Merge remote-tracking branch 'origin/main' into revert/component-types

Signed-off-by: Dmitri Dolguikh <dmitri.external@netbird.io>

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

@@ -0,0 +1,25 @@
+// Package activity records that a principal used a reverse proxy service, so
+// that activity accounting counts people and devices which reach services
+// through the proxy but never touch the dashboard or the management API.
+package activity
+
+import (
+	"context"
+
+	"github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+// Manager records reverse proxy usage against the timestamps activity
+// accounting reads. Both methods are best effort from the caller's point of
+// view: a lost record is corrected by the next request, and no authorization
+// decision reads them back.
+type Manager interface {
+	// RecordUserLogin records a completed SSO sign-in to a proxied service.
+	// Service users have no interactive login and are ignored.
+	RecordUserLogin(ctx context.Context, accountID string, user *types.User) error
+	// RecordPeerSeen records that a peer reached a private service over the
+	// mesh, which is what lets its owner count as active. Peers activity
+	// accounting excludes, and peers already seen recently, are ignored.
+	RecordPeerSeen(ctx context.Context, accountID string, peer *peer.Peer) error
+}

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

@@ -0,0 +1,66 @@
+package manager
+
+import (
+	"context"
+	"time"
+
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/activity"
+	"github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+// peerSeenInterval is how stale a peer's LastSeen must be before reaching a
+// private service refreshes it. Positive tunnel validations are cached on the
+// proxy for five minutes, so without a floor a busy peer would rewrite its row
+// behind every request; an hour still sits well inside the window activity
+// accounting asks about.
+const peerSeenInterval = time.Hour
+
+type managerImpl struct {
+	store store.Store
+}
+
+// NewManager returns the activity manager backed by the management store.
+func NewManager(store store.Store) activity.Manager {
+	return &managerImpl{store: store}
+}
+
+// RecordUserLogin stamps the login the same way the dashboard and device login
+// paths do, so a person who only ever reaches proxied services still has a
+// login on record.
+func (m *managerImpl) RecordUserLogin(ctx context.Context, accountID string, user *types.User) error {
+	if user == nil || user.IsServiceUser {
+		return nil
+	}
+
+	return m.store.SaveUserLastLogin(ctx, accountID, user.Id, time.Now().UTC())
+}
+
+// RecordPeerSeen stamps LastSeen, the column a peer activates its owner
+// through. The peer the caller already holds answers the throttle without a
+// query, so a peer seen inside the interval costs nothing to skip; the same
+// cutoff goes to the store, which enforces it inside the UPDATE so concurrent
+// requests for one peer cannot each write off their own stale read.
+func (m *managerImpl) RecordPeerSeen(ctx context.Context, accountID string, peer *peer.Peer) error {
+	if peer == nil || !countsTowardActivity(peer) {
+		return nil
+	}
+
+	staleBefore := time.Now().UTC().Add(-peerSeenInterval)
+	if peer.Status != nil && peer.Status.LastSeen.After(staleBefore) {
+		return nil
+	}
+
+	_, err := m.store.RefreshPeerLastSeen(ctx, accountID, peer.ID, staleBefore)
+
+	return err
+}
+
+// countsTowardActivity reports whether the peer represents a device a person
+// actually runs. Embedded proxy peers are infrastructure and browser (WASM)
+// clients are ephemeral sessions, so activity accounting ignores both and a
+// write for them could never count.
+func countsTowardActivity(peer *peer.Peer) bool {
+	return !peer.ProxyMeta.Embedded && peer.Meta.KernelVersion != "wasm"
+}

