Add CrowdSec AppSec request inspection to the reverse proxy

* [client] Clear stale installer result before starting update

The installer result file could survive a previous update attempt (e.g.
when the updater wrote it after the restarted daemon already ran its
startup check). A new install attempt left the old file in place, so the
GUI progress window's first GetInstallerResult poll read the outdated
result: a stale success made the GUI quit mid-install, which cancelled
the TriggerUpdate context and aborted the artifact verification; a stale
error surfaced a bogus failure dialog for a succeeding update.

Remove any leftover result file at the start of RunInstallation, before
the download begins, so result watchers only see the current attempt's
outcome.

* [client] Align stale-result warning with log message style

client/android/client.go

@@ -26,6 +26,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/routemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 	"github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -40,11 +42,6 @@ const (
 	AnonymizeLevelStrict  = nbAnonymize.LevelStrictString
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // TunAdapter export internal TunAdapter for mobile
 type TunAdapter interface {
 	device.TunAdapter
@@ -85,6 +82,13 @@ type Client struct {
 	deviceName            string
 	uiVersion             string
 	networkChangeListener listener.NetworkChangeListener
+	// netState outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run and RunWithoutLogin inject it into each new
+	// ConnectClient, which distributes it to every reconnection loop.
+	netState *netstate.State
+
+	// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
+	sweeper *netsweep.Sweeper
 
 	stateMu       sync.RWMutex
 	connectClient *internal.ConnectClient
@@ -156,6 +160,8 @@ func NewClient(androidSDKVersion int, deviceName string, uiVersion string, tunAd
 		recorder:              peer.NewRecorder(""),
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
@@ -196,7 +202,8 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 	}
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	// This path runs the interactive SSO flow, so reaching here means the peer
 	// is authenticated again — release the latch Status() reports from. Clear
@@ -237,7 +244,8 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, cacheDir, cfgFile, connectClient)
 	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
@@ -285,6 +293,24 @@ func (c *Client) GetTunSettings() (*TunSettings, error) {
 	}, nil
 }
 
+// SetNetworkAvailable feeds OS-reported network availability into the client.
+// While unavailable, the internal reconnect loops suspend their attempts and
+// the connection listener reports NoNetwork instead of Connecting; when
+// availability returns, the loops resume immediately with a fresh backoff.
+func (c *Client) SetNetworkAvailable(available bool) {
+	c.netState.Set(available)
+	c.recorder.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange marks the management, signal and relay connections
+// stale after the OS switched networks and schedules a sweep that cuts
+// whatever has not redialed on the new network by then. The engine and the
+// TUN device stay untouched.
+func (c *Client) NotifyNetworkChange() {
+	c.sweeper.MarkNetworkChange()
+	log.Infof("network change: connections marked stale")
+}
+
 // DebugBundle generates a debug bundle, uploads it, and returns the upload key.
 // It works both with and without a running engine. anonymizeLevel is "default"
 // or "strict"; strict also anonymizes internal IP ranges, peer names, and
@@ -525,7 +551,11 @@ func (c *Client) OnUpdatedHostDNS(list *DNSList) error {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	if listener == nil {
+		c.recorder.RemoveConnectionListener()
+		return
+	}
+	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
 }
 
 // RemoveConnectionListener remove connection listener

client/android/connection_listener.go

@@ -0,0 +1,41 @@
+//go:build android
+
+package android
+
+import (
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+// Client state values delivered via ConnectionListener.OnStateChanged,
+// re-exported as basic constants so gomobile emits them into the generated
+// Java bindings. They mirror peer.ClientState*: append-only, never reorder.
+const (
+	ClientStateDisconnected  = int(peer.ClientStateDisconnected)
+	ClientStateConnected     = int(peer.ClientStateConnected)
+	ClientStateConnecting    = int(peer.ClientStateConnecting)
+	ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
+	ClientStateNoNetwork     = int(peer.ClientStateNoNetwork)
+)
+
+// ConnectionListener export internal Listener for mobile. It mirrors
+// peer.Listener with OnStateChanged taking a plain int (one of the
+// ClientState* constants), because gomobile cannot bind named types.
+type ConnectionListener interface {
+	OnStateChanged(state int)
+	OnConnected()
+	OnDisconnected()
+	OnConnecting()
+	OnDisconnecting()
+	OnAddressChanged(string, string)
+	OnPeersListChanged(int)
+}
+
+// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
+// peer.Listener, converting the typed state to the int the binding carries.
+type connectionListenerAdapter struct {
+	ConnectionListener
+}
+
+func (a connectionListenerAdapter) OnStateChanged(state peer.ClientState) {
+	a.ConnectionListener.OnStateChanged(int(state))
+}

client/android/login.go

@@ -191,40 +191,49 @@ func (a *Auth) login(urlOpener URLOpener, isAndroidTV bool) error {
 	return nil
 }
 
-// loginHintSetter is implemented by both concrete flows (PKCE and device code)
-// but absent from the OAuthFlow interface, hence the assertion below — the same
-// way internal/auth wires it in authenticateWithPKCEFlow.
-type loginHintSetter interface {
-	SetLoginHint(hint string)
-}
-
 func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, isAndroidTV bool) (*auth.TokenInfo, error) {
-	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV)
+	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, isAndroidTV, profileLoginHint(a.cfgPath))
 	if err != nil {
 		return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
 	}
 
-	// An empty hint is deliberate, not a fallback: a fresh profile leaves the
-	// choice to the IdP. Switching accounts is done by switching or removing
-	// profiles, not by logging out — logout keeps the email.
-	if a.cfgPath != "" {
-		if hint := readProfileEmail(a.cfgPath); hint != "" {
-			if setter, ok := oAuthFlow.(loginHintSetter); ok {
-				setter.SetLoginHint(hint)
-			}
-		}
+	return runOAuthFlow(a.ctx, oAuthFlow, urlOpener, nil)
+}
+
+// profileLoginHint returns the stored account email for the profile at cfgPath.
+// An empty hint is deliberate, not a fallback: a fresh profile leaves the
+// choice to the IdP. Switching accounts is done by switching or removing
+// profiles, not by logging out — logout keeps the email.
+func profileLoginHint(cfgPath string) string {
+	if cfgPath == "" {
+		return ""
+	}
+	return readProfileEmail(cfgPath)
+}
+
+// runOAuthFlow drives an already acquired OAuth flow to a token: requests the
+// flow info, presents the verification URL through the opener and waits for
+// the browser round-trip. Open is called synchronously — it is what marks the
+// surface as opened on the client side, and a fast token's OnLoginSuccess is
+// a no-op until it has, so the dismissal would be dropped rather than
+// delayed. Openers must therefore not block: they post their UI work and
+// return. onWaiting, when set, runs after the URL is shown, right before the
+// blocking wait.
+func runOAuthFlow(ctx context.Context, flow auth.OAuthFlow, urlOpener URLOpener, onWaiting func()) (*auth.TokenInfo, error) {
+	flowInfo, err := flow.RequestAuthInfo(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("request auth info: %w", err)
 	}
 
-	flowInfo, err := oAuthFlow.RequestAuthInfo(context.TODO())
-	if err != nil {
-		return nil, fmt.Errorf("getting a request OAuth flow info failed: %v", err)
+	urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode)
+
+	if onWaiting != nil {
+		onWaiting()
 	}
 
-	go urlOpener.Open(flowInfo.VerificationURIComplete, flowInfo.UserCode)
-
-	tokenInfo, err := oAuthFlow.WaitToken(a.ctx, flowInfo)
+	tokenInfo, err := flow.WaitToken(ctx, flowInfo)
 	if err != nil {
-		return nil, fmt.Errorf("waiting for browser login failed: %v", err)
+		return nil, fmt.Errorf("wait for token: %w", err)
 	}
 
 	return &tokenInfo, nil

client/android/profile_prefs.go

@@ -0,0 +1,38 @@
+//go:build android
+
+package android
+
+import (
+	"fmt"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+)
+
+type prefsStore interface {
+	Get(namespace string, v any) (bool, error)
+	Put(namespace string, v any) error
+}
+
+type profilePrefs struct {
+	prefs *profilemanager.Prefs
+}
+
+func newProfilePrefs(configDir, profileID string) (*profilePrefs, error) {
+	if configDir == "" || profileID == "" {
+		return nil, fmt.Errorf("profile prefs require a config dir and profile ID")
+	}
+	pm := NewProfileManager(configDir)
+	prefs, err := pm.serviceMgr.ProfilePrefs(profilemanager.ID(profileID), androidUsername)
+	if err != nil {
+		return nil, fmt.Errorf("resolve profile prefs: %w", err)
+	}
+	return &profilePrefs{prefs: prefs}, nil
+}
+
+func (p *profilePrefs) Get(namespace string, v any) (bool, error) {
+	return p.prefs.Get(namespace, v)
+}
+
+func (p *profilePrefs) Put(namespace string, v any) error {
+	return p.prefs.Put(namespace, v)
+}

client/android/ssh_client.go

@@ -0,0 +1,649 @@
+//go:build android
+
+package android
+
+import (
+	"context"
+	"errors"
+	"fmt"
+	"io"
+	"net"
+	"strconv"
+	"strings"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	gossh "golang.org/x/crypto/ssh"
+
+	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/internal/auth"
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	nbssh "github.com/netbirdio/netbird/client/ssh"
+	"github.com/netbirdio/netbird/client/ssh/detection"
+)
+
+const (
+	sshDialTimeout      = 30 * time.Second
+	sshDetectionTimeout = 5 * time.Second
+)
+
+// PasswordRequiredMarker tells Java to prompt for a password and retry. It is
+// a string because gomobile flattens errors to their message, so a sentinel
+// value would not survive the binding.
+const PasswordRequiredMarker = "netbird-ssh-password-required"
+
+// HostKeyUnknownMarker tells Java to show the fingerprint and, on confirmation,
+// retry with TrustHostKey set. The presented fingerprint is appended after the
+// marker so the prompt can display it and the retry can guard against a key
+// that changed between the two connects. Only regular (non-NetBird) servers
+// reach this: NetBird peers verify against the registry.
+const HostKeyUnknownMarker = "netbird-ssh-hostkey-unknown"
+
+var (
+	errPasswordRequired = errors.New(PasswordRequiredMarker)
+	errClientClosed     = errors.New("ssh client closed")
+)
+
+// errHostKeyUnknown carries the presented fingerprint so Connect can build the
+// marker message the Java side parses.
+type errHostKeyUnknown struct {
+	fingerprint string
+}
+
+func (e *errHostKeyUnknown) Error() string {
+	return HostKeyUnknownMarker + ":" + e.fingerprint
+}
+
+// SSHTerminalListener receives SSH session events. It is implemented in Java.
+//
+// All callbacks are invoked from goroutines and may run concurrently with each
+// other; the implementation must be safe to call from any thread.
+type SSHTerminalListener interface {
+	OnConnected()
+	OnData(data []byte)
+	OnClose(reason string)
+	OnError(message string)
+}
+
+// SSHClient is a NetBird-aware SSH client exposed to Java via gomobile.
+//
+// It dials through the running NetBird tunnel and runs a standard SSH session
+// on top with PTY enabled. Host-key verification uses the NetBird-provided
+// peer SSH host keys, identical to the desktop client.
+type SSHClient struct {
+	nb        *Client
+	mu        sync.Mutex
+	listener  SSHTerminalListener
+	urlOpener URLOpener
+
+	sshClient *gossh.Client
+	session   *gossh.Session
+	stdin     io.WriteCloser
+	closed    bool
+
+	// gen identifies the current connection attempt. Connect and Close bump it,
+	// so an in-flight dial or a reader left over from a previous connection
+	// finds itself stale and stays silent instead of publishing OnConnected or
+	// OnClose for a connection the caller already abandoned.
+	gen        uint64
+	dialCancel context.CancelFunc
+
+	// knownHostsConfigDir and knownHostsProfile locate the TOFU store for
+	// regular SSH servers in the profile's preferences. Java supplies them,
+	// since an overlay IP is a different host under a different profile. Empty
+	// until set: without them a regular server cannot be verified and Connect
+	// refuses one.
+	knownHostsConfigDir string
+	knownHostsProfile   string
+	// trustHostKey carries the fingerprint the user confirmed on a previous
+	// attempt, so the retry accepts exactly that key and persists it.
+	trustHostKey string
+}
+
+// NewSSHClient creates a new SSH client bound to the running NetBird Client.
+func NewSSHClient(c *Client) *SSHClient {
+	return &SSHClient{nb: c}
+}
+
+// SetListener registers the Java listener. Must be called before Connect to
+// receive any events.
+func (s *SSHClient) SetListener(l SSHTerminalListener) {
+	s.mu.Lock()
+	s.listener = l
+	s.mu.Unlock()
+}
+
+// SetURLOpener registers the Java URL opener used to display the device-code
+// authorization page in a Custom Tabs window when the target peer requires
+// JWT authentication. Must be set before Connect to be effective.
+func (s *SSHClient) SetURLOpener(opener URLOpener) {
+	s.mu.Lock()
+	s.urlOpener = opener
+	s.mu.Unlock()
+}
+
+// SetKnownHostsStore points the TOFU host-key store at a profile's preferences.
+// Must be set before connecting to a regular SSH server; without it such a
+// server cannot be verified and Connect refuses one.
+func (s *SSHClient) SetKnownHostsStore(configDir, profileID string) {
+	s.mu.Lock()
+	s.knownHostsConfigDir = configDir
+	s.knownHostsProfile = profileID
+	s.mu.Unlock()
+}
+
+// TrustHostKey records the fingerprint the user confirmed for a regular server,
+// so the next Connect accepts that exact key and adds it to the known-hosts
+// store. Passing a fingerprint that no longer matches makes the connect fail
+// rather than trust a key that changed since the prompt.
+func (s *SSHClient) TrustHostKey(fingerprint string) {
+	s.mu.Lock()
+	s.trustHostKey = fingerprint
+	s.mu.Unlock()
+}
+
+// Connect dials the SSH server through the NetBird tunnel and performs the
+// SSH handshake. It auto-detects the server type via SSH banner inspection
+// and selects the appropriate authentication path:
+//
+//   - NetBird-SSH server requiring JWT: launches the OAuth 2.0 device-code
+//     flow, opens the verification URL through the registered URLOpener, and
+//     uses the resulting token as the SSH password. Host-key verification
+//     uses the NetBird peer registry.
+//   - NetBird-SSH server without JWT: authenticates with the NetBird SSH
+//     private key. Host-key verification uses the NetBird peer registry.
+//   - Regular SSH server (e.g. OpenSSH): authenticates with the NetBird key
+//     first (so a user-installed NetBird public key works), then falls back
+//     to the supplied password if non-empty. Host-key verification is
+//     trust-on-first-use against the per-profile known-hosts store.
+//
+// The password parameter is only consulted for regular SSH servers.
+func (s *SSHClient) Connect(host string, port int, user, password string) error {
+	if port < 1 || port > 65535 {
+		return fmt.Errorf("invalid port: %d", port)
+	}
+
+	cfg, cfgPath, cc := s.nb.authSnapshot()
+	if cc == nil {
+		return errors.New("netbird client not running")
+	}
+	if cfg == nil {
+		return errors.New("netbird config not loaded")
+	}
+	engine := cc.Engine()
+	if engine == nil {
+		return errors.New("netbird engine not available")
+	}
+
+	s.mu.Lock()
+	s.gen++
+	gen := s.gen
+	s.mu.Unlock()
+
+	serverType := detectServerType(host, port)
+	log.Debugf("SSH server type: %s", serverType)
+
+	authMethods, hostKeyCallback, err := s.buildAuth(cfg, cfgPath, engine, serverType, password)
+	if err != nil {
+		return err
+	}
+
+	clientConfig := &gossh.ClientConfig{
+		User:            user,
+		Auth:            authMethods,
+		HostKeyCallback: hostKeyCallback,
+		Timeout:         sshDialTimeout,
+	}
+	err = s.dialAndHandshake(gen, host, port, clientConfig)
+
+	// An unknown host key is a prompt, not a failure: return the marker intact
+	// (rootCause would unwrap it) so Java can show the fingerprint and retry.
+	var unknownHost *errHostKeyUnknown
+	if errors.As(err, &unknownHost) {
+		return errors.New(unknownHost.Error())
+	}
+
+	// A regular server may still accept a password, so let the caller ask for
+	// one instead of failing. NetBird servers never use a password, so a
+	// failure there is genuine.
+	if err != nil && serverType != detection.ServerTypeNetBirdJWT &&
+		serverType != detection.ServerTypeNetBirdNoJWT && isAuthFailure(err) &&
+		passwordCouldHelp(err, password != "") {
+		return errPasswordRequired
+	}
+	if err != nil {
+		return rootCause(err)
+	}
+	return nil
+}
+
+// StartSession requests a PTY and starts an interactive shell. Output from
+// the session is forwarded to the listener via OnData.
+func (s *SSHClient) StartSession(cols, rows int) error {
+	err := s.startSession(cols, rows)
+	if err != nil {
+		log.Infof("SSH: start session failed: %v", err)
+		return rootCause(err)
+	}
+	return nil
+}
+
+// Write sends data to the SSH session stdin.
+func (s *SSHClient) Write(data []byte) error {
+	s.mu.Lock()
+	stdin := s.stdin
+	s.mu.Unlock()
+	if stdin == nil {
+		return errors.New("ssh session not started")
+	}
+	if _, err := stdin.Write(data); err != nil {
+		return fmt.Errorf("write stdin: %w", err)
+	}
+	return nil
+}
+
+// Resize updates the PTY window size.
+func (s *SSHClient) Resize(cols, rows int) error {
+	s.mu.Lock()
+	session := s.session
+	s.mu.Unlock()
+	if session == nil {
+		return errors.New("ssh session not started")
+	}
+	return session.WindowChange(rows, cols)
+}
+
+// Reset makes a closed client usable for another Connect: Close leaves the
+// one-shot guard set, and clearing it lets the same client back a reconnect.
+func (s *SSHClient) Reset() {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.closed = false
+}
+
+// Close terminates the SSH session and underlying connection. Safe to call
+// multiple times.
+func (s *SSHClient) Close() error {
+	s.mu.Lock()
+	s.gen++
+	if s.dialCancel != nil {
+		s.dialCancel()
+		s.dialCancel = nil
+	}
+	sshClient := s.sshClient
+	session := s.session
+	stdin := s.stdin
+	s.sshClient = nil
+	s.session = nil
+	s.stdin = nil
+	notify := !s.closed
+	s.closed = true
+	listener := s.listener
+	s.mu.Unlock()
+
+	if stdin != nil {
+		if err := stdin.Close(); err != nil {
+			log.Debugf("ssh: stdin close: %v", err)
+		}
+	}
+	if session != nil {
+		if err := session.Close(); err != nil && !errors.Is(err, io.EOF) {
+			log.Debugf("ssh: session close: %v", err)
+		}
+	}
+	var firstErr error
+	if sshClient != nil {
+		if err := sshClient.Close(); err != nil {
+			firstErr = err
+		}
+	}
+	if notify && listener != nil {
+		listener.OnClose("closed by client")
+	}
+	return firstErr
+}
+
+func (s *SSHClient) startSession(cols, rows int) error {
+	log.Debugf("SSH: starting session %dx%d", cols, rows)
+	s.mu.Lock()
+	sshClient := s.sshClient
+	gen := s.gen
+	s.mu.Unlock()
+
+	if sshClient == nil {
+		return errors.New("ssh client not connected")
+	}
+
+	pty, err := nbssh.StartPTYSession(sshClient, cols, rows)
+	if err != nil {
+		return err
+	}
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		closeQuiet(pty.Session, "stale session")
+		return errClientClosed
+	}
+	s.session = pty.Session
+	s.stdin = pty.Stdin
+	s.mu.Unlock()
+
+	readerDone := make(chan string, 2)
+	go func() { readerDone <- s.readLoop(pty.Stdout, "stdout") }()
+	go func() { readerDone <- s.readLoop(pty.Stderr, "stderr") }()
+	go func() {
+		reason := <-readerDone
+		if second := <-readerDone; reason == "" {
+			reason = second
+		}
+		s.notifyClose(gen, reason)
+	}()
+	log.Debug("SSH: session started, shell running")
+	return nil
+}
+
+func (s *SSHClient) buildAuth(cfg *profilemanager.Config, cfgPath string, engine *internal.Engine,
+	serverType detection.ServerType, password string) ([]gossh.AuthMethod, gossh.HostKeyCallback, error) {
+
+	switch serverType {
+	case detection.ServerTypeNetBirdJWT:
+		token, err := s.requestJWTToken(cfg, cfgPath)
+		if err != nil {
+			return nil, nil, fmt.Errorf("jwt: %w", err)
+		}
+		auths := []gossh.AuthMethod{gossh.Password(token)}
+		return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil
+
+	case detection.ServerTypeNetBirdNoJWT:
+		if cfg.SSHKey == "" {
+			return nil, nil, errors.New("no NetBird SSH key available")
+		}
+		signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey))
+		if err != nil {
+			return nil, nil, fmt.Errorf("parse netbird ssh key: %w", err)
+		}
+		auths := []gossh.AuthMethod{gossh.PublicKeys(signer)}
+		return auths, nbssh.CreateHostKeyCallback(nbssh.PeerKeyLookup(engine.GetPeerSSHKey)), nil
+
+	case detection.ServerTypeRegular:
+		var auths []gossh.AuthMethod
+		if cfg.SSHKey != "" {
+			if signer, err := gossh.ParsePrivateKey([]byte(cfg.SSHKey)); err == nil {
+				auths = append(auths, gossh.PublicKeys(signer))
+			} else {
+				log.Debugf("ssh: parse netbird key for regular auth: %v", err)
+			}
+		}
+		if password != "" {
+			pw := password
+			auths = append(auths, gossh.Password(pw))
+			auths = append(auths, gossh.KeyboardInteractive(func(_, _ string, questions []string, _ []bool) ([]string, error) {
+				answers := make([]string, len(questions))
+				for i := range questions {
+					answers[i] = pw
+				}
+				return answers, nil
+			}))
+		}
+		if len(auths) == 0 {
+			// Nothing to offer at all: ask for a password rather than failing,
+			// so the caller can retry once the user supplies one.
+			return nil, nil, errPasswordRequired
+		}
+		callback, err := s.tofuHostKeyCallback()
+		if err != nil {
+			return nil, nil, err
+		}
+		return auths, callback, nil
+
+	default:
+		return nil, nil, fmt.Errorf("unsupported SSH server type: %v", serverType)
+	}
+}
+
+// tofuHostKeyCallback verifies a regular server's host key against the
+// per-profile known-hosts store. An unknown host returns errHostKeyUnknown so
+// Java can show the fingerprint and, once confirmed, retry with the key
+// trusted; a changed key is rejected outright, as OpenSSH does. When the user
+// has confirmed a fingerprint, the callback accepts exactly that key and
+// appends it to the store.
+func (s *SSHClient) tofuHostKeyCallback() (gossh.HostKeyCallback, error) {
+	s.mu.Lock()
+	configDir := s.knownHostsConfigDir
+	profileID := s.knownHostsProfile
+	trusted := s.trustHostKey
+	s.mu.Unlock()
+
+	if configDir == "" || profileID == "" {
+		return nil, errors.New("no known-hosts store configured for regular SSH")
+	}
+
+	store, err := openKnownHostsStore(configDir, profileID)
+	if err != nil {
+		return nil, fmt.Errorf("load known-hosts store: %w", err)
+	}
+
+	return func(hostname string, remote net.Addr, key gossh.PublicKey) error {
+		verdict, err := store.verify(hostname, remote, key)
+		if err != nil {
+			return err
+		}
+		if verdict == hostKeyMatched {
+			return nil
+		}
+		if verdict == hostKeyChanged {
+			return fmt.Errorf("SSH host key changed for %s (possible attack)", hostname)
+		}
+
+		fingerprint := gossh.FingerprintSHA256(key)
+		if trusted == "" {
+			return &errHostKeyUnknown{fingerprint: fingerprint}
+		}
+		if trusted != fingerprint {
+			return fmt.Errorf("SSH host key changed since it was confirmed for %s", hostname)
+		}
+		if err := store.append(hostname, remote, key); err != nil {
+			return fmt.Errorf("persist trusted host key: %w", err)
+		}
+		// The confirmation is spent: now that the key is stored, a later
+		// reconnect must verify against the file, not re-accept this fingerprint.
+		s.mu.Lock()
+		s.trustHostKey = ""
+		s.mu.Unlock()
+		return nil
+	}, nil
+}
+
+func (s *SSHClient) requestJWTToken(cfg *profilemanager.Config, cfgPath string) (string, error) {
+	s.mu.Lock()
+	urlOpener := s.urlOpener
+	s.mu.Unlock()
+	if urlOpener == nil {
+		return "", errors.New("URL opener not configured for JWT auth")
+	}
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Minute)
+	defer cancel()
+
+	flow, err := auth.NewOAuthFlow(ctx, cfg, false, true, profileLoginHint(cfgPath))
+	if err != nil {
+		return "", fmt.Errorf("create oauth flow: %w", err)
+	}
+
+	// The status callback covers the browser round-trip, which would
+	// otherwise leave the terminal blank.
+	tokenInfo, err := runOAuthFlow(ctx, flow, urlOpener, func() {
+		s.notifyStatus("Waiting for browser authentication...")
+	})
+	if err != nil {
+		return "", err
+	}
+
+	token := tokenInfo.GetTokenToUse()
+	if token == "" {
+		return "", errors.New("empty token returned by IdP")
+	}
+
+	// Tells the client the browser round-trip is over so it can dismiss the
+	// surface it opened, the same way the login and session-extend flows do.
+	// Without it the Custom Tab stays in front of the terminal even though the
+	// token has already been collected.
+	urlOpener.OnLoginSuccess()
+
+	return token, nil
+}
+
+func (s *SSHClient) dialAndHandshake(gen uint64, host string, port int, clientConfig *gossh.ClientConfig) error {
+	addr := net.JoinHostPort(host, strconv.Itoa(port))
+	ctx, cancel := context.WithTimeout(context.Background(), sshDialTimeout)
+	defer cancel()
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		return errClientClosed
+	}
+	s.dialCancel = cancel
+	s.mu.Unlock()
+
+	var dialer net.Dialer
+	conn, err := dialer.DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return fmt.Errorf("dial %s: %w", addr, err)
+	}
+
+	client, err := nbssh.Handshake(ctx, conn, addr, clientConfig)
+	if err != nil {
+		return err
+	}
+
+	s.mu.Lock()
+	if gen != s.gen {
+		s.mu.Unlock()
+		closeQuiet(client, "stale ssh client")
+		return errClientClosed
+	}
+	s.sshClient = client
+	listener := s.listener
+	s.mu.Unlock()
+
+	if listener != nil {
+		listener.OnConnected()
+	}
+	return nil
+}
+
+func (s *SSHClient) readLoop(r io.Reader, name string) string {
+	buf := make([]byte, 4096)
+	for {
+		n, err := r.Read(buf)
+		if n > 0 {
+			s.mu.Lock()
+			listener := s.listener
+			s.mu.Unlock()
+			if listener != nil {
+				chunk := make([]byte, n)
+				copy(chunk, buf[:n])
+				listener.OnData(chunk)
+			}
+		}
+		if err != nil {
+			// EOF is a normal shell exit, so report it without a reason.
+			if errors.Is(err, io.EOF) {
+				return ""
+			}
+			log.Debugf("ssh %s read: %v", name, err)
+			return rootCause(err).Error()
+		}
+	}
+}
+
+// notifyStatus writes a progress line to the terminal through the normal
+// output path, so long steps are visible while nothing else is arriving.
+func (s *SSHClient) notifyStatus(text string) {
+	s.mu.Lock()
+	listener := s.listener
+	s.mu.Unlock()
+	if listener != nil {
+		listener.OnData([]byte("\r\n\x1b[33m" + text + "\x1b[0m\r\n"))
+	}
+}
+
+func (s *SSHClient) notifyClose(gen uint64, reason string) {
+	s.mu.Lock()
+	if gen != s.gen || s.closed {
+		s.mu.Unlock()
+		return
+	}
+	s.closed = true
+	listener := s.listener
+	s.mu.Unlock()
+	if listener != nil {
+		listener.OnClose(reason)
+	}
+}
+
+func closeQuiet(c io.Closer, label string) {
+	if c == nil {
+		return
+	}
+	if err := c.Close(); err != nil && !errors.Is(err, io.EOF) {
+		log.Debugf("ssh: close %s: %v", label, err)
+	}
+}
+
+func detectServerType(host string, port int) detection.ServerType {
+	ctx, cancel := context.WithTimeout(context.Background(), sshDetectionTimeout)
+	defer cancel()
+
+	dialer := &net.Dialer{}
+	serverType, err := detection.DetectSSHServerType(ctx, dialer, host, port)
+	if err != nil {
+		log.Debugf("ssh: server detection failed: %v (assuming regular SSH)", err)
+		return detection.ServerTypeRegular
+	}
+	return serverType
+}
+
+// rootCause returns the innermost error of a %w chain, so the terminal shows
+// "i/o timeout" rather than every layer that added context on the way up.
+func rootCause(err error) error {
+	for {
+		// A joined error has no single root, so keep it as-is.
+		if _, ok := err.(interface{ Unwrap() []error }); ok {
+			return err
+		}
+		next := errors.Unwrap(err)
+		if next == nil {
+			return err
+		}
+		err = next
+	}
+}
+
+// isAuthFailure distinguishes credential rejection from dial, timeout and
+// host-key errors, which retrying with a password would not fix.
+func isAuthFailure(err error) bool {
+	if errors.Is(err, errPasswordRequired) {
+		return true
+	}
+	var partial *gossh.PartialSuccessError
+	if errors.As(err, &partial) {
+		return true
+	}
+	return strings.Contains(err.Error(), "unable to authenticate")
+}
+
+// passwordCouldHelp reports whether prompting for a password again can change
+// the outcome. gossh lists a method under "attempted methods" only when the
+// server offered it, so a supplied password that was never attempted means the
+// server does not accept passwords and the real error should surface instead.
+func passwordCouldHelp(err error, passwordOffered bool) bool {
+	if !passwordOffered {
+		return true
+	}
+	msg := err.Error()
+	return strings.Contains(msg, "password") || strings.Contains(msg, "keyboard-interactive")
+}

client/android/ssh_known_hosts.go

@@ -0,0 +1,168 @@
+//go:build android
+
+package android
+
+import (
+	"bytes"
+	"net"
+	"strconv"
+	"strings"
+	"sync"
+
+	gossh "golang.org/x/crypto/ssh"
+	"golang.org/x/crypto/ssh/knownhosts"
+)
+
+const knownHostsNamespace = "ssh"
+
+const (
+	hostKeyUnknown hostKeyVerdict = iota
+	hostKeyMatched
+	hostKeyChanged
+)
+
+var knownHostsMu sync.Mutex
+
+type hostKeyVerdict uint8
+
+type knownHostsSection struct {
+	KnownHosts []string `json:"knownHosts"`
+}
+
+type knownHostsStore struct {
+	prefs prefsStore
+}
+
+// RemoveKnownHost deletes every known-hosts entry for host:port from the
+// profile's store, so a host trusted for a session that is being deleted does
+// not linger. Java calls this only once no session targets that host, so a
+// shared host stays trusted. A missing entry is not an error: the goal state
+// is "absent".
+func RemoveKnownHost(configDir, profileID, host string, port int) error {
+	store, err := openKnownHostsStore(configDir, profileID)
+	if err != nil {
+		return err
+	}
+	return store.removeHost(host, port)
+}
+
+func openKnownHostsStore(configDir, profileID string) (*knownHostsStore, error) {
+	prefs, err := newProfilePrefs(configDir, profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &knownHostsStore{prefs: prefs}, nil
+}
+
+func (st *knownHostsStore) verify(hostname string, remote net.Addr, key gossh.PublicKey) (hostKeyVerdict, error) {
+	lines, err := st.lines()
+	if err != nil {
+		return hostKeyUnknown, err
+	}
+	targets := knownHostsTargets(hostname, remote)
+
+	verdict := hostKeyUnknown
+	for _, line := range lines {
+		pubKey, ok := knownHostsLineKey(line, targets)
+		if !ok {
+			continue
+		}
+		if pubKey.Type() == key.Type() && bytes.Equal(pubKey.Marshal(), key.Marshal()) {
+			return hostKeyMatched, nil
+		}
+		verdict = hostKeyChanged
+	}
+	return verdict, nil
+}
+
+func (st *knownHostsStore) append(hostname string, remote net.Addr, key gossh.PublicKey) error {
+	line := knownhosts.Line(knownHostsTargets(hostname, remote), key)
+
+	knownHostsMu.Lock()
+	defer knownHostsMu.Unlock()
+
+	lines, err := st.lines()
+	if err != nil {
+		return err
+	}
+	return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: append(lines, line)})
+}
+
+func (st *knownHostsStore) removeHost(host string, port int) error {
+	target := knownhosts.Normalize(net.JoinHostPort(host, strconv.Itoa(port)))
+
+	knownHostsMu.Lock()
+	defer knownHostsMu.Unlock()
+
+	lines, err := st.lines()
+	if err != nil {
+		return err
+	}
+	kept := make([]string, 0, len(lines))
+	for _, line := range lines {
+		if knownHostsLineMatches(line, target) {
+			continue
+		}
+		kept = append(kept, line)
+	}
+	if len(kept) == len(lines) {
+		return nil
+	}
+	return st.prefs.Put(knownHostsNamespace, knownHostsSection{KnownHosts: kept})
+}
+
+func (st *knownHostsStore) lines() ([]string, error) {
+	var section knownHostsSection
+	if _, err := st.prefs.Get(knownHostsNamespace, &section); err != nil {
+		return nil, err
+	}
+	return section.KnownHosts, nil
+}
+
+func knownHostsTargets(hostname string, remote net.Addr) []string {
+	targets := []string{knownhosts.Normalize(hostname)}
+	if remote != nil {
+		if normalized := knownhosts.Normalize(remote.String()); normalized != targets[0] {
+			targets = append(targets, normalized)
+		}
+	}
+	return targets
+}
+
+func knownHostsLineKey(line string, targets []string) (gossh.PublicKey, bool) {
+	trimmed := strings.TrimSpace(line)
+	if trimmed == "" || strings.HasPrefix(trimmed, "#") {
+		return nil, false
+	}
+	_, hosts, pubKey, _, _, err := gossh.ParseKnownHosts([]byte(trimmed))
+	if err != nil {
+		return nil, false
+	}
+	for _, host := range hosts {
+		for _, target := range targets {
+			if host == target {
+				return pubKey, true
+			}
+		}
+	}
+	return nil, false
+}
+
+// knownHostsLineMatches reports whether a known-hosts line's address list
+// contains the normalized target. Comment and blank lines never match.
+func knownHostsLineMatches(line, target string) bool {
+	trimmed := strings.TrimSpace(line)
+	if trimmed == "" || strings.HasPrefix(trimmed, "#") {
+		return false
+	}
+	fields := strings.Fields(trimmed)
+	if len(fields) == 0 {
+		return false
+	}
+	for _, addr := range strings.Split(fields[0], ",") {
+		if addr == target {
+			return true
+		}
+	}
+	return false
+}

client/android/ssh_sessions.go

@@ -0,0 +1,104 @@
+//go:build android
+
+package android
+
+const (
+	sshSessionsNamespace = "ssh-sessions"
+	maxStoredSSHSessions = 50
+)
+
+type sshSessionRecord struct {
+	ID   string `json:"id"`
+	Host string `json:"host"`
+	Port int    `json:"port"`
+	User string `json:"user"`
+}
+
+type sshSessionsSection struct {
+	Sessions []sshSessionRecord `json:"sessions"`
+}
+
+// SSHSessionEntry is one stored SSH session, without any credential.
+type SSHSessionEntry struct {
+	ID   string
+	Host string
+	Port int
+	User string
+}
+
+// SSHSessionArray wraps stored SSH sessions for gomobile compatibility.
+type SSHSessionArray struct {
+	items []*SSHSessionEntry
+}
+
+// NewSSHSessionArray creates an empty session array to fill via Add.
+func NewSSHSessionArray() *SSHSessionArray {
+	return &SSHSessionArray{}
+}
+
+// Add appends a session entry, oldest first.
+func (a *SSHSessionArray) Add(id, host string, port int, user string) {
+	a.items = append(a.items, &SSHSessionEntry{ID: id, Host: host, Port: port, User: user})
+}
+
+// Length returns the number of entries.
+func (a *SSHSessionArray) Length() int {
+	return len(a.items)
+}
+
+// Get returns the entry at index i, or nil when out of range.
+func (a *SSHSessionArray) Get(i int) *SSHSessionEntry {
+	if i < 0 || i >= len(a.items) {
+		return nil
+	}
+	return a.items[i]
+}
+
+// SSHSessionStore reads and writes a profile's stored SSH sessions.
+type SSHSessionStore struct {
+	prefs prefsStore
+}
+
+// NewSSHSessionStore opens the session store of the given profile.
+func NewSSHSessionStore(configDir, profileID string) (*SSHSessionStore, error) {
+	prefs, err := newProfilePrefs(configDir, profileID)
+	if err != nil {
+		return nil, err
+	}
+	return &SSHSessionStore{prefs: prefs}, nil
+}
+
+// Load returns the stored sessions, oldest first.
+func (s *SSHSessionStore) Load() (*SSHSessionArray, error) {
+	var section sshSessionsSection
+	if _, err := s.prefs.Get(sshSessionsNamespace, &section); err != nil {
+		return nil, err
+	}
+
+	out := NewSSHSessionArray()
+	for _, record := range section.Sessions {
+		if record.ID == "" || record.Host == "" {
+			continue
+		}
+		out.Add(record.ID, record.Host, record.Port, record.User)
+	}
+	return out, nil
+}
+
+// Save replaces the stored sessions, keeping only the newest entries when the
+// list exceeds the storage cap.
+func (s *SSHSessionStore) Save(sessions *SSHSessionArray) error {
+	var items []*SSHSessionEntry
+	if sessions != nil {
+		items = sessions.items
+	}
+	if len(items) > maxStoredSSHSessions {
+		items = items[len(items)-maxStoredSSHSessions:]
+	}
+
+	records := make([]sshSessionRecord, 0, len(items))
+	for _, item := range items {
+		records = append(records, sshSessionRecord{ID: item.ID, Host: item.Host, Port: item.Port, User: item.User})
+	}
+	return s.prefs.Put(sshSessionsNamespace, sshSessionsSection{Sessions: records})
+}

client/embed/embed.go

@@ -21,7 +21,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/auth"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
-	sshcommon "github.com/netbirdio/netbird/client/ssh"
+	nbssh "github.com/netbirdio/netbird/client/ssh"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/shared/management/domain"
 	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
@@ -521,12 +521,7 @@ func (c *Client) VerifySSHHostKey(peerAddress string, key []byte) error {
 		return err
 	}
 
-	storedKey, found := engine.GetPeerSSHKey(peerAddress)
-	if !found {
-		return sshcommon.ErrPeerNotFound
-	}
-
-	return sshcommon.VerifyHostKey(storedKey, key, peerAddress)
+	return nbssh.PeerKeyLookup(engine.GetPeerSSHKey).VerifySSHHostKey(peerAddress, key)
 }
 
 // SetPerformance retunes a running Client. Only PreallocatedBuffersPerPool

client/grpc/dialer_generic.go

@@ -16,28 +16,47 @@ import (
 	"google.golang.org/grpc"
 
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netsweep"
 )
 
 func WithCustomDialer(_ bool, _ string) grpc.DialOption {
+	return grpc.WithContextDialer(dialContext)
+}
+
+// WithSweeper dials like WithCustomDialer but registers connections and
+// dials with the sweeper. Append it after WithCustomDialer: gRPC applies
+// dial options in order, so the later context dialer wins.
+func WithSweeper(sweeper *netsweep.Sweeper) grpc.DialOption {
 	return grpc.WithContextDialer(func(ctx context.Context, addr string) (net.Conn, error) {
-		if runtime.GOOS == "linux" {
-			currentUser, err := user.Current()
-			if err != nil {
-				return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
-			}
+		dial := sweeper.StartDial(ctx)
+		defer dial.Release()
 
