[client] Return empty map from test mock GetStats to satisfy nilnil linter

When a peer went idle under lazy connections, the WireGuard peer was
removed and the wake endpoint re-armed with only the overlay allowed
IPs, dropping routed prefixes installed by the route manager. The
asynchronous route-watcher re-add uses update_only, which is a silent
no-op while the peer is absent, so routed subnets stayed black-holed
until the peer was woken by other means.

Split the idle transition from the full close: Conn.Idle tears down
transports, cancels pending delayed endpoint updates and updates the
status without touching the WireGuard peer. The activity listener then
arms the wake endpoint via the new IdlePeerEndpoint operation, which
removes and re-creates the peer in a single transaction: handshake
state is dropped (keeping the handshake-first wake semantics of packet
staging and first-packet capture/reinjection) while the currently
installed allowed IPs are preserved. The read-modify-write runs under
the interface mutex, serializing it against concurrent allowed IP
updates from the route manager.

Conn.Close no longer takes signalToRemote: the idle transition is the
only path that signals GOAWAY to the remote peer.

client/iface/configurer/common.go

@@ -3,6 +3,7 @@ package configurer
 import (
 	"net"
 	"net/netip"
+	"time"
 
 	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 )
@@ -19,6 +20,43 @@ func buildPresharedKeyConfig(peerKey wgtypes.Key, psk wgtypes.Key, updateOnly bo
 	}
 }
 
+// buildIdlePeerEndpointConfig creates a config that removes and re-creates a peer in a
+// single transaction with the given allowed IPs, endpoint and disabled keepalive.
+func buildIdlePeerEndpointConfig(peerKey wgtypes.Key, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) wgtypes.Config {
+	keepAlive := time.Duration(0)
+	return wgtypes.Config{
+		Peers: []wgtypes.PeerConfig{
+			{
+				PublicKey: peerKey,
+				Remove:    true,
+			},
+			{
+				PublicKey:                   peerKey,
+				AllowedIPs:                  prefixesToIPNets(allowedIPs),
+				Endpoint:                    endpoint,
+				PersistentKeepaliveInterval: &keepAlive,
+			},
+		},
+	}
+}
+
+// mergePrefixes returns the union of the two prefix lists, keeping the original order and
+// dropping duplicates.
+func mergePrefixes(current, base []netip.Prefix) []netip.Prefix {
+	merged := make([]netip.Prefix, 0, len(current)+len(base))
+	seen := make(map[netip.Prefix]struct{}, len(current)+len(base))
+	for _, group := range [][]netip.Prefix{current, base} {
+		for _, prefix := range group {
+			if _, ok := seen[prefix]; ok {
+				continue
+			}
+			seen[prefix] = struct{}{}
+			merged = append(merged, prefix)
+		}
+	}
+	return merged
+}
+
 func prefixesToIPNets(prefixes []netip.Prefix) []net.IPNet {
 	ipNets := make([]net.IPNet, len(prefixes))
 	for i, prefix := range prefixes {

client/iface/configurer/kernel_unix.go

@@ -3,6 +3,7 @@
 package configurer
 
 import (
+	"errors"
 	"fmt"
 	"net"
 	"net/netip"
@@ -145,6 +146,39 @@ func (c *KernelConfigurer) RemovePeer(peerKey string) error {
 	return nil
 }
 
