[client] Fix DNS custom zone teardown: handler leak and external CNAME resolution (#6445)

* Restores behavior to create profile if not there on Up

* Allows to restore nerbird status showing of the profile name

* [client] Reduce upFunc cognitive complexity

Extract the profile switch/auto-create logic from upFunc into a dedicated
switchOrCreateProfile helper. The inlined NotFound-retry branch pushed
upFunc over SonarCloud's cognitive complexity threshold (S3776).
No behavior change.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* [client] Make up --profile auto-create idempotent under concurrent runs

Don't fail switchOrCreateProfile on a createProfile error: a concurrent
run may create the profile between the NotFound check and our create
call. Retry the switch regardless and only surface the create error if
the switch also fails. Addresses CodeRabbit race-condition feedback.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

* Share createProfile with addProfileFunc

* But allow conn reusage

* moves switchOrCreateProfile to where it's used

---------

Co-authored-by: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.goreleaser.yaml

@@ -247,7 +247,7 @@ dockers_v2:
        - netbirdio/netbird
        - ghcr.io/netbirdio/netbird
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: client/Dockerfile
      extra_files:
@@ -295,7 +295,7 @@ dockers_v2:
        - netbirdio/relay
        - ghcr.io/netbirdio/relay
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: relay/Dockerfile
      platforms:
@@ -317,7 +317,7 @@ dockers_v2:
        - netbirdio/signal
        - ghcr.io/netbirdio/signal
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: signal/Dockerfile
      platforms:
@@ -339,7 +339,7 @@ dockers_v2:
        - netbirdio/management
        - ghcr.io/netbirdio/management
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: management/Dockerfile
      platforms:
@@ -361,7 +361,7 @@ dockers_v2:
        - netbirdio/upload
        - ghcr.io/netbirdio/upload
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: upload-server/Dockerfile
      platforms:
@@ -383,7 +383,7 @@ dockers_v2:
        - netbirdio/netbird-server
        - ghcr.io/netbirdio/netbird-server
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: combined/Dockerfile
      platforms:
@@ -405,7 +405,7 @@ dockers_v2:
        - netbirdio/reverse-proxy
        - ghcr.io/netbirdio/reverse-proxy
      tags:
-       - "v{{ .Version }}"
+       - "{{ .Version }}"
        - "{{ if eq .Env.SKIP_PUBLISH \"false\" }}latest{{ end }}"
      dockerfile: proxy/Dockerfile
      platforms:

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: %w", 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 {
@@ -109,6 +138,41 @@ func addProfileFunc(cmd *cobra.Command, args []string) error {
 		return err
 	}
 
+	currUser, err := user.Current()
+	if err != nil {
+		return fmt.Errorf("get current user: %w", err)
+	}
+
+	conn, err := DialClientGRPCServer(cmd.Context(), daemonAddr)
+	if err != nil {
+		return fmt.Errorf("connect to service CLI interface: %w", err)
+	}
+	defer conn.Close()
+
+	daemonClient := proto.NewDaemonServiceClient(conn)
+	profileName := args[0]
+
+	id, err := addProfileOnDaemon(cmd.Context(), daemonClient, profileName, currUser.Username)
+	if err != nil {
+		return 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.")
+	}
+
+	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
+	}
+
 	conn, err := DialClientGRPCServer(cmd.Context(), daemonAddr)
 	if err != nil {
 		return fmt.Errorf("connect to service CLI interface: %w", err)
@@ -121,21 +185,43 @@ func addProfileFunc(cmd *cobra.Command, args []string) error {
 	}
 
 	daemonClient := proto.NewDaemonServiceClient(conn)
+	handle := args[0]
+	newProfilename := args[1]
 
-	profileName := args[0]
-
-	_, err = daemonClient.AddProfile(cmd.Context(), &proto.AddProfileRequest{
-		ProfileName: profileName,
-		Username:    currUser.Username,
+	resp, err := daemonClient.RenameProfile(cmd.Context(), &proto.RenameProfileRequest{
+		Handle:         handle,
+		Username:       currUser.Username,
+		NewProfileName: newProfilename,
 	})
 	if err != nil {
-		return err
+		return wrapAmbiguityError(err, handle)
 	}
 
-	cmd.Println("Profile added successfully:", profileName)
+	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 +239,17 @@ 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 +259,7 @@ 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 +276,15 @@ 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 +299,46 @@ 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
+}
+
+// addProfileOnDaemon issues the AddProfile RPC on an existing daemon client
+// and returns the new profile's ID. It is the single entry point for profile
+// creation, shared by `netbird profile add` and the `netbird up --profile
+// <name>` auto-create path.
+func addProfileOnDaemon(ctx context.Context, client proto.DaemonServiceClient, profileName, username string) (profilemanager.ID, error) {
+	resp, err := client.AddProfile(ctx, &proto.AddProfileRequest{
+		ProfileName: profileName,
+		Username:    username,
+	})
+	if err != nil {
+		return "", fmt.Errorf("add profile failed: %w", err)
+	}
+
+	return profilemanager.ID(resp.Id), nil
+}

client/cmd/root.go

@@ -190,6 +190,7 @@ func init() {
 	// profile commands
 	profileCmd.AddCommand(profileListCmd)
 	profileCmd.AddCommand(profileAddCmd)
+	profileCmd.AddCommand(profileRenameCmd)
 	profileCmd.AddCommand(profileRemoveCmd)
 	profileCmd.AddCommand(profileSelectCmd)
 

client/cmd/status.go

@@ -11,7 +11,6 @@ import (
 	"google.golang.org/grpc/status"
 
 	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 	nbstatus "github.com/netbirdio/netbird/client/status"
 	"github.com/netbirdio/netbird/util"
@@ -111,11 +110,10 @@ func statusFunc(cmd *cobra.Command, args []string) error {
 		return nil
 	}
 
-	pm := profilemanager.NewProfileManager()
-	var profName string
-	if activeProf, err := pm.GetActiveProfile(); err == nil {
-		profName = activeProf.Name
-	}
+	// Resolve the active profile's display name via the daemon, which runs
+	// as root and can read the per-user profile files. The local profile
+	// manager only knows the active profile ID, not its display name.
+	profName := getActiveProfileName(ctx)
 
 	var outputInformationHolder = nbstatus.ConvertToStatusOutputOverview(resp.GetFullStatus(), nbstatus.ConvertOptions{
 		Anonymize:            anonymizeFlag,
@@ -167,6 +165,25 @@ func getStatus(ctx context.Context, fullPeerStatus bool, shouldRunProbes bool) (
 	return resp, nil
 }
 
+// getActiveProfileName asks the daemon for the active profile's display
+// name. The daemon runs as root and can read the per-user profile files to
+// resolve the ID to its human-readable name. Returns an empty string on any
+// error so status output degrades gracefully.
+func getActiveProfileName(ctx context.Context) string {
+	conn, err := DialClientGRPCServer(ctx, daemonAddr)
+	if err != nil {
+		return ""
+	}
+	defer conn.Close()
+
+	resp, err := proto.NewDaemonServiceClient(conn).GetActiveProfile(ctx, &proto.GetActiveProfileRequest{})
+	if err != nil {
+		return ""
+	}
+
+	return resp.GetProfileName()
+}
+
 func parseFilters() error {
 	switch strings.ToLower(statusFilter) {
 	case "", "idle", "connecting", "connected":

client/cmd/up.go

@@ -128,16 +128,9 @@ func upFunc(cmd *cobra.Command, args []string) error {
 	var profileSwitched bool
 	// switch profile if provided
 	if profileName != "" {
-		err = switchProfile(cmd.Context(), profileName, username.Username)
-		if err != nil {
+		if err := switchOrCreateProfile(cmd.Context(), pm, profileName, username.Username); err != nil {
 			return fmt.Errorf("switch profile: %v", err)
 		}
-
-		err = pm.SwitchProfile(profileName)
-		if err != nil {
-			return fmt.Errorf("switch profile: %v", err)
-		}
-
 		profileSwitched = true
 	}
 
@@ -152,6 +145,52 @@ func upFunc(cmd *cobra.Command, args []string) error {
 	return runInDaemonMode(ctx, cmd, pm, activeProf, profileSwitched)
 }
 
+// switchOrCreateProfile switches the active profile to the one identified by
+// handle, creating it first when it does not exist yet. This restores the
+// pre-0.73 behaviour where `netbird up --profile <name>` auto-creates a
+// missing profile instead of failing.
+func switchOrCreateProfile(ctx context.Context, pm *profilemanager.ProfileManager, handle, username string) error {
+	resolvedID, err := switchProfile(ctx, handle, username)
+	if err != nil {
+		st, ok := gstatus.FromError(err)
+		if !ok || st.Code() != codes.NotFound {
+			return err
+		}
+		// Don't fail immediately on a create error: a concurrent run may
+		// have created the profile between the NotFound above and this
+		// call, in which case the retried switch still succeeds. Only
+		// surface the create error if the switch also fails.
+		_, createErr := createProfile(ctx, handle, username)
+		if resolvedID, err = switchProfile(ctx, handle, username); err != nil {
+			if createErr != nil {
+				return fmt.Errorf("create profile: %w", createErr)
+			}
+			return err
+		}
+	}
+
+	if err := pm.SwitchProfile(resolvedID); err != nil {
+		return err
+	}
+	return nil
+}
+
+// createProfile dials the daemon and creates a new profile with the given
+// display name, returning its generated ID. Use addProfileOnDaemon directly
+// when a daemon client is already available to reuse the connection.
+func createProfile(ctx context.Context, profileName, 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"+
+			"If the daemon is not running please run: "+
+			"\nnetbird service install \nnetbird service start\n", err)
+	}
+	defer conn.Close()
+
+	return addProfileOnDaemon(ctx, proto.NewDaemonServiceClient(conn), profileName, username)
+}
+
 func runInForegroundMode(ctx context.Context, cmd *cobra.Command, activeProf *profilemanager.Profile) error {
 	// override the default profile filepath if provided
 	if configPath != "" {
@@ -190,7 +229,7 @@ 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)
 	}
@@ -261,10 +300,10 @@ 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 +328,11 @@ 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 +369,7 @@ 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/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/dns/server.go

@@ -6,6 +6,7 @@ import (
 	"fmt"
 	"net/netip"
 	"net/url"
+	"os"
 	"slices"
 	"strings"
 	"sync"
@@ -38,11 +39,15 @@ const (
 	// defaultWarningDelayBase is the starting grace window before a
 	// "Nameserver group unreachable" event fires for a group that's
 	// never been healthy and only has overlay upstreams with no
-	// Connected peer. Per-server and overridable; see warningDelayFor.
-	defaultWarningDelayBase = 30 * time.Second
+	// Connected peer. Per-server and overridable via envWarningDelay;
+	// see warningDelay.
+	defaultWarningDelayBase = 60 * time.Second
 	// warningDelayBonusCap caps the route-count bonus added to the
-	// base grace window. See warningDelayFor.
+	// base grace window. See warningDelay.
 	warningDelayBonusCap = 30 * time.Second
+	// envWarningDelay overrides defaultWarningDelayBase with a Go duration
+	// string (e.g. "90s", "2m"). Invalid or non-positive values are ignored.
+	envWarningDelay = "NB_DNS_HEALTH_WARNING_DELAY"
 )
 