-			// the custom dialer requires root permissions which are not required for use cases run as non-root
-			if currentUser.Uid != "0" {
-				log.Debug("Not running as root, using standard dialer")
-				dialer := &net.Dialer{}
-				return dialer.DialContext(ctx, "tcp", addr)
-			}
-		}
-
-		conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+		conn, err := dialContext(dial.Ctx(), addr)
 		if err != nil {
-			return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+			return nil, err
 		}
-		return conn, nil
+		return dial.WrapConn(conn)
 	})
 }
+
+func dialContext(ctx context.Context, addr string) (net.Conn, error) {
+	if runtime.GOOS == "linux" {
+		currentUser, err := user.Current()
+		if err != nil {
+			return nil, status.Errorf(codes.FailedPrecondition, "failed to get current user: %v", err)
+		}
+
+		// the custom dialer requires root permissions which are not required for use cases run as non-root
+		if currentUser.Uid != "0" {
+			log.Debug("Not running as root, using standard dialer")
+			dialer := &net.Dialer{}
+			return dialer.DialContext(ctx, "tcp", addr)
+		}
+	}
+
+	conn, err := nbnet.NewDialer().DialContext(ctx, "tcp", addr)
+	if err != nil {
+		return nil, fmt.Errorf("nbnet.NewDialer().DialContext: %w", err)
+	}
+	return conn, nil
+}

client/grpc/dialer_js.go

@@ -3,6 +3,7 @@ package grpc
 import (
 	"google.golang.org/grpc"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/util/wsproxy/client"
 )
 
@@ -11,3 +12,8 @@ import (
 func WithCustomDialer(tlsEnabled bool, component string) grpc.DialOption {
 	return client.WithWebSocketDialer(tlsEnabled, component)
 }
+
+// WithSweeper is a no-op on WASM/JS: there is no network change signal.
+func WithSweeper(_ *netsweep.Sweeper) grpc.DialOption {
+	return grpc.EmptyDialOption{}
+}

client/grpc/retry.go

@@ -0,0 +1,49 @@
+package grpc
+
+import (
+	"context"
+	"errors"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+// Retry mirrors backoff.Retry, but the sleep between attempts also wakes on
+// OS network availability transitions: an operation cut down by a network
+// change retries the moment the network settles instead of sleeping through
+// the recovery. A nil netState never fires, leaving plain backoff.Retry
+// behavior.
+func Retry(ctx context.Context, operation backoff.Operation, bo backoff.BackOff, netState *netstate.State) error {
+	bo.Reset()
+	for {
+		err := operation()
+		if err == nil {
+			return nil
+		}
+
+		var permanent *backoff.PermanentError
+		if errors.As(err, &permanent) {
+			return permanent.Err
+		}
+
+		next := bo.NextBackOff()
+		if next == backoff.Stop {
+			if cerr := ctx.Err(); cerr != nil {
+				return cerr
+			}
+			return err
+		}
+
+		timer := time.NewTimer(next)
+		select {
+		case <-timer.C:
+		case <-netState.Changed():
+			timer.Stop()
+		case <-ctx.Done():
+			timer.Stop()
+			return ctx.Err()
+		}
+	}
+}

client/grpc/retry_test.go

@@ -0,0 +1,91 @@
+package grpc
+
+import (
+	"context"
+	"errors"
+	"testing"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+func TestRetryWakesOnNetworkChange(t *testing.T) {
+	ns := netstate.New()
+	attempts := 0
+	operation := func() error {
+		attempts++
+		if attempts == 1 {
+			return errors.New("cut by network change")
+		}
+		return nil
+	}
+
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		ns.Set(false)
+	}()
+
+	start := time.Now()
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Minute), ns)
+
+	require.NoError(t, err)
+	assert.Equal(t, 2, attempts, "network change must cause one immediate retry")
+	assert.Less(t, time.Since(start), time.Second, "the transition must cut the minute-long sleep short")
+}
+
+func TestRetryPermanentError(t *testing.T) {
+	sentinel := errors.New("permission denied")
+	operation := func() error {
+		return backoff.Permanent(sentinel)
+	}
+
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
+	assert.ErrorIs(t, err, sentinel, "permanent errors must stop retries")
+}
+
+func TestRetryNilNetState(t *testing.T) {
+	attempts := 0
+	operation := func() error {
+		attempts++
+		if attempts < 3 {
+			return errors.New("transient")
+		}
+		return nil
+	}
+
+	err := Retry(context.Background(), operation, backoff.NewConstantBackOff(time.Millisecond), nil)
+	require.NoError(t, err)
+	assert.Equal(t, 3, attempts, "nil network state must preserve timed retries")
+}
+
+func TestRetryStops(t *testing.T) {
+	failure := errors.New("still failing")
+	operation := func() error {
+		return failure
+	}
+
+	err := Retry(context.Background(), operation, &backoff.StopBackOff{}, nil)
+	assert.ErrorIs(t, err, failure, "stop backoff must return the operation error")
+}
+
+func TestRetryCtxCancelDuringSleep(t *testing.T) {
+	ctx, cancel := context.WithCancel(context.Background())
+	operation := func() error {
+		return errors.New("failing")
+	}
+
+	go func() {
+		time.Sleep(20 * time.Millisecond)
+		cancel()
+	}()
+
+	start := time.Now()
+	err := Retry(ctx, operation, backoff.NewConstantBackOff(time.Minute), netstate.New())
+
+	assert.ErrorIs(t, err, context.Canceled, "context cancellation must stop the retry loop")
+	assert.Less(t, time.Since(start), time.Second, "context cancellation must interrupt backoff sleep")
+}

client/internal/auth/auth.go

@@ -138,26 +138,37 @@ func (a *Auth) IsSSOSupported(ctx context.Context) (bool, error) {
 
 // GetOAuthFlow returns an OAuth flow (PKCE or Device) using the existing management connection
 // This avoids creating a new connection to the management server
-func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool) (OAuthFlow, error) {
+func (a *Auth) GetOAuthFlow(ctx context.Context, forceDeviceAuth bool, hint string) (OAuthFlow, error) {
 	var flow OAuthFlow
-	var err error
 
-	err = a.withRetry(ctx, func(client *mgm.GrpcClient) error {
+	err := a.withRetry(ctx, func(client *mgm.GrpcClient) error {
 		if forceDeviceAuth {
-			flow, err = a.getDeviceFlow(client)
-			return err
+			deviceFlow, err := a.getDeviceFlow(client)
+			if err != nil {
+				return err
+			}
+			deviceFlow.SetLoginHint(hint)
+			flow = deviceFlow
+			return nil
 		}
 
 		// Try PKCE flow first
-		flow, err = a.getPKCEFlow(client)
+		pkceFlow, err := a.getPKCEFlow(client)
 		if err != nil {
 			// If PKCE not supported, try Device flow
 			if s, ok := status.FromError(err); ok && (s.Code() == codes.NotFound || s.Code() == codes.Unimplemented) {
-				flow, err = a.getDeviceFlow(client)
-				return err
+				deviceFlow, err := a.getDeviceFlow(client)
+				if err != nil {
+					return err
+				}
+				deviceFlow.SetLoginHint(hint)
+				flow = deviceFlow
+				return nil
 			}
 			return err
 		}
+		pkceFlow.SetLoginHint(hint)
+		flow = pkceFlow
 		return nil
 	})
 

client/internal/auth/oauth.go

@@ -97,9 +97,7 @@ func authenticateWithPKCEFlow(ctx context.Context, config *profilemanager.Config
 		return nil, fmt.Errorf("getting pkce authorization flow info failed with error: %v", err)
 	}
 
-	if hint != "" {
-		pkceFlowInfo.SetLoginHint(hint)
-	}
+	pkceFlowInfo.SetLoginHint(hint)
 
 	return pkceFlowInfo, nil
 }
@@ -127,9 +125,7 @@ func authenticateWithDeviceCodeFlow(ctx context.Context, config *profilemanager.
 		}
 	}
 
-	if hint != "" {
-		deviceFlowInfo.SetLoginHint(hint)
-	}
+	deviceFlowInfo.SetLoginHint(hint)
 
 	return deviceFlowInfo, nil
 }

client/internal/connect.go

@@ -38,6 +38,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/ssh"
 	sshconfig "github.com/netbirdio/netbird/client/ssh/config"
@@ -70,18 +72,42 @@ type ConnectClient struct {
 	updateManager *updater.Manager
 
 	persistSyncResponse bool
+
+	// netState gates every reconnection loop on OS-reported network
+	// availability. Nil (the default) disables gating; mobile platforms
+	// inject it via WithNetworkState.
+	netState *netstate.State
+
+	// sweeper cuts the management, signal and relay connections on network
+	// change; nil disables it.
+	sweeper *netsweep.Sweeper
+}
+
+// ConnectClientOption configures optional ConnectClient behavior.
+type ConnectClientOption func(*ConnectClient)
+
+// WithNetworkState injects the OS network availability state that gates every
+// reconnection loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) ConnectClientOption {
+	return func(c *ConnectClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ConnectClientOption {
+	return func(c *ConnectClient) { c.sweeper = sweeper }
 }
 
 func NewConnectClient(
 	ctx context.Context,
 	config *profilemanager.Config,
 	statusRecorder *peer.Status,
+	opts ...ConnectClientOption,
 ) *ConnectClient {
 	// Derive the run context here so Stop owns the cancel that unblocks the run
 	// loop. runCancel is set once at construction, so Stop can call it without
 	// racing the run loop's startup. Callers therefore need not cancel before Stop.
 	runCtx, runCancel := context.WithCancel(ctx)
-	return &ConnectClient{
+	c := &ConnectClient{
 		ctx:            runCtx,
 		runCancel:      runCancel,
 		runExited:      make(chan struct{}),
@@ -89,6 +115,10 @@ func NewConnectClient(
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
 	}
+	for _, opt := range opts {
+		opt(c)
+	}
+	return c
 }
 
 func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
@@ -274,6 +304,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			return nil
 		}
 
+		// suspend connection attempts while the OS reports no usable network
+		if waited, err := c.netState.Wait(c.ctx); err != nil {
+			return nil
+		} else if waited {
+			backOff.Reset()
+		}
+
 		state.Set(StatusConnecting)
 
 		engineCtx, cancel := context.WithCancel(c.ctx)
@@ -285,7 +322,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
-		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
+		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled,
+			mgm.WithNetworkState(c.netState), mgm.WithSweeper(c.sweeper))
 		if err != nil {
 			// On daemon shutdown / Down() the parent context is cancelled
 			// and the dial fails with "context canceled". Wrapping that
@@ -360,7 +398,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}()
 
 		// with the global Netbird config in hand connect (just a connection, no stream yet) Signal
-		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey)
+		signalClient, err := connectToSignal(engineCtx, loginResp.GetNetbirdConfig(), myPrivateKey, c.netState, c.sweeper)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -396,7 +434,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			engineConfig.StateDir = filepath.Dir(path)
 		}
 
-		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU)
+		relayManager := relayClient.NewManager(engineCtx, relayURLs, myPrivateKey.PublicKey().String(), engineConfig.MTU,
+			relayClient.WithNetworkState(c.netState), relayClient.WithSweeper(c.sweeper))
 		c.statusRecorder.SetRelayMgr(relayManager)
 		if len(relayURLs) > 0 {
 			if token != nil {
@@ -424,6 +463,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			UpdateManager:  c.updateManager,
 			ClientMetrics:  c.clientMetrics,
 			MetricsCtx:     c.ctx,
+			NetState:       c.netState,
 		}, mobileDependency)
 		engine.SetSyncResponsePersistence(c.persistSyncResponse)
 		c.engine = engine
@@ -480,6 +520,16 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	// status stream stuck at Connecting.
 	err = backoff.Retry(operation, backoff.WithContext(backOff, c.ctx))
 	if err != nil {
+		// Once the client context is cancelled backoff.WithContext surfaces the
+		// bare context error, and any attempt torn down mid-flight reports the
+		// same. That cancellation is the caller asking us to stop (Stop, Down or
+		// an engine restart), so exit cleanly instead of handing back a failure
+		// the caller would have to distinguish from a real one.
+		if c.ctx.Err() != nil && errors.Is(err, context.Canceled) {
+			log.Info("exiting client retry loop, context cancelled")
+			return nil
+		}
+
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 			state.Set(StatusNeedsLogin)
@@ -673,7 +723,7 @@ func selectMTU(localMTU uint16, peerMTU int32) uint16 {
 }
 
 // connectToSignal creates Signal Service client and established a connection
-func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key) (*signal.GrpcClient, error) {
+func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourPrivateKey wgtypes.Key, netState *netstate.State, sweeper *netsweep.Sweeper) (*signal.GrpcClient, error) {
 	var sigTLSEnabled bool
 	if wtConfig.Signal.Protocol == mgmProto.HostConfig_HTTPS {
 		sigTLSEnabled = true
@@ -681,7 +731,8 @@ func connectToSignal(ctx context.Context, wtConfig *mgmProto.NetbirdConfig, ourP
 		sigTLSEnabled = false
 	}
 
-	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled)
+	signalClient, err := signal.NewClient(ctx, wtConfig.Signal.Uri, ourPrivateKey, sigTLSEnabled,
+		signal.WithNetworkState(netState), signal.WithSweeper(sweeper))
 	if err != nil {
 		log.Errorf("error while connecting to the Signal Exchange Service %s: %s", wtConfig.Signal.Uri, err)
 		return nil, gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Signal Service : %s", err)

client/internal/engine.go

@@ -59,6 +59,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/syncstore"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/jobexec"
+	"github.com/netbirdio/netbird/client/netstate"
 	cProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/system"
 	nbdns "github.com/netbirdio/netbird/dns"
@@ -181,6 +182,9 @@ type EngineServices struct {
 	UpdateManager  *updater.Manager
 	ClientMetrics  *metrics.ClientMetrics
 	MetricsCtx     context.Context
+	// NetState gates the reconnection loops on OS-reported network
+	// availability; nil disables gating.
+	NetState *netstate.State
 }
 
 // Engine is a mechanism responsible for reacting on Signal and Management stream events and managing connections to the remote peers.
@@ -204,6 +208,10 @@ type Engine struct {
 	config    *EngineConfig
 	mobileDep MobileDependency
 
+	// netState gates the peer reconnection guards on OS-reported network
+	// availability; nil disables gating.
+	netState *netstate.State
+
 	// STUNs is a list of STUN servers used by ICE
 	STUNs []*stun.URI
 	// TURNs is a list of STUN servers used by ICE
@@ -337,6 +345,7 @@ func NewEngine(
 		syncMsgMux:         &sync.Mutex{},
 		config:             config,
 		mobileDep:          mobileDep,
+		netState:           services.NetState,
 		STUNs:              []*stun.URI{},
 		TURNs:              []*stun.URI{},
 		networkSerial:      0,
@@ -1893,7 +1902,8 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 			Addr:           e.getRosenpassAddr(),
 			PermissiveMode: e.config.RosenpassPermissive,
 		},
-		ICEConfig: e.createICEConfig(),
+		ICEConfig:    e.createICEConfig(),
+		NetworkState: e.netState,
 	}
 
 	serviceDependencies := peer.ServiceDependencies{

client/internal/peer/conn.go

@@ -26,6 +26,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/portforward"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
+	"github.com/netbirdio/netbird/client/netstate"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
@@ -93,6 +94,10 @@ type ConnConfig struct {
 
 	// ICEConfig ICE protocol configuration
 	ICEConfig icemaker.Config
+
+	// NetworkState gates the reconnection guard on OS-reported network
+	// availability; nil disables gating.
+	NetworkState *netstate.State
 }
 
 type Conn struct {
@@ -254,7 +259,7 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error {
 		conn.handshaker.AddICEListener(conn.workerICE.OnNewOffer)
 	}
 
-	conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher)
+	conn.guard = guard.NewGuard(conn.Log, conn.isConnectedOnAllWay, conn.config.Timeout, conn.srWatcher, conn.config.NetworkState)
 
 	conn.wg.Add(1)
 	go func() {

client/internal/peer/guard/guard.go

@@ -6,6 +6,8 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netstate"
 )
 
 // ConnStatus represents the connection state as seen by the guard.
@@ -31,20 +33,26 @@ type connStatusFunc func() ConnStatus
 // - Relayed connection disconnected
 // - ICE candidate changes
 type Guard struct {
-	log                     *log.Entry
-	isConnectedOnAllWay     connStatusFunc
-	timeout                 time.Duration
-	srWatcher               *SRWatcher
+	log                 *log.Entry
+	isConnectedOnAllWay connStatusFunc
+	timeout             time.Duration
+	srWatcher           *SRWatcher
+	// netState gates reconnect attempts on OS-reported network availability;
+	// nil disables gating.
+	netState                *netstate.State
 	relayedConnDisconnected chan struct{}
 	iCEConnDisconnected     chan struct{}
 }
 
-func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher) *Guard {
+// NewGuard creates a reconnection guard for a peer connection. A nil netState
+// disables network availability gating.
+func NewGuard(log *log.Entry, isConnectedFn connStatusFunc, timeout time.Duration, srWatcher *SRWatcher, netState *netstate.State) *Guard {
 	return &Guard{
 		log:                     log,
 		isConnectedOnAllWay:     isConnectedFn,
 		timeout:                 timeout,
 		srWatcher:               srWatcher,
+		netState:                netState,
 		relayedConnDisconnected: make(chan struct{}, 1),
 		iCEConnDisconnected:     make(chan struct{}, 1),
 	}
@@ -96,9 +104,16 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 	iceState := &iceRetryState{log: g.log}
 	defer iceState.reset()
 
+	netChanged := g.netState.Changed()
+
 	for {
 		select {
 		case <-tickerChannel:
+			// skip attempts while the OS reports no usable network; the
+			// netChanged case below resumes the loop once it returns
+			if !g.netState.IsOnline() {
+				continue
+			}
 			switch g.isConnectedOnAllWay() {
 			case ConnStatusConnected:
 				// all good, nothing to do
@@ -135,6 +150,23 @@ func (g *Guard) reconnectLoopWithRetry(ctx context.Context, callback func()) {
 			tickerChannel = ticker.C
 			iceState.reset()
 
+		case <-netChanged:
+			// Re-arm for the next transition before acting on this one.
+			netChanged = g.netState.Changed()
+			if !g.netState.IsOnline() {
+				continue
+			}
+			// Ticks skipped while offline drove the backoff towards its
+			// maximum without ever attempting, and left the ICE budget
+			// frozen — possibly in hourly mode. Recover on our own so the
+			// peer does not depend on a signal or relay event that never
+			// comes when both stayed up across the outage.
+			g.log.Debugf("network is back, reset reconnection ticker")
+			ticker.Stop()
+			ticker = g.newReconnectTicker(ctx)
+			tickerChannel = ticker.C
+			iceState.reset()
+
 		case <-ctx.Done():
 			g.log.Debugf("context is done, stop reconnect loop")
 			return

client/internal/peer/guard/guard_leak_test.go

@@ -15,7 +15,7 @@ import (
 
 func newTestGuard(status connStatusFunc) *Guard {
 	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
-	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw)
+	return NewGuard(log.WithField("test", "guard"), status, 50*time.Millisecond, srw, nil)
 }
 
 // countBackoffTickerGoroutines returns how many goroutines are currently sitting

client/internal/peer/guard/guard_netstate_test.go

@@ -0,0 +1,107 @@
+package guard
+
+import (
+	"context"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/internal/peer/ice"
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+// newTestGuardWithNetState builds a guard with a realistic MaxInterval: the
+// backoff must be able to grow well past the outage, as it does in production
+// where the timeout is seconds to minutes.
+func newTestGuardWithNetState(status connStatusFunc, netState *netstate.State) *Guard {
+	srw := NewSRWatcher(nil, nil, nil, ice.Config{})
+	return NewGuard(log.WithField("test", "guard"), status, 30*time.Second, srw, netState)
+}
+
+// TestGuard_RecoversAfterOfflineToOnline covers a peer that stays disconnected
+// across a network outage while neither signal nor relay reports an event —
+// both stayed up, as on a short airplane mode toggle over Wi-Fi.
+//
+// Every tick taken while offline is skipped, but it still advances the
+// exponential backoff, so by the time the network returns the next tick can be
+// tens of seconds away. Without an explicit reaction to the transition the
+// peer waits out that interval for a recovery that could start immediately.
+func TestGuard_RecoversAfterOfflineToOnline(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	// Start from the reconnect ticker (800ms initial interval), the state a
+	// peer is in after it loses its connection.
+	go g.Start(ctx, func() { attempts.Add(1) })
+	g.SetRelayedConnDisconnected()
+
+	// Let the backoff climb: 0.8s, 1.6s, 3.2s, 6.4s ... every tick is skipped
+	// while offline, but each one doubles the wait for the next.
+	netState.Set(false)
+	time.Sleep(8 * time.Second)
+
+	offlineAttempts := attempts.Load()
+	if offlineAttempts != 0 {
+		t.Fatalf("callback ran %d times while offline, want 0", offlineAttempts)
+	}
+
+	netState.Set(true)
+
+	// The next organic tick is now several seconds out, so anything within
+	// this window can only come from reacting to the transition itself.
+	pollCtx, stopPolling := context.WithTimeout(ctx, 2*time.Second)
+	defer stopPolling()
+
+	select {
+	case <-pollCtx.Done():
+		t.Fatal("peer was not retried within 2s of the network coming back, " +
+			"with neither a signal nor a relay event to fall back on")
+	case <-pollUntil(pollCtx, func() bool { return attempts.Load() > 0 }):
+	}
+}
+
+// TestGuard_OfflineTransitionDoesNotRetry checks the other direction: going
+// offline must not itself trigger an attempt.
+func TestGuard_OfflineTransitionDoesNotRetry(t *testing.T) {
+	netState := netstate.New()
+
+	var attempts atomic.Int32
+	g := newTestGuardWithNetState(func() ConnStatus { return ConnStatusDisconnected }, netState)
+
+	ctx, cancel := context.WithCancel(context.Background())
+	defer cancel()
+	go g.Start(ctx, func() { attempts.Add(1) })
+
+	netState.Set(false)
+	time.Sleep(5 * time.Second)
+
+	if got := attempts.Load(); got != 0 {
+		t.Fatalf("callback ran %d times after going offline, want 0", got)
+	}
+}
+
+// pollUntil closes the returned channel once cond holds. It gives up when ctx
+// is done, so the polling goroutine never outlives the test that started it.
+func pollUntil(ctx context.Context, cond func() bool) <-chan struct{} {
+	done := make(chan struct{})
+	go func() {
+		for {
+			if cond() {
+				close(done)
+				return
+			}
+			select {
+			case <-ctx.Done():
+				return
+			case <-time.After(10 * time.Millisecond):
+			}
+		}
+	}()
+	return done
+}

client/internal/peer/listener.go

@@ -1,11 +1,40 @@
 package peer
 
+// ClientState identifies the client connection state delivered via
+// Listener.OnStateChanged.
+type ClientState int
+
+// Client states. The numeric values cross the gomobile boundary (the mobile
+// bindings re-export them as integer constants), so they are a wire format:
+// append new states at the end, never reorder or insert.
+const (
+	ClientStateDisconnected ClientState = iota
+	ClientStateConnected
+	ClientStateConnecting
+	ClientStateDisconnecting
+	// ClientStateNoNetwork is an overlay state: it is never stored as the
+	// last notification, only derived from ClientStateConnecting while the
+	// OS reports no usable network (see notifier.effectiveState).
+	ClientStateNoNetwork
+)
+
 // Listener is a callback type about the NetBird network connection state
 type Listener interface {
+	// OnStateChanged reports every client state transition. New states are
+	// delivered only through this callback; the per-state callbacks below
+	// are kept for compatibility and will be removed once all consumers
+	// have migrated.
+	OnStateChanged(state ClientState)
+
+	// Deprecated: consume OnStateChanged instead.
 	OnConnected()
+	// Deprecated: consume OnStateChanged instead.
 	OnDisconnected()
+	// Deprecated: consume OnStateChanged instead.
 	OnConnecting()
+	// Deprecated: consume OnStateChanged instead.
 	OnDisconnecting()
+
 	OnAddressChanged(string, string)
 	OnPeersListChanged(int)
 }

client/internal/peer/notifier.go

@@ -4,31 +4,64 @@ import (
 	"sync"
 )
 
-const (
-	stateDisconnected = iota
-	stateConnected
-	stateConnecting
-	stateDisconnecting
-)
-
 type notifier struct {
+	// publishLock orders state publication: it is held across computing the
+	// effective state and handing it to the listener, so a transition cannot
+	// overtake a newer one and leave the listener on a stale state.
+	publishLock        sync.Mutex
 	serverStateLock    sync.Mutex
 	listenersLock      sync.Mutex
 	listener           Listener
 	currentClientState bool
-	lastNotification   int
+	lastNotification   ClientState
 	lastNumberOfPeers  int
 	lastFqdnAddress    string
 	lastIPAddress      string
+	networkAvailable   bool
 }
 
 func newNotifier() *notifier {
-	return &notifier{}
+	return &notifier{
+		networkAvailable: true,
+	}
+}
+
+// effectiveState maps the computed state to what listeners should see:
+// while the OS reports no usable network, "Connecting" would be a lie —
+// connection attempts are suspended — so it is reported as NoNetwork.
+// Caller must hold serverStateLock.
+func (n *notifier) effectiveState(state ClientState) ClientState {
+	if !n.networkAvailable && state == ClientStateConnecting {
+		return ClientStateNoNetwork
+	}
+	return state
+}
+
+// setNetworkAvailable records the OS network availability and re-notifies
+// the listener when the flag flips the effective state (Connecting <->
+// NoNetwork).
+func (n *notifier) setNetworkAvailable(available bool) {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
+	n.serverStateLock.Lock()
+	if n.networkAvailable == available {
+		n.serverStateLock.Unlock()
+		return
+	}
+	previous := n.effectiveState(n.lastNotification)
+	n.networkAvailable = available
+	current := n.effectiveState(n.lastNotification)
+	n.serverStateLock.Unlock()
+
+	if previous != current {
+		n.notify(current)
+	}
 }
 
 func (n *notifier) setListener(listener Listener) {
 	n.serverStateLock.Lock()
-	lastNotification := n.lastNotification
+	lastNotification := n.effectiveState(n.lastNotification)
 	numOfPeers := n.lastNumberOfPeers
 	fqdnAddress := n.lastFqdnAddress
 	address := n.lastIPAddress
@@ -52,6 +85,9 @@ func (n *notifier) removeListener() {
 }
 
 func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	calculatedState := n.calculateState(mgmState, signalState)
 
@@ -61,43 +97,54 @@ func (n *notifier) updateServerStates(mgmState bool, signalState bool) {
 	}
 
 	n.lastNotification = calculatedState
+	effective := n.effectiveState(calculatedState)
 	n.serverStateLock.Unlock()
 
-	n.notify(calculatedState)
+	n.notify(effective)
 }
 
 func (n *notifier) clientStart() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = true
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
+	effective := n.effectiveState(ClientStateConnecting)
 	n.serverStateLock.Unlock()
 
-	n.notify(stateConnecting)
+	n.notify(effective)
 }
 
 func (n *notifier) clientStop() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = stateDisconnected
+	n.lastNotification = ClientStateDisconnected
 	n.serverStateLock.Unlock()
 
-	n.notify(stateDisconnected)
+	n.notify(ClientStateDisconnected)
 }
 
 func (n *notifier) clientTearDown() {
+	n.publishLock.Lock()
+	defer n.publishLock.Unlock()
+
 	n.serverStateLock.Lock()
 	n.currentClientState = false
-	n.lastNotification = stateDisconnecting
+	n.lastNotification = ClientStateDisconnecting
 	n.serverStateLock.Unlock()
 
-	n.notify(stateDisconnecting)
+	n.notify(ClientStateDisconnecting)
 }
 
-func (n *notifier) isServerStateChanged(newState int) bool {
+func (n *notifier) isServerStateChanged(newState ClientState) bool {
 	return n.lastNotification != newState
 }
 
-func (n *notifier) notify(state int) {
+func (n *notifier) notify(state ClientState) {
 	n.listenersLock.Lock()
 	listener := n.listener
 	n.listenersLock.Unlock()
@@ -109,20 +156,20 @@ func (n *notifier) notify(state int) {
 	notifyListener(listener, state)
 }
 
-func (n *notifier) calculateState(managementConn, signalConn bool) int {
+func (n *notifier) calculateState(managementConn, signalConn bool) ClientState {
 	if managementConn && signalConn {
-		return stateConnected
+		return ClientStateConnected
 	}
 
 	if !managementConn && !signalConn && !n.currentClientState {
-		return stateDisconnected
+		return ClientStateDisconnected
 	}
 
-	if n.lastNotification == stateDisconnecting {
-		return stateDisconnecting
+	if n.lastNotification == ClientStateDisconnecting {
+		return ClientStateDisconnecting
 	}
 
-	return stateConnecting
+	return ClientStateConnecting
 }
 
 func (n *notifier) peerListChanged(numOfPeers int) {
@@ -159,15 +206,19 @@ func (n *notifier) localAddressChanged(fqdn, address string) {
 	listener.OnAddressChanged(fqdn, address)
 }
 
-func notifyListener(l Listener, state int) {
+func notifyListener(l Listener, state ClientState) {
+	// legacy per-state callbacks; NoNetwork is delivered only via
+	// OnStateChanged below
 	switch state {
-	case stateDisconnected:
+	case ClientStateDisconnected:
 		l.OnDisconnected()
-	case stateConnected:
+	case ClientStateConnected:
 		l.OnConnected()
-	case stateConnecting:
+	case ClientStateConnecting:
 		l.OnConnecting()
-	case stateDisconnecting:
+	case ClientStateDisconnecting:
 		l.OnDisconnecting()
 	}
+
+	l.OnStateChanged(state)
 }

client/internal/peer/notifier_concurrent_test.go

@@ -0,0 +1,108 @@
+package peer
+
+import (
+	"sync"
+	"testing"
+	"time"
+)
+
+type recordingListener struct {
+	mu      sync.Mutex
+	states  []ClientState
+	onState func(ClientState)
+}
+
+func (l *recordingListener) OnStateChanged(state ClientState) {
+	l.mu.Lock()
+	l.states = append(l.states, state)
+	hook := l.onState
+	l.mu.Unlock()
+
+	if hook != nil {
+		hook(state)
+	}
+}
+
+func (l *recordingListener) last() (ClientState, bool) {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	if len(l.states) == 0 {
+		return 0, false
+	}
+	return l.states[len(l.states)-1], true
+}
+
+func (l *recordingListener) snapshot() []ClientState {
+	l.mu.Lock()
+	defer l.mu.Unlock()
+	return append([]ClientState(nil), l.states...)
+}
+
+func (l *recordingListener) OnConnected()                    {}
+func (l *recordingListener) OnDisconnected()                 {}
+func (l *recordingListener) OnConnecting()                   {}
+func (l *recordingListener) OnDisconnecting()                {}
+func (l *recordingListener) OnAddressChanged(string, string) {}
+func (l *recordingListener) OnPeersListChanged(int)          {}
+
+// TestNotifier_ConcurrentAvailabilityFlipOrdersPublication holds the first
+// transition inside the listener callback and flips availability again from
+// another goroutine while it is parked. The second flip must not publish
+// ahead of the one in flight, otherwise the listener ends up on a state the
+// notifier already superseded.
+func TestNotifier_ConcurrentAvailabilityFlipOrdersPublication(t *testing.T) {
+	n := newNotifier()
+	n.currentClientState = true
+	n.lastNotification = ClientStateConnecting
+
+	entered := make(chan struct{})
+	release := make(chan struct{})
+
+	l := &recordingListener{}
+	l.onState = func(state ClientState) {
+		if state != ClientStateNoNetwork {
+			return
+		}
+		l.mu.Lock()
+		l.onState = nil
+		l.mu.Unlock()
+		close(entered)
+		<-release
+	}
+	n.listener = l
+
+	var wg sync.WaitGroup
+	wg.Add(1)
+	go func() {
+		defer wg.Done()
+		n.setNetworkAvailable(false)
+	}()
+
+	<-entered
+
+	flipped := make(chan struct{})
+	go func() {
+		defer close(flipped)
+		n.setNetworkAvailable(true)
+	}()
+
+	select {
+	case <-flipped:
+		t.Fatal("the online transition published while the offline one was " +
+			"still in flight; publication is not serialized")
+	case <-time.After(200 * time.Millisecond):
+	}
+
+	close(release)
+	<-flipped
+	wg.Wait()
+
+	got, ok := l.last()
+	if !ok {
+		t.Fatal("listener never observed a state")
+	}
+	if got != ClientStateConnecting {
+		t.Fatalf("listener holds %v after the network came back, want Connecting; sequence: %v",
+			got, l.snapshot())
+	}
+}

client/internal/peer/notifier_test.go

@@ -6,29 +6,32 @@ import (
 )
 
 type mocListener struct {
-	lastState int
+	lastState ClientState
 	wg        sync.WaitGroup
 	peersWg   sync.WaitGroup
 	peers     int
 }
 
 func (l *mocListener) OnConnected() {
-	l.lastState = stateConnected
+	l.lastState = ClientStateConnected
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnected() {
-	l.lastState = stateDisconnected
+	l.lastState = ClientStateDisconnected
 	l.wg.Done()
 }
 func (l *mocListener) OnConnecting() {
-	l.lastState = stateConnecting
+	l.lastState = ClientStateConnecting
 	l.wg.Done()
 }
 func (l *mocListener) OnDisconnecting() {
-	l.lastState = stateDisconnecting
+	l.lastState = ClientStateDisconnecting
 	l.wg.Done()
 }
 
+func (l *mocListener) OnStateChanged(state ClientState) {
+
+}
 func (l *mocListener) OnAddressChanged(host, addr string) {
 
 }
@@ -57,15 +60,15 @@ func Test_notifier_serverState(t *testing.T) {
 
 	type scenario struct {
 		name        string
-		expected    int
+		expected    ClientState
 		mgmState    bool
 		signalState bool
 	}
 	scenarios := []scenario{
-		{"connected", stateConnected, true, true},
-		{"mgm down", stateConnecting, false, true},
-		{"signal down", stateConnecting, true, false},
-		{"disconnected", stateDisconnected, false, false},
+		{"connected", ClientStateConnected, true, true},
+		{"mgm down", ClientStateConnecting, false, true},
+		{"signal down", ClientStateConnecting, true, false},
+		{"disconnected", ClientStateDisconnected, false, false},
 	}
 
 	for _, tt := range scenarios {
@@ -85,7 +88,7 @@ func Test_notifier_SetListener(t *testing.T) {
 	listener.setPeersWaiter()
 
 	n := newNotifier()
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
 	n.setListener(listener)
 	listener.wait()
 	listener.waitPeers()
@@ -99,7 +102,7 @@ func Test_notifier_RemoveListener(t *testing.T) {
 	listener.setWaiter()
 	listener.setPeersWaiter()
 	n := newNotifier()
-	n.lastNotification = stateConnecting
+	n.lastNotification = ClientStateConnecting
 	n.setListener(listener)
 	// setListener replays cached state on a goroutine; wait for both the state
 	// and peers callbacks to finish so we don't race on listener.peers.

client/internal/peer/status.go

@@ -1211,6 +1211,12 @@ func (d *Status) ClientTeardown() {
 	d.notifyStateChange()
 }
 
+// SetNetworkAvailable records the OS-reported network availability; while
+// unavailable, listeners see NoNetwork instead of Connecting.
+func (d *Status) SetNetworkAvailable(available bool) {
+	d.notifier.setNetworkAvailable(available)
+}
+
 // SetConnectionListener set a listener to the notifier
 func (d *Status) SetConnectionListener(listener Listener) {
 	d.notifier.setListener(listener)

client/internal/profilemanager/prefs.go

@@ -0,0 +1,130 @@
+package profilemanager
+
+import (
+	"context"
+	"encoding/json"
+	"fmt"
+	"os"
+	"path/filepath"
+	"sync"
+
+	"github.com/netbirdio/netbird/util"
+)
+
+const prefsFileSuffix = ".prefs.json"
+
+var prefsMu sync.Mutex
+
+// Prefs is a namespaced per-profile preference store backed by a single JSON
+// file next to the profile config; it is deleted together with the profile.
+type Prefs struct {
+	path string
+}
+
+// ProfilePrefs returns the preference store of the profile identified by id.
+func (s *ServiceManager) ProfilePrefs(id ID, username string) (*Prefs, error) {
+	if !IsValidProfileFilenameStem(id) {
+		return nil, fmt.Errorf("invalid profile ID: %q", id)
+	}
+	if id == defaultProfileName {
+		return &Prefs{path: filepath.Join(filepath.Dir(DefaultConfigPath), id.String()+prefsFileSuffix)}, nil
+	}
+	configDir, err := s.getConfigDir(username)
+	if err != nil {
+		return nil, fmt.Errorf("get config directory for user %s: %w", username, err)
+	}
+	return &Prefs{path: filepath.Join(configDir, id.String()+prefsFileSuffix)}, nil
+}
+
+// Get unmarshals the namespace section into v and reports whether it exists.
+func (p *Prefs) Get(namespace string, v any) (bool, error) {
+	if namespace == "" {
+		return false, fmt.Errorf("empty prefs namespace")
+	}
+
+	prefsMu.Lock()
+	defer prefsMu.Unlock()
+
+	sections, err := readPrefsFile(p.path)
+	if err != nil {
+		return false, err
+	}
+	raw, ok := sections[namespace]
+	if !ok {
+		return false, nil
+	}
+	if err := json.Unmarshal(raw, v); err != nil {
+		return false, fmt.Errorf("decode prefs namespace %q: %w", namespace, err)
+	}
+	return true, nil
+}
+
+// Put stores v as the namespace section, replacing any previous value.
+func (p *Prefs) Put(namespace string, v any) error {
+	if namespace == "" {
+		return fmt.Errorf("empty prefs namespace")
+	}
+	raw, err := json.Marshal(v)
+	if err != nil {
+		return fmt.Errorf("encode prefs namespace %q: %w", namespace, err)
+	}
+
+	prefsMu.Lock()
+	defer prefsMu.Unlock()
+
+	sections, err := readPrefsFile(p.path)
+	if err != nil {
+		return err
+	}
+	sections[namespace] = raw
+	return writePrefsFile(p.path, sections)
+}
+
+// Remove deletes the namespace section; a missing one is not an error.
+func (p *Prefs) Remove(namespace string) error {
+	if namespace == "" {
+		return fmt.Errorf("empty prefs namespace")
+	}
+
+	prefsMu.Lock()
+	defer prefsMu.Unlock()
+
+	sections, err := readPrefsFile(p.path)
+	if err != nil {
+		return err
+	}
+	if _, ok := sections[namespace]; !ok {
+		return nil
+	}
+	delete(sections, namespace)
+	return writePrefsFile(p.path, sections)
+}
+
+func removePrefsFile(path string) error {
+	prefsMu.Lock()
+	defer prefsMu.Unlock()
+	return os.Remove(path)
+}
+
+func readPrefsFile(path string) (map[string]json.RawMessage, error) {
+	data, err := os.ReadFile(path)
+	if os.IsNotExist(err) {
+		return map[string]json.RawMessage{}, nil
+	}
+	if err != nil {
+		return nil, fmt.Errorf("read prefs: %w", err)
+	}
+
+	sections := map[string]json.RawMessage{}
+	if err := json.Unmarshal(data, &sections); err != nil {
+		return nil, fmt.Errorf("decode prefs: %w", err)
+	}
+	return sections, nil
+}
+
+func writePrefsFile(path string, sections map[string]json.RawMessage) error {
+	if err := util.WriteJsonWithRestrictedPermission(context.Background(), path, sections); err != nil {
+		return fmt.Errorf("write prefs: %w", err)
+	}
+	return nil
+}

client/internal/profilemanager/prefs_test.go

@@ -0,0 +1,138 @@
+package profilemanager
+
+import (
+	"errors"
+	"os"
+	"path/filepath"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+type testPrefsSection struct {
+	Mode uint8  `json:"mode"`
+	Dest string `json:"dest"`
+}
+
+func TestProfilePrefs_RoundTrip(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefs, err := sm.ProfilePrefs(created.ID, username)
+		require.NoError(t, err)
+
+		require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 2, Dest: "/tmp/x"}))
+		require.NoError(t, prefs.Put("other", map[string]int{"n": 1}))
+
+		var got testPrefsSection
+		found, err := prefs.Get("filedrop", &got)
+		require.NoError(t, err)
+		assert.True(t, found)
+		assert.Equal(t, testPrefsSection{Mode: 2, Dest: "/tmp/x"}, got)
+
+		var other map[string]int
+		found, err = prefs.Get("other", &other)
+		require.NoError(t, err)
+		assert.True(t, found)
+		assert.Equal(t, map[string]int{"n": 1}, other)
+	})
+}
+
+func TestProfilePrefs_GetMissingNamespace(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefs, err := sm.ProfilePrefs(created.ID, username)
+		require.NoError(t, err)
+
+		var got testPrefsSection
+		found, err := prefs.Get("filedrop", &got)
+		require.NoError(t, err)
+		assert.False(t, found)
+	})
+}
+
+func TestProfilePrefs_RemoveNamespace(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefs, err := sm.ProfilePrefs(created.ID, username)
+		require.NoError(t, err)
+
+		require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 1}))
+		require.NoError(t, prefs.Put("other", map[string]int{"n": 1}))
+		require.NoError(t, prefs.Remove("filedrop"))
+		require.NoError(t, prefs.Remove("missing"))
+
+		var got testPrefsSection
+		found, err := prefs.Get("filedrop", &got)
+		require.NoError(t, err)
+		assert.False(t, found)
+
+		var other map[string]int
+		found, err = prefs.Get("other", &other)
+		require.NoError(t, err)
+		assert.True(t, found)
+		assert.Equal(t, map[string]int{"n": 1}, other)
+	})
+}
+
+func TestProfilePrefs_RejectsInvalidID(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		_, err := sm.ProfilePrefs("../escape", username)
+		assert.Error(t, err)
+	})
+}
+
+func TestProfilePrefs_RejectsEmptyNamespace(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefs, err := sm.ProfilePrefs(created.ID, username)
+		require.NoError(t, err)
+
+		_, err = prefs.Get("", &testPrefsSection{})
+		assert.Error(t, err)
+		assert.Error(t, prefs.Put("", testPrefsSection{}))
+		assert.Error(t, prefs.Remove(""))
+	})
+}
+
+func TestProfilePrefs_DefaultProfile(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		prefs, err := sm.ProfilePrefs(defaultProfileName, username)
+		require.NoError(t, err)
+
+		require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 1}))
+
+		expected := filepath.Join(filepath.Dir(DefaultConfigPath), "default"+prefsFileSuffix)
+		_, err = os.Stat(expected)
+		require.NoError(t, err)
+	})
+}
+
+func TestRemoveProfile_DeletesPrefsFile(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefs, err := sm.ProfilePrefs(created.ID, username)
+		require.NoError(t, err)
+		require.NoError(t, prefs.Put("filedrop", testPrefsSection{Mode: 2}))
+
+		configDir, err := sm.getConfigDir(username)
+		require.NoError(t, err)
+		prefsPath := filepath.Join(configDir, created.ID.String()+prefsFileSuffix)
+		_, err = os.Stat(prefsPath)
+		require.NoError(t, err)
+
+		require.NoError(t, sm.RemoveProfile(created.ID, username))
+		_, err = os.Stat(prefsPath)
+		assert.True(t, errors.Is(err, os.ErrNotExist), "prefs file should be removed")
+	})
+}

client/internal/profilemanager/service.go

@@ -420,6 +420,11 @@ func (s *ServiceManager) RemoveProfile(id ID, username string) error {
 		log.Warnf("failed to remove profile state file %s: %v", stateFile, err)
 	}
 