+// IdlePeerEndpoint re-creates the peer pointing at the lazy wake endpoint, dropping
+// handshake state while preserving the peer's currently installed allowed IPs.
+func (c *KernelConfigurer) IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error {
+	peerKeyParsed, err := wgtypes.ParseKey(peerKey)
+	if err != nil {
+		return err
+	}
+
+	var current []netip.Prefix
+	existing, err := c.getPeer(c.deviceName, peerKey)
+	switch {
+	case errors.Is(err, ErrPeerNotFound):
+	case err != nil:
+		return fmt.Errorf("get peer: %w", err)
+	default:
+		for _, ipNet := range existing.AllowedIPs {
+			addr, ok := netip.AddrFromSlice(ipNet.IP)
+			if !ok {
+				log.Warnf("failed to convert allowed IP %s of peer %s", ipNet.String(), peerKey)
+				continue
+			}
+			ones, _ := ipNet.Mask.Size()
+			current = append(current, netip.PrefixFrom(addr.Unmap(), ones))
+		}
+	}
+
+	config := buildIdlePeerEndpointConfig(peerKeyParsed, mergePrefixes(current, allowedIPs), endpoint)
+	if err := c.configure(config); err != nil {
+		return fmt.Errorf(`received error "%w" while setting idle endpoint for peer %s on interface %s`, err, peerKey, c.deviceName)
+	}
+	return nil
+}
+
 func (c *KernelConfigurer) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
 	ipNet := net.IPNet{
 		IP:   allowedIP.Addr().AsSlice(),

client/iface/configurer/usp.go

@@ -210,6 +210,64 @@ func (c *WGUSPConfigurer) RemovePeer(peerKey string) error {
 	return ipcErr
 }
 
+// IdlePeerEndpoint re-creates the peer pointing at the lazy wake endpoint, dropping
+// handshake state while preserving the peer's currently installed allowed IPs.
+func (c *WGUSPConfigurer) IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error {
+	peerKeyParsed, err := wgtypes.ParseKey(peerKey)
+	if err != nil {
+		return err
+	}
+
+	current, err := c.currentAllowedIPs(hex.EncodeToString(peerKeyParsed[:]))
+	if err != nil {
+		return fmt.Errorf("get current allowed IPs: %w", err)
+	}
+
+	config := buildIdlePeerEndpointConfig(peerKeyParsed, mergePrefixes(current, allowedIPs), endpoint)
+	if err := c.device.IpcSet(toWgUserspaceString(config)); err != nil {
+		return fmt.Errorf("set idle peer endpoint: %w", err)
+	}
+
+	if endpoint != nil {
+		addr, err := netip.ParseAddr(endpoint.IP.String())
+		if err != nil {
+			return fmt.Errorf("parse endpoint address: %w", err)
+		}
+		c.activityRecorder.UpsertAddress(peerKey, netip.AddrPortFrom(addr.Unmap(), uint16(endpoint.Port)))
+	}
+	return nil
+}
+
+// currentAllowedIPs returns the allowed IPs currently installed for the peer identified by
+// its hex-encoded public key. It returns an empty list when the peer does not exist.
+func (c *WGUSPConfigurer) currentAllowedIPs(hexKey string) ([]netip.Prefix, error) {
+	ipc, err := c.device.IpcGet()
+	if err != nil {
+		return nil, err
+	}
+
+	var prefixes []netip.Prefix
+	foundPeer := false
+	for _, line := range strings.Split(ipc, "\n") {
+		line = strings.TrimSpace(line)
+		if strings.HasPrefix(line, "public_key=") {
+			foundPeer = line == "public_key="+hexKey
+			continue
+		}
+		if !foundPeer || !strings.HasPrefix(line, "allowed_ip=") {
+			continue
+		}
+
+		prefix, err := netip.ParsePrefix(strings.TrimPrefix(line, "allowed_ip="))
+		if err != nil {
+			log.Warnf("failed to parse allowed IP %q: %v", line, err)
+			continue
+		}
+		prefixes = append(prefixes, prefix)
+	}
+	return prefixes, nil
+}
+
 func (c *WGUSPConfigurer) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
 	ipNet := net.IPNet{
 		IP:   allowedIP.Addr().AsSlice(),

