Add Linux ARM64 UI build

.github/workflows/test-infrastructure-files.yml

@@ -249,35 +249,78 @@ jobs:
           docker compose exec management ls -l /var/lib/netbird/ | grep -i GeoLite2-City_[0-9]*.mmdb
           docker compose exec management ls -l /var/lib/netbird/ | grep -i geonames_[0-9]*.db
 
-  test-legacy-getting-started-scripts:
+  test-getting-started-script:
     runs-on: ubuntu-latest
     steps:
+      - name: Install jq
+        run: sudo apt-get install -y jq
+
       - name: Checkout code
         uses: actions/checkout@9c091bb21b7c1c1d1991bb908d89e4e9dddfe3e0 # v7.0.0
         with:
           persist-credentials: false
 
-      - name: Verify Dex retirement notice
-        run: |
-          if infrastructure_files/getting-started-with-dex.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Dex installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Dex support is not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/local" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+      - name: run script with Zitadel PostgreSQL
+        run: NETBIRD_DOMAIN=use-ip bash -x infrastructure_files/getting-started-with-zitadel.sh
 
-      - name: Verify Zitadel retirement notice
+      - name: test Caddy file gen postgres
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen postgres
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen postgres
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen postgres
         run: |
-          if bash infrastructure_files/getting-started-with-zitadel.sh >stdout.txt 2>stderr.txt; then
-            echo "Expected the retired Zitadel installer to fail"
-            exit 1
-          fi
-          test ! -s stdout.txt
-          grep -Fq "Zitadel support and existing Zitadel deployments are not deprecated." stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-quickstart" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/identity-providers/zitadel" stderr.txt
-          grep -Fq "https://docs.netbird.io/selfhosted/selfhosted-guide" stderr.txt
-          grep -Fq "removed in NetBird v0.80" stderr.txt
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen postgres
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen postgres
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen postgres
+        run: test -f relay.env
+
+      - name: test zdb.env file gen postgres
+        run: test -f zdb.env
+
+      - name: Postgres run cleanup
+        run: |
+          docker compose down --volumes --rmi all
+          rm -rf docker-compose.yml Caddyfile zitadel.env dashboard.env machinekey/zitadel-admin-sa.token turnserver.conf management.json zdb.env
+
+      - name: run script with Zitadel CockroachDB
+        run: bash -x infrastructure_files/getting-started-with-zitadel.sh
+        env:
+          NETBIRD_DOMAIN: use-ip
+          ZITADEL_DATABASE: cockroach
+
+      - name: test Caddy file gen CockroachDB
+        run: test -f Caddyfile
+
+      - name: test docker-compose file gen CockroachDB
+        run: test -f docker-compose.yml
+
+      - name: test management.json file gen CockroachDB
+        run: test -f management.json
+
+      - name: test turnserver.conf file gen CockroachDB
+        run: |
+          set -x
+          test -f turnserver.conf
+          grep external-ip turnserver.conf
+
+      - name: test zitadel.env file gen CockroachDB
+        run: test -f zitadel.env
+
+      - name: test dashboard.env file gen CockroachDB
+        run: test -f dashboard.env
+
+      - name: test relay.env file gen CockroachDB
+        run: test -f relay.env

.goreleaser_ui.yaml

@@ -21,11 +21,10 @@ builds:
       - linux
     goarch:
       - amd64
+      - arm64
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-amd64
     dir: client/ui
@@ -41,8 +40,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
   - id: netbird-ui-windows-arm64
     dir: client/ui
@@ -59,8 +56,6 @@ builds:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
       - -H windowsgui
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 archives:
   - id: linux-arch

.goreleaser_ui_darwin.yaml

@@ -29,8 +29,6 @@ builds:
     ldflags:
       - -s -w -X github.com/netbirdio/netbird/version.version={{.Version}} -X main.commit={{.Commit}} -X main.date={{.CommitDate}} -X main.builtBy=goreleaser
     mod_timestamp: "{{ .CommitTimestamp }}"
-    tags:
-      - production
 
 universal_binaries:
   - id: netbird-ui-darwin

client/android/client.go

@@ -7,7 +7,6 @@ import (
 	"fmt"
 	"os"
 	"slices"
-	"strings"
 	"sync"
 	"time"
 
@@ -300,13 +299,6 @@ func (c *Client) SetInfoLogLevel() {
 // PeersList return with the list of the PeerInfos
 func (c *Client) PeersList() *PeerInfoArray {
 
-	// The recorder only caches transfer counters and handshake times; nothing
-	// refreshes them on its own, so without this they read as zero. The desktop
-	// daemon does the same before serving a full peer status.
-	if err := c.recorder.RefreshWireGuardStats(); err != nil {
-		log.Debugf("failed to refresh WireGuard stats: %v", err)
-	}
-
 	fullStatus := c.recorder.GetFullStatus()
 
 	peerInfos := make([]PeerInfo, len(fullStatus.Peers))
@@ -317,20 +309,6 @@ func (c *Client) PeersList() *PeerInfoArray {
 			FQDN:       p.FQDN,
 			ConnStatus: int(p.ConnStatus),
 			Routes:     PeerRoutes{routes: maps.Keys(p.GetRoutes())},
-
-			PubKey:                     p.PubKey,
-			Latency:                    formatDuration(p.Latency),
-			LatencyMs:                  p.Latency.Milliseconds(),
-			BytesRx:                    p.BytesRx,
-			BytesTx:                    p.BytesTx,
-			ConnStatusUpdate:           formatTime(p.ConnStatusUpdate),
-			Relayed:                    p.Relayed,
-			RosenpassEnabled:           p.RosenpassEnabled,
-			LastWireguardHandshake:     formatTime(p.LastWireguardHandshake),
-			LocalIceCandidateType:      p.LocalIceCandidateType,
-			RemoteIceCandidateType:     p.RemoteIceCandidateType,
-			LocalIceCandidateEndpoint:  p.LocalIceCandidateEndpoint,
-			RemoteIceCandidateEndpoint: p.RemoteIceCandidateEndpoint,
 		}
 		peerInfos[n] = pi
 	}
@@ -461,6 +439,10 @@ func (c *Client) RemoveConnectionListener() {
 	c.recorder.RemoveConnectionListener()
 }
 
+func (c *Client) toggleRoute(command routeCommand) error {
+	return command.toggleRoute()
+}
+
 func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	client := c.getConnectClient()
 	if client == nil {
@@ -480,22 +462,22 @@ func (c *Client) getRouteManager() (routemanager.Manager, error) {
 	return manager, nil
 }
 
-func (c *Client) SelectRoute(id string) error {
+func (c *Client) SelectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.SelectRoutes([]route.NetID{route.NetID(id)}, true)
+	return c.toggleRoute(selectRouteCommand{route: route, manager: manager})
 }
 
-func (c *Client) DeselectRoute(id string) error {
+func (c *Client) DeselectRoute(route string) error {
 	manager, err := c.getRouteManager()
 	if err != nil {
 		return err
 	}
 
-	return manager.DeselectRoutes([]route.NetID{route.NetID(id)})
+	return c.toggleRoute(deselectRouteCommand{route: route, manager: manager})
 }
 
 // getNetworkDomainsFromRoute extracts domains from a route and enriches each domain
@@ -530,28 +512,3 @@ func exportEnvList(list *EnvList) {
 		}
 	}
 }
-
-// formatDuration renders a duration for display, trimming the fractional part
-// to two digits so latencies read as "12.34ms" rather than "12.345678ms".
-func formatDuration(d time.Duration) string {
-	ds := d.String()
-	dotIndex := strings.Index(ds, ".")
-	if dotIndex == -1 {
-		return ds
-	}
-
-	endIndex := min(dotIndex+3, len(ds))
-
-	// Skip the remaining digits so only the unit suffix is appended back.
-	unitStart := endIndex
-	for unitStart < len(ds) && ds[unitStart] >= '0' && ds[unitStart] <= '9' {
-		unitStart++
-	}
-	return ds[:endIndex] + ds[unitStart:]
-}
-
-// formatTime renders a timestamp in UTC using a fixed layout. The zero time is
-// passed through as-is so the UI can recognise it and show "never" instead.
-func formatTime(t time.Time) string {
-	return t.UTC().Format("2006-01-02 15:04:05")
-}

client/android/peer_notifier.go

@@ -12,30 +12,12 @@ const (
 )
 
 // PeerInfo describe information about the peers. It designed for the UI usage
-//
-// The fields below ConnStatus back the peer detail screen. Durations and times
-// are pre-formatted into strings so the UI does not have to know Go's layouts;
-// Latency is additionally exposed as LatencyMs for colour coding.
 type PeerInfo struct {
 	IP         string
 	IPv6       string
 	FQDN       string
 	ConnStatus int
 	Routes     PeerRoutes
-
-	PubKey                     string
-	Latency                    string
-	LatencyMs                  int64
-	BytesRx                    int64
-	BytesTx                    int64
-	ConnStatusUpdate           string
-	Relayed                    bool
-	RosenpassEnabled           bool
-	LastWireguardHandshake     string
-	LocalIceCandidateType      string
-	RemoteIceCandidateType     string
-	LocalIceCandidateEndpoint  string
-	RemoteIceCandidateEndpoint string
 }
 
 func (p *PeerInfo) GetPeerRoutes() *PeerRoutes {

client/android/profile_manager.go

@@ -189,19 +189,6 @@ func (pm *ProfileManager) LogoutProfile(id string) error {
 	return nil
 }
 
-// RenameProfile changes a profile's display name. The profile ID, and therefore
-// its on-disk filename, is left untouched: only the "name" field of the config
-// is rewritten. This works for the default profile too, whose config lives in
-// netbird.cfg rather than under profiles/.
-func (pm *ProfileManager) RenameProfile(id string, newName string) error {
-	if err := pm.serviceMgr.RenameProfile(profilemanager.ID(id), androidUsername, newName); err != nil {
-		return fmt.Errorf("failed to rename profile: %w", err)
-	}
-
-	log.Infof("renamed profile %s to: %s", id, newName)
-	return nil
-}
-
 // RemoveProfile deletes a profile
 func (pm *ProfileManager) RemoveProfile(id string) error {
 	// Use ServiceManager (removes profile from profiles/ directory)

client/android/route_command.go

@@ -0,0 +1,70 @@
+//go:build android
+
+package android
+
+import (
+	"fmt"
+
+	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
+
+	"github.com/netbirdio/netbird/client/internal/routemanager"
+	"github.com/netbirdio/netbird/route"
+)
+
+func executeRouteToggle(id string, manager routemanager.Manager,
+	operationName string,
+	routeOperation func(routes []route.NetID, allRoutes []route.NetID) error) error {
+	netID := route.NetID(id)
+	routes := []route.NetID{netID}
+
+	routesMap := manager.GetClientRoutesWithNetID()
+	routes = route.ExpandV6ExitPairs(routes, routesMap)
+
+	log.Debugf("%s with ids: %v", operationName, routes)
+
+	if err := routeOperation(routes, maps.Keys(routesMap)); err != nil {
+		log.Debugf("error when %s: %s", operationName, err)
+		return fmt.Errorf("error %s: %w", operationName, err)
+	}
+
+	manager.TriggerSelection(manager.GetClientRoutes())
+
+	return nil
+}
+
+type routeCommand interface {
+	toggleRoute() error
+}
+
+type selectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (s selectRouteCommand) toggleRoute() error {
+	routeSelector := s.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	routeOperation := func(routes []route.NetID, allRoutes []route.NetID) error {
+		return routeSelector.SelectRoutes(routes, true, allRoutes)
+	}
+
+	return executeRouteToggle(s.route, s.manager, "selecting route", routeOperation)
+}
+
+type deselectRouteCommand struct {
+	route   string
+	manager routemanager.Manager
+}
+
+func (d deselectRouteCommand) toggleRoute() error {
+	routeSelector := d.manager.GetRouteSelector()
+	if routeSelector == nil {
+		return fmt.Errorf("no route selector available")
+	}
+
+	return executeRouteToggle(d.route, d.manager, "deselecting route", routeSelector.DeselectRoutes)
+}

client/internal/conn_mgr.go

@@ -385,20 +385,11 @@ func inactivityThresholdEnv() *time.Duration {
 		return nil
 	}
 
-	// Documented format: a Go duration such as "30m" or "1h".
-	if d, err := time.ParseDuration(envValue); err == nil {
-		if d <= 0 {
-			return nil
-		}
-		return &d
+	parsedMinutes, err := strconv.Atoi(envValue)
+	if err != nil || parsedMinutes <= 0 {
+		return nil
 	}
 
-	// Backwards compatibility: a bare integer used to be interpreted as minutes.
-	if parsedMinutes, err := strconv.Atoi(envValue); err == nil && parsedMinutes > 0 {
-		d := time.Duration(parsedMinutes) * time.Minute
-		return &d
-	}
-
-	log.Warnf("invalid %s value %q: expected a Go duration such as 30m or 1h", lazyconn.EnvInactivityThreshold, envValue)
-	return nil
+	d := time.Duration(parsedMinutes) * time.Minute
+	return &d
 }

client/internal/conn_mgr_test.go

@@ -104,38 +104,3 @@ func TestConnMgr_ActivatePeerConcurrentWithLifecycle(t *testing.T) {
 	close(done)
 	wg.Wait()
 }
-
-func TestInactivityThresholdEnv(t *testing.T) {
-	tests := []struct {
-		name string
-		val  string
-		want *time.Duration
-	}{
-		{name: "unset", val: "", want: nil},
-		{name: "go duration minutes", val: "30m", want: durPtr(30 * time.Minute)},
-		{name: "go duration hours", val: "1h", want: durPtr(time.Hour)},
-		{name: "go duration seconds", val: "90s", want: durPtr(90 * time.Second)},
-		{name: "bare integer is minutes (backwards compat)", val: "5", want: durPtr(5 * time.Minute)},
-		{name: "zero duration", val: "0s", want: nil},
-		{name: "zero integer", val: "0", want: nil},
-		{name: "negative duration", val: "-5m", want: nil},
-		{name: "garbage", val: "abc", want: nil},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			t.Setenv(lazyconn.EnvInactivityThreshold, tc.val)
-			got := inactivityThresholdEnv()
-			switch {
-			case tc.want == nil && got != nil:
-				t.Fatalf("want nil, got %v", *got)
-			case tc.want != nil && got == nil:
-				t.Fatalf("want %v, got nil", *tc.want)
-			case tc.want != nil && *got != *tc.want:
-				t.Fatalf("want %v, got %v", *tc.want, *got)
-			}
-		})
-	}
-}
-
-func durPtr(d time.Duration) *time.Duration { return &d }

client/internal/connect.go

@@ -34,7 +34,6 @@ import (
 	"github.com/netbirdio/netbird/client/internal/profilemanager"
 	"github.com/netbirdio/netbird/client/internal/statemanager"
 	"github.com/netbirdio/netbird/client/internal/stdnet"
-	"github.com/netbirdio/netbird/client/internal/tunnelnotifier"
 	"github.com/netbirdio/netbird/client/internal/updater"
 	"github.com/netbirdio/netbird/client/internal/updater/installer"
 	nbnet "github.com/netbirdio/netbird/client/net"
@@ -137,13 +136,10 @@ func (c *ConnectClient) RunOniOS(
 	// Set GC percent to 5% to reduce memory usage as iOS only allows 50MB of memory for the extension.
 	debug.SetGCPercent(5)
 
-	notifier := tunnelnotifier.New(networkChangeListener, dnsManager)
-	defer notifier.Close()
-
 	mobileDependency := MobileDependency{
 		FileDescriptor:        fileDescriptor,
-		NetworkChangeListener: notifier,
-		DnsManager:            notifier,
+		NetworkChangeListener: networkChangeListener,
+		DnsManager:            dnsManager,
 		StateFilePath:         stateFilePath,
 		TempDir:               cacheDir,
 	}

client/internal/mobile_dependency.go

@@ -11,14 +11,12 @@ import (
 
 // MobileDependency collect all dependencies for mobile platform
 type MobileDependency struct {
-	// Android and iOS
-	NetworkChangeListener listener.NetworkChangeListener
-
 	// Android only
-	TunAdapter       device.TunAdapter
-	IFaceDiscover    stdnet.ExternalIFaceDiscover
-	HostDNSAddresses []netip.AddrPort
-	DnsReadyListener dns.ReadyListener
+	TunAdapter            device.TunAdapter
+	IFaceDiscover         stdnet.ExternalIFaceDiscover
+	NetworkChangeListener listener.NetworkChangeListener
+	HostDNSAddresses      []netip.AddrPort
+	DnsReadyListener      dns.ReadyListener
 
 	//	iOS only
 	DnsManager     dns.IosDnsManager

client/internal/routemanager/dnsinterceptor/handler.go

@@ -95,7 +95,7 @@ func (d *DnsInterceptor) RemoveRoute() error {
 
 			// AllowedIPs should use real IPs
 			if d.currentPeerKey != "" {
-				if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+				if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 					merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 				}
 			}
@@ -172,7 +172,7 @@ func (d *DnsInterceptor) removeAllowedIP(realPrefix netip.Prefix) error {
 	}
 
 	// AllowedIPs use real IPs
-	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix, d.currentPeerKey); err != nil {
+	if _, err := d.allowedIPsRefcounter.Decrement(realPrefix); err != nil {
 		return fmt.Errorf("remove allowed IP %s: %v", realPrefix, err)
 	}
 
@@ -205,7 +205,7 @@ func (d *DnsInterceptor) RemoveAllowedIPs() error {
 	for _, prefixes := range d.interceptedDomains {
 		for _, prefix := range prefixes {
 			// AllowedIPs use real IPs
-			if _, err := d.allowedIPsRefcounter.Decrement(prefix, d.currentPeerKey); err != nil {
+			if _, err := d.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %v", prefix, err))
 			}
 		}

client/internal/routemanager/dynamic/route.go

@@ -135,7 +135,7 @@ func (r *Route) RemoveAllowedIPs() error {
 	var merr *multierror.Error
 	for _, domainPrefixes := range r.dynamicDomains {
 		for _, prefix := range domainPrefixes {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}
@@ -320,7 +320,7 @@ func (r *Route) removeRoutes(prefixes []netip.Prefix) ([]netip.Prefix, error) {
 			merr = multierror.Append(merr, fmt.Errorf("remove dynamic route for IP %s: %w", prefix, err))
 		}
 		if r.currentPeerKey != "" {
-			if _, err := r.allowedIPsRefcounter.Decrement(prefix, r.currentPeerKey); err != nil {
+			if _, err := r.allowedIPsRefcounter.Decrement(prefix); err != nil {
 				merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %s: %w", prefix, err))
 			}
 		}

client/internal/routemanager/manager.go

@@ -52,10 +52,6 @@ type Manager interface {
 	UpdateRoutes(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	ClassifyRoutes(newRoutes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	TriggerSelection(route.HAMap)
-	SelectRoutes(ids []route.NetID, appendRoute bool) error
-	DeselectRoutes(ids []route.NetID) error
-	SelectAllRoutes()
-	DeselectAllRoutes()
 	GetRouteSelector() *routeselector.RouteSelector
 	GetClientRoutes() route.HAMap
 	GetSelectedClientRoutes() route.HAMap
@@ -220,7 +216,7 @@ func (m *DefaultManager) setupRefCounters(useNoop bool) {
 		)
 	}
 
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New(
 		func(prefix netip.Prefix, peerKey string) (string, error) {
 			// save peerKey to use it in the remove function
 			return peerKey, m.wgInterface.AddAllowedIP(peerKey, prefix)
@@ -804,7 +800,7 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	var info exitNodeInfo
 
 	for haID, routes := range clientRoutes {
-		if !isExitNodeRoutes(routes) {
+		if !m.isExitNodeRoute(routes) {
 			continue
 		}
 
@@ -824,6 +820,13 @@ func (m *DefaultManager) collectExitNodeInfo(clientRoutes route.HAMap) exitNodeI
 	return info
 }
 
+func (m *DefaultManager) isExitNodeRoute(routes []*route.Route) bool {
+	if len(routes) == 0 {
+		return false
+	}
+	return route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network)
+}
+
 func (m *DefaultManager) categorizeUserSelection(netID route.NetID, info *exitNodeInfo) {
 	if m.routeSelector.IsSelected(netID) {
 		info.userSelected = append(info.userSelected, netID)

client/internal/routemanager/mock.go

@@ -16,8 +16,6 @@ type MockManager struct {
 	ClassifyRoutesFunc           func(routes []*route.Route) (map[route.ID]*route.Route, route.HAMap)
 	UpdateRoutesFunc             func(updateSerial uint64, serverRoutes map[route.ID]*route.Route, clientRoutes route.HAMap, useNewDNSRoute bool) error
 	TriggerSelectionFunc         func(haMap route.HAMap)
-	SelectRoutesFunc             func(ids []route.NetID, appendRoute bool) error
-	DeselectRoutesFunc           func(ids []route.NetID) error
 	GetRouteSelectorFunc         func() *routeselector.RouteSelector
 	GetClientRoutesFunc          func() route.HAMap
 	GetSelectedClientRoutesFunc  func() route.HAMap
@@ -57,30 +55,6 @@ func (m *MockManager) TriggerSelection(networks route.HAMap) {
 	}
 }
 
-// SelectRoutes mock implementation of SelectRoutes from Manager interface
-func (m *MockManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if m.SelectRoutesFunc != nil {
-		return m.SelectRoutesFunc(ids, appendRoute)
-	}
-	return nil
-}
-
-// DeselectRoutes mock implementation of DeselectRoutes from Manager interface
-func (m *MockManager) DeselectRoutes(ids []route.NetID) error {
-	if m.DeselectRoutesFunc != nil {
-		return m.DeselectRoutesFunc(ids)
-	}
-	return nil
-}
-
-// SelectAllRoutes mock implementation of SelectAllRoutes from Manager interface
-func (m *MockManager) SelectAllRoutes() {
-}
-
-// DeselectAllRoutes mock implementation of DeselectAllRoutes from Manager interface
-func (m *MockManager) DeselectAllRoutes() {
-}
-
 // GetRouteSelector mock implementation of GetRouteSelector from Manager interface
 func (m *MockManager) GetRouteSelector() *routeselector.RouteSelector {
 	if m.GetRouteSelectorFunc != nil {

client/internal/routemanager/notifier/notifier_ios.go

@@ -3,6 +3,7 @@
 package notifier
 
 import (
+	"container/list"
 	"net/netip"
 	"slices"
 	"sort"
@@ -15,12 +16,20 @@ import (
 
 type Notifier struct {
 	mu              sync.Mutex
+	cond            *sync.Cond
 	currentPrefixes []string
 	listener        listener.NetworkChangeListener
+	queue           *list.List
+	closed          bool
 }
 
 func NewNotifier() *Notifier {
-	return &Notifier{}
+	n := &Notifier{
+		queue: list.New(),
+	}
+	n.cond = sync.NewCond(&n.mu)
+	go n.deliverLoop()
+	return n
 }
 
 func (n *Notifier) SetListener(listener listener.NetworkChangeListener) {
@@ -50,19 +59,44 @@ func (n *Notifier) OnNewPrefixes(prefixes []netip.Prefix) {
 	sort.Strings(newNets)
 
 	n.mu.Lock()
-	defer n.mu.Unlock()
 	if slices.Equal(n.currentPrefixes, newNets) {
+		n.mu.Unlock()
 		return
 	}
 	n.currentPrefixes = newNets
-	if n.listener != nil {
-		n.listener.OnNetworkChanged(strings.Join(n.currentPrefixes, ","))
-	}
+	routes := strings.Join(n.currentPrefixes, ",")
+	n.queue.PushBack(routes)
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) Close() {
+	n.mu.Lock()
+	n.closed = true
+	n.cond.Signal()
+	n.mu.Unlock()
 }
 
 func (n *Notifier) GetInitialRouteRanges() []string {
 	return nil
 }
+
+func (n *Notifier) deliverLoop() {
+	for {
+		n.mu.Lock()
+		for n.queue.Len() == 0 && !n.closed {
+			n.cond.Wait()
+		}
+		if n.closed && n.queue.Len() == 0 {
+			n.mu.Unlock()
+			return
+		}
+		routes := n.queue.Remove(n.queue.Front()).(string)
+		l := n.listener
+		n.mu.Unlock()
+
+		if l != nil {
+			l.OnNetworkChanged(routes)
+		}
+	}
+}

client/internal/routemanager/reconcile_test.go

@@ -54,7 +54,7 @@ func (m *reconcileWGMock) GetNet() *netstack.Net                      { return n
 func TestReconcilePeerAllowedIPs(t *testing.T) {
 	wg := &reconcileWGMock{}
 	m := &DefaultManager{wgInterface: wg}
-	m.allowedIPsRefCounter = refcounter.NewAllowedIPs(
+	m.allowedIPsRefCounter = refcounter.New[netip.Prefix, string, string](
 		func(_ netip.Prefix, peerKey string) (string, error) { return peerKey, nil },
 		func(netip.Prefix, string) error { return nil },
 	)

client/internal/routemanager/refcounter/allowedips.go

@@ -1,206 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"fmt"
-	"net/netip"
-	"sort"
-	"sync"
-
-	"github.com/hashicorp/go-multierror"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-)
-
-// allowedIPsEntry holds the per-peer reference counts for a single prefix and which peer is
-// currently installed in WireGuard. WireGuard allows a prefix on exactly one peer, so at most
-// one peer is active at a time even when several peers reference the prefix.
-type allowedIPsEntry struct {
-	// peers maps a peerKey to the number of references holding the prefix for that peer.
-	peers map[string]int
-	// active is the peerKey currently installed in WireGuard for this prefix ("" if none).
-	active string
-	// total is the sum of all per-peer reference counts (kept in sync with peers).
-	total int
-}
-
-// AllowedIPsRefCounter is a peer-aware reference counter for WireGuard AllowedIPs.
-//
-// The generic Counter keys only by prefix and remembers a single Out value set by the first
-// caller, which it never changes. That is wrong for AllowedIPs: two independent watchers (or
-// multiple resolved domains) can reference the same prefix through different peers, and when the
-// peer currently installed in WireGuard releases its last reference the prefix must be handed over
-// to a surviving peer instead of being left pointing at the released one.
-//
-// It calls add/remove (which program WireGuard) only on the transitions that matter:
-//   - add on the first reference for a prefix, or when swapping the active peer;
-//   - remove on the last reference for a prefix, or on the old peer during a swap.
-type AllowedIPsRefCounter struct {
-	mu      sync.Mutex
-	entries map[netip.Prefix]*allowedIPsEntry
-	add     AddFunc[netip.Prefix, string, string]
-	remove  RemoveFunc[netip.Prefix, string]
-}
-
-// NewAllowedIPs creates a new peer-aware AllowedIPs reference counter.
-// add programs a prefix on a peer in WireGuard and returns the peerKey to store as the active peer.
-// remove unprograms the prefix from the given peer.
-func NewAllowedIPs(add AddFunc[netip.Prefix, string, string], remove RemoveFunc[netip.Prefix, string]) *AllowedIPsRefCounter {
-	return &AllowedIPsRefCounter{
-		entries: map[netip.Prefix]*allowedIPsEntry{},
-		add:     add,
-		remove:  remove,
-	}
-}
-
-// Increment adds a reference to prefix for peerKey. WireGuard is programmed only for the first
-// reference to a prefix; while a different peer is already installed the prefix is left with it
-// (first peer wins, HA at the WireGuard layer is not possible) and only the reference count is kept.
-func (rm *AllowedIPsRefCounter) Increment(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		e = &allowedIPsEntry{peers: map[string]int{}}
-		rm.entries[prefix] = e
-	}
-
-	logCallerF("Increasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-		prefix, peerKey, e.peers[peerKey], e.peers[peerKey]+1, e.total, e.total+1, e.active)
-
-	// Program WireGuard only when nothing is installed yet for this prefix.
-	if e.active == "" {
-		out, err := rm.add(prefix, peerKey)
-		if errors.Is(err, ErrIgnore) {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{Count: e.total, Out: e.active}, nil
-		}
-		if err != nil {
-			if e.total == 0 {
-				delete(rm.entries, prefix)
-			}
-			return Ref[string]{}, fmt.Errorf("failed to add allowed IP %v for peer %s: %w", prefix, peerKey, err)
-		}
-		e.active = out
-	}
-
-	e.peers[peerKey]++
-	e.total++
-
-	return Ref[string]{Count: e.total, Out: e.active}, nil
-}
-
-// Decrement removes a reference to prefix for peerKey. When the peer currently installed in
-// WireGuard releases its last reference, the prefix is swapped to a surviving peer if one exists,
-// otherwise it is removed from WireGuard.
-func (rm *AllowedIPsRefCounter) Decrement(prefix netip.Prefix, peerKey string) (Ref[string], error) {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	e, ok := rm.entries[prefix]
-	if !ok {
-		logCallerF("No allowed IP reference found for prefix %v", prefix)
-		return Ref[string]{}, nil
-	}
-
-	if e.peers[peerKey] > 0 {
-		logCallerF("Decreasing allowed IP ref count for prefix %v peer %s [peer %d -> %d, total %d -> %d, active %q]",
-			prefix, peerKey, e.peers[peerKey], e.peers[peerKey]-1, e.total, e.total-1, e.active)
-		e.peers[peerKey]--
-		e.total--
-		if e.peers[peerKey] == 0 {
-			delete(e.peers, peerKey)
-		}
-	} else {
-		logCallerF("No allowed IP reference found for prefix %v peer %s", prefix, peerKey)
-	}
-
-	// If the peer currently installed in WireGuard still holds references, nothing to reprogram.
-	// Keying the check on the active peer (not the one just released) makes this self-healing:
-	// a prior swap whose remove/add failed leaves e.active pointing at a peer with no references,
-	// and this retries the hand-off on the next Decrement instead of getting stuck.
-	if e.active != "" && e.peers[e.active] > 0 {
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	// Detach the stale/gone active peer from WireGuard before reprogramming.
-	if e.active != "" {
-		if err := rm.remove(prefix, e.active); err != nil {
-			return Ref[string]{Count: e.total, Out: e.active}, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err)
-		}
-		e.active = ""
-	}
-
-	// Hand the prefix over to a surviving peer, or drop the entry when none remain.
-	if survivor, ok := pickSurvivor(e.peers); ok {
-		out, err := rm.add(prefix, survivor)
-		if err != nil {
-			return Ref[string]{Count: e.total, Out: ""}, fmt.Errorf("swap allowed IP %v to peer %s: %w", prefix, survivor, err)
-		}
-		e.active = out
-		return Ref[string]{Count: e.total, Out: e.active}, nil
-	}
-
-	delete(rm.entries, prefix)
-	return Ref[string]{Count: 0, Out: ""}, nil
-}
-
-// Flush removes all prefixes from WireGuard and clears the counter.
-func (rm *AllowedIPsRefCounter) Flush() error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active == "" {
-			continue
-		}
-		logCallerF("Flushing allowed IP for prefix %v peer %s", prefix, e.active)
-		if err := rm.remove(prefix, e.active); err != nil {
-			merr = multierror.Append(merr, fmt.Errorf("remove allowed IP %v for peer %s: %w", prefix, e.active, err))
-		}
-	}
-
-	clear(rm.entries)
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// ReapplyMatching calls apply for every prefix whose currently installed (active) peer satisfies
-// pred, holding the lock for the whole pass. It is used to re-push allowed IPs onto a peer whose
-// WireGuard entry was rebuilt (e.g. a lazy connection cycling idle->wake) without a matching
-// refcounter change, which would otherwise leave the prefix installed in the counter but missing
-// on the device. Only the active peer is considered — a prefix that lost its installed peer to a
-// failed swap is skipped here and reconciled by the next Increment/Decrement.
-func (rm *AllowedIPsRefCounter) ReapplyMatching(pred func(out string) bool, apply func(key netip.Prefix) error) error {
-	rm.mu.Lock()
-	defer rm.mu.Unlock()
-
-	var merr *multierror.Error
-	for prefix, e := range rm.entries {
-		if e.active != "" && pred(e.active) {
-			if err := apply(prefix); err != nil {
-				merr = multierror.Append(merr, err)
-			}
-		}
-	}
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-// pickSurvivor deterministically selects a peer still referencing the prefix. WireGuard cannot do
-// multipath for a single prefix, so any surviving peer is a valid winner; the choice is made stable
-// (lowest peerKey) for predictable behavior and testability.
-func pickSurvivor(peers map[string]int) (string, bool) {
-	if len(peers) == 0 {
-		return "", false
-	}
-	keys := make([]string, 0, len(peers))
-	for k := range peers {
-		keys = append(keys, k)
-	}
-	sort.Strings(keys)
-	return keys[0], true
-}

