn, err := w.relayManager.OpenConn(w.peerCtx, srv, w.config.Key, serverIP)
+	preferForeign := !w.isController
+	remoteRelayServer := relayClient.RelayServer{Addr: remoteOfferAnswer.RelaySrvAddress, IP: remoteOfferAnswer.RelaySrvIP}
+	relayedConn, err := w.relayManager.OpenConn(w.peerCtx, remoteRelayServer, w.config.Key, preferForeign)
 	if err != nil {
 		if errors.Is(err, relayClient.ErrConnAlreadyExists) {
 			w.log.Debugf("handled offer by reusing existing relay connection")
@@ -80,14 +76,13 @@ func (w *WorkerRelay) OnNewOffer(remoteOfferAnswer *OfferAnswer) {
 	w.relayedConn = relayedConn
 	w.relayLock.Unlock()
 
-	err = w.relayManager.AddCloseListener(srv, w.onRelayClientDisconnected)
-	if err != nil {
-		log.Errorf("failed to add close listener: %s", err)
+	if err := w.relayManager.AddCloseListener(relayedConn.RemoteAddr().String(), w.onRelayClientDisconnected); err != nil {
+		w.log.Errorf("failed to add close listener: %s", err)
 		_ = relayedConn.Close()
 		return
 	}
 
-	w.log.Debugf("peer conn opened via Relay: %s", srv)
+	w.log.Debugf("peer conn opened via Relay: %s", relayedConn.RemoteAddr())
 	go w.conn.onRelayConnectionIsReady(RelayConnInfo{
 		relayedConn:     relayedConn,
 		rosenpassPubKey: remoteOfferAnswer.RosenpassPubKey,
@@ -126,13 +121,6 @@ func (w *WorkerRelay) isRelaySupported(answer *OfferAnswer) bool {
 	return answer.RelaySrvAddress != ""
 }
 
-func (w *WorkerRelay) preferredRelayServer(myRelayAddress, remoteRelayAddress string) string {
-	if w.isController {
-		return myRelayAddress
-	}
-	return remoteRelayAddress
-}
-
 func (w *WorkerRelay) onRelayClientDisconnected() {
 	go w.conn.onRelayDisconnected()
 }

client/internal/shell/getent_cgo_unix.go

@@ -1,29 +0,0 @@
-//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_windows.go

@@ -1,31 +0,0 @@
-//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/ios/NetBirdSDK/client.go

@@ -233,6 +233,9 @@ 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
 			}

client/ssh/server/command_execution_unix.go

@@ -20,8 +20,6 @@ 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
@@ -148,10 +146,10 @@ 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 := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
+	env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
 	env = append(env, prepareSSHEnv(session)...)
 	for _, v := range session.Environ() {
-		if shellutil.AcceptEnv(v) {
+		if acceptEnv(v) {
 			env = append(env, v)
 		}
 	}

client/ssh/server/command_execution_windows.go

@@ -15,7 +15,6 @@ 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"
 )
 
@@ -248,10 +247,10 @@ func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, sess
 	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 := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
+		env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
 		env = append(env, prepareSSHEnv(session)...)
 		for _, v := range session.Environ() {
-			if shellutil.AcceptEnv(v) {
+			if acceptEnv(v) {
 				env = append(env, v)
 			}
 		}
@@ -261,7 +260,7 @@ func (s *Server) prepareCommandEnv(logger *log.Entry, localUser *user.User, sess
 	env := userEnv
 	env = append(env, prepareSSHEnv(session)...)
 	for _, v := range session.Environ() {
-		if shellutil.AcceptEnv(v) {
+		if acceptEnv(v) {
 			env = append(env, v)
 		}
 	}
@@ -274,7 +273,7 @@ func (s *Server) handlePtyLogin(logger *log.Entry, session ssh.Session, privileg
 		return false
 	}
 
-	shell := shellutil.GetUserShell(privilegeResult.User.Uid)
+	shell := getUserShell(privilegeResult.User.Uid)
 	logger.Infof("starting interactive shell: %s", shell)
 
 	s.executeCommandWithPty(logger, session, nil, privilegeResult, ptyReq, nil)
@@ -385,7 +384,7 @@ func (s *Server) executeCommandWithPty(logger *log.Entry, session ssh.Session, _
 	}
 
 	username, domain := s.parseUsername(localUser.Username)
-	shell := shellutil.GetUserShell(localUser.Uid)
+	shell := getUserShell(localUser.Uid)
 
 	req := PtyExecutionRequest{
 		Shell:    shell,

client/ssh/server/getent_cgo_unix.go

@@ -0,0 +1,24 @@
+//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_nocgo_unix.go

@@ -1,6 +1,6 @@
 //go:build (!cgo || osusergo) && !windows
 
-package shell
+package server
 
 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 := runGetentPasswd(username)
+	u, _, getentErr := runGetent(username)
 	if getentErr != nil {
 		log.Debugf("getent fallback for %q also failed: %v", username, getentErr)
 		return nil, stdErr
@@ -31,26 +31,8 @@ func LookupWithGetent(username string) (*user.User, error) {
 	return u, nil
 }
 
-// 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) {
+// 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
@@ -60,7 +42,7 @@ 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 := runGetentPasswd(uid)
+	u, _, getentErr := runGetent(uid)
 	if getentErr != nil {
 		return nil, stdErr
 	}
@@ -68,14 +50,14 @@ 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/ssh/server/getent_test.go

@@ -1,4 +1,4 @@
-package shell
+package server
 
 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/ssh/server/getent_unix.go

@@ -1,6 +1,6 @@
 //go:build !windows
 
-package shell
+package server
 
 import (
 	"context"
@@ -14,26 +14,19 @@ 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 := runGetentPasswd(userID)
+func getShellFromGetent(userID string) string {
+	_, shell, err := runGetent(userID)
 	if err != nil {
 		return ""
 	}
 	return shell
 }
 
-// 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) {
+// runGetent executes `getent passwd <query>` and returns the user and login shell.
+func runGetent(query string) (*user.User, string, error) {
 	if !validateGetentInput(query) {
 		return nil, "", fmt.Errorf("invalid getent input: %q", query)
 	}
@@ -49,24 +42,7 @@ func runGetentPasswd(query string) (*user.User, string, error) {
 	return parseGetentPasswd(string(out))
 }
 
-// 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".
+// 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 {
@@ -91,20 +67,6 @@ 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/ssh/server/getent_unix_test.go

@@ -1,6 +1,6 @@
 //go:build !windows
 
-package shell
+package server
 
 import (
 	"os/exec"
@@ -198,7 +198,7 @@ func TestRunGetent_RootUser(t *testing.T) {
 		t.Skip("getent not available on this system")
 	}
 
-	u, shell, err := runGetentPasswd("root")
+	u, shell, err := runGetent("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 := runGetentPasswd("0")
+	u, _, err := runGetent("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 := runGetentPasswd("nonexistent_user_xyzzy_12345")
+	_, _, err := runGetent("nonexistent_user_xyzzy_12345")
 	assert.Error(t, err)
 }
 
 func TestRunGetent_InvalidInput(t *testing.T) {
-	_, _, err := runGetentPasswd("")
+	_, _, err := runGetent("")
 	assert.Error(t, err)
 
-	_, _, err = runGetentPasswd("user\x00name")
+	_, _, err = runGetent("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 := runGetentPasswd("root")
+	_, _, err := runGetent("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 := runGetentPasswd(current.Username)
+	getentUser, _, err := runGetent(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 := runGetentPasswd(current.Uid)
+	getentUser, _, err := runGetent(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 := runGetentPasswd(current.Uid)
+		_, getentShell, getentErr := runGetent(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 := runGetentPasswd(uid)
+		_, getentShell, err := runGetent(uid)
 		if err != nil {
 			continue
 		}

client/ssh/server/getent_windows.go

@@ -0,0 +1,26 @@
+//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/shell.go

@@ -1,14 +1,17 @@
-package shell
+package server
 
 import (
 	"bufio"
 	"fmt"
+	"net"
 	"os"
 	"os/exec"
 	"os/user"
 	"runtime"
+	"strconv"
 	"strings"
 
+	"github.com/gliderlabs/ssh"
 	log "github.com/sirupsen/logrus"
 )
 
@@ -19,9 +22,9 @@ 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()
@@ -53,7 +56,7 @@ func getUnixUserShell(userID string) string {
 		return shell
 	}
 
-	if shell := GetShellFromGetent(userID); shell != "" {
+	if shell := getShellFromGetent(userID); shell != "" {
 		return shell
 	}
 
@@ -64,7 +67,7 @@ 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 {
@@ -98,8 +101,8 @@ 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`
@@ -114,9 +117,9 @@ func PrepareUserEnv(user *user.User, shell string) []string {
 	}
 }
 