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

@@ -0,0 +1,149 @@
+package manager
+
+import (
+	"context"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/management/server/peer"
+	"github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/types"
+)
+
+// recordingStore captures the two writes the activity manager makes. The
+// embedded interface satisfies the rest and panics if anything else is called,
+// which keeps the manager honest about its surface.
+type recordingStore struct {
+	store.Store
+	logins []loginWrite
+	seen   []seenWrite
+}
+
+type loginWrite struct {
+	accountID string
+	userID    string
+	at        time.Time
+}
+
+type seenWrite struct {
+	accountID   string
+	peerID      string
+	staleBefore time.Time
+}
+
+func (s *recordingStore) SaveUserLastLogin(_ context.Context, accountID, userID string, lastLogin time.Time) error {
+	s.logins = append(s.logins, loginWrite{accountID: accountID, userID: userID, at: lastLogin})
+	return nil
+}
+
+func (s *recordingStore) RefreshPeerLastSeen(_ context.Context, accountID, peerID string, staleBefore time.Time) (bool, error) {
+	s.seen = append(s.seen, seenWrite{accountID: accountID, peerID: peerID, staleBefore: staleBefore})
+	return true, nil
+}
+
+func TestRecordUserLogin(t *testing.T) {
+	tests := []struct {
+		name        string
+		user        *types.User
+		expectWrite bool
+	}{
+		{
+			name:        "regular user is recorded",
+			user:        &types.User{Id: "user1", AccountID: "account1"},
+			expectWrite: true,
+		},
+		{
+			// Activity accounting never counts service users, so a row for one
+			// would be noise.
+			name:        "service user is ignored",
+			user:        &types.User{Id: "svc1", AccountID: "account1", IsServiceUser: true},
+			expectWrite: false,
+		},
+		{
+			name:        "missing user is ignored",
+			user:        nil,
+			expectWrite: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			st := &recordingStore{}
+			require.NoError(t, NewManager(st).RecordUserLogin(context.Background(), "account1", tt.user))
+
+			if !tt.expectWrite {
+				assert.Empty(t, st.logins, "no login should have been recorded")
+				return
+			}
+
+			require.Len(t, st.logins, 1, "exactly one login should have been recorded")
+			assert.Equal(t, "account1", st.logins[0].accountID, "login must be recorded against the service account")
+			assert.Equal(t, tt.user.Id, st.logins[0].userID, "login must be recorded against the signing-in user")
+			assert.Equal(t, time.UTC, st.logins[0].at.Location(), "timestamps are written in UTC")
+			assert.WithinDuration(t, time.Now().UTC(), st.logins[0].at, time.Minute, "login should be stamped now")
+		})
+	}
+}
+
+func TestRecordPeerSeen(t *testing.T) {
+	tests := []struct {
+		name        string
+		peer        *peer.Peer
+		expectWrite bool
+	}{
+		{
+			name:        "peer seen long ago is recorded",
+			peer:        &peer.Peer{ID: "peer1", Status: &peer.PeerStatus{LastSeen: time.Now().Add(-3 * time.Hour)}},
+			expectWrite: true,
+		},
+		{
+			name:        "peer never seen is recorded",
+			peer:        &peer.Peer{ID: "peer1", Status: &peer.PeerStatus{}},
+			expectWrite: true,
+		},
+		{
+			// The throttle. The caller already holds the peer, so skipping a
+			// recently seen one costs nothing.
+			name:        "peer seen inside the interval is skipped",
+			peer:        &peer.Peer{ID: "peer1", Status: &peer.PeerStatus{LastSeen: time.Now().Add(-10 * time.Minute)}},
+			expectWrite: false,
+		},
+		{
+			name:        "embedded proxy peer is skipped",
+			peer:        &peer.Peer{ID: "peer1", ProxyMeta: peer.ProxyMeta{Embedded: true}, Status: &peer.PeerStatus{LastSeen: time.Now().Add(-3 * time.Hour)}},
+			expectWrite: false,
+		},
+		{
+			name:        "browser client is skipped",
+			peer:        &peer.Peer{ID: "peer1", Meta: peer.PeerSystemMeta{KernelVersion: "wasm"}, Status: &peer.PeerStatus{LastSeen: time.Now().Add(-3 * time.Hour)}},
+			expectWrite: false,
+		},
+		{
+			name:        "missing peer is ignored",
+			peer:        nil,
+			expectWrite: false,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			st := &recordingStore{}
+			require.NoError(t, NewManager(st).RecordPeerSeen(context.Background(), "account1", tt.peer))
+
+			if !tt.expectWrite {
+				assert.Empty(t, st.seen, "no activity should have been recorded")
+				return
+			}
+
+			require.Len(t, st.seen, 1, "exactly one activity write should have been recorded")
+			assert.Equal(t, "account1", st.seen[0].accountID, "activity must be recorded against the service account")
+			assert.Equal(t, tt.peer.ID, st.seen[0].peerID, "activity must be recorded against the calling peer")
+			assert.Equal(t, time.UTC, st.seen[0].staleBefore.Location(), "cutoffs are passed in UTC")
+			assert.WithinDuration(t, time.Now().UTC().Add(-peerSeenInterval), st.seen[0].staleBefore, time.Minute,
+				"the store must enforce the same interval the local check applies")
+		})
+	}
+}