+	prefsFile := filepath.Join(filepath.Dir(target.Path), id.String()+prefsFileSuffix)
+	if err := removePrefsFile(prefsFile); err != nil && !os.IsNotExist(err) {
+		log.Warnf("failed to remove profile prefs file %s: %v", prefsFile, err)
+	}
+
 	return nil
 }
 

client/internal/updater/installer/installer_common.go

@@ -42,6 +42,9 @@ func NewWithDir(tempDir string) *Installer {
 // This will run by the original service process
 func (u *Installer) RunInstallation(ctx context.Context, targetVersion string) (err error) {
 	resultHandler := NewResultHandler(u.tempDir)
+	if err := resultHandler.ClearStaleResult(); err != nil {
+		log.Warnf("clear stale installer result: %v", err)
+	}
 
 	defer func() {
 		if err != nil {

client/internal/updater/installer/result.go

@@ -54,6 +54,12 @@ func (rh *ResultHandler) GetErrorResultReason() string {
 	return ""
 }
 
+// ClearStaleResult removes a result file left over from a previous installation
+// attempt so result watchers cannot read an outdated outcome for the current attempt.
+func (rh *ResultHandler) ClearStaleResult() error {
+	return rh.cleanup()
+}
+
 func (rh *ResultHandler) WriteSuccess() error {
 	result := Result{
 		Success:    true,

client/ios/NetBirdSDK/client.go

@@ -22,6 +22,8 @@ import (
 	"github.com/netbirdio/netbird/client/internal/listener"
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/formatter"
 	"github.com/netbirdio/netbird/route"
@@ -36,11 +38,6 @@ const (
 	AnonymizeLevelStrict  = nbAnonymize.LevelStrictString
 )
 
-// ConnectionListener export internal Listener for mobile
-type ConnectionListener interface {
-	peer.Listener
-}
-
 // RouteListener export internal RouteListener for mobile
 type NetworkChangeListener interface {
 	listener.NetworkChangeListener
@@ -87,6 +84,12 @@ type Client struct {
 	onHostDnsFn           func([]string)
 	dnsManager            dns.IosDnsManager
 	loginComplete         bool
+	// netState outlives engine restarts: it mirrors the OS connectivity, not
+	// the engine lifecycle. Run injects it into each new ConnectClient, which
+	// distributes it to every reconnection loop.
+	netState *netstate.State
+	// sweeper also outlives engine restarts; NotifyNetworkChange sweeps it.
+	sweeper *netsweep.Sweeper
 	// preloadedConfig holds config loaded from JSON (used on tvOS where file writes are blocked)
 	preloadedConfig *profilemanager.Config
 
@@ -109,6 +112,8 @@ func NewClient(cfgFile, stateFile, cacheDir, logFilePath, deviceName string, osV
 		ctxCancelLock:         &sync.Mutex{},
 		networkChangeListener: networkChangeListener,
 		dnsManager:            dnsManager,
+		netState:              netstate.New(),
+		sweeper:               netsweep.New(),
 	}
 }
 
@@ -184,7 +189,8 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	c.onHostDnsFn = func([]string) {}
 	cfg.WgIface = interfaceName
 
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder,
+		internal.WithNetworkState(c.netState), internal.WithSweeper(c.sweeper))
 	c.setState(cfg, connectClient)
 	// Persist the latest sync response so DebugBundle can include the network
 	// map. On iOS this is backed by disk to keep it out of the constrained
@@ -193,6 +199,25 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
 }
 
+// SetNetworkAvailable feeds OS-reported network availability into the client
+// (e.g. from NWPathMonitor). While unavailable, the internal reconnect loops
+// suspend their attempts and the connection listener reports NoNetwork
+// instead of Connecting; when availability returns, the loops resume
+// immediately with a fresh backoff.
+func (c *Client) SetNetworkAvailable(available bool) {
+	c.netState.Set(available)
+	c.recorder.SetNetworkAvailable(available)
+}
+
+// NotifyNetworkChange marks the management, signal and relay connections
+// stale after the OS switched networks and schedules a sweep that cuts
+// whatever has not redialed on the new network by then. The engine and the
+// TUN device stay untouched.
+func (c *Client) NotifyNetworkChange() {
+	c.sweeper.MarkNetworkChange()
+	log.Infof("network change: connections marked stale")
+}
+
 // Stop the internal client and free the resources
 func (c *Client) Stop() {
 	c.ctxCancelLock.Lock()
@@ -331,7 +356,11 @@ func (c *Client) GetStatusDetails() *StatusDetails {
 
 // SetConnectionListener set the network connection listener
 func (c *Client) SetConnectionListener(listener ConnectionListener) {
-	c.recorder.SetConnectionListener(listener)
+	if listener == nil {
+		c.recorder.RemoveConnectionListener()
+		return
+	}
+	c.recorder.SetConnectionListener(connectionListenerAdapter{listener})
 }
 
 // RemoveConnectionListener remove connection listener

client/ios/NetBirdSDK/connection_listener.go

@@ -0,0 +1,43 @@
+//go:build ios
+
+package NetBirdSDK
+
+import (
+	"github.com/netbirdio/netbird/client/internal/peer"
+)
+
+// Client state values, re-exported as basic constants so gomobile emits them
+// into the generated bindings. They mirror peer.ClientState*: append-only,
+// never reorder.
+const (
+	ClientStateDisconnected  = int(peer.ClientStateDisconnected)
+	ClientStateConnected     = int(peer.ClientStateConnected)
+	ClientStateConnecting    = int(peer.ClientStateConnecting)
+	ClientStateDisconnecting = int(peer.ClientStateDisconnecting)
+	ClientStateNoNetwork     = int(peer.ClientStateNoNetwork)
+)
+
+// ConnectionListener export internal Listener for mobile.
+//
+// It intentionally lacks OnStateChanged for now: adding a method to a gomobile
+// interface breaks every Swift implementation, so the iOS app keeps building
+// against the legacy per-state callbacks. A follow-up will extend it together
+// with the app.
+type ConnectionListener interface {
+	OnConnected()
+	OnDisconnected()
+	OnConnecting()
+	OnDisconnecting()
+	OnAddressChanged(string, string)
+	OnPeersListChanged(int)
+}
+
+// connectionListenerAdapter adapts the gomobile-facing ConnectionListener to
+// peer.Listener.
+type connectionListenerAdapter struct {
+	ConnectionListener
+}
+
+// OnStateChanged is dropped on iOS until the app adopts the state callback;
+// the legacy per-state callbacks continue to fire.
+func (a connectionListenerAdapter) OnStateChanged(peer.ClientState) {}

client/ios/NetBirdSDK/login.go

@@ -323,7 +323,7 @@ func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName strin
 const authInfoRequestTimeout = 30 * time.Second
 
 func (a *Auth) foregroundGetTokenInfo(authClient *auth.Auth, urlOpener URLOpener, forceDeviceAuth bool) (*auth.TokenInfo, error) {
-	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, forceDeviceAuth)
+	oAuthFlow, err := authClient.GetOAuthFlow(a.ctx, forceDeviceAuth, "")
 	if err != nil {
 		return nil, fmt.Errorf("failed to get OAuth flow: %v", err)
 	}

client/netstate/netstate.go

@@ -0,0 +1,110 @@
+// Package netstate tracks OS-reported network availability for the client.
+//
+// A State instance is owned by the platform integration (e.g. the Android or
+// iOS bindings, fed from ConnectivityManager callbacks or NWPathMonitor) and
+// is injected into the connection retry loops (management, signal, relay,
+// peer guards and the top-level connect loop), which consult it to avoid
+// burning CPU and battery on reconnect attempts while the device has no
+// network at all (e.g. airplane mode), and to reset their backoff as soon as
+// the network returns.
+//
+// Consumers hold a *State that may be nil — every non-mobile platform leaves
+// it unset. The read methods are safe on a nil receiver: they report online
+// and never block, so consumers behave as if this package did not exist.
+package netstate
+
+import (
+	"context"
+	"sync"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// State holds the OS-reported network availability. The zero value is not
+// usable; create instances with New.
+type State struct {
+	mu      sync.Mutex
+	online  bool
+	changed chan struct{}
+}
+
+// New creates a State that starts online. Platforms without network tracking
+// pass a nil *State instead: the read methods treat nil as always online and
+// never block, so consumers need no nil guards.
+func New() *State {
+	return &State{
+		online:  true,
+		changed: make(chan struct{}),
+	}
+}
+
+// Set records whether the OS reports any usable network. Transitions wake up
+// all Wait callers immediately. Unlike the read methods, Set is not nil-safe:
+// it is only for the platform owner that created the State with New.
+func (s *State) Set(online bool) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	if s.online == online {
+		return
+	}
+	s.online = online
+	close(s.changed)
+	s.changed = make(chan struct{})
+	log.Infof("OS network availability changed: online=%t", online)
+}
+
+// IsOnline reports whether the OS reports at least one usable network. On a
+// nil receiver — no State injected — it reports online.
+func (s *State) IsOnline() bool {
+	if s == nil {
+		return true
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.online
+}
+
+// Changed returns a channel closed on the next availability transition, for
+// callers that already own a select loop and cannot block in Wait. Re-read it
+// after every fire: each transition installs a fresh channel. On a nil
+// receiver — no State injected — it returns nil, which blocks forever in a
+// select, so the caller simply never observes a transition.
+func (s *State) Changed() <-chan struct{} {
+	if s == nil {
+		return nil
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return s.changed
+}
+
+// Wait blocks while the network is offline. It reports whether it had to
+// wait, so callers can reset their backoff after an outage. It returns early
+// with the context error when ctx is done. On a nil receiver — no State
+// injected — it returns immediately.
+func (s *State) Wait(ctx context.Context) (bool, error) {
+	if s == nil {
+		return false, nil
+	}
+	waited := false
+	for {
+		s.mu.Lock()
+		if s.online {
+			s.mu.Unlock()
+			return waited, nil
+		}
+		ch := s.changed
+		s.mu.Unlock()
+
+		if !waited {
+			waited = true
+			log.Debugf("network is offline, pausing connection attempts")
+		}
+
+		select {
+		case <-ctx.Done():
+			return waited, ctx.Err()
+		case <-ch:
+		}
+	}
+}

client/netstate/netstate_test.go

@@ -0,0 +1,170 @@
+package netstate
+
+import (
+	"context"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestNewStateIsOnline(t *testing.T) {
+	assert.True(t, New().IsOnline(), "a fresh State should start online")
+}
+
+func TestSetTogglesOnlineState(t *testing.T) {
+	s := New()
+
+	s.Set(false)
+	assert.False(t, s.IsOnline(), "state should be offline after Set(false)")
+
+	s.Set(true)
+	assert.True(t, s.IsOnline(), "state should be online after Set(true)")
+}
+
+func TestWaitReturnsImmediatelyWhenOnline(t *testing.T) {
+	s := New()
+
+	ctx, cancel := context.WithTimeout(context.Background(), time.Second)
+	defer cancel()
+
+	waited, err := s.Wait(ctx)
+	require.NoError(t, err)
+	assert.False(t, waited, "Wait should not block when the network is online")
+}
+
+func TestWaitBlocksUntilOnline(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	result := make(chan bool, 1)
+	go func() {
+		waited, err := s.Wait(ctx)
+		if err != nil {
+			result <- false
+			return
+		}
+		result <- waited
+	}()
+
+	// Verify Wait is actually blocking while offline
+	select {
+	case <-result:
+		t.Fatal("Wait should block while the network is offline")
+	case <-time.After(100 * time.Millisecond):
+	}
+
+	s.Set(true)
+
+	select {
+	case waited := <-result:
+		assert.True(t, waited, "Wait should report that it had to wait for the network")
+	case <-time.After(2 * time.Second):
+		t.Fatal("Wait should return promptly after the network becomes available")
+	}
+}
+
+func TestWaitReturnsOnContextCancel(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithCancel(context.Background())
+
+	result := make(chan error, 1)
+	go func() {
+		_, err := s.Wait(ctx)
+		result <- err
+	}()
+
+	cancel()
+
+	select {
+	case err := <-result:
+		assert.ErrorIs(t, err, context.Canceled)
+	case <-time.After(2 * time.Second):
+		t.Fatal("Wait should return promptly after context cancellation")
+	}
+}
+
+func TestWaitWakesAllWaiters(t *testing.T) {
+	s := New()
+	s.Set(false)
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	const waiters = 10
+	var wg sync.WaitGroup
+	results := make(chan bool, waiters)
+	for i := 0; i < waiters; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			waited, err := s.Wait(ctx)
+			if err != nil {
+				results <- false
+				return
+			}
+			results <- waited
+		}()
+	}
+
+	time.Sleep(100 * time.Millisecond)
+	s.Set(true)
+	wg.Wait()
+
+	close(results)
+	count := 0
+	for waited := range results {
+		assert.True(t, waited, "every waiter should report that it waited")
+		count++
+	}
+	assert.Equal(t, waiters, count, "all waiters should have returned")
+}
+
+func TestNilStateReadsAreNoops(t *testing.T) {
+	var s *State
+
+	assert.True(t, s.IsOnline(), "nil State should report online")
+
+	waited, err := s.Wait(context.Background())
+	require.NoError(t, err)
+	assert.False(t, waited, "nil State's Wait should not block")
+}
+
+func TestConcurrentSetAndWait(t *testing.T) {
+	s := New()
+
+	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
+	defer cancel()
+
+	var wg sync.WaitGroup
+	for i := 0; i < 4; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			for j := 0; j < 100; j++ {
+				s.Set(j%2 == 0)
+				s.IsOnline()
+			}
+		}()
+	}
+	for i := 0; i < 4; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			for j := 0; j < 100; j++ {
+				if _, err := s.Wait(ctx); err != nil {
+					return
+				}
+			}
+		}()
+	}
+
+	wg.Wait()
+}

client/netsweep/netsweep.go

@@ -0,0 +1,267 @@
+// Package netsweep cuts network-bound activity when the OS switches networks:
+// a sweep closes the registered connections and aborts the in-flight dials, so
+// their owners redial immediately instead of waiting for the old sockets to
+// time out.
+//
+// A nil *Sweeper disables everything: all methods are nil-safe no-ops.
+package netsweep
+
+import (
+	"context"
+	"errors"
+	"net"
+	"sync"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+// DefaultSweepDelay absorbs network flapping while the OS settles on a
+// default network before the stale registrations are cut.
+const DefaultSweepDelay = 500 * time.Millisecond
+
+const recentMarkWindow = 3 * time.Second
+
+// Config customizes a Sweeper. The zero value applies the defaults.
+type Config struct {
+	// SweepDelay overrides DefaultSweepDelay when positive.
+	SweepDelay time.Duration
+}
+
+// ErrSwept reports that a dial finished after a network change swept its
+// registration. The connection is already closed; the caller must treat it
+// as a failed dial and redial on the new network.
+var ErrSwept = errors.New("netsweep: connection swept by network change")
+
+// sweepID identifies one registration in a sweeper. Connections and dials
+// draw from the same counter, so an id is unique across both registries.
+type sweepID uint64
+
+type connEntry struct {
+	conn net.Conn
+	gen  uint64
+}
+
+// Dial tracks one dial from start to connection registration. It hands the
+// dialed connection to the sweeper atomically, so a sweep can never fall
+// between the dial finishing and the connection being registered.
+type Dial struct {
+	sweeper *Sweeper
+	ctx     context.Context
+	cancel  context.CancelFunc
+	id      sweepID
+	done    bool // set by a sweep, WrapConn or Release; guarded by sweeper.mu
+	gen     uint64
+}
+
+// Ctx returns the dial's context. A sweep cancels it, so a dial started on the
+// old network aborts instead of waiting out its handshake timeout.
+func (d *Dial) Ctx() context.Context {
+	return d.ctx
+}
+
+// Release ends the dial's registration and cancels its context. It is
+// idempotent and safe after WrapConn, so callers can defer it.
+func (d *Dial) Release() {
+	s := d.sweeper
+	if s == nil {
+		return
+	}
+
+	s.mu.Lock()
+	d.done = true
+	delete(s.dials, d.id)
+	s.mu.Unlock()
+
+	d.cancel()
+}
+
+// sweptConn deregisters itself from the sweeper when closed.
+type sweptConn struct {
+	net.Conn
+	sweeper *Sweeper
+	id      sweepID
+}
+
+func (c *sweptConn) Close() error {
+	c.sweeper.deregister(c.id)
+	return c.Conn.Close()
+}
+
+// Sweeper registers live connections and in-flight dials so the
+// network-change sweep can cut everything registered before the change.
+type Sweeper struct {
+	mu         sync.Mutex
+	conns      map[sweepID]connEntry
+	dials      map[sweepID]*Dial
+	nextID     sweepID
+	gen        uint64
+	timer      *time.Timer
+	sweepDelay time.Duration
+	lastMark   time.Time
+}
+
+// New creates an empty sweeper with the default configuration.
+func New() *Sweeper {
+	return NewWithConfig(Config{})
+}
+
+// NewWithConfig creates an empty sweeper customized by cfg.
+func NewWithConfig(cfg Config) *Sweeper {
+	delay := cfg.SweepDelay
+	if delay <= 0 {
+		delay = DefaultSweepDelay
+	}
+	return &Sweeper{
+		conns:      make(map[sweepID]connEntry),
+		dials:      make(map[sweepID]*Dial),
+		sweepDelay: delay,
+	}
+}
+
+// StartDial registers an in-flight dial. Dial with Ctx, hand the result to
+// WrapConn, and Release the dial when the attempt is over, typically deferred.
+func (s *Sweeper) StartDial(ctx context.Context) *Dial {
+	if s == nil {
+		return &Dial{ctx: ctx}
+	}
+
+	ctx, cancel := context.WithCancel(ctx)
+	d := &Dial{sweeper: s, ctx: ctx, cancel: cancel}
+
+	s.mu.Lock()
+	d.id = s.nextID
+	s.nextID++
+	d.gen = s.gen
+	s.dials[d.id] = d
+	s.mu.Unlock()
+
+	return d
+}
+
+// WrapConn hands conn over to the sweeper. If a sweep ran since StartDial,
+// the connection belongs to the old network: it is closed and ErrSwept is
+// returned. Otherwise conn is registered against the next sweep and returned
+// wrapped, deregistering itself on Close. Call it once, before Release.
+func (d *Dial) WrapConn(conn net.Conn) (net.Conn, error) {
+	s := d.sweeper
+	if s == nil {
+		return conn, nil
+	}
+
+	s.mu.Lock()
+	if d.done {
+		s.mu.Unlock()
+		if err := conn.Close(); err != nil {
+			log.Debugf("swept dial close error: %v", err)
+		}
+		return nil, ErrSwept
+	}
+	d.done = true
+	delete(s.dials, d.id)
+	id := s.nextID
+	s.nextID++
+	// The conn inherits the dial's generation: the socket was bound to the
+	// network that was default when the dial started, not when it finished.
+	s.conns[id] = connEntry{conn: conn, gen: d.gen}
+	s.mu.Unlock()
+
+	return &sweptConn{Conn: conn, sweeper: s, id: id}, nil
+}
+
+// MarkNetworkChange records that the OS switched networks: everything
+// registered so far becomes stale, and a sweep is (re)scheduled after the
+// configured delay to cut whatever is still stale by then. Owners that
+// redialed in the meantime hold fresh-generation registrations and survive,
+// so no cancellation is needed around the sweep.
+func (s *Sweeper) MarkNetworkChange() {
+	if s == nil {
+		return
+	}
+
+	s.mu.Lock()
+	s.gen++
+	cutoff := s.gen
+	s.lastMark = time.Now()
+	if s.timer != nil {
+		s.timer.Stop()
+	}
+	s.timer = time.AfterFunc(s.sweepDelay, func() {
+		n := s.sweep(cutoff)
+		log.Infof("network change sweep: closed %d stale connections", n)
+	})
+	s.mu.Unlock()
+}
+
+// QuickRetryBackoff wraps bo so that after each Reset the first retry comes
+// quickly when the disconnect followed a recent network change and the
+// network is online. Any other failure keeps bo's spread, so the clients of
+// a restarted server still scatter their reconnects. A nil sweeper returns
+// bo unchanged.
+func (s *Sweeper) QuickRetryBackoff(ctx context.Context, bo backoff.BackOff, netState *netstate.State) backoff.BackOff {
+	if s == nil {
+		return bo
+	}
+	return backoff.WithContext(newQuickRetryBackoff(bo, s, netState), ctx)
+}
+
+func (s *Sweeper) markedRecently() bool {
+	if s == nil {
+		return false
+	}
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	return !s.lastMark.IsZero() && time.Since(s.lastMark) < recentMarkWindow
+}
+
+// sweep closes the registered connections and aborts the in-flight dials
+// older than cutoff, and returns how many connections it closed. A dial
+// whose connection was not yet handed to WrapConn is marked, so the late
+// WrapConn closes it instead of registering it.
+func (s *Sweeper) sweep(cutoff uint64) int {
+	if s == nil {
+		return 0
+	}
+
+	s.mu.Lock()
+	var conns []net.Conn
+	for id, e := range s.conns {
+		if e.gen < cutoff {
+			delete(s.conns, id)
+			conns = append(conns, e.conn)
+		}
+	}
+	var dials []*Dial
+	for id, d := range s.dials {
+		if d.gen < cutoff {
+			d.done = true
+			delete(s.dials, id)
+			dials = append(dials, d)
+		}
+	}
+	s.mu.Unlock()
+
+	if len(dials) > 0 {
+		log.Debugf("aborting %d in-flight dials", len(dials))
+		for _, d := range dials {
+			d.cancel()
+		}
+	}
+
+	for _, conn := range conns {
+		log.Debugf("sweeping connection %s -> %s", conn.LocalAddr(), conn.RemoteAddr())
+		if err := conn.Close(); err != nil {
+			log.Debugf("swept connection close error: %v", err)
+		}
+	}
+	return len(conns)
+}
+
+func (s *Sweeper) deregister(id sweepID) {
+	s.mu.Lock()
+	delete(s.conns, id)
+	s.mu.Unlock()
+}

client/netsweep/netsweep_test.go

@@ -0,0 +1,241 @@
+package netsweep
+
+import (
+	"context"
+	"math"
+	"net"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+func TestSweepClosesRegisteredConns(t *testing.T) {
+	sweeper := New()
+
+	c1 := wrap(t, sweeper, connPair(t))
+	c2 := wrap(t, sweeper, connPair(t))
+
+	assert.Equal(t, 2, sweeper.sweepAll(), "both live connections should be closed")
+
+	// The wrappers must report closed now.
+	buf := make([]byte, 1)
+	_, err := c1.Read(buf)
+	assert.Error(t, err, "first connection should be unusable after the sweep")
+	_, err = c2.Read(buf)
+	assert.Error(t, err, "second connection should be unusable after the sweep")
+
+	assert.Equal(t, 0, sweeper.sweepAll(), "second sweep should find nothing")
+}
+
+func TestCloseDeregisters(t *testing.T) {
+	sweeper := New()
+
+	conn := wrap(t, sweeper, connPair(t))
+	require.NoError(t, conn.Close())
+
+	assert.Equal(t, 0, sweeper.sweepAll(), "closed connection must leave the registry")
+}
+
+func TestCloseIsIdempotent(t *testing.T) {
+	sweeper := New()
+
+	conn := wrap(t, sweeper, connPair(t))
+	require.NoError(t, conn.Close())
+	assert.Error(t, conn.Close(), "double close surfaces the underlying error but must not panic")
+}
+
+func TestSweepOnlyAffectsOlderConns(t *testing.T) {
+	sweeper := New()
+
+	_ = wrap(t, sweeper, connPair(t))
+	assert.Equal(t, 1, sweeper.sweepAll())
+
+	// A connection dialed after the sweep must survive until the next one.
+	_ = wrap(t, sweeper, connPair(t))
+	assert.Equal(t, 1, sweeper.sweepAll(), "post-sweep connection belongs to the next sweep")
+}
+
+func TestSweepAbortsInFlightDials(t *testing.T) {
+	sweeper := New()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	sweeper.sweepAll()
+
+	assert.ErrorIs(t, dial.Ctx().Err(), context.Canceled, "sweep must cancel the in-flight dial context")
+}
+
+func TestReleasedDialIsNotAborted(t *testing.T) {
+	sweeper := New()
+
+	// Simulate a dial that finished before the sweep.
+	released := sweeper.StartDial(context.Background())
+	released.Release()
+
+	// A dial still in flight during the sweep.
+	pending := sweeper.StartDial(context.Background())
+	defer pending.Release()
+
+	sweeper.sweepAll()
+	assert.ErrorIs(t, pending.Ctx().Err(), context.Canceled, "pending dial must be aborted")
+}
+
+func TestSweepBetweenDialAndHandoffClosesConn(t *testing.T) {
+	sweeper := New()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	// The dial succeeds on the old network, then the sweep lands before the
+	// connection is handed over.
+	conn := connPair(t)
+	assert.Equal(t, 0, sweeper.sweepAll(), "the connection is not registered yet")
+
+	wrapped, err := dial.WrapConn(conn)
+	require.ErrorIs(t, err, ErrSwept)
+	require.Nil(t, wrapped)
+
+	buf := make([]byte, 1)
+	_, err = conn.Read(buf)
+	assert.Error(t, err, "the old-network connection must be closed, not leaked")
+
+	assert.Equal(t, 0, sweeper.sweepAll(), "nothing may leak into the next sweep")
+}
+
+func TestMarkNetworkChangeSparesFreshConns(t *testing.T) {
+	sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond})
+
+	stale := wrap(t, sweeper, connPair(t))
+	sweeper.MarkNetworkChange()
+	_ = wrap(t, sweeper, connPair(t))
+
+	_ = stale.SetReadDeadline(time.Now().Add(time.Second))
+	buf := make([]byte, 1)
+	_, err := stale.Read(buf)
+	require.ErrorIs(t, err, net.ErrClosed, "stale connection must be closed by the delayed sweep")
+
+	assert.Equal(t, 1, sweeper.sweepAll(), "the fresh connection must survive the stale sweep")
+}
+
+func TestMarkNetworkChangeAbortsStaleDials(t *testing.T) {
+	sweeper := NewWithConfig(Config{SweepDelay: 10 * time.Millisecond})
+
+	stale := sweeper.StartDial(context.Background())
+	defer stale.Release()
+	sweeper.MarkNetworkChange()
+	fresh := sweeper.StartDial(context.Background())
+	defer fresh.Release()
+
+	assert.Eventually(t, func() bool {
+		return stale.Ctx().Err() != nil
+	}, time.Second, 5*time.Millisecond, "stale dial must be aborted by the delayed sweep")
+	assert.NoError(t, fresh.Ctx().Err(), "post-mark dial must not be aborted")
+}
+
+func TestConnInheritsDialGeneration(t *testing.T) {
+	sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond})
+
+	// The dial starts before the network change but completes after it: the
+	// socket is bound to the old network, so the sweep must still cut it.
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+	sweeper.MarkNetworkChange()
+
+	wrapped, err := dial.WrapConn(connPair(t))
+	require.NoError(t, err)
+
+	_ = wrapped.SetReadDeadline(time.Now().Add(time.Second))
+	buf := make([]byte, 1)
+	_, err = wrapped.Read(buf)
+	require.ErrorIs(t, err, net.ErrClosed, "old-generation connection must be swept")
+}
+
+func TestRepeatedMarksCoalesce(t *testing.T) {
+	sweeper := NewWithConfig(Config{SweepDelay: 20 * time.Millisecond})
+
+	first := wrap(t, sweeper, connPair(t))
+	sweeper.MarkNetworkChange()
+	second := wrap(t, sweeper, connPair(t))
+	sweeper.MarkNetworkChange()
+	_ = wrap(t, sweeper, connPair(t))
+
+	buf := make([]byte, 1)
+	for _, conn := range []net.Conn{first, second} {
+		_ = conn.SetReadDeadline(time.Now().Add(time.Second))
+		_, err := conn.Read(buf)
+		require.ErrorIs(t, err, net.ErrClosed, "every pre-mark connection must be swept by the rescheduled sweep")
+	}
+	assert.Equal(t, 1, sweeper.sweepAll(), "only the newest-generation connection may remain")
+}
+
+func TestNilSweeperIsNoop(t *testing.T) {
+	var sweeper *Sweeper
+
+	conn := connPair(t)
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	wrapped, err := dial.WrapConn(conn)
+	require.NoError(t, err)
+	assert.Equal(t, conn, wrapped, "nil sweeper must return the conn unchanged")
+	assert.NoError(t, dial.Ctx().Err(), "nil sweeper must not cancel the dial context")
+	assert.Equal(t, 0, sweeper.sweepAll(), "nil sweeper closes nothing")
+}
+
+// wrap registers conn with the sweeper through a completed dial.
+func wrap(t *testing.T, sweeper *Sweeper, conn net.Conn) net.Conn {
+	t.Helper()
+
+	dial := sweeper.StartDial(context.Background())
+	defer dial.Release()
+
+	wrapped, err := dial.WrapConn(conn)
+	require.NoError(t, err)
+	return wrapped
+}
+
+// connPair dials a loopback TCP connection and keeps the accepted peer open
+// until the test ends: a peer that closed early would make the connection
+// unreadable on its own, so a read error after the sweep would prove nothing.
+func connPair(t *testing.T) net.Conn {
+	t.Helper()
+
+	l, err := net.Listen("tcp", "127.0.0.1:0")
+	require.NoError(t, err)
+	t.Cleanup(func() {
+		if err := l.Close(); err != nil {
+			t.Logf("listener close error: %v", err)
+		}
+	})
+
+	accepted := make(chan net.Conn, 1)
+	go func() {
+		conn, err := l.Accept()
+		if err != nil {
+			close(accepted)
+			return
+		}
+		accepted <- conn
+	}()
+
+	conn, err := net.Dial("tcp", l.Addr().String())
+	require.NoError(t, err)
+
+	peer, ok := <-accepted
+	require.True(t, ok, "listener must accept the dialed connection")
+	t.Cleanup(func() {
+		if err := peer.Close(); err != nil {
+			t.Logf("peer close error: %v", err)
+		}
+	})
+
+	return conn
+}
+
+// sweepAll cuts every registration regardless of generation.
+func (s *Sweeper) sweepAll() int {
+	return s.sweep(math.MaxUint64)
+}

client/netsweep/quick_retry.go

@@ -0,0 +1,39 @@
+package netsweep
+
+import (
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+const quickRetryDelay = 200 * time.Millisecond
+
+type quickRetryBackoff struct {
+	backoff.BackOff
+	sweeper  *Sweeper
+	netState *netstate.State
+	used     bool
+}
+
+func newQuickRetryBackoff(bo backoff.BackOff, sweeper *Sweeper, netState *netstate.State) *quickRetryBackoff {
+	return &quickRetryBackoff{
+		BackOff:  bo,
+		sweeper:  sweeper,
+		netState: netState,
+	}
+}
+
+func (b *quickRetryBackoff) NextBackOff() time.Duration {
+	if !b.used && b.sweeper.markedRecently() && b.netState.IsOnline() {
+		b.used = true
+		return quickRetryDelay
+	}
+	return b.BackOff.NextBackOff()
+}
+
+func (b *quickRetryBackoff) Reset() {
+	b.used = false
+	b.BackOff.Reset()
+}

client/netsweep/quick_retry_test.go

@@ -0,0 +1,58 @@
+package netsweep
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/cenkalti/backoff/v4"
+	"github.com/stretchr/testify/assert"
+)
+
+func TestQuickRetryAfterRecentMark(t *testing.T) {
+	sweeper := New()
+	sweeper.MarkNetworkChange()
+
+	slow := backoff.NewConstantBackOff(5 * time.Second)
+	bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
+
+	assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "first retry after a mark must be quick")
+	assert.Equal(t, 5*time.Second, bo.NextBackOff(), "second retry must fall back to the wrapped backoff")
+
+	bo.Reset()
+	assert.Equal(t, quickRetryDelay, bo.NextBackOff(), "reset must re-arm the quick retry")
+}
+
+func TestQuickRetryWithoutMarkKeepsSpread(t *testing.T) {
+	sweeper := New()
+
+	slow := backoff.NewConstantBackOff(5 * time.Second)
+	bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
+
+	assert.Equal(t, 5*time.Second, bo.NextBackOff(), "without a mark the wrapped backoff decides")
+
+	sweeper.mu.Lock()
+	sweeper.lastMark = time.Now().Add(-recentMarkWindow)
+	sweeper.mu.Unlock()
+	assert.Equal(t, 5*time.Second, bo.NextBackOff(), "a stale mark must not trigger the quick retry")
+}
+
+func TestQuickRetryNilSweeperPassthrough(t *testing.T) {
+	var sweeper *Sweeper
+
+	slow := backoff.NewConstantBackOff(5 * time.Second)
+	bo := sweeper.QuickRetryBackoff(context.Background(), slow, nil)
+
+	assert.Equal(t, backoff.BackOff(slow), bo, "nil sweeper must return the backoff unchanged")
+}
+
+func TestQuickRetryHonorsContext(t *testing.T) {
+	sweeper := New()
+	sweeper.MarkNetworkChange()
+
+	ctx, cancel := context.WithCancel(context.Background())
+	cancel()
+	bo := sweeper.QuickRetryBackoff(ctx, backoff.NewConstantBackOff(time.Millisecond), nil)
+
+	assert.Equal(t, backoff.Stop, bo.NextBackOff(), "cancelled context must stop the retry loop")
+}

client/ssh/client/client.go

@@ -313,21 +313,23 @@ func Dial(ctx context.Context, addr, user string, opts DialOptions) (*Client, er
 
 // dialSSH establishes an SSH connection without JWT authentication
 func dialSSH(ctx context.Context, network, addr string, config *ssh.ClientConfig) (*Client, error) {
+	if config.Timeout > 0 {
+		var cancel context.CancelFunc
+		ctx, cancel = context.WithTimeout(ctx, config.Timeout)
+		defer cancel()
+	}
+
 	dialer := &net.Dialer{}
 	conn, err := dialer.DialContext(ctx, network, addr)
 	if err != nil {
 		return nil, fmt.Errorf("dial %s: %w", addr, err)
 	}
 
-	clientConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config)
+	client, err := nbssh.Handshake(ctx, conn, addr, config)
 	if err != nil {
-		if closeErr := conn.Close(); closeErr != nil {
-			log.Debugf("connection close after handshake failure: %v", closeErr)
-		}
-		return nil, fmt.Errorf("ssh handshake: %w", err)
+		return nil, err
 	}
 
-	client := ssh.NewClient(clientConn, chans, reqs)
 	return &Client{
 		client: client,
 	}, nil

client/ssh/client/terminal_unix.go

@@ -12,6 +12,8 @@ import (
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/crypto/ssh"
 	"golang.org/x/term"
+
+	nbssh "github.com/netbirdio/netbird/client/ssh"
 )
 
 func (c *Client) setupTerminalMode(ctx context.Context, session *ssh.Session) error {
@@ -82,37 +84,7 @@ func (c *Client) setupTerminal(session *ssh.Session, fd int) error {
 		return fmt.Errorf("get terminal size: %w", err)
 	}
 
-	modes := ssh.TerminalModes{
-		ssh.ECHO:          1,
-		ssh.TTY_OP_ISPEED: 14400,
-		ssh.TTY_OP_OSPEED: 14400,
-		// Ctrl+C
-		ssh.VINTR: 3,
-		// Ctrl+\
-		ssh.VQUIT: 28,
-		// Backspace
-		ssh.VERASE: 127,
-		// Ctrl+U
-		ssh.VKILL: 21,
-		// Ctrl+D
-		ssh.VEOF:  4,
-		ssh.VEOL:  0,
-		ssh.VEOL2: 0,
-		// Ctrl+Q
-		ssh.VSTART: 17,
-		// Ctrl+S
-		ssh.VSTOP: 19,
-		// Ctrl+Z
-		ssh.VSUSP: 26,
-		// Ctrl+O
-		ssh.VDISCARD: 15,
-		// Ctrl+R
-		ssh.VREPRINT: 18,
-		// Ctrl+W
-		ssh.VWERASE: 23,
-		// Ctrl+V
-		ssh.VLNEXT: 22,
-	}
+	modes := nbssh.DefaultTerminalModes
 
 	terminal := os.Getenv("TERM")
 	if terminal == "" {

client/ssh/client/terminal_windows.go

@@ -10,6 +10,8 @@ import (
 
 	log "github.com/sirupsen/logrus"
 	"golang.org/x/crypto/ssh"
+
+	nbssh "github.com/netbirdio/netbird/client/ssh"
 )
 
 const (
@@ -80,28 +82,14 @@ func (c *Client) setupTerminalMode(_ context.Context, session *ssh.Session) erro
 	w, h := c.getWindowsConsoleSize()
 
 	modes := ssh.TerminalModes{
-		ssh.ECHO:          1,
-		ssh.TTY_OP_ISPEED: 14400,
-		ssh.TTY_OP_OSPEED: 14400,
-		ssh.ICRNL:         1,
-		ssh.OPOST:         1,
-		ssh.ONLCR:         1,
-		ssh.ISIG:          1,
-		ssh.ICANON:        1,
-		ssh.VINTR:         3,   // Ctrl+C
-		ssh.VQUIT:         28,  // Ctrl+\
-		ssh.VERASE:        127, // Backspace
-		ssh.VKILL:         21,  // Ctrl+U
-		ssh.VEOF:          4,   // Ctrl+D
-		ssh.VEOL:          0,
-		ssh.VEOL2:         0,
-		ssh.VSTART:        17, // Ctrl+Q
-		ssh.VSTOP:         19, // Ctrl+S
-		ssh.VSUSP:         26, // Ctrl+Z
-		ssh.VDISCARD:      15, // Ctrl+O
-		ssh.VWERASE:       23, // Ctrl+W
-		ssh.VLNEXT:        22, // Ctrl+V
-		ssh.VREPRINT:      18, // Ctrl+R
+		ssh.ICRNL:  1,
+		ssh.OPOST:  1,
+		ssh.ONLCR:  1,
+		ssh.ISIG:   1,
+		ssh.ICANON: 1,
+	}
+	for mode, value := range nbssh.DefaultTerminalModes {
+		modes[mode] = value
 	}
 
 	if err := session.RequestPty("xterm-256color", h, w, modes); err != nil {

client/ssh/common.go

@@ -35,6 +35,19 @@ type HostKeyVerifier interface {
 	VerifySSHHostKey(peerAddress string, key []byte) error
 }
 
