Run Rosenpass in permissive mode on the embedded proxy

client/embed/embed.go

@@ -85,6 +85,11 @@ type Options struct {
 	DisableIPv6 bool
 	// BlockInbound blocks all inbound connections from peers
 	BlockInbound bool
+	// EnableRosenpass enables the Rosenpass post-quantum key exchange.
+	EnableRosenpass bool
+	// RosenpassPermissive lets a Rosenpass-enabled peer still connect to peers
+	// that do not run Rosenpass (falling back to the plain WireGuard PSK).
+	RosenpassPermissive bool
 	// BlockLANAccess blocks the embedded peer from reaching the host's
 	// LAN (RFC 1918, link-local, loopback) when it's used as a routing
 	// peer. Mirrors profilemanager.ConfigInput.BlockLANAccess. Useful
@@ -203,6 +208,8 @@ func New(opts Options) (*Client, error) {
 		DisableIPv6:         &opts.DisableIPv6,
 		BlockInbound:        &opts.BlockInbound,
 		BlockLANAccess:      &opts.BlockLANAccess,
+		RosenpassEnabled:    &opts.EnableRosenpass,
+		RosenpassPermissive: &opts.RosenpassPermissive,
 		WireguardPort:       opts.WireguardPort,
 		MTU:                 opts.MTU,
 		DNSLabels:           parsedLabels,

client/internal/conn_mgr.go

@@ -2,6 +2,7 @@ package internal
 
 import (
 	"context"
+	"maps"
 	"os"
 	"strconv"
 	"sync"
@@ -14,6 +15,7 @@ import (
 	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/peerstore"
 	"github.com/netbirdio/netbird/route"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 // lazyForce is the resolved local decision for lazy connections, layered above the
@@ -35,13 +37,18 @@ const (
 //
 // The implementation is not thread-safe; it is protected by engine.syncMsgMux.
 type ConnMgr struct {
-	peerStore        *peerstore.Store
-	statusRecorder   *peer.Status
-	iface            lazyconn.WGIface
-	force            lazyForce
-	rosenpassEnabled bool
+	peerStore      *peerstore.Store
+	statusRecorder *peer.Status
+	iface          lazyconn.WGIface
+	force          lazyForce
+	// remoteLazyEnabled caches the account-wide lazy feature flag from management.
+	// It is the default for peers that do not carry a per-peer lazy hint.
+	remoteLazyEnabled bool
 
 	lazyConnMgr *manager.Manager
+	// appliedExcludeList is the exclude set last handed to the lazy manager, kept so an
+	// unchanged set on the next sync skips the O(n) reconciliation.
+	appliedExcludeList map[string]bool
 
 	wg            sync.WaitGroup
 	lazyCtx       context.Context
@@ -50,78 +57,59 @@ type ConnMgr struct {
 
 func NewConnMgr(engineConfig *EngineConfig, statusRecorder *peer.Status, peerStore *peerstore.Store, iface lazyconn.WGIface) *ConnMgr {
 	e := &ConnMgr{
-		peerStore:        peerStore,
-		statusRecorder:   statusRecorder,
-		iface:            iface,
-		force:            resolveLazyForce(engineConfig.LazyConnection),
-		rosenpassEnabled: engineConfig.RosenpassEnabled,
+		peerStore:      peerStore,
+		statusRecorder: statusRecorder,
+		iface:          iface,
+		force:          resolveLazyForce(engineConfig.LazyConnection),
 	}
 	return e
 }
 
-// Start initializes the connection manager. It starts the lazy connection manager when a
-// local override forces it on; with no local override it waits for the management feature flag.
+// Start initializes the connection manager. The lazy connection manager always runs so that
+// per-peer lazy defaults (e.g. proxy peers) work even when the account flag is off; the
+// account flag and the local override decide the default lazy state per peer (see
+// PeerLazyDefault). Rosenpass peers stay lazy-capable too: their connections just never idle
+// on their own, since rosenpass rekey traffic keeps them active.
 func (e *ConnMgr) Start(ctx context.Context) {
 	if e.lazyConnMgr != nil {
 		log.Errorf("lazy connection manager is already started")
 		return
 	}
 
