Fix openapi generated files

The docs still described the retired proxy-side pricing: pricing.Loader,
  pricing_path, MiddlewareDataDir, embedded defaults_pricing.yaml, and the
  symlink-safe Unix loader. Rewrite them for the current design — management
  synthesizes the whole table and ships it in cost_meter's ConfigJSON, so the
  proxy carries no price list and has nothing to reload.

.goreleaser_ui.yaml

@@ -93,9 +93,7 @@ nfpms:
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
     dependencies:
-      - netbird (>= 0.75.0)
-      - libgtk-4-1 (>= 4.14)
-      - libwebkitgtk-6.0-4
+      - netbird
 
   - maintainer: Netbird <dev@netbird.io>
     description: Netbird client UI.
@@ -116,9 +114,7 @@ nfpms:
       - src: client/ui/build/appicon.png
         dst: /usr/share/pixmaps/netbird.png
     dependencies:
-      - netbird >= 0.75.0
-      - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
-      - (webkitgtk6.0 or libwebkitgtk-6_0-4)
+      - netbird
 
     rpm:
       signature:

AGENTS.md

@@ -1,6 +1,6 @@
 # NetBird Agent Guidelines
 
-**NetBird** is an open-source connectivity platform: a WireGuard®-based overlay
+**NetBird** is an open source connectivity platform: a WireGuard®-based overlay
 network with a control plane. The **agent** (`client/`) runs on user machines as
 a privileged daemon and manages the WireGuard interface, routing, firewall, and
 DNS. **Management** (`management/`) is the control plane and REST/gRPC API,

CONTRIBUTING.md

@@ -478,7 +478,7 @@ go test -race ./client/internal/dns/...
 
 ## Checklist before submitting a PR
 
-As a critical network service and open-source project, we must enforce a few
+As a critical network service and open source project, we must enforce a few
 things before submitting a pull request. The
 [pull request template](/.github/pull_request_template.md) mirrors this list —
 fill it in rather than deleting it.

README.md

@@ -130,7 +130,7 @@ In November 2022, NetBird joined the [StartUpSecure program](https://www.forschu
 ![CISPA_Logo_BLACK_EN_RZ_RGB (1)](https://user-images.githubusercontent.com/700848/203091324-c6d311a0-22b5-4b05-a288-91cbc6cdcc46.png)
 
 ### Acknowledgements
-We build on open-source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
+We build on open source technologies like [WireGuard®](https://www.wireguard.com/), [Pion ICE](https://github.com/pion/ice), and [Rosenpass](https://rosenpass.eu). We greatly appreciate the work these projects are doing, and we'd love it if you could support them too (e.g., by starring or contributing).
 
 ### Legal
 This repository is licensed under the BSD-3-Clause license, which applies to all parts of the repository except for the directories management/, signal/ and relay/.

SECURITY.md

@@ -14,7 +14,7 @@ Report security issues one of these two ways:
   on this repository. This is the preferred route: it keeps the discussion, the draft advisory, and the credit in one place.
 - **Email** — `security@netbird.io`.
 
-If the finding affects NetBird Cloud or our hosted infrastructure rather than the open-source code, email us rather than
+If the finding affects NetBird Cloud or our hosted infrastructure rather than the open source code, email us rather than
 filing a repository report.
 
 ### What to include

client/internal/connect.go

@@ -113,14 +113,11 @@ func (c *ConnectClient) RunOnAndroid(
 	stateFilePath string,
 	cacheDir string,
 ) error {
-	notifier := tunnelnotifier.New(networkChangeListener, nil)
-	defer notifier.Close()
-
 	// in case of non Android os these variables will be nil
 	mobileDependency := MobileDependency{
 		TunAdapter:            tunAdapter,
 		IFaceDiscover:         iFaceDiscover,
-		NetworkChangeListener: notifier,
+		NetworkChangeListener: networkChangeListener,
 		HostDNSAddresses:      dnsAddresses,
 		DnsReadyListener:      dnsReadyListener,
 		StateFilePath:         stateFilePath,

client/internal/dns/interface_index.go

@@ -1,15 +0,0 @@
-package dns
-
-import (
-	"fmt"
-	"net"
-)
-
-func getInterfaceIndex(interfaceName string) (int, error) {
-	iface, err := net.InterfaceByName(interfaceName)
-	if err != nil {
-		return 0, fmt.Errorf("lookup interface %q: %w", interfaceName, err)
-	}
-
-	return iface.Index, nil
-}

client/internal/dns/interface_index_test.go

@@ -1,35 +0,0 @@
-package dns
-
-import (
-	"net"
-	"testing"
-)
-
-func TestGetInterfaceIndexExisting(t *testing.T) {
-	interfaces, err := net.Interfaces()
-	if err != nil {
-		t.Fatalf("list network interfaces: %v", err)
-	}
-	if len(interfaces) == 0 {
-		t.Fatal("expected at least one network interface")
-	}
-
-	iface := interfaces[0]
-	index, err := getInterfaceIndex(iface.Name)
-	if err != nil {
-		t.Fatalf("look up existing interface %q: %v", iface.Name, err)
-	}
-	if index != iface.Index {
-		t.Fatalf("expected interface index %d, got %d", iface.Index, index)
-	}
-}
-
-func TestGetInterfaceIndexMissing(t *testing.T) {
-	index, err := getInterfaceIndex("netbird-interface-that-does-not-exist")
-	if index != 0 {
-		t.Fatalf("expected missing interface index to be 0, got %d", index)
-	}
-	if err == nil {
-		t.Fatal("expected missing interface lookup to return an error")
-	}
-}

client/internal/dns/notifier.go

@@ -51,5 +51,7 @@ func (n *notifier) notify() {
 		return
 	}
 
-	n.listener.OnNetworkChanged("")
+	go func(l listener.NetworkChangeListener) {
+		l.OnNetworkChanged("")
+	}(n.listener)
 }

client/internal/dns/upstream_ios.go

@@ -130,3 +130,8 @@ func GetClientPrivate(iface privateClientIface, upstreamIP netip.Addr, dialTimeo
 	}
 	return client, nil
 }
+
+func getInterfaceIndex(interfaceName string) (int, error) {
+	iface, err := net.InterfaceByName(interfaceName)
+	return iface.Index, err
+}

client/internal/profilemanager/state.go

@@ -45,35 +45,12 @@ func (pm *ProfileManager) GetProfileState(id ID) (*ProfileState, error) {
 	return &state, nil
 }
 
-// SetProfileState writes the state file of the profile identified by id. Prefer
-// it over SetActiveProfileState whenever the caller knows which profile the data
-// belongs to: an SSO login spans seconds of user interaction, and the active
-// profile can change during it, which would file the account email under
-// whichever profile happened to be active when the flow returned.
-func (pm *ProfileManager) SetProfileState(id ID, state *ProfileState) error {
+func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 	configDir, err := getConfigDir()
 	if err != nil {
 		return fmt.Errorf("get config directory: %w", err)
 	}
 
-	if id == "" {
-		return fmt.Errorf("empty profile ID")
-	}
-	if id != defaultProfileName && !IsValidProfileFilenameStem(id) {
-		return fmt.Errorf("invalid profile ID: %q", id)
-	}
-
-	stateFile := filepath.Join(configDir, id.String()+".state.json")
-	if err := util.WriteJsonWithRestrictedPermission(context.Background(), stateFile, state); err != nil {
-		return fmt.Errorf("write profile state: %w", err)
-	}
-
-	return nil
-}
-
-// SetActiveProfileState writes the state file of whichever profile is active at
-// call time. Use SetProfileState when the target profile is known.
-func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 	activeProf, err := pm.GetActiveProfile()
 	if err != nil {
 		if errors.Is(err, ErrNoActiveProfile) {
@@ -82,7 +59,18 @@ func (pm *ProfileManager) SetActiveProfileState(state *ProfileState) error {
 		return fmt.Errorf("get active profile: %w", err)
 	}
 
-	return pm.SetProfileState(activeProf.ID, state)
+	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)
+	}
+
+	return nil
 }
 
 // RemoveProfileState deletes the per-profile state file (which holds the

client/internal/routemanager/dnsinterceptor/handler.go

@@ -479,7 +479,7 @@ func (d *DnsInterceptor) removeDNATMappings(realPrefixes []netip.Prefix, logger
 
 // internalDnatFw checks if the firewall supports internal DNAT
 func (d *DnsInterceptor) internalDnatFw() (internalDNATer, bool) {
-	if d.firewall == nil || d.fakeIPManager == nil || runtime.GOOS != "android" {
+	if d.firewall == nil || runtime.GOOS != "android" {
 		return nil, false
 	}
 	fw, ok := d.firewall.(internalDNATer)

client/internal/routemanager/manager.go

@@ -165,36 +165,31 @@ func (m *DefaultManager) setupAndroidRoutes(config ManagerConfig) {
 	routesForComparison := slices.Clone(cr)
 
 	if config.DNSFeatureFlag {
-		cr = append(cr, m.enableFakeIPRoutes()...)
+		m.fakeIPManager = fakeip.NewManager()
+
+		v4ID := uuid.NewString()
+		fakeIPRoute := &route.Route{
+			ID:          route.ID(v4ID),
+			Network:     m.fakeIPManager.GetFakeIPBlock(),
+			NetID:       route.NetID(v4ID),
+			Peer:        m.pubKey,
+			NetworkType: route.IPv4Network,
+		}
+		v6ID := uuid.NewString()
+		fakeIPv6Route := &route.Route{
+			ID:          route.ID(v6ID),
+			Network:     m.fakeIPManager.GetFakeIPv6Block(),
+			NetID:       route.NetID(v6ID),
+			Peer:        m.pubKey,
+			NetworkType: route.IPv6Network,
+		}
+		cr = append(cr, fakeIPRoute, fakeIPv6Route)
+		m.notifier.SetFakeIPRoutes([]*route.Route{fakeIPRoute, fakeIPv6Route})
 	}
 
 	m.notifier.SetInitialClientRoutes(cr, routesForComparison)
 }
 
-func (m *DefaultManager) enableFakeIPRoutes() []*route.Route {
-	m.fakeIPManager = fakeip.NewManager()
-
-	v4ID := uuid.NewString()
-	fakeIPRoute := &route.Route{
-		ID:          route.ID(v4ID),
-		Network:     m.fakeIPManager.GetFakeIPBlock(),
-		NetID:       route.NetID(v4ID),
-		Peer:        m.pubKey,
-		NetworkType: route.IPv4Network,
-	}
-	v6ID := uuid.NewString()
-	fakeIPv6Route := &route.Route{
-		ID:          route.ID(v6ID),
-		Network:     m.fakeIPManager.GetFakeIPv6Block(),
-		NetID:       route.NetID(v6ID),
-		Peer:        m.pubKey,
-		NetworkType: route.IPv6Network,
-	}
-	fakeRoutes := []*route.Route{fakeIPRoute, fakeIPv6Route}
-	m.notifier.SetFakeIPRoutes(fakeRoutes)
-	return fakeRoutes
-}
-
 func (m *DefaultManager) setupRefCounters(useNoop bool) {
 	var once sync.Once
 	var wgIface *net.Interface
@@ -469,9 +464,6 @@ func (m *DefaultManager) UpdateRoutes(
 
 	var merr *multierror.Error
 	if !m.disableClientRoutes {
-		if runtime.GOOS == "android" && useNewDNSRoute && m.fakeIPManager == nil {
-			m.enableFakeIPRoutes()
-		}
 
 		// Update route selector based on management server's isSelected status
 		m.updateRouteSelectorFromManagement(clientRoutes)

client/internal/routemanager/notifier/notifier_android.go

@@ -41,7 +41,6 @@ func (n *Notifier) SetInitialClientRoutes(initialRoutes []*route.Route, routesFo
 // SetFakeIPRoutes stores the fake IP routes to be included in every TUN rebuild.
 func (n *Notifier) SetFakeIPRoutes(routes []*route.Route) {
 	n.fakeIPRoutes = routes
-	n.notify()
 }
 
 func (n *Notifier) OnNewRoutes(idMap route.HAMap) {
@@ -79,7 +78,9 @@ func (n *Notifier) notify() {
 
 	routeStrings := n.routesToStrings(allRoutes)
 	sort.Strings(routeStrings)
-	n.listener.OnNetworkChanged(strings.Join(routeStrings, ","))
+	go func(l listener.NetworkChangeListener) {
+		l.OnNetworkChanged(strings.Join(routeStrings, ","))
+	}(n.listener)
 }
 
 func filterStatic(routes []*route.Route) []*route.Route {
@@ -101,11 +102,16 @@ func (n *Notifier) routesToStrings(routes []*route.Route) []string {
 }
 
 func (n *Notifier) hasRouteDiff(a []*route.Route, b []*route.Route) bool {
-	as := n.routesToStrings(a)
-	bs := n.routesToStrings(b)
-	sort.Strings(as)
-	sort.Strings(bs)
-	return !slices.Equal(as, bs)
+	slices.SortFunc(a, func(x, y *route.Route) int {
+		return strings.Compare(x.NetString(), y.NetString())
+	})
+	slices.SortFunc(b, func(x, y *route.Route) int {
+		return strings.Compare(x.NetString(), y.NetString())
+	})
+
+	return !slices.EqualFunc(a, b, func(x, y *route.Route) bool {
+		return x.NetString() == y.NetString()
+	})
 }
 
 func (n *Notifier) GetInitialRouteRanges() []string {

client/internal/updater/installer/installer_run_darwin.go

@@ -98,44 +98,47 @@ func (u *Installer) startDaemon(daemonFolder string) error {
 func (u *Installer) startUIAsUser() error {
 	log.Infof("starting netbird-ui: %s", uiBinary)
 
-	username, err := consoleUser()
+	// Get the current console user
+	cmd := exec.Command("stat", "-f", "%Su", "/dev/console")
+	output, err := cmd.Output()
 	if err != nil {
-		return err
+		return fmt.Errorf("failed to get console user: %w", err)
 	}
 
+	username := strings.TrimSpace(string(output))
+	if username == "" || username == "root" {
+		return fmt.Errorf("no active user session found")
+	}
+
+	log.Infof("starting UI for user: %s", username)
+
+	// Get user's UID
 	userInfo, err := user.Lookup(username)
 	if err != nil {
-		return fmt.Errorf("lookup user %s: %w", username, err)
+		return fmt.Errorf("failed to lookup user %s: %w", username, err)
 	}
 
-	log.Infof("starting UI for user: %s (uid %s)", username, userInfo.Uid)
-
-	launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "sudo", "-u", username, "-H", "open", "-a", uiBinary)
+	// Start the UI process as the console user using launchctl
+	// This ensures the app runs in the user's context with proper GUI access
+	launchCmd := exec.Command("launchctl", "asuser", userInfo.Uid, "open", "-a", uiBinary)
 	log.Infof("launchCmd: %s", launchCmd.String())
+	// Set the user's home directory for proper macOS app behavior
+	launchCmd.Env = append(os.Environ(), "HOME="+userInfo.HomeDir)
+	log.Infof("set HOME environment variable: %s", userInfo.HomeDir)
 
-	if err := launchCmd.Run(); err != nil {
-		return fmt.Errorf("run UI launch: %w", err)
+	if err := launchCmd.Start(); err != nil {
+		return fmt.Errorf("failed to start UI process: %w", err)
+	}
+
+	// Release the process so it can run independently
+	if err := launchCmd.Process.Release(); err != nil {
+		log.Warnf("failed to release UI process: %v", err)
 	}
 
 	log.Infof("netbird-ui started successfully for user %s", username)
 	return nil
 }
 
-func consoleUser() (string, error) {
-	output, err := exec.Command("stat", "-f", "%Su", "/dev/console").Output()
-	if err != nil {
-		return "", fmt.Errorf("get console user: %w", err)
-	}
-
-	username := strings.TrimSpace(string(output))
-	switch username {
-	case "", "root", "loginwindow", "_mbsetupuser":
-		return "", fmt.Errorf("no active GUI user session, console user: %q", username)
-	}
-
-	return username, nil
-}
-
 func (u *Installer) installPkgFile(ctx context.Context, path string) error {
 	log.Infof("installing pkg file: %s", path)
 

client/ios/NetBirdSDK/client.go

@@ -158,19 +158,13 @@ func (c *Client) Run(fd int32, interfaceName string, envList *EnvList) error {
 	defer c.ctxCancel()
 	c.ctxCancelLock.Unlock()
 
-	// No login pre-flight here. The engine's own loginToManagement (connect.go) performs
-	// the authoritative Login immediately before the first Sync, so a LoginSync() call at
-	// this point only duplicated it — costing two extra Login RPCs (IsLoginRequired +
-	// Login) on every engine start, since IsLoginRequired is itself a full Login RPC.
-	//
-	// Auth failures still reach the caller through the engine path: loginToManagement
-	// returns PermissionDenied, which marks the shared status recorder
-	// (MarkManagementDisconnected) and fires ClientStop → onDisconnected, where
-	// IsLoginRequiredCached() reports login-required. The error is also returned out of Run().
-	//
-	// A pre-flight was also actively harmful when the server is unreachable: its 2-minute
-	// backoff blocked the start and then reported "login required" for what was really a
-	// timeout. The engine instead keeps retrying and recovers when the server returns.
+	auth := NewAuthWithConfig(ctx, cfg)
+	err = auth.LoginSync()
+	if err != nil {
+		return err
+	}
+
+	log.Infof("Auth successful")
 	// todo do not throw error in case of cancelled context
 	ctx = internal.CtxInitState(ctx)
 	c.onHostDnsFn = func([]string) {}

client/ios/NetBirdSDK/login.go

@@ -222,36 +222,17 @@ func (a *Auth) Login(resultListener ErrListener, urlOpener URLOpener, forceDevic
 // LoginWithDeviceName performs interactive login with device authentication support
 // The deviceName parameter allows specifying a custom device name (required for tvOS)
 func (a *Auth) LoginWithDeviceName(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string) {
-	a.startLogin(resultListener, urlOpener, forceDeviceAuth, deviceName, false)
-}
-
-// LoginInteractive performs the same interactive login as LoginWithDeviceName but skips the
-// IsLoginRequired() pre-flight and goes straight to the browser / device-code flow.
-//
-// IsLoginRequired() is itself a full Login RPC against the management server, so when the
-// caller has ALREADY established that login is required it is a pure duplicate. On iOS the
-// main app decides to show the browser based on its own isLoginRequired() check and then
-// calls straight into this method, so re-asking the server would add another Login RPC to
-// every interactive login.
-//
-// Use LoginWithDeviceName when the auth state is unknown and a silent (browser-less) login
-// must still be possible; use this when the browser is going to be shown regardless.
-func (a *Auth) LoginInteractive(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string) {
-	a.startLogin(resultListener, urlOpener, forceDeviceAuth, deviceName, true)
-}
-
-func (a *Auth) startLogin(resultListener ErrListener, urlOpener URLOpener, forceDeviceAuth bool, deviceName string, skipLoginCheck bool) {
 	if resultListener == nil {
-		log.Errorf("startLogin: resultListener is nil")
+		log.Errorf("LoginWithDeviceName: resultListener is nil")
 		return
 	}
 	if urlOpener == nil {
-		log.Errorf("startLogin: urlOpener is nil")
+		log.Errorf("LoginWithDeviceName: urlOpener is nil")
 		resultListener.OnError(fmt.Errorf("urlOpener is nil"))
 		return
 	}
 	go func() {
-		err := a.login(urlOpener, forceDeviceAuth, deviceName, skipLoginCheck)
+		err := a.login(urlOpener, forceDeviceAuth, deviceName)
 		if err != nil {
 			resultListener.OnError(err)
 		} else {
@@ -260,7 +241,7 @@ func (a *Auth) startLogin(resultListener ErrListener, urlOpener URLOpener, force
 	}()
 }
 
-func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName string, skipLoginCheck bool) error {
+func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName string) error {
 	// Create context with device name if provided
 	ctx := a.ctx
 	if deviceName != "" {
@@ -274,13 +255,10 @@ func (a *Auth) login(urlOpener URLOpener, forceDeviceAuth bool, deviceName strin
 	}
 	defer authClient.Close()
 
-	// check if we need to generate JWT token (skipped when the caller already knows)
-	needsLogin := true
-	if !skipLoginCheck {
-		needsLogin, err = authClient.IsLoginRequired(ctx)
-		if err != nil {
-			return fmt.Errorf("failed to check login requirement: %v", err)
-		}
+	// check if we need to generate JWT token
+	needsLogin, err := authClient.IsLoginRequired(ctx)
+	if err != nil {
+		return fmt.Errorf("failed to check login requirement: %v", err)
 	}
 
 	jwtToken := ""

client/server/login_outcome_test.go

@@ -1,89 +0,0 @@
-package server
-
-import (
-	"context"
-	"encoding/json"
-	"errors"
-	"os"
-	"testing"
-
-	"github.com/stretchr/testify/require"
-	"google.golang.org/grpc/codes"
-	gstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/client/internal"
-	"github.com/netbirdio/netbird/client/proto"
-)
-
-// A login that never reached Management is not a decision about the peer's
-// credentials, so it must come back as a retryable error rather than an SSO
-// prompt: the user cannot finish a browser login while Management is down, and
-// the CLI's own backoff resolves the outage on its own once the daemon reports
-// the failure. Reproduces `netbird down; netbird up` printing a device-code URL
-// because Management happened to be restarting when the daemon dialed it.
-func TestLogin_ManagementUnreachableIsReturnedInsteadOfDemandingSSO(t *testing.T) {
-	s, _, _, username, _ := setupServerWithProfile(t)
-	s.rootCtx = internal.CtxInitState(context.Background())
-
-	unreachable := errors.New("create connection: dial context: context deadline exceeded")
-	attempts := 0
-	s.loginAttemptFn = func(context.Context, string, string) (internal.StatusType, error) {
-		attempts++
-		return internal.StatusLoginFailed, unreachable
-	}
-
-	resp, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
-	require.Error(t, err)
-	require.ErrorIs(t, err, unreachable, "the transport failure was replaced by something else")
-	require.Nil(t, resp, "a failed login must not answer with a login response")
-	require.Equal(t, 1, attempts)
-	require.Nil(t, s.oauthAuthFlow.flow, "the daemon started an SSO flow for a peer whose login was never decided")
-
-	status, err := internal.CtxGetState(s.rootCtx).Status()
-	require.NoError(t, err)
-	require.Equal(t, internal.StatusLoginFailed, status,
-		"a peer that could not reach Management is not waiting on a login")
-}
-
-// The counterpart: Management refusing the peer's credentials is a decision, and
-// the SSO flow still has to start for it. The profile carries an unusable
-// private key so the flow setup fails immediately instead of dialing, which is
-// enough to show the branch was entered — the refusal itself is never what comes
-// back out.
-func TestLogin_AuthRefusalStartsSSOFlow(t *testing.T) {
-	s, _, _, username, cfgPath := setupServerWithProfile(t)
-	s.rootCtx = internal.CtxInitState(context.Background())
-	breakProfilePrivateKey(t, cfgPath)
-
-	refused := gstatus.Error(codes.PermissionDenied, "peer is not registered")
-	s.loginAttemptFn = func(context.Context, string, string) (internal.StatusType, error) {
-		return internal.StatusNeedsLogin, refused
-	}
-
-	_, err := s.Login(userCtx(), &proto.LoginRequest{Username: &username})
-	require.Error(t, err)
-	require.NotErrorIs(t, err, refused,
-		"the refusal was handed back to the caller instead of starting the SSO flow")
-
-	status, stateErr := internal.CtxGetState(s.rootCtx).Status()
-	require.NoError(t, stateErr)
-	require.Equal(t, internal.StatusLoginFailed, status,
-		"the SSO flow setup was never reached with the broken key")
-}
-
-// breakProfilePrivateKey replaces the profile's private key with an unparseable
-// one, which makes any attempt to build a Management client fail on the spot.
-func breakProfilePrivateKey(t *testing.T, cfgPath string) {
-	t.Helper()
-
-	raw, err := os.ReadFile(cfgPath)
-	require.NoError(t, err)
-
-	var cfg map[string]any
-	require.NoError(t, json.Unmarshal(raw, &cfg))
-	cfg["PrivateKey"] = "not-a-key"
-
-	patched, err := json.Marshal(cfg)
-	require.NoError(t, err)
-	require.NoError(t, os.WriteFile(cfgPath, patched, 0o600))
-}

client/server/server.go

@@ -135,11 +135,6 @@ type Server struct {
 	updateManager *updater.Manager
 
 	jwtCache *jwtCache
-
-	// loginAttemptFn stands in for the Management login round trip. Tests set
-	// it to drive the login outcomes that need a server on the other end;
-	// production leaves it nil, and every login goes through loginAttempt.
-	loginAttemptFn func(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error)
 }
 
 type oauthAuthFlow struct {
@@ -375,19 +370,7 @@ func (s *Server) connectionGoroutineRunning() bool {
 	}
 }
 
-// attemptLogin runs a login round trip against Management, or the stand-in a
-// test installed in place of it.
-func (s *Server) attemptLogin(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
-	if s.loginAttemptFn != nil {
-		return s.loginAttemptFn(ctx, setupKey, jwtToken)
-	}
-	return s.loginAttempt(ctx, setupKey, jwtToken)
-}
-
-// loginAttempt attempts to login using the provided information. It returns
-// StatusNeedsLogin when Management refused the peer's credentials and
-// StatusLoginFailed for every other failure, so callers can tell an
-// authentication decision apart from a login that never got made.
+// loginAttempt attempts to login using the provided information. it returns a status in case something fails
 func (s *Server) loginAttempt(ctx context.Context, setupKey, jwtToken string) (internal.StatusType, error) {
 	authClient, err := auth.NewAuth(ctx, s.config.PrivateKey, s.config.ManagementURL, s.config)
 	if err != nil {
@@ -640,23 +623,11 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	s.config = config
 	s.mutex.Unlock()
 
-	loginStatus, err := s.attemptLogin(ctx, "", "")
-	if err == nil {
+	if _, err := s.loginAttempt(ctx, "", ""); err == nil {
 		state.Set(internal.StatusIdle)
 		return &proto.LoginResponse{}, nil
 	}
 
-	// Only an authentication refusal means the peer has to (re-)authenticate.
-	// Any other failure leaves the login undecided: Management unreachable, a
-	// restart mid-request, an internal error. Those are returned for the caller
-	// to retry, because turning them into an SSO prompt asks the user to solve
-	// something that is not theirs to solve, and a browser login cannot succeed
-	// while Management is unreachable anyway.
-	if loginStatus != internal.StatusNeedsLogin {
-		state.Set(loginStatus)
-		return nil, err
-	}
-
 	if msg.SetupKey == "" {
 		hint := ""
 		if msg.Hint != nil {
@@ -713,7 +684,7 @@ func (s *Server) Login(callerCtx context.Context, msg *proto.LoginRequest) (*pro
 	// which returns NeedsLogin and parks on the browser leg.
 	state.Set(internal.StatusConnecting)
 