client/internal/routemanager/refcounter/allowedips_test.go

@@ -1,241 +0,0 @@
-package refcounter
-
-import (
-	"errors"
-	"net/netip"
-	"testing"
-)
-
-// fakeWG models WireGuard's cryptokey routing: a prefix can be installed on exactly one peer.
-// failAdd/failRemove make the next add/remove fail once, to exercise the self-healing error paths.
-type fakeWG struct {
-	installed  map[netip.Prefix]string
-	adds       int
-	removes    int
-	failAdd    bool
-	failRemove bool
-}
-
-func newFakeWG() *fakeWG {
-	return &fakeWG{installed: map[netip.Prefix]string{}}
-}
-
-func (f *fakeWG) counter() *AllowedIPsRefCounter {
-	return NewAllowedIPs(
-		func(prefix netip.Prefix, peerKey string) (string, error) {
-			if f.failAdd {
-				f.failAdd = false
-				return "", errors.New("add failed")
-			}
-			f.adds++
-			f.installed[prefix] = peerKey
-			return peerKey, nil
-		},
-		func(prefix netip.Prefix, peerKey string) error {
-			if f.failRemove {
-				f.failRemove = false
-				return errors.New("remove failed")
-			}
-			f.removes++
-			// only clear if this peer is the one installed, mirroring wg semantics
-			if f.installed[prefix] == peerKey {
-				delete(f.installed, prefix)
-			}
-			return nil
-		},
-	)
-}
-
-func mustPrefix(t *testing.T, s string) netip.Prefix {
-	t.Helper()
-	p, err := netip.ParsePrefix(s)
-	if err != nil {
-		t.Fatalf("parse prefix %q: %v", s, err)
-	}
-	return p
-}
-
-func mustIncrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Increment(p, peer)
-	if err != nil {
-		t.Fatalf("Increment(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-func mustDecrement(t *testing.T, c *AllowedIPsRefCounter, p netip.Prefix, peer string) Ref[string] {
-	t.Helper()
-	ref, err := c.Decrement(p, peer)
-	if err != nil {
-		t.Fatalf("Decrement(%v, %s): %v", p, peer, err)
-	}
-	return ref
-}
-
-// TestAllowedIPs_SwapOnActivePeerRemoval reproduces the reported bug: two networks with the same
-// prefix routed by different peers. Removing the network whose peer is installed must hand the
-// prefix over to the surviving peer instead of leaving it on the removed one.
-func TestAllowedIPs_SwapOnActivePeerRemoval(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	// First peer wins while both are present.
-	if got := f.installed[p]; got != "peerA" {
-		t.Fatalf("expected peerA installed, got %q", got)
-	}
-
-	// Remove the active peer's network -> must swap to peerB.
-	mustDecrement(t, c, p, "peerA")
-	if got := f.installed[p]; got != "peerB" {
-		t.Fatalf("BUG: prefix stuck on removed peer, want peerB got %q", got)
-	}
-
-	// Remove the last one -> prefix gone.
-	mustDecrement(t, c, p, "peerB")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix removed, still installed on %q", f.installed[p])
-	}
-}
-
-// TestAllowedIPs_RemoveNonActivePeer removing a non-installed peer must not touch WireGuard.
-func TestAllowedIPs_RemoveNonActivePeer(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	removesBefore := f.removes
-
-	mustDecrement(t, c, p, "peerB")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("active peer must stay peerA, got %q", f.installed[p])
-	}
-	if f.removes != removesBefore {
-		t.Fatalf("removing a non-active peer must not call wg remove")
-	}
-}
-
-// TestAllowedIPs_SamePeerMultipleRefs two references via the same peer must keep the prefix until
-// the last reference is released (the reason the per-peer count must be an int, not a set).
-func TestAllowedIPs_SamePeerMultipleRefs(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerA")
-	if f.adds != 1 {
-		t.Fatalf("expected a single wg add for the same peer, got %d", f.adds)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if f.installed[p] != "peerA" {
-		t.Fatalf("prefix must stay while a reference remains, got %q", f.installed[p])
-	}
-	if f.removes != 0 {
-		t.Fatalf("no wg remove expected while a reference remains, got %d", f.removes)
-	}
-
-	mustDecrement(t, c, p, "peerA")
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("prefix must be removed after last reference")
-	}
-}
-
-// TestAllowedIPs_RefCountAndActive checks the Ref returned to callers (used for the HA-disabled log).
-func TestAllowedIPs_RefCountAndActive(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	ref := mustIncrement(t, c, p, "peerA")
-	if ref.Count != 1 || ref.Out != "peerA" {
-		t.Fatalf("want {1, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-	ref = mustIncrement(t, c, p, "peerB")
-	if ref.Count != 2 || ref.Out != "peerA" {
-		t.Fatalf("want {2, peerA}, got {%d, %q}", ref.Count, ref.Out)
-	}
-}
-
-// TestAllowedIPs_Flush removes everything installed and clears the counter.
-func TestAllowedIPs_Flush(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p1 := mustPrefix(t, "10.44.8.0/24")
-	p2 := mustPrefix(t, "10.44.9.0/24")
-
-	mustIncrement(t, c, p1, "peerA")
-	mustIncrement(t, c, p2, "peerB")
-
-	if err := c.Flush(); err != nil {
-		t.Fatal(err)
-	}
-	if len(f.installed) != 0 {
-		t.Fatalf("expected all prefixes removed, got %v", f.installed)
-	}
-	// After flush, a fresh increment must add again.
-	mustIncrement(t, c, p1, "peerC")
-	if f.installed[p1] != "peerC" {
-		t.Fatalf("counter not reset after flush")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterSwapAddError ensures a failed add during a swap does not permanently
-// strand the prefix: the next Decrement (or Increment) must retry and install a surviving peer.
-func TestAllowedIPs_SelfHealAfterSwapAddError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-	mustIncrement(t, c, p, "peerC")
-
-	// Removing the active peerA triggers a swap to a survivor; make the add fail once.
-	f.failAdd = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed swap add")
-	}
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("nothing should be installed after a failed swap add, got %q", f.installed[p])
-	}
-
-	// A later Decrement of a non-active survivor must retry the hand-off (self-heal), not stay stuck.
-	ref := mustDecrement(t, c, p, "peerC")
-	if got := f.installed[p]; got == "" {
-		t.Fatalf("self-heal failed: prefix left unrouted after add recovered")
-	}
-	if ref.Out == "" {
-		t.Fatalf("expected an active peer after self-heal, got empty")
-	}
-}
-
-// TestAllowedIPs_SelfHealAfterRemoveError ensures a failed remove during a swap is retried instead
-// of leaving e.active stuck on a peer that no longer holds references.
-func TestAllowedIPs_SelfHealAfterRemoveError(t *testing.T) {
-	f := newFakeWG()
-	c := f.counter()
-	p := mustPrefix(t, "10.44.8.0/24")
-
-	mustIncrement(t, c, p, "peerA")
-	mustIncrement(t, c, p, "peerB")
-
-	// Releasing active peerA must detach it (remove) then add peerB; fail the remove once.
-	f.failRemove = true
-	if _, err := c.Decrement(p, "peerA"); err == nil {
-		t.Fatalf("expected error from failed remove")
-	}
-
-	// Next Decrement of the non-active survivor retries: removes stale peerA, installs peerB.
-	mustDecrement(t, c, p, "peerB")
-	// peerB had only one ref, so after retry the prefix is fully released.
-	if _, ok := f.installed[p]; ok {
-		t.Fatalf("expected prefix released after self-heal, still on %q", f.installed[p])
-	}
-}

client/internal/routemanager/refcounter/types.go

@@ -5,7 +5,5 @@ import "net/netip"
 // RouteRefCounter is a Counter for Route, it doesn't take any input on Increment and doesn't use any output on Decrement
 type RouteRefCounter = Counter[netip.Prefix, struct{}, struct{}]
 
-// AllowedIPsRefCounter tracks WireGuard AllowedIPs per prefix. Unlike the generic Counter it is peer-aware:
-// a prefix can be claimed by several peers at once and WireGuard allows a given prefix on exactly one peer,
-// so the counter records the per-peer reference count and swaps the installed peer when the active one is released.
-// See allowedips.go.
+// AllowedIPsRefCounter is a Counter for AllowedIPs, it takes a peer key on Increment and passes it back to Decrement
+type AllowedIPsRefCounter = Counter[netip.Prefix, string, string]

client/internal/routemanager/selection.go

@@ -1,138 +0,0 @@
-package routemanager
-
-import (
-	"fmt"
-	"slices"
-
-	"github.com/hashicorp/go-multierror"
-	log "github.com/sirupsen/logrus"
-	"golang.org/x/exp/maps"
-
-	nberrors "github.com/netbirdio/netbird/client/errors"
-	"github.com/netbirdio/netbird/route"
-)
-
-// SelectRoutes selects the routes with the given network IDs and applies the
-// new selection. V4/v6 exit-node pairs are expanded automatically. Exit nodes
-// are mutually exclusive: if the selection activates an exit node, every other
-// available exit node is deselected so two can't be active at once. With
-// appendRoute=false the previous selection is replaced instead of extended.
-func (m *DefaultManager) SelectRoutes(ids []route.NetID, appendRoute bool) error {
-	if err := m.selectRoutes(ids, appendRoute); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-// DeselectRoutes removes the routes with the given network IDs from the
-// selection and applies the change. V4/v6 exit-node pairs are expanded
-// automatically.
-func (m *DefaultManager) DeselectRoutes(ids []route.NetID) error {
-	if err := m.deselectRoutes(ids); err != nil {
-		return err
-	}
-	m.TriggerSelection(m.GetClientRoutes())
-	return nil
-}
-
-func (m *DefaultManager) deselectRoutes(ids []route.NetID) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-
-	log.Debugf("deselecting routes with ids: %v", routes)
-
-	if err := m.routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
-		return fmt.Errorf("deselect routes: %w", err)
-	}
-
-	return nil
-}
-
-// SelectAllRoutes selects every available route and applies the selection.
-// Exit nodes stay mutually exclusive: at most one remains active.
-func (m *DefaultManager) SelectAllRoutes() {
-	m.selectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectAllRoutes() {
-	m.routeSelector.SelectAllRoutes()
-
-	// Select-all wipes every explicit selection, so exit nodes fall back to
-	// management's auto-apply flags — which may mark several at once.
-	// Reconcile immediately so at most one exit node stays active instead of
-	// waiting for the next network map to enforce it.
-	m.mux.Lock()
-	defer m.mux.Unlock()
-	m.updateRouteSelectorFromManagement(m.clientRoutes)
-}
-
-// DeselectAllRoutes deselects every route and applies the change.
-func (m *DefaultManager) DeselectAllRoutes() {
-	m.routeSelector.DeselectAllRoutes()
-	m.TriggerSelection(m.GetClientRoutes())
-}
-
-func (m *DefaultManager) selectRoutes(ids []route.NetID, appendRoute bool) error {
-	routesMap := m.GetClientRoutesWithNetID()
-	routes := route.ExpandV6ExitPairs(slices.Clone(ids), routesMap)
-	allIDs := maps.Keys(routesMap)
-
-	log.Debugf("selecting routes with ids: %v", routes)
-
-	// A partial failure (e.g. an unknown ID in the request) still selects the
-	// valid routes, so exclusivity below must run regardless of the error.
-	var merr *multierror.Error
-	if err := m.routeSelector.SelectRoutes(routes, appendRoute, allIDs); err != nil {
-		merr = multierror.Append(merr, fmt.Errorf("select routes: %w", err))
-	}
-
-	// Exit nodes are mutually exclusive: if this selection activates an
-	// exit node, deselect every other available exit node so two can't be
-	// selected at once. Non-exit route selections are left untouched.
-	if requestActivatesExitNode(routes, routesMap) {
-		if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
-			if err := m.routeSelector.DeselectRoutes(others, allIDs); err != nil {
-				merr = multierror.Append(merr, fmt.Errorf("deselect sibling exit nodes: %w", err))
-			}
-		}
-	}
-
-	return nberrors.FormatErrorOrNil(merr)
-}
-
-func isExitNodeRoutes(routes []*route.Route) bool {
-	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
-}
-
-// requestActivatesExitNode reports whether any requested NetID maps to an exit
-// node (default route) in the current route table.
-func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
-	for _, id := range requested {
-		if isExitNodeRoutes(routesMap[id]) {
-			return true
-		}
-	}
-	return false
-}
-
-// otherExitNodeIDs returns every available exit-node NetID that is not in the
-// requested set — the siblings to deselect so a single exit node stays active.
-func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
-	keep := make(map[route.NetID]struct{}, len(requested))
-	for _, id := range requested {
-		keep[id] = struct{}{}
-	}
-	var others []route.NetID
-	for id, routes := range routesMap {
-		if !isExitNodeRoutes(routes) {
-			continue
-		}
-		if _, ok := keep[id]; ok {
-			continue
-		}
-		others = append(others, id)
-	}
-	return others
-}

client/internal/routemanager/selection_test.go

@@ -1,129 +0,0 @@
-package routemanager
-
-import (
-	"net/netip"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/client/internal/routeselector"
-	"github.com/netbirdio/netbird/route"
-)
-
-func v6ExitRoute(netID, peer string) *route.Route {
-	return &route.Route{
-		NetID:   route.NetID(netID),
-		Network: netip.MustParsePrefix("::/0"),
-		Peer:    peer,
-	}
-}
-
-func newSelectionTestManager() *DefaultManager {
-	return &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", true)},
-			"exitA-v6|::/0":      {v6ExitRoute("exitA-v6", "p1")},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", true)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-}
-
-func TestSelectRoutes_ExitNodeExclusivity(t *testing.T) {
-	m := newSelectionTestManager()
-
-	// Selecting an exit node selects its v6 pair and deselects the sibling.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "exitA should be selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA-v6"), "the v6 pair follows its v4 base")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "the sibling exit node must be deselected")
-
-	// Switching to the sibling deselects the previous exit node and its v6 pair.
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "exitB should now be selected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "the previous exit node must be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "the previous exit node's v6 pair must be deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-
-	// Selecting a non-exit route leaves the active exit node alone.
-	require.NoError(t, m.selectRoutes([]route.NetID{"lan"}, true))
-	assert.True(t, m.routeSelector.IsSelected("exitB"), "selecting a non-exit route keeps the exit node")
-
-	// Deselecting the active exit node turns every exit node off.
-	require.NoError(t, m.deselectRoutes([]route.NetID{"exitB"}))
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "exitB should be deselected")
-	assert.False(t, m.routeSelector.IsSelected("exitA"), "exitA stays deselected")
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit route selection is untouched")
-}
-
-func TestSelectRoutes_PartialErrorStillEnforcesExclusivity(t *testing.T) {
-	// The unknown ID must be reported, but the valid exit node in the same
-	// request is still selected — so its sibling must still be deselected.
-	// Both orderings are covered: processing must continue past the invalid
-	// ID wherever it sits in the request.
-	requests := map[string][]route.NetID{
-		"invalid id first": {"missing", "exitB"},
-		"invalid id last":  {"exitB", "missing"},
-	}
-
-	for name, ids := range requests {
-		t.Run(name, func(t *testing.T) {
-			m := newSelectionTestManager()
-
-			require.NoError(t, m.selectRoutes([]route.NetID{"exitA"}, true))
-
-			err := m.selectRoutes(ids, true)
-			assert.Error(t, err, "unknown id must be reported")
-			assert.True(t, m.routeSelector.IsSelected("exitB"), "valid exit node from the request is selected")
-			assert.False(t, m.routeSelector.IsSelected("exitA"), "sibling exit node must be deselected despite the error")
-			assert.False(t, m.routeSelector.IsSelected("exitA-v6"), "sibling's v6 pair must be deselected too")
-		})
-	}
-}
-
-func TestSelectAllRoutes_KeepsSingleExitNode(t *testing.T) {
-	// Both exit nodes are marked for auto-apply by management
-	// (SkipAutoApply=false), the state where select-all could turn on two at
-	// once without the immediate reconciliation.
-	m := &DefaultManager{
-		routeSelector: routeselector.NewRouteSelector(),
-		clientRoutes: route.HAMap{
-			"exitA|0.0.0.0/0":    {exitRoute("exitA", "p1", false)},
-			"exitB|0.0.0.0/0":    {exitRoute("exitB", "p2", false)},
-			"lan|192.168.1.0/24": {{NetID: "lan", Network: netip.MustParsePrefix("192.168.1.0/24"), Peer: "p3"}},
-		},
-	}
-
-	require.NoError(t, m.selectRoutes([]route.NetID{"exitB"}, true))
-
-	m.selectAllRoutes()
-
-	assert.True(t, m.routeSelector.IsSelected("lan"), "non-exit routes are all selected")
-	assert.True(t, m.routeSelector.IsSelected("exitA"), "the deterministic management pick stays active")
-	assert.False(t, m.routeSelector.IsSelected("exitB"), "select-all must not leave a second exit node active")
-}
-
-func TestSelectRoutes_UnknownRoute(t *testing.T) {
-	m := newSelectionTestManager()
-
-	assert.Error(t, m.selectRoutes([]route.NetID{"missing"}, true), "selecting an unavailable route must fail")
-	assert.Error(t, m.deselectRoutes([]route.NetID{"missing"}), "deselecting an unavailable route must fail")
-}
-
-func TestExitNodeSelectionHelpers(t *testing.T) {
-	routesMap := map[route.NetID][]*route.Route{
-		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
-		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
-		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
-	}
-
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
-	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
-	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
-
-	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
-	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
-}

client/internal/routemanager/static/route.go

@@ -15,11 +15,6 @@ type Route struct {
 	route                *route.Route
 	routeRefCounter      *refcounter.RouteRefCounter
 	allowedIPsRefcounter *refcounter.AllowedIPsRefCounter
-	// currentPeerKey is the routing peer this watcher currently has the prefix installed on
-	// (the HA winner elected by the watcher). It can differ from route.Peer and change on
-	// failover, so it is recorded on AddAllowedIPs and used on RemoveAllowedIPs to decrement
-	// the exact peer that was incremented.
-	currentPeerKey string
 }
 
 func NewRoute(params common.HandlerParams) *Route {
@@ -57,15 +52,12 @@ func (r *Route) AddAllowedIPs(peerKey string) error {
 			ref.Out,
 		)
 	}
-	r.currentPeerKey = peerKey
 	return nil
 }
 
 func (r *Route) RemoveAllowedIPs() error {
-	var err error
-	if _, decErr := r.allowedIPsRefcounter.Decrement(r.route.Network, r.currentPeerKey); decErr != nil {
-		err = fmt.Errorf("remove allowed IP %s: %w", r.route.Network, decErr)
+	if _, err := r.allowedIPsRefcounter.Decrement(r.route.Network); err != nil {
+		return err
 	}
-	r.currentPeerKey = ""
-	return err
+	return nil
 }

client/internal/routemanager/sysctl/sysctl_linux.go

@@ -20,8 +20,6 @@ const (
 	rpFilterPath          = "net.ipv4.conf.all.rp_filter"
 	rpFilterInterfacePath = "net.ipv4.conf.%s.rp_filter"
 	srcValidMarkPath      = "net.ipv4.conf.all.src_valid_mark"
-	percentEscape         = "%25"
-	dotEscape             = "%2E"
 )
 
 type iface interface {
@@ -58,11 +56,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 			continue
 		}
 
-		// Escape '%' and '.' so they survive the dot-to-slash conversion in Set()
-		safeName := strings.ReplaceAll(intf.Name, "%", percentEscape)
-		safeName = strings.ReplaceAll(safeName, ".", dotEscape)
-
-		i := fmt.Sprintf(rpFilterInterfacePath, safeName)
+		i := fmt.Sprintf(rpFilterInterfacePath, intf.Name)
 		oldVal, err := Set(i, 2, true)
 		if err != nil {
 			result = multierror.Append(result, err)
@@ -76,11 +70,7 @@ func Setup(wgIface iface) (map[string]int, error) {
 
 // Set sets a sysctl configuration, if onlyIfOne is true it will only set the new value if it's set to 1
 func Set(key string, desiredValue int, onlyIfOne bool) (int, error) {
-	path := strings.ReplaceAll(key, ".", "/")
-	// Unescape interface dots and percent signs
-	path = strings.ReplaceAll(path, dotEscape, ".")
-	path = strings.ReplaceAll(path, percentEscape, "%")
-	path = fmt.Sprintf("/proc/sys/%s", path)
+	path := fmt.Sprintf("/proc/sys/%s", strings.ReplaceAll(key, ".", "/"))
 	currentValue, err := os.ReadFile(path)
 	if err != nil {
 		return -1, fmt.Errorf("read sysctl %s: %w", key, err)

client/internal/tunnelnotifier/notifier.go

@@ -1,124 +0,0 @@
-package tunnelnotifier
-
-import (
-	"container/list"
-	"sync"
-
-	"github.com/netbirdio/netbird/client/internal/dns"
-	"github.com/netbirdio/netbird/client/internal/listener"
-)
-
-type eventKind int
-
-const (
-	eventRoutes eventKind = iota
-	eventIfaceIP
-	eventIfaceIPv6
-	eventDNS
-)
-
-var (
-	_ listener.NetworkChangeListener = (*Notifier)(nil)
-	_ dns.IosDnsManager              = (*Notifier)(nil)
-)
-
-type event struct {
-	kind    eventKind
-	payload string
-}
-
-type Notifier struct {
-	mu     sync.Mutex
-	cond   *sync.Cond
-	queue  *list.List
-	closed bool
-	done   chan struct{}
-
-	listener   listener.NetworkChangeListener
-	dnsManager dns.IosDnsManager
-}
-
-func New(l listener.NetworkChangeListener, dm dns.IosDnsManager) *Notifier {
-	n := &Notifier{
-		queue:      list.New(),
-		done:       make(chan struct{}),
-		listener:   l,
-		dnsManager: dm,
-	}
-	n.cond = sync.NewCond(&n.mu)
-	go n.deliverLoop()
-	return n
-}
-
-func (n *Notifier) OnNetworkChanged(routes string) {
-	n.enqueue(event{kind: eventRoutes, payload: routes})
-}
-
-func (n *Notifier) SetInterfaceIP(ip string) {
-	n.enqueue(event{kind: eventIfaceIP, payload: ip})
-}
-
-func (n *Notifier) SetInterfaceIPv6(ip string) {
-	n.enqueue(event{kind: eventIfaceIPv6, payload: ip})
-}
-
-func (n *Notifier) ApplyDns(config string) {
-	n.enqueue(event{kind: eventDNS, payload: config})
-}
-
-// Close stops accepting new events and blocks until the delivery loop has
-// drained all queued events and exited.
-func (n *Notifier) Close() {
-	n.mu.Lock()
-	n.closed = true
-	n.cond.Signal()
-	n.mu.Unlock()
-	<-n.done
-}
-
-func (n *Notifier) enqueue(ev event) {
-	n.mu.Lock()
-	defer n.mu.Unlock()
-	if n.closed {
-		return
-	}
-	n.queue.PushBack(ev)
-	n.cond.Signal()
-}
-
-func (n *Notifier) deliverLoop() {
-	defer close(n.done)
-	for {
-		n.mu.Lock()
-		for n.queue.Len() == 0 && !n.closed {
-			n.cond.Wait()
-		}
-		if n.closed && n.queue.Len() == 0 {
-			n.mu.Unlock()
-			return
-		}
-		ev := n.queue.Remove(n.queue.Front()).(event)
-		l := n.listener
-		dm := n.dnsManager
-		n.mu.Unlock()
-
-		switch ev.kind {
-		case eventRoutes:
-			if l != nil {
-				l.OnNetworkChanged(ev.payload)
-			}
-		case eventIfaceIP:
-			if l != nil {
-				l.SetInterfaceIP(ev.payload)
-			}
-		case eventIfaceIPv6:
-			if l != nil {
-				l.SetInterfaceIPv6(ev.payload)
-			}
-		case eventDNS:
-			if dm != nil {
-				dm.ApplyDns(ev.payload)
-			}
-		}
-	}
-}

client/internal/tunnelnotifier/notifier_test.go

@@ -1,192 +0,0 @@
-package tunnelnotifier
-
-import (
-	"fmt"
-	"sync"
-	"sync/atomic"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-)
-
-type call struct {
-	kind    string
-	payload string
-}
-
-type recorder struct {
-	mu       sync.Mutex
-	calls    []call
-	inFlight atomic.Int32
-	overlap  atomic.Bool
-	delay    time.Duration
-}
-
-func (r *recorder) record(kind, payload string) {
-	if r.inFlight.Add(1) != 1 {
-		r.overlap.Store(true)
-	}
-	if r.delay > 0 {
-		time.Sleep(r.delay)
-	}
-	r.mu.Lock()
-	r.calls = append(r.calls, call{kind: kind, payload: payload})
-	r.mu.Unlock()
-	r.inFlight.Add(-1)
-}
-
-func (r *recorder) count() int {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	return len(r.calls)
-}
-
-func (r *recorder) snapshot() []call {
-	r.mu.Lock()
-	defer r.mu.Unlock()
-	out := make([]call, len(r.calls))
-	copy(out, r.calls)
-	return out
-}
-
-type fakeListener struct {
-	rec *recorder
-}
-
-func (f *fakeListener) OnNetworkChanged(routes string) {
-	f.rec.record("routes", routes)
-}
-
-func (f *fakeListener) SetInterfaceIP(ip string) {
-	f.rec.record("ip", ip)
-}
-
-func (f *fakeListener) SetInterfaceIPv6(ip string) {
-	f.rec.record("ipv6", ip)
-}
-
-type fakeDNSManager struct {
-	rec *recorder
-}
-
-func (f *fakeDNSManager) ApplyDns(config string) {
-	f.rec.record("dns", config)
-}
-
-func TestFIFOOrder(t *testing.T) {
-	rec := &recorder{}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	n.SetInterfaceIP("10.0.0.1")
-	n.SetInterfaceIPv6("fd00::1")
-	n.ApplyDns(`{"domains":[]}`)
-	n.OnNetworkChanged("10.0.0.0/8,192.168.0.0/16")
-	n.ApplyDns(`{"domains":["example.com"]}`)
-
-	require.Eventually(t, func() bool { return rec.count() == 5 }, time.Second, time.Millisecond)
-
-	expected := []call{
-		{kind: "ip", payload: "10.0.0.1"},
-		{kind: "ipv6", payload: "fd00::1"},
-		{kind: "dns", payload: `{"domains":[]}`},
-		{kind: "routes", payload: "10.0.0.0/8,192.168.0.0/16"},
-		{kind: "dns", payload: `{"domains":["example.com"]}`},
-	}
-	assert.Equal(t, expected, rec.snapshot())
-}
-
-func TestNoOverlappingCalls(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const producers = 8
-	const perProducer = 25
-
-	var wg sync.WaitGroup
-	for i := 0; i < producers; i++ {
-		wg.Add(1)
-		go func(id int) {
-			defer wg.Done()
-			for j := 0; j < perProducer; j++ {
-				payload := fmt.Sprintf("%d-%d", id, j)
-				switch j % 4 {
-				case 0:
-					n.OnNetworkChanged(payload)
-				case 1:
-					n.SetInterfaceIP(payload)
-				case 2:
-					n.SetInterfaceIPv6(payload)
-				case 3:
-					n.ApplyDns(payload)
-				}
-			}
-		}(i)
-	}
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == producers*perProducer }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-}
-
-func TestDNSAndRoutesInterleaved(t *testing.T) {
-	rec := &recorder{delay: 100 * time.Microsecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-	defer n.Close()
-
-	const events = 50
-
-	var wg sync.WaitGroup
-	wg.Add(2)
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.ApplyDns(fmt.Sprintf("dns-%d", i))
-		}
-	}()
-	go func() {
-		defer wg.Done()
-		for i := 0; i < events; i++ {
-			n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-		}
-	}()
-	wg.Wait()
-
-	require.Eventually(t, func() bool { return rec.count() == 2*events }, 5*time.Second, time.Millisecond)
-	assert.False(t, rec.overlap.Load())
-
-	var dnsSeen, routesSeen int
-	for _, c := range rec.snapshot() {
-		switch c.kind {
-		case "dns":
-			assert.Equal(t, fmt.Sprintf("dns-%d", dnsSeen), c.payload)
-			dnsSeen++
-		case "routes":
-			assert.Equal(t, fmt.Sprintf("routes-%d", routesSeen), c.payload)
-			routesSeen++
-		}
-	}
-	assert.Equal(t, events, dnsSeen)
-	assert.Equal(t, events, routesSeen)
-}
-
-func TestCloseDrainsQueue(t *testing.T) {
-	rec := &recorder{delay: time.Millisecond}
-	n := New(&fakeListener{rec: rec}, &fakeDNSManager{rec: rec})
-
-	const events = 20
-	for i := 0; i < events; i++ {
-		n.OnNetworkChanged(fmt.Sprintf("routes-%d", i))
-	}
-	n.Close()
-
-	require.Equal(t, events, rec.count(), "Close must not return before all queued events are delivered")
-
-	n.OnNetworkChanged("after-close")
-	n.ApplyDns("after-close")
-	time.Sleep(50 * time.Millisecond)
-	assert.Equal(t, events, rec.count())
-}

client/ios/NetBirdSDK/client.go

@@ -13,6 +13,7 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
+	"golang.org/x/exp/maps"
 