-	switch e.force {
-	case lazyForceOff:
-		log.Infof("lazy connection manager is disabled by local override (%s or MDM policy)", lazyconn.EnvLazyConn)
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	case lazyForceNone:
-		log.Infof("lazy connection manager is managed by the management feature flag")
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	}
-
-	if e.rosenpassEnabled {
-		log.Warnf("rosenpass connection manager is enabled, lazy connection manager will not be started")
-		e.statusRecorder.UpdateLazyConnection(false)
-		return
-	}
-
 	e.initLazyManager(ctx)
-	e.statusRecorder.UpdateLazyConnection(true)
+	e.statusRecorder.UpdateLazyConnection(e.PeerLazyDefault(mgmProto.LazyState_LazyStateDefault))
 }
 
-// UpdatedRemoteFeatureFlag is called when the remote feature flag is updated.
-// If enabled, it initializes the lazy connection manager and start it. Do not need to call Start() again.
-// If disabled, then it closes the lazy connection manager and open the connections to all peers.
-func (e *ConnMgr) UpdatedRemoteFeatureFlag(ctx context.Context, enabled bool) error {
-	// a local override (NB_LAZY_CONN or local config) takes precedence over management
-	if e.force != lazyForceNone {
-		return nil
+// UpdatedRemoteFeatureFlag caches the account-wide lazy feature flag. The manager itself is
+// not started or stopped here; the per-sync exclude-list reconciliation moves normal peers
+// between the lazy and always-active sets when the flag flips.
+func (e *ConnMgr) UpdatedRemoteFeatureFlag(_ context.Context, enabled bool) error {
+	e.remoteLazyEnabled = enabled
+	if e.isStartedWithLazyMgr() {
+		e.statusRecorder.UpdateLazyConnection(e.PeerLazyDefault(mgmProto.LazyState_LazyStateDefault))
+	}
+	return nil
+}
+
+// PeerLazyDefault reports whether a peer should be lazy. The local override
+// (NB_LAZY_CONN/MDM) wins over everything; without a local override the
+// management per-peer state applies (LazyStateLazy/Eager force the decision),
+// and LazyStateDefault follows the account-wide flag.
+func (e *ConnMgr) PeerLazyDefault(state mgmProto.LazyState) bool {
+	switch e.force {
+	case lazyForceOn:
+		return true
+	case lazyForceOff:
+		return false
 	}
 
-	if enabled {
-		// if the lazy connection manager is already started, do not start it again
-		if e.lazyConnMgr != nil {
-			return nil
-		}
-
-		if e.rosenpassEnabled {
-			log.Infof("rosenpass connection manager is enabled, lazy connection manager will not be started")
-			e.statusRecorder.UpdateLazyConnection(false)
-			return nil
-		}
-
-		log.Infof("lazy connection manager is enabled by the management feature flag")
-		e.initLazyManager(ctx)
-		e.statusRecorder.UpdateLazyConnection(true)
-		return e.addPeersToLazyConnManager()
-	} else {
-		if e.lazyConnMgr == nil {
-			e.statusRecorder.UpdateLazyConnection(false)
-			return nil
-		}
-		log.Infof("lazy connection manager is disabled by management feature flag")
-		e.closeManager(ctx)
-		e.statusRecorder.UpdateLazyConnection(false)
-		return nil
+	switch state {
+	case mgmProto.LazyState_LazyStateLazy:
+		return true
+	case mgmProto.LazyState_LazyStateEager:
+		return false
+	default:
+		return e.remoteLazyEnabled
 	}
 }
 
@@ -141,6 +129,13 @@ func (e *ConnMgr) SetExcludeList(ctx context.Context, peerIDs map[string]bool) {
 		return
 	}
 
+	// The exclude set is recomputed every sync but rarely changes; skip the O(n)
+	// store lookups and reconciliation when it matches what was already applied.
+	if maps.Equal(peerIDs, e.appliedExcludeList) {
+		return
+	}
+	e.appliedExcludeList = maps.Clone(peerIDs)
+
 	excludedPeers := make([]lazyconn.PeerConfig, 0, len(peerIDs))
 
 	for peerID := range peerIDs {
@@ -176,12 +171,16 @@ func (e *ConnMgr) SetExcludeList(ctx context.Context, peerIDs map[string]bool) {
 	}
 }
 
-func (e *ConnMgr) AddPeerConn(ctx context.Context, peerKey string, conn *peer.Conn) (exists bool) {
+// AddPeerConn registers a peer connection. permanent requests an always-active connection
+// (the peer belongs to the exclude set: a forwarder, or a peer that is not lazy by policy).
+// Non-permanent peers are handed to the lazy manager. The subsequent SetExcludeList call
+// reconciles membership for existing peers across flag flips.
+func (e *ConnMgr) AddPeerConn(ctx context.Context, peerKey string, conn *peer.Conn, permanent bool) (exists bool) {
 	if success := e.peerStore.AddPeerConn(peerKey, conn); !success {
 		return true
 	}
 
