use API

(We now do AsyncStart + waitEstablishedOrDone, so everything is managed inside the
supervisor)

client/android/client.go

@@ -151,9 +151,9 @@ func (c *Client) Run(platformFiles PlatformFiles, urlOpener URLOpener, isAndroid
 
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, c.recorder)
 	c.setState(cfg, cacheDir, connectClient)
-	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
+	return connectClient.RunOnAndroid(cfg, c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
 // RunWithoutLogin we apply this type of run function when the backed has been started without UI (i.e. after reboot).
@@ -186,9 +186,9 @@ func (c *Client) RunWithoutLogin(platformFiles PlatformFiles, dns *DNSList, dnsR
 
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, c.recorder)
 	c.setState(cfg, cacheDir, connectClient)
-	return connectClient.RunOnAndroid(c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
+	return connectClient.RunOnAndroid(cfg, c.tunAdapter, c.iFaceDiscover, c.networkChangeListener, slices.Clone(dns.items), dnsReadyListener, stateFile, cacheDir)
 }
 
 // Stop the internal client and free the resources

client/android/profile_manager.go

@@ -6,7 +6,6 @@ import (
 	"fmt"
 	"os"
 	"path/filepath"
-	"strings"
 
 	log "github.com/sirupsen/logrus"
 
@@ -24,6 +23,7 @@ const (
 
 // Profile represents a profile for gomobile
 type Profile struct {
+	ID       string
 	Name     string
 	IsActive bool
 }
@@ -53,10 +53,10 @@ func (p *ProfileArray) Get(i int) *Profile {
 ├── state.json                                  ← Default profile state
 ├── active_profile.json                         ← Active profile tracker (JSON with Name + Username)
 └── profiles/                                   ← Subdirectory for non-default profiles
-    ├── work.json                              ← Work profile config
-    ├── work.state.json                        ← Work profile state
-    ├── personal.json                          ← Personal profile config
-    └── personal.state.json                    ← Personal profile state
+    ├── work.json                              			← Legacy work profile config
+    ├── work.state.json                        			← Legacy work profile state
+    ├── 4c5f5c8198c3989cffb5b5394f5a7ae0.json  			← ID profile config
+    ├── 4c5f5c8198c3989cffb5b5394f5a7ae0.state.json ← ID profile state
 */
 
 // ProfileManager manages profiles for Android
@@ -99,6 +99,7 @@ func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
 	var profiles []*Profile
 	for _, p := range internalProfiles {
 		profiles = append(profiles, &Profile{
+			ID:       p.ID.String(),
 			Name:     p.Name,
 			IsActive: p.IsActive,
 		})
@@ -108,55 +109,65 @@ func (pm *ProfileManager) ListProfiles() (*ProfileArray, error) {
 }
 
 // GetActiveProfile returns the currently active profile name
-func (pm *ProfileManager) GetActiveProfile() (string, error) {
+func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
 	// Use ServiceManager to stay consistent with ListProfiles
 	// ServiceManager uses active_profile.json
 	activeState, err := pm.serviceMgr.GetActiveProfileState()
 	if err != nil {
-		return "", fmt.Errorf("failed to get active profile: %w", err)
+		return nil, fmt.Errorf("failed to get active profile: %w", err)
 	}
-	return activeState.Name, nil
+
+	// ActiveProfileState only stores the ID (and username), not the display
+	// name. Resolve the ID to the full profile so callers get the real Name.
+	prof, err := pm.serviceMgr.ResolveProfile(activeState.ID.String(), androidUsername)
+	if err != nil {
+		return nil, fmt.Errorf("failed to resolve active profile %q: %w", activeState.ID, err)
+	}
+	return &Profile{ID: prof.ID.String(), Name: prof.Name, IsActive: true}, nil
 }
 
 // SwitchProfile switches to a different profile
-func (pm *ProfileManager) SwitchProfile(profileName string) error {
+func (pm *ProfileManager) SwitchProfile(id string) error {
 	// Use ServiceManager to stay consistent with ListProfiles
 	// ServiceManager uses active_profile.json
 	err := pm.serviceMgr.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     profileName,
+		ID:       profilemanager.ID(id),
 		Username: androidUsername,
 	})
 	if err != nil {
 		return fmt.Errorf("failed to switch profile: %w", err)
 	}
 
-	log.Infof("switched to profile: %s", profileName)
+	log.Infof("switched to profile: %s", id)
 	return nil
 }
 
 // AddProfile creates a new profile
 func (pm *ProfileManager) AddProfile(profileName string) error {
 	// Use ServiceManager (creates profile in profiles/ directory)
-	if err := pm.serviceMgr.AddProfile(profileName, androidUsername); err != nil {
+	profile, err := pm.serviceMgr.AddProfile(profileName, androidUsername)
+	if err != nil {
 		return fmt.Errorf("failed to add profile: %w", err)
 	}
 
-	log.Infof("created new profile: %s", profileName)
+	log.Infof("created new profile: %s", profile.ID)
 	return nil
 }
 
 // LogoutProfile logs out from a profile (clears authentication)
-func (pm *ProfileManager) LogoutProfile(profileName string) error {
-	profileName = sanitizeProfileName(profileName)
-
-	configPath, err := pm.getProfileConfigPath(profileName)
+func (pm *ProfileManager) LogoutProfile(id string) error {
+	configPath, err := pm.getProfileConfigPath(id)
 	if err != nil {
 		return err
 	}
 
+	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
+		return fmt.Errorf("id '%s' is not valid", id)
+	}
+
 	// Check if profile exists
 	if _, err := os.Stat(configPath); os.IsNotExist(err) {
-		return fmt.Errorf("profile '%s' does not exist", profileName)
+		return fmt.Errorf("profile '%s' does not exist", id)
 	}
 
 	// Read current config using internal profilemanager
@@ -174,53 +185,57 @@ func (pm *ProfileManager) LogoutProfile(profileName string) error {
 		return fmt.Errorf("failed to save config: %w", err)
 	}
 
-	log.Infof("logged out from profile: %s", profileName)
+	log.Infof("logged out from profile: %s", id)
 	return nil
 }
 
 // RemoveProfile deletes a profile
-func (pm *ProfileManager) RemoveProfile(profileName string) error {
+func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)
-	if err := pm.serviceMgr.RemoveProfile(profileName, androidUsername); err != nil {
+	if err := pm.serviceMgr.RemoveProfile(profilemanager.ID(id), androidUsername); err != nil {
 		return fmt.Errorf("failed to remove profile: %w", err)
 	}
 
-	log.Infof("removed profile: %s", profileName)
+	log.Infof("removed profile: %s", id)
 	return nil
 }
 
 // getProfileConfigPath returns the config file path for a profile
 // This is needed for Android-specific path handling (netbird.cfg for default profile)
-func (pm *ProfileManager) getProfileConfigPath(profileName string) (string, error) {
-	if profileName == "" || profileName == profilemanager.DefaultProfileName {
+func (pm *ProfileManager) getProfileConfigPath(id string) (string, error) {
+	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
+		return "", fmt.Errorf("id %q is not valid", id)
+	}
+
+	if id == profilemanager.DefaultProfileName {
 		// Android uses netbird.cfg for default profile instead of default.json
 		// Default profile is stored in root configDir, not in profiles/
 		return filepath.Join(pm.configDir, defaultConfigFilename), nil
 	}
 
-	// Non-default profiles are stored in profiles subdirectory
-	// This matches the Java Preferences.java expectation
-	profileName = sanitizeProfileName(profileName)
 	profilesDir := filepath.Join(pm.configDir, profilesSubdir)
-	return filepath.Join(profilesDir, profileName+".json"), nil
+	return filepath.Join(profilesDir, id+".json"), nil
 }
 
-// GetConfigPath returns the config file path for a given profile
+// GetConfigPath returns the config file path for a given profile id
 // Java should call this instead of constructing paths with Preferences.configFile()
-func (pm *ProfileManager) GetConfigPath(profileName string) (string, error) {
-	return pm.getProfileConfigPath(profileName)
+func (pm *ProfileManager) GetConfigPath(id string) (string, error) {
+	return pm.getProfileConfigPath(id)
 }
 
 // GetStateFilePath returns the state file path for a given profile
 // Java should call this instead of constructing paths with Preferences.stateFile()
-func (pm *ProfileManager) GetStateFilePath(profileName string) (string, error) {
-	if profileName == "" || profileName == profilemanager.DefaultProfileName {
+func (pm *ProfileManager) GetStateFilePath(id string) (string, error) {
+	if id == "" || id == profilemanager.DefaultProfileName {
 		return filepath.Join(pm.configDir, "state.json"), nil
 	}
 
-	profileName = sanitizeProfileName(profileName)
+	if !profilemanager.IsValidProfileFilenameStem(profilemanager.ID(id)) {
+		return "", fmt.Errorf("id %q is not valid", id)
+	}
+
 	profilesDir := filepath.Join(pm.configDir, profilesSubdir)
-	return filepath.Join(profilesDir, profileName+".state.json"), nil
+	return filepath.Join(profilesDir, id+".state.json"), nil
 }
 
 // GetActiveConfigPath returns the config file path for the currently active profile
@@ -230,7 +245,7 @@ func (pm *ProfileManager) GetActiveConfigPath() (string, error) {
 	if err != nil {
 		return "", fmt.Errorf("failed to get active profile: %w", err)
 	}
-	return pm.GetConfigPath(activeProfile)
+	return pm.GetConfigPath(activeProfile.ID)
 }
 
 // GetActiveStateFilePath returns the state file path for the currently active profile
@@ -240,18 +255,5 @@ func (pm *ProfileManager) GetActiveStateFilePath() (string, error) {
 	if err != nil {
 		return "", fmt.Errorf("failed to get active profile: %w", err)
 	}
-	return pm.GetStateFilePath(activeProfile)
-}
-
-// sanitizeProfileName removes invalid characters from profile name
-func sanitizeProfileName(name string) string {
-	// Keep only alphanumeric, underscore, and hyphen
-	var result strings.Builder
-	for _, r := range name {
-		if (r >= 'a' && r <= 'z') || (r >= 'A' && r <= 'Z') ||
-			(r >= '0' && r <= '9') || r == '_' || r == '-' {
-			result.WriteRune(r)
-		}
-	}
-	return result.String()
+	return pm.GetStateFilePath(activeProfile.ID)
 }

client/cmd/login.go

@@ -96,17 +96,19 @@ func doDaemonLogin(ctx context.Context, cmd *cobra.Command, providedSetupKey str
 		dnsLabelsReq = dnsLabelsValidated.ToSafeStringList()
 	}
 
+	handle := activeProf.ID.String()
+
 	loginRequest := proto.LoginRequest{
 		SetupKey:            providedSetupKey,
 		ManagementUrl:       managementURL,
 		IsUnixDesktopClient: isUnixRunningDesktop(),
 		Hostname:            hostName,
 		DnsLabels:           dnsLabelsReq,
-		ProfileName:         &activeProf.Name,
+		ProfileName:         &handle,
 		Username:            &username,
 	}
 
-	profileState, err := pm.GetProfileState(activeProf.Name)
+	profileState, err := pm.GetProfileState(activeProf.ID)
 	if err != nil {
 		log.Debugf("failed to get profile state for login hint: %v", err)
 	} else if profileState.Email != "" {
@@ -170,14 +172,13 @@ func getActiveProfile(ctx context.Context, pm *profilemanager.ProfileManager, pr
 	return activeProf, nil
 }
 
-func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManager, profileName string, username string) error {
-	err := switchProfile(context.Background(), profileName, username)
+func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManager, handle string, username string) error {
+	resolvedID, err := switchProfile(ctx, handle, username)
 	if err != nil {
 		return fmt.Errorf("switch profile on daemon: %v", err)
 	}
 
-	err = pm.SwitchProfile(profileName)
-	if err != nil {
+	if err := pm.SwitchProfile(resolvedID); err != nil {
 		return fmt.Errorf("switch profile: %v", err)
 	}
 
@@ -205,11 +206,15 @@ func switchProfileOnDaemon(ctx context.Context, pm *profilemanager.ProfileManage
 	return nil
 }
 
-func switchProfile(ctx context.Context, profileName string, username string) error {
+// switchProfile asks the daemon to switch to the profile identified by
+// handle (a name, ID, or unique ID prefix). Returns the resolved profile
+// ID so the caller can update the local active-profile state without
+// re-resolving the handle.
+func switchProfile(ctx context.Context, handle string, username string) (profilemanager.ID, error) {
 	conn, err := DialClientGRPCServer(ctx, daemonAddr)
 	if err != nil {
 		//nolint
-		return fmt.Errorf("failed to connect to daemon error: %v\n"+
+		return "", fmt.Errorf("failed to connect to daemon error: %v\n"+
 			"If the daemon is not running please run: "+
 			"\nnetbird service install \nnetbird service start\n", err)
 	}
@@ -217,15 +222,15 @@ func switchProfile(ctx context.Context, profileName string, username string) err
 
 	client := proto.NewDaemonServiceClient(conn)
 
-	_, err = client.SwitchProfile(ctx, &proto.SwitchProfileRequest{
-		ProfileName: &profileName,
+	resp, err := client.SwitchProfile(ctx, &proto.SwitchProfileRequest{
+		ProfileName: &handle,
 		Username:    &username,
 	})
 	if err != nil {
-		return fmt.Errorf("switch profile failed: %v", err)
+		return "", fmt.Errorf("switch profile failed: %v", err)
 	}
 
-	return nil
+	return profilemanager.ID(resp.Id), nil
 }
 
 func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string, activeProf *profilemanager.Profile) error {
@@ -249,7 +254,7 @@ func doForegroundLogin(ctx context.Context, cmd *cobra.Command, setupKey string,
 		return fmt.Errorf("read config file %s: %v", configFilePath, err)
 	}
 
-	err = foregroundLogin(ctx, cmd, config, setupKey, activeProf.Name)
+	err = foregroundLogin(ctx, cmd, config, setupKey, activeProf.ID)
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)
 	}
@@ -277,7 +282,7 @@ func handleSSOLogin(ctx context.Context, cmd *cobra.Command, loginResp *proto.Lo
 	return nil
 }
 
-func foregroundLogin(ctx context.Context, cmd *cobra.Command, config *profilemanager.Config, setupKey, profileName string) error {
+func foregroundLogin(ctx context.Context, cmd *cobra.Command, config *profilemanager.Config, setupKey string, profileID profilemanager.ID) error {
 	authClient, err := auth.NewAuth(ctx, config.PrivateKey, config.ManagementURL, config)
 	if err != nil {
 		return fmt.Errorf("failed to create auth client: %v", err)
@@ -291,7 +296,7 @@ func foregroundLogin(ctx context.Context, cmd *cobra.Command, config *profileman
 
 	jwtToken := ""
 	if setupKey == "" && needsLogin {
-		tokenInfo, err := foregroundGetTokenInfo(ctx, cmd, config, profileName)
+		tokenInfo, err := foregroundGetTokenInfo(ctx, cmd, config, profileID)
 		if err != nil {
 			return fmt.Errorf("interactive sso login failed: %v", err)
 		}
@@ -306,10 +311,10 @@ func foregroundLogin(ctx context.Context, cmd *cobra.Command, config *profileman
 	return nil
 }
 
-func foregroundGetTokenInfo(ctx context.Context, cmd *cobra.Command, config *profilemanager.Config, profileName string) (*auth.TokenInfo, error) {
+func foregroundGetTokenInfo(ctx context.Context, cmd *cobra.Command, config *profilemanager.Config, profileID profilemanager.ID) (*auth.TokenInfo, error) {
 	hint := ""
 	pm := profilemanager.NewProfileManager()
-	profileState, err := pm.GetProfileState(profileName)
+	profileState, err := pm.GetProfileState(profileID)
 	if err != nil {
 		log.Debugf("failed to get profile state for login hint: %v", err)
 	} else if profileState.Email != "" {

client/cmd/login_test.go

@@ -27,7 +27,7 @@ func TestLogin(t *testing.T) {
 	profilemanager.ActiveProfileStatePath = tempDir + "/active_profile.json"
 	sm := profilemanager.ServiceManager{}
 	err = sm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     "default",
+		ID:       "default",
 		Username: currUser.Username,
 	})
 	if err != nil {

client/cmd/profile.go

@@ -2,11 +2,16 @@ package cmd
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"os/user"
+	"strings"
+	"text/tabwriter"
 	"time"
 
 	"github.com/spf13/cobra"
+	"google.golang.org/grpc/codes"
+	gstatus "google.golang.org/grpc/status"
 
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
@@ -14,6 +19,8 @@ import (
 	"github.com/netbirdio/netbird/util"
 )
 
+var profileListShowID bool
+
 var profileCmd = &cobra.Command{
 	Use:   "profile",
 	Short: "Manage NetBird client profiles",
@@ -31,27 +38,40 @@ var profileListCmd = &cobra.Command{
 var profileAddCmd = &cobra.Command{
 	Use:   "add <profile_name>",
 	Short: "Add a new profile",
-	Long:  `Add a new profile to the NetBird client. The profile name must be unique.`,
+	Long:  `Add a new profile. Profile name is free-form, a unique ID is generated for the on-disk config file.`,
 	Args:  cobra.ExactArgs(1),
 	RunE:  addProfileFunc,
 }
 
+var profileRenameCmd = &cobra.Command{
+	Use:   "rename <profile> <new_profile_name>",
+	Short: "Renames an existing profile",
+	Long:  `Renames an existing profile (by a name, ID, or unique ID prefix). Profile name is free-form.`,
+	Args:  cobra.ExactArgs(2),
+	RunE:  renameProfileFunc,
+}
+
 var profileRemoveCmd = &cobra.Command{
-	Use:   "remove <profile_name>",
-	Short: "Remove a profile",
-	Long:  `Remove a profile from the NetBird client. The profile must not be inactive.`,
-	Args:  cobra.ExactArgs(1),
-	RunE:  removeProfileFunc,
+	Use:     "remove <profile>",
+	Short:   "Remove a profile",
+	Long:    `Remove a profile by name, ID, or unique ID prefix.`,
+	Aliases: []string{"rm"},
+	Args:    cobra.ExactArgs(1),
+	RunE:    removeProfileFunc,
 }
 
 var profileSelectCmd = &cobra.Command{
-	Use:   "select <profile_name>",
+	Use:   "select <profile>",
 	Short: "Select a profile",
-	Long:  `Make the specified profile active. This will switch the client to use the selected profile's configuration.`,
+	Long:  `Make the specified profile active. Accepts a name, ID, or unique ID prefix.`,
 	Args:  cobra.ExactArgs(1),
 	RunE:  selectProfileFunc,
 }
 
+func init() {
+	profileListCmd.Flags().BoolVar(&profileListShowID, "show-id", false, "show the profile ID column")
+}
+
 func setupCmd(cmd *cobra.Command) error {
 	SetFlagsFromEnvVars(rootCmd)
 	SetFlagsFromEnvVars(cmd)
@@ -65,6 +85,7 @@ func setupCmd(cmd *cobra.Command) error {
 
 	return nil
 }
+
 func listProfilesFunc(cmd *cobra.Command, _ []string) error {
 	if err := setupCmd(cmd); err != nil {
 		return err
@@ -83,25 +104,33 @@ func listProfilesFunc(cmd *cobra.Command, _ []string) error {
 
 	daemonClient := proto.NewDaemonServiceClient(conn)
 
-	profiles, err := daemonClient.ListProfiles(cmd.Context(), &proto.ListProfilesRequest{
+	resp, err := daemonClient.ListProfiles(cmd.Context(), &proto.ListProfilesRequest{
 		Username: currUser.Username,
 	})
 	if err != nil {
 		return err
 	}
 
-	// list profiles, add a tick if the profile is active
-	cmd.Println("Found", len(profiles.Profiles), "profiles:")
-	for _, profile := range profiles.Profiles {
-		// use a cross to indicate the passive profiles
-		activeMarker := "✗"
-		if profile.IsActive {
-			activeMarker = "✓"
-		}
-		cmd.Println(activeMarker, profile.Name)
+	tw := tabwriter.NewWriter(cmd.OutOrStdout(), 0, 0, 2, ' ', 0)
+	if profileListShowID {
+		fmt.Fprintln(tw, "ID\tNAME\tACTIVE")
+	} else {
+		fmt.Fprintln(tw, "NAME\tACTIVE")
 	}
-
-	return nil
+	for _, profile := range resp.Profiles {
+		marker := ""
+		if profile.IsActive {
+			marker = "✓"
+		}
+		name := profilemanager.StripCtrlChars(profile.Name)
+		id := profilemanager.ID(profile.Id)
+		if profileListShowID {
+			fmt.Fprintf(tw, "%s\t%s\t%s\n", id.ShortID(), name, marker)
+		} else {
+			fmt.Fprintf(tw, "%s\t%s\n", name, marker)
+		}
+	}
+	return tw.Flush()
 }
 
 func addProfileFunc(cmd *cobra.Command, args []string) error {
@@ -121,21 +150,82 @@ func addProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 
 	daemonClient := proto.NewDaemonServiceClient(conn)
-
 	profileName := args[0]
 
-	_, err = daemonClient.AddProfile(cmd.Context(), &proto.AddProfileRequest{
+	resp, err := daemonClient.AddProfile(cmd.Context(), &proto.AddProfileRequest{
 		ProfileName: profileName,
 		Username:    currUser.Username,
 	})
 	if err != nil {
+		return fmt.Errorf("add profile request: %w", err)
+	}
+
+	dupCount, _ := countProfilesWithName(cmd.Context(), daemonClient, currUser.Username, profileName)
+	if dupCount > 1 {
+		cmd.Printf("Warning: %d other profile(s) already use the name %q.\n", dupCount-1, profileName)
+		cmd.Println("Use `netbird profile list --show-id` to disambiguate later.")
+	}
+
+	id := profilemanager.ID(resp.Id)
+	cmd.Printf("Profile added: %s  %s\n", id.ShortID(), profilemanager.StripCtrlChars(profileName))
+	return nil
+
+}
+
+func renameProfileFunc(cmd *cobra.Command, args []string) error {
+	if err := setupCmd(cmd); err != nil {
 		return err
 	}
 
-	cmd.Println("Profile added successfully:", profileName)
+	conn, err := DialClientGRPCServer(cmd.Context(), daemonAddr)
+	if err != nil {
+		return fmt.Errorf("connect to service CLI interface: %w", err)
+	}
+	defer conn.Close()
+
+	currUser, err := user.Current()
+	if err != nil {
+		return fmt.Errorf("get current user: %w", err)
+	}
+
+	daemonClient := proto.NewDaemonServiceClient(conn)
+	handle := args[0]
+	newProfilename := args[1]
+
+	resp, err := daemonClient.RenameProfile(cmd.Context(), &proto.RenameProfileRequest{
+		Handle:         handle,
+		Username:       currUser.Username,
+		NewProfileName: newProfilename,
+	})
+	if err != nil {
+		return wrapAmbiguityError(err, handle)
+	}
+
+	dupCount, _ := countProfilesWithName(cmd.Context(), daemonClient, currUser.Username, newProfilename)
+	if dupCount > 1 {
+		cmd.Printf("Warning: %d other profile(s) already use the name %q.\n", dupCount-1, newProfilename)
+		cmd.Println("Use `netbird profile list --show-id` to disambiguate later.")
+	}
+
+	cmd.Printf("Profile renamed from %s to %s\n", profilemanager.StripCtrlChars(resp.OldProfileName), profilemanager.StripCtrlChars(newProfilename))
+
 	return nil
 }
 
+func countProfilesWithName(ctx context.Context, c proto.DaemonServiceClient, username, name string) (int, error) {
+	resp, err := c.ListProfiles(ctx, &proto.ListProfilesRequest{Username: username})
+	if err != nil {
+		return 0, err
+	}
+	n := 0
+	for _, p := range resp.Profiles {
+		if p.Name == name {
+			n++
+		}
+	}
+	return n, nil
+}
+
 func removeProfileFunc(cmd *cobra.Command, args []string) error {
 	if err := setupCmd(cmd); err != nil {
 		return err
@@ -153,18 +243,17 @@ func removeProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 
 	daemonClient := proto.NewDaemonServiceClient(conn)
+	handle := args[0]
 
-	profileName := args[0]
-
-	_, err = daemonClient.RemoveProfile(cmd.Context(), &proto.RemoveProfileRequest{
-		ProfileName: profileName,
+	resp, err := daemonClient.RemoveProfile(cmd.Context(), &proto.RemoveProfileRequest{
+		ProfileName: handle,
 		Username:    currUser.Username,
 	})
 	if err != nil {
-		return err
+		return wrapAmbiguityError(err, handle)
 	}
 
-	cmd.Println("Profile removed successfully:", profileName)
+	cmd.Printf("Profile removed: %s\n", resp.Id)
 	return nil
 }
 
@@ -174,7 +263,7 @@ func selectProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 
 	profileManager := profilemanager.NewProfileManager()
-	profileName := args[0]
+	handle := args[0]
 
 	currUser, err := user.Current()
 	if err != nil {
@@ -191,32 +280,15 @@ func selectProfileFunc(cmd *cobra.Command, args []string) error {
 
 	daemonClient := proto.NewDaemonServiceClient(conn)
 
-	profiles, err := daemonClient.ListProfiles(ctx, &proto.ListProfilesRequest{
-		Username: currUser.Username,
+	switchResp, err := daemonClient.SwitchProfile(ctx, &proto.SwitchProfileRequest{
+		ProfileName: &handle,
+		Username:    &currUser.Username,
 	})
 	if err != nil {
-		return fmt.Errorf("list profiles: %w", err)
+		return wrapAmbiguityError(err, handle)
 	}
 
