Merge branch 'main' into refactor-combined

management/internals/modules/peers/ephemeral/manager/ephemeral.go

@@ -11,6 +11,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/peers/ephemeral"
 	"github.com/netbirdio/netbird/management/server/activity"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 
 	"github.com/netbirdio/netbird/management/server/store"
 )
@@ -47,6 +48,11 @@ type EphemeralManager struct {
 
 	lifeTime      time.Duration
 	cleanupWindow time.Duration
+
+	// metrics is nil-safe; methods on telemetry.EphemeralPeersMetrics
+	// no-op when the receiver is nil so deployments without an app
+	// metrics provider work unchanged.
+	metrics *telemetry.EphemeralPeersMetrics
 }
 
 // NewEphemeralManager instantiate new EphemeralManager
@@ -60,6 +66,15 @@ func NewEphemeralManager(store store.Store, peersManager peers.Manager) *Ephemer
 	}
 }
 
+// SetMetrics attaches a metrics collector. Safe to call once before
+// LoadInitialPeers; later attachment is fine but earlier loads won't be
+// reflected in the gauge. Pass nil to detach.
+func (e *EphemeralManager) SetMetrics(m *telemetry.EphemeralPeersMetrics) {
+	e.peersLock.Lock()
+	e.metrics = m
+	e.peersLock.Unlock()
+}
+
 // LoadInitialPeers load from the database the ephemeral type of peers and schedule a cleanup procedure to the head
 // of the linked list (to the most deprecated peer). At the end of cleanup it schedules the next cleanup to the new
 // head.
@@ -97,7 +112,9 @@ func (e *EphemeralManager) OnPeerConnected(ctx context.Context, peer *nbpeer.Pee
 	e.peersLock.Lock()
 	defer e.peersLock.Unlock()
 
-	e.removePeer(peer.ID)
+	if e.removePeer(peer.ID) {
+		e.metrics.DecPending(1)
+	}
 
 	// stop the unnecessary timer
 	if e.headPeer == nil && e.timer != nil {
@@ -123,6 +140,7 @@ func (e *EphemeralManager) OnPeerDisconnected(ctx context.Context, peer *nbpeer.
 	}
 
 	e.addPeer(peer.AccountID, peer.ID, e.newDeadLine())
+	e.metrics.IncPending()
 	if e.timer == nil {
 		delay := e.headPeer.deadline.Sub(timeNow()) + e.cleanupWindow
 		if delay < 0 {
@@ -145,6 +163,7 @@ func (e *EphemeralManager) loadEphemeralPeers(ctx context.Context) {
 	for _, p := range peers {
 		e.addPeer(p.AccountID, p.ID, t)
 	}
+	e.metrics.AddPending(int64(len(peers)))
 
 	log.WithContext(ctx).Debugf("loaded ephemeral peer(s): %d", len(peers))
 }
@@ -181,6 +200,15 @@ func (e *EphemeralManager) cleanup(ctx context.Context) {
 
 	e.peersLock.Unlock()
 
+	// Drop the gauge by the number of entries we just took off the list,
+	// regardless of whether the subsequent DeletePeers call succeeds. The
+	// list invariant is what the gauge tracks; failed delete batches are
+	// counted separately via CountCleanupError so we can still see them.
+	if len(deletePeers) > 0 {
+		e.metrics.CountCleanupRun()
+		e.metrics.DecPending(int64(len(deletePeers)))
+	}
+
 	peerIDsPerAccount := make(map[string][]string)
 	for id, p := range deletePeers {
 		peerIDsPerAccount[p.accountID] = append(peerIDsPerAccount[p.accountID], id)
@@ -191,7 +219,10 @@ func (e *EphemeralManager) cleanup(ctx context.Context) {
 		err := e.peersManager.DeletePeers(ctx, accountID, peerIDs, activity.SystemInitiator, true)
 		if err != nil {
 			log.WithContext(ctx).Errorf("failed to delete ephemeral peers: %s", err)
+			e.metrics.CountCleanupError()
+			continue
 		}
+		e.metrics.CountPeersCleaned(int64(len(peerIDs)))
 	}
 }
 
@@ -211,9 +242,12 @@ func (e *EphemeralManager) addPeer(accountID string, peerID string, deadline tim
 	e.tailPeer = ep
 }
 
-func (e *EphemeralManager) removePeer(id string) {
+// removePeer drops the entry from the linked list. Returns true if a
+// matching entry was found and removed so callers can keep the pending
+// metric gauge in sync.
+func (e *EphemeralManager) removePeer(id string) bool {
 	if e.headPeer == nil {
-		return
+		return false
 	}
 
 	if e.headPeer.id == id {
@@ -221,7 +255,7 @@ func (e *EphemeralManager) removePeer(id string) {
 		if e.tailPeer.id == id {
 			e.tailPeer = nil
 		}
-		return
+		return true
 	}
 
 	for p := e.headPeer; p.next != nil; p = p.next {
@@ -231,9 +265,10 @@ func (e *EphemeralManager) removePeer(id string) {
 				e.tailPeer = p
 			}
 			p.next = p.next.next
-			return
+			return true
 		}
 	}
+	return false
 }
 
 func (e *EphemeralManager) isPeerOnList(id string) bool {

management/internals/modules/peers/manager.go

@@ -5,6 +5,7 @@ package peers
 import (
 	"context"
 	"fmt"
+	"net"
 	"time"
 
 	"github.com/rs/xid"
@@ -35,6 +36,14 @@ type Manager interface {
 	SetAccountManager(accountManager account.Manager)
 	GetPeerID(ctx context.Context, peerKey string) (string, error)
 	CreateProxyPeer(ctx context.Context, accountID string, peerKey string, cluster string) error
+	// GetPeerByTunnelIP looks up a peer in accountID by its WireGuard tunnel IP.
+	// Returns nil with an error when no match exists. No permission check;
+	// callers (the proxy's ValidateTunnelPeer RPC) are trusted server components.
+	GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error)
+	// GetPeerWithGroups returns the peer and the list of *types.Group it belongs
+	// to. Used by the proxy's auth path to authorise a request by the calling
+	// peer's group memberships.
+	GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error)
 }
 
 type managerImpl struct {
@@ -99,6 +108,26 @@ func (m *managerImpl) GetPeersByGroupIDs(ctx context.Context, accountID string,
 	return m.store.GetPeersByGroupIDs(ctx, accountID, groupsIDs)
 }
 
+// GetPeerByTunnelIP delegates to the store's indexed lookup.
+func (m *managerImpl) GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error) {
+	return m.store.GetPeerByIP(ctx, store.LockingStrengthNone, accountID, ip)
+}
+
+// GetPeerWithGroups returns the peer plus its group memberships. Any store
+// error returns (nil, nil, err) so callers never receive a valid peer
+// alongside a non-nil error.
+func (m *managerImpl) GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error) {
+	p, err := m.store.GetPeerByID(ctx, store.LockingStrengthNone, accountID, peerID)
+	if err != nil {
+		return nil, nil, err
+	}
+	groups, err := m.store.GetPeerGroups(ctx, store.LockingStrengthNone, accountID, peerID)
+	if err != nil {
+		return nil, nil, err
+	}
+	return p, groups, nil
+}
+
 func (m *managerImpl) DeletePeers(ctx context.Context, accountID string, peerIDs []string, userID string, checkConnected bool) error {
 	settings, err := m.store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
 	if err != nil {

management/internals/modules/peers/manager_mock.go

@@ -6,6 +6,7 @@ package peers
 
 import (
 	context "context"
+	net "net"
 	reflect "reflect"
 
 	gomock "github.com/golang/mock/gomock"
@@ -13,6 +14,7 @@ import (
 	account "github.com/netbirdio/netbird/management/server/account"
 	integrated_validator "github.com/netbirdio/netbird/management/server/integrations/integrated_validator"
 	peer "github.com/netbirdio/netbird/management/server/peer"
+	types "github.com/netbirdio/netbird/management/server/types"
 )
 
 // MockManager is a mock of Manager interface.
@@ -38,6 +40,20 @@ func (m *MockManager) EXPECT() *MockManagerMockRecorder {
 	return m.recorder
 }
 
+// CreateProxyPeer mocks base method.
+func (m *MockManager) CreateProxyPeer(ctx context.Context, accountID, peerKey, cluster string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "CreateProxyPeer", ctx, accountID, peerKey, cluster)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// CreateProxyPeer indicates an expected call of CreateProxyPeer.
+func (mr *MockManagerMockRecorder) CreateProxyPeer(ctx, accountID, peerKey, cluster interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateProxyPeer", reflect.TypeOf((*MockManager)(nil).CreateProxyPeer), ctx, accountID, peerKey, cluster)
+}
+
 // DeletePeers mocks base method.
 func (m *MockManager) DeletePeers(ctx context.Context, accountID string, peerIDs []string, userID string, checkConnected bool) error {
 	m.ctrl.T.Helper()
@@ -97,6 +113,21 @@ func (mr *MockManagerMockRecorder) GetPeerAccountID(ctx, peerID interface{}) *go
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerAccountID", reflect.TypeOf((*MockManager)(nil).GetPeerAccountID), ctx, peerID)
 }
 
+// GetPeerByTunnelIP mocks base method.
+func (m *MockManager) GetPeerByTunnelIP(ctx context.Context, accountID string, ip net.IP) (*peer.Peer, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetPeerByTunnelIP", ctx, accountID, ip)
+	ret0, _ := ret[0].(*peer.Peer)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetPeerByTunnelIP indicates an expected call of GetPeerByTunnelIP.
+func (mr *MockManagerMockRecorder) GetPeerByTunnelIP(ctx, accountID, ip interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerByTunnelIP", reflect.TypeOf((*MockManager)(nil).GetPeerByTunnelIP), ctx, accountID, ip)
+}
+
 // GetPeerID mocks base method.
 func (m *MockManager) GetPeerID(ctx context.Context, peerKey string) (string, error) {
 	m.ctrl.T.Helper()
@@ -112,6 +143,22 @@ func (mr *MockManagerMockRecorder) GetPeerID(ctx, peerKey interface{}) *gomock.C
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerID", reflect.TypeOf((*MockManager)(nil).GetPeerID), ctx, peerKey)
 }
 
+// GetPeerWithGroups mocks base method.
+func (m *MockManager) GetPeerWithGroups(ctx context.Context, accountID, peerID string) (*peer.Peer, []*types.Group, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetPeerWithGroups", ctx, accountID, peerID)
+	ret0, _ := ret[0].(*peer.Peer)
+	ret1, _ := ret[1].([]*types.Group)
+	ret2, _ := ret[2].(error)
+	return ret0, ret1, ret2
+}
+
+// GetPeerWithGroups indicates an expected call of GetPeerWithGroups.
+func (mr *MockManagerMockRecorder) GetPeerWithGroups(ctx, accountID, peerID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetPeerWithGroups", reflect.TypeOf((*MockManager)(nil).GetPeerWithGroups), ctx, accountID, peerID)
+}
+
 // GetPeersByGroupIDs mocks base method.
 func (m *MockManager) GetPeersByGroupIDs(ctx context.Context, accountID string, groupsIDs []string) ([]*peer.Peer, error) {
 	m.ctrl.T.Helper()
@@ -162,17 +209,3 @@ func (mr *MockManagerMockRecorder) SetNetworkMapController(networkMapController
 	mr.mock.ctrl.T.Helper()
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SetNetworkMapController", reflect.TypeOf((*MockManager)(nil).SetNetworkMapController), networkMapController)
 }
-
-// CreateProxyPeer mocks base method.
-func (m *MockManager) CreateProxyPeer(ctx context.Context, accountID string, peerKey string, cluster string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "CreateProxyPeer", ctx, accountID, peerKey, cluster)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// CreateProxyPeer indicates an expected call of CreateProxyPeer.
-func (mr *MockManagerMockRecorder) CreateProxyPeer(ctx, accountID, peerKey, cluster interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateProxyPeer", reflect.TypeOf((*MockManager)(nil).CreateProxyPeer), ctx, accountID, peerKey, cluster)
-}

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

@@ -23,6 +23,8 @@ type Domain struct {
 	// SupportsCrowdSec is populated at query time from proxy cluster capabilities.
 	// Not persisted.
 	SupportsCrowdSec *bool `gorm:"-"`
+	// SupportsPrivate is populated at query time from proxy cluster capabilities. Not persisted.
+	SupportsPrivate *bool `gorm:"-"`
 }
 
 // EventMeta returns activity event metadata for a domain

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

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

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

@@ -35,6 +35,7 @@ type proxyManager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
 type Manager struct {
@@ -93,6 +94,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		d.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, cluster)
 		d.RequireSubdomain = m.proxyManager.ClusterRequireSubdomain(ctx, cluster)
 		d.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, cluster)
+		d.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, cluster)
 		ret = append(ret, d)
 	}
 
@@ -109,6 +111,7 @@ func (m Manager) GetDomains(ctx context.Context, accountID, userID string) ([]*d
 		if d.TargetCluster != "" {
 			cd.SupportsCustomPorts = m.proxyManager.ClusterSupportsCustomPorts(ctx, d.TargetCluster)
 			cd.SupportsCrowdSec = m.proxyManager.ClusterSupportsCrowdSec(ctx, d.TargetCluster)
+			cd.SupportsPrivate = m.proxyManager.ClusterSupportsPrivate(ctx, d.TargetCluster)
 		}
 		// Custom domains never require a subdomain by default since
 		// the account owns them and should be able to use the bare domain.
@@ -304,10 +307,27 @@ func (m Manager) getClusterAllowList(ctx context.Context, accountID string) ([]s
 	if err != nil {
 		return nil, fmt.Errorf("get BYOP cluster addresses: %w", err)
 	}
-	if len(byopAddresses) > 0 {
-		return byopAddresses, nil
+	publicAddresses, err := m.proxyManager.GetActiveClusterAddresses(ctx)
+	if err != nil {
+		return nil, fmt.Errorf("get public cluster addresses: %w", err)
 	}
-	return m.proxyManager.GetActiveClusterAddresses(ctx)
+	seen := make(map[string]struct{}, len(byopAddresses)+len(publicAddresses))
+	merged := make([]string, 0, len(byopAddresses)+len(publicAddresses))
+	for _, addr := range byopAddresses {
+		if _, ok := seen[addr]; ok {
+			continue
+		}
+		seen[addr] = struct{}{}
+		merged = append(merged, addr)
+	}
+	for _, addr := range publicAddresses {
+		if _, ok := seen[addr]; ok {
+			continue
+		}
+		seen[addr] = struct{}{}
+		merged = append(merged, addr)
+	}
+	return merged, nil
 }
 
 func extractClusterFromCustomDomains(serviceDomain string, customDomains []*domain.Domain) (string, bool) {

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

@@ -10,7 +10,7 @@ import (
 )
 
 type mockProxyManager struct {
-	getActiveClusterAddressesFunc          func(ctx context.Context) ([]string, error)
+	getActiveClusterAddressesFunc           func(ctx context.Context) ([]string, error)
 	getActiveClusterAddressesForAccountFunc func(ctx context.Context, accountID string) ([]string, error)
 }
 
@@ -40,22 +40,41 @@ func (m *mockProxyManager) ClusterSupportsCrowdSec(_ context.Context, _ string)
 	return nil
 }
 
-func TestGetClusterAllowList_BYOPProxy(t *testing.T) {
+func (m *mockProxyManager) ClusterSupportsPrivate(_ context.Context, _ string) *bool {
+	return nil
+}
+
+func TestGetClusterAllowList_BYOPMergedWithPublic(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, accID string) ([]string, error) {
 			assert.Equal(t, "acc-123", accID)
 			return []string{"byop.example.com"}, nil
 		},
 		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			t.Fatal("should not call GetActiveClusterAddresses when BYOP addresses exist")
-			return nil, nil
+			return []string{"eu.proxy.netbird.io"}, nil
 		},
 	}
 
 	mgr := Manager{proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
-	assert.Equal(t, []string{"byop.example.com"}, result)
+	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result)
+}
+
+func TestGetClusterAllowList_DeduplicatesBYOPAndPublic(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"shared.example.com", "byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return []string{"shared.example.com", "eu.proxy.netbird.io"}, nil
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"shared.example.com", "byop.example.com", "eu.proxy.netbird.io"}, result)
 }
 
 func TestGetClusterAllowList_NoBYOP_FallbackToShared(t *testing.T) {
@@ -79,10 +98,6 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
 			return nil, errors.New("db error")
 		},
-		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
-			t.Fatal("should not call GetActiveClusterAddresses when BYOP lookup fails")
-			return nil, nil
-		},
 	}
 
 	mgr := Manager{proxyManager: pm}
@@ -92,6 +107,23 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 	assert.Contains(t, err.Error(), "BYOP cluster addresses")
 }
 
+func TestGetClusterAllowList_PublicError_ReturnsError(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return nil, errors.New("db error")
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.Error(t, err)
+	assert.Nil(t, result)
+	assert.Contains(t, err.Error(), "public cluster addresses")
+}
+
 func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	pm := &mockProxyManager{
 		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
@@ -108,3 +140,18 @@ func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 	assert.Equal(t, []string{"eu.proxy.netbird.io"}, result)
 }
 
+func TestGetClusterAllowList_PublicEmpty_BYOPOnly(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return nil, nil
+		},
+	}
+
+	mgr := Manager{proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"byop.example.com"}, result)
+}

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

@@ -19,6 +19,7 @@ type Manager interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 	CleanupStale(ctx context.Context, inactivityDuration time.Duration) error
 	GetAccountProxy(ctx context.Context, accountID string) (*Proxy, error)
 	CountAccountProxies(ctx context.Context, accountID string) (int64, error)

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

@@ -17,10 +17,11 @@ type store interface {
 	UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
 	GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
 	GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error)
-	GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
+	GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(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)
 	CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error)
@@ -137,6 +138,11 @@ func (m Manager) ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string
 	return m.store.GetClusterSupportsCrowdSec(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)
+}
+
 // CleanupStale removes proxies that haven't sent heartbeat in the specified duration
 func (m *Manager) CleanupStale(ctx context.Context, inactivityDuration time.Duration) error {
 	if err := m.store.CleanupStaleProxies(ctx, inactivityDuration); err != nil {
@@ -178,4 +184,3 @@ func (m *Manager) DeleteAccountCluster(ctx context.Context, clusterAddress, acco
 	}
 	return nil
 }
-

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

@@ -15,16 +15,16 @@ import (
 )
 
 type mockStore struct {
-	saveProxyFunc                              func(ctx context.Context, p *proxy.Proxy) error
-	disconnectProxyFunc                        func(ctx context.Context, proxyID, sessionID string) error
-	updateProxyHeartbeatFunc                   func(ctx context.Context, p *proxy.Proxy) error
-	getActiveProxyClusterAddressesFunc         func(ctx context.Context) ([]string, error)
-	getActiveProxyClusterAddressesForAccFunc   func(ctx context.Context, accountID string) ([]string, error)
-	cleanupStaleProxiesFunc                    func(ctx context.Context, d time.Duration) error
-	getProxyByAccountIDFunc                    func(ctx context.Context, accountID string) (*proxy.Proxy, error)
-	countProxiesByAccountIDFunc                func(ctx context.Context, accountID string) (int64, error)
-	isClusterAddressConflictingFunc            func(ctx context.Context, clusterAddress, accountID string) (bool, error)
-	deleteAccountClusterFunc                   func(ctx context.Context, clusterAddress, accountID string) error
+	saveProxyFunc                            func(ctx context.Context, p *proxy.Proxy) error
+	disconnectProxyFunc                      func(ctx context.Context, proxyID, sessionID string) error
+	updateProxyHeartbeatFunc                 func(ctx context.Context, p *proxy.Proxy) error
+	getActiveProxyClusterAddressesFunc       func(ctx context.Context) ([]string, error)
+	getActiveProxyClusterAddressesForAccFunc func(ctx context.Context, accountID string) ([]string, error)
+	cleanupStaleProxiesFunc                  func(ctx context.Context, d time.Duration) error
+	getProxyByAccountIDFunc                  func(ctx context.Context, accountID string) (*proxy.Proxy, error)
+	countProxiesByAccountIDFunc              func(ctx context.Context, accountID string) (int64, error)
+	isClusterAddressConflictingFunc          func(ctx context.Context, clusterAddress, accountID string) (bool, error)
+	deleteAccountClusterFunc                 func(ctx context.Context, clusterAddress, accountID string) error
 }
 
 func (m *mockStore) SaveProxy(ctx context.Context, p *proxy.Proxy) error {
@@ -57,7 +57,7 @@ func (m *mockStore) GetActiveProxyClusterAddressesForAccount(ctx context.Context
 	}
 	return nil, nil
 }
-func (m *mockStore) GetActiveProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
+func (m *mockStore) GetProxyClusters(_ context.Context, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 func (m *mockStore) CleanupStaleProxies(ctx context.Context, d time.Duration) error {
@@ -99,6 +99,9 @@ func (m *mockStore) GetClusterRequireSubdomain(_ context.Context, _ string) *boo
 func (m *mockStore) GetClusterSupportsCrowdSec(_ context.Context, _ string) *bool {
 	return nil
 }
+func (m *mockStore) GetClusterSupportsPrivate(_ context.Context, _ string) *bool {
+	return nil
+}
 
 func newTestManager(s store) *Manager {
 	meter := noop.NewMeterProvider().Meter("test")

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

@@ -92,6 +92,20 @@ func (mr *MockManagerMockRecorder) ClusterSupportsCrowdSec(ctx, clusterAddr inte
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsCrowdSec", reflect.TypeOf((*MockManager)(nil).ClusterSupportsCrowdSec), ctx, clusterAddr)
 }
 
+// ClusterSupportsPrivate mocks base method.
+func (m *MockManager) ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "ClusterSupportsPrivate", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// ClusterSupportsPrivate indicates an expected call of ClusterSupportsPrivate.
+func (mr *MockManagerMockRecorder) ClusterSupportsPrivate(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "ClusterSupportsPrivate", reflect.TypeOf((*MockManager)(nil).ClusterSupportsPrivate), ctx, clusterAddr)
+}
+
 // Connect mocks base method.
 func (m *MockManager) Connect(ctx context.Context, proxyID, sessionID, clusterAddress, ipAddress string, accountID *string, capabilities *Capabilities) (*Proxy, error) {
 	m.ctrl.T.Helper()

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

@@ -20,6 +20,9 @@ type Capabilities struct {
 	RequireSubdomain *bool
 	// SupportsCrowdsec indicates whether this proxy has CrowdSec configured.
 	SupportsCrowdsec *bool
+	// Private indicates whether this proxy supports inbound access via Wireguard
+	// tunnel and netbird-only authentication policies
+	Private *bool
 }
 
 // Proxy represents a reverse proxy instance
@@ -42,10 +45,34 @@ func (Proxy) TableName() string {
 	return "proxies"
 }
 
+// ClusterType is the source of a proxy cluster.
+type ClusterType string
+
+const (
+	// ClusterTypeAccount is a cluster operated by the account itself (BYOP) —
+	// at least one proxy row in the cluster carries a non-NULL account_id.
+	ClusterTypeAccount ClusterType = "account"
+	// ClusterTypeShared is a cluster operated by NetBird and shared across
+	// accounts — all proxy rows in the cluster have account_id IS NULL.
+	ClusterTypeShared ClusterType = "shared"
+)
+
 // Cluster represents a group of proxy nodes serving the same address.
+//
+// Online and ConnectedProxies derive from the same 2-min active window
+// the rest of the module uses, but Cluster rows are not gated on it —
+// the cluster listing surfaces offline clusters too so operators can
+// see and clean them up. The 1-hour heartbeat reaper still bounds the
+// table eventually.
 type Cluster struct {
 	ID               string
 	Address          string
+	Type             ClusterType
+	Online           bool
 	ConnectedProxies int
-	SelfHosted       bool
+	// *bool: nil = no proxy reported the capability; the dashboard renders that as unknown.
+	SupportsCustomPorts *bool
+	RequireSubdomain    *bool
+	SupportsCrowdSec    *bool
+	Private             *bool
 }

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

@@ -9,7 +9,7 @@ import (
 )
 
 type Manager interface {
-	GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error)
+	GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error)
 	DeleteAccountCluster(ctx context.Context, accountID, userID, clusterAddress string) error
 	GetAllServices(ctx context.Context, accountID, userID string) ([]*Service, error)
 	GetService(ctx context.Context, accountID, userID, serviceID string) (*Service, error)

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

@@ -65,20 +65,6 @@ func (mr *MockManagerMockRecorder) CreateServiceFromPeer(ctx, accountID, peerID,
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateServiceFromPeer", reflect.TypeOf((*MockManager)(nil).CreateServiceFromPeer), ctx, accountID, peerID, req)
 }
 
-// DeleteAllServices mocks base method.
-func (m *MockManager) DeleteAllServices(ctx context.Context, accountID, userID string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "DeleteAllServices", ctx, accountID, userID)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// DeleteAllServices indicates an expected call of DeleteAllServices.
-func (mr *MockManagerMockRecorder) DeleteAllServices(ctx, accountID, userID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAllServices", reflect.TypeOf((*MockManager)(nil).DeleteAllServices), ctx, accountID, userID)
-}
-
 // DeleteAccountCluster mocks base method.
 func (m *MockManager) DeleteAccountCluster(ctx context.Context, accountID, userID, clusterAddress string) error {
 	m.ctrl.T.Helper()
@@ -93,6 +79,20 @@ func (mr *MockManagerMockRecorder) DeleteAccountCluster(ctx, accountID, userID,
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockManager)(nil).DeleteAccountCluster), ctx, accountID, userID, clusterAddress)
 }
 
+// DeleteAllServices mocks base method.
+func (m *MockManager) DeleteAllServices(ctx context.Context, accountID, userID string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "DeleteAllServices", ctx, accountID, userID)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// DeleteAllServices indicates an expected call of DeleteAllServices.
+func (mr *MockManagerMockRecorder) DeleteAllServices(ctx, accountID, userID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAllServices", reflect.TypeOf((*MockManager)(nil).DeleteAllServices), ctx, accountID, userID)
+}
+
 // DeleteService mocks base method.
 func (m *MockManager) DeleteService(ctx context.Context, accountID, userID, serviceID string) error {
 	m.ctrl.T.Helper()
@@ -122,21 +122,6 @@ func (mr *MockManagerMockRecorder) GetAccountServices(ctx, accountID interface{}
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAccountServices", reflect.TypeOf((*MockManager)(nil).GetAccountServices), ctx, accountID)
 }
 
-// GetActiveClusters mocks base method.
-func (m *MockManager) GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetActiveClusters", ctx, accountID, userID)
-	ret0, _ := ret[0].([]proxy.Cluster)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// GetActiveClusters indicates an expected call of GetActiveClusters.
-func (mr *MockManagerMockRecorder) GetActiveClusters(ctx, accountID, userID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveClusters", reflect.TypeOf((*MockManager)(nil).GetActiveClusters), ctx, accountID, userID)
-}
-
 // GetAllServices mocks base method.
 func (m *MockManager) GetAllServices(ctx context.Context, accountID, userID string) ([]*Service, error) {
 	m.ctrl.T.Helper()
@@ -152,19 +137,19 @@ func (mr *MockManagerMockRecorder) GetAllServices(ctx, accountID, userID interfa
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAllServices", reflect.TypeOf((*MockManager)(nil).GetAllServices), ctx, accountID, userID)
 }
 
-// GetServiceByDomain mocks base method.
-func (m *MockManager) GetServiceByDomain(ctx context.Context, domain string) (*Service, error) {
+// GetClusters mocks base method.
+func (m *MockManager) GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetServiceByDomain", ctx, domain)
-	ret0, _ := ret[0].(*Service)
+	ret := m.ctrl.Call(m, "GetClusters", ctx, accountID, userID)
+	ret0, _ := ret[0].([]proxy.Cluster)
 	ret1, _ := ret[1].(error)
 	return ret0, ret1
 }
 
-// GetServiceByDomain indicates an expected call of GetServiceByDomain.
-func (mr *MockManagerMockRecorder) GetServiceByDomain(ctx, domain interface{}) *gomock.Call {
+// GetClusters indicates an expected call of GetClusters.
+func (mr *MockManagerMockRecorder) GetClusters(ctx, accountID, userID interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetServiceByDomain", reflect.TypeOf((*MockManager)(nil).GetServiceByDomain), ctx, domain)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusters", reflect.TypeOf((*MockManager)(nil).GetClusters), ctx, accountID, userID)
 }
 
 // GetGlobalServices mocks base method.
@@ -197,6 +182,21 @@ func (mr *MockManagerMockRecorder) GetService(ctx, accountID, userID, serviceID
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetService", reflect.TypeOf((*MockManager)(nil).GetService), ctx, accountID, userID, serviceID)
 }
 
+// GetServiceByDomain mocks base method.
+func (m *MockManager) GetServiceByDomain(ctx context.Context, domain string) (*Service, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetServiceByDomain", ctx, domain)
+	ret0, _ := ret[0].(*Service)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetServiceByDomain indicates an expected call of GetServiceByDomain.
+func (mr *MockManagerMockRecorder) GetServiceByDomain(ctx, domain interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetServiceByDomain", reflect.TypeOf((*MockManager)(nil).GetServiceByDomain), ctx, domain)
+}
+
 // GetServiceByID mocks base method.
 func (m *MockManager) GetServiceByID(ctx context.Context, accountID, serviceID string) (*Service, error) {
 	m.ctrl.T.Helper()

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

@@ -187,7 +187,7 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 		return
 	}
 
-	clusters, err := h.manager.GetActiveClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
+	clusters, err := h.manager.GetClusters(r.Context(), userAuth.AccountId, userAuth.UserId)
 	if err != nil {
 		util.WriteError(r.Context(), err, w)
 		return
@@ -196,10 +196,15 @@ func (h *handler) getClusters(w http.ResponseWriter, r *http.Request) {
 	apiClusters := make([]api.ProxyCluster, 0, len(clusters))
 	for _, c := range clusters {
 		apiClusters = append(apiClusters, api.ProxyCluster{
-			Id:               c.ID,
-			Address:          c.Address,
-			ConnectedProxies: c.ConnectedProxies,
-			SelfHosted:       c.SelfHosted,
+			Id:                  c.ID,
+			Address:             c.Address,
+			Type:                api.ProxyClusterType(c.Type),
+			Online:              c.Online,
+			ConnectedProxies:    c.ConnectedProxies,
+			SupportsCustomPorts: c.SupportsCustomPorts,
+			RequireSubdomain:    c.RequireSubdomain,
+			SupportsCrowdsec:    c.SupportsCrowdSec,
+			Private:             c.Private,
 		})
 	}
 

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

@@ -81,6 +81,8 @@ type ClusterDeriver interface {
 type CapabilityProvider interface {
 	ClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	ClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool
+	ClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool
 }
 
 type Manager struct {
@@ -112,8 +114,12 @@ func (m *Manager) StartExposeReaper(ctx context.Context) {
 	m.exposeReaper.StartExposeReaper(ctx)
 }
 
-// GetActiveClusters returns all active proxy clusters with their connected proxy count.
-func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
+// GetClusters returns every proxy cluster visible to the account
+// (shared + its own BYOP), regardless of whether any proxy in the
+// cluster is currently heartbeating. Each cluster is enriched with the
+// capability flags reported by its active proxies so the dashboard can
+// render feature support without a second round-trip.
+func (m *Manager) GetClusters(ctx context.Context, accountID, userID string) ([]proxy.Cluster, error) {
 	ok, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.Services, operations.Read)
 	if err != nil {
 		return nil, status.NewPermissionValidationError(err)
@@ -122,7 +128,19 @@ func (m *Manager) GetActiveClusters(ctx context.Context, accountID, userID strin
 		return nil, status.NewPermissionDeniedError()
 	}
 
-	return m.store.GetActiveProxyClusters(ctx, accountID)
+	clusters, err := m.store.GetProxyClusters(ctx, accountID)
+	if err != nil {
+		return nil, err
+	}
+
+	for i := range clusters {
+		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].Private = m.capabilities.ClusterSupportsPrivate(ctx, clusters[i].Address)
+	}
+
+	return clusters, nil
 }
 
 // DeleteAccountCluster removes all proxy registrations for the given cluster address
@@ -192,6 +210,9 @@ func (m *Manager) replaceHostByLookup(ctx context.Context, accountID string, s *
 			target.Host = resource.Domain
 		case service.TargetTypeSubnet:
 			// For subnets we do not do any lookups on the resource
+		case service.TargetTypeCluster:
+			// Cluster targets carry the upstream address on target_id; the
+			// proxy resolves the destination at request time.
 		default:
 			return fmt.Errorf("unknown target type: %s", target.TargetType)
 		}
@@ -306,6 +327,10 @@ func (m *Manager) validateSubdomainRequirement(ctx context.Context, domain, clus
 func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
+		return err
+	}
+
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if svc.Domain != "" {
 			if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, ""); err != nil {
@@ -321,10 +346,6 @@ func (m *Manager) persistNewService(ctx context.Context, accountID string, svc *
 			return err
 		}
 
-		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
-			return err
-		}
-
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -435,6 +456,10 @@ func (m *Manager) assignPort(ctx context.Context, tx store.Store, cluster string
 func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, peerID string, svc *service.Service) error {
 	customPorts := m.clusterCustomPorts(ctx, svc)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, svc.Targets); err != nil {
+		return err
+	}
+
 	return m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		if err := m.validateEphemeralPreconditions(ctx, transaction, accountID, peerID, svc); err != nil {
 			return err
@@ -448,10 +473,6 @@ func (m *Manager) persistNewEphemeralService(ctx context.Context, accountID, pee
 			return err
 		}
 
-		if err := validateTargetReferences(ctx, transaction, accountID, svc.Targets); err != nil {
-			return err
-		}
-
 		if err := transaction.CreateService(ctx, svc); err != nil {
 			return fmt.Errorf("create service: %w", err)
 		}
@@ -552,10 +573,22 @@ func (m *Manager) persistServiceUpdate(ctx context.Context, accountID string, se
 	svcForCaps.ProxyCluster = effectiveCluster
 	customPorts := m.clusterCustomPorts(ctx, &svcForCaps)
 
+	if err := validateTargetReferences(ctx, m.store, accountID, service.Targets); err != nil {
+		return nil, err
+	}
+
+	// Validate subdomain requirement *before* the transaction: the underlying
+	// capability lookup talks to the main DB pool, and SQLite's single-connection
+	// pool would self-deadlock if this ran while the tx already held the only
+	// connection.
+	if err := m.validateSubdomainRequirement(ctx, service.Domain, effectiveCluster); err != nil {
+		return nil, err
+	}
+
 	var updateInfo serviceUpdateInfo
 
 	err = m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts)
+		return m.executeServiceUpdate(ctx, transaction, accountID, service, &updateInfo, customPorts, effectiveCluster)
 	})
 
 	return &updateInfo, err
@@ -585,7 +618,7 @@ func (m *Manager) resolveEffectiveCluster(ctx context.Context, accountID string,
 	return existing.ProxyCluster, nil
 }
 
-func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool) error {
+func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.Store, accountID string, service *service.Service, updateInfo *serviceUpdateInfo, customPorts *bool, effectiveCluster string) error {
 	existingService, err := transaction.GetServiceByID(ctx, store.LockingStrengthUpdate, accountID, service.ID)
 	if err != nil {
 		return err
@@ -603,17 +636,13 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	updateInfo.domainChanged = existingService.Domain != service.Domain
 
 	if updateInfo.domainChanged {
-		if err := m.handleDomainChange(ctx, transaction, accountID, service); err != nil {
+		if err := m.handleDomainChange(ctx, transaction, service, effectiveCluster); err != nil {
 			return err
 		}
 	} else {
 		service.ProxyCluster = existingService.ProxyCluster
 	}
 
-	if err := m.validateSubdomainRequirement(ctx, service.Domain, service.ProxyCluster); err != nil {
-		return err
-	}
-
 	m.preserveExistingAuthSecrets(service, existingService)
 	if err := validateHeaderAuthValues(service.Auth.HeaderAuths); err != nil {
 		return err
@@ -628,9 +657,6 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	if err := m.checkPortConflict(ctx, transaction, service); err != nil {
 		return err
 	}
-	if err := validateTargetReferences(ctx, transaction, accountID, service.Targets); err != nil {
-		return err
-	}
 	if err := transaction.UpdateService(ctx, service); err != nil {
 		return fmt.Errorf("update service: %w", err)
 	}
@@ -638,20 +664,18 @@ func (m *Manager) executeServiceUpdate(ctx context.Context, transaction store.St
 	return nil
 }
 
-func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, accountID string, svc *service.Service) error {
+// handleDomainChange validates the new domain is free inside the transaction
+// and applies the pre-resolved cluster (computed outside the tx by
+// resolveEffectiveCluster). It must NOT call clusterDeriver here: that talks
+// to the main DB pool and would self-deadlock under SQLite (max_open_conns=1)
+// because the transaction already holds the only connection.
+func (m *Manager) handleDomainChange(ctx context.Context, transaction store.Store, svc *service.Service, effectiveCluster string) error {
 	if err := m.checkDomainAvailable(ctx, transaction, svc.Domain, svc.ID); err != nil {
 		return err
 	}
-
-	if m.clusterDeriver != nil {
-		newCluster, err := m.clusterDeriver.DeriveClusterFromDomain(ctx, accountID, svc.Domain)
-		if err != nil {
-			log.WithError(err).Warnf("could not derive cluster from domain %s", svc.Domain)
-		} else {
-			svc.ProxyCluster = newCluster
-		}
+	if effectiveCluster != "" {
+		svc.ProxyCluster = effectiveCluster
 	}
-
 	return nil
 }
 
@@ -760,6 +784,10 @@ func validateTargetReferences(ctx context.Context, transaction store.Store, acco
 			if err := validateResourceTarget(ctx, transaction, accountID, target); err != nil {
 				return err
 			}
+		case service.TargetTypeCluster:
+			if err := validateClusterTarget(target); err != nil {
+				return err
+			}
 		default:
 			return status.Errorf(status.InvalidArgument, "unknown target type %q for target %q", target.TargetType, target.TargetId)
 		}
@@ -767,6 +795,13 @@ func validateTargetReferences(ctx context.Context, transaction store.Store, acco
 	return nil
 }
 
+func validateClusterTarget(target *service.Target) error {
+	if !target.Options.DirectUpstream {
+		return status.Errorf(status.InvalidArgument, "cluster target %s has direct upstream disabled", target.Host)
+	}
+	return nil
+}
+
 func validatePeerTarget(ctx context.Context, transaction store.Store, accountID string, target *service.Target) error {
 	if _, err := transaction.GetPeerByID(ctx, store.LockingStrengthShare, accountID, target.TargetId); err != nil {
 		if sErr, ok := status.FromError(err); ok && sErr.Type() == status.NotFound {
@@ -943,12 +978,14 @@ func (m *Manager) ReloadAllServicesForAccount(ctx context.Context, accountID str
 		return fmt.Errorf("failed to get services: %w", err)
 	}
 