+// PeerKeyLookup returns the stored SSH host key for a peer address.
+type PeerKeyLookup func(peerAddress string) ([]byte, bool)
+
+// VerifySSHHostKey implements HostKeyVerifier by looking up the stored key
+// and comparing it against the presented key.
+func (l PeerKeyLookup) VerifySSHHostKey(peerAddress string, presentedKey []byte) error {
+	storedKey, found := l(peerAddress)
+	if !found {
+		return ErrPeerNotFound
+	}
+	return VerifyHostKey(storedKey, presentedKey, peerAddress)
+}
+
 // DaemonHostKeyVerifier implements HostKeyVerifier using the NetBird daemon
 type DaemonHostKeyVerifier struct {
 	client proto.DaemonServiceClient

client/ssh/handshake.go

@@ -0,0 +1,45 @@
+package ssh
+
+import (
+	"context"
+	"fmt"
+	"io"
+	"net"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/crypto/ssh"
+)
+
+// Handshake runs the SSH client handshake on an already dialed conn and
+// returns the resulting client. Dialing bounds only the TCP establishment;
+// without a deadline on the socket a peer that accepts and then goes silent
+// blocks the handshake forever, so the context deadline is applied to conn
+// for the duration of the handshake. conn is closed on any error.
+func Handshake(ctx context.Context, conn net.Conn, addr string, config *ssh.ClientConfig) (*ssh.Client, error) {
+	if deadline, ok := ctx.Deadline(); ok {
+		if err := conn.SetDeadline(deadline); err != nil {
+			closeHandshake(conn, "conn after deadline error")
+			return nil, fmt.Errorf("set handshake deadline: %w", err)
+		}
+	}
+
+	sshConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config)
+	if err != nil {
+		closeHandshake(conn, "conn after handshake error")
+		return nil, fmt.Errorf("ssh handshake: %w", err)
+	}
+
+	if err := conn.SetDeadline(time.Time{}); err != nil {
+		closeHandshake(sshConn, "ssh conn after deadline clear error")
+		return nil, fmt.Errorf("clear handshake deadline: %w", err)
+	}
+
+	return ssh.NewClient(sshConn, chans, reqs), nil
+}
+
+func closeHandshake(c io.Closer, label string) {
+	if err := c.Close(); err != nil {
+		log.Debugf("ssh: close %s: %v", label, err)
+	}
+}

client/ssh/proxy/proxy.go

@@ -610,13 +610,10 @@ func (p *SSHProxy) dialBackend(ctx context.Context, addr, user, jwtToken string)
 		return nil, fmt.Errorf("connect to server: %w", err)
 	}
 
-	clientConn, chans, reqs, err := cryptossh.NewClientConn(conn, addr, config)
-	if err != nil {
-		_ = conn.Close()
-		return nil, fmt.Errorf("SSH handshake: %w", err)
-	}
+	handshakeCtx, cancel := context.WithTimeout(ctx, sshHandshakeTimeout)
+	defer cancel()
 
-	return cryptossh.NewClient(clientConn, chans, reqs), nil
+	return nbssh.Handshake(handshakeCtx, conn, addr, config)
 }
 
 func (p *SSHProxy) verifyHostKey(hostname string, remote net.Addr, key cryptossh.PublicKey) error {

client/ssh/session.go

@@ -0,0 +1,84 @@
+package ssh
+
+import (
+	"fmt"
+	"io"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/crypto/ssh"
+)
+
+// DefaultTerminalModes are the PTY modes used by the interactive terminal clients.
+var DefaultTerminalModes = ssh.TerminalModes{
+	ssh.ECHO:          1,
+	ssh.TTY_OP_ISPEED: 14400,
+	ssh.TTY_OP_OSPEED: 14400,
+	ssh.VINTR:         3,   // Ctrl+C
+	ssh.VQUIT:         28,  // Ctrl+\
+	ssh.VERASE:        127, // Backspace
+	ssh.VKILL:         21,  // Ctrl+U
+	ssh.VEOF:          4,   // Ctrl+D
+	ssh.VEOL:          0,
+	ssh.VEOL2:         0,
+	ssh.VSTART:        17, // Ctrl+Q
+	ssh.VSTOP:         19, // Ctrl+S
+	ssh.VSUSP:         26, // Ctrl+Z
+	ssh.VDISCARD:      15, // Ctrl+O
+	ssh.VREPRINT:      18, // Ctrl+R
+	ssh.VWERASE:       23, // Ctrl+W
+	ssh.VLNEXT:        22, // Ctrl+V
+}
+
+// PTYSession is an interactive shell session with a PTY and its I/O pipes.
+type PTYSession struct {
+	Session *ssh.Session
+	Stdin   io.WriteCloser
+	Stdout  io.Reader
+	Stderr  io.Reader
+}
+
+// StartPTYSession opens a session on the client, requests an xterm-256color PTY
+// with the default terminal modes, wires up the I/O pipes and starts a shell.
+// The session is closed on any error.
+func StartPTYSession(client *ssh.Client, cols, rows int) (*PTYSession, error) {
+	session, err := client.NewSession()
+	if err != nil {
+		return nil, fmt.Errorf("new session: %w", err)
+	}
+
+	pty, err := setupPTYSession(session, cols, rows)
+	if err != nil {
+		if closeErr := session.Close(); closeErr != nil {
+			log.Debugf("ssh: session close after setup error: %v", closeErr)
+		}
+		return nil, err
+	}
+	return pty, nil
+}
+
+// setupPTYSession requests the PTY, opens the pipes and starts the shell on an
+// already created session.
+func setupPTYSession(session *ssh.Session, cols, rows int) (*PTYSession, error) {
+	if err := session.RequestPty("xterm-256color", rows, cols, DefaultTerminalModes); err != nil {
+		return nil, fmt.Errorf("request pty: %w", err)
+	}
+
+	stdin, err := session.StdinPipe()
+	if err != nil {
+		return nil, fmt.Errorf("stdin pipe: %w", err)
+	}
+	stdout, err := session.StdoutPipe()
+	if err != nil {
+		return nil, fmt.Errorf("stdout pipe: %w", err)
+	}
+	stderr, err := session.StderrPipe()
+	if err != nil {
+		return nil, fmt.Errorf("stderr pipe: %w", err)
+	}
+
+	if err := session.Shell(); err != nil {
+		return nil, fmt.Errorf("start shell: %w", err)
+	}
+
+	return &PTYSession{Session: session, Stdin: stdin, Stdout: stdout, Stderr: stderr}, nil
+}

client/wasm/internal/ssh/client.go

@@ -80,13 +80,12 @@ func (c *Client) Connect(host string, port int, username, jwtToken string, ipVer
 		return fmt.Errorf("dial %s: %w", addr, err)
 	}
 
-	sshConn, chans, reqs, err := ssh.NewClientConn(conn, addr, config)
+	sshClient, err := nbssh.Handshake(ctx, conn, addr, config)
 	if err != nil {
-		closeWithLog(conn, "connection after handshake error")
-		return fmt.Errorf("SSH handshake: %w", err)
+		return err
 	}
 
-	c.sshClient = ssh.NewClient(sshConn, chans, reqs)
+	c.sshClient = sshClient
 	logrus.Infof("SSH: Connected to %s", addr)
 
 	return nil
@@ -119,57 +118,26 @@ func (c *Client) getAuthMethods(jwtToken string) ([]ssh.AuthMethod, error) {
 	return []ssh.AuthMethod{ssh.PublicKeys(signer)}, nil
 }
 
-// StartSession starts an SSH session with PTY
+// StartSession starts an SSH session with PTY. It holds the client lock for
+// the whole startup so Close cannot tear the client down mid-setup and the
+// new session cannot be installed into an already closed client.
 func (c *Client) StartSession(cols, rows int) error {
+	c.mu.Lock()
+	defer c.mu.Unlock()
+
 	if c.sshClient == nil {
 		return fmt.Errorf("SSH client not connected")
 	}
 
-	session, err := c.sshClient.NewSession()
+	pty, err := nbssh.StartPTYSession(c.sshClient, cols, rows)
 	if err != nil {
-		return fmt.Errorf("create session: %w", err)
+		return err
 	}
 
-	c.mu.Lock()
-	defer c.mu.Unlock()
-	c.session = session
-
-	modes := ssh.TerminalModes{
-		ssh.ECHO:          1,
-		ssh.TTY_OP_ISPEED: 14400,
-		ssh.TTY_OP_OSPEED: 14400,
-		ssh.VINTR:         3,
-		ssh.VQUIT:         28,
-		ssh.VERASE:        127,
-	}
-
-	if err := session.RequestPty("xterm-256color", rows, cols, modes); err != nil {
-		closeWithLog(session, "session after PTY error")
-		return fmt.Errorf("PTY request: %w", err)
-	}
-
-	c.stdin, err = session.StdinPipe()
-	if err != nil {
-		closeWithLog(session, "session after stdin error")
-		return fmt.Errorf("get stdin: %w", err)
-	}
-
-	c.stdout, err = session.StdoutPipe()
-	if err != nil {
-		closeWithLog(session, "session after stdout error")
-		return fmt.Errorf("get stdout: %w", err)
-	}
-
-	c.stderr, err = session.StderrPipe()
-	if err != nil {
-		closeWithLog(session, "session after stderr error")
-		return fmt.Errorf("get stderr: %w", err)
-	}
-
-	if err := session.Shell(); err != nil {
-		closeWithLog(session, "session after shell error")
-		return fmt.Errorf("start shell: %w", err)
-	}
+	c.session = pty.Session
+	c.stdin = pty.Stdin
+	c.stdout = pty.Stdout
+	c.stderr = pty.Stderr
 
 	logrus.Info("SSH: Session started with PTY")
 	return nil

infrastructure_files/getting-started.sh

@@ -281,6 +281,8 @@ read_enable_crowdsec() {
   echo "CrowdSec checks client IPs against a community threat intelligence database" > /dev/stderr
   echo "and blocks known malicious sources before they reach your services." > /dev/stderr
   echo "A local CrowdSec LAPI container will be added to your deployment." > /dev/stderr
+  echo "It also enables the AppSec (WAF) endpoint, so services can inspect HTTP" > /dev/stderr
+  echo "requests for exploits. Both stay off per service until you enable them." > /dev/stderr
   echo -n "Enable CrowdSec? [y/N]: " > /dev/stderr
   read -r CHOICE < /dev/tty
 
@@ -554,7 +556,8 @@ generate_configuration_files() {
         # TCP ServersTransport for PROXY protocol v2 to the proxy backend
         render_traefik_dynamic > traefik-dynamic.yaml
         if [[ "$ENABLE_CROWDSEC" == "true" ]]; then
-          mkdir -p crowdsec
+          mkdir -p crowdsec/acquis.d
+          render_crowdsec_appsec_acquis > crowdsec/acquis.d/appsec.yaml
         fi
       fi
       ;;
@@ -589,6 +592,23 @@ generate_configuration_files() {
   return 0
 }
 
+# The AppSec (WAF) listener only exists if an appsec acquisition datasource is
+# configured. One datasource is one listener carrying one merged rule set: the
+# protocol has no rule-set selector, so per-service rule variation would need
+# either a second datasource on another port or pre_eval hooks filtering on
+# req.Host.
+render_crowdsec_appsec_acquis() {
+  cat <<EOF
+source: appsec
+listen_addr: 0.0.0.0:7422
+appsec_configs:
+  - crowdsecurity/appsec-default
+labels:
+  type: appsec
+EOF
+  return 0
+}
+
 start_services_and_show_instructions() {
   # For built-in Traefik, start containers immediately
   # For NPM, start containers first (NPM needs services running to create proxy)
@@ -805,7 +825,11 @@ render_docker_compose_traefik_builtin() {
     restart: unless-stopped
     networks: [netbird]
     environment:
-      COLLECTIONS: crowdsecurity/linux
+      # appsec-generic-rules is required alongside appsec-virtual-patching:
+      # the appsec-default config references crowdsecurity/generic-* and
+      # crowdsecurity/experimental-*, which only that collection provides, and
+      # the engine exits at startup if they are missing.
+      COLLECTIONS: crowdsecurity/linux crowdsecurity/appsec-virtual-patching crowdsecurity/appsec-generic-rules
     volumes:
       - ./crowdsec:/etc/crowdsec
       - crowdsec_db:/var/lib/crowdsec/data
@@ -1071,6 +1095,11 @@ EOF
     cat <<EOF
 NB_PROXY_CROWDSEC_API_URL=http://crowdsec:8080
 NB_PROXY_CROWDSEC_API_KEY=$CROWDSEC_BOUNCER_KEY
+# AppSec (WAF) request inspection. Separate endpoint from the LAPI above and
+# validated with the same bouncer key. Setting it makes the proxy advertise the
+# AppSec capability, which is what lets a service select appsec_mode; nothing is
+# inspected until a service opts in.
+NB_PROXY_CROWDSEC_APPSEC_URL=http://crowdsec:7422/
 EOF
   fi
 

management/internals/modules/reverseproxy/domain/domain.go

@@ -23,6 +23,9 @@ type Domain struct {
 	// SupportsCrowdSec is populated at query time from proxy cluster capabilities.
 	// Not persisted.
 	SupportsCrowdSec *bool `gorm:"-"`
+	// SupportsAppSec is populated at query time from proxy cluster capabilities.
+	// Not persisted.
+	SupportsAppSec *bool `gorm:"-"`
 	// SupportsPrivate is populated at query time from proxy cluster capabilities. Not persisted.
 	SupportsPrivate *bool `gorm:"-"`
 }

management/internals/modules/reverseproxy/domain/manager/api.go

@@ -49,6 +49,7 @@ func domainToApi(d *domain.Domain) api.ReverseProxyDomain {
 		SupportsCustomPorts: d.SupportsCustomPorts,
 		RequireSubdomain:    d.RequireSubdomain,
 		SupportsCrowdsec:    d.SupportsCrowdSec,
+		SupportsAppsec:      d.SupportsAppSec,
 		SupportsPrivate:     d.SupportsPrivate,
 	}
 	if d.TargetCluster != "" {

management/internals/modules/reverseproxy/domain/manager/manager.go

@@ -39,6 +39,7 @@ type proxyManager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
@@ -98,6 +99,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		d.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, cluster)
 		d.RequireSubdomain = m.proxyManager.ClusterRequireSubdomain(ctx, cluster)
 		d.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, cluster)
+		d.SupportsAppSec = m.proxyManager.ClusterSupportsAppSec(ctx, cluster)
 		d.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, cluster)
 		ret = append(ret, d)
 	}
@@ -115,6 +117,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		if d.TargetCluster != "" {
 			cd.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, d.TargetCluster)
 			cd.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, d.TargetCluster)
+			cd.SupportsAppSec = m.proxyManager.ClusterSupportsAppSec(ctx, d.TargetCluster)
 			cd.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, d.TargetCluster)
 		}
 		// Custom domains never require a subdomain by default since

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

@@ -46,6 +46,10 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
+func (m *mockProxyManager) ClusterSupportsAppSec(_ context.Context, _ string) *bool {
+	return nil
+}
+
 func (m *mockProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
 	return nil
 }

management/internals/modules/reverseproxy/proxy/manager.go

@@ -19,6 +19,7 @@ type Manager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStale(ctx context.Context, inactivityDuration time.Duration) error
 	GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error)

management/internals/modules/reverseproxy/proxy/manager/manager.go

@@ -21,6 +21,7 @@ type store interface {
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
 	GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error)
@@ -138,6 +139,13 @@ func (m Manager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string
 	return m.store.GetClusterSupportsCrowdSec(ctx, clusterAddr)
 }
 
+// ClusterSupportsAppSec returns whether all active proxies in the cluster have
+// a CrowdSec AppSec endpoint configured (unanimous). Returns nil when no proxy
+// has reported capabilities.
+func (m Manager) ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
+	return m.store.GetClusterSupportsAppSec(ctx, clusterAddr)
+}
+
 // ClusterSupportsPrivate reports whether any active proxy claims the private capability (nil = unreported).
 func (m Manager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
 	return m.store.GetClusterSupportsPrivate(ctx, clusterAddr)

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

@@ -99,6 +99,9 @@ func (m *mockStore) GetClusterRequireSubdomain(_ context.Context, _ string) *boo
 func (m *mockStore) GetClusterSupportsCrowdSec(_ context.Context, _ string) *bool {
 	return nil
 }
+func (m *mockStore) GetClusterSupportsAppSec(_ context.Context, _ string) *bool {
+	return nil
+}
 func (m *mockStore) GetClusterSupportsPrivate(_ context.Context, _ string) *bool {
 	return nil
 }

management/internals/modules/reverseproxy/proxy/manager_mock.go

@@ -50,20 +50,6 @@ func (mr *MockManagerMockRecorder) CleanupStale(ctx, inactivityDuration interfac
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CleanupStale", reflect.TypeOf((*MockManager)(nil).CleanupStale), ctx, inactivityDuration)
 }
 
-// ClusterSupportsCustomPorts mocks base method.
-func (m *MockManager) ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "ClusterSupportsCustomPorts", ctx, clusterAddr)
-	ret0, _ := ret[0].(*bool)
-	return ret0
-}
-
-// ClusterSupportsCustomPorts indicates an expected call of ClusterSupportsCustomPorts.
-func (mr *MockManagerMockRecorder) ClusterSupportsCustomPorts(ctx, clusterAddr interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCustomPorts", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCustomPorts), ctx, clusterAddr)
-}
-
 // ClusterRequireSubdomain mocks base method.
 func (m *MockManager) ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool {
 	m.ctrl.T.Helper()
@@ -78,6 +64,20 @@ func (mr *MockManagerMockRecorder) ClusterRequireSubdomain(ctx, clusterAddr inte
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterRequireSubdomain", reflect.TypeOf((*MockManager)(nil).ClusterRequireSubdomain), ctx, clusterAddr)
 }
 
+// ClusterSupportsAppSec mocks base method.
+func (m *MockManager) ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "ClusterSupportsAppSec", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// ClusterSupportsAppSec indicates an expected call of ClusterSupportsAppSec.
+func (mr *MockManagerMockRecorder) ClusterSupportsAppSec(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsAppSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsAppSec), ctx, clusterAddr)
+}
+
 // ClusterSupportsCrowdSec mocks base method.
 func (m *MockManager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
 	m.ctrl.T.Helper()
@@ -92,6 +92,20 @@ func (mr *MockManagerMockRecorder) ClusterSupportsCrowdSec(ctx, clusterAddr inte
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCrowdSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCrowdSec), ctx, clusterAddr)
 }
 
+// ClusterSupportsCustomPorts mocks base method.
+func (m *MockManager) ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "ClusterSupportsCustomPorts", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// ClusterSupportsCustomPorts indicates an expected call of ClusterSupportsCustomPorts.
+func (mr *MockManagerMockRecorder) ClusterSupportsCustomPorts(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCustomPorts", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCustomPorts), ctx, clusterAddr)
+}
+
 // ClusterSupportsPrivate mocks base method.
 func (m *MockManager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
 	m.ctrl.T.Helper()
@@ -121,6 +135,35 @@ func (mr *MockManagerMockRecorder) Connect(ctx, proxyID, sessionID, clusterAddre
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Connect", reflect.TypeOf((*MockManager)(nil).Connect), ctx, proxyID, sessionID, clusterAddress, ipAddress, accountID, capabilities)
 }
 
+// CountAccountProxies mocks base method.
+func (m *MockManager) CountAccountProxies(ctx context.Context, accountID string) (int64, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "CountAccountProxies", ctx, accountID)
+	ret0, _ := ret[0].(int64)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// CountAccountProxies indicates an expected call of CountAccountProxies.
+func (mr *MockManagerMockRecorder) CountAccountProxies(ctx, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountAccountProxies", reflect.TypeOf((*MockManager)(nil).CountAccountProxies), ctx, accountID)
+}
+
+// DeleteAccountCluster mocks base method.
+func (m *MockManager) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "DeleteAccountCluster", ctx, clusterAddress, accountID)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// DeleteAccountCluster indicates an expected call of DeleteAccountCluster.
+func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
+}
+
 // Disconnect mocks base method.
 func (m *MockManager) Disconnect(ctx context.Context, proxyID, sessionID string) error {
 	m.ctrl.T.Helper()
@@ -135,6 +178,21 @@ func (mr *MockManagerMockRecorder) Disconnect(ctx, proxyID, sessionID interface{
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Disconnect", reflect.TypeOf((*MockManager)(nil).Disconnect), ctx, proxyID, sessionID)
 }
 
+// GetAccountProxy mocks base method.
+func (m *MockManager) GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetAccountProxy", ctx, accountID)
+	ret0, _ := ret[0].(*Proxy)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetAccountProxy indicates an expected call of GetAccountProxy.
+func (mr *MockManagerMockRecorder) GetAccountProxy(ctx, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountProxy", reflect.TypeOf((*MockManager)(nil).GetAccountProxy), ctx, accountID)
+}
+
 // GetActiveClusterAddresses mocks base method.
 func (m *MockManager) GetActiveClusterAddresses(ctx context.Context) ([]string, error) {
 	m.ctrl.T.Helper()
@@ -150,6 +208,7 @@ func (mr *MockManagerMockRecorder) GetActiveClusterAddresses(ctx interface{}) *g
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusterAddresses", reflect.TypeOf((*MockManager)(nil).GetActiveClusterAddresses), ctx)
 }
 
+// GetActiveClusterAddressesForAccount mocks base method.
 func (m *MockManager) GetActiveClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error) {
 	m.ctrl.T.Helper()
 	ret := m.ctrl.Call(m, "GetActiveClusterAddressesForAccount", ctx, accountID)
@@ -158,6 +217,7 @@ func (m *MockManager) GetActiveClusterAddressesForAccount(ctx context.Context, a
 	return ret0, ret1
 }
 
+// GetActiveClusterAddressesForAccount indicates an expected call of GetActiveClusterAddressesForAccount.
 func (mr *MockManagerMockRecorder) GetActiveClusterAddressesForAccount(ctx, accountID interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusterAddressesForAccount", reflect.TypeOf((*MockManager)(nil).GetActiveClusterAddressesForAccount), ctx, accountID)
@@ -177,36 +237,6 @@ func (mr *MockManagerMockRecorder) Heartbeat(ctx, p interface{}) *gomock.Call {
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "Heartbeat", reflect.TypeOf((*MockManager)(nil).Heartbeat), ctx, p)
 }
 
-// GetAccountProxy mocks base method.
-func (m *MockManager) GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetAccountProxy", ctx, accountID)
-	ret0, _ := ret[0].(*Proxy)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// GetAccountProxy indicates an expected call of GetAccountProxy.
-func (mr *MockManagerMockRecorder) GetAccountProxy(ctx, accountID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountProxy", reflect.TypeOf((*MockManager)(nil).GetAccountProxy), ctx, accountID)
-}
-
-// CountAccountProxies mocks base method.
-func (m *MockManager) CountAccountProxies(ctx context.Context, accountID string) (int64, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "CountAccountProxies", ctx, accountID)
-	ret0, _ := ret[0].(int64)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// CountAccountProxies indicates an expected call of CountAccountProxies.
-func (mr *MockManagerMockRecorder) CountAccountProxies(ctx, accountID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountAccountProxies", reflect.TypeOf((*MockManager)(nil).CountAccountProxies), ctx, accountID)
-}
-
 // IsClusterAddressAvailable mocks base method.
 func (m *MockManager) IsClusterAddressAvailable(ctx context.Context, clusterAddress, accountID string) (bool, error) {
 	m.ctrl.T.Helper()
@@ -222,20 +252,6 @@ func (mr *MockManagerMockRecorder) IsClusterAddressAvailable(ctx, clusterAddress
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IsClusterAddressAvailable", reflect.TypeOf((*MockManager)(nil).IsClusterAddressAvailable), ctx, clusterAddress, accountID)
 }
 
-// DeleteAccountCluster mocks base method.
-func (m *MockManager) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "DeleteAccountCluster", ctx, clusterAddress, accountID)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// DeleteAccountCluster indicates an expected call of DeleteAccountCluster.
-func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
-}
-
 // MockController is a mock of Controller interface.
 type MockController struct {
 	ctrl     *gomock.Controller

management/internals/modules/reverseproxy/proxy/proxy.go

@@ -20,6 +20,9 @@ type Capabilities struct {
 	RequireSubdomain *bool
 	// SupportsCrowdsec indicates whether this proxy has CrowdSec configured.
 	SupportsCrowdsec *bool
+	// SupportsAppsec indicates whether this proxy has a CrowdSec AppSec (WAF)
+	// endpoint configured.
+	SupportsAppsec *bool
 	// Private indicates whether this proxy supports inbound access via Wireguard
 	// tunnel and netbird-only authentication policies
 	Private *bool
@@ -74,5 +77,6 @@ type Cluster struct {
 	SupportsCustomPorts *bool
 	RequireSubdomain    *bool
 	SupportsCrowdSec    *bool
+	SupportsAppSec      *bool
 	Private             *bool
 }

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

@@ -204,6 +204,7 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 			SupportsCustomPorts: c.SupportsCustomPorts,
 			RequireSubdomain:    c.RequireSubdomain,
 			SupportsCrowdsec:    c.SupportsCrowdSec,
+			SupportsAppsec:      c.SupportsAppSec,
 			Private:             c.Private,
 		})
 	}

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

@@ -82,6 +82,7 @@ type CapabilityProvider interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
@@ -137,6 +138,7 @@ func (m *Manager) GetClusters(ctx context.Context, accountID, userID string) ([]
 		clusters[i].SupportsCustomPorts = m.capabilities.ClusterSupportsCustomPorts(ctx, clusters[i].Address)
 		clusters[i].RequireSubdomain = m.capabilities.ClusterRequireSubdomain(ctx, clusters[i].Address)
 		clusters[i].SupportsCrowdSec = m.capabilities.ClusterSupportsCrowdSec(ctx, clusters[i].Address)
+		clusters[i].SupportsAppSec = m.capabilities.ClusterSupportsAppSec(ctx, clusters[i].Address)
 		clusters[i].Private = m.capabilities.ClusterSupportsPrivate(ctx, clusters[i].Address)
 	}
 

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

@@ -165,6 +165,22 @@ type AccessRestrictions struct {
 	AllowedCountries []string `json:"allowed_countries,omitempty" gorm:"serializer:json"`
 	BlockedCountries []string `json:"blocked_countries,omitempty" gorm:"serializer:json"`
 	CrowdSecMode     string   `json:"crowdsec_mode,omitempty" gorm:"serializer:json"`
+	// AllowMatch controls how the allowlists combine: "" or "all" require
+	// matching every allowlist (AND), "any" requires matching at least one (OR).
+	// Empty is treated as "all" for backward compatibility with existing records.
+	AllowMatch string `json:"allow_match,omitempty" gorm:"serializer:json"`
+	// AppSecMode is the CrowdSec AppSec (WAF) request inspection mode: "",
+	// "off", "enforce", or "observe". HTTP services only.
+	AppSecMode string `json:"appsec_mode,omitempty" gorm:"serializer:json"`
+}
+
+// isEmpty reports whether no restriction is configured. Both conversions drop
+// the object entirely in that case, so a field missing from this check is
+// silently discarded on the way to the API and the proxy.
+func (r AccessRestrictions) isEmpty() bool {
+	return len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
+		len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
+		r.CrowdSecMode == "" && r.AllowMatch == "" && r.AppSecMode == ""
 }
 
 // Copy returns a deep copy of the AccessRestrictions.
@@ -175,6 +191,8 @@ func (r AccessRestrictions) Copy() AccessRestrictions {
 		AllowedCountries: slices.Clone(r.AllowedCountries),
 		BlockedCountries: slices.Clone(r.BlockedCountries),
 		CrowdSecMode:     r.CrowdSecMode,
+		AllowMatch:       r.AllowMatch,
+		AppSecMode:       r.AppSecMode,
 	}
 }
 
@@ -808,13 +826,23 @@ func restrictionsFromAPI(r *api.AccessRestrictions) (AccessRestrictions, error)
 		}
 		res.CrowdSecMode = string(*r.CrowdsecMode)
 	}
+	if r.AllowMatch != nil {
+		if !r.AllowMatch.Valid() {
+			return AccessRestrictions{}, fmt.Errorf("invalid allow_match %q", *r.AllowMatch)
+		}
+		res.AllowMatch = string(*r.AllowMatch)
+	}
+	if r.AppsecMode != nil {
+		if !r.AppsecMode.Valid() {
+			return AccessRestrictions{}, fmt.Errorf("invalid appsec_mode %q", *r.AppsecMode)
+		}
+		res.AppSecMode = string(*r.AppsecMode)
+	}
 	return res, nil
 }
 
 func restrictionsToAPI(r AccessRestrictions) *api.AccessRestrictions {
-	if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
-		len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
-		r.CrowdSecMode == "" {
+	if r.isEmpty() {
 		return nil
 	}
 	res := &api.AccessRestrictions{}
@@ -834,13 +862,19 @@ func restrictionsToAPI(r AccessRestrictions) *api.AccessRestrictions {
 		mode := api.AccessRestrictionsCrowdsecMode(r.CrowdSecMode)
 		res.CrowdsecMode = &mode
 	}
+	if r.AllowMatch != "" {
+		match := api.AccessRestrictionsAllowMatch(r.AllowMatch)
+		res.AllowMatch = &match
+	}
+	if r.AppSecMode != "" {
+		mode := api.AccessRestrictionsAppsecMode(r.AppSecMode)
+		res.AppsecMode = &mode
+	}
 	return res
 }
 
 func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
-	if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
-		len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
-		r.CrowdSecMode == "" {
+	if r.isEmpty() {
 		return nil
 	}
 	return &proto.AccessRestrictions{
@@ -849,6 +883,8 @@ func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
 		AllowedCountries: r.AllowedCountries,
 		BlockedCountries: r.BlockedCountries,
 		CrowdsecMode:     r.CrowdSecMode,
+		AllowMatch:       r.AllowMatch,
+		AppsecMode:       r.AppSecMode,
 	}
 }
 
@@ -874,6 +910,11 @@ func (s *Service) Validate() error {
 	if err := validateAccessRestrictions(&s.Restrictions); err != nil {
 		return err
 	}
+	// AppSec inspects HTTP requests, so it cannot apply to the L4 modes, which
+	// forward opaque byte streams.
+	if appSecEnabled(s.Restrictions.AppSecMode) && s.Mode != ModeHTTP {
+		return fmt.Errorf("appsec_mode is only supported for HTTP services, got mode %q", s.Mode)
+	}
 	if err := s.validatePrivateRequirements(); err != nil {
 		return err
 	}
@@ -1242,10 +1283,39 @@ func validateCrowdSecMode(mode string) error {
 	}
 }
 
+func validateAllowMatch(mode string) error {
+	switch mode {
+	case "", "all", "any":
+		return nil
+	default:
+		return fmt.Errorf("allow_match %q is invalid", mode)
+	}
+}
+
+func validateAppSecMode(mode string) error {
+	switch mode {
+	case "", "off", "enforce", "observe":
+		return nil
+	default:
+		return fmt.Errorf("appsec_mode %q is invalid", mode)
+	}
+}
+
+// appSecEnabled reports whether the mode asks for request inspection.
+func appSecEnabled(mode string) bool {
+	return mode == "enforce" || mode == "observe"
+}
+
 func validateAccessRestrictions(r *AccessRestrictions) error {
 	if err := validateCrowdSecMode(r.CrowdSecMode); err != nil {
 		return err
 	}
+	if err := validateAllowMatch(r.AllowMatch); err != nil {
+		return err
+	}
+	if err := validateAppSecMode(r.AppSecMode); err != nil {
+		return err
+	}
 
 	if len(r.AllowedCIDRs) > maxCIDREntries {
 		return fmt.Errorf("allowed_cidrs: exceeds maximum of %d entries", maxCIDREntries)

management/internals/modules/reverseproxy/service/service_test.go

@@ -26,6 +26,17 @@ func validProxy() *Service {
 	}
 }
 
+// validL4Proxy returns a service that passes validation in one of the L4 modes.
+func validL4Proxy(mode string) *Service {
+	rp := validProxy()
+	rp.Mode = mode
+	rp.ListenPort = 9000
+	rp.Targets = []*Target{
+		{TargetId: "peer-1", TargetType: TargetTypePeer, Host: "10.0.0.1", Port: 5432, Protocol: mode, Enabled: true},
+	}
+	return rp
+}
+
 func TestValidate_Valid(t *testing.T) {
 	require.NoError(t, validProxy().Validate())
 }
@@ -1302,6 +1313,65 @@ func TestValidate_Private_AcceptsClusterTargetWithAccessGroups(t *testing.T) {
 	require.NoError(t, rp.Validate())
 }
 
+func TestRestrictions_AllowMatch_RoundTrip(t *testing.T) {
+	anyMatch := api.AccessRestrictionsAllowMatchAny
+	apiIn := &api.AccessRestrictions{
+		AllowedCidrs:     &[]string{"203.0.113.0/24"},
+		AllowedCountries: &[]string{"US"},
+		AllowMatch:       &anyMatch,
+	}
+
+	model, err := restrictionsFromAPI(apiIn)
+	require.NoError(t, err)
+	assert.Equal(t, "any", model.AllowMatch)
+
+	apiOut := restrictionsToAPI(model)
+	require.NotNil(t, apiOut.AllowMatch)
+	assert.Equal(t, api.AccessRestrictionsAllowMatchAny, *apiOut.AllowMatch)
+
+	protoOut := restrictionsToProto(model)
+	require.NotNil(t, protoOut)
+	assert.Equal(t, "any", protoOut.AllowMatch)
+}
+
+func TestRestrictions_AllowMatch_EmptyDefaultsToAll(t *testing.T) {
+	// A stored record with no allow_match (existing services) stays empty and
+	// must not surface a value on the API, preserving AND behavior downstream.
+	model, err := restrictionsFromAPI(&api.AccessRestrictions{
+		AllowedCidrs: &[]string{"203.0.113.0/24"},
+	})
+	require.NoError(t, err)
+	assert.Empty(t, model.AllowMatch, "unset allow_match stays empty")
+
+	apiOut := restrictionsToAPI(model)
+	require.NotNil(t, apiOut)
+	assert.Nil(t, apiOut.AllowMatch, "empty allow_match is omitted from the API response")
+}
+
+func TestRestrictions_AllowMatchOnly_Preserved(t *testing.T) {
+	// allow_match set without any list must not be dropped by the emptiness
+	// guards, so it round-trips through both the API and proto conversions.
+	model := AccessRestrictions{AllowMatch: "any"}
+
+	apiOut := restrictionsToAPI(model)
+	require.NotNil(t, apiOut, "allow-match-only restriction must not be omitted from the API response")
+	require.NotNil(t, apiOut.AllowMatch)
+	assert.Equal(t, api.AccessRestrictionsAllowMatchAny, *apiOut.AllowMatch)
+
+	protoOut := restrictionsToProto(model)
+	require.NotNil(t, protoOut, "allow-match-only restriction must not be omitted from the proto output")
+	assert.Equal(t, "any", protoOut.AllowMatch)
+}
+
+func TestValidate_RejectsInvalidAllowMatch(t *testing.T) {
+	rp := validProxy()
+	rp.Restrictions = AccessRestrictions{
+		AllowedCIDRs: []string{"203.0.113.0/24"},
+		AllowMatch:   "sometimes",
+	}
+	assert.ErrorContains(t, rp.Validate(), "allow_match")
+}
+
 func TestValidate_Private_RejectsNonHTTPMode(t *testing.T) {
 	rp := validProxy()
 	rp.Private = true
@@ -1315,3 +1385,68 @@ func TestValidate_Private_RejectsNonHTTPMode(t *testing.T) {
 	}}
 	assert.ErrorContains(t, rp.Validate(), "HTTP")
 }
+
+func TestRestrictions_AppSecMode_RoundTrip(t *testing.T) {
+	mode := api.AccessRestrictionsAppsecModeEnforce
+	apiIn := &api.AccessRestrictions{AppsecMode: &mode}
+
+	model, err := restrictionsFromAPI(apiIn)
+	require.NoError(t, err)
+	assert.Equal(t, "enforce", model.AppSecMode)
+
+	// appsec_mode alone must keep the restrictions object alive on both the API
+	// and proto legs: it is meaningful without any CIDR or country entry.
+	apiOut := restrictionsToAPI(model)
+	require.NotNil(t, apiOut, "appsec_mode alone must not collapse the restrictions to nil")
+	require.NotNil(t, apiOut.AppsecMode)
+	assert.Equal(t, api.AccessRestrictionsAppsecModeEnforce, *apiOut.AppsecMode)
+
+	protoOut := restrictionsToProto(model)
+	require.NotNil(t, protoOut, "appsec_mode alone must reach the proxy")
+	assert.Equal(t, "enforce", protoOut.AppsecMode)
+}
+
+func TestRestrictions_AppSecMode_EmptyIsOmitted(t *testing.T) {
+	model, err := restrictionsFromAPI(&api.AccessRestrictions{
+		AllowedCidrs: &[]string{"203.0.113.0/24"},
+	})
+	require.NoError(t, err)
+	assert.Empty(t, model.AppSecMode)
+
+	apiOut := restrictionsToAPI(model)
+	require.NotNil(t, apiOut)
+	assert.Nil(t, apiOut.AppsecMode, "empty appsec_mode is omitted from the API response")
+}
+
+func TestRestrictions_AppSecMode_CopyIsDeep(t *testing.T) {
+	original := AccessRestrictions{AppSecMode: "observe", CrowdSecMode: "enforce"}
+	assert.Equal(t, original, original.Copy(), "Copy must carry every mode field")
+}
+
+func TestValidate_RejectsInvalidAppSecMode(t *testing.T) {
+	rp := validProxy()
+	rp.Restrictions = AccessRestrictions{AppSecMode: "sometimes"}
+	assert.ErrorContains(t, rp.Validate(), "appsec_mode")
+}
+
+func TestValidate_RejectsAppSecOnL4Modes(t *testing.T) {
+	// AppSec inspects HTTP requests, so the L4 modes cannot honor it. Accepting
+	// the field there would report protection that never runs.
+	for _, mode := range []string{ModeTCP, ModeUDP, ModeTLS} {
+		t.Run(mode, func(t *testing.T) {
+			rp := validL4Proxy(mode)
+			rp.Restrictions = AccessRestrictions{AppSecMode: "enforce"}
+			assert.ErrorContains(t, rp.Validate(), "appsec_mode is only supported for HTTP services")
+		})
+	}
+}
+
+func TestValidate_AllowsAppSecOffOnL4Modes(t *testing.T) {
+	for _, mode := range []string{ModeTCP, ModeUDP, ModeTLS} {
+		t.Run(mode, func(t *testing.T) {
+			rp := validL4Proxy(mode)
+			rp.Restrictions = AccessRestrictions{AppSecMode: "off"}
+			require.NoError(t, rp.Validate(), "an explicit off must not be rejected on L4 services")
+		})
+	}
+}

management/internals/shared/grpc/proxy.go

@@ -562,6 +562,7 @@ func (s *ProxyServiceServer) registerProxyConnection(ctx context.Context, params
 			SupportsCustomPorts: c.SupportsCustomPorts,
 			RequireSubdomain:    c.RequireSubdomain,
 			SupportsCrowdsec:    c.SupportsCrowdsec,
+			SupportsAppsec:      c.SupportsAppsec,
 			Private:             c.Private,
 		}
 	}

management/server/http/handlers/setup_keys/setupkeys_handler.go

@@ -64,6 +64,19 @@ func (h *handler) createSetupKey(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
+	// A one-off key can be used once, and GenerateSetupKey pins its usage limit
+	// at 1 whatever the request says. Silently overriding a caller that asked
+	// for a different number leaves them holding a key that does not do what
+	// they configured, and no way to find out except by using it. Only values
+	// above 1 are refused: usage_limit is a required field with no null, so 0
+	// cannot be told apart from a caller that has nothing to say about it.
+	if types.SetupKeyType(req.Type) == types.SetupKeyOneOff && req.UsageLimit > 1 {
+		util.WriteError(r.Context(), status.Errorf(status.InvalidArgument,
+			"usage_limit %d is not valid for a one-off setup key, which can be used once; use type reusable for a key that can be used more than once",
+			req.UsageLimit), w)
+		return
+	}
+
 	expiresIn := time.Duration(req.ExpiresIn) * time.Second
 
 	if expiresIn < 0 {

management/server/http/handlers/setup_keys/setupkeys_handler_test.go

@@ -134,6 +134,40 @@ func TestSetupKeysHandlers(t *testing.T) {
 			expectedBody:     true,
 			expectedSetupKey: expectedNewKey,
 		},
+		{
+			// A one-off key is used once. Asking for more used to be accepted
+			// and then quietly reduced to 1.
+			name:        "Create One-Off Setup Key With Conflicting Usage Limit",
+			requestType: http.MethodPost,
+			requestPath: "/api/setup-keys",
+			requestBody: bytes.NewBuffer(
+				[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"one-off\",\"expires_in\":86400,\"usage_limit\":5}", newSetupKeyName))),
+			expectedStatus: http.StatusUnprocessableEntity,
+			expectedBody:   false,
+		},
+		{
+			// 0 is what a caller sends when it has nothing to say about the
+			// usage limit, since the field is required and has no null, so it
+			// has to keep working.
+			name:        "Create One-Off Setup Key Without Usage Limit",
+			requestType: http.MethodPost,
+			requestPath: "/api/setup-keys",
+			requestBody: bytes.NewBuffer(
+				[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"one-off\",\"expires_in\":86400,\"usage_limit\":0}", newSetupKeyName))),
+			expectedStatus: http.StatusOK,
+			expectedBody:   false,
+		},
+		{
+			// Only one-off keys are constrained; a reusable key means what it
+			// says.
+			name:        "Create Reusable Setup Key With Usage Limit",
+			requestType: http.MethodPost,
+			requestPath: "/api/setup-keys",
+			requestBody: bytes.NewBuffer(
+				[]byte(fmt.Sprintf("{\"name\":\"%s\",\"type\":\"reusable\",\"expires_in\":86400,\"usage_limit\":5}", newSetupKeyName))),
+			expectedStatus: http.StatusOK,
+			expectedBody:   false,
+		},
 		{
 			name:        "Update Setup Key",
 			requestType: http.MethodPut,

management/server/http/testing/integration/setupkeys_handler_integration_test.go

@@ -136,7 +136,10 @@ func Test_SetupKeys_Create(t *testing.T) {
 			},
 		},
 		{
-			name:        "Create Setup Key as on-off with more than one usage",
+			// The key used to be created anyway, with its usage limit quietly
+			// reduced to 1, so the caller was told a key they had not asked for
+			// was what they asked for.
+			name:        "Create Setup Key as one-off with more than one usage",
 			requestType: http.MethodPost,
 			requestPath: "/api/setup-keys",
 			requestBody: &api.CreateSetupKeyRequest{
@@ -146,23 +149,7 @@ func Test_SetupKeys_Create(t *testing.T) {
 				Type:       "one-off",
 				UsageLimit: 3,
 			},
-			expectedStatus: http.StatusOK,
-			expectedResponse: &api.SetupKey{
-				AutoGroups: []string{},
-				Ephemeral:  false,
-				Expires:    time.Time{},
-				Id:         "",
-				Key:        "",
-				LastUsed:   time.Time{},
-				Name:       testing_tools.NewKeyName,
-				Revoked:    false,
-				State:      "valid",
-				Type:       "one-off",
-				UpdatedAt:  time.Now(),
-				UsageLimit: 1,
-				UsedTimes:  0,
-				Valid:      true,
-			},
+			expectedStatus: http.StatusUnprocessableEntity,
 		},
 		{
 			name:        "Create Setup Key with expiration in the past",

management/server/store/sql_store.go

@@ -6491,6 +6491,7 @@ var validCapabilityColumns = map[string]struct{}{
 	"supports_custom_ports": {},
 	"require_subdomain":     {},
 	"supports_crowdsec":     {},
+	"supports_appsec":       {},
 	"private":               {},
 }
 
