Merge branch 'main' into feature/affected-peers

# Conflicts:
#	management/server/peer.go

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
 			}
@@ -386,6 +401,9 @@ func (am *DefaultAccountManager) UpdateAccountSettings(ctx context.Context, acco
 	if err = am.handleInactivityExpirationSettings(ctx, oldSettings, newSettings, userID, accountID); err != nil {
 		return nil, err
 	}
+	if err = am.handleLocalMfaSettings(ctx, oldSettings, newSettings, userID, accountID); err != nil {
+		return nil, err
+	}
 	if oldSettings.DNSDomain != newSettings.DNSDomain {
 		eventMeta := map[string]any{
 			"old_dns_domain": oldSettings.DNSDomain,
@@ -393,9 +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)
@@ -440,6 +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 {
@@ -602,6 +636,29 @@ func (am *DefaultAccountManager) handleInactivityExpirationSettings(ctx context.
 	return nil
 }
 
+func (am *DefaultAccountManager) handleLocalMfaSettings(ctx context.Context, oldSettings, newSettings *types.Settings, userID, accountID string) error {
+	if oldSettings.LocalMfaEnabled == newSettings.LocalMfaEnabled {
+		return nil
+	}
+
+	embeddedIdp, ok := am.idpManager.(*idp.EmbeddedIdPManager)
+	if !ok {
+		return nil
+	}
+
+	if err := embeddedIdp.SetMFAEnabled(ctx, newSettings.LocalMfaEnabled); err != nil {
+		return fmt.Errorf("failed to toggle MFA: %w", err)
+	}
+
+	if newSettings.LocalMfaEnabled {
+		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountLocalMfaEnabled, nil)
+	} else {
+		am.StoreEvent(ctx, userID, accountID, accountID, activity.AccountLocalMfaDisabled, nil)
+	}
+
+	return nil
+}
+
 func (am *DefaultAccountManager) peerLoginExpirationJob(ctx context.Context, accountID string) func() (time.Duration, bool) {
 	return func() (time.Duration, bool) {
 		//nolint
@@ -1811,35 +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
@@ -2461,6 +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

@@ -1317,17 +1317,31 @@ 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{}
@@ -3113,7 +3192,7 @@ func createManager(t testing.TB) (*DefaultAccountManager, *update_channel.PeersU
 		return nil, nil, err
 	}
 
-	proxyGrpcServer := nbgrpc.NewProxyServiceServer(nil, nil, nil, nbgrpc.ProxyOIDCConfig{}, peersManager, nil, proxyManager)
+	proxyGrpcServer := nbgrpc.NewProxyServiceServer(nil, nil, nil, nbgrpc.ProxyOIDCConfig{}, peersManager, nil, proxyManager, nil)
 	proxyController, err := proxymanager.NewGRPCController(proxyGrpcServer, noop.Meter{})
 	if err != nil {
 		return nil, nil, err
@@ -3980,6 +4059,96 @@ 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/activity/codes.go

@@ -236,6 +236,11 @@ const (
 	// AccountIPv6Disabled indicates that a user disabled IPv6 overlay for the account
 	AccountIPv6Disabled Activity = 122
 
+	// AccountLocalMfaEnabled indicates that a user enabled TOTP MFA for local users
+	AccountLocalMfaEnabled Activity = 123
+	// AccountLocalMfaDisabled indicates that a user disabled TOTP MFA for local users
+	AccountLocalMfaDisabled Activity = 124
+
 	AccountDeleted Activity = 99999
 )
 
@@ -386,6 +391,9 @@ var activityMap = map[Activity]Code{
 	AccountPeerExposeEnabled:  {"Account peer expose enabled", "account.setting.peer.expose.enable"},
 	AccountPeerExposeDisabled: {"Account peer expose disabled", "account.setting.peer.expose.disable"},
 
+	AccountLocalMfaEnabled:  {"Account local MFA enabled", "account.setting.local.mfa.enable"},
+	AccountLocalMfaDisabled: {"Account local MFA disabled", "account.setting.local.mfa.disable"},
+
 	DomainAdded:     {"Domain added", "domain.add"},
 	DomainDeleted:   {"Domain deleted", "domain.delete"},
 	DomainValidated: {"Domain validated", "domain.validate"},

management/server/http/handler.go

@@ -16,6 +16,7 @@ import (
 
 	"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"
 	reverseproxymanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service/manager"
 
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
@@ -144,6 +145,9 @@ func NewAPIHandler(ctx context.Context, accountManager account.Manager, networks
 	if serviceManager != nil && reverseProxyDomainManager != nil {
 		reverseproxymanager.RegisterEndpoints(serviceManager, *reverseProxyDomainManager, reverseProxyAccessLogsManager, permissionsManager, router)
 	}
+
+	proxytoken.RegisterEndpoints(accountManager.GetStore(), permissionsManager, router)
+
 	// Register OAuth callback handler for proxy authentication
 	if proxyGRPCServer != nil {
 		oauthHandler := proxy.NewAuthCallbackHandler(proxyGRPCServer, trustedHTTPProxies)

management/server/http/handlers/accounts/accounts_handler.go

@@ -277,6 +277,9 @@ func (h *handler) updateAccountRequestSettings(req api.PutApiAccountsAccountIdJS
 	if req.Settings.AutoUpdateAlways != nil {
 		returnSettings.AutoUpdateAlways = *req.Settings.AutoUpdateAlways
 	}
+	if req.Settings.LocalMfaEnabled != nil {
+		returnSettings.LocalMfaEnabled = *req.Settings.LocalMfaEnabled
+	}
 	if req.Settings.Ipv6EnabledGroups != nil {
 		returnSettings.IPv6EnabledGroups = *req.Settings.Ipv6EnabledGroups
 	}
@@ -412,6 +415,7 @@ func toAccountResponse(accountID string, settings *types.Settings, meta *types.A
 		Ipv6EnabledGroups:               &settings.IPv6EnabledGroups,
 		EmbeddedIdpEnabled:              &settings.EmbeddedIdpEnabled,
 		LocalAuthDisabled:               &settings.LocalAuthDisabled,
+		LocalMfaEnabled:                 &settings.LocalMfaEnabled,
 	}
 
 	if settings.NetworkRange.IsValid() {

management/server/http/handlers/accounts/accounts_handler_test.go

@@ -131,6 +131,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr(""),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: true,
 			expectedID:    accountID,
@@ -157,6 +158,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr(""),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: false,
 			expectedID:    accountID,
@@ -183,6 +185,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr("latest"),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: false,
 			expectedID:    accountID,
@@ -209,6 +212,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr(""),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: false,
 			expectedID:    accountID,
@@ -235,6 +239,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr(""),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: false,
 			expectedID:    accountID,
@@ -261,6 +266,7 @@ func TestAccounts_AccountsHandler(t *testing.T) {
 				AutoUpdateVersion:               sr(""),
 				EmbeddedIdpEnabled:              br(false),
 				LocalAuthDisabled:               br(false),
+				LocalMfaEnabled:                 br(false),
 			},
 			expectedArray: false,
 			expectedID:    accountID,

