[management] Add SSO session extend flow (management) (#6197)

* add SSO session extend flow (management)

Adds the management-server half of the SSO session-extension feature:

- New ExtendAuthSession gRPC RPC that refreshes a peer's session expiry
  using a fresh JWT, validated through the same pipeline as Login but
  without tearing down the tunnel or redoing the NetworkMap sync.
- Per-peer SessionExpiresAt timestamp on every LoginResponse and
  SyncResponse so connected clients learn the deadline on the existing
  long-lived stream, and admin-side changes (toggling expiration,
  changing the expiration window) reach every peer within seconds.
- SessionExpiresAt(...) helper on Peer that derives the absolute UTC
  deadline from LastLogin + the account-level PeerLoginExpiration
  setting, returning zero when the peer is not SSO-tracked or expiration
  is disabled.

The matching client-side consumer of these fields lands separately.

* encode SessionExpiresAt as 3-state on the wire

Previously the `sessionExpiresAt` field on LoginResponse, SyncResponse
and ExtendAuthSessionResponse was 2-state: a valid timestamp meant
"new deadline", and nil meant "clear". That conflated two distinct
meanings — "no info in this snapshot" vs "expiry is explicitly off /
peer is not SSO-tracked" — so a Sync push that legitimately couldn't
compute the deadline (settings lookup failed) would silently clear the
client's anchor and lose the warning window.

Three states now, encoded on the same field number (no .proto schema
churn — only comments and the server-side encoder change):

  - nil pointer (field absent) → "no info"; client preserves anchor
  - &Timestamp{} (seconds=0, nanos=0) → explicit "disabled / not SSO"
    sentinel; client clears
  - valid timestamp → new absolute UTC deadline

A new encodeSessionExpiresAt helper centralises the zero/non-zero
encoding and is shared by the Sync, Login and ExtendAuthSession
builders. The Sync builder still emits nil when settings are missing.
Login and ExtendAuthSession always carry an authoritative value.

The matching client-side decoder lands on feature/session-extend.

* add UserExtendedPeerSession activity event

ExtendAuthSession previously reused UserLoggedInPeer for its audit
record, which conflated two distinct user actions: a full interactive
SSO login (tunnel re-established, network map resync) versus an
in-place deadline refresh (tunnel untouched). Auditors reading the log
couldn't tell which one happened, and downstream dashboards/alerts on
"login" volume were polluted by routine extends.

Adds a dedicated UserExtendedPeerSession Activity (code 125,
"user.peer.session.extend") and switches ExtendPeerSession over to it.
The peer-extend audit trail is now distinguishable from interactive
logins.

* make ExtendAuthSession JWT-retry backoff cancellable

Skip the retry log and 200ms wait on the final attempt, and replace the
uncancellable time.Sleep with a select on time.After/ctx.Done so an
upstream cancellation aborts the wait instead of running it to
completion.

shared/management/client/client.go

@@ -16,6 +16,10 @@ type Client interface {
 	Job(ctx context.Context, msgHandler func(msg *proto.JobRequest) *proto.JobResponse) error
 	Register(setupKey string, jwtToken string, sysInfo *system.Info, sshKey []byte, dnsLabels domain.List) (*proto.LoginResponse, error)
 	Login(sysInfo *system.Info, sshKey []byte, dnsLabels domain.List) (*proto.LoginResponse, error)
+	// ExtendAuthSession refreshes the peer's SSO session deadline using a fresh JWT.
+	// Returns the new absolute deadline; zero time when the server reports the peer
+	// is not eligible for session extension.
+	ExtendAuthSession(sysInfo *system.Info, jwtToken string) (*proto.ExtendAuthSessionResponse, error)
 	GetDeviceAuthorizationFlow() (*proto.DeviceAuthorizationFlow, error)
 	GetPKCEAuthorizationFlow() (*proto.PKCEAuthorizationFlow, error)
 	GetNetworkMap(sysInfo *system.Info) (*proto.NetworkMap, error)

shared/management/client/grpc.go

@@ -607,6 +607,61 @@ func (c *GrpcClient) Login(sysInfo *system.Info, pubSSHKey []byte, dnsLabels dom
 	return c.login(&proto.LoginRequest{Meta: infoToMetaData(sysInfo), PeerKeys: keys, DnsLabels: dnsLabels.ToPunycodeList()})
 }
 