 // errNoUsableNameservers signals that a merged-domain group has no usable
@@ -135,7 +140,7 @@ type DefaultServer struct {
 	disableSys         bool
 	mux                sync.Mutex
 	service            service
-	dnsMuxMap          registeredHandlerMap
+	dnsMuxHandlers     []handlerWrapper
 	localResolver      *local.Resolver
 	wgInterface        WGIface
 	hostManager        hostManager
@@ -199,8 +204,6 @@ type handlerWrapper struct {
 	priority int
 }
 
-type registeredHandlerMap map[types.HandlerID]handlerWrapper
-
 // DefaultServerConfig holds configuration parameters for NewDefaultServer
 type DefaultServerConfig struct {
 	WgInterface    WGIface
@@ -289,7 +292,6 @@ func newDefaultServer(
 		service:           dnsService,
 		handlerChain:      handlerChain,
 		extraDomains:      make(map[domain.Domain]int),
-		dnsMuxMap:         make(registeredHandlerMap),
 		localResolver:     local.NewResolver(),
 		wgInterface:       wgInterface,
 		statusRecorder:    statusRecorder,
@@ -298,7 +300,7 @@ func newDefaultServer(
 		hostManager:       &noopHostConfigurator{},
 		mgmtCacheResolver: mgmtCacheResolver,
 		currentConfigHash: ^uint64(0), // Initialize to max uint64 to ensure first config is always applied
-		warningDelayBase:  defaultWarningDelayBase,
+		warningDelayBase:  warningDelayBaseFromEnv(),
 		healthRefresh:     make(chan struct{}, 1),
 	}
 	// Wire the local resolver against the peer status recorder so it can
@@ -328,7 +330,7 @@ func (s *DefaultServer) SetRouteSources(selected, active func() route.HAMap) {
 	type routeSettable interface {
 		setSelectedRoutes(func() route.HAMap)
 	}
-	for _, entry := range s.dnsMuxMap {
+	for _, entry := range s.dnsMuxHandlers {
 		if h, ok := entry.handler.(routeSettable); ok {
 			h.setSelectedRoutes(selected)
 		}
@@ -978,19 +980,23 @@ func (s *DefaultServer) usableNameServers(nameServers []nbdns.NameServer) []neti
 
 func (s *DefaultServer) updateMux(muxUpdates []handlerWrapper) {
 	// this will introduce a short period of time when the server is not able to handle DNS requests
-	for _, existing := range s.dnsMuxMap {
+	for _, existing := range s.dnsMuxHandlers {
 		s.deregisterHandler([]string{existing.domain}, existing.priority)
-		existing.handler.Stop()
+		// The local resolver is a persistent singleton shared by every custom
+		// zone and reused across config updates. Its chain registrations are
+		// per-config and must be deregistered, but Stop() cancels its lookup
+		// context (breaking external CNAME-target resolution) and clears its
+		// records, so it must not be torn down here.
+		if existing.handler != s.localResolver {
+			existing.handler.Stop()
+		}
 	}
 
-	muxUpdateMap := make(registeredHandlerMap)
-
 	for _, update := range muxUpdates {
 		s.registerHandler([]string{update.domain}, update.handler, update.priority)
-		muxUpdateMap[update.handler.ID()] = update
 	}
 
-	s.dnsMuxMap = muxUpdateMap
+	s.dnsMuxHandlers = muxUpdates
 }
 
 // updateNSGroupStates records the new group set and pokes the refresher.
@@ -1154,6 +1160,26 @@ func (s *DefaultServer) projectUnhealthy(p *nsGroupProj, servers []netip.AddrPor
 	return false
 }
 
+// warningDelayBaseFromEnv returns the base grace window, honoring
+// envWarningDelay when it holds a valid positive Go duration. Invalid or
+// non-positive values fall back to defaultWarningDelayBase.
+func warningDelayBaseFromEnv() time.Duration {
+	val := os.Getenv(envWarningDelay)
+	if val == "" {
+		return defaultWarningDelayBase
+	}
+	d, err := time.ParseDuration(val)
+	if err != nil {
+		log.Warnf("invalid %s value %q, using default %v: %v", envWarningDelay, val, defaultWarningDelayBase, err)
+		return defaultWarningDelayBase
+	}
+	if d <= 0 {
+		log.Warnf("%s must be positive, got %v, using default %v", envWarningDelay, d, defaultWarningDelayBase)
+		return defaultWarningDelayBase
+	}
+	return d
+}
+
 // warningDelay returns the grace window for the given selected-route
 // count. Scales gently: +1s per 100 routes, capped by
 // warningDelayBonusCap. Parallel handshakes mean handshake time grows
@@ -1204,7 +1230,7 @@ func (s *DefaultServer) groupHasImmediateUpstream(servers []netip.AddrPort, snap
 // in more than one handler.
 func (s *DefaultServer) collectUpstreamHealth() map[netip.AddrPort]UpstreamHealth {
 	merged := make(map[netip.AddrPort]UpstreamHealth)
-	for _, entry := range s.dnsMuxMap {
+	for _, entry := range s.dnsMuxHandlers {
 		reporter, ok := entry.handler.(upstreamHealthReporter)
 		if !ok {
 			continue

client/internal/dns/server_test.go

@@ -104,19 +104,6 @@ func init() {
 	formatter.SetTextFormatter(log.StandardLogger())
 }
 
-func generateDummyHandler(d string, servers []nbdns.NameServer) *upstreamResolverBase {
-	var srvs []netip.AddrPort
-	for _, srv := range servers {
-		srvs = append(srvs, srv.AddrPort())
-	}
-	u := &upstreamResolverBase{
-		domain: domain.Domain(d),
-		cancel: func() {},
-	}
-	u.addRace(srvs)
-	return u
-}
-
 func TestUpdateDNSServer(t *testing.T) {
 
 	nameServers := []nbdns.NameServer{
@@ -132,22 +119,20 @@ func TestUpdateDNSServer(t *testing.T) {
 		},
 	}
 
-	dummyHandler := local.NewResolver()
-
 	testCases := []struct {
 		name                string
-		initUpstreamMap     registeredHandlerMap
+		initUpstreamMap     []handlerWrapper
 		initLocalZones      []nbdns.CustomZone
 		initSerial          uint64
 		inputSerial         uint64
 		inputUpdate         nbdns.Config
 		shouldFail          bool
-		expectedUpstreamMap registeredHandlerMap
+		expectedUpstreamMap []handlerWrapper
 		expectedLocalQs     []dns.Question
 	}{
 		{
 			name:            "Initial Config Should Succeed",
-			initUpstreamMap: make(registeredHandlerMap),
+			initUpstreamMap: nil,
 			initSerial:      0,
 			inputSerial:     1,
 			inputUpdate: nbdns.Config{
@@ -169,20 +154,17 @@ func TestUpdateDNSServer(t *testing.T) {
 					},
 				},
 			},
-			expectedUpstreamMap: registeredHandlerMap{
-				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+			expectedUpstreamMap: []handlerWrapper{
+				{
 					domain:   "netbird.io",
-					handler:  dummyHandler,
 					priority: PriorityUpstream,
 				},
-				dummyHandler.ID(): handlerWrapper{
+				{
 					domain:   "netbird.cloud",
-					handler:  dummyHandler,
 					priority: PriorityLocal,
 				},
-				generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+				{
 					domain:   nbdns.RootZone,
-					handler:  dummyHandler,
 					priority: PriorityDefault,
 				},
 			},
@@ -191,10 +173,10 @@ func TestUpdateDNSServer(t *testing.T) {
 		{
 			name:           "New Config Should Succeed",
 			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: 1, Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: registeredHandlerMap{
-				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+			initUpstreamMap: []handlerWrapper{
+				{
 					domain:   "netbird.cloud",
-					handler:  dummyHandler,
+					handler:  &mockHandler{},
 					priority: PriorityUpstream,
 				},
 			},
@@ -215,15 +197,13 @@ func TestUpdateDNSServer(t *testing.T) {
 					},
 				},
 			},
-			expectedUpstreamMap: registeredHandlerMap{
-				generateDummyHandler("netbird.io", nameServers).ID(): handlerWrapper{
+			expectedUpstreamMap: []handlerWrapper{
+				{
 					domain:   "netbird.io",
-					handler:  dummyHandler,
 					priority: PriorityUpstream,
 				},
-				"local-resolver": handlerWrapper{
+				{
 					domain:   "netbird.cloud",
-					handler:  dummyHandler,
 					priority: PriorityLocal,
 				},
 			},
@@ -232,7 +212,7 @@ func TestUpdateDNSServer(t *testing.T) {
 		{
 			name:            "Smaller Config Serial Should Be Skipped",
 			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: make(registeredHandlerMap),
+			initUpstreamMap: nil,
 			initSerial:      2,
 			inputSerial:     1,
 			shouldFail:      true,
@@ -240,7 +220,7 @@ func TestUpdateDNSServer(t *testing.T) {
 		{
 			name:            "Empty NS Group Domain Or Not Primary Element Should Fail",
 			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: make(registeredHandlerMap),
+			initUpstreamMap: nil,
 			initSerial:      0,
 			inputSerial:     1,
 			inputUpdate: nbdns.Config{
@@ -262,7 +242,7 @@ func TestUpdateDNSServer(t *testing.T) {
 		{
 			name:            "Invalid NS Group Nameservers list Should Fail",
 			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: make(registeredHandlerMap),
+			initUpstreamMap: nil,
 			initSerial:      0,
 			inputSerial:     1,
 			inputUpdate: nbdns.Config{
@@ -284,7 +264,7 @@ func TestUpdateDNSServer(t *testing.T) {
 		{
 			name:            "Invalid Custom Zone Records list Should Skip",
 			initLocalZones:  []nbdns.CustomZone{},
-			initUpstreamMap: make(registeredHandlerMap),
+			initUpstreamMap: nil,
 			initSerial:      0,
 			inputSerial:     1,
 			inputUpdate: nbdns.Config{
@@ -301,42 +281,41 @@ func TestUpdateDNSServer(t *testing.T) {
 					},
 				},
 			},
-			expectedUpstreamMap: registeredHandlerMap{generateDummyHandler(".", nameServers).ID(): handlerWrapper{
+			expectedUpstreamMap: []handlerWrapper{{
 				domain:   ".",
-				handler:  dummyHandler,
 				priority: PriorityDefault,
 			}},
 		},
 		{
 			name:           "Empty Config Should Succeed and Clean Maps",
 			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: registeredHandlerMap{
-				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+			initUpstreamMap: []handlerWrapper{
+				{
 					domain:   zoneRecords[0].Name,
-					handler:  dummyHandler,
+					handler:  &mockHandler{},
 					priority: PriorityUpstream,
 				},
 			},
 			initSerial:          0,
 			inputSerial:         1,
 			inputUpdate:         nbdns.Config{ServiceEnable: true},
-			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedUpstreamMap: nil,
 			expectedLocalQs:     []dns.Question{},
 		},
 		{
 			name:           "Disabled Service Should clean map",
 			initLocalZones: []nbdns.CustomZone{{Domain: "netbird.cloud", Records: []nbdns.SimpleRecord{{Name: "netbird.cloud", Type: int(dns.TypeA), Class: nbdns.DefaultClass, TTL: 300, RData: "10.0.0.1"}}}},
-			initUpstreamMap: registeredHandlerMap{
-				generateDummyHandler(zoneRecords[0].Name, nameServers).ID(): handlerWrapper{
+			initUpstreamMap: []handlerWrapper{
+				{
 					domain:   zoneRecords[0].Name,
-					handler:  dummyHandler,
+					handler:  &mockHandler{},
 					priority: PriorityUpstream,
 				},
 			},
 			initSerial:          0,
 			inputSerial:         1,
 			inputUpdate:         nbdns.Config{ServiceEnable: false},
-			expectedUpstreamMap: make(registeredHandlerMap),
+			expectedUpstreamMap: nil,
 			expectedLocalQs:     []dns.Question{},
 		},
 	}
@@ -393,7 +372,7 @@ func TestUpdateDNSServer(t *testing.T) {
 				}
 			}()
 