-// 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 {
+// 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 {
 	varName := envVar
 	if idx := strings.Index(envVar, "="); idx != -1 {
 		varName = envVar[:idx]
@@ -153,3 +156,29 @@ 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/ssh/server/ssh_env.go

@@ -1,35 +0,0 @@
-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

@@ -9,8 +9,6 @@ import (
 	"strings"
 
 	log "github.com/sirupsen/logrus"
-
-	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 )
 
 var (
@@ -25,8 +23,8 @@ func isPlatformUnix() bool {
 
 // Dependency injection variables for testing - allows mocking dynamic runtime checks
 var (
-	getCurrentUser         = shellutil.CurrentUserWithGetent
-	lookupUser             = shellutil.LookupWithGetent
+	getCurrentUser         = currentUserWithGetent
+	lookupUser             = lookupWithGetent
 	getCurrentOS           = func() string { return runtime.GOOS }
 	getIsProcessPrivileged = isCurrentProcessPrivileged
 

client/ssh/server/userswitching_unix.go

@@ -16,8 +16,6 @@ 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._-]
@@ -162,7 +160,7 @@ 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 := shellutil.GroupIdsWithFallback(u)
+	groupIDStrings, err := groupIdsWithFallback(u)
 	if err != nil {
 		return nil, fmt.Errorf("get group IDs for user %s: %w", u.Username, err)
 	}
@@ -198,7 +196,7 @@ func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, l
 		GID:        gid,
 		Groups:     groups,
 		WorkingDir: localUser.HomeDir,
-		Shell:      shellutil.GetUserShell(localUser.Uid),
+		Shell:      getUserShell(localUser.Uid),
 		Command:    session.RawCommand(),
 		PTY:        hasPty,
 	}
@@ -230,7 +228,7 @@ 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 := shellutil.GetUserShell(localUser.Uid)
+	shell := getUserShell(localUser.Uid)
 	args := s.getShellCommandArgs(shell, session.RawCommand())
 
 	cmd := s.createShellCommand(session.Context(), shell, args)
@@ -247,12 +245,12 @@ func (s *Server) preparePtyEnv(localUser *user.User, ptyReq ssh.Pty, session ssh
 		termType = "xterm-256color"
 	}
 
-	env := shellutil.PrepareUserEnv(localUser, shellutil.GetUserShell(localUser.Uid))
+	env := prepareUserEnv(localUser, getUserShell(localUser.Uid))
 	env = append(env, prepareSSHEnv(session)...)
 	env = append(env, fmt.Sprintf("TERM=%s", termType))
 
 	for _, v := range session.Environ() {
-		if shellutil.AcceptEnv(v) {
+		if acceptEnv(v) {
 			env = append(env, v)
 		}
 	}

client/ssh/server/userswitching_windows.go

@@ -13,8 +13,6 @@ import (
 	"github.com/gliderlabs/ssh"
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/sys/windows"
-
-	shellutil "github.com/netbirdio/netbird/client/internal/shell"
 )
 
 // validateUsername validates Windows usernames according to SAM Account Name rules
@@ -106,7 +104,7 @@ func (s *Server) createExecutorCommand(logger *log.Entry, session ssh.Session, l
 func (s *Server) createUserSwitchCommand(logger *log.Entry, session ssh.Session, localUser *user.User) (*exec.Cmd, func(), error) {
 	username, domain := s.parseUsername(localUser.Username)
 
-	shell := shellutil.GetUserShell(localUser.Uid)
+	shell := getUserShell(localUser.Uid)
 
 	rawCmd := session.RawCommand()
 	var command string

go.mod

@@ -30,7 +30,6 @@ require (
 
 require (
 	github.com/DeRuina/timberjack v1.4.2
-	github.com/Microsoft/go-winio v0.6.2
 	github.com/awnumar/memguard v0.23.0
 	github.com/aws/aws-sdk-go-v2 v1.38.3
 	github.com/aws/aws-sdk-go-v2/aws/protocol/eventstream v1.7.1
@@ -114,7 +113,7 @@ require (
 	github.com/ti-mo/conntrack v0.5.1
 	github.com/ti-mo/netfilter v0.5.2
 	github.com/vmihailenco/msgpack/v5 v5.4.1
-	github.com/wailsapp/wails/v3 v3.0.0-alpha2.111
+	github.com/wailsapp/wails/v3 v3.0.0-alpha2.117
 	github.com/yusufpapurcu/wmi v1.2.4
 	github.com/zcalusic/sysinfo v1.1.3
 	go.opentelemetry.io/contrib/instrumentation/google.golang.org/grpc/otelgrpc v0.67.0
@@ -157,6 +156,7 @@ require (
 	github.com/Masterminds/goutils v1.1.1 // indirect
 	github.com/Masterminds/semver/v3 v3.4.0 // indirect
 	github.com/Masterminds/sprig/v3 v3.3.0 // indirect
+	github.com/Microsoft/go-winio v0.6.2 // indirect
 	github.com/adrg/xdg v0.5.3 // indirect
 	github.com/anmitsu/go-shlex v0.0.0-20200514113438-38f4b401e2be // indirect
 	github.com/apapsch/go-jsonmerge/v2 v2.0.0 // indirect
@@ -303,7 +303,6 @@ require (
 	github.com/tklauser/numcpus v0.10.0 // indirect
 	github.com/vishvananda/netns v0.0.5 // indirect
 	github.com/vmihailenco/tagparser/v2 v2.0.0 // indirect
-	github.com/wailsapp/wails/webview2 v1.0.27 // indirect
 	github.com/wlynxg/anet v0.0.5 // indirect
 	github.com/x448/float16 v0.8.4 // indirect
 	github.com/zeebo/blake3 v0.2.3 // indirect

go.sum

@@ -660,10 +660,8 @@ github.com/vmihailenco/msgpack/v5 v5.4.1 h1:cQriyiUvjTwOHg8QZaPihLWeRAAVoCpE00IU
 github.com/vmihailenco/msgpack/v5 v5.4.1/go.mod h1:GaZTsDaehaPpQVyxrf5mtQlH+pc21PIudVV/E3rRQok=
 github.com/vmihailenco/tagparser/v2 v2.0.0 h1:y09buUbR+b5aycVFQs/g70pqKVZNBmxwAhO7/IwNM9g=
 github.com/vmihailenco/tagparser/v2 v2.0.0/go.mod h1:Wri+At7QHww0WTrCBeu4J6bNtoV6mEfg5OIWRZA9qds=
-github.com/wailsapp/wails/v3 v3.0.0-alpha2.111 h1:MKx1nOnhnDuEGrRBmtxLOJq1NERwailu2cI4BvzWhi4=
-github.com/wailsapp/wails/v3 v3.0.0-alpha2.111/go.mod h1:wrdvmyeCsB/K3YqJDoH8E3MwcN8NXAMnEFaDTW46w60=
-github.com/wailsapp/wails/webview2 v1.0.27 h1:wjgAi/I8BBZ7kUGU8um3XF3ILEfzr96Q2Q1G4GPjMns=
-github.com/wailsapp/wails/webview2 v1.0.27/go.mod h1:zdM4jcO1IaC61RiJL5F1BzgoqBHFIdacz8gPr5exr0o=
+github.com/wailsapp/wails/v3 v3.0.0-alpha2.117 h1:udyjqPG3AIgkod5QDR/WblCkpV8R86BFPSrsWxSyt5Y=
+github.com/wailsapp/wails/v3 v3.0.0-alpha2.117/go.mod h1:74WH2FScMsgucZvHHvv7eOefDXCm/CjuIxqhhZgPhKg=
 github.com/wlynxg/anet v0.0.5 h1:J3VJGi1gvo0JwZ/P1/Yc/8p63SoW98B5dHkYDmpgvvU=
 github.com/wlynxg/anet v0.0.5/go.mod h1:eay5PRQr7fIVAMbTbchTnO9gG65Hg/uYGdc7mguHxoA=
 github.com/x448/float16 v0.8.4 h1:qLwI1I70+NjRFUR3zs1JPUCgaCXSh3SW62uAKT1mSBM=