client/iface/configurer/usp_idle_test.go

@@ -0,0 +1,158 @@
+package configurer
+
+import (
+	"encoding/hex"
+	"net"
+	"net/netip"
+	"strings"
+	"testing"
+	"time"
+
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	wgconn "golang.zx2c4.com/wireguard/conn"
+	"golang.zx2c4.com/wireguard/device"
+	"golang.zx2c4.com/wireguard/tun/netstack"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/iface/bind"
+)
+
+// newTestConfigurer creates a configurer backed by an in-memory wireguard-go device.
+func newTestConfigurer(t *testing.T) *WGUSPConfigurer {
+	t.Helper()
+
+	tunDev, _, err := netstack.CreateNetTUN([]netip.Addr{netip.MustParseAddr("100.64.0.1")}, []netip.Addr{}, 1280)
+	require.NoError(t, err)
+
+	wgDev := device.NewDevice(tunDev, wgconn.NewDefaultBind(), device.NewLogger(device.LogLevelSilent, "[test] "))
+	t.Cleanup(wgDev.Close)
+
+	c := NewUSPConfigurerNoUAPI(wgDev, "utun-test", bind.NewActivityRecorder())
+
+	key, err := wgtypes.GeneratePrivateKey()
+	require.NoError(t, err)
+	require.NoError(t, c.ConfigureInterface(key.String(), 0))
+
+	return c
+}
+
+// peerAllowedIPs returns the allowed IPs currently installed for the given peer.
+func peerAllowedIPs(t *testing.T, c *WGUSPConfigurer, pubKey string) []string {
+	t.Helper()
+
+	var ips []string
+	for _, line := range peerIpcLines(t, c, pubKey) {
+		if strings.HasPrefix(line, "allowed_ip=") {
+			ips = append(ips, strings.TrimPrefix(line, "allowed_ip="))
+		}
+	}
+	return ips
+}
+
+// peerEndpoint returns the endpoint currently installed for the given peer.
+func peerEndpoint(t *testing.T, c *WGUSPConfigurer, pubKey string) string {
+	t.Helper()
+
+	for _, line := range peerIpcLines(t, c, pubKey) {
+		if strings.HasPrefix(line, "endpoint=") {
+			return strings.TrimPrefix(line, "endpoint=")
+		}
+	}
+	return ""
+}
+
+// peerIpcLines returns the uapi config lines belonging to the given peer.
+func peerIpcLines(t *testing.T, c *WGUSPConfigurer, pubKey string) []string {
+	t.Helper()
+
+	key, err := wgtypes.ParseKey(pubKey)
+	require.NoError(t, err)
+	hexKey := hex.EncodeToString(key[:])
+
+	ipc, err := c.device.IpcGet()
+	require.NoError(t, err)
+
+	var lines []string
+	inPeer := false
+	for _, line := range strings.Split(ipc, "\n") {
+		line = strings.TrimSpace(line)
+		if strings.HasPrefix(line, "public_key=") {
+			inPeer = line == "public_key="+hexKey
+			continue
+		}
+		if inPeer && line != "" {
+			lines = append(lines, line)
+		}
+	}
+	return lines
+}
+
+// TestUSPConfigurer_IdlePeerEndpointPreservesAllowedIPs verifies the invariant the lazy idle
+// transition relies on: IdlePeerEndpoint re-creates the peer (dropping handshake state via the
+// remove+add transaction) while keeping every installed allowed IP, including routed
+// prefixes added later by the route manager, and points the endpoint at the wake listener.
+func TestUSPConfigurer_IdlePeerEndpointPreservesAllowedIPs(t *testing.T) {
+	c := newTestConfigurer(t)
+
+	peerKey, err := wgtypes.GeneratePrivateKey()