-	if !e.isStartedWithLazyMgr() {
+	if !e.isStartedWithLazyMgr() || permanent {
 		if err := conn.Open(ctx); err != nil {
 			conn.Log.Errorf("failed to open connection: %v", err)
 		}
@@ -269,6 +268,7 @@ func (e *ConnMgr) Close() {
 	e.lazyCtxCancel()
 	e.wg.Wait()
 	e.lazyConnMgr = nil
+	e.appliedExcludeList = nil
 }
 
 func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
@@ -276,6 +276,7 @@ func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 		InactivityThreshold: inactivityThresholdEnv(),
 	}
 	e.lazyConnMgr = manager.NewManager(cfg, engineCtx, e.peerStore, e.iface)
+	e.appliedExcludeList = nil
 
 	e.lazyCtx, e.lazyCtxCancel = context.WithCancel(engineCtx)
 
@@ -286,43 +287,6 @@ func (e *ConnMgr) initLazyManager(engineCtx context.Context) {
 	}()
 }
 
-func (e *ConnMgr) addPeersToLazyConnManager() error {
-	peers := e.peerStore.PeersPubKey()
-	lazyPeerCfgs := make([]lazyconn.PeerConfig, 0, len(peers))
-	for _, peerID := range peers {
-		var peerConn *peer.Conn
-		var exists bool
-		if peerConn, exists = e.peerStore.PeerConn(peerID); !exists {
-			log.Warnf("failed to find peer conn for peerID: %s", peerID)
-			continue
-		}
-
-		lazyPeerCfg := lazyconn.PeerConfig{
-			PublicKey:  peerID,
-			AllowedIPs: peerConn.WgConfig().AllowedIps,
-			PeerConnID: peerConn.ConnID(),
-			Log:        peerConn.Log,
-		}
-		lazyPeerCfgs = append(lazyPeerCfgs, lazyPeerCfg)
-	}
-
-	return e.lazyConnMgr.AddActivePeers(lazyPeerCfgs)
-}
-
-func (e *ConnMgr) closeManager(ctx context.Context) {
-	if e.lazyConnMgr == nil {
-		return
-	}
-
-	e.lazyCtxCancel()
-	e.wg.Wait()
-	e.lazyConnMgr = nil
-
-	for _, peerID := range e.peerStore.PeersPubKey() {
-		e.peerStore.PeerConnOpen(ctx, peerID)
-	}
-}
-
 func (e *ConnMgr) isStartedWithLazyMgr() bool {
 	return e.lazyConnMgr != nil && e.lazyCtxCancel != nil
 }

client/internal/conn_mgr_test.go

@@ -5,6 +5,7 @@ import (
 	"testing"
 
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
+	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
 )
 