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

@@ -216,6 +216,7 @@ func setupAuthCallbackTest(t *testing.T) *testSetup {
 		nil,
 		usersManager,
 		nil,
+		nil,
 	)
 
 	proxyService.SetServiceManager(&testServiceManager{store: testStore})
@@ -389,6 +390,10 @@ func (m *testServiceManager) DeleteService(_ context.Context, _, _, _ string) er
 	return nil
 }
 
+func (m *testServiceManager) DeleteAccountCluster(_ context.Context, _, _, _ string) error {
+	return nil
+}
+
 func (m *testServiceManager) SetCertificateIssuedAt(_ context.Context, _, _ string) error {
 	return nil
 }
@@ -435,7 +440,11 @@ func (m *testServiceManager) StopServiceFromPeer(_ context.Context, _, _, _ stri
 
 func (m *testServiceManager) StartExposeReaper(_ context.Context) {}
 
-func (m *testServiceManager) GetActiveClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
+func (m *testServiceManager) GetServiceByDomain(ctx context.Context, domain string) (*service.Service, error) {
+	return m.store.GetServiceByDomain(ctx, domain)
+}
+
+func (m *testServiceManager) GetClusters(_ context.Context, _, _ string) ([]nbproxy.Cluster, error) {
 	return nil, nil
 }
 

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

@@ -109,7 +109,7 @@ func BuildApiBlackBoxWithDBState(t testing_tools.TB, sqlFile string, expectedPee
 	if err != nil {
 		t.Fatalf("Failed to create proxy manager: %v", err)
 	}
-	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr)
+	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr, nil)
 	domainManager := manager.NewManager(store, proxyMgr, permissionsManager, am)
 	serviceProxyController, err := proxymanager.NewGRPCController(proxyServiceServer, noopMeter)
 	if err != nil {
@@ -238,7 +238,7 @@ func BuildApiBlackBoxWithDBStateAndPeerChannel(t testing_tools.TB, sqlFile strin
 	if err != nil {
 		t.Fatalf("Failed to create proxy manager: %v", err)
 	}
-	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr)
+	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr, nil)
 	domainManager := manager.NewManager(store, proxyMgr, permissionsManager, am)
 	serviceProxyController, err := proxymanager.NewGRPCController(proxyServiceServer, noopMeter)
 	if err != nil {

management/server/idp/embedded.go

@@ -2,9 +2,13 @@ package idp
 
 import (
 	"context"
+	"encoding/base64"
 	"errors"
 	"fmt"
 	"net/http"
+	"net/url"
+	"os"
+	"path"
 	"strings"
 
 	"github.com/dexidp/dex/storage"
@@ -17,12 +21,13 @@ import (
 )
 
 const (
-	staticClientDashboard  = "netbird-dashboard"
-	staticClientCLI        = "netbird-cli"
-	defaultCLIRedirectURL1 = "http://localhost:53000/"
-	defaultCLIRedirectURL2 = "http://localhost:54000/"
-	defaultScopes          = "openid profile email groups"
-	defaultUserIDClaim     = "sub"
+	staticClientDashboard         = "netbird-dashboard"
+	staticClientCLI               = "netbird-cli"
+	defaultCLIRedirectURL1        = "http://localhost:53000/"
+	defaultCLIRedirectURL2        = "http://localhost:54000/"
+	defaultScopes                 = "openid profile email groups"
+	defaultUserIDClaim            = "sub"
+	sessionCookieEncryptionKeyEnv = "NB_IDP_SESSION_COOKIE_ENCRYPTION_KEY"
 )
 
 // EmbeddedIdPConfig contains configuration for the embedded Dex OIDC identity provider
@@ -49,6 +54,26 @@ type EmbeddedIdPConfig struct {
 	// Existing local users are preserved and will be able to login again if re-enabled.
 	// Cannot be enabled if no external identity provider connectors are configured.
 	LocalAuthDisabled bool
+	// MfaSessionMaxLifetime is the maximum MFA session duration from creation (e.g. "24h").
+	// Defaults to "24h" if empty.
+	MfaSessionMaxLifetime string
+	// MfaSessionIdleTimeout is the idle timeout after which the MFA session expires (e.g. "1h").
+	// Defaults to "1h" if empty.
+	MfaSessionIdleTimeout string
+	// MfaSessionRememberMe controls the default state of the "remember me" checkbox on the
+	// login screen. When true, the session cookie persists across browser tabs/restarts so
+	// MFA is not re-prompted until the session expires. Defaults to false.
+	MfaSessionRememberMe bool
+	// SessionCookieEncryptionKey is the optional AES key used to encrypt embedded IdP session cookies.
+	// It can also be set with NB_IDP_SESSION_COOKIE_ENCRYPTION_KEY. The value must be 16, 24, or 32
+	// bytes when provided as a raw string, or base64-encoded to one of those lengths.
+	SessionCookieEncryptionKey string
+	// Dashboard Post logout redirect URIs, these are required to tell
+	// Dex what to allow when an RP-Initiated logout is started by the frontend
+	// at least one of these must match the dashboard base URL or the dashboard
+	// DASHBOARD_POST_LOGOUT_URL environment variable
+	// WARNING: Dex only uses exact match, not wildcards
+	DashboardPostLogoutRedirectURIs []string
 	// StaticConnectors are additional connectors to seed during initialization
 	StaticConnectors []dex.Connector
 }
@@ -115,10 +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
@@ -126,6 +154,15 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 	// todo: resolve import cycle
 	dashboardRedirectURIs = append(dashboardRedirectURIs, baseURL+"/api/reverse-proxy/callback")
 