-			dnsServer.dnsMuxMap = testCase.initUpstreamMap
+			dnsServer.dnsMuxHandlers = testCase.initUpstreamMap
 			dnsServer.localResolver.Update(testCase.initLocalZones)
 			dnsServer.updateSerial = testCase.initSerial
 
@@ -405,14 +384,20 @@ func TestUpdateDNSServer(t *testing.T) {
 				t.Fatalf("update dns server should not fail, got error: %v", err)
 			}
 
-			if len(dnsServer.dnsMuxMap) != len(testCase.expectedUpstreamMap) {
-				t.Fatalf("update upstream failed, map size is different than expected, want %d, got %d", len(testCase.expectedUpstreamMap), len(dnsServer.dnsMuxMap))
+			if len(dnsServer.dnsMuxHandlers) != len(testCase.expectedUpstreamMap) {
+				t.Fatalf("update upstream failed, map size is different than expected, want %d, got %d", len(testCase.expectedUpstreamMap), len(dnsServer.dnsMuxHandlers))
 			}
 
-			for key := range testCase.expectedUpstreamMap {
-				_, found := dnsServer.dnsMuxMap[key]
+			for _, expected := range testCase.expectedUpstreamMap {
+				found := false
+				for _, got := range dnsServer.dnsMuxHandlers {
+					if got.domain == expected.domain && got.priority == expected.priority {
+						found = true
+						break
+					}
+				}
 				if !found {
-					t.Fatalf("update upstream failed, key %s was not found in the dnsMuxMap: %#v", key, dnsServer.dnsMuxMap)
+					t.Fatalf("update upstream failed, handler for domain=%s priority=%d not found in dnsMuxHandlers: %#v", expected.domain, expected.priority, dnsServer.dnsMuxHandlers)
 				}
 			}
 
@@ -512,8 +497,8 @@ func TestDNSFakeResolverHandleUpdates(t *testing.T) {
 		}
 	}()
 
-	dnsServer.dnsMuxMap = registeredHandlerMap{
-		"id1": handlerWrapper{
+	dnsServer.dnsMuxHandlers = []handlerWrapper{
+		{
 			domain:   zoneRecords[0].Name,
 			handler:  &local.Resolver{},
 			priority: PriorityUpstream,
@@ -1029,15 +1014,15 @@ func (m *mockService) RegisterMux(string, dns.Handler) {}
 func (m *mockService) DeregisterMux(string)            {}
 
 func TestDefaultServer_UpdateMux(t *testing.T) {
-	baseMatchHandlers := registeredHandlerMap{
-		"upstream-group1": {
+	baseMatchHandlers := []handlerWrapper{
+		{
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group1",
 			},
 			priority: PriorityUpstream,
 		},
-		"upstream-group2": {
+		{
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group2",
@@ -1046,15 +1031,15 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 		},
 	}
 
-	baseRootHandlers := registeredHandlerMap{
-		"upstream-root1": {
+	baseRootHandlers := []handlerWrapper{
+		{
 			domain: ".",
 			handler: &mockHandler{
 				Id: "upstream-root1",
 			},
 			priority: PriorityDefault,
 		},
-		"upstream-root2": {
+		{
 			domain: ".",
 			handler: &mockHandler{
 				Id: "upstream-root2",
@@ -1063,22 +1048,22 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 		},
 	}
 
-	baseMixedHandlers := registeredHandlerMap{
-		"upstream-group1": {
+	baseMixedHandlers := []handlerWrapper{
+		{
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group1",
 			},
 			priority: PriorityUpstream,
 		},
-		"upstream-group2": {
+		{
 			domain: "example.com",
 			handler: &mockHandler{
 				Id: "upstream-group2",
 			},
 			priority: PriorityUpstream - 1,
 		},
-		"upstream-other": {
+		{
 			domain: "other.com",
 			handler: &mockHandler{
 				Id: "upstream-other",
@@ -1089,7 +1074,7 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 
 	tests := []struct {
 		name             string
-		initialHandlers  registeredHandlerMap
+		initialHandlers  []handlerWrapper
 		updates          []handlerWrapper
 		expectedHandlers map[string]string // map[HandlerID]domain
 		description      string
@@ -1373,32 +1358,38 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 	for _, tt := range tests {
 		t.Run(tt.name, func(t *testing.T) {
 			server := &DefaultServer{
-				dnsMuxMap:    tt.initialHandlers,
-				handlerChain: NewHandlerChain(),
-				service:      &mockService{},
+				dnsMuxHandlers: tt.initialHandlers,
+				handlerChain:   NewHandlerChain(),
+				service:        &mockService{},
 			}
 
 			// Perform the update
 			server.updateMux(tt.updates)
 
 			// Verify the results
-			assert.Equal(t, len(tt.expectedHandlers), len(server.dnsMuxMap),
+			assert.Equal(t, len(tt.expectedHandlers), len(server.dnsMuxHandlers),
 				"Number of handlers after update doesn't match expected")
 
 			// Check each expected handler
 			for id, expectedDomain := range tt.expectedHandlers {
-				handler, exists := server.dnsMuxMap[types.HandlerID(id)]
-				assert.True(t, exists, "Expected handler %s not found", id)
-				if exists {
-					assert.Equal(t, expectedDomain, handler.domain,
+				var found *handlerWrapper
+				for i := range server.dnsMuxHandlers {
+					if server.dnsMuxHandlers[i].handler.ID() == types.HandlerID(id) {
+						found = &server.dnsMuxHandlers[i]
+						break
+					}
+				}
+				assert.NotNil(t, found, "Expected handler %s not found", id)
+				if found != nil {
+					assert.Equal(t, expectedDomain, found.domain,
 						"Domain mismatch for handler %s", id)
 				}
 			}
 
 			// Verify no unexpected handlers exist
-			for HandlerID := range server.dnsMuxMap {
-				_, expected := tt.expectedHandlers[string(HandlerID)]
-				assert.True(t, expected, "Unexpected handler found: %s", HandlerID)
+			for _, entry := range server.dnsMuxHandlers {
+				_, expected := tt.expectedHandlers[string(entry.handler.ID())]
+				assert.True(t, expected, "Unexpected handler found: %s", entry.handler.ID())
 			}
 
 			// Verify the handlerChain state and order
@@ -1413,7 +1404,7 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 
 				// Verify handler exists in mux
 				foundInMux := false
-				for _, muxEntry := range server.dnsMuxMap {
+				for _, muxEntry := range server.dnsMuxHandlers {
 					if chainEntry.Handler == muxEntry.handler &&
 						chainEntry.Priority == muxEntry.priority &&
 						chainEntry.Pattern == dns.Fqdn(muxEntry.domain) {
@@ -1422,12 +1413,108 @@ func TestDefaultServer_UpdateMux(t *testing.T) {
 					}
 				}
 				assert.True(t, foundInMux,
-					"Handler in chain not found in dnsMuxMap")
+					"Handler in chain not found in dnsMuxHandlers")
 			}
 		})
 	}
 }
 
+// chainHasPattern reports whether the handler chain holds an entry registered
+// for the given fqdn pattern at the given priority.
+func chainHasPattern(s *DefaultServer, pattern string, priority int) bool {
+	for _, h := range s.handlerChain.handlers {
+		if h.OrigPattern == pattern && h.Priority == priority {
+			return true
+		}
+	}
+	return false
+}
+
+// TestDefaultServer_UpdateMux_SharedHandlerZoneRemoval verifies that updateMux
+// tracks each (handler, domain) registration independently when one handler
+// serves multiple zones. Every custom zone is served by the same handler
+// instance (the local resolver, whose ID is the constant "local-resolver"), so
+// removing one zone must deregister exactly that zone's chain entry and leave
+// the others in place. Tracking registrations by handler ID alone collapses all
+// zones onto one entry, leaving removed zones in the chain to answer
+// authoritatively with no records.
+func TestDefaultServer_UpdateMux_SharedHandlerZoneRemoval(t *testing.T) {
+	// One handler serves every custom zone, mirroring s.localResolver.
+	shared := &mockHandler{Id: "local-resolver"}
+
+	server := &DefaultServer{
+		handlerChain: NewHandlerChain(),
+		service:      &mockService{},
+	}
+
+	// Two custom zones under the same handler. The surviving zone is registered
+	// last, mirroring the management emission order.
+	server.updateMux([]handlerWrapper{
+		{domain: "userzone.test", handler: shared, priority: PriorityLocal},
+		{domain: "peerzone.test", handler: shared, priority: PriorityLocal},
+	})
+
+	require.True(t, chainHasPattern(server, "userzone.test.", PriorityLocal),
+		"userzone.test should be registered after the first update")
+	require.True(t, chainHasPattern(server, "peerzone.test.", PriorityLocal),
+		"peerzone.test should be registered after the first update")
+
+	// Remove one zone, keep the other.
+	server.updateMux([]handlerWrapper{
+		{domain: "peerzone.test", handler: shared, priority: PriorityLocal},
+	})
+
+	assert.True(t, chainHasPattern(server, "peerzone.test.", PriorityLocal),
+		"peerzone.test should remain after removing userzone.test")
+	assert.False(t, chainHasPattern(server, "userzone.test.", PriorityLocal),
+		"userzone.test handler must be deregistered, not leaked in the chain")
+}
+
+// TestDefaultServer_UpdateMux_PreservesLocalResolver verifies that updateMux
+// does not tear down the shared local resolver during reconfiguration. The
+// resolver is a process-lifetime singleton reused across config updates;
+// Stop() cancels its lookup context (breaking external CNAME-target
+// resolution) and clears its records. updateMux must deregister its chain
+// entries without stopping it. Records surviving a teardown update is the
+// observable proxy: Stop() would have cleared them.
+func TestDefaultServer_UpdateMux_PreservesLocalResolver(t *testing.T) {
+	resolver := local.NewResolver()
+	require.NoError(t, resolver.RegisterRecord(nbdns.SimpleRecord{
+		Name:  "peer.netbird.cloud.",
+		Type:  int(dns.TypeA),
+		Class: nbdns.DefaultClass,
+		TTL:   300,
+		RData: "10.0.0.1",
+	}))
+
+	server := &DefaultServer{
+		handlerChain:  NewHandlerChain(),
+		service:       &mockService{},
+		localResolver: resolver,
+	}
+
+	server.updateMux([]handlerWrapper{
+		{domain: "netbird.cloud", handler: resolver, priority: PriorityLocal},
+	})
+
+	// Remove the zone. The resolver must survive so its records and lookup
+	// context stay intact for the next registration.
+	server.updateMux(nil)
+
+	var response *dns.Msg
+	resolver.ServeDNS(&test.MockResponseWriter{
+		WriteMsgFunc: func(m *dns.Msg) error {
+			response = m
+			return nil
+		},
+	}, &dns.Msg{Question: []dns.Question{{Name: "peer.netbird.cloud.", Qtype: dns.TypeA, Qclass: dns.ClassINET}}})
+
+	require.NotNil(t, response, "local resolver should answer after teardown")
+	assert.Equal(t, dns.RcodeSuccess, response.Rcode,
+		"local resolver records must survive teardown; updateMux must not Stop() the shared resolver")
+	assert.NotEmpty(t, response.Answer, "answer should contain the surviving record")
+}
+
 func TestExtraDomains(t *testing.T) {
 	tests := []struct {
 		name                string
@@ -2049,7 +2136,6 @@ func TestBuildUpstreamHandler_MergesGroupsPerDomain(t *testing.T) {
 		localResolver: local.NewResolver(),
 		handlerChain:  NewHandlerChain(),
 		hostManager:   &noopHostConfigurator{},
-		dnsMuxMap:     make(registeredHandlerMap),
 	}
 
 	groups := []*nbdns.NameServerGroup{
@@ -2207,7 +2293,7 @@ func TestEvaluateNSGroupHealth(t *testing.T) {
 	}
 }
 
