Merge branch 'main' into notification-localization

client/server/debug.go

@@ -16,6 +16,7 @@ import (
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
 
+	"github.com/netbirdio/netbird/client/anonymize"
 	"github.com/netbirdio/netbird/client/internal/debug"
 	"github.com/netbirdio/netbird/client/internal/ipcauth"
 	"github.com/netbirdio/netbird/client/proto"
@@ -122,6 +123,7 @@ func (s *Server) generateDebugBundle(req *proto.DebugBundleRequest, uiOpener deb
 		},
 		debug.BundleConfig{
 			Anonymize:         req.GetAnonymize(),
+			AnonymizeLevel:    anonymize.ParseLevel(req.GetAnonymizeLevel()),
 			IncludeSystemInfo: req.GetSystemInfo(),
 			LogFileCount:      req.GetLogFileCount(),
 		},

client/server/login_outcome_test.go

@@ -0,0 +1,110 @@
+package server
+
+import (
+	"context"
+	"encoding/json"
+	"errors"
+	"os"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/client/internal"
+	"github.com/netbirdio/netbird/client/proto"
+)
+
+// A login that never reached Management is not a decision about the peer's
+// credentials, so it must come back as a retryable error rather than an SSO
+// prompt: the user cannot finish a browser login while Management is down, and
+// the CLI's own backoff resolves the outage on its own once the daemon reports
+// the failure. Reproduces `netbird down; netbird up` printing a device-code URL
+// because Management happened to be restarting when the daemon dialed it.
+func TestLogin_ManagementUnreachableIsReturnedInsteadOfDemandingSSO(t *testing.T) {
+	s, _, _, username, _ := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+
+	unreachable := errors.New("create connection: dial context: context deadline exceeded")
+	attempts := 0
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		attempts++
+		return false, unreachable
+	}
+
+	resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
+	require.Error(t, err)
+	require.ErrorIs(t, err, unreachable, "the transport failure was replaced by something else")
+	require.Nil(t, resp, "a failed login must not answer with a login response")
+	require.Equal(t, 1, attempts)
+	require.Nil(t, s.oauthAuthFlow.flow, "the daemon started an SSO flow for a peer whose login was never decided")
+
+	status, err := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, err)
+	require.Equal(t, internal.StatusLoginFailed, status,
+		"a peer that could not reach Management is not waiting on a login")
+}
+
+// The counterpart: Management refusing the peer's credentials is a decision, and
+// the SSO flow still has to start for it. The profile carries an unusable
+// private key so the flow setup fails immediately instead of dialing, which is
+// enough to show the branch was entered — the refusal itself is never what comes
+// back out.
+func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
+	s, _, _, username, cfgPath := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+	breakProfilePrivateKey(t, cfgPath)
+
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		return true, nil
+	}
+
+	_, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
+	require.Error(t, err)
+
+	status, stateErr := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, stateErr)
+	require.Equal(t, internal.StatusLoginFailed, status,
+		"the SSO flow setup was never reached with the broken key")
+}
+
+func TestLogin_SetupKeyStillRunsWhenPeerNeedsLogin(t *testing.T) {
+	s, _, _, username, _ := setupServerWithProfile(t)
+	s.rootCtx = internal.CtxInitState(context.Background())
+
+	s.isLoginRequiredFn = func(context.Context) (bool, error) {
+		return true, nil
+	}
+
+	var keysTried []string
+	s.loginAttemptFn = func(_ context.Context, setupKey, _ string) (internal.StatusType, error) {
+		keysTried = append(keysTried, setupKey)
+		return "", nil
+	}
+
+	setupKey := "A2C8E32F-AEB2-4B45-8FD3-8A0C1B2D3E4F"
+	resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username, SetupKey: setupKey})
+	require.NoError(t, err, "the probe's outcome leaked out as the login result")
+	require.NotNil(t, resp)
+	require.Equal(t, []string{setupKey}, keysTried, "the setup key never reached the login attempt")
+	require.Nil(t, s.oauthAuthFlow.flow, "a setup-key login started an SSO flow")
+
+	status, err := internal.CtxGetState(s.rootCtx).Status()
+	require.NoError(t, err)
+	require.Equal(t, internal.StatusIdle, status)
+}
+
+// breakProfilePrivateKey replaces the profile's private key with an unparseable
+// one, which makes any attempt to build a Management client fail on the spot.
+func breakProfilePrivateKey(t *testing.T, cfgPath string) {
+	t.Helper()
+
+	raw, err := os.ReadFile(cfgPath)
+	require.NoError(t, err)
+
+	var cfg map[string]any
+	require.NoError(t, json.Unmarshal(raw, &cfg))
+	cfg["PrivateKey"] = "not-a-key"
+
+	patched, err := json.Marshal(cfg)
+	require.NoError(t, err)
+	require.NoError(t, os.WriteFile(cfgPath, patched, 0o600))
+}

client/server/panic_windows.go

@@ -3,6 +3,7 @@
 package server
 
 import (
+	"errors"
 	"fmt"
 	"os"
 	"path"
@@ -69,7 +70,7 @@ func setStdHandle(f *os.File) error {
 	handle := f.Fd()
 	r0, _, e1 := setStdHandleFn.Call(stdErrorHandle, handle)
 	if r0 == 0 {
-		if e1 != nil {
+		if !errors.Is(e1, syscall.Errno(0)) {
 			return e1
 		}
 		return syscall.EINVAL

client/server/server.go

@@ -135,6 +135,13 @@ type Server struct {
 	updateManager *updater.Manager
 
 	jwtCache *jwtCache
+
+	// loginAttemptFn stands in for the Management login round trip. Tests set
+	// it to drive the login outcomes that need a server on the other end;
+	// production leaves it nil, and every login goes through loginAttempt.
+	loginAttemptFn func(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error)
+
+	isLoginRequiredFn func(ctx context.Context) (bool, error)
 }
 
 type oauthAuthFlow struct {
@@ -370,7 +377,34 @@ func (s *Server) connectionGoroutineRunning() bool {
 	}
 }
 