-	var profileExists bool
-
-	for _, profile := range profiles.Profiles {
-		if profile.Name == profileName {
-			profileExists = true
-			break
-		}
-	}
-
-	if !profileExists {
-		return fmt.Errorf("profile %s does not exist", profileName)
-	}
-
-	if err := switchProfile(cmd.Context(), profileName, currUser.Username); err != nil {
-		return err
-	}
-
-	err = profileManager.SwitchProfile(profileName)
-	if err != nil {
+	if err := profileManager.SwitchProfile(profilemanager.ID(switchResp.Id)); err != nil {
 		return err
 	}
 
@@ -231,6 +303,30 @@ func selectProfileFunc(cmd *cobra.Command, args []string) error {
 		}
 	}
 
-	cmd.Println("Profile switched successfully to:", profileName)
+	id := profilemanager.ID(switchResp.Id)
+	cmd.Printf("Profile switched to: %s\n", id.ShortID())
 	return nil
 }
+
+// wrapAmbiguityError turns the daemon's gRPC InvalidArgument errors
+// (which carry the resolver's message verbatim) into CLI-friendly text
+// that points the user at --show-id.
+func wrapAmbiguityError(err error, handle string) error {
+	if err == nil {
+		return nil
+	}
+	st, ok := gstatus.FromError(err)
+	if !ok {
+		return err
+	}
+	switch st.Code() {
+	case codes.InvalidArgument:
+		msg := st.Message()
+		if strings.Contains(msg, "ambiguous") {
+			return errors.New(msg + "\nRun `netbird profile list --show-id` to see IDs, then select by ID prefix:\n  netbird profile select|remove <id-prefix>")
+		}
+	case codes.NotFound:
+		return fmt.Errorf("profile %q not found", handle)
+	}
+	return err
+}

client/cmd/root.go

@@ -20,6 +20,7 @@ import (
 	"github.com/spf13/cobra"
 	"github.com/spf13/pflag"
 	"google.golang.org/grpc"
+	"google.golang.org/grpc/connectivity"
 	"google.golang.org/grpc/credentials/insecure"
 
 	daddr "github.com/netbirdio/netbird/client/internal/daemonaddr"
@@ -190,6 +191,7 @@ func init() {
 	// profile commands
 	profileCmd.AddCommand(profileListCmd)
 	profileCmd.AddCommand(profileAddCmd)
+	profileCmd.AddCommand(profileRenameCmd)
 	profileCmd.AddCommand(profileRemoveCmd)
 	profileCmd.AddCommand(profileSelectCmd)
 
@@ -260,17 +262,46 @@ func FlagNameToEnvVar(cmdFlag string, prefix string) string {
 	return prefix + upper
 }
 
-// DialClientGRPCServer returns client connection to the daemon server.
+// DialClientGRPCServer returns client connection to the daemon server. It waits
+// (up to the timeout) for the daemon to become reachable so an `up` issued right
+// after `service start` tolerates the startup race. Instead of grpc's blocking
+// dial — whose raw "transport failed" retry warnings are silenced by the logger
+// config — we drive the wait ourselves and emit one clean line per failed attempt.
 func DialClientGRPCServer(ctx context.Context, addr string) (*grpc.ClientConn, error) {
 	ctx, cancel := context.WithTimeout(ctx, time.Second*10)
 	defer cancel()
 
-	return grpc.DialContext(
+	conn, err := grpc.DialContext(
 		ctx,
 		strings.TrimPrefix(addr, "tcp://"),
 		grpc.WithTransportCredentials(insecure.NewCredentials()),
-		grpc.WithBlock(),
 	)
+	if err != nil {
+		return nil, err
+	}
+
+	conn.Connect()
+	for {
+		state := conn.GetState()
+		if state == connectivity.Ready {
+			return conn, nil
+		}
+		// Log only once the connection has actually failed — not during the
+		// brief Idle/Connecting phase on a healthy daemon (avoids a spurious
+		// line + wait when the daemon is already up).
+		if state == connectivity.TransientFailure {
+			log.Infof("waiting for the netbird daemon to become available at %s...", addr)
+		}
+		// Wake on the next state change, but at least every second so a stuck
+		// TransientFailure re-logs at a steady cadence until the timeout.
+		waitCtx, waitCancel := context.WithTimeout(ctx, time.Second)
+		conn.WaitForStateChange(waitCtx, state)
+		waitCancel()
+		if ctx.Err() != nil {
+			_ = conn.Close()
+			return nil, fmt.Errorf("daemon not reachable at %s: %w", addr, ctx.Err())
+		}
+	}
 }
 
 // WithBackOff execute function in backoff cycle.

client/cmd/up.go

@@ -128,13 +128,12 @@ func upFunc(cmd *cobra.Command, args []string) error {
 	var profileSwitched bool
 	// switch profile if provided
 	if profileName != "" {
-		err = switchProfile(cmd.Context(), profileName, username.Username)
+		resolvedID, err := switchProfile(cmd.Context(), profileName, username.Username)
 		if err != nil {
 			return fmt.Errorf("switch profile: %v", err)
 		}
 
-		err = pm.SwitchProfile(profileName)
-		if err != nil {
+		if err := pm.SwitchProfile(resolvedID); err != nil {
 			return fmt.Errorf("switch profile: %v", err)
 		}
 
@@ -190,7 +189,7 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
 
 	_, _ = profilemanager.UpdateOldManagementURL(ctx, config, configFilePath)
 
-	err = foregroundLogin(ctx, cmd, config, providedSetupKey, activeProf.Name)
+	err = foregroundLogin(ctx, cmd, config, providedSetupKey, activeProf.ID)
 	if err != nil {
 		return fmt.Errorf("foreground login failed: %v", err)
 	}
@@ -202,10 +201,10 @@ func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *pr
 	r := peer.NewRecorder(config.ManagementURL.String())
 	r.GetFullStatus()
 
-	connectClient := internal.NewConnectClient(ctx, config, r)
+	connectClient := internal.NewConnectClient(ctx, r)
 	SetupDebugHandler(ctx, config, r, connectClient, "")
 
-	return connectClient.Run(nil, util.FindFirstLogPath(logFiles))
+	return connectClient.Run(config, nil, util.FindFirstLogPath(logFiles))
 }
 
 func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager.ProfileManager, activeProf *profilemanager.Profile, profileSwitched bool) error {
@@ -261,10 +260,10 @@ func runInDaemonMode(ctx context.Context, cmd *cobra.Command, pm *profilemanager
 	}
 
 	// set the new config
-	req := setupSetConfigReq(customDNSAddressConverted, cmd, activeProf.Name, username.Username)
+	req := setupSetConfigReq(customDNSAddressConverted, cmd, activeProf.ID.String(), username.Username)
 	if _, err := client.SetConfig(ctx, req); err != nil {
 		if st, ok := gstatus.FromError(err); ok && st.Code() == codes.Unavailable {
-			log.Warnf("setConfig method is not available in the daemon")
+			log.Warnf("setConfig method is not available in the daemon: %s", st.Message())
 		} else {
 			return fmt.Errorf("call service setConfig method: %v", err)
 		}
@@ -289,10 +288,11 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 		return fmt.Errorf("setup login request: %v", err)
 	}
 
-	loginRequest.ProfileName = &activeProf.Name
+	profileID := activeProf.ID.String()
+	loginRequest.ProfileName = &profileID
 	loginRequest.Username = &username
 
-	profileState, err := pm.GetProfileState(activeProf.Name)
+	profileState, err := pm.GetProfileState(activeProf.ID)
 	if err != nil {
 		log.Debugf("failed to get profile state for login hint: %v", err)
 	} else if profileState.Email != "" {
@@ -329,7 +329,7 @@ func doDaemonUp(ctx context.Context, cmd *cobra.Command, client proto.DaemonServ
 	}
 
 	if _, err := client.Up(ctx, &proto.UpRequest{
-		ProfileName: &activeProf.Name,
+		ProfileName: &profileID,
 		Username:    &username,
 	}); err != nil {
 		return fmt.Errorf("call service up method: %v", err)

client/cmd/up_daemon_test.go

@@ -29,14 +29,14 @@ func TestUpDaemon(t *testing.T) {
 	}
 
 	sm := profilemanager.ServiceManager{}
-	err = sm.AddProfile("test1", currUser.Username)
+	created, err := sm.AddProfile("test1", currUser.Username)
 	if err != nil {
 		t.Fatalf("failed to add profile: %v", err)
 		return
 	}
 
 	err = sm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     "test1",
+		ID:       created.ID,
 		Username: currUser.Username,
 	})
 	if err != nil {

client/embed/embed.go

@@ -264,32 +264,24 @@ func (c *Client) Start(startCtx context.Context) error {
 	if err, _ := authClient.Login(ctx, c.setupKey, c.jwtToken); err != nil {
 		return fmt.Errorf("login: %w", err)
 	}
-	client := internal.NewConnectClient(ctx, c.config, c.recorder)
+	client := internal.NewConnectClient(ctx, c.recorder)
 	client.SetSyncResponsePersistence(true)
 
-	// either startup error (permanent backoff err) or nil err (successful engine up)
+	// The supervisor owns the run; we wait until it is established, ends with a
+	// startup error (permanent backoff err), or startCtx expires.
 	// TODO: make after-startup backoff err available
-	run := make(chan struct{})
-	clientErr := make(chan error, 1)
-	go func() {
-		if err := client.Run(run, ""); err != nil {
-			clientErr <- err
-		}
-	}()
+	client.RunAsync(c.config, nil)
 
-	select {
-	case <-startCtx.Done():
-		// Cancel the client context before stopping: Engine.Start blocks on the
-		// signal stream while holding the engine mutex and only unblocks on
-		// cancellation. Stopping first would deadlock on that mutex.
+	if err := client.WaitEstablishedOrDone(startCtx); err != nil {
+		// Either startCtx expired while connecting, or the run ended before it
+		// established. Cancel the client context before stopping: Engine.Start
+		// blocks on the signal stream while holding the engine mutex and only
+		// unblocks on cancellation. Stopping first would deadlock on that mutex.
 		cancel()
 		if stopErr := client.Stop(); stopErr != nil {
-			return fmt.Errorf("stop error after context done. Stop error: %w. Context done: %w", stopErr, startCtx.Err())
+			return fmt.Errorf("stop error after startup failure. Stop error: %w. Startup: %w", stopErr, err)
 		}
-		return startCtx.Err()
-	case err := <-clientErr:
 		return fmt.Errorf("startup: %w", err)
-	case <-run:
 	}
 
 	c.connect = client

client/internal/connect.go

@@ -18,6 +18,7 @@ import (
 
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/metadata"
 	gstatus "google.golang.org/grpc/status"
 
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
@@ -48,13 +49,23 @@ import (
 	"github.com/netbirdio/netbird/version"
 )
 
-// androidRunOverride is set on Android to inject mobile dependencies
-// when using embed.Client (which calls Run() with empty MobileDependency).
-var androidRunOverride func(c *ConnectClient, runningChan chan struct{}, logPath string) error
+// androidMobileDep is set on Android to inject the MobileDependency for runs
+// started through the generic entry points (Run/RunAsync, e.g. embed.Client).
+// nil on other platforms, where the dependency is empty.
+var androidMobileDep func(config *profilemanager.Config) MobileDependency
+
+// mobileDependency returns the MobileDependency for a run started via the
+// generic entry points. On Android the androidMobileDep provider supplies
+// platform stubs (or real implementations); elsewhere it is empty.
+func (c *ConnectClient) mobileDependency(config *profilemanager.Config) MobileDependency {
+	if androidMobileDep != nil {
+		return androidMobileDep(config)
+	}
+	return MobileDependency{}
+}
 
 type ConnectClient struct {
 	ctx            context.Context
-	config         *profilemanager.Config
 	statusRecorder *peer.Status
 
 	engine        *Engine
@@ -63,35 +74,62 @@ type ConnectClient struct {
 	updateManager *updater.Manager
 
 	persistSyncResponse bool
+
+	// sup serializes all start/stop requests so two lifecycle operations can
+	// never overlap. See connect_lifecycle.go.
+	sup *supervisor
 }
 
 func NewConnectClient(
 	ctx context.Context,
-	config *profilemanager.Config,
 	statusRecorder *peer.Status,
 ) *ConnectClient {
-	return &ConnectClient{
+	c := &ConnectClient{
 		ctx:            ctx,
-		config:         config,
 		statusRecorder: statusRecorder,
 		engineMutex:    sync.Mutex{},
 	}
+	c.sup = newSupervisor(ctx, c.run)
+	return c
 }
 
 func (c *ConnectClient) SetUpdateManager(um *updater.Manager) {
 	c.updateManager = um
 }
 
-// Run with main logic.
-func (c *ConnectClient) Run(runningChan chan struct{}, logPath string) error {
-	if androidRunOverride != nil {
-		return androidRunOverride(c, runningChan, logPath)
-	}
-	return c.run(MobileDependency{}, runningChan, logPath)
+// Run with main logic. md carries optional gRPC metadata (e.g. the UI
+// user-agent) to forward to the management/signal services; nil when none.
+func (c *ConnectClient) Run(config *profilemanager.Config, md metadata.MD, logPath string) error {
+	return c.sup.start(config, md, c.mobileDependency(config), logPath)
+}
+
+// RunAsync starts a client run without blocking. Used by the daemon and embed,
+// which drive the lifecycle through the supervisor rather than blocking on Run;
+// they then wait for the outcome via WaitEstablishedOrDone. The run's lifecycle
+// channels are created and owned by the supervisor — callers never hold them.
+func (c *ConnectClient) RunAsync(config *profilemanager.Config, md metadata.MD) {
+	c.sup.startAsync(config, md, c.mobileDependency(config), "", nil)
+}
+
+// Restart atomically stops any in-flight run and starts a fresh one with the
+// given config. The stop+start happens as a single supervisor operation, so no
+// other lifecycle request can interleave between them — used for explicit
+// restarts (e.g. an MDM policy change) that must not expose a "stopped" window.
+func (c *ConnectClient) Restart(config *profilemanager.Config, md metadata.MD) {
+	c.sup.restartAsync(config, md, c.mobileDependency(config), "")
+}
+
+// WaitEstablishedOrDone blocks until the in-flight run becomes established (nil),
+// ends before that (the run error, or a sentinel on a clean stop), or ctx is
+// cancelled. Returns errNoRunInFlight if no run is in flight. Wraps the wait on
+// the supervisor-owned channels so callers never touch them directly.
+func (c *ConnectClient) WaitEstablishedOrDone(ctx context.Context) error {
+	return c.sup.waitEstablishedOrDone(ctx)
 }
 
 // RunOnAndroid with main logic on mobile system
 func (c *ConnectClient) RunOnAndroid(
+	config *profilemanager.Config,
 	tunAdapter device.TunAdapter,
 	iFaceDiscover stdnet.ExternalIFaceDiscover,
 	networkChangeListener listener.NetworkChangeListener,
@@ -110,10 +148,11 @@ func (c *ConnectClient) RunOnAndroid(
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}
-	return c.run(mobileDependency, nil, "")
+	return c.sup.start(config, nil, mobileDependency, "")
 }
 
 func (c *ConnectClient) RunOniOS(
+	config *profilemanager.Config,
 	fileDescriptor int32,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsManager dns.IosDnsManager,
@@ -131,10 +170,12 @@ func (c *ConnectClient) RunOniOS(
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}
-	return c.run(mobileDependency, nil, logFilePath)
+	return c.sup.start(config, nil, mobileDependency, logFilePath)
 }
 
-func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan struct{}, logPath string) error {
+// run executes a single client run. runCtx is owned by the supervisor: cancelling
+// it tears the run down (it is the parent of the per-attempt engine context).
+func (c *ConnectClient) run(runCtx context.Context, config *profilemanager.Config, mobileDependency MobileDependency, connEstablishedChan chan struct{}, logPath string) error {
 	defer func() {
 		if r := recover(); r != nil {
 			rec := c.statusRecorder
@@ -198,18 +239,18 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	}()
 
 	wrapErr := state.Wrap
-	myPrivateKey, err := wgtypes.ParseKey(c.config.PrivateKey)
+	myPrivateKey, err := wgtypes.ParseKey(config.PrivateKey)
 	if err != nil {
-		log.Errorf("failed parsing Wireguard key %s: [%s]", c.config.PrivateKey, err.Error())
+		log.Errorf("failed parsing Wireguard key %s: [%s]", config.PrivateKey, err.Error())
 		return wrapErr(err)
 	}
 
 	var mgmTlsEnabled bool
-	if c.config.ManagementURL.Scheme == "https" {
+	if config.ManagementURL.Scheme == "https" {
 		mgmTlsEnabled = true
 	}
 
-	publicSSHKey, err := ssh.GeneratePublicKey([]byte(c.config.SSHKey))
+	publicSSHKey, err := ssh.GeneratePublicKey([]byte(config.SSHKey))
 	if err != nil {
 		return err
 	}
@@ -243,13 +284,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	defer c.statusRecorder.ClientStop()
 	operation := func() error {
 		// if context cancelled we not start new backoff cycle
-		if c.ctx.Err() != nil {
+		if runCtx.Err() != nil {
 			return nil
 		}
 
 		state.Set(StatusConnecting)
 
-		engineCtx, cancel := context.WithCancel(c.ctx)
+		engineCtx, cancel := context.WithCancel(runCtx)
 		defer func() {
 			_, err := state.Status()
 			c.statusRecorder.MarkManagementDisconnected(err)
@@ -257,8 +298,8 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 			cancel()
 		}()
 
-		log.Debugf("connecting to the Management service %s", c.config.ManagementURL.Host)
-		mgmClient, err := mgm.NewClient(engineCtx, c.config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
+		log.Debugf("connecting to the Management service %s", config.ManagementURL.Host)
+		mgmClient, err := mgm.NewClient(engineCtx, config.ManagementURL.Host, myPrivateKey, mgmTlsEnabled)
 		if err != nil {
 			return wrapErr(gstatus.Errorf(codes.FailedPrecondition, "failed connecting to Management Service : %s", err))
 		}
@@ -275,7 +316,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}
 		c.clientMetrics.UpdateAgentInfo(agentInfo, myPrivateKey.PublicKey().String())
 
-		log.Debugf("connected to the Management service %s", c.config.ManagementURL.Host)
+		log.Debugf("connected to the Management service %s", config.ManagementURL.Host)
 		defer func() {
 			if err = mgmClient.Close(); err != nil {
 				log.Warnf("failed to close the Management service client %v", err)
@@ -284,13 +325,14 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 
 		// connect (just a connection, no stream yet) and login to Management Service to get an initial global Netbird config
 		loginStarted := time.Now()
-		loginResp, err := loginToManagement(engineCtx, mgmClient, publicSSHKey, c.config)
+		loginResp, err := loginToManagement(engineCtx, mgmClient, publicSSHKey, config)
 		if err != nil {
 			c.clientMetrics.RecordLoginDuration(engineCtx, time.Since(loginStarted), false)
 			log.Debug(err)
 			if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
 				state.Set(StatusNeedsLogin)
-				_ = c.Stop()
+				// No teardown needed: login fails before the engine is started
+				// (engine.Start is below), so there is nothing running to stop.
 				return backoff.Permanent(wrapErr(err)) // unrecoverable error
 			}
 			return wrapErr(err)
@@ -344,7 +386,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		}
 		peerConfig := loginResp.GetPeerConfig()
 
-		engineConfig, err := createEngineConfig(myPrivateKey, c.config, peerConfig, logPath)
+		engineConfig, err := createEngineConfig(myPrivateKey, config, peerConfig, logPath)
 		if err != nil {
 			log.Error(err)
 			return wrapErr(err)
@@ -388,7 +430,7 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		c.engine = engine
 		c.engineMutex.Unlock()
 
-		if err := engine.Start(loginResp.GetNetbirdConfig(), c.config.ManagementURL); err != nil {
+		if err := engine.Start(loginResp.GetNetbirdConfig(), config.ManagementURL); err != nil {
 			log.Errorf("error while starting Netbird Connection Engine: %s", err)
 			return wrapErr(err)
 		}
@@ -396,12 +438,13 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		log.Infof("Netbird engine started, the IP is: %s", peerConfig.GetAddress())
 		state.Set(StatusConnected)
 
-		if runningChan != nil {
-			select {
-			case <-runningChan:
-			default:
-				close(runningChan)
-			}
+		// The supervisor owns connEstablishedChan and it is always present. Guard
+		// against a double close: operation re-runs on ErrResetConnection retries
+		// within the same run, and the channel is closed only on the first connect.
+		select {
+		case <-connEstablishedChan:
+		default:
+			close(connEstablishedChan)
 		}
 
 		<-engineCtx.Done()
@@ -410,14 +453,12 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 		c.engine = nil
 		c.engineMutex.Unlock()
 
-		// todo: consider to remove this condition. Is not thread safe.
-		// We should always call Stop(), but we need to verify that it is idempotent
-		if engine.wgInterface != nil {
-			log.Infof("ensuring %s is removed, Netbird engine context cancelled", engine.wgInterface.Name())
-
-			if err := engine.Stop(); err != nil {
-				log.Errorf("Failed to stop engine: %v", err)
-			}
+		// Always tear the engine down once its context is cancelled. engine.Stop
+		// is nil-guarded per component, so calling it unconditionally is safe and
+		// avoids both the data race on engine.wgInterface and skipping teardown
+		// when the interface was never brought up (e.g. a mid-start failure).
+		if err := engine.Stop(); err != nil {
+			log.Errorf("Failed to stop engine: %v", err)
 		}
 		c.statusRecorder.ClientTeardown()
 
@@ -437,8 +478,9 @@ func (c *ConnectClient) run(mobileDependency MobileDependency, runningChan chan
 	if err != nil {
 		log.Debugf("exiting client retry loop due to unrecoverable error: %s", err)
 		if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied) {
+			// Login failed permanently: the engine was never started, so there
+			// is nothing to tear down — just record that a login is needed.
 			state.Set(StatusNeedsLogin)
-			_ = c.Stop()
 		}
 		return err
 	}
@@ -459,6 +501,22 @@ func parseRelayInfo(loginResp *mgmProto.LoginResponse) ([]string, *hmac.Token) {
 	return relayCfg.GetUrls(), token
 }
 
+// ConnectionRunning reports whether a connection run is currently in flight
+// (connecting, connected, or reconnecting). Answered by the supervisor via a
+// serialized query, so it settles behind an in-flight stop. Distinct from
+// ServiceRunning, which reports whether the service itself is alive.
+func (c *ConnectClient) ConnectionRunning() bool {
+	return c.sup.isRunning()
+}
+
+// ServiceRunning reports whether the client's lifecycle supervisor is alive and
+// able to accept start/stop commands — i.e. its context has not been cancelled
+// (the daemon is not shutting down). Independent of whether a connection run is
+// up (that is ConnectionRunning).
+func (c *ConnectClient) ServiceRunning() bool {
+	return c.sup.ctx.Err() == nil
+}
+
 func (c *ConnectClient) Engine() *Engine {
 	if c == nil {
 		return nil
@@ -515,14 +573,10 @@ func (c *ConnectClient) Status() StatusType {
 	return status
 }
 
+// Stop serializes a stop request through the lifecycle supervisor and blocks
+// until the in-flight run is fully torn down.
 func (c *ConnectClient) Stop() error {
-	engine := c.Engine()
-	if engine != nil {
-		if err := engine.Stop(); err != nil {
-			return fmt.Errorf("stop engine: %w", err)
-		}
-	}
-	return nil
+	return c.sup.stop()
 }
 
 // SetSyncResponsePersistence enables or disables sync response persistence.

client/internal/connect_android_default.go

@@ -7,6 +7,7 @@ import (
 
 	"github.com/netbirdio/netbird/client/internal/dns"
 	"github.com/netbirdio/netbird/client/internal/listener"
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 )
 
@@ -59,19 +60,17 @@ var _ listener.NetworkChangeListener = noopNetworkChangeListener{}
 var _ dns.ReadyListener = noopDnsReadyListener{}
 
 func init() {
-	// Wire up the default override so embed.Client.Start() works on Android
-	// with netstack mode. Provides complete no-op stubs for all mobile
+	// Wire up the default MobileDependency provider so embed.Client.Start() works
+	// on Android with netstack mode. Provides complete no-op stubs for all mobile
 	// dependencies so the engine's existing Android code paths work unchanged.
-	// Applications that need P2P ICE or real DNS should replace this by
-	// setting androidRunOverride before calling Start().
-	androidRunOverride = func(c *ConnectClient, runningChan chan struct{}, logPath string) error {
-		return c.runOnAndroidEmbed(
+	// Applications that need P2P ICE or real DNS should replace this by setting
+	// androidMobileDep before calling Start().
+	androidMobileDep = func(config *profilemanager.Config) MobileDependency {
+		return mobileDependencyForEmbed(
 			noopIFaceDiscover{},
 			noopNetworkChangeListener{},
 			[]netip.AddrPort{},
 			noopDnsReadyListener{},
-			runningChan,
-			logPath,
 		)
 	}
 }

client/internal/connect_android_embed.go

@@ -10,23 +10,18 @@ import (
 	"github.com/netbirdio/netbird/client/internal/stdnet"
 )
 