-// healthStubHandler is a minimal dnsMuxMap entry that exposes a fixed
+// healthStubHandler is a minimal dnsMuxHandlers entry that exposes a fixed
 // UpstreamHealth snapshot, letting tests drive recomputeNSGroupStates
 // without spinning up real handlers.
 type healthStubHandler struct {
@@ -2283,12 +2369,11 @@ func newProjTestFixture(t *testing.T) *projTestFixture {
 		ctx:              context.Background(),
 		wgInterface:      &mocWGIface{},
 		statusRecorder:   recorder,
-		dnsMuxMap:        make(registeredHandlerMap),
 		selectedRoutes:   func() route.HAMap { return fx.selected },
 		activeRoutes:     func() route.HAMap { return fx.active },
 		warningDelayBase: defaultWarningDelayBase,
 	}
-	fx.server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: fx.stub, priority: PriorityUpstream}
+	fx.server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: fx.stub, priority: PriorityUpstream}}
 
 	fx.server.mux.Lock()
 	fx.server.updateNSGroupStates([]*nbdns.NameServerGroup{fx.group})
@@ -2395,7 +2480,6 @@ func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
 		ctx:              context.Background(),
 		wgInterface:      &mocWGIface{},
 		statusRecorder:   recorder,
-		dnsMuxMap:        make(registeredHandlerMap),
 		selectedRoutes:   func() route.HAMap { return nil },
 		activeRoutes:     func() route.HAMap { return nil },
 		warningDelayBase: 50 * time.Millisecond,
@@ -2407,7 +2491,7 @@ func TestProjection_OverlayAddrNoRouteDelaysWarning(t *testing.T) {
 	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{
 		overlayPeer: {LastFail: time.Now(), LastErr: "timeout"},
 	}}
-	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+	server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2444,7 +2528,6 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 		service:           NewServiceViaMemory(wgIface),
 		hostManager:       &noopHostConfigurator{},
 		extraDomains:      map[domain.Domain]int{},
-		dnsMuxMap:         make(registeredHandlerMap),
 		statusRecorder:    peer.NewRecorder("mgm"),
 		selectedRoutes:    func() route.HAMap { return nil },
 		activeRoutes:      func() route.HAMap { return nil },
@@ -2459,7 +2542,7 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 		NameServers: []nbdns.NameServer{{IP: srv.Addr(), NSType: nbdns.UDPNameServerType, Port: int(srv.Port())}},
 	}
 	stub := &healthStubHandler{health: map[netip.AddrPort]UpstreamHealth{srv: {LastOk: time.Now()}}}
-	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+	server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2484,6 +2567,32 @@ func TestProjection_StopClearsHealthState(t *testing.T) {
 // rule 3: startup failures while the peer is handshaking, then the peer
 // comes up and a query succeeds before the grace window elapses. No
 // warning should ever have fired, and no recovery either.
+func TestWarningDelayBaseFromEnv(t *testing.T) {
+	tests := []struct {
+		name string
+		set  bool
+		val  string
+		want time.Duration
+	}{
+		{name: "unset uses default", set: false, want: defaultWarningDelayBase},
+		{name: "valid override", set: true, val: "90s", want: 90 * time.Second},
+		{name: "valid minutes", set: true, val: "2m", want: 2 * time.Minute},
+		{name: "invalid falls back", set: true, val: "notaduration", want: defaultWarningDelayBase},
+		{name: "zero falls back", set: true, val: "0s", want: defaultWarningDelayBase},
+		{name: "negative falls back", set: true, val: "-30s", want: defaultWarningDelayBase},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			t.Setenv(envWarningDelay, tc.val)
+			if !tc.set {
+				os.Unsetenv(envWarningDelay)
+			}
+			assert.Equal(t, tc.want, warningDelayBaseFromEnv(), "grace window base")
+		})
+	}
+}
+
 func TestProjection_OverlayRecoversDuringGrace(t *testing.T) {
 	fx := newProjTestFixture(t)
 	fx.server.warningDelayBase = 200 * time.Millisecond
@@ -2595,7 +2704,6 @@ func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
 	server := &DefaultServer{
 		ctx:              context.Background(),
 		statusRecorder:   recorder,
-		dnsMuxMap:        make(registeredHandlerMap),
 		selectedRoutes:   func() route.HAMap { return overlayMap },
 		activeRoutes:     func() route.HAMap { return nil },
 		warningDelayBase: time.Hour,
@@ -2613,7 +2721,7 @@ func TestProjection_MixedGroupEmitsImmediately(t *testing.T) {
 			overlay: {LastFail: time.Now(), LastErr: "timeout"},
 		},
 	}
-	server.dnsMuxMap["example.com"] = handlerWrapper{domain: "example.com", handler: stub, priority: PriorityUpstream}
+	server.dnsMuxHandlers = []handlerWrapper{{domain: "example.com", handler: stub, priority: PriorityUpstream}}
 
 	server.mux.Lock()
 	server.updateNSGroupStates([]*nbdns.NameServerGroup{group})
@@ -2640,7 +2748,6 @@ func TestDNSLoopPrevention(t *testing.T) {
 		localResolver: local.NewResolver(),
 		handlerChain:  NewHandlerChain(),
 		hostManager:   &noopHostConfigurator{},
-		dnsMuxMap:     make(registeredHandlerMap),
 	}
 
 	tests := []struct {

client/internal/dns/upstream.go

@@ -443,21 +443,25 @@ func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, r *dns.M
 		return raceResult{}, &upstreamFailure{upstream: upstream, reason: "no response"}
 	}
 
+	// A valid response means the upstream is reachable, whatever the Rcode.
+	u.markUpstreamOk(upstream)
+
 	proto := ""
 	if upstreamProto != nil {
 		proto = upstreamProto.protocol
 	}
 
 	if rm.Rcode == dns.RcodeServerFailure || rm.Rcode == dns.RcodeRefused {
+		// SERVFAIL and REFUSED are per-question outcomes (DNSSEC-bogus names,
+		// refused zones, transient recursion errors), not reachability
+		// problems: fail over for a better answer but keep the upstream healthy.
 		if code, ok := nonRetryableEDE(rm); ok {
 			if !hadEdns {
 				stripOPT(rm)
 			}
-			u.markUpstreamOk(upstream)
 			return raceResult{msg: rm, upstream: upstream, protocol: proto, ede: edeName(code)}, nil
 		}
 		reason := dns.RcodeToString[rm.Rcode]
-		u.markUpstreamFail(upstream, reason)
 		return raceResult{}, &upstreamFailure{upstream: upstream, reason: reason}
 	}
 
@@ -465,7 +469,6 @@ func (u *upstreamResolverBase) queryUpstream(parentCtx context.Context, r *dns.M
 		stripOPT(rm)
 	}
 
-	u.markUpstreamOk(upstream)
 	return raceResult{msg: rm, upstream: upstream, protocol: proto}, nil
 }
 

client/internal/dns/upstream_test.go

@@ -517,6 +517,78 @@ func TestUpstreamResolver_HealthTracking(t *testing.T) {
 	assert.NotContains(t, health, bad, "sibling upstream should not be queried when primary answers")
 }
 
+// TestUpstreamResolver_HealthTracking_ResponseMeansReachable verifies that an
+// upstream which answers with SERVFAIL or REFUSED is recorded as healthy:
+// those are per-question outcomes from a reachable server and must not mark
+// the upstream unhealthy. Only transport failures (timeouts) do.
+func TestUpstreamResolver_HealthTracking_ResponseMeansReachable(t *testing.T) {
+	a := netip.MustParseAddrPort("192.0.2.10:53")
+	b := netip.MustParseAddrPort("192.0.2.11:53")
+	timeoutErr := &net.OpError{Op: "read", Err: fmt.Errorf("i/o timeout")}
+
+	tests := []struct {
+		name        string
+		respA       mockUpstreamResponse
+		respB       mockUpstreamResponse
+		wantHealthy bool
+	}{
+		{
+			name:        "both SERVFAIL are reachable",
+			respA:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			respB:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeServerFailure, "")},
+			wantHealthy: true,
+		},
+		{
+			name:        "both REFUSED are reachable",
+			respA:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
+			respB:       mockUpstreamResponse{msg: buildMockResponse(dns.RcodeRefused, "")},
+			wantHealthy: true,
+		},
+		{
+			name:        "timeout marks unhealthy",
+			respA:       mockUpstreamResponse{err: timeoutErr},
+			respB:       mockUpstreamResponse{err: timeoutErr},
+			wantHealthy: false,
+		},
+	}
+
+	for _, tc := range tests {
+		t.Run(tc.name, func(t *testing.T) {
+			mockClient := &mockUpstreamResolverPerServer{
+				responses: map[string]mockUpstreamResponse{
+					a.String(): tc.respA,
+					b.String(): tc.respB,
+				},
+				rtt: time.Millisecond,
+			}
+
+			ctx, cancel := context.WithCancel(context.Background())
+			defer cancel()
+
+			resolver := &upstreamResolverBase{
+				ctx:             ctx,
+				upstreamClient:  mockClient,
+				upstreamTimeout: UpstreamTimeout,
+			}
+			resolver.addRace([]netip.AddrPort{a, b})
+
+			responseWriter := &test.MockResponseWriter{WriteMsgFunc: func(m *dns.Msg) error { return nil }}
+			resolver.ServeDNS(responseWriter, new(dns.Msg).SetQuestion("example.com.", dns.TypeA))
+
+			health := resolver.UpstreamHealth()
+			require.Contains(t, health, a, "primary upstream should have a health record")
+			if tc.wantHealthy {
+				assert.False(t, health[a].LastOk.IsZero(), "responding upstream should have LastOk set")
+				assert.True(t, health[a].LastFail.IsZero(), "responding upstream should not be marked failed")
+				assert.Empty(t, health[a].LastErr, "responding upstream should have no error")
+			} else {
+				assert.False(t, health[a].LastFail.IsZero(), "timed-out upstream should be marked failed")
+				assert.NotEmpty(t, health[a].LastErr, "timed-out upstream should record an error")
+			}
+		})
+	}
+}
+
 func TestFormatFailures(t *testing.T) {
 	testCases := []struct {
 		name     string

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/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/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/server.go

@@ -78,7 +78,7 @@ type Server struct {
 	// 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
+	clientRunning     bool
 	clientRunningChan chan struct{}
 	clientGiveUpChan  chan struct{} // closed when connectWithRetryRuns goroutine exits
 
@@ -375,7 +375,7 @@ 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 +398,17 @@ 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 +535,9 @@ 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 +547,7 @@ 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()
 
@@ -806,10 +785,10 @@ 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 +799,7 @@ 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 {
@@ -864,34 +843,60 @@ func (s *Server) waitForUp(callerCtx context.Context) (*proto.UpResponse, error)
 	}
 }
 