-// loginAttempt attempts to login using the provided information. it returns a status in case something fails
+// attemptLogin runs a login round trip against Management, or the stand-in a
+// test installed in place of it.
+func (s *Server) attemptLogin(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
+	if s.loginAttemptFn != nil {
+		return s.loginAttemptFn(ctx, setupKey, jwtToken)
+	}
+	return s.loginAttempt(ctx, setupKey, jwtToken)
+}
+
+func (s *Server) isLoginRequired(ctx context.Context) (bool, error) {
+	if s.isLoginRequiredFn != nil {
+		return s.isLoginRequiredFn(ctx)
+	}
+
+	authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
+	if err != nil {
+		log.Errorf("failed to create auth client: %v", err)
+		return false, err
+	}
+	defer authClient.Close()
+
+	return authClient.IsLoginRequired(ctx)
+}
+
+// loginAttempt attempts to login using the provided information. It returns
+// StatusNeedsLogin when Management refused the peer's credentials and
+// StatusLoginFailed for every other failure, so callers can tell an
+// authentication decision apart from a login that never got made.
 func (s *Server) loginAttempt(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
 	authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
 	if err != nil {
@@ -623,7 +657,19 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	s.config = config
 	s.mutex.Unlock()
 
-	if _, err := s.loginAttempt(ctx, "", ""); err == nil {
+	// A probe that errors leaves the login undecided: Management unreachable, a
+	// restart mid-request, an internal error. Those are returned for the caller
+	// to retry, because turning them into an SSO prompt asks the user to solve
+	// something that is not theirs to solve, and a browser login cannot succeed
+	// while Management is unreachable anyway. Only Management refusing the
+	// peer's key is a decision, and IsLoginRequired reports that as
+	// needsLogin=true rather than an error.
+	needsLogin, err := s.isLoginRequired(ctx)
+	if err != nil {
+		state.Set(internal.StatusLoginFailed)
+		return nil, err
+	}
+	if !needsLogin {
 		state.Set(internal.StatusIdle)
 		return &proto.LoginResponse{}, nil
 	}
@@ -684,7 +730,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	// which returns NeedsLogin and parks on the browser leg.
 	state.Set(internal.StatusConnecting)
 
-	if loginStatus, err := s.loginAttempt(ctx, msg.SetupKey, ""); err != nil {
+	if loginStatus, err := s.attemptLogin(ctx, msg.SetupKey, ""); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}
@@ -839,7 +885,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 	s.oauthAuthFlow.expiresAt = time.Now()
 	s.mutex.Unlock()
 
-	if loginStatus, err := s.loginAttempt(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
+	if loginStatus, err := s.attemptLogin(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}
@@ -1677,8 +1723,8 @@ func (s *Server) RequestJWTAuth(
 		hint = profilemanager.GetLoginHint()
 	}
 
-	isDesktop := isUnixRunningDesktop()
-	oAuthFlow, err := auth.NewOAuthFlow(ctx, config, isDesktop, false, hint)
+	// the daemon has no graphical session of its own, only the caller can answer this
+	oAuthFlow, err := auth.NewOAuthFlow(ctx, config, msg.GetHasGraphicalSession(), false, hint)
 	if err != nil {
 		return nil, gstatus.Errorf(codes.Internal, "failed to create OAuth flow: %v", err)
 	}
@@ -1769,6 +1815,9 @@ func (s *Server) RequestExtendAuthSession(
 	if connectClient == nil {
 		return nil, gstatus.Errorf(codes.FailedPrecondition, "client is not running")
 	}
+	if connectClient.Engine() == nil {
+		return nil, gstatus.Errorf(codes.FailedPrecondition, "session can no longer be extended, log in again to reconnect")
+	}
 
 	hint := ""
 	if msg.Hint != nil {
@@ -1778,8 +1827,8 @@ func (s *Server) RequestExtendAuthSession(
 		hint = profilemanager.GetLoginHint()
 	}
 
-	isDesktop := isUnixRunningDesktop()
-	oAuthFlow, err := auth.NewOAuthFlow(ctx, config, isDesktop, false, hint)
+	// the daemon has no graphical session of its own, only the caller can answer this
+	oAuthFlow, err := auth.NewOAuthFlow(ctx, config, msg.GetHasGraphicalSession(), false, hint)
 	if err != nil {
 		return nil, gstatus.Errorf(codes.Internal, "failed to create OAuth flow: %v", err)
 	}
@@ -1951,13 +2000,6 @@ func (s *Server) ExposeService(req *proto.ExposeServiceRequest, srv proto.Daemon
 	return nil
 }
 
-func isUnixRunningDesktop() bool {
-	if runtime.GOOS != "linux" && runtime.GOOS != "freebsd" {
-		return false
-	}
-	return os.Getenv("DESKTOP_SESSION") != "" || os.Getenv("XDG_CURRENT_DESKTOP") != ""
-}
-
 func (s *Server) runProbes(ctx context.Context, waitForProbeResult bool) {
 	if s.connectClient == nil {
 		return

client/server/server_privileged_test.go

@@ -10,7 +10,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	"github.com/stretchr/testify/require"
 	"go.opentelemetry.io/otel"