 	"github.com/netbirdio/netbird/client/internal"
 	"github.com/netbirdio/netbird/client/internal/auth"
@@ -636,18 +637,23 @@ func (c *Client) SelectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("select all routes")
-		routeManager.SelectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("select route with id: %s", id)
-	if err := routeManager.SelectRoutes(toNetIDs([]string{id}), true); err != nil {
-		log.Debugf("error when selecting routes: %s", err)
-		return err
+		routeSelector.SelectAllRoutes()
+	} else {
+		log.Debugf("select route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.SelectRoutes(routes, true, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when selecting routes: %s", err)
+			return fmt.Errorf("select routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
+
 }
 
 func (c *Client) DeselectRoute(id string) error {
@@ -661,17 +667,21 @@ func (c *Client) DeselectRoute(id string) error {
 	}
 
 	routeManager := engine.GetRouteManager()
+	routeSelector := routeManager.GetRouteSelector()
 	if id == "All" {
 		log.Debugf("deselect all routes")
-		routeManager.DeselectAllRoutes()
-		return nil
-	}
-
-	log.Debugf("deselect route with id: %s", id)
-	if err := routeManager.DeselectRoutes(toNetIDs([]string{id})); err != nil {
-		log.Debugf("error when deselecting routes: %s", err)
-		return err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		log.Debugf("deselect route with id: %s", id)
+		routes := toNetIDs([]string{id})
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		if err := routeSelector.DeselectRoutes(routes, maps.Keys(routesMap)); err != nil {
+			log.Debugf("error when deselecting routes: %s", err)
+			return fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 	return nil
 }
 

client/server/network.go

@@ -8,6 +8,7 @@ import (
 	"sort"
 	"strings"
 
+	"golang.org/x/exp/maps"
 	"google.golang.org/grpc/codes"
 	gstatus "google.golang.org/grpc/status"
 
@@ -160,11 +161,30 @@ func (s *Server) SelectNetworks(_ context.Context, req *proto.SelectNetworksRequ
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.SelectAllRoutes()
-	} else if err := routeManager.SelectRoutes(toNetIDs(req.GetNetworkIDs()), req.GetAppend()); err != nil {
-		return nil, err
+		routeSelector.SelectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.SelectRoutes(routes, req.GetAppend(), netIdRoutes); err != nil {
+			return nil, fmt.Errorf("select routes: %w", err)
+		}
+
+		// Exit nodes are mutually exclusive: if this selection activates an
+		// exit node, deselect every other available exit node so two can't be
+		// selected at once. Non-exit route selections are left untouched.
+		if requestActivatesExitNode(routes, routesMap) {
+			if others := otherExitNodeIDs(routesMap, routes); len(others) > 0 {
+				if err := routeSelector.DeselectRoutes(others, netIdRoutes); err != nil {
+					return nil, fmt.Errorf("deselect sibling exit nodes: %w", err)
+				}
+			}
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -204,11 +224,19 @@ func (s *Server) DeselectNetworks(_ context.Context, req *proto.SelectNetworksRe
 		return nil, fmt.Errorf("no route manager")
 	}
 
+	routeSelector := routeManager.GetRouteSelector()
 	if req.GetAll() {
-		routeManager.DeselectAllRoutes()
-	} else if err := routeManager.DeselectRoutes(toNetIDs(req.GetNetworkIDs())); err != nil {
-		return nil, err
+		routeSelector.DeselectAllRoutes()
+	} else {
+		routes := toNetIDs(req.GetNetworkIDs())
+		routesMap := routeManager.GetClientRoutesWithNetID()
+		routes = route.ExpandV6ExitPairs(routes, routesMap)
+		netIdRoutes := maps.Keys(routesMap)
+		if err := routeSelector.DeselectRoutes(routes, netIdRoutes); err != nil {
+			return nil, fmt.Errorf("deselect routes: %w", err)
+		}
 	}
+	routeManager.TriggerSelection(routeManager.GetClientRoutes())
 
 	s.statusRecorder.PublishEvent(
 		proto.SystemEvent_INFO,
@@ -233,3 +261,37 @@ func toNetIDs(routes []string) []route.NetID {
 	return netIDs
 }
 
+func isExitNodeRoutes(routes []*route.Route) bool {
+	return len(routes) > 0 && (route.IsV4DefaultRoute(routes[0].Network) || route.IsV6DefaultRoute(routes[0].Network))
+}
+
+// requestActivatesExitNode reports whether any requested NetID maps to an exit
+// node (default route) in the current route table.
+func requestActivatesExitNode(requested []route.NetID, routesMap map[route.NetID][]*route.Route) bool {
+	for _, id := range requested {
+		if isExitNodeRoutes(routesMap[id]) {
+			return true
+		}
+	}
+	return false
+}
+
+// otherExitNodeIDs returns every available exit-node NetID that is not in the
+// requested set — the siblings to deselect so a single exit node stays active.
+func otherExitNodeIDs(routesMap map[route.NetID][]*route.Route, requested []route.NetID) []route.NetID {
+	keep := make(map[route.NetID]struct{}, len(requested))
+	for _, id := range requested {
+		keep[id] = struct{}{}
+	}
+	var others []route.NetID
+	for id, routes := range routesMap {
+		if !isExitNodeRoutes(routes) {
+			continue
+		}
+		if _, ok := keep[id]; ok {
+			continue
+		}
+		others = append(others, id)
+	}
+	return others
+}

client/server/network_exitnode_test.go

@@ -0,0 +1,26 @@
+package server
+
+import (
+	"net/netip"
+	"testing"
+
+	"github.com/stretchr/testify/assert"
+
+	"github.com/netbirdio/netbird/route"
+)
+
+func TestExitNodeSelectionHelpers(t *testing.T) {
+	routesMap := map[route.NetID][]*route.Route{
+		"exitA": {{Network: netip.MustParsePrefix("0.0.0.0/0")}},
+		"exitB": {{Network: netip.MustParsePrefix("::/0")}},
+		"lan":   {{Network: netip.MustParsePrefix("192.168.0.0/16")}},
+	}
+
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitA"}, routesMap), "v4 default route is an exit node")
+	assert.True(t, requestActivatesExitNode([]route.NetID{"exitB"}, routesMap), "v6 default route is an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"lan"}, routesMap), "lan route is not an exit node")
+	assert.False(t, requestActivatesExitNode([]route.NetID{"missing"}, routesMap), "unknown id is not an exit node")
+
+	others := otherExitNodeIDs(routesMap, []route.NetID{"exitB"})
+	assert.ElementsMatch(t, []route.NetID{"exitA"}, others, "only the other exit node is a sibling; the lan route is ignored")
+}

client/ui/frontend/src/modules/auto-update/UpdateVersionCard.tsx

@@ -2,7 +2,6 @@ import { type ReactNode } from "react";
 import { useTranslation } from "react-i18next";
 import { Browser } from "@wailsio/runtime";
 import { DownloadIcon, NotepadText } from "lucide-react";
-import { Update as UpdateSvc } from "@bindings/services";
 import { Button } from "@/components/buttons/Button";
 import { useClientVersion } from "@/contexts/ClientVersionContext";
 import { cn } from "@/lib/cn";
@@ -15,12 +14,6 @@ function openUrl(url: string) {
     });
 }
 
-function openInstallerDownload() {
-    UpdateSvc.DownloadURL()
-        .then(openUrl)
-        .catch(() => openUrl(GITHUB_RELEASES));
-}
-
 export function UpdateVersionCard() {
     const { t } = useTranslation();
     const { updateVersion, enforced, triggerUpdate } = useClientVersion();
@@ -44,7 +37,11 @@ export function UpdateVersionCard() {
                         {t("update.card.installNow")}
                     </Button>
                 ) : (
-                    <Button variant={"primary"} size={"xs"} onClick={openInstallerDownload}>
+                    <Button
+                        variant={"primary"}
+                        size={"xs"}
+                        onClick={() => openUrl(GITHUB_RELEASES)}
+                    >
                         <DownloadIcon size={14} />
                         {t("update.card.getInstaller")}
                     </Button>

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
@@ -102,7 +103,7 @@ 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)
@@ -280,9 +281,6 @@ func newApplication(onSecondInstance func()) *application.App {
 		Linux: application.LinuxOptions{
 			ProgramName: "netbird",
 		},
-		Windows: application.WindowsOptions{
-			WndProcInterceptor: endSessionInterceptor(),
-		},
 		SingleInstance: &application.SingleInstanceOptions{
 			UniqueID: "io.netbird.ui",
 			OnSecondInstanceLaunch: func(_ application.SecondInstanceData) {
@@ -369,9 +367,6 @@ func newMainWindow(app *application.App, prefStore *preferences.Store) *applicat
 
 	// Hide instead of quit on close; "really quit" is reached via tray -> Quit.
 	window.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) {
-		if services.ShuttingDown() {
-			return
-		}
 		e.Cancel()
 		window.Hide()
 	})

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/services/shutdown.go

@@ -1,24 +0,0 @@
-package services
-
-import "sync/atomic"
-
-var (
-	sessionEnding atomic.Bool
-	quitting      atomic.Bool
-)
-
-func BeginSessionEnd() {
-	sessionEnding.Store(true)
-}
-
-func AbortSessionEnd() {
-	sessionEnding.Store(false)
-}
-
-func BeginShutdown() {
-	quitting.Store(true)
-}
-
-func ShuttingDown() bool {
-	return sessionEnding.Load() || quitting.Load()
-}

client/ui/services/update.go

@@ -10,7 +10,6 @@ import (
 
 	"github.com/netbirdio/netbird/client/proto"
 	"github.com/netbirdio/netbird/client/ui/updater"
-	"github.com/netbirdio/netbird/version"
 )
 
 // UpdateResult mirrors TriggerUpdateResponse.
@@ -34,12 +33,6 @@ func (s *Update) GetState() updater.State {
 	return s.holder.Get()
 }
 
-// DownloadURL returns the platform-appropriate installer download link for
-// manual (non-enforced) updates.
-func (s *Update) DownloadURL() string {
-	return version.DownloadUrl()
-}
-
 // Quit exits the app. Scheduled off the calling goroutine so the JS caller's
 // response returns before the runtime tears down.
 func (s *Update) Quit() {

client/ui/services/windowmanager.go

@@ -154,9 +154,6 @@ func NewWindowManager(app *application.App, mainWindow *application.WebviewWindo
 	})
 	// Hide (not destroy) on close to keep React state; reset to General for a flash-free reopen.
 	s.settings.RegisterHook(events.Common.WindowClosing, func(e *application.WindowEvent) {
-		if ShuttingDown() {
-			return
-		}
 		e.Cancel()
 		s.app.Event.Emit(EventSettingsOpen, "general")
 		s.settings.Hide()
@@ -396,9 +393,6 @@ func (s *WindowManager) CloseWelcome() {
 // OpenError shows the custom error dialog; title/message are pre-localised and ride in the
 // start URL. A second error replaces the open one via SetURL. Singleton, destroyed on close.
 func (s *WindowManager) OpenError(title, message string) {
-	if ShuttingDown() {
-		return
-	}
 	s.mu.Lock()
 	defer s.mu.Unlock()
 	startURL := errorDialogURL(title, message)

client/ui/shutdown_other.go

@@ -1,7 +0,0 @@
-//go:build !windows && !android && !ios && !freebsd && !js
-
-package main
-
-func endSessionInterceptor() func(hwnd uintptr, msg uint32, wParam, lParam uintptr) (uintptr, bool) {
-	return nil
-}

client/ui/shutdown_windows.go

@@ -1,36 +0,0 @@
-//go:build windows
-
-package main
-
-import (
-	"os"
-
-	log "github.com/sirupsen/logrus"
-
-	"github.com/netbirdio/netbird/client/ui/services"
-)
-
-const (
-	wmQueryEndSession = 0x0011
-	wmEndSession      = 0x0016
-)
-
-func endSessionInterceptor() func(hwnd uintptr, msg uint32, wParam, lParam uintptr) (uintptr, bool) {
-	return func(_ uintptr, msg uint32, wParam, _ uintptr) (uintptr, bool) {
-		switch msg {
-		case wmQueryEndSession:
-			services.BeginSessionEnd()
-			return 1, true
-		case wmEndSession:
-			if wParam == 0 {
-				services.AbortSessionEnd()
-				return 0, true
-			}
-			log.Info("windows session is ending; exiting immediately")
-			os.Exit(0)
-			return 0, true
-		default:
-			return 0, false
-		}
-	}
-}

client/ui/tray.go

@@ -32,8 +32,9 @@ const (
 
 	quitDownTimeout = 5 * time.Second
 
-	urlGitHubRepo = "https://github.com/netbirdio/netbird"
-	urlDocs       = "https://docs.netbird.io"
+	urlGitHubRepo     = "https://github.com/netbirdio/netbird"
+	urlGitHubReleases = "https://github.com/netbirdio/netbird/releases/latest"
+	urlDocs           = "https://docs.netbird.io"
 )
 
 // TrayServices bundles the services the tray menu needs, grouped so NewTray
@@ -44,7 +45,7 @@ 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
@@ -452,7 +453,6 @@ func (t *Tray) buildMenu() *application.Menu {
 }
 
 func (t *Tray) handleQuit() {
-	services.BeginShutdown()
 	t.profileMu.Lock()
 	if t.switchCancel != nil {
 		t.switchCancel()

client/ui/tray_notify.go

@@ -25,9 +25,6 @@ type sendFn func(notifications.NotificationOptions) error
 // event-dispatch goroutine that panic is fatal process-wide; recover() turns
 // it into a logged no-op.
 func safeSendNotification(send sendFn, what string, opts notifications.NotificationOptions) (err error) {
-	if services.ShuttingDown() {
-		return nil
-	}
 	defer func() {
 		if r := recover(); r != nil {
 			log.Errorf("notify %s: recovered from panic (notification bus unavailable): %v", what, r)
@@ -44,7 +41,7 @@ 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

@@ -13,7 +13,6 @@ import (
 
 	"github.com/netbirdio/netbird/client/ui/services"
 	"github.com/netbirdio/netbird/client/ui/updater"
-	"github.com/netbirdio/netbird/version"
 )
 
 // trayUpdater owns the tray UI that reacts to auto-update. Composed inside Tray.
@@ -21,7 +20,7 @@ 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 +35,7 @@ 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,
@@ -77,15 +76,15 @@ func (u *trayUpdater) applyLanguage() {
 	u.refreshMenuItem(state)
 }
 
-// handleClick opens the installer download link when not Enforced, otherwise
-// shows the progress page and asks the daemon to start the installer.
+// handleClick opens the GitHub releases page when not Enforced, otherwise shows
+// the progress page and asks the daemon to start the installer.
 func (u *trayUpdater) handleClick() {
 	u.mu.Lock()
 	state := u.state
 	u.mu.Unlock()
 
 	if !state.Enforced {
-		_ = u.app.Browser.OpenURL(version.DownloadUrl())
+		_ = u.app.Browser.OpenURL(urlGitHubReleases)
 		return
 	}
 

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

@@ -109,7 +109,7 @@ sequenceDiagram
         Chk->>Inj: continue
         Inj->>Inj: inject NetBird identity headers per provider config
         Inj->>Grd: continue
-        Grd->>Grd: enforce per-provider allowlist (fail-closed backstop)
+        Grd->>Grd: enforce model allowlist
         Grd->>Up: forward (over WireGuard)
         Up-->>Resp: response (JSON or SSE stream)
         Resp->>Resp: parse usage tokens, completion
@@ -135,21 +135,6 @@ sequenceDiagram
   (`redact_pii = settings.RedactPii`). Phones, emails, credit cards,
   PII names — see `redact.go` for the full set. See
   [`modules/31-proxy-middleware-builtin.md`](modules/31-proxy-middleware-builtin.md).
-- The model allowlist is enforced in TWO places. `CheckLLMPolicyLimits`
-  is authoritative: it resolves the policy that governs this
-  (provider, caller-groups) and denies (`deny_code = llm_policy.model_blocked`)
-  when no applicable policy permits the model — so an allowlist scoped to
-  one group/provider never leaks to another, and an un-guardrailed policy
-  is genuinely unrestricted. `llm_guardrail` is a per-provider fail-closed
-  backstop: it only carries an allowlist for a provider every authorising
-  policy restricts, and blocks unknown/undetermined models even when
-  management is unreachable. Because that backstop allowlist is the UNION
-  of every restricting policy's models, per-group narrowing lives only in
-  the authoritative check: during a `CheckLLMPolicyLimits` outage
-  `llm_limit_check` fails open, so a caller can reach any model in the
-  provider's union — a group scoped to model A could reach model B if
-  another group restricts the same provider to B. This is the documented
-  fail-open trade-off; a future flag may switch it to fail-closed.
 - SSE streaming requires special handling on the response side; the
   parser must handle partial chunks without buffering the whole
   stream. See [`modules/32-proxy-llm-parsers.md`](modules/32-proxy-llm-parsers.md).

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

@@ -122,7 +122,7 @@ At request time the path is independent: the proxy calls `SelectPolicyForRequest
   | on_request | 1 | `llm_router` | `{"providers":[{id, models[], upstream_*, auth_header_*, allowed_group_ids[]}]}` | **true** |
   | on_request | 2 | `llm_limit_check` | `{}` | – |
   | 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_request | 4 | `llm_guardrail` | `{"model_allowlist"?, "prompt_capture":{enabled,redact_pii}}` | – |
   | on_response | 5 | `llm_limit_record` | `{}` (runs LAST at runtime) | – |
   | on_response | 6 | `cost_meter` | `{}` | – |
   | on_response | 7 | `llm_response_parser` | `{"capture_completion": <bool>, "redact_pii"?: true}` | – |

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

@@ -244,7 +244,7 @@ no mocks. Tests: `TestChain_AllowPath_StampsAttributionAndRecordsCounter`
 | `llm_router` | `{providers: [{id, models, upstream_scheme, upstream_host, upstream_path?, auth_header_name, auth_header_value, allowed_group_ids}]}` |
 | `llm_limit_check` | `{}` — pulls `MgmtClient` from `FactoryContext` |
 | `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_guardrail` | `{model_allowlist: []string, prompt_capture: {enabled, redact_pii}}` |
 | `llm_response_parser` | `{redact_pii?, capture_completion?: *bool}` |
 | `cost_meter` | `{pricing_path?}` (basename inside data-dir; defaults `pricing.yaml`) |
 | `llm_limit_record` | `{}` — same pattern as `llm_limit_check` |

e2e/agentnetwork/guardrail_block_test.go

@@ -1,209 +0,0 @@
-//go:build e2e
-
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/e2e/harness"
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// pathRoutedGuardrailCase is one provider's self-contained scenario: its own
-// provider, its own guardrail whose allowlist holds ONLY that provider's
-// allowed model, and its own policy. Each case runs in isolation (its own
-// proxy + client), so the guardrail the proxy enforces contains exactly this
-// provider's model — never a mixed cross-provider list.
-type pathRoutedGuardrailCase struct {
-	name       string
-	catalogID  string // agent-network catalog provider id
-	wire       string // harness.WireVertex | harness.WireBedrock
-	allowEntry string // the single model id put on the guardrail allowlist
-	allowModel string // model id sent that MUST be served (200)
-	blockModel string // model id sent that MUST be denied (403 model_blocked)
-}
-
-// TestGuardrailBlocksUnselectedModel_PathRouted is the end-to-end regression
-// guard for the customer report that a model-allowlist guardrail attached to a
-// policy has no effect for PATH-ROUTED providers — where the model travels in
-// the URL, not the JSON body: Google Vertex (…/models/{model}:rawPredict) and
-// AWS Bedrock (/model/{id}/invoke).
-//
-// Each provider is tested in isolation with a guardrail allowlisting a single
-// model of its own: the allowed model (in the URL path) is served (200) and an
-// unselected model (in the URL path) is denied 403 by the guardrail
-// (llm_policy.model_blocked) before the upstream. The Vertex case mirrors the
-// customer verbatim — allow Sonnet, and the unselected model is the exact
-// claude-opus-4-6 they reported reaching the model unblocked. The Bedrock case
-// sends a region-prefixed, versioned inference-profile id so URL-path model
-// normalization is exercised too.
-//
-// The provider is catch-all (no models), so the router forwards any model and a
-// 403 can only come from the guardrail, never model_not_routable. Only the
-// upstream LLM is mocked (the vLLM nginx answers any path with 200); management
-// synth/reconcile, the proxy middleware chain (URL-path model extraction,
-// router, guardrail) and the tunnel are all real, and the guardrail denies
-// before the upstream is dialed so the mock cannot influence the block. A
-// static bearer api key is used so the router injects a static Authorization
-// header instead of minting a GCP token — the only reason path-routed providers
-// normally need live credentials — so the test runs with none and is always on.
-func TestGuardrailBlocksUnselectedModel_PathRouted(t *testing.T) {
-	cases := []pathRoutedGuardrailCase{
-		{
-			name:       "vertex",
-			catalogID:  "vertex_ai_api",
-			wire:       harness.WireVertex,
-			allowEntry: "claude-sonnet-4-5",
-			allowModel: "claude-sonnet-4-5",
-			blockModel: "claude-opus-4-6", // the customer-reported model
-		},
-		{
-			name:       "bedrock",
-			catalogID:  "bedrock_api",
-			wire:       harness.WireBedrock,
-			allowEntry: "anthropic.claude-sonnet-4-5", // normalized catalog id
-			allowModel: "us.anthropic.claude-sonnet-4-5-v1:0",
-			blockModel: "us.anthropic.claude-opus-4-8-v1:0",
-		},
-	}
-
-	for _, tc := range cases {
-		tc := tc
-		t.Run(tc.name, func(t *testing.T) {
-			runPathRoutedGuardrailCase(t, tc)
-		})
-	}
-}
-
-func runPathRoutedGuardrailCase(t *testing.T, tc pathRoutedGuardrailCase) {
-	t.Helper()
-
-	const (
-		vertexProject = "e2e-project"
-		vertexRegion  = "global"
-	)
-
-	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
-	defer cancel()
-
-	vllm, err := harness.StartVLLM(ctx, srv)
-	require.NoError(t, err, "start mock upstream")
-	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
-
-	grp, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-guardrail-" + tc.name})
-	require.NoError(t, err, "create group")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grp.Id) })
-
-	ephemeral := false
-	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
-		Name:       "e2e-guardrail-" + tc.name + "-client",
-		Type:       "reusable",
-		ExpiresIn:  86400,
-		UsageLimit: 0,
-		AutoGroups: []string{grp.Id},
-		Ephemeral:  &ephemeral,
-	})
-	require.NoError(t, err, "mint setup key")
-	require.NotEmpty(t, sk.Key, "setup key plaintext")
-
-	// Catch-all provider (no models) so the router forwards any model; a static
-	// bearer key means the router injects a static auth header instead of minting
-	// a GCP token. Bootstraps the cluster if it isn't already.
-	staticKey := "static-e2e-token"
-	prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:             tc.name,
-		ProviderId:       tc.catalogID,
-		UpstreamUrl:      vllm.URL,
-		ApiKey:           &staticKey,
-		Enabled:          ptr(true),
-		BootstrapCluster: ptr(harness.AgentNetworkCluster),
-	})
-	require.NoError(t, err, "create %s provider", tc.name)
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
-
-	// Guardrail allowlisting ONLY this provider's allowed model.
-	var gr api.AgentNetworkGuardrailRequest
-	gr.Name = "e2e-guardrail-" + tc.name
-	gr.Checks.ModelAllowlist.Enabled = true
-	gr.Checks.ModelAllowlist.Models = []string{tc.allowEntry}
-	guard, err := srv.CreateGuardrail(ctx, gr)
-	require.NoError(t, err, "create guardrail")
-	t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), guard.Id) })
-
-	enabled := true
-	pol, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-guardrail-" + tc.name,
-		Enabled:                &enabled,
-		SourceGroups:           []string{grp.Id},
-		DestinationProviderIds: []string{prov.Id},
-		GuardrailIds:           &[]string{guard.Id},
-	})
-	require.NoError(t, err, "create policy")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), pol.Id) })
-
-	settings, err := srv.GetSettings(ctx)
-	require.NoError(t, err, "read settings")
-	require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned")
-
-	proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-guardrail-"+tc.name+"-proxy")
-	require.NoError(t, err, "mint proxy token")
-	px, err := harness.StartProxy(ctx, srv, proxyToken)
-	require.NoError(t, err, "start proxy")
-	t.Cleanup(func() { _ = px.Terminate(context.Background()) })
-
-	cl, err := harness.StartClient(ctx, srv, sk.Key)
-	require.NoError(t, err, "start client")
-	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
-
-	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management")
-	// Probe first: the GET resolves the endpoint and its first packet wakes the
-	// lazy proxy peer, so WaitProxyPeer then observes it connected.
-	proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint)
-	require.NoError(t, err, "resolve endpoint to proxy IP")
-	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
-		t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background()))
-	}
-
-	send := func(model string) (int, string) {
-		var code int
-		var body string
-		var cerr error
-		switch tc.wire {
-		case harness.WireVertex:
-			code, body, cerr = cl.Vertex(ctx, settings.Endpoint, proxyIP, vertexProject, vertexRegion, model, "Reply with exactly: pong", "")
-		case harness.WireBedrock:
-			code, body, cerr = cl.Bedrock(ctx, settings.Endpoint, proxyIP, model, "Reply with exactly: pong", "")
-		default:
-			t.Fatalf("unsupported wire %q", tc.wire)
-		}
-		require.NoError(t, cerr, "request must reach the proxy for %s", tc.name)
-		return code, body
-	}
-
-	// Allowed model (in the URL path) is served. Retry to absorb tunnel/DNS
-	// jitter on the first call over the freshly warmed tunnel.
-	var code int
-	var body string
-	deadline := time.Now().Add(90 * time.Second)
-	for time.Now().Before(deadline) {
-		code, body = send(tc.allowModel)
-		if code == 200 {
-			break
-		}
-		time.Sleep(5 * time.Second)
-	}
-	assert.Equal(t, 200, code,
-		"allowed %s model (URL path) must be served; body: %s\n=== proxy logs ===\n%s", tc.name, body, px.Logs(context.Background()))
-
-	// Unselected model (in the URL path) must be blocked by the guardrail.
-	code, body = send(tc.blockModel)
-	assert.Equal(t, 403, code,
-		"unselected %s model (URL path) must be denied, not served; body: %s\n=== proxy logs ===\n%s", tc.name, body, px.Logs(context.Background()))
-	assert.Contains(t, body, "llm_policy.model_blocked",
-		"%s denial must come from the guardrail allowlist, not routing; body: %s", tc.name, body)
-}

e2e/agentnetwork/guardrail_groupswitch_test.go

@@ -1,205 +0,0 @@
-//go:build e2e
-
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/e2e/harness"
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// TestGuardrailGroupSwitchTakesEffectAfterTTL proves that moving a peer between
-// groups flips its model-allowlist decision once the proxy's tunnel-peer cache
-// expires. The peer's groups reach the guardrail via ValidateTunnelPeer, which
-// the proxy caches; the switch is invisible until that cache expires. The proxy
-// runs with a short NB_PROXY_TUNNEL_CACHE_TTL so the flip happens in seconds
-// instead of the 5-minute default.
-//
-// Setup: one catch-all provider declaring modelA + modelB; polA (grpA -> allow
-// modelA) and polB (grpB -> allow modelB). The client starts in grpA. modelA is
-// served and modelB denied; after switching the client grpA -> grpB, modelB is
-// served and modelA denied. The cross-group deny comes from management's
-// per-policy/group CheckLLMPolicyLimits (the proxy backstop carries the union).
-func TestGuardrailGroupSwitchTakesEffectAfterTTL(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
-	defer cancel()
-
-	const (
-		modelA = "e2e-model-a"
-		modelB = "e2e-model-b"
-		// Short tunnel-cache TTL so a group switch propagates in seconds.
-		// Exercises the NB_PROXY_TUNNEL_CACHE_TTL override.
-		cacheTTL = 3 * time.Second
-	)
-
-	vllm, err := harness.StartVLLM(ctx, srv)
-	require.NoError(t, err, "start mock upstream")
-	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
-
-	grpA, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-gswitch-a"})
-	require.NoError(t, err, "create group A")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpA.Id) })
-
-	grpB, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-gswitch-b"})
-	require.NoError(t, err, "create group B")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpB.Id) })
-
-	ephemeral := false
-	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
-		Name:       "e2e-gswitch-client",
-		Type:       "reusable",
-		ExpiresIn:  86400,
-		UsageLimit: 0,
-		AutoGroups: []string{grpA.Id}, // client starts in group A
-		Ephemeral:  &ephemeral,
-	})
-	require.NoError(t, err, "mint setup key")
-	require.NotEmpty(t, sk.Key, "setup key plaintext")
-
-	staticKey := "static-e2e-token"
-	prov, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:        "gswitch",
-		ProviderId:  "openai_api",
-		UpstreamUrl: vllm.URL,
-		ApiKey:      &staticKey,
-		Enabled:     ptr(true),
-		Models: &[]api.AgentNetworkProviderModel{
-			{Id: modelA, InputPer1k: 0.001, OutputPer1k: 0.001},
-			{Id: modelB, InputPer1k: 0.001, OutputPer1k: 0.001},
-		},
-		BootstrapCluster: ptr(harness.AgentNetworkCluster),
-	})
-	require.NoError(t, err, "create provider")
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
-
-	mkGuard := func(name, model string) api.AgentNetworkGuardrail {
-		var gr api.AgentNetworkGuardrailRequest
-		gr.Name = name
-		gr.Checks.ModelAllowlist.Enabled = true
-		gr.Checks.ModelAllowlist.Models = []string{model}
-		g, gerr := srv.CreateGuardrail(ctx, gr)
-		require.NoError(t, gerr, "create guardrail %s", name)
-		t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) })
-		return g
-	}
-	gA := mkGuard("e2e-gswitch-a", modelA)
-	gB := mkGuard("e2e-gswitch-b", modelB)
-
-	enabled := true
-	polA, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-gswitch-a",
-		Enabled:                &enabled,
-		SourceGroups:           []string{grpA.Id},
-		DestinationProviderIds: []string{prov.Id},
-		GuardrailIds:           &[]string{gA.Id},
-	})
-	require.NoError(t, err, "create policy A")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polA.Id) })
-
-	polB, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-gswitch-b",
-		Enabled:                &enabled,
-		SourceGroups:           []string{grpB.Id},
-		DestinationProviderIds: []string{prov.Id},
-		GuardrailIds:           &[]string{gB.Id},
-	})
-	require.NoError(t, err, "create policy B")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polB.Id) })
-
-	settings, err := srv.GetSettings(ctx)
-	require.NoError(t, err, "read settings")
-	require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned")
-
-	proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-gswitch-proxy")
-	require.NoError(t, err, "mint proxy token")
-	px, err := harness.StartProxy(ctx, srv, proxyToken, map[string]string{
-		"NB_PROXY_TUNNEL_CACHE_TTL": cacheTTL.String(),
-	})
-	require.NoError(t, err, "start proxy")
-	t.Cleanup(func() { _ = px.Terminate(context.Background()) })
-
-	cl, err := harness.StartClient(ctx, srv, sk.Key)
-	require.NoError(t, err, "start client")
-	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
-
-	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management")
-	proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint)
-	require.NoError(t, err, "resolve endpoint to proxy IP")
-	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
-		t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background()))
-	}
-
-	send := func(model string) (int, string) {
-		code, body, cerr := cl.Chat(ctx, settings.Endpoint, proxyIP, harness.WireChat, model, "Reply with exactly: pong", "")
-		require.NoError(t, cerr, "request must reach the proxy")
-		return code, body
-	}
-	sendUntil := func(model string, want int, timeout time.Duration) (int, string) {
-		var code int
-		var body string
-		deadline := time.Now().Add(timeout)
-		for time.Now().Before(deadline) {
-			code, body = send(model)
-			if code == want {
-				return code, body
-			}
-			time.Sleep(2 * time.Second)
-		}
-		return code, body
-	}
-
-	// Phase 1 — client is in group A: modelA served, modelB denied.
-	code, body := sendUntil(modelA, 200, 90*time.Second)
-	assert.Equal(t, 200, code,
-		"group-A model must be served while the client is in group A; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-	code, body = send(modelB)
-	assert.Equal(t, 403, code,
-		"group-B model must be denied while the client is in group A; body: %s", body)
-	assert.Contains(t, body, "llm_policy.model_blocked")
-
-	// Switch the client peer from group A to group B.
-	peerID := clientPeerInGroup(t, ctx, grpA.Id)
-	_, err = srv.API().Groups.Update(ctx, grpB.Id, api.PutApiGroupsGroupIdJSONRequestBody{
-		Name:  grpB.Name,
-		Peers: &[]string{peerID},
-	})
-	require.NoError(t, err, "add peer to group B")
-	_, err = srv.API().Groups.Update(ctx, grpA.Id, api.PutApiGroupsGroupIdJSONRequestBody{
-		Name:  grpA.Name,
-		Peers: &[]string{},
-	})
-	require.NoError(t, err, "remove peer from group A")
-
-	// Phase 2 — after the short TTL expires the proxy re-validates the peer,
-	// sees group B, and the decision flips. Poll to absorb TTL + re-validation.
-	code, body = sendUntil(modelB, 200, 60*time.Second)
-	assert.Equal(t, 200, code,
-		"after the group switch + TTL, the group-B model must be served; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-	code, body = send(modelA)
-	assert.Equal(t, 403, code,
-		"after the switch, the old group-A model must be denied; body: %s", body)
-	assert.Contains(t, body, "llm_policy.model_blocked")
-}
-
-// clientPeerInGroup returns the id of the single peer that is a member of the
-// given group — the test client. The proxy peer is never added to test groups.
-func clientPeerInGroup(t *testing.T, ctx context.Context, groupID string) string {
-	t.Helper()
-	peers, err := srv.API().Peers.List(ctx)
-	require.NoError(t, err, "list peers")
-	for _, p := range peers {
-		for _, g := range p.Groups {
-			if g.Id == groupID {
-				return p.Id
-			}
-		}
-	}
-	t.Fatalf("no peer found in group %s", groupID)
-	return ""
-}