+// ExtendAuthSession refreshes the peer's SSO session deadline on the management
+// server using a freshly issued JWT. The tunnel is untouched: no network map
+// sync, no peer reconnect. Returns the new absolute UTC deadline (zero time
+// when the server reports the field empty).
+func (c *GrpcClient) ExtendAuthSession(sysInfo *system.Info, jwtToken string) (*proto.ExtendAuthSessionResponse, error) {
+	if !c.ready() {
+		return nil, errors.New(errMsgNoMgmtConnection)
+	}
+
+	serverKey, err := c.getServerPublicKey()
+	if err != nil {
+		return nil, err
+	}
+
+	reqBody, err := encryption.EncryptMessage(*serverKey, c.key, &proto.ExtendAuthSessionRequest{
+		JwtToken: jwtToken,
+		Meta:     infoToMetaData(sysInfo),
+	})
+	if err != nil {
+		log.Errorf("failed to encrypt extend auth session message: %s", err)
+		return nil, err
+	}
+
+	var resp *proto.EncryptedMessage
+	operation := func() error {
+		mgmCtx, cancel := context.WithTimeout(context.Background(), ConnectTimeout)
+		defer cancel()
+
+		var err error
+		resp, err = c.realClient.ExtendAuthSession(mgmCtx, &proto.EncryptedMessage{
+			WgPubKey: c.key.PublicKey().String(),
+			Body:     reqBody,
+		})
+		if err != nil {
+			if s, ok := gstatus.FromError(err); ok && s.Code() == codes.Canceled {
+				return err
+			}
+			return backoff.Permanent(err)
+		}
+		return nil
+	}
+
+	if err := backoff.Retry(operation, nbgrpc.Backoff(c.ctx)); err != nil {
+		log.Errorf("failed to extend auth session on Management Service: %v", err)
+		return nil, err
+	}
+
+	out := &proto.ExtendAuthSessionResponse{}
+	if err := encryption.DecryptMessage(*serverKey, c.key, resp.Body, out); err != nil {
+		log.Errorf("failed to decrypt extend auth session response: %s", err)
+		return nil, err
+	}
+	return out, nil
+}
+
 // GetDeviceAuthorizationFlow returns a device authorization flow information.
 // It also takes care of encrypting and decrypting messages.
 func (c *GrpcClient) GetDeviceAuthorizationFlow() (*proto.DeviceAuthorizationFlow, error) {

shared/management/client/mock.go

@@ -14,6 +14,7 @@ type MockClient struct {
 	SyncFunc                       func(ctx context.Context, sysInfo *system.Info, msgHandler func(msg *proto.SyncResponse) error) error
 	RegisterFunc                   func(setupKey string, jwtToken string, info *system.Info, sshKey []byte, dnsLabels domain.List) (*proto.LoginResponse, error)
 	LoginFunc                      func(info *system.Info, sshKey []byte, dnsLabels domain.List) (*proto.LoginResponse, error)
+	ExtendAuthSessionFunc          func(info *system.Info, jwtToken string) (*proto.ExtendAuthSessionResponse, error)
 	GetDeviceAuthorizationFlowFunc func() (*proto.DeviceAuthorizationFlow, error)
 	GetPKCEAuthorizationFlowFunc   func() (*proto.PKCEAuthorizationFlow, error)
 	GetServerURLFunc               func() string
@@ -65,6 +66,13 @@ func (m *MockClient) Login(info *system.Info, sshKey []byte, dnsLabels domain.Li
 	return m.LoginFunc(info, sshKey, dnsLabels)
 }
 
+func (m *MockClient) ExtendAuthSession(info *system.Info, jwtToken string) (*proto.ExtendAuthSessionResponse, error) {
+	if m.ExtendAuthSessionFunc == nil {
+		return nil, nil
+	}
+	return m.ExtendAuthSessionFunc(info, jwtToken)
+}
+
 func (m *MockClient) GetDeviceAuthorizationFlow() (*proto.DeviceAuthorizationFlow, error) {
 	if m.GetDeviceAuthorizationFlowFunc == nil {
 		return nil, nil

shared/management/proto/management.proto

@@ -52,6 +52,14 @@ service ManagementService {
   // Executes a job on a target peer (e.g., debug bundle)
   rpc Job(stream EncryptedMessage) returns (stream EncryptedMessage) {}
 