-	if loginStatus, err := s.attemptLogin(ctx, msg.SetupKey, ""); err != nil {
+	if loginStatus, err := s.loginAttempt(ctx, msg.SetupKey, ""); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}
@@ -868,7 +839,7 @@ func (s *Server) WaitSSOLogin(callerCtx context.Context, msg *proto.WaitSSOLogin
 	s.oauthAuthFlow.expiresAt = time.Now()
 	s.mutex.Unlock()
 
-	if loginStatus, err := s.attemptLogin(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
+	if loginStatus, err := s.loginAttempt(ctx, "", tokenInfo.GetTokenToUse()); err != nil {
 		state.Set(loginStatus)
 		return nil, err
 	}

client/ui/build/linux/nfpm/nfpm.yaml

@@ -26,17 +26,17 @@ contents:
 
 # Default dependencies for the GTK4 + WebKitGTK 6.0 stack (Ubuntu 24.04+ / Debian 13+)
 depends:
-  - libgtk-4-1 (>= 4.14)
+  - libgtk-4-1
   - libwebkitgtk-6.0-4
   - xdg-utils
 
 # Distribution-specific overrides for different package formats
 overrides:
-  # RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux / openSUSE
+  # RPM packages for Fedora / RHEL / AlmaLinux / Rocky Linux
   rpm:
     depends:
-      - (gtk4 >= 4.14 or libgtk-4-1 >= 4.14)
-      - (webkitgtk6.0 or libwebkitgtk-6_0-4)
+      - gtk4
+      - webkitgtk6.0
       - xdg-utils
 
   # Arch Linux packages

client/ui/frontend/src/lib/connection.ts

@@ -43,12 +43,7 @@ function buildSsoCancelPromise(state: SsoState, signal?: AbortSignal): Promise<v
 }
 
 async function runSsoLogin(
-    result: {
-        verificationUri: string;
-        verificationUriComplete: string;
-        userCode: string;
-        profileId: string;
-    },
+    result: { verificationUri: string; verificationUriComplete: string; userCode: string },
     state: SsoState,
     signal?: AbortSignal,
 ): Promise<void> {
@@ -61,7 +56,7 @@ async function runSsoLogin(
     // suspended, so a frontend-driven Up (a promise continuation) would not
     // fire until the user woke the window (e.g. hovering the tray icon).
     const waitPromise = Connection.WaitSSOLoginAndUp(
-        { userCode: result.userCode, hostname: "", profileId: result.profileId },
+        { userCode: result.userCode, hostname: "" },
         { profileName: "", username: "" },
     );
 

client/ui/main.go

@@ -14,6 +14,7 @@ import (
 	"github.com/sirupsen/logrus"
 	"github.com/wailsapp/wails/v3/pkg/application"
 	"github.com/wailsapp/wails/v3/pkg/events"
+	"github.com/wailsapp/wails/v3/pkg/services/notifications"
 
 	"github.com/netbirdio/netbird/client/ui/authsession"
 	"github.com/netbirdio/netbird/client/ui/i18n"
@@ -62,7 +63,7 @@ type registeredServices struct {
 	profiles        *services.Profiles
 	update          *services.Update
 	daemonFeed      *services.DaemonFeed
-	notifier        *Notifier
+	notifier        *notifications.NotificationService
 	compat          *services.Compat
 	profileSwitcher *services.ProfileSwitcher
 	bundle          *i18n.Bundle
@@ -101,7 +102,7 @@ func main() {
 	updaterHolder := updater.NewHolder(app.Event)
 	update := services.NewUpdate(conn, updaterHolder)
 	daemonFeed := services.NewDaemonFeed(conn, app.Event, updaterHolder, debugLog)
-	notifier := newNotifier()
+	notifier := notifications.New()
 	compat := services.NewCompat(conn)
 	// macOS shows no toast until permission is requested. Run it after
 	// ApplicationStarted so the notifier's Startup has initialised the
@@ -209,7 +210,7 @@ func main() {
 // requestNotificationAuthorization prompts for macOS notification permission.
 // The request blocks until the user responds (up to 3 minutes), so callers run
 // it in a goroutine. No-op on Linux/Windows.
-func requestNotificationAuthorization(notifier *Notifier) {
+func requestNotificationAuthorization(notifier *notifications.NotificationService) {
 	authorized, err := notifier.CheckNotificationAuthorization()
 	if err != nil {
 		logrus.Debugf("check notification authorization: %v", err)

client/ui/notifier.go

@@ -1,101 +0,0 @@
-//go:build !android && !ios && !freebsd && !js
-
-package main
-
-import (
-	"context"
-	"errors"
-	"sync/atomic"
-
-	log "github.com/sirupsen/logrus"
-	"github.com/wailsapp/wails/v3/pkg/application"
-	"github.com/wailsapp/wails/v3/pkg/services/notifications"
-)
-
-var errNotificationsUnavailable = errors.New("notifications unavailable")
-
-// Notifier wraps the Wails notification service so an unavailable backend
-// disables notifications instead of aborting the app. Startup fails for
-// environment reasons (a bare unbundled binary on macOS has no bundle
-// identifier, a headless Linux session has no D-Bus session bus), and Wails
-// treats a service startup error as fatal. After a failed startup every call
-// is a no-op: on macOS, touching UNUserNotificationCenter without a bundle
-// identifier raises an Objective-C exception that recover() cannot catch.
-type Notifier struct {
-	inner     *notifications.NotificationService
-	available atomic.Bool
-}
-
-func newNotifier() *Notifier {
-	return &Notifier{inner: notifications.New()}
-}
-
-// ServiceName implements the Wails service-name hook for startup logs.
-func (n *Notifier) ServiceName() string {
-	return n.inner.ServiceName()
-}
-
-// ServiceStartup starts the platform notifier, downgrading failure to a
-// warning so the app keeps running without notifications.
-func (n *Notifier) ServiceStartup(ctx context.Context, options application.ServiceOptions) error {
-	if err := n.inner.ServiceStartup(ctx, options); err != nil {
-		log.Warnf("notifications disabled: %v", err)
-		return nil
-	}
-	n.available.Store(true)
-	return nil
-}
-
-func (n *Notifier) ServiceShutdown() error {
-	if !n.available.Load() {
-		return nil
-	}
-	return n.inner.ServiceShutdown()
-}
-
-func (n *Notifier) CheckNotificationAuthorization() (bool, error) {
-	if !n.available.Load() {
-		return false, errNotificationsUnavailable
-	}
-	return n.inner.CheckNotificationAuthorization()
-}
-
-func (n *Notifier) RequestNotificationAuthorization() (bool, error) {
-	if !n.available.Load() {
-		return false, errNotificationsUnavailable
-	}
-	return n.inner.RequestNotificationAuthorization()
-}
-
-// SendNotification delivers a notification, silently dropping it when the
-// backend never started (notifications are best-effort everywhere).
-func (n *Notifier) SendNotification(options notifications.NotificationOptions) error {
-	if !n.available.Load() {
-		log.Debugf("notifications disabled, dropping %q", options.ID)
-		return nil
-	}
-	return n.inner.SendNotification(options)
-}
-
-func (n *Notifier) SendNotificationWithActions(options notifications.NotificationOptions) error {
-	if !n.available.Load() {
-		log.Debugf("notifications disabled, dropping %q", options.ID)
-		return nil
-	}
-	return n.inner.SendNotificationWithActions(options)
-}
-
-func (n *Notifier) RegisterNotificationCategory(category notifications.NotificationCategory) error {
-	if !n.available.Load() {
-		return nil
-	}
-	return n.inner.RegisterNotificationCategory(category)
-}
-
-// OnNotificationResponse registers the response callback. Pure Go state, so
-// it is safe (and simply inert) when the backend never started.
-//
-//wails:ignore
-func (n *Notifier) OnNotificationResponse(callback func(result notifications.NotificationResult)) {
-	n.inner.OnNotificationResponse(callback)
-}

client/ui/preferences/store.go

@@ -246,7 +246,6 @@ func (s *Store) ExistedAtLoad() bool {
 func (s *Store) load() error {
 	if _, err := os.Stat(s.path); err != nil {
 		if errors.Is(err, os.ErrNotExist) {
-			log.Infof("no ui preferences file at %s; using defaults", s.path)
 			return nil
 		}
 		return fmt.Errorf("stat preferences: %w", err)

client/ui/services/connection.go

@@ -33,21 +33,12 @@ type LoginResult struct {
 	UserCode                string `json:"userCode"`
 	VerificationURI         string `json:"verificationUri"`
 	VerificationURIComplete string `json:"verificationUriComplete"`
-	// ProfileID is the ID of the profile this login ran against, or "" when the
-	// caller named the profile itself and no ID was resolved. Pass it back in
-	// WaitSSOParams so the account email lands on this profile even if the
-	// active one changes during SSO.
-	ProfileID string `json:"profileId"`
 }
 
 // WaitSSOParams are the inputs to waitSSOLogin.
 type WaitSSOParams struct {
 	UserCode string `json:"userCode"`
 	Hostname string `json:"hostname"`
-	// ProfileID is the profile the login was started for, used to file the
-	// account email against it rather than against whichever profile is active
-	// when the flow returns. Optional: empty falls back to the active profile.
-	ProfileID string `json:"profileId"`
 }
 
 // UpParams selects the profile to bring up.
@@ -86,16 +77,11 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 	// Fall back to the daemon's active profile and the current OS user.
 	profileName := p.ProfileName
 	username := p.Username
-	// Only set when the daemon told us the ID. A caller-supplied ProfileName is
-	// a handle — a display name or an ID prefix resolve too — and the state file
-	// is named after the ID, so passing a handle on would name the wrong file.
-	profileID := ""
 	if profileName == "" {
 		if active, aerr := cli.GetActiveProfile(ctx, &proto.GetActiveProfileRequest{}); aerr == nil {
 			// Address the active profile by ID (the daemon resolves it as a
 			// handle); names can collide, the ID cannot.
 			profileName = active.GetId()
-			profileID = profileName
 			if username == "" {
 				username = active.GetUsername()
 			}
@@ -136,7 +122,6 @@ func (s *Connection) Login(ctx context.Context, p LoginParams) (LoginResult, err
 		UserCode:                resp.GetUserCode(),
 		VerificationURI:         resp.GetVerificationURI(),
 		VerificationURIComplete: resp.GetVerificationURIComplete(),
-		ProfileID:               profileID,
 	}, nil
 }
 
@@ -257,31 +242,6 @@ func (s *Connection) waitSSOLogin(ctx context.Context, p WaitSSOParams) (string,
 		return "", s.classifyDaemonError(err)
 	}
 	log.Infof("SSO login completed, daemon reported success")
-
-	// Persist the account email the same way the CLI does after its own
-	// WaitSSOLogin: the daemon returns it but cannot store it, since it runs as
-	// root and the per-profile state file is user-owned (see Logout below).
-	// Without this the profile has no email, so Profiles.List shows no account
-	// and later logins and session extends go out without a login_hint —
-	// leaving the IdP to guess which account was meant.
-	if email := resp.GetEmail(); email != "" {
-		state := &profilemanager.ProfileState{Email: email}
-		pm := profilemanager.NewProfileManager()
-
-		// Against the profile the login was started for: SSO spans seconds of
-		// user interaction, and a profile switch in that window would otherwise
-		// file the email under the wrong profile.
-		if p.ProfileID != "" {
-			err = pm.SetProfileState(profilemanager.ID(p.ProfileID), state)
-		} else {
-			err = pm.SetActiveProfileState(state)
-		}
-		if err != nil {
-			// Non-fatal: the login itself succeeded.
-			log.Warnf("failed to store account email: %v", err)
-		}
-	}
-
 	return resp.GetEmail(), nil
 }
 

client/ui/services/profile.go

@@ -6,8 +6,6 @@ import (
 	"context"
 	"os/user"
 
-	log "github.com/sirupsen/logrus"
-
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/proto"
 )
@@ -153,31 +151,11 @@ func (s *Profiles) Remove(ctx context.Context, p ProfileRef) error {
 	if err != nil {
 		return err
 	}
-	resp, err := cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
+	_, err = cli.RemoveProfile(ctx, &proto.RemoveProfileRequest{
 		ProfileName: p.ProfileName,
 		Username:    p.Username,
 	})
-	if err != nil {
-		return err
-	}
-
-	// The daemon deletes what it owns but runs as root, so it leaves the
-	// user-owned state file holding the account email behind (same split as
-	// Connection.Logout). Legacy profiles are keyed by name rather than by a
-	// generated ID, so a recreated profile of the same name would inherit the
-	// deleted one's email and offer it as the login_hint.
-	//
-	// Keyed on the ID the daemon resolved, not on the request handle: that may
-	// have been a display name or an ID prefix, which would name a different
-	// file (or none).
-	if id := resp.GetId(); id != "" {
-		if err := profilemanager.NewProfileManager().RemoveProfileState(id); err != nil {
-			// Non-fatal: the profile itself is gone.
-			log.Warnf("failed to remove profile state for %s: %v", id, err)
-		}
-	}
-
-	return nil
+	return err
 }
 
 // Rename changes a profile's display name. The on-disk ID is unaffected, so

client/ui/tray.go

@@ -44,7 +44,7 @@ type TrayServices struct {
 	Profiles        *services.Profiles
 	Networks        *services.Networks
 	DaemonFeed      *services.DaemonFeed
-	Notifier        *Notifier
+	Notifier        *notifications.NotificationService
 	Update          *services.Update
 	ProfileSwitcher *services.ProfileSwitcher
 	WindowManager   *services.WindowManager

client/ui/tray_notify.go

@@ -44,7 +44,7 @@ func safeSendNotification(send sendFn, what string, opts notifications.Notificat
 // notifyIfDaemonOutdated probes the daemon once and fires an OS toast when it
 // is reachable but too old for this UI. A probe error means the daemon isn't
 // reachable (not outdated), so it is left to the normal connection flow.
-func notifyIfDaemonOutdated(compat *services.Compat, notifier *Notifier, loc *Localizer) {
+func notifyIfDaemonOutdated(compat *services.Compat, notifier *notifications.NotificationService, loc *Localizer) {
 	ready, err := compat.DaemonReady(context.Background())
 	if err != nil {
 		log.Debugf("daemon compatibility probe: %v", err)

client/ui/tray_update.go

@@ -21,7 +21,7 @@ type trayUpdater struct {
 	app          *application.App
 	window       *application.WebviewWindow
 	update       *services.Update
-	notifier     *Notifier
+	notifier     *notifications.NotificationService
 	loc          *Localizer
 	onIconChange func()
 	// onMenuChange drives a full tray relayout: the update row lives in the
@@ -36,7 +36,7 @@ type trayUpdater struct {
 	progressWindowOpen bool
 }
 
-func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *Notifier, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
+func newTrayUpdater(app *application.App, window *application.WebviewWindow, update *services.Update, notifier *notifications.NotificationService, loc *Localizer, onIconChange func(), onMenuChange func()) *trayUpdater {
 	u := &trayUpdater{
 		app:          app,
 		window:       window,

combined/cmd/config.go

@@ -83,7 +83,6 @@ type ServerConfig struct {
 // AgentNetworkConfig contains agent-network (LLM gateway) configuration.
 type AgentNetworkConfig struct {
 	PricingDefaultsFile string `yaml:"pricingDefaultsFile"`
-	Zone                string `yaml:"zone"`
 }
 
 // TLSConfig contains TLS/HTTPS settings
@@ -733,7 +732,6 @@ func (c *CombinedConfig) ToManagementConfig() (*nbconfig.Config, error) {
 		PerAccountHighestSupportedSyncMessageVersion: c.Server.PerAccountSupportedSyncMessageVersions,
 		AgentNetwork: nbconfig.AgentNetwork{
 			PricingDefaultsFile: c.Server.AgentNetwork.PricingDefaultsFile,
-			Zone:                c.Server.AgentNetwork.Zone,
 		},
 	}, nil
 }

combined/config.yaml.example

@@ -147,11 +147,3 @@ server:
   #   # is re-read periodically (mtime poll). An explicitly configured path that
   #   # fails to load fails startup; runtime reload errors keep the previous table.
   #   pricingDefaultsFile: "pricing.yaml"
-  #
-  #   # Parent DNS zone that Agent Network gateway endpoints are allocated
-  #   # under, producing <subdomain>.<zone>. Empty (the default) preserves the
-  #   # legacy behaviour of deriving the endpoint from the serving cluster, so
-  #   # self-hosted deployments are unaffected. Captured onto each settings row
-  #   # when that row is created; changing it later does not move existing
-  #   # tenants.
-  #   zone: "gateway.example.com"

docs/agent-networks/01-end-to-end-flows.md

@@ -115,7 +115,7 @@ sequenceDiagram
         Resp->>Resp: parse usage tokens, completion
         Note over Resp: capture_completion gates raw<br/>completion capture
         Resp->>Cost: tokens
-        Cost->>Cost: lookup pricing.yaml + compute cost
+        Cost->>Cost: lookup rates from config-delivered<br/>pricing table + compute cost
         Cost->>Rec: tokens + cost
         Rec->>MgmtGrpc: RecordLLMUsage(provider, model, prompt_t, completion_t, cost, groups, user)
         Rec-->>Log: emit access-log entry<br/>(if EnableLogCollection)

docs/agent-networks/modules/21-management-agentnetwork.md

@@ -15,6 +15,10 @@ Inside the package: `manager.go` is the CRUD + permissions-gated facade; `synthe
 | ---- | ---- |
 | `agentnetwork/manager.go` | Manager interface + CRUD + permission gates + bootstrap-settings + reconcile trigger |
 | `agentnetwork/synthesizer.go` | Settings/policy → wire-format synthesis; sole writer of the proxy middleware chain |
+| `agentnetwork/synthesizer_pricing.go` | `buildCostMeterConfigJSON` — default table + per-provider prices → `cost_meter` config |
+| `agentnetwork/pricing/defaults.go` | Default pricing table derived from the catalog + supplementals; `DefaultTable`, `LookupDefault`, wire `Entry` |
+| `agentnetwork/pricing/override.go` | `LoadFile`/`StartReloader` for `AgentNetwork.PricingDefaultsFile` (mtime poll, merge over compiled-in base) |
+| `agentnetwork/pricing/{exampleyaml,gen}.go` | Generates `defaults_llm_pricing.example.yaml` from the compiled-in table (golden-tested) |
 | `agentnetwork/policyselect.go` | Per-request policy attribution + account-budget ceiling (min-wins) |
 | `agentnetwork/reconcile.go` | Per-account synth diff vs in-memory cache → Create/Update/Delete |
 | `agentnetwork/catalog/catalog.go` | Static provider catalogue (auth headers, identity-injection shapes) |
@@ -48,6 +52,8 @@ flowchart TD
     I --> J[indexProviderGroups: providerID -> sorted source groups]
     J --> K[buildRouterConfigJSON drops orphan providers]
     J --> L[buildIdentityInjectConfigJSON per catalog entry]
+    J --> K2[buildCostMeterConfigJSON: default table + per-provider prices]
+    K2 --> P
     H --> M[mergeGuardrails: union allowlist, OR redact]
     M --> N[applyAccountCollectionControls account toggle = SOLE capture control]
     N --> O[marshalGuardrailConfig]
@@ -60,6 +66,84 @@ flowchart TD
     R --> T[accountManager.UpdateAccountPeers — fans synth ACLs into network map]
 ```
 
+### LLM pricing (management is the sole authority)
+
+**The proxy carries no price list.** Management synthesizes the entire pricing
+table and ships it inside `cost_meter`'s `ConfigJSON`, so a price change reaches
+the proxies as an ordinary mapping push — the chain rebuild installs a fresh
+table and there is nothing to reload on the proxy side.
+
+```mermaid
+flowchart TD
+    A[catalog.All — PricingSurfaces x Models] --> B[buildDefaultTable + supplementalDefaults]
+    B --> C{AgentNetwork.PricingDefaultsFile}
+    C -- absent --> D[compiled-in table serves]
+    C -- loaded --> E[LoadFile: merge file entries WHOLE over compiled base]
+    E --> F[mergedTable atomic.Pointer]
+    D --> G[DefaultTable]
+    F --> G
+    G --> H[buildCostMeterConfigJSON — pricing.defaults]
+    I[types.Provider.Models operator prices] --> J[normalizePricingModelID<br/>bedrock ARN/region/version, vertex @version]
+    J --> K[materializeEntry: default entry as base,<br/>operator input/output verbatim,<br/>cache pointers only when non-nil]
+    K --> L[pricing.providers keyed by provider record ID]
+    H --> M[cost_meter ConfigJSON]
+    L --> M
+    G --> N[GET /catalog — applyDefaultPricing prefills dashboard rows]
+    O[StartReloader: mtime poll every ReloadInterval 1m] --> E
+```
+
+**Two tiers, resolved per request on the proxy** (`synthesizer_pricing.go:22-35`):
+
+- `pricing.defaults` — surface (`openai`/`anthropic`/`bedrock`) → normalized model
+  id → rates. The **full** default table ships to every account: it is small
+  (~10 KB) and it is what keeps gateway-style providers (which enumerate no
+  models, so they claim every model) priced.
+- `pricing.providers` — provider **record** id → normalized model id → rates,
+  matched against the `llm.resolved_provider_id` the router stamps. Entries are
+  **fully materialized here**, at synth time: `materializeEntry` starts from the
+  default entry for that model so cache rates the operator didn't state are
+  inherited, overlays operator `input`/`output` verbatim (**including an explicit
+  0**, which prices a self-hosted or internal endpoint as free rather than
+  silently reverting to list price), and overlays cache-rate **pointers only when
+  non-nil** — `nil` means "inherit the default", an explicit `0` means "no
+  discount, bill this bucket at the input rate". The proxy therefore does two map
+  lookups and no merging.
+
+Same orphan rule as the router: a provider no enabled policy authorises is
+unreachable, so its prices aren't shipped. Model ids are normalized with the
+**same** functions the request parser uses (`NormalizeBedrockModel` /
+`NormalizeVertexModel`), which is what makes the per-record lookup key compare
+equal to the `llm.model` the proxy meters. Post-normalization duplicates resolve
+first-occurrence-wins, matching the routing dedup order.
+
+**`AgentNetwork.PricingDefaultsFile`** (`config.go:190-207`) lets an operator
+replace default rates without a rebuild. Schema is `surface → model → rates`
+(`input_per_1k`, `output_per_1k`, and optional `cached_input_per_1k` /
+`cache_read_per_1k` / `cache_creation_per_1k`). Semantics:
+
+- A **relative** path resolves against `<Datadir>`, so a bare filename lands
+  alongside the store. Empty config probes `<Datadir>/defaults_llm_pricing.yaml`.
+- An **explicitly configured** path is *required to load*: a typo or malformed
+  file fails startup, because the operator believes those rates are live. The
+  conventional probe is optional — an absent file just serves compiled-in
+  defaults, and the path stays watched in case it appears later.
+- File entries **replace** the compiled-in entry for the same (surface, model)
+  **whole** — they are not field-merged, so an entry must repeat the cache rates
+  it wants to keep. Everything the file doesn't mention keeps built-in rates.
+- Unknown YAML fields are rejected (`KnownFields(true)`) and every rate must be
+  finite and non-negative — the same constraints the HTTP API enforces on
+  operator per-provider prices.
+- Reload is an mtime poll (`ReloadInterval`, 1 min) and is **lenient at runtime**:
+  a parse error keeps the previous table, a deleted file reverts to compiled-in
+  defaults. A mid-edit save can never take pricing down.
+
+The live table feeds **both** consumers, which is what keeps them consistent: the
+synthesizer (what proxies actually bill with) and `GET /api/agent-network/catalog`
+via `applyDefaultPricing` (what the dashboard's model-row prices prefill with).
+`defaults_llm_pricing.example.yaml` is generated from the compiled-in table
+(`go generate ./management/internals/modules/agentnetwork/pricing`) and
+golden-tested, so operators start from a file matching the built-in rates exactly.
+
 ### Budget rule resolution (min-wins, group+user bound)
 
 ```mermaid
@@ -124,7 +208,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
   | on_request | 3 | `llm_identity_inject` | `{"providers":[{provider_id, header_pair?, json_metadata?, extra_headers?}]}` | **true** |
   | on_request | 4 | `llm_guardrail` | `{"provider_allowlists"?: {providerID: []model}, "prompt_capture":{enabled,redact_pii}}` | – |
   | on_response | 5 | `llm_limit_record` | `{}` (runs LAST at runtime) | – |
-  | on_response | 6 | `cost_meter` | `{}` | – |
+  | on_response | 6 | `cost_meter` | `{"pricing":{"defaults":{surface:{model:rates}},"providers"?:{providerRecordID:{model:rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}` | – |
   | on_response | 7 | `llm_response_parser` | `{"capture_completion": <bool>, "redact_pii"?: true}` | – |
 - **Synthesized service shape** (`synthesizer.go:739`): `Mode=HTTP`, `Private=true`, `Domain=<subdomain>.<cluster>`, `AccessGroups=unionSourceGroups(enabledPolicies)`, one `TargetTypeCluster` target with `Host=noop.invalid:443` (router rewrites per request), `Options.{DirectUpstream,AgentNetwork}=true`, `DisableAccessLog=!settings.EnableLogCollection`, `CaptureMax{Req,Resp}Bytes=1<<20`, `CaptureContentTypes=["application/json","text/event-stream"]`.
 
@@ -139,6 +223,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
 - **Orphan providers (no enabled policy authorises them) NEVER reach the router** (`synthesizer.go:351-357`); skipped from `identity_inject` for symmetry.
 - **Provider creation refuses empty `api_key`** (`manager.go:175`); **deletion refuses while any policy still references it** (`manager.go:265-273`).
 - **Session keypair stability across provider edits** (`manager.go:226-228`) — server-managed, copied through every `UpdateProvider`, never API-surfaced.
+- **Management is the sole pricing authority.** The proxy has no embedded price list, so an account whose `cost_meter` config carries no `pricing` block bills **nothing** (`cost.skipped=unknown_model`, $0) rather than falling back to stale built-ins. The top-level `pricing` wrapper is also the feature-detection signal in both directions: an old proxy ignores it as an unknown field, and a new proxy reads its absence as "old management".
+- **Per-provider prices are materialized at synth time, not merged on the proxy** (`synthesizer_pricing.go:114-131`). A per-record entry is always complete, so the proxy's lookup is per-record-then-defaults with no field-level fallback between tiers.
+- **An explicit operator price of `0` prices the model as free** — it must not be treated as "unset" and reverted to list price (`synthesizer_pricing.go:49-54`). Only *cache*-rate fields distinguish unset from zero, via `*float64`.
+- **Pricing model ids are normalized with the same functions the request parser uses** (`normalizePricingModelID`). If the two ever diverge, per-record prices silently stop matching and every request falls through to surface defaults.
+- **The default table's coverage is structural, not curated.** It is derived from the catalog via each provider's `PricingSurfaces`; `TestDefaultTable_CoversEveryCatalogModel` fails on an unpriced catalog model and `TestDefaultTable_NoConflictingContributions` fails if two providers contribute the same (surface, model) at different rates.
+- **A pricing-defaults file failure is fatal only at startup, and only for an explicitly configured path.** Runtime reload failures keep the previous table; a deleted file reverts to compiled-in defaults (`pricing/override.go:62-81, 113-148`).
 