management/internals/server/boot.go

@@ -28,6 +28,8 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
 	accesslogsmanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs/manager"
+	proxyactivity "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/activity"
+	proxyactivitymanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/activity/manager"
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	networkmapdb "github.com/netbirdio/netbird/management/internals/network_map_db"
 	networkmapdbfactory "github.com/netbirdio/netbird/management/internals/network_map_db/factory"
@@ -254,6 +256,7 @@ func (s *BaseServer) ReverseProxyGRPCServer() *nbgrpc.ProxyServiceServer {
 		proxyService := nbgrpc.NewProxyServiceServer(s.AccessLogsManager(), s.ProxyTokenStore(), s.PKCEVerifierStore(), s.proxyOIDCConfig(), s.PeersManager(), s.UsersManager(), s.IdpManager(), s.ProxyManager(), s.Store())
 		s.AfterInit(func(s *BaseServer) {
 			proxyService.SetServiceManager(s.ServiceManager())
+			proxyService.SetActivityManager(s.ProxyActivityManager())
 			proxyService.SetProxyController(s.ServiceProxyController())
 			proxyService.SetAgentNetworkSynthesizer(newAgentNetworkSynthesizer(s.Store()))
 			proxyService.SetAgentNetworkLimitsService(s.AgentNetworkManager())
@@ -313,6 +316,13 @@ func (s *BaseServer) PKCEVerifierStore() *nbgrpc.PKCEVerifierStore {
 	})
 }
 
+// ProxyActivityManager records reverse proxy usage for activity accounting.
+func (s *BaseServer) ProxyActivityManager() proxyactivity.Manager {
+	return Create(s, func() proxyactivity.Manager {
+		return proxyactivitymanager.NewManager(s.Store())
+	})
+}
+
 func (s *BaseServer) AccessLogsManager() accesslogs.Manager {
 	return Create(s, func() accesslogs.Manager {
 		accessLogManager := accesslogsmanager.NewManager(s.Store(), s.PermissionsManager(), s.GeoLocationManager())

management/internals/shared/grpc/proxy.go

@@ -32,6 +32,7 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/activity"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/sessionkey"
@@ -128,6 +129,9 @@ type ProxyServiceServer struct {
 	// Manager for IdP-enriched user data (may be nil when no IdP is configured)
 	idpManager idp.Manager
 
+	// Manager that records reverse proxy usage for activity accounting
+	activityManager activity.Manager
+
 	// Store for one-time authentication tokens
 	tokenStore *OneTimeTokenStore
 
@@ -250,6 +254,13 @@ func (s *ProxyServiceServer) SetServiceManager(manager rpservice.Manager) {
 	s.serviceManager = manager
 }
 