e2e/agentnetwork/guardrail_multipolicy_test.go

@@ -1,201 +0,0 @@
-//go:build e2e
-
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/e2e/harness"
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// TestGuardrailMultiPolicyModelAllowlist: modelSelected served (200), grpOther's
-// modelOther denied for the grpMain client (403 model_blocked, no cross-group
-// leak), and openModel on the un-guardrailed policy's provider served (200).
-func TestGuardrailMultiPolicyModelAllowlist(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
-	defer cancel()
-
-	const (
-		modelSelected = "e2e-selected"
-		modelOther    = "e2e-other"
-		openModel     = "e2e-open"
-	)
-
-	vllm, err := harness.StartVLLM(ctx, srv)
-	require.NoError(t, err, "start mock upstream")
-	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
-
-	grpMain, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-guardrail-mp-main"})
-	require.NoError(t, err, "create main group")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpMain.Id) })
-
-	grpOther, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-guardrail-mp-other"})
-	require.NoError(t, err, "create other group")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpOther.Id) })
-
-	ephemeral := false
-	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
-		Name:       "e2e-guardrail-mp-client",
-		Type:       "reusable",
-		ExpiresIn:  86400,
-		UsageLimit: 0,
-		AutoGroups: []string{grpMain.Id}, // client joins grpMain only
-		Ephemeral:  &ephemeral,
-	})
-	require.NoError(t, err, "mint setup key")
-	require.NotEmpty(t, sk.Key, "setup key plaintext")
-
-	staticKey := "static-e2e-token"
-	models := func(ids ...string) *[]api.AgentNetworkProviderModel {
-		out := make([]api.AgentNetworkProviderModel, 0, len(ids))
-		for _, id := range ids {
-			out = append(out, api.AgentNetworkProviderModel{Id: id, InputPer1k: 0.001, OutputPer1k: 0.001})
-		}
-		return &out
-	}
-
-	// pRestricted declares the two guardrailed models so routing is deterministic
-	// (model -> provider). Created first, so it carries the bootstrap cluster.
-	pRestricted, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:             "restricted",
-		ProviderId:       "openai_api",
-		UpstreamUrl:      vllm.URL,
-		ApiKey:           &staticKey,
-		Enabled:          ptr(true),
-		Models:           models(modelSelected, modelOther),
-		BootstrapCluster: ptr(harness.AgentNetworkCluster),
-	})
-	require.NoError(t, err, "create restricted provider")
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), pRestricted.Id) })
-
-	pOpen, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:        "open",
-		ProviderId:  "openai_api",
-		UpstreamUrl: vllm.URL,
-		ApiKey:      &staticKey,
-		Enabled:     ptr(true),
-		Models:      models(openModel),
-	})
-	require.NoError(t, err, "create open provider")
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), pOpen.Id) })
-
-	mkGuardrail := func(name, model string) api.AgentNetworkGuardrail {
-		var gr api.AgentNetworkGuardrailRequest
-		gr.Name = name
-		gr.Checks.ModelAllowlist.Enabled = true
-		gr.Checks.ModelAllowlist.Models = []string{model}
-		g, gerr := srv.CreateGuardrail(ctx, gr)
-		require.NoError(t, gerr, "create guardrail %s", name)
-		t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) })
-		return g
-	}
-	gMain := mkGuardrail("e2e-guardrail-mp-main", modelSelected)
-	gOther := mkGuardrail("e2e-guardrail-mp-other", modelOther)
-
-	enabled := true
-	// polMain: grpMain restricted to modelSelected on pRestricted.
-	polMain, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-guardrail-mp-main",
-		Enabled:                &enabled,
-		SourceGroups:           []string{grpMain.Id},
-		DestinationProviderIds: []string{pRestricted.Id},
-		GuardrailIds:           &[]string{gMain.Id},
-	})
-	require.NoError(t, err, "create main policy")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMain.Id) })
-
-	// polOther: grpOther restricted to modelOther on the SAME provider. The
-	// client is not in grpOther, so modelOther must never be usable by it.
-	polOther, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-guardrail-mp-other",
-		Enabled:                &enabled,
-		SourceGroups:           []string{grpOther.Id},
-		DestinationProviderIds: []string{pRestricted.Id},
-		GuardrailIds:           &[]string{gOther.Id},
-	})
-	require.NoError(t, err, "create other policy")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polOther.Id) })
-
-	// polOpen: grpMain on pOpen with NO guardrail — unrestricted.
-	polOpen, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-guardrail-mp-open",
-		Enabled:                &enabled,
-		SourceGroups:           []string{grpMain.Id},
-		DestinationProviderIds: []string{pOpen.Id},
-	})
-	require.NoError(t, err, "create open policy")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polOpen.Id) })
-
-	settings, err := srv.GetSettings(ctx)
-	require.NoError(t, err, "read settings")
-	require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned")
-
-	proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-guardrail-mp-proxy")
-	require.NoError(t, err, "mint proxy token")
-	px, err := harness.StartProxy(ctx, srv, proxyToken)
-	require.NoError(t, err, "start proxy")
-	t.Cleanup(func() { _ = px.Terminate(context.Background()) })
-
-	cl, err := harness.StartClient(ctx, srv, sk.Key)
-	require.NoError(t, err, "start client")
-	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
-
-	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management")
-	proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint)
-	require.NoError(t, err, "resolve endpoint to proxy IP")
-	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
-		t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background()))
-	}
-
-	send := func(model string) (int, string) {
-		code, body, cerr := cl.Chat(ctx, settings.Endpoint, proxyIP, harness.WireChat, model, "Reply with exactly: pong", "")
-		require.NoError(t, cerr, "request must reach the proxy")
-		return code, body
-	}
-	// sendUntil200 absorbs first-call tunnel/DNS jitter on the freshly warmed tunnel.
-	sendUntil200 := func(model string) (int, string) {
-		var code int
-		var body string
-		deadline := time.Now().Add(90 * time.Second)
-		for time.Now().Before(deadline) {
-			code, body = send(model)
-			if code == 200 {
-				break
-			}
-			time.Sleep(5 * time.Second)
-		}
-		return code, body
-	}
-
-	t.Run("selected model allowed for its group", func(t *testing.T) {
-		code, body := sendUntil200(modelSelected)
-		assert.Equal(t, 200, code,
-			"grpMain's allowlisted model must be served; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-	})
-
-	t.Run("other group's model does not leak", func(t *testing.T) {
-		// modelOther is allowlisted only for grpOther. The grpMain client must be
-		// denied by management's per-policy/group check — not waved through by an
-		// account-wide union. This is the security-critical wrong-ALLOW guard.
-		code, body := send(modelOther)
-		assert.Equal(t, 403, code,
-			"another group's allowlisted model must be denied for this caller; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-		assert.Contains(t, body, "llm_policy.model_blocked",
-			"denial must be a model-allowlist decision; body: %s", body)
-	})
-
-	t.Run("unguarded policy leaves its provider unrestricted", func(t *testing.T) {
-		// polOpen carries no guardrail, so pOpen is unrestricted for grpMain. The
-		// old account-wide union would have blocked openModel (it is on no
-		// allowlist); it must now be served — the false-DENY guard.
-		code, body := sendUntil200(openModel)
-		assert.Equal(t, 200, code,
-			"an un-guardrailed policy's provider must not be blocked by another policy's allowlist; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-	})
-}

e2e/agentnetwork/guardrail_pergroup_providers_test.go

@@ -1,422 +0,0 @@
-//go:build e2e
-
-package agentnetwork
-
-import (
-	"context"
-	"testing"
-	"time"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-
-	"github.com/netbirdio/netbird/e2e/harness"
-	"github.com/netbirdio/netbird/shared/management/http/api"
-)
-
-// pergroupCase describes one provider surface for the per-group allowlist matrix.
-// selectedReq/otherReq are the model identifiers as they travel in the request
-// (URL path for Bedrock/Vertex, body "model" for chat/messages). selectedAllow/
-// otherAllow are the (normalized) forms the guardrail allowlist holds — for
-// Bedrock these differ from the request form so path normalization is exercised.
-type pergroupCase struct {
-	name          string
-	catalogID     string
-	wire          string // "chat", "messages", "vertex", "bedrock"
-	models        *[]api.AgentNetworkProviderModel
-	selectedReq   string
-	selectedAllow string
-	otherReq      string
-	otherAllow    string
-
-	providerID string // filled during setup
-}
-
-// TestGuardrailPerGroupAllowlist_AllProviders proves the per-policy/group model
-// allowlist end to end across every always-on provider surface, including the
-// path-routed ones (Vertex, Bedrock) where the model travels in the URL.
-//
-// For each provider two policies target it: grpMain (the client) is allowed only
-// selectedReq; grpOther (which the client is NOT in) is allowed only otherReq.
-// The client must get selectedReq served (200) and otherReq denied (403,
-// llm_policy.model_blocked) — the cross-group no-leak property. The deny is the
-// authoritative per-policy/group decision from management (the proxy per-provider
-// backstop carries the union of both models), so this also confirms management
-// receives the correct normalized model for path-routed providers.
-func TestGuardrailPerGroupAllowlist_AllProviders(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 20*time.Minute)
-	defer cancel()
-
-	const (
-		vertexProject = "e2e-project"
-		vertexRegion  = "global"
-	)
-
-	priced := func(ids ...string) *[]api.AgentNetworkProviderModel {
-		out := make([]api.AgentNetworkProviderModel, 0, len(ids))
-		for _, id := range ids {
-			out = append(out, api.AgentNetworkProviderModel{Id: id, InputPer1k: 0.001, OutputPer1k: 0.001})
-		}
-		return &out
-	}
-
-	cases := []*pergroupCase{
-		{
-			name: "openai", catalogID: "openai_api", wire: harness.WireChat,
-			models:      priced("oai-model-a", "oai-model-b"),
-			selectedReq: "oai-model-a", selectedAllow: "oai-model-a",
-			otherReq: "oai-model-b", otherAllow: "oai-model-b",
-		},
-		{
-			name: "anthropic", catalogID: "anthropic_api", wire: harness.WireMessages,
-			models:      priced("ant-model-a", "ant-model-b"),
-			selectedReq: "ant-model-a", selectedAllow: "ant-model-a",
-			otherReq: "ant-model-b", otherAllow: "ant-model-b",
-		},
-		{
-			// Vertex catalog ids travel bare in the rawPredict path.
-			name: "vertex", catalogID: "vertex_ai_api", wire: "vertex",
-			selectedReq: "claude-sonnet-4-5", selectedAllow: "claude-sonnet-4-5",
-			otherReq: "claude-opus-4-6", otherAllow: "claude-opus-4-6",
-		},
-		{
-			// Bedrock request ids are region-prefixed/versioned; the parser
-			// normalizes them to the catalog key the allowlist holds.
-			name: "bedrock", catalogID: "bedrock_api", wire: "bedrock",
-			selectedReq: "us.anthropic.claude-sonnet-4-5-v1:0", selectedAllow: "anthropic.claude-sonnet-4-5",
-			otherReq: "us.anthropic.claude-opus-4-8-v1:0", otherAllow: "anthropic.claude-opus-4-8",
-		},
-	}
-
-	vllm, err := harness.StartVLLM(ctx, srv)
-	require.NoError(t, err, "start mock upstream")
-	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
-
-	grpMain, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-pergroup-main"})
-	require.NoError(t, err, "create main group")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpMain.Id) })
-
-	grpOther, err := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: "e2e-pergroup-other"})
-	require.NoError(t, err, "create other group")
-	t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), grpOther.Id) })
-
-	ephemeral := false
-	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
-		Name:       "e2e-pergroup-client",
-		Type:       "reusable",
-		ExpiresIn:  86400,
-		UsageLimit: 0,
-		AutoGroups: []string{grpMain.Id},
-		Ephemeral:  &ephemeral,
-	})
-	require.NoError(t, err, "mint setup key")
-	require.NotEmpty(t, sk.Key, "setup key plaintext")
-
-	staticKey := "static-e2e-token"
-	enabled := true
-
-	for i, c := range cases {
-		req := api.AgentNetworkProviderRequest{
-			Name:        "e2e-pergroup-" + c.name,
-			ProviderId:  c.catalogID,
-			UpstreamUrl: vllm.URL,
-			ApiKey:      &staticKey,
-			Enabled:     ptr(true),
-			Models:      c.models,
-		}
-		if i == 0 {
-			req.BootstrapCluster = ptr(harness.AgentNetworkCluster)
-		}
-		prov, perr := srv.CreateProvider(ctx, req)
-		require.NoError(t, perr, "create provider %s", c.name)
-		c.providerID = prov.Id
-		t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), prov.Id) })
-
-		gSel := mkAllowGuardrail(t, ctx, "e2e-pergroup-"+c.name+"-sel", c.selectedAllow)
-		gOth := mkAllowGuardrail(t, ctx, "e2e-pergroup-"+c.name+"-oth", c.otherAllow)
-
-		polMain, merr := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-			Name:                   "e2e-pergroup-" + c.name + "-main",
-			Enabled:                &enabled,
-			SourceGroups:           []string{grpMain.Id},
-			DestinationProviderIds: []string{prov.Id},
-			GuardrailIds:           &[]string{gSel.Id},
-		})
-		require.NoError(t, merr, "create main policy %s", c.name)
-		t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMain.Id) })
-
-		polOther, oerr := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-			Name:                   "e2e-pergroup-" + c.name + "-other",
-			Enabled:                &enabled,
-			SourceGroups:           []string{grpOther.Id},
-			DestinationProviderIds: []string{prov.Id},
-			GuardrailIds:           &[]string{gOth.Id},
-		})
-		require.NoError(t, oerr, "create other policy %s", c.name)
-		t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polOther.Id) })
-	}
-
-	settings, err := srv.GetSettings(ctx)
-	require.NoError(t, err, "read settings")
-	require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned")
-
-	proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-pergroup-proxy")
-	require.NoError(t, err, "mint proxy token")
-	px, err := harness.StartProxy(ctx, srv, proxyToken)
-	require.NoError(t, err, "start proxy")
-	t.Cleanup(func() { _ = px.Terminate(context.Background()) })
-
-	cl, err := harness.StartClient(ctx, srv, sk.Key)
-	require.NoError(t, err, "start client")
-	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
-
-	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management")
-	proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint)
-	require.NoError(t, err, "resolve endpoint to proxy IP")
-	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
-		t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background()))
-	}
-
-	send := func(c *pergroupCase, model string) (int, string) {
-		var code int
-		var body string
-		var cerr error
-		switch c.wire {
-		case "vertex":
-			code, body, cerr = cl.Vertex(ctx, settings.Endpoint, proxyIP, vertexProject, vertexRegion, model, "Reply with exactly: pong", "")
-		case "bedrock":
-			code, body, cerr = cl.Bedrock(ctx, settings.Endpoint, proxyIP, model, "Reply with exactly: pong", "")
-		default:
-			code, body, cerr = cl.Chat(ctx, settings.Endpoint, proxyIP, c.wire, model, "Reply with exactly: pong", "")
-		}
-		require.NoError(t, cerr, "request must reach the proxy for %s", c.name)
-		return code, body
-	}
-
-	for _, c := range cases {
-		t.Run(c.name, func(t *testing.T) {
-			// grpMain's own model is served. Retry to absorb tunnel/DNS jitter on
-			// the first call over the freshly warmed tunnel.
-			var code int
-			var body string
-			deadline := time.Now().Add(90 * time.Second)
-			for time.Now().Before(deadline) {
-				code, body = send(c, c.selectedReq)
-				if code == 200 {
-					break
-				}
-				time.Sleep(5 * time.Second)
-			}
-			assert.Equal(t, 200, code,
-				"%s: grpMain's allowlisted model must be served; body: %s\n=== proxy logs ===\n%s", c.name, body, px.Logs(context.Background()))
-
-			// grpOther's model must NOT leak to the grpMain client.
-			code, body = send(c, c.otherReq)
-			assert.Equal(t, 403, code,
-				"%s: another group's allowlisted model must be denied for this caller; body: %s\n=== proxy logs ===\n%s", c.name, body, px.Logs(context.Background()))
-			assert.Contains(t, body, "llm_policy.model_blocked",
-				"%s: denial must be a model-allowlist decision, not routing; body: %s", c.name, body)
-		})
-	}
-}
-
-// TestGuardrailMultiGroupUser proves the per-policy/group decision for a caller
-// that belongs to MULTIPLE groups at once. Two scenarios, one shared stack:
-//
-//   - union across the user's groups: the client is in gUX and gUY, each with
-//     its own policy+guardrail on provider P1 (gUX->union-a, gUY->union-b). The
-//     client may use BOTH models (the union of its groups' allowlists) while a
-//     third, un-allowlisted model is denied.
-//   - an un-guardrailed group lifts the restriction: the client is in gMP and
-//     gMQ on provider P2, where gMP restricts to mix-a but gMQ's policy carries
-//     NO guardrail. Because one applicable policy is unrestricted, the client may
-//     use a model on no allowlist (mix-z) as well as mix-a.
-func TestGuardrailMultiGroupUser(t *testing.T) {
-	ctx, cancel := context.WithTimeout(context.Background(), 15*time.Minute)
-	defer cancel()
-
-	const (
-		unionA = "mg-union-a"
-		unionB = "mg-union-b"
-		unionC = "mg-union-c" // allowlisted by neither group
-		mixA   = "mg-mix-a"
-		mixZ   = "mg-mix-z" // on no allowlist; reachable only via the un-guardrailed policy
-	)
-
-	priced := func(ids ...string) *[]api.AgentNetworkProviderModel {
-		out := make([]api.AgentNetworkProviderModel, 0, len(ids))
-		for _, id := range ids {
-			out = append(out, api.AgentNetworkProviderModel{Id: id, InputPer1k: 0.001, OutputPer1k: 0.001})
-		}
-		return &out
-	}
-
-	vllm, err := harness.StartVLLM(ctx, srv)
-	require.NoError(t, err, "start mock upstream")
-	t.Cleanup(func() { _ = vllm.Terminate(context.Background()) })
-
-	mkGroup := func(name string) *api.Group {
-		g, gerr := srv.API().Groups.Create(ctx, api.PostApiGroupsJSONRequestBody{Name: name})
-		require.NoError(t, gerr, "create group %s", name)
-		t.Cleanup(func() { _ = srv.API().Groups.Delete(context.Background(), g.Id) })
-		return g
-	}
-	gUX := mkGroup("e2e-mg-union-x")
-	gUY := mkGroup("e2e-mg-union-y")
-	gMP := mkGroup("e2e-mg-mix-p")
-	gMQ := mkGroup("e2e-mg-mix-q")
-
-	ephemeral := false
-	sk, err := srv.API().SetupKeys.Create(ctx, api.PostApiSetupKeysJSONRequestBody{
-		Name:       "e2e-mg-client",
-		Type:       "reusable",
-		ExpiresIn:  86400,
-		UsageLimit: 0,
-		AutoGroups: []string{gUX.Id, gUY.Id, gMP.Id, gMQ.Id}, // client in all four groups
-		Ephemeral:  &ephemeral,
-	})
-	require.NoError(t, err, "mint setup key")
-	require.NotEmpty(t, sk.Key, "setup key plaintext")
-
-	staticKey := "static-e2e-token"
-	enabled := true
-
-	// P1 — union scenario: two restricting policies, one per group.
-	p1, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:             "e2e-mg-union",
-		ProviderId:       "openai_api",
-		UpstreamUrl:      vllm.URL,
-		ApiKey:           &staticKey,
-		Enabled:          ptr(true),
-		Models:           priced(unionA, unionB, unionC),
-		BootstrapCluster: ptr(harness.AgentNetworkCluster),
-	})
-	require.NoError(t, err, "create union provider")
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), p1.Id) })
-
-	polUX, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-mg-union-x",
-		Enabled:                &enabled,
-		SourceGroups:           []string{gUX.Id},
-		DestinationProviderIds: []string{p1.Id},
-		GuardrailIds:           &[]string{mkAllowGuardrail(t, ctx, "e2e-mg-union-x", unionA).Id},
-	})
-	require.NoError(t, err, "create union policy X")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polUX.Id) })
-
-	polUY, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-mg-union-y",
-		Enabled:                &enabled,
-		SourceGroups:           []string{gUY.Id},
-		DestinationProviderIds: []string{p1.Id},
-		GuardrailIds:           &[]string{mkAllowGuardrail(t, ctx, "e2e-mg-union-y", unionB).Id},
-	})
-	require.NoError(t, err, "create union policy Y")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polUY.Id) })
-
-	// P2 — mixed scenario: one restricting policy + one un-guardrailed policy.
-	p2, err := srv.CreateProvider(ctx, api.AgentNetworkProviderRequest{
-		Name:        "e2e-mg-mix",
-		ProviderId:  "openai_api",
-		UpstreamUrl: vllm.URL,
-		ApiKey:      &staticKey,
-		Enabled:     ptr(true),
-		Models:      priced(mixA, mixZ),
-	})
-	require.NoError(t, err, "create mix provider")
-	t.Cleanup(func() { _ = srv.DeleteProvider(context.Background(), p2.Id) })
-
-	polMP, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-mg-mix-p",
-		Enabled:                &enabled,
-		SourceGroups:           []string{gMP.Id},
-		DestinationProviderIds: []string{p2.Id},
-		GuardrailIds:           &[]string{mkAllowGuardrail(t, ctx, "e2e-mg-mix-p", mixA).Id},
-	})
-	require.NoError(t, err, "create mix policy P")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMP.Id) })
-
-	polMQ, err := srv.CreatePolicy(ctx, api.AgentNetworkPolicyRequest{
-		Name:                   "e2e-mg-mix-q",
-		Enabled:                &enabled,
-		SourceGroups:           []string{gMQ.Id},
-		DestinationProviderIds: []string{p2.Id}, // NO guardrail -> unrestricted
-	})
-	require.NoError(t, err, "create mix policy Q")
-	t.Cleanup(func() { _ = srv.DeletePolicy(context.Background(), polMQ.Id) })
-
-	settings, err := srv.GetSettings(ctx)
-	require.NoError(t, err, "read settings")
-	require.NotEmpty(t, settings.Endpoint, "endpoint must be assigned")
-
-	proxyToken, err := srv.CreateProxyTokenCLI(ctx, "e2e-mg-proxy")
-	require.NoError(t, err, "mint proxy token")
-	px, err := harness.StartProxy(ctx, srv, proxyToken)
-	require.NoError(t, err, "start proxy")
-	t.Cleanup(func() { _ = px.Terminate(context.Background()) })
-
-	cl, err := harness.StartClient(ctx, srv, sk.Key)
-	require.NoError(t, err, "start client")
-	t.Cleanup(func() { _ = cl.Terminate(context.Background()) })
-
-	require.NoError(t, cl.WaitConnected(ctx, 90*time.Second), "client must connect to management")
-	proxyIP, err := cl.ResolveProxyIP(ctx, settings.Endpoint)
-	require.NoError(t, err, "resolve endpoint to proxy IP")
-	if err := cl.WaitProxyPeer(ctx, 180*time.Second); err != nil {
-		t.Fatalf("client did not see the proxy peer: %v\n=== proxy logs ===\n%s", err, px.Logs(context.Background()))
-	}
-
-	send := func(model string) (int, string) {
-		code, body, cerr := cl.Chat(ctx, settings.Endpoint, proxyIP, harness.WireChat, model, "Reply with exactly: pong", "")
-		require.NoError(t, cerr, "request must reach the proxy")
-		return code, body
-	}
-	sendUntil200 := func(model string) (int, string) {
-		var code int
-		var body string
-		deadline := time.Now().Add(90 * time.Second)
-		for time.Now().Before(deadline) {
-			code, body = send(model)
-			if code == 200 {
-				break
-			}
-			time.Sleep(5 * time.Second)
-		}
-		return code, body
-	}
-
-	t.Run("union across the user's groups", func(t *testing.T) {
-		code, body := sendUntil200(unionA)
-		assert.Equal(t, 200, code, "model allowed by group X must be served; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-
-		code, body = sendUntil200(unionB)
-		assert.Equal(t, 200, code, "model allowed by group Y must also be served (union across the user's groups); body: %s", body)
-
-		code, body = send(unionC)
-		assert.Equal(t, 403, code, "a model on neither group's allowlist must be denied; body: %s", body)
-		assert.Contains(t, body, "llm_policy.model_blocked")
-	})
-
-	t.Run("an un-guardrailed group lifts the restriction", func(t *testing.T) {
-		code, body := sendUntil200(mixA)
-		assert.Equal(t, 200, code, "the restricted group's model must be served; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-
-		code, body = sendUntil200(mixZ)
-		assert.Equal(t, 200, code,
-			"a non-allowlisted model must be served because the user is also in a group whose policy has no guardrail; body: %s\n=== proxy logs ===\n%s", body, px.Logs(context.Background()))
-	})
-}
-
-// mkAllowGuardrail creates a guardrail whose model allowlist is enabled and holds
-// exactly the given model, registering cleanup.
-func mkAllowGuardrail(t *testing.T, ctx context.Context, name, model string) api.AgentNetworkGuardrail {
-	t.Helper()
-	var gr api.AgentNetworkGuardrailRequest
-	gr.Name = name
-	gr.Checks.ModelAllowlist.Enabled = true
-	gr.Checks.ModelAllowlist.Models = []string{model}
-	g, err := srv.CreateGuardrail(ctx, gr)
-	require.NoError(t, err, "create guardrail %s", name)
-	t.Cleanup(func() { _ = srv.DeleteGuardrail(context.Background(), g.Id) })
-	return g
-}

e2e/harness/proxy.go

@@ -38,11 +38,7 @@ type Proxy struct {
 // network, registered via the given account proxy token and serving the
 // AgentNetworkCluster over a self-signed wildcard cert. It does not wait for
 // peer connectivity — callers poll management for the proxy peer.
-// StartProxy launches the reverse-proxy container. Optional envOverrides are
-// merged into the container environment after the defaults, so callers can set
-// or override any NB_PROXY_* var (e.g. NB_PROXY_TUNNEL_CACHE_TTL for tests that
-// need a short authorization-cache window).
-func StartProxy(ctx context.Context, c *Combined, proxyToken string, envOverrides ...map[string]string) (*Proxy, error) {
+func StartProxy(ctx context.Context, c *Combined, proxyToken string) (*Proxy, error) {
 	root, err := repoRoot()
 	if err != nil {
 		return nil, err
@@ -97,12 +93,6 @@ func StartProxy(ctx context.Context, c *Combined, proxyToken string, envOverride
 		WaitingFor: wait.ForLog("Initial mapping sync complete").WithStartupTimeout(90 * time.Second),
 	}
 
-	for _, ov := range envOverrides {
-		for k, v := range ov {
-			req.Env[k] = v
-		}
-	}
-
 	ctr, err := testcontainers.GenericContainer(ctx, testcontainers.GenericContainerRequest{
 		ContainerRequest: req,
 		Started:          true,

infrastructure_files/getting-started-with-dex.sh

@@ -1,19 +1,557 @@
-#!/usr/bin/env bash
+#!/bin/bash
 
-cat >&2 <<'EOF'
-ERROR: This legacy installation script has been retired and no longer runs.
+set -e
 
-Dex support is not deprecated. For new deployments, use getting-started.sh:
+# NetBird Getting Started with Dex IDP
+# This script sets up NetBird with Dex as the identity provider
 
-https://docs.netbird.io/selfhosted/selfhosted-quickstart
+# Sed pattern to strip base64 padding characters
+SED_STRIP_PADDING='s/=//g'
 