+	oidcCfg := m.proxyController.GetOIDCValidationConfig()
+
 	for _, s := range services {
 		err = m.replaceHostByLookup(ctx, accountID, s)
 		if err != nil {
 			return fmt.Errorf("failed to replace host by lookup for service %s: %w", s.ID, err)
 		}
-		m.proxyController.SendServiceUpdateToCluster(ctx, accountID, s.ToProtoMapping(service.Update, "", m.proxyController.GetOIDCValidationConfig()), s.ProxyCluster)
+		m.proxyController.SendServiceUpdateToCluster(ctx, accountID, s.ToProtoMapping(service.Update, "", oidcCfg), s.ProxyCluster)
 	}
 
 	return nil

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

@@ -1344,3 +1344,66 @@ func TestValidateSubdomainRequirement(t *testing.T) {
 		})
 	}
 }
+
+func TestValidateTargetReferences_ClusterTargetSkipsLookup(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	// No peer or resource lookups must be issued for cluster targets.
+	targets := []*rpservice.Target{
+		{
+			TargetId:   "eu.proxy.netbird.io",
+			TargetType: rpservice.TargetTypeCluster,
+			Options:    rpservice.TargetOptions{DirectUpstream: true},
+		},
+	}
+	require.NoError(t, validateTargetReferences(ctx, mockStore, accountID, targets), "cluster target must validate without store lookups")
+}
+
+// TestValidateTargetReferences_ClusterTargetRequiresDirectUpstream pins the
+// store-side check that cluster targets must opt into the host-stack dial
+// path. Without DirectUpstream the proxy would route this target through
+// the embedded NetBird client and fail on every request.
+func TestValidateTargetReferences_ClusterTargetRequiresDirectUpstream(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	targets := []*rpservice.Target{
+		{
+			TargetId:   "eu.proxy.netbird.io",
+			TargetType: rpservice.TargetTypeCluster,
+			Host:       "backend.lan",
+		},
+	}
+	err := validateTargetReferences(ctx, mockStore, accountID, targets)
+	require.Error(t, err, "cluster target without direct_upstream must be rejected")
+	assert.ErrorContains(t, err, "direct upstream disabled")
+}
+
+func TestReplaceHostByLookup_SkipsClusterTarget(t *testing.T) {
+	ctx := context.Background()
+	ctrl := gomock.NewController(t)
+	mockStore := store.NewMockStore(ctrl)
+	accountID := "test-account"
+
+	mgr := &Manager{store: mockStore}
+
+	svc := &rpservice.Service{
+		ID:        "svc-1",
+		AccountID: accountID,
+		Targets: []*rpservice.Target{
+			{
+				TargetId:   "eu.proxy.netbird.io",
+				TargetType: rpservice.TargetTypeCluster,
+				Host:       "127.0.0.1",
+			},
+		},
+	}
+
+	require.NoError(t, mgr.replaceHostByLookup(ctx, accountID, svc), "cluster target must not trigger peer/resource lookup")
+	assert.Equal(t, "127.0.0.1", svc.Targets[0].Host, "operator-supplied host must be preserved for cluster target")
+}

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

@@ -45,10 +45,11 @@ const (
 	StatusCertificateFailed  Status = "certificate_failed"
 	StatusError              Status = "error"
 
-	TargetTypePeer   TargetType = "peer"
-	TargetTypeHost   TargetType = "host"
-	TargetTypeDomain TargetType = "domain"
-	TargetTypeSubnet TargetType = "subnet"
+	TargetTypePeer    TargetType = "peer"
+	TargetTypeHost    TargetType = "host"
+	TargetTypeDomain  TargetType = "domain"
+	TargetTypeSubnet  TargetType = "subnet"
+	TargetTypeCluster TargetType = "cluster"
 
 	SourcePermanent = "permanent"
 	SourceEphemeral = "ephemeral"
@@ -60,6 +61,11 @@ type TargetOptions struct {
 	SessionIdleTimeout time.Duration     `json:"session_idle_timeout,omitempty"`
 	PathRewrite        PathRewriteMode   `json:"path_rewrite,omitempty"`
 	CustomHeaders      map[string]string `gorm:"serializer:json" json:"custom_headers,omitempty"`
+	// DirectUpstream bypasses the proxy's embedded NetBird client and dials
+	// the target via the proxy host's network stack. Useful for upstreams
+	// reachable without WireGuard (public APIs, LAN services, localhost
+	// sidecars). Default false.
+	DirectUpstream bool `json:"direct_upstream,omitempty"`
 }
 
 type Target struct {
@@ -67,7 +73,7 @@ type Target struct {
 	AccountID     string        `gorm:"index:idx_target_account;not null" json:"-"`
 	ServiceID     string        `gorm:"index:idx_service_targets;not null" json:"-"`
 	Path          *string       `json:"path,omitempty"`
-	Host          string        `json:"host"` // the Host field is only used for subnet targets, otherwise ignored
+	Host          string        `json:"host"`
 	Port          uint16        `gorm:"index:idx_target_port" json:"port"`
 	Protocol      string        `gorm:"index:idx_target_protocol" json:"protocol"`
 	TargetId      string        `gorm:"index:idx_target_id" json:"target_id"`
@@ -200,6 +206,10 @@ type Service struct {
 	Mode             string `gorm:"default:'http'"`
 	ListenPort       uint16
 	PortAutoAssigned bool
+	// Private marks the service as NetBird-only: auth via ValidateTunnelPeer against AccessGroups instead of SSO. HTTP-only.
+	Private bool
+	// AccessGroups is the group ID allowlist for inbound peers on private services. Mutually exclusive with bearer SSO.
+	AccessGroups []string `json:"access_groups,omitempty" gorm:"serializer:json"`
 }
 
 // InitNewRecord generates a new unique ID and resets metadata for a newly created
@@ -299,6 +309,12 @@ func (s *Service) ToAPIResponse() *api.Service {
 		Mode:               &mode,
 		ListenPort:         &listenPort,
 		PortAutoAssigned:   &s.PortAutoAssigned,
+		Private:            &s.Private,
+	}
+
+	if len(s.AccessGroups) > 0 {
+		groups := append([]string(nil), s.AccessGroups...)
+		resp.AccessGroups = &groups
 	}
 
 	if s.ProxyCluster != "" {
@@ -308,6 +324,7 @@ func (s *Service) ToAPIResponse() *api.Service {
 	return resp
 }
 
+// ToProtoMapping converts the service into the wire format the proxy consumes.
 func (s *Service) ToProtoMapping(operation Operation, authToken string, oidcConfig proxy.OIDCValidationConfig) *proto.ProxyMapping {
 	pathMappings := s.buildPathMappings()
 
@@ -349,6 +366,7 @@ func (s *Service) ToProtoMapping(operation Operation, authToken string, oidcConf
 		RewriteRedirects: s.RewriteRedirects,
 		Mode:             s.Mode,
 		ListenPort:       int32(s.ListenPort), //nolint:gosec
+		Private:          s.Private,
 	}
 
 	if r := restrictionsToProto(s.Restrictions); r != nil {
@@ -381,13 +399,14 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 		}
 
 		// HTTP/HTTPS: build full URL
+		hostNoBrackets := strings.TrimSuffix(strings.TrimPrefix(target.Host, "["), "]")
 		targetURL := url.URL{
 			Scheme: target.Protocol,
-			Host:   target.Host,
+			Host:   bracketIPv6Host(hostNoBrackets),
 			Path:   "/",
 		}
 		if target.Port > 0 && !isDefaultPort(target.Protocol, target.Port) {
-			targetURL.Host = net.JoinHostPort(targetURL.Host, strconv.FormatUint(uint64(target.Port), 10))
+			targetURL.Host = net.JoinHostPort(hostNoBrackets, strconv.FormatUint(uint64(target.Port), 10))
 		}
 
 		path := "/"
@@ -405,6 +424,19 @@ func (s *Service) buildPathMappings() []*proto.PathMapping {
 	return pathMappings
 }
 
+// bracketIPv6Host wraps host in square brackets when it is an IPv6 literal, as
+// required for the Host field of net/url.URL (RFC 3986 §3.2.2). v4-mapped IPv6
+// addresses are bracketed too since their textual form contains colons.
+func bracketIPv6Host(host string) string {
+	if strings.HasPrefix(host, "[") {
+		return host
+	}
+	if addr, err := netip.ParseAddr(host); err == nil && addr.Is6() {
+		return "[" + host + "]"
+	}
+	return host
+}
+
 func operationToProtoType(op Operation) proto.ProxyMappingUpdateType {
 	switch op {
 	case Create:
@@ -441,7 +473,8 @@ func pathRewriteToProto(mode PathRewriteMode) proto.PathRewriteMode {
 }
 
 func targetOptionsToAPI(opts TargetOptions) *api.ServiceTargetOptions {
-	if !opts.SkipTLSVerify && opts.RequestTimeout == 0 && opts.SessionIdleTimeout == 0 && opts.PathRewrite == "" && len(opts.CustomHeaders) == 0 {
+	if !opts.SkipTLSVerify && opts.RequestTimeout == 0 && opts.SessionIdleTimeout == 0 &&
+		opts.PathRewrite == "" && len(opts.CustomHeaders) == 0 && !opts.DirectUpstream {
 		return nil
 	}
 	apiOpts := &api.ServiceTargetOptions{}
@@ -463,17 +496,22 @@ func targetOptionsToAPI(opts TargetOptions) *api.ServiceTargetOptions {
 	if len(opts.CustomHeaders) > 0 {
 		apiOpts.CustomHeaders = &opts.CustomHeaders
 	}
+	if opts.DirectUpstream {
+		apiOpts.DirectUpstream = &opts.DirectUpstream
+	}
 	return apiOpts
 }
 
 func targetOptionsToProto(opts TargetOptions) *proto.PathTargetOptions {
-	if !opts.SkipTLSVerify && opts.PathRewrite == "" && opts.RequestTimeout == 0 && len(opts.CustomHeaders) == 0 {
+	if !opts.SkipTLSVerify && opts.PathRewrite == "" && opts.RequestTimeout == 0 &&
+		len(opts.CustomHeaders) == 0 && !opts.DirectUpstream {
 		return nil
 	}
 	popts := &proto.PathTargetOptions{
-		SkipTlsVerify: opts.SkipTLSVerify,
-		PathRewrite:   pathRewriteToProto(opts.PathRewrite),
-		CustomHeaders: opts.CustomHeaders,
+		SkipTlsVerify:  opts.SkipTLSVerify,
+		PathRewrite:    pathRewriteToProto(opts.PathRewrite),
+		CustomHeaders:  opts.CustomHeaders,
+		DirectUpstream: opts.DirectUpstream,
 	}
 	if opts.RequestTimeout != 0 {
 		popts.RequestTimeout = durationpb.New(opts.RequestTimeout)
@@ -523,6 +561,9 @@ func targetOptionsFromAPI(idx int, o *api.ServiceTargetOptions) (TargetOptions,
 	if o.CustomHeaders != nil {
 		opts.CustomHeaders = *o.CustomHeaders
 	}
+	if o.DirectUpstream != nil {
+		opts.DirectUpstream = *o.DirectUpstream
+	}
 	return opts, nil
 }
 
@@ -537,6 +578,14 @@ func (s *Service) FromAPIRequest(req *api.ServiceRequest, accountID string) erro
 	if req.ListenPort != nil {
 		s.ListenPort = uint16(*req.ListenPort) //nolint:gosec
 	}
+	if req.Private != nil {
+		s.Private = *req.Private
+	}
+	if req.AccessGroups != nil {
+		s.AccessGroups = append([]string(nil), *req.AccessGroups...)
+	} else {
+		s.AccessGroups = nil
+	}
 
 	targets, err := targetsFromAPI(accountID, req.Targets)
 	if err != nil {
@@ -726,6 +775,9 @@ func (s *Service) Validate() error {
 	if err := validateAccessRestrictions(&s.Restrictions); err != nil {
 		return err
 	}
+	if err := s.validatePrivateRequirements(); err != nil {
+		return err
+	}
 
 	switch s.Mode {
 	case ModeHTTP:
@@ -739,6 +791,23 @@ func (s *Service) Validate() error {
 	}
 }
 
+// validatePrivateRequirements enforces the private-service contract: HTTP mode, ≥1 access group, no bearer auth.
+func (s *Service) validatePrivateRequirements() error {
+	if !s.Private {
+		return nil
+	}
+	if s.Mode != "" && s.Mode != ModeHTTP {
+		return fmt.Errorf("private services only support HTTP mode, got %q", s.Mode)
+	}
+	if len(s.AccessGroups) == 0 {
+		return errors.New("private services require at least one access group")
+	}
+	if s.Auth.BearerAuth != nil && s.Auth.BearerAuth.Enabled {
+		return errors.New("private services cannot enable bearer auth (SSO): NetBird-only access and SSO are mutually exclusive")
+	}
+	return nil
+}
+
 func (s *Service) validateHTTPMode() error {
 	if s.Domain == "" {
 		return errors.New("service domain is required")
@@ -785,11 +854,21 @@ func (s *Service) validateHTTPTargets() error {
 	for i, target := range s.Targets {
 		switch target.TargetType {
 		case TargetTypePeer, TargetTypeHost, TargetTypeDomain:
-			// host field will be ignored
+			// Host is normally overwritten by replaceHostByLookup with the
+			// resolved peer IP / resource address; operator-supplied values
+			// are honored only when DirectUpstream is set. Validate the
+			// override here so misconfigured hosts fail fast at API time.
+			if err := validateDirectUpstreamHost(i, target); err != nil {
+				return err
+			}
 		case TargetTypeSubnet:
 			if target.Host == "" {
 				return fmt.Errorf("target %d has empty host but target_type is %q", i, target.TargetType)
 			}
+		case TargetTypeCluster:
+			if err := validateClusterTarget(i, target); err != nil {
+				return err
+			}
 		default:
 			return fmt.Errorf("target %d has invalid target_type %q", i, target.TargetType)
 		}
@@ -807,25 +886,67 @@ func (s *Service) validateHTTPTargets() error {
 	return nil
 }
 
+// validateClusterTarget cluster targets should not have empty hosts and should have direct upstream enabled.
+func validateClusterTarget(idx int, target *Target) error {
+	host := strings.TrimSpace(target.Host)
+	if host == "" {
+		return fmt.Errorf("target %d: has empty host", idx)
+	}
+	if !target.Options.DirectUpstream {
+		return fmt.Errorf("target %d: %s has direct upstream disabled", idx, target.Host)
+	}
+	return validateDirectUpstreamHost(idx, target)
+}
+
+// validateDirectUpstreamHost validates the operator-supplied Host on a
+// peer/host/domain target when DirectUpstream is set. Empty Host is
+// allowed — the lookup fills in the default peer IP / resource address.
+// Without DirectUpstream the Host value is silently overwritten by
+// replaceHostByLookup, so we don't validate it (preserves the historical
+// behaviour where APIs accepted any value and dropped it). Non-empty
+// Host with DirectUpstream must look like a hostname or IP and must
+// not carry a port (port lives on Target.Port).
+func validateDirectUpstreamHost(idx int, target *Target) error {
+	if !target.Options.DirectUpstream {
+		return nil
+	}
+	host := strings.TrimSpace(target.Host)
+	if host == "" {
+		return nil
+	}
+	if strings.ContainsAny(host, " \t/") {
+		return fmt.Errorf("target %d: host %q contains invalid characters", idx, host)
+	}
+	if _, _, err := net.SplitHostPort(host); err == nil {
+		return fmt.Errorf("target %d: host %q must not include a port (set target.port instead)", idx, host)
+	}
+	return nil
+}
+
 func (s *Service) validateL4Target(target *Target) error {
 	// L4 services have a single target; per-target disable is meaningless
 	// (use the service-level Enabled flag instead). Force it on so that
 	// buildPathMappings always includes the target in the proto.
 	target.Enabled = true
 
-	if target.Port == 0 {
-		return errors.New("target port is required for L4 services")
-	}
 	if target.TargetId == "" {
 		return errors.New("target_id is required for L4 services")
 	}
+	if target.TargetType != TargetTypeCluster && target.Port == 0 {
+		return errors.New("target port is required for L4 services")
+	}
 	switch target.TargetType {
 	case TargetTypePeer, TargetTypeHost, TargetTypeDomain:
-		// OK
+		if err := validateDirectUpstreamHost(0, target); err != nil {
+			return err
+		}
 	case TargetTypeSubnet:
 		if target.Host == "" {
 			return errors.New("target host is required for subnet targets")
 		}
+	case TargetTypeCluster:
+		// target_id carries the cluster address; the proxy resolves
+		// the upstream at request time.
 	default:
 		return fmt.Errorf("invalid target_type %q for L4 service", target.TargetType)
 	}
@@ -1160,6 +1281,11 @@ func (s *Service) Copy() *Service {
 		}
 	}
 
+	var accessGroups []string
+	if len(s.AccessGroups) > 0 {
+		accessGroups = append([]string(nil), s.AccessGroups...)
+	}
+
 	return &Service{
 		ID:                s.ID,
 		AccountID:         s.AccountID,
@@ -1181,6 +1307,8 @@ func (s *Service) Copy() *Service {
 		Mode:              s.Mode,
 		ListenPort:        s.ListenPort,
 		PortAutoAssigned:  s.PortAutoAssigned,
+		Private:           s.Private,
+		AccessGroups:      accessGroups,
 	}
 }
 

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

@@ -12,6 +12,7 @@ import (
 
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
 	"github.com/netbirdio/netbird/shared/hash/argon2id"
+	"github.com/netbirdio/netbird/shared/management/http/api"
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
@@ -351,6 +352,83 @@ func TestToProtoMapping_PortInTargetURL(t *testing.T) {
 			port:       80,
 			wantTarget: "https://10.0.0.1:80/",
 		},
+		{
+			name:       "domain host without port is unchanged",
+			protocol:   "http",
+			host:       "example.com",
+			port:       0,
+			wantTarget: "http://example.com/",
+		},
+		{
+			name:       "domain host with non-default port is unchanged",
+			protocol:   "http",
+			host:       "example.com",
+			port:       8080,
+			wantTarget: "http://example.com:8080/",
+		},
+		{
+			name:       "ipv6 host without port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       0,
+			wantTarget: "http://[fb00:cafe:1::3]/",
+		},
+		{
+			name:       "ipv6 host with default port omits port and brackets host",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       80,
+			wantTarget: "http://[fb00:cafe:1::3]/",
+		},
+		{
+			name:       "ipv6 host with non-default port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1::3",
+			port:       8080,
+			wantTarget: "http://[fb00:cafe:1::3]:8080/",
+		},
+		{
+			name:       "ipv6 loopback without port is bracketed",
+			protocol:   "http",
+			host:       "::1",
+			port:       0,
+			wantTarget: "http://[::1]/",
+		},
+		{
+			name:       "ipv6 host with 5-digit port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe::1",
+			port:       18080,
+			wantTarget: "http://[fb00:cafe::1]:18080/",
+		},
+		{
+			name:       "pre-bracketed ipv6 without port stays single-bracketed",
+			protocol:   "http",
+			host:       "[fb00:cafe::1]",
+			port:       0,
+			wantTarget: "http://[fb00:cafe::1]/",
+		},
+		{
+			name:       "pre-bracketed ipv6 with port is not double-bracketed",
+			protocol:   "http",
+			host:       "[fb00:cafe::1]",
+			port:       8080,
+			wantTarget: "http://[fb00:cafe::1]:8080/",
+		},
+		{
+			name:       "v4-mapped ipv6 host without port is bracketed",
+			protocol:   "http",
+			host:       "::ffff:10.0.0.1",
+			port:       0,
+			wantTarget: "http://[::ffff:10.0.0.1]/",
+		},
+		{
+			name:       "full-form 8-group ipv6 without port is bracketed",
+			protocol:   "http",
+			host:       "fb00:cafe:1:0:0:0:0:3",
+			port:       0,
+			wantTarget: "http://[fb00:cafe:1:0:0:0:0:3]/",
+		},
 	}
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
@@ -1039,3 +1117,191 @@ func TestValidate_HeaderAuths(t *testing.T) {
 		assert.Contains(t, err.Error(), "exceeds maximum length")
 	})
 }
+
+func TestValidate_HTTPClusterTarget(t *testing.T) {
+	rp := validProxy()
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	require.NoError(t, rp.Validate(), "HTTP cluster target with target_id, host, and direct_upstream must validate")
+}
+
+func TestValidate_HTTPClusterTarget_RequiresTargetId(t *testing.T) {
+	rp := validProxy()
+	rp.Targets = []*Target{{
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "empty target_id", "cluster target must reject empty target_id")
+}
+
+// TestValidate_HTTPClusterTarget_RequiresHost pins the new cluster-target
+// rule that operator-supplied Host is mandatory: cluster targets dial the
+// upstream via the host network stack (direct_upstream is implied), so an
+// empty Host leaves the proxy with nothing to dial.
+func TestValidate_HTTPClusterTarget_RequiresHost(t *testing.T) {
+	rp := validProxy()
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "empty host", "cluster target must reject empty host")
+}
+
+// TestValidate_HTTPClusterTarget_RequiresDirectUpstream pins the second
+// half of the cluster-target rule: DirectUpstream must be true so the
+// stdlib transport branch in MultiTransport is taken. Without it the
+// embedded NetBird client would try to dial the cluster address through
+// the WG tunnel, which is the wrong network for a cluster upstream.
+func TestValidate_HTTPClusterTarget_RequiresDirectUpstream(t *testing.T) {
+	rp := validProxy()
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "direct upstream disabled", "cluster target must reject direct_upstream=false")
+}
+
+func TestValidate_L4ClusterTarget(t *testing.T) {
+	rp := validProxy()
+	rp.Mode = ModeTCP
+	rp.ListenPort = 9000
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "tcp",
+		Enabled:    true,
+	}}
+	require.NoError(t, rp.Validate(), "L4 cluster target must validate without an explicit port")
+}
+
+func TestService_Copy_RoundtripsPrivate(t *testing.T) {
+	svc := validProxy()
+	svc.Private = true
+	svc.AccessGroups = []string{"grp-admins", "grp-ops"}
+	cp := svc.Copy()
+	require.NotNil(t, cp)
+	assert.True(t, cp.Private)
+	assert.Equal(t, []string{"grp-admins", "grp-ops"}, cp.AccessGroups)
+
+	cp.Private = false
+	assert.True(t, svc.Private)
+
+	cp.AccessGroups[0] = "grp-other"
+	assert.Equal(t, []string{"grp-admins", "grp-ops"}, svc.AccessGroups)
+}
+
+func TestService_APIRoundtrip_Private(t *testing.T) {
+	enabled := true
+	private := true
+	accessGroups := []string{"grp-admins"}
+	targets := []api.ServiceTarget{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: api.ServiceTargetTargetType("cluster"),
+		Protocol:   "http",
+		Port:       80,
+		Enabled:    true,
+	}}
+	req := &api.ServiceRequest{
+		Name:         "svc-private",
+		Domain:       "myapp.eu.proxy.netbird.io",
+		Enabled:      enabled,
+		Private:      &private,
+		AccessGroups: &accessGroups,
+		Targets:      &targets,
+	}
+
+	svc := &Service{}
+	require.NoError(t, svc.FromAPIRequest(req, "acc-1"))
+	assert.True(t, svc.Private)
+	assert.Equal(t, []string{"grp-admins"}, svc.AccessGroups)
+
+	resp := svc.ToAPIResponse()
+	require.NotNil(t, resp.Private)
+	assert.True(t, *resp.Private)
+	require.NotNil(t, resp.AccessGroups)
+	assert.Equal(t, []string{"grp-admins"}, *resp.AccessGroups)
+}
+
+func TestValidate_Private_RequiresAccessGroups(t *testing.T) {
+	rp := validProxy()
+	rp.Private = true
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "access group")
+}
+
+func TestValidate_Private_RejectsBearerAuth(t *testing.T) {
+	rp := validProxy()
+	rp.Private = true
+	rp.AccessGroups = []string{"grp-admins"}
+	rp.Auth.BearerAuth = &BearerAuthConfig{
+		Enabled:            true,
+		DistributionGroups: []string{"grp-sso"},
+	}
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "mutually exclusive")
+}
+
+func TestValidate_Private_AcceptsNonClusterTargets(t *testing.T) {
+	rp := validProxy()
+	rp.Private = true
+	rp.AccessGroups = []string{"grp-admins"}
+	require.NoError(t, rp.Validate())
+}
+
+func TestValidate_Private_AcceptsClusterTargetWithAccessGroups(t *testing.T) {
+	rp := validProxy()
+	rp.Private = true
+	rp.AccessGroups = []string{"grp-admins"}
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "http",
+		Host:       "backend.lan",
+		Options:    TargetOptions{DirectUpstream: true},
+		Enabled:    true,
+	}}
+	require.NoError(t, rp.Validate())
+}
+
+func TestValidate_Private_RejectsNonHTTPMode(t *testing.T) {
+	rp := validProxy()
+	rp.Private = true
+	rp.AccessGroups = []string{"grp-admins"}
+	rp.Mode = ModeTCP
+	rp.Targets = []*Target{{
+		TargetId:   "eu.proxy.netbird.io",
+		TargetType: TargetTypeCluster,
+		Protocol:   "tcp",
+		Enabled:    true,
+	}}
+	assert.ErrorContains(t, rp.Validate(), "HTTP")
+}

management/internals/modules/reverseproxy/sessionkey/sessionkey.go

@@ -20,6 +20,20 @@ type KeyPair struct {
 type Claims struct {
 	jwt.RegisteredClaims
 	Method auth.Method `json:"method"`
+	// Email is the calling user's email address. Carried so the
+	// proxy can stamp identity on upstream requests (e.g.
+	// x-litellm-end-user-id) without an extra management
+	// round-trip on every cookie-bearing request.
+	Email string `json:"email,omitempty"`
+	// Groups carries the user's group IDs so the proxy can stamp them
+	// onto upstream requests (X-NetBird-Groups) from the cookie path
+	// without an extra management round-trip.
+	Groups []string `json:"groups,omitempty"`
+	// GroupNames carries the human-readable display names for the ids
+	// in Groups, ordered identically (positional pairing). Slice may be
+	// shorter than Groups for tokens minted before names were
+	// resolvable; the consumer falls back to ids for missing positions.
+	GroupNames []string `json:"group_names,omitempty"`
 }
 
 func GenerateKeyPair() (*KeyPair, error) {
@@ -34,7 +48,13 @@ func GenerateKeyPair() (*KeyPair, error) {
 	}, nil
 }
 
-func SignToken(privKeyB64, userID, domain string, method auth.Method, expiration time.Duration) (string, error) {
+// SignToken mints a session JWT for the given user and domain. email,
+// groups, and groupNames, when non-empty, are embedded so the proxy can
+// authorise and stamp identity for policy-aware middlewares without a
+// management round-trip on every cookie-bearing request. groupNames
+// pairs positionally with groups; pass nil when names couldn't be
+// resolved.
+func SignToken(privKeyB64, userID, email, domain string, method auth.Method, groups, groupNames []string, expiration time.Duration) (string, error) {
 	privKeyBytes, err := base64.StdEncoding.DecodeString(privKeyB64)
 	if err != nil {
 		return "", fmt.Errorf("decode private key: %w", err)
@@ -56,7 +76,10 @@ func SignToken(privKeyB64, userID, domain string, method auth.Method, expiration
 			IssuedAt:  jwt.NewNumericDate(now),
 			NotBefore: jwt.NewNumericDate(now),
 		},
-		Method: method,
+		Method:     method,
+		Email:      email,
+		Groups:     append([]string(nil), groups...),
+		GroupNames: append([]string(nil), groupNames...),
 	}
 
 	token := jwt.NewWithClaims(jwt.SigningMethodEdDSA, claims)

management/internals/server/boot.go

@@ -10,8 +10,10 @@ import (
 	"slices"
 	"time"
 
+	"github.com/gorilla/mux"
 	grpcMiddleware "github.com/grpc-ecosystem/go-grpc-middleware/v2"
 	"github.com/grpc-ecosystem/go-grpc-middleware/v2/interceptors/realip"
+	"github.com/rs/cors"
 	"github.com/rs/xid"
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc"
@@ -19,7 +21,6 @@ import (
 	"google.golang.org/grpc/keepalive"
 
 	cachestore "github.com/eko/gocache/lib/v4/store"
-	"github.com/netbirdio/management-integrations/integrations"
 
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/formatter/hook"
@@ -27,16 +28,20 @@ import (
 	accesslogsmanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs/manager"
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
 	"github.com/netbirdio/netbird/management/server/activity"
+	activitystore "github.com/netbirdio/netbird/management/server/activity/store"
 	nbcache "github.com/netbirdio/netbird/management/server/cache"
 	nbContext "github.com/netbirdio/netbird/management/server/context"
 	nbhttp "github.com/netbirdio/netbird/management/server/http"
 	"github.com/netbirdio/netbird/management/server/http/middleware"
+	"github.com/netbirdio/netbird/management/server/idp"
 	"github.com/netbirdio/netbird/management/server/store"
 	"github.com/netbirdio/netbird/management/server/telemetry"
 	mgmtProto "github.com/netbirdio/netbird/shared/management/proto"
 	"github.com/netbirdio/netbird/util/crypt"
 )
 
+const apiPrefix = "/api"
+
 var (
 	kaep = keepalive.EnforcementPolicy{
 		MinTime:             15 * time.Second,
@@ -94,12 +99,17 @@ func (s *BaseServer) Store() store.Store {
 
 func (s *BaseServer) EventStore() activity.Store {
 	return Create(s, func() activity.Store {
-		integrationMetrics, err := integrations.InitIntegrationMetrics(context.Background(), s.Metrics())
-		if err != nil {
-			log.Fatalf("failed to initialize integration metrics: %v", err)
+		var err error
+		key := s.Config.DataStoreEncryptionKey
+		if key == "" {
+			log.Debugf("generate new activity store encryption key")
+			key, err = crypt.GenerateKey()
+			if err != nil {
+				log.Fatalf("failed to generate event store encryption key: %v", err)
+			}
 		}
 
-		eventStore, _, err := integrations.InitEventStore(context.Background(), s.Config.Datadir, s.Config.DataStoreEncryptionKey, integrationMetrics)
+		eventStore, err := activitystore.NewSqlStore(context.Background(), s.Config.Datadir, key)
 		if err != nil {
 			log.Fatalf("failed to initialize event store: %v", err)
 		}
@@ -110,7 +120,7 @@ func (s *BaseServer) EventStore() activity.Store {
 
 func (s *BaseServer) APIHandler() http.Handler {
 	return Create(s, func() http.Handler {
-		httpAPIHandler, err := nbhttp.NewAPIHandler(context.Background(), s.AccountManager(), s.NetworksManager(), s.ResourcesManager(), s.RoutesManager(), s.GroupsManager(), s.GeoLocationManager(), s.AuthManager(), s.Metrics(), s.IntegratedValidator(), s.ProxyController(), s.PermissionsManager(), s.PeersManager(), s.SettingsManager(), s.ZonesManager(), s.RecordsManager(), s.NetworkMapController(), s.IdpManager(), s.ServiceManager(), s.ReverseProxyDomainManager(), s.AccessLogsManager(), s.ReverseProxyGRPCServer(), s.Config.ReverseProxy.TrustedHTTPProxies, s.RateLimiter())
+		httpAPIHandler, err := nbhttp.NewAPIHandler(context.Background(), s.Router(), s.AccountManager(), s.NetworksManager(), s.ResourcesManager(), s.RoutesManager(), s.GroupsManager(), s.GeoLocationManager(), s.AuthManager(), s.Metrics(), s.PermissionsManager(), s.SettingsManager(), s.ZonesManager(), s.RecordsManager(), s.NetworkMapController(), s.IdpManager(), s.ServiceManager(), s.ReverseProxyDomainManager(), s.AccessLogsManager(), s.ReverseProxyGRPCServer(), s.Config.ReverseProxy.TrustedHTTPProxies, s.RateLimiter(), s.IsValidChildAccount)
 		if err != nil {
 			log.Fatalf("failed to create API handler: %v", err)
 		}
@@ -118,6 +128,22 @@ func (s *BaseServer) APIHandler() http.Handler {
 	})
 }
 
+// IDPHandler returns the HTTP handler for the embedded IdP (Dex), or nil if
+// the deployment isn't using the embedded variant.
+func (s *BaseServer) IDPHandler() http.Handler {
+	embeddedIdP, ok := s.IdpManager().(*idp.EmbeddedIdPManager)
+	if !ok || embeddedIdP == nil {
+		return nil
+	}
+	return cors.AllowAll().Handler(embeddedIdP.Handler())
+}
+
+func (s *BaseServer) Router() *mux.Router {
+	return Create(s, func() *mux.Router {
+		return mux.NewRouter().PathPrefix(apiPrefix).Subrouter()
+	})
+}
+
 func (s *BaseServer) RateLimiter() *middleware.APIRateLimiter {
 	return Create(s, func() *middleware.APIRateLimiter {
 		cfg, enabled := middleware.RateLimiterConfigFromEnv()

management/internals/server/controllers.go

@@ -19,6 +19,7 @@ import (
 	"github.com/netbirdio/netbird/management/server"
 	"github.com/netbirdio/netbird/management/server/auth"
 	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator"
+	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator/validator"
 	"github.com/netbirdio/netbird/management/server/integrations/port_forwarding"
 	"github.com/netbirdio/netbird/management/server/job"
 	nbjwt "github.com/netbirdio/netbird/shared/auth/jwt"
@@ -38,7 +39,7 @@ func (s *BaseServer) JobManager() *job.Manager {
 
 func (s *BaseServer) IntegratedValidator() integrated_validator.IntegratedValidator {
 	return Create(s, func() integrated_validator.IntegratedValidator {
-		integratedPeerValidator, err := integrations.NewIntegratedValidator(
+		integratedPeerValidator, err := validator.NewIntegratedValidator(
 			context.Background(),
 			s.PeersManager(),
 			s.SettingsManager(),
@@ -112,7 +113,11 @@ func (s *BaseServer) AuthManager() auth.Manager {
 
 func (s *BaseServer) EphemeralManager() ephemeral.Manager {
 	return Create(s, func() ephemeral.Manager {
-		return manager.NewEphemeralManager(s.Store(), s.PeersManager())
+		em := manager.NewEphemeralManager(s.Store(), s.PeersManager())
+		if metrics := s.Metrics(); metrics != nil {
+			em.SetMetrics(metrics.EphemeralPeersMetrics())
+		}
+		return em
 	})
 }
 

management/internals/server/modules.go

@@ -57,13 +57,7 @@ func (s *BaseServer) GeoLocationManager() geolocation.Geolocation {
 
 func (s *BaseServer) PermissionsManager() permissions.Manager {
 	return Create(s, func() permissions.Manager {
-		manager := integrations.InitPermissionsManager(s.Store(), s.Metrics().GetMeter())
-
-		s.AfterInit(func(s *BaseServer) {
-			manager.SetAccountManager(s.AccountManager())
-		})
-
-		return manager
+		return permissions.NewManager(s.Store())
 	})
 }
 
@@ -153,7 +147,6 @@ func (s *BaseServer) IdpManager() idp.Manager {
 			return idpManager
 		}
 
-
 		return nil
 	})
 }
@@ -235,3 +228,7 @@ func (s *BaseServer) ReverseProxyDomainManager() *manager.Manager {
 		return &m
 	})
 }
+
+func (s *BaseServer) IsValidChildAccount(_ context.Context, _, _, _ string) bool {
+	return false
+}

management/internals/server/server.go

@@ -193,7 +193,7 @@ func (s *BaseServer) Start(ctx context.Context) error {
 		log.WithContext(srvCtx).Infof("running gRPC backward compatibility server: %s", compatListener.Addr().String())
 	}
 
-	rootHandler := s.handlerFunc(srvCtx, s.GRPCServer(), s.APIHandler(), s.Metrics().GetMeter())
+	rootHandler := s.handlerFunc(srvCtx, s.GRPCServer(), s.APIHandler(), s.IDPHandler(), s.Metrics().GetMeter())
 	switch {
 	case s.certManager != nil:
 		// a call to certManager.Listener() always creates a new listener so we do it once
@@ -304,7 +304,7 @@ func (s *BaseServer) SetHandlerFunc(handler http.Handler) {
 	log.Tracef("custom handler set successfully")
 }
 
-func (s *BaseServer) handlerFunc(_ context.Context, gRPCHandler *grpc.Server, httpHandler http.Handler, meter metric.Meter) http.Handler {
+func (s *BaseServer) handlerFunc(_ context.Context, gRPCHandler *grpc.Server, httpHandler http.Handler, idpHandler http.Handler, meter metric.Meter) http.Handler {
 	// Check if a custom handler was set (for multiplexing additional services)
 	if customHandler, ok := s.GetContainer("customHandler"); ok {
 		if handler, ok := customHandler.(http.Handler); ok {
@@ -323,6 +323,8 @@ func (s *BaseServer) handlerFunc(_ context.Context, gRPCHandler *grpc.Server, ht
 			gRPCHandler.ServeHTTP(writer, request)
 		case request.URL.Path == wsproxy.ProxyPath+wsproxy.ManagementComponent:
 			wsProxy.Handler().ServeHTTP(writer, request)
+		case idpHandler != nil && strings.HasPrefix(request.URL.Path, "/oauth2"):
+			idpHandler.ServeHTTP(writer, request)
 		default:
 			httpHandler.ServeHTTP(writer, request)
 		}

management/internals/shared/grpc/proxy.go

@@ -9,6 +9,7 @@ import (
 	"encoding/hex"
 	"errors"
 	"fmt"
+	"io"
 	"net"
 	"net/http"
 	"net/url"
@@ -136,9 +137,12 @@ type proxyConnection struct {
 	tokenID      string
 	capabilities *proto.ProxyCapabilities
 	stream       proto.ProxyService_GetMappingUpdateServer
-	sendChan     chan *proto.GetMappingUpdateResponse
-	ctx          context.Context
-	cancel       context.CancelFunc
+	// syncStream is set when the proxy connected via SyncMappings.
+	// When non-nil, the sender goroutine uses this instead of stream.
+	syncStream proto.ProxyService_SyncMappingsServer
+	sendChan   chan *proto.GetMappingUpdateResponse
+	ctx        context.Context
+	cancel     context.CancelFunc
 }
 
 func enforceAccountScope(ctx context.Context, requestAccountID string) error {
@@ -206,145 +210,323 @@ func (s *ProxyServiceServer) SetProxyController(proxyController proxy.Controller
 	s.proxyController = proxyController
 }
 