 ## Things to scrutinize
 
@@ -176,10 +266,12 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
 - **Capture-pointer semantics (restated):** non-agent-network callers see no field → legacy nil-default emit, identical to pre-PR. Agent-network targets always carry an explicit `capture_*` value.
 - **`TestSynthesizeServices_HappyPath` was updated:** request-parser config moved from `{}` to `{"capture_prompt":false}` (`synthesizer_test.go:174`). External snapshot tests against synth output need updating.
 - **`MergedGuardrails` retains zeroed `TokenLimits`/`Budget`/`Retention`** even though `Policy.Limits` carries the real values now; `llm_limit_check` is the authoritative enforcement. Comment at `synthesizer.go:940-948` calls this out.
+- **`cost_meter`'s `pricing` block is version-skew-safe in both directions.** A proxy predating config-delivered pricing ignores the field as unknown JSON (it previously priced from its own embedded table, so it keeps billing — at its own rates, which is the skew to be aware of during a rolling upgrade). A current proxy paired with old management sees no `pricing` block, logs one warning at chain-build time, and records `cost.skipped=unknown_model` — token counting and cap enforcement are unaffected, only the USD annotation goes to $0.
 
 ### Performance
 
 - **`SynthesizeServices` runs on every controller tick / mutation reconcile.** Cost: 4 store reads + optional per-provider keypair backfill. Sort + index + merge are O(N log N) / O(P × G); dominant cost is JSON marshalling. No nested loops escape these dimensions.
+- **The full default pricing table is marshalled into every account's `cost_meter` config on every synth** (~10 KB serialized). This is a deliberate trade: it keeps gateway-style providers priced for every catalog model, and it is the largest single contributor to the synth JSON. `DefaultTable()` itself is a pointer load (or a `sync.Once`-built map) — the cost is the marshal, not the build.
 - **`reconcile.diffMappings` is O(N + M)** with N=M=1 per account today — effectively constant.
 - **`SynthesizeServicesForCluster`** (`synthesizer.go:71`) walks every account on a cluster; per-account failures are **swallowed** (`synthesizer.go:91-93`) so a single misconfigured account doesn't drop the cluster. Runs per proxy reconnect.
 
@@ -188,6 +280,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
 - **Activity codes:** `AgentNetwork{Provider,Policy,Guardrail,BudgetRule}{Created,Updated,Deleted}`; `AgentNetworkSettingsUpdated` with `log_collection/prompt_collection/redact_pii` payload (`manager.go:567-571`). **No activity code for `SelectPolicyForRequest` denies** — surfaced via proxy access log only (likely intentional given volume).
 - **Deny codes** namespaced: `llm_policy.{token,budget}_cap_exceeded`, `llm_account.{token,budget}_cap_exceeded` (`policyselect.go:18-26`).
 - **Reconcile failures are logged at warn and swallowed** (`reconcile.go:42-44`). Persistent synth failures (e.g. unknown catalog id) silently keep the proxy out of sync — consider a manager-level synth-health surface if this becomes a support burden.
+- **Pricing-file lifecycle logs at info** (load, reload, revert-to-built-ins) and **at warn** for a runtime reload failure; the mtime check itself is `Debugf`. There is no metric on reload failures, so an operator who breaks the file mid-flight keeps billing at the previous table with only a log line to show it (`pricing/override.go:113-148`).
 
 ## Test coverage
 
@@ -198,6 +291,9 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
 | `synthesizer_guardrail_realstore_test.go` | `PromptCaptureAccountIsSoleControl`; `PromptCaptureFlowsWhenAccountOptsIn`; `AccountRedactWithoutGuardrailRedact`; `NoGuardrail_CaptureOff`. |
 | `synthesizer_log_collection_realstore_test.go` | `LogCollection{Off_SuppressesAccessLog,On_PermitsAccessLog}` — verifies `DisableAccessLog` propagation through `ToProtoMapping`. |
 | `synthesizer_parser_redact_realstore_test.go` | **Capture-pointer regression suite:** `ParserConfigsCarryRedactPii`; `ParserConfigsSuppressCaptureWhenLogCollectionOnly` (log=on/prompt=off ⇒ both capture flags false); `ParserConfigsOmitRedactPiiWhenOff`. |
+| `synthesizer_pricing_test.go` | `BuildCostMeterConfig_{BedrockModelNormalization,CacheRateNilVsZero,OrphanAndGatewayProviders}` — the per-record tier's three load-bearing rules: keys normalized like the parser's, `nil` cache pointer inherits vs explicit `0` bills at input rate, and orphan / gateway (empty `Models`) providers ship no per-record entry. |
+| `pricing/defaults_test.go` | `DefaultTable_{CoversEveryCatalogModel,NoConflictingContributions,AllRatesFiniteNonNegative,PinnedRates}`; `LookupDefault_SurfaceOrder`. Catalog-derived coverage + rate sanity are structural, not curated. |
+| `pricing/override_test.go` | `LoadFile_{MergesOverCompiledDefaults,MissingPath,RejectsInvalid}`; `Reload_LifeCycle` (mtime detect, parse error keeps previous, delete reverts to built-ins); `ExampleYAML_InSyncWithBuiltins` golden. |
 | `policyselect_test.go` | Mock-store: `NoApplicablePolicies`; `AllowWithLowestGroupAttribution`; `LargerPoolWinsAcrossUsageLevels`; `StaysOnLargerPoolAfterPartialDrain`; `FallsThroughToSmallerPoolWhenLargerExhausted`; `TiebreakBy{LargerGroupPool,CreatedAt}`; `DeniesWhenAllExhausted`; `UncappedPolicyAlwaysWinsAgainstCapped`; `DisabledPolicyIgnored`; `StoreErrorPropagates`; `RejectsEmptyAccount`; `SharesGroupCounterAcrossPolicies`; `AntiFallThroughOnLowestGroup`; `BudgetOnlyExhaustionDenies`; `BudgetTighterThanTokenWins`. |
 | `policyselect_realstore_test.go` | Real-sqlite regression guard: `NoApplicablePolicies`; `AllowAndLowestGroupAttribution`; `LargerPoolWins_FallsThroughWhenExhausted`; `BudgetCapDenies`; `GroupCounterSharedAcrossPolicies`; `DisabledPolicyIgnored`. |
 | `policyselect_account_realstore_test.go` | Account budget rules: `AccountCeilingBindsEvenWithUncappedPolicy` (min-wins); `AccountGroupCeiling`; `AccountTargetUsersBindsOnlyThatUser`; `AccountRuleRecordsToOwnWindow`. |

docs/agent-networks/modules/31-proxy-middleware-builtin.md

@@ -5,7 +5,7 @@ LLM request. The two highest-blast-radius areas are the **capture-pointer
 semantics** and the **limit_check ⇒ limit_record** record-once invariant.
 
 Sibling module: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — the SDK
-adapters + pricing catalog this chain delegates to.
+adapters + pricing table and cost formula this chain delegates to.
 
 ---
 
@@ -34,7 +34,7 @@ rewrites.
 | `llm_identity_inject` | OnRequest | `llm.{resolved_provider_id,authorising_groups}`, `Input.{UserEmail,UserID,UserGroups,UserGroupNames}` | none | header strip/inject + optional body rewrite |
 | `llm_guardrail` | OnRequest | `llm.{model,request_prompt_raw}` | `llm_policy.{decision,reason}`, `llm.request_prompt` | none (model allowlist deny) |
 | `llm_response_parser` | OnResponse | `llm.provider`, `Input.{RespHeaders,RespBody,Status}` | `llm.{input,output,total,cached_input,cache_creation}_tokens`, `llm.response_completion` | none |
-| `cost_meter` | OnResponse | `llm.{provider,model}`, token buckets | `cost.usd_total` or `cost.skipped` | pricing lookup |
+| `cost_meter` | OnResponse | `llm.{provider,model,resolved_provider_id}`, token buckets | `cost.usd_{input,cached_input,cache_creation,output,total,cache}` or `cost.skipped` | none (in-memory pricing lookup) |
 | `llm_limit_record` | OnResponse | `llm.{attribution_group_id,attribution_window_seconds,input_tokens,output_tokens}`, `cost.usd_total` | none | gRPC `RecordLLMUsage` |
 
 [all_test.go:26–40](../../../proxy/internal/middleware/builtin/all_test.go)
@@ -44,7 +44,7 @@ locks the ID set; adding or removing one is a conscious extension.
 
 | File | LOC | Notes |
 |---|---:|---|
-| `builtin.go` | 86 | Registry + `FactoryContext` (ctx, data dir, meter, logger, mgmt client) |
+| `builtin.go` | 90 | Registry + `FactoryContext` (ctx, meter, logger, mgmt client) |
 | `all_test.go` | 41 | Locks the 8-ID registry surface |
 | `agentnetwork_chain_integration_test.go` | 319 | Live sqlite + real gRPC bufconn; gate→recorder wire path |
 | `llm_request_parser/*` | 162 / 66 / 356 | Provider detection, body parse, prompt extraction with capture-pointer gating |
@@ -53,7 +53,7 @@ locks the ID set; adding or removing one is a conscious extension.
 | `llm_identity_inject/*` | 440 / 108 / 666 | HeaderPair (LiteLLM) + JSONMetadata (Portkey) + ExtraHeaders |
 | `llm_guardrail/*` | 176 / 82 / 75 / 219 / 217 | Model allowlist + optional prompt capture with PII redaction |
 | `llm_response_parser/*` | 258 / 222 / 43 / 433 / 169 / 111 | Buffered + SSE accumulation; AWS event-stream accumulator (`streaming_bedrock.go`) for Bedrock; capture-pointer gates completion emit |
-| `cost_meter/*` | 181 / 84 / 439 | Token → USD via `proxy/internal/llm/pricing` |
+| `cost_meter/*` | 236 / 98 / 586 | Token → USD via `proxy/internal/llm/pricing`; both pricing tiers arrive in the middleware config |
 | `llm_limit_record/*` | 144 / 35 / 191 | Post-flight `RecordLLMUsage` (5s, debug-on-error) |
 
 ## Per-middleware
@@ -168,12 +168,46 @@ token schema.
 
 ### cost_meter
 
-Reads `llm.provider` + `llm.model` + token buckets, looks up per-1k rate via
-`pricing.Loader`, emits `cost.usd_total` or a closed-set `cost.skipped`
-reason (`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`,
-`unknown_model`). Loader's hot-reload goroutine is bound to proxy-lifetime
-context via `startReloader`. **Key invariant:** provider-shape switch lives
-in `pricing.Table.Cost` (sibling doc) — `cost_meter` stays provider-agnostic.
+Reads `llm.provider` + `llm.model` + token buckets, looks up the per-1k rates,
+and emits the full `cost.usd_*` breakdown (four per-bucket values plus the
+`_total` and `_cache` aggregates) or a closed-set `cost.skipped` reason
+(`missing_provider/model/tokens`, `unparseable_tokens`, `zero_tokens`,
+`unknown_model`).
+
+**Management owns pricing.** The proxy carries no embedded price list: the whole
+table arrives in this middleware's `ConfigJSON` as
+`{pricing: {defaults, providers}}`, synthesized by management from the catalog
+plus the operator's stored per-provider prices
+([factory.go:13–34](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)).
+Both tiers are validated by `pricing.NewTable` / `pricing.NewEntries` at
+construction, so a non-finite or negative rate fails the chain build. A price
+change is an ordinary mapping push — the chain rebuild yields a fresh instance
+over a fresh immutable table, so there is no data dir, no pricing file, no
+reload goroutine, and nothing to invalidate.
+
+**Two-tier lookup**
+([middleware.go:165–183](../../../proxy/internal/middleware/builtin/cost_meter/middleware.go)):
+
+1. **Per-provider-record** — the operator's stored price for the route that
+   actually served the request, keyed by the `llm.resolved_provider_id` that
+   `llm_router` stamped on the allow path, then by normalized model id. Entries
+   arrive fully materialized (management folds default cache rates in at synth
+   time), so there is no merging here. Absent metadata — no router in the chain
+   — skips this tier.
+2. **Surface defaults** — the catalog-derived table keyed by `llm.provider`
+   (`openai`/`anthropic`/`bedrock`). This is also what prices gateway-style
+   providers, which enumerate no models and therefore get no per-record entry.
+
+**Backward compatibility:** a config with no `pricing` block means management
+predates config-delivered pricing. The factory logs one warning at build time
+and the instance records `cost.skipped=unknown_model` ($0) for every request
+rather than falling back to a stale built-in price list
+([factory.go:55–60](../../../proxy/internal/middleware/builtin/cost_meter/factory.go)).
+
+**Key invariant:** the provider-shape switch lives in `pricing.EntryCosts`
+(sibling doc) and is selected by the **surface**, not by which tier the entry
+came from — `cost_meter` stays provider-agnostic, and a per-record override on
+an Anthropic route still bills its cache buckets additively.
 
 ### llm_limit_record
 
@@ -246,12 +280,14 @@ no mocks. Tests: `TestChain_AllowPath_StampsAttributionAndRecordsCounter`
 | `llm_identity_inject` | `{providers: [{provider_id, header_pair?|json_metadata?, extra_headers?}]}` |
 | `llm_guardrail` | `{provider_allowlists: {providerID: []string}, prompt_capture: {enabled, redact_pii}}` — allowlist keyed by resolved provider id; a provider absent from the map is unrestricted (fail-closed backstop; authoritative per-policy/group check is management's `CheckLLMPolicyLimits`) |
 | `llm_response_parser` | `{redact_pii?, capture_completion?: *bool}` |
-| `cost_meter` | `{pricing_path?}` (basename inside data-dir; defaults `pricing.yaml`) |
+| `cost_meter` | `{pricing: {defaults: {surface: {model: rates}}, providers: {providerRecordID: {model: rates}}}}` — rates are `{input_per_1k, output_per_1k, cached_input_per_1k?, cache_read_per_1k?, cache_creation_per_1k?}`. A missing `pricing` key means "management predates config-delivered pricing": every request records `cost.skipped=unknown_model` |
 | `llm_limit_record` | `{}` — same pattern as `llm_limit_check` |
 
 All factories accept empty / null / `{}` / whitespace as zero-value config;
 only structurally invalid JSON is rejected so misconfig surfaces at chain
-build time.
+build time. `cost_meter` adds a semantic check on top of that: a `pricing`
+block carrying a negative or non-finite rate fails the build too, rather than
+mispricing live traffic.
 
 ## Invariants
 
@@ -320,10 +356,11 @@ non-object `metadata` field
 — header path still attributes, but body-level tag-budget enforcement
 doesn't run for that request.
 
-**Concurrency.** `cost_meter` shares a `pricing.Loader` via
-`atomic.Pointer[Table]`; readers always see a consistent table. Every
-middleware is a stateless value receiver. Integration test uses real bufconn
-gRPC — race detector is the meaningful bar.
+**Concurrency.** `cost_meter`'s two pricing tables are built once from the
+middleware config and never mutated, so the lookup path needs no lock or atomic
+swap — a price change replaces the whole instance. Every middleware is
+otherwise a stateless value receiver. Integration test uses real bufconn gRPC —
+race detector is the meaningful bar.
 
 **Perf.** Hot path is `lookupKV` linear scan over <10 KVs; `cost_meter.Cost`
 is O(1); SSE accumulation is single-pass. No map allocation per call.
@@ -349,13 +386,13 @@ counter accuracy.
 | `llm_guardrail/redact_test.go` | 15 | Email, SSN, phone (E.164 + NA), bearer, IPv4; fixture-driven |
 | `llm_response_parser/middleware_test.go` | 18 | Buffered OAI+Anthro, capture-pointer, redact, truncation |
 | `llm_response_parser/streaming_test.go` | 7 | OAI usage frame, Anthro message_delta, truncated body best-effort |
-| `cost_meter/middleware_test.go` | 17 | Each skip reason, provider-shape, pricing loader integration |
+| `cost_meter/middleware_test.go` | 22 | Each skip reason, provider-shape formulas, config-delivered defaults, per-record-beats-defaults + miss-falls-back, per-record uses surface formula, nil-pricing skips everything, invalid-rate rejection |
 | `llm_limit_record/middleware_test.go` | 7 | Skip-on-no-signal, skip-on-missing-attribution, RPC failure swallowed |
 
 ## Cross-references
 
 - Sibling: [32-proxy-llm-parsers.md](./32-proxy-llm-parsers.md) — SDK adapters
-  + SSE framer + pricing loader.
+  + SSE framer + pricing table and cost formula.
 - Path-routed providers (Vertex AI + Bedrock), `keyfile::` credential, GCP
   token minting, `/bedrock` prefix:
   [50-path-routed-providers.md](./50-path-routed-providers.md).

docs/agent-networks/modules/32-proxy-llm-parsers.md

@@ -9,7 +9,7 @@ pricing table's per-provider cost formula is the highest-leverage place a
 small bug would silently mis-bill operators.
 
 Sibling module: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md)
-— the 8 middlewares that consume this package's parsers + pricing loader.
+— the 8 middlewares that consume this package's parsers + pricing table.
 
 ---
 
@@ -24,8 +24,9 @@ proxy-framework dependencies:
 - `openai.go` / `anthropic.go` / `bedrock.go` — per-provider `Parser` impls.
 - `sse.go` — SSE scanner (`Scanner`, `Event`, `NewScanner`).
 - `errors.go` — sentinels callers branch on with `errors.Is`.
-- `pricing/` — embedded-default + hot-reload override table with
-  symlink-safe Unix loader (build-tagged stub elsewhere).
+- `pricing/` — immutable pricing table + the per-surface cost formula. The
+  rates themselves come from management inside `cost_meter`'s middleware
+  config; this package holds no price list and reads no files.
 - `fixtures/` — captured request/response/stream bodies the tests replay.
 
 The package carries zero proxy-framework dependencies so the same parsers can
@@ -47,12 +48,9 @@ be reused later by a WASM adapter
 | `sse_test.go` | 175 | 12 tests; fixture replay + multiline + size limits |
 | `parser_test.go` | 53 | `Parsers()`, `DetectParser`, provider enum values |
 | `errors.go` | 31 | 6 sentinels: `Err{Unknown,Unsupported}Provider/Model`, `Err{NotLLM,Malformed}Response`, `ErrStreamingUnsupported`, `ErrMalformedRequest` |
-| `pricing/pricing.go` | 421 | `Loader`, `Table`, `Entry`; embedded defaults + atomic swap + mtime reload |
-| `pricing/pricing_unix.go` | 69 | `O_NOFOLLOW` + fstat-from-FD + 1 MiB cap |
-| `pricing/pricing_other.go` | 21 | Stub returning "not supported on this platform" |
-| `pricing/pricing_test.go` | 432 | 21 tests — symlink rejection, reload race, path traversal, oversize |
-| `pricing/defaults_pricing.yaml` | 85 | go:embed source of truth |
-| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream + pricing starter |
+| `pricing/pricing.go` | 234 | `Table`, `Entry`, `EntryJSON`, `Costs`; `NewTable`/`NewEntries` validation + `EntryCosts` formula. No I/O, no reload, no embedded rates |
+| `pricing/pricing_test.go` | 177 | 10 tests — provider-shape formulas, cached clamp, rate fallback, nil-safety, rate validation |
+| `fixtures/*` | 21–59 | OAI chat/responses/stream + Anthro messages/stream |
 
 ## Request body → parser dispatch
 
@@ -188,9 +186,11 @@ response leg, covering both Bedrock body shapes:
   `totalTokens`). `firstNonZero` folds the two naming conventions into one
   `Usage`; when Converse omits `totalTokens` the parser sums the buckets.
 
-`ProviderName()` returns `"bedrock"` — its own `defaults_pricing.yaml` block,
-keyed by the **normalised** model id (region prefix + version suffix stripped by
-the request parser). `ParseResponse` returns `ErrStreamingUnsupported` for an
+`ProviderName()` returns `"bedrock"` — its own pricing surface in the table
+management ships, keyed by the **normalised** model id (region prefix + version
+suffix stripped by the request parser; management normalises its keys the same
+way at synth time so the two compare equal). `ParseResponse` returns
+`ErrStreamingUnsupported` for an
 AWS binary event-stream content-type (`application/vnd.amazon.eventstream`,
 `isAWSEventStream`) so the caller routes to the streaming accumulator instead.
 
@@ -205,11 +205,34 @@ response body. Streaming accumulators live in the middleware package
 ([llm_response_parser/streaming.go](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go))
 but use `llm.NewScanner` so the framing contract stays here.
 
-### Pricing catalog
+### Pricing table
 
-`Table.Cost`
-([pricing.go:129–174](../../../proxy/internal/llm/pricing/pricing.go))
-is the cost formula — most security-relevant math in this module:
+**Management is the sole pricing authority.** The proxy carries no embedded
+price list and reads no pricing file: the whole table arrives inside
+`cost_meter`'s `ConfigJSON` on the ordinary mapping push, and a price change
+is just another push — the chain rebuild constructs a fresh `Table`, so there
+is nothing to reload
+([pricing.go:1–7](../../../proxy/internal/llm/pricing/pricing.go)). The
+management side of the contract (catalog defaults, the operator's stored
+per-provider prices, and `AgentNetwork.PricingDefaultsFile`) is covered in the
+management-side module guide; `cost_meter`'s wire shape is in
+[31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md).
+
+`EntryJSON`
+([pricing.go:36–45](../../../proxy/internal/llm/pricing/pricing.go)) is the
+management→proxy contract — five USD-per-1k rates under `input_per_1k`,
+`output_per_1k`, `cached_input_per_1k`, `cache_read_per_1k`,
+`cache_creation_per_1k`. Management's `pricing.Entry` marshals the identical
+names, and `EntryJSON`/`Entry` are field-identical so `NewEntries` converts by
+direct struct conversion rather than field-by-field copying (a new rate can't
+be silently dropped in transit).
+
+`EntryCosts`
+([pricing.go:183–234](../../../proxy/internal/llm/pricing/pricing.go))
+is the cost formula — most security-relevant math in this module. The
+**surface** (the `llm.provider` value the request parser stamped) selects the
+formula, never the tier the entry came from: a per-provider-record override on
+an Anthropic route still bills its cache buckets additively.
 
 | Provider | Formula |
 |---|---|
@@ -218,7 +241,7 @@ is the cost formula — most security-relevant math in this module:
 | default | `inTokens × InputPer1K + outTokens × OutputPer1K` |
 
 `bedrock` shares the Anthropic additive-cache formula
-([pricing.go:172-174](../../../proxy/internal/llm/pricing/pricing.go)):
+([pricing.go:214–229](../../../proxy/internal/llm/pricing/pricing.go)):
 Anthropic-on-Bedrock reports the same additive cache buckets, while non-Anthropic
 Bedrock models (Nova, Llama) simply report zero in those buckets so cost reduces
 to `input + output`.
@@ -226,15 +249,12 @@ to `input + output`.
 Each per-bucket rate falls back to `InputPer1K` when zero — operators opt in
 to discounts by setting the field.
 
-`Loader`
-([pricing.go:212–268](../../../proxy/internal/llm/pricing/pricing.go))
-overlays an optional `pricing.yaml` from data-dir on top of the go:embed
-defaults. Atomic pointer swap means readers never observe a partial update.
-The mtime-poll reloader (30s default cadence) keeps the previous table on
-parse failure so cost annotation never goes blank during a botched edit.
-
-`defaults_pricing.yaml` is the source of truth for built-in pricing.
-Operator overrides only carry the entries they want to change.
+`Costs`
+([pricing.go:143–163](../../../proxy/internal/llm/pricing/pricing.go)) is the
+per-request split. The four per-bucket fields are the base; `TotalUSD` and
+`CacheUSD` are **derived** in `newCosts` so the aggregates can never drift from
+the breakdown. `InputUSD` is always the non-cached input bucket on both
+provider shapes, so input and cached-input never double-count.
 
 ## Public contracts
 
@@ -264,29 +284,38 @@ Order matters: `DetectFromURL` ties resolve by registration order.
 `ProviderBedrock = 3`. Numeric values are persisted in nothing today but treat
 them as wire-stable — new providers must take fresh numbers.
 
-**`Pricing` lookup**
-([pricing.go:129](../../../proxy/internal/llm/pricing/pricing.go)):
+**`Pricing` construction + lookup**
+([pricing.go:60–130](../../../proxy/internal/llm/pricing/pricing.go)):
 
 ```go
+func NewEntries(raw map[string]map[string]EntryJSON) (map[string]map[string]Entry, error)
+func NewTable(raw map[string]map[string]EntryJSON) (*Table, error)
+
+func (t *Table) Lookup(provider, model string) (Entry, bool)
 func (t *Table) Cost(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (float64, bool)
+func (t *Table) Costs(provider, model string, inTokens, outTokens, cachedInput, cacheCreation int64) (Costs, bool)
+func EntryCosts(entry Entry, surface string, inTokens, outTokens, cachedInput, cacheCreation int64) Costs
 ```
 
-Nil-safe: `t.Cost` on a nil receiver returns `(0, false)`
-([pricing.go:130–132](../../../proxy/internal/llm/pricing/pricing.go)).
-`ok=false` means provider or model is absent from the loaded table; the caller
-emits `cost.skipped=unknown_model`.
+`NewTable` is the surface-keyed defaults table; `NewEntries` returns the raw
+two-level map `cost_meter` uses for the per-provider-record tier (it looks up an
+`Entry` directly and calls `EntryCosts`, so it needs no `Table` wrapper). Both
+reject any non-finite or negative rate, so a corrupt config fails the chain
+build rather than mispricing silently. Nil input yields an empty,
+never-matching table.
+
+Nil-safe: `t.Cost`/`t.Lookup` on a nil receiver returns `ok=false`
+([pricing.go:96–99](../../../proxy/internal/llm/pricing/pricing.go)).
+`ok=false` means the surface or model is absent from the table management sent;
+the caller emits `cost.skipped=unknown_model`.
 
 ## Invariants
 
-1. **Cross-platform pricing build.** `pricing_unix.go` carries the only
-   functional `loadPricing` (uses `syscall.O_NOFOLLOW` and `f.Stat()` on an
-   open descriptor — both Unix-only). `pricing_other.go` is a build-tag
-   fallback that returns `"not supported on this platform"`
-   ([pricing_other.go:14–16](../../../proxy/internal/llm/pricing/pricing_other.go)).
-   The proxy is Linux-only in production today; a Windows port needs an
-   equivalent path-as-handle implementation. Reviewers building on Windows
-   should expect this surface to return an error at startup if an override
-   file is configured.
+1. **The pricing package is pure and platform-independent.** No file I/O, no
+   `//go:embed`, no goroutines, no build tags — the rates arrive as config, so
+   there is nothing platform-specific left to port. Anything reintroducing a
+   read-from-disk path here re-splits pricing authority between management and
+   the proxy, which is exactly what this design removed.
 
 2. **SSE scanner handles partial chunks.** A buffered prefix that doesn't end
    in `\n\n` still yields its accumulated event before `io.EOF`
@@ -298,38 +327,45 @@ emits `cost.skipped=unknown_model`.
    usage rather than aborting
    ([streaming.go:68–73, 144–150](../../../proxy/internal/middleware/builtin/llm_response_parser/streaming.go)).
 