-The current installer includes NetBird's embedded Dex-based identity provider.
-Local users and external identity providers can be managed through the
-NetBird Dashboard:
+check_docker_compose() {
+  if command -v docker-compose &> /dev/null
+  then
+      echo "docker-compose"
+      return
+  fi
+  if docker compose --help &> /dev/null
+  then
+      echo "docker compose"
+      return
+  fi
 
-https://docs.netbird.io/selfhosted/identity-providers/local
+  echo "docker-compose is not installed or not in PATH. Please follow the steps from the official guide: https://docs.docker.com/engine/install/" > /dev/stderr
+  exit 1
+}
 
-This compatibility notice will be removed in NetBird v0.80.
+check_jq() {
+  if ! command -v jq &> /dev/null
+  then
+    echo "jq is not installed or not in PATH, please install with your package manager. e.g. sudo apt install jq" > /dev/stderr
+    exit 1
+  fi
+  return 0
+}
+
+get_main_ip_address() {
+  if [[ "$OSTYPE" == "darwin"* ]]; then
+    interface=$(route -n get default | grep 'interface:' | awk '{print $2}')
+    ip_address=$(ifconfig "$interface" | grep 'inet ' | awk '{print $2}')
+  else
+    interface=$(ip route | grep default | awk '{print $5}' | head -n 1)
+    ip_address=$(ip addr show "$interface" | grep 'inet ' | awk '{print $2}' | cut -d'/' -f1)
+  fi
+
+  echo "$ip_address"
+  return 0
+}
+
+check_nb_domain() {
+  DOMAIN=$1
+  if [[ "$DOMAIN-x" == "-x" ]]; then
+    echo "The NETBIRD_DOMAIN variable cannot be empty." > /dev/stderr
+    return 1
+  fi
+
+  if [[ "$DOMAIN" == "netbird.example.com" ]]; then
+    echo "The NETBIRD_DOMAIN cannot be netbird.example.com" > /dev/stderr
+    return 1
+  fi
+  return 0
+}
+
+read_nb_domain() {
+  READ_NETBIRD_DOMAIN=""
+  echo -n "Enter the domain you want to use for NetBird (e.g. netbird.my-domain.com): " > /dev/stderr
+  read -r READ_NETBIRD_DOMAIN < /dev/tty
+  if ! check_nb_domain "$READ_NETBIRD_DOMAIN"; then
+    read_nb_domain
+  fi
+  echo "$READ_NETBIRD_DOMAIN"
+  return 0
+}
+
+get_turn_external_ip() {
+  TURN_EXTERNAL_IP_CONFIG="#external-ip="
+  IP=$(curl -s -4 https://jsonip.com | jq -r '.ip')
+  if [[ "x-$IP" != "x-" ]]; then
+    TURN_EXTERNAL_IP_CONFIG="external-ip=$IP"
+  fi
+  echo "$TURN_EXTERNAL_IP_CONFIG"
+  return 0
+}
+
+wait_dex() {
+  set +e
+  echo -n "Waiting for Dex to become ready (via $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN)"
+  counter=1
+  while true; do
+    # Check Dex through Caddy proxy (also validates TLS is working)
+    if curl -sk -f -o /dev/null "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex/.well-known/openid-configuration" 2>/dev/null; then
+      break
+    fi
+    if [[ $counter -eq 60 ]]; then
+      echo ""
+      echo "Taking too long. Checking logs..."
+      $DOCKER_COMPOSE_COMMAND logs --tail=20 caddy
+      $DOCKER_COMPOSE_COMMAND logs --tail=20 dex
+    fi
+    echo -n " ."
+    sleep 2
+    counter=$((counter + 1))
+  done
+  echo " done"
+  set -e
+  return 0
+}
+
+init_environment() {
+  CADDY_SECURE_DOMAIN=""
+  NETBIRD_PORT=80
+  NETBIRD_HTTP_PROTOCOL="http"
+  NETBIRD_RELAY_PROTO="rel"
+  TURN_USER="self"
+  TURN_PASSWORD=$(openssl rand -base64 32 | sed "$SED_STRIP_PADDING")
+  NETBIRD_RELAY_AUTH_SECRET=$(openssl rand -base64 32 | sed "$SED_STRIP_PADDING")
+  TURN_MIN_PORT=49152
+  TURN_MAX_PORT=65535
+  TURN_EXTERNAL_IP_CONFIG=$(get_turn_external_ip)
+
+  # Generate secrets for Dex
+  DEX_DASHBOARD_CLIENT_SECRET=$(openssl rand -base64 32 | sed "$SED_STRIP_PADDING")
+
+  # Generate admin password
+  NETBIRD_ADMIN_PASSWORD=$(openssl rand -base64 16 | sed "$SED_STRIP_PADDING")
+
+  if ! check_nb_domain "$NETBIRD_DOMAIN"; then
+    NETBIRD_DOMAIN=$(read_nb_domain)
+  fi
+
+  if [[ "$NETBIRD_DOMAIN" == "use-ip" ]]; then
+    NETBIRD_DOMAIN=$(get_main_ip_address)
+  else
+    NETBIRD_PORT=443
+    CADDY_SECURE_DOMAIN=", $NETBIRD_DOMAIN:$NETBIRD_PORT"
+    NETBIRD_HTTP_PROTOCOL="https"
+    NETBIRD_RELAY_PROTO="rels"
+  fi
+
+  check_jq
+
+  DOCKER_COMPOSE_COMMAND=$(check_docker_compose)
+
+  if [[ -f dex.yaml ]]; then
+    echo "Generated files already exist, if you want to reinitialize the environment, please remove them first."
+    echo "You can use the following commands:"
+    echo "  $DOCKER_COMPOSE_COMMAND down --volumes # to remove all containers and volumes"
+    echo "  rm -f docker-compose.yml Caddyfile dex.yaml dashboard.env turnserver.conf management.json relay.env"
+    echo "Be aware that this will remove all data from the database, and you will have to reconfigure the dashboard."
+    exit 1
+  fi
+
+  echo Rendering initial files...
+  render_docker_compose > docker-compose.yml
+  render_caddyfile > Caddyfile
+  render_dex_config > dex.yaml
+  render_dashboard_env > dashboard.env
+  render_management_json > management.json
+  render_turn_server_conf > turnserver.conf
+  render_relay_env > relay.env
+
+  echo -e "\nStarting Dex IDP\n"
+  $DOCKER_COMPOSE_COMMAND up -d caddy dex
+
+  # Wait for Dex to be ready (through caddy proxy)
+  sleep 3
+  wait_dex
+
+  echo -e "\nStarting NetBird services\n"
+  $DOCKER_COMPOSE_COMMAND up -d
+
+  echo -e "\nDone!\n"
+  echo "You can access the NetBird dashboard at $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN"
+  echo ""
+  echo "Login with the following credentials:"
+  install -m 600 /dev/null .env
+  printf 'Email: admin@%s\nPassword: %s\n' \
+      "$NETBIRD_DOMAIN" "$NETBIRD_ADMIN_PASSWORD" >> .env
+  echo "Email: admin@$NETBIRD_DOMAIN"
+  echo "Password: $NETBIRD_ADMIN_PASSWORD"
+  echo ""
+  echo "Dex admin UI is not available (Dex has no built-in UI)."
+  echo "To add more users, edit dex.yaml and restart: $DOCKER_COMPOSE_COMMAND restart dex"
+  return 0
+}
+
+render_caddyfile() {
+  cat <<EOF
+{
+  debug
+  servers :80,:443 {
+    protocols h1 h2c h2 h3
+  }
+}
+
+(security_headers) {
+    header * {
+        Strict-Transport-Security "max-age=3600; includeSubDomains; preload"
+        X-Content-Type-Options "nosniff"
+        X-Frame-Options "SAMEORIGIN"
+        X-XSS-Protection "1; mode=block"
+        -Server
+        Referrer-Policy strict-origin-when-cross-origin
+    }
+}
+
+:80${CADDY_SECURE_DOMAIN} {
+    import security_headers
+    # Relay
+    reverse_proxy /relay* relay:80
+    # Signal
+    reverse_proxy /signalexchange.SignalExchange/* h2c://signal:10000
+    # Management
+    reverse_proxy /api/* management:80
+    reverse_proxy /management.ManagementService/* h2c://management:80
+    # Dex
+    reverse_proxy /dex/* dex:5556
+    # Dashboard
+    reverse_proxy /* dashboard:80
+}
 EOF
+  return 0
+}
 
-exit 1
+render_dex_config() {
+  # Generate bcrypt hash of the admin password
+  # Using a simple approach - htpasswd or python if available
+  ADMIN_PASSWORD_HASH=""
+  if command -v htpasswd &> /dev/null; then
+    ADMIN_PASSWORD_HASH=$(htpasswd -bnBC 10 "" "$NETBIRD_ADMIN_PASSWORD" | tr -d ':\n')
+  elif command -v python3 &> /dev/null; then
+    ADMIN_PASSWORD_HASH=$(python3 -c "import bcrypt; print(bcrypt.hashpw('$NETBIRD_ADMIN_PASSWORD'.encode(), bcrypt.gensalt(rounds=10)).decode())" 2>/dev/null || echo "")
+  fi
+
+  # Fallback to a known hash if we can't generate one
+  if [[ -z "$ADMIN_PASSWORD_HASH" ]]; then
+    # This is hash of "password" - user should change it
+    ADMIN_PASSWORD_HASH='$2a$10$2b2cU8CPhOTaGrs1HRQuAueS7JTT5ZHsHSzYiFPm1leZck7Mc8T4W'
+    NETBIRD_ADMIN_PASSWORD="password"
+    echo "Warning: Could not generate password hash. Using default password: password. Please change it in dex.yaml" > /dev/stderr
+  fi
+
+  cat <<EOF
+# Dex configuration for NetBird
+# Generated by getting-started-with-dex.sh
+
+issuer: $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex
+
+storage:
+  type: sqlite3
+  config:
+    file: /var/dex/dex.db
+
+web:
+  http: 0.0.0.0:5556
+
+# gRPC API for user management (used by NetBird IDP manager)
+grpc:
+  addr: 0.0.0.0:5557
+
+oauth2:
+  skipApprovalScreen: true
+
+# Static OAuth2 clients for NetBird
+staticClients:
+  # Dashboard client
+  - id: netbird-dashboard
+    name: NetBird Dashboard
+    secret: $DEX_DASHBOARD_CLIENT_SECRET
+    redirectURIs:
+      - $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/nb-auth
+      - $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/nb-silent-auth
+
+  # CLI client (public - uses PKCE)
+  - id: netbird-cli
+    name: NetBird CLI
+    public: true
+    redirectURIs:
+      - http://localhost:53000/
+      - http://localhost:54000/
+
+# Enable password database for static users
+enablePasswordDB: true
+
+# Static users - add more users here as needed
+staticPasswords:
+  - email: "admin@$NETBIRD_DOMAIN"
+    hash: "$ADMIN_PASSWORD_HASH"
+    username: "admin"
+    userID: "$(uuidgen 2>/dev/null || cat /proc/sys/kernel/random/uuid 2>/dev/null || echo "admin-user-id-001")"
+
+# Optional: Add external identity provider connectors
+# connectors:
+#   - type: github
+#     id: github
+#     name: GitHub
+#     config:
+#       clientID: \$GITHUB_CLIENT_ID
+#       clientSecret: \$GITHUB_CLIENT_SECRET
+#       redirectURI: $NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex/callback
+#
+#   - type: ldap
+#     id: ldap
+#     name: LDAP
+#     config:
+#       host: ldap.example.com:636
+#       insecureNoSSL: false
+#       bindDN: cn=admin,dc=example,dc=com
+#       bindPW: admin
+#       userSearch:
+#         baseDN: ou=users,dc=example,dc=com
+#         filter: "(objectClass=person)"
+#         username: uid
+#         idAttr: uid
+#         emailAttr: mail
+#         nameAttr: cn
+EOF
+  return 0
+}
+
+render_turn_server_conf() {
+  cat <<EOF
+listening-port=3478
+$TURN_EXTERNAL_IP_CONFIG
+tls-listening-port=5349
+min-port=$TURN_MIN_PORT
+max-port=$TURN_MAX_PORT
+fingerprint
+lt-cred-mech
+user=$TURN_USER:$TURN_PASSWORD
+realm=wiretrustee.com
+cert=/etc/coturn/certs/cert.pem
+pkey=/etc/coturn/private/privkey.pem
+log-file=stdout
+no-software-attribute
+pidfile="/var/tmp/turnserver.pid"
+no-cli
+EOF
+  return 0
+}
+
+render_management_json() {
+  cat <<EOF
+{
+    "Stuns": [
+        {
+            "Proto": "udp",
+            "URI": "stun:$NETBIRD_DOMAIN:3478"
+        }
+    ],
+    "Relay": {
+        "Addresses": ["$NETBIRD_RELAY_PROTO://$NETBIRD_DOMAIN:$NETBIRD_PORT"],
+        "CredentialsTTL": "24h",
+        "Secret": "$NETBIRD_RELAY_AUTH_SECRET"
+    },
+    "Signal": {
+        "Proto": "$NETBIRD_HTTP_PROTOCOL",
+        "URI": "$NETBIRD_DOMAIN:$NETBIRD_PORT"
+    },
+    "HttpConfig": {
+        "AuthIssuer": "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex",
+        "AuthAudience": "netbird-dashboard",
+        "OIDCConfigEndpoint": "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex/.well-known/openid-configuration"
+    },
+    "IdpManagerConfig": {
+        "ManagerType": "dex",
+        "ClientConfig": {
+            "Issuer": "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex"
+        },
+        "ExtraConfig": {
+            "GRPCAddr": "dex:5557"
+        }
+    },
+    "DeviceAuthorizationFlow": {
+        "Provider": "hosted",
+        "ProviderConfig": {
+            "Audience": "netbird-cli",
+            "ClientID": "netbird-cli",
+            "Scope": "openid profile email offline_access",
+            "DeviceAuthEndpoint": "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex/device/code",
+            "TokenEndpoint": "$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex/token"
+        }
+    },
+    "PKCEAuthorizationFlow": {
+        "ProviderConfig": {
+            "Audience": "netbird-cli",
+            "ClientID": "netbird-cli",
+            "Scope": "openid profile email offline_access",
+            "RedirectURLs": ["http://localhost:53000/", "http://localhost:54000/"]
+        }
+    }
+}
+EOF
+  return 0
+}
+
+render_dashboard_env() {
+  cat <<EOF
+# Endpoints
+NETBIRD_MGMT_API_ENDPOINT=$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN
+NETBIRD_MGMT_GRPC_API_ENDPOINT=$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN
+# OIDC
+AUTH_AUDIENCE=netbird-dashboard
+AUTH_CLIENT_ID=netbird-dashboard
+AUTH_CLIENT_SECRET=$DEX_DASHBOARD_CLIENT_SECRET
+AUTH_AUTHORITY=$NETBIRD_HTTP_PROTOCOL://$NETBIRD_DOMAIN/dex
+USE_AUTH0=false
+AUTH_SUPPORTED_SCOPES=openid profile email offline_access
+AUTH_REDIRECT_URI=/nb-auth
+AUTH_SILENT_REDIRECT_URI=/nb-silent-auth
+# SSL
+NGINX_SSL_PORT=443
+# Letsencrypt
+LETSENCRYPT_DOMAIN=none
+EOF
+  return 0
+}
+
+render_relay_env() {
+  cat <<EOF
+NB_LOG_LEVEL=info
+NB_LISTEN_ADDRESS=:80
+NB_EXPOSED_ADDRESS=$NETBIRD_RELAY_PROTO://$NETBIRD_DOMAIN:$NETBIRD_PORT
+NB_AUTH_SECRET=$NETBIRD_RELAY_AUTH_SECRET
+EOF
+  return 0
+}
+
+render_docker_compose() {
+  cat <<EOF
+services:
+  # Caddy reverse proxy
+  caddy:
+    image: caddy
+    container_name: netbird-caddy
+    restart: unless-stopped
+    networks: [netbird]
+    ports:
+      - '443:443'
+      - '443:443/udp'
+      - '80:80'
+    volumes:
+      - netbird_caddy_data:/data
+      - ./Caddyfile:/etc/caddy/Caddyfile
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # Dex - identity provider
+  dex:
+    image: ghcr.io/dexidp/dex:v2.38.0
+    container_name: netbird-dex
+    restart: unless-stopped
+    networks: [netbird]
+    volumes:
+      - ./dex.yaml:/etc/dex/config.docker.yaml:ro
+      - netbird_dex_data:/var/dex
+    command: ["dex", "serve", "/etc/dex/config.docker.yaml"]
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # UI dashboard
+  dashboard:
+    image: netbirdio/dashboard:latest
+    container_name: netbird-dashboard
+    restart: unless-stopped
+    networks: [netbird]
+    env_file:
+      - ./dashboard.env
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # Signal
+  signal:
+    image: netbirdio/signal:latest
+    container_name: netbird-signal
+    restart: unless-stopped
+    networks: [netbird]
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # Relay
+  relay:
+    image: netbirdio/relay:latest
+    container_name: netbird-relay
+    restart: unless-stopped
+    networks: [netbird]
+    env_file:
+      - ./relay.env
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # Management
+  management:
+    image: netbirdio/management:latest
+    container_name: netbird-management
+    restart: unless-stopped
+    networks: [netbird]
+    volumes:
+      - netbird_management:/var/lib/netbird
+      - ./management.json:/etc/netbird/management.json
+    command: [
+      "--port", "80",
+      "--log-file", "console",
+      "--log-level", "info",
+      "--disable-anonymous-metrics=false",
+      "--single-account-mode-domain=netbird.selfhosted",
+      "--dns-domain=netbird.selfhosted",
+      "--idp-sign-key-refresh-enabled",
+    ]
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+  # Coturn, AKA TURN server
+  coturn:
+    image: coturn/coturn
+    container_name: netbird-coturn
+    restart: unless-stopped
+    volumes:
+      - ./turnserver.conf:/etc/turnserver.conf:ro
+    network_mode: host
+    command:
+      - -c /etc/turnserver.conf
+    logging:
+      driver: "json-file"
+      options:
+        max-size: "500m"
+        max-file: "2"
+
+volumes:
+  netbird_caddy_data:
+  netbird_dex_data:
+  netbird_management:
+
+networks:
+  netbird:
+EOF
+  return 0
+}
+
+init_environment

management/internals/modules/agentnetwork/manager.go

@@ -86,17 +86,12 @@ type Manager interface {
 
 // PolicySelectionInput is the per-request selection envelope. The
 // proxy populates it from CapturedData (account, user, groups) plus
-// the provider llm_router resolved and the model it extracted.
+// the provider llm_router resolved.
 type PolicySelectionInput struct {
 	AccountID  string
 	UserID     string
 	GroupIDs   []string
 	ProviderID string
-	// Model is the already-normalised upstream model id the proxy extracted
-	// (parser strips Bedrock region/version, Vertex @version), so a
-	// case-insensitive compare suffices. Empty = undetermined → not permitted
-	// (fail closed).
-	Model string
 }
 
 // PolicySelectionResult names the policy that "pays" for this request

management/internals/modules/agentnetwork/policyselect.go

@@ -5,7 +5,6 @@ import (
 	"fmt"
 	"math"
 	"sort"
-	"strings"
 	"time"
 
 	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
@@ -36,10 +35,6 @@ const (
 	denyCodeAccountTokenCapExceeded = "llm_account.token_cap_exceeded"
 	//nolint:gosec // account deny code label, not a credential
 	denyCodeAccountBudgetCapExceeded = "llm_account.budget_cap_exceeded"
-	// denyCodeModelBlocked is returned when policies govern the request's
-	// (provider, caller-groups) but none permits the model. Matches the proxy
-	// guardrail's code so both layers surface the same label.
-	denyCodeModelBlocked = "llm_policy.model_blocked"
 )
 
 // consumptionCache holds the consumption counters prefetched for one
@@ -164,25 +159,6 @@ func (m *managerImpl) SelectPolicyForRequest(ctx context.Context, in PolicySelec
 	}
 	candidates := filterApplicablePolicies(policies, in)
 
-	// Model-allowlist gate scoped to the matched policies: keep candidates whose
-	// guardrails permit the model (none enabled = unrestricted), deny when
-	// policies apply but none permits it. Skip the load when none has a guardrail.
-	if len(candidates) > 0 && anyPolicyHasGuardrails(candidates) {
-		guardrailsByID, gErr := m.loadGuardrailsByID(ctx, in.AccountID)
-		if gErr != nil {
-			return nil, gErr
-		}
-		permitted := filterModelPermittedPolicies(candidates, guardrailsByID, in.Model)
-		if len(permitted) == 0 {
-			return &PolicySelectionResult{
-				Allow:      false,
-				DenyCode:   denyCodeModelBlocked,
-				DenyReason: modelBlockedReason(in.Model),
-			}, nil
-		}
-		candidates = permitted
-	}
-
 	// Prefetch every consumption counter the ceiling + candidate policies will
 	// read, in a single store round-trip, then score against the cache.
 	cache, err := m.prefetchConsumption(ctx, in, rules, candidates, now)
@@ -274,90 +250,6 @@ func filterApplicablePolicies(policies []*types.Policy, in PolicySelectionInput)
 	return out
 }
 
-// anyPolicyHasGuardrails reports whether any policy references at least one
-// guardrail, so the selector can skip loading guardrails when none do.
-func anyPolicyHasGuardrails(policies []*types.Policy) bool {
-	for _, p := range policies {
-		if p != nil && len(p.GuardrailIDs) > 0 {
-			return true
-		}
-	}
-	return false
-}
-
-// loadGuardrailsByID loads the account's guardrails indexed by ID. Used by the
-// model-allowlist gate to resolve each candidate policy's attached guardrails.
-func (m *managerImpl) loadGuardrailsByID(ctx context.Context, accountID string) (map[string]*types.Guardrail, error) {
-	guardrails, err := m.store.GetAccountAgentNetworkGuardrails(ctx, store.LockingStrengthNone, accountID)
-	if err != nil {
-		return nil, fmt.Errorf("list account guardrails: %w", err)
-	}
-	byID := make(map[string]*types.Guardrail, len(guardrails))
-	for _, g := range guardrails {
-		if g != nil {
-			byID[g.ID] = g
-		}
-	}
-	return byID, nil
-}
-
-// filterModelPermittedPolicies returns the subset of policies whose guardrails
-// permit the model. Order is preserved so downstream scoring is unaffected.
-func filterModelPermittedPolicies(policies []*types.Policy, byID map[string]*types.Guardrail, model string) []*types.Policy {
-	out := make([]*types.Policy, 0, len(policies))
-	for _, p := range policies {
-		if policyPermitsModel(p, byID, model) {
-			out = append(out, p)
-		}
-	}
-	return out
-}
-
-// policyPermitsModel reports whether a policy permits the model. No
-// allowlist-enabled guardrail = unrestricted (permits any, incl. empty);
-// otherwise the model must be in the union of its allowlists, so an
-// empty/undetermined model fails closed.
-func policyPermitsModel(p *types.Policy, byID map[string]*types.Guardrail, model string) bool {
-	if p == nil {
-		return false
-	}
-	wanted := normaliseModelID(model)
-	restricted := false
-	for _, gID := range p.GuardrailIDs {
-		g, ok := byID[gID]
-		if !ok || g == nil || !g.Checks.ModelAllowlist.Enabled {
-			continue
-		}
-		restricted = true
-		if wanted == "" {
-			continue
-		}
-		for _, allowed := range g.Checks.ModelAllowlist.Models {
-			if normaliseModelID(allowed) == wanted {
-				return true
-			}
-		}
-	}
-	return !restricted
-}
-
-// normaliseModelID lowercases and trims a model identifier so the allowlist
-// compare is case-insensitive and trim-tolerant. Mirrors the proxy guardrail's
-// normaliseModel so both layers agree on what "same model" means.
-func normaliseModelID(model string) string {
-	return strings.ToLower(strings.TrimSpace(model))
-}
-
-// modelBlockedReason builds the human-readable deny reason for a model-allowlist
-// rejection. The model is quoted when known; an undetermined model is reported
-// as such so the access log distinguishes "wrong model" from "no model".
-func modelBlockedReason(model string) string {
-	if normaliseModelID(model) == "" {
-		return "request model could not be determined for the policy allowlist"
-	}
-	return fmt.Sprintf("model %q is not permitted by any applicable policy allowlist", model)
-}
-
 // candidate is the per-policy intermediate the selector ranks. A
 // policy that's been exhausted on any enabled cap never makes it
 // into this slice; the selector's deny envelope carries the latest

management/internals/modules/agentnetwork/policyselect_model_test.go

@@ -1,329 +0,0 @@
-package agentnetwork
-
-import (
-	"context"
-	"errors"
-	"testing"
-	"time"
-
-	"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/store"
-)
-
-// guardedPolicy builds an enabled, uncapped policy that authorises sourceGroups
-// to reach providerID under the given guardrails. Uncapped keeps the selector's
-// headroom scoring trivial so these tests isolate the model-allowlist gate.
-func guardedPolicy(id, account string, sourceGroups []string, providerID string, guardrailIDs ...string) *types.Policy {
-	return &types.Policy{
-		ID:                     id,
-		AccountID:              account,
-		Enabled:                true,
-		SourceGroups:           sourceGroups,
-		DestinationProviderIDs: []string{providerID},
-		GuardrailIDs:           guardrailIDs,
-		CreatedAt:              time.Now().UTC(),
-	}
-}
-
-// allowlistGuardrail builds a guardrail whose model allowlist is enabled and
-// carries the given models.
-func allowlistGuardrail(id, account string, models ...string) *types.Guardrail {
-	return &types.Guardrail{
-		ID:        id,
-		AccountID: account,
-		Checks: types.GuardrailChecks{
-			ModelAllowlist: types.GuardrailModelAllowlist{Enabled: true, Models: models},
-		},
-	}
-}
-
-func expectPolicies(mockStore *store.MockStore, account string, policies ...*types.Policy) {
-	mockStore.EXPECT().
-		GetAccountAgentNetworkPolicies(gomock.Any(), gomock.Any(), account).
-		Return(policies, nil)
-}
-
-func expectGuardrails(mockStore *store.MockStore, account string, guardrails ...*types.Guardrail) {
-	mockStore.EXPECT().
-		GetAccountAgentNetworkGuardrails(gomock.Any(), gomock.Any(), account).
-		Return(guardrails, nil)
-}
-
-// TestSelectPolicy_ModelBlockedByAllowlist proves the authoritative allowlist
-// decision: a policy authorises the (provider, group) but restricts the model,
-// and the requested model isn't on the list, so the request is denied.
-func TestSelectPolicy_ModelBlockedByAllowlist(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		UserID:     "user-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4",
-	})
-	require.NoError(t, err)
-	assert.False(t, res.Allow, "a model outside the only applicable policy's allowlist must be denied")
-	assert.Equal(t, denyCodeModelBlocked, res.DenyCode, "deny code must be model_blocked")
-	assert.NotEmpty(t, res.DenyReason, "deny reason must be populated")
-}
-
-// TestSelectPolicy_ModelAllowedByAllowlist is the allow counterpart: the model
-// is on the applicable policy's allowlist, so selection proceeds normally.
-func TestSelectPolicy_ModelAllowedByAllowlist(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o", "claude-opus-4"))
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		UserID:     "user-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4",
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "a model on the applicable policy's allowlist must be allowed")
-	assert.Equal(t, "pol-A", res.SelectedPolicyID)
-}
-
-// TestSelectPolicy_CaseInsensitiveModelMatch proves the compare tolerates case
-// and surrounding whitespace, matching the proxy guardrail's normalisation.
-func TestSelectPolicy_CaseInsensitiveModelMatch(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "  GPT-4o  "))
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "gpt-4o",
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "case/whitespace variants must match the allowlist entry")
-}
-
-// TestSelectPolicy_UnguardedPolicyIsUnrestricted is the false-deny fix: when two
-// policies authorise the same (provider, group) and one has no guardrail, that
-// policy makes the request unrestricted — not caught by the other's allowlist.
-func TestSelectPolicy_UnguardedPolicyIsUnrestricted(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	restricted := guardedPolicy("pol-restricted", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	open := guardedPolicy("pol-open", "acc-1", []string{"grp-eng"}, "prov-1") // no guardrail
-	expectPolicies(mockStore, "acc-1", restricted, open)
-	expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4",
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "an un-guardrailed policy for the same (provider, group) must leave the request unrestricted")
-	assert.Equal(t, "pol-open", res.SelectedPolicyID, "the unrestricted policy must be the one that pays")
-}
-
-// TestSelectPolicy_AllowlistDoesNotLeakAcrossGroups is the false-allow fix: a
-// model allowlisted only for grp-b must not be usable by a grp-a caller. The
-// selector considers only policies applicable to the caller's groups.
-func TestSelectPolicy_AllowlistDoesNotLeakAcrossGroups(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	polA := guardedPolicy("pol-a", "acc-1", []string{"grp-a"}, "prov-1", "g-a")
-	polB := guardedPolicy("pol-b", "acc-1", []string{"grp-b"}, "prov-1", "g-b")
-	expectPolicies(mockStore, "acc-1", polA, polB)
-	expectGuardrails(mockStore, "acc-1",
-		allowlistGuardrail("g-a", "acc-1", "gpt-4o"),
-		allowlistGuardrail("g-b", "acc-1", "claude-opus-4"),
-	)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-a"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4", // only allowed for grp-b
-	})
-	require.NoError(t, err)
-	assert.False(t, res.Allow, "grp-b's allowlisted model must not leak to a grp-a caller")
-	assert.Equal(t, denyCodeModelBlocked, res.DenyCode)
-}
-
-// TestSelectPolicy_UndeterminedModelFailsClosed proves the fail-closed contract
-// mirrors the proxy: with a restricted applicable policy and an empty model
-// (e.g. a path-routed shape the parser couldn't map), the request is denied.
-func TestSelectPolicy_UndeterminedModelFailsClosed(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1", allowlistGuardrail("g-1", "acc-1", "gpt-4o"))
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "", // undetermined
-	})
-	require.NoError(t, err)
-	assert.False(t, res.Allow, "an undetermined model must fail closed against a restricted policy")
-	assert.Equal(t, denyCodeModelBlocked, res.DenyCode)
-}
-
-// TestSelectPolicy_DisabledAllowlistDoesNotRestrict proves a guardrail whose
-// model allowlist is disabled imposes no model restriction, even though the
-// policy references it.
-func TestSelectPolicy_DisabledAllowlistDoesNotRestrict(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	disabled := &types.Guardrail{
-		ID:        "g-1",
-		AccountID: "acc-1",
-		Checks: types.GuardrailChecks{
-			ModelAllowlist: types.GuardrailModelAllowlist{Enabled: false, Models: []string{"gpt-4o"}},
-		},
-	}
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1", disabled)
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "anything-goes",
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "a disabled allowlist must not restrict the model")
-	assert.Equal(t, "pol-A", res.SelectedPolicyID)
-}
-
-// TestSelectPolicy_UnionAcrossPolicyGuardrails proves a policy with multiple
-// allowlist guardrails permits the union of their models (not just the first).
-func TestSelectPolicy_UnionAcrossPolicyGuardrails(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1", "g-2")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1",
-		allowlistGuardrail("g-1", "acc-1", "gpt-4o"),
-		allowlistGuardrail("g-2", "acc-1", "claude-opus-4"),
-	)
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4", // only in the second guardrail's list
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "a model in any of the policy's allowlist guardrails must be permitted")
-	assert.Equal(t, "pol-A", res.SelectedPolicyID)
-}
-
-// TestSelectPolicy_GuardrailLookupErrorPropagates proves a store failure while
-// resolving the candidate policies' guardrails surfaces as an error, not a
-// silent allow/deny.
-func TestSelectPolicy_GuardrailLookupErrorPropagates(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-1")
-	expectPolicies(mockStore, "acc-1", policy)
-	mockStore.EXPECT().
-		GetAccountAgentNetworkGuardrails(gomock.Any(), gomock.Any(), "acc-1").
-		Return(nil, errors.New("store unavailable"))
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "gpt-4o",
-	})
-	require.Error(t, err, "a guardrail-lookup failure must surface as an error")
-	assert.Nil(t, res)
-}
-
-// TestSelectPolicy_MissingGuardrailReferenceTreatedAsUnrestricted proves a
-// policy referencing a guardrail ID absent from the account's set (a stale
-// reference) imposes no model restriction — same as no guardrail.
-func TestSelectPolicy_MissingGuardrailReferenceTreatedAsUnrestricted(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	policy := guardedPolicy("pol-A", "acc-1", []string{"grp-eng"}, "prov-1", "g-missing")
-	expectPolicies(mockStore, "acc-1", policy)
-	expectGuardrails(mockStore, "acc-1")
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "anything-goes",
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow, "an orphaned guardrail reference must not restrict the model")
-	assert.Equal(t, "pol-A", res.SelectedPolicyID)
-}
-
-// TestSelectPolicy_PartialCandidatesPermittedAfterModelFilter proves the model
-// gate narrows candidates before cap scoring: the permitting policy is selected
-// even though the blocked one has a larger, more attractive cap.
-func TestSelectPolicy_PartialCandidatesPermittedAfterModelFilter(t *testing.T) {
-	ctrl := gomock.NewController(t)
-	mgr, mockStore := newSelectorMgr(t, ctrl)
-
-	polBig := guardedPolicy("pol-big", "acc-1", []string{"grp-eng"}, "prov-1", "g-restrict")
-	polBig.Limits = types.PolicyLimits{
-		TokenLimit: types.PolicyTokenLimit{Enabled: true, GroupCap: 1_000_000, WindowSeconds: 3600},
-	}
-	polSmall := guardedPolicy("pol-small", "acc-1", []string{"grp-eng"}, "prov-1", "g-permit")
-	polSmall.Limits = types.PolicyLimits{
-		TokenLimit: types.PolicyTokenLimit{Enabled: true, GroupCap: 100, WindowSeconds: 3600},
-	}
-	expectPolicies(mockStore, "acc-1", polBig, polSmall)
-	expectGuardrails(mockStore, "acc-1",
-		allowlistGuardrail("g-restrict", "acc-1", "gpt-4o"),
-		allowlistGuardrail("g-permit", "acc-1", "claude-opus-4"),
-	)
-	expectConsumptionBatch(mockStore, nil)
-
-	res, err := mgr.SelectPolicyForRequest(context.Background(), PolicySelectionInput{
-		AccountID:  "acc-1",
-		GroupIDs:   []string{"grp-eng"},
-		ProviderID: "prov-1",
-		Model:      "claude-opus-4", // only pol-small's guardrail permits this
-	})
-	require.NoError(t, err)
-	assert.True(t, res.Allow)
-	assert.Equal(t, "pol-small", res.SelectedPolicyID,
-		"the model filter must exclude pol-big before cap scoring")
-}