+	require.NoError(t, err)
+	pubKey := peerKey.PublicKey().String()
+
+	overlay := netip.MustParsePrefix("100.64.0.5/32")
+	routed := netip.MustParsePrefix("10.99.0.0/24")
+
+	realEndpoint := &net.UDPAddr{IP: net.ParseIP("127.0.0.1"), Port: 51821}
+	require.NoError(t, c.UpdatePeer(pubKey, []netip.Prefix{overlay}, 25*time.Second, realEndpoint, nil))
+	require.NoError(t, c.AddAllowedIP(pubKey, routed))
+
+	ips := peerAllowedIPs(t, c, pubKey)
+	require.Contains(t, ips, overlay.String(), "overlay prefix must be installed before the idle endpoint swap")
+	require.Contains(t, ips, routed.String(), "routed prefix must be installed before the idle endpoint swap")
+
+	wakeEndpoint := &net.UDPAddr{IP: net.ParseIP("127.2.0.5"), Port: 17473}
+	require.NoError(t, c.IdlePeerEndpoint(pubKey, []netip.Prefix{overlay}, wakeEndpoint))
+
+	ips = peerAllowedIPs(t, c, pubKey)
+	assert.Contains(t, ips, routed.String(), "routed prefix must survive the idle endpoint swap")
+	assert.Contains(t, ips, overlay.String(), "overlay prefix must survive the idle endpoint swap")
+	assert.Equal(t, "127.2.0.5:17473", peerEndpoint(t, c, pubKey), "endpoint must point at the wake listener after the idle endpoint swap")
+}
+
+// TestUSPConfigurer_IdlePeerEndpointCreatesMissingPeer verifies the cold-start arm path: when the
+// peer does not exist yet (never connected), IdlePeerEndpoint creates it with the given base
+// allowed IPs and the wake endpoint.
+func TestUSPConfigurer_IdlePeerEndpointCreatesMissingPeer(t *testing.T) {
+	c := newTestConfigurer(t)
+
+	peerKey, err := wgtypes.GeneratePrivateKey()
+	require.NoError(t, err)
+	pubKey := peerKey.PublicKey().String()
+
+	overlay := netip.MustParsePrefix("100.64.0.5/32")
+	wakeEndpoint := &net.UDPAddr{IP: net.ParseIP("127.2.0.5"), Port: 17473}
+
+	require.NoError(t, c.IdlePeerEndpoint(pubKey, []netip.Prefix{overlay}, wakeEndpoint))
+
+	assert.Equal(t, []string{overlay.String()}, peerAllowedIPs(t, c, pubKey), "missing peer must be created with the base allowed IPs")
+	assert.Equal(t, "127.2.0.5:17473", peerEndpoint(t, c, pubKey), "missing peer must be created with the wake endpoint")
+}
+
+// TestUSPConfigurer_AddAllowedIPOnMissingPeerIsSilentNoOp documents the wireguard-go
+// behavior the removed-peer idle flow raced against: AddAllowedIP uses update_only,
+// which is a silent no-op when the peer does not exist. The idle transition must
+// therefore keep the WireGuard peer (Conn.Idle + IdlePeerEndpoint) instead of leaving a
+// window where the peer is absent.
+func TestUSPConfigurer_AddAllowedIPOnMissingPeerIsSilentNoOp(t *testing.T) {
+	c := newTestConfigurer(t)
+
+	peerKey, err := wgtypes.GeneratePrivateKey()
+	require.NoError(t, err)
+	pubKey := peerKey.PublicKey().String()
+
+	routed := netip.MustParsePrefix("10.99.0.0/24")
+
+	require.NoError(t, c.AddAllowedIP(pubKey, routed), "update-only on a missing peer must not return an error")
+
+	assert.Empty(t, peerIpcLines(t, c, pubKey), "update-only call must not create the peer")
+}

