pqkem: recover from persistent rekey failure by re-bootstrapping over signal

OnRekeyFailed now re-runs the KEM bootstrap over Signal (conn.RequestReoffer ->
handshaker.SendOffer) instead of only logging: a fresh signalling offer starts a new
exchange that overwrites the stalled PSK on both sides, resyncing after a persistent
data-path desync. Chosen over a responder-side awaitingAck revert (which fights the
confirm-less ack timing) and a full tunnel teardown (heavier). The tunnel stays up on
the previous PSK meanwhile since Signal is independent of the broken data path.

client/internal/engine.go

@@ -50,6 +50,7 @@ import (
 	icemaker "github.com/netbirdio/netbird/client/internal/peer/ice"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/client/internal/portforward"
+	"github.com/netbirdio/netbird/client/internal/pqkem"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/relay"
 	"github.com/netbirdio/netbird/client/internal/rosenpass"
@@ -197,6 +198,10 @@ type Engine struct {
 	// rpManager is a Rosenpass manager
 	rpManager *rosenpass.Manager
 
+	// pqkemManager runs the ML-KEM post-quantum PSK exchange (gated by NB_ENABLE_PQ_MLKEM).
+	// It owns the data-path transport and peer endpoint routing.
+	pqkemManager *pqkem.Manager
+
 	// syncMsgMux is used to guarantee sequential Management Service message processing
 	syncMsgMux *sync.Mutex
 
@@ -651,6 +656,30 @@ func (e *Engine) Start(netbirdConfig *mgmProto.NetbirdConfig, mgmtURL *url.URL)
 		e.rpManager.SetInterface(e.wgInterface)
 	}
 
+	// Start the ML-KEM PQ manager after the interface is up so its dedicated UDP
+	// transport can bind on the WG overlay IP.
+	if pqkem.Enabled() {
+		tr, pqErr := newPQTransport(e.config.WgAddr.IP)
+		if pqErr != nil {
+			log.Errorf("pqkem: transport bind failed, exchange disabled: %v", pqErr)
+		} else {
+			cbHandler := pqCallbackHandler{
+				wg: e.wgInterface,
+				// On a persistent rekey failure, re-bootstrap the KEM over Signal: a
+				// fresh signalling offer starts a new exchange that overwrites the
+				// stalled PSK on both sides, recovering from a data-path desync.
+				reoffer: func(remoteKey string) {
+					if conn, ok := e.peerStore.PeerConn(remoteKey); ok {
+						conn.RequestReoffer()
+					}
+				},
+			}
+			e.pqkemManager = pqkem.NewManager(pqkem.LocalID(publicKey.String()), cbHandler, pqkem.NewLogger())
+			e.pqkemManager.Start(tr)
+			log.Infof("pqkem: enabled (udp port %d on overlay %s)", e.pqkemManager.LocalPort(), e.config.WgAddr.IP)
+		}
+	}
+
 	// if inbound conns are blocked there is no need to create the ACL manager
 	if e.firewall != nil && !e.config.BlockInbound {
 		e.acl = acl.NewDefaultManager(e.firewall)
@@ -914,6 +943,10 @@ func (e *Engine) removePeer(peerKey string) error {
 
 	e.connMgr.RemovePeerConn(peerKey)
 
+	if e.pqkemManager != nil {
+		e.pqkemManager.RemovePeer(pqkem.RemoteID(peerKey))
+	}
+
 	err := e.statusRecorder.RemovePeer(peerKey)
 	if err != nil {
 		log.Warnf("received error when removing peer %s from status recorder: %v", peerKey, err)
@@ -1900,6 +1933,10 @@ func (e *Engine) createPeerConn(pubKey string, allowedIPs []netip.Prefix, agentV
 		},
 		ICEConfig: e.createICEConfig(),
 	}
+	if e.pqkemManager != nil {
+		config.PQ = pqHandshaker{mgr: e.pqkemManager}
+		config.PQStrict = pqkem.Strict()
+	}
 
 	serviceDependencies := peer.ServiceDependencies{
 		StatusRecorder:     e.statusRecorder,
@@ -2083,6 +2120,10 @@ func (e *Engine) close() {
 		_ = e.rpManager.Close()
 	}
 
+	if e.pqkemManager != nil {
+		e.pqkemManager.Stop()
+	}
+
 	ctx, cancel := context.WithTimeout(context.Background(), 5*time.Second)
 	defer cancel()
 	if err := e.portForwardManager.GracefullyStop(ctx); err != nil {
@@ -2895,6 +2936,8 @@ func convertToOfferAnswer(msg *sProto.Message) (*peer.OfferAnswer, error) {
 		Version:         msg.GetBody().GetNetBirdVersion(),
 		RosenpassPubKey: rosenpassPubKey,
 		RosenpassAddr:   rosenpassAddr,
+		MlkemPayload:    msg.GetBody().GetMlkemPayload(),
+		MlkemPort:       int(msg.GetBody().GetMlkemPort()),
 		RelaySrvAddress: msg.GetBody().GetRelayServerAddress(),
 		RelaySrvIP:      relayIP,
 		SessionID:       sessionID,

client/internal/peer/conn.go

@@ -3,6 +3,7 @@ package peer
 import (
 	"context"
 	"fmt"
+	"math"
 	"net"
 	"net/netip"
 	"runtime"
@@ -26,6 +27,7 @@ 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/monotime"
 	"github.com/netbirdio/netbird/route"
 	relayClient "github.com/netbirdio/netbird/shared/relay/client"
 )
@@ -74,6 +76,34 @@ type RosenpassConfig struct {
 	PermissiveMode bool
 }
 
+// PQHandshaker attaches post-quantum ML-KEM material to signalling offers/answers and
+// feeds received material back. It is implemented by the engine over the pqkem
+// manager and is nil when the PQ exchange is disabled. remoteKey is the peer's
+// WireGuard public key.
+type PQHandshaker interface {
+	// OfferPayload returns the KEM offer to embed in an outgoing offer (nil if this
+	// peer is not the KEM initiator) and the local PQ data-path port to announce.
+	OfferPayload(remoteKey string) (payload []byte, port int)
+	// AnswerPayload processes a received KEM offer (nil if absent) and returns the KEM
+	// answer to embed in the outgoing answer (nil if none) and the local PQ port.
+	AnswerPayload(remoteKey string, recvOffer []byte) (payload []byte, port int)
+	// OnAnswer feeds a received KEM answer (nil if absent).
+	OnAnswer(remoteKey string, recvAnswer []byte)
+	// PSK returns the peer's latest derived post-quantum PSK to program at WG
+	// peer-config time (the pull path). ok is false until one has been derived.
+	PSK(remoteKey string) (wgtypes.Key, bool)
+	// SetRemoteAddr registers the peer's data-path endpoint learned from signalling:
+	// its WG overlay IP with the advertised pq UDP port.
+	SetRemoteAddr(remoteKey string, addr netip.AddrPort)
+	// OnDataPathRekeyed signals a fresh WireGuard handshake for the peer; it clocks the
+	// next chained PSK rotation pushed over the data path. sinceActivity is how long
+	// ago the peer last exchanged real user data, so the rotation can be skipped for
+	// idle tunnels.
+	OnDataPathRekeyed(remoteKey string, sinceActivity time.Duration)
+	// OnDataPathDown signals the peer's tunnel went down.
+	OnDataPathDown(remoteKey string)
+}
+
 // ConnConfig is a peer Connection configuration
 type ConnConfig struct {
 	// Key is a public key of a remote peer
@@ -91,6 +121,12 @@ type ConnConfig struct {
 
 	RosenpassConfig RosenpassConfig
 
+	// PQ carries post-quantum ML-KEM material on offers/answers; nil when disabled.
+	PQ PQHandshaker
+	// PQStrict fails closed: block peer traffic until the ML-KEM PSK is established,
+	// instead of letting the tunnel come up classically and upgrading to PQ later.
+	PQStrict bool
+
 	// ICEConfig ICE protocol configuration
 	ICEConfig icemaker.Config
 }
@@ -149,6 +185,11 @@ type Conn struct {
 	// pendingFirstPacket is the lazyconn-captured handshake init, replayed once the real
 	// transport is up.
 	pendingFirstPacket []byte
+
+	// pqBlockingKey is a per-conn random sentinel PSK used in PQ strict mode to fail
+	// closed: it is programmed until the real ML-KEM PSK is derived, so no session can
+	// form on a non-PQ key. Per-conn random so two strict peers never match by chance.
+	pqBlockingKey *wgtypes.Key
 }
 
 // injectPendingFirstPacket replays the captured handshake through the proxy if present, else
@@ -206,6 +247,14 @@ func NewConn(config ConnConfig, services ServiceDependencies) (*Conn, error) {
 		metricsRecorder:    services.MetricsRecorder,
 	}
 
+	if config.PQ != nil && config.PQStrict {
+		if k, err := wgtypes.GenerateKey(); err != nil {
+			connLog.Errorf("pqkem: failed to generate strict-mode sentinel key, strict fail-closed disabled for this peer: %v", err)
+		} else {
+			conn.pqBlockingKey = &k
+		}
+	}
+
 	return conn, nil
 }
 
@@ -670,6 +719,22 @@ func (conn *Conn) onGuardEvent() {
 	}
 }
 
+// RequestReoffer sends a fresh signalling offer for the peer, re-running the
+// post-quantum bootstrap over Signal. Used to recover from a persistent data-path
+// rekey failure: a new exchange overwrites the stalled PSK on both sides. No-op if the
+// connection is not open yet.
+func (conn *Conn) RequestReoffer() {
+	conn.mu.Lock()
+	h := conn.handshaker
+	conn.mu.Unlock()
+	if h == nil {
+		return
+	}
+	if err := h.SendOffer(); err != nil {
+		conn.Log.Debugf("pqkem: recovery re-offer failed: %v", err)
+	}
+}
+
 func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
 	conn.mu.Lock()
 	defer conn.mu.Unlock()
@@ -681,6 +746,10 @@ func (conn *Conn) onWGDisconnected(watcherCtx context.Context) {
 
 	conn.Log.Warnf("WireGuard handshake timeout detected, closing current connection")
 
+	if conn.config.PQ != nil {
+		conn.config.PQ.OnDataPathDown(conn.config.Key)
+	}
+
 	// Close the active connection based on current priority
 	switch conn.currentConnPriority {
 	case conntype.Relay:
@@ -723,7 +792,7 @@ func (conn *Conn) updateRelayStatus(relayServerAddr string, rosenpassPubKey []by
 		ConnStatus:         conn.evalStatus(),
 		Relayed:            conn.isRelayed(),
 		RelayServerAddress: relayServerAddr,
-		RosenpassEnabled:   isRosenpassEnabled(rosenpassPubKey),
+		RosenpassEnabled:   conn.quantumResistant(rosenpassPubKey),
 	}
 
 	err := conn.statusRecorder.UpdatePeerRelayedState(peerState)
@@ -742,7 +811,7 @@ func (conn *Conn) updateIceState(iceConnInfo ICEConnInfo, updateTime time.Time)
 		RemoteIceCandidateType:     iceConnInfo.RemoteIceCandidateType,
 		LocalIceCandidateEndpoint:  iceConnInfo.LocalIceCandidateEndpoint,
 		RemoteIceCandidateEndpoint: iceConnInfo.RemoteIceCandidateEndpoint,
-		RosenpassEnabled:           isRosenpassEnabled(iceConnInfo.RosenpassPubKey),
+		RosenpassEnabled:           conn.quantumResistant(iceConnInfo.RosenpassPubKey),
 	}
 
 	err := conn.statusRecorder.UpdatePeerICEState(peerState)
@@ -946,6 +1015,35 @@ func (conn *Conn) onWGCheckSuccess() {
 	conn.mu.Lock()
 	conn.wgTimeouts = 0
 	conn.mu.Unlock()
+
+	// A fresh WireGuard handshake clocks the post-quantum PSK rotation. Pass how long
+	// ago the peer last exchanged real user data (keepalives excluded) so the pqkem
+	// manager can skip rotation on idle tunnels — rotating then would push data-path
+	// traffic that keeps the lazy connection artificially active.
+	if conn.config.PQ != nil {
+		conn.config.PQ.OnDataPathRekeyed(conn.config.Key, conn.dataActivityAge())
+	}
+}
+
+// dataActivityAge returns how long ago the peer last exchanged real user data
+// (WireGuard keepalives excluded), per the same LastActivities signal the
+// lazy-connection inactivity monitor uses. It reports a very large duration when no
+// activity has ever been recorded, so the peer is treated as idle.
+//
+// In kernel mode there is no per-peer data-activity signal (LastActivities is
+// userspace-only), so we cannot tell active from idle. We report zero — always
+// "active" — so PSK rotation is not disabled in kernel mode. Lazy back-to-idle is
+// already limited there; the eBPF WG-activity detection (future) will supply a real
+// signal that excludes handshake/pqkem traffic.
+func (conn *Conn) dataActivityAge() time.Duration {
+	if !conn.config.WgConfig.WgInterface.IsUserspaceBind() {
+		return 0
+	}
+	last, ok := conn.config.WgConfig.WgInterface.LastActivities()[conn.config.WgConfig.RemoteKey]
+	if !ok {
+		return time.Duration(math.MaxInt64)
+	}
+	return monotime.Since(last)
 }
 
 // recordConnectionMetrics records connection stage timestamps as metrics
@@ -987,6 +1085,23 @@ func (conn *Conn) AgentVersionString() string {
 }
 
 func (conn *Conn) presharedKey(remoteRosenpassKey []byte) *wgtypes.Key {
+	// Post-quantum: once the ML-KEM exchange has derived a PSK for this peer, program
+	// it here so the peer's next WireGuard handshake adopts it. Applied at peer-config
+	// time (bootstrap / reconnect); steady-state rotation is pushed separately.
+	if conn.config.PQ != nil {
+		if psk, ok := conn.config.PQ.PSK(conn.config.Key); ok {
+			return &psk
+		}
+		if conn.config.PQStrict && conn.pqBlockingKey != nil {
+			// Fail closed: program a non-matching sentinel so no session forms on a
+			// non-PQ key until the ML-KEM exchange derives the real PSK (pushed via
+			// SetPresharedKey once it converges). "pending" — turns into a "stuck"
+			// warning from the manager if the exchange keeps failing (see raiseFailure).
+			conn.Log.Debugf("pqkem: strict mode — no PQ PSK yet, blocking peer traffic until the ML-KEM exchange converges")
+			return conn.pqBlockingKey
+		}
+	}
+
 	if conn.config.RosenpassConfig.PubKey == nil {
 		return conn.config.WgConfig.PreSharedKey
 	}
@@ -1026,6 +1141,21 @@ func isRosenpassEnabled(remoteRosenpassPubKey []byte) bool {
 	return remoteRosenpassPubKey != nil
 }
 
+// quantumResistant reports whether the peer's tunnel is post-quantum protected, for
+// the status "Quantum resistance" field: either Rosenpass (the remote advertised a
+// Rosenpass key) or the ML-KEM exchange (a PQ PSK has been derived for this peer).
+func (conn *Conn) quantumResistant(remoteRosenpassPubKey []byte) bool {
+	if isRosenpassEnabled(remoteRosenpassPubKey) {
+		return true
+	}
+	if conn.config.PQ != nil {
+		if _, ok := conn.config.PQ.PSK(conn.config.Key); ok {
+			return true
+		}
+	}
+	return false
+}
+
 func evalConnStatus(in connStatusInputs) guard.ConnStatus {
 	// "Relay up and needed" — the peer uses relay and the transport is connected.
 	relayUsedAndUp := in.peerUsesRelay && in.relayConnected

client/internal/peer/handshaker.go

@@ -39,6 +39,16 @@ type OfferAnswer struct {
 	// This value is the local Rosenpass server address when sending the message
 	RosenpassAddr string
 
+	// MlkemPayload carries the post-quantum X25519MLKEM768 handshake message
+	// (pqkem-framed offer on an OFFER, answer on an ANSWER) that seeds the
+	// WireGuard PSK. Opaque here — the pqkem library frames and parses it. Nil
+	// when the peer does not run the ML-KEM PQ exchange.
+	MlkemPayload []byte
+
+	// MlkemPort is the peer's ML-KEM PQ service UDP port (bound on its WG overlay
+	// IP) where data-path rekey messages are sent. Zero when not running the exchange.
+	MlkemPort int
+
 	// relay server address
 	RelaySrvAddress string
 	// RelaySrvIP is the IP the remote peer is connected to on its
@@ -81,14 +91,20 @@ type Handshaker struct {
 
 func NewHandshaker(log *log.Entry, config ConnConfig, signaler *Signaler, ice *WorkerICE, relay *WorkerRelay, metricsStages *MetricsStages) *Handshaker {
 	h := &Handshaker{
-		log:            log,
-		config:         config,
-		signaler:       signaler,
-		ice:            ice,
-		relay:          relay,
-		metricsStages:  metricsStages,
-		remoteOffersCh: make(chan OfferAnswer),
-		remoteAnswerCh: make(chan OfferAnswer),
+		log:           log,
+		config:        config,
+		signaler:      signaler,
+		ice:           ice,
+		relay:         relay,
+		metricsStages: metricsStages,
+		// Buffered by 1: the single Listen goroutine can be busy handling an offer
+		// (sendAnswer does a blocking signal send) exactly when the matching answer
+		// arrives on the other channel. Unbuffered, that answer would hit the
+		// non-blocking send's default and be dropped — fatal for the post-quantum
+		// exchange, which needs the answer to converge. A 1-slot cushion lets it wait
+		// until Listen loops back, without ever blocking the signal receiver.
+		remoteOffersCh: make(chan OfferAnswer, 1),
+		remoteAnswerCh: make(chan OfferAnswer, 1),
 	}
 	// assume remote supports ICE until we learn otherwise from received offers
 	h.remoteICESupported.Store(ice != nil)
@@ -120,6 +136,8 @@ func (h *Handshaker) Listen(ctx context.Context) {
 
 			h.updateRemoteICEState(&remoteOfferAnswer)
 