+// proxyConnectParams holds the validated parameters extracted from either
+// a GetMappingUpdateRequest or a SyncMappingsInit message.
+type proxyConnectParams struct {
+	proxyID      string
+	address      string
+	capabilities *proto.ProxyCapabilities
+}
+
 // GetMappingUpdate handles the control stream with proxy clients
 func (s *ProxyServiceServer) GetMappingUpdate(req *proto.GetMappingUpdateRequest, stream proto.ProxyService_GetMappingUpdateServer) error {
-	ctx := stream.Context()
-
-	peerInfo := PeerIPFromContext(ctx)
-	log.Infof("New proxy connection from %s", peerInfo)
-
-	proxyID := req.GetProxyId()
-	if proxyID == "" {
-		return status.Errorf(codes.InvalidArgument, "proxy_id is required")
-	}
-
-	proxyAddress := req.GetAddress()
-	if !isProxyAddressValid(proxyAddress) {
-		return status.Errorf(codes.InvalidArgument, "proxy address is invalid")
-	}
-
-	var accountID *string
-	token := GetProxyTokenFromContext(ctx)
-	if token != nil && token.AccountID != nil {
-		accountID = token.AccountID
-
-		available, err := s.proxyManager.IsClusterAddressAvailable(ctx, proxyAddress, *accountID)
-		if err != nil {
-			return status.Errorf(codes.Internal, "check cluster address: %v", err)
-		}
-		if !available {
-			return status.Errorf(codes.AlreadyExists, "cluster address %s is already in use", proxyAddress)
-		}
-	}
-
-	var tokenID string
-	if token != nil {
-		tokenID = token.ID
-	}
-
-	sessionID := uuid.NewString()
-
-	if old, loaded := s.connectedProxies.Load(proxyID); loaded {
-		oldConn := old.(*proxyConnection)
-		log.WithFields(log.Fields{
-			"proxy_id":       proxyID,
-			"old_session_id": oldConn.sessionID,
-			"new_session_id": sessionID,
-		}).Info("Superseding existing proxy connection")
-		oldConn.cancel()
-	}
-
-	connCtx, cancel := context.WithCancel(ctx)
-	conn := &proxyConnection{
-		proxyID:      proxyID,
-		sessionID:    sessionID,
-		address:      proxyAddress,
-		accountID:    accountID,
-		tokenID:      tokenID,
-		capabilities: req.GetCapabilities(),
-		stream:       stream,
-		sendChan:     make(chan *proto.GetMappingUpdateResponse, 100),
-		ctx:          connCtx,
-		cancel:       cancel,
-	}
-
-	var caps *proxy.Capabilities
-	if c := req.GetCapabilities(); c != nil {
-		caps = &proxy.Capabilities{
-			SupportsCustomPorts: c.SupportsCustomPorts,
-			RequireSubdomain:    c.RequireSubdomain,
-			SupportsCrowdsec:    c.SupportsCrowdsec,
-		}
-	}
-	proxyRecord, err := s.proxyManager.Connect(ctx, proxyID, sessionID, proxyAddress, peerInfo, accountID, caps)
+	params, err := s.validateProxyConnect(req.GetProxyId(), req.GetAddress(), stream.Context())
 	if err != nil {
-		cancel()
-		if accountID != nil {
-			return status.Errorf(codes.Internal, "failed to register BYOP proxy: %v", err)
-		}
-		log.WithContext(ctx).Warnf("failed to register proxy %s in database: %v", proxyID, err)
-		return status.Errorf(codes.Internal, "register proxy in database: %v", err)
+		return err
+	}
+	params.capabilities = req.GetCapabilities()
+
+	conn, proxyRecord, err := s.registerProxyConnection(stream.Context(), params, &proxyConnection{
+		stream: stream,
+	})
+	if err != nil {
+		return err
 	}
 
-	s.connectedProxies.Store(proxyID, conn)
-	if err := s.proxyController.RegisterProxyToCluster(ctx, conn.address, proxyID); err != nil {
-		log.WithContext(ctx).Warnf("Failed to register proxy %s in cluster: %v", proxyID, err)
-	}
-
-	if err := s.sendSnapshot(ctx, conn); err != nil {
-		if s.connectedProxies.CompareAndDelete(proxyID, conn) {
-			if unregErr := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, proxyID); unregErr != nil {
-				log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", proxyID, unregErr)
-			}
-		}
-		cancel()
-		if disconnErr := s.proxyManager.Disconnect(context.Background(), proxyID, sessionID); disconnErr != nil {
-			log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", proxyID, disconnErr)
-		}
-		return fmt.Errorf("send snapshot to proxy %s: %w", proxyID, err)
+	if err := s.sendSnapshot(stream.Context(), conn); err != nil {
+		s.cleanupFailedSnapshot(stream.Context(), conn)
+		return fmt.Errorf("send snapshot to proxy %s: %w", params.proxyID, err)
 	}
 
 	errChan := make(chan error, 2)
 	go s.sender(conn, errChan)
 
-	log.WithFields(log.Fields{
-		"proxy_id":      proxyID,
-		"session_id":    sessionID,
-		"address":       proxyAddress,
-		"cluster_addr":  proxyAddress,
-		"account_id":    accountID,
-		"total_proxies": len(s.GetConnectedProxies()),
-	}).Info("Proxy registered in cluster")
-	defer func() {
-		if !s.connectedProxies.CompareAndDelete(proxyID, conn) {
-			log.Infof("Proxy %s session %s: skipping cleanup, superseded by new connection", proxyID, sessionID)
-			cancel()
+	return s.serveProxyConnection(conn, proxyRecord, errChan, false)
+}
+
+// SyncMappings implements the bidirectional SyncMappings RPC.
+// It mirrors GetMappingUpdate but provides application-level back-pressure:
+// management waits for an ack from the proxy before sending the next batch.
+func (s *ProxyServiceServer) SyncMappings(stream proto.ProxyService_SyncMappingsServer) error {
+	init, err := recvSyncInit(stream)
+	if err != nil {
+		return err
+	}
+
+	params, err := s.validateProxyConnect(init.GetProxyId(), init.GetAddress(), stream.Context())
+	if err != nil {
+		return err
+	}
+	params.capabilities = init.GetCapabilities()
+
+	conn, proxyRecord, err := s.registerProxyConnection(stream.Context(), params, &proxyConnection{
+		syncStream: stream,
+	})
+	if err != nil {
+		return err
+	}
+
+	if err := s.sendSnapshotSync(stream.Context(), conn, stream); err != nil {
+		s.cleanupFailedSnapshot(stream.Context(), conn)
+		return fmt.Errorf("send snapshot to proxy %s: %w", params.proxyID, err)
+	}
+
+	errChan := make(chan error, 2)
+	go s.sender(conn, errChan)
+	go s.drainRecv(stream, errChan)
+
+	return s.serveProxyConnection(conn, proxyRecord, errChan, true)
+}
+
+// recvSyncInit receives and validates the first message on a SyncMappings stream.
+func recvSyncInit(stream proto.ProxyService_SyncMappingsServer) (*proto.SyncMappingsInit, error) {
+	firstMsg, err := stream.Recv()
+	if err != nil {
+		return nil, status.Errorf(codes.Internal, "receive init: %v", err)
+	}
+	init := firstMsg.GetInit()
+	if init == nil {
+		return nil, status.Errorf(codes.InvalidArgument, "first message must be init")
+	}
+	return init, nil
+}
+
+// validateProxyConnect validates the proxy ID and address, and checks cluster
+// address availability for account-scoped tokens.
+func (s *ProxyServiceServer) validateProxyConnect(proxyID, address string, ctx context.Context) (proxyConnectParams, error) {
+	if proxyID == "" {
+		return proxyConnectParams{}, status.Errorf(codes.InvalidArgument, "proxy_id is required")
+	}
+	if !isProxyAddressValid(address) {
+		return proxyConnectParams{}, status.Errorf(codes.InvalidArgument, "proxy address is invalid")
+	}
+
+	token := GetProxyTokenFromContext(ctx)
+	if token != nil && token.AccountID != nil {
+		available, err := s.proxyManager.IsClusterAddressAvailable(ctx, address, *token.AccountID)
+		if err != nil {
+			return proxyConnectParams{}, status.Errorf(codes.Internal, "check cluster address: %v", err)
+		}
+		if !available {
+			return proxyConnectParams{}, status.Errorf(codes.AlreadyExists, "cluster address %s is already in use", address)
+		}
+	}
+
+	return proxyConnectParams{proxyID: proxyID, address: address}, nil
+}
+
+// registerProxyConnection creates a proxyConnection, registers it with the
+// proxy manager and cluster, and stores it in connectedProxies. The caller
+// provides a partially initialised connSeed with stream-specific fields set;
+// the remaining fields are filled in here.
+func (s *ProxyServiceServer) registerProxyConnection(ctx context.Context, params proxyConnectParams, connSeed *proxyConnection) (*proxyConnection, *proxy.Proxy, error) {
+	peerInfo := PeerIPFromContext(ctx)
+
+	var accountID *string
+	var tokenID string
+	if token := GetProxyTokenFromContext(ctx); token != nil {
+		if token.AccountID != nil {
+			accountID = token.AccountID
+		}
+		tokenID = token.ID
+	}
+
+	sessionID := uuid.NewString()
+	s.supersedePriorConnection(params.proxyID, sessionID)
+
+	connCtx, cancel := context.WithCancel(ctx)
+	connSeed.proxyID = params.proxyID
+	connSeed.sessionID = sessionID
+	connSeed.address = params.address
+	connSeed.accountID = accountID
+	connSeed.tokenID = tokenID
+	connSeed.capabilities = params.capabilities
+	connSeed.sendChan = make(chan *proto.GetMappingUpdateResponse, 100)
+	connSeed.ctx = connCtx
+	connSeed.cancel = cancel
+
+	var caps *proxy.Capabilities
+	if c := params.capabilities; c != nil {
+		caps = &proxy.Capabilities{
+			SupportsCustomPorts: c.SupportsCustomPorts,
+			RequireSubdomain:    c.RequireSubdomain,
+			SupportsCrowdsec:    c.SupportsCrowdsec,
+			Private:             c.Private,
+		}
+	}
+
+	proxyRecord, err := s.proxyManager.Connect(ctx, params.proxyID, sessionID, params.address, peerInfo, accountID, caps)
+	if err != nil {
+		cancel()
+		if accountID != nil {
+			return nil, nil, status.Errorf(codes.Internal, "failed to register BYOP proxy: %v", err)
+		}
+		log.WithContext(ctx).Warnf("failed to register proxy %s in database: %v", params.proxyID, err)
+		return nil, nil, status.Errorf(codes.Internal, "register proxy in database: %v", err)
+	}
+
+	s.connectedProxies.Store(params.proxyID, connSeed)
+	if err := s.proxyController.RegisterProxyToCluster(ctx, params.address, params.proxyID); err != nil {
+		log.WithContext(ctx).Warnf("Failed to register proxy %s in cluster: %v", params.proxyID, err)
+	}
+
+	return connSeed, proxyRecord, nil
+}
+
+// supersedePriorConnection cancels any existing connection for the given proxy.
+func (s *ProxyServiceServer) supersedePriorConnection(proxyID, newSessionID string) {
+	if old, loaded := s.connectedProxies.Load(proxyID); loaded {
+		oldConn := old.(*proxyConnection)
+		log.WithFields(log.Fields{
+			"proxy_id":       proxyID,
+			"old_session_id": oldConn.sessionID,
+			"new_session_id": newSessionID,
+		}).Info("Superseding existing proxy connection")
+		oldConn.cancel()
+	}
+}
+
+// cleanupFailedSnapshot removes the connection from the cluster and store
+// after a snapshot send failure.
+func (s *ProxyServiceServer) cleanupFailedSnapshot(ctx context.Context, conn *proxyConnection) {
+	if s.connectedProxies.CompareAndDelete(conn.proxyID, conn) {
+		if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, conn.proxyID); err != nil {
+			log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", conn.proxyID, err)
+		}
+	}
+	conn.cancel()
+	if err := s.proxyManager.Disconnect(context.Background(), conn.proxyID, conn.sessionID); err != nil {
+		log.WithContext(ctx).Debugf("cleanup after snapshot failure for proxy %s: %v", conn.proxyID, err)
+	}
+}
+
+// drainRecv consumes and discards messages from a bidirectional stream.
+// The proxy sends an ack for every incremental update; we don't need them
+// after the snapshot phase. Recv errors are forwarded to errChan.
+func (s *ProxyServiceServer) drainRecv(stream proto.ProxyService_SyncMappingsServer, errChan chan<- error) {
+	for {
+		if _, err := stream.Recv(); err != nil {
+			errChan <- err
 			return
 		}
+	}
+}
 
-		if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, proxyID); err != nil {
-			log.Warnf("Failed to unregister proxy %s from cluster: %v", proxyID, err)
-		}
-		if err := s.proxyManager.Disconnect(context.Background(), proxyID, sessionID); err != nil {
-			log.Warnf("Failed to mark proxy %s as disconnected: %v", proxyID, err)
-		}
+// serveProxyConnection runs the post-snapshot lifecycle: heartbeat, sender,
+// and wait for termination. When bidi is true, normal stream closure (EOF,
+// canceled) is treated as a clean disconnect rather than an error.
+func (s *ProxyServiceServer) serveProxyConnection(conn *proxyConnection, proxyRecord *proxy.Proxy, errChan <-chan error, bidi bool) error {
+	log.WithFields(log.Fields{
+		"proxy_id":      conn.proxyID,
+		"session_id":    conn.sessionID,
+		"address":       conn.address,
+		"cluster_addr":  conn.address,
+		"account_id":    conn.accountID,
+		"total_proxies": len(s.GetConnectedProxies()),
+	}).Info("Proxy registered in cluster")
 
-		cancel()
-		log.Infof("Proxy %s session %s disconnected", proxyID, sessionID)
-	}()
-
-	go s.heartbeat(connCtx, conn, proxyRecord)
+	defer s.disconnectProxy(conn)
+	go s.heartbeat(conn.ctx, conn, proxyRecord)
 
 	select {
 	case err := <-errChan:
-		log.WithContext(ctx).Warnf("Failed to send update: %v", err)
-		return fmt.Errorf("send update to proxy %s: %w", proxyID, err)
-	case <-connCtx.Done():
-		log.WithContext(ctx).Infof("Proxy %s context canceled", proxyID)
-		return connCtx.Err()
+		if bidi && isStreamClosed(err) {
+			log.Infof("Proxy %s stream closed", conn.proxyID)
+			return nil
+		}
+		log.Warnf("Failed to send update: %v", err)
+		return fmt.Errorf("send update to proxy %s: %w", conn.proxyID, err)
+	case <-conn.ctx.Done():
+		log.Infof("Proxy %s context canceled", conn.proxyID)
+		return conn.ctx.Err()
 	}
 }
 
+// disconnectProxy removes the connection from cluster and store, unless it
+// has already been superseded by a newer connection.
+func (s *ProxyServiceServer) disconnectProxy(conn *proxyConnection) {
+	if !s.connectedProxies.CompareAndDelete(conn.proxyID, conn) {
+		log.Infof("Proxy %s session %s: skipping cleanup, superseded by new connection", conn.proxyID, conn.sessionID)
+		conn.cancel()
+		return
+	}
+
+	if err := s.proxyController.UnregisterProxyFromCluster(context.Background(), conn.address, conn.proxyID); err != nil {
+		log.Warnf("Failed to unregister proxy %s from cluster: %v", conn.proxyID, err)
+	}
+	if err := s.proxyManager.Disconnect(context.Background(), conn.proxyID, conn.sessionID); err != nil {
+		log.Warnf("Failed to mark proxy %s as disconnected: %v", conn.proxyID, err)
+	}
+
+	conn.cancel()
+	log.Infof("Proxy %s session %s disconnected", conn.proxyID, conn.sessionID)
+}
+
+// sendSnapshotSync sends the initial snapshot with back-pressure: it sends
+// one batch, then waits for the proxy to ack before sending the next.
+func (s *ProxyServiceServer) sendSnapshotSync(ctx context.Context, conn *proxyConnection, stream proto.ProxyService_SyncMappingsServer) error {
+	if !isProxyAddressValid(conn.address) {
+		return fmt.Errorf("proxy address is invalid")
+	}
+	if s.snapshotBatchSize <= 0 {
+		return fmt.Errorf("invalid snapshot batch size: %d", s.snapshotBatchSize)
+	}
+
+	mappings, err := s.snapshotServiceMappings(ctx, conn)
+	if err != nil {
+		return err
+	}
+
+	for i := 0; i < len(mappings); i += s.snapshotBatchSize {
+		end := i + s.snapshotBatchSize
+		if end > len(mappings) {
+			end = len(mappings)
+		}
+		for _, m := range mappings[i:end] {
+			token, err := s.tokenStore.GenerateToken(m.AccountId, m.Id, s.proxyTokenTTL())
+			if err != nil {
+				return fmt.Errorf("generate auth token for service %s: %w", m.Id, err)
+			}
+			m.AuthToken = token
+		}
+		if err := stream.Send(&proto.SyncMappingsResponse{
+			Mapping:             mappings[i:end],
+			InitialSyncComplete: end == len(mappings),
+		}); err != nil {
+			return fmt.Errorf("send snapshot batch: %w", err)
+		}
+
+		if err := waitForAck(stream); err != nil {
+			return err
+		}
+	}
+
+	if len(mappings) == 0 {
+		if err := stream.Send(&proto.SyncMappingsResponse{
+			InitialSyncComplete: true,
+		}); err != nil {
+			return fmt.Errorf("send snapshot completion: %w", err)
+		}
+
+		if err := waitForAck(stream); err != nil {
+			return err
+		}
+	}
+
+	return nil
+}
+
+func waitForAck(stream proto.ProxyService_SyncMappingsServer) error {
+	msg, err := stream.Recv()
+	if err != nil {
+		return fmt.Errorf("receive ack: %w", err)
+	}
+	if msg.GetAck() == nil {
+		return fmt.Errorf("expected ack, got %T", msg.GetMsg())
+	}
+	return nil
+}
+
 // heartbeat updates the proxy's last_seen timestamp every minute and
 // disconnects the proxy if its access token has been revoked.
 func (s *ProxyServiceServer) heartbeat(ctx context.Context, conn *proxyConnection, p *proxy.Proxy) {
@@ -381,6 +563,9 @@ func (s *ProxyServiceServer) sendSnapshot(ctx context.Context, conn *proxyConnec
 	if !isProxyAddressValid(conn.address) {
 		return fmt.Errorf("proxy address is invalid")
 	}
+	if s.snapshotBatchSize <= 0 {
+		return fmt.Errorf("invalid snapshot batch size: %d", s.snapshotBatchSize)
+	}
 
 	mappings, err := s.snapshotServiceMappings(ctx, conn)
 	if err != nil {
@@ -394,6 +579,13 @@ func (s *ProxyServiceServer) sendSnapshot(ctx context.Context, conn *proxyConnec
 		if end > len(mappings) {
 			end = len(mappings)
 		}
+		for _, m := range mappings[i:end] {
+			token, err := s.tokenStore.GenerateToken(m.AccountId, m.Id, s.proxyTokenTTL())
+			if err != nil {
+				return fmt.Errorf("generate auth token for service %s: %w", m.Id, err)
+			}
+			m.AuthToken = token
+		}
 		if err := conn.stream.Send(&proto.GetMappingUpdateResponse{
 			Mapping:             mappings[i:end],
 			InitialSyncComplete: end == len(mappings),
@@ -425,18 +617,14 @@ func (s *ProxyServiceServer) snapshotServiceMappings(ctx context.Context, conn *
 		return nil, fmt.Errorf("get services from store: %w", err)
 	}
 
+	oidcCfg := s.GetOIDCValidationConfig()
 	var mappings []*proto.ProxyMapping
 	for _, service := range services {
 		if !service.Enabled || service.ProxyCluster == "" || service.ProxyCluster != conn.address {
 			continue
 		}
 
-		token, err := s.tokenStore.GenerateToken(service.AccountID, service.ID, s.proxyTokenTTL())
-		if err != nil {
-			return nil, fmt.Errorf("generate auth token for service %s: %w", service.ID, err)
-		}
-
-		m := service.ToProtoMapping(rpservice.Create, token, s.GetOIDCValidationConfig())
+		m := service.ToProtoMapping(rpservice.Create, "", oidcCfg)
 		if !proxyAcceptsMapping(conn, m) {
 			continue
 		}
@@ -457,12 +645,26 @@ func isProxyAddressValid(addr string) bool {
 	return err == nil
 }
 
-// sender handles sending messages to proxy
+// isStreamClosed returns true for errors that indicate normal stream
+// termination: io.EOF, context cancellation, or gRPC Canceled.
+func isStreamClosed(err error) bool {
+	if err == nil {
+		return false
+	}
+	if errors.Is(err, io.EOF) || errors.Is(err, context.Canceled) {
+		return true
+	}
+	return status.Code(err) == codes.Canceled
+}
+
+// sender handles sending messages to proxy.
+// When conn.syncStream is set the message is sent as SyncMappingsResponse;
+// otherwise the legacy GetMappingUpdateResponse stream is used.
 func (s *ProxyServiceServer) sender(conn *proxyConnection, errChan chan<- error) {
 	for {
 		select {
 		case resp := <-conn.sendChan:
-			if err := conn.stream.Send(resp); err != nil {
+			if err := conn.sendResponse(resp); err != nil {
 				errChan <- err
 				return
 			}
@@ -472,6 +674,17 @@ func (s *ProxyServiceServer) sender(conn *proxyConnection, errChan chan<- error)
 	}
 }
 
+// sendResponse sends a mapping update on whichever stream the proxy connected with.
+func (conn *proxyConnection) sendResponse(resp *proto.GetMappingUpdateResponse) error {
+	if conn.syncStream != nil {
+		return conn.syncStream.Send(&proto.SyncMappingsResponse{
+			Mapping:             resp.Mapping,
+			InitialSyncComplete: resp.InitialSyncComplete,
+		})
+	}
+	return conn.stream.Send(resp)
+}
+
 // SendAccessLog processes access log from proxy
 func (s *ProxyServiceServer) SendAccessLog(ctx context.Context, req *proto.SendAccessLogRequest) (*proto.SendAccessLogResponse, error) {
 	accessLog := req.GetLog()
@@ -538,10 +751,15 @@ func (s *ProxyServiceServer) SendServiceUpdate(update *proto.GetMappingUpdateRes
 				return true
 			}
 			connUpdate = &proto.GetMappingUpdateResponse{
-				Mapping:              filtered,
-				InitialSyncComplete:  update.InitialSyncComplete,
+				Mapping:             filtered,
+				InitialSyncComplete: update.InitialSyncComplete,
 			}
 		}
+		// Drop mappings the proxy lacks capability for (e.g. private without SupportsPrivateService).
+		connUpdate = filterMappingsForProxy(conn, connUpdate)
+		if connUpdate == nil || len(connUpdate.Mapping) == 0 {
+			return true
+		}
 		resp := s.perProxyMessage(connUpdate, conn.proxyID)
 		if resp == nil {
 			log.Warnf("Token generation failed for proxy %s, disconnecting to force resync", conn.proxyID)
@@ -670,16 +888,20 @@ func (s *ProxyServiceServer) SendServiceUpdateToCluster(ctx context.Context, upd
 	}
 }
 
-// proxyAcceptsMapping returns whether the proxy should receive this mapping.
-// Old proxies that never reported capabilities are skipped for non-TLS L4
-// mappings with a custom listen port, since they don't understand the
-// protocol. Proxies that report capabilities (even SupportsCustomPorts=false)
-// are new enough to handle the mapping. TLS uses SNI routing and works on
-// any proxy. Delete operations are always sent so proxies can clean up.
+// proxyAcceptsMapping returns whether the proxy can receive this mapping.
+// Private mappings require SupportsPrivateService; custom-port L4 mappings
+// require SupportsCustomPorts. Remove operations always pass so proxies can
+// clean up.
 func proxyAcceptsMapping(conn *proxyConnection, mapping *proto.ProxyMapping) bool {
 	if mapping.Type == proto.ProxyMappingUpdateType_UPDATE_TYPE_REMOVED {
 		return true
 	}
+	if mapping.GetPrivate() {
+		caps := conn.capabilities
+		if caps == nil || caps.SupportsPrivateService == nil || !*caps.SupportsPrivateService {
+			return false
+		}
+	}
 	if mapping.ListenPort == 0 || mapping.Mode == "tls" {
 		return true
 	}
@@ -688,6 +910,29 @@ func proxyAcceptsMapping(conn *proxyConnection, mapping *proto.ProxyMapping) boo
 	return conn.capabilities != nil && conn.capabilities.SupportsCustomPorts != nil
 }
 
+// filterMappingsForProxy drops mappings the proxy cannot safely receive
+// (e.g. private mappings to a proxy without SupportsPrivateService).
+// Returns the input unchanged when no filtering is needed.
+func filterMappingsForProxy(conn *proxyConnection, update *proto.GetMappingUpdateResponse) *proto.GetMappingUpdateResponse {
+	if update == nil || len(update.Mapping) == 0 {
+		return update
+	}
+	kept := make([]*proto.ProxyMapping, 0, len(update.Mapping))
+	for _, m := range update.Mapping {
+		if !proxyAcceptsMapping(conn, m) {
+			continue
+		}
+		kept = append(kept, m)
+	}
+	if len(kept) == len(update.Mapping) {
+		return update
+	}
+	return &proto.GetMappingUpdateResponse{
+		Mapping:             kept,
+		InitialSyncComplete: update.InitialSyncComplete,
+	}
+}
+
 // perProxyMessage returns a copy of update with a fresh one-time token for
 // create/update operations. For delete operations the original mapping is
 // used unchanged because proxies do not need to authenticate for removal.
@@ -749,7 +994,10 @@ func (s *ProxyServiceServer) Authenticate(ctx context.Context, req *proto.Authen
 
 	authenticated, userId, method := s.authenticateRequest(ctx, req, service)
 
-	token, err := s.generateSessionToken(ctx, authenticated, service, userId, method)
+	// Non-OIDC schemes (PIN/Password/Header) authenticate against per-service
+	// secrets and have no user-level group context, so groups stay nil. Email
+	// is also empty — these schemes don't resolve a user record at sign time.
+	token, err := s.generateSessionToken(ctx, authenticated, service, userId, "", method, nil, nil)
 	if err != nil {
 		return nil, err
 	}
@@ -838,7 +1086,7 @@ func (s *ProxyServiceServer) logAuthenticationError(ctx context.Context, err err
 	}
 }
 
-func (s *ProxyServiceServer) generateSessionToken(ctx context.Context, authenticated bool, service *rpservice.Service, userId string, method proxyauth.Method) (string, error) {
+func (s *ProxyServiceServer) generateSessionToken(ctx context.Context, authenticated bool, service *rpservice.Service, userId, userEmail string, method proxyauth.Method, groupIDs, groupNames []string) (string, error) {
 	if !authenticated || service.SessionPrivateKey == "" {
 		return "", nil
 	}
@@ -846,8 +1094,11 @@ func (s *ProxyServiceServer) generateSessionToken(ctx context.Context, authentic
 	token, err := sessionkey.SignToken(
 		service.SessionPrivateKey,
 		userId,
+		userEmail,
 		service.Domain,
 		method,
+		groupIDs,
+		groupNames,
 		proxyauth.DefaultSessionExpiry,
 	)
 	if err != nil {
@@ -858,6 +1109,26 @@ func (s *ProxyServiceServer) generateSessionToken(ctx context.Context, authentic
 	return token, nil
 }
 
+// pairGroupIDsAndNames splits a slice of resolved *types.Group records
+// into parallel id and name slices. ids[i] and names[i] always pair to
+// the same group. nil entries (orphan ids the manager couldn't resolve)
+// are skipped so the consumer can rely on positional pairing.
+func pairGroupIDsAndNames(groups []*types.Group) (ids, names []string) {
+	if len(groups) == 0 {
+		return nil, nil
+	}
+	ids = make([]string, 0, len(groups))
+	names = make([]string, 0, len(groups))
+	for _, g := range groups {
+		if g == nil {
+			continue
+		}
+		ids = append(ids, g.ID)
+		names = append(names, g.Name)
+	}
+	return ids, names
+}
+
 // SendStatusUpdate handles status updates from proxy clients.
 func (s *ProxyServiceServer) SendStatusUpdate(ctx context.Context, req *proto.SendStatusUpdateRequest) (*proto.SendStatusUpdateResponse, error) {
 	if err := enforceAccountScope(ctx, req.GetAccountId()); err != nil {
@@ -1122,7 +1393,9 @@ func (s *ProxyServiceServer) ValidateState(state string) (verifier, redirectURL
 	return verifier, redirectURL, nil
 }
 
-// GenerateSessionToken creates a signed session JWT for the given domain and user.
+// GenerateSessionToken creates a signed session JWT for the given domain and
+// user. The user's group memberships are embedded in the token so policy-aware
+// middlewares on the proxy can authorise without an extra management round-trip.
 func (s *ProxyServiceServer) GenerateSessionToken(ctx context.Context, domain, userID string, method proxyauth.Method) (string, error) {
 	service, err := s.getServiceByDomain(ctx, domain)
 	if err != nil {
@@ -1133,11 +1406,29 @@ func (s *ProxyServiceServer) GenerateSessionToken(ctx context.Context, domain, u
 		return "", fmt.Errorf("no session key configured for domain: %s", domain)
 	}
 
+	var (
+		email      string
+		groupIDs   []string
+		groupNames []string
+	)
+	if s.usersManager != nil {
+		user, userGroups, uerr := s.usersManager.GetUserWithGroups(ctx, userID)
+		if uerr != nil {
+			log.WithContext(ctx).Debugf("session token mint: lookup user %s: %v", userID, uerr)
+		} else if user != nil {
+			email = user.Email
+			groupIDs, groupNames = pairGroupIDsAndNames(userGroups)
+		}
+	}
+
 	return sessionkey.SignToken(
 		service.SessionPrivateKey,
 		userID,
+		email,
 		domain,
 		method,
+		groupIDs,
+		groupNames,
 		proxyauth.DefaultSessionExpiry,
 	)
 }
@@ -1241,7 +1532,7 @@ func (s *ProxyServiceServer) ValidateSession(ctx context.Context, req *proto.Val
 		}, nil
 	}
 
-	userID, _, err := proxyauth.ValidateSessionJWT(sessionToken, domain, pubKeyBytes)
+	userID, _, _, _, _, err := proxyauth.ValidateSessionJWT(sessionToken, domain, pubKeyBytes)
 	if err != nil {
 		log.WithFields(log.Fields{
 			"domain": domain,
@@ -1254,7 +1545,7 @@ func (s *ProxyServiceServer) ValidateSession(ctx context.Context, req *proto.Val
 		}, nil
 	}
 
-	user, err := s.usersManager.GetUser(ctx, userID)
+	user, userGroups, err := s.usersManager.GetUserWithGroups(ctx, userID)
 	if err != nil {
 		log.WithFields(log.Fields{
 			"domain":  domain,
@@ -1288,12 +1579,15 @@ func (s *ProxyServiceServer) ValidateSession(ctx context.Context, req *proto.Val
 			"user_id": userID,
 			"error":   err.Error(),
 		}).Debug("ValidateSession: access denied")
+		groupIDs, groupNames := pairGroupIDsAndNames(userGroups)
 		//nolint:nilerr
 		return &proto.ValidateSessionResponse{
-			Valid:        false,
-			UserId:       user.Id,
-			UserEmail:    user.Email,
-			DeniedReason: "not_in_group",
+			Valid:          false,
+			UserId:         user.Id,
+			UserEmail:      user.Email,
+			DeniedReason:   "not_in_group",
+			PeerGroupIds:   groupIDs,
+			PeerGroupNames: groupNames,
 		}, nil
 	}
 
@@ -1303,10 +1597,13 @@ func (s *ProxyServiceServer) ValidateSession(ctx context.Context, req *proto.Val
 		"email":   user.Email,
 	}).Debug("ValidateSession: access granted")
 
+	groupIDs, groupNames := pairGroupIDsAndNames(userGroups)
 	return &proto.ValidateSessionResponse{
-		Valid:     true,
-		UserId:    user.Id,
-		UserEmail: user.Email,
+		Valid:          true,
+		UserId:         user.Id,
+		UserEmail:      user.Email,
+		PeerGroupIds:   groupIDs,
+		PeerGroupNames: groupNames,
 	}, nil
 }
 
@@ -1339,3 +1636,154 @@ func (s *ProxyServiceServer) checkGroupAccess(service *rpservice.Service, user *
 }
 
 func ptr[T any](v T) *T { return &v }
+
+// ValidateTunnelPeer resolves an inbound peer by its WireGuard tunnel IP and
+// checks the peer's group membership against the service's access groups.
+// Peers without a user (machine agents, automation workloads) are first-class
+// callers; authorisation runs off peer-group memberships rather than the
+// optional owning user's auto-groups. On success a session JWT is minted so
+// the proxy can install a cookie and skip subsequent management round-trips.
+func (s *ProxyServiceServer) ValidateTunnelPeer(ctx context.Context, req *proto.ValidateTunnelPeerRequest) (*proto.ValidateTunnelPeerResponse, error) {
+	domain := req.GetDomain()
+	tunnelIPStr := req.GetTunnelIp()
+
+	if domain == "" || tunnelIPStr == "" {
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:        false,
+			DeniedReason: "missing domain or tunnel_ip",
+		}, nil
+	}
+
+	tunnelIP := net.ParseIP(tunnelIPStr)
+	if tunnelIP == nil {
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:        false,
+			DeniedReason: "invalid_tunnel_ip",
+		}, nil
+	}
+
+	service, err := s.getServiceByDomain(ctx, domain)
+	if err != nil {
+		log.WithFields(log.Fields{"domain": domain, "error": err.Error()}).Debug("ValidateTunnelPeer: service not found")
+		//nolint:nilerr
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:        false,
+			DeniedReason: "service_not_found",
+		}, nil
+	}
+
+	// Mirror ValidateSession: account-scoped (BYOP) proxy tokens may only
+	// validate and mint session cookies for their own account's domains.
+	if err := enforceAccountScope(ctx, service.AccountID); err != nil {
+		return nil, err
+	}
+
+	peer, err := s.peersManager.GetPeerByTunnelIP(ctx, service.AccountID, tunnelIP)
+	if err != nil || peer == nil {
+		log.WithFields(log.Fields{"domain": domain, "tunnel_ip": tunnelIPStr}).Debug("ValidateTunnelPeer: peer not found")
+		//nolint:nilerr
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:        false,
+			DeniedReason: "peer_not_found",
+		}, nil
+	}
+
+	_, peerGroups, err := s.peersManager.GetPeerWithGroups(ctx, service.AccountID, peer.ID)
+	if err != nil {
+		log.WithFields(log.Fields{"domain": domain, "peer_id": peer.ID, "error": err.Error()}).Debug("ValidateTunnelPeer: peer groups lookup failed")
+		//nolint:nilerr
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:        false,
+			DeniedReason: "peer_not_found",
+		}, nil
+	}
+
+	groupIDs, groupNames := pairGroupIDsAndNames(peerGroups)
+
+	// Resolve the principal: when the peer is linked to a user, the human
+	// is the principal so multiple peers owned by the same user share a
+	// single identity. Unlinked peers (machine agents) are their own
+	// principal keyed on peer.ID. displayIdentity is what upstream gateways
+	// tag spend with — user.Email when linked, peer.Name when not.
+	principalID := peer.ID
+	displayIdentity := peer.Name
+	if peer.UserID != "" {
+		if user, uerr := s.usersManager.GetUser(ctx, peer.UserID); uerr == nil && user != nil {
+			principalID = user.Id
+			if user.Email != "" {
+				displayIdentity = user.Email
+			}
+		}
+	}
+
+	if err := checkPeerGroupAccess(service, groupIDs); err != nil {
+		log.WithFields(log.Fields{"domain": domain, "peer_id": peer.ID, "error": err.Error()}).Debug("ValidateTunnelPeer: access denied")
+		//nolint:nilerr
+		return &proto.ValidateTunnelPeerResponse{
+			Valid:          false,
+			UserId:         principalID,
+			UserEmail:      displayIdentity,
+			DeniedReason:   "not_in_group",
+			PeerGroupIds:   groupIDs,
+			PeerGroupNames: groupNames,
+		}, nil
+	}
+
+	token, err := s.generateSessionToken(ctx, true, service, principalID, displayIdentity, proxyauth.MethodOIDC, groupIDs, groupNames)
+	if err != nil {
+		return nil, err
+	}
+
+	log.WithFields(log.Fields{
+		"domain":       domain,
+		"tunnel_ip":    tunnelIPStr,
+		"peer_id":      peer.ID,
+		"principal_id": principalID,
+	}).Debug("ValidateTunnelPeer: access granted")
+
+	return &proto.ValidateTunnelPeerResponse{
+		Valid:          true,
+		UserId:         principalID,
+		UserEmail:      displayIdentity,
+		SessionToken:   token,
+		PeerGroupIds:   groupIDs,
+		PeerGroupNames: groupNames,
+	}, nil
+}
+
+// checkPeerGroupAccess gates ValidateTunnelPeer by the service's required
+// groups. Private services authorise against AccessGroups (empty list fails
+// closed — Validate() rejects that at save time but the RPC is the security
+// boundary and must not trust upstream state). Bearer-auth services authorise
+// against DistributionGroups when populated. Non-private non-bearer services
+// are open.
+func checkPeerGroupAccess(service *rpservice.Service, peerGroupIDs []string) error {
+	if service.Private {
+		if len(service.AccessGroups) == 0 {
+			return fmt.Errorf("private service has no access groups")
+		}
+		return matchAnyGroup(service.AccessGroups, peerGroupIDs)
+	}
+	if service.Auth.BearerAuth != nil && service.Auth.BearerAuth.Enabled && len(service.Auth.BearerAuth.DistributionGroups) > 0 {
+		return matchAnyGroup(service.Auth.BearerAuth.DistributionGroups, peerGroupIDs)
+	}
+	return nil
+}
+
+// matchAnyGroup returns nil when peerGroupIDs intersects allowedGroups,
+// else a non-nil error.
+func matchAnyGroup(allowedGroups, peerGroupIDs []string) error {
+	if len(allowedGroups) == 0 {
+		return fmt.Errorf("no allowed groups configured")
+	}
+	allowed := make(map[string]struct{}, len(allowedGroups))
+	for _, g := range allowedGroups {
+		allowed[g] = struct{}{}
+	}
+	for _, g := range peerGroupIDs {
+		if _, ok := allowed[g]; ok {
+			return nil
+		}
+	}
+	return fmt.Errorf("peer not in allowed groups")
+}

management/internals/shared/grpc/proxy_group_access_test.go

@@ -109,7 +109,7 @@ func (m *mockReverseProxyManager) GetServiceByDomain(_ context.Context, domain s
 	return nil, errors.New("service not found for domain: " + domain)
 }
 
-func (m *mockReverseProxyManager) GetActiveClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
+func (m *mockReverseProxyManager) GetClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 
@@ -129,6 +129,14 @@ func (m *mockUsersManager) GetUser(ctx context.Context, userID string) (*types.U
 	return user, nil
 }
 