-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 +911,9 @@ 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()
@@ -924,7 +929,7 @@ 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.
@@ -1014,22 +1019,27 @@ 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 +1101,30 @@ 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 +1132,20 @@ 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 != nil {
 		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)
@@ -1558,15 +1563,14 @@ 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 +1675,39 @@ 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 +1715,29 @@ 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 +1760,7 @@ 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 +1769,9 @@ 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 +1782,23 @@ 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
 }
 

client/server/server_test.go

@@ -97,7 +97,7 @@ func TestConnectWithRetryRuns(t *testing.T) {
 
 	pm := profilemanager.ServiceManager{}
 	err = pm.SetActiveProfileState(&profilemanager.ActiveProfileState{
-		Name:     "test-profile",
+		ID:       "test-profile",
 		Username: currUser.Username,
 	})
 	if err != nil {
@@ -158,7 +158,7 @@ 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 +228,7 @@ 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/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()

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

@@ -434,7 +434,7 @@ func TestDeletePeerService_SourcePeerValidation(t *testing.T) {
 		t.Helper()
 		tokenStore := nbgrpc.NewOneTimeTokenStore(context.Background(), testCacheStore(t))
 		pkceStore := nbgrpc.NewPKCEVerifierStore(context.Background(), testCacheStore(t))
-		srv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil)
+		srv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil, nil)
 		return srv
 	}
 
@@ -723,7 +723,7 @@ func setupIntegrationTest(t *testing.T) (*Manager, store.Store) {
 
 	tokenStore := nbgrpc.NewOneTimeTokenStore(ctx, testCacheStore(t))
 	pkceStore := nbgrpc.NewPKCEVerifierStore(ctx, testCacheStore(t))
-	proxySrv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil)
+	proxySrv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil, nil)
 
 	proxyController, err := proxymanager.NewGRPCController(proxySrv, noop.NewMeterProvider().Meter(""))
 	require.NoError(t, err)
@@ -1147,7 +1147,7 @@ func TestDeleteService_DeletesTargets(t *testing.T) {
 
 	tokenStore := nbgrpc.NewOneTimeTokenStore(ctx, testCacheStore(t))
 	pkceStore := nbgrpc.NewPKCEVerifierStore(ctx, testCacheStore(t))
-	proxySrv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil)
+	proxySrv := nbgrpc.NewProxyServiceServer(nil, tokenStore, pkceStore, nbgrpc.ProxyOIDCConfig{}, nil, nil, nil, nil, nil)
 
 	proxyController, err := proxymanager.NewGRPCController(proxySrv, noop.NewMeterProvider().Meter(""))
 	require.NoError(t, err)

management/internals/server/boot.go

@@ -219,7 +219,7 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
 
 func (s *BaseServer) ReverseProxyGRPCServer() *nbgrpc.ProxyServiceServer {
 	return Create(s, func() *nbgrpc.ProxyServiceServer {
-		proxyService := nbgrpc.NewProxyServiceServer(s.AccessLogsManager(), s.ProxyTokenStore(), s.PKCEVerifierStore(), s.proxyOIDCConfig(), s.PeersManager(), s.UsersManager(), s.ProxyManager(), s.Store())
+		proxyService := nbgrpc.NewProxyServiceServer(s.AccessLogsManager(), s.ProxyTokenStore(), s.PKCEVerifierStore(), s.proxyOIDCConfig(), s.PeersManager(), s.UsersManager(), s.IdpManager(), s.ProxyManager(), s.Store())
 		s.AfterInit(func(s *BaseServer) {
 			proxyService.SetServiceManager(s.ServiceManager())
 			proxyService.SetProxyController(s.ServiceProxyController())

management/internals/shared/grpc/proxy.go

@@ -33,6 +33,8 @@ import (
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/sessionkey"
+	"github.com/netbirdio/netbird/management/server/idp"
+	"github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/management/server/users"
 	proxyauth "github.com/netbirdio/netbird/proxy/auth"
@@ -82,6 +84,9 @@ type ProxyServiceServer struct {
 	// Manager for users
 	usersManager users.Manager
 
+	// Manager for IdP-enriched user data (may be nil when no IdP is configured)
+	idpManager idp.Manager
+
 	// Store for one-time authentication tokens
 	tokenStore *OneTimeTokenStore
 
@@ -157,7 +162,7 @@ func enforceAccountScope(ctx context.Context, requestAccountID string) error {
 }
 
 // NewProxyServiceServer creates a new proxy service server.
-func NewProxyServiceServer(accessLogMgr accesslogs.Manager, tokenStore *OneTimeTokenStore, pkceStore *PKCEVerifierStore, oidcConfig ProxyOIDCConfig, peersManager peers.Manager, usersManager users.Manager, proxyMgr proxy.Manager, tokenChecker ProxyTokenChecker) *ProxyServiceServer {
+func NewProxyServiceServer(accessLogMgr accesslogs.Manager, tokenStore *OneTimeTokenStore, pkceStore *PKCEVerifierStore, oidcConfig ProxyOIDCConfig, peersManager peers.Manager, usersManager users.Manager, idpManager idp.Manager, proxyMgr proxy.Manager, tokenChecker ProxyTokenChecker) *ProxyServiceServer {
 	ctx, cancel := context.WithCancel(context.Background())
 	s := &ProxyServiceServer{
 		accessLogManager:  accessLogMgr,
@@ -166,6 +171,7 @@ func NewProxyServiceServer(accessLogMgr accesslogs.Manager, tokenStore *OneTimeT
 		pkceVerifierStore: pkceStore,
 		peersManager:      peersManager,
 		usersManager:      usersManager,
+		idpManager:        idpManager,
 		proxyManager:      proxyMgr,
 		tokenChecker:      tokenChecker,
 		snapshotBatchSize: snapshotBatchSizeFromEnv(),
@@ -1702,22 +1708,7 @@ func (s *ProxyServiceServer) ValidateTunnelPeer(ctx context.Context, req *proto.
 	}
 
 	groupIDs, groupNames := pairGroupIDsAndNames(peerGroups)
-
-	// Resolve the principal: when the peer is linked to a user, the human
-	// is the principal so multiple peers owned by the same user share a
-	// single identity. Unlinked peers (machine agents) are their own
-	// principal keyed on peer.ID. displayIdentity is what upstream gateways
-	// tag spend with — user.Email when linked, peer.Name when not.
-	principalID := peer.ID
-	displayIdentity := peer.Name
-	if peer.UserID != "" {
-		if user, uerr := s.usersManager.GetUser(ctx, peer.UserID); uerr == nil && user != nil {
-			principalID = user.Id
-			if user.Email != "" {
-				displayIdentity = user.Email
-			}
-		}
-	}
+	principalID, displayIdentity := s.getTunnelPeerInfo(ctx, domain, service, peer)
 
 	if err := checkPeerGroupAccess(service, groupIDs); err != nil {
 		log.WithFields(log.Fields{"domain": domain, "peer_id": peer.ID, "error": err.Error()}).Debug("ValidateTunnelPeer: access denied")
@@ -1754,6 +1745,45 @@ func (s *ProxyServiceServer) ValidateTunnelPeer(ctx context.Context, req *proto.
 	}, nil
 }
 
+// getTunnelPeerInfo returns the principal ID and display name for a peer, e.g. a
+// user or peer ID, and peer name or user email.
+func (s *ProxyServiceServer) getTunnelPeerInfo(ctx context.Context, domain string, service *rpservice.Service, peer *peer.Peer) (string, string) {
+	// Resolve the principal: when the peer is linked to a user, the human is the
+	// principal so multiple peers owned by the same user share a single
+	// identity. Unlinked peers (machine agents) are their own principal keyed on
+	// peer.ID. displayIdentity is what upstream gateways tag spend with —
+	// user.Email when linked, peer.Name when not.
+
+	// If the peer isn't associated with a user, return the peer info directly.
+	if peer.UserID == "" {
+		return peer.ID, peer.Name
+	}
+
+	// Otherwise, if the peer is linked to a user, the user is the principal and
+	// if an IdP is available, we gather details on the user from it.
+	principalID := peer.UserID
+	displayIdentity := peer.Name
+	// Stored column first (cheap, but often empty for OIDC-provisioned users).
+	if user, uerr := s.usersManager.GetUser(ctx, peer.UserID); uerr == nil && user != nil {
+		principalID = user.Id
+		if user.Email != "" {
+			displayIdentity = user.Email
+		}
+	}
+	// IdP enrichment wins when available — the stored email column is a
+	// best-effort cache and is frequently empty for OIDC users. Enrichment
+	// failures must never fail the RPC; we simply keep the stored/peer identity.
+	if s.idpManager != nil {
+		if ud, uerr := s.idpManager.GetUserDataByID(ctx, peer.UserID, idp.AppMetadata{WTAccountID: service.AccountID}); uerr == nil && ud != nil && ud.Email != "" {
+			displayIdentity = ud.Email
+		} else if uerr != nil {
+			log.WithFields(log.Fields{"domain": domain, "user_id": peer.UserID, "error": uerr.Error()}).Debug("ValidateTunnelPeer: IdP user enrichment failed; using stored/peer identity")
+		}
+	}
+
+	return principalID, displayIdentity
+}
+
 // checkPeerGroupAccess gates ValidateTunnelPeer by the service's required
 // groups. Private services authorise against AccessGroups (empty list fails
 // closed — Validate() rejects that at save time but the RPC is the security

management/internals/shared/grpc/proxy_group_access_test.go

@@ -3,14 +3,19 @@ package grpc
 import (
 	"context"
 	"errors"
+	"net"
 	"testing"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
 
+	"github.com/netbirdio/netbird/management/internals/modules/peers"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/proxy"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
+	"github.com/netbirdio/netbird/management/server/idp"
+	"github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
 type mockReverseProxyManager struct {
@@ -137,6 +142,52 @@ func (m *mockUsersManager) GetUserWithGroups(ctx context.Context, userID string)
 	return user, nil, nil
 }
 
+// mockTunnelPeersManager implements only the two peers.Manager methods that
+// ValidateTunnelPeer calls; the embedded interface satisfies the rest (and
+// panics if any unexpected method is invoked).
+type mockTunnelPeersManager struct {
+	peers.Manager
+	peer      *peer.Peer
+	peerErr   error
+	groups    []*types.Group
+	groupsErr error
+}
+
+func (m *mockTunnelPeersManager) GetPeerByTunnelIP(_ context.Context, _ string, _ net.IP) (*peer.Peer, error) {
+	return m.peer, m.peerErr
+}
+
+func (m *mockTunnelPeersManager) GetPeerWithGroups(_ context.Context, _, _ string) (*peer.Peer, []*types.Group, error) {
+	return m.peer, m.groups, m.groupsErr
+}
+
+// mockTunnelIdpManager implements only GetUserDataByID; the embedded interface
+// satisfies the rest of idp.Manager. hasData==false returns (nil, nil) to model
+// an IdP that knows nothing about the user.
+type mockTunnelIdpManager struct {
+	idp.Manager
+	email    string
+	hasData  bool
+	err      error
+	gotCalls int
+	gotMeta  []idp.AppMetadata
+}
+
+func (m *mockTunnelIdpManager) GetUserDataByID(_ context.Context, userID string, meta idp.AppMetadata) (*idp.UserData, error) {
+	m.gotCalls++
+	m.gotMeta = append(m.gotMeta, meta)
+	if m.err != nil {
+		return nil, m.err
+	}
+	if !m.hasData {
+		// This might not be a thing any of the actual IDP implementations do,
+		// i.e. return a nil value with no error, but it seems valuable to test
+		// that behavior here.
+		return nil, nil //nolint:nilnil
+	}
+	return &idp.UserData{ID: userID, Email: m.email}, nil
+}
+
 func TestValidateUserGroupAccess(t *testing.T) {
 	tests := []struct {
 		name             string
@@ -354,6 +405,163 @@ func TestValidateUserGroupAccess(t *testing.T) {
 	}
 }
 