proxy/internal/llm/bedrock_model.go

@@ -0,0 +1,38 @@
+package llm
+
+import (
+	"regexp"
+	"strings"
+)
+
+// bedrockRegionPrefixes are the cross-region inference-profile prefixes that
+// front a Bedrock model id (e.g. "eu.anthropic.claude-...").
+var bedrockRegionPrefixes = []string{"us.", "eu.", "apac.", "global."}
+
+// bedrockVersionSuffix matches the trailing "-vN[:N]" or "-YYYYMMDD-vN[:N]"
+// version/throughput suffix of a Bedrock model id.
+var bedrockVersionSuffix = regexp.MustCompile(`-(\d{8}-)?v\d+(:\d+)?$`)
+
+// NormalizeBedrockModel strips an ARN wrapper, a cross-region inference-profile
+// prefix, and the version/throughput suffix from a Bedrock model id so it
+// matches the catalog/pricing key, e.g.
+// "eu.anthropic.claude-sonnet-4-5-20250929-v1:0" -> "anthropic.claude-sonnet-4-5"
+// and the inference-profile ARN's last segment likewise. It is the single
+// source of truth shared by the request parser (which normalizes the request
+// model from the URL path) and the router (which normalizes the operator's
+// registered Bedrock model ids so both sides compare equal).
+func NormalizeBedrockModel(modelID string) string {
+	m := modelID
+	if strings.HasPrefix(m, "arn:") {
+		if i := strings.LastIndex(m, "/"); i >= 0 {
+			m = m[i+1:]
+		}
+	}
+	for _, p := range bedrockRegionPrefixes {
+		if strings.HasPrefix(m, p) {
+			m = m[len(p):]
+			break
+		}
+	}
+	return bedrockVersionSuffix.ReplaceAllString(m, "")
+}

proxy/internal/llm/bedrock_model_test.go

@@ -0,0 +1,23 @@
+package llm
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestNormalizeBedrockModel(t *testing.T) {
+	cases := map[string]string{
+		"eu.anthropic.claude-sonnet-4-5-20250929-v1:0": "anthropic.claude-sonnet-4-5",
+		"us.anthropic.claude-haiku-4-5":                "anthropic.claude-haiku-4-5",
+		"us.anthropic.claude-opus-4-8-20250101-v1:0":   "anthropic.claude-opus-4-8",
+		"anthropic.claude-sonnet-4-5-20250929-v1:0":    "anthropic.claude-sonnet-4-5",
+		"meta.llama3-3-70b-instruct-v1:0":              "meta.llama3-3-70b-instruct",
+		"amazon.nova-pro-v1:0":                         "amazon.nova-pro",
+		// Inference-profile ARN — model id lives in the last path segment.
+		"arn:aws:bedrock:eu-central-1:123456789012:inference-profile/eu.anthropic.claude-sonnet-4-5-20250929-v1:0": "anthropic.claude-sonnet-4-5",
+	}
+	for in, want := range cases {
+		require.Equal(t, want, NormalizeBedrockModel(in), "normalize %q", in)
+	}
+}

proxy/internal/middleware/builtin/llm_router/bedrock_route_test.go

@@ -0,0 +1,30 @@
+package llm_router
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+)
+
+// TestRouteClaimsModel_BedrockNormalizesCandidate guards the fix for the native
+// Bedrock routing gap: the request model reaches the router already normalized
+// (the parser strips the region/inference-profile prefix and version suffix),
+// so a provider registered with the raw inference-profile id must still match.
+func TestRouteClaimsModel_BedrockNormalizesCandidate(t *testing.T) {
+	route := ProviderRoute{Bedrock: true, Models: []string{"us.anthropic.claude-haiku-4-5"}}
+	assert.True(t, routeClaimsModel(route, "anthropic.claude-haiku-4-5"),
+		"raw region-prefixed Bedrock model must match the normalized request model")
+	assert.False(t, routeClaimsModel(route, "anthropic.claude-opus-4-8"),
+		"a model outside the provider's list must not match")
+
+	// A provider registered with the already-normalized id also matches.
+	normalized := ProviderRoute{Bedrock: true, Models: []string{"anthropic.claude-haiku-4-5"}}
+	assert.True(t, routeClaimsModel(normalized, "anthropic.claude-haiku-4-5"),
+		"normalized Bedrock model must match")
+
+	// Non-Bedrock routes keep exact matching (no prefix stripping).
+	openai := ProviderRoute{Models: []string{"gpt-4o"}}
+	assert.True(t, routeClaimsModel(openai, "gpt-4o"), "exact model must match")
+	assert.False(t, routeClaimsModel(openai, "us.gpt-4o"),
+		"non-Bedrock routes must not strip a us. prefix")
+}

proxy/internal/middleware/builtin/llm_router/middleware.go

@@ -23,6 +23,7 @@ import (
 	"golang.org/x/oauth2"
 	"golang.org/x/oauth2/google"
 
+	"github.com/netbirdio/netbird/proxy/internal/llm"
 	"github.com/netbirdio/netbird/proxy/internal/middleware"
 )
 
@@ -555,6 +556,14 @@ func routeClaimsModel(route ProviderRoute, model string) bool {
 		if candidate == model {
 			return true
 		}
+		// Bedrock request models reach the router already normalized (the parser
+		// strips the region / inference-profile prefix and version suffix), but
+		// the operator may register the raw inference-profile id (e.g.
+		// "us.anthropic.claude-haiku-4-5"). Normalize the candidate so both sides
+		// compare equal; otherwise a native Bedrock request denies as not-routable.
+		if route.Bedrock && llm.NormalizeBedrockModel(candidate) == model {
+			return true
+		}
 	}
 	return false
 }

shared/relay/client/fallback_opener.go

@@ -0,0 +1,176 @@
+package client
+
+import (
+	"context"
+	"errors"
+	"net"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+const (
+	raceTotalTimeout  = 40 * time.Second
+	raceFallbackDelay = 10 * time.Second
+)
+
+type raceAttempt struct {
+	conn net.Conn
+	err  error
+}
+
+type raceOutcome struct {
+	conn net.Conn
+	err  error
+	done bool
+}
+
+type connRace struct {
+	opener            *FallbackOpener
+	peerKey           string
+	remoteRelayServer RelayServer
+	preferForeign     bool
+
+	raceCtx         context.Context
+	otherCtx        context.Context
+	cancelPreferred context.CancelFunc
+	cancelOther     context.CancelFunc
+	results         chan raceAttempt
+	fallbackTimer   *time.Timer
+
+	otherStarted bool
+	settled      int
+	lastErr      error
+}
+
+type FallbackOpener struct {
+	home         *Client
+	foreignStore *ForeignRelaysStore
+
+	fallbackDelay time.Duration
+	totalTimeout  time.Duration
+	// openFn performs a single attempt. It is overridable in tests; when nil the
+	// real home/foreign dispatch in open is used.
+	openFn func(ctx context.Context, peerKey string, remoteRelayServer RelayServer, foreign bool) raceAttempt
+}
+
+func NewFallbackOpener(home *Client, foreignStore *ForeignRelaysStore) *FallbackOpener {
+	return &FallbackOpener{
+		home:          home,
+		foreignStore:  foreignStore,
+		fallbackDelay: raceFallbackDelay,
+		totalTimeout:  raceTotalTimeout,
+	}
+}
+
+func (r *FallbackOpener) Run(ctx context.Context, peerKey string, remoteRelayServer RelayServer, preferForeign bool) (net.Conn, error) {
+	raceCtx, cancel := context.WithTimeout(ctx, r.totalTimeout)
+	defer cancel()
+
+	preferredCtx, cancelPreferred := context.WithCancel(raceCtx)
+	otherCtx, cancelOther := context.WithCancel(raceCtx)
+
+	race := &connRace{
+		opener:            r,
+		peerKey:           peerKey,
+		remoteRelayServer: remoteRelayServer,
+		preferForeign:     preferForeign,
+		raceCtx:           raceCtx,
+		otherCtx:          otherCtx,
+		cancelPreferred:   cancelPreferred,
+		cancelOther:       cancelOther,
+		results:           make(chan raceAttempt, 2),
+		fallbackTimer:     time.NewTimer(r.fallbackDelay),
+	}
+	defer race.fallbackTimer.Stop()
+
+	go func() {
+		race.results <- r.open(preferredCtx, peerKey, remoteRelayServer, preferForeign)
+	}()
+
+	for {
+		select {
+		case <-race.fallbackTimer.C:
+			race.startOther()
+		case res := <-race.results:
+			if o := race.handleResult(res); o.done {
+				return o.conn, o.err
+			}
+		case <-raceCtx.Done():
+			return race.onTimeout()
+		}
+	}
+}
+
+func (c *connRace) startOther() {
+	if c.otherStarted {
+		return
+	}
+	c.otherStarted = true
+	c.fallbackTimer.Stop()
+	go func() {
+		c.results <- c.opener.open(c.otherCtx, c.peerKey, c.remoteRelayServer, !c.preferForeign)
+	}()
+}
+
+func (c *connRace) handleResult(res raceAttempt) raceOutcome {
+	if (res.err == nil && res.conn != nil) || errors.Is(res.err, ErrConnAlreadyExists) {
+		c.settled++
+		c.stop()
+		return raceOutcome{conn: res.conn, err: res.err, done: true}
+	}
+
+	c.lastErr = res.err
+	c.settled++
+	if !c.otherStarted {
+		c.startOther()
+		return raceOutcome{}
+	}
+	if c.settled == 2 {
+		c.cancelPreferred()
+		c.cancelOther()
+		return raceOutcome{err: c.lastErr, done: true}
+	}
+	return raceOutcome{}
+}
+
+func (c *connRace) onTimeout() (net.Conn, error) {
+	c.stop()
+	if c.lastErr != nil {
+		return nil, c.lastErr
+	}
+	return nil, c.raceCtx.Err()
+}
+
+func (c *connRace) stop() {
+	c.cancelPreferred()
+	c.cancelOther()
+	go c.opener.drainLoser(c.results, c.settled, c.otherStarted)
+}
+
+func (r *FallbackOpener) open(ctx context.Context, peerKey string, remoteRelayServer RelayServer, foreign bool) raceAttempt {
+	if r.openFn != nil {
+		return r.openFn(ctx, peerKey, remoteRelayServer, foreign)
+	}
+	if foreign {
+		conn, err := r.foreignStore.OpenConn(ctx, peerKey, remoteRelayServer)
+		return raceAttempt{conn: conn, err: err}
+	}
+	conn, err := r.home.OpenConn(ctx, peerKey)
+	return raceAttempt{conn: conn, err: err}
+}
+
+func (r *FallbackOpener) drainLoser(results chan raceAttempt, settled int, otherStarted bool) {
+	started := 1
+	if otherStarted {
+		started = 2
+	}
+	for i := settled; i < started; i++ {
+		res := <-results
+		if res.conn != nil {
+			if err := res.conn.Close(); err != nil {
+				log.Debugf("failed to close losing relay connection: %v", err)
+			}
+		}
+	}
+}