 func TestResolveLazyForce(t *testing.T) {
@@ -38,3 +39,90 @@ func TestResolveLazyForce(t *testing.T) {
 		})
 	}
 }
+
+func TestPeerLazyDefault(t *testing.T) {
+	tests := []struct {
+		name          string
+		force         lazyForce
+		remoteEnabled bool
+		state         mgmProto.LazyState
+		want          bool
+	}{
+		{name: "force on wins over eager state", force: lazyForceOn, state: mgmProto.LazyState_LazyStateEager, want: true},
+		{name: "force off wins over lazy state", force: lazyForceOff, remoteEnabled: true, state: mgmProto.LazyState_LazyStateLazy, want: false},
+		{name: "none, default, account off -> active", force: lazyForceNone, state: mgmProto.LazyState_LazyStateDefault, want: false},
+		{name: "none, default, account on -> lazy", force: lazyForceNone, remoteEnabled: true, state: mgmProto.LazyState_LazyStateDefault, want: true},
+		{name: "none, lazy state, account off -> lazy", force: lazyForceNone, state: mgmProto.LazyState_LazyStateLazy, want: true},
+		{name: "none, eager state, account on -> active", force: lazyForceNone, remoteEnabled: true, state: mgmProto.LazyState_LazyStateEager, want: false},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			e := &ConnMgr{force: tt.force, remoteLazyEnabled: tt.remoteEnabled}
+			if got := e.PeerLazyDefault(tt.state); got != tt.want {
+				t.Fatalf("PeerLazyDefault(%v) = %v, want %v", tt.state, got, tt.want)
+			}
+		})
+	}
+}
+
+// TestToExcludedLazyPeers covers the per-peer lazy classification (proxy vs
+// normal, across the force/account-flag matrix). Forwarder-target exclusion is
+// covered by TestToExcludedLazyPeers_ForwardTarget.
+func TestToExcludedLazyPeers(t *testing.T) {
+	const (
+		normalKey = "normal"
+		lazyKey   = "lazy-state"
+		eagerKey  = "eager-state"
+	)
+
+	peers := []*mgmProto.RemotePeerConfig{
+		{WgPubKey: normalKey, AllowedIps: []string{"100.64.0.1/32"}},
+		{WgPubKey: lazyKey, AllowedIps: []string{"100.64.0.2/32"}, LazyState: mgmProto.LazyState_LazyStateLazy},
+		{WgPubKey: eagerKey, AllowedIps: []string{"100.64.0.3/32"}, LazyState: mgmProto.LazyState_LazyStateEager},
+	}
+
+	tests := []struct {
+		name          string
+		force         lazyForce
+		remoteEnabled bool
+		want          map[string]bool
+	}{
+		{
+			name:  "account off: lazy-state peer lazy, normal + eager active",
+			force: lazyForceNone, remoteEnabled: false,
+			want: map[string]bool{normalKey: true, eagerKey: true},
+		},
+		{
+			name:  "account on: only eager-state peer active",
+			force: lazyForceNone, remoteEnabled: true,
+			want: map[string]bool{eagerKey: true},
+		},
+		{
+			name:  "force off: everything active",
+			force: lazyForceOff, remoteEnabled: true,
+			want: map[string]bool{normalKey: true, lazyKey: true, eagerKey: true},
+		},
+		{
+			name:  "force on: nothing active",
+			force: lazyForceOn, remoteEnabled: false,
+			want: map[string]bool{},
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			e := &Engine{connMgr: &ConnMgr{force: tt.force, remoteLazyEnabled: tt.remoteEnabled}}
+			got := e.toExcludedLazyPeers(peers)
+
+			if len(got) != len(tt.want) {
+				t.Fatalf("toExcludedLazyPeers() = %v, want %v", got, tt.want)
+			}
+			for k := range tt.want {
+				if !got[k] {
+					t.Fatalf("expected peer %s excluded, got %v", k, got)
+				}
+			}
+		})
+	}
+}

client/internal/engine.go

@@ -842,8 +842,7 @@ func (e *Engine) modifyPeers(peersUpdate []*mgmProto.RemotePeerConfig) error {
 	}
 	// third, add the peer connections again
 	for _, p := range modified {
-		err := e.addNewPeer(p)
-		if err != nil {
+		if err := e.addNewPeer(p); err != nil {
 			return err
 		}
 	}
@@ -1403,8 +1402,12 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 		return nil
 	}
 
-	if err := e.connMgr.UpdatedRemoteFeatureFlag(e.ctx, networkMap.GetPeerConfig().GetLazyConnectionEnabled()); err != nil {
-		log.Errorf("failed to update lazy connection feature flag: %v", err)
+	// Only update the flag when the sync carries a peer config; a nil peer config
+	// (e.g. a partial update) must not reset the cached flag to false.
+	if peerConfig := networkMap.GetPeerConfig(); peerConfig != nil {
+		if err := e.connMgr.UpdatedRemoteFeatureFlag(e.ctx, peerConfig.GetLazyConnectionEnabled()); err != nil {
+			log.Errorf("failed to update lazy connection feature flag: %v", err)
+		}
 	}
 
 	if e.firewall != nil {
@@ -1470,8 +1473,7 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	// Ingress forward rules
 	done = e.phase("forward_rules")
-	forwardingRules, err := e.updateForwardRules(networkMap.GetForwardingRules())
-	if err != nil {
+	if _, err := e.updateForwardRules(networkMap.GetForwardingRules()); err != nil {
 		log.Errorf("failed to update forward rules, err: %v", err)
 	}
 	done()
@@ -1489,8 +1491,7 @@ func (e *Engine) updateNetworkMap(networkMap *mgmProto.NetworkMap) error {
 