@@ -6521,6 +6522,14 @@ func (s *SqlStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr s
 	return s.getClusterUnanimousCapability(ctx, clusterAddr, "supports_crowdsec")
 }
 
+// GetClusterSupportsAppSec returns whether all active proxies in the cluster
+// have a CrowdSec AppSec endpoint configured. Returns nil when no proxy
+// reported the capability. Unanimous for the same reason as CrowdSec: a single
+// proxy without AppSec would let requests through uninspected.
+func (s *SqlStore) GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
+	return s.getClusterUnanimousCapability(ctx, clusterAddr, "supports_appsec")
+}
+
 // getClusterUnanimousCapability returns an aggregated boolean capability
 // requiring all active proxies in the cluster to report true.
 func (s *SqlStore) getClusterUnanimousCapability(ctx context.Context, clusterAddr, column string) *bool {

management/server/store/sql_store_proxy_capability_test.go

@@ -0,0 +1,119 @@
+package store
+
+import (
+	"context"
+	"fmt"
+	"os"
+	"runtime"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
+)
+
+// Capabilities travel proxy → gRPC → embedded gorm columns → aggregation → API.
+// A field dropped at any of those hops reads as "capability absent", which is
+// indistinguishable from a proxy that never reported it: the dashboard simply
+// hides the feature and nothing fails. These assertions cover the persistence
+// and aggregation hops.
+func TestSqlStore_ClusterCapabilityAggregation(t *testing.T) {
+	if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
+		t.Skip("skip CI tests on darwin and windows")
+	}
+
+	yes, no := true, false
+
+	tests := []struct {
+		name          string
+		reported      []*bool // one entry per connected proxy in the cluster
+		wantAppSec    *bool
+		wantAssertion string
+	}{
+		{
+			name:          "unreported stays unknown",
+			reported:      []*bool{nil},
+			wantAppSec:    nil,
+			wantAssertion: "an unreported capability must not read as false",
+		},
+		{
+			name:          "single proxy reporting true",
+			reported:      []*bool{&yes},
+			wantAppSec:    &yes,
+			wantAssertion: "a reported capability must survive persistence",
+		},
+		{
+			name:          "one proxy without it disables the cluster",
+			reported:      []*bool{&yes, &no},
+			wantAppSec:    &no,
+			wantAssertion: "capability must be unanimous, so a rolling upgrade cannot leave traffic uninspected",
+		},
+		{
+			name:          "one proxy yet to report disables the cluster",
+			reported:      []*bool{&yes, nil},
+			wantAppSec:    &no,
+			wantAssertion: "a proxy that has not reported must not count as capable",
+		},
+	}
+
+	runTestForAllEngines(t, "", func(t *testing.T, store Store) {
+		ctx := context.Background()
+		for i, tt := range tests {
+			t.Run(tt.name, func(t *testing.T) {
+				cluster := fmt.Sprintf("cluster-%d.proxy.example", i)
+				for j, reported := range tt.reported {
+					require.NoError(t, store.SaveProxy(ctx, &proxy.Proxy{
+						ID:             fmt.Sprintf("proxy-%d-%d", i, j),
+						ClusterAddress: cluster,
+						Status:         proxy.StatusConnected,
+						LastSeen:       time.Now(),
+						Capabilities:   proxy.Capabilities{SupportsAppsec: reported},
+					}))
+				}
+
+				got := store.GetClusterSupportsAppSec(ctx, cluster)
+				if tt.wantAppSec == nil {
+					assert.Nil(t, got, tt.wantAssertion)
+					return
+				}
+				require.NotNil(t, got, tt.wantAssertion)
+				assert.Equal(t, *tt.wantAppSec, *got, tt.wantAssertion)
+			})
+		}
+	})
+}
+
+// AppSec and IP reputation are separate endpoints, so a cluster can have either
+// without the other. Gating one on the other would silently disable a feature
+// the operator configured.
+func TestSqlStore_ClusterCapabilitiesAreIndependent(t *testing.T) {
+	if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
+		t.Skip("skip CI tests on darwin and windows")
+	}
+
+	runTestForAllEngines(t, "", func(t *testing.T, store Store) {
+		ctx := context.Background()
+		const cluster = "independent.proxy.example"
+		yes, no := true, false
+
+		require.NoError(t, store.SaveProxy(ctx, &proxy.Proxy{
+			ID:             "proxy-independent",
+			ClusterAddress: cluster,
+			Status:         proxy.StatusConnected,
+			LastSeen:       time.Now(),
+			Capabilities: proxy.Capabilities{
+				SupportsAppsec:   &yes,
+				SupportsCrowdsec: &no,
+			},
+		}))
+
+		appsec := store.GetClusterSupportsAppSec(ctx, cluster)
+		crowdsec := store.GetClusterSupportsCrowdSec(ctx, cluster)
+		require.NotNil(t, appsec)
+		require.NotNil(t, crowdsec)
+		assert.True(t, *appsec, "AppSec must not be gated on CrowdSec")
+		assert.False(t, *crowdsec, "CrowdSec must not be implied by AppSec")
+	})
+}

management/server/store/sql_store_service_test.go

@@ -133,3 +133,46 @@ func TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip(t *testing.T) {
 		assert.True(t, tg.Options.DisableAccessLog, "options disable access log")
 	})
 }
+
+func TestSqlStore_GetAccount_ServiceRestrictionsRoundtrip(t *testing.T) {
+	if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
+		t.Skip("skip CI tests on darwin and windows")
+	}
+
+	runTestForAllEngines(t, "", func(t *testing.T, store Store) {
+		ctx := context.Background()
+		account := newAccountWithId(ctx, "account_svc_restrictions", "testuser", "")
+		require.NoError(t, store.SaveAccount(ctx, account))
+
+		svc := &rpservice.Service{
+			ID:        "svc-restrictions",
+			AccountID: account.Id,
+			Name:      "restricted-svc",
+			Domain:    "restricted.example",
+			Enabled:   true,
+			Mode:      rpservice.ModeHTTP,
+			Restrictions: rpservice.AccessRestrictions{
+				AllowedCIDRs:     []string{"203.0.113.0/24"},
+				AllowedCountries: []string{"US"},
+				AllowMatch:       "any",
+				CrowdSecMode:     "observe",
+				AppSecMode:       "enforce",
+			},
+		}
+		require.NoError(t, store.CreateService(ctx, svc))
+
+		loaded, err := store.GetAccount(ctx, account.Id)
+		require.NoError(t, err)
+		require.Len(t, loaded.Services, 1)
+
+		// Restrictions are stored as a JSON blob; confirm the whole struct,
+		// including allow_match and the CrowdSec modes, survives the read path
+		// (Postgres pgx path included via runTestForAllEngines).
+		got := loaded.Services[0].Restrictions
+		assert.Equal(t, []string{"203.0.113.0/24"}, got.AllowedCIDRs)
+		assert.Equal(t, []string{"US"}, got.AllowedCountries)
+		assert.Equal(t, "any", got.AllowMatch)
+		assert.Equal(t, "observe", got.CrowdSecMode)
+		assert.Equal(t, "enforce", got.AppSecMode)
+	})
+}

management/server/store/store.go

@@ -329,6 +329,7 @@ type Store interface {
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStaleProxies(ctx context.Context, inactivityDuration time.Duration) error
 	GetAllProxies(ctx context.Context) ([]*proxy.Proxy, error)

management/server/store/store_mock.go

@@ -1878,6 +1878,20 @@ func (mr *MockStoreMockRecorder) GetClusterRequireSubdomain(ctx, clusterAddr int
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterRequireSubdomain", reflect.TypeOf((*MockStore)(nil).GetClusterRequireSubdomain), ctx, clusterAddr)
 }
 
+// GetClusterSupportsAppSec mocks base method.
+func (m *MockStore) GetClusterSupportsAppSec(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetClusterSupportsAppSec", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// GetClusterSupportsAppSec indicates an expected call of GetClusterSupportsAppSec.
+func (mr *MockStoreMockRecorder) GetClusterSupportsAppSec(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsAppSec", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsAppSec), ctx, clusterAddr)
+}
+
 // GetClusterSupportsCrowdSec mocks base method.
 func (m *MockStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
 	m.ctrl.T.Helper()

proxy/cmd/proxy/cmd/root.go

@@ -79,6 +79,11 @@ var (
 	geoDataDir            string
 	crowdsecAPIURL        string
 	crowdsecAPIKey        string
+	appsecURL             string
+	appsecTimeout         time.Duration
+	appsecMaxBodyBytes    int64
+	captureBudgetBytes    int64
+	appsecMaxConcurrent   int
 )
 
 var rootCmd = &cobra.Command{
@@ -125,6 +130,11 @@ func init() {
 	rootCmd.Flags().StringVar(&geoDataDir, "geo-data-dir", envStringOrDefault("NB_PROXY_GEO_DATA_DIR", "/var/lib/netbird/geolocation"), "Directory for the GeoLite2 MMDB file (auto-downloaded if missing)")
 	rootCmd.Flags().StringVar(&crowdsecAPIURL, "crowdsec-api-url", envStringOrDefault("NB_PROXY_CROWDSEC_API_URL", ""), "CrowdSec LAPI URL for IP reputation checks")
 	rootCmd.Flags().StringVar(&crowdsecAPIKey, "crowdsec-api-key", envStringOrDefault("NB_PROXY_CROWDSEC_API_KEY", ""), "CrowdSec bouncer API key")
+	rootCmd.Flags().StringVar(&appsecURL, "crowdsec-appsec-url", envStringOrDefault("NB_PROXY_CROWDSEC_APPSEC_URL", ""), "CrowdSec AppSec (WAF) endpoint for HTTP request inspection, e.g. http://127.0.0.1:7422/ (reuses the bouncer API key)")
+	rootCmd.Flags().DurationVar(&appsecTimeout, "crowdsec-appsec-timeout", envDurationOrDefault("NB_PROXY_CROWDSEC_APPSEC_TIMEOUT", 0), "Timeout for a single AppSec inspection call (0 = 200ms)")
+	rootCmd.Flags().IntVar(&appsecMaxConcurrent, "crowdsec-appsec-max-concurrent", int(envInt64OrDefault("NB_PROXY_CROWDSEC_APPSEC_MAX_CONCURRENT", 0)), "Cap on AppSec inspections in flight; further requests are denied in enforce mode rather than queued (0 = 256, negative = no cap)")
+	rootCmd.Flags().Int64Var(&captureBudgetBytes, "capture-budget-bytes", envInt64OrDefault("NB_PROXY_CAPTURE_BUDGET_BYTES", 0), "Total in-flight request-body buffering across the proxy, shared by AppSec inspection and agent-network capture (0 = 256MiB)")
+	rootCmd.Flags().Int64Var(&appsecMaxBodyBytes, "crowdsec-appsec-max-body-bytes", envInt64OrDefault("NB_PROXY_CROWDSEC_APPSEC_MAX_BODY_BYTES", 0), "Cap on the request body mirrored to AppSec (0 = 64KiB, negative = headers and URI only)")
 }
 
 // Execute runs the root command.
@@ -218,47 +228,59 @@ func runServer(cmd *cobra.Command, args []string) error {
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGTERM, syscall.SIGINT)
 	defer stop()
 
-	srv := proxy.New(ctx, proxy.Config{
-		ListenAddr:               addr,
-		Logger:                   logger,
-		Version:                  Version,
-		ManagementAddress:        mgmtAddr,
-		ProxyURL:                 proxyDomain,
-		ProxyToken:               proxyToken,
-		CertificateDirectory:     certDir,
-		CertificateFile:          certFile,
-		CertificateKeyFile:       certKeyFile,
-		GenerateACMECertificates: acmeCerts,
-		ACMEChallengeAddress:     acmeAddr,
-		ACMEDirectory:            acmeDir,
-		ACMEEABKID:               acmeEABKID,
-		ACMEEABHMACKey:           acmeEABHMACKey,
-		ACMEChallengeType:        acmeChallengeType,
-		DebugEndpointEnabled:     debugEndpoint,
-		DebugEndpointAddress:     debugEndpointAddr,
-		HealthAddr:               healthAddr,
-		ForwardedProto:           forwardedProto,
-		TrustedProxies:           parsedTrustedProxies,
-		CertLockMethod:           nbacme.CertLockMethod(certLockMethod),
-		WildcardCertDir:          wildcardCertDir,
-		WireguardPort:            wgPort,
-		Performance:              perf,
-		ProxyProtocol:            proxyProtocol,
-		PreSharedKey:             preSharedKey,
-		SupportsCustomPorts:      supportsCustomPorts,
-		RequireSubdomain:         requireSubdomain,
-		Private:                  private,
-		MaxDialTimeout:           maxDialTimeout,
-		MaxSessionIdleTimeout:    maxSessionIdleTimeout,
-		MappingBatchWatchdog:     envDurationOrDefault("NB_PROXY_MAPPING_BATCH_WATCHDOG", 0),
-		GeoDataDir:               geoDataDir,
-		CrowdSecAPIURL:           crowdsecAPIURL,
-		CrowdSecAPIKey:           crowdsecAPIKey,
-	})
+	srv := proxy.New(ctx, serverConfig(logger, proxyToken, parsedTrustedProxies, perf))
 
 	return srv.ListenAndServe(ctx, addr)
 }
 
+// serverConfig maps the parsed flags and environment onto the proxy config.
+// Kept separate from runServer so registering a new flag does not grow the
+// startup path.
+func serverConfig(logger *log.Logger, proxyToken string, trustedProxyList *trustedproxy.List, perf embed.Performance) proxy.Config {
+	return proxy.Config{
+		ListenAddr:                   addr,
+		Logger:                       logger,
+		Version:                      Version,
+		ManagementAddress:            mgmtAddr,
+		ProxyURL:                     proxyDomain,
+		ProxyToken:                   proxyToken,
+		CertificateDirectory:         certDir,
+		CertificateFile:              certFile,
+		CertificateKeyFile:           certKeyFile,
+		GenerateACMECertificates:     acmeCerts,
+		ACMEChallengeAddress:         acmeAddr,
+		ACMEDirectory:                acmeDir,
+		ACMEEABKID:                   acmeEABKID,
+		ACMEEABHMACKey:               acmeEABHMACKey,
+		ACMEChallengeType:            acmeChallengeType,
+		DebugEndpointEnabled:         debugEndpoint,
+		DebugEndpointAddress:         debugEndpointAddr,
+		HealthAddr:                   healthAddr,
+		ForwardedProto:               forwardedProto,
+		TrustedProxies:               trustedProxyList,
+		CertLockMethod:               nbacme.CertLockMethod(certLockMethod),
+		WildcardCertDir:              wildcardCertDir,
+		WireguardPort:                wgPort,
+		Performance:                  perf,
+		ProxyProtocol:                proxyProtocol,
+		PreSharedKey:                 preSharedKey,
+		SupportsCustomPorts:          supportsCustomPorts,
+		RequireSubdomain:             requireSubdomain,
+		Private:                      private,
+		MaxDialTimeout:               maxDialTimeout,
+		MaxSessionIdleTimeout:        maxSessionIdleTimeout,
+		MappingBatchWatchdog:         envDurationOrDefault("NB_PROXY_MAPPING_BATCH_WATCHDOG", 0),
+		GeoDataDir:                   geoDataDir,
+		CrowdSecAPIURL:               crowdsecAPIURL,
+		CrowdSecAPIKey:               crowdsecAPIKey,
+		CrowdSecAppSecURL:            appsecURL,
+		CrowdSecAppSecTimeout:        appsecTimeout,
+		CrowdSecAppSecMaxBodyBytes:   appsecMaxBodyBytes,
+		CrowdSecAppSecMaxConcurrent:  appsecMaxConcurrent,
+		MiddlewareCaptureBudgetBytes: captureBudgetBytes,
+	}
+}
+
 func envBoolOrDefault(key string, def bool) bool {
 	v, exists := os.LookupEnv(key)
 	if !exists {
@@ -293,6 +315,19 @@ func envUint16OrDefault(key string, def uint16) uint16 {
 	return uint16(parsed)
 }
 
+func envInt64OrDefault(key string, def int64) int64 {
+	v, exists := os.LookupEnv(key)
+	if !exists {
+		return def
+	}
+	parsed, err := strconv.ParseInt(v, 10, 64)
+	if err != nil {
+		log.Warnf("parse %s=%q: %v, using default %d", key, v, err, def)
+		return def
+	}
+	return parsed
+}
+
 func envDurationOrDefault(key string, def time.Duration) time.Duration {
 	v, exists := os.LookupEnv(key)
 	if !exists {

proxy/internal/appsec/body.go

@@ -0,0 +1,163 @@
+package appsec
+
+import (
+	"bytes"
+	"errors"
+	"io"
+	"mime"
+	"net/http"
+	"net/url"
+	"slices"
+	"strings"
+)
+
+// bufferBody reads up to limit+1 bytes from r.Body and always restores r.Body so
+// the request stays forwardable. oversize reports that the body exceeded limit, in
+// which case the returned prefix must not be used for inspection: the bytes are
+// only read so they can be replayed to the backend.
+func bufferBody(r *http.Request, limit int64) (body []byte, oversize bool, err error) {
+	original := r.Body
+	buf, readErr := io.ReadAll(io.LimitReader(original, limit+1))
+	if readErr != nil && !errors.Is(readErr, io.EOF) {
+		// Restore what was read so a downstream retry sees a consistent stream,
+		// then surface the failure.
+		r.Body = replay(buf, original)
+		return nil, false, readErr
+	}
+
+	if int64(len(buf)) > limit {
+		r.Body = replay(buf, original)
+		return nil, true, nil
+	}
+
+	// The whole body is buffered, so the original is drained and can be closed.
+	// A close error on a drained read-only body does not invalidate the bytes.
+	_ = original.Close()
+	r.Body = io.NopCloser(bytes.NewReader(buf))
+	// Framing is deliberately left as the client sent it. Rewriting a chunked
+	// request to a fixed Content-Length here would be invisible to the client
+	// but not to the rest of the chain: a later body capture with a smaller cap
+	// sees a known length over its cap and skips capture entirely, where an
+	// unknown length would have given it a truncated prefix. Inspecting a
+	// request must not change what any other layer gets to inspect.
+	return buf, false, nil
+}
+
+// replay returns a ReadCloser that yields the already-read prefix followed by
+// the remainder of the original stream, and closes the original.
+func replay(prefix []byte, rest io.ReadCloser) io.ReadCloser {
+	return struct {
+		io.Reader
+		io.Closer
+	}{
+		Reader: io.MultiReader(bytes.NewReader(prefix), rest),
+		Closer: rest,
+	}
+}
+
+// redactedPlaceholder replaces a credential value in the mirrored body. It is
+// inert for rule matching, and its fixed length leaks nothing about the secret.
+const redactedPlaceholder = "redacted"
+
+// redactFormFields returns the body to mirror for a URL-encoded form, with the
+// values of the named fields replaced. The proxy's own password / PIN login
+// form posts to the service path itself, so without this the plaintext
+// credential would reach the Security Engine.
+//
+// Only the credential values are removed, never the whole body: dropping the
+// body outright would let a caller exempt any payload from inspection just by
+// appending a field named "password". Everything else in the form stays
+// inspectable, which is the point.
+//
+// Returns body unchanged when it is not a URL-encoded form or carries none of
+// the fields.
+//
+// Substitution happens on the raw bytes rather than by re-encoding parsed
+// values. Re-encoding would drop pairs that url.ParseQuery rejects, so a
+// payload hidden in a malformed pair alongside a credential-named field would
+// never be inspected while a tolerant backend parser still acted on it. Working
+// byte-wise also avoids reordering keys and normalizing escapes, so the engine
+// sees the same bytes the backend will.
+//
+// Field names match case-sensitively, on purpose: the caller passes the exact
+// names the login handler reads via r.FormValue, and that lookup is itself
+// case-sensitive. A "Password" field is therefore never a credential as far as
+// the proxy is concerned, and redacting it would only blind the WAF to a value
+// the proxy does not own.
+func redactFormFields(contentType string, body []byte, fields []string) []byte {
+	if len(fields) == 0 || len(body) == 0 {
+		return body
+	}
+	media, _, err := mime.ParseMediaType(contentType)
+	if err != nil || media != "application/x-www-form-urlencoded" {
+		return body
+	}
+	return redactURLEncoded(body, fields)
+}
+
+// redactURLEncoded replaces the values of the named keys in a URL-encoded
+// key/value sequence, the shared syntax of a query string and a form body.
+func redactURLEncoded(raw []byte, fields []string) []byte {
+	// Split on "&" only, matching how Go's form parser delimits pairs.
+	segments := bytes.Split(raw, []byte("&"))
+	redacted := false
+	for i, segment := range segments {
+		rawKey, _, hasValue := bytes.Cut(segment, []byte("="))
+		if !hasValue {
+			continue
+		}
+		// Compare the decoded name, so an escaped spelling of the field
+		// ("pass%77ord") is redacted too: the reader decodes before looking it
+		// up. A key that fails to decode never reaches that reader either,
+		// since the parser drops the pair.
+		name, err := url.QueryUnescape(string(rawKey))
+		if err != nil || !slices.Contains(fields, name) {
+			continue
+		}
+		// Keep the key bytes as sent and replace only the value. Assigning a
+		// fresh slice leaves raw untouched, which matters: the caller restored
+		// the request body from the same buffer.
+		segments[i] = []byte(string(rawKey) + "=" + redactedPlaceholder)
+		redacted = true
+	}
+	if !redacted {
+		return raw
+	}
+	return bytes.Join(segments, []byte("&"))
+}
+
+// redactQuery replaces the values of the named query parameters in a raw query
+// string, leaving every other byte as sent.
+func redactQuery(rawQuery string, params []string) string {
+	if len(params) == 0 || rawQuery == "" {
+		return rawQuery
+	}
+	return string(redactURLEncoded([]byte(rawQuery), params))
+}
+
+// redactCookieHeader replaces the values of the named cookies in a Cookie
+// header, keeping the others intact: cookies are a zone WAF rules match on, so
+// dropping the whole header would cost real coverage.
+func redactCookieHeader(value string, names []string) string {
+	if len(names) == 0 || value == "" {
+		return value
+	}
+	parts := strings.Split(value, ";")
+	redacted := false
+	for i, part := range parts {
+		name, _, hasValue := strings.Cut(part, "=")
+		if !hasValue {
+			continue
+		}
+		// Cookie names are case-sensitive and are not percent-decoded.
+		if !slices.Contains(names, strings.TrimSpace(name)) {
+			continue
+		}
+		parts[i] = name + "=" + redactedPlaceholder
+		redacted = true
+	}
+	if !redacted {
+		return value
+	}
+	return strings.Join(parts, ";")
+}

proxy/internal/appsec/client.go

@@ -0,0 +1,571 @@
+// Package appsec implements the CrowdSec AppSec (WAF) side of the remediation
+// component protocol: each inspected HTTP request is mirrored to the Security
+// Engine's AppSec endpoint, which replies with an allow / ban / captcha verdict
+// for that request.
+//
+// This is a separate endpoint from the LAPI decision stream used by the
+// crowdsec package: LAPI answers "is this IP known bad", AppSec answers "is
+// this request an attack". The two are configured and enabled independently.
+package appsec
+
+import (
+	"bytes"
+	"context"
+	"encoding/json"
+	"errors"
+	"fmt"
+	"io"
+	"net/http"
+	"net/netip"
+	"net/url"
+	"strings"
+	"sync"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/proxy/internal/netutil"
+	"github.com/netbirdio/netbird/proxy/internal/restrict"
+)
+
+// Header names the AppSec component reads off the mirrored request. IP, URI and
+// Verb are mandatory: the engine answers 500 when any of them is missing.
+const (
+	headerAPIKey        = "X-Crowdsec-Appsec-Api-Key" //nolint:gosec // G101: a header name, not a credential
+	headerIP            = "X-Crowdsec-Appsec-Ip"
+	headerURI           = "X-Crowdsec-Appsec-Uri"
+	headerVerb          = "X-Crowdsec-Appsec-Verb"
+	headerHost          = "X-Crowdsec-Appsec-Host"
+	headerUserAgent     = "X-Crowdsec-Appsec-User-Agent"
+	headerHTTPVersion   = "X-Crowdsec-Appsec-Http-Version"
+	headerTransactionID = "X-Crowdsec-Appsec-Transaction-Id"
+)
+
+// headerPrefix covers every protocol header. Any client-supplied header in this
+// namespace is dropped before forwarding so a caller cannot influence the
+// engine's view of its own address, or replay an API key.
+const headerPrefix = "X-Crowdsec-Appsec-"
+
+// Remediation actions the engine can return.
+const (
+	actionAllow   = "allow"
+	actionBan     = "ban"
+	actionCaptcha = "captcha"
+)
+
+const (
+	// DefaultTimeout matches the 200ms budget CrowdSec's remediation component
+	// spec sets for the blocking AppSec call.
+	DefaultTimeout = 200 * time.Millisecond
+	// MinTimeout and MaxTimeout bound the configured inspection timeout.
+	// Inspection is synchronous, so the upper bound is what keeps a
+	// mis-set value from parking every request to an inspected service on a
+	// slow engine; the lower bound keeps the call from timing out before the
+	// engine can realistically answer. Mirrors the per-middleware bounds the
+	// proxy already applies to in-path calls.
+	MinTimeout = 10 * time.Millisecond
+	MaxTimeout = 5 * time.Second
+	// DefaultMaxBodyBytes caps the request body mirrored to the engine.
+	// Requests with a larger body are inspected on headers and URI only.
+	DefaultMaxBodyBytes int64 = 64 << 10
+	// DefaultMaxConcurrent bounds inspections in flight toward the engine. The
+	// point is to fail fast instead of parking a goroutine per request for the
+	// whole timeout once the engine is saturated: a slow engine otherwise turns
+	// a traffic burst into a pile of waiters that all time out anyway. Sized so
+	// a healthy engine (single-digit milliseconds per call) never reaches it.
+	DefaultMaxConcurrent = 256
+	// MaxConcurrentLimit is the ceiling for that bound.
+	MaxConcurrentLimit = 4096
+	// MaxBodyBytesLimit is the ceiling for that cap. A single request can hold
+	// this much in memory; the shared Budget is what bounds the total across
+	// concurrent requests. Matches the proxy-wide body-capture ceiling.
+	MaxBodyBytesLimit int64 = 8 << 20
+	// maxResponseBytes bounds how much of a verdict response is read. The
+	// engine answers with a two-field JSON object, so anything beyond this is
+	// not a response we can act on.
+	maxResponseBytes int64 = 4 << 10
+)
+
+// Reasons the request body was not mirrored. Reported so an access-log reader
+// can distinguish "inspected and clean" from "never inspected", and so an
+// oversize opt-out is visible rather than silent.
+const (
+	BypassOversize = "oversize"
+	BypassUpgrade  = "upgrade"
+	BypassDisabled = "disabled"
+	BypassBudget   = "budget_exhausted"
+)
+
+// ErrUnavailable reports that the engine could not produce a verdict: the call
+// failed, timed out, or the engine rejected it (401 bad key, 500 malformed).
+// Distinguished from a block verdict so the caller can apply the per-service
+// mode: enforce fails closed, observe allows.
+var ErrUnavailable = errors.New("appsec engine unavailable")
+
+// Config configures a Client.
+type Config struct {
+	// URL is the AppSec endpoint, e.g. http://127.0.0.1:7422/.
+	URL string
+	// APIKey is the CrowdSec bouncer API key. The AppSec component validates it
+	// against LAPI, so the same key used for the decision stream works here.
+	APIKey string
+	// Timeout bounds a single inspection call. Zero means DefaultTimeout.
+	Timeout time.Duration
+	// MaxBodyBytes caps the mirrored request body. Zero means
+	// DefaultMaxBodyBytes; negative disables body forwarding entirely.
+	MaxBodyBytes int64
+	// MaxConcurrent bounds inspections in flight toward the engine. Zero means
+	// DefaultMaxConcurrent; negative disables the bound.
+	MaxConcurrent int
+	// Budget bounds the total body buffering in flight across all inspected
+	// requests. Nil disables that ceiling, which leaves the worst case at
+	// MaxBodyBytes times the concurrent request count; callers serving
+	// untrusted traffic should share the proxy-wide capture budget here.
+	Budget Budget
+	Logger *log.Entry
+}
+
+// Budget is the shared allowance for in-flight body buffering. Acquire reports
+// whether n bytes could be reserved; every successful Acquire is matched by a
+// Release of the same n. Satisfied by the proxy's capture budget, so AppSec and
+// the middleware body tap draw down one pool rather than two independent ones.
+type Budget interface {
+	Acquire(n int64) bool
+	Release(n int64)
+}
+
+// Client mirrors HTTP requests to a CrowdSec AppSec endpoint. It holds no
+// per-service state and is safe for concurrent use.
+type Client struct {
+	url          string
+	apiKey       string
+	maxBodyBytes int64
+	// sem bounds in-flight inspections. Nil when the bound is disabled.
+	sem    chan struct{}
+	budget Budget
+	http   *http.Client
+	logger *log.Entry
+}
+
+// New validates the config and returns a Client. The endpoint is not contacted
+// here: the engine may come up after the proxy.
+func New(cfg Config) (*Client, error) {
+	if cfg.URL == "" {
+		return nil, errors.New("appsec url is empty")
+	}
+	if cfg.APIKey == "" {
+		return nil, errors.New("appsec api key is empty")
+	}
+	parsed, err := url.Parse(cfg.URL)
+	if err != nil {
+		return nil, fmt.Errorf("parse appsec url: %w", err)
+	}
+	if parsed.Scheme != "http" && parsed.Scheme != "https" {
+		return nil, fmt.Errorf("appsec url scheme %q is not http(s)", parsed.Scheme)
+	}
+	if parsed.Host == "" {
+		return nil, errors.New("appsec url has no host")
+	}
+
+	logger := cfg.Logger
+	if logger == nil {
+		logger = log.NewEntry(log.StandardLogger())
+	}
+
+	timeout := cfg.Timeout
+	switch {
+	case timeout <= 0:
+		timeout = DefaultTimeout
+	case timeout < MinTimeout:
+		logger.Warnf("appsec timeout %s is below the minimum, using %s", timeout, MinTimeout)
+		timeout = MinTimeout
+	case timeout > MaxTimeout:
+		logger.Warnf("appsec timeout %s exceeds the maximum, using %s", timeout, MaxTimeout)
+		timeout = MaxTimeout
+	}
+
+	// A negative cap is meaningful: forward no body at all.
+	maxBody := cfg.MaxBodyBytes
+	switch {
+	case maxBody == 0:
+		maxBody = DefaultMaxBodyBytes
+	case maxBody > MaxBodyBytesLimit:
+		logger.Warnf("appsec max body %d exceeds the maximum, using %d", maxBody, MaxBodyBytesLimit)
+		maxBody = MaxBodyBytesLimit
+	}
+
+	maxConcurrent := cfg.MaxConcurrent
+	switch {
+	case maxConcurrent == 0:
+		maxConcurrent = DefaultMaxConcurrent
+	case maxConcurrent > MaxConcurrentLimit:
+		logger.Warnf("appsec max concurrent %d exceeds the maximum, using %d", maxConcurrent, MaxConcurrentLimit)
+		maxConcurrent = MaxConcurrentLimit
+	}
+	var sem chan struct{}
+	if maxConcurrent > 0 {
+		sem = make(chan struct{}, maxConcurrent)
+	}
+
+	return &Client{
+		url:          cfg.URL,
+		apiKey:       cfg.APIKey,
+		maxBodyBytes: maxBody,
+		sem:          sem,
+		budget:       cfg.Budget,
+		logger:       logger,
+		http: &http.Client{
+			Timeout: timeout,
+			Transport: &http.Transport{
+				MaxIdleConns:        100,
+				MaxIdleConnsPerHost: 32,
+				IdleConnTimeout:     90 * time.Second,
+			},
+		},
+	}, nil
+}
+
+// Request is one inspection request.
+type Request struct {
+	// HTTP is the in-flight client request. Inspect buffers and restores its
+	// body, so the request stays forwardable afterwards.
+	HTTP *http.Request
+	// ClientIP is the resolved client address (after trusted-proxy handling).
+	ClientIP netip.Addr
+	// TransactionID correlates the engine's alert with the proxy's access log
+	// entry. Empty lets the engine generate its own UUID.
+	TransactionID string
+	// RedactBodyFields lists form fields whose values are replaced before the
+	// body is mirrored. Used to keep credentials submitted to the proxy's own
+	// login form out of the engine while still inspecting the rest.
+	RedactBodyFields []string
+	// RedactHeaders, RedactCookies and RedactQueryParams name the credentials
+	// the proxy already withholds from backends: the header-auth values, its
+	// session cookie, and the OIDC session token. The engine logs and alerts on
+	// what it inspects, so mirroring them there would reintroduce the leak the
+	// upstream strippers exist to prevent. Only the values are replaced, so the
+	// surrounding headers, cookies and query stay inspectable.
+	RedactHeaders     []string
+	RedactCookies     []string
+	RedactQueryParams []string
+}
+
+// Result is the outcome of an inspection.
+type Result struct {
+	Verdict restrict.Verdict
+	// BodyBypass names why the request body was not mirrored, empty when it
+	// was (or when the request had none). The engine still saw the headers and
+	// URI, so this is a coverage note, not a failure.
+	BodyBypass string
+	// Release returns the buffered body's budget reservation. Never nil, so it
+	// is always safe to defer. It must run only once the request has been
+	// served, not when Inspect returns: the buffer stays alive as r.Body for
+	// the backend to read, so releasing earlier would let the budget admit
+	// buffering that is still resident.
+	Release func()
+}
+
+// noopRelease is the Release for inspections that reserved no budget.
+func noopRelease() {}
+
+// Inspect mirrors r to the AppSec engine and returns its verdict. A nil error
+// with restrict.Allow means the request passed. On failure it returns
+// DenyAppSecUnavailable wrapped with ErrUnavailable; the caller decides whether
+// that blocks, based on the per-service mode.
+func (c *Client) Inspect(ctx context.Context, req Request) (Result, error) {
+	if c == nil {
+		return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease}, ErrUnavailable
+	}
+	if req.HTTP == nil {
+		return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease}, fmt.Errorf("%w: nil request", ErrUnavailable)
+	}
+
+	// release is carried out to the caller rather than deferred here: the
+	// buffered body outlives this call as r.Body.
+	if !c.acquireSlot() {
+		// Deny rather than wave through: a flood must not be a way to switch
+		// inspection off. Enforce blocks, observe logs and allows, exactly as
+		// for an unreachable engine.
+		return Result{Verdict: restrict.DenyAppSecUnavailable, Release: noopRelease},
+			fmt.Errorf("%w: %d inspections already in flight", ErrUnavailable, cap(c.sem))
+	}
+	defer c.releaseSlot()
+
+	body, bypass, release, err := c.readBody(req)
+	if err != nil {
+		return Result{Verdict: restrict.DenyAppSecUnavailable, Release: release}, fmt.Errorf("%w: read body: %w", ErrUnavailable, err)
+	}
+
+	outbound, err := c.buildRequest(ctx, req, body)
+	if err != nil {
+		return Result{Verdict: restrict.DenyAppSecUnavailable, BodyBypass: bypass, Release: release}, fmt.Errorf("%w: %w", ErrUnavailable, err)
+	}
+
+	resp, err := c.http.Do(outbound)
+	if err != nil {
+		return Result{Verdict: restrict.DenyAppSecUnavailable, BodyBypass: bypass, Release: release}, fmt.Errorf("%w: %w", ErrUnavailable, err)
+	}
+	defer func() {
+		// Drain before closing. net/http only returns a connection to the idle
+		// pool once its body is read to EOF; closing with bytes outstanding
+		// discards it. Every verdict carries a JSON body, so skipping this
+		// would cost a fresh handshake per inspected request, inside the
+		// timeout budget.
+		if _, err := io.Copy(io.Discard, io.LimitReader(resp.Body, maxResponseBytes)); err != nil {
+			c.logger.Tracef("drain appsec response body: %v", err)
+		}
+		if err := resp.Body.Close(); err != nil {
+			c.logger.Tracef("close appsec response body: %v", err)
+		}
+	}()
+
+	verdict, err := c.verdict(resp)
+	return Result{Verdict: verdict, BodyBypass: bypass, Release: release}, err
+}
+
+// acquireSlot takes an in-flight slot without blocking, reporting false when
+// the engine is already at capacity.
+func (c *Client) acquireSlot() bool {
+	if c.sem == nil {
+		return true
+	}
+	select {
+	case c.sem <- struct{}{}:
+		return true
+	default:
+		return false
+	}
+}
+
+// releaseSlot returns the slot. Scoped to the engine call, not the request: the
+// buffered body outlives the call but the engine's attention does not.
+func (c *Client) releaseSlot() {
+	if c.sem == nil {
+		return
+	}
+	select {
+	case <-c.sem:
+	default:
+	}
+}
+
+// readBody buffers the body so it can be mirrored, always restoring it on the
+// original request. Returns nil when there is no body to forward: no body at
+// all, an upgrade request, or a body over the cap. A login form is forwarded
+// with its credential values redacted rather than suppressed.
+// release is never nil; the caller invokes it once the request has been served.
+func (c *Client) readBody(req Request) (body []byte, bypass string, release func(), err error) {
+	r := req.HTTP
+	if r.Body == nil || r.Body == http.NoBody {
+		return nil, "", noopRelease, nil
+	}
+	if c.maxBodyBytes < 0 {
+		return nil, BypassDisabled, noopRelease, nil
+	}
+	// A genuine upgrade request carries no body to inspect (net/http hands us
+	// http.NoBody, caught above); the hijacked stream is reached through
+	// Hijacker, never r.Body. The test has to be the forwarder's own, because a
+	// looser one would skip inspection for requests the forwarder still
+	// delivers to the backend with their body intact.
+	if netutil.IsUpgradeRequest(r.Header) {
+		return nil, BypassUpgrade, noopRelease, nil
+	}
+	// A Content-Length over the cap is known to be too large before reading.
+	if r.ContentLength > c.maxBodyBytes {
+		return nil, BypassOversize, noopRelease, nil
+	}
+
+	// Reserve the whole cap rather than the eventual length: the reservation
+	// has to be made before the body is read, and until then the only bound
+	// known is the cap. Skipping inspection when the pool is drained keeps a
+	// burst of large bodies from being an out-of-memory lever; the bypass is
+	// recorded so the gap in coverage is visible.
+	release = noopRelease
+	if c.budget != nil {
+		if !c.budget.Acquire(c.maxBodyBytes) {
+			c.logger.Debugf("appsec buffer budget exhausted, inspecting headers and URI only")
+			return nil, BypassBudget, noopRelease, nil
+		}
+		var once sync.Once
+		release = func() { once.Do(func() { c.budget.Release(c.maxBodyBytes) }) }
+	}
+
+	buffered, oversize, err := bufferBody(r, c.maxBodyBytes)
+	if err != nil {
+		// bufferBody restored r.Body from the bytes it did read, so the
+		// reservation stays held until the caller releases it.
+		return nil, "", release, err
+	}
+	// An oversize body was only partially read: a truncated prefix changes the
+	// engine's verdict in both directions, so inspect headers and URI only.
+	if oversize {
+		return nil, BypassOversize, release, nil
+	}
+	return redactFormFields(r.Header.Get("Content-Type"), buffered, req.RedactBodyFields), "", release, nil
+}
+
+// buildRequest assembles the mirrored request. Per the protocol it is a GET
+// when there is no body and a POST otherwise; bytes.Reader gives the outbound
+// request an accurate Content-Length, which the engine relies on to read the
+// body at all.
+func (c *Client) buildRequest(ctx context.Context, req Request, body []byte) (*http.Request, error) {
+	method := http.MethodGet
+	var payload io.Reader
+	if len(body) > 0 {
+		method = http.MethodPost
+		payload = bytes.NewReader(body)
+	}
+
+	outbound, err := http.NewRequestWithContext(ctx, method, c.url, payload)
+	if err != nil {
+		return nil, fmt.Errorf("build appsec request: %w", err)
+	}
+
+	r := req.HTTP
+	copyInspectableHeaders(outbound.Header, r.Header)
+	redactSecrets(outbound.Header, req)
+
+	outbound.Header.Set(headerAPIKey, c.apiKey)
+	outbound.Header.Set(headerIP, req.ClientIP.Unmap().String())
+	outbound.Header.Set(headerURI, mirroredURI(r.URL, req.RedactQueryParams))
+	outbound.Header.Set(headerVerb, r.Method)
+	outbound.Header.Set(headerHost, r.Host)
+	if ua := r.UserAgent(); ua != "" {
+		outbound.Header.Set(headerUserAgent, ua)
+	}
+	outbound.Header.Set(headerHTTPVersion, httpVersion(r))
+	if req.TransactionID != "" {
+		outbound.Header.Set(headerTransactionID, req.TransactionID)
+	}
+	return outbound, nil
+}
+
+// verdict maps the engine's response to a restrict.Verdict. 200 is a pass and
+// 401/500 are engine-side failures; every other status carries a remediation in
+// the body. The blocked status code is operator-configurable
+// (blocked_http_code), so the action field decides, not the status.
+func (c *Client) verdict(resp *http.Response) (restrict.Verdict, error) {
+	switch resp.StatusCode {
+	case http.StatusUnauthorized:
+		return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: rejected api key", ErrUnavailable)
+	case http.StatusInternalServerError:
+		return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: engine error", ErrUnavailable)
+	}
+
+	// Every status, 200 included, has to carry a decodable remediation. Taking a
+	// bare 200 as a pass would mean a URL pointing at anything that answers 200
+	// (a health endpoint, a load balancer's default page) silently allows every
+	// request while the service reports itself as enforcing.
+
+	var decoded struct {
+		Action string `json:"action"`
+	}
+	if err := json.NewDecoder(io.LimitReader(resp.Body, maxResponseBytes)).Decode(&decoded); err != nil {
+		// Every remediation carries a decodable action, so a response without
+		// one is not a verdict: most often the URL points at something that is
+		// not the AppSec endpoint, which answers 404 with HTML. Reported as
+		// unavailable rather than a ban so the access log names the real fault
+		// instead of sending an operator hunting for a rule that never fired.
+		// Enforce still blocks either way; only the recorded reason differs.
+		return restrict.DenyAppSecUnavailable, fmt.Errorf("%w: undecodable response (status %d): %w", ErrUnavailable, resp.StatusCode, err)
+	}
+
+	switch decoded.Action {
+	case actionAllow:
+		return restrict.Allow, nil
+	case actionCaptcha:
+		return restrict.DenyAppSecCaptcha, nil
+	case actionBan:
+		return restrict.DenyAppSecBan, nil
+	case "":
+		// Decodable JSON without a remediation is not a verdict either: the
+		// endpoint answered, but not as the engine. Same reasoning as an
+		// undecodable body, and the same reason to point at configuration.
+		return restrict.DenyAppSecUnavailable,
+			fmt.Errorf("%w: response carried no remediation (status %d)", ErrUnavailable, resp.StatusCode)
+	default:
+		// A remediation we do not implement still means the engine flagged the
+		// request, so deny.
+		c.logger.Debugf("unknown appsec action %q (status %d), treating as ban", decoded.Action, resp.StatusCode)
+		return restrict.DenyAppSecBan, nil
+	}
+}
+
+// copyInspectableHeaders copies the client's headers, which are what the WAF
+// rules actually match on, dropping hop-by-hop headers that describe the
+// proxy-to-engine connection rather than the client request, and any header in
+// the AppSec protocol namespace.
+func copyInspectableHeaders(dst, src http.Header) {
+	for name, values := range src {
+		if hopByHopHeaders[http.CanonicalHeaderKey(name)] {
+			continue
+		}
+		if strings.HasPrefix(http.CanonicalHeaderKey(name), headerPrefix) {
+			continue
+		}
+		dst[http.CanonicalHeaderKey(name)] = append([]string(nil), values...)
+	}
+	// Content-Length describes the mirrored payload, not the client's: net/http
+	// sets it from the body we actually attach. Content-Type is kept either way
+	// so rules matching on it still fire when the body was not forwarded.
+	dst.Del("Content-Length")
+}
+
+// redactSecrets replaces the credential values the proxy withholds from
+// backends, so the mirrored copy does not carry them either.
+func redactSecrets(dst http.Header, req Request) {
+	for _, name := range req.RedactHeaders {
+		// Presence, not Get: a header whose first value is empty still carries
+		// its later values to the engine, while the upstream strip deletes the
+		// name outright. Set collapses every value into the placeholder.
+		if len(dst.Values(name)) > 0 {
+			dst.Set(name, redactedPlaceholder)
+		}
+	}
+	// Every Cookie line, not just the first: a client may send several, and Get
+	// would leave the session cookie in any later one mirrored in the clear.
+	if cookies := dst.Values("Cookie"); len(cookies) > 0 {
+		redacted := make([]string, len(cookies))
+		for i, cookie := range cookies {
+			redacted[i] = redactCookieHeader(cookie, req.RedactCookies)
+		}
+		dst["Cookie"] = redacted
+	}
+}
+
+// mirroredURI renders the request target for the URI header, with the named
+// query parameter values replaced.
+func mirroredURI(u *url.URL, redactParams []string) string {
+	uri := u.RequestURI()
+	if u.RawQuery == "" || len(redactParams) == 0 {
+		return uri
+	}
+	redacted := redactQuery(u.RawQuery, redactParams)
+	if redacted == u.RawQuery {
+		return uri
+	}
+	// RequestURI is path + "?" + RawQuery; swap only the query part so the
+	// path keeps its original encoding.
+	return strings.TrimSuffix(uri, u.RawQuery) + redacted
+}
+
+var hopByHopHeaders = map[string]bool{
+	"Connection":          true,
+	"Keep-Alive":          true,
+	"Proxy-Authenticate":  true,
+	"Proxy-Authorization": true,
+	"Proxy-Connection":    true,
+	"Te":                  true,
+	"Trailer":             true,
+	"Transfer-Encoding":   true,
+	"Upgrade":             true,
+}
+
+// httpVersion renders the two-digit form the engine parses ("11", "20").
+func httpVersion(r *http.Request) string {
+	major, minor := r.ProtoMajor, r.ProtoMinor
+	if major < 0 || major > 9 || minor < 0 || minor > 9 {
+		return ""
+	}
+	return fmt.Sprintf("%d%d", major, minor)
+}