+// SetActivityManager wires the manager that records reverse proxy usage.
+func (s *ProxyServiceServer) SetActivityManager(manager activity.Manager) {
+	s.mu.Lock()
+	defer s.mu.Unlock()
+	s.activityManager = manager
+}
+
 // SetAgentNetworkSynthesizer wires the agent-network service synthesiser.
 // Optional — when nil the snapshot path skips agent-network synthesis. The
 // modules layer injects this after both the proxy server and the agent-network
@@ -1717,7 +1728,7 @@ func (s *ProxyServiceServer) GenerateSessionToken(ctx context.Context, domain, u
 
 	groupIDs, groupNames := pairGroupIDsAndNames(userGroups)
 
-	return sessionkey.SignToken(
+	token, err := sessionkey.SignToken(
 		service.SessionPrivateKey,
 		userID,
 		user.Email,
@@ -1727,6 +1738,25 @@ func (s *ProxyServiceServer) GenerateSessionToken(ctx context.Context, domain, u
 		groupNames,
 		proxyauth.DefaultSessionExpiry,
 	)
+	if err != nil {
+		return "", err
+	}
+
+	s.recordUserLogin(ctx, service.AccountID, user)
+
+	return token, nil
+}
+
+// recordUserLogin hands the sign-in to the activity manager. The RPC must not
+// fail on it, so the error is logged and dropped here rather than returned.
+func (s *ProxyServiceServer) recordUserLogin(ctx context.Context, accountID string, user *types.User) {
+	if s.activityManager == nil {
+		return
+	}
+
+	if err := s.activityManager.RecordUserLogin(ctx, accountID, user); err != nil {
+		log.WithContext(ctx).Debugf("record proxy login for user %s: %v", user.Id, err)
+	}
 }
 
 // ValidateUserGroupAccess checks if a user has access to a service.
@@ -2076,6 +2106,8 @@ func (s *ProxyServiceServer) ValidateTunnelPeer(ctx context.Context, req *proto.
 		return nil, err
 	}
 
+	s.recordPeerSeen(ctx, service.AccountID, peer)
+
 	log.WithFields(log.Fields{
 		"domain":       domain,
 		"tunnel_ip":    tunnelIPStr,
@@ -2093,6 +2125,18 @@ func (s *ProxyServiceServer) ValidateTunnelPeer(ctx context.Context, req *proto.
 	}, nil
 }
 
+// recordPeerSeen hands the mesh request to the activity manager. The RPC must
+// not fail on it, so the error is logged and dropped here rather than returned.
+func (s *ProxyServiceServer) recordPeerSeen(ctx context.Context, accountID string, peer *peer.Peer) {
+	if s.activityManager == nil {
+		return
+	}
+
+	if err := s.activityManager.RecordPeerSeen(ctx, accountID, peer); err != nil {
+		log.WithContext(ctx).Debugf("record proxy activity for peer %s: %v", peer.ID, err)
+	}
+}
+
 // resolvePeerOwner returns the user a peer is linked to, once per request so
 // the status gate and the identity resolution below share a single lookup.
 // Unlinked peers (machine agents) have no owner. A lookup that fails returns

management/internals/shared/grpc/proxy_group_access_test.go

@@ -5,6 +5,7 @@ import (
 	"errors"
 	"net"
 	"testing"
+	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -155,6 +156,27 @@ type mockTunnelPeersManager struct {
 	groupsErr error
 }
 
+// mockActivityManager records what the RPC handed to the activity manager. The
+// policy (throttling, exclusions) is the manager's and is tested there; these
+// tests only pin which requests reach it.
+type mockActivityManager struct {
+	seenMarks []seenMark
+}
+
+type seenMark struct {
+	accountID string
+	peerID    string
+}
+
+func (m *mockActivityManager) RecordUserLogin(_ context.Context, _ string, _ *types.User) error {
+	return nil
+}
+
+func (m *mockActivityManager) RecordPeerSeen(_ context.Context, accountID string, peer *peer.Peer) error {
+	m.seenMarks = append(m.seenMarks, seenMark{accountID: accountID, peerID: peer.ID})
+	return nil
+}
+
 func (m *mockTunnelPeersManager) GetPeerByTunnelIP(_ context.Context, _ string, _ net.IP) (*peer.Peer, error) {
 	return m.peer, m.peerErr
 }
@@ -745,6 +767,78 @@ func TestValidateTunnelPeerOwnerStatus(t *testing.T) {
 	}
 }
 