 	// must set the exclude list after the peers are added. Without it the manager can not figure out the peers parameters from the store
 	done = e.phase("lazy_exclude")
-	excludedLazyPeers := e.toExcludedLazyPeers(forwardingRules, remotePeers)
-	e.connMgr.SetExcludeList(e.ctx, excludedLazyPeers)
+	e.connMgr.SetExcludeList(e.ctx, e.toExcludedLazyPeers(remotePeers))
 	done()
 
 	e.networkSerial = serial
@@ -1734,15 +1735,15 @@ func addrToString(addr netip.Addr) string {
 // addNewPeers adds peers that were not know before but arrived from the Management service with the update
 func (e *Engine) addNewPeers(peersUpdate []*mgmProto.RemotePeerConfig) error {
 	for _, p := range peersUpdate {
-		err := e.addNewPeer(p)
-		if err != nil {
+		if err := e.addNewPeer(p); err != nil {
 			return err
 		}
 	}
 	return nil
 }
 
-// addNewPeer add peer if connection doesn't exist
+// addNewPeer add peer if connection doesn't exist. A peer that is not lazy by
+// policy gets an always-active connection instead.
 func (e *Engine) addNewPeer(peerConfig *mgmProto.RemotePeerConfig) error {
 	peerKey := peerConfig.GetWgPubKey()
 	peerIPs := make([]netip.Prefix, 0, len(peerConfig.GetAllowedIps()))
@@ -1777,7 +1778,8 @@ func (e *Engine) addNewPeer(peerConfig *mgmProto.RemotePeerConfig) error {
 		log.Warnf("error adding peer %s to status recorder, got error: %v", peerKey, err)
 	}
 
-	if exists := e.connMgr.AddPeerConn(e.ctx, peerKey, conn); exists {
+	permanent := !e.connMgr.PeerLazyDefault(peerConfig.GetLazyState())
+	if exists := e.connMgr.AddPeerConn(e.ctx, peerKey, conn, permanent); exists {
 		conn.Close(false)
 		return fmt.Errorf("peer already exists: %s", peerKey)
 	}
@@ -2603,46 +2605,19 @@ func (e *Engine) updateForwardRules(rules []*mgmProto.ForwardingRule) ([]firewal
 	return forwardingRules, nberrors.FormatErrorOrNil(merr)
 }
 
-func (e *Engine) toExcludedLazyPeers(rules []firewallManager.ForwardRule, peers []*mgmProto.RemotePeerConfig) map[string]bool {
+// toExcludedLazyPeers returns the peers that must have an always-active
+// connection: those that are not lazy by policy (the per-peer lazy state or the
+// account flag, subject to the local override).
+func (e *Engine) toExcludedLazyPeers(peers []*mgmProto.RemotePeerConfig) map[string]bool {
 	excludedPeers := make(map[string]bool)
-
-	// Ingress forward targets: inbound forwarded traffic is initiated remotely and
-	// cannot wake a lazy connection, so the peer routing the target must stay
-	// permanently connected. AllowedIPs are already parsed on the peer conn, so
-	// reuse those typed prefixes instead of re-parsing the network map strings.
-	for _, r := range rules {
-		for _, p := range peers {
-			if e.peerRoutesAddr(p, r.TranslatedAddress) {
-				log.Infof("exclude forwarder peer from lazy connection: %s", p.GetWgPubKey())
-				excludedPeers[p.GetWgPubKey()] = true
-			}
+	for _, p := range peers {
+		if !e.connMgr.PeerLazyDefault(p.GetLazyState()) {
+			excludedPeers[p.GetWgPubKey()] = true
 		}
 	}
-
 	return excludedPeers
 }
 
-// peerRoutesAddr reports whether the peer is a router for addr, matched against
-// the peer's already-parsed AllowedIPs from the store (the same typed value the
-// lazy manager consumes) rather than re-parsing the network map strings.
-func (e *Engine) peerRoutesAddr(p *mgmProto.RemotePeerConfig, addr netip.Addr) bool {
-	prefixes, ok := e.peerStore.AllowedIPs(p.GetWgPubKey())
-	if !ok {
-		return false
-	}
-	return prefixesContain(prefixes, addr)
-}
-
-// prefixesContain reports whether addr falls within any of the prefixes.
-func prefixesContain(prefixes []netip.Prefix, addr netip.Addr) bool {
-	for _, prefix := range prefixes {
-		if prefix.Contains(addr) {
-			return true
-		}
-	}
-	return false
-}
-
 // isChecksEqual checks if two slices of checks are equal.
 func isChecksEqual(checks1, checks2 []*mgmProto.Checks) bool {
 	normalize := func(checks []*mgmProto.Checks) []string {