-// runOnAndroidEmbed is like RunOnAndroid but accepts a runningChan
-// so embed.Client.Start() can detect when the engine is ready.
-// It provides complete MobileDependency so the engine's existing
-// Android code paths work unchanged.
-func (c *ConnectClient) runOnAndroidEmbed(
+// mobileDependencyForEmbed builds the MobileDependency used by embed.Client on
+// Android so the engine's existing Android code paths work unchanged.
+func mobileDependencyForEmbed(
 	iFaceDiscover stdnet.ExternalIFaceDiscover,
 	networkChangeListener listener.NetworkChangeListener,
 	dnsAddresses []netip.AddrPort,
 	dnsReadyListener dns.ReadyListener,
-	runningChan chan struct{},
-	logPath string,
-) error {
-	mobileDependency := MobileDependency{
+) MobileDependency {
+	return MobileDependency{
 		IFaceDiscover:         iFaceDiscover,
 		NetworkChangeListener: networkChangeListener,
 		HostDNSAddresses:      dnsAddresses,
 		DnsReadyListener:      dnsReadyListener,
 	}
-	return c.run(mobileDependency, runningChan, logPath)
 }

client/internal/connect_lifecycle.go

@@ -0,0 +1,362 @@
+package internal
+
+import (
+	"context"
+	"errors"
+
+	"google.golang.org/grpc/metadata"
+
+	"github.com/netbirdio/netbird/client/internal/profilemanager"
+)
+
+// errAlreadyRunning is returned when a start is requested while a run is already
+// in flight.
+var errAlreadyRunning = errors.New("client is already running")
+
+// errNoRunInFlight is returned by waitEstablishedOrDone when no run is active.
+var errNoRunInFlight = errors.New("no connection run in flight")
+
+// errStoppedBeforeEstablished is returned when a run ended (cleanly) before the
+// connection was established.
+var errStoppedBeforeEstablished = errors.New("run stopped before the connection was established")
+
+// lifecycleOp is a serialized lifecycle operation processed by the supervisor.
+type lifecycleOp int
+
+const (
+	opStart lifecycleOp = iota
+	opStop
+	opRestart
+	opStatus
+	opWaitEstablished
+)
+
+// lifecycleCmd is a single lifecycle request handed to the supervisor goroutine.
+// They all flow through the same cmdCh so they are strictly ordered (FIFO) with
+// respect to each other.
+type lifecycleCmd struct {
+	op        lifecycleOp
+	config    *profilemanager.Config
+	md        metadata.MD
+	mobileDep MobileDependency
+	logPath   string
+
+	// done is the caller's notification channel (nil for fire-and-forget). Its
+	// meaning depends on op:
+	//   - opStart: receives the run's end result when the run terminates, or
+	//     errAlreadyRunning immediately if a run is already in flight.
+	//   - opStop: receives nil once the in-flight run has fully unwound.
+	//   - opWaitEstablished: receives the wait outcome (see waitEstablishedOrDone).
+	done chan error
+
+	reply   chan bool       // opStatus only: receives whether a run is in flight
+	waitCtx context.Context // opWaitEstablished only: the waiter's cancellation context
+}
+
+// runState holds the lifecycle channels of a single in-flight run, owned by the
+// loop goroutine. It never escapes the supervisor as an API; the only readers
+// are the per-wait goroutines the loop spawns for opWaitEstablished.
+//
+// connEstablishedChan is closed by the run once the connection is established.
+// The supervisor creates and owns it — callers no longer supply it; they observe
+// it through waitEstablishedOrDone. ended is closed (broadcast) when the run
+// terminates, so any number of waiters can observe it; err is the run's end
+// result, valid only after ended is closed.
+type runState struct {
+	connEstablishedChan chan struct{} // closed by the run on established
+	ended               chan struct{} // closed by finishRun when the run terminates
+	err                 error         // run end result, valid after ended is closed
+}
+
+// runEndResult is sent by the run goroutine to the supervisor when a run ends,
+// whether on its own (error / external context cancellation) or because of a Stop.
+type runEndResult struct {
+	err error
+}
+
+// runFunc executes a single client run bound to the supervisor-owned context,
+// with the config supplied by the start request.
+type runFunc func(ctx context.Context, config *profilemanager.Config, mobileDep MobileDependency, connEstablishedChan chan struct{}, logPath string) error
+
+// supervisor serializes start/stop of a single client run. Every request goes
+// through cmdCh and is handled one at a time by the loop goroutine, so two
+// lifecycle operations can never overlap and their order is preserved (FIFO).
+// The loop goroutine is the sole owner of curStart/runCancel, so that state
+// needs no locking. The loop exits when the parent context is cancelled.
+type supervisor struct {
+	ctx      context.Context
+	run      runFunc
+	cmdCh    chan lifecycleCmd
+	runEnded chan runEndResult
+
+	// owned exclusively by the loop goroutine. curStart is the in-flight start
+	// command (nil = idle); its done channel is notified when the run ends.
+	// curRun holds that run's lifecycle channels; runCancel cancels it.
+	curStart  *lifecycleCmd
+	curRun    *runState
+	runCancel context.CancelFunc
+}
+
+func newSupervisor(ctx context.Context, run runFunc) *supervisor {
+	s := &supervisor{
+		ctx:      ctx,
+		run:      run,
+		cmdCh:    make(chan lifecycleCmd, 16),
+		runEnded: make(chan runEndResult, 1),
+	}
+	go s.loop()
+	return s
+}
+
+func (s *supervisor) loop() {
+	for {
+		select {
+		case <-s.ctx.Done():
+			s.shutdown()
+			return
+		case cmd := <-s.cmdCh:
+			switch cmd.op {
+			case opStart:
+				s.handleStart(cmd)
+			case opStop:
+				s.handleStop(cmd)
+			case opRestart:
+				s.handleRestart(cmd)
+			case opStatus:
+				cmd.reply <- (s.isRunningInternal())
+			case opWaitEstablished:
+				s.handleWaitEstablished(cmd)
+			}
+		case res := <-s.runEnded:
+			// Run ended on its own, without an explicit Stop.
+			s.finishRun(res.err)
+		}
+	}
+}
+
+func (s *supervisor) handleStart(cmd lifecycleCmd) {
+	if s.isRunningInternal() {
+		notify(cmd.done, errAlreadyRunning)
+		return
+	}
+
+	runCtx, cancel := context.WithCancel(s.ctx)
+	if cmd.md != nil {
+		// Carry caller-supplied gRPC metadata (e.g. UI user-agent) into the run
+		// context so the engine's management/signal calls forward it. The cancel
+		// still drives runCtx (metadata wrapping preserves cancellation).
+		runCtx = metadata.NewOutgoingContext(runCtx, cmd.md)
+	}
+	s.runCancel = cancel
+	s.curStart = &cmd
+	s.curRun = &runState{connEstablishedChan: make(chan struct{}), ended: make(chan struct{})}
+
+	go func(ctx context.Context, cfg *profilemanager.Config, m MobileDependency, established chan struct{}, lp string) {
+		err := s.run(ctx, cfg, m, established, lp)
+		s.runEnded <- runEndResult{err: err}
+	}(runCtx, cmd.config, cmd.mobileDep, s.curRun.connEstablishedChan, cmd.logPath)
+}
+
+func (s *supervisor) handleStop(cmd lifecycleCmd) {
+	if !s.isRunningInternal() {
+		notify(cmd.done, nil)
+		return
+	}
+	s.stopCurrentRun()
+	notify(cmd.done, nil)
+}
+
+// handleRestart tears down any in-flight run and starts a fresh one in a single
+// loop turn. No other command can interleave between the stop and the start
+// (the loop is single-threaded), so the swap is atomic without relying on any
+// daemon-side lock — that is what an explicit restart (e.g. MDM config change)
+// needs to avoid a window where the client is observably stopped.
+func (s *supervisor) handleRestart(cmd lifecycleCmd) {
+	if s.isRunningInternal() {
+		s.stopCurrentRun()
+	}
+	s.handleStart(cmd)
+}
+
+// stopCurrentRun cancels the in-flight run and blocks the supervisor until it
+// has fully unwound, so the next action starts from a clean slate. The run
+// goroutine reports completion via runEnded. Caller must hold an in-flight run
+// (curStart != nil).
+func (s *supervisor) stopCurrentRun() {
+	s.runCancel()
+	res := <-s.runEnded
+	s.finishRun(res.err)
+}
+
+// finishRun resets lifecycle state after a run terminates and hands the run
+// error back to whoever asked to be notified of the start.
+func (s *supervisor) finishRun(err error) {
+	s.runCancel = nil
+	if s.isRunningInternal() {
+		// Publish the result to the broadcast channel before nil-ing curRun, so
+		// any opWaitEstablished goroutines blocked on ended observe err.
+		s.curRun.err = err
+		close(s.curRun.ended)
+		s.curRun = nil
+
+		notify(s.curStart.done, err)
+		s.curStart = nil
+	}
+}
+
+// handleWaitEstablished answers an opWaitEstablished request. The select itself
+// runs in a spawned goroutine on the run's channels so it never blocks the loop;
+// the loop only snapshots the in-flight run's channels (which it owns) here.
+func (s *supervisor) handleWaitEstablished(cmd lifecycleCmd) {
+	caller := cmd.done
+	if !s.isRunningInternal() {
+		notify(caller, errNoRunInFlight)
+		return
+	}
+	rs := s.curRun
+	established := rs.connEstablishedChan
+	ctx := cmd.waitCtx
+	go func() {
+		select {
+		case <-established:
+			notify(caller, nil)
+		case <-rs.ended:
+			if rs.err != nil {
+				notify(caller, rs.err)
+				return
+			}
+			notify(caller, errStoppedBeforeEstablished)
+		case <-ctx.Done():
+			notify(caller, ctx.Err())
+		}
+	}()
+}
+
+// shutdown tears down the in-flight run when the parent context is cancelled,
+// then fails any still-queued commands so their callers never hang.
+func (s *supervisor) shutdown() {
+	if s.runCancel != nil {
+		s.runCancel()
+		res := <-s.runEnded
+		s.finishRun(res.err)
+	}
+	for {
+		select {
+		case cmd := <-s.cmdCh:
+			notify(cmd.done, s.ctx.Err())
+		default:
+			return
+		}
+	}
+}
+
+// startAsync enqueues a start without blocking. If done is non-nil it receives
+// the run's end result (or errAlreadyRunning on rejection, or the context error
+// on shutdown).
+func (s *supervisor) startAsync(config *profilemanager.Config, md metadata.MD, mobileDep MobileDependency, logPath string, done chan error) {
+	cmd := lifecycleCmd{op: opStart, config: config, md: md, mobileDep: mobileDep, logPath: logPath, done: done}
+	select {
+	case s.cmdCh <- cmd:
+	case <-s.ctx.Done():
+		notify(done, s.ctx.Err())
+	}
+}
+
+// restartAsync enqueues an atomic stop+start without blocking. The supervisor
+// tears down any in-flight run and starts a fresh one with the supplied config
+// in a single loop turn (see handleRestart). Fire-and-forget: the new run owns
+// its lifecycle channels, observed via waitEstablishedOrDone.
+func (s *supervisor) restartAsync(config *profilemanager.Config, md metadata.MD, mobileDep MobileDependency, logPath string) {
+	cmd := lifecycleCmd{op: opRestart, config: config, md: md, mobileDep: mobileDep, logPath: logPath}
+	select {
+	case s.cmdCh <- cmd:
+	case <-s.ctx.Done():
+	}
+}
+
+// start enqueues a start and blocks until the run terminates, preserving the
+// blocking contract of the legacy Run entry points.
+func (s *supervisor) start(config *profilemanager.Config, md metadata.MD, mobileDep MobileDependency, logPath string) error {
+	done := make(chan error, 1)
+	s.startAsync(config, md, mobileDep, logPath, done)
+	select {
+	case err := <-done:
+		return err
+	case <-s.ctx.Done():
+		return s.ctx.Err()
+	}
+}
+
+// isRunning asks the loop whether a run is in flight. The query is serialized
+// with start/stop, so during a stop it waits for the teardown to settle and
+// then reports the final state — never a transient "half-stopped".
+func (s *supervisor) isRunning() bool {
+	reply := make(chan bool, 1)
+	select {
+	case s.cmdCh <- lifecycleCmd{op: opStatus, reply: reply}:
+	case <-s.ctx.Done():
+		return false
+	}
+	select {
+	case r := <-reply:
+		return r
+	case <-s.ctx.Done():
+		return false
+	}
+}
+
+func (s *supervisor) isRunningInternal() bool {
+	return s.curStart != nil
+}
+
+// waitEstablishedOrDone blocks until the in-flight run becomes established
+// (returns nil) or ends before that (returns the run error, or
+// errStoppedBeforeEstablished on a clean stop), or ctx is cancelled. Returns
+// errNoRunInFlight if no run is in flight. The wait is performed by a goroutine
+// spawned inside the loop (see handleWaitEstablished); the run's channels never
+// leave the supervisor.
+func (s *supervisor) waitEstablishedOrDone(ctx context.Context) error {
+	reply := make(chan error, 1)
+	select {
+	case s.cmdCh <- lifecycleCmd{op: opWaitEstablished, waitCtx: ctx, done: reply}:
+	case <-ctx.Done():
+		return ctx.Err()
+	case <-s.ctx.Done():
+		return s.ctx.Err()
+	}
+	select {
+	case err := <-reply:
+		return err
+	case <-s.ctx.Done():
+		return s.ctx.Err()
+	}
+}
+
+// stop enqueues a stop and blocks until the in-flight run is fully torn down.
+func (s *supervisor) stop() error {
+	done := make(chan error, 1)
+	select {
+	case s.cmdCh <- lifecycleCmd{op: opStop, done: done}:
+	case <-s.ctx.Done():
+		return s.ctx.Err()
+	}
+	select {
+	case err := <-done:
+		return err
+	case <-s.ctx.Done():
+		return s.ctx.Err()
+	}
+}
+
+// notify sends on a caller-supplied channel without blocking. The channel is
+// expected to be buffered (cap 1); a nil channel means the caller did not ask
+// to be notified.
+func notify(ch chan error, err error) {
+	if ch == nil {
+		return
+	}
+	select {
+	case ch <- err:
+	default:
+	}
+}

client/internal/debug/debug_test.go

@@ -843,6 +843,7 @@ func TestAddConfig_AllFieldsCovered(t *testing.T) {
 		"PreSharedKey":      "sensitive: WireGuard pre-shared key",
 		"SSHKey":            "sensitive: SSH private key",
 		"ClientCertKeyPair": "non-config: parsed cert pair, not serialized",
+		"Name":              "non-config: profile name is not needed for debug purposes",
 		"policy":            "non-config: in-memory MDM policy snapshot, surfaced via Config.Policy() / GetConfigResponse.MDMManagedFields",
 	}
 

client/internal/engine.go

@@ -22,6 +22,8 @@ import (
 	log "github.com/sirupsen/logrus"
 	"golang.zx2c4.com/wireguard/tun/netstack"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+	"google.golang.org/grpc/codes"
+	gstatus "google.golang.org/grpc/status"
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
 	"github.com/netbirdio/netbird/client/firewall"
@@ -1125,6 +1127,20 @@ func (e *Engine) hasIPv6Changed(conf *mgmProto.PeerConfig) bool {
 	return !current.HasIPv6() || current.IPv6 != prefix.Addr() || current.IPv6Net != prefix.Masked()
 }
 
+// wrapDisconnectError classifies a receive-loop failure before the run is torn
+// down. An auth rejection (PermissionDenied/Unauthenticated) means the session
+// needs re-login and retrying is futile, so mark it terminal (NeedsLogin) — run()
+// then exits on its own instead of spinning the backoff. Any other failure is a
+// recoverable connection reset that the backoff should retry.
+func (e *Engine) wrapDisconnectError(err error) {
+	state := CtxGetState(e.ctx)
+	if s, ok := gstatus.FromError(err); ok && (s.Code() == codes.PermissionDenied || s.Code() == codes.Unauthenticated) {
+		state.Set(StatusNeedsLogin)
+		return
+	}
+	_ = state.Wrap(ErrResetConnection)
+}
+
 func (e *Engine) receiveJobEvents() {
 	e.jobExecutorWG.Add(1)
 	go func() {
@@ -1151,9 +1167,9 @@ func (e *Engine) receiveJobEvents() {
 			}
 		})
 		if err != nil {
-			// happens if management is unavailable for a long time.
-			// We want to cancel the operation of the whole client
-			_ = CtxGetState(e.ctx).Wrap(ErrResetConnection)
+			// happens if management is unavailable for a long time, or rejects
+			// us (auth). wrapDisconnectError decides retry vs needs-login.
+			e.wrapDisconnectError(err)
 			e.clientCancel()
 			return
 		}
@@ -1235,9 +1251,9 @@ func (e *Engine) receiveManagementEvents() {
 
 		err = e.mgmClient.Sync(e.ctx, info, e.handleSync)
 		if err != nil {
-			// happens if management is unavailable for a long time.
-			// We want to cancel the operation of the whole client
-			_ = CtxGetState(e.ctx).Wrap(ErrResetConnection)
+			// happens if management is unavailable for a long time, or rejects
+			// us (auth). wrapDisconnectError decides retry vs needs-login.
+			e.wrapDisconnectError(err)
 			e.clientCancel()
 			return
 		}
@@ -1761,9 +1777,9 @@ func (e *Engine) receiveSignalEvents() {
 			return nil
 		})
 		if err != nil {
-			// happens if signal is unavailable for a long time.
-			// We want to cancel the operation of the whole client
-			_ = CtxGetState(e.ctx).Wrap(ErrResetConnection)
+			// happens if signal is unavailable for a long time, or rejects us
+			// (auth). wrapDisconnectError decides retry vs needs-login.
+			e.wrapDisconnectError(err)
 			e.clientCancel()
 			return
 		}

client/internal/profilemanager/config.go

@@ -108,6 +108,10 @@ type ConfigInput struct {
 
 // Config Configuration type
 type Config struct {
+	// Name is the human-readable profile name shown in CLI/UI listings.
+	// It is independent of the profile's on-disk filename (which is the ID).
+	Name string
+
 	// Wireguard private key of local peer
 	PrivateKey                    string
 	PreSharedKey                  string
@@ -270,6 +274,16 @@ func createNewConfig(input ConfigInput) (*Config, error) {
 }
 
 func (config *Config) apply(input ConfigInput) (updated bool, err error) {
+	if config.Name != "" {
+		sanitized, err := sanitizeDisplayName(config.Name)
+		if err != nil {
+			return false, fmt.Errorf("invalid profile name: %w", err)
+		}
+		if sanitized != config.Name {
+			config.Name = sanitized
+			updated = true
+		}
+	}
 	if config.ManagementURL == nil {
 		log.Infof("using default Management URL %s", DefaultManagementURL)
 		config.ManagementURL, err = parseURL("Management URL", DefaultManagementURL)

client/internal/profilemanager/id.go

@@ -0,0 +1,118 @@
+package profilemanager
+
+import (
+	"crypto/rand"
+	"encoding/hex"
+	"fmt"
+	"path/filepath"
+	"strings"
+	"unicode"
+	"unicode/utf8"
+)
+
+const (
+	// profileIDByteLen is the number of random bytes generated for a new
+	// profile ID. The resulting hex string is twice this length.
+	profileIDByteLen = 16
+
+	// shortIDLen is the number of leading characters of an ID we render in
+	// list output. Profiles per device are few, so 8 chars is collision-safe
+	// in practice and easy to type as a prefix.
+	shortIDLen = 8
+
+	// maxProfileNameLen caps the human-readable profile name to keep table
+	// output legible and prevent denial-of-service via huge JSON fields.
+	maxProfileNameLen = 128
+
+	// maxProfileIDLen bounds the on-disk filename we'll accept. New
+	// IDs are 32 hex chars, legacy stems are sanitized profile names. The
+	// cap is generous enough to cover both without permitting absurdly
+	// long filenames.
+	maxProfileIDLen = 64
+)
+
+type ID string
+
+// generateProfileID returns a new random hex ID for a profile file.
+func generateProfileID() (ID, error) {
+	buf := make([]byte, profileIDByteLen)
+	if _, err := rand.Read(buf); err != nil {
+		return "", fmt.Errorf("read random bytes: %w", err)
+	}
+	return ID(hex.EncodeToString(buf)), nil
+}
+
+// IsValidProfileFilenameStem reports whether id is safe to use as the stem
+// of a profile JSON filename.
+func IsValidProfileFilenameStem(id ID) bool {
+	s := id.String()
+	if s == "" || len(s) > maxProfileIDLen {
+		return false
+	}
+	if s == defaultProfileName {
+		return true
+	}
+	if strings.ContainsAny(s, `/\`) || strings.Contains(s, "..") {
+		return false
+	}
+	// filepath.Base catches any leftover separators on platforms with
+	// exotic path conventions.
+	if filepath.Base(s) != s {
+		return false
+	}
+	for _, r := range s {
+		if !(unicode.IsLetter(r) || unicode.IsDigit(r) || r == '_' || r == '-') {
+			return false
+		}
+	}
+	return true
+}
+
+// sanitizeDisplayName normalizes a user-supplied profile display name for
+// storage. It strips ASCII control characters, rejects invalid UTF-8, and
+// caps the length. Emojis, spaces, punctuation, and non-ASCII letters are
+// preserved. Returns an error if nothing usable remains.
+func sanitizeDisplayName(name string) (string, error) {
+	if !utf8.ValidString(name) {
+		return "", fmt.Errorf("name is not valid UTF-8")
+	}
+	name = StripCtrlChars(name)
+	name = strings.TrimSpace(name)
+	if name == "" {
+		return "", fmt.Errorf("name is empty after sanitization")
+	}
+	if utf8.RuneCountInString(name) > maxProfileNameLen {
+		return "", fmt.Errorf("name exceeds %d characters", maxProfileNameLen)
+	}
+	return name, nil
+}
+
+// StripCtrlChars control characters from a name before printing it.
+func StripCtrlChars(name string) string {
+	var b strings.Builder
+	b.Grow(len(name))
+	for _, r := range name {
+		// Skip C0 controls and DEL, plus C1 controls (0x80–0x9F).
+		if r < 0x20 || r == 0x7F || (r >= 0x80 && r <= 0x9F) {
+			continue
+		}
+		b.WriteRune(r)
+	}
+	return b.String()
+}
+
+// ShortID truncates an ID for display.
+func (id ID) ShortID() string {
+	if id == DefaultProfileName {
+		return DefaultProfileName
+	}
+	runes := []rune(id)
+	if len(runes) <= shortIDLen {
+		return id.String()
+	}
+	return string(runes[:shortIDLen])
+}
+
+func (id ID) String() string {
+	return string(id)
+}

client/internal/profilemanager/profilemanager.go

@@ -19,19 +19,41 @@ const (
 )
 
 type Profile struct {
-	Name     string
+	// ID is the on-disk filename stem (without .json). For new profiles
+	// it is a 32-char hex string; legacy profiles created before the
+	// ID-keyed layout keep their original name as their ID. The reserved
+	// value "default" identifies the special default profile.
+	ID ID
+	// Name is the human-readable display name. Falls back to ID when the
+	// underlying JSON has no "name" field set.
+	Name string
+	// Path is the absolute path to the profile JSON. Populated by the
+	// loader so callers do not have to reconstruct it from ID + dir.
+	Path     string
 	IsActive bool
 }
 
 func (p *Profile) FilePath() (string, error) {
-	if p.Name == "" {
-		return "", fmt.Errorf("active profile name is empty")
+	if p.Path != "" {
+		return p.Path, nil
 	}
 
-	if p.Name == defaultProfileName {
+	id := p.ID
+	if id == "" {
+		id = ID(p.Name)
+	}
+	if id == "" {
+		return "", fmt.Errorf("profile ID is empty")
+	}
+
+	if id == defaultProfileName {
 		return DefaultConfigPath, nil
 	}
 
+	if !IsValidProfileFilenameStem(id) {
+		return "", fmt.Errorf("invalid profile ID: %q", id)
+	}
+
 	username, err := user.Current()
 	if err != nil {
 		return "", fmt.Errorf("failed to get current user: %w", err)
@@ -42,10 +64,13 @@ func (p *Profile) FilePath() (string, error) {
 		return "", fmt.Errorf("failed to get config directory for user %s: %w", username.Username, err)
 	}
 
-	return filepath.Join(configDir, p.Name+".json"), nil
+	return filepath.Join(configDir, id.String()+".json"), nil
 }
 
 func (p *Profile) IsDefault() bool {
+	if p.ID != "" {
+		return p.ID == defaultProfileName
+	}
 	return p.Name == defaultProfileName
 }
 
@@ -57,18 +82,24 @@ func NewProfileManager() *ProfileManager {
 	return &ProfileManager{}
 }
 
+// GetActiveProfile returns the active profile as recorded in the local
+// user state file. Only ID is populated.
 func (pm *ProfileManager) GetActiveProfile() (*Profile, error) {
 	pm.mu.Lock()
 	defer pm.mu.Unlock()
 
-	prof := pm.getActiveProfileState()
-	return &Profile{Name: prof}, nil
+	id := pm.getActiveProfileState()
+	return &Profile{ID: id}, nil
 }
 
-func (pm *ProfileManager) SwitchProfile(profileName string) error {
-	profileName = sanitizeProfileName(profileName)
+// SwitchProfile records the given profile ID as active in the local user
+// state file.
+func (pm *ProfileManager) SwitchProfile(id ID) error {
+	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
+		return fmt.Errorf("invalid profile ID: %q", id)
+	}
 
-	if err := pm.setActiveProfileState(profileName); err != nil {
+	if err := pm.setActiveProfileState(id); err != nil {
 		return fmt.Errorf("failed to switch profile: %w", err)
 	}
 	return nil
@@ -85,7 +116,7 @@ func sanitizeProfileName(name string) string {
 	}, name)
 }
 
-func (pm *ProfileManager) getActiveProfileState() string {
+func (pm *ProfileManager) getActiveProfileState() ID {
 
 	configDir, err := getConfigDir()
 	if err != nil {
@@ -113,10 +144,10 @@ func (pm *ProfileManager) getActiveProfileState() string {
 		return defaultProfileName
 	}
 