+	dashboardPostLogoutRedirectURIs := c.DashboardPostLogoutRedirectURIs
+	// It is safe to assume that most installations will share the location of the
+	// 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{
@@ -148,21 +185,28 @@ func (c *EmbeddedIdPConfig) ToYAMLConfig() (*dex.YAMLConfig, error) {
 		EnablePasswordDB: true,
 		StaticClients: []storage.Client{
 			{
-				ID:           staticClientDashboard,
-				Name:         "NetBird Dashboard",
-				Public:       true,
-				RedirectURIs: dashboardRedirectURIs,
+				ID:                     staticClientDashboard,
+				Name:                   "NetBird Dashboard",
+				Public:                 true,
+				RedirectURIs:           redirectURIs,
+				PostLogoutRedirectURIs: sanitizePostLogoutRedirectURIs(dashboardPostLogoutRedirectURIs),
 			},
 			{
 				ID:           staticClientCLI,
 				Name:         "NetBird CLI",
 				Public:       true,
-				RedirectURIs: cliRedirectURIs,
+				RedirectURIs: redirectURIs,
 			},
 		},
 		StaticConnectors: c.StaticConnectors,
 	}
 
+	// Always initialize MFA providers and sessions so TOTP can be toggled at runtime.
+	// MFAChain on clients is NOT set here — it's synced from the DB setting on startup.
+	if err := configureMFA(cfg, c.MfaSessionMaxLifetime, c.MfaSessionIdleTimeout, c.MfaSessionRememberMe, c.SessionCookieEncryptionKey); err != nil {
+		return nil, err
+	}
+
 	// Add owner user if provided
 	if c.Owner != nil && c.Owner.Email != "" && c.Owner.Hash != "" {
 		username := c.Owner.Username
@@ -182,6 +226,108 @@ 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
+func sanitizePostLogoutRedirectURIs(uris []string) []string {
+	result := make([]string, 0)
+	for _, uri := range uris {
+		if strings.HasSuffix(uri, "/") {
+			result = append(result, uri)
+			result = append(result, strings.TrimSuffix(uri, "/"))
+		} else {
+			result = append(result, uri)
+			result = append(result, uri+"/")
+		}
+	}
+
+	return result
+}
+
+func configureMFA(cfg *dex.YAMLConfig, sessionMaxLifetime, sessionIdleTimeout string, rememberMe bool, sessionCookieEncryptionKey string) error {
+	cfg.MFA.Authenticators = []dex.MFAAuthenticator{{
+		ID: "default-totp",
+		// Has to be caps otherwise it will fail
+		Type: "TOTP",
+		Config: map[string]interface{}{
+			"issuer": "NetBird",
+		},
+		ConnectorTypes: []string{"local"},
+	}}
+
+	if sessionMaxLifetime == "" {
+		sessionMaxLifetime = "24h"
+	}
+	if sessionIdleTimeout == "" {
+		sessionIdleTimeout = "1h"
+	}
+
+	cookieEncryptionKey, err := resolveSessionCookieEncryptionKey(sessionCookieEncryptionKey)
+	if err != nil {
+		return err
+	}
+
+	cfg.Sessions = &dex.Sessions{
+		CookieName:                 "netbird-session",
+		AbsoluteLifetime:           sessionMaxLifetime,
+		ValidIfNotUsedFor:          sessionIdleTimeout,
+		RememberMeCheckedByDefault: &rememberMe,
+		SSOSharedWithDefault:       "all",
+		CookieEncryptionKey:        cookieEncryptionKey,
+	}
+	// Absolutely required, otherwise the dex server will omit the MFA configuration entirely
+	os.Setenv("DEX_SESSIONS_ENABLED", "true")
+
+	// Note: MFAChain on clients is NOT set here.
+	// It is toggled at runtime via SetMFAEnabled() based on the account settings DB value.
+	return nil
+}
+
+func resolveSessionCookieEncryptionKey(configuredKey string) (string, error) {
+	key := strings.TrimSpace(configuredKey)
+	if key == "" {
+		key = strings.TrimSpace(os.Getenv(sessionCookieEncryptionKeyEnv))
+	}
+	if key == "" {
+		return "", nil
+	}
+
+	if validSessionCookieEncryptionKeyLength(len([]byte(key))) {
+		return key, nil
+	}
+
+	for _, encoding := range []*base64.Encoding{
+		base64.StdEncoding,
+		base64.RawStdEncoding,
+		base64.URLEncoding,
+		base64.RawURLEncoding,
+	} {
+		decoded, err := encoding.DecodeString(key)
+		if err == nil && validSessionCookieEncryptionKeyLength(len(decoded)) {
+			return string(decoded), nil
+		}
+	}
+
+	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 {
+	switch length {
+	case 16, 24, 32:
+		return true
+	default:
+		return false
+	}
+}
+
 // Compile-time check that EmbeddedIdPManager implements Manager interface
 var _ Manager = (*EmbeddedIdPManager)(nil)
 
@@ -215,6 +361,7 @@ type EmbeddedIdPManager struct {
 	provider   *dex.Provider
 	appMetrics telemetry.AppMetrics
 	config     EmbeddedIdPConfig
+	mfaEnabled bool
 }
 
 // NewEmbeddedIdPManager creates a new instance of EmbeddedIdPManager from a configuration.
@@ -641,6 +788,27 @@ func (m *EmbeddedIdPManager) IsLocalAuthDisabled() bool {
 	return m.config.LocalAuthDisabled
 }
 
+// SetMFAEnabled enables or disables TOTP MFA for local users by updating the MFAChain on OAuth2 clients.
+func (m *EmbeddedIdPManager) SetMFAEnabled(ctx context.Context, enabled bool) error {
+	var mfaChain []string
+	if enabled {
+		mfaChain = []string{"default-totp"}
+	}
+	if err := m.provider.SetClientsMFAChain(ctx, []string{
+		staticClientCLI,
+		staticClientDashboard,
+	}, mfaChain); err != nil {
+		return fmt.Errorf("failed to set MFA enabled=%v: %w", enabled, err)
+	}
+	m.mfaEnabled = enabled
+	return nil
+}
+
+// IsMFAEnabled returns whether TOTP MFA is currently enabled for local users.
+func (m *EmbeddedIdPManager) IsMFAEnabled() bool {
+	return m.mfaEnabled
+}
+
 // HasNonLocalConnectors checks if there are any identity provider connectors other than local.
 func (m *EmbeddedIdPManager) HasNonLocalConnectors(ctx context.Context) (bool, error) {
 	return m.provider.HasNonLocalConnectors(ctx)