proxy/internal/auth/appsec_test.go

@@ -0,0 +1,306 @@
+package auth
+
+import (
+	"crypto/ed25519"
+	"encoding/base64"
+	"io"
+	"net/http"
+	"net/http/httptest"
+	"strings"
+	"sync"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/proxy/internal/appsec"
+	"github.com/netbirdio/netbird/proxy/internal/proxy"
+	"github.com/netbirdio/netbird/proxy/internal/restrict"
+	"github.com/netbirdio/netbird/proxy/internal/types"
+)
+
+// appsecEngine is a stub AppSec component returning a fixed remediation.
+func appsecEngine(t *testing.T, status int, body string) *httptest.Server {
+	t.Helper()
+	srv := httptest.NewServer(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		w.WriteHeader(status)
+		if body != "" {
+			_, _ = w.Write([]byte(body))
+		}
+	}))
+	t.Cleanup(srv.Close)
+	return srv
+}
+
+// serveWithAppSec runs a request through the middleware for a domain configured
+// with the given AppSec mode, returning the response and the captured metadata.
+func serveWithAppSec(t *testing.T, mode restrict.AppSecMode, client *appsec.Client, r *http.Request) (*httptest.ResponseRecorder, map[string]string, bool) {
+	t.Helper()
+
+	mw := NewMiddleware(log.StandardLogger(), nil, nil)
+	mw.SetAppSec(client)
+	require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
+		AccountID:  types.AccountID("acct-1"),
+		ServiceID:  types.ServiceID("svc-1"),
+		AppSecMode: mode,
+	}))
+
+	reached := false
+	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
+		reached = true
+		w.WriteHeader(http.StatusOK)
+	}))
+
+	cd := proxy.NewCapturedData("req-1")
+	r = r.WithContext(proxy.WithCapturedData(r.Context(), cd))
+	rec := httptest.NewRecorder()
+	handler.ServeHTTP(rec, r)
+
+	return rec, cd.GetMetadata(), reached
+}
+
+func appsecRequest() *http.Request {
+	r := httptest.NewRequest(http.MethodGet, "http://svc.example.com/?x=/etc/passwd", nil)
+	r.Host = "svc.example.com"
+	r.RemoteAddr = "203.0.113.7:44444"
+	return r
+}
+
+func TestCheckAppSec_EnforceBlocksBannedRequest(t *testing.T) {
+	srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban","http_status":403}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
+
+	assert.Equal(t, http.StatusForbidden, rec.Code)
+	assert.False(t, reached, "a banned request must not reach the backend")
+	assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
+	assert.NotContains(t, meta, "appsec_mode", "enforce is the default, only observe is annotated")
+}
+
+func TestCheckAppSec_ObserveAllowsAndRecordsVerdict(t *testing.T) {
+	srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban","http_status":403}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecObserve, client, appsecRequest())
+
+	assert.Equal(t, http.StatusOK, rec.Code)
+	assert.True(t, reached, "observe mode must not block")
+	assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
+	assert.Equal(t, "observe", meta["appsec_mode"])
+}
+
+func TestCheckAppSec_AllowedRequestPasses(t *testing.T) {
+	srv := appsecEngine(t, http.StatusOK, `{"action":"allow","http_status":200}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
+
+	assert.Equal(t, http.StatusOK, rec.Code)
+	assert.True(t, reached)
+	assert.NotContains(t, meta, "appsec_verdict", "a clean request records no verdict")
+}
+
+func TestCheckAppSec_OffSkipsInspection(t *testing.T) {
+	// An engine that would ban everything; the mode must keep us away from it.
+	srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecOff, client, appsecRequest())
+
+	assert.Equal(t, http.StatusOK, rec.Code)
+	assert.True(t, reached)
+	assert.Empty(t, meta)
+}
+
+func TestCheckAppSec_EnforceFailsClosedWithoutClient(t *testing.T) {
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, nil, appsecRequest())
+
+	assert.Equal(t, http.StatusForbidden, rec.Code,
+		"enforce with no configured endpoint must deny rather than pass traffic uninspected")
+	assert.False(t, reached)
+	assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
+}
+
+func TestCheckAppSec_ObserveAllowsWithoutClient(t *testing.T) {
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecObserve, nil, appsecRequest())
+
+	assert.Equal(t, http.StatusOK, rec.Code)
+	assert.True(t, reached)
+	assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
+	assert.Equal(t, "observe", meta["appsec_mode"])
+}
+
+func TestCheckAppSec_EnforceFailsClosedWhenEngineUnreachable(t *testing.T) {
+	client, err := appsec.New(appsec.Config{URL: "http://127.0.0.1:1/", APIKey: "k"})
+	require.NoError(t, err)
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, appsecRequest())
+
+	assert.Equal(t, http.StatusForbidden, rec.Code)
+	assert.False(t, reached)
+	assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
+}
+
+func TestCheckAppSec_InspectsOverlayTraffic(t *testing.T) {
+	srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	// Requests arriving over the WireGuard overlay skip the geo and IP-reputation
+	// checks, but request content is just as inspectable.
+	r := appsecRequest()
+	r = r.WithContext(types.WithOverlayOrigin(r.Context()))
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
+
+	assert.Equal(t, http.StatusForbidden, rec.Code, "overlay traffic must still be inspected")
+	assert.False(t, reached)
+	assert.Equal(t, "appsec_ban", meta["appsec_verdict"])
+}
+
+func TestCheckAppSec_UnresolvableClientIPFailsClosed(t *testing.T) {
+	srv := appsecEngine(t, http.StatusOK, `{"action":"allow"}`)
+	client, err := appsec.New(appsec.Config{URL: srv.URL, APIKey: "k"})
+	require.NoError(t, err)
+
+	r := appsecRequest()
+	r.RemoteAddr = "not-an-address"
+
+	rec, meta, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
+
+	assert.Equal(t, http.StatusForbidden, rec.Code,
+		"the engine requires a client address; a request we cannot attribute must not pass")
+	assert.False(t, reached)
+	assert.Equal(t, "appsec_unavailable", meta["appsec_verdict"])
+}
+
+// The redaction sets are resolved from the domain's schemes at registration, so
+// what AppSec withholds cannot drift from what those schemes actually accept.
+func TestAddDomain_ResolvesRedactionSetsFromSchemes(t *testing.T) {
+	mw := NewMiddleware(log.StandardLogger(), nil, nil)
+	require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
+		Schemes: []Scheme{
+			NewPassword(nil, "svc-1", "acct-1"),
+			NewHeader(nil, "svc-1", "acct-1", "X-Api-Key"),
+		},
+		SessionPublicKey:  base64.StdEncoding.EncodeToString(make([]byte, ed25519.PublicKeySize)),
+		SessionExpiration: time.Hour,
+		AppSecMode:        restrict.AppSecEnforce,
+	}))
+
+	mw.domainsMux.RLock()
+	config := mw.domains["svc.example.com"]
+	mw.domainsMux.RUnlock()
+
+	assert.Equal(t, []string{"password"}, config.redactBodyFields)
+	assert.Equal(t, []string{"X-Api-Key"}, config.redactHeaders)
+	// r.FormValue merges the query into the form, so a credential passed there
+	// authenticates and must be redacted alongside the OIDC session token.
+	assert.Equal(t, []string{"session_token", "password"}, config.redactQueryParams)
+}
+
+// countingBudget records reservations so a test can observe when the
+// middleware hands them back.
+type countingBudget struct {
+	mu        sync.Mutex
+	total     int64
+	used      int64
+	maxAtOnce int64
+}
+
+func (b *countingBudget) Acquire(n int64) bool {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	if b.used+n > b.total {
+		return false
+	}
+	b.used += n
+	if b.used > b.maxAtOnce {
+		b.maxAtOnce = b.used
+	}
+	return true
+}
+
+func (b *countingBudget) Release(n int64) {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	b.used -= n
+}
+
+func (b *countingBudget) inUse() int64 {
+	b.mu.Lock()
+	defer b.mu.Unlock()
+	return b.used
+}
+
+// The buffered body stays alive as r.Body until the backend has read it, so
+// Protect must hold the reservation for the whole request and return it only
+// once the handler chain has unwound. Releasing inside Inspect would let the
+// budget admit buffering that is still resident.
+func TestProtect_AppSecBudgetHeldForRequestAndReleasedAfter(t *testing.T) {
+	srv := appsecEngine(t, http.StatusOK, `{"action":"allow"}`)
+	budget := &countingBudget{total: 1 << 20}
+	client, err := appsec.New(appsec.Config{
+		URL:          srv.URL,
+		APIKey:       "k",
+		MaxBodyBytes: 4096,
+		Budget:       budget,
+	})
+	require.NoError(t, err)
+
+	mw := NewMiddleware(log.StandardLogger(), nil, nil)
+	mw.SetAppSec(client)
+	require.NoError(t, mw.AddDomain("svc.example.com", DomainSettings{
+		AccountID:  types.AccountID("acct-1"),
+		ServiceID:  types.ServiceID("svc-1"),
+		AppSecMode: restrict.AppSecEnforce,
+	}))
+
+	var inHandler int64
+	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
+		// The backend reads the buffered body here, so the reservation must
+		// still be held at this point.
+		inHandler = budget.inUse()
+		_, _ = io.ReadAll(r.Body)
+		w.WriteHeader(http.StatusOK)
+	}))
+
+	r := httptest.NewRequest(http.MethodPost, "http://svc.example.com/", strings.NewReader("payload"))
+	r.Host = "svc.example.com"
+	cd := proxy.NewCapturedData("req-1")
+	r = r.WithContext(proxy.WithCapturedData(r.Context(), cd))
+
+	handler.ServeHTTP(httptest.NewRecorder(), r)
+
+	assert.Equal(t, int64(4096), inHandler, "the reservation must be held while the backend reads the body")
+	assert.Equal(t, int64(0), budget.inUse(), "Protect must release the reservation once the request is served")
+}
+
+// A denied request never reaches the backend, but Protect still has to hand the
+// reservation back or the pool leaks one cap per blocked request.
+func TestProtect_AppSecBudgetReleasedOnDeny(t *testing.T) {
+	srv := appsecEngine(t, http.StatusForbidden, `{"action":"ban"}`)
+	budget := &countingBudget{total: 1 << 20}
+	client, err := appsec.New(appsec.Config{
+		URL:          srv.URL,
+		APIKey:       "k",
+		MaxBodyBytes: 4096,
+		Budget:       budget,
+	})
+	require.NoError(t, err)
+
+	r := httptest.NewRequest(http.MethodPost, "http://svc.example.com/", strings.NewReader("payload"))
+	r.Host = "svc.example.com"
+	rec, _, reached := serveWithAppSec(t, restrict.AppSecEnforce, client, r)
+
+	assert.False(t, reached, "a banned request must not reach the backend")
+	assert.Equal(t, http.StatusForbidden, rec.Code)
+	assert.Equal(t, int64(0), budget.inUse(), "a blocked request must not leak its reservation")
+}

proxy/internal/auth/header.go

@@ -39,6 +39,11 @@ func (Header) Type() auth.Method {
 	return auth.MethodHeader
 }
 
+// HeaderName returns the request header this scheme reads its credential from.
+func (h Header) HeaderName() string {
+	return h.headerName
+}
+
 // Authenticate checks for the configured header in the request. If absent,
 // returns empty (unauthenticated). If present, validates via gRPC.
 func (h Header) Authenticate(r *http.Request) (string, string, error) {

proxy/internal/auth/middleware.go

@@ -18,6 +18,7 @@ import (
 	"google.golang.org/grpc"
 
 	"github.com/netbirdio/netbird/proxy/auth"
+	"github.com/netbirdio/netbird/proxy/internal/appsec"
 	"github.com/netbirdio/netbird/proxy/internal/proxy"
 	"github.com/netbirdio/netbird/proxy/internal/restrict"
 	"github.com/netbirdio/netbird/proxy/internal/types"
@@ -25,6 +26,11 @@ import (
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
+// sessionCookieNames is the cookie set AppSec redacts before mirroring: the
+// proxy's session cookie is a bearer credential for the service, and the
+// reverse proxy already strips it before forwarding upstream.
+var sessionCookieNames = []string{auth.SessionCookieName}
+
 // errValidationUnavailable indicates that session validation failed due to
 // an infrastructure error (e.g. gRPC unavailable), not an invalid token.
 var errValidationUnavailable = errors.New("session validation unavailable")
@@ -59,6 +65,14 @@ type DomainConfig struct {
 	IPRestrictions    *restrict.Filter
 	// Private routes the domain through ValidateTunnelPeer; failure → 403.
 	Private bool
+	// AppSecMode enables CrowdSec AppSec request inspection for this domain.
+	AppSecMode restrict.AppSecMode
+	// redact* name the credentials this domain's schemes accept, resolved once
+	// at registration. AppSec replaces their values before mirroring a request,
+	// matching what the reverse proxy strips before forwarding upstream.
+	redactBodyFields  []string
+	redactHeaders     []string
+	redactQueryParams []string
 }
 
 type validationResult struct {
@@ -82,6 +96,9 @@ type Middleware struct {
 	sessionValidator SessionValidator
 	geo              restrict.GeoResolver
 	tunnelCache      *tunnelValidationCache
+	// appsec is the shared CrowdSec AppSec client, nil when the proxy has no
+	// AppSec endpoint configured. Set once during startup, before serving.
+	appsec *appsec.Client
 }
 
 // NewMiddleware creates a new authentication middleware. The sessionValidator is
@@ -99,6 +116,12 @@ func NewMiddleware(logger *log.Logger, sessionValidator SessionValidator, geo re
 	}
 }
 
+// SetAppSec installs the shared CrowdSec AppSec client. Must be called during
+// startup, before the middleware serves any request.
+func (mw *Middleware) SetAppSec(client *appsec.Client) {
+	mw.appsec = client
+}
+
 // Protect wraps next with per-domain authentication and IP restriction checks.
 // Requests whose Host is not registered pass through unchanged.
 func (mw *Middleware) Protect(next http.Handler) http.Handler {
@@ -123,6 +146,14 @@ func (mw *Middleware) Protect(next http.Handler) http.Handler {
 			return
 		}
 
+		// Deferred, not released here: the inspected body stays alive as r.Body
+		// until the backend has read it, which happens inside next.ServeHTTP.
+		appSecAllowed, releaseAppSec := mw.checkAppSec(w, r, config)
+		defer releaseAppSec()
+		if !appSecAllowed {
+			return
+		}
+
 		// Private services bypass operator schemes and gate on tunnel peer.
 		if config.Private {
 			if mw.forwardWithTunnelPeer(w, r, host, config, next) {
@@ -262,6 +293,134 @@ func (mw *Middleware) checkIPRestrictions(w http.ResponseWriter, r *http.Request
 	return false
 }
 
+// checkAppSec mirrors the request to the CrowdSec AppSec engine when the domain
+// enables inspection. Returns false when the request was blocked and a response
+// has been written.
+//
+// The returned release frees the body-buffering budget the inspection reserved
+// and is never nil. It must run only after the request has been served, since
+// the buffered body stays alive as r.Body for the backend to read.
+//
+// Every non-allow remediation blocks with 403, captcha included: the proxy has
+// no challenge flow to serve. The distinct verdict is still recorded so the
+// access log shows which remediation the engine actually chose.
+//
+// Unlike the geo and IP-reputation checks, this runs for overlay traffic too:
+// AppSec inspects request content, which is just as meaningful when the caller
+// reached the proxy through the WireGuard tunnel.
+func (mw *Middleware) checkAppSec(w http.ResponseWriter, r *http.Request, config DomainConfig) (bool, func()) {
+	if !config.AppSecMode.Enabled() {
+		return true, func() {}
+	}
+
+	verdict, release := mw.inspectAppSec(r, config)
+	if verdict == restrict.Allow {
+		return true, release
+	}
+
+	observe := config.AppSecMode == restrict.AppSecObserve
+	if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
+		cd.SetMetadata("appsec_verdict", verdict.String())
+		if observe {
+			cd.SetMetadata("appsec_mode", "observe")
+		}
+	}
+
+	if observe {
+		mw.logger.Debugf("AppSec observe: would block %s for %s (%s)", r.RemoteAddr, r.Host, verdict)
+		return true, release
+	}
+
+	mw.markDenied(r, verdict.String())
+	mw.logger.Debugf("AppSec: %s for %s %s", verdict, r.Host, r.RemoteAddr)
+	http.Error(w, "Forbidden", http.StatusForbidden)
+	return false, release
+}
+
+// inspectAppSec runs the AppSec call and returns its verdict. Failures come
+// back as DenyAppSecUnavailable regardless of mode so observe mode still
+// records that inspection did not happen; the caller decides what blocks. The
+// returned release is never nil.
+func (mw *Middleware) inspectAppSec(r *http.Request, config DomainConfig) (restrict.Verdict, func()) {
+	// Mode requested but the proxy has no AppSec endpoint configured. Management
+	// gates this on the cluster capability; a stale mapping can still arrive.
+	if mw.appsec == nil {
+		mw.logger.Debugf("AppSec mode %q requested for %s but no AppSec endpoint is configured", config.AppSecMode, r.Host)
+		return restrict.DenyAppSecUnavailable, func() {}
+	}
+
+	clientIP := mw.resolveClientIP(r)
+	if !clientIP.IsValid() {
+		// The engine requires a client address, and a request whose source we
+		// cannot establish is exactly the kind we must not wave through.
+		mw.logger.Debugf("AppSec: cannot resolve client address for %q", r.RemoteAddr)
+		return restrict.DenyAppSecUnavailable, func() {}
+	}
+
+	req := appsec.Request{
+		HTTP:              r,
+		ClientIP:          clientIP,
+		RedactBodyFields:  config.redactBodyFields,
+		RedactHeaders:     config.redactHeaders,
+		RedactCookies:     sessionCookieNames,
+		RedactQueryParams: config.redactQueryParams,
+	}
+	if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
+		req.TransactionID = cd.GetRequestID()
+	}
+
+	result, err := mw.appsec.Inspect(r.Context(), req)
+	if err != nil {
+		mw.logger.Debugf("AppSec inspection failed for %s: %v", r.Host, err)
+	}
+	// Record when the body went uninspected: headers and URI were still
+	// checked, but an operator reading the log should not read a clean verdict
+	// as "the payload was examined". Oversize is reachable by padding, so its
+	// absence from the log would hide a deliberate opt-out.
+	if result.BodyBypass != "" {
+		if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
+			cd.SetMetadata("appsec_body_bypass", result.BodyBypass)
+		}
+	}
+	return result.Verdict, result.Release
+}
+
+// credentialFormFields lists the login form fields whose values are redacted
+// from the mirrored body, so a password or PIN submitted to the proxy's own
+// login form never reaches the Security Engine.
+func credentialFormFields(schemes []Scheme) []string {
+	var fields []string
+	for _, s := range schemes {
+		switch s.Type() {
+		case auth.MethodPassword:
+			fields = append(fields, passwordFormId)
+		case auth.MethodPIN:
+			fields = append(fields, pinFormId)
+		}
+	}
+	return fields
+}
+
+// credentialHeaders lists the request headers whose values are redacted from
+// the mirrored request. A header-auth scheme carries a session token the proxy
+// validates and never forwards upstream, so the engine must not see it either.
+func credentialHeaders(schemes []Scheme) []string {
+	var names []string
+	for _, s := range schemes {
+		// Structural, not a concrete Header assertion: if the scheme is ever
+		// registered as a pointer, a type assertion would quietly stop matching
+		// and the header would start reaching the engine again.
+		named, ok := s.(interface{ HeaderName() string })
+		if !ok {
+			continue
+		}
+		if name := named.HeaderName(); name != "" {
+			names = append(names, name)
+		}
+	}
+	return names
+}
+
 // resolveClientIP extracts the real client IP from CapturedData, falling back to r.RemoteAddr.
 func (mw *Middleware) resolveClientIP(r *http.Request) netip.Addr {
 	if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
@@ -281,12 +440,18 @@ func (mw *Middleware) resolveClientIP(r *http.Request) netip.Addr {
 	return addr.Unmap()
 }
 
-// blockIPRestriction sets captured data fields for an IP-restriction block event.
-func (mw *Middleware) blockIPRestriction(r *http.Request, reason string) {
+// markDenied records the deny reason on the captured data so the access log
+// attributes the response to the proxy rather than the backend.
+func (mw *Middleware) markDenied(r *http.Request, reason string) {
 	if cd := proxy.CapturedDataFromContext(r.Context()); cd != nil {
 		cd.SetOrigin(proxy.OriginAuth)
 		cd.SetAuthMethod(reason)
 	}
+}
+
+// blockIPRestriction sets captured data fields for an IP-restriction block event.
+func (mw *Middleware) blockIPRestriction(r *http.Request, reason string) {
+	mw.markDenied(r, reason)
 	mw.logger.Debugf("IP restriction: %s for %s", reason, r.RemoteAddr)
 }
 
@@ -637,45 +802,61 @@ func wasCredentialSubmitted(r *http.Request, method auth.Method) bool {
 	case auth.MethodPassword:
 		return r.FormValue("password") != ""
 	case auth.MethodOIDC:
-		return r.URL.Query().Get("session_token") != ""
+		return r.URL.Query().Get(sessionTokenParam) != ""
 	}
 	return false
 }
 
-// AddDomain registers authentication schemes for the given domain. With schemes a valid session public key is required.
-// private=true forces ValidateTunnelPeer enforcement (403 on failure) regardless of the schemes list.
-func (mw *Middleware) AddDomain(domain string, schemes []Scheme, publicKeyB64 string, expiration time.Duration, accountID types.AccountID, serviceID types.ServiceID, ipRestrictions *restrict.Filter, private bool) error {
-	if len(schemes) == 0 {
-		mw.domainsMux.Lock()
-		defer mw.domainsMux.Unlock()
-		mw.domains[domain] = DomainConfig{
-			AccountID:      accountID,
-			ServiceID:      serviceID,
-			IPRestrictions: ipRestrictions,
-			Private:        private,
-		}
-		return nil
+// DomainSettings is the per-domain configuration AddDomain applies.
+type DomainSettings struct {
+	Schemes []Scheme
+	// SessionPublicKey is the base64-encoded ed25519 key used to verify session
+	// cookies. Required when Schemes is non-empty.
+	SessionPublicKey  string
+	SessionExpiration time.Duration
+	AccountID         types.AccountID
+	ServiceID         types.ServiceID
+	IPRestrictions    *restrict.Filter
+	// Private forces ValidateTunnelPeer enforcement (403 on failure) regardless
+	// of the schemes list.
+	Private    bool
+	AppSecMode restrict.AppSecMode
+}
+
+// AddDomain registers authentication schemes for the given domain. With schemes
+// a valid session public key is required.
+func (mw *Middleware) AddDomain(domain string, settings DomainSettings) error {
+	credentialFields := credentialFormFields(settings.Schemes)
+	config := DomainConfig{
+		AccountID:        settings.AccountID,
+		ServiceID:        settings.ServiceID,
+		IPRestrictions:   settings.IPRestrictions,
+		Private:          settings.Private,
+		AppSecMode:       settings.AppSecMode,
+		redactBodyFields: credentialFields,
+		redactHeaders:    credentialHeaders(settings.Schemes),
+		// A credential can arrive in the query too: r.FormValue merges the URL
+		// query into the form, so "?password=..." authenticates just as a form
+		// post does and must not be mirrored in the clear either.
+		redactQueryParams: append([]string{sessionTokenParam}, credentialFields...),
 	}
 
-	pubKeyBytes, err := base64.StdEncoding.DecodeString(publicKeyB64)
-	if err != nil {
-		return fmt.Errorf("decode session public key for domain %s: %w", domain, err)
-	}
-	if len(pubKeyBytes) != ed25519.PublicKeySize {
-		return fmt.Errorf("invalid session public key size for domain %s: got %d, want %d", domain, len(pubKeyBytes), ed25519.PublicKeySize)
+	if len(settings.Schemes) > 0 {
+		pubKeyBytes, err := base64.StdEncoding.DecodeString(settings.SessionPublicKey)
+		if err != nil {
+			return fmt.Errorf("decode session public key for domain %s: %w", domain, err)
+		}
+		if len(pubKeyBytes) != ed25519.PublicKeySize {
+			return fmt.Errorf("invalid session public key size for domain %s: got %d, want %d", domain, len(pubKeyBytes), ed25519.PublicKeySize)
+		}
+		config.Schemes = settings.Schemes
+		config.SessionPublicKey = pubKeyBytes
+		config.SessionExpiration = settings.SessionExpiration
 	}
 
 	mw.domainsMux.Lock()
 	defer mw.domainsMux.Unlock()
-	mw.domains[domain] = DomainConfig{
-		Schemes:           schemes,
-		SessionPublicKey:  pubKeyBytes,
-		SessionExpiration: expiration,
-		AccountID:         accountID,
-		ServiceID:         serviceID,
-		IPRestrictions:    ipRestrictions,
-		Private:           private,
-	}
+	mw.domains[domain] = config
 	return nil
 }
 
@@ -730,10 +911,10 @@ func (mw *Middleware) validateSessionToken(ctx context.Context, host, token stri
 // parameter removed so it doesn't linger in the browser's address bar or history.
 func stripSessionTokenParam(u *url.URL) string {
 	q := u.Query()
-	if !q.Has("session_token") {
+	if !q.Has(sessionTokenParam) {
 		return u.RequestURI()
 	}
-	q.Del("session_token")
+	q.Del(sessionTokenParam)
 	clean := *u
 	clean.RawQuery = q.Encode()
 	return clean.RequestURI()

proxy/internal/auth/middleware_test.go

@@ -64,7 +64,7 @@ func TestAddDomain_ValidKey(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	err := mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour})
 	require.NoError(t, err)
 
 	mw.domainsMux.RLock()
@@ -81,7 +81,7 @@ func TestAddDomain_EmptyKey(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	err := mw.AddDomain("example.com", []Scheme{scheme}, "", time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionExpiration: time.Hour})
 	require.Error(t, err)
 	assert.Contains(t, err.Error(), "invalid session public key size")
 
@@ -95,7 +95,7 @@ func TestAddDomain_InvalidBase64(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	err := mw.AddDomain("example.com", []Scheme{scheme}, "not-valid-base64!!!", time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "not-valid-base64!!!", SessionExpiration: time.Hour})
 	require.Error(t, err)
 	assert.Contains(t, err.Error(), "decode session public key")
 
@@ -110,7 +110,7 @@ func TestAddDomain_WrongKeySize(t *testing.T) {
 
 	shortKey := base64.StdEncoding.EncodeToString([]byte("tooshort"))
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	err := mw.AddDomain("example.com", []Scheme{scheme}, shortKey, time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: shortKey, SessionExpiration: time.Hour})
 	require.Error(t, err)
 	assert.Contains(t, err.Error(), "invalid session public key size")
 
@@ -123,7 +123,7 @@ func TestAddDomain_WrongKeySize(t *testing.T) {
 func TestAddDomain_NoSchemes_NoKeyRequired(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{SessionExpiration: time.Hour})
 	require.NoError(t, err, "domains with no auth schemes should not require a key")
 
 	mw.domainsMux.RLock()
@@ -139,8 +139,8 @@ func TestAddDomain_OverwritesPreviousConfig(t *testing.T) {
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
 
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp1.PublicKey, time.Hour, "", "", nil, false))
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp2.PublicKey, 2*time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp1.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp2.PublicKey, SessionExpiration: 2 * time.Hour}))
 
 	mw.domainsMux.RLock()
 	config := mw.domains["example.com"]
@@ -156,7 +156,7 @@ func TestRemoveDomain(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	mw.RemoveDomain("example.com")
 
@@ -180,7 +180,7 @@ func TestProtect_UnknownDomainPassesThrough(t *testing.T) {
 
 func TestProtect_DomainWithNoSchemesPassesThrough(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
-	require.NoError(t, mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -197,7 +197,7 @@ func TestProtect_UnauthenticatedRequestIsBlocked(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	var backendCalled bool
 	backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -218,7 +218,7 @@ func TestProtect_HostWithPortIsMatched(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	var backendCalled bool
 	backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -239,7 +239,7 @@ func TestProtect_ValidSessionCookiePassesThrough(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, time.Hour)
 	require.NoError(t, err)
@@ -272,7 +272,7 @@ func TestProtect_SessionCookieGroupsPropagate(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	groups := []string{"engineering", "sre"}
 	token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, groups, nil, time.Hour)
@@ -337,7 +337,7 @@ func TestProtect_PrivateService_TunnelPeerGroupsPropagate(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	// Private service: no operator schemes — auth gates solely on the tunnel peer.
-	require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, true))
+	require.NoError(t, mw.AddDomain("agent.example.com", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
 
 	cd := proxy.NewCapturedData("")
 	cd.SetClientIP(netip.MustParseAddr("100.90.1.14")) // CGNAT tunnel source
@@ -377,7 +377,7 @@ func TestProtect_PrivateService_TunnelPeerDenied(t *testing.T) {
 	}}
 	mw := NewMiddleware(log.StandardLogger(), validator, nil)
 	kp := generateTestKeyPair(t)
-	require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, true))
+	require.NoError(t, mw.AddDomain("agent.example.com", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
 
 	cd := proxy.NewCapturedData("")
 	cd.SetClientIP(netip.MustParseAddr("100.90.1.14"))
@@ -405,7 +405,7 @@ func TestProtect_ExpiredSessionCookieIsRejected(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	// Sign a token that expired 1 second ago.
 	token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, -time.Second)
@@ -431,7 +431,7 @@ func TestProtect_WrongDomainCookieIsRejected(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	// Token signed for a different domain audience.
 	token, err := sessionkey.SignToken(kp.PrivateKey, "test-user", "", "other.com", auth.MethodPIN, nil, nil, time.Hour)
@@ -458,7 +458,7 @@ func TestProtect_WrongKeyCookieIsRejected(t *testing.T) {
 	kp2 := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp1.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp1.PublicKey, SessionExpiration: time.Hour}))
 