shared/relay/client/fallback_opener_test.go

@@ -0,0 +1,450 @@
+package client
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"net"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// The FallbackOpener race is driven by a single goroutine (Run's select loop)
+// with worker goroutines that communicate only through the buffered results
+// channel and the two cancel contexts. These tests exercise that state machine
+// in isolation via an injected openFn, so no relay server or network is needed.
+// Timing is scaled down through the fallbackDelay/totalTimeout fields.
+
+// raceFakeConn tracks whether Close was called. Only Close is exercised by the
+// race logic (drainLoser closes losers; Run returns the winner untouched).
+type raceFakeConn struct {
+	net.Conn
+	label  string
+	closed atomic.Bool
+}
+
+func (c *raceFakeConn) Close() error {
+	c.closed.Store(true)
+	return nil
+}
+
+// raceAttemptScript describes how a single scripted attempt behaves.
+type raceAttemptScript struct {
+	delay time.Duration
+	conn  *raceFakeConn // non-nil => the attempt succeeds and returns this conn
+	err   error         // returned when conn is nil
+	// ignoreCtx makes the attempt complete after delay even if its context is
+	// cancelled. It models an OpenConn that produced a real connection right as
+	// the race cancelled it - exactly the case drainLoser must clean up.
+	ignoreCtx bool
+}
+
+// fakeOpener replaces FallbackOpener.open. Scripts are keyed by the foreign
+// flag, so which script is "preferred" depends on the preferForeign argument
+// passed to Run.
+type fakeOpener struct {
+	mu      sync.Mutex
+	scripts map[bool]raceAttemptScript
+	calls   []bool // foreign flag of each open() invocation, in order
+}
+
+func (f *fakeOpener) open(ctx context.Context, _ string, _ RelayServer, foreign bool) raceAttempt {
+	f.mu.Lock()
+	f.calls = append(f.calls, foreign)
+	s, ok := f.scripts[foreign]
+	f.mu.Unlock()
+	if !ok {
+		return raceAttempt{err: fmt.Errorf("no script for foreign=%v", foreign)}
+	}
+
+	if s.delay > 0 {
+		timer := time.NewTimer(s.delay)
+		defer timer.Stop()
+		if s.ignoreCtx {
+			<-timer.C
+		} else {
+			select {
+			case <-timer.C:
+			case <-ctx.Done():
+				return raceAttempt{err: ctx.Err()}
+			}
+		}
+	}
+
+	if s.conn != nil {
+		return raceAttempt{conn: s.conn}
+	}
+	return raceAttempt{err: s.err}
+}
+
+func (f *fakeOpener) callCount() int {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return len(f.calls)
+}
+
+func (f *fakeOpener) firstCallForeign(t *testing.T) bool {
+	t.Helper()
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	require.NotEmpty(t, f.calls, "expected at least one open attempt")
+	return f.calls[0]
+}
+
+func newTestOpener(f *fakeOpener, fallbackDelay, totalTimeout time.Duration) *FallbackOpener {
+	o := NewFallbackOpener(nil, nil)
+	o.openFn = f.open
+	o.fallbackDelay = fallbackDelay
+	o.totalTimeout = totalTimeout
+	return o
+}
+
+const (
+	// controller prefers the home relay, i.e. preferForeign == false.
+	preferHome    = false
+	preferForeign = true
+)
+
+var errAttempt = errors.New("attempt failed")
+
+// The preferred attempt wins before the fallback timer fires, so the other
+// attempt is never started.
+func TestFallbackOpener_PreferredWinsImmediately(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {conn: homeConn},                            // preferred (home): instant success
+		true:  {delay: 5 * time.Second, conn: foreignConn}, // would never finish in time
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, homeConn, conn)
+	assert.Equal(t, 1, f.callCount(), "other attempt must not start when preferred wins first")
+	assert.False(t, f.firstCallForeign(t), "home must be tried first when preferring home")
+	assert.False(t, foreignConn.closed.Load())
+}
+
+// preferForeign flips which relay is tried first.
+func TestFallbackOpener_PreferForeignRoutesForeignFirst(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		true:  {conn: foreignConn}, // preferred (foreign): instant success
+		false: {delay: 5 * time.Second, conn: &raceFakeConn{}},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferForeign)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 1, f.callCount())
+	assert.True(t, f.firstCallForeign(t), "foreign must be tried first when preferring foreign")
+}
+
+// ErrConnAlreadyExists counts as success: Run returns it and does not start the
+// other attempt.
+func TestFallbackOpener_ErrConnAlreadyExistsIsSuccess(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: ErrConnAlreadyExists},
+		true:  {delay: 5 * time.Second, conn: &raceFakeConn{}},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.ErrorIs(t, err, ErrConnAlreadyExists)
+	assert.Nil(t, conn)
+	assert.Equal(t, 1, f.callCount(), "other attempt must not start on ErrConnAlreadyExists")
+}
+
+// A preferred failure starts the other attempt immediately, without waiting for
+// the fallback timer.
+func TestFallbackOpener_PreferredFailsStartsOtherBeforeTimer(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: errAttempt}, // preferred fails instantly
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},
+	}}
+	fallbackDelay := 500 * time.Millisecond
+	o := newTestOpener(f, fallbackDelay, 2*time.Second)
+
+	start := time.Now()
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+	elapsed := time.Since(start)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.Less(t, elapsed, fallbackDelay/2, "fallback must not wait for the timer after a preferred failure")
+}
+
+// When the preferred attempt is slow, the fallback timer starts the other
+// attempt and its success wins.
+func TestFallbackOpener_TimerStartsOtherWhenPreferredSlow(t *testing.T) {
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second}, // preferred hangs until cancelled
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},
+	}}
+	fallbackDelay := 40 * time.Millisecond
+	o := newTestOpener(f, fallbackDelay, 2*time.Second)
+
+	start := time.Now()
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+	elapsed := time.Since(start)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.GreaterOrEqual(t, elapsed, fallbackDelay, "other must not start before the fallback timer fires")
+}
+
+// Both attempts fail: Run returns the last error and tries both relays.
+func TestFallbackOpener_BothFail(t *testing.T) {
+	errOther := errors.New("other failed")
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {err: errAttempt},
+		true:  {err: errOther},
+	}}
+	o := newTestOpener(f, 40*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, errOther, "the most recent error should be surfaced")
+	assert.Equal(t, 2, f.callCount())
+}
+
+// When both attempts succeed, drainLoser must close the losing connection so it
+// is not leaked. Here the preferred attempt wins and the foreign loser - which
+// produced a real conn despite being cancelled - is closed.
+func TestFallbackOpener_DoubleSuccessClosesLoser(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 30 * time.Millisecond, conn: homeConn},                     // preferred wins
+		true:  {delay: 80 * time.Millisecond, conn: foreignConn, ignoreCtx: true}, // loser yields a conn after cancel
+	}}
+	o := newTestOpener(f, 15*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, homeConn, conn)
+	assert.Equal(t, 2, f.callCount())
+	assert.False(t, homeConn.closed.Load(), "the winning connection must not be closed")
+	require.Eventually(t, foreignConn.closed.Load, time.Second, 5*time.Millisecond,