-3. **`defaults_pricing.yaml` is the source of truth.** Compiled into the
-   binary via `//go:embed`
-   ([pricing.go:29–30](../../../proxy/internal/llm/pricing/pricing.go)).
-   `DefaultTable()` parses once and panics on parse failure
-   ([pricing.go:42–49](../../../proxy/internal/llm/pricing/pricing.go))
-   — by design: a broken embedded YAML must not ship to production.
+3. **Management is the only source of rates.** `Table` has no constructor that
+   invents prices: the only way in is `NewTable`/`NewEntries` over the wire map
+   management sent. A missing or empty `pricing` block therefore means *no
+   prices at all* (`cost_meter` records `cost.skipped=unknown_model`, $0) —
+   never a stale built-in fallback that would silently bill list price.
 
-4. **Loader path validation.** `resolveMiddlewareDataPath`
-   ([pricing.go:370–394](../../../proxy/internal/llm/pricing/pricing.go))
-   rejects absolute paths, traversal segments, and basenames that fail
-   `basenameRegex = ^[a-zA-Z0-9._-]+$`. The resolved path must remain
-   inside `baseDir` even after `filepath.Clean`. Tests:
-   `TestNewLoader_PathValidation`, `TestNewLoader_PathValidation_Extended`,
-   `TestNewLoader_SymlinkOutsideBaseDirRejected`, `TestNewLoader_SymlinkRejected`.
+4. **Tables are immutable once built.** `Table.entries` is written only in
+   `NewEntries` and never mutated afterwards, and `cost_meter`'s `perRecord`
+   map is likewise build-time-only
+   ([pricing.go:47–52](../../../proxy/internal/llm/pricing/pricing.go)). This
+   is what makes the no-reload design safe: a price change arrives as a mapping
+   push that builds a new middleware instance over a new table, so concurrent
+   readers can't observe a half-updated price list and no atomic swap or lock
+   is needed on the hot path.
 
-5. **Unix loader symlink safety.** `O_NOFOLLOW` on open, `f.Stat()` on the
-   open descriptor (never re-stat by path), `info.Mode().IsRegular()` check,
-   `io.LimitReader(f, maxPricingBytes+1)` with a final size assertion
-   ([pricing_unix.go:25–57](../../../proxy/internal/llm/pricing/pricing_unix.go)).
-   A mid-read symlink swap is detected because the fstat is on the original
-   fd. Test: `TestNewLoader_RejectsOversizedFile_FixesM4`.
+5. **Rate validation happens at chain-build time, not per request.**
+   `NewEntries` rejects negative, NaN, and ±Inf rates field by field
+   ([pricing.go:60–83](../../../proxy/internal/llm/pricing/pricing.go)), naming
+   the offending surface/model/field in the error. Management enforces the same
+   constraints at its API boundary and in its YAML parser, so this is
+   defense-in-depth — but it means a corrupt push fails loudly at build instead
+   of producing negative costs on live traffic. Test:
+   `TestNewTable_ValidatesRates`.
 
-6. **`yaml.NewDecoder(...).KnownFields(true)`**
-   ([pricing.go:397–398](../../../proxy/internal/llm/pricing/pricing.go))
-   rejects YAML files that carry fields not in the schema. A typo in an
-   operator override file fails loud instead of silently zeroing rates.
+6. **New rates must be added to `Entry`, `EntryJSON`, *and* management's
+   `pricing.Entry` together.** `NewEntries` converts by direct struct
+   conversion `Entry(e)`
+   ([pricing.go:76–78](../../../proxy/internal/llm/pricing/pricing.go)), which
+   only compiles while the two structs stay field-identical — so the proxy half
+   is compiler-enforced. The management half is not: a rate added there but not
+   here unmarshals into nothing and prices that bucket at `InputPer1K`.
 
 ## Things to scrutinise
 
-**Correctness.** Verify OpenAI cached-prompt clamp at
-[pricing.go:147–149](../../../proxy/internal/llm/pricing/pricing.go)
-short-circuits before subtraction. `Anthropic.TotalTokens` sums all four
+**Correctness.** Verify the OpenAI cached-prompt clamp at
+[pricing.go:203–206](../../../proxy/internal/llm/pricing/pricing.go)
+short-circuits before subtraction. Negative token counts are clamped to zero up
+front ([pricing.go:186–197](../../../proxy/internal/llm/pricing/pricing.go)) so
+no formula can yield a negative cost. `Anthropic.TotalTokens` sums all four
 buckets (in + out + cache_read + cache_creation) — downstream dashboards
 need to know this differs from `input + output`.
 `OpenAIParser.ExtractPrompt` falls through `messages → input → prompt`; a
@@ -338,22 +374,27 @@ noting).
 
 **Security.** `Scanner.maxLine = 1 MiB`; a 2 MiB single-line `data:` event
 errors from `Scanner.Next` and both accumulators stop with partial usage.
-Pricing file 1 MiB cap is orders of magnitude larger than realistic. Confirm
-new schema additions are mirrored in both `pricingFile` and `Entry`;
-`KnownFields(true)` will reject silently-typo'd operator overrides
-otherwise.
+Pricing is no longer file-backed, so the loader's path-traversal / symlink /
+oversize surface is gone entirely — the config channel (an authenticated
+mapping push from management) is now the only way rates enter the proxy, and
+`NewEntries` is the validation boundary on it. A new rate added to management's
+`pricing.Entry` but not to `EntryJSON` here is the remaining silent-mispricing
+path (see invariant 6).
 
-**Concurrency.** `Loader.table` is `atomic.Pointer[Table]`; readers never
-block or see a torn table. `Loader.Reload` is one goroutine, cancelled via
-context (`TestLoader_ReloadBackgroundLoopCancellation`). `DefaultTable()`
-uses `sync.Once`. Per-call `Scanner` instances mean no shared state across
-concurrent response-parser calls.
+**Concurrency.** Nothing in this package is shared mutable state: tables are
+built once and never written again, so `cost_meter`'s hot path is lock-free by
+construction rather than by atomic swap. Per-call `Scanner` instances mean no
+shared state across concurrent response-parser calls.
 
-**Perf.** `Table.Cost` is two map lookups + multiplications, O(1).
-`Scanner.Next` is one `ReadString('\n')` per line. Pricing reload poll 30s.
+**Perf.** `Table.Cost` is two map lookups + multiplications, O(1); the
+per-provider-record tier adds at most one more lookup. `Scanner.Next` is one
+`ReadString('\n')` per line. No background goroutines and no per-request
+allocation of pricing state.
 
-**Observability.** Reload failures count via `metric.Int64Counter` keyed
-`plugin`; warning log rate-limited at 5 min so a broken file doesn't flood.
+**Observability.** A config carrying no `pricing` block logs one warning at
+chain-build time (`cost_meter` factory) and then records
+`cost.skipped=unknown_model` per request, so an old-management deployment is
+visible in both logs and the access log rather than quietly reporting $0.
 Parser errors return sentinels — middleware uses `errors.Is` to map to the
 right `cost.skipped` reason.
 
@@ -365,7 +406,7 @@ right `cost.skipped` reason.
 | `openai_test.go` | 11 | Chat Completions + Responses API + legacy `prompt`; cached-tokens subset for both naming conventions; fixture replays |
 | `anthropic_test.go` | 7 | Messages + legacy `/v1/complete`; streaming REJECTED on `ParseResponse` (must use scanner); fixture replays |
 | `sse_test.go` | 12 | Fixture replay both providers; multiline `data:`; CRLF; comment skip; trailing-event-without-blank-line; oversize rejection |
-| `pricing/pricing_test.go` | 21 | Provider-shape switch; cached-rate fallback; cached-clamp; symlink rejection (target outside basedir + symlink to file); path validation matrix; oversize rejection; reload-keeps-previous-on-parse-error; mtime change detection; goroutine cancellation |
+| `pricing/pricing_test.go` | 10 | Provider-shape switch (surface selects the formula); cached-rate + cache-read/creation fallback to `InputPer1K`; cached-clamp; negative-token clamp; nil-receiver safety; rate validation (negative / NaN / Inf rejected); nil + empty table |
 
 **Fixtures** ([proxy/internal/llm/fixtures/](../../../proxy/internal/llm/fixtures/)):
 `openai_chat_completion.json` (chat.completions with usage),
@@ -373,14 +414,15 @@ right `cost.skipped` reason.
 `openai_stream.txt` (3 deltas + usage + `[DONE]`),
 `anthropic_messages.json` (Messages API non-streaming),
 `anthropic_stream.txt` (full 7-event sequence: message_start →
-content_block_{start,delta×2,stop} → message_delta (usage) → message_stop),
-`pricing.yaml` (realistic-pricing starter for operator overrides).
+content_block_{start,delta×2,stop} → message_delta (usage) → message_stop).
+No pricing fixture: the table is config-delivered, so pricing tests construct
+it in-process from a wire-shape map.
 
 ## Cross-references
 
 - Sibling: [31-proxy-middleware-builtin.md](./31-proxy-middleware-builtin.md)
   — the chain that calls `llm.Parsers()`, `llm.ParserByName`,
-  `llm.NewScanner`, `pricing.NewLoader`.
+  `llm.NewScanner`, `pricing.NewTable` / `pricing.NewEntries`.
 - Path-routed providers (Vertex AI + Bedrock), credential syntax, and the
   Bedrock AWS event-stream accumulator:
   [50-path-routed-providers.md](./50-path-routed-providers.md).

docs/agent-networks/modules/33-proxy-runtime.md

@@ -1,7 +1,7 @@
 # proxy/runtime — translate + serve + log
 
 > **Risk level:** High — every config push from management is translated here, and the chain runs on every HTTP request to a synth target.
-> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareDataDir`, `MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path.
+> **Backward-compat impact:** Additive at the wire (`PathTargetOptions.middlewares`, `agent_network`, `disable_access_log`, capture caps) and on the proxy `Server` struct (`MiddlewareCaptureBudgetBytes`). Non-agent-network targets stay on the no-middleware fast path. Middleware config is entirely wire-delivered — no proxy-side data dir is involved, including for LLM pricing, which management ships inside `cost_meter`'s config.
 
 ## Module boundary
 
@@ -114,8 +114,7 @@ At **request time** the access-log middleware stamps `CapturedData`; the auth ch
 
 ## Public contracts touched
 
-- `proxy.Server.MiddlewareDataDir` (string) — base dir for file-backed middleware config (server.go:238-241).
-- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:248-250).
+- `proxy.Server.MiddlewareCaptureBudgetBytes` (int64) — process-wide capture cap; defaults to 256 MiB (server.go:249-253). There is no `MiddlewareDataDir`: no built-in middleware reads config from disk, so `builtin.FactoryContext` carries only the proxy-lifetime context, meter, logger, and management client.
 - `proxy/internal/proxy.WithMiddlewareManager(*middleware.Manager) Option` — new option on `NewReverseProxy`; nil keeps the fast path (reverseproxy.go:48-56).
 - `proxy/internal/proxy.PathTarget` adds `Middlewares`, `CaptureConfig`, `AgentNetwork`, `DisableAccessLog` (servicemapping.go:27-51), all zero-default.
 - `proxy/internal/proxy.CapturedData` adds `agentNetwork`, `suppressAccessLog`, `userGroupNames` behind `sync.RWMutex`; slices deep-copied (context.go:47-66, 183-258).

docs/agent-networks/modules/50-path-routed-providers.md

@@ -87,9 +87,9 @@ strips the `@version` suffix from the model, and maps the publisher to a parser
 surface via `vertexPublisherVendor`:
 
 - `anthropic` → `llm.provider="anthropic"` → metered through the Anthropic
-  parser, priced under the **`anthropic`** block in `defaults_pricing.yaml`
-  (the parser emits the standard Anthropic provider label, so Vertex Claude
-  reuses first-party Anthropic prices).
+  parser, priced under the **`anthropic`** surface of the pricing table
+  management ships (the parser emits the standard Anthropic provider label, so
+  Vertex Claude reuses first-party Anthropic prices).
 - `openai` → `llm.provider="openai"` (reserved; not in the catalog lineup
   today).
 - anything else (notably `google` / Gemini) → empty vendor → **no parser**.
@@ -104,8 +104,9 @@ is omitted from the catalog.
 
 > Caveat: cross-region inference profiles in `eu` / `apac` carry a ~10% price
 > premium that the base per-token rates do **not** model — cost annotations for
-> those regions read low. Operators who need exact regional billing override
-> the affected entries in `pricing.yaml`.
+> those regions read low. Operators who need exact regional billing set the
+> affected models' prices on the provider record, or replace the default entries
+> via management's `AgentNetwork.PricingDefaultsFile`.
 
 ## AWS Bedrock (`bedrock_api`)
 
@@ -211,15 +212,19 @@ so a model-listing call can't be rewritten onto an upstream that would 404 it.
 ## Catalog ↔ pricing cross-check
 
 Catalog prices and context windows are cross-checked against LiteLLM's
-`model_prices_and_context_window.json`. The proxy's embedded
-`defaults_pricing.yaml` covers **every metered first-party model** the catalog
-enumerates — guarded by
-`TestDefaultTable_FirstPartyModelCoverage`
-([pricing/defaults_coverage_test.go](../../../proxy/internal/llm/pricing/defaults_coverage_test.go)),
-which fails if a catalog model has no embedded price. Bedrock entries are keyed
-by the **normalised** id the request parser emits (region prefix + version
-suffix stripped). Vertex Claude carries no Bedrock-style prefix, so it prices
-straight off the `anthropic` block.
+`model_prices_and_context_window.json`. The **catalog is the source of default
+prices**: management's `pricing.DefaultTable` folds every catalog provider's
+models into the surfaces that provider declares (`PricingSurfaces`), so coverage
+is structural rather than maintained in a parallel file
+([pricing/defaults.go](../../../management/internals/modules/agentnetwork/pricing/defaults.go)).
+`TestDefaultTable_CoversEveryCatalogModel` fails if a catalog model ends up
+unpriced, and `TestDefaultTable_NoConflictingContributions` fails if two
+providers contribute the same (surface, model) at different rates. Bedrock
+entries are keyed by the **normalised** id the request parser emits (region
+prefix + version suffix stripped) — management applies the same normalisation to
+per-provider prices at synth time, so the two keys compare equal. Vertex Claude
+carries no Bedrock-style prefix, so it prices straight off the `anthropic`
+surface.
 
 ## Things to scrutinise
 
@@ -232,16 +237,17 @@ operator-misconfigured Vertex provider and unmetered Gemini traffic; verify
 publishers).
 
 **Correctness.** `normalizeBedrockModel` is the join between the wire id and the
-pricing key — a model that normalises to something not in `defaults_pricing.yaml`
-meters at `cost.skipped=unknown_model` rather than failing the request. The
+pricing key — a model that normalises to something absent from the shipped
+pricing table meters at `cost.skipped=unknown_model` rather than failing the
+request. The
 `/bedrock` prefix strip must run on both the parser side (so the model is
 extracted) and the router side (so the upstream path is native); a regression in
 either silently breaks the other.
 
 **Metering caveats.** eu/apac cross-region Bedrock + Vertex profiles carry a
-~10% premium not modelled by base pricing — flagged in both the catalog comment
-and `defaults_pricing.yaml`. Operators needing exact regional billing override
-the relevant entries.
+~10% premium not modelled by base pricing — flagged in the catalog comment.
+Operators needing exact regional billing set per-provider prices on the model
+rows (or replace the default entries via `AgentNetwork.PricingDefaultsFile`).
 
 ## Cross-references
 

funding.json

@@ -6,7 +6,7 @@
     "name": "NetBird GmbH",
     "email": "hello@netbird.io",
     "phone": "",
-    "description": "NetBird GmbH is a Berlin-based software company specializing in the development of open-source network security solutions. Network security is utterly complex and expensive, accessible only to companies with multi-million dollar IT budgets. In contrast, there are millions of companies left behind. Our mission is to create an advanced network and cybersecurity platform that is both easy-to-use and affordable for teams of all sizes and budgets. By leveraging the open-source strategy and technological advancements, NetBird aims to set the industry standard for connecting and securing IT infrastructure.",
+    "description": "NetBird GmbH is a Berlin-based software company specializing in the development of open source network security solutions. Network security is utterly complex and expensive, accessible only to companies with multi-million dollar IT budgets. In contrast, there are millions of companies left behind. Our mission is to create an advanced network and cybersecurity platform that is both easy-to-use and affordable for teams of all sizes and budgets. By leveraging the open source strategy and technological advancements, NetBird aims to set the industry standard for connecting and securing IT infrastructure.",
     "webpageUrl": {
       "url": "https://github.com/netbirdio"
     }
@@ -15,7 +15,7 @@
     {
       "guid": "netbird",
       "name": "NetBird",
-      "description": "NetBird is a configuration-free peer-to-peer private network and a centralized access control system combined in a single open-source platform. It makes it easy to create secure WireGuard-based private networks for your organization or home.",
+      "description": "NetBird is a configuration-free peer-to-peer private network and a centralized access control system combined in a single open source platform. It makes it easy to create secure WireGuard-based private networks for your organization or home.",
       "webpageUrl": {
         "url": "https://github.com/netbirdio/netbird"
       },
@@ -59,7 +59,7 @@
         "guid": "support-yearly",
         "status": "active",
         "name": "Support Open Source Development and Maintenance - Yearly",
-        "description": "This will help us partially cover the yearly cost of maintaining the open-source NetBird project.",
+        "description": "This will help us partially cover the yearly cost of maintaining the open source NetBird project.",
         "amount": 100000,
         "currency": "USD",
         "frequency": "yearly",
@@ -72,7 +72,7 @@
         "guid": "support-one-time-year",
         "status": "active",
         "name": "Support Open Source Development and Maintenance - One Year",
-        "description": "This will help us partially cover the yearly cost of maintaining the open-source NetBird project.",
+        "description": "This will help us partially cover the yearly cost of maintaining the open source NetBird project.",
         "amount": 100000,
         "currency": "USD",
         "frequency": "one-time",
@@ -85,7 +85,7 @@
         "guid": "support-one-time-monthly",
         "status": "active",
         "name": "Support Open Source Development and Maintenance - Monthly",
-        "description": "This will help us partially cover the monthly cost of maintaining the open-source NetBird project.",
+        "description": "This will help us partially cover the monthly cost of maintaining the open source NetBird project.",
         "amount": 10000,
         "currency": "USD",
         "frequency": "monthly",
@@ -98,7 +98,7 @@
         "guid": "support-monthly",
         "status": "active",
         "name": "Support Open Source Development and Maintenance - One Month",
-        "description": "This will help us partially cover the monthly cost of maintaining the open-source NetBird project.",
+        "description": "This will help us partially cover the monthly cost of maintaining the open source NetBird project.",
         "amount": 10000,
         "currency": "USD",
         "frequency": "monthly",

infrastructure_files/management.json.tmpl

@@ -39,9 +39,6 @@
         ]
     },
     "DisableDefaultPolicy": $NETBIRD_MGMT_DISABLE_DEFAULT_POLICY,
-    "AgentNetwork": {
-        "Zone": "$NETBIRD_AGENT_NETWORK_ZONE"
-    },
     "Datadir": "",
     "DataStoreEncryptionKey": "$NETBIRD_DATASTORE_ENC_KEY",
     "StoreConfig": {

management/internals/modules/agentnetwork/allocate_test.go

@@ -1,296 +0,0 @@
-package agentnetwork
-
-import (
-	"context"
-	"errors"
-	"fmt"
-	"math/rand"
-	"runtime"
-	"testing"
-
-	"github.com/golang/mock/gomock"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/labelgen"
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-	"github.com/netbirdio/netbird/management/server/store"
-	nbtypes "github.com/netbirdio/netbird/management/server/types"
-	"github.com/netbirdio/netbird/shared/management/status"
-)
-
-// TestIsUniqueConstraintError_RecognisesAllThreeDialects — the allocator's
-// retry loop hinges on this. A missed dialect turns a retryable collision into
-// a hard provider-create failure.
-func TestIsUniqueConstraintError_RecognisesAllThreeDialects(t *testing.T) {
-	for name, err := range map[string]error{
-		"postgres": errors.New(`ERROR: duplicate key value violates unique constraint (SQLSTATE 23505)`),
-		"mysql":    errors.New(`Error 1062 (23000): Duplicate entry 'brave-otter'`),
-		"sqlite":   errors.New(`UNIQUE constraint failed: agent_network_settings.subdomain`),
-	} {
-		assert.True(t, isUniqueConstraintError(err), "%s violation must be recognised", name)
-	}
-
-	assert.False(t, isUniqueConstraintError(errors.New("connection refused")),
-		"unrelated errors must not be treated as retryable collisions")
-}
-
-// newAllocatorTestStore wires a real sqlite store, mirroring the pattern in
-// provider_bootstrap_test.go's bootstrapFixture. The allocator tests exercise
-// bootstrapSettingsIfNeeded directly against a managerImpl built in-package,
-// so no permissions manager or account manager is needed.
-func newAllocatorTestStore(t *testing.T) store.Store {
-	t.Helper()
-	if runtime.GOOS == "windows" {
-		t.Skip("sqlite store not properly supported on Windows yet")
-	}
-	t.Setenv("NETBIRD_STORE_ENGINE", string(nbtypes.SqliteStoreEngine))
-
-	st, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
-	require.NoError(t, err, "test store setup must succeed")
-	t.Cleanup(cleanUp)
-	return st
-}
-
-// TestBootstrapSettings_StampsZoneAndTupleLabel — new rows must carry the
-// configured zone and a tuple label, which together give the tenant a
-// placement-independent address.
-func TestBootstrapSettings_StampsZoneAndTupleLabel(t *testing.T) {
-	ctx := context.Background()
-	st := newAllocatorTestStore(t)
-
-	m := &managerImpl{
-		store:    st,
-		zone:     "gateway.example",
-		labelRng: rand.New(rand.NewSource(1)),
-	}
-
-	settings, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.NoError(t, err, "bootstrap must succeed")
-	require.NotNil(t, settings)
-
-	assert.Equal(t, "gateway.example", settings.Zone, "new row must carry the configured zone")
-	assert.Equal(t, "cluster1.example.com", settings.Cluster)
-	assert.Contains(t, settings.Subdomain, "-", "subdomain must be an adjective-noun tuple label")
-	assert.Equal(t, "account1", settings.AccountID)
-	assert.Equal(t, settings.Subdomain+".gateway.example", settings.Endpoint(),
-		"endpoint must be placement-independent, hanging off the zone rather than the cluster")
-
-	persisted, err := st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-	require.NoError(t, err)
-	assert.Equal(t, settings.Subdomain, persisted.Subdomain, "returned settings must match the persisted row")
-	assert.Equal(t, "gateway.example", persisted.Zone)
-}
-
-// TestBootstrapSettings_RetriesOnCollision forces a duplicate by pre-inserting
-// a row whose subdomain matches the next label the seeded rng will draw, then
-// asserts allocation still succeeds with a different label and that no error
-// escapes.
-func TestBootstrapSettings_RetriesOnCollision(t *testing.T) {
-	ctx := context.Background()
-	st := newAllocatorTestStore(t)
-
-	const seed = 7
-
-	// Precompute the label a freshly seeded rng will draw first, without
-	// disturbing the rng the manager will actually use.
-	predictor := rand.New(rand.NewSource(seed))
-	firstDraw := labelgen.PickTuple(predictor)
-	require.NotEmpty(t, firstDraw, "test precondition: label pools must be non-empty")
-
-	// Pre-insert a colliding row on a different account so the allocator's
-	// first attempt hits the unique index and must retry.
-	require.NoError(t, st.CreateAgentNetworkSettings(ctx, &types.Settings{
-		AccountID: "other-account",
-		Cluster:   "cluster1.example.com",
-		Subdomain: firstDraw,
-	}), "seeding the colliding row must succeed")
-
-	m := &managerImpl{
-		store:    st,
-		labelRng: rand.New(rand.NewSource(seed)),
-	}
-
-	settings, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.NoError(t, err, "allocation must succeed after retrying past the collision")
-	require.NotNil(t, settings)
-	assert.NotEqual(t, firstDraw, settings.Subdomain,
-		"the retried allocation must not reuse the already-taken label")
-}
-
-// TestBootstrapSettings_IsIdempotent — calling twice for one account returns
-// the existing row unchanged (the early-return path), and does NOT
-// re-allocate.
-func TestBootstrapSettings_IsIdempotent(t *testing.T) {
-	ctx := context.Background()
-	st := newAllocatorTestStore(t)
-
-	m := &managerImpl{
-		store:    st,
-		labelRng: rand.New(rand.NewSource(3)),
-	}
-
-	first, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.NoError(t, err)
-	require.NotNil(t, first)
-
-	second, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster2.example.com")
-	require.NoError(t, err, "second call must not error")
-	require.NotNil(t, second)
-
-	assert.Equal(t, first.Subdomain, second.Subdomain, "second call must return the existing subdomain unchanged")
-	assert.Equal(t, first.Cluster, second.Cluster, "second call must not repin the cluster to the new hint")
-
-	all, err := st.GetAllAgentNetworkSettings(ctx, store.LockingStrengthNone)
-	require.NoError(t, err)
-	var forAccount int
-	for _, s := range all {
-		if s.AccountID == "account1" {
-			forAccount++
-		}
-	}
-	assert.Equal(t, 1, forAccount, "exactly one row must exist for the account; no re-allocation")
-}
-
-// TestBootstrapSettings_FailsAfterExhaustingAttempts — the retry loop's
-// failure mode. maxSubdomainAllocationAttempts consecutive collisions must
-// surface an error rather than inserting a duplicate, silently succeeding, or
-// looping forever.
-//
-// Seed 11 was checked to produce maxSubdomainAllocationAttempts distinct
-// labels from labelgen.PickTuple; a seed that repeated a label would leave
-// fewer than maxAttempts rows pre-inserted and the allocator would succeed on
-// the repeat instead of exhausting.
-func TestBootstrapSettings_FailsAfterExhaustingAttempts(t *testing.T) {
-	ctx := context.Background()
-	st := newAllocatorTestStore(t)
-
-	const seed = 11
-	predictor := rand.New(rand.NewSource(seed))
-	seen := make(map[string]struct{}, maxSubdomainAllocationAttempts)
-	for i := 0; i < maxSubdomainAllocationAttempts; i++ {
-		label := labelgen.PickTuple(predictor)
-		_, dup := seen[label]
-		require.False(t, dup, "test precondition: seed %d must draw %d distinct labels, got a repeat %q at draw %d", seed, maxSubdomainAllocationAttempts, label, i)
-		seen[label] = struct{}{}
-
-		require.NoError(t, st.CreateAgentNetworkSettings(ctx, &types.Settings{
-			AccountID: fmt.Sprintf("squatter-%d", i),
-			Cluster:   "cluster1.example.com",
-			Subdomain: label,
-		}), "seeding colliding row %d must succeed", i)
-	}
-
-	m := &managerImpl{
-		store:    st,
-		labelRng: rand.New(rand.NewSource(seed)),
-	}
-
-	settings, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.Error(t, err, "exhausting every attempt to a collision must not silently succeed")
-	assert.Nil(t, settings, "no settings row may be returned on failure")
-	assert.Contains(t, err.Error(), "attempts exhausted")
-
-	_, err = st.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-	assert.Error(t, err, "no settings row must be persisted for the account when allocation fails")
-}
-
-// TestBootstrapSettings_ConcurrentBootstrapReturnsWinnersRow covers the
-// same-account race: Settings' primary key is AccountID, and the
-// existence pre-check in bootstrapSettingsIfNeeded runs outside the
-// transaction, so two concurrent first-provider creates for the same
-// account can both observe NotFound and both proceed to allocate. The
-// loser's INSERT then fails on the primary key rather than the subdomain
-// unique index — a string isUniqueConstraintError still recognises — and
-// must not be treated as a label collision to retry past; it must
-// re-read and return the winner's row.
-//
-// This is scripted against a gomock store rather than driven by real
-// goroutines against the sqlite test store: NewTestStoreFromSQL caps the
-// pool at a single open connection (see its startup log,
-// "max open db connections to 1"), which serialises statement execution
-// enough that reliably forcing the exact interleaving this test needs —
-// both pre-checks observing NotFound before either INSERT lands — would
-// depend on goroutine scheduling rather than the store, making a
-// real-goroutine version flaky rather than deterministic. Scripting the
-// exact sequence (pre-check miss, PK-shaped insert failure, re-read hit)
-// through a MockStore exercises the same re-read branch precisely and
-// deterministically.
-func TestBootstrapSettings_ConcurrentBootstrapReturnsWinnersRow(t *testing.T) {
-	ctx := context.Background()
-	ctrl := gomock.NewController(t)
-	mockStore := store.NewMockStore(ctrl)
-
-	winner := &types.Settings{
-		AccountID: "account1",
-		Cluster:   "cluster1.example.com",
-		Subdomain: "brave-otter",
-	}
-
-	gomock.InOrder(
-		// The pre-check: no row yet, so this bootstrap proceeds to allocate.
-		mockStore.EXPECT().
-			GetAgentNetworkSettings(gomock.Any(), store.LockingStrengthNone, "account1").
-			Return(nil, status.Errorf(status.NotFound, "agent network settings not found")),
-		// The insert loses the race. The message shape is the sqlite wording
-		// for a primary-key violation on account_id (not the subdomain
-		// index); this test locks down that the retry path recognizes that
-		// shape as a race loss and re-reads the winner's row, rather than
-		// misclassifying it as a subdomain conflict.
-		mockStore.EXPECT().
-			ExecuteInTransaction(gomock.Any(), gomock.Any()).
-			DoAndReturn(func(_ context.Context, f func(store.Store) error) error {
-				return f(mockStore)
-			}),
-		// The re-read after the PK conflict finds the concurrent winner's row.
-		mockStore.EXPECT().
-			GetAgentNetworkSettings(gomock.Any(), store.LockingStrengthNone, "account1").
-			Return(winner, nil),
-	)
-	mockStore.EXPECT().
-		CreateAgentNetworkSettings(gomock.Any(), gomock.Any()).
-		Return(errors.New("UNIQUE constraint failed: agent_network_settings.account_id"))
-
-	m := &managerImpl{
-		store:    mockStore,
-		labelRng: rand.New(rand.NewSource(9)),
-	}
-
-	settings, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.NoError(t, err, "losing the same-account race must not surface as an error")
-	require.NotNil(t, settings)
-	assert.Same(t, winner, settings, "the loser must return the concurrent winner's row, not retry past it")
-}
-
-// TestBootstrapSettings_NonRetryableErrorFailsImmediately guards the
-// isUniqueConstraintError branch itself: a regression that dropped that check
-// and retried on every ExecuteInTransaction error would leave every other test
-// in this file green, because none of them feed the loop a non-collision
-// failure. A generic store error must surface immediately, wrapped, and must
-// not be retried — asserting ExecuteInTransaction was called exactly once is
-// what proves the loop didn't retry.
-func TestBootstrapSettings_NonRetryableErrorFailsImmediately(t *testing.T) {
-	ctx := context.Background()
-	ctrl := gomock.NewController(t)
-	mockStore := store.NewMockStore(ctrl)
-
-	mockStore.EXPECT().
-		GetAgentNetworkSettings(gomock.Any(), store.LockingStrengthNone, "account1").
-		Return(nil, status.Errorf(status.NotFound, "agent network settings not found"))
-
-	mockStore.EXPECT().
-		ExecuteInTransaction(gomock.Any(), gomock.Any()).
-		Return(errors.New("connection refused")).
-		Times(1)
-
-	m := &managerImpl{
-		store:    mockStore,
-		labelRng: rand.New(rand.NewSource(5)),
-	}
-
-	settings, err := m.bootstrapSettingsIfNeeded(ctx, "account1", "cluster1.example.com")
-	require.Error(t, err, "a non-collision store error must surface, not be swallowed")
-	assert.Nil(t, settings)
-	assert.Contains(t, err.Error(), "create agent network settings",
-		"the non-retryable error must be wrapped and returned, not retried past")
-}