client/iface/device/interface.go

@@ -15,6 +15,7 @@ type WGConfigurer interface {
 	ConfigureInterface(privateKey string, port int) error
 	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
 	RemovePeer(peerKey string) error
+	IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error
 	AddAllowedIP(peerKey string, allowedIP netip.Prefix) error
 	RemoveAllowedIP(peerKey string, allowedIP netip.Prefix) error
 	SetPresharedKey(peerKey string, psk wgtypes.Key, updateOnly bool) error

client/iface/iface.go

@@ -184,6 +184,19 @@ func (w *WGIface) RemovePeer(peerKey string) error {
 	return w.configurer.RemovePeer(peerKey)
 }
 
+// IdlePeerEndpoint re-creates the peer pointing at the lazy wake endpoint, dropping
+// handshake state while preserving the peer's currently installed allowed IPs.
+func (w *WGIface) IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error {
+	w.mu.Lock()
+	defer w.mu.Unlock()
+	if w.configurer == nil {
+		return ErrIfaceNotFound
+	}
+
+	log.Debugf("Resetting peer on interface %s: %s, endpoint %s", w.tun.DeviceName(), peerKey, endpoint)
+	return w.configurer.IdlePeerEndpoint(peerKey, allowedIPs, endpoint)
+}
+
 // AddAllowedIP adds a prefix to the allowed IPs list of peer
 func (w *WGIface) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
 	w.mu.Lock()

client/internal/conn_mgr.go

@@ -228,7 +228,7 @@ func (e *ConnMgr) RemovePeerConn(peerKey string) {
 	if !ok {
 		return
 	}
-	defer conn.Close(false)
+	defer conn.Close()
 
 	if !e.isStartedWithLazyMgr() {
 		return

client/internal/engine.go

@@ -1778,7 +1778,7 @@ func (e *Engine) addNewPeer(peerConfig *mgmProto.RemotePeerConfig) error {
 	}
 
 	if exists := e.connMgr.AddPeerConn(e.ctx, peerKey, conn); exists {
-		conn.Close(false)
+		conn.Close()
 		return fmt.Errorf("peer already exists: %s", peerKey)
 	}
 

client/internal/engine_test.go

@@ -53,6 +53,7 @@ type MockWGIface struct {
 	UpdateAddrFunc             func(newAddr wgaddr.Address) error
 	UpdatePeerFunc             func(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
 	RemovePeerFunc             func(peerKey string) error
+	IdlePeerEndpointFunc       func(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error
 	AddAllowedIPFunc           func(peerKey string, allowedIP netip.Prefix) error
 	RemoveAllowedIPFunc        func(peerKey string, allowedIP netip.Prefix) error
 	CloseFunc                  func() error
@@ -124,6 +125,13 @@ func (m *MockWGIface) RemovePeer(peerKey string) error {
 	return m.RemovePeerFunc(peerKey)
 }
 
+func (m *MockWGIface) IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error {
+	if m.IdlePeerEndpointFunc == nil {
+		return nil
+	}
+	return m.IdlePeerEndpointFunc(peerKey, allowedIPs, endpoint)
+}
+
 func (m *MockWGIface) AddAllowedIP(peerKey string, allowedIP netip.Prefix) error {
 	return m.AddAllowedIPFunc(peerKey, allowedIP)
 }

client/internal/iface_common.go

@@ -32,6 +32,7 @@ type wgIfaceBase interface {
 	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
 	RemoveEndpointAddress(key string) error
 	RemovePeer(peerKey string) error
+	IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error
 	AddAllowedIP(peerKey string, allowedIP netip.Prefix) error
 	RemoveAllowedIP(peerKey string, allowedIP netip.Prefix) error
 	Close() error

client/internal/lazyconn/activity/listener_bind.go

@@ -106,7 +106,7 @@ func (d *BindListener) setupLazyConn() error {
 		IP:   d.fakeIP.AsSlice(),
 		Port: lazyBindPort,
 	}
-	return d.wgIface.UpdatePeer(d.peerCfg.PublicKey, d.peerCfg.AllowedIPs, 0, endpoint, nil)
+	return d.wgIface.IdlePeerEndpoint(d.peerCfg.PublicKey, d.peerCfg.AllowedIPs, endpoint)
 }
 
 // ReadPackets blocks until activity is detected on the LazyConn or the listener is closed.

client/internal/lazyconn/activity/listener_bind_test.go

@@ -9,7 +9,6 @@ import (
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
 	"github.com/netbirdio/netbird/client/iface/device"
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
@@ -45,7 +44,7 @@ type MockWGIfaceBind struct {
 	endpointMgr *mockEndpointManager
 }
 