client/internal/engine_lazy_exclude_test.go

@@ -1,87 +0,0 @@
-package internal
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-
-	firewallManager "github.com/netbirdio/netbird/client/firewall/manager"
-	"github.com/netbirdio/netbird/client/internal/peer"
-	"github.com/netbirdio/netbird/client/internal/peerstore"
-	mgmProto "github.com/netbirdio/netbird/shared/management/proto"
-)
-
-func TestPrefixesContain(t *testing.T) {
-	tests := []struct {
-		name     string
-		prefixes []string
-		addr     string
-		want     bool
-	}{
-		{name: "own overlay /32 matches", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.145", want: true},
-		{name: "addr inside routed subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.121.208.4", want: true},
-		{name: "addr outside subnet", prefixes: []string{"10.121.0.0/16"}, addr: "10.122.0.1", want: false},
-		{name: "different /32", prefixes: []string{"100.110.8.145/32"}, addr: "100.110.8.146", want: false},
-		{name: "ipv6 /128 matches", prefixes: []string{"fd00::1/128"}, addr: "fd00::1", want: true},
-		{name: "no prefixes", prefixes: nil, addr: "10.121.208.4", want: false},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			prefixes := make([]netip.Prefix, 0, len(tt.prefixes))
-			for _, p := range tt.prefixes {
-				prefixes = append(prefixes, netip.MustParsePrefix(p))
-			}
-			require.Equal(t, tt.want, prefixesContain(prefixes, netip.MustParseAddr(tt.addr)))
-		})
-	}
-}
-
-// TestToExcludedLazyPeers_ForwardTarget guards a regression: the forward-target
-// peer (the peer routing a ForwardRule.TranslatedAddress) must be excluded from
-// lazy connections, matched via the peer's already-parsed AllowedIPs.
-func TestToExcludedLazyPeers_ForwardTarget(t *testing.T) {
-	const targetPeerKey = "cccccccccccccccccccccccccccccccccccccccccc0="
-	const otherPeerKey = "dddddddddddddddddddddddddddddddddddddddddd0="
-
-	store := peerstore.NewConnStore()
-	store.AddPeerConn(targetPeerKey, newTestConn(t, targetPeerKey, "100.110.8.145/32"))
-	store.AddPeerConn(otherPeerKey, newTestConn(t, otherPeerKey, "100.110.9.10/32"))
-
-	e := &Engine{peerStore: store}
-
-	peers := []*mgmProto.RemotePeerConfig{
-		{WgPubKey: targetPeerKey, AllowedIps: []string{"100.110.8.145/32"}},
-		{WgPubKey: otherPeerKey, AllowedIps: []string{"100.110.9.10/32"}},
-	}
-	rules := []firewallManager.ForwardRule{
-		{TranslatedAddress: netip.MustParseAddr("100.110.8.145")},
-	}
-
-	excluded := e.toExcludedLazyPeers(rules, peers)
-
-	require.True(t, excluded[targetPeerKey], "forward-target peer must be excluded from lazy connections")
-	require.False(t, excluded[otherPeerKey], "non-target peer must not be excluded")
-	require.Len(t, excluded, 1)
-}
-
-func TestToExcludedLazyPeers_NoRules(t *testing.T) {
-	e := &Engine{peerStore: peerstore.NewConnStore()}
-
-	peers := []*mgmProto.RemotePeerConfig{
-		{WgPubKey: "peer-a", AllowedIps: []string{"100.110.8.145/32"}},
-	}
-
-	require.Empty(t, e.toExcludedLazyPeers(nil, peers))
-}
-
-func newTestConn(t *testing.T, key, allowedIP string) *peer.Conn {
-	t.Helper()
-	conn, err := peer.NewConn(peer.ConnConfig{
-		Key:      key,
-		WgConfig: peer.WgConfig{AllowedIps: []netip.Prefix{netip.MustParsePrefix(allowedIP)}},
-	}, peer.ServiceDependencies{})
-	require.NoError(t, err)
-	return conn
-}

client/internal/engine_test.go

@@ -279,7 +279,8 @@ func TestEngine_UpdateNetworkMap(t *testing.T) {
 	}, MobileDependency{})
 
 	wgIface := &MockWGIface{
-		NameFunc: func() string { return "utun102" },
+		NameFunc:            func() string { return "utun102" },
+		IsUserspaceBindFunc: func() bool { return true },
 		RemovePeerFunc: func(peerKey string) error {
 			return nil
 		},