-	return profileName
+	return ID(profileName)
 }
 
-func (pm *ProfileManager) setActiveProfileState(profileName string) error {
+func (pm *ProfileManager) setActiveProfileState(id ID) error {
 
 	configDir, err := getConfigDir()
 	if err != nil {
@@ -125,7 +156,7 @@ func (pm *ProfileManager) setActiveProfileState(profileName string) error {
 
 	statePath := filepath.Join(configDir, activeProfileStateFilename)
 
-	err = os.WriteFile(statePath, []byte(profileName), 0600)
+	err = os.WriteFile(statePath, []byte(id), 0600)
 	if err != nil {
 		return fmt.Errorf("failed to write active profile state: %w", err)
 	}
@@ -142,7 +173,7 @@ func GetLoginHint() string {
 		return ""
 	}
 
-	profileState, err := pm.GetProfileState(activeProf.Name)
+	profileState, err := pm.GetProfileState(activeProf.ID)
 	if err != nil {
 		log.Debugf("failed to get profile state for login hint: %v", err)
 		return ""

client/internal/profilemanager/profilemanager_test.go

@@ -50,14 +50,14 @@ func TestServiceManager_CreateAndGetDefaultProfile(t *testing.T) {
 
 			state, err := sm.GetActiveProfileState()
 			assert.NoError(t, err)
-			assert.Equal(t, state.Name, defaultProfileName) // No active profile state yet
+			assert.Equal(t, defaultProfileName, state.ID.String()) // No active profile state yet
 
 			err = sm.SetActiveProfileStateToDefault()
 			assert.NoError(t, err)
 
 			active, err := sm.GetActiveProfileState()
 			assert.NoError(t, err)
-			assert.Equal(t, "default", active.Name)
+			assert.Equal(t, "default", active.ID.String())
 		})
 	})
 }
@@ -92,14 +92,14 @@ func TestServiceManager_SetActiveProfileState(t *testing.T) {
 			currUser, err := user.Current()
 			assert.NoError(t, err)
 			sm := &ServiceManager{}
-			state := &ActiveProfileState{Name: "foo", Username: currUser.Username}
+			state := &ActiveProfileState{ID: "foo", Username: currUser.Username}
 			err = sm.SetActiveProfileState(state)
 			assert.NoError(t, err)
 
 			// Should error on nil or incomplete state
 			err = sm.SetActiveProfileState(nil)
 			assert.Error(t, err)
-			err = sm.SetActiveProfileState(&ActiveProfileState{Name: "", Username: ""})
+			err = sm.SetActiveProfileState(&ActiveProfileState{ID: "", Username: ""})
 			assert.Error(t, err)
 		})
 	})

client/internal/profilemanager/service.go

@@ -2,6 +2,7 @@ package profilemanager
 
 import (
 	"context"
+	"encoding/json"
 	"errors"
 	"fmt"
 	"io"
@@ -23,12 +24,43 @@ var (
 	DefaultConfigPathDir   = ""
 	DefaultConfigPath      = ""
 	ActiveProfileStatePath = ""
-)
 
-var (
 	ErrorOldDefaultConfigNotFound = errors.New("old default config not found")
 )
 
+// ErrAmbiguousHandle is returned when a profile handle (ID prefix or name)
+// matches more than one profile. Callers can render Candidates to help the
+// user disambiguate.
+type ErrAmbiguousHandle struct {
+	Handle     string
+	Candidates []Profile
+	Kind       AmbiguityKind
+}
+
+// AmbiguityKind describes which matcher produced the ambiguity, so callers
+// can tailor the error message.
+type AmbiguityKind int
+
+const (
+	AmbiguityKindIDPrefix AmbiguityKind = iota
+	AmbiguityKindName
+)
+
+// profileMeta is the minimal slice of a profile JSON we need, so we avoid
+// reading all fields
+type profileMeta struct {
+	Name string
+}
+
+func (e *ErrAmbiguousHandle) Error() string {
+	switch e.Kind {
+	case AmbiguityKindIDPrefix:
+		return fmt.Sprintf("ID prefix %q is ambiguous (matches %d profiles)", e.Handle, len(e.Candidates))
+	default:
+		return fmt.Sprintf("name %q is ambiguous (%d profiles share this name)", e.Handle, len(e.Candidates))
+	}
+}
+
 func init() {
 
 	DefaultConfigPathDir = "/var/lib/netbird/"
@@ -54,25 +86,34 @@ func init() {
 }
 
 type ActiveProfileState struct {
-	Name     string `json:"name"`
+	// ID is the on-disk filename stem of the active profile. The JSON tag stays
+	// as "name" for backwards compatibility with active state files written
+	// before the ID-based config files. Legacy values were profile names, which
+	// were also the legacy filename stems, so they still resolve to the correct
+	// file on disk.
+	ID       ID     `json:"name"`
 	Username string `json:"username"`
 }
 
 func (a *ActiveProfileState) FilePath() (string, error) {
-	if a.Name == "" {
-		return "", fmt.Errorf("active profile name is empty")
+	if a.ID == "" {
+		return "", fmt.Errorf("active profile ID is empty")
 	}
 
-	if a.Name == defaultProfileName {
+	if a.ID == defaultProfileName {
 		return DefaultConfigPath, nil
 	}
 
+	if !IsValidProfileFilenameStem(a.ID) {
+		return "", fmt.Errorf("invalid profile ID: %q", a.ID)
+	}
+
 	configDir, err := getConfigDirForUser(a.Username)
 	if err != nil {
 		return "", fmt.Errorf("failed to get config directory for user %s: %w", a.Username, err)
 	}
 
-	return filepath.Join(configDir, a.Name+".json"), nil
+	return filepath.Join(configDir, a.ID.String()+".json"), nil
 }
 
 type ServiceManager struct {
@@ -178,7 +219,7 @@ func (s *ServiceManager) GetActiveProfileState() (*ActiveProfileState, error) {
 				return nil, fmt.Errorf("failed to set active profile to default: %w", err)
 			}
 			return &ActiveProfileState{
-				Name:     "default",
+				ID:       defaultProfileName,
 				Username: "",
 			}, nil
 		} else {
@@ -186,12 +227,12 @@ func (s *ServiceManager) GetActiveProfileState() (*ActiveProfileState, error) {
 		}
 	}
 
-	if activeProfile.Name == "" {
+	if activeProfile.ID == "" {
 		if err := s.SetActiveProfileStateToDefault(); err != nil {
 			return nil, fmt.Errorf("failed to set active profile to default: %w", err)
 		}
 		return &ActiveProfileState{
-			Name:     "default",
+			ID:       defaultProfileName,
 			Username: "",
 		}, nil
 	}
@@ -216,25 +257,29 @@ func (s *ServiceManager) setDefaultActiveState() error {
 }
 
 func (s *ServiceManager) SetActiveProfileState(a *ActiveProfileState) error {
-	if a == nil || a.Name == "" {
+	if a == nil || a.ID == "" {
 		return errors.New("invalid active profile state")
 	}
 
-	if a.Name != defaultProfileName && a.Username == "" {
-		return fmt.Errorf("username must be set for non-default profiles, got: %s", a.Name)
+	if a.ID != defaultProfileName && a.Username == "" {
+		return fmt.Errorf("username must be set for non-default profiles, got: %s", a.ID)
+	}
+
+	if a.ID != defaultProfileName && !IsValidProfileFilenameStem(a.ID) {
+		return fmt.Errorf("invalid profile ID: %q", a.ID)
 	}
 
 	if err := util.WriteJsonWithRestrictedPermission(context.Background(), ActiveProfileStatePath, a); err != nil {
 		return fmt.Errorf("failed to write active profile state: %w", err)
 	}
 
-	log.Infof("active profile set to %s for %s", a.Name, a.Username)
+	log.Infof("active profile set to %s for %s", a.ID, a.Username)
 	return nil
 }
 
 func (s *ServiceManager) SetActiveProfileStateToDefault() error {
 	return s.SetActiveProfileState(&ActiveProfileState{
-		Name:     "default",
+		ID:       defaultProfileName,
 		Username: "",
 	})
 }
@@ -243,57 +288,117 @@ func (s *ServiceManager) DefaultProfilePath() string {
 	return DefaultConfigPath
 }
 
-func (s *ServiceManager) AddProfile(profileName, username string) error {
+// AddProfile creates a new profile with a generated ID. The user-supplied
+// displayName is stored inside the JSON's name field, the on-disk filename
+// uses the generated ID.
+//
+// The returned Profile carries the freshly-generated ID so callers can
+// show it to the user (and so the gRPC AddProfileResponse can include
+// it).
+func (s *ServiceManager) AddProfile(displayName, username string) (*Profile, error) {
 	configDir, err := s.getConfigDir(username)
 	if err != nil {
-		return fmt.Errorf("failed to get config directory: %w", err)
+		return nil, fmt.Errorf("failed to get config directory: %w", err)
 	}
 
-	profileName = sanitizeProfileName(profileName)
-
-	if profileName == defaultProfileName {
-		return fmt.Errorf("cannot create profile with reserved name: %s", defaultProfileName)
-	}
-
-	profPath := filepath.Join(configDir, profileName+".json")
-	profileExists, err := fileExists(profPath)
+	displayName, err = sanitizeDisplayName(displayName)
 	if err != nil {
-		return fmt.Errorf("failed to check if profile exists: %w", err)
-	}
-	if profileExists {
-		return ErrProfileAlreadyExists
+		return nil, fmt.Errorf("invalid profile name: %w", err)
 	}
 
+	id, err := generateProfileID()
+	if err != nil {
+		return nil, fmt.Errorf("generate profile id: %w", err)
+	}
+
+	profPath := filepath.Join(configDir, id.String()+".json")
 	cfg, err := createNewConfig(ConfigInput{ConfigPath: profPath})
 	if err != nil {
-		return fmt.Errorf("failed to create new config: %w", err)
+		return nil, fmt.Errorf("failed to create new config: %w", err)
+	}
+	cfg.Name = displayName
+
+	if err := util.WriteJson(context.Background(), profPath, cfg); err != nil {
+		return nil, fmt.Errorf("failed to write profile config: %w", err)
 	}
 
-	err = util.WriteJson(context.Background(), profPath, cfg)
+	return &Profile{
+		ID:   id,
+		Name: displayName,
+		Path: profPath,
+	}, nil
+}
+
+func (s *ServiceManager) RenameProfile(id ID, username string, newName string) error {
+	displayName, err := sanitizeDisplayName(newName)
 	if err != nil {
-		return fmt.Errorf("failed to write profile config: %w", err)
+		return fmt.Errorf("invalid profile name: %w", err)
 	}
 
+	if !IsValidProfileFilenameStem(id) {
+		return fmt.Errorf("invalid profile ID: %q", id)
+	}
+
+	profiles, err := s.loadAllProfiles(username)
+	if err != nil {
+		return fmt.Errorf("load profiles: %w", err)
+	}
+
+	var target *Profile
+	for i := range profiles {
+		if profiles[i].ID == id {
+			target = &profiles[i]
+			break
+		}
+	}
+	if target == nil {
+		return ErrProfileNotFound
+	}
+
+	data, err := os.ReadFile(target.Path)
+	if err != nil {
+		return err
+	}
+	var cfg Config
+	if err := json.Unmarshal(data, &cfg); err != nil {
+		return err
+	}
+	cfg.Name = displayName
+
+	if err := util.WriteJson(context.Background(), target.Path, cfg); err != nil {
+		return fmt.Errorf("failed to write profile name: %w", err)
+	}
 	return nil
 }
 
-func (s *ServiceManager) RemoveProfile(profileName, username string) error {
-	configDir, err := s.getConfigDir(username)
-	if err != nil {
-		return fmt.Errorf("failed to get config directory: %w", err)
+// RemoveProfile deletes the profile identified by id. Callers must have
+// already resolved any user-supplied handle to a concrete ID via
+// ResolveProfile.
+func (s *ServiceManager) RemoveProfile(id ID, username string) error {
+	if id == defaultProfileName {
+		defaultName := readProfileName(DefaultConfigPath)
+		if defaultName == "" {
+			defaultName = defaultProfileName
+		}
+		return fmt.Errorf("cannot remove default profile with name: %s", defaultName)
+	}
+	if !IsValidProfileFilenameStem(id) {
+		return fmt.Errorf("invalid profile ID: %q", id)
 	}
 
-	profileName = sanitizeProfileName(profileName)
-
-	if profileName == defaultProfileName {
-		return fmt.Errorf("cannot remove profile with reserved name: %s", defaultProfileName)
-	}
-	profPath := filepath.Join(configDir, profileName+".json")
-	profileExists, err := fileExists(profPath)
+	profiles, err := s.loadAllProfiles(username)
 	if err != nil {
-		return fmt.Errorf("failed to check if profile exists: %w", err)
+		return fmt.Errorf("load profiles: %w", err)
 	}
-	if !profileExists {
+
+	var target *Profile
+	for i := range profiles {
+		if profiles[i].ID == id {
+			target = &profiles[i]
+			break
+		}
+	}
+	if target == nil {
 		return ErrProfileNotFound
 	}
 
@@ -301,57 +406,26 @@ func (s *ServiceManager) RemoveProfile(profileName, username string) error {
 	if err != nil && !errors.Is(err, ErrNoActiveProfile) {
 		return fmt.Errorf("failed to get active profile: %w", err)
 	}
-
-	if activeProf != nil && activeProf.Name == profileName {
-		return fmt.Errorf("cannot remove active profile: %s", profileName)
+	if activeProf != nil && activeProf.ID == id {
+		return fmt.Errorf("cannot remove active profile: %s", id)
 	}
 
-	err = util.RemoveJson(profPath)
-	if err != nil {
+	if err := util.RemoveJson(target.Path); err != nil {
 		return fmt.Errorf("failed to remove profile config: %w", err)
 	}
+
+	stateFile := filepath.Join(filepath.Dir(target.Path), id.String()+".state.json")
+	if err := os.Remove(stateFile); err != nil && !os.IsNotExist(err) {
+		log.Warnf("failed to remove profile state file %s: %v", stateFile, err)
+	}
+
 	return nil
 }
 
+// ListProfiles returns every profile for the given user, including the
+// default profile, with IsActive flags set.
 func (s *ServiceManager) ListProfiles(username string) ([]Profile, error) {
-	configDir, err := s.getConfigDir(username)
-	if err != nil {
-		return nil, fmt.Errorf("failed to get config directory: %w", err)
-	}
-
-	files, err := util.ListFiles(configDir, "*.json")
-	if err != nil {
-		return nil, fmt.Errorf("failed to list profile files: %w", err)
-	}
-
-	var filtered []string
-	for _, file := range files {
-		if strings.HasSuffix(file, "state.json") {
-			continue // skip state files
-		}
-		filtered = append(filtered, file)
-	}
-	sort.Strings(filtered)
-
-	var activeProfName string
-	activeProf, err := s.GetActiveProfileState()
-	if err == nil {
-		activeProfName = activeProf.Name
-	}
-
-	var profiles []Profile
-	// add default profile always
-	profiles = append(profiles, Profile{Name: defaultProfileName, IsActive: activeProfName == "" || activeProfName == defaultProfileName})
-	for _, file := range filtered {
-		profileName := strings.TrimSuffix(filepath.Base(file), ".json")
-		var isActive bool
-		if activeProfName != "" && activeProfName == profileName {
-			isActive = true
-		}
-		profiles = append(profiles, Profile{Name: profileName, IsActive: isActive})
-	}
-
-	return profiles, nil
+	return s.loadAllProfiles(username)
 }
 
 // GetStatePath returns the path to the state file based on the operating system
@@ -369,7 +443,12 @@ func (s *ServiceManager) GetStatePath() string {
 		return defaultStatePath
 	}
 
-	if activeProf.Name == defaultProfileName {
+	if activeProf.ID == defaultProfileName {
+		return defaultStatePath
+	}
+
+	if !IsValidProfileFilenameStem(activeProf.ID) {
+		log.Warnf("invalid active profile ID %q, using default state path", activeProf.ID)
 		return defaultStatePath
 	}
 
@@ -379,7 +458,7 @@ func (s *ServiceManager) GetStatePath() string {
 		return defaultStatePath
 	}
 
-	return filepath.Join(configDir, activeProf.Name+".state.json")
+	return filepath.Join(configDir, activeProf.ID.String()+".state.json")
 }
 
 // getConfigDir returns the profiles directory, using profilesDir if set, otherwise getConfigDirForUser
@@ -390,3 +469,169 @@ func (s *ServiceManager) getConfigDir(username string) (string, error) {
 
 	return getConfigDirForUser(username)
 }
+
+// loadAllProfiles returns every profile visible to the daemon for the
+// given user, including the default profile. The returned slice is sorted
+// by ID for a stable display order.
+//
+// Each Profile is fully populated: ID is the filename stem, Name comes
+// from the JSON's "name" field (falling back to the filename stem when absent)
+// and Path is built from a basename read off disk.
+func (s *ServiceManager) loadAllProfiles(username string) ([]Profile, error) {
+	activeID, activeIsDefault := s.activeProfileID()
+	defaultName := readProfileName(DefaultConfigPath)
+	if defaultName == "" {
+		defaultName = defaultProfileName
+	}
+
+	profiles := []Profile{{
+		ID:       defaultProfileName,
+		Name:     defaultName,
+		Path:     DefaultConfigPath,
+		IsActive: activeIsDefault,
+	}}
+
+	configDir, err := s.getConfigDir(username)
+	if err != nil {
+		return nil, fmt.Errorf("get config directory: %w", err)
+	}
+
+	entries, err := os.ReadDir(configDir)
+	if err != nil {
+		if errors.Is(err, os.ErrNotExist) {
+			return profiles, nil
+		}
+		return nil, fmt.Errorf("read profile directory: %w", err)
+	}
+
+	var fileProfiles []Profile
+	for _, entry := range entries {
+		if entry.IsDir() {
+			continue
+		}
+		base := entry.Name()
+		if !strings.HasSuffix(base, ".json") {
+			continue
+		}
+		if strings.HasSuffix(base, ".state.json") {
+			continue
+		}
+		stem := ID(strings.TrimSuffix(base, ".json"))
+		if stem == defaultProfileName {
+			// default lives at the top-level config dir, not under /<user>
+			continue
+		}
+		if !IsValidProfileFilenameStem(ID(stem)) {
+			continue
+		}
+		path := filepath.Join(configDir, base)
+		name := readProfileName(path)
+		if name == "" {
+			name = stem.String()
+		}
+		fileProfiles = append(fileProfiles, Profile{
+			ID:       stem,
+			Name:     name,
+			Path:     path,
+			IsActive: stem == ID(activeID),
+		})
+	}
+
+	sort.Slice(fileProfiles, func(i, j int) bool {
+		if fileProfiles[i].Name != fileProfiles[j].Name {
+			return fileProfiles[i].Name < fileProfiles[j].Name
+		}
+		// Sort tie-break on ID so duplicate names always render in the same order.
+		return fileProfiles[i].ID < fileProfiles[j].ID
+	})
+	profiles = append(profiles, fileProfiles...)
+	return profiles, nil
+}
+
+// readProfileName parses just the "name" field from the profile Json.
+func readProfileName(path string) string {
+	data, err := os.ReadFile(path)
+	if err != nil {
+		return ""
+	}
+	var meta profileMeta
+	if err := json.Unmarshal(data, &meta); err != nil {
+		return ""
+	}
+	return meta.Name
+}
+
+// activeProfileID returns the currently-active profile's ID. The second
+// return value is true when the active profile is the default one.
+func (s *ServiceManager) activeProfileID() (ID, bool) {
+	state, err := s.GetActiveProfileState()
+	if err != nil || state == nil {
+		return defaultProfileName, true
+	}
+	if state.ID == "" || state.ID == defaultProfileName {
+		return defaultProfileName, true
+	}
+	return state.ID, false
+}
+
+// ResolveProfile turns a user-supplied handle into a Profile. Resolution
+// precedence is: exact ID match, then unique exact name, then unique ID
+// prefix. Ambiguous matches return *ErrAmbiguousHandle so callers can
+// surface the candidates.
+func (s *ServiceManager) ResolveProfile(handle, username string) (*Profile, error) {
+	if handle == "" {
+		return nil, fmt.Errorf("profile handle is empty")
+	}
+
+	profiles, err := s.loadAllProfiles(username)
+	if err != nil {
+		return nil, err
+	}
+
+	for i := range profiles {
+		if profiles[i].ID == ID(handle) {
+			return &profiles[i], nil
+		}
+	}
+
+	var nameMatches []Profile
+	for i := range profiles {
+		if profiles[i].Name == handle {
+			nameMatches = append(nameMatches, profiles[i])
+		}
+	}
+	if len(nameMatches) == 1 {
+		return &nameMatches[0], nil
+	}
+	if len(nameMatches) > 1 {
+		return nil, &ErrAmbiguousHandle{
+			Handle:     handle,
+			Candidates: nameMatches,
+			Kind:       AmbiguityKindName,
+		}
+	}
+
+	// ID prefix match. Skip the default profile so `select d` does not
+	// accidentally pick it via prefix.
+	var prefixMatches []Profile
+	for i := range profiles {
+		if profiles[i].ID == defaultProfileName {
+			continue
+		}
+		if strings.HasPrefix(profiles[i].ID.String(), handle) {
+			prefixMatches = append(prefixMatches, profiles[i])
+		}
+	}
+	if len(prefixMatches) == 1 {
+		return &prefixMatches[0], nil
+	}
+	if len(prefixMatches) > 1 {
+		return nil, &ErrAmbiguousHandle{
+			Handle:     handle,
+			Candidates: prefixMatches,
+			Kind:       AmbiguityKindIDPrefix,
+		}
+	}
+
+	return nil, ErrProfileNotFound
+}

client/internal/profilemanager/service_test.go

@@ -0,0 +1,230 @@
+package profilemanager
+
+import (
+	"context"
+	"errors"
+	"os"
+	"os/user"
+	"path/filepath"
+	"strings"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+
+	"github.com/netbirdio/netbird/util"
+)
+
+// withTestSM wires up patched globals + a clean config dir and returns a
+// fully initialized ServiceManager plus the username we are scoped to.
+func withTestSM(t *testing.T, fn func(sm *ServiceManager, username string)) {
+	t.Helper()
+	withTempConfigDir(t, func(configDir string) {
+		withPatchedGlobals(t, configDir, func() {
+			u, err := user.Current()
+			require.NoError(t, err)
+			sm := &ServiceManager{}
+			require.NoError(t, sm.CreateDefaultProfile())
+			fn(sm, u.Username)
+		})
+	})
+}
+
+func TestServiceProfile_ExactID(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		got, err := sm.ResolveProfile(created.ID.String(), username)
+		require.NoError(t, err)
+		assert.Equal(t, created.ID, got.ID)
+		assert.Equal(t, "work", got.Name)
+	})
+}
+
+func TestServiceProfile_IDPrefix(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		prefix := created.ID[:4]
+		got, err := sm.ResolveProfile(prefix.String(), username)
+		require.NoError(t, err)
+		assert.Equal(t, created.ID, got.ID)
+	})
+}
+
+func TestServiceProfile_AmbiguousPrefix(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		// Plant two profiles whose IDs share a known prefix by writing
+		// the files directly, since generated IDs are random.
+		configDir, err := sm.getConfigDir(username)
+		require.NoError(t, err)
+		for _, id := range []string{"abcd1111aaaa", "abcd2222bbbb"} {
+			path := filepath.Join(configDir, id+".json")
+			require.NoError(t, util.WriteJson(context.Background(), path, &Config{Name: id}))
+		}
+
+		_, err = sm.ResolveProfile("abcd", username)
+		var amb *ErrAmbiguousHandle
+		require.ErrorAs(t, err, &amb)
+		assert.Equal(t, AmbiguityKindIDPrefix, amb.Kind)
+		assert.Len(t, amb.Candidates, 2)
+	})
+}
+
+func TestServiceProfile_ExactNameUnique(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		_, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		got, err := sm.ResolveProfile("work", username)
+		require.NoError(t, err)
+		assert.Equal(t, "work", got.Name)
+	})
+}
+
+func TestServiceProfile_AmbiguousName(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		_, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+		_, err = sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		_, err = sm.ResolveProfile("work", username)
+		var amb *ErrAmbiguousHandle
+		require.ErrorAs(t, err, &amb)
+		assert.Equal(t, AmbiguityKindName, amb.Kind)
+		assert.Len(t, amb.Candidates, 2)
+	})
+}
+
+func TestServiceProfile_NotFound(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		_, err := sm.ResolveProfile("nope", username)
+		assert.ErrorIs(t, err, ErrProfileNotFound)
+	})
+}
+
+func TestServiceProfile_DefaultByExactID(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		got, err := sm.ResolveProfile(defaultProfileName, username)
+		require.NoError(t, err)
+		assert.Equal(t, defaultProfileName, got.ID.String())
+	})
+}
+
+func TestServiceProfile_LegacyFilenameCoexists(t *testing.T) {
+	// Legacy profiles stored as <name>.json with no "name" JSON field
+	// should still be discoverable by name and removable by name.
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		configDir, err := sm.getConfigDir(username)
+		require.NoError(t, err)
+		path := filepath.Join(configDir, "legacy.json")
+		require.NoError(t, util.WriteJson(context.Background(), path, &Config{}))
+
+		got, err := sm.ResolveProfile("legacy", username)
+		require.NoError(t, err)
+		assert.Equal(t, "legacy", got.ID.String())
+		// Name falls back to the filename stem when JSON omits it.
+		assert.Equal(t, "legacy", got.Name)
+	})
+}
+
+func TestAddProfile_AllowsDuplicateWithFlag(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		first, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		second, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+		assert.NotEqual(t, first.ID, second.ID)
+		assert.Equal(t, "work", second.Name)
+	})
+}
+
+func TestAddProfile_RejectsInvalidNames(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		cases := []string{
+			"",                                       // empty
+			"\x00\x01",                               // only control chars (becomes empty)
+			strings.Repeat("a", maxProfileNameLen+1), // too long
+		}
+		for _, name := range cases {
+			_, err := sm.AddProfile(name, username)
+			assert.Error(t, err, "expected error for %q", name)
+		}
+	})
+}
+
+func TestRemoveProfile_RejectsInvalidID(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		err := sm.RemoveProfile("../escape", username)
+		assert.Error(t, err)
+	})
+}
+
+func TestSanitizeDisplayName(t *testing.T) {
+	cases := []struct {
+		in      string
+		want    string
+		wantErr bool
+	}{
+		{"work", "work", false},
+		{"My Work Account", "My Work Account", false},
+		{"emoji 🚀 ok", "emoji 🚀 ok", false},
+		{"漢字テスト", "漢字テスト", false},
+		{"with\x00null", "withnull", false},
+		{"\x01\x02\x03", "", true},
+		{"", "", true},
+	}
+	for _, tc := range cases {
+		got, err := sanitizeDisplayName(tc.in)
+		if tc.wantErr {
+			assert.Error(t, err, "case %q", tc.in)
+			continue
+		}
+		assert.NoError(t, err, "case %q", tc.in)
+		assert.Equal(t, tc.want, got, "case %q", tc.in)
+	}
+}
+
+func TestIsValidProfileFilenameStem(t *testing.T) {
+	cases := []struct {
+		in   string
+		want bool
+	}{
+		{"default", true},
+		{"abc123def456", true},
+		{"legacy-name", true},
+		{"legacy_name", true},
+		{"", false},
+		{"..", false},
+		{"../etc", false},
+		{"foo/bar", false},
+		{`foo\bar`, false},
+		{"with space", false},
+		{"with.dot", false},
+		{strings.Repeat("a", maxProfileIDLen+1), false},
+	}
+	for _, tc := range cases {
+		got := IsValidProfileFilenameStem(ID(tc.in))
+		assert.Equal(t, tc.want, got, "case %q", tc.in)
+	}
+}
+
+func TestRemoveProfile_DeletesStateFile(t *testing.T) {
+	withTestSM(t, func(sm *ServiceManager, username string) {
+		created, err := sm.AddProfile("work", username)
+		require.NoError(t, err)
+
+		configDir, err := sm.getConfigDir(username)
+		require.NoError(t, err)
+		statePath := filepath.Join(configDir, created.ID.String()+".state.json")
+		require.NoError(t, os.WriteFile(statePath, []byte(`{"email":"a@b"}`), 0600))
+
+		require.NoError(t, sm.RemoveProfile(created.ID, username))
+		_, err = os.Stat(statePath)
+		assert.True(t, errors.Is(err, os.ErrNotExist), "state file should be removed")
+	})
+}

client/internal/profilemanager/state.go

@@ -13,13 +13,20 @@ type ProfileState struct {
 	Email string `json:"email"`
 }
 
-func (pm *ProfileManager) GetProfileState(profileName string) (*ProfileState, error) {
+// GetProfileState reads the per-profile state file keyed by profile ID.
+// The state file lives in the user's config directory. Legacy state files
+// keyed by the old profile name remain readable.
+func (pm *ProfileManager) GetProfileState(id ID) (*ProfileState, error) {
 	configDir, err := getConfigDir()
 	if err != nil {
 		return nil, fmt.Errorf("get config directory: %w", err)
 	}
 