+// TestValidateTunnelPeerUserEmailEnrichment verifies the UserEmail/UserId
+// resolution in ValidateTunnelPeer, including the IdP-enrichment fallback order
+// (IdP email -> stored User.Email -> peer.Name).
+func TestValidateTunnelPeerUserEmailEnrichment(t *testing.T) {
+	const (
+		domain    = "app.example.com"
+		accountID = "account1"
+		peerID    = "peer1"
+		peerName  = "peer-display-name"
+		userID    = "user1"
+	)
+
+	storedUser := map[string]*types.User{userID: {Id: userID, AccountID: accountID, Email: "stored@example.com"}}
+	storedUserNoEmail := map[string]*types.User{userID: {Id: userID, AccountID: accountID, Email: ""}}
+
+	tests := []struct {
+		name         string
+		peerUserID   string
+		storedUsers  map[string]*types.User
+		storedErr    error
+		noIdP        bool
+		idpEmail     string
+		idpHasData   bool
+		idpErr       error
+		expectEmail  string
+		expectUserID string
+		expectIdPHit bool
+	}{
+		{
+			name:         "idp email wins over stored email",
+			peerUserID:   userID,
+			storedUsers:  storedUser,
+			idpEmail:     "idp@example.com",
+			idpHasData:   true,
+			expectEmail:  "idp@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "stored email when idp returns empty email",
+			peerUserID:   userID,
+			storedUsers:  storedUser,
+			idpEmail:     "",
+			idpHasData:   true,
+			expectEmail:  "stored@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "stored email when idp has no data",
+			peerUserID:   userID,
+			storedUsers:  storedUser,
+			idpHasData:   false,
+			expectEmail:  "stored@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "stored email when idp errors",
+			peerUserID:   userID,
+			storedUsers:  storedUser,
+			idpErr:       errors.New("idp unreachable"),
+			expectEmail:  "stored@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "stored email when no idp manager",
+			peerUserID:   userID,
+			storedUsers:  storedUser,
+			noIdP:        true,
+			expectEmail:  "stored@example.com",
+			expectUserID: userID,
+		},
+		{
+			name:         "idp email when stored email is empty",
+			peerUserID:   userID,
+			storedUsers:  storedUserNoEmail,
+			idpEmail:     "idp@example.com",
+			idpHasData:   true,
+			expectEmail:  "idp@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "idp email when stored user missing keeps peer.UserID as principal",
+			peerUserID:   userID,
+			storedUsers:  map[string]*types.User{},
+			idpEmail:     "idp@example.com",
+			idpHasData:   true,
+			expectEmail:  "idp@example.com",
+			expectUserID: userID,
+			expectIdPHit: true,
+		},
+		{
+			name:         "unlinked peer uses peer name and never consults idp",
+			peerUserID:   "",
+			storedUsers:  storedUser,
+			idpEmail:     "idp@example.com",
+			idpHasData:   true,
+			expectEmail:  peerName,
+			expectUserID: peerID,
+			expectIdPHit: false,
+		},
+		{
+			name:         "linked peer with empty stored email and no idp falls back to peer name",
+			peerUserID:   userID,
+			storedUsers:  storedUserNoEmail,
+			noIdP:        true,
+			expectEmail:  peerName,
+			expectUserID: userID,
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			svc := &service.Service{Domain: domain, AccountID: accountID}
+			server := &ProxyServiceServer{
+				serviceManager: &mockReverseProxyManager{
+					proxiesByAccount: map[string][]*service.Service{accountID: {svc}},
+				},
+				peersManager: &mockTunnelPeersManager{
+					peer: &peer.Peer{ID: peerID, Name: peerName, UserID: tt.peerUserID},
+				},
+				usersManager: &mockUsersManager{users: tt.storedUsers, err: tt.storedErr},
+			}
+
+			var idpMock *mockTunnelIdpManager
+			if !tt.noIdP {
+				idpMock = &mockTunnelIdpManager{email: tt.idpEmail, hasData: tt.idpHasData, err: tt.idpErr}
+				server.idpManager = idpMock
+			}
+
+			resp, err := server.ValidateTunnelPeer(context.Background(), &proto.ValidateTunnelPeerRequest{
+				Domain:   domain,
+				TunnelIp: "100.64.0.1",
+			})
+
+			require.NoError(t, err)
+			require.NotNil(t, resp)
+			assert.True(t, resp.GetValid(), "expected access granted")
+			assert.Equal(t, tt.expectEmail, resp.GetUserEmail())
+			assert.Equal(t, tt.expectUserID, resp.GetUserId())
+
+			if idpMock != nil {
+				if tt.expectIdPHit {
+					assert.Equal(t, 1, idpMock.gotCalls, "expected IdP to be consulted")
+					require.Len(t, idpMock.gotMeta, 1)
+					assert.Equal(t, accountID, idpMock.gotMeta[0].WTAccountID)
+				} else {
+					assert.Equal(t, 0, idpMock.gotCalls, "expected IdP to not be consulted")
+				}
+			}
+		})
+	}
+}
+
 func TestGetAccountProxyByDomain(t *testing.T) {
 	tests := []struct {
 		name             string

management/internals/shared/grpc/validate_session_test.go

@@ -42,7 +42,7 @@ func setupValidateSessionTest(t *testing.T) *validateSessionTestSetup {
 	tokenStore := NewOneTimeTokenStore(ctx, testCacheStore(t))
 	pkceStore := NewPKCEVerifierStore(ctx, testCacheStore(t))
 
-	proxyService := NewProxyServiceServer(nil, tokenStore, pkceStore, ProxyOIDCConfig{}, nil, usersManager, proxyManager, nil)
+	proxyService := NewProxyServiceServer(nil, tokenStore, pkceStore, ProxyOIDCConfig{}, nil, usersManager, nil, proxyManager, nil)
 	proxyService.SetServiceManager(serviceManager)
 
 	createTestProxies(t, ctx, testStore)

management/server/account_test.go

@@ -3215,7 +3215,7 @@ func createManager(t testing.TB) (*DefaultAccountManager, *update_channel.PeersU
 		return nil, nil, err
 	}
 
-	proxyGrpcServer := nbgrpc.NewProxyServiceServer(nil, nil, nil, nbgrpc.ProxyOIDCConfig{}, peersManager, nil, proxyManager, nil)
+	proxyGrpcServer := nbgrpc.NewProxyServiceServer(nil, nil, nil, nbgrpc.ProxyOIDCConfig{}, peersManager, nil, nil, proxyManager, nil)
 	proxyController, err := proxymanager.NewGRPCController(proxyGrpcServer, noop.Meter{})
 	if err != nil {
 		return nil, nil, err

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

@@ -217,6 +217,7 @@ func setupAuthCallbackTest(t *testing.T) *testSetup {
 		usersManager,
 		nil,
 		nil,
+		nil,
 	)
 
 	proxyService.SetServiceManager(&testServiceManager{store: testStore})

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

@@ -110,7 +110,7 @@ func BuildApiBlackBoxWithDBState(t testing_tools.TB, sqlFile string, expectedPee
 	if err != nil {
 		t.Fatalf("Failed to create proxy manager: %v", err)
 	}
-	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr, nil)
+	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, nil, proxyMgr, nil)
 	domainManager := manager.NewManager(store, proxyMgr, permissionsManager, am)
 	serviceProxyController, err := proxymanager.NewGRPCController(proxyServiceServer, noopMeter)
 	if err != nil {
@@ -240,7 +240,7 @@ func BuildApiBlackBoxWithDBStateAndPeerChannel(t testing_tools.TB, sqlFile strin
 	if err != nil {
 		t.Fatalf("Failed to create proxy manager: %v", err)
 	}
-	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, proxyMgr, nil)
+	proxyServiceServer := nbgrpc.NewProxyServiceServer(accessLogsManager, proxyTokenStore, pkceverifierStore, nbgrpc.ProxyOIDCConfig{}, peersManager, userManager, nil, proxyMgr, nil)
 	domainManager := manager.NewManager(store, proxyMgr, permissionsManager, am)
 	serviceProxyController, err := proxymanager.NewGRPCController(proxyServiceServer, noopMeter)
 	if err != nil {

management/server/peer.go

@@ -982,8 +982,6 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 	var peer *nbpeer.Peer
 	var updated, versionChanged, ipv6CapabilityChanged bool
 	var err error
-	var postureChecks []*posture.Checks
-	var peerGroupIDs []string
 
 	settings, err := am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
 	if err != nil {
@@ -1011,13 +1009,8 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 			return status.NewPeerLoginExpiredError()
 		}
 
-		peerGroupIDs, err = getPeerGroupIDs(ctx, transaction, accountID, peer.ID)
-		if err != nil {
-			return err
-		}
-
 		oldHasIPv6Cap := peer.HasCapability(nbpeer.PeerCapabilityIPv6Overlay)
-		updated, versionChanged = peer.UpdateMetaIfNew(sync.Meta)
+		updated, versionChanged = peer.UpdateMetaIfNew(ctx, sync.Meta)
 		ipv6CapabilityChanged = oldHasIPv6Cap != peer.HasCapability(nbpeer.PeerCapabilityIPv6Overlay)
 		if updated {
 			am.metrics.AccountManagerMetrics().CountPeerMetUpdate()
@@ -1025,11 +1018,6 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 			if err = transaction.SavePeer(ctx, accountID, peer); err != nil {
 				return err
 			}
-
-			postureChecks, err = getPeerPostureChecks(ctx, transaction, accountID, peer.ID)
-			if err != nil {
-				return err
-			}
 		}
 		return nil
 	})
@@ -1037,6 +1025,11 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 		return nil, nil, nil, 0, err
 	}
 
+	peerGroupIDs, err := getPeerGroupIDs(ctx, am.Store, accountID, peer.ID)
+	if err != nil {
+		return nil, nil, nil, 0, err
+	}
+
 	peerNotValid, isStatusChanged, err := am.integratedPeerValidator.IsNotValidPeer(ctx, accountID, peer, peerGroupIDs, settings.Extra)
 	if err != nil {
 		return nil, nil, nil, 0, err
@@ -1047,9 +1040,9 @@ func (am *DefaultAccountManager) SyncPeer(ctx context.Context, sync types.PeerSy
 		return nil, nil, nil, 0, err
 	}
 