+		"the losing connection must be closed by drainLoser")
+}
+
+// Winner selection is purely by result arrival order, not by preference: when
+// the non-preferred attempt returns first it wins even though home was
+// preferred. This is the mechanism behind the split-relay concern - two peers
+// racing independently have no shared tie-break, so under adversarial timing
+// they can settle on different relays. Documented here as current behavior.
+func TestFallbackOpener_FasterOtherWinsDespitePreference(t *testing.T) {
+	homeConn := &raceFakeConn{label: "home"}
+	foreignConn := &raceFakeConn{label: "foreign"}
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 60 * time.Millisecond, conn: homeConn, ignoreCtx: true}, // preferred but slower
+		true:  {delay: 5 * time.Millisecond, conn: foreignConn},                // other is faster
+	}}
+	o := newTestOpener(f, 15*time.Millisecond, 2*time.Second)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.NoError(t, err)
+	require.Same(t, foreignConn, conn, "the first successful attempt wins regardless of preference")
+	require.Eventually(t, homeConn.closed.Load, time.Second, 5*time.Millisecond,
+		"the slower preferred attempt becomes the loser and is closed")
+}
+
+// The whole race is bounded by totalTimeout. With no attempt succeeding or
+// failing, Run returns the deadline error.
+func TestFallbackOpener_TotalTimeout(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second},
+		true:  {delay: 5 * time.Second},
+	}}
+	o := newTestOpener(f, 20*time.Millisecond, 80*time.Millisecond)
+
+	conn, err := o.Run(context.Background(), "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, context.DeadlineExceeded)
+}
+
+// Cancelling the caller's context aborts the race promptly with the cancel
+// error, even before the fallback timer would fire.
+func TestFallbackOpener_ParentContextCanceled(t *testing.T) {
+	f := &fakeOpener{scripts: map[bool]raceAttemptScript{
+		false: {delay: 5 * time.Second},
+		true:  {delay: 5 * time.Second},
+	}}
+	// fallbackDelay large so the timer never fires; only the parent cancel ends the race.
+	o := newTestOpener(f, 5*time.Second, 5*time.Second)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		cancel()
+	}()
+
+	start := time.Now()
+	conn, err := o.Run(ctx, "peer", RelayServer{Addr: "srv"}, preferHome)
+
+	require.Error(t, err)
+	assert.Nil(t, conn)
+	assert.ErrorIs(t, err, context.Canceled)
+	assert.Less(t, time.Since(start), time.Second, "must return shortly after the parent context is cancelled")
+	assert.Equal(t, 1, f.callCount(), "the other attempt must not start")
+}
+
+// rendezvous models the relay-level requirement that a relayed connection is
+// established only once BOTH peers subscribe to the same relay server. arrive
+// records a peer's presence on a relay and returns a channel that closes when
+// the second peer arrives, so an attempt can only complete after a real
+// rendezvous - the same coupling the production code depends on.
+type rendezvous struct {
+	mu       sync.Mutex
+	arrivals map[string]int
+	gates    map[string]chan struct{}
+}
+
+func newRendezvous() *rendezvous {
+	return &rendezvous{arrivals: map[string]int{}, gates: map[string]chan struct{}{}}
+}
+
+func (r *rendezvous) arrive(relay string) <-chan struct{} {
+	r.mu.Lock()
+	defer r.mu.Unlock()
+	g, ok := r.gates[relay]
+	if !ok {
+		g = make(chan struct{})
+		r.gates[relay] = g
+	}
+	r.arrivals[relay]++
+	if r.arrivals[relay] == 2 {
+		close(g)
+	}
+	return g
+}
+
+// splitPeer is one peer's view of the two relays. relayFor maps the foreign
+// flag to a relay name; postDelay is how long after the rendezvous that peer's
+// OpenConn takes to return (its per-relay subscribe latency). Different values
+// per peer model the asymmetric timing that triggers finding #1.
+type splitPeer struct {
+	rv        *rendezvous
+	relayFor  map[bool]string
+	postDelay map[string]time.Duration
+}
+
+func (p *splitPeer) open(ctx context.Context, _ string, _ RelayServer, foreign bool) raceAttempt {
+	relay := p.relayFor[foreign]
+
+	select {
+	case <-p.rv.arrive(relay):
+	case <-ctx.Done():
+		return raceAttempt{err: ctx.Err()}
+	}
+
+	timer := time.NewTimer(p.postDelay[relay])
+	defer timer.Stop()
+	select {
+	case <-timer.C:
+	case <-ctx.Done():
+		return raceAttempt{err: ctx.Err()}
+	}
+	return raceAttempt{conn: &raceFakeConn{label: relay}}
+}
+
+// TestFallbackOpener_SplitRelaySelection reproduces finding #1: the two peers
+// run FallbackOpener.Run independently with no shared tie-break, so the winner
+// is chosen purely by local result-arrival order. Under an adversarial - but
+// self-consistent - timing profile they settle on DIFFERENT relays.
+//
+// Both peers prefer relayA (the controller's home). The split needs each peer's
+// preferred relayA to be slow enough that both start their fallback (so both
+// relays actually rendezvous), and then each peer's fast path to be a different
+// relay:
+//   - peerA: relayA slow (abandoned), relayB fast  -> peerA wins relayB
+//   - peerB: relayA fast (wins),      relayB slow  -> peerB wins relayA
+//
+// Each winner then cancels its attempt on the relay the OTHER peer actually
+// kept, leaving two half-open relayed connections that were both reported as
+// successful. When a deterministic cross-peer tie-break is added to fix this,
+// invert the assertion below to require convergence.
+func TestFallbackOpener_SplitRelaySelection(t *testing.T) {
+	const (
+		relayA = "relayA" // controller's home relay; both peers prefer it
+		relayB = "relayB" // non-controller's home relay
+	)
+	rv := newRendezvous()
+
+	peerA := &splitPeer{
+		rv:       rv,
+		relayFor: map[bool]string{false: relayA, true: relayB}, // home=relayA
+		postDelay: map[string]time.Duration{
+			relayA: 500 * time.Millisecond, // preferred but slow -> abandoned
+			relayB: 10 * time.Millisecond,  // fallback is fast -> peerA wins relayB
+		},
+	}
+	peerB := &splitPeer{
+		rv:       rv,
+		relayFor: map[bool]string{false: relayB, true: relayA}, // home=relayB
+		postDelay: map[string]time.Duration{
+			relayA: 80 * time.Millisecond,  // preferred, wins - but only after starting fallback
+			relayB: 500 * time.Millisecond, // fallback (home) is slow -> abandoned
+		},
+	}
+
+	fallbackDelay := 30 * time.Millisecond
+	newPeerOpener := func(p *splitPeer) *FallbackOpener {
+		o := NewFallbackOpener(nil, nil)
+		o.openFn = p.open
+		o.fallbackDelay = fallbackDelay
+		o.totalTimeout = 5 * time.Second
+		return o
+	}
+	oA := newPeerOpener(peerA)
+	oB := newPeerOpener(peerB)
+
+	type result struct {
+		conn net.Conn
+		err  error
+	}
+	var ra, rb result
+	var wg sync.WaitGroup
+	wg.Add(2)
+	go func() {
+		defer wg.Done()
+		ra.conn, ra.err = oA.Run(context.Background(), "peerB", RelayServer{Addr: relayB}, preferHome)
+	}()
+	go func() {
+		defer wg.Done()
+		rb.conn, rb.err = oB.Run(context.Background(), "peerA", RelayServer{Addr: relayA}, preferForeign)
+	}()
+	wg.Wait()
+
+	require.NoError(t, ra.err)
+	require.NoError(t, rb.err)
+	aRelay := ra.conn.(*raceFakeConn).label
+	bRelay := rb.conn.(*raceFakeConn).label
+	t.Logf("peerA settled on %s, peerB settled on %s", aRelay, bRelay)
+
+	assert.Equal(t, aRelay, bRelay,
+		"peers selected different relays with no cross-peer tie-break")
+	assert.Equal(t, relayB, aRelay, "peerA abandoned its slow preferred relay and won the fallback")
+	assert.Equal(t, relayA, bRelay, "peerB won its preferred relay after starting the fallback")
+}