-	stateFile := filepath.Join(configDir, profileName+".state.json")
+	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
+		return nil, fmt.Errorf("invalid profile ID: %q", id)
+	}
+
+	stateFile := filepath.Join(configDir, id.String()+".state.json")
 	stateFileExists, err := fileExists(stateFile)
 	if err != nil {
 		return nil, fmt.Errorf("failed to check if profile state file exists: %w", err)
@@ -51,7 +58,12 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 		return fmt.Errorf("get active profile: %w", err)
 	}
 
-	stateFile := filepath.Join(configDir, activeProf.Name+".state.json")
+	id := activeProf.ID
+	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
+		return fmt.Errorf("invalid active profile ID: %q", id)
+	}
+
+	stateFile := filepath.Join(configDir, id.String()+".state.json")
 	err = util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state)
 	if err != nil {
 		return fmt.Errorf("write profile state: %w", err)

client/ios/NetBirdSDK/client.go

@@ -171,13 +171,13 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	c.onHostDnsFn = func([]string) {}
 	cfg.WgIface = interfaceName
 
-	connectClient := internal.NewConnectClient(ctx, cfg, c.recorder)
+	connectClient := internal.NewConnectClient(ctx, c.recorder)
 	c.setState(cfg, connectClient)
 	// Persist the latest sync response so DebugBundle can include the network
 	// map. On iOS this is backed by disk to keep it out of the constrained
 	// process memory (see the syncstore package).
 	connectClient.SetSyncResponsePersistence(true)
-	return connectClient.RunOniOS(fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
+	return connectClient.RunOniOS(cfg, fd, c.networkChangeListener, c.dnsManager, c.stateFile, c.cacheDir, c.logFilePath)
 }
 
 // Stop the internal client and free the resources

client/proto/daemon.proto

@@ -85,6 +85,8 @@ service DaemonService {
 
   rpc AddProfile(AddProfileRequest) returns (AddProfileResponse) {}
 
+  rpc RenameProfile(RenameProfileRequest) returns (RenameProfileResponse) {}
+
   rpc RemoveProfile(RemoveProfileRequest) returns (RemoveProfileResponse) {}
 
   rpc ListProfiles(ListProfilesRequest) returns (ListProfilesResponse) {}
@@ -625,11 +627,18 @@ message GetEventsResponse {
 }
 
 message SwitchProfileRequest {
+  // profileName is treated as a handle: exact ID, unique ID prefix, or
+  // unique display name. The daemon resolves it server-side.
   optional string profileName = 1;
   optional string username = 2;
 }
 
-message SwitchProfileResponse {}
+message SwitchProfileResponse {
+  // id is the resolved on-disk ID of the profile that became active.
+  // Lets CLI clients update their local active-profile state without
+  // duplicating the resolution logic.
+  string id = 1;
+}
 
 message SetConfigRequest {
   string username = 1;
@@ -696,17 +705,42 @@ message SetConfigResponse{}
 
 message AddProfileRequest {
   string username = 1;
+  // profileName carries the human-readable display name for the new
+  // profile. The on-disk filename is a separately-generated ID.
   string profileName = 2;
 }
 
-message AddProfileResponse {}
+message AddProfileResponse {
+  // id is the generated on-disk ID of the new profile. CLI clients
+  // display a truncated form, UI clients can ignore it.
+  string id = 1;
+}
+
+message RenameProfileRequest {
+  string username = 1;
+  // handle: an exact ID, a unique ID prefix, or a unique display name.
+  string handle = 2;
+  // newProfileName is the new human-readable display name for the profile.
+  string newProfileName = 3;
+}
+
+message RenameProfileResponse {
+  // confirm the old profile name after resolving handle.
+  string oldProfileName = 1;
+}
 
 message RemoveProfileRequest {
   string username = 1;
+  // profileName is treated as a handle: an exact ID, a unique ID
+  // prefix, or a unique display name. Resolution happens server-side.
   string profileName = 2;
 }
 
-message RemoveProfileResponse {}
+message RemoveProfileResponse {
+  // id is the full resolved ID of the removed profile, so callers can
+  // confirm exactly which profile a name/prefix handle resolved to.
+  string id = 1;
+}
 
 message ListProfilesRequest {
   string username = 1;
@@ -719,6 +753,7 @@ message ListProfilesResponse {
 message Profile {
   string name = 1;
   bool is_active = 2;
+  string id = 3;
 }
 
 message GetActiveProfileRequest {}
@@ -726,6 +761,7 @@ message GetActiveProfileRequest {}
 message GetActiveProfileResponse {
   string profileName = 1;
   string username = 2;
+  string id = 3;
 }
 
 message LogoutRequest {

client/proto/daemon_grpc.pb.go

@@ -45,6 +45,7 @@ const (
 	DaemonService_SwitchProfile_FullMethodName              = "/daemon.DaemonService/SwitchProfile"
 	DaemonService_SetConfig_FullMethodName                  = "/daemon.DaemonService/SetConfig"
 	DaemonService_AddProfile_FullMethodName                 = "/daemon.DaemonService/AddProfile"
+	DaemonService_RenameProfile_FullMethodName              = "/daemon.DaemonService/RenameProfile"
 	DaemonService_RemoveProfile_FullMethodName              = "/daemon.DaemonService/RemoveProfile"
 	DaemonService_ListProfiles_FullMethodName               = "/daemon.DaemonService/ListProfiles"
 	DaemonService_GetActiveProfile_FullMethodName           = "/daemon.DaemonService/GetActiveProfile"
@@ -112,6 +113,7 @@ type DaemonServiceClient interface {
 	SwitchProfile(ctx context.Context, in *SwitchProfileRequest, opts ...grpc.CallOption) (*SwitchProfileResponse, error)
 	SetConfig(ctx context.Context, in *SetConfigRequest, opts ...grpc.CallOption) (*SetConfigResponse, error)
 	AddProfile(ctx context.Context, in *AddProfileRequest, opts ...grpc.CallOption) (*AddProfileResponse, error)
+	RenameProfile(ctx context.Context, in *RenameProfileRequest, opts ...grpc.CallOption) (*RenameProfileResponse, error)
 	RemoveProfile(ctx context.Context, in *RemoveProfileRequest, opts ...grpc.CallOption) (*RemoveProfileResponse, error)
 	ListProfiles(ctx context.Context, in *ListProfilesRequest, opts ...grpc.CallOption) (*ListProfilesResponse, error)
 	GetActiveProfile(ctx context.Context, in *GetActiveProfileRequest, opts ...grpc.CallOption) (*GetActiveProfileResponse, error)
@@ -422,6 +424,16 @@ func (c *daemonServiceClient) AddProfile(ctx context.Context, in *AddProfileRequ
 	return out, nil
 }
 
+func (c *daemonServiceClient) RenameProfile(ctx context.Context, in *RenameProfileRequest, opts ...grpc.CallOption) (*RenameProfileResponse, error) {
+	cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
+	out := new(RenameProfileResponse)
+	err := c.cc.Invoke(ctx, DaemonService_RenameProfile_FullMethodName, in, out, cOpts...)
+	if err != nil {
+		return nil, err
+	}
+	return out, nil
+}
+
 func (c *daemonServiceClient) RemoveProfile(ctx context.Context, in *RemoveProfileRequest, opts ...grpc.CallOption) (*RemoveProfileResponse, error) {
 	cOpts := append([]grpc.CallOption{grpc.StaticMethod()}, opts...)
 	out := new(RemoveProfileResponse)
@@ -613,6 +625,7 @@ type DaemonServiceServer interface {
 	SwitchProfile(context.Context, *SwitchProfileRequest) (*SwitchProfileResponse, error)
 	SetConfig(context.Context, *SetConfigRequest) (*SetConfigResponse, error)
 	AddProfile(context.Context, *AddProfileRequest) (*AddProfileResponse, error)
+	RenameProfile(context.Context, *RenameProfileRequest) (*RenameProfileResponse, error)
 	RemoveProfile(context.Context, *RemoveProfileRequest) (*RemoveProfileResponse, error)
 	ListProfiles(context.Context, *ListProfilesRequest) (*ListProfilesResponse, error)
 	GetActiveProfile(context.Context, *GetActiveProfileRequest) (*GetActiveProfileResponse, error)
@@ -723,6 +736,9 @@ func (UnimplementedDaemonServiceServer) SetConfig(context.Context, *SetConfigReq
 func (UnimplementedDaemonServiceServer) AddProfile(context.Context, *AddProfileRequest) (*AddProfileResponse, error) {
 	return nil, status.Error(codes.Unimplemented, "method AddProfile not implemented")
 }
+func (UnimplementedDaemonServiceServer) RenameProfile(context.Context, *RenameProfileRequest) (*RenameProfileResponse, error) {
+	return nil, status.Error(codes.Unimplemented, "method RenameProfile not implemented")
+}
 func (UnimplementedDaemonServiceServer) RemoveProfile(context.Context, *RemoveProfileRequest) (*RemoveProfileResponse, error) {
 	return nil, status.Error(codes.Unimplemented, "method RemoveProfile not implemented")
 }
@@ -1237,6 +1253,24 @@ func _DaemonService_AddProfile_Handler(srv interface{}, ctx context.Context, dec
 	return interceptor(ctx, in, info, handler)
 }
 
+func _DaemonService_RenameProfile_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
+	in := new(RenameProfileRequest)
+	if err := dec(in); err != nil {
+		return nil, err
+	}
+	if interceptor == nil {
+		return srv.(DaemonServiceServer).RenameProfile(ctx, in)
+	}
+	info := &grpc.UnaryServerInfo{
+		Server:     srv,
+		FullMethod: DaemonService_RenameProfile_FullMethodName,
+	}
+	handler := func(ctx context.Context, req interface{}) (interface{}, error) {
+		return srv.(DaemonServiceServer).RenameProfile(ctx, req.(*RenameProfileRequest))
+	}
+	return interceptor(ctx, in, info, handler)
+}
+
 func _DaemonService_RemoveProfile_Handler(srv interface{}, ctx context.Context, dec func(interface{}) error, interceptor grpc.UnaryServerInterceptor) (interface{}, error) {
 	in := new(RemoveProfileRequest)
 	if err := dec(in); err != nil {
@@ -1567,6 +1601,10 @@ var DaemonService_ServiceDesc = grpc.ServiceDesc{
 			MethodName: "AddProfile",
 			Handler:    _DaemonService_AddProfile_Handler,
 		},
+		{
+			MethodName: "RenameProfile",
+			Handler:    _DaemonService_RenameProfile_Handler,
+		},
 		{
 			MethodName: "RemoveProfile",
 			Handler:    _DaemonService_RemoveProfile_Handler,

client/server/capture.go

@@ -344,9 +344,6 @@ func (s *Server) clearCaptureIfOwner(sess *capture.Session, engine *internal.Eng
 }
 
 func (s *Server) getCaptureEngineLocked() (*internal.Engine, error) {
-	if s.connectClient == nil {
-		return nil, status.Error(codes.FailedPrecondition, "client not connected")
-	}
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return nil, status.Error(codes.FailedPrecondition, "engine not initialized")

client/server/debug.go

@@ -5,7 +5,6 @@ package server
 import (
 	"bytes"
 	"context"
-	"errors"
 	"fmt"
 	"runtime/pprof"
 
@@ -28,11 +27,9 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 	}
 
 	var clientMetrics debug.MetricsExporter
-	if s.connectClient != nil {
-		if engine := s.connectClient.Engine(); engine != nil {
-			if cm := engine.GetClientMetrics(); cm != nil {
-				clientMetrics = cm
-			}
+	if engine := s.connectClient.Engine(); engine != nil {
+		if cm := engine.GetClientMetrics(); cm != nil {
+			clientMetrics = cm
 		}
 	}
 
@@ -48,13 +45,10 @@ func (s *Server) DebugBundle(_ context.Context, req *proto.DebugBundleRequest) (
 	defer s.cleanupBundleCapture()
 
 	var refreshStatus func()
-	if s.connectClient != nil {
-		engine := s.connectClient.Engine()
-		if engine != nil {
-			refreshStatus = func() {
-				log.Debug("refreshing system health status for debug bundle")
-				engine.RunHealthProbes(true)
-			}
+	if engine := s.connectClient.Engine(); engine != nil {
+		refreshStatus = func() {
+			log.Debug("refreshing system health status for debug bundle")
+			engine.RunHealthProbes(true)
 		}
 	}
 
@@ -118,9 +112,7 @@ func (s *Server) SetLogLevel(_ context.Context, req *proto.SetLogLevelRequest) (
 
 	log.SetLevel(level)
 
-	if s.connectClient != nil {
-		s.connectClient.SetLogLevel(level)
-	}
+	s.connectClient.SetLogLevel(level)
 
 	log.Infof("Log level set to %s", level.String())
 
@@ -134,20 +126,13 @@ func (s *Server) SetSyncResponsePersistence(_ context.Context, req *proto.SetSyn
 
 	enabled := req.GetEnabled()
 	s.persistSyncResponse = enabled
-	if s.connectClient != nil {
-		s.connectClient.SetSyncResponsePersistence(enabled)
-	}
+	s.connectClient.SetSyncResponsePersistence(enabled)
 
 	return &proto.SetSyncResponsePersistenceResponse{}, nil
 }
 
 func (s *Server) getLatestSyncResponse() (*mgmProto.SyncResponse, error) {
-	cClient := s.connectClient
-	if cClient == nil {
-		return nil, errors.New("connect client is not initialized")
-	}
-
-	return cClient.GetLatestSyncResponse()
+	return s.connectClient.GetLatestSyncResponse()
 }
 
 // StartCPUProfile starts CPU profiling in the daemon.

client/server/login_overrides_test.go

@@ -79,7 +79,7 @@ func TestPersistLoginOverrides(t *testing.T) {
 			_, err := profilemanager.UpdateOrCreateConfig(seed)
 			require.NoError(t, err, "seed config")
 
-			activeProf := &profilemanager.ActiveProfileState{Name: "default"}
+			activeProf := &profilemanager.ActiveProfileState{ID: "default"}
 			err = persistLoginOverrides(activeProf, tt.newMgmtURL, tt.newPSK)
 			require.NoError(t, err, "persistLoginOverrides")
 

client/server/mdm.go

@@ -3,7 +3,6 @@ package server
 import (
 	"context"
 	"fmt"
-	"time"
 
 	log "github.com/sirupsen/logrus"
 	"google.golang.org/grpc/codes"
@@ -39,12 +38,11 @@ type conflictCheck struct {
 // OS-native managed-config store reports a diff vs the last observation.
 //
 // Restart sequence:
-//  1. Cancel the active engine context (terminates connectWithRetryRuns).
-//  2. Wait briefly for that goroutine to exit (giveUpChan is closed on exit).
-//  3. Re-resolve Config from disk + MDM policy (Config.apply re-runs
+//  1. Stop the in-flight run via the supervisor (blocks until fully torn down).
+//  2. Re-resolve Config from disk + MDM policy (Config.apply re-runs
 //     applyMDMPolicy with the freshly loaded Policy).
-//  4. Spawn a fresh connectWithRetryRuns with the new context and config.
-//  5. Broadcast a SystemEvent so any GUI / CLI subscriber (SubscribeEvents
+//  3. Start a fresh run with the new config.
+//  4. Broadcast a SystemEvent so any GUI / CLI subscriber (SubscribeEvents
 //     RPC) can refresh its cached config view without polling.
 //
 // The callback runs in the ticker's own goroutine. Ticker has already
@@ -52,39 +50,24 @@ type conflictCheck struct {
 func (s *Server) onMDMPolicyChange(_, _ *mdm.Policy) error {
 	log.Warn("MDM policy changed; restarting engine to apply new configuration")
 
-	// Hold s.mutex for the entire restart sequence (cancel + quiescence
-	// wait + re-spawn). Any concurrent Up/Down/Status arriving while
-	// MDM is restarting blocks on the Lock until we are done — they
-	// then observe the post-restart state coherently. This is safe
-	// because the connectWithRetryRuns goroutine no longer acquires
-	// s.mutex in its defer (intent vs. goroutine-alive concerns are
-	// fully separated; see the connectionGoroutineRunning helper).
+	// Hold s.mutex for the entire restart sequence (stop + re-start). Any
+	// concurrent Up/Down/Status arriving while MDM is restarting blocks on the
+	// Lock until we are done — they then observe the post-restart state coherently.
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
 
-	if !s.clientRunning {
-		// The client is not running, so there's no engine to restart.
+	if !s.connectClient.ConnectionRunning() {
+		// No run in flight, so there's no engine to restart.
 		return nil
 	}
+
+	// Cancel daemon-side login/status activities tied to the old run; the run
+	// itself is torn down atomically by the supervisor inside Restart (see
+	// restartEngineForMDMLocked), which stops and re-starts in one operation.
 	if s.actCancel != nil {
 		s.actCancel()
 	}
 
-	// Wait for previous connectWithRetryRuns to exit so we don't end up
-	// with two goroutines fighting over the same status recorder + engine.
-	// The teardown engages a fan-out of engine goroutines (peer workers,
-	// signal handler, route manager, ...). close(clientGiveUpChan)
-	// happens in the function-scope defer of connectWithRetryRuns, on
-	// every exit path (ctx cancel, backoff exhausted, panic) — see the
-	// defer in server.go.
-	if s.clientGiveUpChan != nil {
-		select {
-		case <-s.clientGiveUpChan:
-		case <-time.After(10 * time.Second):
-			return fmt.Errorf("failed to restart the engine due to timeout")
-		}
-	}
-
 	if err := s.restartEngineForMDMLocked(); err != nil {
 		log.Errorf("MDM restart failed: %v", err)
 		return err
@@ -131,14 +114,13 @@ func (s *Server) publishConfigChangedEvent(source string) {
 }
 
 // restartEngineForMDMLocked re-resolves the active profile config
-// (re-running applyMDMPolicy via Config.apply) and re-spawns
-// connectWithRetryRuns. Mirrors the tail of Server.Start so a runtime
-// MDM change behaves identically to a fresh boot under the new policy.
+// (re-running applyMDMPolicy via Config.apply) and starts a fresh run.
+// Mirrors the tail of Server.Start so a runtime MDM change behaves
+// identically to a fresh boot under the new policy.
 //
 // MUST be called with s.mutex held — onMDMPolicyChange holds the lock
-// for the entire restart sequence (cancel + quiescence wait + re-spawn)
-// so concurrent Up/Down/Status RPCs observe a coherent post-restart
-// state.
+// for the entire restart sequence so concurrent Up/Down/Status RPCs
+// observe a coherent post-restart state.
 func (s *Server) restartEngineForMDMLocked() error {
 	activeProf, err := s.profileManager.GetActiveProfileState()
 	if err != nil {
@@ -154,13 +136,13 @@ func (s *Server) restartEngineForMDMLocked() error {
 	s.statusRecorder.UpdateRosenpass(config.RosenpassEnabled, config.RosenpassPermissive)
 	s.statusRecorder.UpdateLazyConnection(config.LazyConnectionEnabled)
 
-	ctx, cancel := context.WithCancel(s.rootCtx)
+	_, cancel := context.WithCancel(s.rootCtx)
 	s.actCancel = cancel
-	s.clientRunning = true
-	s.clientRunningChan = make(chan struct{})
-	s.clientGiveUpChan = make(chan struct{})
-	log.Info("MDM restart: spawning connectWithRetryRuns with re-resolved config")
-	go s.connectWithRetryRuns(ctx, config, s.statusRecorder, s.clientRunningChan, s.clientGiveUpChan)
+	log.Info("MDM restart: atomically restarting the run with re-resolved config")
+	// MDM restart has no incoming RPC metadata; fire and forget. Restart is a
+	// single supervisor op (atomic stop+start), so there is no observable
+	// "stopped" window between tearing down the old run and starting the new.
+	s.connectClient.Restart(config, nil)
 	s.publishConfigChangedEvent("mdm")
 	return nil
 }

client/server/network.go

@@ -34,10 +34,6 @@ func (s *Server) ListNetworks(context.Context, *proto.ListNetworksRequest) (*pro
 		return nil, gstatus.Errorf(codes.Unavailable, errNetworksDisabled)
 	}
 
-	if s.connectClient == nil {
-		return nil, fmt.Errorf("not connected")
-	}
-
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return nil, fmt.Errorf("not connected")
@@ -147,10 +143,6 @@ func (s *Server) SelectNetworks(_ context.Context, req *proto.SelectNetworksRequ
 		return nil, gstatus.Errorf(codes.Unavailable, errNetworksDisabled)
 	}
 
-	if s.connectClient == nil {
-		return nil, fmt.Errorf("not connected")
-	}
-
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return nil, fmt.Errorf("not connected")
@@ -199,10 +191,6 @@ func (s *Server) DeselectNetworks(_ context.Context, req *proto.SelectNetworksRe
 		return nil, gstatus.Errorf(codes.Unavailable, errNetworksDisabled)
 	}
 
-	if s.connectClient == nil {
-		return nil, fmt.Errorf("not connected")
-	}
-
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return nil, fmt.Errorf("not connected")

client/server/server.go

@@ -8,12 +8,10 @@ import (
 	"os"
 	"os/exec"
 	"runtime"
-	"strconv"
 	"sync"
 	"sync/atomic"
 	"time"
 
-	"github.com/cenkalti/backoff/v4"
 	log "github.com/sirupsen/logrus"
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 	"google.golang.org/grpc/codes"
@@ -39,15 +37,7 @@ import (
 )
 
 const (
-	probeThreshold          = time.Second * 5
-	retryInitialIntervalVar = "NB_CONN_RETRY_INTERVAL_TIME"
-	maxRetryIntervalVar     = "NB_CONN_MAX_RETRY_INTERVAL_TIME"
-	maxRetryTimeVar         = "NB_CONN_MAX_RETRY_TIME_TIME"
-	retryMultiplierVar      = "NB_CONN_RETRY_MULTIPLIER"
-	defaultInitialRetryTime = 30 * time.Minute
-	defaultMaxRetryInterval = 60 * time.Minute
-	defaultMaxRetryTime     = 14 * 24 * time.Hour
-	defaultRetryMultiplier  = 1.7
+	probeThreshold = time.Second * 5
 