-	if isStatusChanged || sync.UpdateAccountPeers || ipv6CapabilityChanged || updated || (len(postureChecks) > 0 || versionChanged) {
+	if isStatusChanged || sync.UpdateAccountPeers || ipv6CapabilityChanged || (updated && (len(resPostureChecks) > 0 || versionChanged)) {
 		changedPeerIDs := []string{peer.ID}
-		affectedPeerIDs := am.syncPeerAffectedPeers(ctx, accountID, peer.ID, nmap, peerNotValid, updated, len(postureChecks) > 0)
+		affectedPeerIDs := am.syncPeerAffectedPeers(ctx, accountID, peer.ID, nmap, peerNotValid, updated, len(resPostureChecks) > 0)
 		if err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs); err != nil {
 			return nil, nil, nil, 0, fmt.Errorf("notify network map controller of peer update: %w", err)
 		}
@@ -1124,7 +1117,7 @@ func (am *DefaultAccountManager) LoginPeer(ctx context.Context, login types.Peer
 	}
 
 	var peer *nbpeer.Peer
-	var shouldStorePeer bool
+	var shouldStorePeer, shouldUpdatePeers bool
 	var peerGroupIDs []string
 
 	settings, err := am.Store.GetAccountSettings(ctx, store.LockingStrengthNone, accountID)
@@ -1151,14 +1144,10 @@ func (am *DefaultAccountManager) LoginPeer(ctx context.Context, login types.Peer
 
 			if changed {
 				shouldStorePeer = true
+				shouldUpdatePeers = true
 			}
 		}
 
-		peerGroupIDs, err = getPeerGroupIDs(ctx, transaction, accountID, peer.ID)
-		if err != nil {
-			return err
-		}
-
 		if peer.SSHKey != login.SSHKey {
 			peer.SSHKey = login.SSHKey
 			shouldStorePeer = true
@@ -1180,7 +1169,15 @@ func (am *DefaultAccountManager) LoginPeer(ctx context.Context, login types.Peer
 		return nil, nil, nil, false, err
 	}
 
-	isRequiresApproval, isStatusChanged, err := am.integratedPeerValidator.IsNotValidPeer(ctx, accountID, peer, peerGroupIDs, settings.Extra)
+	// This is needed to keep in memory for the peer config. Otherwise browser client will end in a retry loop
+	peer.UpdateMetaIfNew(ctx, login.Meta)
+
+	peerGroupIDs, err = getPeerGroupIDs(ctx, am.Store, accountID, peer.ID)
+	if err != nil {
+		return nil, nil, nil, false, err
+	}
+
+	isRequiresApproval, _, err := am.integratedPeerValidator.IsNotValidPeer(ctx, accountID, peer, peerGroupIDs, settings.Extra)
 	if err != nil {
 		return nil, nil, nil, false, err
 	}
@@ -1190,7 +1187,7 @@ func (am *DefaultAccountManager) LoginPeer(ctx context.Context, login types.Peer
 		return nil, nil, nil, false, err
 	}
 
-	if isStatusChanged || shouldStorePeer {
+	if shouldUpdatePeers {
 		changedPeerIDs := []string{peer.ID}
 		affectedPeerIDs := am.resolveAffectedPeersForPeerChanges(ctx, am.Store, accountID, changedPeerIDs)
 		if err = am.networkMapController.OnPeersUpdated(ctx, accountID, changedPeerIDs, affectedPeerIDs); err != nil {
@@ -1286,12 +1283,22 @@ func getPeerLoginInfo(ctx context.Context, transaction store.Store, accountID st
 		return network, nil, false, nil
 	}
 
-	postureChecks, err := getPeerPostureChecks(ctx, transaction, accountID, peer.ID)
+	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
 	if err != nil {
 		return nil, nil, false, err
 	}
 
-	enableSSH, err := isPeerSSHEnabled(ctx, transaction, accountID, peer)
+	peerGroupIDs, err := transaction.GetPeerGroupIDs(ctx, store.LockingStrengthNone, accountID, peer.ID)
+	if err != nil {
+		return nil, nil, false, err
+	}
+
+	postureChecks, err := getPeerPostureChecks(ctx, transaction, accountID, peerGroupIDs, policies)
+	if err != nil {
+		return nil, nil, false, err
+	}
+
+	enableSSH, err := isPeerSSHEnabled(ctx, peer, policies, peerGroupIDs)
 	if err != nil {
 		return nil, nil, false, err
 	}
@@ -1299,32 +1306,16 @@ func getPeerLoginInfo(ctx context.Context, transaction store.Store, accountID st
 	return network, postureChecks, enableSSH, nil
 }
 
-func isPeerSSHEnabled(ctx context.Context, transaction store.Store, accountID string, peer *nbpeer.Peer) (bool, error) {
-	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		return false, err
+func isPeerSSHEnabled(ctx context.Context, peer *nbpeer.Peer, policies []*types.Policy, peerGroupIDs []string) (bool, error) {
+	groupIDsMap := make(map[string]struct{}, len(peerGroupIDs))
+	for _, peerID := range peerGroupIDs {
+		groupIDsMap[peerID] = struct{}{}
 	}
-
-	peerGroups, err := transaction.GetPeerGroups(ctx, store.LockingStrengthNone, accountID, peer.ID)
-	if err != nil {
-		return false, err
-	}
-
-	peerGroupIDs := make(map[string]struct{}, len(peerGroups))
-	for _, g := range peerGroups {
-		peerGroupIDs[g.ID] = struct{}{}
-	}
-
-	return types.PeerSSHEnabledFromPolicies(policies, peer.ID, peerGroupIDs, peer.SSHEnabled), nil
+	return types.PeerSSHEnabledFromPolicies(policies, peer.ID, groupIDsMap, peer.SSHEnabled), nil
 }
 
 // getPeerPostureChecks returns the posture checks for the peer.
-func getPeerPostureChecks(ctx context.Context, transaction store.Store, accountID, peerID string) ([]*posture.Checks, error) {
-	policies, err := transaction.GetAccountPolicies(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		return nil, err
-	}
-
+func getPeerPostureChecks(ctx context.Context, transaction store.Store, accountID string, peerGroupIDs []string, policies []*types.Policy) ([]*posture.Checks, error) {
 	if len(policies) == 0 {
 		return nil, nil
 	}
@@ -1336,11 +1327,7 @@ func getPeerPostureChecks(ctx context.Context, transaction store.Store, accountI
 			continue
 		}
 
-		postureChecksIDs, err := processPeerPostureChecks(ctx, transaction, policy, accountID, peerID)
-		if err != nil {
-			return nil, err
-		}
-
+		postureChecksIDs := processPeerPostureChecks(policy, peerGroupIDs)
 		peerPostureChecksIDs = append(peerPostureChecksIDs, postureChecksIDs...)
 	}
 
@@ -1353,29 +1340,19 @@ func getPeerPostureChecks(ctx context.Context, transaction store.Store, accountI
 }
 
 // processPeerPostureChecks checks if the peer is in the source group of the policy and returns the posture checks.
-func processPeerPostureChecks(ctx context.Context, transaction store.Store, policy *types.Policy, accountID, peerID string) ([]string, error) {
+func processPeerPostureChecks(policy *types.Policy, peerGroupIDs []string) []string {
 	for _, rule := range policy.Rules {
 		if !rule.Enabled {
 			continue
 		}
 
-		sourceGroups, err := transaction.GetGroupsByIDs(ctx, store.LockingStrengthNone, accountID, rule.Sources)
-		if err != nil {
-			return nil, err
-		}
-
 		for _, sourceGroup := range rule.Sources {
-			group, ok := sourceGroups[sourceGroup]
-			if !ok {
-				return nil, fmt.Errorf("failed to check peer in policy source group")
-			}
-
-			if slices.Contains(group.Peers, peerID) {
-				return policy.SourcePostureChecks, nil
+			if slices.Contains(peerGroupIDs, sourceGroup) {
+				return policy.SourcePostureChecks
 			}
 		}
 	}
-	return nil, nil
+	return nil
 }
 
 // checkIFPeerNeedsLoginWithoutLock checks if the peer needs login without acquiring the account lock. The check validate if the peer was not added via SSO

management/server/peer/peer.go

@@ -1,12 +1,16 @@
 package peer
 
 import (
+	"context"
+	"fmt"
 	"net"
 	"net/netip"
 	"slices"
-	"sort"
+	"strings"
 	"time"
 
+	log "github.com/sirupsen/logrus"
+
 	"github.com/netbirdio/netbird/management/server/util"
 	"github.com/netbirdio/netbird/shared/management/http/api"
 )
@@ -162,49 +166,7 @@ type PeerSystemMeta struct { //nolint:revive
 }
 
 func (p PeerSystemMeta) isEqual(other PeerSystemMeta) bool {
-	sort.Slice(p.NetworkAddresses, func(i, j int) bool {
-		return p.NetworkAddresses[i].Mac < p.NetworkAddresses[j].Mac
-	})
-	sort.Slice(other.NetworkAddresses, func(i, j int) bool {
-		return other.NetworkAddresses[i].Mac < other.NetworkAddresses[j].Mac
-	})
-	equalNetworkAddresses := slices.EqualFunc(p.NetworkAddresses, other.NetworkAddresses, func(addr NetworkAddress, oAddr NetworkAddress) bool {
-		return addr.Mac == oAddr.Mac && addr.NetIP == oAddr.NetIP
-	})
-	if !equalNetworkAddresses {
-		return false
-	}
-
-	sort.Slice(p.Files, func(i, j int) bool {
-		return p.Files[i].Path < p.Files[j].Path
-	})
-	sort.Slice(other.Files, func(i, j int) bool {
-		return other.Files[i].Path < other.Files[j].Path
-	})
-	equalFiles := slices.EqualFunc(p.Files, other.Files, func(file File, oFile File) bool {
-		return file.Path == oFile.Path && file.Exist == oFile.Exist && file.ProcessIsRunning == oFile.ProcessIsRunning
-	})
-	if !equalFiles {
-		return false
-	}
-
-	return p.Hostname == other.Hostname &&
-		p.GoOS == other.GoOS &&
-		p.Kernel == other.Kernel &&
-		p.KernelVersion == other.KernelVersion &&
-		p.Core == other.Core &&
-		p.Platform == other.Platform &&
-		p.OS == other.OS &&
-		p.OSVersion == other.OSVersion &&
-		p.WtVersion == other.WtVersion &&
-		p.UIVersion == other.UIVersion &&
-		p.SystemSerialNumber == other.SystemSerialNumber &&
-		p.SystemProductName == other.SystemProductName &&
-		p.SystemManufacturer == other.SystemManufacturer &&
-		p.Environment.Cloud == other.Environment.Cloud &&
-		p.Environment.Platform == other.Environment.Platform &&
-		p.Flags.isEqual(other.Flags) &&
-		capabilitiesEqual(p.Capabilities, other.Capabilities)
+	return len(metaDiff(p, other)) == 0
 }
 
 func (p PeerSystemMeta) isEmpty() bool {
@@ -296,7 +258,7 @@ func (p *Peer) Copy() *Peer {
 
 // UpdateMetaIfNew updates peer's system metadata if new information is provided
 // returns true if meta was updated, false otherwise
-func (p *Peer) UpdateMetaIfNew(meta PeerSystemMeta) (updated, versionChanged bool) {
+func (p *Peer) UpdateMetaIfNew(ctx context.Context, meta PeerSystemMeta) (updated, versionChanged bool) {
 	if meta.isEmpty() {
 		return updated, versionChanged
 	}
@@ -308,14 +270,121 @@ func (p *Peer) UpdateMetaIfNew(meta PeerSystemMeta) (updated, versionChanged boo
 		meta.UIVersion = p.Meta.UIVersion
 	}
 
-	if p.Meta.isEqual(meta) {
-		return updated, versionChanged
+	oldVersion := p.Meta.WtVersion
+
+	diff := metaDiff(p.Meta, meta)
+	if len(diff) != 0 {
+		p.Meta = meta
+		updated = true
 	}
-	p.Meta = meta
-	updated = true
+
+	versionInfo := ""
+	if versionChanged {
+		versionInfo = fmt.Sprintf("version changed: %s -> %s, ", oldVersion, meta.WtVersion)
+	}
+
+	if len(diff) > 0 || versionChanged {
+		log.WithContext(ctx).
+			Debugf("peer meta updated, %s%d field(s) changed: %s", versionInfo, len(diff), strings.Join(diff, ", "))
+	}
+
 	return updated, versionChanged
 }
 