management/internals/shared/grpc/conversion.go

@@ -164,6 +164,7 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	// filtered at the source (network map builder).
 	includeIPv6 := peer.SupportsIPv6() && peer.IPv6.IsValid()
 	useSourcePrefixes := peer.SupportsSourcePrefixes()
+	localIsProxy := peer.ProxyMeta.Embedded
 
 	response := &proto.SyncResponse{
 		PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH),
@@ -183,7 +184,7 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	response.NetworkMap.PeerConfig = response.PeerConfig
 
 	remotePeers := make([]*proto.RemotePeerConfig, 0, len(networkMap.Peers)+len(networkMap.OfflinePeers))
-	remotePeers = appendRemotePeerConfig(remotePeers, networkMap.Peers, dnsName, includeIPv6)
+	remotePeers = appendRemotePeerConfig(remotePeers, networkMap.Peers, dnsName, includeIPv6, localIsProxy)
 
 	if !shouldSkipSendingDeprecatedRemotePeers(peer.Meta.WtVersion) {
 		response.RemotePeers = remotePeers
@@ -193,7 +194,7 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	response.RemotePeersIsEmpty = len(remotePeers) == 0
 	response.NetworkMap.RemotePeersIsEmpty = response.RemotePeersIsEmpty
 
-	response.NetworkMap.OfflinePeers = appendRemotePeerConfig(nil, networkMap.OfflinePeers, dnsName, includeIPv6)
+	response.NetworkMap.OfflinePeers = appendRemotePeerConfig(nil, networkMap.OfflinePeers, dnsName, includeIPv6, localIsProxy)
 
 	firewallRules := toProtocolFirewallRules(networkMap.FirewallRules, includeIPv6, useSourcePrefixes)
 	response.NetworkMap.FirewallRules = firewallRules
@@ -292,7 +293,7 @@ func shouldSkipSendingDeprecatedRemotePeers(peerVersion string) bool {
 	return precomputedDeprecatedRemotePeersConstraint.Check(peerNBVersion)
 }
 
-func appendRemotePeerConfig(dst []*proto.RemotePeerConfig, peers []*nbpeer.Peer, dnsName string, includeIPv6 bool) []*proto.RemotePeerConfig {
+func appendRemotePeerConfig(dst []*proto.RemotePeerConfig, peers []*nbpeer.Peer, dnsName string, includeIPv6 bool, localIsProxy bool) []*proto.RemotePeerConfig {
 	for _, rPeer := range peers {
 		allowedIPs := []string{rPeer.IP.String() + "/32"}
 		if includeIPv6 && rPeer.IPv6.IsValid() {
@@ -304,11 +305,24 @@ func appendRemotePeerConfig(dst []*proto.RemotePeerConfig, peers []*nbpeer.Peer,
 			SshConfig:    &proto.SSHConfig{SshPubKey: []byte(rPeer.SSHKey)},
 			Fqdn:         rPeer.FQDN(dnsName),
 			AgentVersion: rPeer.Meta.WtVersion,
+			LazyState:    lazyStateFor(localIsProxy, rPeer),
 		})
 	}
 	return dst
 }
 
+// lazyStateFor returns the per-peer lazy override for a remote peer. Connections
+// involving an ephemeral proxy peer on either endpoint default to lazy so shared
+// proxy infrastructure is not kept permanently connected to every peer. All
+// other peers follow the account-wide flag. A future admin-facing per-peer
+// setting can return LazyStateEager here to force a peer always-active.
+func lazyStateFor(localIsProxy bool, rPeer *nbpeer.Peer) proto.LazyState {
+	if localIsProxy || rPeer.ProxyMeta.Embedded {
+		return proto.LazyState_LazyStateLazy
+	}
+	return proto.LazyState_LazyStateDefault
+}
+
 // toProtocolDNSConfig converts nbdns.Config to proto.DNSConfig using the cache
 func toProtocolDNSConfig(update nbdns.Config, cache *cache.DNSConfigCache, forwardPort int64) *proto.DNSConfig {
 	protoUpdate := &proto.DNSConfig{

proxy/internal/roundtrip/netbird.go

@@ -30,6 +30,12 @@ import (
 
 const deviceNamePrefix = "ingress-proxy-"
 