+func (m *mockUsersManager) GetUserWithGroups(ctx context.Context, userID string) (*types.User, []*types.Group, error) {
+	user, err := m.GetUser(ctx, userID)
+	if err != nil {
+		return nil, nil, err
+	}
+	return user, nil, nil
+}
+
 func TestValidateUserGroupAccess(t *testing.T) {
 	tests := []struct {
 		name             string
@@ -420,3 +428,46 @@ func TestGetAccountProxyByDomain(t *testing.T) {
 		})
 	}
 }
+
+func TestCheckPeerGroupAccess(t *testing.T) {
+	t.Run("private with empty AccessGroups denies", func(t *testing.T) {
+		svc := &service.Service{Private: true, AccessGroups: nil}
+		err := checkPeerGroupAccess(svc, []string{"grp-admins"})
+		require.Error(t, err)
+		assert.Contains(t, err.Error(), "no access groups")
+	})
+
+	t.Run("private with peer in AccessGroups allows", func(t *testing.T) {
+		svc := &service.Service{Private: true, AccessGroups: []string{"grp-admins", "grp-ops"}}
+		assert.NoError(t, checkPeerGroupAccess(svc, []string{"grp-other", "grp-ops"}))
+	})
+
+	t.Run("private with peer outside AccessGroups denies", func(t *testing.T) {
+		svc := &service.Service{Private: true, AccessGroups: []string{"grp-admins"}}
+		assert.Error(t, checkPeerGroupAccess(svc, []string{"grp-other"}))
+	})
+
+	t.Run("bearer enabled with empty DistributionGroups allows", func(t *testing.T) {
+		svc := &service.Service{
+			Auth: service.AuthConfig{BearerAuth: &service.BearerAuthConfig{Enabled: true}},
+		}
+		assert.NoError(t, checkPeerGroupAccess(svc, []string{"grp-anyone"}))
+	})
+
+	t.Run("bearer enabled gates on DistributionGroups", func(t *testing.T) {
+		svc := &service.Service{
+			Auth: service.AuthConfig{
+				BearerAuth: &service.BearerAuthConfig{
+					Enabled:            true,
+					DistributionGroups: []string{"grp-allowed"},
+				},
+			},
+		}
+		assert.NoError(t, checkPeerGroupAccess(svc, []string{"grp-allowed"}))
+		assert.Error(t, checkPeerGroupAccess(svc, []string{"grp-other"}))
+	})
+
+	t.Run("non-private non-bearer is open", func(t *testing.T) {
+		assert.NoError(t, checkPeerGroupAccess(&service.Service{}, nil))
+	})
+}

management/internals/shared/grpc/proxy_snapshot_test.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"fmt"
 	"testing"
+	"time"
 
 	"github.com/golang/mock/gomock"
 	"github.com/stretchr/testify/assert"
@@ -172,3 +173,55 @@ func TestSendSnapshot_EmptySnapshot(t *testing.T) {
 	assert.Empty(t, stream.messages[0].Mapping)
 	assert.True(t, stream.messages[0].InitialSyncComplete)
 }
+
+type hookingStream struct {
+	grpc.ServerStream
+	onSend func(*proto.GetMappingUpdateResponse)
+}
+
+func (s *hookingStream) Send(m *proto.GetMappingUpdateResponse) error {
+	if s.onSend != nil {
+		s.onSend(m)
+	}
+	return nil
+}
+
+func (s *hookingStream) Context() context.Context     { return context.Background() }
+func (s *hookingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *hookingStream) SendHeader(metadata.MD) error { return nil }
+func (s *hookingStream) SetTrailer(metadata.MD)       {}
+func (s *hookingStream) SendMsg(any) error            { return nil }
+func (s *hookingStream) RecvMsg(any) error            { return nil }
+
+func TestSendSnapshot_TokensRemainValidUnderSlowSend(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 6
+	const ttl = 100 * time.Millisecond
+	const sendDelay = 200 * time.Millisecond
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+	s.tokenTTL = ttl
+
+	var validateErrs []error
+	stream := &hookingStream{
+		onSend: func(resp *proto.GetMappingUpdateResponse) {
+			for _, m := range resp.Mapping {
+				if err := s.tokenStore.ValidateAndConsume(m.AuthToken, m.AccountId, m.Id); err != nil {
+					validateErrs = append(validateErrs, fmt.Errorf("svc %s: %w", m.Id, err))
+				}
+			}
+			time.Sleep(sendDelay)
+		},
+	}
+	conn := &proxyConnection{proxyID: "proxy-a", address: cluster, stream: stream}
+
+	require.NoError(t, s.sendSnapshot(context.Background(), conn))
+	require.Empty(t, validateErrs,
+		"tokens must remain valid even when batches are sent slowly: lazy per-batch generation guarantees freshness")
+}

management/internals/shared/grpc/server.go

@@ -522,10 +522,11 @@ func (s *Server) sendJob(ctx context.Context, peerKey wgtypes.Key, job *job.Even
 }
 
 func (s *Server) cancelPeerRoutines(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {
-	unlock := s.acquirePeerLockByUID(ctx, peer.Key)
+	uncanceledCTX := context.WithoutCancel(ctx)
+	unlock := s.acquirePeerLockByUID(uncanceledCTX, peer.Key)
 	defer unlock()
 
-	s.cancelPeerRoutinesWithoutLock(ctx, accountID, peer, streamStartTime)
+	s.cancelPeerRoutinesWithoutLock(uncanceledCTX, accountID, peer, streamStartTime)
 }
 
 func (s *Server) cancelPeerRoutinesWithoutLock(ctx context.Context, accountID string, peer *nbpeer.Peer, streamStartTime time.Time) {

management/internals/shared/grpc/sync_mappings_test.go

@@ -0,0 +1,411 @@
+package grpc
+
+import (
+	"context"
+	"fmt"
+	"sync"
+	"testing"
+	"time"
+
+	"github.com/golang/mock/gomock"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/metadata"
+
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+// syncRecordingStream is a mock ProxyService_SyncMappingsServer that records
+// sent messages and returns pre-loaded ack responses from Recv.
+type syncRecordingStream struct {
+	grpc.ServerStream
+
+	mu       sync.Mutex
+	sent     []*proto.SyncMappingsResponse
+	recvMsgs []*proto.SyncMappingsRequest
+	recvIdx  int
+}
+
+func (s *syncRecordingStream) Send(m *proto.SyncMappingsResponse) error {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.sent = append(s.sent, m)
+	return nil
+}
+
+func (s *syncRecordingStream) Recv() (*proto.SyncMappingsRequest, error) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	if s.recvIdx >= len(s.recvMsgs) {
+		return nil, fmt.Errorf("no more recv messages")
+	}
+	msg := s.recvMsgs[s.recvIdx]
+	s.recvIdx++
+	return msg, nil
+}
+
+func (s *syncRecordingStream) Context() context.Context     { return context.Background() }
+func (s *syncRecordingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *syncRecordingStream) SendHeader(metadata.MD) error { return nil }
+func (s *syncRecordingStream) SetTrailer(metadata.MD)       {}
+func (s *syncRecordingStream) SendMsg(any) error            { return nil }
+func (s *syncRecordingStream) RecvMsg(any) error            { return nil }
+
+func ackMsg() *proto.SyncMappingsRequest {
+	return &proto.SyncMappingsRequest{
+		Msg: &proto.SyncMappingsRequest_Ack{Ack: &proto.SyncMappingsAck{}},
+	}
+}
+
+func TestSendSnapshotSync_BatchesWithAcks(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 3
+	const totalServices = 7 // 3 + 3 + 1 → 3 batches, 3 acks (one per batch, including final)
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg(), ackMsg(), ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 3, "should send ceil(7/3) = 3 batches")
+
+	assert.Len(t, stream.sent[0].Mapping, 3)
+	assert.False(t, stream.sent[0].InitialSyncComplete)
+
+	assert.Len(t, stream.sent[1].Mapping, 3)
+	assert.False(t, stream.sent[1].InitialSyncComplete)
+
+	assert.Len(t, stream.sent[2].Mapping, 1)
+	assert.True(t, stream.sent[2].InitialSyncComplete)
+
+	// All 3 acks consumed — including the final batch.
+	assert.Equal(t, 3, stream.recvIdx)
+}
+
+func TestSendSnapshotSync_SingleBatchWaitsForAck(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 100
+	const totalServices = 5
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1)
+	assert.Len(t, stream.sent[0].Mapping, totalServices)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+	assert.Equal(t, 1, stream.recvIdx, "final batch ack must be consumed")
+}
+
+func TestSendSnapshotSync_EmptySnapshot(t *testing.T) {
+	const cluster = "cluster.example.com"
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(nil, nil)
+
+	s := newSnapshotTestServer(t, 500)
+	s.serviceManager = mgr
+
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{ackMsg()},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1, "empty snapshot must still send sync-complete")
+	assert.Empty(t, stream.sent[0].Mapping)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+	assert.Equal(t, 1, stream.recvIdx, "empty snapshot ack must be consumed")
+}
+
+func TestSendSnapshotSync_MissingAckReturnsError(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4 // 2 batches → 1 ack needed, but we provide none
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	// No acks available — Recv will return error.
+	stream := &syncRecordingStream{}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "receive ack")
+	// First batch should have been sent before the error.
+	require.Len(t, stream.sent, 1)
+}
+
+func TestSendSnapshotSync_WrongMessageInsteadOfAck(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	// Send an init message instead of an ack.
+	stream := &syncRecordingStream{
+		recvMsgs: []*proto.SyncMappingsRequest{
+			{Msg: &proto.SyncMappingsRequest_Init{Init: &proto.SyncMappingsInit{ProxyId: "bad"}}},
+		},
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.Error(t, err)
+	assert.Contains(t, err.Error(), "expected ack")
+}
+
+func TestSendSnapshotSync_BackPressureOrdering(t *testing.T) {
+	// Verify batches are sent strictly sequentially — batch N+1 is not sent
+	// until the ack for batch N is received, including the final batch.
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 6 // 3 batches, 3 acks
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+
+	var mu sync.Mutex
+	var events []string
+
+	// Build a stream that logs send/recv events so we can verify ordering.
+	ackCh := make(chan struct{}, 3)
+	stream := &orderTrackingStream{
+		mu:     &mu,
+		events: &events,
+		ackCh:  ackCh,
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	// Feed acks asynchronously after a short delay to simulate real proxy.
+	go func() {
+		for range 3 {
+			time.Sleep(10 * time.Millisecond)
+			ackCh <- struct{}{}
+		}
+	}()
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+
+	mu.Lock()
+	defer mu.Unlock()
+
+	// Expected: send, recv-ack, send, recv-ack, send, recv-ack.
+	require.Len(t, events, 6)
+	assert.Equal(t, "send", events[0])
+	assert.Equal(t, "recv", events[1])
+	assert.Equal(t, "send", events[2])
+	assert.Equal(t, "recv", events[3])
+	assert.Equal(t, "send", events[4])
+	assert.Equal(t, "recv", events[5])
+}
+
+// orderTrackingStream logs "send" and "recv" events and blocks Recv until
+// an ack is signaled via ackCh.
+type orderTrackingStream struct {
+	grpc.ServerStream
+	mu     *sync.Mutex
+	events *[]string
+	ackCh  chan struct{}
+}
+
+func (s *orderTrackingStream) Send(_ *proto.SyncMappingsResponse) error {
+	s.mu.Lock()
+	*s.events = append(*s.events, "send")
+	s.mu.Unlock()
+	return nil
+}
+
+func (s *orderTrackingStream) Recv() (*proto.SyncMappingsRequest, error) {
+	<-s.ackCh
+	s.mu.Lock()
+	*s.events = append(*s.events, "recv")
+	s.mu.Unlock()
+	return ackMsg(), nil
+}
+
+func (s *orderTrackingStream) Context() context.Context     { return context.Background() }
+func (s *orderTrackingStream) SetHeader(metadata.MD) error  { return nil }
+func (s *orderTrackingStream) SendHeader(metadata.MD) error { return nil }
+func (s *orderTrackingStream) SetTrailer(metadata.MD)       {}
+func (s *orderTrackingStream) SendMsg(any) error            { return nil }
+func (s *orderTrackingStream) RecvMsg(any) error            { return nil }
+
+func TestSendSnapshotSync_TokensGeneratedPerBatch(t *testing.T) {
+	const cluster = "cluster.example.com"
+	const batchSize = 2
+	const totalServices = 4
+	const ttl = 100 * time.Millisecond
+	const ackDelay = 200 * time.Millisecond
+
+	ctrl := gomock.NewController(t)
+	mgr := rpservice.NewMockManager(ctrl)
+	mgr.EXPECT().GetGlobalServices(gomock.Any()).Return(makeServices(totalServices, cluster), nil)
+
+	s := newSnapshotTestServer(t, batchSize)
+	s.serviceManager = mgr
+	s.tokenTTL = ttl
+
+	// Build a stream that validates tokens immediately on Send, then
+	// delays the ack to ensure the next batch's tokens are generated fresh.
+	var validateErrs []error
+	ackCh := make(chan struct{}, 2)
+	stream := &tokenValidatingSyncStream{
+		tokenStore:   s.tokenStore,
+		validateErrs: &validateErrs,
+		ackCh:        ackCh,
+	}
+	conn := &proxyConnection{
+		proxyID:    "proxy-a",
+		address:    cluster,
+		syncStream: stream,
+	}
+
+	go func() {
+		// Delay first ack so that if tokens were all generated upfront they'd expire.
+		time.Sleep(ackDelay)
+		ackCh <- struct{}{}
+		// Final batch ack — immediate.
+		ackCh <- struct{}{}
+	}()
+
+	err := s.sendSnapshotSync(context.Background(), conn, stream)
+	require.NoError(t, err)
+	require.Empty(t, validateErrs,
+		"tokens must remain valid: per-batch generation guarantees freshness")
+}
+
+type tokenValidatingSyncStream struct {
+	grpc.ServerStream
+	tokenStore   *OneTimeTokenStore
+	validateErrs *[]error
+	ackCh        chan struct{}
+}
+
+func (s *tokenValidatingSyncStream) Send(m *proto.SyncMappingsResponse) error {
+	for _, mapping := range m.Mapping {
+		if err := s.tokenStore.ValidateAndConsume(mapping.AuthToken, mapping.AccountId, mapping.Id); err != nil {
+			*s.validateErrs = append(*s.validateErrs, fmt.Errorf("svc %s: %w", mapping.Id, err))
+		}
+	}
+	return nil
+}
+
+func (s *tokenValidatingSyncStream) Recv() (*proto.SyncMappingsRequest, error) {
+	<-s.ackCh
+	return ackMsg(), nil
+}
+
+func (s *tokenValidatingSyncStream) Context() context.Context     { return context.Background() }
+func (s *tokenValidatingSyncStream) SetHeader(metadata.MD) error  { return nil }
+func (s *tokenValidatingSyncStream) SendHeader(metadata.MD) error { return nil }
+func (s *tokenValidatingSyncStream) SetTrailer(metadata.MD)       {}
+func (s *tokenValidatingSyncStream) SendMsg(any) error            { return nil }
+func (s *tokenValidatingSyncStream) RecvMsg(any) error            { return nil }
+
+func TestConnectionSendResponse_RoutesToSyncStream(t *testing.T) {
+	stream := &syncRecordingStream{}
+	conn := &proxyConnection{
+		syncStream: stream,
+	}
+
+	resp := &proto.GetMappingUpdateResponse{
+		Mapping: []*proto.ProxyMapping{
+			{Id: "svc-1", AccountId: "acct-1", Domain: "example.com"},
+		},
+		InitialSyncComplete: true,
+	}
+
+	err := conn.sendResponse(resp)
+	require.NoError(t, err)
+
+	require.Len(t, stream.sent, 1)
+	assert.Len(t, stream.sent[0].Mapping, 1)
+	assert.Equal(t, "svc-1", stream.sent[0].Mapping[0].Id)
+	assert.True(t, stream.sent[0].InitialSyncComplete)
+}
+
+func TestConnectionSendResponse_RoutesToLegacyStream(t *testing.T) {
+	stream := &recordingStream{}
+	conn := &proxyConnection{
+		stream: stream,
+	}
+
+	resp := &proto.GetMappingUpdateResponse{
+		Mapping: []*proto.ProxyMapping{
+			{Id: "svc-2", AccountId: "acct-2"},
+		},
+	}
+
+	err := conn.sendResponse(resp)
+	require.NoError(t, err)
+
+	require.Len(t, stream.messages, 1)
+	assert.Equal(t, "svc-2", stream.messages[0].Mapping[0].Id)
+}

management/internals/shared/grpc/validate_session_test.go

@@ -102,7 +102,7 @@ func generateSessionKeyPair(t *testing.T) (string, string) {
 
 func createSessionToken(t *testing.T, privKeyB64, userID, domain string) string {
 	t.Helper()
-	token, err := sessionkey.SignToken(privKeyB64, userID, domain, auth.MethodOIDC, time.Hour)
+	token, err := sessionkey.SignToken(privKeyB64, userID, domain, auth.MethodOIDC, nil, time.Hour)
 	require.NoError(t, err)
 	return token
 }
@@ -125,6 +125,7 @@ func TestValidateSession_UserAllowed(t *testing.T) {
 	assert.True(t, resp.Valid, "User should be allowed access")
 	assert.Equal(t, "allowedUserId", resp.UserId)
 	assert.Empty(t, resp.DeniedReason)
+	assert.Equal(t, []string{"allowedGroupId"}, resp.GetPeerGroupIds(), "PeerGroupIds must mirror the resolved user's group memberships")
 }
 
 func TestValidateSession_UserNotInAllowedGroup(t *testing.T) {
@@ -145,6 +146,7 @@ func TestValidateSession_UserNotInAllowedGroup(t *testing.T) {
 	assert.False(t, resp.Valid, "User not in group should be denied")
 	assert.Equal(t, "not_in_group", resp.DeniedReason)
 	assert.Equal(t, "nonGroupUserId", resp.UserId)
+	assert.Empty(t, resp.GetPeerGroupIds(), "PeerGroupIds must mirror the resolved user's actual (empty) memberships on denial")
 }
 
 func TestValidateSession_UserInDifferentAccount(t *testing.T) {
@@ -322,21 +324,29 @@ func (m *testValidateSessionServiceManager) GetServiceByDomain(ctx context.Conte
 	return m.store.GetServiceByDomain(ctx, domain)
 }
 
-func (m *testValidateSessionServiceManager) GetActiveClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
+func (m *testValidateSessionServiceManager) GetClusters(_ context.Context, _, _ string) ([]proxy.Cluster, error) {
 	return nil, nil
 }
 
+func (m *testValidateSessionServiceManager) DeleteAccountCluster(_ context.Context, _, _, _ string) error {
+	return nil
+}
+
 type testValidateSessionProxyManager struct{}
 
-func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _ string, _ *string, _ *proxy.Capabilities) error {
+func (m *testValidateSessionProxyManager) Connect(_ context.Context, _, _, _, _ string, _ *string, _ *proxy.Capabilities) (*proxy.Proxy, error) {
+	return nil, nil
+}
+
+func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _, _ string) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) Disconnect(_ context.Context, _ string) error {
+func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _ *proxy.Proxy) error {
 	return nil
 }
 
-func (m *testValidateSessionProxyManager) Heartbeat(_ context.Context, _, _, _ string) error {
+func (m *testValidateSessionProxyManager) DeleteAccountCluster(_ context.Context, _, _ string) error {
 	return nil
 }
 

management/server/account.go

@@ -291,10 +291,15 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		return nil, status.NewPermissionDeniedError()
 	}
 
+	// Canonicalize the incoming range so a caller-supplied prefix with host bits
+	// (e.g. 100.64.1.1/16) compares equal to the masked form stored on network.Net.
+	newSettings.NetworkRange = newSettings.NetworkRange.Masked()
+
 	var oldSettings *types.Settings
 	var updateAccountPeers bool
 	var groupChangesAffectPeers bool
 	var reloadReverseProxy bool
+	var effectiveOldNetworkRange netip.Prefix
 
 	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
 		var groupsUpdated bool
@@ -308,6 +313,16 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			return err
 		}
 
+		// No lock: the transaction already holds Settings(Update), and network.Net is
+		// only mutated by reallocateAccountPeerIPs, which is reachable only through
+		// this same code path. A Share lock here would extend an unnecessary row lock
+		// and complicate ordering against updatePeerIPv6InTransaction.
+		network, err := transaction.GetAccountNetwork(ctx, store.LockingStrengthNone, accountID)
+		if err != nil {
+			return fmt.Errorf("get account network: %w", err)
+		}
+		effectiveOldNetworkRange = prefixFromIPNet(network.Net)
+
 		if oldSettings.Extra != nil && newSettings.Extra != nil &&
 			oldSettings.Extra.PeerApprovalEnabled && !newSettings.Extra.PeerApprovalEnabled {
 			approvedCount, err := transaction.ApproveAccountPeers(ctx, accountID)
@@ -321,7 +336,7 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 			}
 		}
 
-		if oldSettings.NetworkRange != newSettings.NetworkRange {
+		if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
 			if err = am.reallocateAccountPeerIPs(ctx, transaction, accountID, newSettings.NetworkRange); err != nil {
 				return err
 			}
@@ -396,9 +411,9 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountDNSDomainUpdated, eventMeta)
 	}
-	if oldSettings.NetworkRange != newSettings.NetworkRange {
+	if newSettings.NetworkRange.IsValid() && newSettings.NetworkRange != effectiveOldNetworkRange {
 		eventMeta := map[string]any{
-			"old_network_range": oldSettings.NetworkRange.String(),
+			"old_network_range": effectiveOldNetworkRange.String(),
 			"new_network_range": newSettings.NetworkRange.String(),
 		}
 		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountNetworkRangeUpdated, eventMeta)
@@ -443,6 +458,22 @@ func ipv6SettingsChanged(old, updated *types.Settings) bool {
 	return !slices.Equal(oldGroups, newGroups)
 }
 
+// prefixFromIPNet returns the overlay prefix actually allocated on the account
+// network, or an invalid prefix if none is set. Settings.NetworkRange is a
+// user-facing override that is empty on legacy accounts, so the effective
+// range must be read from network.Net to compare against an incoming update.
+func prefixFromIPNet(ipNet net.IPNet) netip.Prefix {
+	if ipNet.IP == nil {
+		return netip.Prefix{}
+	}
+	addr, ok := netip.AddrFromSlice(ipNet.IP)
+	if !ok {
+		return netip.Prefix{}
+	}
+	ones, _ := ipNet.Mask.Size()
+	return netip.PrefixFrom(addr.Unmap(), ones)
+}
+
 func (am *DefaultAccountManager) validateSettingsUpdate(ctx context.Context, transaction store.Store, newSettings, oldSettings *types.Settings, userID, accountID string) error {
 	halfYearLimit := 180 * 24 * time.Hour
 	if newSettings.PeerLoginExpiration > halfYearLimit {
@@ -1837,35 +1868,32 @@ func domainIsUpToDate(domain string, domainCategory string, userAuth auth.UserAu
 	return domainCategory == types.PrivateCategory || userAuth.DomainCategory != types.PrivateCategory || domain != userAuth.Domain
 }
 
+// SyncAndMarkPeer is the per-Sync entry point: it refreshes the peer's
+// network map and then marks the peer connected with a session token
+// derived from syncTime (the moment the gRPC stream opened). Any
+// concurrent stream that started earlier loses the optimistic-lock race
+// in MarkPeerConnected and bails without writing.
 func (am *DefaultAccountManager) SyncAndMarkPeer(ctx context.Context, accountID string, peerPubKey string, meta nbpeer.PeerSystemMeta, realIP net.IP, syncTime time.Time) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error) {
 	peer, netMap, postureChecks, dnsfwdPort, err := am.SyncPeer(ctx, types.PeerSync{WireGuardPubKey: peerPubKey, Meta: meta}, accountID)
 	if err != nil {
 		return nil, nil, nil, 0, fmt.Errorf("error syncing peer: %w", err)
 	}
 
-	err = am.MarkPeerConnected(ctx, peerPubKey, true, realIP, accountID, syncTime)
-	if err != nil {
+	if err := am.MarkPeerConnected(ctx, peerPubKey, realIP, accountID, syncTime.UnixNano()); err != nil {
 		log.WithContext(ctx).Warnf("failed marking peer as connected %s %v", peerPubKey, err)
 	}
 
 	return peer, netMap, postureChecks, dnsfwdPort, nil
 }
 
+// OnPeerDisconnected is invoked when a sync stream ends. It marks the
+// peer disconnected only when the stored SessionStartedAt matches the
+// nanosecond token derived from streamStartTime — i.e. only when this
+// is the stream that currently owns the peer's session. A mismatch
+// means a newer stream has already replaced us, so the disconnect is
+// dropped.
 func (am *DefaultAccountManager) OnPeerDisconnected(ctx context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
-	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
-	if err != nil {
-		log.WithContext(ctx).Warnf("failed to get peer %s for disconnect check: %v", peerPubKey, err)
-		return nil
-	}
-
-	if peer.Status.LastSeen.After(streamStartTime) {
-		log.WithContext(ctx).Tracef("peer %s has newer activity (lastSeen=%s > streamStart=%s), skipping disconnect",
-			peerPubKey, peer.Status.LastSeen.Format(time.RFC3339), streamStartTime.Format(time.RFC3339))
-		return nil
-	}
-
-	err = am.MarkPeerConnected(ctx, peerPubKey, false, nil, accountID, time.Now().UTC())
-	if err != nil {
+	if err := am.MarkPeerDisconnected(ctx, peerPubKey, accountID, streamStartTime.UnixNano()); err != nil {
 		log.WithContext(ctx).Warnf("failed marking peer as disconnected %s %v", peerPubKey, err)
 	}
 	return nil
@@ -2487,6 +2515,18 @@ func (am *DefaultAccountManager) buildIPv6AllowedPeers(ctx context.Context, tran
 			allowedPeers[peerID] = struct{}{}
 		}
 	}
+
+	// Embedded proxy peers sit outside regular group membership but must
+	// participate in any v6-enabled overlay to reach v6-only peers.
+	peers, err := transaction.GetAccountPeers(ctx, store.LockingStrengthNone, accountID, "", "")
+	if err != nil {
+		return nil, fmt.Errorf("get peers: %w", err)
+	}
+	for _, p := range peers {
+		if p.ProxyMeta.Embedded {
+			allowedPeers[p.ID] = struct{}{}
+		}
+	}
 	return allowedPeers, nil
 }
 

management/server/account/manager.go

@@ -61,7 +61,8 @@ type Manager interface {
 	GetUserFromUserAuth(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
 	ListUsers(ctx context.Context, accountID string) ([]*types.User, error)
 	GetPeers(ctx context.Context, accountID, userID, nameFilter, ipFilter string) ([]*nbpeer.Peer, error)
-	MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error
+	MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error
+	MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error
 	DeletePeer(ctx context.Context, accountID, peerID, userID string) error
 	UpdatePeer(ctx context.Context, accountID, userID string, p *nbpeer.Peer) (*nbpeer.Peer, error)
 	UpdatePeerIP(ctx context.Context, accountID, userID, peerID string, newIP netip.Addr) error

management/server/account/manager_mock.go

@@ -1305,17 +1305,31 @@ func (mr *MockManagerMockRecorder) LoginPeer(ctx, login interface{}) *gomock.Cal
 }
 
 // MarkPeerConnected mocks base method.
-func (m *MockManager) MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
+func (m *MockManager) MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "MarkPeerConnected", ctx, peerKey, connected, realIP, accountID, syncTime)
+	ret := m.ctrl.Call(m, "MarkPeerConnected", ctx, peerKey, realIP, accountID, sessionStartedAt)
 	ret0, _ := ret[0].(error)
 	return ret0
 }
 
 // MarkPeerConnected indicates an expected call of MarkPeerConnected.
-func (mr *MockManagerMockRecorder) MarkPeerConnected(ctx, peerKey, connected, realIP, accountID, syncTime interface{}) *gomock.Call {
+func (mr *MockManagerMockRecorder) MarkPeerConnected(ctx, peerKey, realIP, accountID, sessionStartedAt interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerConnected", reflect.TypeOf((*MockManager)(nil).MarkPeerConnected), ctx, peerKey, connected, realIP, accountID, syncTime)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerConnected", reflect.TypeOf((*MockManager)(nil).MarkPeerConnected), ctx, peerKey, realIP, accountID, sessionStartedAt)
+}
+
+// MarkPeerDisconnected mocks base method.
+func (m *MockManager) MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "MarkPeerDisconnected", ctx, peerKey, accountID, sessionStartedAt)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// MarkPeerDisconnected indicates an expected call of MarkPeerDisconnected.
+func (mr *MockManagerMockRecorder) MarkPeerDisconnected(ctx, peerKey, accountID, sessionStartedAt interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerDisconnected", reflect.TypeOf((*MockManager)(nil).MarkPeerDisconnected), ctx, peerKey, accountID, sessionStartedAt)
 }
 
 // OnPeerDisconnected mocks base method.

management/server/account_test.go

@@ -1813,7 +1813,7 @@ func TestDefaultAccountManager_UpdatePeer_PeerLoginExpiration(t *testing.T) {
 	accountID, err := manager.GetAccountIDByUserID(context.Background(), auth.UserAuth{UserId: userID})
 	require.NoError(t, err, "unable to get the account")
 
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	_, err = manager.UpdateAccountSettings(context.Background(), accountID, userID, &types.Settings{
@@ -1884,7 +1884,7 @@ func TestDefaultAccountManager_MarkPeerConnected_PeerLoginExpiration(t *testing.
 	require.NoError(t, err, "unable to get the account")
 
 	// when we mark peer as connected, the peer login expiration routine should trigger
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	failed := waitTimeout(wg, time.Second)
@@ -1910,15 +1910,16 @@ func TestDefaultAccountManager_OnPeerDisconnected_LastSeenCheck(t *testing.T) {
 	}, false)
 	require.NoError(t, err, "unable to add peer")
 
-	t.Run("disconnect peer when streamStartTime is after LastSeen", func(t *testing.T) {
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, time.Now().UTC())
+	t.Run("disconnect peer when session token matches", func(t *testing.T) {
+		streamStartTime := time.Now().UTC()
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, streamStartTime.UnixNano())
 		require.NoError(t, err, "unable to mark peer connected")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err, "unable to get peer")
 		require.True(t, peer.Status.Connected, "peer should be connected")
-
-		streamStartTime := time.Now().UTC()
+		require.Equal(t, streamStartTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should equal the token we passed in")
 
 		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, streamStartTime)
 		require.NoError(t, err)
@@ -1926,49 +1927,127 @@ func TestDefaultAccountManager_OnPeerDisconnected_LastSeenCheck(t *testing.T) {
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.False(t, peer.Status.Connected, "peer should be disconnected")
+		require.Equal(t, int64(0), peer.Status.SessionStartedAt, "SessionStartedAt should be reset to 0")
 	})
 
-	t.Run("skip disconnect when LastSeen is after streamStartTime (zombie stream protection)", func(t *testing.T) {
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, time.Now().UTC())
+	t.Run("skip disconnect when stored session is newer (zombie stream protection)", func(t *testing.T) {
+		// Newer stream wins on connect (sets SessionStartedAt = now ns).
+		streamStartTime := time.Now().UTC()
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, streamStartTime.UnixNano())
 		require.NoError(t, err, "unable to mark peer connected")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should be connected")
 
-		streamStartTime := peer.Status.LastSeen.Add(-1 * time.Hour)
+		// Older stream tries to mark disconnect with its own (older) session token —
+		// fencing kicks in and the write is dropped.
+		staleStreamStartTime := streamStartTime.Add(-1 * time.Hour)
 
-		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, streamStartTime)
+		err = manager.OnPeerDisconnected(context.Background(), accountID, peerPubKey, staleStreamStartTime)
 		require.NoError(t, err)
 
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected,
-			"peer should remain connected because LastSeen > streamStartTime (zombie stream protection)")
+			"peer should remain connected because the stored session is newer than the disconnect token")
+		require.Equal(t, streamStartTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should still hold the winning stream's token")
 	})
 
-	t.Run("skip stale connect when peer already has newer LastSeen (blocked goroutine protection)", func(t *testing.T) {
+	t.Run("skip stale connect when stored session is newer (blocked goroutine protection)", func(t *testing.T) {
 		node2SyncTime := time.Now().UTC()
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, node2SyncTime)
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, node2SyncTime.UnixNano())
 		require.NoError(t, err, "node 2 should connect peer")
 
 		peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should be connected")
-		require.Equal(t, node2SyncTime.Unix(), peer.Status.LastSeen.Unix(), "LastSeen should be node2SyncTime")
+		require.Equal(t, node2SyncTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should equal node2SyncTime token")
 
 		node1StaleSyncTime := node2SyncTime.Add(-1 * time.Minute)
-		err = manager.MarkPeerConnected(context.Background(), peerPubKey, true, nil, accountID, node1StaleSyncTime)
+		err = manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, node1StaleSyncTime.UnixNano())
 		require.NoError(t, err, "stale connect should not return error")
 
 		peer, err = manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
 		require.NoError(t, err)
 		require.True(t, peer.Status.Connected, "peer should still be connected")
-		require.Equal(t, node2SyncTime.Unix(), peer.Status.LastSeen.Unix(),
-			"LastSeen should NOT be overwritten by stale syncTime from blocked goroutine")
+		require.Equal(t, node2SyncTime.UnixNano(), peer.Status.SessionStartedAt,
+			"SessionStartedAt should NOT be overwritten by stale token from blocked goroutine")
 	})
 }
 
+// TestDefaultAccountManager_MarkPeerConnected_ConcurrentRace exercises the
+// fencing protocol under contention: many goroutines race to mark the
+// same peer connected with distinct session tokens at the same time.
+// The contract is that the highest token always wins and is what remains
+// in the store, regardless of execution order.
+func TestDefaultAccountManager_MarkPeerConnected_ConcurrentRace(t *testing.T) {
+	manager, _, err := createManager(t)
+	require.NoError(t, err, "unable to create account manager")
+
+	accountID, err := manager.GetAccountIDByUserID(context.Background(), auth.UserAuth{UserId: userID})
+	require.NoError(t, err, "unable to get account")
+
+	key, err := wgtypes.GenerateKey()
+	require.NoError(t, err, "unable to generate WireGuard key")
+	peerPubKey := key.PublicKey().String()
+
+	_, _, _, err = manager.AddPeer(context.Background(), "", "", userID, &nbpeer.Peer{
+		Key:  peerPubKey,
+		Meta: nbpeer.PeerSystemMeta{Hostname: "race-peer"},
+	}, false)
+	require.NoError(t, err, "unable to add peer")
+
+	const workers = 16
+	base := time.Now().UTC().UnixNano()
+	tokens := make([]int64, workers)
+	for i := range tokens {
+		// Spread tokens by 1ms so the comparison is unambiguous; the
+		// largest is index workers-1.
+		tokens[i] = base + int64(i)*int64(time.Millisecond)
+	}
+	expected := tokens[workers-1]
+
+	var ready sync.WaitGroup
+	ready.Add(workers)
+	var start sync.WaitGroup
+	start.Add(1)
+	var done sync.WaitGroup
+	done.Add(workers)
+
+	// require.* calls t.FailNow which is documented as unsafe from
+	// non-test goroutines (it calls runtime.Goexit on the wrong stack and
+	// races with the WaitGroup). Collect errors here and assert from the
+	// main goroutine after done.Wait().
+	errs := make(chan error, workers)
+
+	for i := 0; i < workers; i++ {
+		token := tokens[i]
+		go func() {
+			defer done.Done()
+			ready.Done()
+			start.Wait()
+			errs <- manager.MarkPeerConnected(context.Background(), peerPubKey, nil, accountID, token)
+		}()
+	}
+
+	ready.Wait()
+	start.Done()
+	done.Wait()
+	close(errs)
+	for err := range errs {
+		require.NoError(t, err, "MarkPeerConnected must not error under contention")
+	}
+
+	peer, err := manager.Store.GetPeerByPeerPubKey(context.Background(), store.LockingStrengthNone, peerPubKey)
+	require.NoError(t, err)
+	require.True(t, peer.Status.Connected, "peer should be connected after the race")
+	require.Equal(t, expected, peer.Status.SessionStartedAt,
+		"the largest token must win regardless of execution order")
+}
+
 func TestDefaultAccountManager_UpdateAccountSettings_PeerLoginExpiration(t *testing.T) {
 	manager, _, err := createManager(t)
 	require.NoError(t, err, "unable to create account manager")
@@ -1991,7 +2070,7 @@ func TestDefaultAccountManager_UpdateAccountSettings_PeerLoginExpiration(t *test
 	account, err := manager.Store.GetAccount(context.Background(), accountID)
 	require.NoError(t, err, "unable to get the account")
 
-	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), true, nil, accountID, time.Now().UTC())
+	err = manager.MarkPeerConnected(context.Background(), key.PublicKey().String(), nil, accountID, time.Now().UTC().UnixNano())
 	require.NoError(t, err, "unable to mark peer connected")
 
 	wg := &sync.WaitGroup{}
@@ -3970,6 +4049,96 @@ func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangeChange(t *testi
 	}
 }
 
+// TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved guards against
+// peer IP reallocation when a settings update carries the network range that is already
+// in use. Legacy accounts have Settings.NetworkRange unset in the DB while network.Net
+// holds the actual allocated overlay; the dashboard backfills the GET response from
+// network.Net and echoes the value back on PUT, so the diff must be against the
+// effective range to avoid renumbering every peer on an unrelated settings change.
+func TestDefaultAccountManager_UpdateAccountSettings_NetworkRangePreserved(t *testing.T) {
+	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
+	ctx := context.Background()
+
+	settings, err := manager.Store.GetAccountSettings(ctx, store.LockingStrengthNone, account.Id)
+	require.NoError(t, err)
+	require.False(t, settings.NetworkRange.IsValid(), "precondition: new accounts leave Settings.NetworkRange unset")
+
+	network, err := manager.Store.GetAccountNetwork(ctx, store.LockingStrengthNone, account.Id)
+	require.NoError(t, err)
+	require.NotNil(t, network.Net.IP, "precondition: network.Net should be allocated")
+	addr, ok := netip.AddrFromSlice(network.Net.IP)
+	require.True(t, ok)
+	ones, _ := network.Net.Mask.Size()
+	effective := netip.PrefixFrom(addr.Unmap(), ones)
+	require.True(t, effective.IsValid())
+
+	before := map[string]netip.Addr{peer1.ID: peer1.IP, peer2.ID: peer2.IP, peer3.ID: peer3.IP}
+
+	// Round-trip the effective range as if the dashboard echoed back the GET-backfilled value.
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               effective,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err := manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	require.Len(t, peers, len(before))
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when range matches effective", p.ID)
+	}
+
+	// Carrying the same range with host bits set must also be a no-op once canonicalized.
+	hostBitsForm := netip.PrefixFrom(peer1.IP, ones)
+	require.NotEqual(t, effective, hostBitsForm, "precondition: host-bit form should differ before masking")
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               hostBitsForm,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change for host-bit-set equivalent range", p.ID)
+	}
+
+	// Omitting NetworkRange (invalid prefix) must also be a no-op.
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.Equal(t, before[p.ID], p.IP, "peer %s IP should not change when NetworkRange omitted", p.ID)
+	}
+
+	// Sanity: an actually different range still triggers reallocation.
+	newRange := netip.MustParsePrefix("100.99.0.0/16")
+	_, err = manager.UpdateAccountSettings(ctx, account.Id, userID, &types.Settings{
+		PeerLoginExpirationEnabled: true,
+		PeerLoginExpiration:        types.DefaultPeerLoginExpiration,
+		NetworkRange:               newRange,
+		Extra:                      &types.ExtraSettings{},
+	})
+	require.NoError(t, err)
+
+	peers, err = manager.Store.GetAccountPeers(ctx, store.LockingStrengthNone, account.Id, "", "")
+	require.NoError(t, err)
+	for _, p := range peers {
+		assert.True(t, newRange.Contains(p.IP), "peer %s should be in new range %s, got %s", p.ID, newRange, p.IP)
+		assert.NotEqual(t, before[p.ID], p.IP, "peer %s IP should change on real range update", p.ID)
+	}
+}
+
 func TestDefaultAccountManager_UpdateAccountSettings_IPv6EnabledGroups(t *testing.T) {
 	manager, _, account, peer1, peer2, peer3 := setupNetworkMapTest(t)
 	ctx := context.Background()

management/server/http/handler.go

@@ -15,15 +15,13 @@ import (
 	"github.com/netbirdio/netbird/management/server/types"
 