management/internals/modules/agentnetwork/domainlookup_test.go

@@ -1,120 +0,0 @@
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/server/store"
-)
-
-// TestSynthesizeServiceForDomain_ResolvesZoneBasedEndpoint — with a Zone the
-// hostname's parent is the zone, not the cluster, so the old "strip the first
-// label and match a cluster" prefilter found nothing and every zone-based
-// tenant failed to resolve on the auth path.
-func TestSynthesizeServiceForDomain_ResolvesZoneBasedEndpoint(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := store.NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	settings := newSynthTestSettings()
-	settings.Cluster = "eu.proxy.netbird.io"
-	settings.Zone = "gateway.netbird.ai"
-	settings.Subdomain = "brave-otter"
-	require.NoError(t, s.SaveAgentNetworkSettings(ctx, settings))
-	provider := newSynthTestProvider()
-	require.NoError(t, s.SaveAgentNetworkProvider(ctx, provider))
-	require.NoError(t, s.SaveAgentNetworkPolicy(ctx, newSynthTestPolicy(provider.ID, "grp-eng", "")))
-
-	domain := "brave-otter.gateway.netbird.ai"
-	svc, err := SynthesizeServiceForDomain(ctx, s, domain)
-	require.NoError(t, err)
-	require.NotNil(t, svc, "zone-based endpoint must resolve to the owning account's service")
-	assert.Equal(t, domain, svc.Domain)
-}
-
-// TestSynthesizeServiceForDomain_ResolvesLegacyClusterEndpoint — the
-// non-breaking guarantee. A row with no Zone still resolves at
-// <subdomain>.<cluster>, because the subdomain is the first label either way.
-func TestSynthesizeServiceForDomain_ResolvesLegacyClusterEndpoint(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := store.NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	settings := newSynthTestSettings()
-	settings.Cluster = "eu.proxy.netbird.io"
-	settings.Zone = ""
-	settings.Subdomain = "swift-heron"
-	require.NoError(t, s.SaveAgentNetworkSettings(ctx, settings))
-	provider := newSynthTestProvider()
-	require.NoError(t, s.SaveAgentNetworkProvider(ctx, provider))
-	require.NoError(t, s.SaveAgentNetworkPolicy(ctx, newSynthTestPolicy(provider.ID, "grp-eng", "")))
-
-	domain := "swift-heron.eu.proxy.netbird.io"
-	svc, err := SynthesizeServiceForDomain(ctx, s, domain)
-	require.NoError(t, err)
-	require.NotNil(t, svc, "legacy cluster-based endpoint must still resolve")
-	assert.Equal(t, domain, svc.Domain)
-}
-
-// TestSynthesizeServiceForDomain_LabelMatchesButParentDoesNot — the label is
-// globally unique, so a lookup by first label can hit a row that does NOT own
-// the queried hostname. That must resolve to nothing rather than to the wrong
-// account's service.
-func TestSynthesizeServiceForDomain_LabelMatchesButParentDoesNot(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := store.NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	settings := newSynthTestSettings()
-	settings.Cluster = "eu.proxy.netbird.io"
-	settings.Zone = "gateway.netbird.ai"
-	settings.Subdomain = "brave-otter"
-	require.NoError(t, s.SaveAgentNetworkSettings(ctx, settings))
-	provider := newSynthTestProvider()
-	require.NoError(t, s.SaveAgentNetworkProvider(ctx, provider))
-	require.NoError(t, s.SaveAgentNetworkPolicy(ctx, newSynthTestPolicy(provider.ID, "grp-eng", "")))
-
-	svc, err := SynthesizeServiceForDomain(ctx, s, "brave-otter.someone-elses.zone")
-	require.NoError(t, err)
-	assert.Nil(t, svc, "label matched a different endpoint's parent; must not resolve to the wrong account")
-}
-
-// TestSynthesizeServiceForDomain_UnknownLabel — a hostname whose first label
-// belongs to no account is a miss, not an error: the caller falls back to the
-// persisted-service lookup and a returned error would mask that.
-func TestSynthesizeServiceForDomain_UnknownLabel(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := store.NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	svc, err := SynthesizeServiceForDomain(ctx, s, "nobody-home.gateway.netbird.ai")
-	require.NoError(t, err)
-	assert.Nil(t, svc, "unknown label must be a miss, not an error")
-}
-
-// TestSynthesizeServiceForDomain_DegenerateInput — empty and single-label
-// hostnames have no dot to cut a subdomain label from, so they resolve to no
-// service, same as any other unowned hostname. The early-return guard that
-// catches them is an optimisation (it skips a store round trip that would
-// only miss anyway), not what makes this case correct — "" and "localhost"
-// would still come back nil, nil even without it, via the same not-found
-// fallthrough TestSynthesizeServiceForDomain_UnknownLabel exercises.
-func TestSynthesizeServiceForDomain_DegenerateInput(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := store.NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	for _, domain := range []string{"", "localhost"} {
-		svc, err := SynthesizeServiceForDomain(ctx, s, domain)
-		require.NoError(t, err, "domain %q", domain)
-		assert.Nil(t, svc, "domain %q has no subdomain label to look up", domain)
-	}
-}

management/internals/modules/agentnetwork/handlers/handlers_test.go

@@ -61,7 +61,7 @@ func newAgentNetworkHandlerFixture(t *testing.T) *agentNetworkHandlerFixture {
 		Return(true, context.Background(), nil).
 		AnyTimes()
 
-	manager := agentnetwork.NewManager(st, perms, nil, nil, "")
+	manager := agentnetwork.NewManager(st, perms, nil, nil)
 	h := &handler{manager: manager}
 
 	router := mux.NewRouter()

management/internals/modules/agentnetwork/labelgen/adjectives.go

@@ -1,39 +0,0 @@
-// Package labelgen produces DNS-safe Agent Network subdomain labels.
-//
-// The adjective pool below pairs with the noun pool in words.go to form
-// `<adjective>-<noun>` labels. It is kept separate because words.go is almost
-// entirely nouns — drawing both halves from it produced unreadable pairs like
-// "millet-hammock". Entries are lowercase ASCII, 4-12 chars, free of hyphens
-// and digits, screened for offensive/brand/region-specific terms, and disjoint
-// from the noun pool (enforced by TestAdjectives_AreDisjointFromNouns).
-package labelgen
-
-// adjectives is the descriptor half of a generated label.
-var adjectives = []string{
-	"able", "active", "adept", "agile", "airy", "alert", "amiable", "ample",
-	"ancient", "ardent", "artful", "astute", "balmy", "blithe", "bold", "bonny",
-	"brave", "breezy", "brisk", "bubbly", "buoyant", "bushy", "candid", "canny",
-	"cheery", "chilly", "chipper", "chunky", "civil", "classic", "clever", "comely",
-	"compact", "cordial", "cosmic", "courtly", "crafty", "creamy", "crisp", "cuddly",
-	"curious", "dainty", "dapper", "daring", "dashing", "deft", "dewy", "diligent",
-	"downy", "dreamy", "dulcet", "durable", "dusky", "eager", "earnest", "earthy",
-	"easy", "elated", "elegant", "epic", "fabled", "faithful", "fancy", "fearless",
-	"feisty", "fervent", "fleet", "fluffy", "fond", "frisky", "frosty", "gallant",
-	"genial", "genteel", "gentle", "giddy", "gilded", "glad", "glassy", "gleaming",
-	"glossy", "graceful", "grand", "grainy", "hale", "hardy", "hearty", "hefty",
-	"honest", "hopeful", "humble", "hushed", "immense", "jaunty", "jolly", "jovial",
-	"joyful", "jubilant", "keen", "kindly", "kindred", "lanky", "leafy", "limber",
-	"lively", "lofty", "loyal", "lucent", "lucid", "luminous", "lush", "maroon",
-	"mellow", "merry", "mighty", "mindful", "mirthful", "misty", "modest", "muted",
-	"nifty", "nimble", "noble", "patient", "peaceful", "pearly", "peppy", "perky",
-	"petite", "placid", "playful", "pleasant", "plucky", "plush", "polite", "posh",
-	"prancing", "pristine", "prompt", "proud", "prudent", "quaint", "quick", "quirky",
-	"radiant", "ready", "regal", "restful", "robust", "rosy", "ruddy", "rugged",
-	"sandy", "satin", "saucy", "savvy", "sedate", "serene", "shady", "shiny",
-	"silken", "silky", "sincere", "sleek", "slender", "smart", "smooth", "snappy",
-	"snug", "soaring", "sparkly", "spiffy", "spirited", "sprightly", "spry", "stalwart",
-	"stately", "steady", "sterling", "stoic", "stormy", "stout", "sturdy", "sunlit",
-	"supple", "svelte", "tawny", "tender", "tidy", "timeless", "trusty", "upbeat",
-	"urbane", "valiant", "vast", "vernal", "vibrant", "vintage", "whimsy", "willing",
-	"windy", "winsome", "wintry", "witty", "worthy", "zesty", "zippy",
-}

management/internals/modules/agentnetwork/labelgen/labelgen.go

@@ -2,11 +2,18 @@
 package labelgen
 
 import (
+	"fmt"
 	"math/rand"
 	"sort"
 	"sync"
 )
 
+// pickAttempts caps the random retries before falling back to the
+// suffixed form. Eight is a soft compromise: with a near-empty taken
+// set the very first pick almost always succeeds; when the wordlist is
+// densely populated the fallback eventually fires anyway.
+const pickAttempts = 8
+
 var (
 	dedupOnce sync.Once
 	uniqWords []string
@@ -30,19 +37,30 @@ func uniqueWords() []string {
 	return uniqWords
 }
 
-// PickTuple returns an adjective-noun label such as "brave-otter". It is still
-// a single DNS label.
-//
-// It takes no `taken` set and has no fallback suffix. The noun pool holds 857
-// entries, which is ample per cluster but a hard ceiling once labels must be
-// unique across one shared zone; pairing an adjective with a noun spans
-// len(adjectives) * 857 instead. Uniqueness is enforced by a database
-// constraint and retried by the caller, rather than guessed from a pre-read
-// set that a concurrent allocation can invalidate.
-func PickTuple(rng *rand.Rand) string {
-	nouns := uniqueWords()
-	if len(nouns) == 0 || len(adjectives) == 0 {
-		return ""
+// PickUnique selects a label not already in `taken`. It tries up to
+// pickAttempts random picks; on exhaustion it scans the deduplicated
+// wordlist for any remaining free entry, and if none is left appends
+// `-<fallbackSuffix>` to a deterministic word and returns. The caller
+// is responsible for seeding rng (math/rand).
+func PickUnique(rng *rand.Rand, taken map[string]struct{}, fallbackSuffix string) string {
+	pool := uniqueWords()
+	if len(pool) == 0 {
+		return fallbackSuffix
 	}
-	return adjectives[rng.Intn(len(adjectives))] + "-" + nouns[rng.Intn(len(nouns))]
+
+	for i := 0; i < pickAttempts; i++ {
+		w := pool[rng.Intn(len(pool))]
+		if _, ok := taken[w]; !ok {
+			return w
+		}
+	}
+
+	for _, w := range pool {
+		if _, ok := taken[w]; !ok {
+			return w
+		}
+	}
+
+	w := pool[rng.Intn(len(pool))]
+	return fmt.Sprintf("%s-%s", w, fallbackSuffix)
 }

management/internals/modules/agentnetwork/labelgen/labelgen_test.go

@@ -9,6 +9,78 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
+// TestPickUnique_DeterministicWithSeededRng locks the property the
+// caller relies on: same seed + same taken set → same pick. Without
+// that, the bootstrap flow can't reproduce a label across retries.
+func TestPickUnique_DeterministicWithSeededRng(t *testing.T) {
+	taken := map[string]struct{}{}
+
+	rngA := rand.New(rand.NewSource(42))
+	rngB := rand.New(rand.NewSource(42))
+
+	a := PickUnique(rngA, taken, "abcd")
+	b := PickUnique(rngB, taken, "abcd")
+
+	assert.Equal(t, a, b, "Same seed and taken set must produce identical pick")
+}
+
+// TestPickUnique_AvoidsTakenWordsWhenMostAreReserved seeds taken with
+// every word in the pool except a handful and confirms PickUnique
+// finds one of the remaining free entries instead of returning the
+// fallback form.
+func TestPickUnique_AvoidsTakenWordsWhenMostAreReserved(t *testing.T) {
+	pool := uniqueWords()
+	require.NotEmpty(t, pool, "wordlist must be populated for the test to mean anything")
+
+	free := map[string]struct{}{
+		pool[0]:           {},
+		pool[len(pool)/2]: {},
+		pool[len(pool)-1]: {},
+	}
+
+	taken := make(map[string]struct{}, len(pool))
+	for _, w := range pool {
+		if _, ok := free[w]; ok {
+			continue
+		}
+		taken[w] = struct{}{}
+	}
+
+	rng := rand.New(rand.NewSource(7))
+	got := PickUnique(rng, taken, "abcd")
+
+	_, isFree := free[got]
+	assert.True(t, isFree, "PickUnique must return one of the free words; got %q", got)
+	assert.NotContains(t, got, "-", "Free pick must not be the suffix fallback form")
+}
+
+// TestPickUnique_FallsBackWhenAllReserved exhausts the pool and
+// confirms PickUnique appends the supplied suffix instead of
+// returning a duplicate.
+func TestPickUnique_FallsBackWhenAllReserved(t *testing.T) {
+	pool := uniqueWords()
+
+	taken := make(map[string]struct{}, len(pool))
+	for _, w := range pool {
+		taken[w] = struct{}{}
+	}
+
+	rng := rand.New(rand.NewSource(99))
+	got := PickUnique(rng, taken, "abcd")
+
+	assert.True(t, strings.HasSuffix(got, "-abcd"), "Exhausted pool must produce <word>-<suffix>; got %q", got)
+
+	prefix := strings.TrimSuffix(got, "-abcd")
+	found := false
+	for _, w := range pool {
+		if w == prefix {
+			found = true
+			break
+		}
+	}
+	assert.True(t, found, "Fallback prefix must be drawn from the wordlist; got %q", prefix)
+}
+
 // TestUniqueWords_DropsDuplicates guards against authoring slips in
 // words.go: every entry must be unique and DNS-safe.
 func TestUniqueWords_DropsDuplicates(t *testing.T) {
@@ -27,82 +99,3 @@ func TestUniqueWords_DropsDuplicates(t *testing.T) {
 	}
 	assert.GreaterOrEqual(t, len(pool), 500, "Pool must contain at least 500 unique words")
 }
-
-// TestPickTuple_ShapeAndPoolMembership locks the wire-visible shape: an
-// adjective and a noun, each from its own pool, joined by a single hyphen so
-// the result stays one DNS label.
-func TestPickTuple_ShapeAndPoolMembership(t *testing.T) {
-	nouns := uniqueWords()
-	inNouns := make(map[string]struct{}, len(nouns))
-	for _, w := range nouns {
-		inNouns[w] = struct{}{}
-	}
-	inAdjectives := make(map[string]struct{}, len(adjectives))
-	for _, a := range adjectives {
-		inAdjectives[a] = struct{}{}
-	}
-
-	rng := rand.New(rand.NewSource(7))
-	for i := 0; i < 200; i++ {
-		got := PickTuple(rng)
-
-		parts := strings.Split(got, "-")
-		require.Len(t, parts, 2, "PickTuple must produce exactly two hyphen-joined words; got %q", got)
-
-		_, adjOK := inAdjectives[parts[0]]
-		assert.True(t, adjOK, "First half must be an adjective; %q not in adjectives (from %q)", parts[0], got)
-		_, nounOK := inNouns[parts[1]]
-		assert.True(t, nounOK, "Second half must be a noun; %q not in words (from %q)", parts[1], got)
-
-		assert.LessOrEqual(t, len(got), 63, "Label must fit a DNS label; got %q (%d chars)", got, len(got))
-	}
-}
-
-// TestAdjectives_AreDisjointFromNouns keeps the namespace a clean product and
-// prevents nonsense like "azure-azure": a handful of the noun pool's entries
-// are adjectival, and any overlap would let the same word land on both sides.
-func TestAdjectives_AreDisjointFromNouns(t *testing.T) {
-	nouns := make(map[string]struct{}, len(uniqueWords()))
-	for _, w := range uniqueWords() {
-		nouns[w] = struct{}{}
-	}
-	for _, a := range adjectives {
-		_, clash := nouns[a]
-		assert.False(t, clash, "Adjective %q also appears in the noun pool; remove it from one list", a)
-	}
-}
-
-// TestAdjectives_AreDNSSafeAndDeduplicated mirrors the curation contract stated
-// in words.go: lowercase ASCII, 4-12 chars, no digits or hyphens, no repeats.
-func TestAdjectives_AreDNSSafeAndDeduplicated(t *testing.T) {
-	seen := make(map[string]struct{}, len(adjectives))
-	for _, a := range adjectives {
-		_, dup := seen[a]
-		assert.False(t, dup, "Duplicate adjective %q", a)
-		seen[a] = struct{}{}
-
-		assert.Regexp(t, `^[a-z]{4,12}$`, a, "Adjective %q must be 4-12 lowercase ASCII letters", a)
-	}
-	assert.Greater(t, len(adjectives), 150, "Adjective pool too small to give a useful namespace")
-}
-
-// TestPickTuple_DeterministicWithSeededRng documents that generation is a pure
-// function of the rng, which is what makes allocation retries reproducible in tests.
-func TestPickTuple_DeterministicWithSeededRng(t *testing.T) {
-	a := PickTuple(rand.New(rand.NewSource(42)))
-	b := PickTuple(rand.New(rand.NewSource(42)))
-	assert.Equal(t, a, b, "Same seed must yield the same tuple")
-}
-
-// TestPickTuple_SpansALargeNamespace guards the reason we moved to tuples: a
-// single-word pool caps the GLOBAL namespace at 857. Drawing many tuples must
-// yield overwhelmingly distinct values.
-func TestPickTuple_SpansALargeNamespace(t *testing.T) {
-	rng := rand.New(rand.NewSource(11))
-	seen := make(map[string]struct{}, 2000)
-	for i := 0; i < 2000; i++ {
-		seen[PickTuple(rng)] = struct{}{}
-	}
-	assert.Greater(t, len(seen), 1900,
-		"2000 draws should be nearly all distinct across a ~200k namespace; got %d unique", len(seen))
-}

management/internals/modules/agentnetwork/labelgen/words.go

@@ -6,7 +6,7 @@
 // hand-checked to avoid offensive, brand, or region-specific terms.
 package labelgen
 
-// words is the pool PickTuple draws its noun from. The slice is intentionally
+// words is the pool PickUnique selects from. The slice is intentionally
 // not sorted — random picks distribute across the list naturally.
 var words = []string{
 	"acorn", "adobe", "agate", "alder", "almond", "alpine", "amber", "amethyst",

management/internals/modules/agentnetwork/manager.go

@@ -122,10 +122,6 @@ type managerImpl struct {
 	permissionsManager permissions.Manager
 	proxyController    proxy.Controller
 
-	// zone is the parent DNS zone stamped onto newly allocated settings rows.
-	// Empty keeps the legacy <subdomain>.<cluster> endpoint form.
-	zone string
-
 	// reconcileCache holds the last set of synthesised proxy mappings
 	// per account so reconcile can emit precise Create/Update/Delete
 	// updates instead of a full re-push on every mutation. Keyed by
@@ -133,7 +129,7 @@ type managerImpl struct {
 	reconcileMu    sync.Mutex
 	reconcileCache map[string]map[string]*proto.ProxyMapping
 
-	// labelRngMu guards labelRng. PickTuple consumes math/rand.Source
+	// labelRngMu guards labelRng. PickUnique consumes math/rand.Source
 	// state; concurrent provider creates would otherwise race.
 	labelRngMu sync.Mutex
 	labelRng   *rand.Rand
@@ -149,28 +145,26 @@ func NewManager(
 	permissionsManager permissions.Manager,
 	accountManager account.Manager,
 	proxyController proxy.Controller,
-	zone string,
 ) Manager {
 	return &managerImpl{
 		store:              store,
 		accountManager:     accountManager,
 		permissionsManager: permissionsManager,
 		proxyController:    proxyController,
-		zone:               zone,
 		reconcileCache:     make(map[string]map[string]*proto.ProxyMapping),
 		labelRng:           rand.New(rand.NewSource(time.Now().UnixNano())),
 	}
 }
 
 func (m *managerImpl) GetAllProviders(ctx context.Context, accountID, userID string) ([]*types.Provider, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, providerID string) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkProviderByID(ctx, store.LockingStrengthNone, accountID, providerID)
@@ -181,14 +175,9 @@ func (m *managerImpl) GetProvider(ctx context.Context, accountID, userID, provid
 // been created yet; otherwise it is ignored (the cluster is pinned on
 // Settings and every provider in the account routes through it).
 func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provider *types.Provider, bootstrapCluster string) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
-	if strings.TrimSpace(bootstrapCluster) != "" {
-		if err := m.requireSettingsBootstrapPermission(ctx, provider.AccountID, userID); err != nil {
-			return nil, err
-		}
-	}
 
 	// An empty api_key would silently produce a synthesised service
 	// that 401s on every upstream request. Surface the misconfiguration
@@ -229,7 +218,7 @@ func (m *managerImpl) CreateProvider(ctx context.Context, userID string, provide
 }
 
 func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provider *types.Provider) (*types.Provider, error) {
-	if err := m.requirePermission(ctx, provider.AccountID, userID, modules.AgentNetworkProviders, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, provider.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -268,7 +257,7 @@ func (m *managerImpl) UpdateProvider(ctx context.Context, userID string, provide
 }
 
 func (m *managerImpl) DeleteProvider(ctx context.Context, accountID, userID, providerID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkProviders, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -309,22 +298,6 @@ func (m *managerImpl) DeleteProvider(ctx context.Context, accountID, userID, pro
 	return nil
 }
 