+// envProxyRosenpass toggles Rosenpass (permissive) on the embedded proxy client. Defaults to on.
+const envProxyRosenpass = "NB_PROXY_ROSENPASS" //nolint:gosec // env var name, not a credential
+
+// envProxyClientLogLevel sets the embedded NetBird client's log level.
+const envProxyClientLogLevel = "NB_PROXY_CLIENT_LOG_LEVEL"
+
 const clientStopTimeout = 30 * time.Second
 
 const createProxyPeerTimeout = 30 * time.Second
@@ -353,11 +359,11 @@ func (n *NetBird) createClientEntry(ctx context.Context, accountID types.Account
 	// NB_PROXY_CLIENT_LOG_LEVEL (e.g. "trace") to surface the embedded NetBird
 	// client's relay / signal / handshake detail for local debugging.
 	clientLogLevel := log.WarnLevel.String()
-	if v := strings.TrimSpace(os.Getenv("NB_PROXY_CLIENT_LOG_LEVEL")); v != "" {
+	if v := strings.TrimSpace(os.Getenv(envProxyClientLogLevel)); v != "" {
 		if lvl, err := log.ParseLevel(v); err == nil {
 			clientLogLevel = lvl.String()
 		} else {
-			n.logger.Warnf("invalid NB_PROXY_CLIENT_LOG_LEVEL %q, using %q: %v", v, clientLogLevel, err)
+			n.logger.Warnf("invalid %s %q, using %q: %v", envProxyClientLogLevel, v, clientLogLevel, err)
 		}
 	}
 
@@ -367,15 +373,26 @@ func (n *NetBird) createClientEntry(ctx context.Context, accountID types.Account
 		}
 	})
 
+	// Rosenpass runs in permissive mode by default so the embedded proxy can
+	// establish connections with Rosenpass-enabled peers (which otherwise fail
+	// on a PSK mismatch) while still falling back to plain WireGuard for peers
+	// that do not run Rosenpass. Set NB_PROXY_ROSENPASS=false to disable it.
+	rosenpassEnabled := true
+	if v, ok := envBool(envProxyRosenpass, n.logger); ok {
+		rosenpassEnabled = v
+	}
+
 	// Create embedded NetBird client with the generated private key.
 	// The peer has already been created via CreateProxyPeer RPC with the public key.
 	wgPort := int(n.clientCfg.WGPort)
 	embedOpts := embed.Options{
-		DeviceName:    deviceNamePrefix + n.proxyID,
-		ManagementURL: n.clientCfg.MgmtAddr,
-		PrivateKey:    privateKey.String(),
-		LogLevel:      clientLogLevel,
-		BlockInbound:  n.clientCfg.BlockInbound,
+		DeviceName:          deviceNamePrefix + n.proxyID,
+		ManagementURL:       n.clientCfg.MgmtAddr,
+		PrivateKey:          privateKey.String(),
+		LogLevel:            clientLogLevel,
+		BlockInbound:        n.clientCfg.BlockInbound,
+		EnableRosenpass:     rosenpassEnabled,
+		RosenpassPermissive: rosenpassEnabled,
 		// The embedded proxy peer must never be a stepping stone into
 		// the proxy host's LAN: it only exists to reach NetBird mesh
 		// targets or, when direct_upstream is set, the host network
@@ -899,6 +916,8 @@ func logEmbedOptions(logger *log.Logger, accountID types.AccountID, serviceID ty
 		"mtu":                   mtu,
 		"block_inbound":         opts.BlockInbound,
 		"block_lan_access":      opts.BlockLANAccess,
+		"rosenpass_enabled":     opts.EnableRosenpass,
+		"rosenpass_permissive":  opts.RosenpassPermissive,
 		"disable_ipv6":          opts.DisableIPv6,
 		"disable_client_routes": opts.DisableClientRoutes,
 		"no_userspace":          opts.NoUserspace,

shared/management/proto/management.proto

@@ -486,6 +486,22 @@ message RemotePeerConfig {
   string fqdn = 4;
 
   string agentVersion = 5;
+
+  // lazyState is the management per-peer override for lazy (on-demand)
+  // connections to this remote peer. LazyStateDefault follows the account-wide
+  // flag; LazyStateLazy forces lazy; LazyStateEager forces an always-active
+  // connection. A local NB_LAZY_CONN/MDM override still wins over this.
+  LazyState lazyState = 6;
+}
+
+// LazyState is the management per-peer override for lazy connections.
+enum LazyState {
+  // Follow the account-wide lazy connection flag.
+  LazyStateDefault = 0;
+  // Force a lazy (on-demand) connection regardless of the account flag.
+  LazyStateLazy = 1;
+  // Force an always-active connection regardless of the account flag.
+  LazyStateEager = 2;
 }
 
 // SSHConfig represents SSH configurations of a peer.