 	// JWT token cache TTL for the client daemon (disabled by default)
 	defaultJWTCacheTTL = 0
@@ -72,15 +62,8 @@ type Server struct {
 	mutex  sync.Mutex
 	config *profilemanager.Config
 	proto.UnimplementedDaemonServiceServer
-	// clientRunning tracks "the daemon wants to be connected" — set true by
-	// Start / Up, cleared by Down / Logout. Persists across retry
-	// loops, signal disconnects, and ErrResetConnection cycles. NOT
-	// changed by connectWithRetryRuns goroutine exit — for that
-	// (goroutine-still-alive) check, see connectionGoroutineRunning() which
-	// derives from clientGiveUpChan close state. Protected by s.mutex.
-	clientRunning          bool
-	clientRunningChan chan struct{}
-	clientGiveUpChan  chan struct{} // closed when connectWithRetryRuns goroutine exits
+	// Run state (in-flight? established/done channels?) is owned entirely by the
+	// supervisor inside connectClient — the daemon keeps no per-run fields.
 
 	connectClient *internal.ConnectClient
 
@@ -136,6 +119,13 @@ func New(ctx context.Context, logFile string, configFile string, profilesDisable
 		networksDisabled:       networksDisabled,
 		jwtCache:               newJWTCache(),
 	}
+	// The ConnectClient is daemon-lifetime: build it exactly once, here. Its
+	// supervisor lives as long as the daemon; Up/Down/MDM and reconnects all
+	// drive this same instance. updateManager isn't ready yet (created in
+	// Start) and is injected there via SetUpdateManager.
+	s.connectClient = internal.NewConnectClient(ctx, s.statusRecorder)
+	s.connectClient.SetSyncResponsePersistence(s.persistSyncResponse)
+
 	agent := &serverAgent{s}
 	s.sleepHandler = sleephandler.New(agent)
 	s.startSleepDetector()
@@ -147,7 +137,7 @@ func (s *Server) Start() error {
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
 
-	if s.clientRunning {
+	if s.connectClient.ConnectionRunning() {
 		return nil
 	}
 
@@ -165,6 +155,7 @@ func (s *Server) Start() error {
 		stateMgr := statemanager.New(s.profileManager.GetStatePath())
 		s.updateManager = updater.NewManager(s.statusRecorder, stateMgr)
 		s.updateManager.CheckUpdateSuccess(s.rootCtx)
+		s.connectClient.SetUpdateManager(s.updateManager)
 	}
 
 	// MDM policy reload ticker: every minute the desktop daemon re-reads
@@ -190,7 +181,9 @@ func (s *Server) Start() error {
 		return nil
 	}
 
-	ctx, cancel := context.WithCancel(s.rootCtx)
+	// actCancel cancels in-flight foreground operations (login/status); the run
+	// itself is owned by the supervisor and stopped via Stop, not this cancel.
+	_, cancel := context.WithCancel(s.rootCtx)
 	s.actCancel = cancel
 
 	// copy old default config
@@ -232,99 +225,14 @@ func (s *Server) Start() error {
 		return nil
 	}
 
-	s.clientRunning = true
-	s.clientRunningChan = make(chan struct{})
-	s.clientGiveUpChan = make(chan struct{})
-	go s.connectWithRetryRuns(ctx, config, s.statusRecorder, s.clientRunningChan, s.clientGiveUpChan)
+	// Boot autoconnect: no incoming RPC metadata. The supervisor runs the
+	// client and reconnects internally; we just fire and forget (the run owns
+	// its established/done channels).
+	s.connectClient.RunAsync(config, nil)
 	s.publishConfigChangedEvent("startup")
 	return nil
 }
 
-// connectWithRetryRuns runs the client connection with a backoff strategy where we retry the operation as additional
-// mechanism to keep the client connected even when the connection is lost.
-// we cancel retry if the client receive a stop or down command, or if disable auto connect is configured.
-//
-// The goroutine's exit is signalled to the daemon via close(giveUpChan)
-// — placed in the function-scope defer so every return path (panic,
-// DisableAutoConnect early-exit, backoff exhausted, ctx cancel) closes
-// it. Callers that need to observe "is the goroutine still alive?" use
-// Server.connectionGoroutineRunning() which non-blockingly checks the close state
-// of clientGiveUpChan. The defer does NOT touch s.mutex; the daemon's
-// "intent" (clientRunning) is maintained by the RPC handlers, not by this
-// goroutine.
-func (s *Server) connectWithRetryRuns(ctx context.Context, profileConfig *profilemanager.Config, statusRecorder *peer.Status, runningChan chan struct{}, giveUpChan chan struct{}) {
-	defer func() {
-		if giveUpChan != nil {
-			close(giveUpChan)
-		}
-	}()
-
-	if s.config.DisableAutoConnect {
-		if err := s.connect(ctx, s.config, s.statusRecorder, runningChan); err != nil {
-			log.Debugf("run client connection exited with error: %v", err)
-		}
-		log.Tracef("client connection exited")
-		return
-	}
-
-	backOff := getConnectWithBackoff(ctx)
-	go func() {
-		t := time.NewTicker(24 * time.Hour)
-		for {
-			select {
-			case <-ctx.Done():
-				t.Stop()
-				return
-			case <-t.C:
-				mgmtState := statusRecorder.GetManagementState()
-				signalState := statusRecorder.GetSignalState()
-				if mgmtState.Connected && signalState.Connected {
-					log.Tracef("resetting status")
-					backOff.Reset()
-				} else {
-					log.Tracef("not resetting status: mgmt: %v, signal: %v", mgmtState.Connected, signalState.Connected)
-				}
-			}
-		}
-	}()
-
-	runOperation := func() error {
-		err := s.connect(ctx, profileConfig, statusRecorder, runningChan)
-		if err != nil {
-			log.Debugf("run client connection exited with error: %v. Will retry in the background", err)
-			return err
-		}
-
-		log.Tracef("client connection exited gracefully, do not need to retry")
-		return nil
-	}
-
-	if err := backoff.Retry(runOperation, backOff); err != nil {
-		log.Errorf("operation failed: %v", err)
-	}
-	// giveUpChan is closed by the function-scope defer.
-}
-
-// connectionGoroutineRunning reports whether the connectWithRetryRuns goroutine is
-// still running. Returns false when no goroutine has ever been started
-// AND when the most recent one has already closed clientGiveUpChan on
-// exit (whether due to ctx cancel, DisableAutoConnect single-shot
-// completion, or backoff retry exhaustion).
-//
-// MUST be called with s.mutex held — accesses s.clientGiveUpChan which
-// is written by Start/Up under the same lock.
-func (s *Server) connectionGoroutineRunning() bool {
-	if s.clientGiveUpChan == nil {
-		return false
-	}
-	select {
-	case <-s.clientGiveUpChan:
-		return false
-	default:
-		return true
-	}
-}
-
 // loginAttempt attempts to login using the provided information. it returns a status in case something fails
 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)
@@ -375,7 +283,7 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques
 		return nil, err
 	}
 
-	config, err := setConfigInputFromRequest(msg)
+	config, err := s.setConfigInputFromRequest(msg)
 	if err != nil {
 		return nil, err
 	}
@@ -398,17 +306,17 @@ func (s *Server) SetConfig(callerCtx context.Context, msg *proto.SetConfigReques
 // field is its own optional case. Returns the resolved ConfigInput
 // and a non-nil error only when the active profile file path cannot
 // be determined.
-func setConfigInputFromRequest(msg *proto.SetConfigRequest) (profilemanager.ConfigInput, error) {
+func (s *Server) setConfigInputFromRequest(msg *proto.SetConfigRequest) (profilemanager.ConfigInput, error) {
 	var config profilemanager.ConfigInput
 
-	profState := profilemanager.ActiveProfileState{
-		Name:     msg.ProfileName,
-		Username: msg.Username,
-	}
-	profPath, err := profState.FilePath()
+	resolved, err := s.resolveProfileHandle(msg.ProfileName, msg.Username)
 	if err != nil {
-		log.Errorf("failed to get active profile file path: %v", err)
-		return config, fmt.Errorf("failed to get active profile file path: %w", err)
+		log.Errorf("failed to resolve profile %q: %v", msg.ProfileName, err)
+		return config, err
+	}
+	profPath := resolved.Path
+	if profPath == "" {
+		profPath = profilemanager.DefaultConfigPath
 	}
 	config.ConfigPath = profPath
 
@@ -535,30 +443,9 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	}
 
 	if msg.ProfileName != nil {
-		if *msg.ProfileName != "default" && (msg.Username == nil || *msg.Username == "") {
-			log.Errorf("profile name is set to %s, but username is not provided", *msg.ProfileName)
-			return nil, fmt.Errorf("profile name is set to %s, but username is not provided", *msg.ProfileName)
-		}
-
-		var username string
-		if *msg.ProfileName != "default" {
-			username = *msg.Username
-		}
-
-		if *msg.ProfileName != activeProf.Name && username != activeProf.Username {
-			if s.checkProfilesDisabled() {
-				log.Errorf("profiles are disabled, you cannot use this feature without profiles enabled")
-				return nil, gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
-			}
-
-			log.Infof("switching to profile %s for user '%s'", *msg.ProfileName, username)
-			if err := s.profileManager.SetActiveProfileState(&profilemanager.ActiveProfileState{
-				Name:     *msg.ProfileName,
-				Username: username,
-			}); err != nil {
-				log.Errorf("failed to set active profile state: %v", err)
-				return nil, fmt.Errorf("failed to set active profile state: %w", err)
-			}
+		if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
+			log.Errorf("failed to switch profile: %v", err)
+			return nil, err
 		}
 	}
 
@@ -568,7 +455,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 		return nil, fmt.Errorf("failed to get active profile state: %w", err)
 	}
 
-	log.Infof("active profile: %s for %s", activeProf.Name, activeProf.Username)
+	log.Infof("active profile: %s for %s", activeProf.ID, activeProf.Username)
 
 	s.mutex.Lock()
 
@@ -741,13 +628,22 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 // Up starts engine work in the daemon.
 func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpResponse, error) {
 	s.mutex.Lock()
-	// clientRunning is the daemon-intent flag (set by previous Up/Start, cleared
-	// by Down). connectionGoroutineRunning() reports whether the previous retry-loop
-	// goroutine is still trying. When intent is up AND goroutine is alive,
-	// the existing engine is on the job — just wait for it. When intent
-	// is up but the goroutine has given up (backoff exhausted) OR when
-	// intent is down, fall through to spawn a fresh retry loop.
-	if s.clientRunning && s.connectionGoroutineRunning() {
+
+	// The client (and its supervisor) is built once in New(), so a nil here
+	// never happens in production — Up is only reachable after New() has run and
+	// the gRPC server is serving. The real case this guards is the daemon
+	// SHUTTING DOWN: rootCtx is cancelled, the supervisor is no longer accepting
+	// commands, so ServiceRunning() is false even though the client exists. Bail
+	// loud instead of enqueuing a run that will never start. (nil only happens in
+	// tests that build a Server without New(); ServiceRunning is nil-safe.)
+	if !s.connectClient.ServiceRunning() {
+		s.mutex.Unlock()
+		return nil, fmt.Errorf("service is not running, start the netbird service for 'up' to take effect")
+	}
+
+	// If a connection run is already in flight, the existing engine is on the
+	// job — just wait for it. Otherwise fall through to start a fresh run.
+	if s.connectClient.ConnectionRunning() {
 		state := internal.CtxGetState(s.rootCtx)
 		status, err := state.Status()
 		if err != nil {
@@ -785,14 +681,14 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 	if s.actCancel != nil {
 		s.actCancel()
 	}
-	ctx, cancel := context.WithCancel(s.rootCtx)
-	md, ok := metadata.FromIncomingContext(callerCtx)
-	if ok {
-		ctx = metadata.NewOutgoingContext(ctx, md)
-	}
-
+	// actCancel cancels in-flight foreground ops (login/status); the run is
+	// owned by the supervisor and stopped via Stop, not this cancel.
+	_, cancel := context.WithCancel(s.rootCtx)
 	s.actCancel = cancel
 
+	// Forward the caller's gRPC metadata (e.g. UI user-agent) into the run.
+	md, _ := metadata.FromIncomingContext(callerCtx)
+
 	if s.config == nil {
 		s.mutex.Unlock()
 		return nil, fmt.Errorf("config is not defined, please call login command first")
@@ -806,10 +702,10 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 	}
 
 	if msg != nil && msg.ProfileName != nil {
-		if err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
+		if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
 			s.mutex.Unlock()
 			log.Errorf("failed to switch profile: %v", err)
-			return nil, fmt.Errorf("failed to switch profile: %w", err)
+			return nil, err
 		}
 	}
 
@@ -820,7 +716,7 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 		return nil, fmt.Errorf("failed to get active profile state: %w", err)
 	}
 
-	log.Infof("active profile: %s for %s", activeProf.Name, activeProf.Username)
+	log.Infof("active profile: %s for %s", activeProf.ID, activeProf.Username)
 
 	config, _, err := s.getConfig(activeProf)
 	if err != nil {
@@ -833,65 +729,82 @@ func (s *Server) Up(callerCtx context.Context, msg *proto.UpRequest) (*proto.UpR
 	s.statusRecorder.UpdateManagementAddress(s.config.ManagementURL.String())
 	s.statusRecorder.UpdateRosenpass(s.config.RosenpassEnabled, s.config.RosenpassPermissive)
 
-	s.clientRunning = true
-	s.clientRunningChan = make(chan struct{})
-	s.clientGiveUpChan = make(chan struct{})
-
-	go s.connectWithRetryRuns(ctx, s.config, s.statusRecorder, s.clientRunningChan, s.clientGiveUpChan)
+	s.connectClient.RunAsync(s.config, md)
 	s.publishConfigChangedEvent("up_rpc")
 
 	s.mutex.Unlock()
 	return s.waitForUp(callerCtx)
 }
 
-// todo: handle potential race conditions
+// waitForUp blocks until the in-flight run becomes established (success) or ends
+// before that (failure). The wait is owned by the supervisor (via the client) —
+// the daemon holds no per-run state here.
 func (s *Server) waitForUp(callerCtx context.Context) (*proto.UpResponse, error) {
 	timeoutCtx, cancel := context.WithTimeout(callerCtx, 50*time.Second)
 	defer cancel()
 
-	select {
-	case <-s.clientGiveUpChan:
-		return nil, fmt.Errorf("client gave up to connect")
-	case <-s.clientRunningChan:
-		s.isSessionActive.Store(true)
-		return &proto.UpResponse{}, nil
-	case <-callerCtx.Done():
-		log.Debug("context done, stopping the wait for engine to become ready")
-		return nil, callerCtx.Err()
-	case <-timeoutCtx.Done():
-		log.Debug("up is timed out, stopping the wait for engine to become ready")
-		return nil, timeoutCtx.Err()
+	if err := s.connectClient.WaitEstablishedOrDone(timeoutCtx); err != nil {
+		log.Debugf("waiting for the connection to be established failed: %v", err)
+		return nil, fmt.Errorf("connection not established: %w", err)
 	}
+	s.isSessionActive.Store(true)
+	return &proto.UpResponse{}, nil
 }
 
-func (s *Server) switchProfileIfNeeded(profileName string, userName *string, activeProf *profilemanager.ActiveProfileState) error {
-	if profileName != "default" && (userName == nil || *userName == "") {
-		log.Errorf("profile name is set to %s, but username is not provided", profileName)
-		return fmt.Errorf("profile name is set to %s, but username is not provided", profileName)
+// resolveProfileHandle resolves a wire-level profile handle (display
+// name, ID, or unique ID prefix) to a concrete profile. Returns gRPC
+// status errors so handlers can return them directly.
+func (s *Server) resolveProfileHandle(handle, username string) (*profilemanager.Profile, error) {
+	p, err := s.profileManager.ResolveProfile(handle, username)
+	if err == nil {
+		return p, nil
+	}
+	var amb *profilemanager.ErrAmbiguousHandle
+	if errors.As(err, &amb) {
+		return nil, gstatus.Errorf(codes.InvalidArgument, "%v", amb)
+	}
+	if errors.Is(err, profilemanager.ErrProfileNotFound) {
+		return nil, gstatus.Errorf(codes.NotFound, "profile %q not found", handle)
+	}
+	return nil, fmt.Errorf("resolve profile: %w", err)
+}
+
+// switchProfileIfNeeded resolves the user-supplied handle, updates the
+// active profile state if it differs from the current one, and returns
+// the resolved profile so callers can include its ID in RPC responses.
+func (s *Server) switchProfileIfNeeded(handle string, userName *string, activeProf *profilemanager.ActiveProfileState) (*profilemanager.Profile, error) {
+	if handle != profilemanager.DefaultProfileName && (userName == nil || *userName == "") {
+		log.Errorf("profile name is set to %s, but username is not provided", handle)
+		return nil, fmt.Errorf("profile name is set to %s, but username is not provided", handle)
 	}
 
 	var username string
-	if profileName != "default" {
+	if handle != profilemanager.DefaultProfileName {
 		username = *userName
 	}
 
-	if profileName != activeProf.Name || username != activeProf.Username {
+	resolved, err := s.resolveProfileHandle(handle, username)
+	if err != nil {
+		return nil, err
+	}
+
+	if resolved.ID != activeProf.ID || username != activeProf.Username {
 		if s.checkProfilesDisabled() {
 			log.Errorf("profiles are disabled, you cannot use this feature without profiles enabled")
-			return gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
+			return nil, gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
 		}
 
-		log.Infof("switching to profile %s for user %s", profileName, username)
+		log.Infof("switching to profile %s (%s) for user %s", resolved.Name, resolved.ID, username)
 		if err := s.profileManager.SetActiveProfileState(&profilemanager.ActiveProfileState{
-			Name:     profileName,
+			ID:       resolved.ID,
 			Username: username,
 		}); err != nil {
 			log.Errorf("failed to set active profile state: %v", err)
-			return fmt.Errorf("failed to set active profile state: %w", err)
+			return nil, fmt.Errorf("failed to set active profile state: %w", err)
 		}
 	}
 
-	return nil
+	return resolved, nil
 }
 
 // SwitchProfile switches the active profile in the daemon.
@@ -906,9 +819,9 @@ func (s *Server) SwitchProfile(callerCtx context.Context, msg *proto.SwitchProfi
 	}
 
 	if msg != nil && msg.ProfileName != nil {
-		if err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
+		if _, err := s.switchProfileIfNeeded(*msg.ProfileName, msg.Username, activeProf); err != nil {
 			log.Errorf("failed to switch profile: %v", err)
-			return nil, fmt.Errorf("failed to switch profile: %w", err)
+			return nil, err
 		}
 	}
 	activeProf, err = s.profileManager.GetActiveProfileState()
@@ -924,17 +837,17 @@ func (s *Server) SwitchProfile(callerCtx context.Context, msg *proto.SwitchProfi
 
 	s.config = config
 
-	return &proto.SwitchProfileResponse{}, nil
+	return &proto.SwitchProfileResponse{Id: activeProf.ID.String()}, nil
 }
 
 // Down engine work in the daemon.
 func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownResponse, error) {
 	s.mutex.Lock()
+	defer s.mutex.Unlock()
 
-	giveUpChan := s.clientGiveUpChan
-
+	// cleanupConnection stops the run through the supervisor, which blocks until
+	// the run has fully unwound — no separate goroutine-quiescence wait needed.
 	if err := s.cleanupConnection(); err != nil {
-		s.mutex.Unlock()
 		// todo review to update the status in case any type of error
 		log.Errorf("failed to shut down properly: %v", err)
 		return nil, err
@@ -943,20 +856,6 @@ func (s *Server) Down(ctx context.Context, _ *proto.DownRequest) (*proto.DownRes
 	state := internal.CtxGetState(s.rootCtx)
 	state.Set(internal.StatusIdle)
 
-	s.mutex.Unlock()
-
-	// Wait for the connectWithRetryRuns goroutine to finish with a short timeout.
-	// This prevents the goroutine from setting ErrResetConnection after Down() returns.
-	// The giveUpChan is closed at the end of connectWithRetryRuns.
-	if giveUpChan != nil {
-		select {
-		case <-giveUpChan:
-			log.Debugf("client goroutine finished successfully")
-		case <-time.After(5 * time.Second):
-			log.Warnf("timeout waiting for client goroutine to finish, proceeding anyway")
-		}
-	}
-
 	return &proto.DownResponse{}, nil
 }
 
@@ -967,34 +866,19 @@ func (s *Server) cleanupConnection() error {
 		return ErrServiceNotUp
 	}
 
-	// Daemon intent flips to "down" — all callers (Down RPC,
-	// Logout RPC handlers) tear down the connection because the user
-	// explicitly asked for it. MDM restart does NOT go through this
-	// path, so its clientRunning stays true.
-	s.clientRunning = false
-
-	// Capture the engine reference before cancelling the context.
-	// After actCancel(), the connectWithRetryRuns goroutine wakes up
-	// and sets connectClient.engine = nil, causing connectClient.Stop()
-	// to skip the engine shutdown entirely.
-	var engine *internal.Engine
-	if s.connectClient != nil {
-		engine = s.connectClient.Engine()
+	// Tear the client down through the lifecycle supervisor BEFORE cancelling
+	// the retry context. Stop serializes on the supervisor queue and blocks
+	// until the in-flight run has fully unwound (a clean, synchronous teardown).
+	// It must run before actCancel: cancelling the context first would make
+	// Stop observe a dead context and return early without waiting.
+	if err := s.connectClient.Stop(); err != nil {
+		return err
 	}
 
+	// Stop the retry goroutine so it does not start a fresh run. The client
+	// itself is daemon-lifetime and intentionally kept (a later Up reuses it).
 	s.actCancel()
 
-	if s.connectClient == nil {
-		return nil
-	}
-
-	if engine != nil {
-		if err := engine.Stop(); err != nil {
-			return err
-		}
-	}
-
-	s.connectClient = nil
 	s.isSessionActive.Store(false)
 
 	log.Infof("service is down")
@@ -1014,22 +898,27 @@ func (s *Server) Logout(ctx context.Context, msg *proto.LogoutRequest) (*proto.L
 }
 
 func (s *Server) handleProfileLogout(ctx context.Context, msg *proto.LogoutRequest) (*proto.LogoutResponse, error) {
-	if err := s.validateProfileOperation(*msg.ProfileName, true); err != nil {
-		return nil, err
-	}
-
 	if msg.Username == nil || *msg.Username == "" {
 		return nil, gstatus.Errorf(codes.InvalidArgument, "username must be provided when profile name is specified")
 	}
 	username := *msg.Username
 
-	if err := s.logoutFromProfile(ctx, *msg.ProfileName, username); err != nil {
-		log.Errorf("failed to logout from profile %s: %v", *msg.ProfileName, err)
+	resolved, err := s.resolveProfileHandle(*msg.ProfileName, username)
+	if err != nil {
+		return nil, err
+	}
+
+	if err := s.validateProfileOperation(resolved.ID, true); err != nil {
+		return nil, err
+	}
+
+	if err := s.logoutFromProfile(ctx, resolved); err != nil {
+		log.Errorf("failed to logout from profile %s: %v", resolved.ID, err)
 		return nil, gstatus.Errorf(codes.Internal, "logout: %v", err)
 	}
 
 	activeProf, _ := s.profileManager.GetActiveProfileState()
-	if activeProf != nil && activeProf.Name == *msg.ProfileName {
+	if activeProf != nil && activeProf.ID == resolved.ID {
 		if err := s.cleanupConnection(); err != nil && !errors.Is(err, ErrServiceNotUp) {
 			log.Errorf("failed to cleanup connection: %v", err)
 		}
@@ -1091,30 +980,30 @@ func (s *Server) getConfig(activeProf *profilemanager.ActiveProfileState) (*prof
 	return config, configExisted, nil
 }
 
-func (s *Server) canRemoveProfile(profileName string) error {
-	if profileName == profilemanager.DefaultProfileName {
+func (s *Server) canRemoveProfile(id profilemanager.ID) error {
+	if id == profilemanager.DefaultProfileName {
 		return fmt.Errorf("remove profile with reserved name: %s", profilemanager.DefaultProfileName)
 	}
 
 	activeProf, err := s.profileManager.GetActiveProfileState()
-	if err == nil && activeProf.Name == profileName {
-		return fmt.Errorf("remove active profile: %s", profileName)
+	if err == nil && activeProf.ID == id {
+		return fmt.Errorf("remove active profile: %s", id)
 	}
 
 	return nil
 }
 
-func (s *Server) validateProfileOperation(profileName string, allowActiveProfile bool) error {
+func (s *Server) validateProfileOperation(id profilemanager.ID, allowActiveProfile bool) error {
 	if s.checkProfilesDisabled() {
 		return gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
 	}
 
-	if profileName == "" {
+	if id == "" {
 		return gstatus.Errorf(codes.InvalidArgument, "profile name must be provided")
 	}
 
 	if !allowActiveProfile {
-		if err := s.canRemoveProfile(profileName); err != nil {
+		if err := s.canRemoveProfile(id); err != nil {
 			return gstatus.Errorf(codes.InvalidArgument, "%v", err)
 		}
 	}
@@ -1122,25 +1011,20 @@ func (s *Server) validateProfileOperation(profileName string, allowActiveProfile
 	return nil
 }
 
-// logoutFromProfile logs out from a specific profile by loading its config and sending logout request
-func (s *Server) logoutFromProfile(ctx context.Context, profileName, username string) error {
+func (s *Server) logoutFromProfile(ctx context.Context, profile *profilemanager.Profile) error {
 	activeProf, err := s.profileManager.GetActiveProfileState()
-	if err == nil && activeProf.Name == profileName && s.connectClient != nil {
+	if err == nil && activeProf.ID == profile.ID && s.connectClient.ConnectionRunning() {
 		return s.sendLogoutRequest(ctx)
 	}
 