management/server/idp/embedded_test.go

@@ -2,6 +2,7 @@ package idp
 
 import (
 	"context"
+	"encoding/base64"
 	"os"
 	"path/filepath"
 	"testing"
@@ -313,6 +314,100 @@ 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, "")
+
+	rawKey := "0123456789abcdef0123456789abcdef"
+	config := &EmbeddedIdPConfig{
+		Enabled:                    true,
+		Issuer:                     "http://localhost:5556/dex",
+		SessionCookieEncryptionKey: base64.StdEncoding.EncodeToString([]byte(rawKey)),
+		Storage: EmbeddedStorageConfig{
+			Type: "sqlite3",
+			Config: EmbeddedStorageTypeConfig{
+				File: filepath.Join(t.TempDir(), "dex.db"),
+			},
+		},
+	}
+
+	yamlConfig, err := config.ToYAMLConfig()
+	require.NoError(t, err)
+	require.NotNil(t, yamlConfig.Sessions)
+	assert.Equal(t, rawKey, yamlConfig.Sessions.CookieEncryptionKey)
+}
+
+func TestResolveSessionCookieEncryptionKey(t *testing.T) {
+	rawKey := "0123456789abcdef0123456789abcdef"
+
+	t.Run("uses raw configured key", func(t *testing.T) {
+		t.Setenv(sessionCookieEncryptionKeyEnv, "")
+
+		key, err := resolveSessionCookieEncryptionKey(rawKey)
+		require.NoError(t, err)
+		assert.Equal(t, rawKey, key)
+	})
+
+	t.Run("uses base64 configured key", func(t *testing.T) {
+		t.Setenv(sessionCookieEncryptionKeyEnv, "")
+
+		key, err := resolveSessionCookieEncryptionKey(base64.StdEncoding.EncodeToString([]byte(rawKey)))
+		require.NoError(t, err)
+		assert.Equal(t, rawKey, key)
+	})
+
+	t.Run("falls back to env var", func(t *testing.T) {
+		t.Setenv(sessionCookieEncryptionKeyEnv, rawKey)
+
+		key, err := resolveSessionCookieEncryptionKey("")
+		require.NoError(t, err)
+		assert.Equal(t, rawKey, key)
+	})
+
+	t.Run("empty key disables encryption", func(t *testing.T) {
+		t.Setenv(sessionCookieEncryptionKeyEnv, "")
+
+		key, err := resolveSessionCookieEncryptionKey("")
+		require.NoError(t, err)
+		assert.Empty(t, key)
+	})
+
+	t.Run("rejects invalid key length", func(t *testing.T) {
+		t.Setenv(sessionCookieEncryptionKeyEnv, "")
+
+		_, err := resolveSessionCookieEncryptionKey("32")
+		require.Error(t, err)
+		assert.Contains(t, err.Error(), sessionCookieEncryptionKeyEnv)
+	})
+}
+
 func TestEmbeddedIdPManager_GetLocalKeysLocation(t *testing.T) {
 	ctx := context.Background()
 

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)
@@ -241,7 +242,14 @@ 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
 }
 
@@ -342,13 +350,21 @@ 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/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"
 )
 
@@ -63,48 +63,57 @@ 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)
 		}
@@ -122,41 +131,60 @@ func (am *DefaultAccountManager) MarkPeerConnected(ctx context.Context, peerPubK
 	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)
-			}
-		}
-	}
-
-	log.WithContext(ctx).Debugf("saving peer status for peer %s is connected: %t", peer.ID, connected)
-
-	err := transaction.SavePeerStatus(ctx, accountID, peer.ID, *newStatus)
+	peer, err := am.Store.GetPeerByPeerPubKey(ctx, store.LockingStrengthNone, peerPubKey)
 	if err != nil {
-		return false, err
+		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
 	}
 
-	return oldStatus.LoginExpired, nil
+	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)
+	return nil
+}
+
+// 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 {
+		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)
+	}
 }
 
 // UpdatePeer updates peer. Only Peer.Name, Peer.SSHEnabled, Peer.LoginExpirationEnabled and Peer.InactivityExpirationEnabled can be updated.
@@ -770,16 +798,19 @@ 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

@@ -2221,6 +2221,9 @@ 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/sql_store.go

@@ -8,6 +8,7 @@ import (
 	"fmt"
 	"net"
 	"net/netip"
+	"net/url"
 	"os"
 	"path/filepath"
 	"runtime"
@@ -236,7 +237,6 @@ func (s *SqlStore) GetPeerJobs(ctx context.Context, accountID, peerID string) ([
 		Where(accountAndPeerIDQueryCondition, accountID, peerID).
 		Order("created_at DESC").
 		Find(&jobs).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("failed to fetch jobs from store: %s", err)
 		return nil, err
@@ -464,7 +464,6 @@ func (s *SqlStore) SavePeer(ctx context.Context, accountID string, peer *nbpeer.
 