-// isUniqueConstraintError reports whether err is a duplicate-key rejection.
-//
-// The equivalent helper in management/server is unexported, so it cannot be
-// reused from here; this is a deliberate duplicate rather than a new dependency
-// on that package for a single three-line matcher. Keep the two in sync if a
-// dialect is added.
-func isUniqueConstraintError(err error) bool {
-	if err == nil {
-		return false
-	}
-	msg := err.Error()
-	return strings.Contains(msg, "(SQLSTATE 23505)") || // postgres
-		strings.Contains(msg, "Error 1062 (23000)") || // mysql
-		strings.Contains(msg, "UNIQUE constraint failed") // sqlite
-}
-
 func pluralize(n int, singular, plural string) string {
 	if n == 1 {
 		return singular
@@ -333,21 +306,21 @@ func pluralize(n int, singular, plural string) string {
 }
 
 func (m *managerImpl) GetAllPolicies(ctx context.Context, accountID, userID string) ([]*types.Policy, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkPolicies(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetPolicy(ctx context.Context, accountID, userID, policyID string) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkPolicyByID(ctx, store.LockingStrengthNone, accountID, policyID)
 }
 
 func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -373,7 +346,7 @@ func (m *managerImpl) CreatePolicy(ctx context.Context, userID string, policy *t
 }
 
 func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *types.Policy) (*types.Policy, error) {
-	if err := m.requirePermission(ctx, policy.AccountID, userID, modules.AgentNetworkPolicies, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, policy.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -400,7 +373,7 @@ func (m *managerImpl) UpdatePolicy(ctx context.Context, userID string, policy *t
 }
 
 func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, policyID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkPolicies, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -420,21 +393,21 @@ func (m *managerImpl) DeletePolicy(ctx context.Context, accountID, userID, polic
 }
 
 func (m *managerImpl) GetAllGuardrails(ctx context.Context, accountID, userID string) ([]*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkGuardrails(ctx, store.LockingStrengthNone, accountID)
 }
 
 func (m *managerImpl) GetGuardrail(ctx context.Context, accountID, userID, guardrailID string) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkGuardrailByID(ctx, store.LockingStrengthNone, accountID, guardrailID)
 }
 
 func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -456,7 +429,7 @@ func (m *managerImpl) CreateGuardrail(ctx context.Context, userID string, guardr
 }
 
 func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardrail *types.Guardrail) (*types.Guardrail, error) {
-	if err := m.requirePermission(ctx, guardrail.AccountID, userID, modules.AgentNetworkGuardrails, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, guardrail.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -479,7 +452,7 @@ func (m *managerImpl) UpdateGuardrail(ctx context.Context, userID string, guardr
 }
 
 func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, guardrailID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkGuardrails, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -500,7 +473,7 @@ func (m *managerImpl) DeleteGuardrail(ctx context.Context, accountID, userID, gu
 
 // GetAllBudgetRules returns every account-level budget rule for the account.
 func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID string) ([]*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAccountAgentNetworkBudgetRules(ctx, store.LockingStrengthNone, accountID)
@@ -508,7 +481,7 @@ func (m *managerImpl) GetAllBudgetRules(ctx context.Context, accountID, userID s
 
 // GetBudgetRule returns a single account-level budget rule.
 func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, ruleID string) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkBudgetRuleByID(ctx, store.LockingStrengthNone, accountID, ruleID)
@@ -518,7 +491,7 @@ func (m *managerImpl) GetBudgetRule(ctx context.Context, accountID, userID, rule
 // enforced at request time (CheckLLMPolicyLimits), not baked into the synth
 // proxy config, so no reconcile is needed.
 func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Create); err != nil {
+	if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Create); err != nil {
 		return nil, err
 	}
 
@@ -540,7 +513,7 @@ func (m *managerImpl) CreateBudgetRule(ctx context.Context, userID string, rule
 
 // UpdateBudgetRule updates an existing account-level budget rule.
 func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule *types.AccountBudgetRule) (*types.AccountBudgetRule, error) {
-	if err := m.requirePermission(ctx, rule.AccountID, userID, modules.AgentNetworkBudgets, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, rule.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -563,7 +536,7 @@ func (m *managerImpl) UpdateBudgetRule(ctx context.Context, userID string, rule
 
 // DeleteBudgetRule removes an account-level budget rule.
 func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, ruleID string) error {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkBudgets, operations.Delete); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Delete); err != nil {
 		return err
 	}
 
@@ -588,7 +561,7 @@ func (m *managerImpl) DeleteBudgetRule(ctx context.Context, accountID, userID, r
 // gating, access-log emission), a reconcile is triggered so the proxy and peer
 // network maps converge on the new state.
 func (m *managerImpl) UpdateSettings(ctx context.Context, userID string, settings *types.Settings) (*types.Settings, error) {
-	if err := m.requirePermission(ctx, settings.AccountID, userID, modules.AgentNetworkSettings, operations.Update); err != nil {
+	if err := m.requirePermission(ctx, settings.AccountID, userID, operations.Update); err != nil {
 		return nil, err
 	}
 
@@ -642,37 +615,18 @@ func (m *managerImpl) validateProviderRefs(ctx context.Context, accountID string
 // Returns the underlying status.NotFound when no row has been
 // bootstrapped yet (i.e. the account has no providers).
 func (m *managerImpl) GetSettings(ctx context.Context, accountID, userID string) (*types.Settings, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
 }
 
-// requireSettingsBootstrapPermission gates the one-time settings bootstrap a
-// first provider create performs. Pinning the account's cluster and subdomain
-// is a settings write, so it needs the settings permission on top of the
-// provider one. No-op once the settings row exists.
-func (m *managerImpl) requireSettingsBootstrapPermission(ctx context.Context, accountID, userID string) error {
-	_, err := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID)
-	if err == nil {
-		return nil
-	}
-	var sErr *status.Error
-	if !errors.As(err, &sErr) || sErr.Type() != status.NotFound {
-		return fmt.Errorf("get agent network settings: %w", err)
-	}
-	return m.requirePermission(ctx, accountID, userID, modules.AgentNetworkSettings, operations.Create)
-}
-
-// maxSubdomainAllocationAttempts bounds the allocate-and-insert retry loop in
-// bootstrapSettingsIfNeeded. Package-level (rather than function-local) so
-// tests can assert on the exhaustion path without duplicating the literal.
-const maxSubdomainAllocationAttempts = 10
-
-// bootstrapSettingsIfNeeded creates the per-account agent-network settings
-// row when missing, allocating a subdomain unique across the whole zone.
-// Idempotent: if a row already exists it is returned untouched and the
-// cluster hint is ignored.
+// bootstrapSettingsIfNeeded creates the per-account agent-network
+// settings row when missing. The cluster comes from the create-time
+// hint the dashboard sends (auto-picked from the active cluster list);
+// the subdomain is picked from the curated wordlist avoiding
+// collisions on the same cluster. Idempotent: if a row already exists
+// it is returned untouched and the hint is ignored.
 func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID, providerCluster string) (*types.Settings, error) {
 	if accountID == "" {
 		return nil, fmt.Errorf("bootstrap settings: account id is required")
@@ -690,66 +644,40 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
 		return nil, fmt.Errorf("get agent network settings: %w", err)
 	}
 
-	// Labels must be unique across the whole zone; the database's unique index
-	// enforces that, and the loop below retries with a fresh label whenever an
-	// attempt is rejected.
+	siblings, err := m.store.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, providerCluster)
+	if err != nil {
+		return nil, fmt.Errorf("list agent network settings on cluster: %w", err)
+	}
+	taken := make(map[string]struct{}, len(siblings))
+	for _, s := range siblings {
+		taken[s.Subdomain] = struct{}{}
+	}
+
+	suffix := accountID
+	if len(suffix) > 4 {
+		suffix = suffix[:4]
+	}
+
+	m.labelRngMu.Lock()
+	subdomain := labelgen.PickUnique(m.labelRng, taken, suffix)
+	m.labelRngMu.Unlock()
+
 	now := time.Now().UTC()
 	settings := &types.Settings{
-		AccountID:              accountID,
-		Cluster:                providerCluster,
-		Zone:                   m.zone,
+		AccountID: accountID,
+		Cluster:   providerCluster,
+		Subdomain: subdomain,
+		// Logs on by default; usage is collected regardless. Retention bounds
+		// how long full log rows are kept.
 		EnableLogCollection:    true,
 		AccessLogRetentionDays: types.DefaultAccessLogRetentionDays,
 		CreatedAt:              now,
 		UpdatedAt:              now,
 	}
-
-	for attempt := 1; attempt <= maxSubdomainAllocationAttempts; attempt++ {
-		m.labelRngMu.Lock()
-		settings.Subdomain = labelgen.PickTuple(m.labelRng)
-		m.labelRngMu.Unlock()
-
-		if settings.Subdomain == "" {
-			// Only reachable if either word pool were emptied; a database
-			// insert of an empty subdomain would collide with the unique
-			// index in a confusing way and produce a broken endpoint like
-			// ".gateway.example". Fail loudly instead of looping or inserting.
-			return nil, fmt.Errorf(
-				"allocate agent network subdomain for account %s: label generator returned an empty label",
-				accountID)
-		}
-
-		// Each attempt gets its own transaction wrapping a single INSERT: on
-		// postgres a failed statement poisons the enclosing transaction, so a
-		// fresh transaction per attempt is what makes the retry loop work on
-		// that dialect at all.
-		err := m.store.ExecuteInTransaction(ctx, func(transaction store.Store) error {
-			return transaction.CreateAgentNetworkSettings(ctx, settings)
-		})
-		if err == nil {
-			return settings, nil
-		}
-		if isUniqueConstraintError(err) {
-			// A concurrent bootstrap for this account may have won the race: the
-			// pre-check above is outside the transaction, and the settings PK is
-			// account_id, so the loser's insert fails on the primary key rather
-			// than the subdomain index. Re-read before assuming the label was
-			// taken, so a same-account race resolves immediately instead of
-			// burning every remaining attempt on the same primary-key conflict.
-			if existing, getErr := m.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, accountID); getErr == nil {
-				return existing, nil
-			}
-			log.WithContext(ctx).Tracef(
-				"agent-network subdomain %q taken, retrying (attempt %d/%d)",
-				settings.Subdomain, attempt, maxSubdomainAllocationAttempts)
-			continue
-		}
-		return nil, fmt.Errorf("create agent network settings: %w", err)
+	if err := m.store.SaveAgentNetworkSettings(ctx, settings); err != nil {
+		return nil, fmt.Errorf("save agent network settings: %w", err)
 	}
-
-	return nil, fmt.Errorf(
-		"allocate agent network subdomain for account %s: %d attempts exhausted",
-		accountID, maxSubdomainAllocationAttempts)
+	return settings, nil
 }
 
 // ListConsumption returns every consumption row recorded for the
@@ -757,7 +685,7 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
 // counter view; permission gate is the same Read role that gates
 // every other agent-network surface.
 func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID string) ([]*types.Consumption, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	return m.store.ListAgentNetworkConsumption(ctx, store.LockingStrengthNone, accountID)
@@ -766,7 +694,7 @@ func (m *managerImpl) ListConsumption(ctx context.Context, accountID, userID str
 // ListAccessLogs returns a paginated, server-side-filtered page of
 // agent-network access logs plus the total count matching the filter.
 func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLog, int64, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, 0, err
 	}
 	return m.store.GetAgentNetworkAccessLogs(ctx, store.LockingStrengthNone, accountID, filter)
@@ -776,7 +704,7 @@ func (m *managerImpl) ListAccessLogs(ctx context.Context, accountID, userID stri
 // agent-network access logs grouped by session, plus the total number of
 // sessions matching the filter.
 func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkAccessLogSession, int64, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkLogs, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, 0, err
 	}
 	return m.store.GetAgentNetworkAccessLogSessions(ctx, store.LockingStrengthNone, accountID, filter)
@@ -785,7 +713,7 @@ func (m *managerImpl) ListAccessLogSessions(ctx context.Context, accountID, user
 // GetUsageOverview returns the filtered usage rows aggregated into time buckets
 // at the requested granularity, oldest-first.
 func (m *managerImpl) GetUsageOverview(ctx context.Context, accountID, userID string, filter types.AgentNetworkAccessLogFilter, granularity types.UsageGranularity) ([]*types.AgentNetworkUsageBucket, error) {
-	if err := m.requirePermission(ctx, accountID, userID, modules.AgentNetworkUsage, operations.Read); err != nil {
+	if err := m.requirePermission(ctx, accountID, userID, operations.Read); err != nil {
 		return nil, err
 	}
 	rows, err := m.store.GetAgentNetworkUsageRows(ctx, store.LockingStrengthNone, accountID, filter)
@@ -859,8 +787,8 @@ func (m *managerImpl) RecordConsumption(ctx context.Context, accountID string, k
 	return m.store.IncrementAgentNetworkConsumption(ctx, accountID, kind, dimID, windowSeconds, windowStart, tokensIn, tokensOut, costUSD)
 }
 
-func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, module modules.Module, op operations.Operation) error {
-	ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, module, op)
+func (m *managerImpl) requirePermission(ctx context.Context, accountID, userID string, op operations.Operation) error {
+	ok, _, err := m.permissionsManager.ValidateUserPermissions(ctx, accountID, userID, modules.AgentNetwork, op)
 	if err != nil {
 		return status.NewPermissionValidationError(err)
 	}

management/internals/modules/agentnetwork/provider_bootstrap_test.go

@@ -1,134 +0,0 @@
-package agentnetwork
-
-import (
-	"context"
-	"runtime"
-	"testing"
-
-	"github.com/golang/mock/gomock"
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-	"github.com/netbirdio/netbird/management/server/account"
-	"github.com/netbirdio/netbird/management/server/permissions"
-	"github.com/netbirdio/netbird/management/server/permissions/modules"
-	"github.com/netbirdio/netbird/management/server/permissions/operations"
-	"github.com/netbirdio/netbird/management/server/store"
-	nbtypes "github.com/netbirdio/netbird/management/server/types"
-	"github.com/netbirdio/netbird/shared/management/status"
-)
-
-// bootstrapFixture wires a real sqlite store to a gomock permissions manager
-// so tests can grant the provider permission while denying (or never
-// expecting) the settings one.
-type bootstrapFixture struct {
-	manager Manager
-	store   store.Store
-	perms   *permissions.MockManager
-}
-
-func newBootstrapFixture(t *testing.T) *bootstrapFixture {
-	t.Helper()
-	if runtime.GOOS == "windows" {
-		t.Skip("sqlite store not properly supported on Windows yet")
-	}
-	t.Setenv("NETBIRD_STORE_ENGINE", string(nbtypes.SqliteStoreEngine))
-
-	st, cleanUp, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
-	require.NoError(t, err, "test store setup must succeed")
-	t.Cleanup(cleanUp)
-
-	ctrl := gomock.NewController(t)
-	perms := permissions.NewMockManager(ctrl)
-
-	accounts := account.NewMockManager(ctrl)
-	accounts.EXPECT().StoreEvent(gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-	accounts.EXPECT().UpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-	accounts.EXPECT().BufferUpdateAccountPeers(gomock.Any(), gomock.Any(), gomock.Any()).AnyTimes()
-
-	return &bootstrapFixture{
-		manager: NewManager(st, perms, accounts, nil, ""),
-		store:   st,
-		perms:   perms,
-	}
-}
-
-func (f *bootstrapFixture) expectPermission(accountID, userID string, module modules.Module, op operations.Operation, allowed bool) {
-	f.perms.EXPECT().
-		ValidateUserPermissions(gomock.Any(), accountID, userID, module, op).
-		Return(allowed, context.Background(), nil)
-}
-
-func newBootstrapProvider(accountID string) *types.Provider {
-	p := types.NewProvider(accountID)
-	p.Name = "openai"
-	p.UpstreamURL = "https://api.openai.com"
-	p.APIKey = "sk-test"
-	p.Enabled = true
-	return p
-}
-
-// TestCreateProviderBootstrapRequiresSettingsPermission pins the gate on the
-// one-time settings bootstrap: creating the first provider with a
-// bootstrap_cluster pins the account's cluster and subdomain, which is a
-// settings write and must not ride on the providers permission alone.
-func TestCreateProviderBootstrapRequiresSettingsPermission(t *testing.T) {
-	ctx := context.Background()
-
-	t.Run("denied without settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-		f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, false)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.Error(t, err, "bootstrap without settings permission must fail")
-		var sErr *status.Error
-		require.ErrorAs(t, err, &sErr)
-		assert.Equal(t, status.PermissionDenied, sErr.Type(), "denial should surface as permission denied")
-
-		providers, err := f.store.GetAccountAgentNetworkProviders(ctx, store.LockingStrengthNone, "account1")
-		require.NoError(t, err)
-		assert.Empty(t, providers, "provider must not be persisted when bootstrap is denied")
-		_, err = f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-		assert.Error(t, err, "settings row must not be created when bootstrap is denied")
-	})
-
-	t.Run("allowed with settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-		f.expectPermission("account1", "user1", modules.AgentNetworkSettings, operations.Create, true)
-
-		created, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.NoError(t, err, "bootstrap with both permissions must succeed")
-		require.NotNil(t, created)
-
-		settings, err := f.store.GetAgentNetworkSettings(ctx, store.LockingStrengthNone, "account1")
-		require.NoError(t, err, "bootstrap must create the settings row")
-		assert.Equal(t, "cluster1.example.com", settings.Cluster, "settings should pin the bootstrap cluster")
-	})
-
-	t.Run("existing settings need no settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		require.NoError(t, f.store.SaveAgentNetworkSettings(ctx, &types.Settings{
-			AccountID: "account1",
-			Cluster:   "cluster1.example.com",
-			Subdomain: "existing",
-		}), "pre-existing settings row setup must succeed")
-
-		// Only the providers permission may be consulted: gomock fails the
-		// test on any unexpected settings-permission call.
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "cluster1.example.com")
-		require.NoError(t, err, "create with existing settings must not require the settings permission")
-	})
-
-	t.Run("no bootstrap cluster needs no settings permission", func(t *testing.T) {
-		f := newBootstrapFixture(t)
-		f.expectPermission("account1", "user1", modules.AgentNetworkProviders, operations.Create, true)
-
-		_, err := f.manager.CreateProvider(ctx, "user1", newBootstrapProvider("account1"), "")
-		require.NoError(t, err, "create without bootstrap must not require the settings permission")
-	})
-}

management/internals/modules/agentnetwork/synthesizer.go

@@ -116,46 +116,45 @@ func SynthesizeServicesForCluster(ctx context.Context, s store.Store, clusterAdd
 }
 
 // SynthesizeServiceForDomain resolves a single agent-network service by its
-// endpoint hostname. Both endpoint shapes put the account's label in the first
-// DNS label — <subdomain>.<cluster> and <subdomain>.<zone> — and the label is
-// globally unique, so this is a single indexed lookup for either shape. It
-// synthesises only the owning account rather than every tenant on a cluster,
-// which is what auth/session paths previously paid. Returns nil (no error) when
-// no account owns the hostname.
+// public endpoint domain. It lists the (few) settings rows on the domain's
+// cluster, matches the one whose endpoint equals the domain, and synthesises
+// only that account — avoiding full per-account synthesis for every tenant on
+// the cluster, which is what auth/session paths previously paid. Returns nil
+// (no error) when no account owns the domain.
 func SynthesizeServiceForDomain(ctx context.Context, s store.Store, domain string) (*rpservice.Service, error) {
 	domain = strings.TrimSpace(domain)
-	subdomain, _, found := strings.Cut(domain, ".")
-	if !found || subdomain == "" {
-		return nil, nil //nolint:nilnil // no label to resolve: not an owned endpoint
-	}
-
-	settings, err := s.GetAgentNetworkSettingsBySubdomain(ctx, store.LockingStrengthNone, subdomain)
-	if err != nil {
-		var sErr *status.Error
-		if errors.As(err, &sErr) && sErr.Type() == status.NotFound {
-			return nil, nil //nolint:nilnil // no account owns the label
+	cluster := clusterFromDomain(domain)
+	if domain != "" && cluster != "" {
+		settingsRows, err := s.GetAgentNetworkSettingsByCluster(ctx, store.LockingStrengthNone, cluster)
+		if err != nil {
+			return nil, fmt.Errorf("list agent network settings on cluster: %w", err)
 		}
-		// A real store failure must surface: the caller treats nil as "not an
-		// agent-network endpoint" and would silently mask a database error.
-		return nil, fmt.Errorf("get agent network settings by subdomain: %w", err)
-	}
-
-	// The label is unique but the parent is not implied by it: a row owning
-	// "brave-otter" does not own "brave-otter.some-other.zone".
-	if settings.Endpoint() != domain {
-		return nil, nil //nolint:nilnil // label matched a different endpoint
-	}
-
-	services, err := SynthesizeServices(ctx, s, settings.AccountID)
-	if err != nil {
-		return nil, err
-	}
-	for _, svc := range services {
-		if svc != nil && svc.Domain == domain {
-			return svc, nil
+		for _, settings := range settingsRows {
+			if settings == nil || settings.Endpoint() != domain {
+				continue
+			}
+			services, serr := SynthesizeServices(ctx, s, settings.AccountID)
+			if serr != nil {
+				return nil, serr
+			}
+			for _, svc := range services {
+				if svc != nil && svc.Domain == domain {
+					return svc, nil
+				}
+			}
+			break
 		}
 	}
-	return nil, nil //nolint:nilnil // owner found but it emits no service
+	return nil, nil //nolint:nilnil // optional lookup: no account owns the domain
+}
+
+// clusterFromDomain returns the cluster portion of an endpoint domain (every
+// label after the first).
+func clusterFromDomain(domain string) string {
+	if i := strings.IndexByte(domain, '.'); i >= 0 {
+		return domain[i+1:]
+	}
+	return ""
 }
 
 // SynthesizeServices builds the in-memory reverse-proxy service that
@@ -945,7 +944,6 @@ func buildAccountService(
 		Name:         "agent-network-" + accountID,
 		Domain:       domain,
 		ProxyCluster: cluster,
-		DNSZone:      settings.Zone, // empty for legacy rows → unchanged behavior
 		Mode:         rpservice.ModeHTTP,
 		Enabled:      true,
 		Private:      true,

management/internals/modules/agentnetwork/types/settings.go

@@ -18,14 +18,6 @@ type Settings struct {
 	AccountID string `gorm:"primaryKey"`
 	Cluster   string
 	Subdomain string `gorm:"index:idx_agent_network_settings_cluster_subdomain"`
-	// Zone is the placement-independent parent zone the endpoint lives under,
-	// captured from server config when the row is allocated. Immutable, like
-	// Cluster and Subdomain.
-	//
-	// Empty means "legacy": the endpoint falls back to <subdomain>.<cluster>,
-	// which embeds the serving proxy. Existing rows and any deployment that
-	// configures no zone keep that behaviour unchanged.
-	Zone string
 
 	// Account-level collection controls sourced by the synthesizer.
 	// EnableLogCollection gates the per-request access-log trail and defaults
@@ -50,17 +42,9 @@ type Settings struct {
 // schema cohesive.
 func (Settings) TableName() string { return "agent_network_settings" }
 
-// Endpoint returns the bare hostname agents reach this account at.
-//
-// With a Zone set this is `<subdomain>.<zone>` — deliberately independent of
-// which proxy serves the account, so moving between a shared and a private
-// proxy (or between clusters) is a DNS change only and never alters the
-// tenant's address. With no Zone it falls back to the legacy
-// `<subdomain>.<cluster>` form.
+// Endpoint returns the bare hostname agents reach this account at:
+// `<subdomain>.<cluster>`.
 func (s *Settings) Endpoint() string {
-	if s.Zone != "" {
-		return s.Subdomain + "." + s.Zone
-	}
 	return s.Subdomain + "." + s.Cluster
 }
 

management/internals/modules/agentnetwork/types/settings_test.go

@@ -1,31 +0,0 @@
-package types
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-)
-
-// TestEndpoint_PrefersZoneOverCluster locks the decoupling: when a Zone is set
-// the hostname must NOT embed the serving cluster, so moving a tenant between
-// proxies never changes their address.
-func TestEndpoint_PrefersZoneOverCluster(t *testing.T) {
-	s := &Settings{Subdomain: "brave-otter", Cluster: "eu.proxy.netbird.io", Zone: "gateway.netbird.ai"}
-	assert.Equal(t, "brave-otter.gateway.netbird.ai", s.Endpoint())
-}
-
-// TestEndpoint_FallsBackToClusterWhenZoneEmpty is the compatibility guarantee:
-// existing rows (and every self-hosted deployment, which sets no zone) keep
-// exactly the address they have today.
-func TestEndpoint_FallsBackToClusterWhenZoneEmpty(t *testing.T) {
-	s := &Settings{Subdomain: "otter", Cluster: "eu.proxy.netbird.io"}
-	assert.Equal(t, "otter.eu.proxy.netbird.io", s.Endpoint())
-}
-
-// TestToAPIResponse_ExposesZoneAndDerivedEndpoint — the dashboard renders
-// Endpoint verbatim, so it must reflect the zone.
-func TestToAPIResponse_ExposesZoneAndDerivedEndpoint(t *testing.T) {
-	s := &Settings{Subdomain: "brave-otter", Cluster: "eu.proxy.netbird.io", Zone: "gateway.netbird.ai"}
-	resp := s.ToAPIResponse()
-	assert.Equal(t, "brave-otter.gateway.netbird.ai", resp.Endpoint)
-}

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

@@ -255,13 +255,6 @@ type Service struct {
 	Private bool
 	// AccessGroups is the group ID allowlist for inbound peers on private services. Mutually exclusive with bearer SSO.
 	AccessGroups []string `json:"access_groups,omitempty" gorm:"serializer:json"`
-	// DNSZone is the parent zone a private service's synthesized mesh A record
-	// hangs under, for the case where that zone cannot be derived from
-	// ProxyCluster or a validated custom domain — i.e. placement-free
-	// agent-network endpoints, which are <subdomain>.<zone>. In-memory only:
-	// set by the agent-network synthesizer on services it builds per read,
-	// never stored and never exposed on the API or the proxy wire.
-	DNSZone string `gorm:"-" json:"-"`
 }
 
 // InitNewRecord generates a new unique ID and resets metadata for a newly created
@@ -1419,7 +1412,6 @@ func (s *Service) Copy() *Service {
 		PortAutoAssigned:  s.PortAutoAssigned,
 		Private:           s.Private,
 		AccessGroups:      accessGroups,
-		DNSZone:           s.DNSZone,
 	}
 }
 

management/internals/modules/reverseproxy/service/service_test.go

@@ -1215,17 +1215,6 @@ func TestService_Copy_RoundtripsPrivate(t *testing.T) {
 	assert.Equal(t, []string{"grp-admins", "grp-ops"}, svc.AccessGroups)
 }
 
-// TestServiceCopy_PreservesDNSZone — DNSZone is in-memory only, so it is easy
-// to omit from Copy()'s explicit field list; if it is dropped, a copied
-// account silently loses its zone apex and the tenant's endpoint resolves to
-// nothing.
-func TestServiceCopy_PreservesDNSZone(t *testing.T) {
-	svc := &Service{Domain: "brave-otter.gateway.netbird.ai", DNSZone: "gateway.netbird.ai"}
-	cp := svc.Copy()
-	require.NotNil(t, cp)
-	assert.Equal(t, "gateway.netbird.ai", cp.DNSZone)
-}
-
 func TestService_APIRoundtrip_Private(t *testing.T) {
 	enabled := true
 	private := true

management/internals/server/boot.go

@@ -24,13 +24,13 @@ import (
 
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/formatter/hook"
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs"
 	accesslogsmanager "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/accesslogs/manager"
 	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
 	nbgrpc "github.com/netbirdio/netbird/management/internals/shared/grpc"
 	"github.com/netbirdio/netbird/management/server/activity"
 	activitystore "github.com/netbirdio/netbird/management/server/activity/store"
+	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
 	nbcache "github.com/netbirdio/netbird/management/server/cache"
 	nbContext "github.com/netbirdio/netbird/management/server/context"
 	nbhttp "github.com/netbirdio/netbird/management/server/http"
@@ -184,10 +184,6 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
 			grpc.ChainStreamInterceptor(realip.StreamServerInterceptorOpts(realipOpts...), streamInterceptor, proxyStream),
 		}
 