-	profileState := &profilemanager.ActiveProfileState{
-		Name:     profileName,
-		Username: username,
-	}
-	profilePath, err := profileState.FilePath()
-	if err != nil {
-		return fmt.Errorf("get profile path: %w", err)
+	cfgPath := profile.Path
+	if cfgPath == "" {
+		cfgPath = profilemanager.DefaultConfigPath
 	}
 
-	config, err := profilemanager.GetConfig(profilePath)
+	config, err := profilemanager.GetConfig(cfgPath)
 	if err != nil {
-		return fmt.Errorf("profile '%s' not found", profileName)
+		return fmt.Errorf("profile '%s' not found", profile.ID)
 	}
 
 	return s.sendLogoutRequestWithConfig(ctx, config)
@@ -1175,48 +1059,13 @@ func (s *Server) Status(
 	ctx context.Context,
 	msg *proto.StatusRequest,
 ) (*proto.StatusResponse, error) {
-	s.mutex.Lock()
-	// Only wait if the retry-loop goroutine is alive and making
-	// progress. clientRunning=true with connectionGoroutineRunning=false means the
-	// backoff has given up — there is nothing to wait for; let the
-	// caller observe the failed status directly.
-	alive := s.connectionGoroutineRunning()
-	s.mutex.Unlock()
-
-	if msg.WaitForReady != nil && *msg.WaitForReady && alive {
-		state := internal.CtxGetState(s.rootCtx)
-		status, err := state.Status()
-		if err != nil {
-			return nil, err
-		}
-
-		if status != internal.StatusIdle && status != internal.StatusConnected && status != internal.StatusConnecting {
-			s.actCancel()
-		}
-
-		ticker := time.NewTicker(1 * time.Second)
-		defer ticker.Stop()
-	loop:
-		for {
-			select {
-			case <-s.clientGiveUpChan:
-				ticker.Stop()
-				break loop
-			case <-s.clientRunningChan:
-				ticker.Stop()
-				break loop
-			case <-ticker.C:
-				status, err := state.Status()
-				if err != nil {
-					continue
-				}
-				if status != internal.StatusIdle && status != internal.StatusConnected && status != internal.StatusConnecting {
-					s.actCancel()
-				}
-				continue
-			case <-ctx.Done():
-				return nil, ctx.Err()
-			}
+	// A run that hits a terminal auth failure now exits on its own (engine marks
+	// NeedsLogin), so we no longer poll-and-cancel: we wait for the in-flight run
+	// to become established or to end. With no run in flight this returns
+	// immediately (errNoRunInFlight); either way we then report the status below.
+	if msg.WaitForReady != nil && *msg.WaitForReady {
+		if err := s.connectClient.WaitEstablishedOrDone(ctx); err != nil && ctx.Err() != nil {
+			return nil, ctx.Err()
 		}
 	}
 
@@ -1254,10 +1103,6 @@ func (s *Server) getSSHServerState() *proto.SSHServerState {
 	connectClient := s.connectClient
 	s.mutex.Unlock()
 
-	if connectClient == nil {
-		return nil
-	}
-
 	engine := connectClient.Engine()
 	if engine == nil {
 		return nil
@@ -1295,10 +1140,6 @@ func (s *Server) GetPeerSSHHostKey(
 	statusRecorder := s.statusRecorder
 	s.mutex.Unlock()
 
-	if connectClient == nil {
-		return nil, errors.New("client not initialized")
-	}
-
 	engine := connectClient.Engine()
 	if engine == nil {
 		return nil, errors.New("engine not started")
@@ -1465,17 +1306,13 @@ func (s *Server) WaitJWTToken(
 // ExposeService exposes a local port via the NetBird reverse proxy.
 func (s *Server) ExposeService(req *proto.ExposeServiceRequest, srv proto.DaemonService_ExposeServiceServer) error {
 	s.mutex.Lock()
-	if !s.clientRunning {
+	if !s.connectClient.ConnectionRunning() {
 		s.mutex.Unlock()
 		return gstatus.Errorf(codes.FailedPrecondition, "client is not running, run 'netbird up' first")
 	}
 	connectClient := s.connectClient
 	s.mutex.Unlock()
 
-	if connectClient == nil {
-		return gstatus.Errorf(codes.FailedPrecondition, "client not initialized")
-	}
-
 	engine := connectClient.Engine()
 	if engine == nil {
 		return gstatus.Errorf(codes.FailedPrecondition, "engine not initialized")
@@ -1529,10 +1366,6 @@ func isUnixRunningDesktop() bool {
 }
 
 func (s *Server) runProbes(waitForProbeResult bool) {
-	if s.connectClient == nil {
-		return
-	}
-
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return
@@ -1558,15 +1391,14 @@ func (s *Server) GetConfig(ctx context.Context, req *proto.GetConfigRequest) (*p
 		return nil, ctx.Err()
 	}
 
-	prof := profilemanager.ActiveProfileState{
-		Name:     req.ProfileName,
-		Username: req.Username,
-	}
-
-	cfgPath, err := prof.FilePath()
+	resolved, err := s.resolveProfileHandle(req.ProfileName, req.Username)
 	if err != nil {
-		log.Errorf("failed to get active profile file path: %v", err)
-		return nil, fmt.Errorf("failed to get active profile file path: %w", err)
+		log.Errorf("failed to resolve profile %q: %v", req.ProfileName, err)
+		return nil, err
+	}
+	cfgPath := resolved.Path
+	if cfgPath == "" {
+		cfgPath = profilemanager.DefaultConfigPath
 	}
 
 	cfg, err := profilemanager.GetConfig(cfgPath)
@@ -1671,12 +1503,39 @@ func (s *Server) AddProfile(ctx context.Context, msg *proto.AddProfileRequest) (
 		return nil, gstatus.Errorf(codes.InvalidArgument, "profile name and username must be provided")
 	}
 
-	if err := s.profileManager.AddProfile(msg.ProfileName, msg.Username); err != nil {
+	created, err := s.profileManager.AddProfile(msg.ProfileName, msg.Username)
+	if err != nil {
 		log.Errorf("failed to create profile: %v", err)
 		return nil, fmt.Errorf("failed to create profile: %w", err)
 	}
 
-	return &proto.AddProfileResponse{}, nil
+	return &proto.AddProfileResponse{Id: created.ID.String()}, nil
+}
+
+func (s *Server) RenameProfile(ctx context.Context, msg *proto.RenameProfileRequest) (*proto.RenameProfileResponse, error) {
+	s.mutex.Lock()
+	defer s.mutex.Unlock()
+
+	if s.checkProfilesDisabled() {
+		return nil, gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
+	}
+
+	if msg.Handle == "" || msg.Username == "" || msg.NewProfileName == "" {
+		return nil, gstatus.Errorf(codes.InvalidArgument, "profile name, username and new profile name must be provided")
+	}
+
+	resolved, err := s.resolveProfileHandle(msg.Handle, msg.Username)
+	if err != nil {
+		return nil, err
+	}
+
+	err = s.profileManager.RenameProfile(resolved.ID, msg.Username, msg.NewProfileName)
+	if err != nil {
+		log.Errorf("failed to rename profile: %v", err)
+		return nil, fmt.Errorf("failed to rename profile: %w", err)
+	}
+
+	return &proto.RenameProfileResponse{OldProfileName: resolved.Name}, nil
 }
 
 // RemoveProfile removes a profile from the daemon.
@@ -1684,20 +1543,29 @@ func (s *Server) RemoveProfile(ctx context.Context, msg *proto.RemoveProfileRequ
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
 
-	if err := s.validateProfileOperation(msg.ProfileName, false); err != nil {
+	if s.checkProfilesDisabled() {
+		return nil, gstatus.Errorf(codes.Unavailable, errProfilesDisabled)
+	}
+
+	if msg.ProfileName == "" {
+		return nil, gstatus.Errorf(codes.InvalidArgument, "profile name must be provided")
+	}
+
+	resolved, err := s.resolveProfileHandle(msg.ProfileName, msg.Username)
+	if err != nil {
 		return nil, err
 	}
 
-	if err := s.logoutFromProfile(ctx, msg.ProfileName, msg.Username); err != nil {
-		log.Warnf("failed to logout from profile %s before removal: %v", msg.ProfileName, err)
+	if err := s.logoutFromProfile(ctx, resolved); err != nil {
+		log.Warnf("failed to logout from profile %s before removal: %v", resolved.ID, err)
 	}
 
-	if err := s.profileManager.RemoveProfile(msg.ProfileName, msg.Username); err != nil {
+	if err := s.profileManager.RemoveProfile(resolved.ID, msg.Username); err != nil {
 		log.Errorf("failed to remove profile: %v", err)
 		return nil, fmt.Errorf("failed to remove profile: %w", err)
 	}
 
-	return &proto.RemoveProfileResponse{}, nil
+	return &proto.RemoveProfileResponse{Id: resolved.ID.String()}, nil
 }
 
 // ListProfiles lists all profiles in the daemon.
@@ -1720,6 +1588,7 @@ func (s *Server) ListProfiles(ctx context.Context, msg *proto.ListProfilesReques
 	}
 	for i, profile := range profiles {
 		response.Profiles[i] = &proto.Profile{
+			Id:       profile.ID.String(),
 			Name:     profile.Name,
 			IsActive: profile.IsActive,
 		}
@@ -1728,7 +1597,9 @@ func (s *Server) ListProfiles(ctx context.Context, msg *proto.ListProfilesReques
 	return response, nil
 }
 
-// GetActiveProfile returns the active profile in the daemon.
+// GetActiveProfile returns the active profile in the daemon. The ProfileName
+// field carries the display name for backwards compatibility with UI clients,
+// new callers should prefer Id.
 func (s *Server) GetActiveProfile(ctx context.Context, msg *proto.GetActiveProfileRequest) (*proto.GetActiveProfileResponse, error) {
 	s.mutex.Lock()
 	defer s.mutex.Unlock()
@@ -1739,9 +1610,23 @@ func (s *Server) GetActiveProfile(ctx context.Context, msg *proto.GetActiveProfi
 		return nil, fmt.Errorf("failed to get active profile state: %w", err)
 	}
 
+	// Fallback to legacy name == ID
+	displayName := activeProfile.ID.String()
+	if activeProfile.ID != profilemanager.DefaultProfileName {
+		if profiles, lerr := s.profileManager.ListProfiles(activeProfile.Username); lerr == nil {
+			for _, p := range profiles {
+				if p.ID == activeProfile.ID {
+					displayName = p.Name
+					break
+				}
+			}
+		}
+	}
+
 	return &proto.GetActiveProfileResponse{
-		ProfileName: activeProfile.Name,
+		ProfileName: displayName,
 		Username:    activeProfile.Username,
+		Id:          activeProfile.ID.String(),
 	}, nil
 }
 
@@ -1759,22 +1644,6 @@ func (s *Server) GetFeatures(ctx context.Context, msg *proto.GetFeaturesRequest)
 	return features, nil
 }
 
-func (s *Server) connect(ctx context.Context, config *profilemanager.Config, statusRecorder *peer.Status, runningChan chan struct{}) error {
-	log.Tracef("running client connection")
-	client := internal.NewConnectClient(ctx, config, statusRecorder)
-	client.SetUpdateManager(s.updateManager)
-	client.SetSyncResponsePersistence(s.persistSyncResponse)
-
-	s.mutex.Lock()
-	s.connectClient = client
-	s.mutex.Unlock()
-
-	if err := client.Run(runningChan, s.logFile); err != nil {
-		return err
-	}
-	return nil
-}
-
 // MDM authority: when the platform-native MDM source sets a kill switch
 // key (regardless of true/false value), that value wins. The CLI flag
 // supplied at service install time is the fallback used only when the
@@ -1836,45 +1705,6 @@ func (s *Server) onSessionExpire() {
 	}
 }
 
-// getConnectWithBackoff returns a backoff with exponential backoff strategy for connection retries
-func getConnectWithBackoff(ctx context.Context) backoff.BackOff {
-	initialInterval := parseEnvDuration(retryInitialIntervalVar, defaultInitialRetryTime)
-	maxInterval := parseEnvDuration(maxRetryIntervalVar, defaultMaxRetryInterval)
-	maxElapsedTime := parseEnvDuration(maxRetryTimeVar, defaultMaxRetryTime)
-	multiplier := defaultRetryMultiplier
-
-	if envValue := os.Getenv(retryMultiplierVar); envValue != "" {
-		// parse the multiplier from the environment variable string value to float64
-		value, err := strconv.ParseFloat(envValue, 64)
-		if err != nil {
-			log.Warnf("unable to parse environment variable %s: %s. using default: %f", retryMultiplierVar, envValue, multiplier)
-		} else {
-			multiplier = value
-		}
-	}
-
-	return backoff.WithContext(&backoff.ExponentialBackOff{
-		InitialInterval:     initialInterval,
-		RandomizationFactor: 1,
-		Multiplier:          multiplier,
-		MaxInterval:         maxInterval,
-		MaxElapsedTime:      maxElapsedTime, // 14 days
-		Stop:                backoff.Stop,
-		Clock:               backoff.SystemClock,
-	}, ctx)
-}
-
-// parseEnvDuration parses the environment variable and returns the duration
-func parseEnvDuration(envVar string, defaultDuration time.Duration) time.Duration {
-	if envValue := os.Getenv(envVar); envValue != "" {
-		if duration, err := time.ParseDuration(envValue); err == nil {
-			return duration
-		}
-		log.Warnf("unable to parse environment variable %s: %s. using default: %s", envVar, envValue, defaultDuration)
-	}
-	return defaultDuration
-}
-
 // sendTerminalNotification sends a terminal notification message
 // to inform the user that the NetBird connection session has expired.
 func sendTerminalNotification() error {

client/server/server_connect_test.go

@@ -15,14 +15,19 @@ import (
 )
 
 func newTestServer() *Server {
-	return &Server{
-		rootCtx:        context.Background(),
+	ctx := context.Background()
+	s := &Server{
+		rootCtx:        ctx,
 		statusRecorder: peer.NewRecorder(""),
 	}
+	// Honor the production invariant: the daemon-lifetime client always exists
+	// (built in New). Server methods rely on s.connectClient being non-nil.
+	s.connectClient = internal.NewConnectClient(ctx, s.statusRecorder)
+	return s
 }
 
 func newDummyConnectClient(ctx context.Context) *internal.ConnectClient {
-	return internal.NewConnectClient(ctx, nil, nil)
+	return internal.NewConnectClient(ctx, nil)
 }
 
 // TestConnectSetsClientWithMutex validates that connect() sets s.connectClient
@@ -87,41 +92,36 @@ func TestConcurrentConnectClientAccess(t *testing.T) {
 	assert.Equal(t, 50, nilCount+setCount, "all goroutines should complete without panic")
 }
 
-// TestCleanupConnection_ClearsConnectClient validates that cleanupConnection
-// properly nils out connectClient.
-func TestCleanupConnection_ClearsConnectClient(t *testing.T) {
+// TestCleanupConnection_KeepsClientStopsRunning validates that cleanupConnection
+// clears the daemon "up" intent but KEEPS the daemon-lifetime ConnectClient
+// (it is reused across Up/Down; only the run is stopped).
+func TestCleanupConnection_KeepsClientStopsRunning(t *testing.T) {
 	s := newTestServer()
 	_, cancel := context.WithCancel(context.Background())
 	s.actCancel = cancel
 
-	s.connectClient = newDummyConnectClient(context.Background())
-	s.clientRunning = true
-
 	err := s.cleanupConnection()
 	require.NoError(t, err)
 
-	assert.Nil(t, s.connectClient, "connectClient should be nil after cleanup")
-	assert.False(t, s.clientRunning, "clientRunning should be cleared after cleanup (intent = down)")
+	assert.NotNil(t, s.connectClient, "connectClient is daemon-lifetime and must persist after cleanup")
+	assert.False(t, s.connectClient.ConnectionRunning(), "no run should be in flight after cleanup")
 }
 
-// TestCleanState_NilConnectClient validates that CleanState doesn't panic
-// when connectClient is nil.
-func TestCleanState_NilConnectClient(t *testing.T) {
+// TestCleanState_NotConnected validates that CleanState doesn't panic when no
+// connection run is in flight.
+func TestCleanState_NotConnected(t *testing.T) {
 	s := newTestServer()
-	s.connectClient = nil
-	s.profileManager = nil // will cause error if it tries to proceed past the nil check
+	s.profileManager = nil // will cause error if it tries to proceed
 
-	// Should not panic — the nil check should prevent calling Status() on nil
 	assert.NotPanics(t, func() {
 		_, _ = s.CleanState(context.Background(), &proto.CleanStateRequest{All: true})
 	})
 }
 
-// TestDeleteState_NilConnectClient validates that DeleteState doesn't panic
-// when connectClient is nil.
-func TestDeleteState_NilConnectClient(t *testing.T) {
+// TestDeleteState_NotConnected validates that DeleteState doesn't panic when no
+// connection run is in flight.
+func TestDeleteState_NotConnected(t *testing.T) {
 	s := newTestServer()
-	s.connectClient = nil
 	s.profileManager = nil
 
 	assert.NotPanics(t, func() {
@@ -129,60 +129,6 @@ func TestDeleteState_NilConnectClient(t *testing.T) {
 	})
 }
 
-// TestDownThenUp_StaleRunningChan documents the known state issue where
-// clientRunningChan from a previous connection is already closed, causing
-// waitForUp() to return immediately on reconnect.
-func TestDownThenUp_StaleRunningChan(t *testing.T) {
-	s := newTestServer()
-
-	// Simulate state after a successful connection
-	s.clientRunning = true
-	s.clientRunningChan = make(chan struct{})
-	close(s.clientRunningChan) // closed when engine started
-	s.clientGiveUpChan = make(chan struct{})
-	s.connectClient = newDummyConnectClient(context.Background())
-
-	_, cancel := context.WithCancel(context.Background())
-	s.actCancel = cancel
-
-	// Simulate Down(): cleanupConnection sets connectClient = nil and
-	// flips clientRunning to false (intent = down). The connectionGoroutineRunning state
-	// remains independent of intent — derived from clientGiveUpChan.
-	s.mutex.Lock()
-	err := s.cleanupConnection()
-	s.mutex.Unlock()
-	require.NoError(t, err)
-
-	// After cleanup: connectClient is nil, clientRunning is false (intent
-	// cleared by cleanupConnection), connectionGoroutineRunning may still be true
-	// (goroutine teardown is independent of the intent flag).
-	s.mutex.Lock()
-	assert.Nil(t, s.connectClient, "connectClient should be nil after cleanup")
-	assert.False(t, s.clientRunning, "clientRunning should be cleared by cleanupConnection (intent = down)")
-	s.mutex.Unlock()
-
-	// waitForUp() returns immediately due to stale closed clientRunningChan
-	ctx, ctxCancel := context.WithTimeout(context.Background(), 2*time.Second)
-	defer ctxCancel()
-
-	waitDone := make(chan error, 1)
-	go func() {
-		_, err := s.waitForUp(ctx)
-		waitDone <- err
-	}()
-
-	select {
-	case err := <-waitDone:
-		assert.NoError(t, err, "waitForUp returns success on stale channel")
-		// But connectClient is still nil — this is the stale state issue
-		s.mutex.Lock()
-		assert.Nil(t, s.connectClient, "connectClient is nil despite waitForUp success")
-		s.mutex.Unlock()
-	case <-time.After(1 * time.Second):
-		t.Fatal("waitForUp should have returned immediately due to stale closed channel")
-	}
-}
-
 // TestConnectClient_EngineNilOnFreshClient validates that a newly created
 // ConnectClient has nil Engine (before Run is called).
 func TestConnectClient_EngineNilOnFreshClient(t *testing.T) {

client/server/server_test.go

@@ -31,7 +31,6 @@ import (
 	"google.golang.org/grpc/keepalive"
 
 	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/peer"
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	daemonProto "github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/management/server"
@@ -61,65 +60,6 @@ var (
 	}
 )
 
-// TestConnectWithRetryRuns checks that the connectWithRetry function runs and runs the retries according to the times specified via environment variables
-// we will use a management server started via to simulate the server and capture the number of retries
-func TestConnectWithRetryRuns(t *testing.T) {
-	// start the signal server
-	_, signalAddr, err := startSignal(t)
-	if err != nil {
-		t.Fatalf("failed to start signal server: %v", err)
-	}
-
-	counter := 0
-	// start the management server
-	_, mgmtAddr, err := startManagement(t, signalAddr, &counter)
-	if err != nil {
-		t.Fatalf("failed to start management server: %v", err)
-	}
-
-	ctx := internal.CtxInitState(context.Background())
-
-	ctx, cancel := context.WithDeadline(ctx, time.Now().Add(30*time.Second))
-	defer cancel()
-	// create new server
-	ic := profilemanager.ConfigInput{
-		ManagementURL: "http://" + mgmtAddr,
-		ConfigPath:    t.TempDir() + "/test-profile.json",
-	}
-
-	config, err := profilemanager.UpdateOrCreateConfig(ic)
-	if err != nil {
-		t.Fatalf("failed to create config: %v", err)
-	}
-
-	currUser, err := user.Current()
-	require.NoError(t, err)
-
-	pm := profilemanager.ServiceManager{}
-	err = pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     "test-profile",
-		Username: currUser.Username,
-	})
-	if err != nil {
-		t.Fatalf("failed to set active profile state: %v", err)
-	}
-
-	s := New(ctx, "debug", "", false, false, false, false)
-
-	s.config = config
-
-	s.statusRecorder = peer.NewRecorder(config.ManagementURL.String())
-	t.Setenv(retryInitialIntervalVar, "1s")
-	t.Setenv(maxRetryIntervalVar, "2s")
-	t.Setenv(maxRetryTimeVar, "5s")
-	t.Setenv(retryMultiplierVar, "1")
-
-	s.connectWithRetryRuns(ctx, config, s.statusRecorder, nil, nil)
-	if counter < 3 {
-		t.Fatalf("expected counter > 2, got %d", counter)
-	}
-}
-
 func TestServer_Up(t *testing.T) {
 	tempDir := t.TempDir()
 	origDefaultProfileDir := profilemanager.DefaultConfigPathDir
@@ -158,7 +98,7 @@ func TestServer_Up(t *testing.T) {
 
 	pm := profilemanager.ServiceManager{}
 	err = pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     profName,
+		ID:       profilemanager.ID(profName),
 		Username: currUser.Username,
 	})
 	if err != nil {
@@ -228,7 +168,7 @@ func TestServer_SubcribeEvents(t *testing.T) {
 
 	pm := profilemanager.ServiceManager{}
 	err = pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     "default",
+		ID:       "default",
 		Username: currUser.Username,
 	})
 	if err != nil {

client/server/setconfig_mdm_test.go

@@ -62,7 +62,7 @@ func setupServerWithProfile(t *testing.T) (s *Server, ctx context.Context, profN
 
 	pm := profilemanager.ServiceManager{}
 	require.NoError(t, pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     profName,
+		ID:       profilemanager.ID(profName),
 		Username: currUser.Username,
 	}))
 
@@ -107,9 +107,9 @@ func TestSetConfig_MDMReject_SingleField(t *testing.T) {
 
 func TestSetConfig_MDMReject_MultipleFields(t *testing.T) {
 	withMDMPolicy(t, mdm.NewPolicy(map[string]any{
-		mdm.KeyManagementURL:     "https://mdm.example.com:443",
-		mdm.KeyBlockInbound:      true,
-		mdm.KeyRosenpassEnabled:  true,
+		mdm.KeyManagementURL:    "https://mdm.example.com:443",
+		mdm.KeyBlockInbound:     true,
+		mdm.KeyRosenpassEnabled: true,
 	}))
 
 	s, ctx, profName, username, _ := setupServerWithProfile(t)

client/server/setconfig_test.go

@@ -47,7 +47,7 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 
 	pm := profilemanager.ServiceManager{}
 	err = pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     profName,
+		ID:       profilemanager.ID(profName),
 		Username: currUser.Username,
 	})
 	require.NoError(t, err)
@@ -96,7 +96,7 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 		DisableNotifications:  &disableNotifications,
 		LazyConnectionEnabled: &lazyConnectionEnabled,
 		BlockInbound:          &blockInbound,
-		DisableIpv6:          &disableIPv6,
+		DisableIpv6:           &disableIPv6,
 		NatExternalIPs:        []string{"1.2.3.4", "5.6.7.8"},
 		CleanNATExternalIPs:   false,
 		CustomDNSAddress:      []byte("1.1.1.1:53"),
@@ -112,7 +112,7 @@ func TestSetConfig_AllFieldsSaved(t *testing.T) {
 	require.NoError(t, err)
 
 	profState := profilemanager.ActiveProfileState{
-		Name:     profName,
+		ID:       profilemanager.ID(profName),
 		Username: currUser.Username,
 	}
 	cfgPath, err := profState.FilePath()

client/server/state.go

@@ -9,7 +9,6 @@ import (
 	"google.golang.org/grpc/status"
 
 	nberrors "github.com/netbirdio/netbird/client/errors"
-	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/routemanager/systemops"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/proto"
@@ -38,7 +37,7 @@ func (s *Server) ListStates(_ context.Context, _ *proto.ListStatesRequest) (*pro
 
 // CleanState handles cleaning of states (performing cleanup operations)
 func (s *Server) CleanState(ctx context.Context, req *proto.CleanStateRequest) (*proto.CleanStateResponse, error) {
-	if s.connectClient != nil && (s.connectClient.Status() == internal.StatusConnected || s.connectClient.Status() == internal.StatusConnecting) {
+	if s.connectClient.ConnectionRunning() {
 		return nil, status.Errorf(codes.FailedPrecondition, "cannot clean state while connecting or connected, run 'netbird down' first.")
 	}
 