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
-	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxytoken"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	reverseproxymanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service/manager"
 
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
 	idpmanager "github.com/netbirdio/netbird/management/server/idp"
 
-	"github.com/netbirdio/management-integrations/integrations"
-
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map"
 	"github.com/netbirdio/netbird/management/internals/modules/zones"
 	zonesManager "github.com/netbirdio/netbird/management/internals/modules/zones/manager"
@@ -32,12 +30,10 @@ import (
 	"github.com/netbirdio/netbird/management/server/account"
 	"github.com/netbirdio/netbird/management/server/settings"
 
-	"github.com/netbirdio/netbird/management/server/integrations/port_forwarding"
 	"github.com/netbirdio/netbird/management/server/permissions"
 
 	"github.com/netbirdio/netbird/management/server/http/handlers/proxy"
 
-	nbpeers "github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/server/auth"
 	"github.com/netbirdio/netbird/management/server/geolocation"
 	nbgroups "github.com/netbirdio/netbird/management/server/groups"
@@ -56,17 +52,14 @@ import (
 	"github.com/netbirdio/netbird/management/server/http/middleware"
 	"github.com/netbirdio/netbird/management/server/http/middleware/bypass"
 	nbinstance "github.com/netbirdio/netbird/management/server/instance"
-	"github.com/netbirdio/netbird/management/server/integrations/integrated_validator"
 	nbnetworks "github.com/netbirdio/netbird/management/server/networks"
 	"github.com/netbirdio/netbird/management/server/networks/resources"
 	"github.com/netbirdio/netbird/management/server/networks/routers"
 	"github.com/netbirdio/netbird/management/server/telemetry"
 )
 
-const apiPrefix = "/api"
-
 // NewAPIHandler creates the Management service HTTP API handler registering all the available endpoints.
-func NewAPIHandler(ctx context.Context, accountManager account.Manager, networksManager nbnetworks.Manager, resourceManager resources.Manager, routerManager routers.Manager, groupsManager nbgroups.Manager, LocationManager geolocation.Geolocation, authManager auth.Manager, appMetrics telemetry.AppMetrics, integratedValidator integrated_validator.IntegratedValidator, proxyController port_forwarding.Controller, permissionsManager permissions.Manager, peersManager nbpeers.Manager, settingsManager settings.Manager, zManager zones.Manager, rManager records.Manager, networkMapController network_map.Controller, idpManager idpmanager.Manager, serviceManager service.Manager, reverseProxyDomainManager *manager.Manager, reverseProxyAccessLogsManager accesslogs.Manager, proxyGRPCServer *nbgrpc.ProxyServiceServer, trustedHTTPProxies []netip.Prefix, rateLimiter *middleware.APIRateLimiter) (http.Handler, error) {
+func NewAPIHandler(ctx context.Context, router *mux.Router, accountManager account.Manager, networksManager nbnetworks.Manager, resourceManager resources.Manager, routerManager routers.Manager, groupsManager nbgroups.Manager, LocationManager geolocation.Geolocation, authManager auth.Manager, appMetrics telemetry.AppMetrics, permissionsManager permissions.Manager, settingsManager settings.Manager, zManager zones.Manager, rManager records.Manager, networkMapController network_map.Controller, idpManager idpmanager.Manager, serviceManager service.Manager, reverseProxyDomainManager *manager.Manager, reverseProxyAccessLogsManager accesslogs.Manager, proxyGRPCServer *nbgrpc.ProxyServiceServer, trustedHTTPProxies []netip.Prefix, rateLimiter *middleware.APIRateLimiter, isValidChildAccount middleware.IsValidChildAccountFunc) (http.Handler, error) {
 
 	// Register bypass paths for unauthenticated endpoints
 	if err := bypass.AddBypassPath("/api/instance"); err != nil {
@@ -100,25 +93,16 @@ func NewAPIHandler(ctx context.Context, accountManager account.Manager, networks
 		accountManager.GetUserFromUserAuth,
 		rateLimiter,
 		appMetrics.GetMeter(),
+		isValidChildAccount,
 	)
 
 	corsMiddleware := cors.AllowAll()
 
-	rootRouter := mux.NewRouter()
 	metricsMiddleware := appMetrics.HTTPMiddleware()
 
-	prefix := apiPrefix
-	router := rootRouter.PathPrefix(prefix).Subrouter()
-
 	router.Use(metricsMiddleware.Handler, corsMiddleware.Handler, authMiddleware.Handler)
 
-	if _, err := integrations.RegisterHandlers(ctx, prefix, router, accountManager, integratedValidator, appMetrics.GetMeter(), permissionsManager, peersManager, proxyController, settingsManager); err != nil {
-		return nil, fmt.Errorf("register integrations endpoints: %w", err)
-	}
-
-	// Check if embedded IdP is enabled for instance manager
-	embeddedIdP, embeddedIdpEnabled := idpManager.(*idpmanager.EmbeddedIdPManager)
-	instanceManager, err := nbinstance.NewManager(ctx, accountManager.GetStore(), embeddedIdP)
+	instanceManager, err := nbinstance.NewManager(ctx, accountManager.GetStore(), idpManager)
 	if err != nil {
 		return nil, fmt.Errorf("failed to create instance manager: %w", err)
 	}
@@ -154,10 +138,5 @@ func NewAPIHandler(ctx context.Context, accountManager account.Manager, networks
 		oauthHandler.RegisterEndpoints(router)
 	}
 
-	// Mount embedded IdP handler at /oauth2 path if configured
-	if embeddedIdpEnabled {
-		rootRouter.PathPrefix("/oauth2").Handler(corsMiddleware.Handler(embeddedIdP.Handler()))
-	}
-
-	return rootRouter, nil
+	return router, nil
 }

management/server/http/handlers/proxy/auth_callback_integration_test.go

@@ -444,7 +444,7 @@ func (m *testServiceManager) GetServiceByDomain(ctx context.Context, domain stri
 	return m.store.GetServiceByDomain(ctx, domain)
 }
 
-func (m *testServiceManager) GetActiveClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
+func (m *testServiceManager) GetClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
 	return nil, nil
 }
 

management/server/http/middleware/auth_middleware.go

@@ -11,8 +11,6 @@ import (
 	log "github.com/sirupsen/logrus"
 	"go.opentelemetry.io/otel/metric"
 
-	"github.com/netbirdio/management-integrations/integrations"
-
 	serverauth "github.com/netbirdio/netbird/management/server/auth"
 	nbcontext "github.com/netbirdio/netbird/management/server/context"
 	"github.com/netbirdio/netbird/management/server/http/middleware/bypass"
@@ -27,6 +25,8 @@ type SyncUserJWTGroupsFunc func(ctx context.Context, userAuth auth.UserAuth) err
 
 type GetUserFromUserAuthFunc func(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
 
+type IsValidChildAccountFunc func(ctx context.Context, userID, accountID, childAccountID string) bool
+
 // AuthMiddleware middleware to verify personal access tokens (PAT) and JWT tokens
 type AuthMiddleware struct {
 	authManager         serverauth.Manager
@@ -35,6 +35,7 @@ type AuthMiddleware struct {
 	syncUserJWTGroups   SyncUserJWTGroupsFunc
 	rateLimiter         *APIRateLimiter
 	patUsageTracker     *PATUsageTracker
+	isValidChildAccount IsValidChildAccountFunc
 }
 
 // NewAuthMiddleware instance constructor
@@ -45,6 +46,7 @@ func NewAuthMiddleware(
 	getUserFromUserAuth GetUserFromUserAuthFunc,
 	rateLimiter *APIRateLimiter,
 	meter metric.Meter,
+	isValidChildAccount IsValidChildAccountFunc,
 ) *AuthMiddleware {
 	var patUsageTracker *PATUsageTracker
 	if meter != nil {
@@ -62,6 +64,7 @@ func NewAuthMiddleware(
 		getUserFromUserAuth: getUserFromUserAuth,
 		rateLimiter:         rateLimiter,
 		patUsageTracker:     patUsageTracker,
+		isValidChildAccount: isValidChildAccount,
 	}
 }
 
@@ -124,7 +127,7 @@ func (m *AuthMiddleware) checkJWTFromRequest(r *http.Request, authHeaderParts []
 	}
 
 	if impersonate, ok := r.URL.Query()["account"]; ok && len(impersonate) == 1 {
-		if integrations.IsValidChildAccount(ctx, userAuth.UserId, userAuth.AccountId, impersonate[0]) {
+		if m.isValidChildAccount(ctx, userAuth.UserId, userAuth.AccountId, impersonate[0]) {
 			userAuth.AccountId = impersonate[0]
 			userAuth.IsChild = true
 		}
@@ -203,7 +206,7 @@ func (m *AuthMiddleware) checkPATFromRequest(r *http.Request, authHeaderParts []
 	}
 
 	if impersonate, ok := r.URL.Query()["account"]; ok && len(impersonate) == 1 {
-		if integrations.IsValidChildAccount(r.Context(), userAuth.UserId, userAuth.AccountId, impersonate[0]) {
+		if m.isValidChildAccount(r.Context(), userAuth.UserId, userAuth.AccountId, impersonate[0]) {
 			userAuth.AccountId = impersonate[0]
 			userAuth.IsChild = true
 		}

management/server/http/middleware/auth_middleware_test.go

@@ -211,6 +211,7 @@ func TestAuthMiddleware_Handler(t *testing.T) {
 		},
 		disabledLimiter,
 		nil,
+		func(_ context.Context, _, _, _ string) bool { return false },
 	)
 
 	handlerToTest := authMiddleware.Handler(nextHandler)
@@ -270,6 +271,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -322,6 +324,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -365,6 +368,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -409,6 +413,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -473,6 +478,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -532,6 +538,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -587,6 +594,7 @@ func TestAuthMiddleware_RateLimiting(t *testing.T) {
 			},
 			NewAPIRateLimiter(rateLimitConfig),
 			nil,
+			func(_ context.Context, _, _, _ string) bool { return false },
 		)
 
 		handler := authMiddleware.Handler(http.HandlerFunc(func(w http.ResponseWriter, r *http.Request) {
@@ -687,6 +695,7 @@ func TestAuthMiddleware_Handler_Child(t *testing.T) {
 		},
 		disabledLimiter,
 		nil,
+		func(_ context.Context, _, _, _ string) bool { return false },
 	)
 
 	for _, tc := range tt {

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

@@ -1319,7 +1319,7 @@ func Test_NetworkRouters_Update(t *testing.T) {
 			},
 		},
 		{
-			name:      "Update non-existing router creates it",
+			name:      "Update non-existing router returns not found",
 			networkId: "testNetworkId",
 			routerId:  "nonExistingRouterId",
 			requestBody: &api.NetworkRouterRequest{
@@ -1328,11 +1328,7 @@ func Test_NetworkRouters_Update(t *testing.T) {
 				Metric:     100,
 				Enabled:    true,
 			},
-			expectedStatus: http.StatusOK,
-			verifyResponse: func(t *testing.T, router *api.NetworkRouter) {
-				t.Helper()
-				assert.Equal(t, "nonExistingRouterId", router.Id)
-			},
+			expectedStatus: http.StatusNotFound,
 		},
 		{
 			name:      "Update router with both peer and peer_groups",

management/server/http/testing/testing_tools/channel/channel.go

@@ -7,6 +7,7 @@ import (
 	"time"
 
 	"github.com/golang-jwt/jwt/v5"
+	"github.com/gorilla/mux"
 	"github.com/stretchr/testify/assert"
 
 	"go.opentelemetry.io/otel/metric/noop"
@@ -135,7 +136,8 @@ func BuildApiBlackBoxWithDBState(t testing_tools.TB, sqlFile string, expectedPee
 	customZonesManager := zonesManager.NewManager(store, am, permissionsManager, "")
 	zoneRecordsManager := recordsManager.NewManager(store, am, permissionsManager)
 
-	apiHandler, err := http2.NewAPIHandler(context.Background(), am, networksManager, resourcesManager, routersManager, groupsManager, geoMock, authManagerMock, metrics, validatorMock, proxyController, permissionsManager, peersManager, settingsManager, customZonesManager, zoneRecordsManager, networkMapController, nil, serviceManager, nil, nil, nil, nil, nil)
+	apiRouter := mux.NewRouter().PathPrefix("/api").Subrouter()
+	apiHandler, err := http2.NewAPIHandler(context.Background(), apiRouter, am, networksManager, resourcesManager, routersManager, groupsManager, geoMock, authManagerMock, metrics, permissionsManager, settingsManager, customZonesManager, zoneRecordsManager, networkMapController, nil, serviceManager, nil, nil, nil, nil, nil, nil)
 	if err != nil {
 		t.Fatalf("Failed to create API handler: %v", err)
 	}
@@ -264,7 +266,8 @@ func BuildApiBlackBoxWithDBStateAndPeerChannel(t testing_tools.TB, sqlFile strin
 	customZonesManager := zonesManager.NewManager(store, am, permissionsManager, "")
 	zoneRecordsManager := recordsManager.NewManager(store, am, permissionsManager)
 
-	apiHandler, err := http2.NewAPIHandler(context.Background(), am, networksManager, resourcesManager, routersManager, groupsManager, geoMock, authManagerMock, metrics, validatorMock, proxyController, permissionsManager, peersManager, settingsManager, customZonesManager, zoneRecordsManager, networkMapController, nil, serviceManager, nil, nil, nil, nil, nil)
+	apiRouter := mux.NewRouter().PathPrefix("/api").Subrouter()
+	apiHandler, err := http2.NewAPIHandler(context.Background(), apiRouter, am, networksManager, resourcesManager, routersManager, groupsManager, geoMock, authManagerMock, metrics, permissionsManager, settingsManager, customZonesManager, zoneRecordsManager, networkMapController, nil, serviceManager, nil, nil, nil, nil, nil, nil)
 	if err != nil {
 		t.Fatalf("Failed to create API handler: %v", err)
 	}

management/server/idp/embedded.go

@@ -6,7 +6,9 @@ import (
 	"errors"
 	"fmt"
 	"net/http"
+	"net/url"
 	"os"
+	"path"
 	"strings"
 
 	"github.com/dexidp/dex/storage"
@@ -138,10 +140,13 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 		return nil, fmt.Errorf("invalid IdP storage config: %w", err)
 	}
 
-	// Build CLI redirect URIs including the device callback (both relative and absolute)
+	// Build CLI redirect URIs including the device callback. Dex uses the issuer-relative
+	// path (for example, /oauth2/device/callback) when completing the device flow, so
+	// include it explicitly in addition to the legacy bare path and absolute URL.
 	cliRedirectURIs := c.CLIRedirectURIs
 	cliRedirectURIs = append(cliRedirectURIs, "/device/callback")
-	cliRedirectURIs = append(cliRedirectURIs, c.Issuer+"/device/callback")
+	cliRedirectURIs = append(cliRedirectURIs, issuerRelativeDeviceCallback(c.Issuer))
+	cliRedirectURIs = append(cliRedirectURIs, strings.TrimSuffix(c.Issuer, "/")+"/device/callback")
 
 	// Build dashboard redirect URIs including the OAuth callback for proxy authentication
 	dashboardRedirectURIs := c.DashboardRedirectURIs
@@ -154,6 +159,10 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 	// MGMT api and the dashboard, adding baseURL means less configuration for the instance admin
 	dashboardPostLogoutRedirectURIs = append(dashboardPostLogoutRedirectURIs, baseURL)
 
+	redirectURIs := make([]string, 0)
+	redirectURIs = append(redirectURIs, cliRedirectURIs...)
+	redirectURIs = append(redirectURIs, dashboardRedirectURIs...)
+
 	cfg := &dex.YAMLConfig{
 		Issuer: c.Issuer,
 		Storage: dex.Storage{
@@ -179,14 +188,14 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 				ID:                     staticClientDashboard,
 				Name:                   "NetBird Dashboard",
 				Public:                 true,
-				RedirectURIs:           dashboardRedirectURIs,
+				RedirectURIs:           redirectURIs,
 				PostLogoutRedirectURIs: sanitizePostLogoutRedirectURIs(dashboardPostLogoutRedirectURIs),
 			},
 			{
 				ID:           staticClientCLI,
 				Name:         "NetBird CLI",
 				Public:       true,
-				RedirectURIs: cliRedirectURIs,
+				RedirectURIs: redirectURIs,
 			},
 		},
 		StaticConnectors: c.StaticConnectors,
@@ -217,6 +226,14 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 	return cfg, nil
 }
 
+func issuerRelativeDeviceCallback(issuer string) string {
+	u, err := url.Parse(issuer)
+	if err != nil || u.Path == "" {
+		return "/device/callback"
+	}
+	return path.Join(u.Path, "/device/callback")
+}
+
 // Due to how the frontend generates the logout, sometimes it appends a trailing slash
 // and because Dex only allows exact matches, we need to make sure we always have both
 // versions of each provided uri
@@ -299,7 +316,7 @@ func resolveSessionCookieEncryptionKey(configuredKey string) (string, error) {
 		}
 	}
 
-	return "", fmt.Errorf("invalid embedded IdP session cookie encryption key: %s (or sessionCookieEncryptionKey) must be 16, 24, or 32 bytes as a raw string or base64-encoded to one of those lengths; got %d raw bytes", sessionCookieEncryptionKeyEnv, len([]byte(key)))
+	return "", fmt.Errorf("invalid embedded IdP session cookie encryption key:%s (or sessionCookieEncryptionKey) must be 16, 24, or 32 bytes as a raw string or base64-encoded to one of those lengths; got %d raw bytes", sessionCookieEncryptionKeyEnv, len([]byte(key)))
 }
 
 func validSessionCookieEncryptionKeyLength(length int) bool {

management/server/idp/embedded_test.go

@@ -314,6 +314,34 @@ func TestEmbeddedIdPManager_UpdateUserPassword(t *testing.T) {
 	})
 }
 
+func TestEmbeddedIdPConfig_ToYAMLConfig_IncludesDeviceCallbackRedirectURI(t *testing.T) {
+	config := &EmbeddedIdPConfig{
+		Enabled: true,
+		Issuer:  "https://example.com/oauth2",
+		Storage: EmbeddedStorageConfig{
+			Type: "sqlite3",
+			Config: EmbeddedStorageTypeConfig{
+				File: filepath.Join(t.TempDir(), "dex.db"),
+			},
+		},
+	}
+
+	yamlConfig, err := config.ToYAMLConfig()
+	require.NoError(t, err)
+
+	var cliRedirectURIs []string
+	for _, client := range yamlConfig.StaticClients {
+		if client.ID == staticClientCLI {
+			cliRedirectURIs = client.RedirectURIs
+			break
+		}
+	}
+	require.NotEmpty(t, cliRedirectURIs)
+	assert.Contains(t, cliRedirectURIs, "/device/callback")
+	assert.Contains(t, cliRedirectURIs, "/oauth2/device/callback")
+	assert.Contains(t, cliRedirectURIs, "https://example.com/oauth2/device/callback")
+}
+
 func TestEmbeddedIdPConfig_ToYAMLConfig_SessionCookieEncryptionKey(t *testing.T) {
 	t.Setenv(sessionCookieEncryptionKeyEnv, "")
 

management/server/integrations/integrated_validator/validator/validator.go

@@ -0,0 +1,62 @@
+package validator
+
+import (
+	"context"
+
+	cachestore "github.com/eko/gocache/lib/v4/store"
+
+	"github.com/netbirdio/netbird/management/internals/modules/peers"
+	"github.com/netbirdio/netbird/management/server/activity"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/settings"
+	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/shared/management/proto"
+)
+
+type IntegratedValidatorImpl struct{}
+
+func NewIntegratedValidator(_ context.Context, _ peers.Manager, _ settings.Manager, _ activity.Store, _ cachestore.StoreInterface) (*IntegratedValidatorImpl, error) {
+	return &IntegratedValidatorImpl{}, nil
+}
+
+func (v *IntegratedValidatorImpl) ValidateExtraSettings(context.Context, *types.ExtraSettings, *types.ExtraSettings, string, string) error {
+	return nil
+}
+
+func (v *IntegratedValidatorImpl) ValidatePeer(_ context.Context, update *nbpeer.Peer, _ *nbpeer.Peer, _ string, _ string, _ string, _ []string, _ *types.ExtraSettings) (*nbpeer.Peer, bool, error) {
+	return update, false, nil
+}
+
+func (v *IntegratedValidatorImpl) PreparePeer(_ context.Context, _ string, peer *nbpeer.Peer, _ []string, _ *types.ExtraSettings, _ bool) *nbpeer.Peer {
+	return peer.Copy()
+}
+
+func (v *IntegratedValidatorImpl) IsNotValidPeer(_ context.Context, _ string, _ *nbpeer.Peer, _ []string, _ *types.ExtraSettings) (bool, bool, error) {
+	return false, false, nil
+}
+
+func (v *IntegratedValidatorImpl) GetValidatedPeers(_ context.Context, _ string, _ []*types.Group, peers []*nbpeer.Peer, _ *types.ExtraSettings) (map[string]struct{}, error) {
+	validatedPeers := make(map[string]struct{})
+	for _, p := range peers {
+		validatedPeers[p.ID] = struct{}{}
+	}
+	return validatedPeers, nil
+}
+
+func (v *IntegratedValidatorImpl) GetInvalidPeers(_ context.Context, _ string, _ *types.ExtraSettings) (map[string]string, error) {
+	return make(map[string]string), nil
+}
+
+func (v *IntegratedValidatorImpl) PeerDeleted(_ context.Context, _, _ string, _ *types.ExtraSettings) error {
+	return nil
+}
+
+func (v *IntegratedValidatorImpl) SetPeerInvalidationListener(_ func(accountID string, peerIDs []string)) {
+}
+
+func (v *IntegratedValidatorImpl) Stop(_ context.Context) {
+}
+
+func (v *IntegratedValidatorImpl) ValidateFlowResponse(_ context.Context, _ string, flowResponse *proto.PKCEAuthorizationFlow) *proto.PKCEAuthorizationFlow {
+	return flowResponse
+}

management/server/metrics/selfhosted.go

@@ -17,6 +17,7 @@ import (
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	log "github.com/sirupsen/logrus"
 
+	"github.com/netbirdio/netbird/management/server/store"
 	"github.com/netbirdio/netbird/management/server/types"
 	nbversion "github.com/netbirdio/netbird/version"
 )
@@ -53,6 +54,7 @@ type DataSource interface {
 	GetAllAccounts(ctx context.Context) []*types.Account
 	GetStoreEngine() types.Engine
 	GetCustomDomainsCounts(ctx context.Context) (total int64, validated int64, err error)
+	GetProxyMetrics(ctx context.Context) (store.ProxyMetrics, error)
 }
 
 // ConnManager peer connection manager that holds state for current active connections
@@ -223,6 +225,12 @@ func (w *Worker) generateProperties(ctx context.Context) properties {
 		servicesAuthPassword      int
 		servicesAuthPin           int
 		servicesAuthOIDC          int
+		// Private-service signals — track adoption of NetBird-only mode
+		// (services backed by an embedded proxy peer + access groups).
+		servicesPrivate                int
+		servicesPrivateWithGroups      int
+		servicesPrivateAccessGroupsSum int
+		servicesWithDirectUpstream     int
 	)
 	start := time.Now()
 	metricsProperties := make(properties)
@@ -380,9 +388,31 @@ func (w *Worker) generateProperties(ctx context.Context) properties {
 			if service.Auth.BearerAuth != nil && service.Auth.BearerAuth.Enabled {
 				servicesAuthOIDC++
 			}
+
+			if service.Private {
+				servicesPrivate++
+				if len(service.AccessGroups) > 0 {
+					servicesPrivateWithGroups++
+				}
+				servicesPrivateAccessGroupsSum += len(service.AccessGroups)
+			}
+
+			for _, target := range service.Targets {
+				if target.Options.DirectUpstream {
+					servicesWithDirectUpstream++
+					break
+				}
+			}
 		}
 	}
 
+	// Proxy / BYOP cluster signals come from the proxies table aggregated
+	// across all accounts in a single store query; nil on FileStore.
+	proxyMetrics, err := w.dataSource.GetProxyMetrics(ctx)
+	if err != nil {
+		log.WithContext(ctx).Debugf("collect proxy metrics: %v", err)
+	}
+
 	minActivePeerVersion, maxActivePeerVersion := getMinMaxVersion(peerActiveVersions)
 	metricsProperties["uptime"] = uptime
 	metricsProperties["accounts"] = accounts
@@ -430,6 +460,15 @@ func (w *Worker) generateProperties(ctx context.Context) properties {
 	metricsProperties["services_auth_password"] = servicesAuthPassword
 	metricsProperties["services_auth_pin"] = servicesAuthPin
 	metricsProperties["services_auth_oidc"] = servicesAuthOIDC
+	metricsProperties["services_private"] = servicesPrivate
+	metricsProperties["services_private_with_access_groups"] = servicesPrivateWithGroups
+	metricsProperties["services_private_access_groups_sum"] = servicesPrivateAccessGroupsSum
+	metricsProperties["services_with_direct_upstream"] = servicesWithDirectUpstream
+	metricsProperties["proxy_clusters"] = proxyMetrics.Clusters
+	metricsProperties["proxy_clusters_byop"] = proxyMetrics.ClustersBYOP
+	metricsProperties["proxy_clusters_private"] = proxyMetrics.ClustersPrivate
+	metricsProperties["proxies"] = proxyMetrics.Proxies
+	metricsProperties["proxies_connected"] = proxyMetrics.ProxiesConnected
 	metricsProperties["custom_domains"] = customDomains
 	metricsProperties["custom_domains_validated"] = customDomainsValidated
 

management/server/metrics/selfhosted_test.go

@@ -12,6 +12,7 @@ import (
 	networkTypes "github.com/netbirdio/netbird/management/server/networks/types"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/posture"
+	"github.com/netbirdio/netbird/management/server/store"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/route"
 )
@@ -123,7 +124,7 @@ func (mockDatasource) GetAllAccounts(_ context.Context) []*types.Account {
 					Enabled: true,
 					Targets: []*rpservice.Target{
 						{TargetType: "peer"},
-						{TargetType: "host"},
+						{TargetType: "host", Options: rpservice.TargetOptions{DirectUpstream: true}},
 					},
 					Auth: rpservice.AuthConfig{
 						PasswordAuth: &rpservice.PasswordAuthConfig{Enabled: true},
@@ -141,6 +142,16 @@ func (mockDatasource) GetAllAccounts(_ context.Context) []*types.Account {
 					},
 					Meta: rpservice.Meta{Status: string(rpservice.StatusPending)},
 				},
+				{
+					ID:           "svc3-private",
+					Enabled:      true,
+					Private:      true,
+					AccessGroups: []string{"grp-eng", "grp-ops"},
+					Targets: []*rpservice.Target{
+						{TargetType: "cluster", Options: rpservice.TargetOptions{DirectUpstream: true}},
+					},
+					Meta: rpservice.Meta{Status: string(rpservice.StatusActive)},
+				},
 			},
 		},
 		{
@@ -254,6 +265,18 @@ func (mockDatasource) GetCustomDomainsCounts(_ context.Context) (int64, int64, e
 	return 3, 2, nil
 }
 
+// GetProxyMetrics returns canned proxy/cluster counts so the
+// generateProperties test can assert the BYOP signals end-to-end.
+func (mockDatasource) GetProxyMetrics(_ context.Context) (store.ProxyMetrics, error) {
+	return store.ProxyMetrics{
+		Clusters:         3,
+		ClustersBYOP:     1,
+		ClustersPrivate:  1,
+		Proxies:          4,
+		ProxiesConnected: 2,
+	}, nil
+}
+
 // TestGenerateProperties tests and validate the properties generation by using the mockDatasource for the Worker.generateProperties
 func TestGenerateProperties(t *testing.T) {
 	ds := mockDatasource{}
@@ -393,17 +416,17 @@ func TestGenerateProperties(t *testing.T) {
 		t.Errorf("expected 3 embedded_idp_count, got %v", properties["embedded_idp_count"])
 	}
 
-	if properties["services"] != 2 {
-		t.Errorf("expected 2 services, got %v", properties["services"])
+	if properties["services"] != 3 {
+		t.Errorf("expected 3 services, got %v", properties["services"])
 	}
-	if properties["services_enabled"] != 1 {
-		t.Errorf("expected 1 services_enabled, got %v", properties["services_enabled"])
+	if properties["services_enabled"] != 2 {
+		t.Errorf("expected 2 services_enabled, got %v", properties["services_enabled"])
 	}
-	if properties["services_targets"] != 3 {
-		t.Errorf("expected 3 services_targets, got %v", properties["services_targets"])
+	if properties["services_targets"] != 4 {
+		t.Errorf("expected 4 services_targets, got %v", properties["services_targets"])
 	}
-	if properties["services_status_active"] != 1 {
-		t.Errorf("expected 1 services_status_active, got %v", properties["services_status_active"])
+	if properties["services_status_active"] != 2 {
+		t.Errorf("expected 2 services_status_active, got %v", properties["services_status_active"])
 	}
 	if properties["services_status_pending"] != 1 {
 		t.Errorf("expected 1 services_status_pending, got %v", properties["services_status_pending"])
@@ -420,6 +443,9 @@ func TestGenerateProperties(t *testing.T) {
 	if properties["services_target_type_domain"] != 1 {
 		t.Errorf("expected 1 services_target_type_domain, got %v", properties["services_target_type_domain"])
 	}
+	if properties["services_target_type_cluster"] != 1 {
+		t.Errorf("expected 1 services_target_type_cluster, got %v", properties["services_target_type_cluster"])
+	}
 	if properties["services_auth_password"] != 1 {
 		t.Errorf("expected 1 services_auth_password, got %v", properties["services_auth_password"])
 	}
@@ -429,6 +455,33 @@ func TestGenerateProperties(t *testing.T) {
 	if properties["services_auth_pin"] != 0 {
 		t.Errorf("expected 0 services_auth_pin, got %v", properties["services_auth_pin"])
 	}
+	if properties["services_private"] != 1 {
+		t.Errorf("expected 1 services_private, got %v", properties["services_private"])
+	}
+	if properties["services_private_with_access_groups"] != 1 {
+		t.Errorf("expected 1 services_private_with_access_groups, got %v", properties["services_private_with_access_groups"])
+	}
+	if properties["services_private_access_groups_sum"] != 2 {
+		t.Errorf("expected 2 services_private_access_groups_sum, got %v", properties["services_private_access_groups_sum"])
+	}
+	if properties["services_with_direct_upstream"] != 2 {
+		t.Errorf("expected 2 services_with_direct_upstream, got %v", properties["services_with_direct_upstream"])
+	}
+	if properties["proxy_clusters"] != int64(3) {
+		t.Errorf("expected 3 proxy_clusters, got %v", properties["proxy_clusters"])
+	}
+	if properties["proxy_clusters_byop"] != int64(1) {
+		t.Errorf("expected 1 proxy_clusters_byop, got %v", properties["proxy_clusters_byop"])
+	}
+	if properties["proxy_clusters_private"] != int64(1) {
+		t.Errorf("expected 1 proxy_clusters_private, got %v", properties["proxy_clusters_private"])
+	}
+	if properties["proxies"] != int64(4) {
+		t.Errorf("expected 4 proxies, got %v", properties["proxies"])
+	}
+	if properties["proxies_connected"] != int64(2) {
+		t.Errorf("expected 2 proxies_connected, got %v", properties["proxies_connected"])
+	}
 	if properties["custom_domains"] != int64(3) {
 		t.Errorf("expected 3 custom_domains, got %v", properties["custom_domains"])
 	}

management/server/migration/migration_test.go

@@ -198,7 +198,11 @@ func TestMigrateNetIPFieldFromBlobToJSON_WithJSONData(t *testing.T) {
 	require.NoError(t, err, "Failed to insert account")
 
 	account.PeersG = []nbpeer.Peer{
-		{AccountID: "1234", Location: nbpeer.Location{ConnectionIP: net.IP{10, 0, 0, 1}}},
+		{
+			AccountID: "1234",
+			Location:  nbpeer.Location{ConnectionIP: net.IP{10, 0, 0, 1}},
+			Status:    &nbpeer.PeerStatus{LastSeen: time.Now()},
+		},
 	}
 
 	err = db.Save(account).Error

management/server/mock_server/account_mock.go

@@ -38,7 +38,8 @@ type MockAccountManager struct {
 	GetUserFromUserAuthFunc               func(ctx context.Context, userAuth auth.UserAuth) (*types.User, error)
 	ListUsersFunc                         func(ctx context.Context, accountID string) ([]*types.User, error)
 	GetPeersFunc                          func(ctx context.Context, accountID, userID, nameFilter, ipFilter string) ([]*nbpeer.Peer, error)
-	MarkPeerConnectedFunc                 func(ctx context.Context, peerKey string, connected bool, realIP net.IP, syncTime time.Time) error
+	MarkPeerConnectedFunc                 func(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error
+	MarkPeerDisconnectedFunc              func(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error
 	SyncAndMarkPeerFunc                   func(ctx context.Context, accountID string, peerPubKey string, meta nbpeer.PeerSystemMeta, realIP net.IP, syncTime time.Time) (*nbpeer.Peer, *types.NetworkMap, []*posture.Checks, int64, error)
 	DeletePeerFunc                        func(ctx context.Context, accountID, peerKey, userID string) error
 	GetNetworkMapFunc                     func(ctx context.Context, peerKey string) (*types.NetworkMap, error)
@@ -227,7 +228,14 @@ func (am *MockAccountManager) SyncAndMarkPeer(ctx context.Context, accountID str
 	return nil, nil, nil, 0, status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
 }
 
-func (am *MockAccountManager) OnPeerDisconnected(_ context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
+func (am *MockAccountManager) OnPeerDisconnected(ctx context.Context, accountID string, peerPubKey string, streamStartTime time.Time) error {
+	// Mirror DefaultAccountManager.OnPeerDisconnected: drive the fencing
+	// hook so tests that inject MarkPeerDisconnectedFunc actually observe
+	// disconnect events. Falls through to nil when no hook is set, which
+	// is the original behaviour.
+	if am.MarkPeerDisconnectedFunc != nil {
+		return am.MarkPeerDisconnectedFunc(ctx, peerPubKey, accountID, streamStartTime.UnixNano())
+	}
 	return nil
 }
 
@@ -328,13 +336,21 @@ func (am *MockAccountManager) GetAccountIDByUserID(ctx context.Context, userAuth
 }
 
 // MarkPeerConnected mock implementation of MarkPeerConnected from server.AccountManager interface
-func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
+func (am *MockAccountManager) MarkPeerConnected(ctx context.Context, peerKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
 	if am.MarkPeerConnectedFunc != nil {
-		return am.MarkPeerConnectedFunc(ctx, peerKey, connected, realIP, syncTime)
+		return am.MarkPeerConnectedFunc(ctx, peerKey, realIP, accountID, sessionStartedAt)
 	}
 	return status.Errorf(codes.Unimplemented, "method MarkPeerConnected is not implemented")
 }
 
+// MarkPeerDisconnected mock implementation of MarkPeerDisconnected from server.AccountManager interface
+func (am *MockAccountManager) MarkPeerDisconnected(ctx context.Context, peerKey string, accountID string, sessionStartedAt int64) error {
+	if am.MarkPeerDisconnectedFunc != nil {
+		return am.MarkPeerDisconnectedFunc(ctx, peerKey, accountID, sessionStartedAt)
+	}
+	return status.Errorf(codes.Unimplemented, "method MarkPeerDisconnected is not implemented")
+}
+
 // DeleteAccount mock implementation of DeleteAccount from server.AccountManager interface
 func (am *MockAccountManager) DeleteAccount(ctx context.Context, accountID, userID string) error {
 	if am.DeleteAccountFunc != nil {

management/server/networks/manager_test.go

@@ -34,8 +34,11 @@ func Test_GetAllNetworksReturnsNetworks(t *testing.T) {
 
 	networks, err := manager.GetAllNetworks(ctx, accountID, userID)
 	require.NoError(t, err)
-	require.Len(t, networks, 1)
-	require.Equal(t, "testNetworkId", networks[0].ID)
+	ids := make([]string, 0, len(networks))
+	for _, n := range networks {
+		ids = append(ids, n.ID)
+	}
+	require.ElementsMatch(t, []string{"testNetworkId", "secondNetworkId"}, ids)
 }
 
 func Test_GetAllNetworksReturnsPermissionDenied(t *testing.T) {

management/server/networks/routers/manager.go

@@ -102,7 +102,7 @@ func (m *managerImpl) CreateRouter(ctx context.Context, userID string, router *t
 
 		router.ID = xid.New().String()
 
-		err = transaction.SaveNetworkRouter(ctx, router)
+		err = transaction.CreateNetworkRouter(ctx, router)
 		if err != nil {
 			return fmt.Errorf("failed to create network router: %w", err)
 		}
@@ -162,11 +162,20 @@ func (m *managerImpl) UpdateRouter(ctx context.Context, userID string, router *t
 			return fmt.Errorf("failed to get network: %w", err)
 		}
 
-		if network.ID != router.NetworkID {
+		existing, err := transaction.GetNetworkRouterByID(ctx, store.LockingStrengthUpdate, router.AccountID, router.ID)
+		if err != nil {
+			return fmt.Errorf("failed to get network router: %w", err)
+		}
+
+		if existing.AccountID != router.AccountID {
+			return status.NewNetworkRouterNotFoundError(router.ID)
+		}
+
+		if existing.NetworkID != router.NetworkID {
 			return status.NewRouterNotPartOfNetworkError(router.ID, router.NetworkID)
 		}
 
-		err = transaction.SaveNetworkRouter(ctx, router)
+		err = transaction.UpdateNetworkRouter(ctx, router)
 		if err != nil {
 			return fmt.Errorf("failed to update network router: %w", err)
 		}

management/server/networks/routers/manager_test.go

@@ -195,6 +195,7 @@ func Test_UpdateRouterSuccessfully(t *testing.T) {
 	if err != nil {
 		require.NoError(t, err)
 	}
+	router.ID = "testRouterId"
 
 	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
 	if err != nil {
@@ -210,6 +211,102 @@ func Test_UpdateRouterSuccessfully(t *testing.T) {
 	require.Equal(t, router.Metric, updatedRouter.Metric)
 }
 