+			h.pqRegisterEndpoint(remoteOfferAnswer.MlkemPort)
+
 			if h.relayListener != nil {
 				h.relayListener.Notify(&remoteOfferAnswer)
 			}
@@ -128,7 +146,7 @@ func (h *Handshaker) Listen(ctx context.Context) {
 				h.iceListener(&remoteOfferAnswer)
 			}
 
-			if err := h.sendAnswer(); err != nil {
+			if err := h.sendAnswer(&remoteOfferAnswer); err != nil {
 				h.log.Errorf("failed to send remote offer confirmation: %s", err)
 				continue
 			}
@@ -142,6 +160,8 @@ func (h *Handshaker) Listen(ctx context.Context) {
 
 			h.updateRemoteICEState(&remoteOfferAnswer)
 
+			h.pqRegisterEndpoint(remoteOfferAnswer.MlkemPort)
+
 			if h.relayListener != nil {
 				h.relayListener.Notify(&remoteOfferAnswer)
 			}
@@ -149,6 +169,10 @@ func (h *Handshaker) Listen(ctx context.Context) {
 			if h.iceListener != nil && h.RemoteICESupported() {
 				h.iceListener(&remoteOfferAnswer)
 			}
+
+			if h.config.PQ != nil {
+				h.config.PQ.OnAnswer(h.config.Key, remoteOfferAnswer.MlkemPayload)
+			}
 		case <-ctx.Done():
 			h.log.Infof("stop listening for remote offers and answers")
 			return
@@ -156,6 +180,16 @@ func (h *Handshaker) Listen(ctx context.Context) {
 	}
 }
 
+// pqRegisterEndpoint feeds the post-quantum handshaker the peer's data-path endpoint
+// (its WG overlay IP plus the advertised pq UDP port) learned from a remote offer/answer.
+func (h *Handshaker) pqRegisterEndpoint(remotePort int) {
+	if h.config.PQ == nil || remotePort <= 0 || remotePort > 65535 || len(h.config.WgConfig.AllowedIps) == 0 {
+		return
+	}
+	addr := netip.AddrPortFrom(h.config.WgConfig.AllowedIps[0].Addr(), uint16(remotePort))
+	h.config.PQ.SetRemoteAddr(h.config.Key, addr)
+}
+
 func (h *Handshaker) SendOffer() error {
 	h.mu.Lock()
 	defer h.mu.Unlock()
@@ -195,13 +229,23 @@ func (h *Handshaker) sendOffer() error {
 	}
 
 	offer := h.buildOfferAnswer()
+	if h.config.PQ != nil {
+		offer.MlkemPayload, offer.MlkemPort = h.config.PQ.OfferPayload(h.config.Key)
+	}
 	h.log.Debugf("sending offer with serial: %s", offer.SessionIDString())
 
 	return h.signaler.SignalOffer(offer, h.config.Key)
 }
 
-func (h *Handshaker) sendAnswer() error {
+func (h *Handshaker) sendAnswer(remoteOffer *OfferAnswer) error {
 	answer := h.buildOfferAnswer()
+	if h.config.PQ != nil {
+		var recvOffer []byte
+		if remoteOffer != nil {
+			recvOffer = remoteOffer.MlkemPayload
+		}
+		answer.MlkemPayload, answer.MlkemPort = h.config.PQ.AnswerPayload(h.config.Key, recvOffer)
+	}
 	h.log.Debugf("sending answer with serial: %s", answer.SessionIDString())
 
 	return h.signaler.SignalAnswer(answer, h.config.Key)

client/internal/peer/iface.go

@@ -10,6 +10,7 @@ import (
 	"github.com/netbirdio/netbird/client/iface/configurer"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/iface/wgproxy"
+	"github.com/netbirdio/netbird/monotime"
 )
 
 type WGIface interface {
@@ -19,4 +20,11 @@ type WGIface interface {
 	GetProxy() wgproxy.Proxy
 	Address() wgaddr.Address
 	RemoveEndpointAddress(key string) error
+	// LastActivities returns the last real-data activity time per peer (WireGuard
+	// keepalives excluded), used to gate post-quantum PSK rotation on active tunnels.
+	LastActivities() map[string]monotime.Time
+	// IsUserspaceBind reports whether WireGuard runs in userspace. Only there does
+	// LastActivities track per-peer data activity; in kernel mode it is unavailable,
+	// so PSK rotation cannot be gated on activity.
+	IsUserspaceBind() bool
 }

client/internal/peer/signaler.go

@@ -63,6 +63,8 @@ func (s *Signaler) signalOfferAnswer(offerAnswer OfferAnswer, remoteKey string,
 		},
 		RosenpassPubKey: offerAnswer.RosenpassPubKey,
 		RosenpassAddr:   offerAnswer.RosenpassAddr,
+		MlkemPayload:    offerAnswer.MlkemPayload,
+		MlkemPort:       offerAnswer.MlkemPort,
 		RelaySrvAddress: offerAnswer.RelaySrvAddress,
 		RelaySrvIP:      offerAnswer.RelaySrvIP,
 		SessionID:       sessionIDBytes,

client/internal/pqkem/bench_test.go

@@ -0,0 +1,59 @@
+package pqkem
+
+import (
+	"crypto/ecdh"
+	"crypto/mlkem"
+	"crypto/rand"
+	"testing"
+)
+
+func BenchmarkX25519Keygen(b *testing.B) {
+	c := ecdh.X25519()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := c.GenerateKey(rand.Reader); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkX25519ECDH(b *testing.B) {
+	c := ecdh.X25519()
+	a, _ := c.GenerateKey(rand.Reader)
+	p, _ := c.GenerateKey(rand.Reader)
+	pub := p.PublicKey()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := a.ECDH(pub); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkMLKEMKeygen(b *testing.B) {
+	for i := 0; i < b.N; i++ {
+		if _, err := mlkem.GenerateKey768(); err != nil {
+			b.Fatal(err)
+		}
+	}
+}
+
+func BenchmarkMLKEMEncaps(b *testing.B) {
+	dk, _ := mlkem.GenerateKey768()
+	ek := dk.EncapsulationKey()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		_, _ = ek.Encapsulate()
+	}
+}
+
+func BenchmarkMLKEMDecaps(b *testing.B) {
+	dk, _ := mlkem.GenerateKey768()
+	_, ct := dk.EncapsulationKey().Encapsulate()
+	b.ResetTimer()
+	for i := 0; i < b.N; i++ {
+		if _, err := dk.Decapsulate(ct); err != nil {
+			b.Fatal(err)
+		}
+	}
+}

client/internal/pqkem/callbacks.go

@@ -0,0 +1,18 @@
+package pqkem
+
+// CallbackHandler is implemented by the host and invoked by the library. The
+// library only reports events; the host owns the reaction. Keeping this an
+// interface — rather than touching the transport or keying directly — is what lets
+// the KEM code be extracted as a standalone library.
+type CallbackHandler interface {
+	// OnNewPSKReady fires when a fresh post-quantum PSK has been derived for a peer
+	// and must be programmed into the consumer's secure channel. It is invoked at
+	// the commit point of each side: the initiator on receiving the answer, the
+	// responder on receiving the confirm.
+	OnNewPSKReady(remoteID RemoteID, psk PSK) error
+
+	// OnRekeyFailed fires when an exchange fails to converge within the allotted
+	// time. The host should tear the peer connection down so it re-establishes, and
+	// log a WARN. The library reports the event; it does not dictate the reaction.
+	OnRekeyFailed(remoteID RemoteID) error
+}

client/internal/pqkem/convergence.go

@@ -0,0 +1,271 @@
+package pqkem
+
+import (
+	"context"
+	"crypto/sha256"
+	"encoding/hex"
+	"time"
+)
+
+// idHex renders an exchange ID for logs.
+func idHex(id ExchangeID) string { return hex.EncodeToString(id[:]) }
+
+// pskFingerprint is a short, non-secret digest of a derived PSK: identical on both
+// peers iff they derived the same key. Logged instead of the raw PSK so debug logs
+// never carry the actual WireGuard preshared key.
+func pskFingerprint(psk PSK) string {
+	sum := sha256.Sum256(psk[:])
+	return hex.EncodeToString(sum[:8])
+}
+
+// startExchange creates a fresh initiator exchange (acknowledging ackID, zero for a
+// bootstrap) and returns the framed offer for the caller to send — pushed over the
+// data path for a chained rekey, or handed to the host for signalling when viaSignal
+// is set. Any previous in-flight exchange for the peer is cancelled.
+func (m *Manager) startExchange(remoteID RemoteID, viaSignal bool, ackID ExchangeID) ([]byte, error) {
+	init, err := NewInitiator()
+	if err != nil {
+		return nil, err
+	}
+	id, err := newExchangeID()
+	if err != nil {
+		return nil, err
+	}
+	raw, err := (&OfferMsg{ExchangeID: id, AckID: ackID, KEMOffer: init.Offer()}).Encode()
+	if err != nil {
+		return nil, err
+	}
+
+	ctx, cancel := context.WithCancel(m.rootCtx)
+	m.mu.Lock()
+	if old := m.exchanges[remoteID]; old != nil && old.cancel != nil {
+		old.cancel()
+	}
+	m.exchanges[remoteID] = &exchangeCtl{
+		id:        id,
+		state:     stateAwaitingAnswer,
+		startedAt: time.Now(),
+		cancel:    cancel,
+		lastSent:  raw,
+		initiator: init,
+		viaSignal: viaSignal,
+	}
+	m.mu.Unlock()
+
+	m.wait.Add(1)
+	go m.initiatorLoop(ctx, remoteID, id)
+
+	via := "data-path"
+	if viaSignal {
+		via = "signal"
+	}
+	m.trace("pqkem: offer sent", "peer", remoteID, "exchange", idHex(id), "acks", idHex(ackID), "via", via)
+	return raw, nil
+}
+
+// processOffer (responder) first acknowledges the previous exchange the offer names
+// (that offer riding the data path under the freshly adopted key proves it worked),
+// then derives the PSK for the new offer, commits it optimistically, and returns the
+// framed answer. A duplicate offer returns the cached answer without re-deriving.
+func (m *Manager) processOffer(remoteID RemoteID, o *OfferMsg) ([]byte, error) {
+	m.trace("pqkem: offer received", "peer", remoteID, "exchange", idHex(o.ExchangeID), "acks", idHex(o.AckID))
+
+	if o.AckID != (ExchangeID{}) {
+		m.ackConverged(remoteID, o.AckID)
+	}
+
+	m.mu.Lock()
+	if ex := m.exchanges[remoteID]; ex != nil && ex.id == o.ExchangeID {
+		state, last := ex.state, ex.lastSent
+		m.mu.Unlock()
+		if state == stateReserved {
+			return nil, nil
+		}
+		m.trace("pqkem: duplicate offer, resending cached answer", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+		return last, nil
+	}
+	// Reserve the slot so a concurrent duplicate offer bails.
+	m.exchanges[remoteID] = &exchangeCtl{id: o.ExchangeID, state: stateReserved, startedAt: time.Now()}
+	m.mu.Unlock()
+
+	answerBytes, psk, err := Respond(o.KEMOffer, m.binding(remoteID))
+	if err != nil {
+		return nil, err
+	}
+	raw, err := (&AnswerMsg{ExchangeID: o.ExchangeID, KEMAnswer: answerBytes}).Encode()
+	if err != nil {
+		return nil, err
+	}
+
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != o.ExchangeID {
+		m.mu.Unlock()
+		m.trace("pqkem: exchange superseded during respond, dropping answer", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+		return nil, nil
+	}
+	ex.state = stateAwaitingAck
+	ex.lastSent = raw
+	ex.pendingPSK = psk
+	m.psks[remoteID] = psk
+	m.mu.Unlock()
+
+	m.trace("pqkem: new PSK derived", "peer", remoteID, "exchange", idHex(o.ExchangeID), "role", "responder", "psk_fp", pskFingerprint(psk))
+
+	// Commit optimistically so our data path can rekey to the new PSK.
+	if err := m.cbHandler.OnNewPSKReady(remoteID, psk); err != nil {
+		return nil, err
+	}
+	m.trace("pqkem: answer sent", "peer", remoteID, "exchange", idHex(o.ExchangeID))
+	return raw, nil
+}
+
+// processAnswer (initiator) derives and commits the PSK and parks in
+// stateAwaitingRekey; the next offer (chained from OnDataPathRekeyed) will acknowledge
+// this exchange. Only valid in stateAwaitingAnswer; advancing the state under the
+// lock makes a concurrent/duplicate answer bail.
+func (m *Manager) processAnswer(remoteID RemoteID, a *AnswerMsg) error {
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != a.ExchangeID || ex.state != stateAwaitingAnswer {
+		haveID := "none"
+		if ex != nil {
+			haveID = idHex(ex.id)
+		}
+		m.mu.Unlock()
+		m.trace("pqkem: unexpected answer dropped (inconsistency)", "peer", remoteID, "answer_for", idHex(a.ExchangeID), "have_exchange", haveID)
+		return nil
+	}
+	ex.state = stateAwaitingRekey
+	init := ex.initiator
+	ex.initiator = nil
+	m.mu.Unlock()
+
+	m.trace("pqkem: answer received", "peer", remoteID, "exchange", idHex(a.ExchangeID))
+
+	psk, err := init.Finish(a.KEMAnswer, m.binding(remoteID))
+	if err != nil {
+		return err
+	}
+
+	// The initiator has converged: the responder must have derived the key to answer.
+	m.mu.Lock()
+	m.established[remoteID] = true
+	m.failures[remoteID] = 0
+	m.psks[remoteID] = psk
+	m.mu.Unlock()
+
+	m.trace("pqkem: new PSK derived", "peer", remoteID, "exchange", idHex(a.ExchangeID), "role", "initiator", "psk_fp", pskFingerprint(psk))
+
+	return m.cbHandler.OnNewPSKReady(remoteID, psk)
+}
+
+// ackConverged (responder) records convergence of the exchange named by ackID: a
+// later offer acknowledging it proves both sides operate on that exchange's key. Only
+// acts on a matching stateAwaitingAck exchange; anything else is ignored.
+func (m *Manager) ackConverged(remoteID RemoteID, ackID ExchangeID) {
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	if ex == nil || ex.id != ackID || ex.state != stateAwaitingAck {
+		m.mu.Unlock()
+		m.trace("pqkem: ack for unknown/mismatched exchange, ignored (inconsistency)", "peer", remoteID, "acks", idHex(ackID))
+		return
+	}
+	delete(m.exchanges, remoteID)
+	m.established[remoteID] = true
+	m.failures[remoteID] = 0
+	_ = time.Since(ex.startedAt) // convergence latency (metrics hook, later step)
+	m.mu.Unlock()
+
+	m.trace("pqkem: previous exchange confirmed by ack", "peer", remoteID, "exchange", idHex(ackID))
+}
+
+// initiatorLoop enforces the offer->answer convergence deadline and retransmits the
+// initiator's outstanding data-path offer while awaiting the answer (a
+// signalling-bootstrapped offer is retransmitted by the host, so it is not resent
+// here). Exhausting the deadline before the answer arrives is a failure. Once the
+// answer is in (state past awaitingAnswer) the loop exits: the next rotation is driven
+// by OnDataPathRekeyed, and the idle wait for it has no deadline.
+func (m *Manager) initiatorLoop(ctx context.Context, remoteID RemoteID, id ExchangeID) {
+	defer m.wait.Done()
+	t := time.NewTicker(m.retryInterval)
+	defer t.Stop()
+
+	attempts := 0
+	for {
+		select {
+		case <-ctx.Done():
+			return
+		case <-t.C:
+			m.mu.Lock()
+			ex := m.exchanges[remoteID]
+			if ex == nil || ex.id != id {
+				m.mu.Unlock()
+				return
+			}
+
+			switch ex.state {
+			case stateAwaitingAnswer:
+				if attempts >= m.maxRetries {
+					delete(m.exchanges, remoteID)
+					initial := !m.established[remoteID]
+					fail := m.registerFailureLocked(remoteID)
+					m.mu.Unlock()
+					m.raiseFailure(remoteID, fail, initial)
+					return
+				}
+				viaSignal := ex.viaSignal
+				msg := ex.lastSent
+				attempts++
+				m.mu.Unlock()
+				if !viaSignal {
+					if err := m.pushDataPath(remoteID, msg); err != nil {
+						m.logger.Warn("pqkem: offer retransmit failed", "peer", remoteID, "err", err)
+					}
+				}
+
+			default:
+				// Past awaiting the answer (converged) or superseded: the loop's job
+				// is done. The next rotation is driven externally by OnDataPathRekeyed,
+				// so there is no deadline while idle-waiting for it (that wait can be
+				// as long as the transport's natural rekey interval).
+				m.mu.Unlock()
+				return
+			}
+		}
+	}
+}
+
+// registerFailureLocked applies policy B and reports whether OnRekeyFailed is due:
+// an initial exchange (peer never established) fails immediately; a rekey tolerates
+// up to maxRekeyFailures consecutive misses (we stay on the still-valid previous
+// PSK) before failing. Assumes m.mu is held.
+func (m *Manager) registerFailureLocked(remoteID RemoteID) bool {
+	if !m.established[remoteID] {
+		return true
+	}
+	m.failures[remoteID]++
+	if m.failures[remoteID] >= m.maxRekeyFailures {
+		m.failures[remoteID] = 0
+		return true
+	}
+	return false
+}
+
+// raiseFailure reports a convergence failure. initial distinguishes a never-established
+// peer (bootstrap failed → no PQ PSK at all; in strict mode the peer stays blocked =
+// "stuck") from a rekey failure (a previous PSK is still in force and traffic continues).
+func (m *Manager) raiseFailure(remoteID RemoteID, fail, initial bool) {
+	if !fail {
+		m.logger.Warn("pqkem: rekey attempt timed out, will retry next cycle", "peer", remoteID)
+		return
+	}
+	if initial {
+		m.logger.Warn("pqkem: initial exchange failed — no PQ PSK established for peer (strict mode keeps the peer blocked until it converges)", "peer", remoteID)
+	} else {
+		m.logger.Warn("pqkem: rekey failed after retries — staying on the previous PSK", "peer", remoteID)
+	}
+	if err := m.cbHandler.OnRekeyFailed(remoteID); err != nil {
+		m.logger.Error("pqkem: OnRekeyFailed handler error", "peer", remoteID, "err", err)
+	}
+}