 		return nil
 	})
-
 	if err != nil {
 		return err
 	}
@@ -500,8 +499,9 @@ 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).
@@ -518,6 +518,69 @@ 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
@@ -1515,6 +1578,7 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 			settings_jwt_groups_enabled, settings_jwt_groups_claim_name, settings_jwt_allow_groups,
 			settings_routing_peer_dns_resolution_enabled, settings_dns_domain, settings_network_range,
 			settings_network_range_v6, settings_ipv6_enabled_groups, settings_lazy_connection_enabled,
+			settings_local_mfa_enabled,
 			-- Embedded ExtraSettings
 			settings_extra_peer_approval_enabled, settings_extra_user_approval_required,
 			settings_extra_integrated_validator, settings_extra_integrated_validator_groups
@@ -1536,6 +1600,7 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 		sNetworkRangeV6                  sql.NullString
 		sIPv6EnabledGroups               sql.NullString
 		sLazyConnectionEnabled           sql.NullBool
+		sLocalMFAEnabled                 sql.NullBool
 		sExtraPeerApprovalEnabled        sql.NullBool
 		sExtraUserApprovalRequired       sql.NullBool
 		sExtraIntegratedValidator        sql.NullString
@@ -1558,6 +1623,7 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 		&sJWTGroupsEnabled, &sJWTGroupsClaimName, &sJWTAllowGroups,
 		&sRoutingPeerDNSResolutionEnabled, &sDNSDomain, &sNetworkRange,
 		&sNetworkRangeV6, &sIPv6EnabledGroups, &sLazyConnectionEnabled,
+		&sLocalMFAEnabled,
 		&sExtraPeerApprovalEnabled, &sExtraUserApprovalRequired,
 		&sExtraIntegratedValidator, &sExtraIntegratedValidatorGroups,
 	)
@@ -1620,6 +1686,9 @@ func (s *SqlStore) getAccount(ctx context.Context, accountID string) (*types.Acc
 	if sLazyConnectionEnabled.Valid {
 		account.Settings.LazyConnectionEnabled = sLazyConnectionEnabled.Bool
 	}
+	if sLocalMFAEnabled.Valid {
+		account.Settings.LocalMfaEnabled = sLocalMFAEnabled.Bool
+	}
 	if sJWTAllowGroups.Valid {
 		_ = json.Unmarshal([]byte(sJWTAllowGroups.String), &account.Settings.JWTAllowGroups)
 	}
@@ -1719,9 +1788,10 @@ 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
@@ -1734,6 +1804,7 @@ 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
@@ -1748,8 +1819,9 @@ 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 {
@@ -1776,6 +1848,9 @@ 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
 			}
@@ -2791,12 +2866,27 @@ 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())
@@ -3062,7 +3152,6 @@ func (s *SqlStore) AddPeerToAllGroup(ctx context.Context, accountID string, peer
 		GroupID:   groupID,
 		PeerID:    peerID,
 	}).Error
-
 	if err != nil {
 		return status.Errorf(status.Internal, "error adding peer to group 'All': %v", err)
 	}
@@ -3082,7 +3171,6 @@ func (s *SqlStore) AddPeerToGroup(ctx context.Context, accountID, peerID, groupI
 		Columns:   []clause.Column{{Name: "group_id"}, {Name: "peer_id"}},
 		DoNothing: true,
 	}).Create(peer).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("failed to add peer %s to group %s for account %s: %v", peerID, groupID, accountID, err)
 		return status.Errorf(status.Internal, "failed to add peer to group")
@@ -3095,7 +3183,6 @@ func (s *SqlStore) AddPeerToGroup(ctx context.Context, accountID, peerID, groupI
 func (s *SqlStore) RemovePeerFromGroup(ctx context.Context, peerID string, groupID string) error {
 	err := s.db.
 		Delete(&types.GroupPeer{}, "group_id = ? AND peer_id = ?", groupID, peerID).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("failed to remove peer %s from group %s: %v", peerID, groupID, err)
 		return status.Errorf(status.Internal, "failed to remove peer from group")
@@ -3108,7 +3195,6 @@ func (s *SqlStore) RemovePeerFromGroup(ctx context.Context, peerID string, group
 func (s *SqlStore) RemovePeerFromAllGroups(ctx context.Context, peerID string) error {
 	err := s.db.
 		Delete(&types.GroupPeer{}, "peer_id = ?", peerID).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("failed to remove peer %s from all groups: %v", peerID, err)
 		return status.Errorf(status.Internal, "failed to remove peer from all groups")
@@ -3403,7 +3489,7 @@ 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()
@@ -4514,6 +4600,47 @@ func (s *SqlStore) RevokeProxyAccessToken(ctx context.Context, tokenID string) e
 	return nil
 }
 
+func (s *SqlStore) GetProxyAccessTokensByAccountID(ctx context.Context, lockStrength LockingStrength, accountID string) ([]*types.ProxyAccessToken, error) {
+	tx := s.db
+	if lockStrength != LockingStrengthNone {
+		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
+	}
+
+	var tokens []*types.ProxyAccessToken
+	result := tx.Where("account_id = ?", accountID).Find(&tokens)
+	if result.Error != nil {
+		return nil, status.Errorf(status.Internal, "get proxy access tokens by account: %v", result.Error)
+	}
+
+	return tokens, nil
+}
+
+func (s *SqlStore) IsProxyAccessTokenValid(ctx context.Context, tokenID string) (bool, error) {
+	token, err := s.GetProxyAccessTokenByID(ctx, LockingStrengthNone, tokenID)
+	if err != nil {
+		return false, err
+	}
+	return token.IsValid(), nil
+}
+
+func (s *SqlStore) GetProxyAccessTokenByID(ctx context.Context, lockStrength LockingStrength, tokenID string) (*types.ProxyAccessToken, error) {
+	tx := s.db
+	if lockStrength != LockingStrengthNone {
+		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
+	}
+
+	var token types.ProxyAccessToken
+	result := tx.Take(&token, idQueryCondition, tokenID)
+	if result.Error != nil {
+		if errors.Is(result.Error, gorm.ErrRecordNotFound) {
+			return nil, status.Errorf(status.NotFound, "proxy access token not found")
+		}
+		return nil, status.Errorf(status.Internal, "get proxy access token by ID: %v", result.Error)
+	}
+
+	return &token, nil
+}
+
 // MarkProxyAccessTokenUsed updates the last used timestamp for a proxy access token.
 func (s *SqlStore) MarkProxyAccessTokenUsed(ctx context.Context, tokenID string) error {
 	result := s.db.Model(&types.ProxyAccessToken{}).
@@ -4999,7 +5126,6 @@ func (s *SqlStore) UpdateService(ctx context.Context, service *rpservice.Service
 
 		return nil
 	})
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("failed to update service to store: %v", err)
 		return status.Errorf(status.Internal, "failed to update service to store")
@@ -5523,7 +5649,7 @@ func (s *SqlStore) DisconnectProxy(ctx context.Context, proxyID, sessionID strin
 		Model(&proxy.Proxy{}).
 		Where("id = ? AND session_id = ?", proxyID, sessionID).
 		Updates(map[string]any{
-			"status":          "disconnected",
+			"status":          proxy.StatusDisconnected,
 			"disconnected_at": now,
 			"last_seen":       now,
 		})
@@ -5554,7 +5680,7 @@ func (s *SqlStore) UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) err
 	if result.RowsAffected == 0 {
 		p.LastSeen = now
 		p.ConnectedAt = &now
-		p.Status = "connected"
+		p.Status = proxy.StatusConnected
 		if err := s.db.Create(p).Error; err != nil {
 			log.WithContext(ctx).Debugf("proxy %s session %s: heartbeat fallback insert skipped: %v", p.ID, p.SessionID, err)
 		}
@@ -5563,13 +5689,15 @@ func (s *SqlStore) UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) err
 	return nil
 }
 