+// TestValidateTunnelPeerRecordsActivity pins that a granted mesh request is
+// handed to the activity manager. Which of those the manager then writes is its
+// own decision, covered by its tests.
+func TestValidateTunnelPeerRecordsActivity(t *testing.T) {
+	const (
+		domain    = "app.example.com"
+		accountID = "account1"
+		peerID    = "peer1"
+	)
+
+	activityManager := &mockActivityManager{}
+	server := &ProxyServiceServer{
+		activityManager: activityManager,
+		serviceManager: &mockReverseProxyManager{
+			proxiesByAccount: map[string][]*service.Service{
+				accountID: {{Domain: domain, AccountID: accountID}},
+			},
+		},
+		peersManager: &mockTunnelPeersManager{
+			peer: &peer.Peer{ID: peerID, Name: "agent", Status: &peer.PeerStatus{LastSeen: time.Now().Add(-3 * time.Hour)}},
+		},
+		usersManager: &mockUsersManager{users: map[string]*types.User{}},
+	}
+
+	resp, err := server.ValidateTunnelPeer(context.Background(), &proto.ValidateTunnelPeerRequest{
+		Domain:   domain,
+		TunnelIp: "100.64.0.1",
+	})
+
+	require.NoError(t, err)
+	require.True(t, resp.GetValid(), "peer should be granted access")
+
+	require.Len(t, activityManager.seenMarks, 1, "a granted peer should reach the activity manager once")
+	assert.Equal(t, accountID, activityManager.seenMarks[0].accountID, "activity must be attributed to the service account")
+	assert.Equal(t, peerID, activityManager.seenMarks[0].peerID, "activity must be attributed to the calling peer")
+}
+
+// TestValidateTunnelPeerDeniedRecordsNoActivity keeps the write on the granted
+// path only: a refused peer is not evidence its owner was active.
+func TestValidateTunnelPeerDeniedRecordsNoActivity(t *testing.T) {
+	const (
+		domain    = "app.example.com"
+		accountID = "account1"
+	)
+
+	activityManager := &mockActivityManager{}
+	server := &ProxyServiceServer{
+		activityManager: activityManager,
+		serviceManager: &mockReverseProxyManager{
+			proxiesByAccount: map[string][]*service.Service{
+				accountID: {{Domain: domain, AccountID: accountID}},
+			},
+		},
+		peersManager: &mockTunnelPeersManager{
+			peer: &peer.Peer{ID: "peer1", Name: "agent", UserID: "user1", Status: &peer.PeerStatus{LastSeen: time.Now().Add(-3 * time.Hour)}},
+		},
+		// The owner is blocked, so the tunnel gate denies before the mint.
+		usersManager: &mockUsersManager{users: map[string]*types.User{
+			"user1": {Id: "user1", AccountID: accountID, Blocked: true},
+		}},
+	}
+
+	resp, err := server.ValidateTunnelPeer(context.Background(), &proto.ValidateTunnelPeerRequest{
+		Domain:   domain,
+		TunnelIp: "100.64.0.1",
+	})
+
+	require.NoError(t, err)
+	require.False(t, resp.GetValid(), "blocked owner should be denied")
+	assert.Empty(t, activityManager.seenMarks, "a denied peer must not be marked seen")
+}
+
 func TestGetAccountProxyByDomain(t *testing.T) {
 	tests := []struct {
 		name             string