client/internal/pqkem/convergence_test.go

@@ -0,0 +1,74 @@
+package pqkem
+
+import (
+	"net/netip"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+// dropTransport is a pqkem.Transport that silently discards everything.
+type dropTransport struct{}
+
+func (dropTransport) Send(netip.AddrPort, []byte) error { return nil }
+func (dropTransport) LocalPort() int                    { return 0 }
+func (dropTransport) Run(func(netip.AddrPort, []byte))  {}
+func (dropTransport) Close() error                      { return nil }
+
+func failedCount(f *fakeWG) int {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return len(f.failed)
+}
+
+func TestManager_InitialTimeoutFailsImmediately(t *testing.T) {
+	wg := newFakeWG()
+	d := NewManager("bbbb", wg, nil) // bbbb > aaaa -> initiator
+	d.Start(dropTransport{})
+	d.retryInterval = 5 * time.Millisecond
+	d.maxRetries = 3
+	defer d.Stop()
+
+	// Bootstrap offer is produced for signalling; no answer ever comes back -> the
+	// initial exchange fails fast.
+	offer, err := d.SignalOffer("aaaa")
+	require.NoError(t, err)
+	require.NotNil(t, offer)
+
+	require.Eventually(t, func() bool { return failedCount(wg) == 1 }, time.Second, 5*time.Millisecond)
+}
+
+func TestManager_RekeyToleratesKFailures(t *testing.T) {
+	dA, dB, _, wgB, lbB := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	// Tighten B's timings before any exchange loop spawns (the loop reads these
+	// fields, so writing them after a loop is running would race).
+	dB.retryInterval = 5 * time.Millisecond
+	dB.maxRetries = 2
+
+	// Establish: bootstrap + data-path-rekeyed so B becomes established and its data
+	// path is usable.
+	bootstrap(t, dA, dB)
+	dA.OnDataPathRekeyed("bbbb", 0)
+	dB.OnDataPathRekeyed("aaaa", 0)
+	require.NotEqual(t, PSK{}, wgB.psk("aaaa"))
+
+	// Drop B's outbound so rekeys can no longer converge.
+	lbB.drop.Store(true)
+
+	// K-1 data-path rekeys must NOT raise OnRekeyFailed.
+	for i := 0; i < DefaultMaxRekeyFailures-1; i++ {
+		_, err := dB.startExchange("aaaa", false, ExchangeID{})
+		require.NoError(t, err)
+		time.Sleep(50 * time.Millisecond)
+	}
+	require.Equal(t, 0, failedCount(wgB), "no failure before K attempts")
+
+	// The K-th failure raises it once.
+	_, err := dB.startExchange("aaaa", false, ExchangeID{})
+	require.NoError(t, err)
+	require.Eventually(t, func() bool { return failedCount(wgB) == 1 }, time.Second, 5*time.Millisecond)
+}

client/internal/pqkem/env.go

@@ -0,0 +1,138 @@
+package pqkem
+
+import (
+	"context"
+	"log/slog"
+	"os"
+	"strconv"
+	"strings"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// EnvEnabled is the environment variable that turns the ML-KEM post-quantum
+// exchange on for this client. Accepts on/off aliases plus anything
+// strconv.ParseBool understands (true/false/1/0).
+const EnvEnabled = "NB_ENABLE_PQ_MLKEM"
+
+// Enabled reports whether the ML-KEM PQ exchange is enabled via the environment.
+// An empty or unrecognized value is treated as disabled.
+func Enabled() bool {
+	raw := strings.ToLower(strings.TrimSpace(os.Getenv(EnvEnabled)))
+	switch raw {
+	case "":
+		return false
+	case "on":
+		return true
+	case "off":
+		return false
+	}
+	enabled, err := strconv.ParseBool(raw)
+	if err != nil {
+		log.Warnf("failed to parse %s value %q: %v", EnvEnabled, raw, err)
+		return false
+	}
+	return enabled
+}
+
+// EnvStrict enables strict (fail-closed) mode: block peer traffic until the ML-KEM
+// PSK has been established, instead of the default opportunistic behaviour that lets
+// the tunnel come up classically and upgrades to PQ once the exchange converges.
+const EnvStrict = "NB_PQ_MLKEM_STRICT"
+
+// Strict reports whether strict (fail-closed) mode is enabled via the environment.
+// An empty or unrecognized value is treated as disabled (opportunistic).
+func Strict() bool {
+	switch strings.ToLower(strings.TrimSpace(os.Getenv(EnvStrict))) {
+	case "on":
+		return true
+	case "", "off":
+		return false
+	}
+	enabled, err := strconv.ParseBool(strings.TrimSpace(os.Getenv(EnvStrict)))
+	if err != nil {
+		log.Warnf("failed to parse %s value %q: %v", EnvStrict, os.Getenv(EnvStrict), err)
+		return false
+	}
+	return enabled
+}
+
+// EnvLogLevel overrides the ML-KEM manager's slog level (trace/debug/info/warn/error).
+// Defaults to info. The verbose per-exchange lifecycle logs are emitted at trace.
+const EnvLogLevel = "NB_PQ_MLKEM_LOG_LEVEL"
+
+// LevelTrace is a custom slog level below Debug for the verbose per-exchange lifecycle
+// logs, so they stay off unless NB_PQ_MLKEM_LOG_LEVEL=trace (and the daemon log level
+// is trace, since the records are forwarded to logrus).
+const LevelTrace = slog.LevelDebug - 4
+
+// NewLogger builds the slog logger for the ML-KEM manager. It forwards records to
+// logrus so PQ logs land in the same sink as the rest of the daemon (console +
+// client.log) rather than stdout. Verbosity is gated by EnvLogLevel.
+func NewLogger() *slog.Logger {
+	return slog.New(slogToLogrus{})
+}
+
+func logLevel() slog.Level {
+	switch strings.ToLower(strings.TrimSpace(os.Getenv(EnvLogLevel))) {
+	case "trace":
+		return LevelTrace
+	case "debug":
+		return slog.LevelDebug
+	case "warn":
+		return slog.LevelWarn
+	case "error":
+		return slog.LevelError
+	default:
+		return slog.LevelInfo
+	}
+}
+
+// slogToLogrus is a slog.Handler that forwards records to logrus, so the ML-KEM
+// manager's logs go wherever the daemon's logrus is configured (console + client.log)
+// instead of stdout. Verbosity is gated by EnvLogLevel via logLevel().
+type slogToLogrus struct {
+	fields log.Fields
+}
+
+func (h slogToLogrus) Enabled(_ context.Context, level slog.Level) bool {
+	return level >= logLevel()
+}
+
+func (h slogToLogrus) Handle(_ context.Context, r slog.Record) error {
+	fields := make(log.Fields, len(h.fields)+r.NumAttrs())
+	for k, v := range h.fields {
+		fields[k] = v
+	}
+	r.Attrs(func(a slog.Attr) bool {
+		fields[a.Key] = a.Value.Any()
+		return true
+	})
+	entry := log.WithFields(fields)
+	switch {
+	case r.Level >= slog.LevelError:
+		entry.Error(r.Message)
+	case r.Level >= slog.LevelWarn:
+		entry.Warn(r.Message)
+	case r.Level >= slog.LevelInfo:
+		entry.Info(r.Message)
+	case r.Level >= slog.LevelDebug:
+		entry.Debug(r.Message)
+	default:
+		entry.Trace(r.Message)
+	}
+	return nil
+}
+
+func (h slogToLogrus) WithAttrs(attrs []slog.Attr) slog.Handler {
+	fields := make(log.Fields, len(h.fields)+len(attrs))
+	for k, v := range h.fields {
+		fields[k] = v
+	}
+	for _, a := range attrs {
+		fields[a.Key] = a.Value.Any()
+	}
+	return slogToLogrus{fields: fields}
+}
+
+func (h slogToLogrus) WithGroup(_ string) slog.Handler { return h }

client/internal/pqkem/kem.go

@@ -0,0 +1,178 @@
+// Package pqkem is a spike (NET-1406) for a post-quantum pre-shared-key exchange
+// that could replace Rosenpass. It performs an X25519MLKEM768 hybrid key
+// encapsulation and derives a 32-byte pre-shared key (PSK).
+//
+// The exchange is a single round trip designed to ride the (already
+// authenticated) Signal offer/answer channel:
+//
+//	initiator --Offer(1216B)--> responder
+//	initiator <--Answer(1120B)-- responder
+//
+// Both sides then hold the same PSK, which is bound to the two peers' identities
+// (their peer identity keys) so the derived key cannot be transplanted
+// to a different peer pair even if the transport authentication were bypassed.
+//
+// Combiner note: this follows draft-ietf-tls-ecdhe-mlkem for X25519MLKEM768 — on
+// the wire ML-KEM ‖ X25519 (the draft deliberately reversed the share order for
+// this group), and ML-KEM_ss ‖ X25519_ss as the KDF input. The PSK is derived with
+// HKDF-SHA256 over that hybrid secret, salted with a domain-separation label and
+// bound (via the HKDF info) to the full transcript and the canonicalised peer
+// identities.
+package pqkem
+
+import (
+	"crypto/ecdh"
+	"crypto/hkdf"
+	"crypto/mlkem"
+	"crypto/rand"
+	"crypto/sha256"
+	"fmt"
+)
+
+const (
+	// OfferSize is the initiator message: ML-KEM-768 encapsulation key ‖ X25519 public key
+	// (share order per draft-ietf-tls-ecdhe-mlkem for X25519MLKEM768).
+	OfferSize = mlkem.EncapsulationKeySize768 + 32 // 1216
+	// AnswerSize is the responder message: ML-KEM-768 ciphertext ‖ X25519 public key.
+	AnswerSize = mlkem.CiphertextSize768 + 32 // 1120
+
+	pskLabel = "netbird-pq-psk-v1"
+)
+
+// PSK is the 32-byte derived pre-shared key handed to the consumer to key its channel.
+type PSK [32]byte
+
+// Binding identifies the peer pair the PSK is derived for. Callers set both
+// peer identity keys; the order does not matter (it is canonicalised).
+type Binding struct {
+	LocalID  []byte
+	RemoteID []byte
+}
+
+// Initiator holds the ephemeral secrets between Offer and Finish.
+type Initiator struct {
+	x25519  *ecdh.PrivateKey
+	mlkemDK *mlkem.DecapsulationKey768
+	offer   []byte
+}
+
+// NewInitiator generates the ephemeral X25519 + ML-KEM-768 keypairs.
+func NewInitiator() (*Initiator, error) {
+	x, err := ecdh.X25519().GenerateKey(rand.Reader)
+	if err != nil {
+		return nil, fmt.Errorf("x25519 keygen: %w", err)
+	}
+	dk, err := mlkem.GenerateKey768()
+	if err != nil {
+		return nil, fmt.Errorf("ml-kem keygen: %w", err)
+	}
+
+	offer := make([]byte, 0, OfferSize)
+	offer = append(offer, dk.EncapsulationKey().Bytes()...)
+	offer = append(offer, x.PublicKey().Bytes()...)
+
+	return &Initiator{x25519: x, mlkemDK: dk, offer: offer}, nil
+}
+
+// Offer returns the initiator message to send over Signal.
+func (i *Initiator) Offer() []byte {
+	return i.offer
+}
+
+// Finish consumes the responder's answer and derives the PSK.
+func (i *Initiator) Finish(answer []byte, b Binding) (PSK, error) {
+	if len(answer) != AnswerSize {
+		return PSK{}, fmt.Errorf("answer: got %d bytes, want %d", len(answer), AnswerSize)
+	}
+	ct := answer[:mlkem.CiphertextSize768]
+	peerX := answer[mlkem.CiphertextSize768:]
+
+	ssMLKEM, err := i.mlkemDK.Decapsulate(ct)
+	if err != nil {
+		return PSK{}, fmt.Errorf("ml-kem decapsulate: %w", err)
+	}
+	pub, err := ecdh.X25519().NewPublicKey(peerX)
+	if err != nil {
+		return PSK{}, fmt.Errorf("parse peer x25519: %w", err)
+	}
+	ssX, err := i.x25519.ECDH(pub)
+	if err != nil {
+		return PSK{}, fmt.Errorf("x25519 ecdh: %w", err)
+	}
+
+	return derivePSK(ssMLKEM, ssX, i.offer, answer, b)
+}
+
+// Respond consumes an initiator offer, produces the answer, and derives the PSK.
+func Respond(offer []byte, b Binding) (answer []byte, psk PSK, err error) {
+	if len(offer) != OfferSize {
+		return nil, PSK{}, fmt.Errorf("offer: got %d bytes, want %d", len(offer), OfferSize)
+	}
+	peerEK := offer[:mlkem.EncapsulationKeySize768]
+	peerX := offer[mlkem.EncapsulationKeySize768:]
+
+	ek, err := mlkem.NewEncapsulationKey768(peerEK)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("parse peer ml-kem key: %w", err)
+	}
+	ssMLKEM, ct := ek.Encapsulate()
+
+	x, err := ecdh.X25519().GenerateKey(rand.Reader)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("x25519 keygen: %w", err)
+	}
+	pub, err := ecdh.X25519().NewPublicKey(peerX)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("parse peer x25519: %w", err)
+	}
+	ssX, err := x.ECDH(pub)
+	if err != nil {
+		return nil, PSK{}, fmt.Errorf("x25519 ecdh: %w", err)
+	}
+
+	answer = make([]byte, 0, AnswerSize)
+	answer = append(answer, ct...)
+	answer = append(answer, x.PublicKey().Bytes()...)
+
+	// derivePSK uses the same argument order on both sides; the responder's local
+	// binding is the mirror of the initiator's, canonicalised inside derivePSK.
+	psk, err = derivePSK(ssMLKEM, ssX, offer, answer, b)
+	if err != nil {
+		return nil, PSK{}, err
+	}
+	return answer, psk, nil
+}
+
+// derivePSK runs HKDF-SHA256 over the hybrid shared secret (ML-KEM_ss ‖ X25519_ss,
+// per draft-ietf-tls-ecdhe-mlkem), salted with the domain-separation label, and binds
+// the result — via the HKDF info — to the full transcript (offer ‖ answer) and the
+// canonicalised peer identities, so the PSK cannot be transplanted to another peer
+// pair or a different exchange.
+func derivePSK(ssMLKEM, ssX, offer, answer []byte, b Binding) (PSK, error) {
+	lo, hi := canonicalPair(b.LocalID, b.RemoteID)
+
+	ikm := make([]byte, 0, len(ssMLKEM)+len(ssX))
+	ikm = append(ikm, ssMLKEM...)
+	ikm = append(ikm, ssX...)
+
+	info := make([]byte, 0, len(offer)+len(answer)+len(lo)+len(hi))
+	info = append(info, offer...)
+	info = append(info, answer...)
+	info = append(info, lo...)
+	info = append(info, hi...)
+
+	var psk PSK
+	key, err := hkdf.Key(sha256.New, ikm, []byte(pskLabel), string(info), len(psk))
+	if err != nil {
+		return PSK{}, fmt.Errorf("hkdf derive psk: %w", err)
+	}
+	copy(psk[:], key)
+	return psk, nil
+}
+
+func canonicalPair(a, b []byte) (lo, hi []byte) {
+	if string(a) <= string(b) {
+		return a, b
+	}
+	return b, a
+}