-// GetActiveProxyClusterAddresses returns all unique cluster addresses for active proxies
+// GetActiveProxyClusterAddresses returns the unique cluster addresses of active
+// shared proxies (those without an account scope). BYOP cluster addresses are
+// excluded; use GetActiveProxyClusterAddressesForAccount to retrieve them.
 func (s *SqlStore) GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error) {
 	var addresses []string
 
 	result := s.db.
 		Model(&proxy.Proxy{}).
-		Where("status = ? AND last_seen > ?", "connected", time.Now().Add(-proxyActiveThreshold)).
+		Where("account_id IS NULL AND status = ? AND last_seen > ?", proxy.StatusConnected, time.Now().Add(-proxyActiveThreshold)).
 		Distinct("cluster_address").
 		Pluck("cluster_address", &addresses)
 
@@ -5581,19 +5709,129 @@ func (s *SqlStore) GetActiveProxyClusterAddresses(ctx context.Context) ([]string
 	return addresses, nil
 }
 
-// GetActiveProxyClusters returns all active proxy clusters with their connected proxy count.
-func (s *SqlStore) GetActiveProxyClusters(ctx context.Context) ([]proxy.Cluster, error) {
-	var clusters []proxy.Cluster
+func (s *SqlStore) GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error) {
+	var addresses []string
 
-	result := s.db.Model(&proxy.Proxy{}).
-		Select("cluster_address as address, COUNT(*) as connected_proxies").
-		Where("status = ? AND last_seen > ?", "connected", time.Now().Add(-proxyActiveThreshold)).
-		Group("cluster_address").
-		Scan(&clusters)
+	result := s.db.
+		Model(&proxy.Proxy{}).
+		Where("account_id = ? AND status = ? AND last_seen > ?", accountID, proxy.StatusConnected, time.Now().Add(-proxyActiveThreshold)).
+		Distinct("cluster_address").
+		Pluck("cluster_address", &addresses)
 
 	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")
+		return nil, status.Errorf(status.Internal, "failed to get active proxy cluster addresses for account")
+	}
+
+	return addresses, nil
+}
+
+func (s *SqlStore) GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error) {
+	var p proxy.Proxy
+	result := s.db.Where("account_id = ?", accountID).Take(&p)
+	if result.Error != nil {
+		if errors.Is(result.Error, gorm.ErrRecordNotFound) {
+			return nil, status.Errorf(status.NotFound, "proxy not found for account")
+		}
+		return nil, status.Errorf(status.Internal, "get proxy by account ID: %v", result.Error)
+	}
+	return &p, nil
+}
+
+func (s *SqlStore) CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error) {
+	var count int64
+	result := s.db.Model(&proxy.Proxy{}).Where("account_id = ?", accountID).Count(&count)
+	if result.Error != nil {
+		return 0, status.Errorf(status.Internal, "count proxies by account ID: %v", result.Error)
+	}
+	return count, nil
+}
+
+func (s *SqlStore) IsClusterAddressConflicting(ctx context.Context, clusterAddress, accountID string) (bool, error) {
+	var count int64
+	result := s.db.
+		Model(&proxy.Proxy{}).
+		Where("cluster_address = ? AND (account_id IS NULL OR account_id != ?)", clusterAddress, accountID).
+		Count(&count)
+	if result.Error != nil {
+		return false, status.Errorf(status.Internal, "check cluster address conflict: %v", result.Error)
+	}
+	return count > 0, nil
+}
+
+func (s *SqlStore) DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error {
+	result := s.db.
+		Where("cluster_address = ? AND account_id = ?", clusterAddress, accountID).
+		Delete(&proxy.Proxy{})
+	if result.Error != nil {
+		return status.Errorf(status.Internal, "delete account cluster: %v", result.Error)
+	}
+	if result.RowsAffected == 0 {
+		return status.Errorf(status.NotFound, "cluster not found")
+	}
+	return nil
+}
+
+// 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(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(&rows)
+
+	if result.Error != nil {
+		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
@@ -5655,7 +5893,6 @@ func (s *SqlStore) getClusterUnanimousCapability(ctx context.Context, clusterAdd
 		Where("cluster_address = ? AND status = ? AND last_seen > ?",
 			clusterAddr, "connected", time.Now().Add(-proxyActiveThreshold)).
 		Scan(&result).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("query cluster capability %s for %s: %v", column, clusterAddr, err)
 		return nil
@@ -5697,7 +5934,6 @@ func (s *SqlStore) getClusterCapability(ctx context.Context, clusterAddr, column
 		Where("cluster_address = ? AND status = ? AND last_seen > ?",
 			clusterAddr, "connected", time.Now().Add(-proxyActiveThreshold)).
 		Scan(&result).Error
-
 	if err != nil {
 		log.WithContext(ctx).Errorf("query cluster capability %s for %s: %v", column, clusterAddr, err)
 		return nil

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_test.go

@@ -4592,3 +4592,55 @@ 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

@@ -114,6 +114,9 @@ type Store interface {
 
 	GetProxyAccessTokenByHashedToken(ctx context.Context, lockStrength LockingStrength, hashedToken types.HashedProxyToken) (*types.ProxyAccessToken, error)
 	GetAllProxyAccessTokens(ctx context.Context, lockStrength LockingStrength) ([]*types.ProxyAccessToken, error)
+	GetProxyAccessTokensByAccountID(ctx context.Context, lockStrength LockingStrength, accountID string) ([]*types.ProxyAccessToken, error)
+	GetProxyAccessTokenByID(ctx context.Context, lockStrength LockingStrength, tokenID string) (*types.ProxyAccessToken, error)
+	IsProxyAccessTokenValid(ctx context.Context, tokenID string) (bool, error)
 	SaveProxyAccessToken(ctx context.Context, token *types.ProxyAccessToken) error
 	RevokeProxyAccessToken(ctx context.Context, tokenID string) error
 	MarkProxyAccessTokenUsed(ctx context.Context, tokenID string) error
@@ -166,6 +169,21 @@ 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
@@ -290,11 +308,16 @@ type Store interface {
 	DisconnectProxy(ctx context.Context, proxyID, sessionID string) error
 	UpdateProxyHeartbeat(ctx context.Context, p *proxy.Proxy) error
 	GetActiveProxyClusterAddresses(ctx context.Context) ([]string, error)
-	GetActiveProxyClusters(ctx context.Context) ([]proxy.Cluster, error)
+	GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, 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
 	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)
+	IsClusterAddressConflicting(ctx context.Context, clusterAddress, accountID string) (bool, error)
+	DeleteAccountCluster(ctx context.Context, clusterAddress, accountID string) error
 