+func Test_UpdateRouterRejectsCrossAccountID(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// Admin of testAccountId tries to update a router that belongs to otherAccountId
+	// by passing the other account's router ID through the URL.
+	router, err := types.NewNetworkRouter("testAccountId", "testNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+	router.ID = "otherRouterId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	updatedRouter, err := manager.UpdateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, updatedRouter)
+
+	// The other account's router must be untouched.
+	stored, err := s.GetNetworkRouterByID(ctx, store.LockingStrengthNone, "otherAccountId", "otherRouterId")
+	require.NoError(t, err)
+	require.Equal(t, "otherAccountId", stored.AccountID)
+	require.Equal(t, "otherNetworkId", stored.NetworkID)
+	require.Equal(t, "otherPeer", stored.Peer)
+	require.Equal(t, 1, stored.Metric)
+}
+
+func Test_CreateRouterRejectsCrossAccountID(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// Admin of testAccountId tries to create a router in otherAccountId's network.
+	// The permission check is on router.AccountID (their own), but the network
+	// lookup must fail because (testAccountId, otherNetworkId) does not exist.
+	router, err := types.NewNetworkRouter("testAccountId", "otherNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	createdRouter, err := manager.CreateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, createdRouter)
+
+	// No router should have been created in either account's scope under otherNetworkId.
+	routersInOther, err := s.GetNetworkRoutersByNetID(ctx, store.LockingStrengthNone, "otherAccountId", "otherNetworkId")
+	require.NoError(t, err)
+	require.Len(t, routersInOther, 1)
+	require.Equal(t, "otherRouterId", routersInOther[0].ID)
+}
+
+func Test_UpdateRouterRejectsNetworkMismatch(t *testing.T) {
+	ctx := context.Background()
+	userID := "testAdminId"
+
+	// The router exists in testNetworkId, but the caller submits secondNetworkId
+	// (a different network in the same account). The update must be refused.
+	router, err := types.NewNetworkRouter("testAccountId", "secondNetworkId", "testPeerId", []string{}, false, 1, true)
+	if err != nil {
+		require.NoError(t, err)
+	}
+	router.ID = "testRouterId"
+
+	s, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "../../testdata/networks.sql", t.TempDir())
+	if err != nil {
+		t.Fatal(err)
+	}
+	t.Cleanup(cleanUp)
+	permissionsManager := permissions.NewManager(s)
+	am := mock_server.MockAccountManager{}
+	manager := NewManager(s, permissionsManager, &am)
+
+	updatedRouter, err := manager.UpdateRouter(ctx, userID, router)
+	require.Error(t, err)
+	require.Nil(t, updatedRouter)
+
+	stored, err := s.GetNetworkRouterByID(ctx, store.LockingStrengthNone, "testAccountId", "testRouterId")
+	require.NoError(t, err)
+	require.Equal(t, "testNetworkId", stored.NetworkID)
+}
+
 func Test_UpdateRouterFailsWithPermissionDenied(t *testing.T) {
 	ctx := context.Background()
 	userID := "testUserId"

management/server/peer.go

@@ -16,7 +16,6 @@ import (
 	"golang.org/x/exp/maps"
 
 	nbdns "github.com/netbirdio/netbird/dns"
-	"github.com/netbirdio/netbird/management/server/geolocation"
 	"github.com/netbirdio/netbird/management/server/idp"
 	routerTypes "github.com/netbirdio/netbird/management/server/networks/routers/types"
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
@@ -29,6 +28,7 @@ import (
 
 	"github.com/netbirdio/netbird/management/server/activity"
 	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/telemetry"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
@@ -63,98 +63,148 @@ func (am *DefaultAccountManager) GetPeers(ctx context.Context, accountID, userID
 	return am.Store.GetUserPeers(ctx, store.LockingStrengthNone, accountID, userID)
 }
 
-// MarkPeerConnected marks peer as connected (true) or disconnected (false)
-// syncTime is used as the LastSeen timestamp and for stale request detection
-func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubKey string, connected bool, realIP net.IP, accountID string, syncTime time.Time) error {
-	var peer *nbpeer.Peer
-	var settings *types.Settings
-	var expired bool
-	var err error
-	var skipped bool
+// MarkPeerConnected marks a peer as connected with optimistic-locked
+// fencing on PeerStatus.SessionStartedAt. The sessionStartedAt argument
+// is the start time of the gRPC sync stream that owns this update,
+// expressed as Unix nanoseconds — only the call whose token is greater
+// than what's stored wins. LastSeen is written by the database itself;
+// we never pass it down.
+//
+// Disconnects use MarkPeerDisconnected and require the session to match
+// exactly; see PeerStatus.SessionStartedAt for the protocol.
+func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubKey string, realIP net.IP, accountID string, sessionStartedAt int64) error {
+	start := time.Now()
+	defer func() {
+		am.metrics.AccountManagerMetrics().RecordPeerStatusUpdateDuration(telemetry.PeerStatusConnect, time.Since(start))
+	}()
 
-	err = am.Store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-		peer, err = transaction.GetPeerByPeerPubKey(ctx, store.LockingStrengthUpdate, peerPubKey)
-		if err != nil {
-			return err
+	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
+	if err != nil {
+		outcome := telemetry.PeerStatusError
+		if s, ok := status.FromError(err); ok && s.Type() == status.NotFound {
+			outcome = telemetry.PeerStatusPeerNotFound
 		}
-
-		if connected && !syncTime.After(peer.Status.LastSeen) {
-			log.WithContext(ctx).Tracef("peer %s has newer activity (lastSeen=%s >= syncTime=%s), skipping connect",
-				peer.ID, peer.Status.LastSeen.Format(time.RFC3339), syncTime.Format(time.RFC3339))
-			skipped = true
-			return nil
-		}
-
-		expired, err = updatePeerStatusAndLocation(ctx, am.geo, transaction, peer, connected, realIP, accountID, syncTime)
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, outcome)
 		return err
-	})
-	if skipped {
+	}
+
+	updated, err := am.Store.MarkPeerConnectedIfNewerSession(ctx, accountID, peer.ID, sessionStartedAt)
+	if err != nil {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusError)
+		return err
+	}
+	if !updated {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusStale)
+		log.WithContext(ctx).Tracef("peer %s already has a newer session in store, skipping connect", peer.ID)
 		return nil
 	}
-	if err != nil {
-		return err
+	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusConnect, telemetry.PeerStatusApplied)
+
+	if am.geo != nil && realIP != nil {
+		am.updatePeerLocationIfChanged(ctx, accountID, peer, realIP)
 	}
 
+	expired := peer.Status != nil && peer.Status.LoginExpired
+
 	if peer.AddedWithSSOLogin() {
-		settings, err = am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
+		settings, err := am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
 		if err != nil {
 			return err
 		}
-
 		if peer.LoginExpirationEnabled && settings.PeerLoginExpirationEnabled {
 			am.schedulePeerLoginExpiration(ctx, accountID)
 		}
-
 		if peer.InactivityExpirationEnabled && settings.PeerInactivityExpirationEnabled {
 			am.checkAndSchedulePeerInactivityExpiration(ctx, accountID)
 		}
 	}
 
 	if expired {
-		err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID})
-		if err != nil {
+		if err = am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID}); err != nil {
 			return fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
 	}
 
+	// An embedded proxy peer flipping to connected is the trigger for
+	// SynthesizePrivateServiceZones to emit DNS A records pointing at its
+	// tunnel IP. Without an account-wide netmap recompute, user peers keep
+	// the stale synth (or no synth at all on first connect) until some
+	// other change pokes the controller. Fire OnPeersUpdated so the
+	// buffered recompute fans the new state out to every peer.
+	if peer.ProxyMeta.Embedded {
+		if err := am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID}); err != nil {
+			log.WithContext(ctx).Warnf("notify network map controller of embedded proxy %s connect: %v", peer.ID, err)
+		}
+	}
+
 	return nil
 }
 
-func updatePeerStatusAndLocation(ctx context.Context, geo geolocation.Geolocation, transaction store.Store, peer *nbpeer.Peer, connected bool, realIP net.IP, accountID string, syncTime time.Time) (bool, error) {
-	oldStatus := peer.Status.Copy()
-	newStatus := oldStatus
-	newStatus.LastSeen = syncTime
-	newStatus.Connected = connected
-	// whenever peer got connected that means that it logged in successfully
-	if newStatus.Connected {
-		newStatus.LoginExpired = false
-	}
-	peer.Status = newStatus
+// MarkPeerDisconnected marks a peer as disconnected, but only when the
+// stored session token matches the one passed in. A mismatch means a
+// newer stream has already taken ownership of the peer — disconnects from
+// the older stream are ignored. LastSeen is written by the database.
+func (am *DefaultAccountManager) MarkPeerDisconnected(ctx context.Context, peerPubKey string, accountID string, sessionStartedAt int64) error {
+	start := time.Now()
+	defer func() {
+		am.metrics.AccountManagerMetrics().RecordPeerStatusUpdateDuration(telemetry.PeerStatusDisconnect, time.Since(start))
+	}()
 
-	if geo != nil && realIP != nil {
-		location, err := geo.Lookup(realIP)
-		if err != nil {
-			log.WithContext(ctx).Warnf("failed to get location for peer %s realip: [%s]: %v", peer.ID, realIP.String(), err)
-		} else {
-			peer.Location.ConnectionIP = realIP
-			peer.Location.CountryCode = location.Country.ISOCode
-			peer.Location.CityName = location.City.Names.En
-			peer.Location.GeoNameID = location.City.GeonameID
-			err = transaction.SavePeerLocation(ctx, accountID, peer)
-			if err != nil {
-				log.WithContext(ctx).Warnf("could not store location for peer %s: %s", peer.ID, err)
-			}
+	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
+	if err != nil {
+		outcome := telemetry.PeerStatusError
+		if s, ok := status.FromError(err); ok && s.Type() == status.NotFound {
+			outcome = telemetry.PeerStatusPeerNotFound
+		}
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, outcome)
+		return err
+	}
+
+	updated, err := am.Store.MarkPeerDisconnectedIfSameSession(ctx, accountID, peer.ID, sessionStartedAt)
+	if err != nil {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusError)
+		return err
+	}
+	if !updated {
+		am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusStale)
+		log.WithContext(ctx).Tracef("peer %s session token mismatch on disconnect (token=%d), skipping",
+			peer.ID, sessionStartedAt)
+		return nil
+	}
+	am.metrics.AccountManagerMetrics().CountPeerStatusUpdate(telemetry.PeerStatusDisconnect, telemetry.PeerStatusApplied)
+
+	// Symmetric with MarkPeerConnected: when an embedded proxy peer goes
+	// offline, drive an account-wide netmap recompute so the synthesized
+	// DNS records that pointed at it are pulled. Without this the records
+	// linger client-side at TTL until something else triggers a refresh.
+	if peer.ProxyMeta.Embedded {
+		if err := am.networkMapController.OnPeersUpdated(ctx, accountID, []string{peer.ID}); err != nil {
+			log.WithContext(ctx).Warnf("notify network map controller of embedded proxy %s disconnect: %v", peer.ID, err)
 		}
 	}
 
-	log.WithContext(ctx).Debugf("saving peer status for peer %s is connected: %t", peer.ID, connected)
+	return nil
+}
 
-	err := transaction.SavePeerStatus(ctx, accountID, peer.ID, *newStatus)
+// updatePeerLocationIfChanged refreshes the geolocation on a separate
+// row update, only when the connection IP actually changed. Geo lookups
+// are expensive so we skip same-IP reconnects.
+func (am *DefaultAccountManager) updatePeerLocationIfChanged(ctx context.Context, accountID string, peer *nbpeer.Peer, realIP net.IP) {
+	if peer.Location.ConnectionIP != nil && peer.Location.ConnectionIP.Equal(realIP) {
+		return
+	}
+	location, err := am.geo.Lookup(realIP)
 	if err != nil {
-		return false, err
+		log.WithContext(ctx).Warnf("failed to get location for peer %s realip: [%s]: %v", peer.ID, realIP.String(), err)
+		return
+	}
+	peer.Location.ConnectionIP = realIP
+	peer.Location.CountryCode = location.Country.ISOCode
+	peer.Location.CityName = location.City.Names.En
+	peer.Location.GeoNameID = location.City.GeonameID
+	if err := am.Store.SavePeerLocation(ctx, accountID, peer); err != nil {
+		log.WithContext(ctx).Warnf("could not store location for peer %s: %s", peer.ID, err)
 	}
-
-	return oldStatus.LoginExpired, nil
 }
 
 // UpdatePeer updates peer. Only Peer.Name, Peer.SSHEnabled, Peer.LoginExpirationEnabled and Peer.InactivityExpirationEnabled can be updated.
@@ -762,16 +812,19 @@ func (am *DefaultAccountManager) AddPeer(ctx context.Context, accountID, setupKe
 		newPeer.IP = freeIP
 
 		if len(settings.IPv6EnabledGroups) > 0 && network.NetV6.IP != nil {
-			var allGroupID string
-			if !peer.ProxyMeta.Embedded {
-				allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, "All")
-				if err != nil {
-					log.WithContext(ctx).Debugf("get All group for IPv6 allocation: %v", err)
-				} else {
+			// Embedded proxy peers are not group members but participate in any
+			// IPv6-enabled overlay so reverse-proxy traffic reaches v6-only peers.
+			allocate := peer.ProxyMeta.Embedded
+			if !allocate {
+				var allGroupID string
+				if allGroup, err := am.Store.GetGroupByName(ctx, store.LockingStrengthNone, accountID, types.GroupAllName); err == nil {
 					allGroupID = allGroup.ID
+				} else {
+					log.WithContext(ctx).Debugf("get All group for IPv6 allocation: %v", err)
 				}
+				allocate = peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID)
 			}
-			if peerWillHaveIPv6(settings, peerAddConfig.GroupsToAdd, allGroupID) {
+			if allocate {
 				v6Prefix, err := netip.ParsePrefix(network.NetV6.String())
 				if err != nil {
 					return nil, nil, nil, fmt.Errorf("parse IPv6 prefix: %w", err)

management/server/peer/peer.go

@@ -74,8 +74,19 @@ type ProxyMeta struct {
 }
 
 type PeerStatus struct { //nolint:revive
-	// LastSeen is the last time peer was connected to the management service
+	// LastSeen is the last time the peer status was updated (i.e. the last
+	// time we observed the peer being alive on a sync stream). Written by
+	// the database (CURRENT_TIMESTAMP) — callers do not supply it.
 	LastSeen time.Time
+	// SessionStartedAt records when the currently-active sync stream began,
+	// stored as Unix nanoseconds. It acts as the optimistic-locking token
+	// for status updates: a stream is only allowed to mutate the peer's
+	// status when its own token strictly exceeds the stored token (when connecting)
+	// or matches it exactly (for disconnects). Zero means "no
+	// active session". Integer nanoseconds are used so equality is
+	// precision-safe across drivers, and so the predicates compose to a
+	// single bigint comparison.
+	SessionStartedAt int64 `gorm:"not null;default:0"`
 	// Connected indicates whether peer is connected to the management service or not
 	Connected bool
 	// LoginExpired
@@ -375,10 +386,14 @@ func (p *Peer) EventMeta(dnsDomain string) map[string]any {
 	return meta
 }
 
-// Copy PeerStatus
+// Copy PeerStatus. SessionStartedAt must be propagated so clone-based
+// callers (Peer.Copy, MarkLoginExpired, UpdateLastLogin) don't silently
+// reset the fencing token to zero — that would let any subsequent
+// SavePeerStatus write reopen the optimistic-lock window.
 func (p *PeerStatus) Copy() *PeerStatus {
 	return &PeerStatus{
 		LastSeen:         p.LastSeen,
+		SessionStartedAt: p.SessionStartedAt,
 		Connected:        p.Connected,
 		LoginExpired:     p.LoginExpired,
 		RequiresApproval: p.RequiresApproval,

management/server/peer_test.go

@@ -2218,6 +2218,9 @@ func Test_IsUniqueConstraintError(t *testing.T) {
 		ID:        "test-peer-id",
 		AccountID: "bf1c8084-ba50-4ce7-9439-34653001fc3b",
 		DNSLabel:  "test-peer-dns-label",
+		Status: &nbpeer.PeerStatus{
+			LastSeen: time.Now(),
+		},
 	}
 
 	for _, tt := range tests {

management/server/store/file_store.go

@@ -274,3 +274,9 @@ func (s *FileStore) SetFieldEncrypt(_ *crypt.FieldEncrypt) {
 func (s *FileStore) GetCustomDomainsCounts(_ context.Context) (int64, int64, error) {
 	return 0, 0, nil
 }
+
+// GetProxyMetrics is a no-op for FileStore — proxy/cluster state isn't
+// persisted in the JSON file format.
+func (s *FileStore) GetProxyMetrics(_ context.Context) (ProxyMetrics, error) {
+	return ProxyMetrics{}, nil
+}

management/server/store/sql_store.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"net/url"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -497,8 +498,9 @@ func (s *SqlStore) SavePeerStatus(ctx context.Context, accountID, peerID string,
 	peerCopy.Status = &peerStatus
 
 	fieldsToUpdate := []string{
-		"peer_status_last_seen", "peer_status_connected",
-		"peer_status_login_expired", "peer_status_required_approval",
+		"peer_status_last_seen", "peer_status_session_started_at",
+		"peer_status_connected", "peer_status_login_expired",
+		"peer_status_requires_approval",
 	}
 	result := s.db.Model(&nbpeer.Peer{}).
 		Select(fieldsToUpdate).
@@ -515,6 +517,69 @@ func (s *SqlStore) SavePeerStatus(ctx context.Context, accountID, peerID string,
 	return nil
 }
 
+// MarkPeerConnectedIfNewerSession is an atomic optimistic-locked update.
+// The peer is marked connected with the given session token only when
+// the stored SessionStartedAt is strictly smaller than the incoming
+// one — equivalently, when no newer stream has already taken ownership.
+// The sentinel zero (set on peer creation or after a disconnect) counts
+// as the smallest possible token. This is the write half of the
+// fencing protocol described on PeerStatus.SessionStartedAt.
+//
+// The post-write side effects in the caller — geo lookup,
+// schedulePeerLoginExpiration, checkAndSchedulePeerInactivityExpiration,
+// OnPeersUpdated — all run AFTER this method returns and are deliberately
+// outside the database write so they cannot extend the row-lock window.
+//
+// LastSeen is set to the database's clock (CURRENT_TIMESTAMP) at the
+// moment the row is written. The caller never supplies LastSeen because
+// the value would otherwise drift under lock contention — a Go-side
+// time.Now() taken before the write can land minutes later than the
+// actual UPDATE under load, which previously caused real ordering bugs.
+func (s *SqlStore) MarkPeerConnectedIfNewerSession(ctx context.Context, accountID, peerID string, newSessionStartedAt int64) (bool, error) {
+	result := s.db.WithContext(ctx).
+		Model(&nbpeer.Peer{}).
+		Where(accountAndIDQueryCondition, accountID, peerID).
+		Where("peer_status_session_started_at < ?", newSessionStartedAt).
+		Updates(map[string]any{
+			"peer_status_connected":          true,
+			"peer_status_last_seen":          gorm.Expr("CURRENT_TIMESTAMP"),
+			"peer_status_session_started_at": newSessionStartedAt,
+			"peer_status_login_expired":      false,
+		})
+	if result.Error != nil {
+		return false, status.Errorf(status.Internal, "mark peer connected: %v", result.Error)
+	}
+	return result.RowsAffected > 0, nil
+}
+
+// MarkPeerDisconnectedIfSameSession is an atomic optimistic-locked update.
+// The peer is marked disconnected only when the stored SessionStartedAt
+// matches the incoming token — meaning the stream that owns the current
+// session is the one ending. If a newer stream has already replaced the
+// session, the update is skipped. LastSeen is set to CURRENT_TIMESTAMP at
+// write time; see MarkPeerConnectedIfNewerSession for the rationale.
+//
+// A zero sessionStartedAt is rejected at the call site; the underlying
+// WHERE on equality would otherwise match every never-connected peer.
+func (s *SqlStore) MarkPeerDisconnectedIfSameSession(ctx context.Context, accountID, peerID string, sessionStartedAt int64) (bool, error) {
+	if sessionStartedAt == 0 {
+		return false, nil
+	}
+	result := s.db.WithContext(ctx).
+		Model(&nbpeer.Peer{}).
+		Where(accountAndIDQueryCondition, accountID, peerID).
+		Where("peer_status_session_started_at = ?", sessionStartedAt).
+		Updates(map[string]any{
+			"peer_status_connected":          false,
+			"peer_status_last_seen":          gorm.Expr("CURRENT_TIMESTAMP"),
+			"peer_status_session_started_at": int64(0),
+		})
+	if result.Error != nil {
+		return false, status.Errorf(status.Internal, "mark peer disconnected: %v", result.Error)
+	}
+	return result.RowsAffected > 0, nil
+}
+
 func (s *SqlStore) SavePeerLocation(ctx context.Context, accountID string, peerWithLocation *nbpeer.Peer) error {
 	// To maintain data integrity, we create a copy of the peer's location to prevent unintended updates to other fields.
 	var peerCopy nbpeer.Peer
@@ -1025,6 +1090,38 @@ func (s *SqlStore) GetCustomDomainsCounts(ctx context.Context) (int64, int64, er
 	return total, validated, nil
 }
 
+// GetProxyMetrics aggregates per-cluster + per-proxy counts for the
+// self-hosted telemetry payload. Single round-trip via conditional
+// aggregations so a large proxies table doesn't fan out into multiple
+// queries.
+func (s *SqlStore) GetProxyMetrics(ctx context.Context) (ProxyMetrics, error) {
+	var m ProxyMetrics
+	activeCutoff := time.Now().Add(-proxyActiveThreshold)
+
+	// COUNT(DISTINCT ... CASE WHEN ...) is portable across sqlite/postgres
+	// (MySQL too) and keeps the round-trip to one. proxy.StatusConnected
+	// is the same string the cluster-capability queries use; the active
+	// window matches the cluster-capability semantics (only proxies
+	// heartbeating within ~2 * heartbeat interval count as connected).
+	row := s.db.WithContext(ctx).
+		Model(&proxy.Proxy{}).
+		Select(
+			"COUNT(DISTINCT cluster_address) AS clusters, "+
+				"COUNT(DISTINCT CASE WHEN account_id IS NOT NULL THEN cluster_address END) AS clusters_byop, "+
+				"COUNT(DISTINCT CASE WHEN private = ? THEN cluster_address END) AS clusters_private, "+
+				"COUNT(*) AS proxies, "+
+				"COUNT(CASE WHEN status = ? AND last_seen > ? THEN 1 END) AS proxies_connected",
+			true,
+			proxy.StatusConnected,
+			activeCutoff,
+		).
+		Row()
+	if err := row.Scan(&m.Clusters, &m.ClustersBYOP, &m.ClustersPrivate, &m.Proxies, &m.ProxiesConnected); err != nil {
+		return ProxyMetrics{}, fmt.Errorf("scan proxy metrics: %w", err)
+	}
+	return m, nil
+}
+
 func (s *SqlStore) GetAllAccounts(ctx context.Context) (all []*types.Account) {
 	var accounts []types.Account
 	result := s.db.Find(&accounts)
@@ -1722,9 +1819,10 @@ func (s *SqlStore) getPeers(ctx context.Context, accountID string) ([]nbpeer.Pee
 	inactivity_expiration_enabled, last_login, created_at, ephemeral, extra_dns_labels, allow_extra_dns_labels, meta_hostname,
 	meta_go_os, meta_kernel, meta_core, meta_platform, meta_os, meta_os_version, meta_wt_version, meta_ui_version,
 	meta_kernel_version, meta_network_addresses, meta_system_serial_number, meta_system_product_name, meta_system_manufacturer,
-	meta_environment, meta_flags, meta_files, meta_capabilities, peer_status_last_seen, peer_status_connected, peer_status_login_expired,
-	peer_status_requires_approval, location_connection_ip, location_country_code, location_city_name,
-	location_geo_name_id, proxy_meta_embedded, proxy_meta_cluster, ipv6 FROM peers WHERE account_id = $1`
+	meta_environment, meta_flags, meta_files, meta_capabilities, peer_status_last_seen, peer_status_session_started_at,
+	peer_status_connected, peer_status_login_expired, peer_status_requires_approval, location_connection_ip,
+	location_country_code, location_city_name, location_geo_name_id, proxy_meta_embedded, proxy_meta_cluster, ipv6
+	FROM peers WHERE account_id = $1`
 	rows, err := s.pool.Query(ctx, query, accountID)
 	if err != nil {
 		return nil, err
@@ -1737,6 +1835,7 @@ func (s *SqlStore) getPeers(ctx context.Context, accountID string) ([]nbpeer.Pee
 			lastLogin, createdAt                                                                            sql.NullTime
 			sshEnabled, loginExpirationEnabled, inactivityExpirationEnabled, ephemeral, allowExtraDNSLabels sql.NullBool
 			peerStatusLastSeen                                                                              sql.NullTime
+			peerStatusSessionStartedAt                                                                      sql.NullInt64
 			peerStatusConnected, peerStatusLoginExpired, peerStatusRequiresApproval, proxyEmbedded          sql.NullBool
 			ip, extraDNS, netAddr, env, flags, files, capabilities, connIP, ipv6                            []byte
 			metaHostname, metaGoOS, metaKernel, metaCore, metaPlatform                                      sql.NullString
@@ -1751,8 +1850,9 @@ func (s *SqlStore) getPeers(ctx context.Context, accountID string) ([]nbpeer.Pee
 			&allowExtraDNSLabels, &metaHostname, &metaGoOS, &metaKernel, &metaCore, &metaPlatform,
 			&metaOS, &metaOSVersion, &metaWtVersion, &metaUIVersion, &metaKernelVersion, &netAddr,
 			&metaSystemSerialNumber, &metaSystemProductName, &metaSystemManufacturer, &env, &flags, &files, &capabilities,
-			&peerStatusLastSeen, &peerStatusConnected, &peerStatusLoginExpired, &peerStatusRequiresApproval, &connIP,
-			&locationCountryCode, &locationCityName, &locationGeoNameID, &proxyEmbedded, &proxyCluster, &ipv6)
+			&peerStatusLastSeen, &peerStatusSessionStartedAt, &peerStatusConnected, &peerStatusLoginExpired,
+			&peerStatusRequiresApproval, &connIP, &locationCountryCode, &locationCityName, &locationGeoNameID,
+			&proxyEmbedded, &proxyCluster, &ipv6)
 
 		if err == nil {
 			if lastLogin.Valid {
@@ -1779,6 +1879,9 @@ func (s *SqlStore) getPeers(ctx context.Context, accountID string) ([]nbpeer.Pee
 			if peerStatusLastSeen.Valid {
 				p.Status.LastSeen = peerStatusLastSeen.Time
 			}
+			if peerStatusSessionStartedAt.Valid {
+				p.Status.SessionStartedAt = peerStatusSessionStartedAt.Int64
+			}
 			if peerStatusConnected.Valid {
 				p.Status.Connected = peerStatusConnected.Bool
 			}
@@ -2107,7 +2210,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 	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
+		mode, listen_port, port_auto_assigned, source, source_peer, terminated,
+		private, access_groups
 		FROM services WHERE account_id = $1`
 
 	const targetsQuery = `SELECT id, account_id, service_id, path, host, port, protocol,
@@ -2122,10 +2226,11 @@ 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 accessGroups []byte
 		var createdAt, certIssuedAt sql.NullTime
 		var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
 		var mode, source, sourcePeer sql.NullString
-		var terminated, portAutoAssigned sql.NullBool
+		var terminated, portAutoAssigned, private sql.NullBool
 		var listenPort sql.NullInt64
 		err := row.Scan(
 			&s.ID,
@@ -2148,6 +2253,8 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			&source,
 			&sourcePeer,
 			&terminated,
+			&private,
+			&accessGroups,
 		)
 		if err != nil {
 			return nil, err
@@ -2159,6 +2266,16 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 			}
 		}
 
+		if len(accessGroups) > 0 {
+			if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
+				return nil, fmt.Errorf("unmarshal access_groups: %w", err)
+			}
+		}
+
+		if private.Valid {
+			s.Private = private.Bool
+		}
+
 		s.Meta = rpservice.Meta{}
 		if createdAt.Valid {
 			s.Meta.CreatedAt = createdAt.Time
@@ -2794,12 +2911,27 @@ func NewSqliteStore(ctx context.Context, dataDir string, metrics telemetry.AppMe
 		connStr = filepath.Join(dataDir, filePath)
 	}
 
-	// Append query parameters: user-provided take precedence, otherwise default to cache=shared on non-Windows
-	if hasQuery {
-		connStr += "?" + query
-	} else if runtime.GOOS != "windows" {
+	// Compose query parameters. User-provided ?_busy_timeout (or its mattn alias
+	// ?_timeout) overrides our default; otherwise inject 30s so SQLite waits at
+	// most that long on a lock instead of blocking the only Go-side connection.
+	// mattn/go-sqlite3 applies PRAGMA from the DSN on every fresh connection, so
+	// the value survives ConnMaxIdleTime/ConnMaxLifetime recycling. cache=shared
+	// stays the default on non-Windows for the same reason as before.
+	parsed, _ := url.ParseQuery(query)
+	var defaults []string
+	if parsed.Get("_busy_timeout") == "" && parsed.Get("_timeout") == "" {
+		defaults = append(defaults, "_busy_timeout=30000")
+	}
+	if !hasQuery && runtime.GOOS != "windows" {
 		// To avoid `The process cannot access the file because it is being used by another process` on Windows
-		connStr += "?cache=shared"
+		defaults = append(defaults, "cache=shared")
+	}
+	parts := defaults
+	if hasQuery {
+		parts = append(parts, query)
+	}
+	if len(parts) > 0 {
+		connStr += "?" + strings.Join(parts, "&")
 	}
 
 	db, err := gorm.Open(sqlite.Open(connStr), getGormConfig())
@@ -3402,7 +3534,7 @@ func (s *SqlStore) IncrementNetworkSerial(ctx context.Context, accountId string)
 }
 
 func (s *SqlStore) ExecuteInTransaction(ctx context.Context, operation func(store Store) error) error {
-	timeoutCtx, cancel := context.WithTimeout(context.Background(), s.transactionTimeout)
+	timeoutCtx, cancel := context.WithTimeout(ctx, s.transactionTimeout)
 	defer cancel()
 
 	startTime := time.Now()
@@ -4229,11 +4361,27 @@ func (s *SqlStore) GetNetworkRouterByID(ctx context.Context, lockStrength Lockin
 	return netRouter, nil
 }
 
-func (s *SqlStore) SaveNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error {
-	result := s.db.Save(router)
+func (s *SqlStore) CreateNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error {
+	if err := s.db.Create(router).Error; err != nil {
+		log.WithContext(ctx).Errorf("failed to create network router in store: %v", err)
+		return status.Errorf(status.Internal, "failed to create network router in store")
+	}
+
+	return nil
+}
+
+func (s *SqlStore) UpdateNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error {
+	result := s.db.
+		Select("*").
+		Where(accountAndIDQueryCondition, router.AccountID, router.ID).
+		Updates(router)
 	if result.Error != nil {
-		log.WithContext(ctx).Errorf("failed to save network router to store: %v", result.Error)
-		return status.Errorf(status.Internal, "failed to save network router to store")
+		log.WithContext(ctx).Errorf("failed to update network router in store: %v", result.Error)
+		return status.Errorf(status.Internal, "failed to update network router in store")
+	}
+
+	if result.RowsAffected == 0 {
+		return status.NewNetworkRouterNotFoundError(router.ID)
 	}
 
 	return nil
@@ -5650,19 +5798,67 @@ func (s *SqlStore) DeleteAccountCluster(ctx context.Context, clusterAddress, acc
 	return nil
 }
 
-func (s *SqlStore) GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error) {
-	var clusters []proxy.Cluster
+// GetProxyClusters returns every cluster the account can see (shared
+// plus its own BYOP), regardless of whether any proxy in the cluster
+// is currently heartbeating. Online and ConnectedProxies are derived
+// from the 2-min active window so the dashboard can render offline
+// clusters distinctly; the 1-hour heartbeat reaper still removes rows
+// that go quiet for too long.
+//
+// AccountOwned is determined by whether any proxy row in the group
+// carries a non-NULL account_id; the caller maps that to Cluster.Type.
+// Capability flags are NOT filled here — the handler enriches them via
+// the per-cluster capability lookups.
+func (s *SqlStore) GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error) {
+	activeCutoff := time.Now().Add(-proxyActiveThreshold)
 
+	type clusterRow struct {
+		ID               string
+		Address          string
+		ConnectedProxies int
+		Online           bool
+		AccountOwned     bool
+	}
+
+	var rows []clusterRow
 	result := s.db.Model(&proxy.Proxy{}).
-		Select("MIN(id) as id, cluster_address as address, COUNT(*) as connected_proxies, COUNT(account_id) > 0 as self_hosted").
-		Where("status = ? AND last_seen > ? AND (account_id IS NULL OR account_id = ?)",
-			proxy.StatusConnected, time.Now().Add(-proxyActiveThreshold), accountID).
+		Select(
+			"MIN(id) AS id, "+
+				"cluster_address AS address, "+
+				// COUNT(CASE WHEN ... THEN 1 END) counts only non-NULL — i.e. only
+				// rows that satisfy the predicate — so it works portably across
+				// sqlite/postgres/mysql without dialect-specific FILTER syntax.
+				"COUNT(CASE WHEN status = ? AND last_seen > ? THEN 1 END) AS connected_proxies, "+
+				// MAX(CASE …) > 0 expresses BOOL_OR in a way Postgres tolerates
+				// (Postgres can't MAX a boolean column).
+				"MAX(CASE WHEN status = ? AND last_seen > ? THEN 1 ELSE 0 END) > 0 AS online, "+
+				"MAX(CASE WHEN account_id IS NOT NULL THEN 1 ELSE 0 END) > 0 AS account_owned",
+			proxy.StatusConnected, activeCutoff,
+			proxy.StatusConnected, activeCutoff,
+		).
+		Where("account_id IS NULL OR account_id = ?", accountID).
 		Group("cluster_address").
-		Scan(&clusters)
+		Scan(&rows)
 
 	if result.Error != nil {
-		log.WithContext(ctx).Errorf("failed to get active proxy clusters: %v", result.Error)
-		return nil, status.Errorf(status.Internal, "get active proxy clusters")
+		log.WithContext(ctx).Errorf("failed to get proxy clusters: %v", result.Error)
+		return nil, status.Errorf(status.Internal, "get proxy clusters")
+	}
+
+	clusters := make([]proxy.Cluster, 0, len(rows))
+	for _, r := range rows {
+		c := proxy.Cluster{
+			ID:               r.ID,
+			Address:          r.Address,
+			Online:           r.Online,
+			ConnectedProxies: r.ConnectedProxies,
+		}
+		if r.AccountOwned {
+			c.Type = proxy.ClusterTypeAccount
+		} else {
+			c.Type = proxy.ClusterTypeShared
+		}
+		clusters = append(clusters, c)
 	}
 
 	return clusters, nil
@@ -5676,6 +5872,7 @@ var validCapabilityColumns = map[string]struct{}{
 	"supports_custom_ports": {},
 	"require_subdomain":     {},
 	"supports_crowdsec":     {},
+	"private":               {},
 }
 
 // GetClusterSupportsCustomPorts returns whether any active proxy in the cluster
@@ -5690,6 +5887,12 @@ func (s *SqlStore) GetClusterRequireSubdomain(ctx context.Context, clusterAddr s
 	return s.getClusterCapability(ctx, clusterAddr, "require_subdomain")
 }
 
+// GetClusterSupportsPrivate reports whether any active proxy in the cluster
+// has the private capability (nil = unreported).
+func (s *SqlStore) GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
+	return s.getClusterCapability(ctx, clusterAddr, "private")
+}
+
 // GetClusterSupportsCrowdSec returns whether all active proxies in the cluster
 // have CrowdSec configured. Returns nil when no proxy reported the capability.
 // Unlike other capabilities that use ANY-true (for rolling upgrades), CrowdSec

management/server/store/sql_store_proxy_clusters_test.go

@@ -0,0 +1,109 @@
+package store
+
+import (
+	"context"
+	"os"
+	"runtime"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	rpproxy "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
+)
+
+// TestSqlStore_GetProxyClusters_DerivesOnlineAndType guards the
+// account-visible cluster list against silent regressions in two
+// dimensions:
+//
+//  1. Online derivation: a cluster with one stale and one fresh proxy
+//     is online and counts only the fresh proxy; a cluster whose
+//     proxies all heartbeated outside the 2-min window appears offline
+//     with connected_proxies = 0 (rather than disappearing, which is
+//     what the old query did).
+//  2. Type derivation: a cluster scoped to the calling account is
+//     reported as `account`; a cluster with account_id IS NULL is
+//     reported as `shared`. Clusters scoped to other accounts must not
+//     leak into the result.
+//
+// Capability flags are intentionally not asserted here — they're filled
+// by the manager (handler) layer from the per-cluster capability
+// lookups, not by the store query.
+func TestSqlStore_GetProxyClusters_DerivesOnlineAndType(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()
+		accountID := "acct-clusters"
+		require.NoError(t, store.SaveAccount(ctx, newAccountWithId(ctx, accountID, "user-1", "")))
+
+		otherAccountID := "acct-other"
+		require.NoError(t, store.SaveAccount(ctx, newAccountWithId(ctx, otherAccountID, "user-2", "")))
+
+		acctID := accountID
+		otherID := otherAccountID
+
+		fresh := time.Now().Add(-30 * time.Second)
+		stale := time.Now().Add(-30 * time.Minute)
+
+		mustSave := func(id, cluster string, accID *string, status string, lastSeen time.Time) {
+			require.NoError(t, store.SaveProxy(ctx, &rpproxy.Proxy{
+				ID:             id,
+				SessionID:      id + "-sess",
+				ClusterAddress: cluster,
+				IPAddress:      "10.0.0.1",
+				AccountID:      accID,
+				LastSeen:       lastSeen,
+				Status:         status,
+			}))
+		}
+
+		// shared-mixed: one fresh + one stale proxy → online, connected=1
+		mustSave("p-shared-fresh", "shared-mixed.netbird.io", nil, rpproxy.StatusConnected, fresh)
+		mustSave("p-shared-stale", "shared-mixed.netbird.io", nil, rpproxy.StatusConnected, stale)
+
+		// shared-offline: only stale proxies → offline, connected=0,
+		// but row must still appear (this is the new semantic — old
+		// query would have dropped it entirely).
+		mustSave("p-shared-off", "shared-offline.netbird.io", nil, rpproxy.StatusConnected, stale)
+
+		// account-online: BYOP cluster owned by acctID, fresh
+		mustSave("p-acct-fresh", "byop.acct.example", &acctID, rpproxy.StatusConnected, fresh)
+
+		// other-account: must not surface for acctID
+		mustSave("p-other", "byop.other.example", &otherID, rpproxy.StatusConnected, fresh)
+
+		clusters, err := store.GetProxyClusters(ctx, accountID)
+		require.NoError(t, err)
+
+		byAddr := map[string]rpproxy.Cluster{}
+		for _, c := range clusters {
+			byAddr[c.Address] = c
+		}
+
+		assert.NotContains(t, byAddr, "byop.other.example",
+			"another account's BYOP cluster must not leak into this account's listing")
+
+		require.Contains(t, byAddr, "shared-mixed.netbird.io")
+		mixed := byAddr["shared-mixed.netbird.io"]
+		assert.Equal(t, rpproxy.ClusterTypeShared, mixed.Type, "shared cluster (account_id IS NULL) must be reported as Type=shared")
+		assert.True(t, mixed.Online, "cluster with a fresh proxy must be online")
+		assert.Equal(t, 1, mixed.ConnectedProxies, "connected_proxies must count only fresh proxies; the stale one should not bump the count")
+
+		require.Contains(t, byAddr, "shared-offline.netbird.io",
+			"offline clusters must still appear so the dashboard can render them — the old GetActiveProxyClusters would have dropped this row, which is the regression this test guards against")
+		offline := byAddr["shared-offline.netbird.io"]
+		assert.Equal(t, rpproxy.ClusterTypeShared, offline.Type)
+		assert.False(t, offline.Online, "no fresh heartbeat → offline")
+		assert.Equal(t, 0, offline.ConnectedProxies, "no fresh proxies → connected_proxies=0")
+
+		require.Contains(t, byAddr, "byop.acct.example")
+		acct := byAddr["byop.acct.example"]
+		assert.Equal(t, rpproxy.ClusterTypeAccount, acct.Type, "BYOP cluster owned by the account must be reported as Type=account")
+		assert.True(t, acct.Online)
+		assert.Equal(t, 1, acct.ConnectedProxies)
+	})
+}

management/server/store/sql_store_service_test.go

@@ -0,0 +1,46 @@
+package store
+
+import (
+	"context"
+	"os"
+	"runtime"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
+)
+
+func TestSqlStore_GetAccount_PrivateServiceRoundtrip(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_private_svc", "testuser", "")
+		require.NoError(t, store.SaveAccount(ctx, account))
+
+		svc := &rpservice.Service{
+			ID:           "svc-private",
+			AccountID:    account.Id,
+			Name:         "private-svc",
+			Domain:       "private.example",
+			ProxyCluster: "cluster.example",
+			Enabled:      true,
+			Mode:         rpservice.ModeHTTP,
+			Private:      true,
+			AccessGroups: []string{"grp-admins", "grp-ops"},
+		}
+		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]
+		assert.True(t, got.Private)
+		assert.Equal(t, []string{"grp-admins", "grp-ops"}, got.AccessGroups)
+	})
+}

management/server/store/sql_store_test.go

@@ -2399,7 +2399,7 @@ func TestSqlStore_GetNetworkRouterByID(t *testing.T) {
 	}
 }
 