client/internal/pqkem/kem_test.go

@@ -0,0 +1,89 @@
+package pqkem
+
+import (
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+)
+
+var (
+	wgA = []byte("peer-A-wireguard-pubkey-32bytes!")
+	wgB = []byte("peer-B-wireguard-pubkey-32bytes!")
+)
+
+func TestExchange_DerivesMatchingPSK(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	require.Len(t, init.Offer(), OfferSize)
+
+	answer, pskB, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+	require.Len(t, answer, AnswerSize)
+
+	pskA, err := init.Finish(answer, Binding{LocalID: wgA, RemoteID: wgB})
+	require.NoError(t, err)
+
+	require.Equal(t, pskB, pskA, "both sides must derive the same PSK")
+	require.NotEqual(t, PSK{}, pskA, "PSK must not be zero")
+}
+
+func TestExchange_PSKBoundToPeerIdentities(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	// responder computes with the honest pair...
+	_, pskHonest, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+
+	// ...a second responder run with a different peer identity yields a different PSK,
+	// even though the KEM material would otherwise combine identically.
+	wgC := []byte("peer-C-wireguard-pubkey-32bytes!")
+	_, pskWrong, err := Respond(init.Offer(), Binding{LocalID: wgC, RemoteID: wgA})
+	require.NoError(t, err)
+
+	require.NotEqual(t, pskHonest, pskWrong, "PSK must be bound to the peer pair")
+}
+
+func TestExchange_RejectsMalformedMessages(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+
+	_, _, err = Respond(init.Offer()[:10], Binding{})
+	require.Error(t, err)
+
+	_, err = init.Finish([]byte("too short"), Binding{})
+	require.Error(t, err)
+}
+
+// TestExchange_ReportSizesAndTiming is a spike measurement, not a pass/fail gate.
+// Run with: go test -run TestExchange_ReportSizesAndTiming -v ./client/internal/pqkem/
+func TestExchange_ReportSizesAndTiming(t *testing.T) {
+	const iters = 200
+
+	var tInit, tResp, tFinish time.Duration
+	for i := 0; i < iters; i++ {
+		s0 := time.Now()
+		init, err := NewInitiator()
+		require.NoError(t, err)
+		tInit += time.Since(s0)
+
+		s1 := time.Now()
+		answer, _, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+		require.NoError(t, err)
+		tResp += time.Since(s1)
+
+		s2 := time.Now()
+		_, err = init.Finish(answer, Binding{LocalID: wgA, RemoteID: wgB})
+		require.NoError(t, err)
+		tFinish += time.Since(s2)
+	}
+
+	t.Logf("wire sizes:   offer=%d B   answer=%d B   (Rosenpass static pubkey ~524160 B)", OfferSize, AnswerSize)
+	t.Logf("total on-wire per handshake: %d B  (~%.0fx smaller than RP static key)", OfferSize+AnswerSize, 524160.0/float64(OfferSize+AnswerSize))
+	t.Logf("avg NewInitiator (keygen): %s", tInit/iters)
+	t.Logf("avg Respond (encaps+dh):   %s", tResp/iters)
+	t.Logf("avg Finish (decaps+dh):    %s", tFinish/iters)
+	t.Logf("avg full handshake CPU:    %s", (tInit+tResp+tFinish)/iters)
+}

client/internal/pqkem/manager.go

@@ -0,0 +1,399 @@
+package pqkem
+
+import (
+	"context"
+	"crypto/rand"
+	"fmt"
+	"log/slog"
+	"net/netip"
+	"sync"
+	"time"
+)
+
+const (
+	// DefaultRetryInterval is how often the initiator retransmits its outstanding
+	// data-path offer while awaiting the answer.
+	DefaultRetryInterval = 2 * time.Second
+	// DefaultMaxRetries bounds how many ticks an exchange may run before it is
+	// declared failed. The convergence deadline is thus MaxRetries * RetryInterval.
+	DefaultMaxRetries = 10
+	// DefaultMaxRekeyFailures is how many consecutive rekey (non-initial) failures
+	// are tolerated before OnRekeyFailed. The initial exchange fails immediately.
+	DefaultMaxRekeyFailures = 3
+
+	// rotationActivityWindow gates rotation on recent real-data activity: a rekey
+	// clocks a rotation only if the peer exchanged user data within this window. It
+	// must stay shorter than the data path's rekey interval (WireGuard
+	// REKEY_AFTER_TIME ~120s) so the rotation's own traffic — which itself renews the
+	// activity signal — ages out before the next rekey, letting an idle tunnel stop
+	// rotating instead of self-sustaining.
+	rotationActivityWindow = 90 * time.Second
+)
+
+// LocalID and RemoteID are peer identity keys (e.g. WireGuard public keys). They are
+// distinct types so the local and a remote identity cannot be mixed up.
+type (
+	LocalID  string
+	RemoteID string
+)
+
+// Transport is the data-path socket the Manager drives (the analogue of
+// go-rosenpass's Conn). It is a dumb mover of bytes to/from endpoints: the Manager
+// owns the remoteID<->endpoint routing and hands the transport a resolved endpoint
+// to Send, and reverse-resolves the source of each inbound datagram. Its lifecycle
+// belongs to the Manager (Run at Start, Close at Stop).
+type Transport interface {
+	// Send delivers msg to the given data-path endpoint.
+	Send(endpoint netip.AddrPort, msg []byte) error
+	// LocalPort is the bound local UDP port, announced to peers so they know where
+	// to send data-path messages.
+	LocalPort() int
+	// Run starts delivering inbound datagrams as (source endpoint, msg) to onInbound
+	// and returns immediately; it runs until Close.
+	Run(onInbound func(src netip.AddrPort, msg []byte))
+	// Close stops delivery and releases the socket.
+	Close() error
+}
+
+// exchangeState is the single source of truth for an exchange's role and phase.
+type exchangeState uint8
+
+const (
+	stateReserved       exchangeState = iota // responder: deriving the answer
+	stateAwaitingAnswer                      // initiator: offer sent, awaiting the answer
+	stateAwaitingRekey                       // initiator: PSK derived+set, awaiting OnDataPathRekeyed to chain the next offer
+	stateAwaitingAck                         // responder: answer sent, awaiting the next offer that acks this exchange
+)
+
+// exchangeCtl holds all state for one in-flight exchange with a peer, under the
+// Manager's single lock. state drives every decision. lastSent is the current
+// data-path retransmit payload (the offer, for the initiator). initiator is the
+// ephemeral handle used at Finish; pendingPSK is the responder's derived key.
+// viaSignal records that the offer went to the host for the signalling channel, so
+// the loop does not retransmit it on the data path. Only the initiator runs a
+// retransmit loop, so only it sets cancel.
+type exchangeCtl struct {
+	id         ExchangeID
+	state      exchangeState
+	startedAt  time.Time
+	cancel     context.CancelFunc
+	lastSent   []byte
+	initiator  *Initiator
+	pendingPSK PSK
+	viaSignal  bool
+}
+
+// Manager is the stateful orchestrator — the analogue of go-rosenpass's Server. It
+// drives the X25519MLKEM768 exchange, owns the peer endpoint routing and the data-path
+// transport, and surfaces the derived PSK and convergence to the host via
+// CallbackHandler. It is event-driven: the bootstrap is triggered by the host
+// (SignalOffer) and each rotation is clocked by OnDataPathRekeyed. The cryptography is
+// the pure kem.go primitives; all state lives here under one lock.
+type Manager struct {
+	localID   LocalID
+	cbHandler CallbackHandler
+	logger    *slog.Logger
+
+	retryInterval    time.Duration
+	maxRetries       int
+	maxRekeyFailures int
+
+	rootCtx    context.Context
+	rootCancel context.CancelFunc
+
+	mu          sync.Mutex
+	transport   Transport
+	exchanges   map[RemoteID]*exchangeCtl   // in-flight exchange per peer
+	established map[RemoteID]bool           // peer has completed at least one exchange
+	failures    map[RemoteID]int            // consecutive rekey failures per peer
+	psks        map[RemoteID]PSK            // latest derived PSK per peer (pulled at WG peer-config time)
+	peerAddrs   map[RemoteID]netip.AddrPort // remoteID -> data-path endpoint (send routing)
+	peersByAddr map[netip.AddrPort]RemoteID // reverse: source endpoint -> remoteID (inbound)
+	wait        sync.WaitGroup
+}
+
+// NewManager builds a manager for the local peer identified by its peer identity key
+// (used for the deterministic initiator role and the identity binding). A nil logger
+// falls back to slog.Default(). Install the data-path transport with Start.
+func NewManager(localID LocalID, h CallbackHandler, logger *slog.Logger) *Manager {
+	if logger == nil {
+		logger = slog.Default()
+	}
+	ctx, cancel := context.WithCancel(context.Background())
+	return &Manager{
+		localID:          localID,
+		cbHandler:        h,
+		logger:           logger,
+		retryInterval:    DefaultRetryInterval,
+		maxRetries:       DefaultMaxRetries,
+		maxRekeyFailures: DefaultMaxRekeyFailures,
+		rootCtx:          ctx,
+		rootCancel:       cancel,
+		exchanges:        make(map[RemoteID]*exchangeCtl),
+		established:      make(map[RemoteID]bool),
+		failures:         make(map[RemoteID]int),
+		psks:             make(map[RemoteID]PSK),
+		peerAddrs:        make(map[RemoteID]netip.AddrPort),
+		peersByAddr:      make(map[netip.AddrPort]RemoteID),
+	}
+}
+
+// Start installs the data-path transport and begins its inbound delivery. The Manager
+// owns it from here; Stop closes it. Start/Stop are the transport lifecycle pair.
+func (m *Manager) Start(t Transport) {
+	m.mu.Lock()
+	m.transport = t
+	m.mu.Unlock()
+	if t != nil {
+		t.Run(m.onDataPathInbound)
+	}
+}
+
+// LocalPort is the data-path transport's bound UDP port (0 if no transport), to be
+// announced to peers.
+func (m *Manager) LocalPort() int {
+	m.mu.Lock()
+	t := m.transport
+	m.mu.Unlock()
+	if t == nil {
+		return 0
+	}
+	return t.LocalPort()
+}
+
+// IsInitiator reports whether the local peer drives the exchange for this remote
+// peer. Roles are deterministic (lexicographic identity-key compare) so exactly one
+// side initiates, mirroring how Rosenpass picks its handshake initiator.
+func (m *Manager) IsInitiator(remoteID RemoteID) bool {
+	return string(m.localID) > string(remoteID)
+}
+
+// PSK returns the latest PSK derived for the peer, for the host to program at WG
+// peer-config time (the pull path). ok is false until an exchange has derived one.
+func (m *Manager) PSK(remoteID RemoteID) (PSK, bool) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	psk, ok := m.psks[remoteID]
+	return psk, ok
+}
+
+// trace logs at LevelTrace, the verbose per-exchange lifecycle level gated by
+// NB_PQ_MLKEM_LOG_LEVEL=trace.
+func (m *Manager) trace(msg string, args ...any) {
+	m.logger.Log(context.Background(), LevelTrace, msg, args...)
+}
+
+// AddPeer registers where a peer's data-path messages are sent and received: its
+// overlay endpoint (IP:port). Re-adding updates the endpoint.
+func (m *Manager) AddPeer(remoteID RemoteID, endpoint netip.AddrPort) {
+	if !endpoint.IsValid() {
+		return
+	}
+	m.mu.Lock()
+	if old, ok := m.peerAddrs[remoteID]; ok {
+		delete(m.peersByAddr, old)
+	}
+	m.peerAddrs[remoteID] = endpoint
+	m.peersByAddr[endpoint] = remoteID
+	m.mu.Unlock()
+}
+
+// RemovePeer stops any in-flight exchange for a peer and drops its state and routing.
+func (m *Manager) RemovePeer(remoteID RemoteID) {
+	m.mu.Lock()
+	if ex, ok := m.exchanges[remoteID]; ok {
+		if ex.cancel != nil {
+			ex.cancel()
+		}
+		delete(m.exchanges, remoteID)
+	}
+	delete(m.established, remoteID)
+	delete(m.failures, remoteID)
+	delete(m.psks, remoteID)
+	if ep, ok := m.peerAddrs[remoteID]; ok {
+		delete(m.peersByAddr, ep)
+		delete(m.peerAddrs, remoteID)
+	}
+	m.mu.Unlock()
+}
+
+// Stop cancels all in-flight exchanges, closes the transport, and waits for the
+// exchange goroutines to exit.
+func (m *Manager) Stop() {
+	m.rootCancel()
+	m.wait.Wait()
+	m.mu.Lock()
+	t := m.transport
+	m.transport = nil
+	m.exchanges = make(map[RemoteID]*exchangeCtl)
+	m.psks = make(map[RemoteID]PSK)
+	m.mu.Unlock()
+	if t != nil {
+		if err := t.Close(); err != nil {
+			m.logger.Warn("pqkem: closing data-path transport", "err", err)
+		}
+	}
+}
+
+// ---- Signalling channel (host-driven; rides the host's negotiation) ----
+
+// SignalOffer returns the KEM offer for the host to embed in its outgoing offer to
+// remoteID (bootstrap). It returns (nil, nil) when the local peer is not the
+// initiator. It is idempotent for an in-flight bootstrap: a repeat call returns the
+// same offer rather than starting a new exchange.
+func (m *Manager) SignalOffer(remoteID RemoteID) ([]byte, error) {
+	if !m.IsInitiator(remoteID) {
+		return nil, nil
+	}
+	m.mu.Lock()
+	if ex := m.exchanges[remoteID]; ex != nil && ex.viaSignal && ex.state == stateAwaitingAnswer {
+		last := ex.lastSent
+		m.mu.Unlock()
+		return last, nil
+	}
+	m.mu.Unlock()
+	// bootstrap offer acknowledges nothing (zero AckID).
+	return m.startExchange(remoteID, true, ExchangeID{})
+}
+
+// SignalOnOffer processes a KEM offer the host extracted from an incoming offer and
+// returns the KEM answer for the host to embed in its outgoing answer.
+func (m *Manager) SignalOnOffer(remoteID RemoteID, offer []byte) ([]byte, error) {
+	typ, msg, err := Decode(offer)
+	if err != nil {
+		return nil, fmt.Errorf("decode signal offer from %s: %w", remoteID, err)
+	}
+	if typ != MsgOffer {
+		return nil, fmt.Errorf("expected offer from %s, got type %d", remoteID, typ)
+	}
+	return m.processOffer(remoteID, msg.(*OfferMsg))
+}
+
+// SignalOnAnswer processes a KEM answer the host extracted from an incoming answer.
+// There is no reply: the next offer (over the data path) acknowledges this exchange.
+func (m *Manager) SignalOnAnswer(remoteID RemoteID, answer []byte) error {
+	typ, msg, err := Decode(answer)
+	if err != nil {
+		return fmt.Errorf("decode signal answer from %s: %w", remoteID, err)
+	}
+	if typ != MsgAnswer {
+		return fmt.Errorf("expected answer from %s, got type %d", remoteID, typ)
+	}
+	return m.processAnswer(remoteID, msg.(*AnswerMsg))
+}
+
+// ---- Data path ----
+
+// onDataPathInbound is the transport's inbound handler: it reverse-resolves the
+// source endpoint to a peer and dispatches. Unknown sources are dropped.
+func (m *Manager) onDataPathInbound(src netip.AddrPort, msg []byte) {
+	m.mu.Lock()
+	remoteID, ok := m.peersByAddr[src]
+	m.mu.Unlock()
+	if !ok {
+		return
+	}
+	if err := m.OnDataPathMessage(remoteID, msg); err != nil {
+		m.trace("pqkem: inbound", "peer", remoteID, "err", err)
+	}
+}
+
+// OnDataPathMessage handles a KEM message received over the data path from remoteID
+// and pushes any reply back over the data path.
+func (m *Manager) OnDataPathMessage(remoteID RemoteID, raw []byte) error {
+	typ, msg, err := Decode(raw)
+	if err != nil {
+		return fmt.Errorf("decode data-path msg from %s: %w", remoteID, err)
+	}
+	switch typ {
+	case MsgOffer:
+		answer, err := m.processOffer(remoteID, msg.(*OfferMsg))
+		if err != nil {
+			return err
+		}
+		if answer == nil {
+			return nil
+		}
+		return m.pushDataPath(remoteID, answer)
+	case MsgAnswer:
+		return m.processAnswer(remoteID, msg.(*AnswerMsg))
+	default:
+		return fmt.Errorf("unhandled data-path message type %d from %s", typ, remoteID)
+	}
+}
+
+// OnDataPathRekeyed notifies that the peer's data path is up and freshly keyed with
+// the latest PSK (fired on first establishment AND every rekey). If we are the
+// initiator that just derived a PSK, it chains the next exchange: a fresh offer over
+// the data path that acknowledges the just-completed one (its arrival under the new
+// key proves to the responder that the key works).
+// OnDataPathRekeyed clocks the next chained PSK rotation on a fresh data-path rekey.
+// sinceActivity is how long ago the peer last exchanged real user data; when it
+// exceeds rotationActivityWindow the tunnel is treated as idle and rotation is
+// skipped — an idle tunnel has nothing to protect, and rotating would emit data-path
+// traffic that keeps the peer artificially active (see conn.onWGCheckSuccess).
+func (m *Manager) OnDataPathRekeyed(remoteID RemoteID, sinceActivity time.Duration) {
+	if sinceActivity >= rotationActivityWindow {
+		m.trace("pqkem: peer idle, skipping data-path rotation", "peer", remoteID, "since_activity", sinceActivity)
+		return
+	}
+
+	m.mu.Lock()
+	ex := m.exchanges[remoteID]
+	chain := ex != nil && ex.state == stateAwaitingRekey
+	var ackID ExchangeID
+	if chain {
+		ackID = ex.id
+	}
+	m.mu.Unlock()
+
+	m.trace("pqkem: data-path rekey signal", "peer", remoteID, "chaining", chain)
+	if !chain {
+		return
+	}
+	offer, err := m.startExchange(remoteID, false, ackID)
+	if err != nil {
+		m.logger.Error("pqkem: chain offer failed to start", "peer", remoteID, "err", err)
+		return
+	}
+	if err := m.pushDataPath(remoteID, offer); err != nil {
+		m.logger.Warn("pqkem: send chain offer failed", "peer", remoteID, "err", err)
+		return
+	}
+	m.trace("pqkem: chain offer sent over data path", "peer", remoteID)
+}
+
+// OnDataPathDown notifies that the peer's data path went down. Rotations resume once
+// the host re-bootstraps over signalling on reconnect; in-flight data-path sends will
+// simply fail until then. Reserved as an explicit hook.
+func (m *Manager) OnDataPathDown(remoteID RemoteID) {}
+
+// ---- internals ----
+
+// pushDataPath resolves the peer's endpoint and sends over the data-path transport,
+// erroring if the peer is unknown or no transport is set.
+func (m *Manager) pushDataPath(remoteID RemoteID, msg []byte) error {
+	m.mu.Lock()
+	ep, ok := m.peerAddrs[remoteID]
+	t := m.transport
+	m.mu.Unlock()
+	if !ok {
+		return fmt.Errorf("no data-path endpoint for peer %s", remoteID)
+	}
+	if t == nil {
+		return fmt.Errorf("no data-path transport")
+	}
+	return t.Send(ep, msg)
+}
+
+func (m *Manager) binding(remoteID RemoteID) Binding {
+	return Binding{LocalID: []byte(m.localID), RemoteID: []byte(remoteID)}
+}
+
+func newExchangeID() (ExchangeID, error) {
+	var id ExchangeID
+	if _, err := rand.Read(id[:]); err != nil {
+		return ExchangeID{}, fmt.Errorf("generate exchange id: %w", err)
+	}
+	return id, nil
+}