+  // ExtendAuthSession refreshes the peer's session expiry deadline using a fresh JWT.
+  // Same JWT validation pipeline as Login (including jwt.UserID == peer.UserID check),
+  // but does not redo the network-map sync. Only valid for SSO-registered peers where
+  // login expiration is enabled. The tunnel remains up.
+  // EncryptedMessage of the request has a body of ExtendAuthSessionRequest.
+  // EncryptedMessage of the response has a body of ExtendAuthSessionResponse.
+  rpc ExtendAuthSession(EncryptedMessage) returns (EncryptedMessage) {}
+
   // CreateExpose creates a temporary reverse proxy service for a peer
   rpc CreateExpose(EncryptedMessage) returns (EncryptedMessage) {}
 
@@ -133,6 +141,15 @@ message SyncResponse {
 
   // Posture checks to be evaluated by client
   repeated Checks Checks = 6;
+
+  // 3-state session deadline. Carried on every Sync snapshot so admin-side
+  // changes propagate live without a client reconnect.
+  //   field unset (nil)        → snapshot carries no info; client keeps the
+  //                              deadline it already had
+  //   set, seconds=0 nanos=0   → explicit "expiry disabled" or peer is not
+  //                              SSO-registered; client clears its anchor
+  //   set, valid timestamp     → new absolute UTC deadline
+  google.protobuf.Timestamp sessionExpiresAt = 7;
 }
 
 message  SyncMetaRequest {
@@ -244,6 +261,31 @@ message LoginResponse {
   PeerConfig peerConfig = 2;
   // Posture checks to be evaluated by client
   repeated Checks Checks = 3;
+
+  // 3-state session deadline; same encoding as SyncResponse.sessionExpiresAt.
+  //   field unset (nil)        → no info; client keeps any deadline it had
+  //   set, seconds=0 nanos=0   → explicit "expiry disabled" / non-SSO peer
+  //   set, valid timestamp     → new absolute UTC deadline
+  google.protobuf.Timestamp sessionExpiresAt = 4;
+}
+
+// ExtendAuthSessionRequest carries a fresh JWT to refresh the peer's session deadline.
+// The encrypted body of an EncryptedMessage with this payload is sent to the
+// ExtendAuthSession RPC.
+message ExtendAuthSessionRequest {
+  // SSO token (must be a fresh, valid JWT for the peer's owning user)
+  string jwtToken = 1;
+  // Meta data of the peer (used for IdP user info refresh consistent with Login)
+  PeerSystemMeta meta = 2;
+}
+
+// ExtendAuthSessionResponse contains the refreshed session deadline.
+message ExtendAuthSessionResponse {
+  // 3-state session deadline; same encoding as SyncResponse.sessionExpiresAt.
+  // In practice ExtendAuthSession only succeeds for SSO peers with expiry
+  // enabled, so this carries a valid timestamp on the success path. The
+  // 3-state encoding is documented here for symmetry with Login/Sync.
+  google.protobuf.Timestamp sessionExpiresAt = 1;
 }
 
 message ServerKeyResponse {

shared/management/proto/management_grpc.pb.go

@@ -52,6 +52,13 @@ type ManagementServiceClient interface {
 	Logout(ctx context.Context, in *EncryptedMessage, opts ...grpc.CallOption) (*Empty, error)
 	// Executes a job on a target peer (e.g., debug bundle)
 	Job(ctx context.Context, opts ...grpc.CallOption) (ManagementService_JobClient, error)
+	// ExtendAuthSession refreshes the peer's session expiry deadline using a fresh JWT.
+	// Same JWT validation pipeline as Login (including jwt.UserID == peer.UserID check),
+	// but does not redo the network-map sync. Only valid for SSO-registered peers where
+	// login expiration is enabled. The tunnel remains up.
+	// EncryptedMessage of the request has a body of ExtendAuthSessionRequest.
+	// EncryptedMessage of the response has a body of ExtendAuthSessionResponse.
+	ExtendAuthSession(ctx context.Context, in *EncryptedMessage, opts ...grpc.CallOption) (*EncryptedMessage, error)
 	// CreateExpose creates a temporary reverse proxy service for a peer
 	CreateExpose(ctx context.Context, in *EncryptedMessage, opts ...grpc.CallOption) (*EncryptedMessage, error)
 	// RenewExpose extends the TTL of an active expose session
@@ -194,6 +201,15 @@ func (x *managementServiceJobClient) Recv() (*EncryptedMessage, error) {
 	return m, nil
 }
 