-func TestSqlStore_SaveNetworkRouter(t *testing.T) {
+func TestSqlStore_CreateNetworkRouter(t *testing.T) {
 	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", t.TempDir())
 	t.Cleanup(cleanup)
 	require.NoError(t, err)
@@ -2410,7 +2410,7 @@ func TestSqlStore_SaveNetworkRouter(t *testing.T) {
 	netRouter, err := routerTypes.NewNetworkRouter(accountID, networkID, "", []string{"net-router-grp"}, true, 0, true)
 	require.NoError(t, err)
 
-	err = store.SaveNetworkRouter(context.Background(), netRouter)
+	err = store.CreateNetworkRouter(context.Background(), netRouter)
 	require.NoError(t, err)
 
 	savedNetRouter, err := store.GetNetworkRouterByID(context.Background(), LockingStrengthNone, accountID, netRouter.ID)
@@ -2418,6 +2418,39 @@ func TestSqlStore_SaveNetworkRouter(t *testing.T) {
 	require.Equal(t, netRouter, savedNetRouter)
 }
 
+func TestSqlStore_UpdateNetworkRouter(t *testing.T) {
+	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", t.TempDir())
+	t.Cleanup(cleanup)
+	require.NoError(t, err)
+
+	accountID := "bf1c8084-ba50-4ce7-9439-34653001fc3b"
+	networkID := "ct286bi7qv930dsrrug0"
+	routerID := "ctc20ji7qv9ck2sebc80"
+
+	netRouter := &routerTypes.NetworkRouter{
+		ID:         routerID,
+		AccountID:  accountID,
+		NetworkID:  networkID,
+		Peer:       "",
+		PeerGroups: []string{"net-router-grp"},
+		Masquerade: true,
+		Metric:     42,
+		Enabled:    true,
+	}
+
+	err = store.UpdateNetworkRouter(context.Background(), netRouter)
+	require.NoError(t, err)
+
+	savedNetRouter, err := store.GetNetworkRouterByID(context.Background(), LockingStrengthNone, accountID, routerID)
+	require.NoError(t, err)
+	require.Equal(t, netRouter, savedNetRouter)
+
+	// Updating a router under a different account must not match any row.
+	netRouter.AccountID = "non-existent-account"
+	err = store.UpdateNetworkRouter(context.Background(), netRouter)
+	require.Error(t, err)
+}
+
 func TestSqlStore_DeleteNetworkRouter(t *testing.T) {
 	store, cleanup, err := NewTestStoreFromSQL(context.Background(), "../testdata/store.sql", t.TempDir())
 	t.Cleanup(cleanup)
@@ -4592,3 +4625,55 @@ func TestSqlStore_DeleteZoneDNSRecords(t *testing.T) {
 	require.NoError(t, err)
 	assert.Equal(t, 0, len(remainingRecords))
 }
+
+// TestNewSqliteStore_BusyTimeoutApplied opens a fresh SQLite store and verifies
+// that the _busy_timeout DSN parameter took effect at the driver level. Without
+// this, lock contention on the single SQLite connection waits indefinitely on
+// the Go side and can be hidden behind the 5-minute transactionTimeout.
+func TestNewSqliteStore_BusyTimeoutApplied(t *testing.T) {
+	dir := t.TempDir()
+	store, err := NewSqliteStore(context.Background(), dir, nil, true)
+	require.NoError(t, err)
+	t.Cleanup(func() {
+		_ = store.Close(context.Background())
+	})
+
+	sqlDB, err := store.db.DB()
+	require.NoError(t, err)
+	row := sqlDB.QueryRow("PRAGMA busy_timeout")
+	var busyTimeout int
+	require.NoError(t, row.Scan(&busyTimeout))
+	assert.Equal(t, 30000, busyTimeout, "SQLite busy_timeout must be set via DSN so it survives connection recycling")
+}
+
+// TestNewSqliteStore_BusyTimeoutRespectsUserOverride confirms that an operator
+// passing _busy_timeout or its mattn alias _timeout via NB_STORE_ENGINE_SQLITE_FILE
+// wins over our 30s default. This guards the DSN merge logic in NewSqliteStore.
+func TestNewSqliteStore_BusyTimeoutRespectsUserOverride(t *testing.T) {
+	cases := []struct {
+		name     string
+		envFile  string
+		expected int
+	}{
+		{name: "explicit _busy_timeout wins", envFile: "store.db?_busy_timeout=5000", expected: 5000},
+		{name: "alias _timeout wins", envFile: "store.db?_timeout=7000", expected: 7000},
+	}
+	for _, tc := range cases {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv("NB_STORE_ENGINE_SQLITE_FILE", tc.envFile)
+			dir := t.TempDir()
+			store, err := NewSqliteStore(context.Background(), dir, nil, true)
+			require.NoError(t, err)
+			t.Cleanup(func() {
+				_ = store.Close(context.Background())
+			})
+
+			sqlDB, err := store.db.DB()
+			require.NoError(t, err)
+			row := sqlDB.QueryRow("PRAGMA busy_timeout")
+			var busyTimeout int
+			require.NoError(t, row.Scan(&busyTimeout))
+			assert.Equal(t, tc.expected, busyTimeout)
+		})
+	}
+}

management/server/store/store.go

@@ -167,6 +167,21 @@ type Store interface {
 	GetAllEphemeralPeers(ctx context.Context, lockStrength LockingStrength) ([]*nbpeer.Peer, error)
 	SavePeer(ctx context.Context, accountID string, peer *nbpeer.Peer) error
 	SavePeerStatus(ctx context.Context, accountID, peerID string, status nbpeer.PeerStatus) error
+	// MarkPeerConnectedIfNewerSession sets the peer to connected with the
+	// given session token, but only when the stored SessionStartedAt is
+	// strictly less than newSessionStartedAt (the sentinel zero counts as
+	// "older"). LastSeen is recorded by the database at the moment the
+	// row is updated — never by the caller — so it always reflects the
+	// real write time even under lock contention.
+	// Returns true when the update happened, false when this stream lost
+	// the race against a newer session.
+	MarkPeerConnectedIfNewerSession(ctx context.Context, accountID, peerID string, newSessionStartedAt int64) (bool, error)
+	// MarkPeerDisconnectedIfSameSession sets the peer to disconnected and
+	// resets SessionStartedAt to zero, but only when the stored
+	// SessionStartedAt equals the given sessionStartedAt. LastSeen is
+	// recorded by the database. Returns true when the update happened,
+	// false when a newer session has taken over.
+	MarkPeerDisconnectedIfSameSession(ctx context.Context, accountID, peerID string, sessionStartedAt int64) (bool, error)
 	SavePeerLocation(ctx context.Context, accountID string, peer *nbpeer.Peer) error
 	ApproveAccountPeers(ctx context.Context, accountID string) (int, error)
 	DeletePeer(ctx context.Context, accountID string, peerID string) error
@@ -213,7 +228,8 @@ type Store interface {
 	GetNetworkRoutersByNetID(ctx context.Context, lockStrength LockingStrength, accountID, netID string) ([]*routerTypes.NetworkRouter, error)
 	GetNetworkRoutersByAccountID(ctx context.Context, lockStrength LockingStrength, accountID string) ([]*routerTypes.NetworkRouter, error)
 	GetNetworkRouterByID(ctx context.Context, lockStrength LockingStrength, accountID, routerID string) (*routerTypes.NetworkRouter, error)
-	SaveNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error
+	CreateNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error
+	UpdateNetworkRouter(ctx context.Context, router *routerTypes.NetworkRouter) error
 	DeleteNetworkRouter(ctx context.Context, accountID, routerID string) error
 
 	GetNetworkResourcesByNetID(ctx context.Context, lockStrength LockingStrength, accountID, netID string) ([]*resourceTypes.NetworkResource, error)
@@ -292,10 +308,11 @@ type Store interface {
 	UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
 	GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
 	GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error)
-	GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
+	GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error)
 	GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool
 	GetClusterRequireSubdomain(ctx context.Context, clusterAddr string) *bool
 	GetClusterSupportsCrowdSec(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)
 	CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error)
@@ -304,9 +321,38 @@ type Store interface {
 
 	GetCustomDomainsCounts(ctx context.Context) (total int64, validated int64, err error)
 
+	// GetProxyMetrics returns aggregated proxy / cluster counts for the
+	// self-hosted metrics worker. Self-hosted only — file-based stores
+	// return a zero-valued struct.
+	GetProxyMetrics(ctx context.Context) (ProxyMetrics, error)
+
 	GetRoutingPeerNetworks(ctx context.Context, accountID, peerID string) ([]string, error)
 }
 
+// ProxyMetrics aggregates self-hosted proxy + cluster usage signals
+// surfaced to the telemetry payload. Each field is best-effort: when a
+// store cannot answer (e.g. FileStore) all fields are zero.
+type ProxyMetrics struct {
+	// Clusters counts distinct cluster_address values across the proxies
+	// table — every cluster the management server has heard from, online or not.
+	Clusters int64
+	// ClustersBYOP counts distinct cluster_address values that are owned
+	// by an account (account_id IS NOT NULL). These are bring-your-own-proxy
+	// installations as opposed to NetBird-operated shared clusters.
+	ClustersBYOP int64
+	// ClustersPrivate counts distinct cluster_address values where at
+	// least one proxy reported the private capability (embedded
+	// `netbird proxy` running inside a client).
+	ClustersPrivate int64
+	// Proxies is the total number of proxy rows currently persisted.
+	Proxies int64
+	// ProxiesConnected is the subset of proxies whose status is
+	// "connected" AND last_seen falls within the active heartbeat window
+	// (~2 * heartbeat interval). Proxies the controller hasn't pruned
+	// yet but that are visibly stale don't count.
+	ProxiesConnected int64
+}
+
 const (
 	postgresDsnEnv       = "NB_STORE_ENGINE_POSTGRES_DSN"
 	postgresDsnEnvLegacy = "NETBIRD_STORE_ENGINE_POSTGRES_DSN"
@@ -456,6 +502,9 @@ func getMigrationsPreAuto(ctx context.Context) []migrationFunc {
 		func(db *gorm.DB) error {
 			return migration.MigrateNewField[types.User](ctx, db, "email", "")
 		},
+		func(db *gorm.DB) error {
+			return migration.MigrateNewField[nbpeer.Peer](ctx, db, "peer_status_session_started_at", int64(0))
+		},
 		func(db *gorm.DB) error {
 			return migration.RemoveDuplicatePeerKeys(ctx, db)
 		},

management/server/store/store_mock.go

@@ -310,6 +310,20 @@ func (mr *MockStoreMockRecorder) CreateGroups(ctx, accountID, groups interface{}
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateGroups", reflect.TypeOf((*MockStore)(nil).CreateGroups), ctx, accountID, groups)
 }
 
+// CreateNetworkRouter mocks base method.
+func (m *MockStore) CreateNetworkRouter(ctx context.Context, router *types0.NetworkRouter) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "CreateNetworkRouter", ctx, router)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// CreateNetworkRouter indicates an expected call of CreateNetworkRouter.
+func (mr *MockStoreMockRecorder) CreateNetworkRouter(ctx, router interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateNetworkRouter", reflect.TypeOf((*MockStore)(nil).CreateNetworkRouter), ctx, router)
+}
+
 // CreatePeerJob mocks base method.
 func (m *MockStore) CreatePeerJob(ctx context.Context, job *types2.Job) error {
 	m.ctrl.T.Helper()
@@ -380,6 +394,20 @@ func (mr *MockStoreMockRecorder) DeleteAccount(ctx, account interface{}) *gomock
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccount", reflect.TypeOf((*MockStore)(nil).DeleteAccount), ctx, account)
 }
 
+// DeleteAccountCluster mocks base method.
+func (m *MockStore) 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 *MockStoreMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockStore)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
+}
+
 // DeleteCustomDomain mocks base method.
 func (m *MockStore) DeleteCustomDomain(ctx context.Context, accountID, domainID string) error {
 	m.ctrl.T.Helper()
@@ -577,20 +605,6 @@ func (mr *MockStoreMockRecorder) DeletePostureChecks(ctx, accountID, postureChec
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeletePostureChecks", reflect.TypeOf((*MockStore)(nil).DeletePostureChecks), ctx, accountID, postureChecksID)
 }
 
-// DeleteAccountCluster mocks base method.
-func (m *MockStore) 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 *MockStoreMockRecorder) DeleteAccountCluster(ctx, clusterAddress, accountID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteAccountCluster", reflect.TypeOf((*MockStore)(nil).DeleteAccountCluster), ctx, clusterAddress, accountID)
-}
-
 // DeleteRoute mocks base method.
 func (m *MockStore) DeleteRoute(ctx context.Context, accountID, routeID string) error {
 	m.ctrl.T.Helper()
@@ -731,6 +745,20 @@ func (mr *MockStoreMockRecorder) DeleteZoneDNSRecords(ctx, accountID, zoneID int
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DeleteZoneDNSRecords", reflect.TypeOf((*MockStore)(nil).DeleteZoneDNSRecords), ctx, accountID, zoneID)
 }
 
+// DisconnectProxy mocks base method.
+func (m *MockStore) DisconnectProxy(ctx context.Context, proxyID, sessionID string) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "DisconnectProxy", ctx, proxyID, sessionID)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// DisconnectProxy indicates an expected call of DisconnectProxy.
+func (mr *MockStoreMockRecorder) DisconnectProxy(ctx, proxyID, sessionID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DisconnectProxy", reflect.TypeOf((*MockStore)(nil).DisconnectProxy), ctx, proxyID, sessionID)
+}
+
 // EphemeralServiceExists mocks base method.
 func (m *MockStore) EphemeralServiceExists(ctx context.Context, lockStrength LockingStrength, accountID, peerID, domain string) (bool, error) {
 	m.ctrl.T.Helper()
@@ -1332,21 +1360,6 @@ func (mr *MockStoreMockRecorder) GetActiveProxyClusterAddressesForAccount(ctx, a
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveProxyClusterAddressesForAccount", reflect.TypeOf((*MockStore)(nil).GetActiveProxyClusterAddressesForAccount), ctx, accountID)
 }
 
-// GetActiveProxyClusters mocks base method.
-func (m *MockStore) GetActiveProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetActiveProxyClusters", ctx, accountID)
-	ret0, _ := ret[0].([]proxy.Cluster)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// GetActiveProxyClusters indicates an expected call of GetActiveProxyClusters.
-func (mr *MockStoreMockRecorder) GetActiveProxyClusters(ctx, accountID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveProxyClusters", reflect.TypeOf((*MockStore)(nil).GetActiveProxyClusters), ctx, accountID)
-}
-
 // GetAllAccounts mocks base method.
 func (m *MockStore) GetAllAccounts(ctx context.Context) []*types2.Account {
 	m.ctrl.T.Helper()
@@ -1448,6 +1461,20 @@ func (mr *MockStoreMockRecorder) GetClusterSupportsCustomPorts(ctx, clusterAddr
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsCustomPorts", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsCustomPorts), ctx, clusterAddr)
 }
 
+// GetClusterSupportsPrivate mocks base method.
+func (m *MockStore) GetClusterSupportsPrivate(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetClusterSupportsPrivate", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// GetClusterSupportsPrivate indicates an expected call of GetClusterSupportsPrivate.
+func (mr *MockStoreMockRecorder) GetClusterSupportsPrivate(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsPrivate", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsPrivate), ctx, clusterAddr)
+}
+
 // GetCustomDomain mocks base method.
 func (m *MockStore) GetCustomDomain(ctx context.Context, accountID, domainID string) (*domain.Domain, error) {
 	m.ctrl.T.Helper()
@@ -2048,6 +2075,36 @@ func (mr *MockStoreMockRecorder) GetProxyByAccountID(ctx, accountID interface{})
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyByAccountID", reflect.TypeOf((*MockStore)(nil).GetProxyByAccountID), ctx, accountID)
 }
 
+// GetProxyClusters mocks base method.
+func (m *MockStore) GetProxyClusters(ctx context.Context, accountID string) ([]proxy.Cluster, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetProxyClusters", ctx, accountID)
+	ret0, _ := ret[0].([]proxy.Cluster)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetProxyClusters indicates an expected call of GetProxyClusters.
+func (mr *MockStoreMockRecorder) GetProxyClusters(ctx, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyClusters", reflect.TypeOf((*MockStore)(nil).GetProxyClusters), ctx, accountID)
+}
+
+// GetProxyMetrics mocks base method.
+func (m *MockStore) GetProxyMetrics(ctx context.Context) (ProxyMetrics, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetProxyMetrics", ctx)
+	ret0, _ := ret[0].(ProxyMetrics)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetProxyMetrics indicates an expected call of GetProxyMetrics.
+func (mr *MockStoreMockRecorder) GetProxyMetrics(ctx interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyMetrics", reflect.TypeOf((*MockStore)(nil).GetProxyMetrics), ctx)
+}
+
 // GetResourceGroups mocks base method.
 func (m *MockStore) GetResourceGroups(ctx context.Context, lockStrength LockingStrength, accountID, resourceID string) ([]*types2.Group, error) {
 	m.ctrl.T.Helper()
@@ -2598,6 +2655,36 @@ func (mr *MockStoreMockRecorder) MarkPATUsed(ctx, patID interface{}) *gomock.Cal
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPATUsed", reflect.TypeOf((*MockStore)(nil).MarkPATUsed), ctx, patID)
 }
 
+// MarkPeerConnectedIfNewerSession mocks base method.
+func (m *MockStore) MarkPeerConnectedIfNewerSession(ctx context.Context, accountID, peerID string, newSessionStartedAt int64) (bool, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "MarkPeerConnectedIfNewerSession", ctx, accountID, peerID, newSessionStartedAt)
+	ret0, _ := ret[0].(bool)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// MarkPeerConnectedIfNewerSession indicates an expected call of MarkPeerConnectedIfNewerSession.
+func (mr *MockStoreMockRecorder) MarkPeerConnectedIfNewerSession(ctx, accountID, peerID, newSessionStartedAt interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerConnectedIfNewerSession", reflect.TypeOf((*MockStore)(nil).MarkPeerConnectedIfNewerSession), ctx, accountID, peerID, newSessionStartedAt)
+}
+
+// MarkPeerDisconnectedIfSameSession mocks base method.
+func (m *MockStore) MarkPeerDisconnectedIfSameSession(ctx context.Context, accountID, peerID string, sessionStartedAt int64) (bool, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "MarkPeerDisconnectedIfSameSession", ctx, accountID, peerID, sessionStartedAt)
+	ret0, _ := ret[0].(bool)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// MarkPeerDisconnectedIfSameSession indicates an expected call of MarkPeerDisconnectedIfSameSession.
+func (mr *MockStoreMockRecorder) MarkPeerDisconnectedIfSameSession(ctx, accountID, peerID, sessionStartedAt interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "MarkPeerDisconnectedIfSameSession", reflect.TypeOf((*MockStore)(nil).MarkPeerDisconnectedIfSameSession), ctx, accountID, peerID, sessionStartedAt)
+}
+
 // MarkPendingJobsAsFailed mocks base method.
 func (m *MockStore) MarkPendingJobsAsFailed(ctx context.Context, accountID, peerID, jobID, reason string) error {
 	m.ctrl.T.Helper()
@@ -2808,20 +2895,6 @@ func (mr *MockStoreMockRecorder) SaveNetworkResource(ctx, resource interface{})
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SaveNetworkResource", reflect.TypeOf((*MockStore)(nil).SaveNetworkResource), ctx, resource)
 }
 
-// SaveNetworkRouter mocks base method.
-func (m *MockStore) SaveNetworkRouter(ctx context.Context, router *types0.NetworkRouter) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "SaveNetworkRouter", ctx, router)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// SaveNetworkRouter indicates an expected call of SaveNetworkRouter.
-func (mr *MockStoreMockRecorder) SaveNetworkRouter(ctx, router interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SaveNetworkRouter", reflect.TypeOf((*MockStore)(nil).SaveNetworkRouter), ctx, router)
-}
-
 // SavePAT mocks base method.
 func (m *MockStore) SavePAT(ctx context.Context, pat *types2.PersonalAccessToken) error {
 	m.ctrl.T.Helper()
@@ -2920,20 +2993,6 @@ func (mr *MockStoreMockRecorder) SaveProxy(ctx, proxy interface{}) *gomock.Call
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SaveProxy", reflect.TypeOf((*MockStore)(nil).SaveProxy), ctx, proxy)
 }
 
-// DisconnectProxy mocks base method.
-func (m *MockStore) DisconnectProxy(ctx context.Context, proxyID, sessionID string) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "DisconnectProxy", ctx, proxyID, sessionID)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// DisconnectProxy indicates an expected call of DisconnectProxy.
-func (mr *MockStoreMockRecorder) DisconnectProxy(ctx, proxyID, sessionID interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "DisconnectProxy", reflect.TypeOf((*MockStore)(nil).DisconnectProxy), ctx, proxyID, sessionID)
-}
-
 // SaveProxyAccessToken mocks base method.
 func (m *MockStore) SaveProxyAccessToken(ctx context.Context, token *types2.ProxyAccessToken) error {
 	m.ctrl.T.Helper()
@@ -3143,6 +3202,20 @@ func (mr *MockStoreMockRecorder) UpdateGroups(ctx, accountID, groups interface{}
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateGroups", reflect.TypeOf((*MockStore)(nil).UpdateGroups), ctx, accountID, groups)
 }
 
+// UpdateNetworkRouter mocks base method.
+func (m *MockStore) UpdateNetworkRouter(ctx context.Context, router *types0.NetworkRouter) error {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "UpdateNetworkRouter", ctx, router)
+	ret0, _ := ret[0].(error)
+	return ret0
+}
+
+// UpdateNetworkRouter indicates an expected call of UpdateNetworkRouter.
+func (mr *MockStoreMockRecorder) UpdateNetworkRouter(ctx, router interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "UpdateNetworkRouter", reflect.TypeOf((*MockStore)(nil).UpdateNetworkRouter), ctx, router)
+}
+
 // UpdateProxyHeartbeat mocks base method.
 func (m *MockStore) UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error {
 	m.ctrl.T.Helper()

management/server/telemetry/accountmanager_metrics.go

@@ -16,6 +16,8 @@ type AccountManagerMetrics struct {
 	getPeerNetworkMapDurationMs  metric.Float64Histogram
 	networkMapObjectCount        metric.Int64Histogram
 	peerMetaUpdateCount          metric.Int64Counter
+	peerStatusUpdateCounter      metric.Int64Counter
+	peerStatusUpdateDurationMs   metric.Float64Histogram
 }
 
 // NewAccountManagerMetrics creates an instance of AccountManagerMetrics
@@ -64,6 +66,24 @@ func NewAccountManagerMetrics(ctx context.Context, meter metric.Meter) (*Account
 		return nil, err
 	}
 
+	// peerStatusUpdateCounter records every attempt to mark a peer as connected or disconnected
+	peerStatusUpdateCounter, err := meter.Int64Counter("management.account.peer.status.update.counter",
+		metric.WithUnit("1"),
+		metric.WithDescription("Number of peer status update attempts, labeled by operation (connect|disconnect) and outcome (applied|stale|error|peer_not_found)"))
+	if err != nil {
+		return nil, err
+	}
+
+	peerStatusUpdateDurationMs, err := meter.Float64Histogram("management.account.peer.status.update.duration.ms",
+		metric.WithUnit("milliseconds"),
+		metric.WithExplicitBucketBoundaries(
+			1, 5, 15, 25, 50, 100, 250, 500, 1000, 2000, 5000,
+		),
+		metric.WithDescription("Duration of a peer status update (fence UPDATE + post-write side effects), labeled by operation"))
+	if err != nil {
+		return nil, err
+	}
+
 	return &AccountManagerMetrics{
 		ctx:                          ctx,
 		getPeerNetworkMapDurationMs:  getPeerNetworkMapDurationMs,
@@ -71,10 +91,35 @@ func NewAccountManagerMetrics(ctx context.Context, meter metric.Meter) (*Account
 		updateAccountPeersCounter:    updateAccountPeersCounter,
 		networkMapObjectCount:        networkMapObjectCount,
 		peerMetaUpdateCount:          peerMetaUpdateCount,
+		peerStatusUpdateCounter:      peerStatusUpdateCounter,
+		peerStatusUpdateDurationMs:   peerStatusUpdateDurationMs,
 	}, nil
 
 }
 
+// PeerStatusOperation labels the kind of fence-locked peer status write.
+type PeerStatusOperation string
+
+// PeerStatusOutcome labels how a fence-locked peer status write resolved.
+type PeerStatusOutcome string
+
+const (
+	PeerStatusConnect    PeerStatusOperation = "connect"
+	PeerStatusDisconnect PeerStatusOperation = "disconnect"
+
+	// PeerStatusApplied — the fence WHERE matched and the UPDATE landed.
+	PeerStatusApplied PeerStatusOutcome = "applied"
+	// PeerStatusStale — the fence WHERE rejected the write because a
+	// newer session has already taken ownership (connect: stored token
+	// >= incoming; disconnect: stored token != incoming).
+	PeerStatusStale PeerStatusOutcome = "stale"
+	// PeerStatusError — the store returned a non-NotFound error.
+	PeerStatusError PeerStatusOutcome = "error"
+	// PeerStatusPeerNotFound — the peer lookup failed (the peer was
+	// deleted between the gRPC sync handshake and the status write).
+	PeerStatusPeerNotFound PeerStatusOutcome = "peer_not_found"
+)
+
 // CountUpdateAccountPeersDuration counts the duration of updating account peers
 func (metrics *AccountManagerMetrics) CountUpdateAccountPeersDuration(duration time.Duration) {
 	metrics.updateAccountPeersDurationMs.Record(metrics.ctx, float64(duration.Nanoseconds())/1e6)
@@ -104,3 +149,23 @@ func (metrics *AccountManagerMetrics) CountUpdateAccountPeersTriggered(resource,
 func (metrics *AccountManagerMetrics) CountPeerMetUpdate() {
 	metrics.peerMetaUpdateCount.Add(metrics.ctx, 1)
 }
+
+// CountPeerStatusUpdate increments the connect/disconnect counter,
+// labeled by operation and outcome. Both labels are bounded enums.
+func (metrics *AccountManagerMetrics) CountPeerStatusUpdate(op PeerStatusOperation, outcome PeerStatusOutcome) {
+	metrics.peerStatusUpdateCounter.Add(metrics.ctx, 1,
+		metric.WithAttributes(
+			attribute.String("operation", string(op)),
+			attribute.String("outcome", string(outcome)),
+		),
+	)
+}
+
+// RecordPeerStatusUpdateDuration records the wall-clock time spent
+// running a peer status update (including post-write side effects),
+// labeled by operation.
+func (metrics *AccountManagerMetrics) RecordPeerStatusUpdateDuration(op PeerStatusOperation, d time.Duration) {
+	metrics.peerStatusUpdateDurationMs.Record(metrics.ctx, float64(d.Nanoseconds())/1e6,
+		metric.WithAttributes(attribute.String("operation", string(op))),
+	)
+}

management/server/telemetry/app_metrics.go

@@ -29,6 +29,7 @@ type MockAppMetrics struct {
 	StoreMetricsFunc             func() *StoreMetrics
 	UpdateChannelMetricsFunc     func() *UpdateChannelMetrics
 	AddAccountManagerMetricsFunc func() *AccountManagerMetrics
+	EphemeralPeersMetricsFunc    func() *EphemeralPeersMetrics
 }
 
 // GetMeter mocks the GetMeter function of the AppMetrics interface
@@ -103,6 +104,14 @@ func (mock *MockAppMetrics) AccountManagerMetrics() *AccountManagerMetrics {
 	return nil
 }
 
+// EphemeralPeersMetrics mocks the MockAppMetrics function of the EphemeralPeersMetrics interface
+func (mock *MockAppMetrics) EphemeralPeersMetrics() *EphemeralPeersMetrics {
+	if mock.EphemeralPeersMetricsFunc != nil {
+		return mock.EphemeralPeersMetricsFunc()
+	}
+	return nil
+}
+
 // AppMetrics is metrics interface
 type AppMetrics interface {
 	GetMeter() metric2.Meter
@@ -114,6 +123,7 @@ type AppMetrics interface {
 	StoreMetrics() *StoreMetrics
 	UpdateChannelMetrics() *UpdateChannelMetrics
 	AccountManagerMetrics() *AccountManagerMetrics
+	EphemeralPeersMetrics() *EphemeralPeersMetrics
 }
 
 // defaultAppMetrics are core application metrics based on OpenTelemetry https://opentelemetry.io/
@@ -129,6 +139,7 @@ type defaultAppMetrics struct {
 	storeMetrics          *StoreMetrics
 	updateChannelMetrics  *UpdateChannelMetrics
 	accountManagerMetrics *AccountManagerMetrics
+	ephemeralMetrics      *EphemeralPeersMetrics
 }
 
 // IDPMetrics returns metrics for the idp package
@@ -161,6 +172,11 @@ func (appMetrics *defaultAppMetrics) AccountManagerMetrics() *AccountManagerMetr
 	return appMetrics.accountManagerMetrics
 }
 
+// EphemeralPeersMetrics returns metrics for the ephemeral peer cleanup loop
+func (appMetrics *defaultAppMetrics) EphemeralPeersMetrics() *EphemeralPeersMetrics {
+	return appMetrics.ephemeralMetrics
+}
+
 // Close stop application metrics HTTP handler and closes listener.
 func (appMetrics *defaultAppMetrics) Close() error {
 	if appMetrics.listener == nil {
@@ -245,6 +261,11 @@ func NewDefaultAppMetrics(ctx context.Context) (AppMetrics, error) {
 		return nil, fmt.Errorf("failed to initialize account manager metrics: %w", err)
 	}
 
+	ephemeralMetrics, err := NewEphemeralPeersMetrics(ctx, meter)
+	if err != nil {
+		return nil, fmt.Errorf("failed to initialize ephemeral peers metrics: %w", err)
+	}
+
 	return &defaultAppMetrics{
 		Meter:                 meter,
 		ctx:                   ctx,
@@ -254,6 +275,7 @@ func NewDefaultAppMetrics(ctx context.Context) (AppMetrics, error) {
 		storeMetrics:          storeMetrics,
 		updateChannelMetrics:  updateChannelMetrics,
 		accountManagerMetrics: accountManagerMetrics,
+		ephemeralMetrics:      ephemeralMetrics,
 	}, nil
 }
 
@@ -290,6 +312,11 @@ func NewAppMetricsWithMeter(ctx context.Context, meter metric2.Meter) (AppMetric
 		return nil, fmt.Errorf("failed to initialize account manager metrics: %w", err)
 	}
 
+	ephemeralMetrics, err := NewEphemeralPeersMetrics(ctx, meter)
+	if err != nil {
+		return nil, fmt.Errorf("failed to initialize ephemeral peers metrics: %w", err)
+	}
+
 	return &defaultAppMetrics{
 		Meter:                 meter,
 		ctx:                   ctx,
@@ -300,5 +327,6 @@ func NewAppMetricsWithMeter(ctx context.Context, meter metric2.Meter) (AppMetric
 		storeMetrics:          storeMetrics,
 		updateChannelMetrics:  updateChannelMetrics,
 		accountManagerMetrics: accountManagerMetrics,
+		ephemeralMetrics:      ephemeralMetrics,
 	}, nil
 }

management/server/telemetry/ephemeral_metrics.go

@@ -0,0 +1,115 @@
+package telemetry
+
+import (
+	"context"
+
+	"go.opentelemetry.io/otel/metric"
+)
+
+// EphemeralPeersMetrics tracks the ephemeral peer cleanup pipeline: how
+// many peers are currently scheduled for deletion, how many tick runs
+// the cleaner has performed, how many peers it has removed, and how
+// many delete batches failed.
+type EphemeralPeersMetrics struct {
+	ctx context.Context
+
+	pending      metric.Int64UpDownCounter
+	cleanupRuns  metric.Int64Counter
+	peersCleaned metric.Int64Counter
+	errors       metric.Int64Counter
+}
+
+// NewEphemeralPeersMetrics constructs the ephemeral cleanup counters.
+func NewEphemeralPeersMetrics(ctx context.Context, meter metric.Meter) (*EphemeralPeersMetrics, error) {
+	pending, err := meter.Int64UpDownCounter("management.ephemeral.peers.pending",
+		metric.WithUnit("1"),
+		metric.WithDescription("Number of ephemeral peers currently waiting to be cleaned up"))
+	if err != nil {
+		return nil, err
+	}
+
+	cleanupRuns, err := meter.Int64Counter("management.ephemeral.cleanup.runs.counter",
+		metric.WithUnit("1"),
+		metric.WithDescription("Number of ephemeral cleanup ticks that processed at least one peer"))
+	if err != nil {
+		return nil, err
+	}
+
+	peersCleaned, err := meter.Int64Counter("management.ephemeral.peers.cleaned.counter",
+		metric.WithUnit("1"),
+		metric.WithDescription("Total number of ephemeral peers deleted by the cleanup loop"))
+	if err != nil {
+		return nil, err
+	}
+
+	errors, err := meter.Int64Counter("management.ephemeral.cleanup.errors.counter",
+		metric.WithUnit("1"),
+		metric.WithDescription("Number of ephemeral cleanup batches (per account) that failed to delete"))
+	if err != nil {
+		return nil, err
+	}
+
+	return &EphemeralPeersMetrics{
+		ctx:          ctx,
+		pending:      pending,
+		cleanupRuns:  cleanupRuns,
+		peersCleaned: peersCleaned,
+		errors:       errors,
+	}, nil
+}
+
+// All methods are nil-receiver safe so callers that haven't wired metrics
+// (tests, self-hosted with metrics off) can invoke them unconditionally.
+
+// IncPending bumps the pending gauge when a peer is added to the cleanup list.
+func (m *EphemeralPeersMetrics) IncPending() {
+	if m == nil {
+		return
+	}
+	m.pending.Add(m.ctx, 1)
+}
+
+// AddPending bumps the pending gauge by n — used at startup when the
+// initial set of ephemeral peers is loaded from the store.
+func (m *EphemeralPeersMetrics) AddPending(n int64) {
+	if m == nil || n <= 0 {
+		return
+	}
+	m.pending.Add(m.ctx, n)
+}
+
+// DecPending decreases the pending gauge — used both when a peer reconnects
+// before its deadline (removed from the list) and when a cleanup tick
+// actually deletes it.
+func (m *EphemeralPeersMetrics) DecPending(n int64) {
+	if m == nil || n <= 0 {
+		return
+	}
+	m.pending.Add(m.ctx, -n)
+}
+
+// CountCleanupRun records one cleanup pass that processed >0 peers. Idle
+// ticks (nothing to do) deliberately don't increment so the rate
+// reflects useful work.
+func (m *EphemeralPeersMetrics) CountCleanupRun() {
+	if m == nil {
+		return
+	}
+	m.cleanupRuns.Add(m.ctx, 1)
+}
+
+// CountPeersCleaned records the number of peers a single tick deleted.
+func (m *EphemeralPeersMetrics) CountPeersCleaned(n int64) {
+	if m == nil || n <= 0 {
+		return
+	}
+	m.peersCleaned.Add(m.ctx, n)
+}
+
+// CountCleanupError records a failed delete batch.
+func (m *EphemeralPeersMetrics) CountCleanupError() {
+	if m == nil {
+		return
+	}
+	m.errors.Add(m.ctx, 1)
+}

management/server/testdata/networks.sql

@@ -9,9 +9,13 @@ INSERT INTO peers VALUES('testPeerId','testAccountId','5rvhvriKJZ3S9oxYToVj5TzDM
 
 CREATE TABLE `networks` (`id` text,`account_id` text,`name` text,`description` text,PRIMARY KEY (`id`),CONSTRAINT `fk_accounts_networks` FOREIGN KEY (`account_id`) REFERENCES `accounts`(`id`));
 INSERT INTO networks VALUES('testNetworkId','testAccountId','some-name','some-description');
+INSERT INTO networks VALUES('secondNetworkId','testAccountId','second-name','second-description');
 
 CREATE TABLE `network_routers` (`id` text,`network_id` text,`account_id` text,`peer` text,`peer_groups` text,`masquerade` numeric,`metric` integer,PRIMARY KEY (`id`),CONSTRAINT `fk_accounts_network_routers` FOREIGN KEY (`account_id`) REFERENCES `accounts`(`id`));
 INSERT INTO network_routers VALUES('testRouterId','testNetworkId','testAccountId','','["csquuo4jcko732k1ag00"]',0,9999);
+INSERT INTO accounts VALUES('otherAccountId','','2024-10-02 16:01:38.000000000+00:00','other.com','private',1,'otherNetworkIdentifier','{"IP":"100.65.0.0","Mask":"//8AAA=="}','',0,'[]',0,86400000000000,0,0,0,'',NULL,NULL,NULL);
+INSERT INTO networks VALUES('otherNetworkId','otherAccountId','other-net','other-description');
+INSERT INTO network_routers VALUES('otherRouterId','otherNetworkId','otherAccountId','otherPeer',NULL,0,1);
 