shared/relay/client/foreign_relays_store.go

@@ -0,0 +1,155 @@
+package client
+
+import (
+	"context"
+	"net"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/sync/singleflight"
+
+	relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
+)
+
+type foreignRelay struct {
+	client  *Client
+	created time.Time
+	inUse   int
+}
+
+type ForeignRelaysStore struct {
+	mu      sync.RWMutex
+	clients map[string]*foreignRelay
+
+	group singleflight.Group
+
+	ctx                  context.Context
+	tokenStore           *relayAuth.TokenStore
+	peerID               string
+	mtu                  uint16
+	transportFallback    *transportFallback
+	onDisconnect         func(string)
+	keepUnusedServerTime time.Duration
+}
+
+func NewForeignRelaysStore(ctx context.Context, tokenStore *relayAuth.TokenStore, peerID string, mtu uint16, transportFallback *transportFallback, onDisconnect func(string), keepUnusedServerTime time.Duration) *ForeignRelaysStore {
+	return &ForeignRelaysStore{
+		clients:              make(map[string]*foreignRelay),
+		ctx:                  ctx,
+		tokenStore:           tokenStore,
+		peerID:               peerID,
+		mtu:                  mtu,
+		transportFallback:    transportFallback,
+		onDisconnect:         onDisconnect,
+		keepUnusedServerTime: keepUnusedServerTime,
+	}
+}
+
+func (f *ForeignRelaysStore) OpenConn(ctx context.Context, peerKey string, remoteRelayServer RelayServer) (net.Conn, error) {
+	fr, err := f.acquire(remoteRelayServer)
+	if err != nil {
+		return nil, err
+	}
+	defer f.release(fr)
+
+	return fr.client.OpenConn(ctx, peerKey)
+}
+
+func (f *ForeignRelaysStore) acquire(remoteRelayServer RelayServer) (*foreignRelay, error) {
+	f.mu.Lock()
+	if fr, ok := f.clients[remoteRelayServer.Addr]; ok {
+		fr.inUse++
+		f.mu.Unlock()
+		return fr, nil
+	}
+	f.mu.Unlock()
+
+	v, err, _ := f.group.Do(remoteRelayServer.Addr, func() (any, error) {
+		f.mu.RLock()
+		fr, ok := f.clients[remoteRelayServer.Addr]
+		f.mu.RUnlock()
+		if ok {
+			return fr, nil
+		}
+
+		relayClient := NewClientWithServerIP(remoteRelayServer.Addr, remoteRelayServer.IP, f.tokenStore, f.peerID, f.mtu)
+		relayClient.SetTransportFallback(f.transportFallback)
+		if err := relayClient.Connect(f.ctx); err != nil {
+			return nil, err
+		}
+		relayClient.SetOnDisconnectListener(f.onDisconnect)
+
+		f.mu.Lock()
+		fr = &foreignRelay{client: relayClient, created: time.Now()}
+		f.clients[remoteRelayServer.Addr] = fr
+		f.mu.Unlock()
+		return fr, nil
+	})
+	if err != nil {
+		return nil, err
+	}
+
+	fr := v.(*foreignRelay)
+	f.mu.Lock()
+	if cur, ok := f.clients[remoteRelayServer.Addr]; !ok || cur != fr {
+		f.mu.Unlock()
+		return f.acquire(remoteRelayServer)
+	}
+	fr.inUse++
+	f.mu.Unlock()
+	return fr, nil
+}
+
+func (f *ForeignRelaysStore) release(fr *foreignRelay) {
+	f.mu.Lock()
+	fr.inUse--
+	f.mu.Unlock()
+}
+
+func (f *ForeignRelaysStore) evict(serverAddress string) {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	if _, ok := f.clients[serverAddress]; ok {
+		delete(f.clients, serverAddress)
+		log.Debugf("evicted disconnected foreign relay client: %s", serverAddress)
+	}
+}
+
+func (f *ForeignRelaysStore) cleanupUnused() {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+
+	for addr, fr := range f.clients {
+		if time.Since(fr.created) <= f.keepUnusedServerTime {
+			continue
+		}
+		if fr.inUse > 0 {
+			continue
+		}
+		if fr.client.HasConns() {
+			continue
+		}
+		fr.client.SetOnDisconnectListener(nil)
+		go func() {
+			_ = fr.client.Close()
+		}()
+		log.Debugf("clean up unused relay server connection: %s", addr)
+		delete(f.clients, addr)
+	}
+}
+
+func (f *ForeignRelaysStore) states() []RelayConnState {
+	f.mu.RLock()
+	clients := make([]*Client, 0, len(f.clients))
+	for _, fr := range f.clients {
+		clients = append(clients, fr.client)
+	}
+	f.mu.RUnlock()
+
+	states := make([]RelayConnState, 0, len(clients))
+	for _, c := range clients {
+		states = append(states, relayConnState(c))
+	}
+	return states
+}

shared/relay/client/manager.go

@@ -22,27 +22,6 @@ var (
 	ErrRelayClientNotConnected = fmt.Errorf("relay client not connected")
 )
 
-// RelayTrack hold the relay clients for the foreign relay servers.
-// With the mutex can ensure we can open new connection in case the relay connection has been established with
-// the relay server.
-type RelayTrack struct {
-	sync.RWMutex
-	relayClient *Client
-	err         error
-	created     time.Time
-	// ready is closed once the dial started by openConnVia finishes (relayClient
-	// or err is set). Callers reusing a track wait on this instead of the track
-	// lock, so the dial never runs under rt.Lock.
-	ready chan struct{}
-}
-
-func NewRelayTrack() *RelayTrack {
-	return &RelayTrack{
-		created: time.Now(),
-		ready:   make(chan struct{}),
-	}
-}
-
 type OnServerCloseListener func()
 
 // ManagerOption configures a Manager at construction time.
@@ -59,6 +38,11 @@ type RelayConnState struct {
 	Err error
 }
 
+type RelayServer struct {
+	Addr string
+	IP   netip.Addr
+}
+
 // WithMaxBackoffInterval caps the exponential backoff between reconnect
 // attempts to the home relay. A non-positive value keeps the default.
 func WithMaxBackoffInterval(d time.Duration) ManagerOption {
@@ -83,8 +67,7 @@ type Manager struct {
 	relayClientMu  sync.RWMutex
 	reconnectGuard *Guard
 
-	relayClients      map[string]*RelayTrack
-	relayClientsMutex sync.RWMutex
+	foreign *ForeignRelaysStore
 
 	onDisconnectedListeners map[string]*list.List
 	onReconnectedListenerFn func()
@@ -120,7 +103,6 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 			ConnectionTimeout: defaultConnectionTimeout,
 			TransportFallback: tf,
 		},
-		relayClients:            make(map[string]*RelayTrack),
 		onDisconnectedListeners: make(map[string]*list.List),
 		cleanupInterval:         relayCleanupInterval,
 		keepUnusedServerTime:    keepUnusedServerTime,
@@ -128,6 +110,7 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 	for _, opt := range opts {
 		opt(m)
 	}
+	m.foreign = NewForeignRelaysStore(ctx, tokenStore, peerID, mtu, tf, m.onServerDisconnected, m.keepUnusedServerTime)
 	m.serverPicker.ServerURLs.Store(serverURLs)
 	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
 	return m
@@ -159,40 +142,26 @@ func (m *Manager) Serve() error {
 	return err
 }
 
-// OpenConn opens a connection to the given peer key. If the peer is on the same relay server, the connection will be
-// established via the relay server. If the peer is on a different relay server, the manager will establish a new
-// connection to the relay server. It returns back with a net.Conn what represent the remote peer connection.
-//
-// serverIP, when valid and serverAddress is foreign, is used as a dial target if the FQDN-based dial fails.
-// Ignored for the local home-server path. TLS verification still uses the FQDN via SNI.
-func (m *Manager) OpenConn(ctx context.Context, serverAddress, peerKey string, serverIP netip.Addr) (net.Conn, error) {
+func (m *Manager) OpenConn(ctx context.Context, remoteRelayServer RelayServer, peerKey string, preferForeign bool) (net.Conn, error) {
 	m.relayClientMu.RLock()
-	defer m.relayClientMu.RUnlock()
+	relayClient := m.relayClient
+	m.relayClientMu.RUnlock()
 
-	if m.relayClient == nil {
+	if relayClient == nil {
 		return nil, ErrRelayClientNotConnected
 	}
 
-	foreign, err := m.isForeignServer(serverAddress)
+	foreign, err := m.isForeignServer(relayClient, remoteRelayServer.Addr)
 	if err != nil {
 		return nil, err
 	}
 
-	var (
-		netConn net.Conn
-	)
 	if !foreign {
-		log.Debugf("open peer connection via permanent server: %s", peerKey)
-		netConn, err = m.relayClient.OpenConn(ctx, peerKey)
-	} else {
-		log.Debugf("open peer connection via foreign server: %s", serverAddress)
-		netConn, err = m.openConnVia(ctx, serverAddress, peerKey, serverIP)
-	}
-	if err != nil {
-		return nil, err
+		return relayClient.OpenConn(ctx, peerKey)
 	}
 
-	return netConn, err
+	opener := NewFallbackOpener(relayClient, m.foreign)
+	return opener.Run(ctx, peerKey, remoteRelayServer, preferForeign)
 }
 
 // Ready returns true if the home Relay client is connected to the relay server.
@@ -223,7 +192,7 @@ func (m *Manager) AddCloseListener(serverAddress string, onClosedListener OnServ
 		return ErrRelayClientNotConnected
 	}
 