 	GetCustomDomainsCounts(ctx context.Context) (total int64, validated int64, err error)
 
@@ -450,6 +473,9 @@ 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)
 		},
@@ -498,6 +524,9 @@ func getMigrationsPostAuto(ctx context.Context) []migrationFunc {
 		func(db *gorm.DB) error {
 			return migration.CreateIndexIfNotExists[nbpeer.Peer](ctx, db, "idx_peers_key_unique", "key")
 		},
+		func(db *gorm.DB) error {
+			return migration.DropIndex[proxy.Proxy](ctx, db, "idx_proxy_account_id_unique")
+		},
 	}
 }
 

management/server/store/store_mock.go

@@ -166,20 +166,6 @@ func (mr *MockStoreMockRecorder) CleanupStaleProxies(ctx, inactivityDuration int
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CleanupStaleProxies", reflect.TypeOf((*MockStore)(nil).CleanupStaleProxies), ctx, inactivityDuration)
 }
 
-// GetClusterSupportsCrowdSec mocks base method.
-func (m *MockStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetClusterSupportsCrowdSec", ctx, clusterAddr)
-	ret0, _ := ret[0].(*bool)
-	return ret0
-}
-
-// GetClusterSupportsCrowdSec indicates an expected call of GetClusterSupportsCrowdSec.
-func (mr *MockStoreMockRecorder) GetClusterSupportsCrowdSec(ctx, clusterAddr interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsCrowdSec", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsCrowdSec), ctx, clusterAddr)
-}
-
 // Close mocks base method.
 func (m *MockStore) Close(ctx context.Context) error {
 	m.ctrl.T.Helper()
@@ -238,6 +224,21 @@ func (mr *MockStoreMockRecorder) CountEphemeralServicesByPeer(ctx, lockStrength,
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountEphemeralServicesByPeer", reflect.TypeOf((*MockStore)(nil).CountEphemeralServicesByPeer), ctx, lockStrength, accountID, peerID)
 }
 
+// CountProxiesByAccountID mocks base method.
+func (m *MockStore) CountProxiesByAccountID(ctx context.Context, accountID string) (int64, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "CountProxiesByAccountID", ctx, accountID)
+	ret0, _ := ret[0].(int64)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// CountProxiesByAccountID indicates an expected call of CountProxiesByAccountID.
+func (mr *MockStoreMockRecorder) CountProxiesByAccountID(ctx, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CountProxiesByAccountID", reflect.TypeOf((*MockStore)(nil).CountProxiesByAccountID), ctx, accountID)
+}
+
 // CreateAccessLog mocks base method.
 func (m *MockStore) CreateAccessLog(ctx context.Context, log *accesslogs.AccessLogEntry) error {
 	m.ctrl.T.Helper()
@@ -379,6 +380,20 @@ 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()
@@ -716,6 +731,20 @@ 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()
@@ -1302,19 +1331,19 @@ func (mr *MockStoreMockRecorder) GetActiveProxyClusterAddresses(ctx interface{})
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveProxyClusterAddresses", reflect.TypeOf((*MockStore)(nil).GetActiveProxyClusterAddresses), ctx)
 }
 
-// GetActiveProxyClusters mocks base method.
-func (m *MockStore) GetActiveProxyClusters(ctx context.Context) ([]proxy.Cluster, error) {
+// GetActiveProxyClusterAddressesForAccount mocks base method.
+func (m *MockStore) GetActiveProxyClusterAddressesForAccount(ctx context.Context, accountID string) ([]string, error) {
 	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetActiveProxyClusters", ctx)
-	ret0, _ := ret[0].([]proxy.Cluster)
+	ret := m.ctrl.Call(m, "GetActiveProxyClusterAddressesForAccount", ctx, accountID)
+	ret0, _ := ret[0].([]string)
 	ret1, _ := ret[1].(error)
 	return ret0, ret1
 }
 
-// GetActiveProxyClusters indicates an expected call of GetActiveProxyClusters.
-func (mr *MockStoreMockRecorder) GetActiveProxyClusters(ctx interface{}) *gomock.Call {
+// GetActiveProxyClusterAddressesForAccount indicates an expected call of GetActiveProxyClusterAddressesForAccount.
+func (mr *MockStoreMockRecorder) GetActiveProxyClusterAddressesForAccount(ctx, accountID interface{}) *gomock.Call {
 	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveProxyClusters", reflect.TypeOf((*MockStore)(nil).GetActiveProxyClusters), ctx)
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetActiveProxyClusterAddressesForAccount", reflect.TypeOf((*MockStore)(nil).GetActiveProxyClusterAddressesForAccount), ctx, accountID)
 }
 
 // GetAllAccounts mocks base method.
@@ -1390,6 +1419,20 @@ func (mr *MockStoreMockRecorder) GetClusterRequireSubdomain(ctx, clusterAddr int
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterRequireSubdomain", reflect.TypeOf((*MockStore)(nil).GetClusterRequireSubdomain), ctx, clusterAddr)
 }
 
+// GetClusterSupportsCrowdSec mocks base method.
+func (m *MockStore) GetClusterSupportsCrowdSec(ctx context.Context, clusterAddr string) *bool {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetClusterSupportsCrowdSec", ctx, clusterAddr)
+	ret0, _ := ret[0].(*bool)
+	return ret0
+}
+
+// GetClusterSupportsCrowdSec indicates an expected call of GetClusterSupportsCrowdSec.
+func (mr *MockStoreMockRecorder) GetClusterSupportsCrowdSec(ctx, clusterAddr interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetClusterSupportsCrowdSec", reflect.TypeOf((*MockStore)(nil).GetClusterSupportsCrowdSec), ctx, clusterAddr)
+}
+
 // GetClusterSupportsCustomPorts mocks base method.
 func (m *MockStore) GetClusterSupportsCustomPorts(ctx context.Context, clusterAddr string) *bool {
 	m.ctrl.T.Helper()
@@ -1989,6 +2032,66 @@ func (mr *MockStoreMockRecorder) GetProxyAccessTokenByHashedToken(ctx, lockStren
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyAccessTokenByHashedToken", reflect.TypeOf((*MockStore)(nil).GetProxyAccessTokenByHashedToken), ctx, lockStrength, hashedToken)
 }
 