client/internal/pqkem/manager_test.go

@@ -0,0 +1,193 @@
+package pqkem
+
+import (
+	"fmt"
+	"net/netip"
+	"sync"
+	"sync/atomic"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+// netSwitch is an in-memory UDP fabric: transports register their endpoint and get
+// datagrams delivered to their inbound handler.
+type netSwitch struct {
+	mu sync.Mutex
+	h  map[netip.AddrPort]func(netip.AddrPort, []byte)
+}
+
+func newSwitch() *netSwitch {
+	return &netSwitch{h: map[netip.AddrPort]func(netip.AddrPort, []byte){}}
+}
+
+func (s *netSwitch) register(ep netip.AddrPort, fn func(netip.AddrPort, []byte)) {
+	s.mu.Lock()
+	s.h[ep] = fn
+	s.mu.Unlock()
+}
+
+func (s *netSwitch) deliver(dst, src netip.AddrPort, msg []byte) error {
+	s.mu.Lock()
+	fn := s.h[dst]
+	s.mu.Unlock()
+	if fn == nil {
+		return fmt.Errorf("no route to %s", dst)
+	}
+	fn(src, msg)
+	return nil
+}
+
+// loopback is an endpoint-based pqkem.Transport over a netSwitch, with a switchable
+// drop flag.
+type loopback struct {
+	ep   netip.AddrPort
+	sw   *netSwitch
+	drop atomic.Bool
+}
+
+func (l *loopback) Send(dst netip.AddrPort, msg []byte) error {
+	if l.drop.Load() {
+		return nil
+	}
+	return l.sw.deliver(dst, l.ep, append([]byte(nil), msg...))
+}
+
+func (l *loopback) LocalPort() int                             { return int(l.ep.Port()) }
+func (l *loopback) Run(onInbound func(netip.AddrPort, []byte)) { l.sw.register(l.ep, onInbound) }
+func (l *loopback) Close() error                               { return nil }
+
+type fakeWG struct {
+	mu     sync.Mutex
+	psks   map[RemoteID]PSK
+	failed []RemoteID
+}
+
+func newFakeWG() *fakeWG { return &fakeWG{psks: map[RemoteID]PSK{}} }
+
+func (f *fakeWG) OnNewPSKReady(remoteID RemoteID, psk PSK) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	f.psks[remoteID] = psk
+	return nil
+}
+
+func (f *fakeWG) OnRekeyFailed(remoteID RemoteID) error {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	f.failed = append(f.failed, remoteID)
+	return nil
+}
+
+func (f *fakeWG) psk(peer RemoteID) PSK {
+	f.mu.Lock()
+	defer f.mu.Unlock()
+	return f.psks[peer]
+}
+
+var (
+	epA = netip.MustParseAddrPort("100.64.0.1:51833")
+	epB = netip.MustParseAddrPort("100.64.0.2:51833")
+)
+
+// pair builds two wired managers (B is the initiator, "bbbb" > "aaaa") sharing a
+// netSwitch, with each peer's data-path endpoint registered. lbB is B's loopback
+// (for toggling drop).
+func pair(t *testing.T) (dA, dB *Manager, wgA, wgB *fakeWG, lbB *loopback) {
+	t.Helper()
+	sw := newSwitch()
+	wgA = newFakeWG()
+	wgB = newFakeWG()
+	dA = NewManager("aaaa", wgA, nil)
+	dB = NewManager("bbbb", wgB, nil)
+	dA.Start(&loopback{ep: epA, sw: sw})
+	lbB = &loopback{ep: epB, sw: sw}
+	dB.Start(lbB)
+	dA.AddPeer("bbbb", epB)
+	dB.AddPeer("aaaa", epA)
+	return dA, dB, wgA, wgB, lbB
+}
+
+// bootstrap runs the signalling offer/answer (the test plays the host carrying bytes).
+func bootstrap(t *testing.T, dA, dB *Manager) {
+	t.Helper()
+	offer, err := dB.SignalOffer("aaaa")
+	require.NoError(t, err)
+	require.NotNil(t, offer)
+	answer, err := dA.SignalOnOffer("bbbb", offer)
+	require.NoError(t, err)
+	require.NotNil(t, answer)
+	require.NoError(t, dB.SignalOnAnswer("aaaa", answer))
+}
+
+func TestManager_BootstrapDerivesSamePSK(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+
+	pskA := wgA.psk("bbbb")
+	pskB := wgB.psk("aaaa")
+	require.NotEqual(t, PSK{}, pskA)
+	require.Equal(t, pskB, pskA, "both sides derive the same PSK from the bootstrap exchange")
+}
+
+func TestManager_ChainRotatesAndAcks(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+	psk1 := wgB.psk("aaaa")
+
+	// Data path up: B (initiator) chains the next offer over the data path, which
+	// rotates both to a fresh PSK and acknowledges A.
+	dA.OnDataPathRekeyed("bbbb", 0)
+	dB.OnDataPathRekeyed("aaaa", 0)
+
+	psk2A := wgA.psk("bbbb")
+	psk2B := wgB.psk("aaaa")
+	require.Equal(t, psk2B, psk2A, "both sides converge on the rotated PSK")
+	require.NotEqual(t, psk1, psk2B, "the chain rotated to a new PSK")
+}
+
+func TestManager_RotationSkippedWhenIdle(t *testing.T) {
+	dA, dB, wgA, wgB, _ := pair(t)
+	defer dA.Stop()
+	defer dB.Stop()
+
+	bootstrap(t, dA, dB)
+	psk1 := wgB.psk("aaaa")
+	require.NotEqual(t, PSK{}, psk1)
+
+	// Idle: the peer's last real-data activity is older than the window, so a rekey
+	// must NOT clock a rotation.
+	dA.OnDataPathRekeyed("bbbb", rotationActivityWindow)
+	dB.OnDataPathRekeyed("aaaa", rotationActivityWindow)
+	require.Equal(t, psk1, wgB.psk("aaaa"), "idle peer must not rotate the PSK")
+	require.Equal(t, psk1, wgA.psk("bbbb"), "idle peer must not rotate the PSK")
+
+	// Active: activity within the window clocks the rotation as usual.
+	dA.OnDataPathRekeyed("bbbb", rotationActivityWindow-1)
+	dB.OnDataPathRekeyed("aaaa", rotationActivityWindow-1)
+	psk2 := wgB.psk("aaaa")
+	require.NotEqual(t, psk1, psk2, "recent activity must clock a rotation")
+	require.Equal(t, psk2, wgA.psk("bbbb"), "both sides converge on the rotated PSK")
+}
+
+func TestManager_NonInitiatorReturnsNoOffer(t *testing.T) {
+	dA := NewManager("aaaa", newFakeWG(), nil)
+	defer dA.Stop()
+
+	offer, err := dA.SignalOffer("bbbb") // not the initiator vs "bbbb"
+	require.NoError(t, err)
+	require.Nil(t, offer)
+}
+
+func TestManager_StopIsIdempotent(t *testing.T) {
+	dA := NewManager("aaaa", newFakeWG(), nil)
+	dA.Start(&loopback{ep: epA, sw: newSwitch()})
+	dA.Stop()
+	dA.Stop() // must not panic or hang
+}

client/internal/pqkem/message.go

@@ -0,0 +1,121 @@
+package pqkem
+
+import (
+	"crypto/mlkem"
+	"fmt"
+)
+
+// Wire framing for the PQ-KEM exchange. Messages are self-contained, versioned,
+// transport-agnostic byte blobs: the same bytes ride the signalling channel
+// (initial bootstrap) or a data-tunnel packet (rekey). The library only ever sees
+// opaque []byte at the transport seam.
+//
+// Layout (all messages): [type:1][version:1][exchangeID:16][payload...]
+//
+// There is no confirm message: an exchange is acknowledged by the NEXT offer, which
+// carries the acked exchange's id (see OfferMsg.AckID) and — riding the data path
+// under the freshly adopted key — proves that key works.
+
+const (
+	// ProtocolVersion is bumped on any wire-incompatible change; a peer rejects
+	// messages it does not understand rather than misparsing them.
+	ProtocolVersion uint8 = 1
+
+	// ExchangeIDSize identifies one exchange so answers/acks correlate and stale
+	// messages are dropped.
+	ExchangeIDSize = 16
+
+	headerSize = 1 + 1 + ExchangeIDSize
+)
+
+// MsgType tags the two message kinds of the exchange.
+type MsgType uint8
+
+const (
+	MsgOffer MsgType = iota + 1
+	MsgAnswer
+)
+
+// ExchangeID is the per-exchange correlator. The zero value means "none" (an offer
+// that acknowledges nothing, i.e. the first exchange of a connection).
+type ExchangeID [ExchangeIDSize]byte
+
+// OfferMsg carries the initiator's public material (X25519 pub ‖ ML-KEM encap key)
+// and AckID, the id of the previous exchange this offer acknowledges (zero if none).
+type OfferMsg struct {
+	ExchangeID ExchangeID
+	AckID      ExchangeID
+	// KEMOffer is the raw Initiator.Offer() blob (OfferSize bytes).
+	KEMOffer []byte
+}
+
+// AnswerMsg carries the responder's reply (ML-KEM ciphertext ‖ X25519 pub) for the
+// round identified by ExchangeID.
+type AnswerMsg struct {
+	ExchangeID ExchangeID
+	// KEMAnswer is the raw Respond() answer blob (AnswerSize bytes).
+	KEMAnswer []byte
+}
+
+// Encode serialises the offer with its framed header (payload = AckID ‖ KEMOffer).
+func (m *OfferMsg) Encode() ([]byte, error) {
+	if len(m.KEMOffer) != OfferSize {
+		return nil, fmt.Errorf("offer payload: got %d, want %d", len(m.KEMOffer), OfferSize)
+	}
+	payload := make([]byte, 0, ExchangeIDSize+OfferSize)
+	payload = append(payload, m.AckID[:]...)
+	payload = append(payload, m.KEMOffer...)
+	return frame(MsgOffer, m.ExchangeID, payload), nil
+}
+
+// Encode serialises the answer with its framed header.
+func (m *AnswerMsg) Encode() ([]byte, error) {
+	if len(m.KEMAnswer) != AnswerSize {
+		return nil, fmt.Errorf("answer payload: got %d, want %d", len(m.KEMAnswer), AnswerSize)
+	}
+	return frame(MsgAnswer, m.ExchangeID, m.KEMAnswer), nil
+}
+
+// Decode parses a framed message into one of *OfferMsg / *AnswerMsg.
+func Decode(buf []byte) (MsgType, any, error) {
+	if len(buf) < headerSize {
+		return 0, nil, fmt.Errorf("message too short: %d bytes", len(buf))
+	}
+	typ := MsgType(buf[0])
+	if ver := buf[1]; ver != ProtocolVersion {
+		return typ, nil, fmt.Errorf("unsupported protocol version %d (want %d)", ver, ProtocolVersion)
+	}
+
+	var id ExchangeID
+	copy(id[:], buf[2:headerSize])
+	payload := buf[headerSize:]
+
+	switch typ {
+	case MsgOffer:
+		if len(payload) != ExchangeIDSize+OfferSize {
+			return typ, nil, fmt.Errorf("offer payload: got %d, want %d", len(payload), ExchangeIDSize+OfferSize)
+		}
+		var ack ExchangeID
+		copy(ack[:], payload[:ExchangeIDSize])
+		return typ, &OfferMsg{ExchangeID: id, AckID: ack, KEMOffer: payload[ExchangeIDSize:]}, nil
+	case MsgAnswer:
+		if len(payload) != AnswerSize {
+			return typ, nil, fmt.Errorf("answer payload: got %d, want %d", len(payload), AnswerSize)
+		}
+		return typ, &AnswerMsg{ExchangeID: id, KEMAnswer: payload}, nil
+	default:
+		return typ, nil, fmt.Errorf("unknown message type %d", typ)
+	}
+}
+
+func frame(typ MsgType, id ExchangeID, payload []byte) []byte {
+	buf := make([]byte, headerSize+len(payload))
+	buf[0] = byte(typ)
+	buf[1] = ProtocolVersion
+	copy(buf[2:], id[:])
+	copy(buf[headerSize:], payload)
+	return buf
+}
+
+// compile-time assurance the KEM blob sizes referenced here stay in sync with kem.go.
+var _ = [1]struct{}{}[OfferSize-(32+mlkem.EncapsulationKeySize768)]