-	foreign, err := m.isForeignServer(serverAddress)
+	foreign, err := m.isForeignServer(m.relayClient, serverAddress)
 	if err != nil {
 		return err
 	}
@@ -287,26 +256,7 @@ func (m *Manager) RelayStates() []RelayConnState {
 		states = append(states, st)
 	}
 
-	// Snapshot the tracks, then query each outside the map lock: a track can be
-	// held by an in-progress Connect, and blocking on it must not stall other
-	// relay operations.
-	m.relayClientsMutex.RLock()
-	tracks := make([]*RelayTrack, 0, len(m.relayClients))
-	for _, rt := range m.relayClients {
-		tracks = append(tracks, rt)
-	}
-	m.relayClientsMutex.RUnlock()
-
-	// Only connected foreign relays carry state; a failed connect is evicted
-	// immediately (openConnVia), so there is no error state to surface.
-	for _, rt := range tracks {
-		rt.RLock()
-		rc := rt.relayClient
-		rt.RUnlock()
-		if rc != nil {
-			states = append(states, relayConnState(rc))
-		}
-	}
+	states = append(states, m.foreign.states()...)
 
 	return states
 }
@@ -327,76 +277,6 @@ func (m *Manager) UpdateToken(token *relayAuth.Token) error {
 	return m.tokenStore.UpdateToken(token)
 }
 
-func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string, serverIP netip.Addr) (net.Conn, error) {
-	// check if already has a connection to the desired relay server
-	m.relayClientsMutex.RLock()
-	rt, ok := m.relayClients[serverAddress]
-	m.relayClientsMutex.RUnlock()
-	if ok {
-		return m.openConnOnTrack(ctx, rt, peerKey)
-	}
-
-	// if not, establish a new connection but check it again (because changed the lock type) before starting the
-	// connection
-	m.relayClientsMutex.Lock()
-	rt, ok = m.relayClients[serverAddress]
-	if ok {
-		m.relayClientsMutex.Unlock()
-		return m.openConnOnTrack(ctx, rt, peerKey)
-	}
-
-	// Publish the track and release the map lock BEFORE dialing, so the dial does
-	// not run under rt.Lock (which would block RelayStates and the cleanup loop
-	// for the full dial). Concurrent callers find this track and wait on rt.ready.
-	rt = NewRelayTrack()
-	m.relayClients[serverAddress] = rt
-	m.relayClientsMutex.Unlock()
-
-	relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
-	relayClient.SetTransportFallback(m.transportFallback)
-	err := relayClient.Connect(m.ctx)
-	if err != nil {
-		rt.Lock()
-		rt.err = err
-		rt.Unlock()
-		close(rt.ready)
-		m.relayClientsMutex.Lock()
-		delete(m.relayClients, serverAddress)
-		m.relayClientsMutex.Unlock()
-		return nil, err
-	}
-	// if connection closed then delete the relay client from the list
-	relayClient.SetOnDisconnectListener(m.onServerDisconnected)
-	rt.Lock()
-	rt.relayClient = relayClient
-	rt.Unlock()
-	close(rt.ready)
-
-	return relayClient.OpenConn(ctx, peerKey)
-}
-
-// openConnOnTrack opens a peer connection through an existing relay track,
-// waiting for the dial started by another openConnVia call to finish. It waits
-// on rt.ready rather than the track lock, so it neither holds nor contends the
-// track lock across the dial.
-func (m *Manager) openConnOnTrack(ctx context.Context, rt *RelayTrack, peerKey string) (net.Conn, error) {
-	select {
-	case <-rt.ready:
-	case <-ctx.Done():
-		return nil, ctx.Err()
-	}
-
-	rt.RLock()
-	defer rt.RUnlock()
-	if rt.err != nil {
-		return nil, rt.err
-	}
-	if rt.relayClient == nil {
-		return nil, ErrRelayClientNotConnected
-	}
-	return rt.relayClient.OpenConn(ctx, peerKey)
-}
-
 func (m *Manager) onServerConnected() {
 	m.listenerLock.Lock()
 	defer m.listenerLock.Unlock()
@@ -422,21 +302,12 @@ func (m *Manager) onServerDisconnected(serverAddress string) {
 	m.relayClientMu.Unlock()
 
 	if !isHome {
-		m.evictForeignRelay(serverAddress)
+		m.foreign.evict(serverAddress)
 	}
 
 	m.notifyOnDisconnectListeners(serverAddress)
 }
 
-func (m *Manager) evictForeignRelay(serverAddress string) {
-	m.relayClientsMutex.Lock()
-	defer m.relayClientsMutex.Unlock()
-	if _, ok := m.relayClients[serverAddress]; ok {
-		delete(m.relayClients, serverAddress)
-		log.Debugf("evicted disconnected foreign relay client: %s", serverAddress)
-	}
-}
-
 func (m *Manager) listenGuardEvent(ctx context.Context) {
 	for {
 		select {
@@ -459,8 +330,8 @@ func (m *Manager) storeClient(client *Client) {
 	m.relayClient.SetOnDisconnectListener(m.onServerDisconnected)
 }
 
-func (m *Manager) isForeignServer(address string) (bool, error) {
-	rAddr, err := m.relayClient.ServerInstanceURL()
+func (m *Manager) isForeignServer(relayClient *Client, address string) (bool, error) {
+	rAddr, err := relayClient.ServerInstanceURL()
 	if err != nil {
 		return false, fmt.Errorf("relay client not connected")
 	}
@@ -475,50 +346,11 @@ func (m *Manager) startCleanupLoop() {
 		case <-m.ctx.Done():
 			return
 		case <-ticker.C:
-			m.cleanUpUnusedRelays()
+			m.foreign.cleanupUnused()
 		}
 	}
 }
 
-func (m *Manager) cleanUpUnusedRelays() {
-	m.relayClientsMutex.Lock()
-	defer m.relayClientsMutex.Unlock()
-
-	for addr, rt := range m.relayClients {
-		rt.Lock()
-		// if the connection failed to the server the relay client will be nil
-		// but the instance will be kept in the relayClients until the next locking
-		if rt.err != nil {
-			rt.Unlock()
-			continue
-		}
-
-		// dial still in progress (openConnVia publishes the track before Connect
-		// completes and no longer holds rt.Lock during it), nothing to clean up.
-		if rt.relayClient == nil {
-			rt.Unlock()
-			continue
-		}
-
-		if time.Since(rt.created) <= m.keepUnusedServerTime {
-			rt.Unlock()
-			continue
-		}
-
-		if rt.relayClient.HasConns() {
-			rt.Unlock()
-			continue
-		}
-		rt.relayClient.SetOnDisconnectListener(nil)
-		go func() {
-			_ = rt.relayClient.Close()
-		}()
-		log.Debugf("clean up unused relay server connection: %s", addr)
-		delete(m.relayClients, addr)
-		rt.Unlock()
-	}
-}
-
 func (m *Manager) addListener(serverAddress string, onClosedListener OnServerCloseListener) {
 	m.listenerLock.Lock()
 	defer m.listenerLock.Unlock()

shared/relay/client/manager_cleanup_test.go

@@ -2,17 +2,14 @@ package client
 
 import (
 	"context"
-	"net/netip"
 	"testing"
 	"time"
-
-	"github.com/stretchr/testify/require"
 )
 
 // TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial drives a real, hanging foreign
-// relay dial and asserts cleanUpUnusedRelays does not stall behind it.
+// relay dial and asserts the foreign store cleanup does not stall behind it.
 func TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial(t *testing.T) {
-	serverAddr := stallingRelayListener(t)
+	serverAddr, accepted := stallingRelayListener(t)
 
 	mCtx, mCancel := context.WithCancel(context.Background())
 	t.Cleanup(mCancel)
@@ -22,39 +19,32 @@ func TestCleanUpUnusedRelays_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	dialDone := make(chan struct{})
 	go func() {
 		defer close(dialDone)
-		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+		_, _ = m.foreign.OpenConn(mCtx, "peerKey", RelayServer{Addr: serverAddr})
 	}()
 
-	// The track appears in the map once the dial is in flight.
-	require.Eventually(t, func() bool {
-		m.relayClientsMutex.RLock()
-		defer m.relayClientsMutex.RUnlock()
-		_, ok := m.relayClients[serverAddr]
-		return ok
-	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+	select {
+	case <-accepted:
+	case <-time.After(5 * time.Second):
+		t.Fatal("relay dial did not reach the listener")
+	}
 
 	cleanupDone := make(chan struct{})
 	go func() {
 		defer close(cleanupDone)
-		m.cleanUpUnusedRelays()
+		m.foreign.cleanupUnused()
 	}()
 
 	select {
 	case <-cleanupDone:
 	case <-time.After(2 * time.Second):
-		t.Fatal("cleanUpUnusedRelays blocked on an in-progress relay dial while holding the relay map lock")
+		t.Fatal("cleanupUnused blocked on an in-progress relay dial")
 	}
 