@@ -81,7 +80,7 @@ func (s *Server) CleanState(ctx context.Context, req *proto.CleanStateRequest) (
 
 // DeleteState handles deletion of states without cleanup
 func (s *Server) DeleteState(ctx context.Context, req *proto.DeleteStateRequest) (*proto.DeleteStateResponse, error) {
-	if s.connectClient != nil && (s.connectClient.Status() == internal.StatusConnected || s.connectClient.Status() == internal.StatusConnecting) {
+	if s.connectClient.ConnectionRunning() {
 		return nil, status.Errorf(codes.FailedPrecondition, "cannot clean state while connecting or connected, run 'netbird down' first.")
 	}
 

client/server/trace.go

@@ -62,10 +62,6 @@ func (s *Server) TracePacket(_ context.Context, req *proto.TracePacketRequest) (
 }
 
 func (s *Server) getPacketTracer() (packetTracer, *internal.Engine, error) {
-	if s.connectClient == nil {
-		return nil, nil, fmt.Errorf("connect client not initialized")
-	}
-
 	engine := s.connectClient.Engine()
 	if engine == nil {
 		return nil, nil, fmt.Errorf("engine not initialized")

client/ui/client_ui.go

@@ -645,7 +645,7 @@ func (s *serviceClient) buildSetConfigRequest(iMngURL string, port, mtu int64) (
 	}
 
 	req := &proto.SetConfigRequest{
-		ProfileName: activeProf.Name,
+		ProfileName: activeProf.ID.String(),
 		Username:    currUser.Username,
 	}
 
@@ -818,13 +818,15 @@ func (s *serviceClient) login(ctx context.Context, openURL bool) (*proto.LoginRe
 		return nil, fmt.Errorf("get current user: %w", err)
 	}
 
+	handle := activeProf.ID.String()
+
 	loginReq := &proto.LoginRequest{
 		IsUnixDesktopClient: runtime.GOOS == "linux" || runtime.GOOS == "freebsd",
-		ProfileName:         &activeProf.Name,
+		ProfileName:         &handle,
 		Username:            &currUser.Username,
 	}
 
-	profileState, err := s.profileManager.GetProfileState(activeProf.Name)
+	profileState, err := s.profileManager.GetProfileState(activeProf.ID)
 	if err != nil {
 		log.Debugf("failed to get profile state for login hint: %v", err)
 	} else if profileState.Email != "" {
@@ -1367,7 +1369,7 @@ func (s *serviceClient) getSrvConfig() {
 	}
 
 	srvCfg, err := conn.GetConfig(s.ctx, &proto.GetConfigRequest{
-		ProfileName: activeProf.Name,
+		ProfileName: activeProf.ID.String(),
 		Username:    currUser.Username,
 	})
 	if err != nil {
@@ -1613,7 +1615,7 @@ func (s *serviceClient) loadSettings() {
 	}
 
 	cfg, err := conn.GetConfig(s.ctx, &proto.GetConfigRequest{
-		ProfileName: activeProf.Name,
+		ProfileName: activeProf.ID.String(),
 		Username:    currUser.Username,
 	})
 	if err != nil {
@@ -1813,7 +1815,7 @@ func (s *serviceClient) updateConfig() error {
 	}
 
 	req := proto.SetConfigRequest{
-		ProfileName:           activeProf.Name,
+		ProfileName:           activeProf.ID.String(),
 		Username:              currUser.Username,
 		DisableAutoConnect:    &disableAutoStart,
 		ServerSSHAllowed:      &sshAllowed,

client/ui/profile.go

@@ -66,7 +66,7 @@ func (s *serviceClient) showProfilesUI() {
 			} else {
 				indicator.SetText("")
 			}
-			nameLabel.SetText(profile.Name)
+			nameLabel.SetText(formatProfileLabel(profile, profiles))
 
 			// Configure Select/Active button
 			selectBtn.SetText(func() string {
@@ -88,7 +88,7 @@ func (s *serviceClient) showProfilesUI() {
 							return
 						}
 						// switch
-						err = s.switchProfile(profile.Name)
+						err = s.switchProfile(profile.ID)
 						if err != nil {
 							log.Errorf("failed to switch profile: %v", err)
 							dialog.ShowError(errors.New("failed to select profile"), s.wProfiles)
@@ -130,7 +130,7 @@ func (s *serviceClient) showProfilesUI() {
 			logoutBtn.Show()
 			logoutBtn.SetText("Deregister")
 			logoutBtn.OnTapped = func() {
-				s.handleProfileLogout(profile.Name, refresh)
+				s.handleProfileLogout(profile, refresh)
 			}
 
 			// Remove profile
@@ -144,7 +144,7 @@ func (s *serviceClient) showProfilesUI() {
 							return
 						}
 
-						err = s.removeProfile(profile.Name)
+						err = s.removeProfile(profile.ID)
 						if err != nil {
 							log.Errorf("failed to remove profile: %v", err)
 							dialog.ShowError(fmt.Errorf("failed to remove profile"), s.wProfiles)
@@ -250,7 +250,7 @@ func (s *serviceClient) addProfile(profileName string) error {
 	return nil
 }
 
-func (s *serviceClient) switchProfile(profileName string) error {
+func (s *serviceClient) switchProfile(handle string) error {
 	conn, err := s.getSrvClient(defaultFailTimeout)
 	if err != nil {
 		return fmt.Errorf(getClientFMT, err)
@@ -261,15 +261,15 @@ func (s *serviceClient) switchProfile(profileName string) error {
 		return fmt.Errorf("get current user: %w", err)
 	}
 
-	if _, err := conn.SwitchProfile(s.ctx, &proto.SwitchProfileRequest{
-		ProfileName: &profileName,
+	resp, err := conn.SwitchProfile(s.ctx, &proto.SwitchProfileRequest{
+		ProfileName: &handle,
 		Username:    &currUser.Username,
-	}); err != nil {
+	})
+	if err != nil {
 		return fmt.Errorf("switch profile failed: %w", err)
 	}
 
-	err = s.profileManager.SwitchProfile(profileName)
-	if err != nil {
+	if err := s.profileManager.SwitchProfile(profilemanager.ID(resp.Id)); err != nil {
 		return fmt.Errorf("switch profile: %w", err)
 	}
 
@@ -299,10 +299,27 @@ func (s *serviceClient) removeProfile(profileName string) error {
 }
 
 type Profile struct {
+	ID       string
 	Name     string
 	IsActive bool
 }
 
+// formatProfileLabel returns the display label for a profile. Profiles can
+// share the same Name, so when more than one profile in profiles carries this
+// Name, a short form of the ID is appended to disambiguate the entries.
+func formatProfileLabel(profile Profile, profiles []Profile) string {
+	count := 0
+	for _, p := range profiles {
+		if p.Name == profile.Name {
+			count++
+		}
+	}
+	if count <= 1 {
+		return profile.Name
+	}
+	return fmt.Sprintf("%s (%s)", profile.Name, profilemanager.ID(profile.ID).ShortID())
+}
+
 func (s *serviceClient) getProfiles() ([]Profile, error) {
 	conn, err := s.getSrvClient(defaultFailTimeout)
 	if err != nil {
@@ -324,6 +341,7 @@ func (s *serviceClient) getProfiles() ([]Profile, error) {
 
 	for _, profile := range profilesResp.Profiles {
 		profiles = append(profiles, Profile{
+			ID:       profile.Id,
 			Name:     profile.Name,
 			IsActive: profile.IsActive,
 		})
@@ -332,10 +350,10 @@ func (s *serviceClient) getProfiles() ([]Profile, error) {
 	return profiles, nil
 }
 
-func (s *serviceClient) handleProfileLogout(profileName string, refreshCallback func()) {
+func (s *serviceClient) handleProfileLogout(profile Profile, refreshCallback func()) {
 	dialog.ShowConfirm(
 		"Deregister",
-		fmt.Sprintf("Are you sure you want to deregister from '%s'?", profileName),
+		fmt.Sprintf("Are you sure you want to deregister from '%s'?", profile.Name),
 		func(confirm bool) {
 			if !confirm {
 				return
@@ -356,8 +374,10 @@ func (s *serviceClient) handleProfileLogout(profileName string, refreshCallback
 			}
 
 			username := currUser.Username
+			// ProfileName is treated as a handle; send the ID so the
+			// daemon resolves to exactly this profile.
 			_, err = conn.Logout(s.ctx, &proto.LogoutRequest{
-				ProfileName: &profileName,
+				ProfileName: &profile.ID,
 				Username:    &username,
 			})
 			if err != nil {
@@ -368,7 +388,7 @@ func (s *serviceClient) handleProfileLogout(profileName string, refreshCallback
 
 			dialog.ShowInformation(
 				"Deregistered",
-				fmt.Sprintf("Successfully deregistered from '%s'", profileName),
+				fmt.Sprintf("Successfully deregistered from '%s'", profile.Name),
 				s.wProfiles,
 			)
 
@@ -461,6 +481,7 @@ func (p *profileMenu) getProfiles() ([]Profile, error) {
 
 	for _, profile := range profilesResp.Profiles {
 		profiles = append(profiles, Profile{
+			ID:       profile.Id,
 			Name:     profile.Name,
 			IsActive: profile.IsActive,
 		})
@@ -501,7 +522,7 @@ func (p *profileMenu) refresh() {
 	}
 
 	if activeProf.ProfileName == "default" || activeProf.Username == currUser.Username {
-		activeProfState, err := p.profileManager.GetProfileState(activeProf.ProfileName)
+		activeProfState, err := p.profileManager.GetProfileState(profilemanager.ID(activeProf.Id))
 		if err != nil {
 			log.Warnf("failed to get active profile state: %v", err)
 			p.emailMenuItem.Hide()
@@ -512,7 +533,7 @@ func (p *profileMenu) refresh() {
 	}
 
 	for _, profile := range profiles {
-		item := p.profileMenuItem.AddSubMenuItem(profile.Name, "")
+		item := p.profileMenuItem.AddSubMenuItem(formatProfileLabel(profile, profiles), "")
 		if profile.IsActive {
 			item.Check()
 		}
@@ -541,8 +562,8 @@ func (p *profileMenu) refresh() {
 						return
 					}
 
-					_, err = conn.SwitchProfile(ctx, &proto.SwitchProfileRequest{
-						ProfileName: &profile.Name,
+					switchResp, err := conn.SwitchProfile(ctx, &proto.SwitchProfileRequest{
+						ProfileName: &profile.ID,
 						Username:    &currUser.Username,
 					})
 					if err != nil {
@@ -552,7 +573,7 @@ func (p *profileMenu) refresh() {
 						return
 					}
 
-					err = p.profileManager.SwitchProfile(profile.Name)
+					err = p.profileManager.SwitchProfile(profilemanager.ID(switchResp.Id))
 					if err != nil {
 						log.Errorf("failed to switch profile '%s': %v", profile.Name, err)
 						return
@@ -727,7 +748,10 @@ func (p *profileMenu) updateMenu() {
 			}
 
 			sort.Slice(profiles, func(i, j int) bool {
-				return profiles[i].Name < profiles[j].Name
+				if profiles[i].Name != profiles[j].Name {
+					return profiles[i].Name < profiles[j].Name
+				}
+				return profiles[i].ID < profiles[j].ID
 			})
 
 			p.mu.Lock()

docker/build-env/README.md

@@ -0,0 +1,56 @@
+# Build environments
+
+Dockerfiles that pin the same toolchain CI uses, so a developer can
+reproduce a CI build locally without installing platform SDKs on their
+workstation. The version pins in each `Dockerfile` must stay in lockstep
+with `.github/workflows/`.
+
+## `android/`
+
+Mirrors `.github/workflows/mobile-build-validation.yml` (`android_build`
+job). Carries Go 1.25.5, Adopt JDK 11, Android cmdline-tools 8512546,
+NDK 23.1.7779620 and gomobile pinned at the CI commit. Use it to
+produce `netbird.aar` from `./client/android`:
+
+```bash
+docker build -t netbird/build-android docker/build-env/android
+docker run --rm -v "$PWD:/src" -w /src netbird/build-android \
+    gomobile bind \
+    -o netbird.aar \
+    -javapkg=io.netbird.gomobile \
+    -ldflags="-checklinkname=0 \
+              -X golang.zx2c4.com/wireguard/ipc.socketDirectory=/data/data/io.netbird.client/cache/wireguard \
+              -X github.com/netbirdio/netbird/version.version=local" \
+    ./client/android
+```
+
+To build the full Android APK, bind-mount the `android-client` repo as
+well and run its own `./gradlew assembleDebug` from inside the
+container (the gradle wrapper ships with `android-client`).
+
+## `windows-cross/`
+
+Cross-compiles Windows binaries from Linux using `mingw-w64`. Lets you
+verify that `GOOS=windows go build ./...` compiles cleanly without
+needing a Windows VM. Cannot run Windows tests — the `golang-test-windows`
+CI job executes on a native `windows-latest` runner with wintun.dll
+and PsExec, neither of which lives under Linux containers.
+
+```bash
+docker build -t netbird/build-windows docker/build-env/windows-cross
+docker run --rm -v "$PWD:/src" -w /src netbird/build-windows \
+    bash -c 'GOOS=windows GOARCH=amd64 go build ./...'
+```
+
+## What is NOT here
+
+- **iOS / macOS**: cannot legally run macOS in Docker (Apple EULA),
+  and Xcode is not redistributable. The `ios_build` CI job uses a
+  `macos-latest` GitHub runner; locally you need a real Mac.
+
+- **Native Windows tests**: see note above. The Linux+mingw image
+  builds, it does not execute Windows-host code paths
+  (registry, wintun, services, PsExec workflows).
+
+When CI version pins change, update the corresponding `ARG` lines in
+the Dockerfiles and the README's table of versions.

docker/build-env/android/Dockerfile

@@ -0,0 +1,86 @@
+# Android build environment.
+#
+# Mirrors the toolchain pinned by .github/workflows/mobile-build-validation.yml
+# so a `gomobile bind` against ./client/android in this image produces the
+# same netbird.aar that CI builds.
+#
+# Tooling versions (must stay in sync with the CI workflow):
+#   - Ubuntu 22.04 (matches the ubuntu-latest GitHub runner)
+#   - Go 1.25.5 (matches go.mod)
+#   - Adopt JDK 11 (matches actions/setup-java@v3 java-version: 11, distribution: adopt)
+#   - Android SDK cmdline-tools 8512546
+#   - Android NDK 23.1.7779620
+#   - gomobile commit v0.0.0-20251113184115-a159579294ab
+#
+# Usage (from the netbird repo root):
+#
+#   docker build -t netbird/build-android docker/build-env/android
+#
+#   # bind the netbird checkout in and run the same gomobile command CI runs
+#   docker run --rm -v "$PWD:/src" -w /src netbird/build-android \
+#       gomobile bind \
+#       -o netbird.aar \
+#       -javapkg=io.netbird.gomobile \
+#       -ldflags="-checklinkname=0 \
+#                 -X golang.zx2c4.com/wireguard/ipc.socketDirectory=/data/data/io.netbird.client/cache/wireguard \
+#                 -X github.com/netbirdio/netbird/version.version=local" \
+#       ./client/android
+#
+# To build the full APK, mount the android-client repo too and run
+# `./gradlew assembleDebug` from /android-client (this image carries
+# gradle's prerequisites JDK + Android SDK but not the gradle wrapper —
+# that ships with android-client).
+
+FROM ubuntu:22.04
+
+ARG DEBIAN_FRONTEND=noninteractive
+
+# Versions — bump in lockstep with .github/workflows/mobile-build-validation.yml.
+ARG GO_VERSION=1.25.5
+ARG ANDROID_CMDLINE_TOOLS_VERSION=8512546
+ARG ANDROID_NDK_VERSION=23.1.7779620
+ARG GOMOBILE_VERSION=v0.0.0-20251113184115-a159579294ab
+
+ENV ANDROID_HOME=/opt/android-sdk
+ENV ANDROID_NDK_HOME=${ANDROID_HOME}/ndk/${ANDROID_NDK_VERSION}
+ENV JAVA_HOME=/usr/lib/jvm/java-11-openjdk-amd64
+ENV GOPATH=/go
+ENV GOTOOLCHAIN=local
+ENV CGO_ENABLED=0
+ENV PATH=${GOPATH}/bin:/usr/local/go/bin:${ANDROID_HOME}/cmdline-tools/latest/bin:${ANDROID_HOME}/platform-tools:${JAVA_HOME}/bin:${PATH}
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        ca-certificates \
+        curl \
+        unzip \
+        git \
+        openjdk-11-jdk-headless \
+        build-essential \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Go (matches go.mod). actions/setup-go fetches the same tarball.
+RUN curl -fsSL "https://go.dev/dl/go${GO_VERSION}.linux-amd64.tar.gz" \
+        | tar -C /usr/local -xz \
+    && go version
+
+# Install Android SDK command-line tools, accept licenses, install NDK.
+RUN mkdir -p "${ANDROID_HOME}/cmdline-tools" \
+    && curl -fsSL -o /tmp/cmdline.zip \
+        "https://dl.google.com/android/repository/commandlinetools-linux-${ANDROID_CMDLINE_TOOLS_VERSION}_latest.zip" \
+    && unzip -q /tmp/cmdline.zip -d "${ANDROID_HOME}/cmdline-tools" \
+    && mv "${ANDROID_HOME}/cmdline-tools/cmdline-tools" "${ANDROID_HOME}/cmdline-tools/latest" \
+    && rm /tmp/cmdline.zip \
+    && yes | sdkmanager --licenses > /dev/null \
+    && sdkmanager --install "ndk;${ANDROID_NDK_VERSION}" "platform-tools" > /dev/null
+
+# Install gomobile at the same commit CI pins. Don't run `gomobile init` here:
+# `init` resolves the NDK at runtime, do it on the first bind in the mounted
+# workspace so the cache lands on the host volume.
+RUN GOBIN=/usr/local/bin go install "golang.org/x/mobile/cmd/gomobile@${GOMOBILE_VERSION}" \
+    && gomobile version
+
+WORKDIR /src
+
+# Default entrypoint is a plain shell so the image is composable: callers pass
+# the full gomobile / gradle command they want to run.
+CMD ["/bin/bash"]

docker/build-env/windows-cross/Dockerfile

@@ -0,0 +1,63 @@
+# Windows-cross build environment.
+#
+# Cross-compiles Windows .exe targets from a Linux container using
+# mingw-w64. Mirrors the toolchain set used by
+# .github/workflows/golang-test-windows.yml insofar as that is possible
+# without a Windows kernel.
+#
+# IMPORTANT — what this image CAN do:
+#   - `GOOS=windows go build ./...` to validate that Windows builds compile
+#   - CGO Windows cross-compile via x86_64-w64-mingw32-gcc when CGO_ENABLED=1
+#     (matches CI's choco-installed mingw-w64)
+#
+# IMPORTANT — what this image CANNOT do:
+#   - Run Windows binaries (no Windows kernel under Docker on Linux).
+#   - Replicate the CI's `go test` runs which execute on a real
+#     windows-latest runner (wintun.dll, PsExec, registry, etc.).
+#     Use the CI for that or a native Windows VM.
+#
+# Usage (from the netbird repo root):
+#
+#   docker build -t netbird/build-windows docker/build-env/windows-cross
+#
+#   # Cross-compile a static client (.exe) from Linux:
+#   docker run --rm -v "$PWD:/src" -w /src netbird/build-windows \
+#       bash -c 'CGO_ENABLED=1 GOOS=windows GOARCH=amd64 \
+#           CC=x86_64-w64-mingw32-gcc CXX=x86_64-w64-mingw32-g++ \
+#           go build -o netbird.exe ./client'
+#
+#   # Just validate that everything *compiles* on Windows (no CGO):
+#   docker run --rm -v "$PWD:/src" -w /src netbird/build-windows \
+#       bash -c 'GOOS=windows GOARCH=amd64 go build ./...'
+#
+# Tooling versions (keep in sync with go.mod and any future explicit pin
+# documented in golang-test-windows.yml):
+#   - Ubuntu 22.04
+#   - Go 1.25.5 (matches go.mod)
+#   - mingw-w64 (Ubuntu package — pin further if drift becomes a problem)
+
+FROM ubuntu:22.04
+
+ARG DEBIAN_FRONTEND=noninteractive
+ARG GO_VERSION=1.25.5
+
+ENV GOPATH=/go
+ENV GOTOOLCHAIN=local
+ENV PATH=${GOPATH}/bin:/usr/local/go/bin:${PATH}
+
+RUN apt-get update && apt-get install -y --no-install-recommends \
+        ca-certificates \
+        curl \
+        git \
+        build-essential \
+        mingw-w64 \
+    && rm -rf /var/lib/apt/lists/*
+
+# Install Go (matches go.mod).
+RUN curl -fsSL "https://go.dev/dl/go${GO_VERSION}.linux-amd64.tar.gz" \
+        | tar -C /usr/local -xz \
+    && go version
+
+WORKDIR /src
+
+CMD ["/bin/bash"]

signal/peer/peer.go

@@ -26,6 +26,10 @@ type Peer struct {
 
 	// a gRpc connection stream to the Peer
 	Stream proto.SignalExchange_ConnectStreamServer
+	// sendMu serializes writes to Stream. gRPC forbids concurrent SendMsg on
+	// the same ServerStream, and a peer can be the target of many senders at
+	// once.
+	sendMu sync.Mutex
 
 	// registration time
 	RegisteredAt time.Time
@@ -33,6 +37,13 @@ type Peer struct {
 	Cancel context.CancelFunc
 }
 
+// Send writes a message to the peer's stream, serializing concurrent senders.
+func (p *Peer) Send(msg *proto.EncryptedMessage) error {
+	p.sendMu.Lock()
+	defer p.sendMu.Unlock()
+	return p.Stream.Send(msg)
+}
+
 // NewPeer creates a new instance of a connected Peer
 func NewPeer(id string, stream proto.SignalExchange_ConnectStreamServer, cancel context.CancelFunc) *Peer {
 	return &Peer{

signal/server/concurrent_send_test.go

@@ -0,0 +1,67 @@
+package server
+
+import (
+	"context"
+	"sync"
+	"sync/atomic"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/require"
+	"go.opentelemetry.io/otel"
+
+	"github.com/netbirdio/netbird/shared/signal/proto"
+	"github.com/netbirdio/netbird/signal/peer"
+)
+
+// concurrencyCheckStream records the maximum number of Send calls in flight at
+// once. gRPC forbids concurrent SendMsg on the same ServerStream, so a correct
+// server must never have more than one in flight per peer.
+type concurrencyCheckStream struct {
+	proto.SignalExchange_ConnectStreamServer
+	ctx      context.Context
+	inflight atomic.Int32
+	maxSeen  atomic.Int32
+}
+
+func (s *concurrencyCheckStream) Send(*proto.EncryptedMessage) error {
+	n := s.inflight.Add(1)
+	for {
+		old := s.maxSeen.Load()
+		if n <= old || s.maxSeen.CompareAndSwap(old, n) {
+			break
+		}
+	}
+	// Widen the window so overlapping callers are reliably observed.
+	time.Sleep(time.Millisecond)
+	s.inflight.Add(-1)
+	return nil
+}
+
+func (s *concurrencyCheckStream) Context() context.Context { return s.ctx }
+
+// TestForwardMessageToPeerSerializesSend verifies that concurrent forwards to the
+// same peer never call Stream.Send concurrently, which would violate the gRPC
+// ServerStream contract.
+func TestForwardMessageToPeerSerializesSend(t *testing.T) {
+	s, err := NewServer(context.Background(), otel.Meter(""))
+	require.NoError(t, err)
+
+	const peerID = "peerX"
+	stream := &concurrencyCheckStream{ctx: context.Background()}
+	_, cancel := context.WithCancel(context.Background())
+	t.Cleanup(cancel)
+	require.NoError(t, s.registry.Register(peer.NewPeer(peerID, stream, cancel)))
+
+	var wg sync.WaitGroup
+	for i := 0; i < 50; i++ {
+		wg.Add(1)
+		go func() {
+			defer wg.Done()
+			s.forwardMessageToPeer(context.Background(), &proto.EncryptedMessage{Key: "sender", RemoteKey: peerID})
+		}()
+	}
+	wg.Wait()
+
+	require.Equal(t, int32(1), stream.maxSeen.Load(), "Stream.Send must never run concurrently on the same peer stream")
+}

signal/server/signal.go

@@ -179,7 +179,7 @@ func (s *Server) forwardMessageToPeer(ctx context.Context, msg *proto.EncryptedM
 	sendResultChan := make(chan error, 1)
 	go func() {
 		select {
-		case sendResultChan <- dstPeer.Stream.Send(msg):
+		case sendResultChan <- dstPeer.Send(msg):
 			return
 		case <-dstPeer.Stream.Context().Done():
 			return

util/log.go

@@ -140,7 +140,12 @@ func newRotatedOutput(logPath string) io.Writer {
 func setGRPCLibLogger(logger *log.Logger) {
 	logOut := logger.Writer()
 	if os.Getenv("GRPC_GO_LOG_SEVERITY_LEVEL") != "info" {
-		grpclog.SetLoggerV2(grpclog.NewLoggerV2(io.Discard, logOut, logOut))
+		// Discard grpc info AND warning logs by default — the warning stream is
+		// dominated by benign connection-retry noise ("addrConn.createTransport
+		// failed", "transport is closing") that surfaces e.g. when the CLI dials
+		// a daemon that is still starting or already gone. Errors are kept. Set
+		// GRPC_GO_LOG_SEVERITY_LEVEL=info to get the full verbose grpc logging.
+		grpclog.SetLoggerV2(grpclog.NewLoggerV2(io.Discard, io.Discard, logOut))
 		return
 	}