management/internals/modules/agentnetwork/synthesizer.go

@@ -235,12 +235,7 @@ func SynthesizeServices(ctx context.Context, s store.Store, accountID string) ([
 
 	mergedGuardrails := mergeGuardrails(enabledPolicies, guardrailsByID)
 	applyAccountCollectionControls(&mergedGuardrails, settings)
-	// The proxy guardrail is a per-provider fail-closed backstop; the
-	// authoritative per-policy/group decision is management's
-	// SelectPolicyForRequest. A provider lands in this map only when every
-	// authorising policy restricts models.
-	providerAllowlists := buildProviderAllowlists(enabledPolicies, guardrailsByID)
-	guardrailJSON, err := marshalGuardrailConfig(providerAllowlists, mergedGuardrails.PromptCapture)
+	guardrailJSON, err := marshalGuardrailConfig(mergedGuardrails)
 	if err != nil {
 		return nil, err
 	}
@@ -785,12 +780,10 @@ func buildMiddlewareChain(routerCfgJSON, identityInjectJSON, guardrailJSON []byt
 
 // guardrailConfig is the JSON shape the proxy-side llm_guardrail
 // middleware expects. Mirrors the proxy registration documented in
-// the management→proxy contract. provider_allowlists is keyed by the
-// resolved provider id llm_router stamps; a provider absent from the map is
-// unrestricted at the proxy layer.
+// the management→proxy contract.
 type guardrailConfig struct {
-	ProviderAllowlists map[string][]string    `json:"provider_allowlists,omitempty"`
-	PromptCapture      guardrailPromptCapture `json:"prompt_capture"`
+	ModelAllowlist []string               `json:"model_allowlist,omitempty"`
+	PromptCapture  guardrailPromptCapture `json:"prompt_capture"`
 }
 
 type guardrailPromptCapture struct {
@@ -835,10 +828,13 @@ func applyAccountCollectionControls(merged *MergedGuardrails, settings *types.Se
 	merged.PromptCapture.RedactPii = settings.RedactPii || merged.PromptCapture.RedactPii
 }
 
-func marshalGuardrailConfig(providerAllowlists map[string][]string, capture MergedPromptCapture) ([]byte, error) {
+func marshalGuardrailConfig(merged MergedGuardrails) ([]byte, error) {
 	cfg := guardrailConfig{
-		ProviderAllowlists: providerAllowlists,
-		PromptCapture:      guardrailPromptCapture(capture),
+		ModelAllowlist: merged.ModelAllowlist,
+		PromptCapture: guardrailPromptCapture{
+			Enabled:   merged.PromptCapture.Enabled,
+			RedactPii: merged.PromptCapture.RedactPii,
+		},
 	}
 	out, err := json.Marshal(cfg)
 	if err != nil {
@@ -847,74 +843,6 @@ func marshalGuardrailConfig(providerAllowlists map[string][]string, capture Merg
 	return out, nil
 }
 
-// buildProviderAllowlists returns the proxy's per-provider backstop: a provider
-// is included only when every authorising policy restricts models (their union);
-// if any leaves it unrestricted it is omitted, so management decides per group.
-func buildProviderAllowlists(policies []*types.Policy, byID map[string]*types.Guardrail) map[string][]string {
-	type providerAcc struct {
-		models          map[string]struct{}
-		anyUnrestricted bool
-	}
-	accs := make(map[string]*providerAcc)
-	for _, p := range policies {
-		if p == nil {
-			continue
-		}
-		restricted, models := policyModelAllowlist(p, byID)
-		for _, providerID := range p.DestinationProviderIDs {
-			if providerID == "" {
-				continue
-			}
-			acc, ok := accs[providerID]
-			if !ok {
-				acc = &providerAcc{models: make(map[string]struct{})}
-				accs[providerID] = acc
-			}
-			if !restricted {
-				acc.anyUnrestricted = true
-				continue
-			}
-			for _, m := range models {
-				acc.models[m] = struct{}{}
-			}
-		}
-	}
-	out := make(map[string][]string, len(accs))
-	for providerID, acc := range accs {
-		if acc.anyUnrestricted {
-			continue
-		}
-		models := make([]string, 0, len(acc.models))
-		for m := range acc.models {
-			models = append(models, m)
-		}
-		sort.Strings(models)
-		out[providerID] = models
-	}
-	return out
-}
-
-// policyModelAllowlist reports whether a policy restricts models (has an
-// allowlist-enabled guardrail) and the union of allowed models. Models are
-// verbatim; the proxy factory lowercases/trims them at decode time.
-func policyModelAllowlist(p *types.Policy, byID map[string]*types.Guardrail) (bool, []string) {
-	restricted := false
-	var models []string
-	for _, gID := range p.GuardrailIDs {
-		g, ok := byID[gID]
-		if !ok || g == nil || !g.Checks.ModelAllowlist.Enabled {
-			continue
-		}
-		restricted = true
-		for _, m := range g.Checks.ModelAllowlist.Models {
-			if m != "" {
-				models = append(models, m)
-			}
-		}
-	}
-	return restricted, models
-}
-
 // buildAccountService composes the per-account gateway Service. The
 // target carries the noop placeholder URL — the router middleware
 // rewrites every request to the matched provider's upstream before the
@@ -1058,11 +986,38 @@ func unionSourceGroups(policies []*types.Policy) []string {
 	return out
 }
 
-// MergedGuardrails is the synthesiser's fold target. Only prompt capture is
-// merged here — the model allowlist is emitted per-provider, and
-// token/budget/retention moved onto Policy.Limits and account Settings.
+// MergedGuardrails is the JSON shape passed to the proxy via the
+// guardrail middleware's config_json. Mirrors the proxy-side
+// expectations and is intentionally distinct from
+// types.GuardrailChecks so we can evolve either side independently.
 type MergedGuardrails struct {
-	PromptCapture MergedPromptCapture
+	ModelAllowlist []string            `json:"model_allowlist,omitempty"`
+	TokenLimits    MergedTokenLimits   `json:"token_limits"`
+	Budget         MergedBudget        `json:"budget"`
+	PromptCapture  MergedPromptCapture `json:"prompt_capture"`
+	Retention      MergedRetention     `json:"retention"`
+}
+
+type MergedTokenLimits struct {
+	Hourly  *MergedTokenWindow `json:"hourly,omitempty"`
+	Daily   *MergedTokenWindow `json:"daily,omitempty"`
+	Monthly *MergedTokenWindow `json:"monthly,omitempty"`
+}
+
+type MergedTokenWindow struct {
+	MaxInputTokens  int `json:"max_input_tokens,omitempty"`
+	MaxOutputTokens int `json:"max_output_tokens,omitempty"`
+}
+
+type MergedBudget struct {
+	Hourly  *MergedBudgetWindow `json:"hourly,omitempty"`
+	Daily   *MergedBudgetWindow `json:"daily,omitempty"`
+	Monthly *MergedBudgetWindow `json:"monthly,omitempty"`
+}
+
+type MergedBudgetWindow struct {
+	SoftCapUSD float64 `json:"soft_cap_usd,omitempty"`
+	HardCapUSD float64 `json:"hard_cap_usd,omitempty"`
 }
 
 type MergedPromptCapture struct {
@@ -1070,31 +1025,64 @@ type MergedPromptCapture struct {
 	RedactPii bool `json:"redact_pii"`
 }
 
-// mergeGuardrails folds the referencing policies' guardrails into the
-// prompt-capture decision only. The model allowlist is enforced per-policy/group
-// in management and shipped per-provider; token/budget/retention live off
-// guardrails now.
+type MergedRetention struct {
+	Enabled bool `json:"enabled"`
+	Days    int  `json:"days"`
+}
+
+// mergeGuardrails computes the effective guardrail spec applied at the
+// proxy, given the referencing policies and the account's guardrail
+// catalogue. Policy enabled-ness is the caller's responsibility — only
+// enabled policies should be passed in.
 //
-// Merge rule — prompt capture: enabled if any policy enables it; redact_pii
-// sticks if any enabling policy turns it on.
+// Merge rules:
+//   - Model allowlist:   union of allowlists across policies that enable it.
+//   - Token / Budget:    most-restrictive (min of non-zero caps) per window.
+//   - Prompt capture:    enabled if any policy enables it; redact_pii sticks
+//     if any enabling policy turns it on.
+//   - Retention:         enabled if any enables it; smallest non-zero days wins.
 func mergeGuardrails(policies []*types.Policy, byID map[string]*types.Guardrail) MergedGuardrails {
 	merged := MergedGuardrails{}
+	allowlist := make(map[string]struct{})
+	allowlistEnabled := false
+
 	for _, policy := range policies {
 		for _, gID := range policy.GuardrailIDs {
 			g, ok := byID[gID]
 			if !ok || g == nil {
 				continue
 			}
-			mergeGuardrail(g, &merged)
+			mergeGuardrail(g, &merged, allowlist, &allowlistEnabled)
 		}
 	}
+
+	if allowlistEnabled {
+		merged.ModelAllowlist = make([]string, 0, len(allowlist))
+		for m := range allowlist {
+			merged.ModelAllowlist = append(merged.ModelAllowlist, m)
+		}
+		sort.Strings(merged.ModelAllowlist)
+	}
 	return merged
 }
 
-// mergeGuardrail folds a single guardrail's prompt-capture settings into the
-// running merge: enabled / redact-pii stick once any enabling guardrail turns
-// them on.
-func mergeGuardrail(g *types.Guardrail, merged *MergedGuardrails) {
+// mergeGuardrail folds a single guardrail's enabled checks into the
+// running merge: model-allowlist models join the shared set (and flip
+// allowlistEnabled), and prompt-capture / redact-pii stick once any
+// enabling guardrail turns them on.
+//
+// TokenLimits, Budget, and Retention have moved off guardrails — token
+// and budget caps now live on the Policy itself (Policy.Limits) and
+// retention moves to account-level Settings — so they are not merged here.
+func mergeGuardrail(g *types.Guardrail, merged *MergedGuardrails, allowlist map[string]struct{}, allowlistEnabled *bool) {
+	if g.Checks.ModelAllowlist.Enabled {
+		*allowlistEnabled = true
+		for _, m := range g.Checks.ModelAllowlist.Models {
+			if m != "" {
+				allowlist[m] = struct{}{}
+			}
+		}
+	}
 	if g.Checks.PromptCapture.Enabled {
 		merged.PromptCapture.Enabled = true
 		if g.Checks.PromptCapture.RedactPii {

management/internals/modules/agentnetwork/synthesizer_guardrail_realstore_test.go

@@ -81,8 +81,8 @@ func TestSynthesizeServices_RealStore_PromptCaptureAccountIsSoleControl(t *testi
 	require.Len(t, services, 1)
 
 	cfg := decodeServiceGuardrailConfig(t, services[0])
-	assert.Equal(t, map[string][]string{"prov-1": {"gpt-5.4"}}, cfg.ProviderAllowlists,
-		"model allowlist is a pure policy guardrail and must reach the per-provider config")
+	assert.Equal(t, []string{"gpt-5.4"}, cfg.ModelAllowlist,
+		"model allowlist is a pure policy guardrail and must always reach the config")
 	assert.False(t, cfg.PromptCapture.Enabled,
 		"prompt capture must be off when the account toggle is off, even with a capture-enabled guardrail")
 }
@@ -172,7 +172,7 @@ func TestSynthesizeServices_RealStore_NoGuardrail_CaptureOff(t *testing.T) {
 	require.Len(t, services, 1, "exactly one synth service expected")
 
 	cfg := decodeServiceGuardrailConfig(t, services[0])
-	assert.Empty(t, cfg.ProviderAllowlists, "no guardrail → provider unrestricted (absent from map)")
+	assert.Empty(t, cfg.ModelAllowlist, "no guardrail → no allowlist")
 	assert.False(t, cfg.PromptCapture.Enabled, "no guardrail → prompt capture off by default")
 	assert.False(t, cfg.PromptCapture.RedactPii, "no guardrail → redact off by default")
 }

management/internals/modules/agentnetwork/synthesizer_provider_allowlist_test.go

@@ -1,95 +0,0 @@
-package agentnetwork
-
-import (
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
-)
-
-// policyForProviders builds an enabled policy authorising the given providers
-// under the given guardrails (both optional). Groups are irrelevant to
-// buildProviderAllowlists, which keys purely on destination provider.
-func policyForProviders(id string, guardrailIDs []string, providerIDs ...string) *types.Policy {
-	return &types.Policy{
-		ID:                     id,
-		Enabled:                true,
-		DestinationProviderIDs: providerIDs,
-		GuardrailIDs:           guardrailIDs,
-	}
-}
-
-func TestBuildProviderAllowlists(t *testing.T) {
-	byID := map[string]*types.Guardrail{
-		"g-4o":       allowlistGuardrail("g-4o", "acc-1", "gpt-4o"),
-		"g-opus":     allowlistGuardrail("g-opus", "acc-1", "claude-opus-4"),
-		"g-disabled": {ID: "g-disabled", Checks: types.GuardrailChecks{ModelAllowlist: types.GuardrailModelAllowlist{Enabled: false, Models: []string{"gpt-4o"}}}},
-	}
-
-	t.Run("all authorising policies restrict yields per-provider union", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-4o"}, "prov-x"),
-			policyForProviders("p2", []string{"g-opus"}, "prov-x"),
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.Equal(t, map[string][]string{"prov-x": {"claude-opus-4", "gpt-4o"}}, got,
-			"a provider every policy restricts carries the sorted union of their models")
-	})
-
-	t.Run("any un-guardrailed policy leaves the provider unrestricted (omitted)", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-4o"}, "prov-x"),
-			policyForProviders("p2", nil, "prov-x"), // no guardrail
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.NotContains(t, got, "prov-x",
-			"a provider reachable by an un-guardrailed policy must be omitted so the proxy treats it as unrestricted")
-	})
-
-	t.Run("a disabled allowlist counts as unrestricted", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-disabled"}, "prov-x"),
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.NotContains(t, got, "prov-x",
-			"a policy whose only guardrail has a disabled allowlist is unrestricted")
-	})
-
-	t.Run("providers are isolated from one another", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-4o"}, "prov-x"),
-			policyForProviders("p2", []string{"g-opus"}, "prov-y"),
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.Equal(t, []string{"gpt-4o"}, got["prov-x"], "prov-x keeps only its own model")
-		assert.Equal(t, []string{"claude-opus-4"}, got["prov-y"], "prov-y keeps only its own model")
-	})
-
-	t.Run("one policy authorising two providers restricts both", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-4o"}, "prov-x", "prov-y"),
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.Equal(t, []string{"gpt-4o"}, got["prov-x"])
-		assert.Equal(t, []string{"gpt-4o"}, got["prov-y"])
-	})
-
-	t.Run("union across a single policy's guardrails", func(t *testing.T) {
-		policies := []*types.Policy{
-			policyForProviders("p1", []string{"g-4o", "g-opus"}, "prov-x"),
-		}
-		got := buildProviderAllowlists(policies, byID)
-		assert.ElementsMatch(t, []string{"claude-opus-4", "gpt-4o"}, got["prov-x"],
-			"a policy's own multiple allowlist guardrails union together")
-	})
-
-	t.Run("an enabled allowlist with no models denies everything", func(t *testing.T) {
-		empty := map[string]*types.Guardrail{"g-empty": allowlistGuardrail("g-empty", "acc-1")}
-		got := buildProviderAllowlists([]*types.Policy{
-			policyForProviders("p1", []string{"g-empty"}, "prov-x"),
-		}, empty)
-		assert.Equal(t, map[string][]string{"prov-x": {}}, got,
-			"an enabled-but-empty allowlist is restricted with an empty set, not unrestricted")
-	})
-}

management/internals/modules/agentnetwork/synthesizer_test.go

@@ -1031,12 +1031,8 @@ func TestSynthesizeServices_GuardrailMerge_AllowlistUnion_LimitsRestrictive(t *t
 
 	var cfg guardrailConfig
 	require.NoError(t, json.Unmarshal(guardrailJSON, &cfg), "guardrail config must unmarshal cleanly")
-	// Both policies restrict the same provider, so the per-provider backstop
-	// carries the union of their models — a coarse gate that management's
-	// per-policy/group check narrows; it only blocks models outside the union
-	// when management is down.
-	assert.ElementsMatch(t, []string{"gpt-5.4-mini", "gpt-5.4-pro"}, cfg.ProviderAllowlists["prov-1"],
-		"per-provider allowlist union must keep both models")
+	assert.ElementsMatch(t, []string{"gpt-5.4-mini", "gpt-5.4-pro"}, cfg.ModelAllowlist,
+		"model allowlist union must keep both models")
 }
 
 func TestSynthesizeServices_BackfillsMissingSessionKeys(t *testing.T) {

management/internals/shared/grpc/components_envelope_response.go

@@ -50,7 +50,7 @@ func ToComponentSyncResponse(
 	// TODO (dmitri) consider using invariants?
 	//
 	enableSSH := computeSSHEnabledForPeer(components, peer)
-	peerConfig := toPeerConfig(peer, components.Network, dnsName, settings, httpConfig, deviceFlowConfig, enableSSH, components.ForceRoutingPeerDNSResolution)
+	peerConfig := toPeerConfig(peer, components.Network, dnsName, settings, httpConfig, deviceFlowConfig, enableSSH)
 
 	includeIPv6 := peer.SupportsIPv6() && peer.IPv6.IsValid()
 	useSourcePrefixes := peer.SupportsSourcePrefixes()

management/internals/shared/grpc/conversion.go

@@ -119,7 +119,7 @@ func toNetbirdConfig(config *nbconfig.Config, turnCredentials *Token, relayToken
 	return nbConfig
 }
 
-func toPeerConfig(peer *nbpeer.Peer, network *types.Network, dnsName string, settings *types.Settings, httpConfig *nbconfig.HttpServerConfig, deviceFlowConfig *nbconfig.DeviceAuthorizationFlow, enableSSH bool, forceRoutingPeerDNS bool) *proto.PeerConfig {
+func toPeerConfig(peer *nbpeer.Peer, network *types.Network, dnsName string, settings *types.Settings, httpConfig *nbconfig.HttpServerConfig, deviceFlowConfig *nbconfig.DeviceAuthorizationFlow, enableSSH bool) *proto.PeerConfig {
 	netmask, _ := network.Net.Mask.Size()
 	fqdn := peer.FQDN(dnsName)
 
@@ -135,7 +135,7 @@ func toPeerConfig(peer *nbpeer.Peer, network *types.Network, dnsName string, set
 		Address:                         fmt.Sprintf("%s/%d", peer.IP.String(), netmask),
 		SshConfig:                       sshConfig,
 		Fqdn:                            fqdn,
-		RoutingPeerDnsResolutionEnabled: settings.RoutingPeerDNSResolutionEnabled || peer.ProxyMeta.Embedded || forceRoutingPeerDNS,
+		RoutingPeerDnsResolutionEnabled: settings.RoutingPeerDNSResolutionEnabled,
 		LazyConnectionEnabled:           settings.LazyConnectionEnabled,
 		AutoUpdate: &proto.AutoUpdateSettings{
 			Version:      settings.AutoUpdateVersion,
@@ -162,12 +162,12 @@ func ToSyncResponse(ctx context.Context, config *nbconfig.Config, httpConfig *nb
 	useSourcePrefixes := peer.SupportsSourcePrefixes()
 
 	response := &proto.SyncResponse{
-		PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH, networkMap.ForceRoutingPeerDNSResolution),
+		PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH),
 		NetworkMap: &proto.NetworkMap{
 			Serial:     networkMap.Network.CurrentSerial(),
 			Routes:     networkmap.ToProtocolRoutes(networkMap.Routes),
 			DNSConfig:  networkmap.ToProtocolDNSConfig(networkMap.DNSConfig, dnsCache, dnsFwdPort),
-			PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH, networkMap.ForceRoutingPeerDNSResolution),
+			PeerConfig: toPeerConfig(peer, networkMap.Network, dnsName, settings, httpConfig, deviceFlowConfig, networkMap.EnableSSH),
 		},
 		Checks: toProtocolChecks(ctx, checks),
 	}

management/internals/shared/grpc/conversion_test.go

@@ -2,7 +2,6 @@ package grpc
 
 import (
 	"fmt"
-	"net"
 	"net/netip"
 	"reflect"
 	"testing"
@@ -15,7 +14,6 @@ import (
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map"
 	"github.com/netbirdio/netbird/management/internals/controllers/network_map/controller/cache"
 	nbconfig "github.com/netbirdio/netbird/management/internals/server/config"
-	nbpeer "github.com/netbirdio/netbird/management/server/peer"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/shared/management/networkmap"
 )
@@ -303,35 +301,3 @@ func TestToNetbirdConfig_RelayInvariant(t *testing.T) {
 		assert.True(t, nbCfg.Metrics.Enabled, "metrics flag should carry the settings value")
 	})
 }
-
-func TestToPeerConfig_RoutingPeerDNSResolution(t *testing.T) {
-	network := &types.Network{Net: net.IPNet{IP: net.IPv4(100, 0, 0, 0), Mask: net.CIDRMask(8, 32)}}
-
-	newPeer := func(embedded bool) *nbpeer.Peer {
-		p := &nbpeer.Peer{IP: netip.MustParseAddr("100.0.0.1")}
-		p.ProxyMeta.Embedded = embedded
-		return p
-	}
-
-	tests := []struct {
-		name        string
-		globalFlag  bool
-		embedded    bool
-		forceParam  bool
-		wantEnabled bool
-	}{
-		{name: "global off, regular peer, no force", wantEnabled: false},
-		{name: "global on wins", globalFlag: true, wantEnabled: true},
-		{name: "embedded proxy peer forced", embedded: true, wantEnabled: true},
-		{name: "routing peer forced via param", forceParam: true, wantEnabled: true},
-	}
-
-	for _, tt := range tests {
-		t.Run(tt.name, func(t *testing.T) {
-			settings := &types.Settings{RoutingPeerDNSResolutionEnabled: tt.globalFlag}
-			cfg := toPeerConfig(newPeer(tt.embedded), network, "netbird.selfhosted", settings, nil, nil, false, tt.forceParam)
-			assert.Equal(t, tt.wantEnabled, cfg.RoutingPeerDnsResolutionEnabled,
-				"RoutingPeerDnsResolutionEnabled should reflect global || embedded || forced")
-		})
-	}
-}

management/internals/shared/grpc/proxy.go

@@ -285,7 +285,6 @@ func (s *ProxyServiceServer) CheckLLMPolicyLimits(ctx context.Context, req *prot
 		UserID:     req.GetUserId(),
 		GroupIDs:   req.GetGroupIds(),
 		ProviderID: req.GetProviderId(),
-		Model:      req.GetModel(),
 	})
 	if err != nil {
 		log.WithContext(ctx).Errorf("select policy for request: %v", err)

management/internals/shared/grpc/proxy_llm_policy_limits_test.go

@@ -1,138 +0,0 @@
-package grpc
-
-import (
-	"context"
-	"errors"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"google.golang.org/grpc/codes"
-	grpcstatus "google.golang.org/grpc/status"
-
-	"github.com/netbirdio/netbird/management/internals/modules/agentnetwork"
-	"github.com/netbirdio/netbird/shared/management/proto"
-)
-
-// fakeAgentNetworkLimits records the PolicySelectionInput it was invoked with
-// and returns a pre-programmed result, so tests can assert what the handler
-// forwards to the selector.
-type fakeAgentNetworkLimits struct {
-	gotInput agentnetwork.PolicySelectionInput
-	result   *agentnetwork.PolicySelectionResult
-	err      error
-}
-
-func (f *fakeAgentNetworkLimits) SelectPolicyForRequest(_ context.Context, in agentnetwork.PolicySelectionInput) (*agentnetwork.PolicySelectionResult, error) {
-	f.gotInput = in
-	if f.err != nil {
-		return nil, f.err
-	}
-	return f.result, nil
-}
-
-func (f *fakeAgentNetworkLimits) RecordUsage(_ context.Context, _ agentnetwork.RecordUsageInput) error {
-	return nil
-}
-
-// TestCheckLLMPolicyLimits_ForwardsModelToSelector proves the wiring added here:
-// the model the proxy extracted must reach the selector's Model unchanged,
-// alongside the account/user/group/provider fields.
-func TestCheckLLMPolicyLimits_ForwardsModelToSelector(t *testing.T) {
-	fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{Allow: true, SelectedPolicyID: "pol-1"}}
-	s := &ProxyServiceServer{}
-	s.SetAgentNetworkLimitsService(fake)
-
-	req := &proto.CheckLLMPolicyLimitsRequest{
-		AccountId:  "acc-1",
-		UserId:     "user-1",
-		GroupIds:   []string{"grp-a", "grp-b"},
-		ProviderId: "prov-1",
-		Model:      "claude-opus-4",
-	}
-
-	resp, err := s.CheckLLMPolicyLimits(context.Background(), req)
-	require.NoError(t, err)
-	require.NotNil(t, resp)
-
-	assert.Equal(t, "acc-1", fake.gotInput.AccountID)
-	assert.Equal(t, "user-1", fake.gotInput.UserID)
-	assert.Equal(t, []string{"grp-a", "grp-b"}, fake.gotInput.GroupIDs)
-	assert.Equal(t, "prov-1", fake.gotInput.ProviderID)
-	assert.Equal(t, "claude-opus-4", fake.gotInput.Model,
-		"the request's model must be forwarded to the selector")
-}
-
-// TestCheckLLMPolicyLimits_EmptyModelForwardedAsEmpty proves an undetermined
-// model (empty string) is forwarded as-is; the selector decides how to treat it.
-func TestCheckLLMPolicyLimits_EmptyModelForwardedAsEmpty(t *testing.T) {
-	fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{Allow: true}}
-	s := &ProxyServiceServer{}
-	s.SetAgentNetworkLimitsService(fake)
-
-	req := &proto.CheckLLMPolicyLimitsRequest{
-		AccountId:  "acc-1",
-		ProviderId: "prov-1",
-	}
-
-	_, err := s.CheckLLMPolicyLimits(context.Background(), req)
-	require.NoError(t, err)
-	assert.Equal(t, "", fake.gotInput.Model, "an absent model must be forwarded as empty, not fabricated")
-}
-
-// TestCheckLLMPolicyLimits_DenyResponseCarriesModelBlockedCode proves the deny
-// envelope surfaces the model-allowlist deny code + reason through the response.
-func TestCheckLLMPolicyLimits_DenyResponseCarriesModelBlockedCode(t *testing.T) {
-	fake := &fakeAgentNetworkLimits{result: &agentnetwork.PolicySelectionResult{
-		Allow:      false,
-		DenyCode:   "llm_policy.model_blocked",
-		DenyReason: `model "claude-opus-4" is not permitted by any applicable policy allowlist`,
-	}}
-	s := &ProxyServiceServer{}
-	s.SetAgentNetworkLimitsService(fake)
-
-	resp, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
-		AccountId:  "acc-1",
-		ProviderId: "prov-1",
-		Model:      "claude-opus-4",
-	})
-	require.NoError(t, err)
-	require.NotNil(t, resp)
-	assert.Equal(t, "deny", resp.Decision)
-	assert.Equal(t, "llm_policy.model_blocked", resp.DenyCode)
-	assert.NotEmpty(t, resp.DenyReason)
-	assert.Empty(t, resp.SelectedPolicyId, "a denied request must carry no selected policy")
-}
-
-// TestCheckLLMPolicyLimits_SelectorErrorSurfacesAsInternal proves a selector
-// failure surfaces as an Internal gRPC error rather than a silent allow.
-func TestCheckLLMPolicyLimits_SelectorErrorSurfacesAsInternal(t *testing.T) {
-	fake := &fakeAgentNetworkLimits{err: errors.New("boom")}
-	s := &ProxyServiceServer{}
-	s.SetAgentNetworkLimitsService(fake)
-
-	_, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
-		AccountId:  "acc-1",
-		ProviderId: "prov-1",
-		Model:      "gpt-4o",
-	})
-	require.Error(t, err)
-	st, ok := grpcstatus.FromError(err)
-	require.True(t, ok)
-	assert.Equal(t, codes.Internal, st.Code(), "selector errors must never fail open on the hot path")
-}
-
-// TestCheckLLMPolicyLimits_UnconfiguredServiceReturnsUnimplemented locks the
-// fallback: with no limits service wired the RPC returns Unimplemented.
-func TestCheckLLMPolicyLimits_UnconfiguredServiceReturnsUnimplemented(t *testing.T) {
-	s := &ProxyServiceServer{}
-
-	_, err := s.CheckLLMPolicyLimits(context.Background(), &proto.CheckLLMPolicyLimitsRequest{
-		AccountId:  "acc-1",
-		ProviderId: "prov-1",
-	})
-	require.Error(t, err)
-	st, ok := grpcstatus.FromError(err)
-	require.True(t, ok)
-	assert.Equal(t, codes.Unimplemented, st.Code())
-}

management/internals/shared/grpc/server.go

@@ -921,7 +921,7 @@ func (s *Server) prepareLoginResponse(ctx context.Context, peer *nbpeer.Peer, ne
 	// if peer has reached this point then it has logged in
 	loginResp := &proto.LoginResponse{
 		NetbirdConfig: toNetbirdConfig(s.config, nil, relayToken, nil, settings),
-		PeerConfig:    toPeerConfig(peer, network, s.networkMapController.GetDNSDomain(settings), settings, s.config.HttpConfig, s.config.DeviceAuthorizationFlow, enableSSH, false),
+		PeerConfig:    toPeerConfig(peer, network, s.networkMapController.GetDNSDomain(settings), settings, s.config.HttpConfig, s.config.DeviceAuthorizationFlow, enableSSH),
 		Checks:        toProtocolChecks(ctx, postureChecks),
 	}
 

management/server/store/sql_store.go

@@ -6,7 +6,6 @@ import (
 	"encoding/json"
 	"errors"
 	"fmt"
-	"math"
 	"net"
 	"net/netip"
 	"net/url"
@@ -2259,30 +2258,117 @@ func (s *SqlStore) getPostureChecks(ctx context.Context, accountID string) ([]*p
 	return checks, nil
 }
 