-	m.relayClientsMutex.RLock()
-	_, stillTracked := m.relayClients[serverAddr]
-	m.relayClientsMutex.RUnlock()
-	require.True(t, stillTracked, "an in-progress relay dial must not be evicted by cleanup")
-
 	// Release the hanging dial so the goroutine can exit cleanly.
 	mCancel()
 	select {
 	case <-dialDone:
 	case <-time.After(5 * time.Second):
-		t.Fatal("openConnVia did not return after context cancellation")
+		t.Fatal("foreign OpenConn did not return after context cancellation")
 	}
 }

shared/relay/client/manager_relaystates_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"net"
-	"net/netip"
 	"sync"
 	"testing"
 	"time"
@@ -13,13 +12,16 @@ import (
 
 // stallingRelayListener accepts TCP connections and holds them open without ever
 // responding, so a relay handshake dialed against it blocks until its context is
-// cancelled. It returns the "rel://host:port" URL to dial.
-func stallingRelayListener(t *testing.T) string {
+// cancelled. accepted is signalled once per incoming connection so a caller can
+// wait until a dial has actually reached the listener. It returns the
+// "rel://host:port" URL to dial.
+func stallingRelayListener(t *testing.T) (string, <-chan struct{}) {
 	t.Helper()
 
 	ln, err := net.Listen("tcp", "127.0.0.1:0")
 	require.NoError(t, err)
 
+	accepted := make(chan struct{}, 1)
 	var mu sync.Mutex
 	var conns []net.Conn
 	go func() {
@@ -31,6 +33,10 @@ func stallingRelayListener(t *testing.T) string {
 			mu.Lock()
 			conns = append(conns, c)
 			mu.Unlock()
+			select {
+			case accepted <- struct{}{}:
+			default:
+			}
 		}
 	}()
 	t.Cleanup(func() {
@@ -42,14 +48,14 @@ func stallingRelayListener(t *testing.T) string {
 		mu.Unlock()
 	})
 
-	return "rel://" + ln.Addr().String()
+	return "rel://" + ln.Addr().String(), accepted
 }
 
 // TestRelayStates_DoesNotBlockOnRealHangingDial is a regression test for
 // RelayStates() called by a "status -d command" hanging behind an in-progress
-// relay dial.
+// foreign relay dial.
 func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
-	serverAddr := stallingRelayListener(t)
+	serverAddr, accepted := stallingRelayListener(t)
 
 	mCtx, mCancel := context.WithCancel(context.Background())
 	t.Cleanup(mCancel)
@@ -59,15 +65,14 @@ func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	dialDone := make(chan struct{})
 	go func() {
 		defer close(dialDone)
-		_, _ = m.openConnVia(mCtx, serverAddr, "peerKey", netip.Addr{})
+		_, _ = m.foreign.OpenConn(mCtx, "peerKey", RelayServer{Addr: serverAddr})
 	}()
 
-	require.Eventually(t, func() bool {
-		m.relayClientsMutex.RLock()
-		defer m.relayClientsMutex.RUnlock()
-		_, ok := m.relayClients[serverAddr]
-		return ok
-	}, 5*time.Second, 5*time.Millisecond, "relay dial did not start")
+	select {
+	case <-accepted:
+	case <-time.After(5 * time.Second):
+		t.Fatal("relay dial did not reach the listener")
+	}
 
 	done := make(chan []RelayConnState, 1)
 	go func() {
@@ -86,6 +91,6 @@ func TestRelayStates_DoesNotBlockOnRealHangingDial(t *testing.T) {
 	select {
 	case <-dialDone:
 	case <-time.After(5 * time.Second):
-		t.Fatal("openConnVia did not return after context cancellation")
+		t.Fatal("foreign OpenConn did not return after context cancellation")
 	}
 }

shared/relay/client/manager_serverip_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"io"
-	"net/netip"
 	"testing"
 	"time"
 
@@ -85,7 +84,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 	t.Run("no server IP, dial fails", func(t *testing.T) {
 		dialCtx, dialCancel := context.WithTimeout(ctx, 5*time.Second)
 		defer dialCancel()
-		_, err := mgrAlice.OpenConn(dialCtx, brokenFQDN, "bob", netip.Addr{})
+		_, err := mgrAlice.OpenConn(dialCtx, RelayServer{Addr: brokenFQDN}, "bob", true)
 		if err == nil {
 			t.Fatalf("expected OpenConn to fail without server IP, got success")
 		}
@@ -95,7 +94,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 		// Bob waits for Alice's incoming peer connection on his side.
 		bobSideCh := make(chan error, 1)
 		go func() {
-			conn, err := mgrBob.OpenConn(ctx, bobRealAddr, "alice", netip.Addr{})
+			conn, err := mgrBob.OpenConn(ctx, RelayServer{Addr: bobRealAddr}, "alice", false)
 			if err != nil {
 				bobSideCh <- err
 				return
@@ -113,7 +112,7 @@ func TestManager_ForeignRelayServerIP(t *testing.T) {
 			bobSideCh <- nil
 		}()
 
-		aliceConn, err := mgrAlice.OpenConn(ctx, brokenFQDN, "bob", bobAdvertisedIP)
+		aliceConn, err := mgrAlice.OpenConn(ctx, RelayServer{Addr: brokenFQDN, IP: bobAdvertisedIP}, "bob", true)
 		if err != nil {
 			t.Fatalf("alice OpenConn with server IP: %s", err)
 		}

shared/relay/client/manager_test.go

@@ -3,7 +3,6 @@ package client
 import (
 	"context"
 	"fmt"
-	"net/netip"
 	"testing"
 	"time"
 
@@ -106,11 +105,11 @@ func TestForeignConn(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to get relay address: %s", err)
 	}
-	connAliceToBob, err := clientAlice.OpenConn(ctx, bobsSrvAddr, "bob", netip.Addr{})
+	connAliceToBob, err := clientAlice.OpenConn(ctx, RelayServer{Addr: bobsSrvAddr}, "bob", true)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
-	connBobToAlice, err := clientBob.OpenConn(ctx, bobsSrvAddr, "alice", netip.Addr{})
+	connBobToAlice, err := clientBob.OpenConn(ctx, RelayServer{Addr: bobsSrvAddr}, "alice", false)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
@@ -210,7 +209,7 @@ func TestForeginConnClose(t *testing.T) {
 	if err != nil {
 		t.Fatalf("failed to serve manager: %s", err)
 	}
-	conn, err := mgr.OpenConn(ctx, toURL(srvCfg2)[0], "bob", netip.Addr{})
+	conn, err := mgr.OpenConn(ctx, RelayServer{Addr: toURL(srvCfg2)[0]}, "bob", true)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}
@@ -302,7 +301,7 @@ func TestForeignAutoClose(t *testing.T) {
 	}
 
 	t.Log("open connection to another peer")
-	if _, err = mgr.OpenConn(ctx, foreignServerURL, "anotherpeer", netip.Addr{}); err == nil {
+	if _, err = mgr.OpenConn(ctx, RelayServer{Addr: foreignServerURL}, "anotherpeer", true); err == nil {
 		t.Fatalf("should have failed to open connection to another peer")
 	}
 
@@ -372,7 +371,7 @@ func TestAutoReconnect(t *testing.T) {
 	if err != nil {
 		t.Errorf("failed to get relay address: %s", err)
 	}
-	conn, err := clientAlice.OpenConn(ctx, ra, "bob", netip.Addr{})
+	conn, err := clientAlice.OpenConn(ctx, RelayServer{Addr: ra}, "bob", false)
 	if err != nil {
 		t.Errorf("failed to bind channel: %s", err)
 	}
@@ -392,7 +391,7 @@ func TestAutoReconnect(t *testing.T) {
 	}
 
 	log.Infof("reopent the connection")
-	_, err = clientAlice.OpenConn(ctx, ra, "bob", netip.Addr{})
+	_, err = clientAlice.OpenConn(ctx, RelayServer{Addr: ra}, "bob", false)
 	if err != nil {
 		t.Errorf("failed to open channel: %s", err)
 	}
@@ -454,7 +453,7 @@ func TestNotifierDoubleAdd(t *testing.T) {
 		t.Fatalf("failed to serve manager: %s", err)
 	}
 
-	conn1, err := clientAlice.OpenConn(ctx, clientAlice.ServerURLs()[0], "bob", netip.Addr{})
+	conn1, err := clientAlice.OpenConn(ctx, RelayServer{Addr: clientAlice.ServerURLs()[0]}, "bob", false)
 	if err != nil {
 		t.Fatalf("failed to bind channel: %s", err)
 	}