+// GetProxyAccessTokenByID mocks base method.
+func (m *MockStore) GetProxyAccessTokenByID(ctx context.Context, lockStrength LockingStrength, tokenID string) (*types2.ProxyAccessToken, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetProxyAccessTokenByID", ctx, lockStrength, tokenID)
+	ret0, _ := ret[0].(*types2.ProxyAccessToken)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetProxyAccessTokenByID indicates an expected call of GetProxyAccessTokenByID.
+func (mr *MockStoreMockRecorder) GetProxyAccessTokenByID(ctx, lockStrength, tokenID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyAccessTokenByID", reflect.TypeOf((*MockStore)(nil).GetProxyAccessTokenByID), ctx, lockStrength, tokenID)
+}
+
+// GetProxyAccessTokensByAccountID mocks base method.
+func (m *MockStore) GetProxyAccessTokensByAccountID(ctx context.Context, lockStrength LockingStrength, accountID string) ([]*types2.ProxyAccessToken, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetProxyAccessTokensByAccountID", ctx, lockStrength, accountID)
+	ret0, _ := ret[0].([]*types2.ProxyAccessToken)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetProxyAccessTokensByAccountID indicates an expected call of GetProxyAccessTokensByAccountID.
+func (mr *MockStoreMockRecorder) GetProxyAccessTokensByAccountID(ctx, lockStrength, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetProxyAccessTokensByAccountID", reflect.TypeOf((*MockStore)(nil).GetProxyAccessTokensByAccountID), ctx, lockStrength, accountID)
+}
+
+// GetProxyByAccountID mocks base method.
+func (m *MockStore) GetProxyByAccountID(ctx context.Context, accountID string) (*proxy.Proxy, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "GetProxyByAccountID", ctx, accountID)
+	ret0, _ := ret[0].(*proxy.Proxy)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// GetProxyByAccountID indicates an expected call of GetProxyByAccountID.
+func (mr *MockStoreMockRecorder) GetProxyByAccountID(ctx, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	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)
+}
+
 // GetResourceGroups mocks base method.
 func (m *MockStore) GetResourceGroups(ctx context.Context, lockStrength LockingStrength, accountID, resourceID string) ([]*types2.Group, error) {
 	m.ctrl.T.Helper()
@@ -2421,6 +2524,21 @@ func (mr *MockStoreMockRecorder) IncrementSetupKeyUsage(ctx, setupKeyID interfac
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IncrementSetupKeyUsage", reflect.TypeOf((*MockStore)(nil).IncrementSetupKeyUsage), ctx, setupKeyID)
 }
 
+// IsClusterAddressConflicting mocks base method.
+func (m *MockStore) IsClusterAddressConflicting(ctx context.Context, clusterAddress, accountID string) (bool, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "IsClusterAddressConflicting", ctx, clusterAddress, accountID)
+	ret0, _ := ret[0].(bool)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// IsClusterAddressConflicting indicates an expected call of IsClusterAddressConflicting.
+func (mr *MockStoreMockRecorder) IsClusterAddressConflicting(ctx, clusterAddress, accountID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IsClusterAddressConflicting", reflect.TypeOf((*MockStore)(nil).IsClusterAddressConflicting), ctx, clusterAddress, accountID)
+}
+
 // IsPrimaryAccount mocks base method.
 func (m *MockStore) IsPrimaryAccount(ctx context.Context, accountID string) (bool, string, error) {
 	m.ctrl.T.Helper()
@@ -2437,6 +2555,21 @@ func (mr *MockStoreMockRecorder) IsPrimaryAccount(ctx, accountID interface{}) *g
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IsPrimaryAccount", reflect.TypeOf((*MockStore)(nil).IsPrimaryAccount), ctx, accountID)
 }
 
+// IsProxyAccessTokenValid mocks base method.
+func (m *MockStore) IsProxyAccessTokenValid(ctx context.Context, tokenID string) (bool, error) {
+	m.ctrl.T.Helper()
+	ret := m.ctrl.Call(m, "IsProxyAccessTokenValid", ctx, tokenID)
+	ret0, _ := ret[0].(bool)
+	ret1, _ := ret[1].(error)
+	return ret0, ret1
+}
+
+// IsProxyAccessTokenValid indicates an expected call of IsProxyAccessTokenValid.
+func (mr *MockStoreMockRecorder) IsProxyAccessTokenValid(ctx, tokenID interface{}) *gomock.Call {
+	mr.mock.ctrl.T.Helper()
+	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "IsProxyAccessTokenValid", reflect.TypeOf((*MockStore)(nil).IsProxyAccessTokenValid), ctx, tokenID)
+}
+
 // ListCustomDomains mocks base method.
 func (m *MockStore) ListCustomDomains(ctx context.Context, accountID string) ([]*domain.Domain, error) {
 	m.ctrl.T.Helper()
@@ -2789,6 +2922,36 @@ func (mr *MockStoreMockRecorder) SavePeerStatus(ctx, accountID, peerID, status i
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "SavePeerStatus", reflect.TypeOf((*MockStore)(nil).SavePeerStatus), ctx, accountID, peerID, status)
 }
 
+// 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)
+}
+
 // SavePolicy mocks base method.
 func (m *MockStore) SavePolicy(ctx context.Context, policy *types2.Policy) error {
 	m.ctrl.T.Helper()
@@ -2831,20 +2994,6 @@ 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()

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/types/account.go

@@ -598,28 +598,21 @@ 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 +622,11 @@ 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
 }
 

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/types/settings.go

@@ -80,6 +80,10 @@ type Settings struct {
 	// LocalAuthDisabled indicates if local (email/password) authentication is disabled.
 	// This is a runtime-only field, not stored in the database.
 	LocalAuthDisabled bool `gorm:"-"`
+
+	// LocalMfaEnabled indicates if TOTP MFA is enabled for local users.
+	// Only applicable when the embedded IDP is enabled.
+	LocalMfaEnabled bool
 }
 
 // Copy copies the Settings struct
@@ -108,6 +112,7 @@ func (s *Settings) Copy() *Settings {
 		IPv6EnabledGroups:               slices.Clone(s.IPv6EnabledGroups),
 		EmbeddedIdpEnabled:              s.EmbeddedIdpEnabled,
 		LocalAuthDisabled:               s.LocalAuthDisabled,
+		LocalMfaEnabled:                 s.LocalMfaEnabled,
 	}
 	if s.Extra != nil {
 		settings.Extra = s.Extra.Copy()