-// serviceSelectColumns and targetSelectColumns are the column lists the Postgres
-// pgx read path scans. They must stay in sync with the rpservice.Service and
-// rpservice.Target gorm models; TestPgxServiceColumnsMatchGorm enforces this.
-const serviceSelectColumns = `id, account_id, name, domain, enabled, auth, restrictions,
-	meta_created_at, meta_certificate_issued_at, meta_last_renewed_at, meta_status, proxy_cluster,
-	pass_host_header, rewrite_redirects, session_private_key, session_public_key,
-	mode, listen_port, port_auto_assigned, source, source_peer, terminated,
-	private, access_groups`
-
-const targetSelectColumns = `id, account_id, service_id, path, host, port, protocol,
-	target_id, target_type, enabled, proxy_protocol,
-	skip_tls_verify, request_timeout, session_idle_timeout, path_rewrite, custom_headers,
-	direct_upstream, middlewares, capture_max_request_bytes, capture_max_response_bytes,
-	capture_content_types, agent_network, disable_access_log`
-
 func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpservice.Service, error) {
-	const serviceQuery = `SELECT ` + serviceSelectColumns + ` FROM services WHERE account_id = $1`
+	const serviceQuery = `SELECT id, account_id, name, domain, enabled, auth,
+		meta_created_at, meta_certificate_issued_at, meta_status, proxy_cluster,
+		pass_host_header, rewrite_redirects, session_private_key, session_public_key,
+		mode, listen_port, port_auto_assigned, source, source_peer, terminated,
+		private, access_groups
+		FROM services WHERE account_id = $1`
+
+	const targetsQuery = `SELECT id, account_id, service_id, path, host, port, protocol,
+		target_id, target_type, enabled
+		FROM targets WHERE service_id = ANY($1)`
 
 	serviceRows, err := s.pool.Query(ctx, serviceQuery, accountID)
 	if err != nil {
 		return nil, err
 	}
 
-	services, err := pgx.CollectRows(serviceRows, scanService)
+	services, err := pgx.CollectRows(serviceRows, func(row pgx.CollectableRow) (*rpservice.Service, error) {
+		var s rpservice.Service
+		var auth []byte
+		var accessGroups []byte
+		var createdAt, certIssuedAt sql.NullTime
+		var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
+		var mode, source, sourcePeer sql.NullString
+		var terminated, portAutoAssigned, private sql.NullBool
+		var listenPort sql.NullInt64
+		err := row.Scan(
+			&s.ID,
+			&s.AccountID,
+			&s.Name,
+			&s.Domain,
+			&s.Enabled,
+			&auth,
+			&createdAt,
+			&certIssuedAt,
+			&status,
+			&proxyCluster,
+			&s.PassHostHeader,
+			&s.RewriteRedirects,
+			&sessionPrivateKey,
+			&sessionPublicKey,
+			&mode,
+			&listenPort,
+			&portAutoAssigned,
+			&source,
+			&sourcePeer,
+			&terminated,
+			&private,
+			&accessGroups,
+		)
+		if err != nil {
+			return nil, err
+		}
+
+		if auth != nil {
+			if err := json.Unmarshal(auth, &s.Auth); err != nil {
+				return nil, err
+			}
+		}
+
+		if len(accessGroups) > 0 {
+			if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
+				return nil, fmt.Errorf("unmarshal access_groups: %w", err)
+			}
+		}
+
+		if private.Valid {
+			s.Private = private.Bool
+		}
+
+		s.Meta = rpservice.Meta{}
+		if createdAt.Valid {
+			s.Meta.CreatedAt = createdAt.Time
+		}
+		if certIssuedAt.Valid {
+			t := certIssuedAt.Time
+			s.Meta.CertificateIssuedAt = &t
+		}
+		if status.Valid {
+			s.Meta.Status = status.String
+		}
+		if proxyCluster.Valid {
+			s.ProxyCluster = proxyCluster.String
+		}
+		if sessionPrivateKey.Valid {
+			s.SessionPrivateKey = sessionPrivateKey.String
+		}
+		if sessionPublicKey.Valid {
+			s.SessionPublicKey = sessionPublicKey.String
+		}
+		if mode.Valid {
+			s.Mode = mode.String
+		}
+		if source.Valid {
+			s.Source = source.String
+		}
+		if sourcePeer.Valid {
+			s.SourcePeer = sourcePeer.String
+		}
+		if terminated.Valid {
+			s.Terminated = terminated.Bool
+		}
+		if portAutoAssigned.Valid {
+			s.PortAutoAssigned = portAutoAssigned.Bool
+		}
+		if listenPort.Valid {
+			s.ListenPort = uint16(listenPort.Int64)
+		}
+		s.Targets = []*rpservice.Target{}
+		return &s, nil
+	})
 	if err != nil {
 		return nil, err
 	}
@@ -2293,12 +2379,39 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 
 	serviceIDs := make([]string, len(services))
 	serviceMap := make(map[string]*rpservice.Service)
-	for i, svc := range services {
-		serviceIDs[i] = svc.ID
-		serviceMap[svc.ID] = svc
+	for i, s := range services {
+		serviceIDs[i] = s.ID
+		serviceMap[s.ID] = s
 	}
 
-	targets, err := s.getServiceTargets(ctx, serviceIDs)
+	targetRows, err := s.pool.Query(ctx, targetsQuery, serviceIDs)
+	if err != nil {
+		return nil, err
+	}
+
+	targets, err := pgx.CollectRows(targetRows, func(row pgx.CollectableRow) (*rpservice.Target, error) {
+		var t rpservice.Target
+		var path sql.NullString
+		err := row.Scan(
+			&t.ID,
+			&t.AccountID,
+			&t.ServiceID,
+			&path,
+			&t.Host,
+			&t.Port,
+			&t.Protocol,
+			&t.TargetId,
+			&t.TargetType,
+			&t.Enabled,
+		)
+		if err != nil {
+			return nil, err
+		}
+		if path.Valid {
+			t.Path = &path.String
+		}
+		return &t, nil
+	})
 	if err != nil {
 		return nil, err
 	}
@@ -2312,201 +2425,6 @@ func (s *SqlStore) getServices(ctx context.Context, accountID string) ([]*rpserv
 	return services, nil
 }
 
-func scanService(row pgx.CollectableRow) (*rpservice.Service, error) {
-	var s rpservice.Service
-	var auth []byte
-	var restrictions []byte
-	var accessGroups []byte
-	var createdAt, certIssuedAt, lastRenewedAt sql.NullTime
-	var status, proxyCluster, sessionPrivateKey, sessionPublicKey sql.NullString
-	var mode, source, sourcePeer sql.NullString
-	var terminated, portAutoAssigned, private sql.NullBool
-	var listenPort sql.NullInt64
-	err := row.Scan(
-		&s.ID,
-		&s.AccountID,
-		&s.Name,
-		&s.Domain,
-		&s.Enabled,
-		&auth,
-		&restrictions,
-		&createdAt,
-		&certIssuedAt,
-		&lastRenewedAt,
-		&status,
-		&proxyCluster,
-		&s.PassHostHeader,
-		&s.RewriteRedirects,
-		&sessionPrivateKey,
-		&sessionPublicKey,
-		&mode,
-		&listenPort,
-		&portAutoAssigned,
-		&source,
-		&sourcePeer,
-		&terminated,
-		&private,
-		&accessGroups,
-	)
-	if err != nil {
-		return nil, err
-	}
-
-	if auth != nil {
-		if err := json.Unmarshal(auth, &s.Auth); err != nil {
-			return nil, err
-		}
-	}
-
-	if len(restrictions) > 0 {
-		if err := json.Unmarshal(restrictions, &s.Restrictions); err != nil {
-			return nil, fmt.Errorf("unmarshal restrictions: %w", err)
-		}
-	}
-
-	if len(accessGroups) > 0 {
-		if err := json.Unmarshal(accessGroups, &s.AccessGroups); err != nil {
-			return nil, fmt.Errorf("unmarshal access_groups: %w", err)
-		}
-	}
-
-	if private.Valid {
-		s.Private = private.Bool
-	}
-
-	s.Meta = serviceMetaFromRow(createdAt, certIssuedAt, lastRenewedAt, status)
-	if proxyCluster.Valid {
-		s.ProxyCluster = proxyCluster.String
-	}
-	if sessionPrivateKey.Valid {
-		s.SessionPrivateKey = sessionPrivateKey.String
-	}
-	if sessionPublicKey.Valid {
-		s.SessionPublicKey = sessionPublicKey.String
-	}
-	if mode.Valid {
-		s.Mode = mode.String
-	}
-	if source.Valid {
-		s.Source = source.String
-	}
-	if sourcePeer.Valid {
-		s.SourcePeer = sourcePeer.String
-	}
-	if terminated.Valid {
-		s.Terminated = terminated.Bool
-	}
-	if portAutoAssigned.Valid {
-		s.PortAutoAssigned = portAutoAssigned.Bool
-	}
-	if listenPort.Valid {
-		if listenPort.Int64 < 0 || listenPort.Int64 > math.MaxUint16 {
-			return nil, fmt.Errorf("listen_port %d out of range", listenPort.Int64)
-		}
-		s.ListenPort = uint16(listenPort.Int64)
-	}
-	s.Targets = []*rpservice.Target{}
-	return &s, nil
-}
-
-func serviceMetaFromRow(createdAt, certIssuedAt, lastRenewedAt sql.NullTime, status sql.NullString) rpservice.Meta {
-	meta := rpservice.Meta{}
-	if createdAt.Valid {
-		meta.CreatedAt = createdAt.Time
-	}
-	if certIssuedAt.Valid {
-		t := certIssuedAt.Time
-		meta.CertificateIssuedAt = &t
-	}
-	if lastRenewedAt.Valid {
-		t := lastRenewedAt.Time
-		meta.LastRenewedAt = &t
-	}
-	if status.Valid {
-		meta.Status = status.String
-	}
-	return meta
-}
-
-func (s *SqlStore) getServiceTargets(ctx context.Context, serviceIDs []string) ([]*rpservice.Target, error) {
-	const targetsQuery = `SELECT ` + targetSelectColumns + ` FROM targets WHERE service_id = ANY($1)`
-
-	rows, err := s.pool.Query(ctx, targetsQuery, serviceIDs)
-	if err != nil {
-		return nil, err
-	}
-
-	return pgx.CollectRows(rows, scanTarget)
-}
-
-func scanTarget(row pgx.CollectableRow) (*rpservice.Target, error) {
-	var t rpservice.Target
-	var path sql.NullString
-	var pathRewrite sql.NullString
-	var proxyProtocol, skipTLSVerify, directUpstream, agentNetwork, disableAccessLog sql.NullBool
-	var requestTimeout, sessionIdleTimeout, captureMaxRequestBytes, captureMaxResponseBytes sql.NullInt64
-	var customHeaders, middlewares, captureContentTypes []byte
-	err := row.Scan(
-		&t.ID,
-		&t.AccountID,
-		&t.ServiceID,
-		&path,
-		&t.Host,
-		&t.Port,
-		&t.Protocol,
-		&t.TargetId,
-		&t.TargetType,
-		&t.Enabled,
-		&proxyProtocol,
-		&skipTLSVerify,
-		&requestTimeout,
-		&sessionIdleTimeout,
-		&pathRewrite,
-		&customHeaders,
-		&directUpstream,
-		&middlewares,
-		&captureMaxRequestBytes,
-		&captureMaxResponseBytes,
-		&captureContentTypes,
-		&agentNetwork,
-		&disableAccessLog,
-	)
-	if err != nil {
-		return nil, err
-	}
-	if path.Valid {
-		t.Path = &path.String
-	}
-
-	t.ProxyProtocol = proxyProtocol.Bool
-	t.Options.SkipTLSVerify = skipTLSVerify.Bool
-	t.Options.RequestTimeout = time.Duration(requestTimeout.Int64)
-	t.Options.SessionIdleTimeout = time.Duration(sessionIdleTimeout.Int64)
-	t.Options.PathRewrite = rpservice.PathRewriteMode(pathRewrite.String)
-	t.Options.DirectUpstream = directUpstream.Bool
-	t.Options.CaptureMaxRequestBytes = captureMaxRequestBytes.Int64
-	t.Options.CaptureMaxResponseBytes = captureMaxResponseBytes.Int64
-	t.Options.AgentNetwork = agentNetwork.Bool
-	t.Options.DisableAccessLog = disableAccessLog.Bool
-
-	if len(customHeaders) > 0 {
-		if err := json.Unmarshal(customHeaders, &t.Options.CustomHeaders); err != nil {
-			return nil, fmt.Errorf("unmarshal custom_headers: %w", err)
-		}
-	}
-	if len(middlewares) > 0 {
-		if err := json.Unmarshal(middlewares, &t.Options.Middlewares); err != nil {
-			return nil, fmt.Errorf("unmarshal middlewares: %w", err)
-		}
-	}
-	if len(captureContentTypes) > 0 {
-		if err := json.Unmarshal(captureContentTypes, &t.Options.CaptureContentTypes); err != nil {
-			return nil, fmt.Errorf("unmarshal capture_content_types: %w", err)
-		}
-	}
-	return &t, nil
-}
-
 func (s *SqlStore) getNetworks(ctx context.Context, accountID string) ([]*networkTypes.Network, error) {
 	const query = `SELECT id, account_id, public_id, name, description FROM networks WHERE account_id = $1`
 	rows, err := s.pool.Query(ctx, query, accountID)

management/server/store/sql_store_pgx_parity_test.go

@@ -1,74 +0,0 @@
-package store
-
-import (
-	"strings"
-	"sync"
-	"testing"
-
-	"github.com/stretchr/testify/assert"
-	"github.com/stretchr/testify/require"
-	"gorm.io/gorm/schema"
-
-	rpservice "github.com/netbirdio/netbird/management/internals/modules/reverseproxy/service"
-)
-
-// TestPgxServiceColumnsMatchGorm guards the Postgres pgx read path against
-// drifting from the gorm model. The SQLite/MySQL gorm path loads rows by struct,
-// so a new column on a model is picked up automatically, but the hand-written
-// pgx SELECT in sql_store.go must be updated by hand. This test fails when a
-// gorm column is missing from the pgx column list, which otherwise silently
-// returns zero-valued on Postgres with no compile error.
-func TestPgxServiceColumnsMatchGorm(t *testing.T) {
-	tests := []struct {
-		name          string
-		model         any
-		selectColumns string
-		// excluded lists gorm columns intentionally not loaded by the pgx path.
-		excluded map[string]struct{}
-	}{
-		{
-			name:          "service",
-			model:         &rpservice.Service{},
-			selectColumns: serviceSelectColumns,
-		},
-		{
-			name:          "target",
-			model:         &rpservice.Target{},
-			selectColumns: targetSelectColumns,
-		},
-	}
-
-	for _, tc := range tests {
-		t.Run(tc.name, func(t *testing.T) {
-			selected := parseColumnList(tc.selectColumns)
-			for _, col := range gormColumnNames(t, tc.model) {
-				if _, ok := tc.excluded[col]; ok {
-					continue
-				}
-				_, ok := selected[col]
-				assert.Truef(t, ok,
-					"gorm column %q is not read by the Postgres pgx SELECT; add it to %sSelectColumns in sql_store.go (or to the test's excluded set if it is intentionally not loaded)",
-					col, tc.name)
-			}
-		})
-	}
-}
-
-func parseColumnList(cols string) map[string]struct{} {
-	set := make(map[string]struct{})
-	for _, c := range strings.Split(cols, ",") {
-		if c = strings.TrimSpace(c); c != "" {
-			set[c] = struct{}{}
-		}
-	}
-	return set
-}
-
-// gormColumnNames returns the DB column names gorm would migrate for the model,
-// using the same default naming strategy the store configures.
-func gormColumnNames(t *testing.T, model any) []string {
-	t.Helper()
-	sch, err := schema.Parse(model, &sync.Map{}, schema.NamingStrategy{})
-	require.NoError(t, err)
-	return sch.DBNames
-}

management/server/store/sql_store_service_test.go

@@ -5,7 +5,6 @@ import (
 	"os"
 	"runtime"
 	"testing"
-	"time"
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -45,91 +44,3 @@ func TestSqlStore_GetAccount_PrivateServiceRoundtrip(t *testing.T) {
 		assert.Equal(t, []string{"grp-admins", "grp-ops"}, got.AccessGroups)
 	})
 }
-
-// TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip guards the Postgres pgx
-// read path (getServices) against silently dropping columns present on the gorm
-// model. Before the fix these fields loaded correctly on SQLite but came back
-// zero-valued on Postgres because the hand-written SELECT and scan omitted them.
-func TestSqlStore_GetAccount_ServiceTargetOptionsRoundtrip(t *testing.T) {
-	if os.Getenv("CI") == "true" && (runtime.GOOS == "darwin" || runtime.GOOS == "windows") {
-		t.Skip("skip CI tests on darwin and windows")
-	}
-
-	runTestForAllEngines(t, "", func(t *testing.T, store Store) {
-		ctx := context.Background()
-		account := newAccountWithId(ctx, "account_svc_opts", "testuser", "")
-		require.NoError(t, store.SaveAccount(ctx, account))
-
-		renewedAt := time.Now().UTC().Truncate(time.Second)
-		targetPath := "/api"
-		svc := &rpservice.Service{
-			ID:        "svc-opts",
-			AccountID: account.Id,
-			Name:      "opts-svc",
-			Domain:    "opts.example",
-			Enabled:   true,
-			Mode:      rpservice.ModeHTTP,
-			Restrictions: rpservice.AccessRestrictions{
-				AllowedCIDRs:     []string{"10.0.0.0/8"},
-				BlockedCountries: []string{"XX"},
-				CrowdSecMode:     "block",
-			},
-			Meta: rpservice.Meta{
-				LastRenewedAt: &renewedAt,
-			},
-			Targets: []*rpservice.Target{
-				{
-					AccountID:     account.Id,
-					ServiceID:     "svc-opts",
-					Path:          &targetPath,
-					Host:          "backend.internal",
-					Port:          8080,
-					Protocol:      "http",
-					TargetId:      "tgt-1",
-					Enabled:       true,
-					ProxyProtocol: true,
-					Options: rpservice.TargetOptions{
-						SkipTLSVerify:           true,
-						RequestTimeout:          30 * time.Second,
-						SessionIdleTimeout:      5 * time.Minute,
-						PathRewrite:             rpservice.PathRewritePreserve,
-						CustomHeaders:           map[string]string{"X-Foo": "bar"},
-						DirectUpstream:          true,
-						CaptureMaxRequestBytes:  1024,
-						CaptureMaxResponseBytes: 2048,
-						CaptureContentTypes:     []string{"application/json"},
-						AgentNetwork:            true,
-						DisableAccessLog:        true,
-					},
-				},
-			},
-		}
-		require.NoError(t, store.CreateService(ctx, svc))
-
-		loaded, err := store.GetAccount(ctx, account.Id)
-		require.NoError(t, err)
-		require.Len(t, loaded.Services, 1)
-
-		got := loaded.Services[0]
-		assert.Equal(t, []string{"10.0.0.0/8"}, got.Restrictions.AllowedCIDRs, "restrictions allowed CIDRs")
-		assert.Equal(t, []string{"XX"}, got.Restrictions.BlockedCountries, "restrictions blocked countries")
-		assert.Equal(t, "block", got.Restrictions.CrowdSecMode, "restrictions crowdsec mode")
-		require.NotNil(t, got.Meta.LastRenewedAt, "meta last renewed at")
-		assert.WithinDuration(t, renewedAt, *got.Meta.LastRenewedAt, time.Second, "meta last renewed at")
-
-		require.Len(t, got.Targets, 1)
-		tg := got.Targets[0]
-		assert.True(t, tg.ProxyProtocol, "target proxy protocol")
-		assert.True(t, tg.Options.SkipTLSVerify, "options skip TLS verify")
-		assert.Equal(t, 30*time.Second, tg.Options.RequestTimeout, "options request timeout")
-		assert.Equal(t, 5*time.Minute, tg.Options.SessionIdleTimeout, "options session idle timeout")
-		assert.Equal(t, rpservice.PathRewritePreserve, tg.Options.PathRewrite, "options path rewrite")
-		assert.Equal(t, map[string]string{"X-Foo": "bar"}, tg.Options.CustomHeaders, "options custom headers")
-		assert.True(t, tg.Options.DirectUpstream, "options direct upstream")
-		assert.Equal(t, int64(1024), tg.Options.CaptureMaxRequestBytes, "options capture max request bytes")
-		assert.Equal(t, int64(2048), tg.Options.CaptureMaxResponseBytes, "options capture max response bytes")
-		assert.Equal(t, []string{"application/json"}, tg.Options.CaptureContentTypes, "options capture content types")
-		assert.True(t, tg.Options.AgentNetwork, "options agent network")
-		assert.True(t, tg.Options.DisableAccessLog, "options disable access log")
-	})
-}

management/server/types/account.go

@@ -1517,54 +1517,6 @@ func (a *Account) GetResourceRoutersMap() map[string]map[string]*routerTypes.Net
 	return routers
 }
 
-// forcesRoutingPeerDNSResolution reports whether the given peer must run
-// routing-peer DNS resolution regardless of the account-global
-// RoutingPeerDNSResolutionEnabled setting. It returns true when the peer is a
-// router for a domain network resource that is targeted by an enabled
-// reverse-proxy service, so the peer's DNS forwarder starts and can resolve
-// the target for the embedded proxy peers. Embedded proxy peers themselves are
-// handled at PeerConfig build time.
-func (a *Account) forcesRoutingPeerDNSResolution(peerID string, routers map[string]map[string]*routerTypes.NetworkRouter) bool {
-	targeted := a.proxyTargetedDomainResourceIDs()
-	if len(targeted) == 0 {
-		return false
-	}
-
-	for _, resource := range a.NetworkResources {
-		if resource == nil || !resource.Enabled || resource.Type != resourceTypes.Domain {
-			continue
-		}
-		if _, ok := targeted[resource.ID]; !ok {
-			continue
-		}
-		if _, isRouter := routers[resource.NetworkID][peerID]; isRouter {
-			return true
-		}
-	}
-
-	return false
-}
-
-// proxyTargetedDomainResourceIDs returns the set of domain network resource IDs
-// targeted by an enabled, non-terminated reverse-proxy service.
-func (a *Account) proxyTargetedDomainResourceIDs() map[string]struct{} {
-	ids := make(map[string]struct{})
-	for _, svc := range a.Services {
-		if svc == nil || !svc.Enabled || svc.Terminated {
-			continue
-		}
-		for _, target := range svc.Targets {
-			if target == nil || !target.Enabled {
-				continue
-			}
-			if target.TargetType == service.TargetTypeDomain {
-				ids[target.TargetId] = struct{}{}
-			}
-		}
-	}
-	return ids
-}
-
 // getPoliciesSourcePeers collects all unique peers from the source groups defined in the given policies.
 func getPoliciesSourcePeers(policies []*Policy, groups map[string]*Group) map[string]struct{} {
 	sourcePeers := make(map[string]struct{})

management/server/types/account_components.go

@@ -140,8 +140,6 @@ func (a *Account) GetPeerNetworkMapComponents(
 		RouterPeers:               make(map[string]*ComponentPeer),
 		NetworkXIDToPublicID:      make(map[string]string, len(a.Networks)),
 		PostureCheckXIDToPublicID: make(map[string]string, len(a.PostureChecks)),
-
-		ForceRoutingPeerDNSResolution: a.forcesRoutingPeerDNSResolution(peerID, routers),
 	}
 	for _, n := range a.Networks {
 		if n != nil {

management/server/types/account_test.go

@@ -1751,71 +1751,3 @@ func hasPrivateAccessPolicy(account *Account, serviceID string) bool {
 	}
 	return false
 }
-
-func TestForcesRoutingPeerDNSResolution(t *testing.T) {
-	buildAccountRes := func(serviceEnabled, targetEnabled, resourceEnabled bool, targetType service.TargetType, resType resourceTypes.NetworkResourceType) *Account {
-		return &Account{
-			Id: "accountID",
-			Groups: map[string]*Group{
-				"router-group": {ID: "router-group", Peers: []string{"router-peer-grp"}},
-			},
-			NetworkRouters: []*routerTypes.NetworkRouter{
-				{ID: "r1", NetworkID: "net-1", AccountID: "accountID", Peer: "router-peer", Enabled: true},
-				{ID: "r2", NetworkID: "net-1", AccountID: "accountID", PeerGroups: []string{"router-group"}, Enabled: true},
-			},
-			NetworkResources: []*resourceTypes.NetworkResource{
-				{ID: "res-domain", AccountID: "accountID", NetworkID: "net-1", Type: resType, Domain: "example.org", Enabled: resourceEnabled},
-			},
-			Services: []*service.Service{
-				{
-					ID: "svc-1", AccountID: "accountID", Enabled: serviceEnabled,
-					Targets: []*service.Target{
-						{TargetId: "res-domain", TargetType: targetType, Enabled: targetEnabled},
-					},
-				},
-			},
-		}
-	}
-
-	buildAccount := func(serviceEnabled, targetEnabled, resourceEnabled bool, targetType service.TargetType) *Account {
-		return buildAccountRes(serviceEnabled, targetEnabled, resourceEnabled, targetType, resourceTypes.Domain)
-	}
-
-	t.Run("router peer for RP-targeted domain resource is forced", func(t *testing.T) {
-		account := buildAccount(true, true, true, service.TargetTypeDomain)
-		routers := account.GetResourceRoutersMap()
-		assert.True(t, account.forcesRoutingPeerDNSResolution("router-peer", routers), "direct router peer should be forced")
-		assert.True(t, account.forcesRoutingPeerDNSResolution("router-peer-grp", routers), "group-member router peer should be forced")
-	})
-
-	t.Run("non-router peer is not forced", func(t *testing.T) {
-		account := buildAccount(true, true, true, service.TargetTypeDomain)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("other-peer", account.GetResourceRoutersMap()))
-	})
-
-	t.Run("not forced when service disabled", func(t *testing.T) {
-		account := buildAccount(false, true, true, service.TargetTypeDomain)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("router-peer", account.GetResourceRoutersMap()))
-	})
-
-	t.Run("not forced when target disabled", func(t *testing.T) {
-		account := buildAccount(true, false, true, service.TargetTypeDomain)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("router-peer", account.GetResourceRoutersMap()))
-	})
-
-	t.Run("not forced when resource disabled", func(t *testing.T) {
-		account := buildAccount(true, true, false, service.TargetTypeDomain)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("router-peer", account.GetResourceRoutersMap()))
-	})
-
-	t.Run("not forced for non-domain target type", func(t *testing.T) {
-		account := buildAccount(true, true, true, service.TargetTypePeer)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("router-peer", account.GetResourceRoutersMap()))
-	})
-
-	t.Run("not forced when targeted resource is not a domain", func(t *testing.T) {
-		account := buildAccountRes(true, true, true, service.TargetTypeDomain, resourceTypes.Host)
-		assert.False(t, account.forcesRoutingPeerDNSResolution("router-peer", account.GetResourceRoutersMap()),
-			"a domain target pointing at a non-domain resource must not force resolution")
-	})
-}

management/server/user.go

@@ -321,10 +321,6 @@ func (am *DefaultAccountManager) DeleteUser(ctx context.Context, accountID, init
 		return err
 	}
 