client/internal/pqkem/message_test.go

@@ -0,0 +1,57 @@
+package pqkem
+
+import (
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+func TestMessageRoundTrip(t *testing.T) {
+	init, err := NewInitiator()
+	require.NoError(t, err)
+	answer, _, err := Respond(init.Offer(), Binding{LocalID: wgB, RemoteID: wgA})
+	require.NoError(t, err)
+
+	id := ExchangeID{1, 2, 3, 4}
+	ack := ExchangeID{9, 9, 9}
+
+	offBytes, err := (&OfferMsg{ExchangeID: id, AckID: ack, KEMOffer: init.Offer()}).Encode()
+	require.NoError(t, err)
+	typ, decoded, err := Decode(offBytes)
+	require.NoError(t, err)
+	require.Equal(t, MsgOffer, typ)
+	require.Equal(t, id, decoded.(*OfferMsg).ExchangeID)
+	require.Equal(t, ack, decoded.(*OfferMsg).AckID)
+	require.Equal(t, init.Offer(), decoded.(*OfferMsg).KEMOffer)
+
+	ansBytes, err := (&AnswerMsg{ExchangeID: id, KEMAnswer: answer}).Encode()
+	require.NoError(t, err)
+	typ, decoded, err = Decode(ansBytes)
+	require.NoError(t, err)
+	require.Equal(t, MsgAnswer, typ)
+	require.Equal(t, answer, decoded.(*AnswerMsg).KEMAnswer)
+}
+
+func TestDecodeRejects(t *testing.T) {
+	// too short
+	_, _, err := Decode([]byte{1, 1})
+	require.Error(t, err)
+
+	// wrong version
+	bad := make([]byte, headerSize+ExchangeIDSize+OfferSize)
+	bad[0] = byte(MsgOffer)
+	bad[1] = ProtocolVersion + 1
+	_, _, err = Decode(bad)
+	require.Error(t, err)
+
+	// unknown type
+	bad2 := make([]byte, headerSize)
+	bad2[0] = 99
+	bad2[1] = ProtocolVersion
+	_, _, err = Decode(bad2)
+	require.Error(t, err)
+
+	// offer with wrong payload size
+	_, err = (&OfferMsg{KEMOffer: []byte{1, 2, 3}}).Encode()
+	require.Error(t, err)
+}

client/internal/pqkem_adapter.go

@@ -0,0 +1,114 @@
+package internal
+
+import (
+	"net/netip"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/internal/pqkem"
+)
+
+// pqPresharedKeySetter is the subset of the WireGuard interface the ML-KEM callback
+// needs: programming a peer's preshared key. *iface.WGIface satisfies it.
+type pqPresharedKeySetter interface {
+	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error
+}
+
+// pqCallbackHandler programs the derived PQ PSK onto the WireGuard peer. It is the
+// engine-side implementation of pqkem.CallbackHandler.
+type pqCallbackHandler struct {
+	wg pqPresharedKeySetter
+	// reoffer re-bootstraps the KEM over Signal for a peer (a fresh signalling offer)
+	// to recover from a persistent data-path rekey failure. Nil disables recovery.
+	reoffer func(remoteKey string)
+}
+
+// OnNewPSKReady programs the freshly derived PSK for the peer (updateOnly: a no-op
+// if the peer is not present, mirroring Rosenpass). remoteID is the peer's WG pubkey.
+func (h pqCallbackHandler) OnNewPSKReady(remoteID pqkem.RemoteID, psk pqkem.PSK) error {
+	// updateOnly: applies to an already-configured peer (rotation). At bootstrap the
+	// peer is not configured yet, so this is a no-op there and the PSK is instead
+	// pulled at peer-config time (pqHandshaker.PSK / conn.presharedKey).
+	log.Tracef("pqkem: programming PSK for peer %s", remoteID)
+	return h.wg.SetPresharedKey(string(remoteID), wgtypes.Key(psk), true)
+}
+
+// OnRekeyFailed reports a failed PQ (re)key convergence and re-bootstraps the KEM over
+// Signal to recover: a fresh signalling offer starts a new exchange that overwrites the
+// stalled PSK on both sides, resyncing after a persistent data-path desync. The tunnel
+// stays up on the previous PSK meanwhile (the Signal channel is independent of the
+// broken data path).
+func (h pqCallbackHandler) OnRekeyFailed(remoteID pqkem.RemoteID) error {
+	log.Warnf("pqkem: post-quantum rekey failed for peer %s, re-bootstrapping over signal", remoteID)
+	if h.reoffer != nil {
+		h.reoffer(string(remoteID))
+	}
+	return nil
+}
+
+// pqHandshaker adapts the pqkem manager to peer.PQHandshaker (string peer keys),
+// wiring the host's signalling offers/answers to the KEM exchange.
+type pqHandshaker struct {
+	mgr *pqkem.Manager
+}
+
+func (p pqHandshaker) OfferPayload(remoteKey string) ([]byte, int) {
+	payload, err := p.mgr.SignalOffer(pqkem.RemoteID(remoteKey))
+	if err != nil {
+		log.Warnf("pqkem: build offer for %s: %v", remoteKey, err)
+	}
+	return payload, p.mgr.LocalPort()
+}
+
+func (p pqHandshaker) AnswerPayload(remoteKey string, recvOffer []byte) ([]byte, int) {
+	if len(recvOffer) == 0 {
+		return nil, p.mgr.LocalPort()
+	}
+	payload, err := p.mgr.SignalOnOffer(pqkem.RemoteID(remoteKey), recvOffer)
+	if err != nil {
+		log.Warnf("pqkem: build answer for %s: %v", remoteKey, err)
+	}
+	return payload, p.mgr.LocalPort()
+}
+
+func (p pqHandshaker) OnAnswer(remoteKey string, recvAnswer []byte) {
+	if len(recvAnswer) == 0 {
+		return
+	}
+	if err := p.mgr.SignalOnAnswer(pqkem.RemoteID(remoteKey), recvAnswer); err != nil {
+		log.Warnf("pqkem: process answer from %s: %v", remoteKey, err)
+	}
+}
+
+// PSK exposes the peer's derived PSK for the conn to program at WG peer-config time.
+func (p pqHandshaker) PSK(remoteKey string) (wgtypes.Key, bool) {
+	psk, ok := p.mgr.PSK(pqkem.RemoteID(remoteKey))
+	if !ok {
+		return wgtypes.Key{}, false
+	}
+	return wgtypes.Key(psk), true
+}
+
+// SetRemoteAddr registers the peer's data-path endpoint (overlay IP + pq UDP port)
+// learned from signalling. Sends only ever fire once the tunnel is up (clocked by
+// OnDataPathRekeyed), so registering here is safe even before connection-up.
+func (p pqHandshaker) SetRemoteAddr(remoteKey string, addr netip.AddrPort) {
+	if !addr.IsValid() || addr.Port() == 0 {
+		return
+	}
+	p.mgr.AddPeer(pqkem.RemoteID(remoteKey), addr)
+}
+
+// OnDataPathRekeyed clocks the next chained PSK rotation on a fresh WG handshake.
+// sinceActivity is how long ago the peer last exchanged real user data; the manager
+// skips rotation for idle tunnels.
+func (p pqHandshaker) OnDataPathRekeyed(remoteKey string, sinceActivity time.Duration) {
+	p.mgr.OnDataPathRekeyed(pqkem.RemoteID(remoteKey), sinceActivity)
+}
+
+// OnDataPathDown signals the peer's tunnel went down.
+func (p pqHandshaker) OnDataPathDown(remoteKey string) {
+	p.mgr.OnDataPathDown(pqkem.RemoteID(remoteKey))
+}

client/internal/pqkem_transport.go

@@ -0,0 +1,72 @@
+package internal
+
+import (
+	"fmt"
+	"net"
+	"net/netip"
+
+	log "github.com/sirupsen/logrus"
+)
+
+// DefaultPort is the preferred UDP port for the ML-KEM data-path service, bound on
+// the WG overlay IP. Since each client owns a distinct overlay IP, this port is
+// almost always free, so it need not be announced (peers assume it). A peer only
+// announces Body.mlkemPort when a collision forced it onto a different port.
+const DefaultPort = 51833
+
+// pqTransport is the ML-KEM data-path transport: a dumb UDP socket bound on the WG
+// overlay IP. It implements pqkem.Transport — the manager owns the remoteID<->endpoint
+// routing and drives this socket's lifecycle (Run / Close).
+type pqTransport struct {
+	conn *net.UDPConn
+	port int
+}
+
+// newPQTransport binds a UDP socket on the WG overlay IP, preferring DefaultPort and
+// falling back to an OS-assigned ephemeral port if it is in use. Call it after the WG
+// interface is up so the overlay IP is assigned; when the bound port is not
+// DefaultPort it must be announced to peers via Body.mlkemPort.
+func newPQTransport(overlayIP netip.Addr) (*pqTransport, error) {
+	if !overlayIP.IsValid() {
+		return nil, fmt.Errorf("invalid overlay IP for pqkem transport")
+	}
+	ip := net.IP(overlayIP.AsSlice())
+	conn, err := net.ListenUDP("udp4", &net.UDPAddr{IP: ip, Port: DefaultPort})
+	if err != nil {
+		log.Debugf("pqkem: default port %d unavailable on %s (%v), using an ephemeral port", DefaultPort, overlayIP, err)
+		conn, err = net.ListenUDP("udp4", &net.UDPAddr{IP: ip, Port: 0})
+		if err != nil {
+			return nil, fmt.Errorf("bind pqkem udp on overlay %s: %w", overlayIP, err)
+		}
+	}
+	return &pqTransport{conn: conn, port: conn.LocalAddr().(*net.UDPAddr).Port}, nil
+}
+
+// Send implements pqkem.Transport.
+func (t *pqTransport) Send(endpoint netip.AddrPort, msg []byte) error {
+	_, err := t.conn.WriteToUDPAddrPort(msg, endpoint)
+	return err
+}
+
+// LocalPort implements pqkem.Transport.
+func (t *pqTransport) LocalPort() int { return t.port }
+
+// Run implements pqkem.Transport: the receive loop, delivering each datagram as
+// (source endpoint, msg). Exits when the socket is closed.
+func (t *pqTransport) Run(onInbound func(src netip.AddrPort, msg []byte)) {
+	go func() {
+		buf := make([]byte, 2048)
+		for {
+			n, src, err := t.conn.ReadFromUDPAddrPort(buf)
+			if err != nil {
+				return
+			}
+			msg := make([]byte, n)
+			copy(msg, buf[:n])
+			onInbound(src, msg)
+		}
+	}()
+}
+
+// Close implements pqkem.Transport.
+func (t *pqTransport) Close() error { return t.conn.Close() }

client/ios/NetBirdSDK/version.go

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

infrastructure_files/getting-started.sh

@@ -228,8 +228,6 @@ 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
 
@@ -499,8 +497,7 @@ 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/acquis.d
-          render_crowdsec_appsec_acquis > crowdsec/acquis.d/appsec.yaml
+          mkdir -p crowdsec
         fi
       fi
       ;;
@@ -534,23 +531,6 @@ 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)
@@ -762,11 +742,7 @@ render_docker_compose_traefik_builtin() {
     restart: unless-stopped
     networks: [netbird]
     environment:
-      # 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
+      COLLECTIONS: crowdsecurity/linux
     volumes:
       - ./crowdsec:/etc/crowdsec
       - crowdsec_db:/var/lib/crowdsec/data
@@ -1031,11 +1007,6 @@ 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

@@ -23,9 +23,6 @@ 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

@@ -49,7 +49,6 @@ 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

@@ -35,7 +35,6 @@ 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
 }
 
@@ -95,7 +94,6 @@ 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)
 	}
@@ -113,7 +111,6 @@ 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

@@ -40,10 +40,6 @@ 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

@@ -19,7 +19,6 @@ 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

@@ -21,7 +21,6 @@ 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)
@@ -139,13 +138,6 @@ 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

@@ -99,9 +99,6 @@ 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

@@ -50,6 +50,20 @@ 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()
@@ -64,20 +78,6 @@ 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()
@@ -92,20 +92,6 @@ 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()
@@ -135,35 +121,6 @@ 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()
@@ -178,21 +135,6 @@ 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()
@@ -208,7 +150,6 @@ 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)
@@ -217,7 +158,6 @@ 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)
@@ -237,6 +177,36 @@ 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()
@@ -252,6 +222,20 @@ 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

@@ -20,9 +20,6 @@ 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
@@ -77,6 +74,5 @@ type Cluster struct {
 	SupportsCustomPorts *bool
 	RequireSubdomain    *bool
 	SupportsCrowdSec    *bool
-	SupportsAppSec      *bool
 	Private             *bool
 }

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

@@ -204,7 +204,6 @@ 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

@@ -82,7 +82,6 @@ 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
 }
 
@@ -138,7 +137,6 @@ 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

@@ -165,18 +165,6 @@ 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"`
-	// 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.AppSecMode == ""
 }
 
 // Copy returns a deep copy of the AccessRestrictions.
@@ -187,7 +175,6 @@ func (r AccessRestrictions) Copy() AccessRestrictions {
 		AllowedCountries: slices.Clone(r.AllowedCountries),
 		BlockedCountries: slices.Clone(r.BlockedCountries),
 		CrowdSecMode:     r.CrowdSecMode,
-		AppSecMode:       r.AppSecMode,
 	}
 }
 
@@ -821,17 +808,13 @@ func restrictionsFromAPI(r *api.AccessRestrictions) (AccessRestrictions, error)
 		}
 		res.CrowdSecMode = string(*r.CrowdsecMode)
 	}
-	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 r.isEmpty() {
+	if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
+		len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
+		r.CrowdSecMode == "" {
 		return nil
 	}
 	res := &api.AccessRestrictions{}
@@ -851,15 +834,13 @@ func restrictionsToAPI(r AccessRestrictions) *api.AccessRestrictions {
 		mode := api.AccessRestrictionsCrowdsecMode(r.CrowdSecMode)
 		res.CrowdsecMode = &mode
 	}
-	if r.AppSecMode != "" {
-		mode := api.AccessRestrictionsAppsecMode(r.AppSecMode)
-		res.AppsecMode = &mode
-	}
 	return res
 }
 
 func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
-	if r.isEmpty() {
+	if len(r.AllowedCIDRs) == 0 && len(r.BlockedCIDRs) == 0 &&
+		len(r.AllowedCountries) == 0 && len(r.BlockedCountries) == 0 &&
+		r.CrowdSecMode == "" {
 		return nil
 	}
 	return &proto.AccessRestrictions{
@@ -868,7 +849,6 @@ func restrictionsToProto(r AccessRestrictions) *proto.AccessRestrictions {
 		AllowedCountries: r.AllowedCountries,
 		BlockedCountries: r.BlockedCountries,
 		CrowdsecMode:     r.CrowdSecMode,
-		AppsecMode:       r.AppSecMode,
 	}
 }
 
@@ -894,11 +874,6 @@ 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
 	}
@@ -1267,27 +1242,10 @@ func validateCrowdSecMode(mode string) error {
 	}
 }
 
-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 := 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

@@ -26,17 +26,6 @@ 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())
 }
@@ -1326,68 +1315,3 @@ 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

@@ -29,7 +29,6 @@ import (
 
 	"github.com/netbirdio/netbird/shared/management/domain"
 
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
@@ -37,6 +36,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/sessionkey"
 	"github.com/netbirdio/netbird/management/server/idp"
 	"github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/management/server/users"
 	proxyauth "github.com/netbirdio/netbird/proxy/auth"
@@ -505,7 +505,6 @@ 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/store/sql_store.go

@@ -2259,7 +2259,7 @@ func (s *SqlStore) getPostureChecks(ctx context.Context, accountID string) ([]*p
 }
 
 func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpservice.Service, error) {
-	const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth, restrictions,
+	const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth,
 		meta_created_at, meta_certificate_issued_at, meta_status, proxy_cluster,
 		pass_host_header, rewrite_redirects, session_private_key, session_public_key,
 		mode, listen_port, port_auto_assigned, source, source_peer, terminated,
@@ -2278,7 +2278,6 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 	services, err := pgx.CollectRows(serviceRows, func(row pgx.CollectableRow) (*rpservice.Service, error) {
 		var s rpservice.Service
 		var auth []byte
-		var restrictions []byte
 		var accessGroups []byte
 		var createdAt, certIssuedAt sql.NullTime
 		var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
@@ -2292,7 +2291,6 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			&s.Domain,
 			&s.Enabled,
 			&auth,
-			&restrictions,
 			&createdAt,
 			&certIssuedAt,
 			&status,
@@ -2320,12 +2318,6 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			}
 		}
 
-		if len(restrictions) > 0 {
-			if err := json.Unmarshal(restrictions, &s.Restrictions); err != nil {
-				return nil, fmt.Errorf("unmarshal restrictions: %w", err)
-			}
-		}
-
 		if len(accessGroups) > 0 {
 			if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
 				return nil, fmt.Errorf("unmarshal access_groups: %w", err)
@@ -6365,7 +6357,6 @@ var validCapabilityColumns = map[string]struct{}{
 	"supports_custom_ports": {},
 	"require_subdomain":     {},
 	"supports_crowdsec":     {},
-	"supports_appsec":       {},
 	"private":               {},
 }
 