-		// Append interceptors contributed by registered gRPC extensions. These
-		// run after the built-in chain (ChainUnaryInterceptor is additive).
-		gRPCOpts = appendExtensionInterceptors(gRPCOpts, s.grpcExtensions)
-
 		if s.Config.HttpConfig.LetsEncryptDomain != "" {
 			certManager, err := encryption.CreateCertManager(s.Config.Datadir, s.Config.HttpConfig.LetsEncryptDomain)
 			if err != nil {
@@ -219,9 +215,6 @@ func (s *BaseServer) GRPCServer() *grpc.Server {
 		mgmtProto.RegisterProxyServiceServer(gRPCAPIHandler, s.ReverseProxyGRPCServer())
 		log.Info("ProxyService registered on gRPC server")
 
-		// Register services contributed by external modules via the extension seam.
-		registerExtensions(gRPCAPIHandler, s.grpcExtensions)
-
 		return gRPCAPIHandler
 	})
 }

management/internals/server/config/config.go

@@ -204,15 +204,6 @@ type AgentNetwork struct {
 	// prefill with). An explicitly configured path that fails to load
 	// fails startup; runtime reload errors keep the previous table.
 	PricingDefaultsFile string
-
-	// Zone is the parent DNS zone that Agent Network gateway endpoints are
-	// allocated under, producing <subdomain>.<zone>.
-	//
-	// Empty (the default) preserves the legacy behaviour of deriving the
-	// endpoint from the serving cluster, so self-hosted deployments are
-	// unaffected. It is captured onto each settings row when that row is
-	// created; changing it later does not move existing tenants.
-	Zone string
 }
 
 // ReverseProxy contains reverse proxy configuration in front of management.

management/internals/server/grpc_extension.go

@@ -1,74 +0,0 @@
-package server
-
-import (
-	"context"
-
-	"google.golang.org/grpc"
-)
-
-// GRPCExtension bundles an external module's contribution to the management
-// gRPC server: the registration of one or more services onto the shared
-// grpc.Server, any server-wide interceptors those services require, and an
-// optional shutdown hook. It is a generic extension point with no knowledge of
-// any specific service.
-type GRPCExtension struct {
-	// Register is invoked with the shared grpc.Server (as a ServiceRegistrar)
-	// after the built-in services are registered. It may register any number of
-	// services. May be nil.
-	Register func(grpc.ServiceRegistrar)
-	// UnaryInterceptors are appended to the server's unary interceptor chain,
-	// running after the built-in interceptors. May be empty.
-	UnaryInterceptors []grpc.UnaryServerInterceptor
-	// StreamInterceptors are appended to the server's stream interceptor chain,
-	// running after the built-in interceptors. May be empty.
-	StreamInterceptors []grpc.StreamServerInterceptor
-	// Shutdown, if non-nil, is called once during Stop() with the context
-	// governing server shutdown, which carries a deadline. The hook MUST
-	// return promptly and MUST abandon its work once that context is
-	// cancelled or expires: it runs before the rest of Stop()'s cleanup
-	// (store, event store, embedded IdP) and before Stop() itself checks the
-	// context's deadline, so a hook that ignores the context will delay all
-	// of that cleanup and prevent Stop() from returning on time. May be nil.
-	Shutdown func(ctx context.Context)
-}
-
-// RegisterGRPCExtension registers a gRPC extension. Call before the gRPC server
-// is first built (i.e. before Start); registrations after that have no effect.
-func (s *BaseServer) RegisterGRPCExtension(ext GRPCExtension) {
-	s.grpcExtensions = append(s.grpcExtensions, ext)
-}
-
-// appendExtensionInterceptors appends each extension's interceptors to the gRPC
-// server options as additional chained interceptors. grpc.ChainUnaryInterceptor
-// and grpc.ChainStreamInterceptor are additive, so the returned options run the
-// extension interceptors after any interceptors already present in opts.
-func appendExtensionInterceptors(opts []grpc.ServerOption, exts []GRPCExtension) []grpc.ServerOption {
-	for _, ext := range exts {
-		if len(ext.UnaryInterceptors) > 0 {
-			opts = append(opts, grpc.ChainUnaryInterceptor(ext.UnaryInterceptors...))
-		}
-		if len(ext.StreamInterceptors) > 0 {
-			opts = append(opts, grpc.ChainStreamInterceptor(ext.StreamInterceptors...))
-		}
-	}
-	return opts
-}
-
-// registerExtensions registers each extension's services onto reg.
-func registerExtensions(reg grpc.ServiceRegistrar, exts []GRPCExtension) {
-	for _, ext := range exts {
-		if ext.Register != nil {
-			ext.Register(reg)
-		}
-	}
-}
-
-// runExtensionShutdownHooks calls each extension's shutdown hook, if set,
-// passing ctx through so hooks can honor its deadline/cancellation.
-func runExtensionShutdownHooks(ctx context.Context, exts []GRPCExtension) {
-	for _, ext := range exts {
-		if ext.Shutdown != nil {
-			ext.Shutdown(ctx)
-		}
-	}
-}

management/internals/server/grpc_extension_test.go

@@ -1,160 +0,0 @@
-package server
-
-import (
-	"context"
-	"net"
-	"sync/atomic"
-	"testing"
-
-	"google.golang.org/grpc"
-	"google.golang.org/grpc/credentials/insecure"
-	"google.golang.org/grpc/health"
-	healthgrpc "google.golang.org/grpc/health/grpc_health_v1"
-	"google.golang.org/grpc/test/bufconn"
-)
-
-// Test that an extension's interceptors and service registration are actually
-// wired onto a real in-process gRPC server via the helpers, and that shutdown
-// hooks run. This validates the load-bearing assumption that
-// grpc.ChainUnaryInterceptor is additive (extension interceptors run in
-// addition to any base chain).
-func TestGRPCExtensionAppliedToServer(t *testing.T) {
-	var unaryCalls atomic.Int32
-	var streamShutdownCalled atomic.Bool
-
-	ext := GRPCExtension{
-		Register: func(reg grpc.ServiceRegistrar) {
-			healthgrpc.RegisterHealthServer(reg, health.NewServer())
-		},
-		UnaryInterceptors: []grpc.UnaryServerInterceptor{
-			func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
-				unaryCalls.Add(1)
-				return handler(ctx, req)
-			},
-		},
-		Shutdown: func(ctx context.Context) { streamShutdownCalled.Store(true) },
-	}
-	exts := []GRPCExtension{ext}
-
-	// Base options mimic GRPCServer(): a pre-existing chain the extension appends to.
-	var baseUnaryCalls atomic.Int32
-	opts := []grpc.ServerOption{
-		grpc.ChainUnaryInterceptor(func(ctx context.Context, req any, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (any, error) {
-			baseUnaryCalls.Add(1)
-			return handler(ctx, req)
-		}),
-	}
-	opts = appendExtensionInterceptors(opts, exts)
-
-	srv := grpc.NewServer(opts...)
-	registerExtensions(srv, exts)
-
-	lis := bufconn.Listen(1024 * 1024)
-	go func() { _ = srv.Serve(lis) }()
-	t.Cleanup(srv.Stop)
-
-	conn, err := grpc.NewClient("passthrough:///bufnet",
-		grpc.WithContextDialer(func(ctx context.Context, _ string) (net.Conn, error) { return lis.DialContext(ctx) }),
-		grpc.WithTransportCredentials(insecure.NewCredentials()))
-	if err != nil {
-		t.Fatal(err)
-	}
-	t.Cleanup(func() { _ = conn.Close() })
-
-	_, err = healthgrpc.NewHealthClient(conn).Check(context.Background(), &healthgrpc.HealthCheckRequest{})
-	if err != nil {
-		t.Fatalf("health check via extension-registered service failed: %v", err)
-	}
-	if baseUnaryCalls.Load() != 1 {
-		t.Errorf("base interceptor calls = %d, want 1 (base chain must be preserved)", baseUnaryCalls.Load())
-	}
-	if unaryCalls.Load() != 1 {
-		t.Errorf("extension interceptor calls = %d, want 1", unaryCalls.Load())
-	}
-
-	runExtensionShutdownHooks(context.Background(), exts)
-	if !streamShutdownCalled.Load() {
-		t.Error("extension shutdown hook was not called")
-	}
-}
-
-// TestGRPCExtensionShutdownHookReceivesCallerContext asserts that each hook receives
-// a non-nil context and that it is the very same context the caller passed
-// in, so hooks can rely on values/deadlines placed on it by Stop().
-func TestGRPCExtensionShutdownHookReceivesCallerContext(t *testing.T) {
-	type sentinelKey struct{}
-	want := "shutdown-ctx-sentinel"
-	ctx := context.WithValue(context.Background(), sentinelKey{}, want)
-
-	var called bool
-	ext := GRPCExtension{
-		Shutdown: func(hookCtx context.Context) {
-			called = true
-			if hookCtx == nil {
-				t.Fatal("hook received a nil context")
-			}
-			got, _ := hookCtx.Value(sentinelKey{}).(string)
-			if got != want {
-				t.Errorf("hook context sentinel = %q, want %q (not the caller's context)", got, want)
-			}
-		},
-	}
-
-	runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
-	if !called {
-		t.Fatal("shutdown hook was not called")
-	}
-}
-
-// TestGRPCExtensionShutdownHookObservesCancellation documents, by test, that
-// hooks can honor cancellation/deadlines: a hook given an already-cancelled
-// context must see ctx.Err() != nil and a closed Done() channel.
-func TestGRPCExtensionShutdownHookObservesCancellation(t *testing.T) {
-	ctx, cancel := context.WithCancel(context.Background())
-	cancel()
-
-	var called bool
-	ext := GRPCExtension{
-		Shutdown: func(hookCtx context.Context) {
-			called = true
-			if hookCtx.Err() == nil {
-				t.Error("hook context Err() = nil, want non-nil for a cancelled context")
-			}
-			select {
-			case <-hookCtx.Done():
-			default:
-				t.Error("hook context Done() channel is not closed for a cancelled context")
-			}
-		},
-	}
-
-	runExtensionShutdownHooks(ctx, []GRPCExtension{ext})
-	if !called {
-		t.Fatal("shutdown hook was not called")
-	}
-}
-
-// TestGRPCExtensionShutdownHookNilSkipped asserts that an extension
-// with a nil Shutdown hook is skipped without panicking, and that hooks for
-// other extensions still run.
-func TestGRPCExtensionShutdownHookNilSkipped(t *testing.T) {
-	var called atomic.Bool
-	exts := []GRPCExtension{
-		{Shutdown: nil},
-		{Shutdown: func(context.Context) { called.Store(true) }},
-	}
-
-	runExtensionShutdownHooks(context.Background(), exts)
-	if !called.Load() {
-		t.Error("shutdown hook for non-nil extension was not called")
-	}
-}
-
-func TestRegisterGRPCExtensionAccumulates(t *testing.T) {
-	s := &BaseServer{}
-	s.RegisterGRPCExtension(GRPCExtension{})
-	s.RegisterGRPCExtension(GRPCExtension{})
-	if len(s.grpcExtensions) != 2 {
-		t.Fatalf("grpcExtensions len = %d, want 2", len(s.grpcExtensions))
-	}
-}

management/internals/server/modules.go

@@ -202,7 +202,6 @@ func (s *BaseServer) AgentNetworkManager() agentnetwork.Manager {
 			s.PermissionsManager(),
 			s.AccountManager(),
 			s.ServiceProxyController(),
-			s.Config.AgentNetwork.Zone,
 		)
 		// Sweep expired agent-network access logs per account retention,
 		// reusing the reverse-proxy cleanup interval config.

management/internals/server/server.go

@@ -68,11 +68,6 @@ type BaseServer struct {
 
 	proxyAuthClose func()
 
-	// grpcExtensions holds additional gRPC services, interceptors, and shutdown
-	// hooks registered by external modules via RegisterGRPCExtension. Populated
-	// during boot (single-threaded), consumed by GRPCServer() and Stop().
-	grpcExtensions []GRPCExtension
-
 	listener    net.Listener
 	certManager *autocert.Manager
 	update      *version.Update
@@ -262,7 +257,6 @@ func (s *BaseServer) Stop() error {
 		s.proxyAuthClose()
 		s.proxyAuthClose = nil
 	}
-	runExtensionShutdownHooks(ctx, s.grpcExtensions)
 	_ = s.Store().Close(ctx)
 	_ = s.EventStore().Close(ctx)
 	if s.update != nil {

management/internals/shared/grpc/components_encoder.go

@@ -61,8 +61,6 @@ func EncodeNetworkMapEnvelope(in ComponentsEnvelopeInput) *proto.NetworkMapEnvel
 		return &proto.NetworkMapEnvelope{
 			Payload: &proto.NetworkMapEnvelope_Full{
 				Full: &proto.NetworkMapComponentsFull{
-					Serial:     networkSerial(c.Network),
-					Network:    toAccountNetwork(c.Network),
 					PeerConfig: in.PeerConfig,
 					// components.Peers always contains the target peer
 					Peers:            []*proto.PeerCompact{toPeerCompact(c.Peers[c.PeerID])},

management/internals/shared/grpc/components_encoder_test.go

@@ -758,9 +758,6 @@ func TestEncodeNetworkMapEnvelope_NilComponentsGracefulDegrade(t *testing.T) {
 	assert.Equal(t, "netbird.cloud", full.DnsDomain)
 	assert.Len(t, full.Peers, 1)
 	assert.Empty(t, full.Policies)
-	require.NotNil(t, full.Network, "client runs Calculate() over the envelope and dereferences Network unconditionally; a nil here would crash the receiver")
-	assert.Equal(t, "net-empty", full.Network.Identifier)
-	assert.Equal(t, uint64(9), full.Serial)
 }
 
 func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
@@ -779,12 +776,6 @@ func TestEncodeNetworkMapEnvelope_AccountSettingsAlwaysEmitted(t *testing.T) {
 func emptyNetworkMapComponents() *types.NetworkMapComponents {
 	return types.EmptyNetworkMapComponents(
 		&types.NetworkMapComponents{
-			PeerID: "peer-id", Peers: map[string]*types.ComponentPeer{"peer-id": {}},
-			Network: &types.Network{
-				Identifier: "net-empty",
-				Net:        net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)},
-				Serial:     9,
-			},
-		},
+			PeerID: "peer-id", Peers: map[string]*types.ComponentPeer{"peer-id": {}}},
 	)
 }

management/server/agentnetwork_budgetrule_realstack_test.go

@@ -30,7 +30,7 @@ func TestAgentNetwork_BudgetRuleCRUD_RealManager(t *testing.T) {
 	account := newAccountWithId(ctx, accountID, adminUserID, "agent-net.test", "", "", false)
 	require.NoError(t, am.Store.SaveAccount(ctx, account), "SaveAccount must succeed")
 
-	mgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil, "")
+	mgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil)
 
 	created, err := mgr.CreateBudgetRule(ctx, adminUserID, &agenttypes.AccountBudgetRule{
 		AccountID:    accountID,
@@ -82,7 +82,7 @@ func TestAgentNetwork_UpdateSettings_PreservesImmutableAndTogglesCollection(t *t
 	account := newAccountWithId(ctx, accountID, adminUserID, "agent-net.test", "", "", false)
 	require.NoError(t, am.Store.SaveAccount(ctx, account), "SaveAccount must succeed")
 
-	mgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil, "")
+	mgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil)
 
 	// Creating a provider bootstraps the settings row (cluster + subdomain).
 	_, err = mgr.CreateProvider(ctx, adminUserID, &agenttypes.Provider{

management/server/agentnetwork_realstack_test.go

@@ -90,7 +90,7 @@ func TestAgentNetwork_ProviderCRUD_FansOutToProxyAndClientPeers(t *testing.T) {
 	// Real agentnetwork manager wired to the real account manager. proxyController
 	// is nil (no gRPC cluster fan-out here) — the reconcile still fires
 	// UpdateAccountPeers, which is the path under test.
-	agentMgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil, "")
+	agentMgr := agentnetwork.NewManager(am.Store, permissions.NewManager(am.Store), am, nil)
 
 	provider, err := agentMgr.CreateProvider(ctx, adminUserID, &agenttypes.Provider{
 		AccountID:   accountID,

management/server/permissions/manager.go

@@ -82,9 +82,6 @@ func (m *managerImpl) ValidateUserPermissions(
 	return m.ValidateRoleModuleAccess(ctx, accountID, role, module, operation), ctxEnriched, nil
 }
 
-// ValidateRoleModuleAccess resolves an operation against the role's explicit
-// grant for the module, then the grant for its parent module when the module
-// is a dotted submodule, and finally the role's AutoAllowNew default.
 func (m *managerImpl) ValidateRoleModuleAccess(
 	ctx context.Context,
 	accountID string,
@@ -92,7 +89,7 @@ func (m *managerImpl) ValidateRoleModuleAccess(
 	module modules.Module,
 	operation operations.Operation,
 ) bool {
-	if permissions, ok := lookupModulePermissions(role, module); ok {
+	if permissions, ok := role.Permissions[module]; ok {
 		if allowed, exists := permissions[operation]; exists {
 			return allowed
 		}
@@ -103,21 +100,6 @@ func (m *managerImpl) ValidateRoleModuleAccess(
 	return role.AutoAllowNew[operation]
 }
 
-// lookupModulePermissions returns the role's explicit permission set for the
-// module, falling back to the parent module's set for dotted submodules. The
-// second return reports whether any explicit set was found.
-func lookupModulePermissions(role roles.RolePermissions, module modules.Module) (map[operations.Operation]bool, bool) {
-	if permissions, ok := role.Permissions[module]; ok {
-		return permissions, true
-	}
-	if parent, hasParent := module.Parent(); hasParent {
-		if permissions, ok := role.Permissions[parent]; ok {
-			return permissions, true
-		}
-	}
-	return nil, false
-}
-
 func (m *managerImpl) ValidateAccountAccess(ctx context.Context, accountID string, user *types.User, allowOwnerAndAdmin bool) (context.Context, error) {
 	if user.AccountID != accountID {
 		return ctx, status.NewUserNotPartOfAccountError()
@@ -137,7 +119,7 @@ func (m *managerImpl) GetPermissionsByRole(ctx context.Context, role types.UserR
 	permissions := roles.Permissions{}
 
 	for k := range modules.All {
-		if rolePermissions, ok := lookupModulePermissions(roleMap, k); ok {
+		if rolePermissions, ok := roleMap.Permissions[k]; ok {
 			permissions[k] = rolePermissions
 			continue
 		}

management/server/permissions/manager_test.go

@@ -1,139 +0,0 @@
-package permissions
-
-import (
-	"context"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/management/server/permissions/modules"
-	"github.com/netbirdio/netbird/management/server/permissions/operations"
-	"github.com/netbirdio/netbird/management/server/permissions/roles"
-	"github.com/netbirdio/netbird/management/server/types"
-)
-
-func TestValidateRoleModuleAccessSubmoduleCascade(t *testing.T) {
-	manager := NewManager(nil)
-	ctx := context.Background()
-
-	fullAccess := map[operations.Operation]bool{
-		operations.Read:   true,
-		operations.Create: true,
-		operations.Update: true,
-		operations.Delete: true,
-	}
-	readOnly := map[operations.Operation]bool{
-		operations.Read:   true,
-		operations.Create: false,
-		operations.Update: false,
-		operations.Delete: false,
-	}
-	denyAll := map[operations.Operation]bool{
-		operations.Read:   false,
-		operations.Create: false,
-		operations.Update: false,
-		operations.Delete: false,
-	}
-
-	t.Run("parent grant covers submodules", func(t *testing.T) {
-		role := roles.RolePermissions{
-			AutoAllowNew: denyAll,
-			Permissions:  roles.Permissions{modules.AgentNetwork: fullAccess},
-		}
-		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Create),
-			"parent full grant should allow create on a submodule")
-		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
-			"parent full grant should allow read on a submodule")
-	})
-
-	t.Run("submodule grant does not leak to parent or siblings", func(t *testing.T) {
-		role := roles.RolePermissions{
-			AutoAllowNew: denyAll,
-			Permissions:  roles.Permissions{modules.AgentNetworkUsage: readOnly},
-		}
-		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
-			"explicit submodule read should be allowed")
-		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Create),
-			"read-only submodule grant should not allow create")
-		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetwork, operations.Read),
-			"submodule grant should not grant the parent module")
-		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
-			"submodule grant should not grant a sibling submodule")
-	})
-
-	t.Run("explicit submodule entry wins over parent grant", func(t *testing.T) {
-		role := roles.RolePermissions{
-			AutoAllowNew: denyAll,
-			Permissions: roles.Permissions{
-				modules.AgentNetwork:     fullAccess,
-				modules.AgentNetworkLogs: denyAll,
-			},
-		}
-		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkLogs, operations.Read),
-			"explicit submodule deny should override the parent grant")
-		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkUsage, operations.Read),
-			"sibling submodules should still resolve through the parent grant")
-	})
-
-	t.Run("auto allow applies when neither submodule nor parent is granted", func(t *testing.T) {
-		role := roles.RolePermissions{
-			AutoAllowNew: readOnly,
-		}
-		assert.True(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Read),
-			"auto-allow read should apply to submodules")
-		assert.False(t, manager.ValidateRoleModuleAccess(ctx, "account", role, modules.AgentNetworkProviders, operations.Delete),
-			"auto-allow should not grant unlisted operations")
-	})
-}
-
-// TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules pins the behavior the
-// submodule split must not change: every built-in role resolves the new
-// submodules exactly as it resolved the agent_network module before.
-func TestExistingRolesKeepAgentNetworkBehaviorOnSubmodules(t *testing.T) {
-	manager := NewManager(nil)
-	ctx := context.Background()
-
-	submodules := []modules.Module{
-		modules.AgentNetworkProviders,
-		modules.AgentNetworkPolicies,
-		modules.AgentNetworkGuardrails,
-		modules.AgentNetworkBudgets,
-		modules.AgentNetworkUsage,
-		modules.AgentNetworkLogs,
-		modules.AgentNetworkSettings,
-	}
-	allOperations := []operations.Operation{operations.Read, operations.Create, operations.Update, operations.Delete}
-
-	for _, role := range []types.UserRole{types.UserRoleOwner, types.UserRoleAdmin, types.UserRoleAuditor, types.UserRoleNetworkAdmin, types.UserRoleUser} {
-		rolePermissions, ok := roles.RolesMap[role]
-		require.True(t, ok, "role %s must exist in RolesMap", role)
-
-		for _, sub := range submodules {
-			for _, op := range allOperations {
-				expected := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, modules.AgentNetwork, op)
-				actual := manager.ValidateRoleModuleAccess(ctx, "account", rolePermissions, sub, op)
-				assert.Equal(t, expected, actual, "role %s: %s on %s should match the agent_network module", role, op, sub)
-			}
-		}
-	}
-}
-
-func TestGetPermissionsByRoleIncludesSubmodules(t *testing.T) {
-	manager := NewManager(nil)
-	ctx := context.Background()
-
-	permissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAuditor)
-	require.NoError(t, err, "auditor role must resolve")
-
-	usage, ok := permissions[modules.AgentNetworkUsage]
-	require.True(t, ok, "permissions map should contain the usage submodule")
-	assert.True(t, usage[operations.Read], "auditor should read the usage submodule")
-	assert.False(t, usage[operations.Update], "auditor should not update the usage submodule")
-
-	adminPermissions, err := manager.GetPermissionsByRole(ctx, types.UserRoleAdmin)
-	require.NoError(t, err, "admin role must resolve")
-	providers, ok := adminPermissions[modules.AgentNetworkProviders]
-	require.True(t, ok, "permissions map should contain the providers submodule")
-	assert.True(t, providers[operations.Delete], "admin should delete on the providers submodule")
-}

management/server/permissions/modules/module.go

@@ -1,7 +1,5 @@
 package modules
 
-import "strings"
-
 type Module string
 
 const (
@@ -22,17 +20,6 @@ const (
 	IdentityProviders Module = "identity_providers"
 	Services          Module = "services"
 	AgentNetwork      Module = "agent_network"
-
-	// Agent Network submodules. A role may grant one of these directly
-	// or grant the AgentNetwork parent, which covers all of them (see
-	// permissions.Manager cascade resolution).
-	AgentNetworkProviders  Module = "agent_network.providers"
-	AgentNetworkPolicies   Module = "agent_network.policies"
-	AgentNetworkGuardrails Module = "agent_network.guardrails"
-	AgentNetworkBudgets    Module = "agent_network.budgets"
-	AgentNetworkUsage      Module = "agent_network.usage"
-	AgentNetworkLogs       Module = "agent_network.logs"
-	AgentNetworkSettings   Module = "agent_network.settings"
 )
 
 var All = map[Module]struct{}{
@@ -53,21 +40,4 @@ var All = map[Module]struct{}{
 	IdentityProviders: {},
 	Services:          {},
 	AgentNetwork:      {},
-
-	AgentNetworkProviders:  {},
-	AgentNetworkPolicies:   {},
-	AgentNetworkGuardrails: {},
-	AgentNetworkBudgets:    {},
-	AgentNetworkUsage:      {},
-	AgentNetworkLogs:       {},
-	AgentNetworkSettings:   {},
-}
-
-// Parent returns the module owning a dotted submodule name and true, or the
-// module itself and false when it has no parent.
-func (m Module) Parent() (Module, bool) {
-	if i := strings.IndexByte(string(m), '.'); i > 0 {
-		return Module(string(m)[:i]), true
-	}
-	return m, false
 }

management/server/store/sql_store_agentnetwork.go

@@ -334,30 +334,6 @@ func (s *SqlStore) GetAgentNetworkSettingsByCluster(ctx context.Context, lockStr
 	return settings, nil
 }
 
-// GetAgentNetworkSettingsBySubdomain returns the settings row that owns the
-// given subdomain label. The label is globally unique (enforced by
-// idx_agent_network_settings_subdomain_unique), so at most one row can match,
-// which makes this an indexed point lookup rather than a scan.
-func (s *SqlStore) GetAgentNetworkSettingsBySubdomain(ctx context.Context, lockStrength LockingStrength, subdomain string) (*agentNetworkTypes.Settings, error) {
-	tx := s.db
-	if lockStrength != LockingStrengthNone {
-		tx = tx.Clauses(clause.Locking{Strength: string(lockStrength)})
-	}
-
-	var settings agentNetworkTypes.Settings
-	result := tx.Take(&settings, "subdomain = ?", subdomain)
-	if result.Error != nil {
-		if errors.Is(result.Error, gorm.ErrRecordNotFound) {
-			return nil, status.Errorf(status.NotFound, "agent network settings for subdomain %s not found", subdomain)
-		}
-
-		log.WithContext(ctx).Errorf("failed to get agent network settings by subdomain from store: %v", result.Error)
-		return nil, status.Errorf(status.Internal, "failed to get agent network settings by subdomain from store")
-	}
-
-	return &settings, nil
-}
-
 // SaveAgentNetworkSettings upserts the per-account Agent Network
 // settings row.
 func (s *SqlStore) SaveAgentNetworkSettings(ctx context.Context, settings *agentNetworkTypes.Settings) error {
@@ -370,21 +346,6 @@ func (s *SqlStore) SaveAgentNetworkSettings(ctx context.Context, settings *agent
 	return nil
 }
 