+// metaDiff returns a human-readable list of the fields that differ between the
+// old and new meta, each formatted as `field: <old> -> <new>`. It is the single
+// source of truth for meta comparison: isEqual reports equality as an empty
+// diff, so the log line can never disagree with the change decision. Slices are
+// cloned before sorting, so callers' meta is not mutated.
+func metaDiff(oldMeta, newMeta PeerSystemMeta) []string {
+	var diff []string
+	add := func(field string, oldVal, newVal any) {
+		diff = append(diff, fmt.Sprintf("%s: %v -> %v", field, oldVal, newVal))
+	}
+
+	if oldMeta.Hostname != newMeta.Hostname {
+		add("hostname", oldMeta.Hostname, newMeta.Hostname)
+	}
+	if oldMeta.GoOS != newMeta.GoOS {
+		add("goos", oldMeta.GoOS, newMeta.GoOS)
+	}
+	if oldMeta.Kernel != newMeta.Kernel {
+		add("kernel", oldMeta.Kernel, newMeta.Kernel)
+	}
+	if oldMeta.KernelVersion != newMeta.KernelVersion {
+		add("kernel_version", oldMeta.KernelVersion, newMeta.KernelVersion)
+	}
+	if oldMeta.Core != newMeta.Core {
+		add("core", oldMeta.Core, newMeta.Core)
+	}
+	if oldMeta.Platform != newMeta.Platform {
+		add("platform", oldMeta.Platform, newMeta.Platform)
+	}
+	if oldMeta.OS != newMeta.OS {
+		add("os", oldMeta.OS, newMeta.OS)
+	}
+	if oldMeta.OSVersion != newMeta.OSVersion {
+		add("os_version", oldMeta.OSVersion, newMeta.OSVersion)
+	}
+	if oldMeta.WtVersion != newMeta.WtVersion {
+		add("wt_version", oldMeta.WtVersion, newMeta.WtVersion)
+	}
+	if oldMeta.UIVersion != newMeta.UIVersion {
+		add("ui_version", oldMeta.UIVersion, newMeta.UIVersion)
+	}
+	if oldMeta.SystemSerialNumber != newMeta.SystemSerialNumber {
+		add("system_serial_number", oldMeta.SystemSerialNumber, newMeta.SystemSerialNumber)
+	}
+	if oldMeta.SystemProductName != newMeta.SystemProductName {
+		add("system_product_name", oldMeta.SystemProductName, newMeta.SystemProductName)
+	}
+	if oldMeta.SystemManufacturer != newMeta.SystemManufacturer {
+		add("system_manufacturer", oldMeta.SystemManufacturer, newMeta.SystemManufacturer)
+	}
+	if oldMeta.Environment.Cloud != newMeta.Environment.Cloud {
+		add("environment_cloud", oldMeta.Environment.Cloud, newMeta.Environment.Cloud)
+	}
+	if oldMeta.Environment.Platform != newMeta.Environment.Platform {
+		add("environment_platform", oldMeta.Environment.Platform, newMeta.Environment.Platform)
+	}
+	if !oldMeta.Flags.isEqual(newMeta.Flags) {
+		add("flags", fmt.Sprintf("%+v", oldMeta.Flags), fmt.Sprintf("%+v", newMeta.Flags))
+	}
+	if !capabilitiesEqual(oldMeta.Capabilities, newMeta.Capabilities) {
+		add("capabilities", oldMeta.Capabilities, newMeta.Capabilities)
+	}
+
+	if !sameMultiset(oldMeta.NetworkAddresses, newMeta.NetworkAddresses) {
+		add("network_addresses", fmt.Sprintf("%v", oldMeta.NetworkAddresses), fmt.Sprintf("%v", newMeta.NetworkAddresses))
+	}
+
+	if !sameMultiset(oldMeta.Files, newMeta.Files) {
+		add("files", fmt.Sprintf("%v", oldMeta.Files), fmt.Sprintf("%v", newMeta.Files))
+	}
+
+	return diff
+}
+
+// sameMultiset reports whether two slices contain the same elements with the
+// same multiplicity, ignoring order. The element type is the comparison key, so
+// every field participates in equality.
+func sameMultiset[T comparable](a, b []T) bool {
+	if len(a) != len(b) {
+		return false
+	}
+	counts := make(map[T]int, len(a))
+	for _, v := range a {
+		counts[v]++
+	}
+	for _, v := range b {
+		counts[v]--
+		if counts[v] == 0 {
+			delete(counts, v)
+		}
+	}
+	return len(counts) == 0
+}
+
 // GetLastLogin returns the last login time of the peer.
 func (p *Peer) GetLastLogin() time.Time {
 	if p.LastLogin != nil {

management/server/peer/peer_metadiff_test.go

@@ -0,0 +1,113 @@
+package peer
+
+import (
+	"net/netip"
+	"reflect"
+	"testing"
+
+	"github.com/stretchr/testify/require"
+)
+
+// metaDiffExtraEntries accounts for PeerSystemMeta fields that metaDiff does not
+// map 1:1 to a single diff entry. Today the only such field is Environment, which
+// is exploded into two checks (Cloud, Platform) and therefore yields one extra
+// entry beyond its single struct field. If you teach metaDiff to explode another
+// field into N entries, bump this by N-1; if you collapse a field, lower it.
+const metaDiffExtraEntries = 1
+
+// TestMetaDiff_CoversAllFields fully populates a PeerSystemMeta with non-zero
+// values and diffs it against the zero value, then asserts metaDiff emits exactly
+// one entry per exported field (plus metaDiffExtraEntries for fields it explodes).
+//
+// The expected count is derived from the struct via reflection, so adding a field
+// to PeerSystemMeta raises the expectation automatically — but the actual diff
+// only grows if metaDiff was taught to compare the new field. A mismatch means
+// someone changed the struct without updating metaDiff (or this test's
+// extra-entry accounting), which is exactly what we want to catch.
+func TestMetaDiff_CoversAllFields(t *testing.T) {
+	var full PeerSystemMeta
+	exported := populateAll(t, reflect.ValueOf(&full).Elem())
+	require.NotZero(t, exported, "expected PeerSystemMeta to expose fields")
+
+	diff := metaDiff(PeerSystemMeta{}, full)
+
+	require.Len(t, diff, exported+metaDiffExtraEntries,
+		"metaDiff entry count no longer matches PeerSystemMeta's fields: a field was "+
+			"likely added or removed without updating metaDiff (or metaDiffExtraEntries). "+
+			"diff was: %v", diff)
+
+	require.False(t, full.isEqual(PeerSystemMeta{}),
+		"isEqual must report a fully-populated meta as different from the zero value")
+}
+
+// TestFlags_isEqualChecksEveryField guards the one field that the count-based
+// TestMetaDiff_CoversAllFields cannot: metaDiff collapses all of Flags into a
+// single "flags" diff entry, so a new Flags field that Flags.isEqual forgets to
+// compare would not change the diff count. This flips each Flags field on its own
+// and asserts Flags.isEqual notices, so adding a Flags field without comparing it
+// fails here.
+func TestFlags_isEqualChecksEveryField(t *testing.T) {
+	typ := reflect.TypeOf(Flags{})
+	for i := 0; i < typ.NumField(); i++ {
+		f := typ.Field(i)
+		require.Equal(t, reflect.Bool, f.Type.Kind(),
+			"Flags.%s is not a bool; extend this test to set it non-zero", f.Name)
+
+		var a, b Flags
+		reflect.ValueOf(&b).Elem().Field(i).SetBool(true)
+		require.False(t, a.isEqual(b), "Flags.isEqual ignores field %s", f.Name)
+	}
+}
+
+// populateAll sets every exported field of the struct to a deterministic non-zero
+// value, recursing into nested structs and the element type of struct slices so
+// that each leaf differs from zero. It returns the number of exported fields on
+// the top-level struct. netip.Prefix is treated as an opaque leaf (it has no
+// settable exported fields and is comparable with ==).
+func populateAll(t *testing.T, v reflect.Value) int {
+	t.Helper()
+
+	typ := v.Type()
+	exported := 0
+	for i := 0; i < typ.NumField(); i++ {
+		f := typ.Field(i)
+		if f.PkgPath != "" { // unexported
+			continue
+		}
+		exported++
+		setNonZero(t, v.Field(i))
+	}
+	return exported
+}
+
+// setNonZero assigns a deterministic non-zero value to a field based on its kind,
+// recursing into nested structs and populating one element of slice fields.
+func setNonZero(t *testing.T, field reflect.Value) {
+	t.Helper()
+
+	if field.Type() == reflect.TypeOf(netip.Prefix{}) {
+		field.Set(reflect.ValueOf(netip.MustParsePrefix("10.0.0.0/24")))
+		return
+	}
+
+	switch field.Kind() {
+	case reflect.String:
+		field.SetString("non-zero")
+	case reflect.Bool:
+		field.SetBool(true)
+	case reflect.Int, reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64:
+		field.SetInt(7)
+	case reflect.Uint, reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64:
+		field.SetUint(7)
+	case reflect.Float32, reflect.Float64:
+		field.SetFloat(7)
+	case reflect.Struct:
+		populateAll(t, field)
+	case reflect.Slice:
+		s := reflect.MakeSlice(field.Type(), 1, 1)
+		setNonZero(t, s.Index(0))
+		field.Set(s)
+	default:
+		t.Fatalf("unhandled field kind %s; extend setNonZero", field.Kind())
+	}
+}

proxy/management_byop_integration_test.go

@@ -125,6 +125,7 @@ func setupBYOPIntegrationTest(t *testing.T) *byopTestSetup {
 		oidcConfig,
 		nil,
 		usersManager,
+		nil,
 		realProxyManager,
 		nil,
 	)

proxy/management_integration_test.go

@@ -140,6 +140,7 @@ func setupIntegrationTest(t *testing.T) *integrationTestSetup {
 		oidcConfig,
 		nil,
 		usersManager,
+		nil,
 		proxyManager,
 		nil,
 	)

release_files/freebsd-port-diff.sh

@@ -21,7 +21,8 @@ AWK_FIRST_FIELD='{print $1}'
 
 fetch_all_tags() {
     curl -sL "https://github.com/${GITHUB_REPO}/tags" 2>/dev/null | \
-        grep -oE '/releases/tag/v[0-9]+\.[0-9]+\.[0-9]+' | \
+        grep -oE '/releases/tag/v[0-9]+\.[0-9]+\.[0-9]+([^"]+)?' | \
+        grep -iv 'rc' | \
         sed 's/.*\/v//' | \
         sort -u -V
     return 0

release_files/freebsd-port-issue-body.sh

@@ -32,7 +32,8 @@ fetch_current_ports_version() {
 fetch_all_tags() {
     # Fetch tags from GitHub tags page (no rate limiting, no auth needed)
     curl -sL "https://github.com/${GITHUB_REPO}/tags" 2>/dev/null | \
-        grep -oE '/releases/tag/v[0-9]+\.[0-9]+\.[0-9]+' | \
+        grep -oE '/releases/tag/v[0-9]+\.[0-9]+\.[0-9]+([^"]+)?' | \
+        grep -iv 'rc' | \
         sed 's/.*\/v//' | \
         sort -u -V
     return 0

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