 	// Token signed with a different private key.
 	token, err := sessionkey.SignToken(kp2.PrivateKey, "test-user", "", "example.com", auth.MethodPIN, nil, nil, time.Hour)
@@ -495,7 +495,7 @@ func TestProtect_SchemeAuthRedirectsWithCookie(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	var backendCalled bool
 	backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -548,7 +548,7 @@ func TestProtect_FailedAuthDoesNotSetCookie(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -584,7 +584,7 @@ func TestProtect_MultipleSchemes(t *testing.T) {
 			return "", "password", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{pinScheme, passwordScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{pinScheme, passwordScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	var backendCalled bool
 	backend := http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -614,7 +614,7 @@ func TestProtect_InvalidTokenFromSchemeReturns400(t *testing.T) {
 			return "invalid-jwt-token", "", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -638,7 +638,7 @@ func TestAddDomain_RandomBytes32NotEd25519(t *testing.T) {
 	key := base64.StdEncoding.EncodeToString(randomBytes)
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
 
-	err = mw.AddDomain("example.com", []Scheme{scheme}, key, time.Hour, "", "", nil, false)
+	err = mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: key, SessionExpiration: time.Hour})
 	require.NoError(t, err, "any 32-byte key should be accepted at registration time")
 }
 
@@ -647,10 +647,10 @@ func TestAddDomain_InvalidKeyDoesNotCorruptExistingConfig(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	// Attempt to overwrite with an invalid key.
-	err := mw.AddDomain("example.com", []Scheme{scheme}, "bad", time.Hour, "", "", nil, false)
+	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "bad", SessionExpiration: time.Hour})
 	require.Error(t, err)
 
 	// The original valid config should still be intact.
@@ -674,7 +674,7 @@ func TestProtect_FailedPinAuthCapturesAuthMethod(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -701,7 +701,7 @@ func TestProtect_FailedPasswordAuthCapturesAuthMethod(t *testing.T) {
 			return "", "password", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -728,7 +728,7 @@ func TestProtect_NoCredentialsDoesNotCaptureAuthMethod(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -815,8 +815,7 @@ func TestWasCredentialSubmitted(t *testing.T) {
 func TestCheckIPRestrictions_UnparseableAddress(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
-		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}}), false)
+	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}})})
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -851,8 +850,7 @@ func TestCheckIPRestrictions_UsesCapturedDataClientIP(t *testing.T) {
 	// trusted proxies), checkIPRestrictions should use that IP, not RemoteAddr.
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
-		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}}), false)
+	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}})})
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -892,8 +890,7 @@ func TestCheckIPRestrictions_NilGeoWithCountryRules(t *testing.T) {
 	// Geo is nil, country restrictions are configured: must deny (fail-close).
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
-		restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}}), false)
+	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}})})
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -916,11 +913,10 @@ func TestCheckIPRestrictions_NilGeoWithCountryRules(t *testing.T) {
 func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
-		restrict.ParseFilter(restrict.FilterConfig{
-			AllowedCIDRs:     []string{"100.64.0.0/10"},
-			AllowedCountries: []string{"US"},
-		}), false)
+	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{
+		AllowedCIDRs:     []string{"100.64.0.0/10"},
+		AllowedCountries: []string{"US"},
+	})})
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -953,8 +949,7 @@ func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
 func TestCheckIPRestrictions_OverlayOriginRespectsCIDR(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
-		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}}), false)
+	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}})})
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -982,7 +977,7 @@ func TestProtect_OIDCOnlyRedirectsDirectly(t *testing.T) {
 			return "", oidcURL, nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1011,7 +1006,7 @@ func TestProtect_OIDCWithOtherMethodShowsLoginPage(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{oidcScheme, pinScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{oidcScheme, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1055,7 +1050,7 @@ func TestProtect_HeaderAuth_ForwardsOnSuccess(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	var backendCalled bool
 	capturedData := proxy.NewCapturedData("")
@@ -1098,7 +1093,7 @@ func TestProtect_HeaderAuth_MissingHeaderFallsThrough(t *testing.T) {
 	hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
 	// Also add a PIN scheme so we can verify fallthrough behavior.
 	pinScheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr, pinScheme}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1118,7 +1113,7 @@ func TestProtect_HeaderAuth_WrongValueReturns401(t *testing.T) {
 		return &proto.AuthenticateResponse{Success: false}, nil
 	}}
 	hdr := NewHeader(mock, "svc1", "acc1", "X-API-Key")
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -1141,7 +1136,7 @@ func TestProtect_HeaderAuth_InfraErrorReturns502(t *testing.T) {
 		return nil, errors.New("gRPC unavailable")
 	}}
 	hdr := NewHeader(mock, "svc1", "acc1", "X-API-Key")
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1158,7 +1153,7 @@ func TestProtect_HeaderAuth_SubsequentRequestUsesSessionCookie(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	hdr := newHeaderSchemeWithToken(t, kp, "X-API-Key", "secret-key")
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
 		w.WriteHeader(http.StatusOK)
@@ -1218,7 +1213,7 @@ func TestProtect_HeaderAuth_MultipleValuesSameHeader(t *testing.T) {
 
 	// Single Header scheme (as if one entry existed), but the mock checks both values.
 	hdr := NewHeader(mock, "svc1", "acc1", "Authorization")
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
 
 	var backendCalled bool
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -1276,7 +1271,7 @@ func TestProtect_OIDCOnPlainHTTP_BlockedWith400(t *testing.T) {
 			return "", "https://idp.example.com/authorize", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1300,7 +1295,7 @@ func TestProtect_OIDCOverTLS_NotBlocked(t *testing.T) {
 			return "", "https://idp.example.com/authorize", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1320,7 +1315,7 @@ func TestProtect_NonOIDCSchemes_PlainHTTP_NotBlocked(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1350,7 +1345,7 @@ func TestProtect_TunnelPeerFastPath_RequiresInboundMarker(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1385,7 +1380,7 @@ func TestProtect_TunnelPeerFastPath_TakesPathWithInboundMarker(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
+	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
 
 	handler := mw.Protect(newPassthroughHandler())
 

proxy/internal/auth/oidc.go

@@ -13,6 +13,10 @@ import (
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
+// sessionTokenParam is the query parameter the management server uses to hand
+// the minted session token back to the proxy after an OIDC login.
+const sessionTokenParam = "session_token"
+
 type urlGenerator interface {
 	GetOIDCURL(context.Context, *proto.GetOIDCURLRequest, ...grpc.CallOption) (*proto.GetOIDCURLResponse, error)
 }
@@ -43,7 +47,7 @@ func (o OIDC) Authenticate(r *http.Request) (string, string, error) {
 	// Check for the session_token query param (from OIDC redirects).
 	// The management server passes the token in the URL because it cannot set
 	// cookies for the proxy's domain (cookies are domain-scoped per RFC 6265).
-	if token := r.URL.Query().Get("session_token"); token != "" {
+	if token := r.URL.Query().Get(sessionTokenParam); token != "" {
 		return token, "", nil
 	}
 

proxy/internal/auth/tunnel_lookup_test.go

@@ -44,7 +44,7 @@ func (s *stubSessionValidator) ValidateTunnelPeer(_ context.Context, in *proto.V
 func newTunnelMiddleware(t *testing.T, validator SessionValidator) *Middleware {
 	t.Helper()
 	mw := NewMiddleware(log.New(), validator, nil)
-	require.NoError(t, mw.AddDomain("svc.example", nil, "", 0, "acct-1", "svc-1", nil, false))
+	require.NoError(t, mw.AddDomain("svc.example", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1"}))
 	return mw
 }
 
@@ -235,8 +235,8 @@ func TestForwardWithTunnelPeer_RoutesAccountIDIntoCacheKey(t *testing.T) {
 	}
 	mw := NewMiddleware(log.New(), validator, nil)
 
-	require.NoError(t, mw.AddDomain("svc-a.example", nil, "", 0, "acct-a", "svc-a", nil, false))
-	require.NoError(t, mw.AddDomain("svc-b.example", nil, "", 0, "acct-b", "svc-b", nil, false))
+	require.NoError(t, mw.AddDomain("svc-a.example", DomainSettings{AccountID: "acct-a", ServiceID: "svc-a"}))
+	require.NoError(t, mw.AddDomain("svc-b.example", DomainSettings{AccountID: "acct-b", ServiceID: "svc-b"}))
 
 	// The fast-path requires the inbound-listener marker on the context.
 	// The peerstore lookup itself is account-agnostic at this level
@@ -299,7 +299,7 @@ func TestForwardWithTunnelPeer_LocalLookupShortCircuitDoesNotPopulateCache(t *te
 
 func TestPrivateService_FailsClosedOnTunnelPeerFailure(t *testing.T) {
 	mw := NewMiddleware(log.New(), nil, nil)
-	require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, true))
+	require.NoError(t, mw.AddDomain("private.svc", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
 
 	called := false
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -328,7 +328,7 @@ func TestPrivateService_ForwardsOnTunnelPeerSuccess(t *testing.T) {
 		},
 	}
 	mw := NewMiddleware(log.New(), validator, nil)
-	require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, true))
+	require.NoError(t, mw.AddDomain("private.svc", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
 
 	called := false
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {

proxy/internal/middleware/bodytap/request.go

@@ -21,6 +21,8 @@ import (
 	"strconv"
 	"strings"
 	"sync"
+
+	"github.com/netbirdio/netbird/proxy/internal/netutil"
 )
 
 // MaxRoutingScanBytes bounds how far ScanRoutingFields will read into a
@@ -34,7 +36,6 @@ const MaxRoutingScanBytes int64 = 32 << 20
 // metadata key by the chain when a request body is not surfaced.
 const (
 	BypassUpgradeHeader    = "upgrade_header"
-	BypassConnectionUpgrd  = "connection_upgrade"
 	BypassContentType      = "content_type_not_allowed"
 	BypassBudget           = "capture_budget_exhausted"
 	BypassNoConfig         = "no_capture_config"
@@ -125,12 +126,13 @@ func CaptureRequest(r *http.Request, cfg *Config, b Budget) (body []byte, trunca
 	if cfg.MaxRequestBytes <= 0 {
 		return nil, false, 0, BypassCapZero, release, nil
 	}
-	if r.Header.Get("Upgrade") != "" {
+	// The predicate has to be the forwarder's own: a looser one (either header
+	// on its own) skips capture for requests the forwarder still delivers to
+	// the upstream with their body intact, which hides them from every
+	// deny-capable middleware in the chain.
+	if netutil.IsUpgradeRequest(r.Header) {
 		return nil, false, 0, BypassUpgradeHeader, release, nil
 	}
-	if strings.EqualFold(r.Header.Get("Connection"), "upgrade") {
-		return nil, false, 0, BypassConnectionUpgrd, release, nil
-	}
 	if !contentTypeAllowed(r.Header.Get("Content-Type"), cfg.ContentTypes) {
 		return nil, false, 0, BypassContentType, release, nil
 	}

proxy/internal/netutil/upgrade.go

@@ -0,0 +1,23 @@
+package netutil
+
+import (
+	"net/http"
+
+	"golang.org/x/net/http/httpguts"
+)
+
+// IsUpgradeRequest reports whether r is a protocol-upgrade request, using the
+// same predicate httputil.ReverseProxy applies when it decides to hand the
+// connection over instead of proxying normally.
+//
+// Matching the forwarder exactly matters for anything that inspects a request
+// before it is proxied: a looser test (an Upgrade header on its own, say) marks
+// a request as an upgrade and skips inspection, while the forwarder still
+// delivers it to the backend as an ordinary request with its body intact. That
+// gap is a body-inspection bypass reachable by adding one header.
+func IsUpgradeRequest(h http.Header) bool {
+	if !httpguts.HeaderValuesContainsToken(h["Connection"], "Upgrade") {
+		return false
+	}
+	return h.Get("Upgrade") != ""
+}

proxy/internal/restrict/restrict.go

@@ -50,6 +50,59 @@ const (
 	CrowdSecObserve CrowdSecMode = "observe"
 )
 
+// AllowMatch controls how the configured allowlists (CIDR, country) combine.
+// Blocklists are always a separate hard-deny gate and are unaffected by it.
+type AllowMatch string
+
+const (
+	// AllowMatchAll requires the address to match every configured allowlist
+	// (AND). This is the default and preserves the historical behavior.
+	AllowMatchAll AllowMatch = "all"
+	// AllowMatchAny requires the address to match at least one configured
+	// allowlist (OR), e.g. "allowed country OR allowed CIDR".
+	AllowMatchAny AllowMatch = "any"
+)
+
+// normalizeAllowMatch maps unknown or empty values to the restrictive default
+// (AllowMatchAll) so an unrecognized mode never loosens access.
+func normalizeAllowMatch(m AllowMatch) AllowMatch {
+	if m == AllowMatchAny {
+		return AllowMatchAny
+	}
+	return AllowMatchAll
+}
+
+// AppSecMode is the per-service CrowdSec AppSec (WAF) enforcement mode.
+type AppSecMode string
+
+const (
+	// AppSecOff disables request inspection.
+	AppSecOff AppSecMode = ""
+	// AppSecEnforce blocks requests the engine flags, and fails closed when the
+	// engine is unreachable.
+	AppSecEnforce AppSecMode = "enforce"
+	// AppSecObserve records the verdict without blocking.
+	AppSecObserve AppSecMode = "observe"
+)
+
+// ParseAppSecMode maps a wire value to an AppSecMode. Unrecognized values map
+// to AppSecOff so a typo never turns inspection into an unintended block.
+func ParseAppSecMode(s string) AppSecMode {
+	switch AppSecMode(s) {
+	case AppSecEnforce:
+		return AppSecEnforce
+	case AppSecObserve:
+		return AppSecObserve
+	default:
+		return AppSecOff
+	}
+}
+
+// Enabled reports whether the mode asks for request inspection.
+func (m AppSecMode) Enabled() bool {
+	return m == AppSecEnforce || m == AppSecObserve
+}
+
 // Filter evaluates IP restrictions. CIDR checks are performed first
 // (cheap), followed by country lookups (more expensive) only when needed.
 type Filter struct {
@@ -59,6 +112,9 @@ type Filter struct {
 	BlockedCountries []string
 	CrowdSec         CrowdSecChecker
 	CrowdSecMode     CrowdSecMode
+	// AllowMatch controls how the allowlists combine (AND vs OR). Empty means
+	// AllowMatchAll.
+	AllowMatch AllowMatch
 }
 
 // FilterConfig holds the raw configuration for building a Filter.
@@ -69,6 +125,7 @@ type FilterConfig struct {
 	BlockedCountries []string
 	CrowdSec         CrowdSecChecker
 	CrowdSecMode     CrowdSecMode
+	AllowMatch       AllowMatch
 	Logger           *log.Entry
 }
 
@@ -89,6 +146,7 @@ func ParseFilter(cfg FilterConfig) *Filter {
 	f := &Filter{
 		AllowedCountries: normalizeCountryCodes(cfg.AllowedCountries),
 		BlockedCountries: normalizeCountryCodes(cfg.BlockedCountries),
+		AllowMatch:       normalizeAllowMatch(cfg.AllowMatch),
 	}
 	if hasCS {
 		f.CrowdSec = cfg.CrowdSec
@@ -146,6 +204,13 @@ const (
 	// DenyCrowdSecUnavailable indicates enforce mode but the bouncer has not
 	// completed its initial sync.
 	DenyCrowdSecUnavailable
+	// DenyAppSecBan indicates a CrowdSec AppSec "ban" remediation.
+	DenyAppSecBan
+	// DenyAppSecCaptcha indicates a CrowdSec AppSec "captcha" remediation.
+	DenyAppSecCaptcha
+	// DenyAppSecUnavailable indicates enforce mode but the AppSec engine could
+	// not produce a verdict (unreachable, timed out, or it rejected the call).
+	DenyAppSecUnavailable
 )
 
 // String returns the deny reason string matching the HTTP auth mechanism names.
@@ -167,6 +232,12 @@ func (v Verdict) String() string {
 		return "crowdsec_throttle"
 	case DenyCrowdSecUnavailable:
 		return "crowdsec_unavailable"
+	case DenyAppSecBan:
+		return "appsec_ban"
+	case DenyAppSecCaptcha:
+		return "appsec_captcha"
+	case DenyAppSecUnavailable:
+		return "appsec_unavailable"
 	default:
 		return "unknown"
 	}
@@ -182,6 +253,16 @@ func (v Verdict) IsCrowdSec() bool {
 	}
 }
 
+// IsAppSec returns true when the verdict originates from an AppSec inspection.
+func (v Verdict) IsAppSec() bool {
+	switch v {
+	case DenyAppSecBan, DenyAppSecCaptcha, DenyAppSecUnavailable:
+		return true
+	default:
+		return false
+	}
+}
+
 // IsObserveOnly returns true when v is a CrowdSec verdict and the filter is in
 // observe mode. Callers should log the verdict but not block the request.
 func (f *Filter) IsObserveOnly(v Verdict) bool {
@@ -216,6 +297,10 @@ func (f *Filter) Check(addr netip.Addr, geo GeoResolver) Verdict {
 	// IPv4 CIDR rules match regardless of how the address was received.
 	addr = addr.Unmap()
 
+	if f.AllowMatch == AllowMatchAny {
+		return f.checkAny(addr, geo)
+	}
+
 	if v := f.checkCIDR(addr); v != Allow {
 		return v
 	}
@@ -225,6 +310,68 @@ func (f *Filter) Check(addr netip.Addr, geo GeoResolver) Verdict {
 	return f.checkCrowdSec(addr)
 }
 
+// checkAny evaluates the filter with OR semantics across allowlists: the
+// address is admitted if it matches any configured allowlist (CIDR or country).
+// Blocklists remain a hard-deny gate evaluated first and are independent of the
+// allow-combine mode, so a blocklist match (or unverifiable country block) still
+// denies. CrowdSec runs last, as in the default path.
+//
+// The country is resolved at most once and shared by both the blocklist and the
+// allowlist, matching what the all-mode path does. Splitting the two checks into
+// separate helpers cost a second geo lookup per connection whenever both country
+// lists were configured.
+func (f *Filter) checkAny(addr netip.Addr, geo GeoResolver) Verdict {
+	for _, prefix := range f.BlockedCIDRs {
+		if prefix.Contains(addr) {
+			return DenyCIDR
+		}
+	}
+
+	cidrActive := len(f.AllowedCIDRs) > 0
+	cidrAllowed := false
+	if cidrActive {
+		for _, prefix := range f.AllowedCIDRs {
+			if prefix.Contains(addr) {
+				cidrAllowed = true
+				break
+			}
+		}
+	}
+
+	countryActive := len(f.AllowedCountries) > 0
+	// The blocklist is a hard gate, so it needs the country even when a CIDR
+	// allowlist already admitted the address. The allowlist needs it only when
+	// the CIDR list did not admit it, which is why a matching allowed CIDR
+	// still skips the lookup when no country blocklist is configured.
+	needCountry := len(f.BlockedCountries) > 0 || (countryActive && !cidrAllowed)
+
+	country := ""
+	if needCountry {
+		if geo == nil || !geo.Available() {
+			return DenyGeoUnavailable
+		}
+		country = geo.LookupAddr(addr).CountryCode
+	}
+
+	if country != "" && slices.Contains(f.BlockedCountries, country) {
+		return DenyCountry
+	}
+
+	allowed := (!cidrActive && !countryActive) ||
+		cidrAllowed ||
+		(countryActive && country != "" && slices.Contains(f.AllowedCountries, country))
+	if !allowed {
+		// Both allowlists missing is reported against the CIDR list, the one
+		// checked first, so the reason stays stable for existing access logs.
+		if cidrActive {
+			return DenyCIDR
+		}
+		return DenyCountry
+	}
+
+	return f.checkCrowdSec(addr)
+}
+
 func (f *Filter) checkCIDR(addr netip.Addr) Verdict {
 	if len(f.AllowedCIDRs) > 0 {
 		allowed := false

proxy/internal/restrict/restrict_test.go

@@ -5,6 +5,7 @@ import (
 	"testing"
 
 	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
 
 	"github.com/netbirdio/netbird/proxy/internal/geolocation"
 )
@@ -150,6 +151,187 @@ func TestFilter_Check_CIDRAllowThenCountryBlock(t *testing.T) {
 	assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("192.168.1.1"), geo), "CIDR denied before country check")
 }
 
+// TestFilter_Check_CrossCategoryAllowlistsAreAND documents the current
+// behavior: when both a CIDR allowlist and a country allowlist are set, a
+// request must satisfy BOTH to be allowed (AND across categories). There is no
+// way today to express "allow if in allowed country OR in allowed CIDR", e.g.
+// "allow all US traffic plus our office IP abroad". This is the gap an
+// any/all allow-combine mode would close; the cases marked "GAP" are the ones
+// that would flip to Allow under an "any" mode.
+func TestFilter_Check_CrossCategoryAllowlistsAreAND(t *testing.T) {
+	officeAbroad := "203.0.113.7" // in allowed CIDR, but country not in allowlist
+	usOutsideOffice := "1.1.1.1"  // allowed country, but not in allowed CIDR
+	usOffice := "203.0.113.8"     // both
+	neither := "198.51.100.1"     // neither
+
+	geo := newMockGeo(map[string]string{
+		officeAbroad:    "DE",
+		usOutsideOffice: "US",
+		usOffice:        "US",
+		neither:         "CN",
+	})
+	f := ParseFilter(FilterConfig{
+		AllowedCIDRs:     []string{"203.0.113.0/24"},
+		AllowedCountries: []string{"US"},
+	})
+
+	assert.Equal(t, Allow, f.Check(netip.MustParseAddr(usOffice), geo), "in allowed CIDR and allowed country")
+	assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr(officeAbroad), geo), "GAP: in allowed CIDR but country not allowed; any-mode should Allow")
+	assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr(usOutsideOffice), geo), "GAP: allowed country but not in allowed CIDR; any-mode should Allow")
+	assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr(neither), geo), "neither: denied under both modes")
+}
+
+// TestFilter_Check_CrossCategoryBlockAndAllow locks the current (all/AND)
+// cross-category semantics that the evaluator must preserve: a blocklist match
+// in any category denies regardless of allowlists, and blocklists across
+// categories are effectively OR (a match in either denies).
+func TestFilter_Check_CrossCategoryBlockAndAllow(t *testing.T) {
+	geo := newMockGeo(map[string]string{
+		"1.1.1.1":  "US",
+		"10.1.2.3": "US",
+		"2.2.2.2":  "CN",
+		"3.3.3.3":  "US",
+	})
+
+	t.Run("country allowlist with CIDR blocklist", func(t *testing.T) {
+		f := ParseFilter(FilterConfig{
+			AllowedCountries: []string{"US"},
+			BlockedCIDRs:     []string{"10.1.0.0/16"},
+		})
+		assert.Equal(t, Allow, f.Check(netip.MustParseAddr("1.1.1.1"), geo), "US and not in blocked CIDR")
+		assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("10.1.2.3"), geo), "US but in blocked CIDR, block wins")
+		assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("2.2.2.2"), geo), "not in allowed country")
+	})
+
+	t.Run("blocklists across categories are OR", func(t *testing.T) {
+		f := ParseFilter(FilterConfig{
+			BlockedCIDRs:     []string{"10.1.0.0/16"},
+			BlockedCountries: []string{"CN"},
+		})
+		assert.Equal(t, DenyCIDR, f.Check(netip.MustParseAddr("10.1.2.3"), geo), "in blocked CIDR")
+		assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("2.2.2.2"), geo), "in blocked country")
+		assert.Equal(t, Allow, f.Check(netip.MustParseAddr("3.3.3.3"), geo), "in neither blocklist")
+	})
+}
+
+// TestFilter_Check_AllowCIDRPlusAllowCountryDeniesGeolessLAN documents a trap
+// with all/AND mode: pairing an allowed CIDR (a private LAN) with an allowed
+// country denies the LAN source, because a private IP has no country in the
+// geo DB and an active country allowlist denies unknown countries. Under an
+// "any" mode the CIDR match alone would admit it. This is the strongest reason
+// allow-CIDR + allow-country usually wants OR, not AND.
+func TestFilter_Check_AllowCIDRPlusAllowCountryDeniesGeolessLAN(t *testing.T) {
+	geo := newMockGeo(map[string]string{}) // no entries: every lookup is unknown country
+	f := ParseFilter(FilterConfig{
+		AllowedCIDRs:     []string{"192.168.50.0/24"},
+		AllowedCountries: []string{"US"},
+	})
+
+	got := f.Check(netip.MustParseAddr("192.168.50.5"), geo)
+	assert.Equal(t, DenyCountry, got, "GAP: LAN source in allowed CIDR is denied by the country allowlist; any-mode should Allow")
+}
+
+func TestFilter_Check_AllowMatchAny(t *testing.T) {
+	bannedIP := "203.0.113.9"
+	geo := newMockGeo(map[string]string{
+		"1.1.1.1":      "US", // allowed country, outside allowed CIDR
+		"203.0.113.7":  "DE", // allowed CIDR, non-allowed country
+		"203.0.113.8":  "US", // both
+		bannedIP:       "US", // allowed CIDR, but CrowdSec-banned
+		"198.51.100.1": "CN", // neither
+		"2.2.2.2":      "CN", // blocked country, but in allowed CIDR
+	})
+
+	tests := []struct {
+		name   string
+		config FilterConfig
+		addr   string
+		geo    GeoResolver
+		want   Verdict
+	}{
+		{
+			name:   "in allowed CIDR only",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "203.0.113.7", geo: geo, want: Allow,
+		},
+		{
+			name:   "in allowed country only",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "1.1.1.1", geo: geo, want: Allow,
+		},
+		{
+			name:   "in both",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "203.0.113.8", geo: geo, want: Allow,
+		},
+		{
+			name:   "in neither",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "198.51.100.1", geo: geo, want: DenyCIDR,
+		},
+		{
+			name:   "geoless LAN admitted via CIDR (the #597 trap, fixed)",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"192.168.50.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "192.168.50.5", geo: newMockGeo(map[string]string{}), want: Allow,
+		},
+		{
+			name:   "CIDR match short-circuits geo when geo unavailable",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "203.0.113.7", geo: &unavailableGeo{}, want: Allow,
+		},
+		{
+			name:   "geo unavailable fails closed when CIDR does not match",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"203.0.113.0/24"}, AllowedCountries: []string{"US"}},
+			addr:   "1.1.1.1", geo: &unavailableGeo{}, want: DenyGeoUnavailable,
+		},
+		{
+			name:   "block gate wins over allowed CIDR (blocked country)",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCIDRs: []string{"0.0.0.0/0"}, BlockedCountries: []string{"CN"}},
+			addr:   "2.2.2.2", geo: geo, want: DenyCountry,
+		},
+		{
+			name:   "block gate wins over allowed country (blocked CIDR)",
+			config: FilterConfig{AllowMatch: AllowMatchAny, AllowedCountries: []string{"US"}, BlockedCIDRs: []string{"203.0.113.0/24"}},
+			addr:   "203.0.113.8", geo: geo, want: DenyCIDR,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			f := ParseFilter(tc.config)
+			assert.Equal(t, tc.want, f.Check(netip.MustParseAddr(tc.addr), tc.geo))
+		})
+	}
+}
+
+func TestFilter_Check_AllowMatchAny_CrowdSecStillRuns(t *testing.T) {
+	bannedIP := "203.0.113.9"
+	cs := &mockCrowdSec{decisions: map[string]*CrowdSecDecision{bannedIP: {Type: DecisionBan}}, ready: true}
+	geo := newMockGeo(map[string]string{bannedIP: "US", "203.0.113.7": "US"})
+
+	f := ParseFilter(FilterConfig{
+		AllowMatch:   AllowMatchAny,
+		AllowedCIDRs: []string{"203.0.113.0/24"},
+		CrowdSec:     cs,
+		CrowdSecMode: CrowdSecEnforce,
+	})
+	assert.Equal(t, DenyCrowdSecBan, f.Check(netip.MustParseAddr(bannedIP), geo), "CrowdSec ban denies even when allowlist admits")
+	assert.Equal(t, Allow, f.Check(netip.MustParseAddr("203.0.113.7"), geo), "clean IP in allowed CIDR is allowed")
+}
+
+func TestFilter_Check_UnknownAllowMatchDefaultsToAll(t *testing.T) {
+	// An unrecognized allow-combine mode must fall back to the restrictive
+	// AND default, never loosen access.
+	geo := newMockGeo(map[string]string{"203.0.113.7": "DE"})
+	f := ParseFilter(FilterConfig{
+		AllowMatch:       AllowMatch("bogus"),
+		AllowedCIDRs:     []string{"203.0.113.0/24"},
+		AllowedCountries: []string{"US"},
+	})
+	assert.Equal(t, AllowMatchAll, f.AllowMatch, "unknown mode normalizes to all")
+	assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("203.0.113.7"), geo), "AND semantics: in CIDR but wrong country denied")
+}
+
 func TestParseFilter_Empty(t *testing.T) {
 	f := ParseFilter(FilterConfig{})
 	assert.Nil(t, f)
@@ -552,3 +734,81 @@ func TestFilter_HasRestrictions_CrowdSec(t *testing.T) {
 	f2 := ParseFilter(FilterConfig{CrowdSec: nil, CrowdSecMode: CrowdSecEnforce})
 	assert.True(t, f2.HasRestrictions())
 }
+
+// countingGeo records how many times an address was resolved.
+type countingGeo struct {
+	countries map[string]string
+	lookups   int
+}
+
+func (c *countingGeo) LookupAddr(addr netip.Addr) geolocation.Result {
+	c.lookups++
+	return geolocation.Result{CountryCode: c.countries[addr.String()]}
+}
+
+func (c *countingGeo) Available() bool { return true }
+
+// The geo lookup is the expensive part of the check and runs per connection, so
+// "any" mode must resolve the country once and share it between the blocklist
+// and the allowlist, the way "all" mode does.
+func TestCheck_AnyResolvesCountryOnce(t *testing.T) {
+	tests := []struct {
+		name        string
+		ip          string
+		want        Verdict
+		wantLookups int
+	}{
+		{"blocked and allowed lists both active", "203.0.113.1", Allow, 1},
+		{"blocked country denies", "198.51.100.1", DenyCountry, 1},
+		{"neither allowlist matches", "192.0.2.1", DenyCIDR, 1},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			geo := &countingGeo{countries: map[string]string{
+				"203.0.113.1":  "US",
+				"198.51.100.1": "CN",
+				"192.0.2.1":    "FR",
+			}}
+			f := ParseFilter(FilterConfig{
+				AllowedCIDRs:     []string{"10.0.0.0/8"},
+				AllowedCountries: []string{"US"},
+				BlockedCountries: []string{"CN"},
+				AllowMatch:       AllowMatchAny,
+			})
+			require.NotNil(t, f)
+
+			assert.Equal(t, tt.want, f.Check(netip.MustParseAddr(tt.ip), geo))
+			assert.Equal(t, tt.wantLookups, geo.lookups, "the country must be resolved at most once per check")
+		})
+	}
+}
+
+// A matching allowed CIDR short-circuits the allowlist, so with no country
+// blocklist configured there is nothing left to resolve.
+func TestCheck_AnySkipsLookupWhenCIDRAdmits(t *testing.T) {
+	geo := &countingGeo{countries: map[string]string{"10.1.2.3": "US"}}
+	f := ParseFilter(FilterConfig{
+		AllowedCIDRs:     []string{"10.0.0.0/8"},
+		AllowedCountries: []string{"DE"},
+		AllowMatch:       AllowMatchAny,
+	})
+	require.NotNil(t, f)
+
+	assert.Equal(t, Allow, f.Check(netip.MustParseAddr("10.1.2.3"), geo))
+	assert.Zero(t, geo.lookups, "an admitted CIDR needs no geo lookup")
+}
+
+// The blocklist is a hard gate, so it is consulted even when a CIDR allowlist
+// already admitted the address.
+func TestCheck_AnyBlocklistOutranksAllowedCIDR(t *testing.T) {
+	geo := &countingGeo{countries: map[string]string{"10.1.2.3": "CN"}}
+	f := ParseFilter(FilterConfig{
+		AllowedCIDRs:     []string{"10.0.0.0/8"},
+		BlockedCountries: []string{"CN"},
+		AllowMatch:       AllowMatchAny,
+	})
+	require.NotNil(t, f)
+
+	assert.Equal(t, DenyCountry, f.Check(netip.MustParseAddr("10.1.2.3"), geo))
+	assert.Equal(t, 1, geo.lookups)
+}

proxy/lifecycle.go

@@ -126,6 +126,23 @@ type Config struct {
 	// CrowdSecAPIKey is the CrowdSec bouncer API key. Empty disables
 	// CrowdSec.
 	CrowdSecAPIKey string
+	// CrowdSecAppSecURL is the CrowdSec AppSec (WAF) endpoint. Empty disables
+	// HTTP request inspection.
+	CrowdSecAppSecURL string
+	// CrowdSecAppSecTimeout bounds a single AppSec inspection call. Zero falls
+	// back to the internal default.
+	CrowdSecAppSecTimeout time.Duration
+	// CrowdSecAppSecMaxBodyBytes caps the request body mirrored to AppSec.
+	// Zero falls back to the internal default; negative forwards no body.
+	CrowdSecAppSecMaxBodyBytes int64
+	// CrowdSecAppSecMaxConcurrent bounds AppSec inspections in flight toward
+	// the engine. Zero falls back to the internal default; negative removes
+	// the bound.
+	CrowdSecAppSecMaxConcurrent int
+	// MiddlewareCaptureBudgetBytes bounds the total request-body buffering in
+	// flight across the proxy, shared by AppSec inspection and the
+	// agent-network capture. Zero falls back to the internal default.
+	MiddlewareCaptureBudgetBytes int64
 }
 
 // New builds a Server from cfg without performing any I/O. No goroutines
@@ -135,42 +152,47 @@ type Config struct {
 // directly) byte-for-byte equivalent.
 func New(ctx context.Context, cfg Config) *Server {
 	return &Server{
-		ctx:                      ctx,
-		ListenAddr:               cfg.ListenAddr,
-		ID:                       cfg.ID,
-		Logger:                   cfg.Logger,
-		Version:                  cfg.Version,
-		ProxyURL:                 cfg.ProxyURL,
-		ManagementAddress:        cfg.ManagementAddress,
-		ProxyToken:               cfg.ProxyToken,
-		CertificateDirectory:     cfg.CertificateDirectory,
-		CertificateFile:          cfg.CertificateFile,
-		CertificateKeyFile:       cfg.CertificateKeyFile,
-		GenerateACMECertificates: cfg.GenerateACMECertificates,
-		ACMEChallengeAddress:     cfg.ACMEChallengeAddress,
-		ACMEDirectory:            cfg.ACMEDirectory,
-		ACMEEABKID:               cfg.ACMEEABKID,
-		ACMEEABHMACKey:           cfg.ACMEEABHMACKey,
-		ACMEChallengeType:        cfg.ACMEChallengeType,
-		CertLockMethod:           cfg.CertLockMethod,
-		WildcardCertDir:          cfg.WildcardCertDir,
-		DebugEndpointEnabled:     cfg.DebugEndpointEnabled,
-		DebugEndpointAddress:     cfg.DebugEndpointAddress,
-		HealthAddress:            cfg.HealthAddr,
-		ForwardedProto:           cfg.ForwardedProto,
-		TrustedProxies:           cfg.TrustedProxies,
-		WireguardPort:            cfg.WireguardPort,
-		ProxyProtocol:            cfg.ProxyProtocol,
-		PreSharedKey:             cfg.PreSharedKey,
-		Performance:              cfg.Performance,
-		SupportsCustomPorts:      cfg.SupportsCustomPorts,
-		RequireSubdomain:         cfg.RequireSubdomain,
-		Private:                  cfg.Private,
-		MaxDialTimeout:           cfg.MaxDialTimeout,
-		MaxSessionIdleTimeout:    cfg.MaxSessionIdleTimeout,
-		MappingBatchWatchdog:     cfg.MappingBatchWatchdog,
-		GeoDataDir:               cfg.GeoDataDir,
-		CrowdSecAPIURL:           cfg.CrowdSecAPIURL,
-		CrowdSecAPIKey:           cfg.CrowdSecAPIKey,
+		ctx:                          ctx,
+		ListenAddr:                   cfg.ListenAddr,
+		ID:                           cfg.ID,
+		Logger:                       cfg.Logger,
+		Version:                      cfg.Version,
+		ProxyURL:                     cfg.ProxyURL,
+		ManagementAddress:            cfg.ManagementAddress,
+		ProxyToken:                   cfg.ProxyToken,
+		CertificateDirectory:         cfg.CertificateDirectory,
+		CertificateFile:              cfg.CertificateFile,
+		CertificateKeyFile:           cfg.CertificateKeyFile,
+		GenerateACMECertificates:     cfg.GenerateACMECertificates,
+		ACMEChallengeAddress:         cfg.ACMEChallengeAddress,
+		ACMEDirectory:                cfg.ACMEDirectory,
+		ACMEEABKID:                   cfg.ACMEEABKID,
+		ACMEEABHMACKey:               cfg.ACMEEABHMACKey,
+		ACMEChallengeType:            cfg.ACMEChallengeType,
+		CertLockMethod:               cfg.CertLockMethod,
+		WildcardCertDir:              cfg.WildcardCertDir,
+		DebugEndpointEnabled:         cfg.DebugEndpointEnabled,
+		DebugEndpointAddress:         cfg.DebugEndpointAddress,
+		HealthAddress:                cfg.HealthAddr,
+		ForwardedProto:               cfg.ForwardedProto,
+		TrustedProxies:               cfg.TrustedProxies,
+		WireguardPort:                cfg.WireguardPort,
+		ProxyProtocol:                cfg.ProxyProtocol,
+		PreSharedKey:                 cfg.PreSharedKey,
+		Performance:                  cfg.Performance,
+		SupportsCustomPorts:          cfg.SupportsCustomPorts,
+		RequireSubdomain:             cfg.RequireSubdomain,
+		Private:                      cfg.Private,
+		MaxDialTimeout:               cfg.MaxDialTimeout,
+		MaxSessionIdleTimeout:        cfg.MaxSessionIdleTimeout,
+		MappingBatchWatchdog:         cfg.MappingBatchWatchdog,
+		GeoDataDir:                   cfg.GeoDataDir,
+		CrowdSecAPIURL:               cfg.CrowdSecAPIURL,
+		CrowdSecAPIKey:               cfg.CrowdSecAPIKey,
+		CrowdSecAppSecURL:            cfg.CrowdSecAppSecURL,
+		CrowdSecAppSecTimeout:        cfg.CrowdSecAppSecTimeout,
+		CrowdSecAppSecMaxBodyBytes:   cfg.CrowdSecAppSecMaxBodyBytes,
+		CrowdSecAppSecMaxConcurrent:  cfg.CrowdSecAppSecMaxConcurrent,
+		MiddlewareCaptureBudgetBytes: cfg.MiddlewareCaptureBudgetBytes,
 	}
 }

proxy/lifecycle_test.go

@@ -0,0 +1,45 @@
+package proxy
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+)
+
+// New maps Config onto Server field by field, and a field left out of that
+// literal still compiles: the knob is simply parsed and then dropped, so an
+// operator setting it sees the default with no error anywhere. These assertions
+// are the only thing standing between a new setting and that silent no-op.
+func TestNew_ForwardsOperatorTuning(t *testing.T) {
+	cfg := Config{
+		ManagementAddress:            "http://localhost:8080",
+		ProxyToken:                   "token",
+		CrowdSecAPIURL:               "http://crowdsec:8080/",
+		CrowdSecAPIKey:               "key",
+		CrowdSecAppSecURL:            "http://crowdsec:7422/",
+		CrowdSecAppSecTimeout:        321 * time.Millisecond,
+		CrowdSecAppSecMaxBodyBytes:   4321,
+		CrowdSecAppSecMaxConcurrent:  17,
+		MiddlewareCaptureBudgetBytes: 5 << 20,
+		MaxDialTimeout:               7 * time.Second,
+		MaxSessionIdleTimeout:        11 * time.Second,
+		GeoDataDir:                   "/var/lib/geo",
+	}
+
+	srv := New(context.Background(), cfg)
+	require.NotNil(t, srv)
+
+	assert.Equal(t, cfg.CrowdSecAPIURL, srv.CrowdSecAPIURL)
+	assert.Equal(t, cfg.CrowdSecAPIKey, srv.CrowdSecAPIKey)
+	assert.Equal(t, cfg.CrowdSecAppSecURL, srv.CrowdSecAppSecURL)
+	assert.Equal(t, cfg.CrowdSecAppSecTimeout, srv.CrowdSecAppSecTimeout)
+	assert.Equal(t, cfg.CrowdSecAppSecMaxBodyBytes, srv.CrowdSecAppSecMaxBodyBytes)
+	assert.Equal(t, cfg.CrowdSecAppSecMaxConcurrent, srv.CrowdSecAppSecMaxConcurrent)
+	assert.Equal(t, cfg.MiddlewareCaptureBudgetBytes, srv.MiddlewareCaptureBudgetBytes)
+	assert.Equal(t, cfg.MaxDialTimeout, srv.MaxDialTimeout)
+	assert.Equal(t, cfg.MaxSessionIdleTimeout, srv.MaxSessionIdleTimeout)
+	assert.Equal(t, cfg.GeoDataDir, srv.GeoDataDir)
+}

proxy/management_integration_test.go

@@ -240,6 +240,10 @@ func (m *testProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
+func (m *testProxyManager) ClusterSupportsAppSec(_ context.Context, _ string) *bool {
+	return nil
+}
+
 func (m *testProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
 	return nil
 }
@@ -562,16 +566,11 @@ func TestIntegration_ProxyConnection_ReconnectDoesNotDuplicateState(t *testing.T
 				addMappingCalls.Add(1)
 