-	if targetUser.AccountID != accountID {
-		return status.NewUserNotFoundError(targetUserID)
-	}
-
 	if targetUser.Role == types.UserRoleOwner {
 		return status.NewOwnerDeletePermissionError()
 	}

management/server/user_test.go

@@ -802,52 +802,6 @@ func TestUser_DeleteUser_SelfDelete(t *testing.T) {
 	}
 }
 
-func TestUser_DeleteUser_OtherAccount(t *testing.T) {
-	testStore, cleanup, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
-	if err != nil {
-		t.Fatalf("Error when creating store: %s", err)
-	}
-	t.Cleanup(cleanup)
-
-	account := newAccountWithId(context.Background(), mockAccountID, mockUserID, "", "", "", false)
-	if err = testStore.SaveAccount(context.Background(), account); err != nil {
-		t.Fatalf("Error when saving account: %s", err)
-	}
-
-	otherAccount := newAccountWithId(context.Background(), "otherAccount", "otherOwner", "", "", "", false)
-	otherAccount.Users["otherRegularUser"] = &types.User{
-		Id:        "otherRegularUser",
-		AccountID: "otherAccount",
-		Role:      types.UserRoleUser,
-	}
-	otherAccount.Users["otherServiceUser"] = &types.User{
-		Id:              "otherServiceUser",
-		AccountID:       "otherAccount",
-		Role:            types.UserRoleUser,
-		IsServiceUser:   true,
-		ServiceUserName: "otherServiceUser",
-	}
-	if err = testStore.SaveAccount(context.Background(), otherAccount); err != nil {
-		t.Fatalf("Error when saving other account: %s", err)
-	}
-
-	am := DefaultAccountManager{
-		Store:              testStore,
-		eventStore:         &activity.InMemoryEventStore{},
-		permissionsManager: permissions.NewManager(testStore),
-	}
-
-	for _, targetUserID := range []string{"otherRegularUser", "otherServiceUser"} {
-		t.Run(targetUserID, func(t *testing.T) {
-			err := am.DeleteUser(context.Background(), mockAccountID, mockUserID, targetUserID)
-			assert.Equal(t, status.NewUserNotFoundError(targetUserID), err)
-
-			_, err = testStore.GetUserByUserID(context.Background(), store.LockingStrengthNone, targetUserID)
-			assert.NoError(t, err, "user of another account must not be deleted")
-		})
-	}
-}
-
 func TestUser_DeleteUser_regularUser(t *testing.T) {
 	store, cleanup, err := store.NewTestStoreFromSQL(context.Background(), "", t.TempDir())
 	if err != nil {

proxy/internal/auth/tunnel_cache.go

@@ -3,30 +3,20 @@ package auth
 import (
 	"context"
 	"net/netip"
-	"os"
-	"strings"
 	"sync"
 	"time"
 
-	log "github.com/sirupsen/logrus"
 	"golang.org/x/sync/singleflight"
 
 	"github.com/netbirdio/netbird/proxy/internal/types"
 	"github.com/netbirdio/netbird/shared/management/proto"
 )
 
-// tunnelCacheTTL is the default cap on how long a positive ValidateTunnelPeer
-// result is reused before re-fetching from management. 5 minutes balances
-// freshness against management load on busy mesh networks. Override it with
-// envTunnelCacheTTL when an account needs authorization changes to take effect
-// sooner (at the cost of more ValidateTunnelPeer RPCs).
+// tunnelCacheTTL caps how long a positive ValidateTunnelPeer result is
+// reused before re-fetching from management. 5 minutes balances freshness
+// against management load on busy mesh networks.
 const tunnelCacheTTL = 300 * time.Second
 
-// envTunnelCacheTTL overrides tunnelCacheTTL. The value is a Go duration string
-// (e.g. "30s", "2m"); an unset, unparseable, or non-positive value keeps the
-// default.
-const envTunnelCacheTTL = "NB_PROXY_TUNNEL_CACHE_TTL"
-
 // tunnelCachePerAccount caps the number of cached identities per account.
 // Bounded eviction avoids memory growth in pathological cases (huge peer
 // roster, brief request bursts) while staying generous for normal use.
@@ -70,35 +60,16 @@ type accountBucket struct {
 	order []tunnelCacheKey
 }
 
-// newTunnelValidationCache constructs a cache with the configured TTL
-// (envTunnelCacheTTL override or default) and default bounds.
+// newTunnelValidationCache constructs a cache with default TTL and bounds.
 func newTunnelValidationCache() *tunnelValidationCache {
 	return &tunnelValidationCache{
 		entries: make(map[types.AccountID]*accountBucket),
-		ttl:     tunnelCacheTTLFromEnv(),
+		ttl:     tunnelCacheTTL,
 		maxSize: tunnelCachePerAccount,
 		now:     time.Now,
 	}
 }
 
-// tunnelCacheTTLFromEnv returns the tunnel-cache TTL, honoring the
-// envTunnelCacheTTL override. The override must be a positive Go duration
-// string (e.g. "30s", "2m"); anything unset, unparseable, or non-positive
-// falls back to tunnelCacheTTL.
-func tunnelCacheTTLFromEnv() time.Duration {
-	raw := strings.TrimSpace(os.Getenv(envTunnelCacheTTL))
-	if raw == "" {
-		return tunnelCacheTTL
-	}
-	d, err := time.ParseDuration(raw)
-	if err != nil || d <= 0 {
-		log.Warnf("ignoring invalid %s=%q (want a positive Go duration like 30s or 2m); using default %s",
-			envTunnelCacheTTL, raw, tunnelCacheTTL)
-		return tunnelCacheTTL
-	}
-	return d
-}
-
 // get returns a cached response for the key, or nil when missing or
 // expired. Expired entries are evicted lazily on read.
 func (c *tunnelValidationCache) get(key tunnelCacheKey) *proto.ValidateTunnelPeerResponse {

proxy/internal/auth/tunnel_cache_test.go

@@ -169,32 +169,3 @@ func TestTunnelCache_BoundedSizeEvictsOldest(t *testing.T) {
 	assert.NotNil(t, cache.get(keys[1]), "second-newest must remain cached")
 	assert.NotNil(t, cache.get(keys[2]), "newest must remain cached")
 }
-
-func TestTunnelCacheTTLFromEnv(t *testing.T) {
-	t.Run("unset uses default", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "")
-		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
-	})
-	t.Run("valid duration overrides", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "45s")
-		assert.Equal(t, 45*time.Second, tunnelCacheTTLFromEnv())
-	})
-	t.Run("whitespace trimmed", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "  2m ")
-		assert.Equal(t, 2*time.Minute, tunnelCacheTTLFromEnv())
-	})
-	t.Run("unparseable uses default", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "nonsense")
-		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
-	})
-	t.Run("non-positive uses default", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "0s")
-		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
-		t.Setenv(envTunnelCacheTTL, "-30s")
-		assert.Equal(t, tunnelCacheTTL, tunnelCacheTTLFromEnv())
-	})
-	t.Run("constructor honors override", func(t *testing.T) {
-		t.Setenv(envTunnelCacheTTL, "90s")
-		assert.Equal(t, 90*time.Second, newTunnelValidationCache().ttl)
-	})
-}

proxy/internal/middleware/builtin/llm_guardrail/factory.go

@@ -10,15 +10,11 @@ import (
 )
 
 // Config is the JSON-decoded shape accepted by the factory. The
-// runtime path consumes the normalised allowlists; raw config is not
+// runtime path consumes the normalised allowlist; raw config is not
 // retained beyond construction.
 type Config struct {
-	// ProviderAllowlists maps a resolved provider id (KeyLLMResolvedProviderID) to
-	// its model allowlist. A provider present is restricted to those models; one
-	// absent is unrestricted. Kept per-provider so one provider's list can't leak
-	// onto another.
-	ProviderAllowlists map[string][]string `json:"provider_allowlists,omitempty"`
-	PromptCapture      PromptCapture       `json:"prompt_capture"`
+	ModelAllowlist []string      `json:"model_allowlist"`
+	PromptCapture  PromptCapture `json:"prompt_capture"`
 }
 
 // PromptCapture toggles the optional prompt capture + redaction step
@@ -58,28 +54,21 @@ func isEmptyJSON(raw []byte) bool {
 	return false
 }
 
-// normaliseConfig lowercases and trims allowlist entries for case-insensitive
-// matching; empty entries drop. A provider whose entries all drop keeps an empty
-// (non-nil) list — "deny every model" — distinct from an absent provider
-// (unrestricted).
+// normaliseConfig lowercases and trims allowlist entries so the runtime
+// match is case-insensitive. Empty entries are dropped.
 func normaliseConfig(cfg Config) Config {
-	if len(cfg.ProviderAllowlists) == 0 {
-		cfg.ProviderAllowlists = nil
+	if len(cfg.ModelAllowlist) == 0 {
 		return cfg
 	}
-	cleaned := make(map[string][]string, len(cfg.ProviderAllowlists))
-	for provider, models := range cfg.ProviderAllowlists {
-		list := make([]string, 0, len(models))
-		for _, entry := range models {
-			n := normaliseModel(entry)
-			if n == "" {
-				continue
-			}
-			list = append(list, n)
+	cleaned := make([]string, 0, len(cfg.ModelAllowlist))
+	for _, entry := range cfg.ModelAllowlist {
+		n := normaliseModel(entry)
+		if n == "" {
+			continue
 		}
-		cleaned[provider] = list
+		cleaned = append(cleaned, n)
 	}
-	cfg.ProviderAllowlists = cleaned
+	cfg.ModelAllowlist = cleaned
 	return cfg
 }
 

proxy/internal/middleware/builtin/llm_guardrail/middleware.go

@@ -83,9 +83,8 @@ func (m *Middleware) MutationsSupported() bool { return false }
 // prompt capture only affects the metadata emitted alongside an allow.
 func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middleware.Output, error) {
 	model, modelPresent := lookupMetadata(in.Metadata, middleware.KeyLLMModel)
-	providerID, _ := lookupMetadata(in.Metadata, middleware.KeyLLMResolvedProviderID)
 
-	if denial := m.evaluateAllowlist(providerID, model, modelPresent); denial != nil {
+	if denial := m.evaluateAllowlist(model, modelPresent); denial != nil {
 		return denial, nil
 	}
 
@@ -111,32 +110,20 @@ func (m *Middleware) Invoke(_ context.Context, in *middleware.Input) (*middlewar
 // is a no-op.
 func (m *Middleware) Close() error { return nil }
 
-// evaluateAllowlist denies when the resolved provider's allowlist rejects the
-// model; nil means proceed. Scoped to the provider llm_router resolved, so an
-// unrestricted provider (absent from config) is never caught by another's list.
-func (m *Middleware) evaluateAllowlist(providerID, model string, modelPresent bool) *middleware.Output {
-	if len(m.cfg.ProviderAllowlists) == 0 {
+// evaluateAllowlist returns a deny Output when the configured allowlist
+// rejects the model. A nil return means the request should proceed.
+func (m *Middleware) evaluateAllowlist(model string, modelPresent bool) *middleware.Output {
+	if len(m.cfg.ModelAllowlist) == 0 {
 		return nil
 	}
-	// Restrictions exist but the resolved provider is unknown, so we can't tell
-	// if this request targets a restricted provider — fail closed. llm_router
-	// normally stamps the provider first, so this is a defensive guard.
-	if providerID == "" {
-		return denyModel("", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
-	}
-	allowlist, restricted := m.cfg.ProviderAllowlists[providerID]
-	if !restricted {
-		// This provider has no allowlist (some authorising policy left it
-		// unrestricted); management owns any per-policy/group decision.
-		return nil
-	}
-	// Fail closed: with an allowlist in effect for this provider, a request whose
-	// model the parser couldn't extract (absent/empty) is denied. This enforces
-	// the allowlist for path-routed providers (Bedrock, Vertex) with no body model.
+	// Fail closed: with an allowlist configured, a request whose model the
+	// upstream parser could not extract (absent or empty) must be denied rather
+	// than allowed. This is what enforces the allowlist for URL/path-routed
+	// providers (Bedrock, Vertex, ...) whose model lives outside the JSON body.
 	if !modelPresent || normaliseModel(model) == "" {
 		return denyModel("", denyCodeModelUnknown, denyMessageModelUnknown, denyReasonModelUnknown)
 	}
-	if modelInAllowlist(allowlist, model) {
+	if m.modelInAllowlist(model) {
 		return nil
 	}
 	return denyModel(model, denyCodeModel, denyMessageModel, denyReasonModel)
@@ -164,15 +151,14 @@ func denyModel(model, code, message, reason string) *middleware.Output {
 	}
 }
 
-// modelInAllowlist reports whether the model matches any entry in the supplied
-// (already-normalised) allowlist under the case-insensitive, trim-tolerant
-// comparison rule.
-func modelInAllowlist(allowlist []string, model string) bool {
+// modelInAllowlist reports whether the model matches any allowlist
+// entry under the case-insensitive, trim-tolerant comparison rule.
+func (m *Middleware) modelInAllowlist(model string) bool {
 	normalised := normaliseModel(model)
 	if normalised == "" {
 		return false
 	}
-	for _, allowed := range allowlist {
+	for _, allowed := range m.cfg.ModelAllowlist {
 		if allowed == normalised {
 			return true
 		}

proxy/internal/middleware/builtin/llm_guardrail/middleware_test.go

@@ -26,25 +26,6 @@ func newInput(meta ...middleware.KV) *middleware.Input {
 	return &middleware.Input{Slot: middleware.SlotOnRequest, Metadata: meta}
 }
 
-const (
-	testProvider  = "prov-1"
-	otherProvider = "prov-2"
-)
-
-// providerCfg builds a Config restricting testProvider to the given models.
-func providerCfg(models ...string) Config {
-	return Config{ProviderAllowlists: map[string][]string{testProvider: models}}
-}
-
-// newInputProvider builds an input that carries a resolved provider id (as
-// llm_router would stamp) plus any extra metadata.
-func newInputProvider(provider string, meta ...middleware.KV) *middleware.Input {
-	all := make([]middleware.KV, 0, len(meta)+1)
-	all = append(all, middleware.KV{Key: middleware.KeyLLMResolvedProviderID, Value: provider})
-	all = append(all, meta...)
-	return &middleware.Input{Slot: middleware.SlotOnRequest, Metadata: all}
-}
-
 func TestMiddlewareIdentity(t *testing.T) {
 	mw := New(Config{})
 	assert.Equal(t, ID, mw.ID(), "middleware ID must be llm_guardrail")
@@ -66,12 +47,12 @@ func TestMiddlewareIdentity(t *testing.T) {
 
 func TestAllowlistEmptyAllowsAnyModel(t *testing.T) {
 	mw := New(Config{})
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	out, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
 	))
 	require.NoError(t, err)
 	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionAllow, out.Decision, "no provider allowlists must allow any model")
+	assert.Equal(t, middleware.DecisionAllow, out.Decision, "empty allowlist must allow any model")
 	v, ok := metaValue(t, out.Metadata, middleware.KeyLLMPolicyDecision)
 	require.True(t, ok, "decision metadata must be emitted")
 	assert.Equal(t, "allow", v, "decision must be allow")
@@ -81,8 +62,8 @@ func TestAllowlistEmptyAllowsAnyModel(t *testing.T) {
 }
 
 func TestAllowlistMatchAllows(t *testing.T) {
-	mw := New(providerCfg("gpt-4o", "claude-opus-4"))
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	mw := New(Config{ModelAllowlist: []string{"gpt-4o", "claude-opus-4"}})
+	out, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
 	))
 	require.NoError(t, err)
@@ -90,8 +71,8 @@ func TestAllowlistMatchAllows(t *testing.T) {
 }
 
 func TestAllowlistMissDenies(t *testing.T) {
-	mw := New(providerCfg("gpt-4o"))
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	mw := New(Config{ModelAllowlist: []string{"gpt-4o"}})
+	out, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "claude-opus-4"},
 	))
 	require.NoError(t, err)
@@ -110,10 +91,10 @@ func TestAllowlistMissDenies(t *testing.T) {
 }
 
 func TestAllowlistCaseInsensitive(t *testing.T) {
-	mw := New(providerCfg("  GPT-4o  ", "Claude-OPUS-4"))
+	mw := New(Config{ModelAllowlist: []string{"  GPT-4o  ", "Claude-OPUS-4"}})
 	cases := []string{"gpt-4o", "GPT-4O", "  claude-opus-4 "}
 	for _, model := range cases {
-		out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+		out, err := mw.Invoke(context.Background(), newInput(
 			middleware.KV{Key: middleware.KeyLLMModel, Value: model},
 		))
 		require.NoError(t, err)
@@ -122,15 +103,14 @@ func TestAllowlistCaseInsensitive(t *testing.T) {
 }
 
 func TestAllowlistMissingModelKeyDenies(t *testing.T) {
-	// Fail closed: with an allowlist in effect for the resolved provider, a
-	// request whose model the parser could not extract (URL/path-routed
-	// providers such as Bedrock or Vertex whose shape wasn't recognised) must be
-	// denied, not allowed.
-	mw := New(providerCfg("gpt-4o"))
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider))
+	// Fail closed: with an allowlist configured, a request whose model the
+	// parser could not extract (URL/path-routed providers such as Bedrock or
+	// Vertex whose shape wasn't recognised) must be denied, not allowed.
+	mw := New(Config{ModelAllowlist: []string{"gpt-4o"}})
+	out, err := mw.Invoke(context.Background(), newInput())
 	require.NoError(t, err)
 	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "absent model must be denied when the provider is restricted")
+	assert.Equal(t, middleware.DecisionDeny, out.Decision, "absent model must be denied when an allowlist is set")
 	assert.Equal(t, 403, out.DenyStatus, "deny status must be 403")
 	require.NotNil(t, out.DenyReason, "deny reason must be populated")
 	assert.Equal(t, "llm_policy.model_unknown", out.DenyReason.Code, "deny code must be model_unknown")
@@ -142,101 +122,26 @@ func TestAllowlistMissingModelKeyDenies(t *testing.T) {
 
 func TestAllowlistEmptyModelValueDenies(t *testing.T) {
 	// A present-but-empty model is as undeterminable as an absent one.
-	mw := New(providerCfg("gpt-4o"))
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	mw := New(Config{ModelAllowlist: []string{"gpt-4o"}})
+	out, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "   "},
 	))
 	require.NoError(t, err)
 	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "empty model must be denied when the provider is restricted")
+	assert.Equal(t, middleware.DecisionDeny, out.Decision, "empty model must be denied when an allowlist is set")
 	require.NotNil(t, out.DenyReason, "deny reason must be populated")
 	assert.Equal(t, "llm_policy.model_unknown", out.DenyReason.Code, "deny code must be model_unknown")
 }
 
 func TestAllowlistEmptyListAllowsMissingModel(t *testing.T) {
-	// Without any provider allowlists there is nothing to enforce, so a missing
-	// model is still allowed — the fail-closed rule only applies when a
-	// restriction is in effect.
+	// Without an allowlist there is nothing to enforce, so a missing model is
+	// still allowed — the fail-closed rule only applies when a list is set.
 	mw := New(Config{})
 	out, err := mw.Invoke(context.Background(), newInput())
 	require.NoError(t, err)
 	assert.Equal(t, middleware.DecisionAllow, out.Decision, "no allowlist must allow even without a model")
 }
 
-func TestUnrestrictedProviderAllowsAnyModel(t *testing.T) {
-	// The request resolved to otherProvider, which has no allowlist, so its
-	// traffic must not be caught by testProvider's restriction — the
-	// cross-provider-leak / false-deny guard.
-	mw := New(providerCfg("gpt-4o"))
-	out, err := mw.Invoke(context.Background(), newInputProvider(otherProvider,
-		middleware.KV{Key: middleware.KeyLLMModel, Value: "claude-opus-4"},
-	))
-	require.NoError(t, err)
-	assert.Equal(t, middleware.DecisionAllow, out.Decision, "an unrestricted provider must not inherit another provider's allowlist")
-}
-
-func TestPerProviderAllowlistsAreIsolated(t *testing.T) {
-	// gpt-4o is allowed only on testProvider; claude-opus-4 only on
-	// otherProvider. A model allowlisted for one provider must not be usable on
-	// the other — the fail-closed layer never unions allowlists across providers.
-	mw := New(Config{ProviderAllowlists: map[string][]string{
-		testProvider:  {"gpt-4o"},
-		otherProvider: {"claude-opus-4"},
-	}})
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
-		middleware.KV{Key: middleware.KeyLLMModel, Value: "claude-opus-4"},
-	))
-	require.NoError(t, err)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "claude-opus-4 is allowed only on otherProvider, not testProvider")
-	require.NotNil(t, out.DenyReason)
-	assert.Equal(t, "llm_policy.model_blocked", out.DenyReason.Code, "cross-provider model must be blocked, not model_unknown")
-}
-
-func TestRestrictionsButNoResolvedProviderFailsClosed(t *testing.T) {
-	// Restrictions exist for the account but the resolved provider id is absent,
-	// so the request cannot be scoped to a provider. Fail closed rather than
-	// wave it through.
-	mw := New(providerCfg("gpt-4o"))
-	out, err := mw.Invoke(context.Background(), newInput(
-		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
-	))
-	require.NoError(t, err)
-	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "missing resolved provider must fail closed when restrictions exist")
-	require.NotNil(t, out.DenyReason)
-	assert.Equal(t, "llm_policy.model_unknown", out.DenyReason.Code, "deny code must be model_unknown")
-}
-
-func TestEnabledButEmptyAllowlistDeniesEveryModel(t *testing.T) {
-	// An allowlist-enabled provider with zero models is distinct from an
-	// unrestricted (absent) provider: it must deny every model.
-	mw := New(providerCfg())
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
-		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
-	))
-	require.NoError(t, err)
-	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "an enabled-but-empty allowlist must deny every model")
-	require.NotNil(t, out.DenyReason)
-	assert.Equal(t, "llm_policy.model_blocked", out.DenyReason.Code, "deny code must be model_blocked, not model_unknown")
-}
-
-func TestFactoryAllEmptyEntriesDenyEveryModel(t *testing.T) {
-	// All the provider's entries are blank; they collapse to a non-nil empty
-	// list (deny everything for that provider), not "no restriction".
-	raw := []byte(`{"provider_allowlists":{"prov-1":["","   "]}}`)
-	mw, err := Factory{}.New(raw)
-	require.NoError(t, err)
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
-		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
-	))
-	require.NoError(t, err)
-	require.NotNil(t, out)
-	assert.Equal(t, middleware.DecisionDeny, out.Decision, "all-blank allowlist entries must still restrict the provider")
-	require.NotNil(t, out.DenyReason)
-	assert.Equal(t, "llm_policy.model_blocked", out.DenyReason.Code, "deny code must be model_blocked")
-}
-
 func TestPromptCaptureDisabledEmitsNoPrompt(t *testing.T) {
 	mw := New(Config{})
 	out, err := mw.Invoke(context.Background(), newInput(
@@ -312,8 +217,8 @@ func TestFactoryAcceptsZeroConfigs(t *testing.T) {
 
 func TestFactoryDecodesValidConfig(t *testing.T) {
 	cfg := Config{
-		ProviderAllowlists: map[string][]string{testProvider: {"gpt-4o"}},
-		PromptCapture:      PromptCapture{Enabled: true, RedactPii: true},
+		ModelAllowlist: []string{"gpt-4o"},
+		PromptCapture:  PromptCapture{Enabled: true, RedactPii: true},
 	}
 	raw, err := json.Marshal(cfg)
 	require.NoError(t, err, "marshalling test config must succeed")
@@ -329,15 +234,15 @@ func TestFactoryRejectsMalformedJSON(t *testing.T) {
 }
 
 func TestFactoryNormalisesAllowlist(t *testing.T) {
-	raw := []byte(`{"provider_allowlists":{"prov-1":["  GPT-4o  ","",""," Claude-3 "]}}`)
+	raw := []byte(`{"model_allowlist":["  GPT-4o  ","",""," Claude-3 "]}`)
 	mw, err := Factory{}.New(raw)
 	require.NoError(t, err)
-	out, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	out, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "gpt-4o"},
 	))
 	require.NoError(t, err)
 	assert.Equal(t, middleware.DecisionAllow, out.Decision, "factory must lowercase + trim allowlist entries")
-	out2, err := mw.Invoke(context.Background(), newInputProvider(testProvider,
+	out2, err := mw.Invoke(context.Background(), newInput(
 		middleware.KV{Key: middleware.KeyLLMModel, Value: "claude-3"},
 	))
 	require.NoError(t, err)

proxy/internal/middleware/builtin/llm_limit_check/middleware.go

@@ -175,7 +175,7 @@ func denyFromManagement(resp *proto.CheckLLMPolicyLimitsResponse) *middleware.Ou
 		DenyStatus: 403,
 		DenyReason: &middleware.DenyReason{
 			Code:    code,
-			Message: denyMessageForCode(code),
+			Message: "LLM policy limit exceeded",
 		},
 		Metadata: []middleware.KV{
 			{Key: middleware.KeyLLMPolicyDecision, Value: "deny"},
@@ -184,21 +184,6 @@ func denyFromManagement(resp *proto.CheckLLMPolicyLimitsResponse) *middleware.Ou
 	}
 }
 
-// denyMessageForCode maps a management deny code to a public message.
-// Model-allowlist rejections get a model-specific message matching the
-// local guardrail; everything else keeps the generic quota wording. The
-// message stays generic so it never leaks internal quota detail.
-func denyMessageForCode(code string) string {
-	switch code {
-	case "llm_policy.model_blocked":
-		return "model is not in the policy allowlist"
-	case "llm_policy.model_unknown":
-		return "request model could not be determined for the policy allowlist"
-	default:
-		return "LLM policy limit exceeded"
-	}
-}
-
 // lookupKV returns the value associated with key, or the empty
 // string when absent.
 func lookupKV(kvs []middleware.KV, key string) string {

proxy/internal/middleware/builtin/llm_limit_check/middleware_test.go

@@ -115,46 +115,6 @@ func TestInvoke_DenyConvertsToProxyDeny(t *testing.T) {
 	assert.NotContains(t, out.DenyReason.Message, "1000", "internal cap numbers must not reach the caller")
 }
 
-// TestInvoke_ModelDenyMessages proves a model-allowlist rejection gets a
-// model-specific public message rather than the generic quota wording, so a
-// blocked or undetermined model reads consistently with the local guardrail.
-func TestInvoke_ModelDenyMessages(t *testing.T) {
-	cases := []struct {
-		name    string
-		code    string
-		message string
-	}{
-		{"blocked", "llm_policy.model_blocked", "model is not in the policy allowlist"},
-		{"unknown", "llm_policy.model_unknown", "request model could not be determined for the policy allowlist"},
-	}
-	for _, tc := range cases {
-		t.Run(tc.name, func(t *testing.T) {
-			mgmt := &fakeMgmt{
-				checkResp: &proto.CheckLLMPolicyLimitsResponse{
-					Decision: "deny",
-					DenyCode: tc.code,
-				},
-			}
-			m := New(mgmt, nil)
-
-			out := runInvoke(t, m, &middleware.Input{
-				AccountID:  "acc-1",
-				UserGroups: []string{"grp-engineers"},
-				Metadata: []middleware.KV{
-					{Key: middleware.KeyLLMResolvedProviderID, Value: "prov-1"},
-					{Key: middleware.KeyLLMModel, Value: "some-model"},
-				},
-			})
-
-			assert.Equal(t, middleware.DecisionDeny, out.Decision)
-			require.NotNil(t, out.DenyReason, "deny envelope must carry a reason payload")
-			assert.Equal(t, tc.code, out.DenyReason.Code, "canonical deny code surfaces to the caller")
-			assert.Equal(t, tc.message, out.DenyReason.Message,
-				"model denials must use a model-specific message, matching the local guardrail")
-		})
-	}
-}
-
 // TestInvoke_NoMgmtClientPassesThrough proves the partial-wiring
 // safety: a middleware constructed without a management client
 // allows every request without attribution. This makes a half-set-up

proxy/internal/middleware/builtin/llm_request_parser/guardrail_allowlist_test.go

@@ -25,17 +25,10 @@ func runParserGuardrail(t *testing.T, url string, body []byte, allowlist []strin
 	})
 	require.NoError(t, err, "parser must not error")
 
-	const providerID = "prov-under-test"
-	guard := llm_guardrail.New(llm_guardrail.Config{
-		ProviderAllowlists: map[string][]string{providerID: allowlist},
-	})
-	// The real chain has llm_router stamp the resolved provider id before the
-	// guardrail runs; the parser doesn't, so add it here so the guardrail can
-	// scope the allowlist to this provider.
-	meta := append([]middleware.KV{{Key: middleware.KeyLLMResolvedProviderID, Value: providerID}}, parsed.Metadata...)
+	guard := llm_guardrail.New(llm_guardrail.Config{ModelAllowlist: allowlist})
 	out, err := guard.Invoke(context.Background(), &middleware.Input{
 		Slot:     middleware.SlotOnRequest,
-		Metadata: meta,
+		Metadata: parsed.Metadata,
 	})
 	require.NoError(t, err, "guardrail must not error")
 	require.NotNil(t, out, "guardrail must return an output")

shared/management/types/network.go

@@ -47,10 +47,6 @@ type NetworkMap struct {
 	ForwardingRules     []*ForwardingRule
 	AuthorizedUsers     map[string]map[string]struct{}
 	EnableSSH           bool
-	// ForceRoutingPeerDNSResolution forces the peer to run/use routing-peer DNS
-	// resolution regardless of the account-global setting, for reverse-proxy
-	// domain targets.
-	ForceRoutingPeerDNSResolution bool
 }
 
 func (nm *NetworkMap) Merge(other *NetworkMap) {
@@ -60,7 +56,6 @@ func (nm *NetworkMap) Merge(other *NetworkMap) {
 	nm.FirewallRules = mergeUnique(nm.FirewallRules, other.FirewallRules)
 	nm.RoutesFirewallRules = mergeUnique(nm.RoutesFirewallRules, other.RoutesFirewallRules)
 	nm.ForwardingRules = mergeUnique(nm.ForwardingRules, other.ForwardingRules)
-	nm.ForceRoutingPeerDNSResolution = nm.ForceRoutingPeerDNSResolution || other.ForceRoutingPeerDNSResolution
 }
 
 type comparableObject[T any] interface {

shared/management/types/networkmap_components.go

@@ -56,11 +56,6 @@ type NetworkMapComponents struct {
 
 	// true when returning an empty-like map (returned instead of nil)
 	empty bool
-
-	// ForceRoutingPeerDNSResolution forces the peer to run/use routing-peer DNS
-	// resolution regardless of the account-global setting, for reverse-proxy
-	// domain targets.
-	ForceRoutingPeerDNSResolution bool
 }
 
 type routeIndexEntry struct {
@@ -195,8 +190,6 @@ func (c *NetworkMapComponents) Calculate(ctx context.Context) *NetworkMap {
 		RoutesFirewallRules: append(networkResourcesFirewallRules, routesFirewallRules...),
 		AuthorizedUsers:     authorizedUsers,
 		EnableSSH:           sshEnabled,
-
-		ForceRoutingPeerDNSResolution: c.ForceRoutingPeerDNSResolution,
 	}
 }