@@ -6396,14 +6387,6 @@ 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

@@ -1,119 +0,0 @@
-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

@@ -44,42 +44,3 @@ func TestSqlStore_GetAccount_PrivateServiceRoundtrip(t *testing.T) {
 		assert.Equal(t, []string{"grp-admins", "grp-ops"}, got.AccessGroups)
 	})
 }
-
-// Restrictions are stored as a JSON blob, and the Postgres read path lists
-// columns by hand: a mode that is not read there is silently off on Postgres
-// while working in SQLite dev.
-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"},
-				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)
-
-		got := loaded.Services[0].Restrictions
-		assert.Equal(t, []string{"203.0.113.0/24"}, got.AllowedCIDRs)
-		assert.Equal(t, "observe", got.CrowdSecMode)
-		assert.Equal(t, "enforce", got.AppSecMode)
-	})
-}

management/server/store/store.go

@@ -321,7 +321,6 @@ 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

@@ -1835,20 +1835,6 @@ 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

@@ -79,11 +79,6 @@ var (
 	geoDataDir            string
 	crowdsecAPIURL        string
 	crowdsecAPIKey        string
-	appsecURL             string
-	appsecTimeout         time.Duration
-	appsecMaxBodyBytes    int64
-	captureBudgetBytes    int64
-	appsecMaxConcurrent   int
 )
 
 var rootCmd = &cobra.Command{
@@ -130,11 +125,6 @@ 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.
@@ -228,59 +218,47 @@ func runServer(cmd *cobra.Command, args []string) error {
 	ctx, stop := signal.NotifyContext(context.Background(), syscall.SIGTERM, syscall.SIGINT)
 	defer stop()
 
-	srv := proxy.New(ctx, serverConfig(logger, proxyToken, parsedTrustedProxies, perf))
+	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,
+	})
 
 	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 {
@@ -315,19 +293,6 @@ 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

@@ -1,163 +0,0 @@
-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

@@ -1,571 +0,0 @@
-// 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

@@ -1,306 +0,0 @@
-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

@@ -39,11 +39,6 @@ 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

@@ -18,7 +18,6 @@ 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"
@@ -26,11 +25,6 @@ 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")
@@ -65,14 +59,6 @@ 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 {
@@ -96,9 +82,6 @@ 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
@@ -116,12 +99,6 @@ 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 {
@@ -146,14 +123,6 @@ 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) {
@@ -293,134 +262,6 @@ 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 {
@@ -440,18 +281,12 @@ func (mw *Middleware) resolveClientIP(r *http.Request) netip.Addr {
 	return addr.Unmap()
 }
 
-// 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) {
+// blockIPRestriction sets captured data fields for an IP-restriction block event.
+func (mw *Middleware) blockIPRestriction(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)
 }
 
@@ -802,61 +637,45 @@ func wasCredentialSubmitted(r *http.Request, method auth.Method) bool {
 	case auth.MethodPassword:
 		return r.FormValue("password") != ""
 	case auth.MethodOIDC:
-		return r.URL.Query().Get(sessionTokenParam) != ""
+		return r.URL.Query().Get("session_token") != ""
 	}
 	return false
 }
 
-// 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...),
+// 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
 	}
 
-	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
+	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)
 	}
 
 	mw.domainsMux.Lock()
 	defer mw.domainsMux.Unlock()
-	mw.domains[domain] = config
+	mw.domains[domain] = DomainConfig{
+		Schemes:           schemes,
+		SessionPublicKey:  pubKeyBytes,
+		SessionExpiration: expiration,
+		AccountID:         accountID,
+		ServiceID:         serviceID,
+		IPRestrictions:    ipRestrictions,
+		Private:           private,
+	}
 	return nil
 }
 
@@ -911,10 +730,10 @@ 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(sessionTokenParam) {
+	if !q.Has("session_token") {
 		return u.RequestURI()
 	}
-	q.Del(sessionTokenParam)
+	q.Del("session_token")
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false)
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", []Scheme{scheme}, "", time.Hour, "", "", nil, false)
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "not-valid-base64!!!", SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", []Scheme{scheme}, "not-valid-base64!!!", time.Hour, "", "", nil, false)
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: shortKey, SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", []Scheme{scheme}, shortKey, time.Hour, "", "", nil, false)
 	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", DomainSettings{SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false)
 	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", 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}))
+	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))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", nil, "", time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
+	require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, 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", DomainSettings{SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
+	require.NoError(t, mw.AddDomain("agent.example.com", nil, kp.PublicKey, time.Hour, "acct-1", "svc-1", nil, 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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	// 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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	// 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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp1.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp1.PublicKey, time.Hour, "", "", nil, false))
 
 	// 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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -584,7 +584,7 @@ func TestProtect_MultipleSchemes(t *testing.T) {
 			return "", "password", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{pinScheme, passwordScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{pinScheme, passwordScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: key, SessionExpiration: time.Hour})
+	err = mw.AddDomain("example.com", []Scheme{scheme}, key, time.Hour, "", "", nil, false)
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	// Attempt to overwrite with an invalid key.
-	err := mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: "bad", SessionExpiration: time.Hour})
+	err := mw.AddDomain("example.com", []Scheme{scheme}, "bad", time.Hour, "", "", nil, false)
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -815,7 +815,8 @@ func TestWasCredentialSubmitted(t *testing.T) {
 func TestCheckIPRestrictions_UnparseableAddress(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}})})
+	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
+		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"10.0.0.0/8"}}), false)
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -850,7 +851,8 @@ 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", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}})})
+	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
+		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"203.0.113.0/24"}}), false)
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -890,7 +892,8 @@ 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", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}})})
+	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
+		restrict.ParseFilter(restrict.FilterConfig{AllowedCountries: []string{"US"}}), false)
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -913,10 +916,11 @@ func TestCheckIPRestrictions_NilGeoWithCountryRules(t *testing.T) {
 func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	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"},
-	})})
+	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
+		restrict.ParseFilter(restrict.FilterConfig{
+			AllowedCIDRs:     []string{"100.64.0.0/10"},
+			AllowedCountries: []string{"US"},
+		}), false)
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -949,7 +953,8 @@ func TestCheckIPRestrictions_OverlayOriginSkipsCountryRules(t *testing.T) {
 func TestCheckIPRestrictions_OverlayOriginRespectsCIDR(t *testing.T) {
 	mw := NewMiddleware(log.StandardLogger(), nil, nil)
 
-	err := mw.AddDomain("example.com", DomainSettings{AccountID: "acc1", ServiceID: "svc1", IPRestrictions: restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}})})
+	err := mw.AddDomain("example.com", nil, "", 0, "acc1", "svc1",
+		restrict.ParseFilter(restrict.FilterConfig{AllowedCIDRs: []string{"100.64.0.0/16"}}), false)
 	require.NoError(t, err)
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -977,7 +982,7 @@ func TestProtect_OIDCOnlyRedirectsDirectly(t *testing.T) {
 			return "", oidcURL, nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1006,7 +1011,7 @@ func TestProtect_OIDCWithOtherMethodShowsLoginPage(t *testing.T) {
 			return "", "pin", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{oidcScheme, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{oidcScheme, pinScheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1050,7 +1055,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	var backendCalled bool
 	capturedData := proxy.NewCapturedData("")
@@ -1093,7 +1098,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr, pinScheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr, pinScheme}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1113,7 +1118,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	capturedData := proxy.NewCapturedData("")
 	handler := mw.Protect(newPassthroughHandler())
@@ -1136,7 +1141,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1153,7 +1158,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
 		w.WriteHeader(http.StatusOK)
@@ -1213,7 +1218,7 @@ 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", DomainSettings{Schemes: []Scheme{hdr}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour, AccountID: "acc1", ServiceID: "svc1"}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{hdr}, kp.PublicKey, time.Hour, "acc1", "svc1", nil, false))
 
 	var backendCalled bool
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {
@@ -1271,7 +1276,7 @@ func TestProtect_OIDCOnPlainHTTP_BlockedWith400(t *testing.T) {
 			return "", "https://idp.example.com/authorize", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1295,7 +1300,7 @@ func TestProtect_OIDCOverTLS_NotBlocked(t *testing.T) {
 			return "", "https://idp.example.com/authorize", nil
 		},
 	}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1315,7 +1320,7 @@ 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", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1345,7 +1350,7 @@ func TestProtect_TunnelPeerFastPath_RequiresInboundMarker(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 
@@ -1380,7 +1385,7 @@ func TestProtect_TunnelPeerFastPath_TakesPathWithInboundMarker(t *testing.T) {
 	kp := generateTestKeyPair(t)
 
 	scheme := &stubScheme{method: auth.MethodPIN, promptID: "pin"}
-	require.NoError(t, mw.AddDomain("example.com", DomainSettings{Schemes: []Scheme{scheme}, SessionPublicKey: kp.PublicKey, SessionExpiration: time.Hour}))
+	require.NoError(t, mw.AddDomain("example.com", []Scheme{scheme}, kp.PublicKey, time.Hour, "", "", nil, false))
 
 	handler := mw.Protect(newPassthroughHandler())
 

proxy/internal/auth/oidc.go

@@ -13,10 +13,6 @@ 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)
 }
@@ -47,7 +43,7 @@ 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(sessionTokenParam); token != "" {
+	if token := r.URL.Query().Get("session_token"); 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", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1"}))
+	require.NoError(t, mw.AddDomain("svc.example", nil, "", 0, "acct-1", "svc-1", nil, false))
 	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", DomainSettings{AccountID: "acct-a", ServiceID: "svc-a"}))
-	require.NoError(t, mw.AddDomain("svc-b.example", DomainSettings{AccountID: "acct-b", ServiceID: "svc-b"}))
+	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))
 
 	// 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", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
+	require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, 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", DomainSettings{AccountID: "acct-1", ServiceID: "svc-1", Private: true}))
+	require.NoError(t, mw.AddDomain("private.svc", nil, "", 0, "acct-1", "svc-1", nil, true))
 
 	called := false
 	handler := mw.Protect(http.HandlerFunc(func(w http.ResponseWriter, _ *http.Request) {

proxy/internal/llm/pricing/defaults_coverage_test.go

@@ -28,12 +28,12 @@ func TestDefaultTable_FirstPartyModelCoverage(t *testing.T) {
 			"ministral-8b-latest", "mistral-embed",
 		},
 		"anthropic": {
-			"claude-fable-5", "claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6",
+			"claude-fable-5", "claude-opus-5", "claude-opus-4-8", "claude-opus-4-7", "claude-opus-4-6",
 			"claude-opus-4-1", "claude-sonnet-4-6", "claude-sonnet-4-5", "claude-haiku-4-5",
 		},
 		// bedrock keys are the normalized ids the request parser emits.
 		"bedrock": {
-			"anthropic.claude-opus-4-8", "anthropic.claude-opus-4-7", "anthropic.claude-opus-4-6",
+			"anthropic.claude-opus-5", "anthropic.claude-opus-4-8", "anthropic.claude-opus-4-7", "anthropic.claude-opus-4-6",
 			"anthropic.claude-opus-4-1", "anthropic.claude-sonnet-4-6", "anthropic.claude-sonnet-4-5",
 			"anthropic.claude-haiku-4-5", "meta.llama3-3-70b-instruct",
 			"amazon.nova-pro", "amazon.nova-lite", "amazon.nova-micro", "amazon.nova-2-lite",

proxy/internal/llm/pricing/defaults_pricing.yaml

@@ -180,6 +180,11 @@ anthropic:
     output_per_1k: 0.050
     cache_read_per_1k: 0.001
     cache_creation_per_1k: 0.0125
+  claude-opus-5:
+    input_per_1k: 0.005
+    output_per_1k: 0.025
+    cache_read_per_1k: 0.0005
+    cache_creation_per_1k: 0.00625
   claude-opus-4-8:
     input_per_1k: 0.005
     output_per_1k: 0.025
@@ -236,6 +241,11 @@ bedrock:
   # eu.anthropic.claude-sonnet-4-5-20250929-v1:0 -> anthropic.claude-sonnet-4-5.
   # Anthropic-on-Bedrock keeps the additive cache buckets (read ≈0.1x input,
   # write ≈1.25x input); Nova / Llama report no cache, so cost is input+output.
+  anthropic.claude-opus-5:
+    input_per_1k: 0.005
+    output_per_1k: 0.025
+    cache_read_per_1k: 0.0005
+    cache_creation_per_1k: 0.00625
   anthropic.claude-opus-4-8:
     input_per_1k: 0.005
     output_per_1k: 0.025

proxy/internal/middleware/bodytap/request.go

@@ -21,8 +21,6 @@ import (
 	"strconv"
 	"strings"
 	"sync"
-
-	"github.com/netbirdio/netbird/proxy/internal/netutil"
 )
 
 // MaxRoutingScanBytes bounds how far ScanRoutingFields will read into a
@@ -36,6 +34,7 @@ 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"
@@ -126,13 +125,12 @@ func CaptureRequest(r *http.Request, cfg *Config, b Budget) (body []byte, trunca
 	if cfg.MaxRequestBytes <= 0 {
 		return nil, false, 0, BypassCapZero, release, nil
 	}
-	// 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) {
+	if r.Header.Get("Upgrade") != "" {
 		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

@@ -1,23 +0,0 @@
-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

@@ -50,37 +50,6 @@ const (
 	CrowdSecObserve CrowdSecMode = "observe"
 )
 
-// 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 {
@@ -177,13 +146,6 @@ 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.
@@ -205,12 +167,6 @@ 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"
 	}
@@ -226,16 +182,6 @@ 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 {

proxy/lifecycle.go

@@ -126,23 +126,6 @@ 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
@@ -152,47 +135,42 @@ 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,
-		CrowdSecAppSecURL:            cfg.CrowdSecAppSecURL,
-		CrowdSecAppSecTimeout:        cfg.CrowdSecAppSecTimeout,
-		CrowdSecAppSecMaxBodyBytes:   cfg.CrowdSecAppSecMaxBodyBytes,
-		CrowdSecAppSecMaxConcurrent:  cfg.CrowdSecAppSecMaxConcurrent,
-		MiddlewareCaptureBudgetBytes: cfg.MiddlewareCaptureBudgetBytes,
+		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,
 	}
 }

proxy/lifecycle_test.go

@@ -1,45 +0,0 @@
-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

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

proxy/server.go

@@ -45,7 +45,6 @@ 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"
@@ -127,10 +126,6 @@ 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{}
@@ -243,20 +238,6 @@ 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.
@@ -403,13 +384,6 @@ 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)
 
@@ -437,7 +411,6 @@ 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()
@@ -1301,7 +1274,6 @@ 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
@@ -1309,7 +1281,6 @@ func (s *Server) proxyCapabilities() *proto.ProxyCapabilities {
 		SupportsCustomPorts:    &s.SupportsCustomPorts,
 		RequireSubdomain:       &s.RequireSubdomain,
 		SupportsCrowdsec:       &supportsCrowdSec,
-		SupportsAppsec:         &supportsAppSec,
 		Private:                &privateCapability,
 		SupportsPrivateService: &supportsPrivateService,
 	}
@@ -1937,67 +1908,6 @@ func (s *Server) parseRestrictions(mapping *proto.ProxyMapping) *restrict.Filter
 	})
 }
 
-// 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) {
@@ -2164,17 +2074,7 @@ func (s *Server) updateMapping(ctx context.Context, mapping *proto.ProxyMapping)
 	s.warnIfGeoUnavailable(mapping.GetDomain(), mapping.GetAccessRestrictions())
 
 	maxSessionAge := time.Duration(mapping.GetAuth().GetMaxSessionAgeSeconds()) * time.Second
-	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 {
+	if err := s.auth.AddDomain(mapping.GetDomain(), schemes, mapping.GetAuth().GetSessionKey(), maxSessionAge, accountID, svcID, ipRestrictions, mapping.GetPrivate()); err != nil {
 		return fmt.Errorf("auth setup for domain %s: %w", mapping.GetDomain(), err)
 	}
 	m := s.protoToMapping(ctx, mapping)

shared/management/http/api/openapi.yml

@@ -3379,18 +3379,6 @@ components:
             - "observe"
           default: "off"
           description: CrowdSec IP reputation mode. Only available when the proxy cluster supports CrowdSec.
-        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:
@@ -3527,10 +3515,6 @@ 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.
@@ -3590,10 +3574,6 @@ 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

@@ -17,27 +17,6 @@ const (
 	TokenAuthScopes  tokenAuthContextKey  = "TokenAuth.Scopes"
 )
 
-// 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"
@@ -1561,9 +1540,6 @@ type AccessRestrictions struct {
 	// 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"`
 
@@ -1574,9 +1550,6 @@ type AccessRestrictions struct {
 	CrowdsecMode *AccessRestrictionsCrowdsecMode `json:"crowdsec_mode,omitempty"`
 }
 
-// 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
 
@@ -4755,9 +4728,6 @@ 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"`
 
@@ -4826,9 +4796,6 @@ 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

@@ -73,10 +73,6 @@ 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.
@@ -207,10 +203,6 @@ message AccessRestrictions {
   repeated string blocked_countries = 4;
   // CrowdSec IP reputation mode: "", "off", "enforce", or "observe".
   string crowdsec_mode = 5;
-  // 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/signal/client/client.go