 				// Apply to real auth middleware (idempotent)
-				err := authMw.AddDomain(
-					mapping.GetDomain(),
-					nil,
-					"",
-					0,
-					proxytypes.AccountID(mapping.GetAccountId()),
-					proxytypes.ServiceID(mapping.GetId()),
-					nil,
-					mapping.GetPrivate(),
-				)
+				err := authMw.AddDomain(mapping.GetDomain(), auth.DomainSettings{
+					AccountID: proxytypes.AccountID(mapping.GetAccountId()),
+					ServiceID: proxytypes.ServiceID(mapping.GetId()),
+					Private:   mapping.GetPrivate(),
+				})
 				require.NoError(t, err)
 
 				// Apply to real proxy (idempotent)

proxy/server.go

@@ -45,6 +45,7 @@ import (
 	"github.com/netbirdio/netbird/client/embed"
 	"github.com/netbirdio/netbird/proxy/internal/accesslog"
 	"github.com/netbirdio/netbird/proxy/internal/acme"
+	"github.com/netbirdio/netbird/proxy/internal/appsec"
 	"github.com/netbirdio/netbird/proxy/internal/auth"
 	"github.com/netbirdio/netbird/proxy/internal/certwatch"
 	"github.com/netbirdio/netbird/proxy/internal/conntrack"
@@ -126,6 +127,10 @@ type Server struct {
 	crowdsecMu       sync.Mutex
 	crowdsecServices map[types.ServiceID]bool
 
+	// appsecClient is the shared CrowdSec AppSec client, nil when no AppSec
+	// endpoint is configured. Stateless, so it needs no per-service lifecycle.
+	appsecClient *appsec.Client
+
 	// routerReady is closed once mainRouter is fully initialized.
 	// The mapping worker waits on this before processing updates.
 	routerReady chan struct{}
@@ -238,6 +243,20 @@ type Server struct {
 	CrowdSecAPIURL string
 	// CrowdSecAPIKey is the CrowdSec bouncer API key. Empty disables CrowdSec.
 	CrowdSecAPIKey string
+	// CrowdSecAppSecURL is the CrowdSec AppSec (WAF) endpoint, e.g.
+	// http://127.0.0.1:7422/. Empty disables request inspection. Requires
+	// CrowdSecAPIKey, which the AppSec component validates against LAPI.
+	CrowdSecAppSecURL string
+	// CrowdSecAppSecTimeout bounds a single AppSec inspection call.
+	// Zero means appsec.DefaultTimeout.
+	CrowdSecAppSecTimeout time.Duration
+	// CrowdSecAppSecMaxBodyBytes caps the request body mirrored to the AppSec
+	// engine. Zero means appsec.DefaultMaxBodyBytes; negative disables body
+	// forwarding, leaving header and URI inspection.
+	CrowdSecAppSecMaxBodyBytes int64
+	// CrowdSecAppSecMaxConcurrent bounds AppSec inspections in flight. Zero
+	// means appsec.DefaultMaxConcurrent; negative removes the bound.
+	CrowdSecAppSecMaxConcurrent int
 	// MaxSessionIdleTimeout caps the per-service session idle timeout.
 	// Zero means no cap (the proxy honors whatever management sends).
 	// Set via NB_PROXY_MAX_SESSION_IDLE_TIMEOUT for shared deployments.
@@ -380,6 +399,13 @@ func (s *Server) Start(ctx context.Context) error {
 
 	s.crowdsecRegistry = crowdsec.NewRegistry(s.CrowdSecAPIURL, s.CrowdSecAPIKey, log.NewEntry(s.Logger))
 	s.crowdsecServices = make(map[types.ServiceID]bool)
+	// Must precede the mapping worker: the worker opens the management stream
+	// and reports proxyCapabilities, which reads appsecClient. Building it
+	// afterwards would both race the read and, when the worker won, advertise
+	// the proxy as AppSec-incapable for the lifetime of that stream.
+	if err := s.initAppSec(); err != nil {
+		return err
+	}
 
 	go s.newManagementMappingWorker(runCtx, s.mgmtClient)
 
@@ -407,6 +433,7 @@ func (s *Server) Start(ctx context.Context) error {
 	}()
 
 	s.auth = auth.NewMiddleware(s.Logger, s.mgmtClient, s.geo)
+	s.auth.SetAppSec(s.appsecClient)
 	s.accessLog = accesslog.NewLogger(s.mgmtClient, s.Logger, s.TrustedProxies)
 
 	s.startDebugEndpoint()
@@ -1270,6 +1297,7 @@ func (s *Server) newManagementMappingWorker(ctx context.Context, client proto.Pr
 
 func (s *Server) proxyCapabilities() *proto.ProxyCapabilities {
 	supportsCrowdSec := s.crowdsecRegistry.Available()
+	supportsAppSec := s.appsecClient != nil
 	privateCapability := s.Private
 	// Always true: this build enforces ProxyMapping.private via the auth middleware.
 	supportsPrivateService := true
@@ -1277,6 +1305,7 @@ func (s *Server) proxyCapabilities() *proto.ProxyCapabilities {
 		SupportsCustomPorts:    &s.SupportsCustomPorts,
 		RequireSubdomain:       &s.RequireSubdomain,
 		SupportsCrowdsec:       &supportsCrowdSec,
+		SupportsAppsec:         &supportsAppSec,
 		Private:                &privateCapability,
 		SupportsPrivateService: &supportsPrivateService,
 	}
@@ -1900,10 +1929,72 @@ func (s *Server) parseRestrictions(mapping *proto.ProxyMapping) *restrict.Filter
 		BlockedCountries: r.GetBlockedCountries(),
 		CrowdSec:         checker,
 		CrowdSecMode:     csMode,
+		AllowMatch:       restrict.AllowMatch(r.GetAllowMatch()),
 		Logger:           log.NewEntry(s.Logger),
 	})
 }
 
+// initAppSec builds the shared AppSec client when an endpoint is configured.
+// A configured-but-invalid endpoint is a startup error rather than a silent
+// downgrade: services asking for enforce would otherwise fail closed on every
+// request with no indication why.
+//
+// Runs before the management stream opens so the reported capability is stable;
+// the auth middleware picks the client up separately once it exists.
+func (s *Server) initAppSec() error {
+	if s.CrowdSecAppSecURL == "" {
+		return nil
+	}
+	if s.CrowdSecAPIKey == "" {
+		return errors.New("crowdsec appsec url is set but the crowdsec api key is empty")
+	}
+
+	// Share the middleware capture budget rather than opening a second pool:
+	// AppSec buffers before authentication, so its ceiling has to count against
+	// the same proxy-wide allowance the body tap draws from.
+	var budget appsec.Budget
+	if s.middlewareManager != nil {
+		budget = s.middlewareManager.Budget()
+	}
+
+	client, err := appsec.New(appsec.Config{
+		URL:           s.CrowdSecAppSecURL,
+		APIKey:        s.CrowdSecAPIKey,
+		Timeout:       s.CrowdSecAppSecTimeout,
+		MaxBodyBytes:  s.CrowdSecAppSecMaxBodyBytes,
+		MaxConcurrent: s.CrowdSecAppSecMaxConcurrent,
+		Budget:        budget,
+		Logger:        log.NewEntry(s.Logger),
+	})
+	if err != nil {
+		return fmt.Errorf("init crowdsec appsec: %w", err)
+	}
+
+	s.appsecClient = client
+	s.Logger.Infof("CrowdSec AppSec inspection available at %s", s.CrowdSecAppSecURL)
+	return nil
+}
+
+// appSecMode resolves the per-service AppSec mode. A service asking for
+// inspection on a proxy with no AppSec endpoint keeps its mode so the auth
+// middleware fails closed for enforce, mirroring the CrowdSec behavior.
+func (s *Server) appSecMode(mapping *proto.ProxyMapping) restrict.AppSecMode {
+	raw := mapping.GetAccessRestrictions().GetAppsecMode()
+	mode := restrict.ParseAppSecMode(raw)
+	// An unrecognized value disables inspection, which is the safe default but a
+	// silent one: with a newer management and an older proxy, a mode this build
+	// does not know would look identical to "off" on a service the operator set
+	// to enforce. Say so rather than leaving it to be discovered.
+	if mode == restrict.AppSecOff && raw != "" && raw != "off" {
+		s.Logger.Warnf("service %s requests unrecognized AppSec mode %q; this build supports %q and %q, so inspection is disabled",
+			mapping.GetId(), raw, restrict.AppSecEnforce, restrict.AppSecObserve)
+	}
+	if mode.Enabled() && s.appsecClient == nil {
+		s.Logger.Warnf("service %s requests AppSec mode %q but proxy has no AppSec endpoint configured", mapping.GetId(), mode)
+	}
+	return mode
+}
+
 // releaseCrowdSec releases the CrowdSec bouncer reference for the given
 // service if it had one.
 func (s *Server) releaseCrowdSec(svcID types.ServiceID) {
@@ -2070,7 +2161,17 @@ func (s *Server) updateMapping(ctx context.Context, mapping *proto.ProxyMapping)
 	s.warnIfGeoUnavailable(mapping.GetDomain(), mapping.GetAccessRestrictions())
 
 	maxSessionAge := time.Duration(mapping.GetAuth().GetMaxSessionAgeSeconds()) * time.Second
-	if err := s.auth.AddDomain(mapping.GetDomain(), schemes, mapping.GetAuth().GetSessionKey(), maxSessionAge, accountID, svcID, ipRestrictions, mapping.GetPrivate()); err != nil {
+	settings := auth.DomainSettings{
+		Schemes:           schemes,
+		SessionPublicKey:  mapping.GetAuth().GetSessionKey(),
+		SessionExpiration: maxSessionAge,
+		AccountID:         accountID,
+		ServiceID:         svcID,
+		IPRestrictions:    ipRestrictions,
+		Private:           mapping.GetPrivate(),
+		AppSecMode:        s.appSecMode(mapping),
+	}
+	if err := s.auth.AddDomain(mapping.GetDomain(), settings); err != nil {
 		return fmt.Errorf("auth setup for domain %s: %w", mapping.GetDomain(), err)
 	}
 	m := s.protoToMapping(ctx, mapping)

shared/management/client/grpc.go

@@ -21,6 +21,8 @@ import (
 	"google.golang.org/grpc/connectivity"
 
 	nbgrpc "github.com/netbirdio/netbird/client/grpc"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -62,6 +64,13 @@ type GrpcClient struct {
 	connStateCallbackLock sync.RWMutex
 	serverURL             string
 
+	// netState gates the stream retry loop on OS-reported network
+	// availability; nil (the default) disables gating.
+	netState *netstate.State
+
+	// sweeper cuts the transport connections on network change; nil disables it.
+	sweeper *netsweep.Sweeper
+
 	// syncStreamErr holds the last Sync stream error, or nil while the stream
 	// is established and healthy. GetServerKey succeeds even when the peer
 	// cannot sync (e.g. the server returns "settings not found"), so the
@@ -111,16 +120,43 @@ func MaxRecvMsgSize() int {
 	return size
 }
 
+// Option configures optional GrpcClient behavior.
+type Option func(*GrpcClient)
+
+// WithNetworkState injects the OS network availability state that gates the
+// stream retry loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) Option {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) Option {
+	return func(c *GrpcClient) { c.sweeper = sweeper }
+}
+
 // NewClient creates a new client to Management service
-func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
-	var conn *grpc.ClientConn
+func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool, opts ...Option) (*GrpcClient, error) {
+	// Options apply before dialing: the sweeper must wrap the first connection too.
+	c := &GrpcClient{
+		key:                   ourPrivateKey,
+		ctx:                   ctx,
+		connStateCallbackLock: sync.RWMutex{},
+		serverURL:             addr,
+	}
+	for _, opt := range opts {
+		opt(c)
+	}
 
 	var extraOpts []grpc.DialOption
 	if maxSize := MaxRecvMsgSize(); maxSize > 0 {
 		extraOpts = append(extraOpts, grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(maxSize)))
 		log.Infof("management gRPC max receive message size set to %d bytes", maxSize)
 	}
+	if c.sweeper != nil {
+		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
+	}
 
+	var conn *grpc.ClientConn
 	operation := func() error {
 		var err error
 		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.ManagementComponent, extraOpts...)
@@ -136,16 +172,9 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
 		return nil, err
 	}
 
-	realClient := proto.NewManagementServiceClient(conn)
-
-	return &GrpcClient{
-		key:                   ourPrivateKey,
-		realClient:            realClient,
-		ctx:                   ctx,
-		conn:                  conn,
-		connStateCallbackLock: sync.RWMutex{},
-		serverURL:             addr,
-	}, nil
+	c.conn = conn
+	c.realClient = proto.NewManagementServiceClient(conn)
+	return c, nil
 }
 
 // GetServerURL returns the management server URL
@@ -206,16 +235,33 @@ func (c *GrpcClient) withMgmtStream(
 	ctx context.Context,
 	handler func(ctx context.Context, serverPubKey wgtypes.Key, backOff backoff.BackOff) error,
 ) error {
-	backOff := defaultBackoff(ctx)
+	backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
 	operation := func() error {
-		log.Debugf("management connection state %v", c.conn.GetState())
-		connState := c.conn.GetState()
+		// suspend reconnect attempts while the OS reports no usable network.
+		// Wait only errors on a cancelled context, which means shutdown, so
+		// stop the loop without reporting a failure.
+		if waited, err := c.netState.Wait(ctx); err != nil {
+			log.Debugf("management connection context has been canceled while offline, this usually indicates shutdown")
+			return nil //nolint:nilerr // a cancelled context means shutdown, not a retryable failure
+		} else if waited {
+			backOff.Reset()
+		}
 
+		connState := c.conn.GetState()
+		log.Debugf("management connection state %v", connState)
 		if connState == connectivity.Shutdown {
 			return backoff.Permanent(fmt.Errorf("connection to management has been shut down"))
-		} else if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+		}
+		if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+			// A dial may already be in flight (e.g. the other stream triggered
+			// it after a network change); wait for it to settle and proceed if
+			// the channel became usable, instead of burning a backoff round on
+			// a successful dial. A failed dial errors out as before.
 			c.conn.WaitForStateChange(ctx, connState)
-			return fmt.Errorf("connection to management is not ready and in %s state", connState)
+			connState = c.conn.GetState()
+			if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+				return fmt.Errorf("connection to management is not ready and in %s state", connState)
+			}
 		}
 
 		serverPubKey, err := c.getServerPublicKey()
@@ -227,7 +273,7 @@ func (c *GrpcClient) withMgmtStream(
 		return handler(ctx, *serverPubKey, backOff)
 	}
 
-	err := backoff.Retry(operation, backOff)
+	err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
 	if err != nil {
 		log.Warnf("exiting the Management service connection retry loop due to the unrecoverable error: %s", err)
 	}

shared/management/http/api/openapi.yml

@@ -3380,6 +3380,30 @@ components:
             - "observe"
           default: "off"
           description: CrowdSec IP reputation mode. Only available when the proxy cluster supports CrowdSec.
+        allow_match:
+          type: string
+          enum:
+            - "all"
+            - "any"
+          default: "all"
+          description: >-
+            How the allowlists (allowed_cidrs, allowed_countries) combine.
+            "all" (default) requires a connection to match every configured
+            allowlist (AND); "any" requires it to match at least one (OR), e.g.
+            an allowed country OR an allowed CIDR. Blocklists always reject on
+            match regardless of this setting.
+        appsec_mode:
+          type: string
+          enum:
+            - "off"
+            - "enforce"
+            - "observe"
+          default: "off"
+          description: >-
+            CrowdSec AppSec (WAF) request inspection mode. Only available when
+            the proxy cluster supports AppSec, and only applied to HTTP
+            services. "enforce" blocks requests the WAF flags; "observe" records
+            the verdict in the access log without blocking.
     PasswordAuthConfig:
       type: object
       properties:
@@ -3516,6 +3540,10 @@ components:
           type: boolean
           description: Whether all active proxies in the cluster have CrowdSec configured
           example: false
+        supports_appsec:
+          type: boolean
+          description: Whether all active proxies in the cluster have a CrowdSec AppSec (WAF) endpoint configured
+          example: false
         private:
           type: boolean
           description: True when at least one connected proxy in this cluster is running embedded in a netbird client (`netbird proxy`) and serving over a WireGuard tunnel. Lets the dashboard distinguish per-peer / private clusters from centralised ones.
@@ -3575,6 +3603,10 @@ components:
           type: boolean
           description: Whether the proxy cluster has CrowdSec configured
           example: false
+        supports_appsec:
+          type: boolean
+          description: Whether the proxy cluster has a CrowdSec AppSec (WAF) endpoint configured
+          example: false
         supports_private:
           type: boolean
           description: Whether the proxy cluster supports private (NetBird-only) services. True when at least one connected proxy in the cluster runs embedded in a netbird client.

shared/management/http/api/types.gen.go

@@ -17,6 +17,45 @@ const (
 	TokenAuthScopes  tokenAuthContextKey  = "TokenAuth.Scopes"
 )
 
+// Defines values for AccessRestrictionsAllowMatch.
+const (
+	AccessRestrictionsAllowMatchAll AccessRestrictionsAllowMatch = "all"
+	AccessRestrictionsAllowMatchAny AccessRestrictionsAllowMatch = "any"
+)
+
+// Valid indicates whether the value is a known member of the AccessRestrictionsAllowMatch enum.
+func (e AccessRestrictionsAllowMatch) Valid() bool {
+	switch e {
+	case AccessRestrictionsAllowMatchAll:
+		return true
+	case AccessRestrictionsAllowMatchAny:
+		return true
+	default:
+		return false
+	}
+}
+
+// Defines values for AccessRestrictionsAppsecMode.
+const (
+	AccessRestrictionsAppsecModeEnforce AccessRestrictionsAppsecMode = "enforce"
+	AccessRestrictionsAppsecModeObserve AccessRestrictionsAppsecMode = "observe"
+	AccessRestrictionsAppsecModeOff     AccessRestrictionsAppsecMode = "off"
+)
+
+// Valid indicates whether the value is a known member of the AccessRestrictionsAppsecMode enum.
+func (e AccessRestrictionsAppsecMode) Valid() bool {
+	switch e {
+	case AccessRestrictionsAppsecModeEnforce:
+		return true
+	case AccessRestrictionsAppsecModeObserve:
+		return true
+	case AccessRestrictionsAppsecModeOff:
+		return true
+	default:
+		return false
+	}
+}
+
 // Defines values for AccessRestrictionsCrowdsecMode.
 const (
 	AccessRestrictionsCrowdsecModeEnforce AccessRestrictionsCrowdsecMode = "enforce"
@@ -1534,12 +1573,18 @@ func (e PutApiIntegrationsMspTenantsIdInviteJSONBodyValue) Valid() bool {
 
 // AccessRestrictions Connection-level access restrictions based on IP address or geography. Applies to both HTTP and L4 services.
 type AccessRestrictions struct {
+	// AllowMatch How the allowlists (allowed_cidrs, allowed_countries) combine. "all" (default) requires a connection to match every configured allowlist (AND); "any" requires it to match at least one (OR), e.g. an allowed country OR an allowed CIDR. Blocklists always reject on match regardless of this setting.
+	AllowMatch *AccessRestrictionsAllowMatch `json:"allow_match,omitempty"`
+
 	// AllowedCidrs CIDR allowlist. If non-empty, only IPs matching these CIDRs are allowed.
 	AllowedCidrs *[]string `json:"allowed_cidrs,omitempty"`
 
 	// AllowedCountries ISO 3166-1 alpha-2 country codes to allow. If non-empty, only these countries are permitted.
 	AllowedCountries *[]string `json:"allowed_countries,omitempty"`
 
+	// AppsecMode CrowdSec AppSec (WAF) request inspection mode. Only available when the proxy cluster supports AppSec, and only applied to HTTP services. "enforce" blocks requests the WAF flags; "observe" records the verdict in the access log without blocking.
+	AppsecMode *AccessRestrictionsAppsecMode `json:"appsec_mode,omitempty"`
+
 	// BlockedCidrs CIDR blocklist. Connections from these CIDRs are rejected. Evaluated after allowed_cidrs.
 	BlockedCidrs *[]string `json:"blocked_cidrs,omitempty"`
 
@@ -1550,6 +1595,12 @@ type AccessRestrictions struct {
 	CrowdsecMode *AccessRestrictionsCrowdsecMode `json:"crowdsec_mode,omitempty"`
 }
 
+// AccessRestrictionsAllowMatch How the allowlists (allowed_cidrs, allowed_countries) combine. "all" (default) requires a connection to match every configured allowlist (AND); "any" requires it to match at least one (OR), e.g. an allowed country OR an allowed CIDR. Blocklists always reject on match regardless of this setting.
+type AccessRestrictionsAllowMatch string
+
+// AccessRestrictionsAppsecMode CrowdSec AppSec (WAF) request inspection mode. Only available when the proxy cluster supports AppSec, and only applied to HTTP services. "enforce" blocks requests the WAF flags; "observe" records the verdict in the access log without blocking.
+type AccessRestrictionsAppsecMode string
+
 // AccessRestrictionsCrowdsecMode CrowdSec IP reputation mode. Only available when the proxy cluster supports CrowdSec.
 type AccessRestrictionsCrowdsecMode string
 
@@ -4773,6 +4824,9 @@ type ProxyCluster struct {
 	// RequireSubdomain Whether services on this cluster must include a subdomain label
 	RequireSubdomain *bool `json:"require_subdomain,omitempty"`
 
+	// SupportsAppsec Whether all active proxies in the cluster have a CrowdSec AppSec (WAF) endpoint configured
+	SupportsAppsec *bool `json:"supports_appsec,omitempty"`
+
 	// SupportsCrowdsec Whether all active proxies in the cluster have CrowdSec configured
 	SupportsCrowdsec *bool `json:"supports_crowdsec,omitempty"`
 
@@ -4841,6 +4895,9 @@ type ReverseProxyDomain struct {
 	// RequireSubdomain Whether a subdomain label is required in front of this domain. When true, the domain cannot be used bare.
 	RequireSubdomain *bool `json:"require_subdomain,omitempty"`
 
+	// SupportsAppsec Whether the proxy cluster has a CrowdSec AppSec (WAF) endpoint configured
+	SupportsAppsec *bool `json:"supports_appsec,omitempty"`
+
 	// SupportsCrowdsec Whether the proxy cluster has CrowdSec configured
 	SupportsCrowdsec *bool `json:"supports_crowdsec,omitempty"`
 

shared/management/proto/proxy_service.proto

@@ -73,6 +73,10 @@ message ProxyCapabilities {
   optional bool private = 4;
   // Whether the proxy enforces ProxyMapping.private (fails closed on ValidateTunnelPeer failure). Management MUST NOT stream private mappings to proxies that don't claim this.
   optional bool supports_private_service = 5;
+  // Whether the proxy has a CrowdSec AppSec (WAF) endpoint configured and can
+  // inspect HTTP requests. Independent of supports_crowdsec: AppSec is a
+  // separate endpoint on the Security Engine and applies to HTTP services only.
+  optional bool supports_appsec = 6;
 }
 
 // GetMappingUpdateRequest is sent to initialise a mapping stream.
@@ -203,6 +207,14 @@ message AccessRestrictions {
   repeated string blocked_countries = 4;
   // CrowdSec IP reputation mode: "", "off", "enforce", or "observe".
   string crowdsec_mode = 5;
+  // How the allowlists (CIDR, country) combine: "" or "all" require matching
+  // every allowlist (AND); "any" requires matching at least one (OR).
+  // Blocklists are always a hard-deny gate, independent of this mode.
+  string allow_match = 6;
+  // CrowdSec AppSec (WAF) request inspection mode: "", "off", "enforce", or
+  // "observe". HTTP services only: "enforce" and "observe" are rejected at
+  // validation for TCP/UDP/TLS services, which carry no requests to inspect.
+  string appsec_mode = 7;
 }
 
 message ProxyMapping {

shared/relay/client/client.go

@@ -14,6 +14,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	"github.com/netbirdio/netbird/shared/relay/client/dialer"
 	netErr "github.com/netbirdio/netbird/shared/relay/client/dialer/net"
@@ -184,6 +185,10 @@ type Client struct {
 	// datagram-sized transport is avoided on subsequent connects. Shared via
 	// the manager.
 	transportFallback *transportFallback
+
+	// sweeper cuts the relay connection on network change; the read loop
+	// reports the disconnect and the guard reconnects. Shared via the manager.
+	sweeper *netsweep.Sweeper
 	// datagramFallbackTriggered guards a single fallback per connection so a
 	// burst of oversized datagrams triggers one reconnect, not many.
 	datagramFallbackTriggered atomic.Bool
@@ -393,6 +398,12 @@ func (c *Client) Close() error {
 }
 
 func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
+	// A sweep cancels this context, so a dial started on the old network
+	// aborts instead of waiting out its handshake timeout.
+	dial := c.sweeper.StartDial(ctx)
+	defer dial.Release()
+	ctx = dial.Ctx()
+
 	mode := transportModeFromEnv()
 	dialers := c.getDialers(mode)
 
@@ -417,12 +428,19 @@ func (c *Client) connect(ctx context.Context) (*RelayAddr, error) {
 			return nil, fmt.Errorf("dial via FQDN: %w", err)
 		}
 	}
-	c.relayConn = conn
-	c.datagramFallbackTriggered.Store(false)
+	// Read the transport off the concrete connection: the sweeper's wrapper
+	// embeds net.Conn only, so it does not promote Protocol().
 	if tc, ok := conn.(transportConn); ok {
 		c.transport = tc.Protocol()
 	}
 
+	conn, err := dial.WrapConn(conn)
+	if err != nil {
+		return nil, fmt.Errorf("register connection: %w", err)
+	}
+	c.relayConn = conn
+	c.datagramFallbackTriggered.Store(false)
+
 	instanceURL, err := c.handShake(ctx)
 	if err != nil {
 		cErr := conn.Close()

shared/relay/client/guard.go

@@ -7,9 +7,22 @@ import (
 
 	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
+
+	"github.com/netbirdio/netbird/client/netstate"
 )
 
-const defaultMaxBackoffInterval = 60 * time.Second
+const (
+	defaultMaxBackoffInterval = 60 * time.Second
+
+	// quickReconnectBudget bounds how long a quick reconnect waits for the
+	// network before handing the retry over to the ticker.
+	quickReconnectBudget = 1500 * time.Millisecond
+
+	// verdictSettleWindow is how long an online verdict must hold before it
+	// is trusted: the disconnect often precedes the OS offline flag by a few
+	// milliseconds.
+	verdictSettleWindow = 200 * time.Millisecond
+)
 
 // Guard manage the reconnection tries to the Relay server in case of disconnection event.
 type Guard struct {
@@ -22,14 +35,19 @@ type Guard struct {
 	// attempts.
 	maxBackoffInterval time.Duration
 
+	// netState gates reconnect attempts on OS-reported network availability;
+	// nil disables gating.
+	netState *netstate.State
+
 	// lastErr is the error from the most recent failed reconnect attempt,
 	// surfaced as the home relay status while disconnected.
 	lastErr atomic.Pointer[error]
 }
 
 // NewGuard creates a new guard for the relay client. A non-positive
-// maxBackoffInterval falls back to defaultMaxBackoffInterval.
-func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration) *Guard {
+// maxBackoffInterval falls back to defaultMaxBackoffInterval. A nil netState
+// disables network availability gating.
+func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration, netState *netstate.State) *Guard {
 	if maxBackoffInterval <= 0 {
 		maxBackoffInterval = defaultMaxBackoffInterval
 	}
@@ -38,6 +56,7 @@ func NewGuard(sp *ServerPicker, maxBackoffInterval time.Duration) *Guard {
 		OnReconnected:      make(chan struct{}, 1),
 		serverPicker:       sp,
 		maxBackoffInterval: maxBackoffInterval,
+		netState:           netState,
 	}
 	return g
 }
@@ -70,11 +89,21 @@ func (g *Guard) StartReconnectTrys(ctx context.Context, relayClient *Client) {
 
 	// start a ticker to pick a new server
 	ticker := g.exponentTicker(ctx)
-	defer ticker.Stop()
+	defer func() {
+		ticker.Stop()
+	}()
 
 	for {
 		select {
 		case <-ticker.C:
+			// suspend reconnect attempts while the OS reports no usable network
+			if waited, err := g.netState.Wait(ctx); err != nil {
+				return
+			} else if waited {
+				ticker.Stop()
+				ticker = g.exponentTicker(ctx)
+				continue
+			}
 			if err := g.retry(ctx); err != nil {
 				log.Errorf("failed to pick new Relay server: %s", err)
 				g.setLastError(err)
@@ -100,7 +129,12 @@ func (g *Guard) tryToQuickReconnect(parentCtx context.Context, rc *Client) bool
 		return false
 	}
 
-	if cancelled := waiteBeforeRetry(parentCtx); !cancelled {
+	if ok := g.waitForNetwork(parentCtx); !ok {
+		return false
+	}
+
+	// Still offline after the budget: leave the retry to the ticker.
+	if !g.netState.IsOnline() {
 		return false
 	}
 
@@ -166,14 +200,47 @@ func (g *Guard) exponentTicker(ctx context.Context) *backoff.Ticker {
 	return backoff.NewTicker(bo)
 }
 
-func waiteBeforeRetry(ctx context.Context) bool {
-	timer := time.NewTimer(1500 * time.Millisecond)
-	defer timer.Stop()
+// waitForNetwork waits out the settle window while online, or waits for the
+// network to return while offline, within the budget. Returns false when ctx
+// is cancelled. Without an injected netState it degrades to a fixed
+// budget-long sleep, the pre-netstate behavior.
+func (g *Guard) waitForNetwork(ctx context.Context) bool {
+	budget := time.NewTimer(quickReconnectBudget)
+	defer budget.Stop()
 
-	select {
-	case <-timer.C:
-		return true
-	case <-ctx.Done():
-		return false
+	settleWindow := verdictSettleWindow
+	if g.netState == nil {
+		settleWindow = quickReconnectBudget
+	}
+	settle := time.NewTimer(settleWindow)
+	defer settle.Stop()
+
+	for {
+		// Channel first, flag second: a flip in between still fires the channel.
+		changedCh := g.netState.Changed()
+		if g.netState.IsOnline() {
+			select {
+			case <-settle.C:
+				return true
+			case <-changedCh:
+			case <-ctx.Done():
+				return false
+			}
+		} else {
+			select {
+			case <-budget.C:
+				return true
+			case <-changedCh:
+			case <-ctx.Done():
+				return false
+			}
+		}
+		if !settle.Stop() {
+			select {
+			case <-settle.C:
+			default:
+			}
+		}
+		settle.Reset(settleWindow)
 	}
 }

shared/relay/client/guard_test.go

@@ -0,0 +1,30 @@
+package client
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/netbirdio/netbird/client/netstate"
+)
+
+func TestWaitForNetworkSettlesAfterOutage(t *testing.T) {
+	ns := netstate.New()
+	ns.Set(false)
+	g := NewGuard(nil, 0, ns)
+
+	const outage = 2 * verdictSettleWindow
+	start := time.Now()
+	go func() {
+		time.Sleep(outage)
+		ns.Set(true)
+	}()
+
+	ok := g.waitForNetwork(context.Background())
+	elapsed := time.Since(start)
+
+	assert.True(t, ok, "recovered network must let the quick reconnect proceed")
+	assert.GreaterOrEqual(t, elapsed, outage+verdictSettleWindow, "reconnect must wait a full settle window after the network returns")
+}

shared/relay/client/manager.go

@@ -12,6 +12,8 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	relayAuth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 )
 
@@ -65,6 +67,17 @@ func WithMaxBackoffInterval(d time.Duration) ManagerOption {
 	return func(m *Manager) { m.maxBackoffInterval = d }
 }
 
+// WithNetworkState injects the OS network availability state that gates the
+// reconnect guard; without it reconnect attempts are not gated.
+func WithNetworkState(netState *netstate.State) ManagerOption {
+	return func(m *Manager) { m.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) ManagerOption {
+	return func(m *Manager) { m.sweeper = sweeper }
+}
+
 // Manager is a manager for the relay client instances. It establishes one persistent connection to the given relay URL
 // and automatically reconnect to them in case disconnection.
 // The manager also manage temporary relay connection. If a client wants to communicate with a client on a
@@ -92,6 +105,8 @@ type Manager struct {
 
 	mtu                uint16
 	maxBackoffInterval time.Duration
+	netState           *netstate.State
+	sweeper            *netsweep.Sweeper
 
 	cleanupInterval      time.Duration
 	keepUnusedServerTime time.Duration
@@ -128,8 +143,9 @@ func NewManager(ctx context.Context, serverURLs []string, peerID string, mtu uin
 	for _, opt := range opts {
 		opt(m)
 	}
+	m.serverPicker.Sweeper = m.sweeper
 	m.serverPicker.ServerURLs.Store(serverURLs)
-	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval)
+	m.reconnectGuard = NewGuard(m.serverPicker, m.maxBackoffInterval, m.netState)
 	return m
 }
 
@@ -354,6 +370,7 @@ func (m *Manager) openConnVia(ctx context.Context, serverAddress, peerKey string
 
 	relayClient := NewClientWithServerIP(serverAddress, serverIP, m.tokenStore, m.peerID, m.mtu)
 	relayClient.SetTransportFallback(m.transportFallback)
+	relayClient.sweeper = m.sweeper
 	err := relayClient.Connect(m.ctx)
 	if err != nil {
 		rt.Lock()

shared/relay/client/picker.go

@@ -9,6 +9,7 @@ import (
 
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/client/netsweep"
 	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 )
 
@@ -30,6 +31,7 @@ type ServerPicker struct {
 	MTU               uint16
 	ConnectionTimeout time.Duration
 	TransportFallback *transportFallback
+	Sweeper           *netsweep.Sweeper
 }
 
 func (sp *ServerPicker) PickServer(parentCtx context.Context) (*Client, error) {
@@ -73,6 +75,7 @@ func (sp *ServerPicker) startConnection(ctx context.Context, resultChan chan con
 	log.Infof("try to connecting to relay server: %s", url)
 	relayClient := NewClient(url, sp.TokenStore, sp.PeerID, sp.MTU)
 	relayClient.SetTransportFallback(sp.TransportFallback)
+	relayClient.sweeper = sp.Sweeper
 	err := relayClient.Connect(ctx)
 	resultChan <- connResult{
 		RelayClient: relayClient,

shared/signal/client/grpc.go

@@ -19,6 +19,8 @@ import (
 	"google.golang.org/grpc/status"
 
 	nbgrpc "github.com/netbirdio/netbird/client/grpc"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/client"
 	"github.com/netbirdio/netbird/shared/signal/proto"
@@ -65,6 +67,13 @@ type GrpcClient struct {
 	connStateCallback     ConnStateNotifier
 	connStateCallbackLock sync.RWMutex
 
+	// netState gates the Receive retry loop on OS-reported network
+	// availability; nil (the default) disables gating.
+	netState *netstate.State
+
+	// sweeper cuts the transport connections on network change; nil disables it.
+	sweeper *netsweep.Sweeper
+
 	onReconnectedListenerFn func()
 
 	decryptionWorker       *Worker
@@ -88,13 +97,43 @@ type GrpcClient struct {
 	watchdogWg            sync.WaitGroup
 }
 
-// NewClient creates a new Signal client
-func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
-	var conn *grpc.ClientConn
+// Option configures optional GrpcClient behavior.
+type Option func(*GrpcClient)
 
+// WithNetworkState injects the OS network availability state that gates the
+// Receive retry loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) Option {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) Option {
+	return func(c *GrpcClient) { c.sweeper = sweeper }
+}
+
+// NewClient creates a new Signal client
+func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled bool, opts ...Option) (*GrpcClient, error) {
+	// Options apply before dialing: the sweeper must wrap the first connection too.
+	c := &GrpcClient{
+		ctx:                   ctx,
+		key:                   key,
+		mux:                   sync.Mutex{},
+		status:                StreamDisconnected,
+		connStateCallbackLock: sync.RWMutex{},
+	}
+	for _, opt := range opts {
+		opt(c)
+	}
+
+	var extraOpts []grpc.DialOption
+	if c.sweeper != nil {
+		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
+	}
+
+	var conn *grpc.ClientConn
 	operation := func() error {
 		var err error
-		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent)
+		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.SignalComponent, extraOpts...)
 		if err != nil {
 			return fmt.Errorf("create connection: %w", err)
 		}
@@ -109,15 +148,9 @@ func NewClient(ctx context.Context, addr string, key wgtypes.Key, tlsEnabled boo
 
 	log.Debugf("connected to Signal Service: %v", conn.Target())
 
-	return &GrpcClient{
-		realClient:            proto.NewSignalExchangeClient(conn),
-		ctx:                   ctx,
-		signalConn:            conn,
-		key:                   key,
-		mux:                   sync.Mutex{},
-		status:                StreamDisconnected,
-		connStateCallbackLock: sync.RWMutex{},
-	}, nil
+	c.signalConn = conn
+	c.realClient = proto.NewSignalExchangeClient(conn)
+	return c, nil
 }
 
 func (c *GrpcClient) StreamConnected() bool {
@@ -165,19 +198,36 @@ func defaultBackoff(ctx context.Context) backoff.BackOff {
 // The connection retry logic will try to reconnect for 30 min and if wasn't successful will propagate the error to the function caller.
 func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Message) error) error {
 
-	var backOff = defaultBackoff(ctx)
+	backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
 
 	operation := func() error {
+		// suspend reconnect attempts while the OS reports no usable network.
+		// Wait only errors on a cancelled context, which means shutdown, so
+		// stop the loop without reporting a failure.
+		if waited, err := c.netState.Wait(ctx); err != nil {
+			log.Debugf("signal connection context has been canceled while offline, this usually indicates shutdown")
+			return nil
+		} else if waited {
+			backOff.Reset()
+		}
 
 		c.notifyStreamDisconnected()
 
-		log.Debugf("signal connection state %v", c.signalConn.GetState())
 		connState := c.signalConn.GetState()
+		log.Debugf("signal connection state %v", connState)
 		if connState == connectivity.Shutdown {
 			return backoff.Permanent(fmt.Errorf("connection to signal has been shut down"))
-		} else if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+		}
+		if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+			// A dial may already be in flight (e.g. triggered by another RPC
+			// after a network change); wait for it to settle and proceed if
+			// the channel became usable, instead of burning a backoff round on
+			// a successful dial. A failed dial errors out as before.
 			c.signalConn.WaitForStateChange(ctx, connState)
-			return fmt.Errorf("connection to signal is not ready and in %s state", connState)
+			connState = c.signalConn.GetState()
+			if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+				return fmt.Errorf("connection to signal is not ready and in %s state", connState)
+			}
 		}
 
 		// connect to Signal stream identifying ourselves with a public WireGuard key
@@ -231,7 +281,7 @@ func (c *GrpcClient) Receive(ctx context.Context, msgHandler func(msg *proto.Mes
 		return nil
 	}
 
-	err := backoff.Retry(operation, backOff)
+	err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
 	if err != nil {
 		log.Errorf("exiting the Signal service connection retry loop due to the unrecoverable error: %v", err)
 		return err