 CREATE TABLE `network_resources` (`id` text,`network_id` text,`account_id` text,`name` text,`description` text,`type` text,`address` text,PRIMARY KEY (`id`),CONSTRAINT `fk_accounts_network_resources` FOREIGN KEY (`account_id`) REFERENCES `accounts`(`id`));
 INSERT INTO network_resources VALUES('testResourceId','testNetworkId','testAccountId','some-name','some-description','host','3.3.3.3/32');

management/server/types/account.go

@@ -32,7 +32,9 @@ import (
 )
 
 const (
-	defaultTTL                      = 300
+	defaultTTL = 300
+	// privateServiceDNSRecordTTL is short so proxy-peer changes propagate quickly to clients.
+	privateServiceDNSRecordTTL      = 5
 	DefaultPeerLoginExpiration      = 24 * time.Hour
 	DefaultPeerInactivityExpiration = 10 * time.Minute
 
@@ -254,6 +256,117 @@ func getUniqueHostLabel(name string, peerLabels LookupMap) string {
 	return ""
 }
 
+// SynthesizePrivateServiceZones returns in-memory CustomZones with A records pointing each enabled private service the peer can reach at the cluster's proxy-peer IPs. One zone per cluster (multiple services share); records gated by AccessGroups.
+func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZone {
+	peer, ok := a.Peers[peerID]
+	if !ok || peer == nil {
+		return nil
+	}
+	if len(a.Services) == 0 {
+		return nil
+	}
+
+	proxyPeersByCluster := a.GetProxyPeers()
+	if len(proxyPeersByCluster) == 0 {
+		return nil
+	}
+
+	peerGroups := a.GetPeerGroups(peerID)
+	zonesByCluster := map[string]*nbdns.CustomZone{}
+
+	for _, svc := range a.Services {
+		if svc == nil || !svc.Enabled || !svc.Private {
+			continue
+		}
+		if len(svc.AccessGroups) == 0 {
+			continue
+		}
+		if !peerInDistributionGroups(peerGroups, svc.AccessGroups) {
+			continue
+		}
+		proxyPeers := proxyPeersByCluster[svc.ProxyCluster]
+		if len(proxyPeers) == 0 {
+			continue
+		}
+
+		zone, exists := zonesByCluster[svc.ProxyCluster]
+		if !exists {
+			// NonAuthoritative makes this a match-only zone: queries for
+			// names without an explicit record fall through to the
+			// upstream resolver instead of returning NXDOMAIN. Without
+			// it, adding a single private service would black-hole every
+			// other name under the cluster apex.
+			zone = &nbdns.CustomZone{
+				Domain:           dns.Fqdn(svc.ProxyCluster),
+				Records:          []nbdns.SimpleRecord{},
+				NonAuthoritative: true,
+			}
+			zonesByCluster[svc.ProxyCluster] = zone
+		}
+
+		emitted := 0
+		skippedDisconnected := 0
+		for _, p := range proxyPeers {
+			if p == nil || !p.IP.IsValid() {
+				continue
+			}
+			// Only emit a record when the proxy peer is actually
+			// connected. A disconnected proxy peer's tunnel IP won't
+			// answer; pointing DNS at it would produce a black hole
+			// for as long as the record is cached client-side.
+			if p.Status == nil || !p.Status.Connected {
+				skippedDisconnected++
+				continue
+			}
+			zone.Records = append(zone.Records, nbdns.SimpleRecord{
+				Name:  dns.Fqdn(svc.Domain),
+				Type:  int(dns.TypeA),
+				Class: nbdns.DefaultClass,
+				TTL:   privateServiceDNSRecordTTL,
+				RData: p.IP.String(),
+			})
+			emitted++
+		}
+		// Disagreement with the firewall path is the typical
+		// "domain doesn't reach client but firewall rules do"
+		// symptom: the synth service is otherwise fine, only the
+		// proxy peer's persisted Connected flag is wrong (most
+		// likely the connection reaper marked it disconnected even
+		// though the gRPC stream is alive).
+		if emitted == 0 && skippedDisconnected > 0 {
+			log.Debugf("private-zone synth: svc %s domain=%s cluster=%s emitted_zero proxy_peers=%d all_disconnected=%d (firewall would still fire)",
+				svc.ID, svc.Domain, svc.ProxyCluster, len(proxyPeers), skippedDisconnected)
+		}
+	}
+
+	out := make([]nbdns.CustomZone, 0, len(zonesByCluster))
+	for _, zone := range zonesByCluster {
+		if len(zone.Records) == 0 {
+			continue
+		}
+		out = append(out, *zone)
+	}
+	if len(out) == 0 && len(a.Services) > 0 {
+		// Targeted diagnostic for the "firewall yes, DNS no" divergence —
+		// fires only when services exist but synth returns zero zones,
+		// so accounts without private services produce no noise.
+		log.Debugf("private-zone synth: peer %s account %s returned 0 zones from %d candidate service(s)",
+			peerID, a.Id, len(a.Services))
+	}
+	return out
+}
+
+// peerInDistributionGroups reports whether any of the peer's groups
+// matches the service's bearer-auth distribution_groups.
+func peerInDistributionGroups(peerGroups LookupMap, distributionGroups []string) bool {
+	for _, gid := range distributionGroups {
+		if _, ok := peerGroups[gid]; ok {
+			return true
+		}
+	}
+	return false
+}
+
 func (a *Account) GetPeersCustomZone(ctx context.Context, dnsDomain string) nbdns.CustomZone {
 	var merr *multierror.Error
 
@@ -598,28 +711,21 @@ func (a *Account) GetPeerGroups(peerID string) LookupMap {
 	return groupList
 }
 
-// PeerIPv6Allowed reports whether the given peer is in any of the account's IPv6 enabled groups.
+// PeerIPv6Allowed reports whether the given peer participates in the IPv6 overlay.
 // Returns false if IPv6 is disabled or no groups are configured.
 func (a *Account) PeerIPv6Allowed(peerID string) bool {
-	if len(a.Settings.IPv6EnabledGroups) == 0 {
-		return false
-	}
-
-	for _, groupID := range a.Settings.IPv6EnabledGroups {
-		group, ok := a.Groups[groupID]
-		if !ok {
-			continue
-		}
-		if slices.Contains(group.Peers, peerID) {
-			return true
-		}
-	}
-	return false
+	_, ok := a.peerIPv6AllowedSet()[peerID]
+	return ok
 }
 
-// peerIPv6AllowedSet returns a set of peer IDs that belong to any IPv6-enabled group.
+// peerIPv6AllowedSet returns the set of peer IDs that participate in the IPv6 overlay:
+// members of any IPv6-enabled group, plus every embedded proxy peer (which sit outside
+// regular group membership but must reach v6-enabled peers).
 func (a *Account) peerIPv6AllowedSet() map[string]struct{} {
 	result := make(map[string]struct{})
+	if len(a.Settings.IPv6EnabledGroups) == 0 {
+		return result
+	}
 	for _, groupID := range a.Settings.IPv6EnabledGroups {
 		group, ok := a.Groups[groupID]
 		if !ok {
@@ -629,6 +735,11 @@ func (a *Account) peerIPv6AllowedSet() map[string]struct{} {
 			result[peerID] = struct{}{}
 		}
 	}
+	for id, p := range a.Peers {
+		if p != nil && p.ProxyMeta.Embedded {
+			result[id] = struct{}{}
+		}
+	}
 	return result
 }
 
@@ -1500,6 +1611,53 @@ func (a *Account) injectServiceProxyPolicies(ctx context.Context, service *servi
 		a.injectTargetProxyPolicies(ctx, service, target, proxyPeers)
 	}
 
+	a.injectPrivateServicePolicies(service, proxyPeers)
+}
+
+// injectPrivateServicePolicies synthesises an in-memory ACL: AccessGroups → cluster proxy peers on TCP 80/443.
+func (a *Account) injectPrivateServicePolicies(svc *service.Service, proxyPeers []*nbpeer.Peer) {
+	if !svc.Private {
+		return
+	}
+	if len(svc.AccessGroups) == 0 {
+		return
+	}
+	if len(proxyPeers) == 0 {
+		return
+	}
+	for _, proxyPeer := range proxyPeers {
+		a.Policies = append(a.Policies, a.createPrivateServicePolicy(svc, proxyPeer))
+	}
+}
+
+func (a *Account) createPrivateServicePolicy(svc *service.Service, proxyPeer *nbpeer.Peer) *Policy {
+	policyID := fmt.Sprintf("private-access-%s-%s", svc.ID, proxyPeer.ID)
+	sources := append([]string(nil), svc.AccessGroups...)
+	return &Policy{
+		ID:      policyID,
+		Name:    fmt.Sprintf("Private Access to %s", svc.Name),
+		Enabled: true,
+		Rules: []*PolicyRule{
+			{
+				ID:       policyID,
+				PolicyID: policyID,
+				Name:     fmt.Sprintf("Allow access groups to reach %s", svc.Name),
+				Enabled:  true,
+				Sources:  sources,
+				DestinationResource: Resource{
+					ID:   proxyPeer.ID,
+					Type: ResourceTypePeer,
+				},
+				Bidirectional: false,
+				Protocol:      PolicyRuleProtocolTCP,
+				Action:        PolicyTrafficActionAccept,
+				PortRanges: []RulePortRange{
+					{Start: 80, End: 80},
+					{Start: 443, End: 443},
+				},
+			},
+		},
+	}
 }
 
 func (a *Account) injectTargetProxyPolicies(ctx context.Context, service *service.Service, target *service.Target, proxyPeers []*nbpeer.Peer) {

management/server/types/account_components.go

@@ -119,6 +119,7 @@ func (a *Account) GetPeerNetworkMapComponents(
 
 	peerGroups := a.GetPeerGroups(peerID)
 	components.AccountZones = filterPeerAppliedZones(ctx, accountZones, peerGroups)
+	components.AccountZones = append(components.AccountZones, a.SynthesizePrivateServiceZones(peerID)...)
 
 	for _, nsGroup := range a.NameServerGroups {
 		if nsGroup.Enabled {

management/server/types/account_private_netmap_test.go

@@ -0,0 +1,85 @@
+package types
+
+import (
+	"context"
+	"testing"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	nbdns "github.com/netbirdio/netbird/dns"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+)
+
+func TestPrivateService_NetworkMap_UserPeer_AndProxyPeer(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Peers["user-peer"].Meta.WtVersion = "0.50.0"
+	account.Peers["proxy-peer"].Meta.WtVersion = "0.50.0"
+
+	ctx := context.Background()
+	account.InjectProxyPolicies(ctx)
+
+	validated := map[string]struct{}{
+		"user-peer":  {},
+		"proxy-peer": {},
+	}
+
+	t.Run("user-peer update", func(t *testing.T) {
+		nm := account.GetPeerNetworkMapFromComponents(ctx, "user-peer", nbdns.CustomZone{}, nil, validated, nil, nil, nil, nil)
+		require.NotNil(t, nm)
+
+		zone, ok := findCustomZone(nm.DNSConfig.CustomZones, "eu.proxy.netbird.io")
+		require.True(t, ok)
+		require.Len(t, zone.Records, 1)
+		assert.Equal(t, "myapp.eu.proxy.netbird.io.", zone.Records[0].Name)
+		assert.Equal(t, int(dns.TypeA), zone.Records[0].Type)
+		assert.Equal(t, "100.64.0.99", zone.Records[0].RData)
+
+		assert.Contains(t, netmapPeerIDs(nm.Peers), "proxy-peer")
+		assertPrivateServiceFirewallRules(t, nm.FirewallRules, "100.64.0.99", FirewallRuleDirectionOUT)
+	})
+
+	t.Run("proxy-peer update", func(t *testing.T) {
+		nm := account.GetPeerNetworkMapFromComponents(ctx, "proxy-peer", nbdns.CustomZone{}, nil, validated, nil, nil, nil, nil)
+		require.NotNil(t, nm)
+
+		assert.Contains(t, netmapPeerIDs(nm.Peers), "user-peer")
+		assertPrivateServiceFirewallRules(t, nm.FirewallRules, "100.64.0.10", FirewallRuleDirectionIN)
+	})
+}
+
+func netmapPeerIDs(peers []*nbpeer.Peer) []string {
+	ids := make([]string, 0, len(peers))
+	for _, p := range peers {
+		if p == nil {
+			continue
+		}
+		ids = append(ids, p.ID)
+	}
+	return ids
+}
+
+func assertPrivateServiceFirewallRules(t *testing.T, rules []*FirewallRule, peerIP string, direction int) {
+	t.Helper()
+	wantPorts := map[uint16]bool{80: false, 443: false}
+	for _, r := range rules {
+		if r == nil || r.PeerIP != peerIP || r.Direction != direction {
+			continue
+		}
+		if r.Protocol != string(PolicyRuleProtocolTCP) || r.Action != string(PolicyTrafficActionAccept) {
+			continue
+		}
+		switch {
+		case r.PortRange.Start == r.PortRange.End && r.PortRange.Start != 0:
+			wantPorts[r.PortRange.Start] = true
+		case r.Port == "80":
+			wantPorts[80] = true
+		case r.Port == "443":
+			wantPorts[443] = true
+		}
+	}
+	for port, found := range wantPorts {
+		assert.Truef(t, found, "missing TCP accept rule on port %d for peer %s direction %d", port, peerIP, direction)
+	}
+}

management/server/types/account_private_zones_test.go

@@ -0,0 +1,256 @@
+package types
+
+import (
+	"context"
+	"net"
+	"net/netip"
+	"testing"
+
+	"github.com/miekg/dns"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
+	nbpeer "github.com/netbirdio/netbird/management/server/peer"
+)
+
+func privateZoneTestAccount(t *testing.T) *Account {
+	t.Helper()
+	return &Account{
+		Id:       "acct-1",
+		Settings: &Settings{},
+		Network: &Network{
+			Identifier: "net-1",
+			Net:        net.IPNet{IP: net.ParseIP("100.64.0.0"), Mask: net.CIDRMask(10, 32)},
+		},
+		Peers: map[string]*nbpeer.Peer{
+			"user-peer": {
+				ID:        "user-peer",
+				AccountID: "acct-1",
+				Key:       "user-peer-key",
+				IP:        netip.MustParseAddr("100.64.0.10"),
+				Status:    &nbpeer.PeerStatus{Connected: true},
+			},
+			"proxy-peer": {
+				ID:        "proxy-peer",
+				AccountID: "acct-1",
+				Key:       "proxy-peer-key",
+				IP:        netip.MustParseAddr("100.64.0.99"),
+				Status:    &nbpeer.PeerStatus{Connected: true},
+				ProxyMeta: nbpeer.ProxyMeta{
+					Embedded: true,
+					Cluster:  "eu.proxy.netbird.io",
+				},
+			},
+		},
+		Groups: map[string]*Group{
+			"grp-admins": {
+				ID:    "grp-admins",
+				Name:  "admins",
+				Peers: []string{"user-peer"},
+			},
+		},
+		Services: []*service.Service{
+			{
+				ID:           "svc-1",
+				AccountID:    "acct-1",
+				Name:         "myapp",
+				Domain:       "myapp.eu.proxy.netbird.io",
+				ProxyCluster: "eu.proxy.netbird.io",
+				Enabled:      true,
+				Private:      true,
+				Mode:         service.ModeHTTP,
+				AccessGroups: []string{"grp-admins"},
+			},
+		},
+	}
+}
+
+func TestSynthesizePrivateServiceZones_PeerInGroup_GetsRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	require.Len(t, zones, 1, "one cluster should produce one zone")
+	zone := zones[0]
+	assert.Equal(t, "eu.proxy.netbird.io.", zone.Domain, "zone apex must be the cluster FQDN")
+	assert.True(t, zone.NonAuthoritative, "synth zone must be match-only so unrelated sibling names fall through to the upstream resolver")
+	require.Len(t, zone.Records, 1, "one private service yields one A record")
+	rec := zone.Records[0]
+	assert.Equal(t, "myapp.eu.proxy.netbird.io.", rec.Name, "record name is the service FQDN")
+	assert.Equal(t, int(dns.TypeA), rec.Type, "record type must be A")
+	assert.Equal(t, "100.64.0.99", rec.RData, "record points at the embedded proxy peer's tunnel IP")
+	assert.Equal(t, privateServiceDNSRecordTTL, rec.TTL, "TTL must match the synth-records constant")
+	assert.Equal(t, nbdns.DefaultClass, rec.Class, "record class must be the package default")
+}
+
+func TestSynthesizePrivateServiceZones_PeerNotInGroup_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Groups["grp-admins"].Peers = nil
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "peer outside distribution_groups must not see private-service records")
+}
+
+func TestSynthesizePrivateServiceZones_NotPrivate_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Services[0].Private = false
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "non-private service must not produce DNS records")
+}
+
+func TestSynthesizePrivateServiceZones_NoAccessGroups_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Services[0].AccessGroups = nil
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "private service without bearer auth must not produce DNS records")
+}
+
+func TestSynthesizePrivateServiceZones_NoProxyPeers_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	delete(account.Peers, "proxy-peer")
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "no embedded proxy peer in cluster means no record to emit")
+}
+
+func TestSynthesizePrivateServiceZones_DisabledService_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Services[0].Enabled = false
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "disabled service must not produce DNS records")
+}
+
+func TestSynthesizePrivateServiceZones_DisconnectedProxyPeer_NoRecord(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Peers["proxy-peer"].Status = &nbpeer.PeerStatus{Connected: false}
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	assert.Empty(t, zones, "disconnected proxy peer must not produce a DNS record (would be a black hole)")
+}
+
+func TestSynthesizePrivateServiceZones_PartiallyDisconnectedProxyPeers_OnlyConnectedSurface(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Peers["proxy-peer-2"] = &nbpeer.Peer{
+		ID:        "proxy-peer-2",
+		AccountID: "acct-1",
+		Key:       "proxy-peer-2-key",
+		IP:        netip.MustParseAddr("100.64.0.100"),
+		Status:    &nbpeer.PeerStatus{Connected: false},
+		ProxyMeta: nbpeer.ProxyMeta{Embedded: true, Cluster: "eu.proxy.netbird.io"},
+	}
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	require.Len(t, zones, 1)
+	require.Len(t, zones[0].Records, 1, "only the connected proxy peer must surface")
+	assert.Equal(t, "100.64.0.99", zones[0].Records[0].RData)
+}
+
+func TestSynthesizePrivateServiceZones_MultipleProxyPeers_RoundRobin(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Peers["proxy-peer-2"] = &nbpeer.Peer{
+		ID:        "proxy-peer-2",
+		AccountID: "acct-1",
+		Key:       "proxy-peer-2-key",
+		IP:        netip.MustParseAddr("100.64.0.100"),
+		Status:    &nbpeer.PeerStatus{Connected: true},
+		ProxyMeta: nbpeer.ProxyMeta{Embedded: true, Cluster: "eu.proxy.netbird.io"},
+	}
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	require.Len(t, zones, 1, "still one cluster yields one zone")
+	require.Len(t, zones[0].Records, 2, "two proxy peers must produce two A records on the same name")
+	rdata := []string{zones[0].Records[0].RData, zones[0].Records[1].RData}
+	assert.ElementsMatch(t, []string{"100.64.0.99", "100.64.0.100"}, rdata, "both proxy peer IPs must surface")
+}
+
+// findCustomZone returns the CustomZone whose Domain equals the FQDN
+// of want, or a zero value when not found. Tests use it to assert
+// that the synth zone reaches dnsUpdate.CustomZones end-to-end.
+func findCustomZone(zones []nbdns.CustomZone, want string) (nbdns.CustomZone, bool) {
+	wantFqdn := dns.Fqdn(want)
+	for _, z := range zones {
+		if z.Domain == wantFqdn {
+			return z, true
+		}
+	}
+	return nbdns.CustomZone{}, false
+}
+
+// TestPrivateZone_GetPeerNetworkMapFromComponents_ShipsSynthZone
+// covers the components-based builder path. The components builder
+// appends SynthesizePrivateServiceZones to AccountZones; the
+// CalculateNetworkMapFromComponents step then merges AccountZones
+// into dnsUpdate.CustomZones.
+func TestPrivateZone_GetPeerNetworkMapFromComponents_ShipsSynthZone(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	ctx := context.Background()
+	validated := map[string]struct{}{
+		"user-peer":  {},
+		"proxy-peer": {},
+	}
+
+	nm := account.GetPeerNetworkMapFromComponents(ctx, "user-peer", nbdns.CustomZone{}, nil, validated, nil, nil, nil, nil)
+	require.NotNil(t, nm, "network map must be produced for an in-account peer")
+
+	zone, ok := findCustomZone(nm.DNSConfig.CustomZones, "eu.proxy.netbird.io")
+	require.True(t, ok, "shipped CustomZones must include the synth zone for the cluster")
+	require.Len(t, zone.Records, 1, "exactly one record per private service per connected proxy peer")
+	rec := zone.Records[0]
+	assert.Equal(t, "myapp.eu.proxy.netbird.io.", rec.Name, "record name is the service FQDN")
+	assert.Equal(t, "100.64.0.99", rec.RData, "record points at the embedded proxy peer's tunnel IP")
+}
+
+// TestPrivateZone_GetPeerNetworkMap_PeerOutsideGroups_OmitsSynthZone
+// confirms the negative case the user encountered: a peer whose
+// groups don't overlap the policy's distribution_groups gets a
+// network map with no synth zone (and the wildcard / peer zones still
+// flow through). This is the test mirror of the runtime confusion
+// where the user looked at a non-distribution-group peer and assumed
+// the synth path was broken.
+func TestPrivateZone_GetPeerNetworkMap_PeerOutsideGroups_OmitsSynthZone(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Peers["outsider"] = &nbpeer.Peer{
+		ID:        "outsider",
+		AccountID: "acct-1",
+		Key:       "outsider-key",
+		IP:        netip.MustParseAddr("100.64.0.20"),
+		Status:    &nbpeer.PeerStatus{Connected: true},
+	}
+	ctx := context.Background()
+	validated := map[string]struct{}{
+		"user-peer":  {},
+		"proxy-peer": {},
+		"outsider":   {},
+	}
+
+	nm := account.GetPeerNetworkMapFromComponents(ctx, "outsider", nbdns.CustomZone{}, nil, validated, nil, nil, nil, nil)
+	require.NotNil(t, nm)
+
+	_, ok := findCustomZone(nm.DNSConfig.CustomZones, "eu.proxy.netbird.io")
+	assert.False(t, ok, "peer outside the distribution_groups must not see the synth zone")
+}
+
+func TestSynthesizePrivateServiceZones_TwoServicesSameCluster_OneZone(t *testing.T) {
+	account := privateZoneTestAccount(t)
+	account.Services = append(account.Services, &service.Service{
+		ID:           "svc-2",
+		AccountID:    "acct-1",
+		Name:         "anotherapp",
+		Domain:       "anotherapp.eu.proxy.netbird.io",
+		ProxyCluster: "eu.proxy.netbird.io",
+		Enabled:      true,
+		Private:      true,
+		Mode:         service.ModeHTTP,
+		AccessGroups: []string{"grp-admins"},
+	})
+
+	zones := account.SynthesizePrivateServiceZones("user-peer")
+	require.Len(t, zones, 1, "two services on the same cluster must collapse into one zone")
+	require.Len(t, zones[0].Records, 2, "two services yield two A records")
+	names := []string{zones[0].Records[0].Name, zones[0].Records[1].Name}
+	assert.ElementsMatch(t, []string{"myapp.eu.proxy.netbird.io.", "anotherapp.eu.proxy.netbird.io."}, names, "both service domains must surface")
+}

management/server/types/account_test.go

@@ -3,6 +3,7 @@ package types
 import (
 	"context"
 	"fmt"
+	"net"
 	"net/netip"
 	"testing"
 
@@ -11,6 +12,7 @@ import (
 	"github.com/stretchr/testify/require"
 
 	nbdns "github.com/netbirdio/netbird/dns"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/zones"
 	"github.com/netbirdio/netbird/management/internals/modules/zones/records"
 	resourceTypes "github.com/netbirdio/netbird/management/server/networks/resources/types"
@@ -82,9 +84,9 @@ func setupTestAccount() *Account {
 		},
 		Groups: map[string]*Group{
 			"groupAll": {
-				ID:    "groupAll",
-				Name:  "All",
-				Peers: []string{"peer1", "peer2", "peer3", "peer11", "peer12", "peer21", "peer31", "peer32", "peer41", "peer51", "peer61"},
+				ID:     "groupAll",
+				Name:   "All",
+				Peers:  []string{"peer1", "peer2", "peer3", "peer11", "peer12", "peer21", "peer31", "peer32", "peer41", "peer51", "peer61"},
 				Issued: GroupIssuedAPI,
 			},
 			"group1": {
@@ -1583,3 +1585,203 @@ func Test_filterPeerAppliedZones(t *testing.T) {
 		})
 	}
 }
+
+func TestInjectPrivateServicePolicies_ProxyPeerGetsInboundRule(t *testing.T) {
+	ctx := context.Background()
+
+	userPeerIP := netip.MustParseAddr("100.64.0.10")
+	proxyPeerIP := netip.MustParseAddr("100.64.0.99")
+
+	account := &Account{
+		Id: "acct-1",
+		Network: &Network{
+			Identifier: "net-1",
+			Net:        net.IPNet{IP: net.ParseIP("100.64.0.0"), Mask: net.CIDRMask(10, 32)},
+		},
+		Peers: map[string]*nbpeer.Peer{
+			"user-peer": {
+				ID:        "user-peer",
+				AccountID: "acct-1",
+				Key:       "user-peer-key",
+				IP:        userPeerIP,
+			},
+			"proxy-peer": {
+				ID:        "proxy-peer",
+				AccountID: "acct-1",
+				Key:       "proxy-peer-key",
+				IP:        proxyPeerIP,
+				ProxyMeta: nbpeer.ProxyMeta{
+					Embedded: true,
+					Cluster:  "eu.proxy.netbird.io",
+				},
+			},
+		},
+		Groups: map[string]*Group{
+			"grp-admins": {
+				ID:    "grp-admins",
+				Name:  "admins",
+				Peers: []string{"user-peer"},
+			},
+		},
+		Services: []*service.Service{
+			{
+				ID:           "svc-1",
+				AccountID:    "acct-1",
+				Name:         "myapp",
+				Domain:       "myapp.eu.proxy.netbird.io",
+				ProxyCluster: "eu.proxy.netbird.io",
+				Enabled:      true,
+				Private:      true,
+				Mode:         service.ModeHTTP,
+				AccessGroups: []string{"grp-admins"},
+				Targets: []*service.Target{
+					{
+						TargetId:   "eu.proxy.netbird.io",
+						TargetType: service.TargetTypeCluster,
+						Protocol:   "http",
+						Host:       "127.0.0.1",
+						Port:       8080,
+						Enabled:    true,
+					},
+				},
+			},
+		},
+	}
+
+	account.InjectProxyPolicies(ctx)
+
+	var found *Policy
+	for _, p := range account.Policies {
+		if p != nil && p.ID == "private-access-svc-1-proxy-peer" {
+			found = p
+			break
+		}
+	}
+	require.NotNil(t, found, "expected synthesised private-access policy in account.Policies")
+	require.Len(t, found.Rules, 1, "policy should have exactly one rule")
+	rule := found.Rules[0]
+	assert.Equal(t, []string{"grp-admins"}, rule.Sources, "sources should be group IDs verbatim")
+	assert.Equal(t, "proxy-peer", rule.DestinationResource.ID, "destination resource should be the proxy peer ID")
+	assert.Equal(t, ResourceTypePeer, rule.DestinationResource.Type, "destination resource type should be peer")
+
+	validatedPeersMap := map[string]struct{}{
+		"user-peer":  {},
+		"proxy-peer": {},
+	}
+
+	proxyPeer := account.Peers["proxy-peer"]
+	aclPeers, firewallRules, _, _ := account.GetPeerConnectionResources(ctx, proxyPeer, validatedPeersMap, nil)
+
+	var sawUserAsAclPeer bool
+	for _, p := range aclPeers {
+		if p.ID == "user-peer" {
+			sawUserAsAclPeer = true
+			break
+		}
+	}
+	assert.True(t, sawUserAsAclPeer, "proxy peer should see the user peer as an ACL peer")
+
+	var inboundRules []*FirewallRule
+	for _, r := range firewallRules {
+		if r.Direction == FirewallRuleDirectionIN && r.PeerIP == userPeerIP.String() {
+			inboundRules = append(inboundRules, r)
+		}
+	}
+	assert.NotEmpty(t, inboundRules, "proxy peer should have inbound firewall rules from the user peer")
+}
+
+func TestInjectPrivateServicePolicies_NotPrivate_NoPolicy(t *testing.T) {
+	ctx := context.Background()
+	account := privateServiceTestAccount(t)
+	account.Services[0].Private = false
+
+	account.InjectProxyPolicies(ctx)
+	assert.False(t, hasPrivateAccessPolicy(account, "svc-1"), "non-private service must not synthesise an access policy")
+}
+
+func TestInjectPrivateServicePolicies_EmptyAccessGroups_NoPolicy(t *testing.T) {
+	ctx := context.Background()
+	account := privateServiceTestAccount(t)
+	account.Services[0].AccessGroups = nil
+
+	account.InjectProxyPolicies(ctx)
+	assert.False(t, hasPrivateAccessPolicy(account, "svc-1"), "private service with no access groups must not synthesise a policy")
+}
+
+func TestInjectPrivateServicePolicies_NoProxyPeers_NoPolicy(t *testing.T) {
+	ctx := context.Background()
+	account := privateServiceTestAccount(t)
+	delete(account.Peers, "proxy-peer")
+
+	account.InjectProxyPolicies(ctx)
+	assert.False(t, hasPrivateAccessPolicy(account, "svc-1"), "policy must not synthesise when the cluster has no proxy peers")
+}
+
+func privateServiceTestAccount(t *testing.T) *Account {
+	t.Helper()
+	return &Account{
+		Id: "acct-1",
+		Network: &Network{
+			Identifier: "net-1",
+			Net:        net.IPNet{IP: net.ParseIP("100.64.0.0"), Mask: net.CIDRMask(10, 32)},
+		},
+		Peers: map[string]*nbpeer.Peer{
+			"user-peer": {
+				ID:        "user-peer",
+				AccountID: "acct-1",
+				Key:       "user-peer-key",
+				IP:        netip.MustParseAddr("100.64.0.10"),
+			},
+			"proxy-peer": {
+				ID:        "proxy-peer",
+				AccountID: "acct-1",
+				Key:       "proxy-peer-key",
+				IP:        netip.MustParseAddr("100.64.0.99"),
+				ProxyMeta: nbpeer.ProxyMeta{
+					Embedded: true,
+					Cluster:  "eu.proxy.netbird.io",
+				},
+			},
+		},
+		Groups: map[string]*Group{
+			"grp-admins": {
+				ID:    "grp-admins",
+				Name:  "admins",
+				Peers: []string{"user-peer"},
+			},
+		},
+		Services: []*service.Service{
+			{
+				ID:           "svc-1",
+				AccountID:    "acct-1",
+				Name:         "myapp",
+				Domain:       "myapp.eu.proxy.netbird.io",
+				ProxyCluster: "eu.proxy.netbird.io",
+				Enabled:      true,
+				Private:      true,
+				Mode:         service.ModeHTTP,
+				AccessGroups: []string{"grp-admins"},
+				Targets: []*service.Target{
+					{
+						TargetId:   "eu.proxy.netbird.io",
+						TargetType: service.TargetTypeCluster,
+						Protocol:   "http",
+						Host:       "127.0.0.1",
+						Port:       8080,
+						Enabled:    true,
+					},
+				},
+			},
+		},
+	}
+}
+
+func hasPrivateAccessPolicy(account *Account, serviceID string) bool {
+	prefix := "private-access-" + serviceID + "-"
+	for _, p := range account.Policies {
+		if p != nil && len(p.ID) > len(prefix) && p.ID[:len(prefix)] == prefix {
+			return true
+		}
+	}
+	return false
+}

management/server/types/group.go

@@ -92,9 +92,12 @@ func (g *Group) HasPeers() bool {
 	return len(g.Peers) > 0
 }
 
+// GroupAllName is the reserved name of the default group that contains every peer in an account.
+const GroupAllName = "All"
+
 // IsGroupAll checks if the group is a default "All" group.
 func (g *Group) IsGroupAll() bool {
-	return g.Name == "All"
+	return g.Name == GroupAllName
 }
 
 // AddPeer adds peerID to Peers if not present, returning true if added.

management/server/types/ipv6_groups_test.go

@@ -232,3 +232,33 @@ func TestIPv6RecalculationOnGroupChange(t *testing.T) {
 		assert.True(t, account.PeerIPv6Allowed("peer3"), "peer3 now in infra")
 	})
 }
+
+func TestPeerIPv6AllowedEmbeddedProxy(t *testing.T) {
+	account := &Account{
+		Peers: map[string]*nbpeer.Peer{
+			"peer1": {ID: "peer1"},
+			"proxy": {ID: "proxy", ProxyMeta: nbpeer.ProxyMeta{Embedded: true, Cluster: "netbird.test"}},
+		},
+		Groups: map[string]*Group{
+			"group-devs": {ID: "group-devs", Peers: []string{"peer1"}},
+		},
+		Settings: &Settings{},
+	}
+
+	t.Run("embedded proxy allowed when any v6 group exists, without group membership", func(t *testing.T) {
+		account.Settings.IPv6EnabledGroups = []string{"group-devs"}
+		assert.True(t, account.PeerIPv6Allowed("proxy"), "embedded proxy participates in v6 overlay")
+		assert.True(t, account.PeerIPv6Allowed("peer1"), "regular peer in enabled group still allowed")
+	})
+
+	t.Run("embedded proxy denied when no v6 group enabled", func(t *testing.T) {
+		account.Settings.IPv6EnabledGroups = nil
+		assert.False(t, account.PeerIPv6Allowed("proxy"), "v6 disabled account-wide denies embedded proxies too")
+	})
+
+	t.Run("non-embedded peer outside any enabled group is not pulled in", func(t *testing.T) {
+		account.Settings.IPv6EnabledGroups = []string{"group-devs"}
+		account.Peers["lonely"] = &nbpeer.Peer{ID: "lonely"}
+		assert.False(t, account.PeerIPv6Allowed("lonely"), "embedded-proxy bypass must not leak to regular peers")
+	})
+}

management/server/user.go

@@ -762,7 +762,7 @@ func (am *DefaultAccountManager) processUserUpdate(ctx context.Context, transact
 		}
 
 		// Ensure the initiator still has admin privileges
-		if initiatorUser.HasAdminPower() && !freshInitiator.HasAdminPower() {
+		if !freshInitiator.HasAdminPower() {
 			return false, nil, nil, nil, status.Errorf(status.PermissionDenied, "initiator role was changed during request processing")
 		}
 		initiatorUser = freshInitiator
@@ -906,19 +906,23 @@ func validateUserUpdate(groupsMap map[string]*types.Group, initiatorUser, oldUse
 		return nil
 	}
 
+	if !initiatorUser.HasAdminPower() {
+		return status.Errorf(status.PermissionDenied, "only admins and owners can update users")
+	}
+
 	if initiatorUser.HasAdminPower() && initiatorUser.Id == update.Id && oldUser.Blocked != update.Blocked {
 		return status.Errorf(status.PermissionDenied, "admins can't block or unblock themselves")
 	}
 	if initiatorUser.HasAdminPower() && initiatorUser.Id == update.Id && update.Role != initiatorUser.Role {
 		return status.Errorf(status.PermissionDenied, "admins can't change their role")
 	}
-	if initiatorUser.Role == types.UserRoleAdmin && oldUser.Role == types.UserRoleOwner && update.Role != oldUser.Role {
+	if initiatorUser.Role != types.UserRoleOwner && oldUser.Role == types.UserRoleOwner && update.Role != oldUser.Role {
 		return status.Errorf(status.PermissionDenied, "only owners can remove owner role from their user")
 	}
-	if initiatorUser.Role == types.UserRoleAdmin && oldUser.Role == types.UserRoleOwner && update.IsBlocked() && !oldUser.IsBlocked() {
+	if oldUser.Role == types.UserRoleOwner && update.IsBlocked() && !oldUser.IsBlocked() {
 		return status.Errorf(status.PermissionDenied, "unable to block owner user")
 	}
-	if initiatorUser.Role == types.UserRoleAdmin && update.Role == types.UserRoleOwner && update.Role != oldUser.Role {
+	if initiatorUser.Role != types.UserRoleOwner && update.Role == types.UserRoleOwner && update.Role != oldUser.Role {
 		return status.Errorf(status.PermissionDenied, "only owners can add owner role to other users")
 	}
 	if oldUser.IsServiceUser && update.Role == types.UserRoleOwner {

management/server/users/manager.go

@@ -10,6 +10,7 @@ import (
 
 type Manager interface {
 	GetUser(ctx context.Context, userID string) (*types.User, error)
+	GetUserWithGroups(ctx context.Context, userID string) (*types.User, []*types.Group, error)
 }
 
 type managerImpl struct {
@@ -29,6 +30,31 @@ func (m *managerImpl) GetUser(ctx context.Context, userID string) (*types.User,
 	return m.store.GetUserByUserID(ctx, store.LockingStrengthNone, userID)
 }
 
+// GetUserWithGroups returns the user and the *types.Group records for the user's AutoGroups, in the same order as
+// AutoGroups. Group ids that don't resolve to a stored group are skipped from the returned slice (the parallel id list is
+// derivable from the returned User). Wraps two store calls today; can be optimised to a single JOIN later if needed.
+// Any store error returns (nil, nil, err) so callers never receive a valid user alongside a non-nil error.
+func (m *managerImpl) GetUserWithGroups(ctx context.Context, userID string) (*types.User, []*types.Group, error) {
+	user, err := m.store.GetUserByUserID(ctx, store.LockingStrengthNone, userID)
+	if err != nil {
+		return nil, nil, err
+	}
+	if len(user.AutoGroups) == 0 {
+		return user, nil, nil
+	}
+	groupsMap, err := m.store.GetGroupsByIDs(ctx, store.LockingStrengthNone, user.AccountID, user.AutoGroups)
+	if err != nil {
+		return nil, nil, err
+	}
+	groups := make([]*types.Group, 0, len(user.AutoGroups))
+	for _, id := range user.AutoGroups {
+		if g, ok := groupsMap[id]; ok && g != nil {
+			groups = append(groups, g)
+		}
+	}
+	return user, groups, nil
+}
+
 func NewManagerMock() Manager {
 	return &managerMock{}
 }
@@ -47,3 +73,11 @@ func (m *managerMock) GetUser(ctx context.Context, userID string) (*types.User,
 		return nil, errors.New("user not found")
 	}
 }
+
+func (m *managerMock) GetUserWithGroups(ctx context.Context, userID string) (*types.User, []*types.Group, error) {
+	user, err := m.GetUser(ctx, userID)
+	if err != nil {
+		return nil, nil, err
+	}
+	return user, nil, nil
+}