+func (c *managementServiceClient) ExtendAuthSession(ctx context.Context, in *EncryptedMessage, opts ...grpc.CallOption) (*EncryptedMessage, error) {
+	out := new(EncryptedMessage)
+	err := c.cc.Invoke(ctx, "/management.ManagementService/ExtendAuthSession", in, out, opts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
 func (c *managementServiceClient) CreateExpose(ctx context.Context, in *EncryptedMessage, opts ...grpc.CallOption) (*EncryptedMessage, error) {
 	out := new(EncryptedMessage)
 	err := c.cc.Invoke(ctx, "/management.ManagementService/CreateExpose", in, out, opts...)
@@ -259,6 +275,13 @@ type ManagementServiceServer interface {
 	Logout(context.Context, *EncryptedMessage) (*Empty, error)
 	// Executes a job on a target peer (e.g., debug bundle)
 	Job(ManagementService_JobServer) error
+	// ExtendAuthSession refreshes the peer's session expiry deadline using a fresh JWT.
+	// Same JWT validation pipeline as Login (including jwt.UserID == peer.UserID check),
+	// but does not redo the network-map sync. Only valid for SSO-registered peers where
+	// login expiration is enabled. The tunnel remains up.
+	// EncryptedMessage of the request has a body of ExtendAuthSessionRequest.
+	// EncryptedMessage of the response has a body of ExtendAuthSessionResponse.
+	ExtendAuthSession(context.Context, *EncryptedMessage) (*EncryptedMessage, error)
 	// CreateExpose creates a temporary reverse proxy service for a peer
 	CreateExpose(context.Context, *EncryptedMessage) (*EncryptedMessage, error)
 	// RenewExpose extends the TTL of an active expose session
@@ -299,6 +322,9 @@ func (UnimplementedManagementServiceServer) Logout(context.Context, *EncryptedMe
 func (UnimplementedManagementServiceServer) Job(ManagementService_JobServer) error {
 	return status.Errorf(codes.Unimplemented, "method Job not implemented")
 }
+func (UnimplementedManagementServiceServer) ExtendAuthSession(context.Context, *EncryptedMessage) (*EncryptedMessage, error) {
+	return nil, status.Errorf(codes.Unimplemented, "method ExtendAuthSession not implemented")
+}
 func (UnimplementedManagementServiceServer) CreateExpose(context.Context, *EncryptedMessage) (*EncryptedMessage, error) {
 	return nil, status.Errorf(codes.Unimplemented, "method CreateExpose not implemented")
 }
@@ -494,6 +520,24 @@ func (x *managementServiceJobServer) Recv() (*EncryptedMessage, error) {
 	return m, nil
 }
 
+func _ManagementService_ExtendAuthSession_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(EncryptedMessage)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(ManagementServiceServer).ExtendAuthSession(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: "/management.ManagementService/ExtendAuthSession",
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(ManagementServiceServer).ExtendAuthSession(ctx, req.(*EncryptedMessage))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
 func _ManagementService_CreateExpose_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
 	in := new(EncryptedMessage)
 	if err := dec(in); err != nil {
@@ -583,6 +627,10 @@ var ManagementService_ServiceDesc = grpc.ServiceDesc{
 			MethodName: "Logout",
 			Handler:    _ManagementService_Logout_Handler,
 		},
+		{
+			MethodName: "ExtendAuthSession",
+			Handler:    _ManagementService_ExtendAuthSession_Handler,
+		},
 		{
 			MethodName: "CreateExpose",
 			Handler:    _ManagementService_CreateExpose_Handler,