-// CreateAgentNetworkSettings inserts a new settings row.
-//
-// Unlike SaveAgentNetworkSettings (an upsert) this is a plain INSERT, and it
-// returns the driver error unwrapped. Both properties are required by the
-// subdomain allocator: it relies on the unique index rejecting a duplicate
-// label, and on being able to recognise that rejection so it can retry with a
-// fresh label instead of surfacing an error.
-func (s *SqlStore) CreateAgentNetworkSettings(ctx context.Context, settings *agentNetworkTypes.Settings) error {
-	if err := s.db.Create(settings).Error; err != nil {
-		log.WithContext(ctx).Debugf("failed to create agent network settings: %v", err)
-		return err
-	}
-	return nil
-}
-
 // IncrementAgentNetworkConsumption atomically upserts the consumption
 // row keyed on (account, dim_kind, dim_id, window_seconds, window_start)
 // and adds the supplied deltas. Concurrent calls from multiple proxy

management/server/store/sql_store_agentnetwork_settings_test.go

@@ -1,77 +0,0 @@
-package store
-
-import (
-	"context"
-	"strings"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	agentNetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-)
-
-// TestAgentNetworkSettings_SubdomainIsGloballyUnique is the guard for the whole
-// allocation scheme: the label is now globally unique rather than per-cluster,
-// and the allocator depends on the DATABASE saying no. Two different accounts on
-// two different clusters must not be able to hold the same subdomain.
-func TestAgentNetworkSettings_SubdomainIsGloballyUnique(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	first := &agentNetworkTypes.Settings{
-		AccountID: "acc-unique-1",
-		Cluster:   "eu.proxy.example",
-		Subdomain: "brave-otter",
-		Zone:      "gateway.example",
-	}
-	require.NoError(t, s.CreateAgentNetworkSettings(ctx, first), "first insert must succeed")
-
-	// Deliberately a different account AND a different cluster: under the old
-	// per-cluster scheme this was legal, and it is exactly what must now fail.
-	second := &agentNetworkTypes.Settings{
-		AccountID: "acc-unique-2",
-		Cluster:   "us.proxy.example",
-		Subdomain: "brave-otter",
-		Zone:      "gateway.example",
-	}
-	err = s.CreateAgentNetworkSettings(ctx, second)
-	require.Error(t, err, "duplicate subdomain must be rejected by the unique index")
-
-	// The allocator recognises conflicts by matching the driver's message, so an
-	// error that does not carry a unique-violation signature is useless to it
-	// even though it is non-nil. These are the three signatures management's
-	// isUniqueConstraintError matches (postgres / mysql / sqlite).
-	msg := err.Error()
-	assert.True(t,
-		strings.Contains(msg, "(SQLSTATE 23505)") ||
-			strings.Contains(msg, "Error 1062 (23000)") ||
-			strings.Contains(msg, "UNIQUE constraint failed"),
-		"error must be the raw driver error, recognisable as a unique violation; got %q", msg)
-}
-
-// TestAgentNetworkSettings_CreateThenReadBack keeps CreateAgentNetworkSettings
-// honest as an insert path: the row it writes must be fully readable, including
-// the new Zone column.
-func TestAgentNetworkSettings_CreateThenReadBack(t *testing.T) {
-	ctx := context.Background()
-	s, cleanup, err := NewTestStoreFromSQL(ctx, "", t.TempDir())
-	require.NoError(t, err, "real sqlite test store must come up")
-	defer cleanup()
-
-	want := &agentNetworkTypes.Settings{
-		AccountID: "acc-readback-1",
-		Cluster:   "eu.proxy.example",
-		Subdomain: "swift-heron",
-		Zone:      "gateway.example",
-	}
-	require.NoError(t, s.CreateAgentNetworkSettings(ctx, want))
-
-	got, err := s.GetAgentNetworkSettings(ctx, LockingStrengthNone, "acc-readback-1")
-	require.NoError(t, err, "the inserted row must be readable")
-	assert.Equal(t, "swift-heron", got.Subdomain)
-	assert.Equal(t, "gateway.example", got.Zone, "the Zone column must round-trip")
-	assert.Equal(t, "swift-heron.gateway.example", got.Endpoint(), "endpoint derives from zone")
-}

management/server/store/store.go

@@ -361,9 +361,7 @@ type Store interface {
 	GetAgentNetworkSettings(ctx context.Context, lockStrength LockingStrength, accountID string) (*agentNetworkTypes.Settings, error)
 	GetAllAgentNetworkSettings(ctx context.Context, lockStrength LockingStrength) ([]*agentNetworkTypes.Settings, error)
 	GetAgentNetworkSettingsByCluster(ctx context.Context, lockStrength LockingStrength, cluster string) ([]*agentNetworkTypes.Settings, error)
-	GetAgentNetworkSettingsBySubdomain(ctx context.Context, lockStrength LockingStrength, subdomain string) (*agentNetworkTypes.Settings, error)
 	SaveAgentNetworkSettings(ctx context.Context, settings *agentNetworkTypes.Settings) error
-	CreateAgentNetworkSettings(ctx context.Context, settings *agentNetworkTypes.Settings) error
 	IncrementAgentNetworkConsumption(ctx context.Context, accountID string, kind agentNetworkTypes.ConsumptionDimension, dimID string, windowSeconds int64, windowStart time.Time, tokensIn, tokensOut int64, costUSD float64) error
 	IncrementAgentNetworkConsumptionBatch(ctx context.Context, accountID string, keys []agentNetworkTypes.ConsumptionKey, tokensIn, tokensOut int64, costUSD float64) error
 	GetAgentNetworkConsumption(ctx context.Context, lockStrength LockingStrength, accountID string, kind agentNetworkTypes.ConsumptionDimension, dimID string, windowSeconds int64, windowStart time.Time) (*agentNetworkTypes.Consumption, error)
@@ -660,28 +658,6 @@ func getMigrationsPostAuto(ctx context.Context) []migrationFunc {
 		func(db *gorm.DB) error {
 			return migration.FoldCostAggregatesIntoBuckets[agentNetworkTypes.AgentNetworkUsage](ctx, db)
 		},
-		func(db *gorm.DB) error {
-			// Enforce globally-unique agent-network subdomains.
-			//
-			// Uniqueness used to be per-cluster and advisory (a pre-read
-			// "taken" set with no DB constraint). Once the endpoint hangs off a
-			// shared zone the label must be unique across that whole zone, and
-			// the allocator depends on the database rejecting duplicates so it
-			// can retry with a fresh label.
-			//
-			// The pre-existing idx_agent_network_settings_cluster_subdomain is
-			// left in place: it is non-unique and indexes subdomain alone
-			// (Cluster carries no tag), so it neither conflicts nor suffices.
-			// It must also stay for a second, load-bearing reason on mysql:
-			// its gorm:"index:" tag on the Subdomain field is what makes gorm
-			// size that column as varchar(191) instead of longtext. mysql
-			// cannot put a longtext column in a unique index at all, so
-			// dropping this "redundant" index as unneeded would silently
-			// break the migration above on that dialect.
-			return migration.CreateIndexIfNotExists[agentNetworkTypes.Settings](
-				ctx, db, "idx_agent_network_settings_subdomain_unique", "subdomain",
-			)
-		},
 	}
 }
 

management/server/store/store_mock.go

@@ -268,20 +268,6 @@ func (mr *MockStoreMockRecorder) CreateAgentNetworkAccessLog(ctx, entry, groups
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateAgentNetworkAccessLog", reflect.TypeOf((*MockStore)(nil).CreateAgentNetworkAccessLog), ctx, entry, groups)
 }
 
-// CreateAgentNetworkSettings mocks base method.
-func (m *MockStore) CreateAgentNetworkSettings(ctx context.Context, settings *types.Settings) error {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "CreateAgentNetworkSettings", ctx, settings)
-	ret0, _ := ret[0].(error)
-	return ret0
-}
-
-// CreateAgentNetworkSettings indicates an expected call of CreateAgentNetworkSettings.
-func (mr *MockStoreMockRecorder) CreateAgentNetworkSettings(ctx, settings interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "CreateAgentNetworkSettings", reflect.TypeOf((*MockStore)(nil).CreateAgentNetworkSettings), ctx, settings)
-}
-
 // CreateAgentNetworkUsage mocks base method.
 func (m *MockStore) CreateAgentNetworkUsage(ctx context.Context, usage *types.AgentNetworkUsage, groups []types.AgentNetworkUsageGroup) error {
 	m.ctrl.T.Helper()
@@ -1716,21 +1702,6 @@ func (mr *MockStoreMockRecorder) GetAgentNetworkSettingsByCluster(ctx, lockStren
 	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAgentNetworkSettingsByCluster", reflect.TypeOf((*MockStore)(nil).GetAgentNetworkSettingsByCluster), ctx, lockStrength, cluster)
 }
 
-// GetAgentNetworkSettingsBySubdomain mocks base method.
-func (m *MockStore) GetAgentNetworkSettingsBySubdomain(ctx context.Context, lockStrength LockingStrength, subdomain string) (*types.Settings, error) {
-	m.ctrl.T.Helper()
-	ret := m.ctrl.Call(m, "GetAgentNetworkSettingsBySubdomain", ctx, lockStrength, subdomain)
-	ret0, _ := ret[0].(*types.Settings)
-	ret1, _ := ret[1].(error)
-	return ret0, ret1
-}
-
-// GetAgentNetworkSettingsBySubdomain indicates an expected call of GetAgentNetworkSettingsBySubdomain.
-func (mr *MockStoreMockRecorder) GetAgentNetworkSettingsBySubdomain(ctx, lockStrength, subdomain interface{}) *gomock.Call {
-	mr.mock.ctrl.T.Helper()
-	return mr.mock.ctrl.RecordCallWithMethodType(mr.mock, "GetAgentNetworkSettingsBySubdomain", reflect.TypeOf((*MockStore)(nil).GetAgentNetworkSettingsBySubdomain), ctx, lockStrength, subdomain)
-}
-
 // GetAgentNetworkUsageRows mocks base method.
 func (m *MockStore) GetAgentNetworkUsageRows(ctx context.Context, lockStrength LockingStrength, accountID string, filter types.AgentNetworkAccessLogFilter) ([]*types.AgentNetworkUsage, error) {
 	m.ctrl.T.Helper()

management/server/types/account.go

@@ -254,7 +254,6 @@ func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZon
 
 	peerGroups := a.GetPeerGroups(peerID)
 	zonesByApex := map[string]*nbdns.CustomZone{}
-	var skippedNoZoneApex []string
 
 	for _, svc := range a.Services {
 		if svc == nil || !svc.Enabled || !svc.Private {
@@ -273,15 +272,6 @@ func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZon
 
 		serviceDomainZone := a.privateServiceDomainZone(svc)
 		if serviceDomainZone == "" {
-			// This service passed every gate above (enabled, private,
-			// AccessGroups, connected proxy peers) and would otherwise have
-			// emitted a record, but its domain matches neither its DNSZone,
-			// its ProxyCluster, nor any validated custom-domain row. Collected
-			// rather than logged here — this runs per peer x per service, and
-			// logging inline here would reintroduce the per-peer noise the
-			// "0 zones" diagnostic below deliberately avoids.
-			skippedNoZoneApex = append(skippedNoZoneApex,
-				fmt.Sprintf("%s(domain=%s cluster=%s dns_zone=%q)", svc.ID, svc.Domain, svc.ProxyCluster, svc.DNSZone))
 			continue
 		}
 
@@ -335,10 +325,6 @@ func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZon
 				svc.ID, svc.Domain, svc.ProxyCluster, len(proxyPeers), skippedDisconnected)
 		}
 	}
-	if len(skippedNoZoneApex) > 0 {
-		log.Debugf("private-zone synth: peer %s account %s skipped %d service(s) with no matching zone apex: %s",
-			peerID, a.Id, len(skippedNoZoneApex), strings.Join(skippedNoZoneApex, ", "))
-	}
 
 	out := make([]nbdns.CustomZone, 0, len(zonesByApex))
 	for _, zone := range zonesByApex {
@@ -358,18 +344,8 @@ func (a *Account) SynthesizePrivateServiceZones(peerID string) []nbdns.CustomZon
 }
 
 // privateServiceDomainZone returns the DNS zone name for the given private service domain by
-// checking its DNSZone, then the proxy cluster domain, then the custom domains.
+// looking at the proxy cluster domain then the custom domains.
 func (a *Account) privateServiceDomainZone(svc *service.Service) string {
-	// Placement-free endpoints (<subdomain>.<zone>) carry their zone
-	// explicitly: it is server config, so it matches neither the serving
-	// proxy's address nor any per-account custom-domain row. Checked first so
-	// the apex stays the zone even once ProxyCluster becomes the tenant
-	// hostname itself (a private managed proxy), which would otherwise make the
-	// apex the full hostname and churn the client's zone set on cutover.
-	if svc.DNSZone != "" && domainFromSuffix(svc.Domain, svc.DNSZone) {
-		return svc.DNSZone
-	}
-
 	if domainFromSuffix(svc.Domain, svc.ProxyCluster) {
 		return svc.ProxyCluster
 	}

management/server/types/account_private_zones_test.go

@@ -423,39 +423,6 @@ func TestSynthesizePrivateServiceZones_MixedClusterCustomAndPublic(t *testing.T)
 		"only the 4 private custom services surface in the custom zone (public one excluded)")
 }
 
-// TestSynthesizePrivateServiceZones_ZoneBasedEndpoint_UsesZoneApex — a
-// zone-based tenant still served by the SHARED proxy has a hostname whose
-// parent is the zone, matching neither ProxyCluster nor any validated
-// custom-domain row. Without DNSZone the apex resolves to "" and the service is
-// skipped entirely, so the tenant's endpoint resolves to nothing.
-func TestSynthesizePrivateServiceZones_ZoneBasedEndpoint_UsesZoneApex(t *testing.T) {
-	account := privateZoneTestAccount(t)
-	svc := account.Services[0]
-	svc.Domain = "brave-otter.gateway.netbird.ai"
-	svc.DNSZone = "gateway.netbird.ai"
-	// ProxyCluster stays the shared cluster address — the pre-private cohort.
-
-	zones := account.SynthesizePrivateServiceZones("user-peer")
-	require.Len(t, zones, 1, "a zone-based endpoint must still produce one zone")
-	assert.Equal(t, "gateway.netbird.ai.", zones[0].Domain, "apex must be the placement-free zone, not the cluster")
-	require.Len(t, zones[0].Records, 1)
-	assert.Equal(t, "brave-otter.gateway.netbird.ai.", zones[0].Records[0].Name)
-	assert.Equal(t, "100.64.0.99", zones[0].Records[0].RData, "still points at the serving proxy peer")
-}
-
-// TestSynthesizePrivateServiceZones_UnvalidatedDomain_StillSkipped locks the
-// scope of the fix: a service matching no cluster suffix, no validated custom
-// domain, AND carrying no DNSZone must keep resolving to nothing. A blanket
-// "use the parent domain" fallback would hand it mesh DNS and bypass domain
-// validation.
-func TestSynthesizePrivateServiceZones_UnvalidatedDomain_StillSkipped(t *testing.T) {
-	account := privateZoneTestAccount(t)
-	account.Services[0].Domain = "api.unvalidated.example.com"
-
-	zones := account.SynthesizePrivateServiceZones("user-peer")
-	assert.Empty(t, zones, "no cluster suffix, no validated Domains row, no DNSZone → no records")
-}
-
 // recordNames returns the record names of a zone for order-independent assertions.
 func recordNames(zone nbdns.CustomZone) []string {
 	names := make([]string, 0, len(zone.Records))

management/server/types/proxy_access_token.go

@@ -68,7 +68,7 @@ type ProxyAccessTokenGenerated struct {
 // CreateNewProxyAccessToken generates a new proxy access token.
 // Returns the token with hashed value stored and plain token for one-time display.
 func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *string, createdBy string) (*ProxyAccessTokenGenerated, error) {
-	hashedToken, plainToken, err := GenerateProxyToken()
+	hashedToken, plainToken, err := generateProxyToken()
 	if err != nil {
 		return nil, err
 	}
@@ -94,10 +94,7 @@ func CreateNewProxyAccessToken(name string, expiresIn time.Duration, accountID *
 	}, nil
 }
 
-// GenerateProxyToken generates a new random proxy token, returning its SHA-256
-// hash (for storage) and the one-time plaintext. Exported so external modules
-// can mint tokens in the canonical proxy-token format.
-func GenerateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
+func generateProxyToken() (HashedProxyToken, PlainProxyToken, error) {
 	secret, err := b.Random(ProxyTokenSecretLength)
 	if err != nil {
 		return "", "", err

management/server/types/proxy_access_token_test.go

@@ -1,7 +1,6 @@
 package types
 
 import (
-	"strings"
 	"testing"
 	"time"
 
@@ -124,22 +123,6 @@ func TestCreateNewProxyAccessToken(t *testing.T) {
 	})
 }
 
-func TestGenerateProxyToken(t *testing.T) {
-	hashed, plain, err := GenerateProxyToken()
-	if err != nil {
-		t.Fatal(err)
-	}
-	if err := plain.Validate(); err != nil {
-		t.Errorf("generated token failed Validate(): %v", err)
-	}
-	if plain.Hash() != hashed {
-		t.Error("returned hashed token does not match Hash(plain)")
-	}
-	if !strings.HasPrefix(string(plain), ProxyTokenPrefix) {
-		t.Errorf("token %q missing prefix %q", plain, ProxyTokenPrefix)
-	}
-}
-
 func TestProxyAccessToken_IsExpired(t *testing.T) {
 	past := time.Now().Add(-1 * time.Hour)
 	future := time.Now().Add(1 * time.Hour)

proxy/internal/middleware/builtin/agentnetwork_chain_integration_test.go

@@ -53,7 +53,7 @@ func newChainIntegration(t *testing.T) *chainIntegrationFixture {
 	require.NoError(t, err)
 	t.Cleanup(cleanUp)
 
-	manager := agentnetwork.NewManager(st, nil, nil, nil, "")
+	manager := agentnetwork.NewManager(st, nil, nil, nil)
 
 	server := &mgmtgrpc.ProxyServiceServer{}
 	server.SetAgentNetworkLimitsService(manager)

proxy/internal/proxy/agent_network_chain_realstack_test.go

@@ -102,7 +102,7 @@ func TestReverseProxy_AgentNetworkRequest_FullChain(t *testing.T) {
 	require.NoError(t, err, "real sqlite test store must come up")
 	t.Cleanup(cleanup)
 
-	anMgr := agentnetwork.NewManager(st, nil, nil, nil, "")
+	anMgr := agentnetwork.NewManager(st, nil, nil, nil)
 	server := &mgmtgrpc.ProxyServiceServer{}
 	server.SetAgentNetworkLimitsService(anMgr)
 

release_files/darwin_pkg/postinstall

@@ -30,23 +30,7 @@ mkdir -p /usr/local/bin/
     $AGENT service install || true
     $AGENT service start || true
 
-    console_user=$(stat -f%Su /dev/console 2>/dev/null)
-    case "$console_user" in
-        ""|root|loginwindow|_mbsetupuser)
-            echo "No active GUI user session (console user: '${console_user:-none}'); skipping UI launch."
-            ;;
-        *)
-            uid=$(id -u "$console_user" 2>/dev/null)
-            if [ -z "$uid" ]; then
-                echo "Could not resolve uid for console user '$console_user'; skipping UI launch."
-            else
-                echo "Launching NetBird UI as console user $console_user (uid $uid)."
-                if ! launchctl asuser "$uid" sudo -u "$console_user" -H open "$APP"; then
-                    echo "Failed to launch NetBird UI; if autostart is enabled it will start at next login."
-                fi
-            fi
-            ;;
-    esac
+    open $APP
 
     echo "Finished Netbird installation successfully"
     exit 0 # all good

shared/management/http/api/openapi.yml

@@ -4607,7 +4607,7 @@ components:
 
     FleetDMMatchAttributes:
       type: object
-      description: Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open-source version. Premium-only attributes are marked accordingly
+      description: Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open source version. Premium-only attributes are marked accordingly
       additionalProperties: false
       properties:
         disk_encryption_enabled:

shared/management/http/api/types.gen.go

@@ -2852,7 +2852,7 @@ type EDRFleetDMRequest struct {
 	// LastSyncedInterval The devices last sync requirement interval in hours. Minimum value is 24 hours
 	LastSyncedInterval int `json:"last_synced_interval"`
 
-	// MatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open-source version. Premium-only attributes are marked accordingly
+	// MatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open source version. Premium-only attributes are marked accordingly
 	MatchAttributes FleetDMMatchAttributes `json:"match_attributes"`
 }
 
@@ -2885,7 +2885,7 @@ type EDRFleetDMResponse struct {
 	// LastSyncedInterval The devices last sync requirement interval in hours.
 	LastSyncedInterval int `json:"last_synced_interval"`
 
-	// MatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open-source version. Premium-only attributes are marked accordingly
+	// MatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open source version. Premium-only attributes are marked accordingly
 	MatchAttributes FleetDMMatchAttributes `json:"match_attributes"`
 
 	// UpdatedAt Timestamp of when the integration was last updated.
@@ -3105,7 +3105,7 @@ type Event struct {
 // EventActivityCode The string code of the activity that occurred during the event
 type EventActivityCode string
 
-// FleetDMMatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open-source version. Premium-only attributes are marked accordingly
+// FleetDMMatchAttributes Attribute conditions to match when approving FleetDM hosts. Most attributes work with FleetDM's free/open source version. Premium-only attributes are marked accordingly
 type FleetDMMatchAttributes struct {
 	// DiskEncryptionEnabled Whether disk encryption (FileVault/BitLocker) must be enabled on the host
 	DiskEncryptionEnabled *bool `json:"disk_encryption_enabled,omitempty"`

shared/management/networkmap/decode.go

@@ -228,17 +228,15 @@ func DecodeEnvelope(env *proto.NetworkMapEnvelope) (*types.NetworkMapComponents,
 	return c, nil
 }
 
-// decodeAccountNetwork never returns nil — Calculate() dereferences
-// c.Network unconditionally, and servers that predate the fix omit the field
-// entirely from the empty-components envelope.
 func decodeAccountNetwork(an *proto.AccountNetwork) *types.Network {
-	n := &types.Network{}
 	if an == nil {
-		return n
+		return nil
+	}
+	n := &types.Network{
+		Identifier: an.Identifier,
+		Dns:        an.Dns,
+		Serial:     an.Serial,
 	}
-	n.Identifier = an.Identifier
-	n.Dns = an.Dns
-	n.Serial = an.Serial
 	if an.NetCidr != "" {
 		if _, ipnet, err := net.ParseCIDR(an.NetCidr); err == nil && ipnet != nil {
 			n.Net = *ipnet

shared/management/networkmap/envelope_test.go

@@ -221,66 +221,6 @@ func TestEnvelopeRoundTrip_AllGroupShortCircuitParity(t *testing.T) {
 		"client-side Calculate must connect the same remote peers as the server")
 }
 
-// TestEnvelopeToNetworkMap_EmptyComponents covers the graceful-degrade path
-// the server takes for a peer that is missing from the account or absent from
-// the validated-peers map. The legacy server short-circuited before
-// Calculate() and shipped a NetworkMap carrying only the account Network; the
-// components path runs Calculate() on the client instead, so the envelope must
-// carry Network or the client panics dereferencing a nil *types.Network.
-func TestEnvelopeToNetworkMap_EmptyComponents(t *testing.T) {
-	localPeerKey := randomWgKey(t)
-	c := types.EmptyNetworkMapComponents(&types.NetworkMapComponents{
-		PeerID: "peer-A",
-		Network: &types.Network{
-			Identifier: "net-empty",
-			Net:        net.IPNet{IP: net.IP{100, 64, 0, 0}, Mask: net.CIDRMask(10, 32)},
-			Serial:     7,
-		},
-		Peers: map[string]*types.ComponentPeer{
-			"peer-A": {ID: "peer-A", Key: localPeerKey, IP: netip.AddrFrom4([4]byte{100, 64, 0, 1})},
-		},
-	})
-
-	envelope := mgmtgrpc.EncodeNetworkMapEnvelope(mgmtgrpc.ComponentsEnvelopeInput{
-		Components: c,
-		DNSDomain:  "netbird.cloud",
-	})
-	require.NotNil(t, envelope.GetFull().Network, "empty envelope must carry the account Network")
-
-	wire, err := goproto.Marshal(envelope)
-	require.NoError(t, err, "marshal envelope")
-	var decoded proto.NetworkMapEnvelope
-	require.NoError(t, goproto.Unmarshal(wire, &decoded), "unmarshal envelope")
-
-	result, err := nbnetworkmap.EnvelopeToNetworkMap(context.Background(), &decoded, localPeerKey, "netbird.cloud")
-	require.NoError(t, err, "EnvelopeToNetworkMap must degrade gracefully on empty components")
-	require.Equal(t, uint64(7), result.NetworkMap.Serial)
-	require.Empty(t, result.NetworkMap.RemotePeers, "unvalidated peer connects to nobody")
-}
-
-// TestEnvelopeToNetworkMap_MissingNetwork simulates a server that omits
-// AccountNetwork from the envelope. Clients must degrade rather than panic, so
-// they survive talking to a management server that predates the encoder fix.
-func TestEnvelopeToNetworkMap_MissingNetwork(t *testing.T) {
-	c, localPeerKey := buildSmokeComponents(t)
-
-	envelope := mgmtgrpc.EncodeNetworkMapEnvelope(mgmtgrpc.ComponentsEnvelopeInput{
-		Components: c,
-		DNSDomain:  "netbird.cloud",
-	})
-	envelope.GetFull().Network = nil
-
-	wire, err := goproto.Marshal(envelope)
-	require.NoError(t, err, "marshal envelope")
-	var decoded proto.NetworkMapEnvelope
-	require.NoError(t, goproto.Unmarshal(wire, &decoded), "unmarshal envelope")
-
-	result, err := nbnetworkmap.EnvelopeToNetworkMap(context.Background(), &decoded, localPeerKey, "netbird.cloud")
-	require.NoError(t, err, "a missing AccountNetwork must not panic the client")
-	require.NotNil(t, result.Components.Network)
-	require.NotEmpty(t, result.NetworkMap.RemotePeers, "the rest of the snapshot stays usable")
-}
-
 // buildSmokeComponents returns a minimal NetworkMapComponents (2 peers, 1
 // group, 1 allow policy) plus the receiving peer's WG public key. Sufficient
 // to validate the encode → marshal → decode → Calculate pipeline produces