@@ -52,6 +52,11 @@ type CredentialPayload struct {
 	Credential      *Credential
 	RosenpassPubKey []byte
 	RosenpassAddr   string
+	// MlkemPayload is the opaque post-quantum KEM handshake message riding this
+	// OFFER/ANSWER (see Body.mlkemPayload). Nil when not running the PQ exchange.
+	MlkemPayload []byte
+	// MlkemPort is the sender's ML-KEM PQ service UDP port (0 when not running).
+	MlkemPort       int
 	RelaySrvAddress string
 	RelaySrvIP      netip.Addr
 	SessionID       []byte
@@ -89,6 +94,13 @@ func MarshalCredential(myKey wgtypes.Key, remoteKey string, p CredentialPayload)
 	if p.RelaySrvIP.IsValid() {
 		body.RelayServerIP = p.RelaySrvIP.Unmap().AsSlice()
 	}
+	if len(p.MlkemPayload) > 0 {
+		body.MlkemPayload = p.MlkemPayload
+	}
+	if p.MlkemPort > 0 {
+		port := uint32(p.MlkemPort)
+		body.MlkemPort = &port
+	}
 	return &proto.Message{
 		Key:       myKey.PublicKey().String(),
 		RemoteKey: remoteKey,

shared/signal/proto/signalexchange.pb.go

@@ -239,6 +239,16 @@ type Body struct {
 	// fallback dial target when DNS resolution of relayServerAddress fails.
 	// SNI/TLS verification still uses relayServerAddress.
 	RelayServerIP []byte `protobuf:"bytes,11,opt,name=relayServerIP,proto3,oneof" json:"relayServerIP,omitempty"`
+	// mlkemPayload carries a post-quantum X25519MLKEM768 handshake message that
+	// seeds the WireGuard PSK, riding this Body's OFFER/ANSWER: on an OFFER it is
+	// the KEM offer, on an ANSWER the KEM answer. It is opaque to signal — the
+	// pqkem library frames and parses it. Absent when the sender does not run the
+	// ML-KEM PQ exchange; unknown to older clients, which ignore it.
+	MlkemPayload []byte `protobuf:"bytes,12,opt,name=mlkemPayload,proto3,oneof" json:"mlkemPayload,omitempty"`
+	// mlkemPort is the UDP port of the sender's ML-KEM PQ service, bound on its
+	// WireGuard overlay IP. Peers send subsequent rekey messages there over the
+	// data path. Zero/absent when the ML-KEM PQ exchange is not running.
+	MlkemPort *uint32 `protobuf:"varint,13,opt,name=mlkemPort,proto3,oneof" json:"mlkemPort,omitempty"`
 }
 
 func (x *Body) Reset() {
@@ -343,6 +353,20 @@ func (x *Body) GetRelayServerIP() []byte {
 	return nil
 }
 
+func (x *Body) GetMlkemPayload() []byte {
+	if x != nil {
+		return x.MlkemPayload
+	}
+	return nil
+}
+
+func (x *Body) GetMlkemPort() uint32 {
+	if x != nil && x.MlkemPort != nil {
+		return *x.MlkemPort
+	}
+	return 0
+}
+
 // Mode indicates a connection mode
 type Mode struct {
 	state         protoimpl.MessageState
@@ -466,7 +490,7 @@ var file_signalexchange_proto_rawDesc = []byte{
 	0x52, 0x09, 0x72, 0x65, 0x6d, 0x6f, 0x74, 0x65, 0x4b, 0x65, 0x79, 0x12, 0x28, 0x0a, 0x04, 0x62,
 	0x6f, 0x64, 0x79, 0x18, 0x04, 0x20, 0x01, 0x28, 0x0b, 0x32, 0x14, 0x2e, 0x73, 0x69, 0x67, 0x6e,
 	0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x42, 0x6f, 0x64, 0x79, 0x52,
-	0x04, 0x62, 0x6f, 0x64, 0x79, 0x22, 0xd2, 0x04, 0x0a, 0x04, 0x42, 0x6f, 0x64, 0x79, 0x12, 0x2d,
+	0x04, 0x62, 0x6f, 0x64, 0x79, 0x22, 0xbd, 0x05, 0x0a, 0x04, 0x42, 0x6f, 0x64, 0x79, 0x12, 0x2d,
 	0x0a, 0x04, 0x74, 0x79, 0x70, 0x65, 0x18, 0x01, 0x20, 0x01, 0x28, 0x0e, 0x32, 0x19, 0x2e, 0x73,
 	0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x42, 0x6f,
 	0x64, 0x79, 0x2e, 0x54, 0x79, 0x70, 0x65, 0x52, 0x04, 0x74, 0x79, 0x70, 0x65, 0x12, 0x18, 0x0a,
@@ -494,39 +518,46 @@ var file_signalexchange_proto_rawDesc = []byte{
 	0x52, 0x09, 0x73, 0x65, 0x73, 0x73, 0x69, 0x6f, 0x6e, 0x49, 0x64, 0x88, 0x01, 0x01, 0x12, 0x29,
 	0x0a, 0x0d, 0x72, 0x65, 0x6c, 0x61, 0x79, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72, 0x49, 0x50, 0x18,
 	0x0b, 0x20, 0x01, 0x28, 0x0c, 0x48, 0x02, 0x52, 0x0d, 0x72, 0x65, 0x6c, 0x61, 0x79, 0x53, 0x65,
-	0x72, 0x76, 0x65, 0x72, 0x49, 0x50, 0x88, 0x01, 0x01, 0x22, 0x52, 0x0a, 0x04, 0x54, 0x79, 0x70,
-	0x65, 0x12, 0x09, 0x0a, 0x05, 0x4f, 0x46, 0x46, 0x45, 0x52, 0x10, 0x00, 0x12, 0x0a, 0x0a, 0x06,
-	0x41, 0x4e, 0x53, 0x57, 0x45, 0x52, 0x10, 0x01, 0x12, 0x0d, 0x0a, 0x09, 0x43, 0x41, 0x4e, 0x44,
-	0x49, 0x44, 0x41, 0x54, 0x45, 0x10, 0x02, 0x12, 0x08, 0x0a, 0x04, 0x4d, 0x4f, 0x44, 0x45, 0x10,
-	0x04, 0x12, 0x0b, 0x0a, 0x07, 0x47, 0x4f, 0x5f, 0x49, 0x44, 0x4c, 0x45, 0x10, 0x05, 0x12, 0x0d,
-	0x0a, 0x09, 0x48, 0x45, 0x41, 0x52, 0x54, 0x42, 0x45, 0x41, 0x54, 0x10, 0x06, 0x42, 0x15, 0x0a,
-	0x13, 0x5f, 0x72, 0x65, 0x6c, 0x61, 0x79, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72, 0x41, 0x64, 0x64,
-	0x72, 0x65, 0x73, 0x73, 0x42, 0x0c, 0x0a, 0x0a, 0x5f, 0x73, 0x65, 0x73, 0x73, 0x69, 0x6f, 0x6e,
-	0x49, 0x64, 0x42, 0x10, 0x0a, 0x0e, 0x5f, 0x72, 0x65, 0x6c, 0x61, 0x79, 0x53, 0x65, 0x72, 0x76,
-	0x65, 0x72, 0x49, 0x50, 0x4a, 0x04, 0x08, 0x09, 0x10, 0x0a, 0x22, 0x2e, 0x0a, 0x04, 0x4d, 0x6f,
-	0x64, 0x65, 0x12, 0x1b, 0x0a, 0x06, 0x64, 0x69, 0x72, 0x65, 0x63, 0x74, 0x18, 0x01, 0x20, 0x01,
-	0x28, 0x08, 0x48, 0x00, 0x52, 0x06, 0x64, 0x69, 0x72, 0x65, 0x63, 0x74, 0x88, 0x01, 0x01, 0x42,
-	0x09, 0x0a, 0x07, 0x5f, 0x64, 0x69, 0x72, 0x65, 0x63, 0x74, 0x22, 0x6d, 0x0a, 0x0f, 0x52, 0x6f,
-	0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12, 0x28, 0x0a,
-	0x0f, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x50, 0x75, 0x62, 0x4b, 0x65, 0x79,
-	0x18, 0x01, 0x20, 0x01, 0x28, 0x0c, 0x52, 0x0f, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73,
-	0x73, 0x50, 0x75, 0x62, 0x4b, 0x65, 0x79, 0x12, 0x30, 0x0a, 0x13, 0x72, 0x6f, 0x73, 0x65, 0x6e,
-	0x70, 0x61, 0x73, 0x73, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72, 0x41, 0x64, 0x64, 0x72, 0x18, 0x02,
-	0x20, 0x01, 0x28, 0x09, 0x52, 0x13, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x53,
-	0x65, 0x72, 0x76, 0x65, 0x72, 0x41, 0x64, 0x64, 0x72, 0x32, 0xb9, 0x01, 0x0a, 0x0e, 0x53, 0x69,
-	0x67, 0x6e, 0x61, 0x6c, 0x45, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x12, 0x4c, 0x0a, 0x04,
-	0x53, 0x65, 0x6e, 0x64, 0x12, 0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63,
-	0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x4d,
-	0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65,
+	0x72, 0x76, 0x65, 0x72, 0x49, 0x50, 0x88, 0x01, 0x01, 0x12, 0x27, 0x0a, 0x0c, 0x6d, 0x6c, 0x6b,
+	0x65, 0x6d, 0x50, 0x61, 0x79, 0x6c, 0x6f, 0x61, 0x64, 0x18, 0x0c, 0x20, 0x01, 0x28, 0x0c, 0x48,
+	0x03, 0x52, 0x0c, 0x6d, 0x6c, 0x6b, 0x65, 0x6d, 0x50, 0x61, 0x79, 0x6c, 0x6f, 0x61, 0x64, 0x88,
+	0x01, 0x01, 0x12, 0x21, 0x0a, 0x09, 0x6d, 0x6c, 0x6b, 0x65, 0x6d, 0x50, 0x6f, 0x72, 0x74, 0x18,
+	0x0d, 0x20, 0x01, 0x28, 0x0d, 0x48, 0x04, 0x52, 0x09, 0x6d, 0x6c, 0x6b, 0x65, 0x6d, 0x50, 0x6f,
+	0x72, 0x74, 0x88, 0x01, 0x01, 0x22, 0x52, 0x0a, 0x04, 0x54, 0x79, 0x70, 0x65, 0x12, 0x09, 0x0a,
+	0x05, 0x4f, 0x46, 0x46, 0x45, 0x52, 0x10, 0x00, 0x12, 0x0a, 0x0a, 0x06, 0x41, 0x4e, 0x53, 0x57,
+	0x45, 0x52, 0x10, 0x01, 0x12, 0x0d, 0x0a, 0x09, 0x43, 0x41, 0x4e, 0x44, 0x49, 0x44, 0x41, 0x54,
+	0x45, 0x10, 0x02, 0x12, 0x08, 0x0a, 0x04, 0x4d, 0x4f, 0x44, 0x45, 0x10, 0x04, 0x12, 0x0b, 0x0a,
+	0x07, 0x47, 0x4f, 0x5f, 0x49, 0x44, 0x4c, 0x45, 0x10, 0x05, 0x12, 0x0d, 0x0a, 0x09, 0x48, 0x45,
+	0x41, 0x52, 0x54, 0x42, 0x45, 0x41, 0x54, 0x10, 0x06, 0x42, 0x15, 0x0a, 0x13, 0x5f, 0x72, 0x65,
+	0x6c, 0x61, 0x79, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72, 0x41, 0x64, 0x64, 0x72, 0x65, 0x73, 0x73,
+	0x42, 0x0c, 0x0a, 0x0a, 0x5f, 0x73, 0x65, 0x73, 0x73, 0x69, 0x6f, 0x6e, 0x49, 0x64, 0x42, 0x10,
+	0x0a, 0x0e, 0x5f, 0x72, 0x65, 0x6c, 0x61, 0x79, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72, 0x49, 0x50,
+	0x42, 0x0f, 0x0a, 0x0d, 0x5f, 0x6d, 0x6c, 0x6b, 0x65, 0x6d, 0x50, 0x61, 0x79, 0x6c, 0x6f, 0x61,
+	0x64, 0x42, 0x0c, 0x0a, 0x0a, 0x5f, 0x6d, 0x6c, 0x6b, 0x65, 0x6d, 0x50, 0x6f, 0x72, 0x74, 0x4a,
+	0x04, 0x08, 0x09, 0x10, 0x0a, 0x22, 0x2e, 0x0a, 0x04, 0x4d, 0x6f, 0x64, 0x65, 0x12, 0x1b, 0x0a,
+	0x06, 0x64, 0x69, 0x72, 0x65, 0x63, 0x74, 0x18, 0x01, 0x20, 0x01, 0x28, 0x08, 0x48, 0x00, 0x52,
+	0x06, 0x64, 0x69, 0x72, 0x65, 0x63, 0x74, 0x88, 0x01, 0x01, 0x42, 0x09, 0x0a, 0x07, 0x5f, 0x64,
+	0x69, 0x72, 0x65, 0x63, 0x74, 0x22, 0x6d, 0x0a, 0x0f, 0x52, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61,
+	0x73, 0x73, 0x43, 0x6f, 0x6e, 0x66, 0x69, 0x67, 0x12, 0x28, 0x0a, 0x0f, 0x72, 0x6f, 0x73, 0x65,
+	0x6e, 0x70, 0x61, 0x73, 0x73, 0x50, 0x75, 0x62, 0x4b, 0x65, 0x79, 0x18, 0x01, 0x20, 0x01, 0x28,
+	0x0c, 0x52, 0x0f, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x50, 0x75, 0x62, 0x4b,
+	0x65, 0x79, 0x12, 0x30, 0x0a, 0x13, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x53,
+	0x65, 0x72, 0x76, 0x65, 0x72, 0x41, 0x64, 0x64, 0x72, 0x18, 0x02, 0x20, 0x01, 0x28, 0x09, 0x52,
+	0x13, 0x72, 0x6f, 0x73, 0x65, 0x6e, 0x70, 0x61, 0x73, 0x73, 0x53, 0x65, 0x72, 0x76, 0x65, 0x72,
+	0x41, 0x64, 0x64, 0x72, 0x32, 0xb9, 0x01, 0x0a, 0x0e, 0x53, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x45,
+	0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x12, 0x4c, 0x0a, 0x04, 0x53, 0x65, 0x6e, 0x64, 0x12,
+	0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65,
+	0x2e, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67,
+	0x65, 0x1a, 0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e,
+	0x67, 0x65, 0x2e, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x4d, 0x65, 0x73, 0x73,
+	0x61, 0x67, 0x65, 0x22, 0x00, 0x12, 0x59, 0x0a, 0x0d, 0x43, 0x6f, 0x6e, 0x6e, 0x65, 0x63, 0x74,
+	0x53, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x12, 0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65,
 	0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65,
-	0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x00, 0x12, 0x59, 0x0a, 0x0d, 0x43, 0x6f,
-	0x6e, 0x6e, 0x65, 0x63, 0x74, 0x53, 0x74, 0x72, 0x65, 0x61, 0x6d, 0x12, 0x20, 0x2e, 0x73, 0x69,
-	0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x45, 0x6e, 0x63,
-	0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x20, 0x2e,
-	0x73, 0x69, 0x67, 0x6e, 0x61, 0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x45,
-	0x6e, 0x63, 0x72, 0x79, 0x70, 0x74, 0x65, 0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22,
-	0x00, 0x28, 0x01, 0x30, 0x01, 0x42, 0x08, 0x5a, 0x06, 0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62,
-	0x06, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x33,
+	0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x1a, 0x20, 0x2e, 0x73, 0x69, 0x67, 0x6e, 0x61,
+	0x6c, 0x65, 0x78, 0x63, 0x68, 0x61, 0x6e, 0x67, 0x65, 0x2e, 0x45, 0x6e, 0x63, 0x72, 0x79, 0x70,
+	0x74, 0x65, 0x64, 0x4d, 0x65, 0x73, 0x73, 0x61, 0x67, 0x65, 0x22, 0x00, 0x28, 0x01, 0x30, 0x01,
+	0x42, 0x08, 0x5a, 0x06, 0x2f, 0x70, 0x72, 0x6f, 0x74, 0x6f, 0x62, 0x06, 0x70, 0x72, 0x6f, 0x74,
+	0x6f, 0x33,
 }
 
 var (

shared/signal/proto/signalexchange.proto

@@ -75,6 +75,18 @@ message Body {
   // fallback dial target when DNS resolution of relayServerAddress fails.
   // SNI/TLS verification still uses relayServerAddress.
   optional bytes relayServerIP = 11;
+
+  // mlkemPayload carries a post-quantum X25519MLKEM768 handshake message that
+  // seeds the WireGuard PSK, riding this Body's OFFER/ANSWER: on an OFFER it is
+  // the KEM offer, on an ANSWER the KEM answer. It is opaque to signal — the
+  // pqkem library frames and parses it. Absent when the sender does not run the
+  // ML-KEM PQ exchange; unknown to older clients, which ignore it.
+  optional bytes mlkemPayload = 12;
+
+  // mlkemPort is the UDP port of the sender's ML-KEM PQ service, bound on its
+  // WireGuard overlay IP. Peers send subsequent rekey messages there over the
+  // data path. Zero/absent when the ML-KEM PQ exchange is not running.
+  optional uint32 mlkemPort = 13;
 }
 
 // Mode indicates a connection mode