-func (m *MockWGIfaceBind) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
+func (m *MockWGIfaceBind) IdlePeerEndpoint(string, []netip.Prefix, *net.UDPAddr) error {
 	return nil
 }
 

client/internal/lazyconn/activity/listener_udp.go

@@ -101,7 +101,7 @@ func (d *UDPListener) Close() {
 
 func (d *UDPListener) createEndpoint() error {
 	d.peerCfg.Log.Debugf("creating lazy endpoint: %s", d.endpoint.String())
-	return d.wgIface.UpdatePeer(d.peerCfg.PublicKey, d.peerCfg.AllowedIPs, 0, d.endpoint, nil)
+	return d.wgIface.IdlePeerEndpoint(d.peerCfg.PublicKey, d.peerCfg.AllowedIPs, d.endpoint)
 }
 
 func (d *UDPListener) newConn() (*net.UDPConn, error) {

client/internal/lazyconn/activity/manager.go

@@ -5,10 +5,8 @@ import (
 	"net"
 	"net/netip"
 	"sync"
-	"time"
 
 	log "github.com/sirupsen/logrus"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
@@ -30,7 +28,7 @@ type Event struct {
 }
 
 type WgInterface interface {
-	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
+	IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error
 	IsUserspaceBind() bool
 	Address() wgaddr.Address
 	MTU() uint16

client/internal/lazyconn/activity/manager_test.go

@@ -8,7 +8,6 @@ import (
 	"time"
 
 	log "github.com/sirupsen/logrus"
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/client/internal/lazyconn"
@@ -26,7 +25,7 @@ func (m *MocPeer) ConnID() peerid.ConnID {
 type MocWGIface struct {
 }
 
-func (m MocWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
+func (m MocWGIface) IdlePeerEndpoint(string, []netip.Prefix, *net.UDPAddr) error {
 	return nil
 }
 

client/internal/lazyconn/manager/manager.go

@@ -280,7 +280,7 @@ func (m *Manager) DeactivatePeer(peerID peerid.ConnID) {
 		return
 	}
 
-	m.peerStore.PeerConnClose(mp.peerCfg.PublicKey)
+	m.peerStore.PeerConnIdle(mp.peerCfg.PublicKey, false)
 
 	mp.peerCfg.Log.Infof("start activity monitor")
 
@@ -569,7 +569,7 @@ func (m *Manager) onPeerInactivityTimedOut(peerIDs map[string]struct{}) {
 		mp.peerCfg.Log.Infof("connection timed out")
 
 		// this is blocking operation, potentially can be optimized
-		m.peerStore.PeerConnIdle(mp.peerCfg.PublicKey)
+		m.peerStore.PeerConnIdle(mp.peerCfg.PublicKey, true)
 
 		mp.expectedWatcher = watcherActivity
 

client/internal/lazyconn/wgiface.go

@@ -3,9 +3,6 @@ package lazyconn
 import (
 	"net"
 	"net/netip"
-	"time"
-
-	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
 
 	"github.com/netbirdio/netbird/client/iface/wgaddr"
 	"github.com/netbirdio/netbird/monotime"
@@ -13,7 +10,7 @@ import (
 
 type WGIface interface {
 	RemovePeer(peerKey string) error
-	UpdatePeer(peerKey string, allowedIps []netip.Prefix, keepAlive time.Duration, endpoint *net.UDPAddr, preSharedKey *wgtypes.Key) error
+	IdlePeerEndpoint(peerKey string, allowedIPs []netip.Prefix, endpoint *net.UDPAddr) error
 	IsUserspaceBind() bool
 	Address() wgaddr.Address
 	LastActivities() map[string]monotime.Time

client/internal/peer/conn.go

@@ -285,8 +285,20 @@ func (conn *Conn) open(engineCtx context.Context, firstPacket []byte) error {
 	return nil
 }
 
-// Close closes this peer Conn issuing a close event to the Conn closeCh
-func (conn *Conn) Close(signalToRemote bool) {
+// Close closes this peer Conn issuing a close event to the Conn closeCh and removes the WireGuard peer
+func (conn *Conn) Close() {
+	conn.close(false, true)
+}
+
+// Idle tears down the connection for the lazy idle state: transports and proxies are
+// closed but the WireGuard peer is kept, so its AllowedIPs (including routed prefixes
+// installed by the route manager) survive until the activity listener re-points the
+// endpoint at the wake listener.
+func (conn *Conn) Idle(signalToRemote bool) {
+	conn.close(signalToRemote, false)
+}
+
+func (conn *Conn) close(signalToRemote bool, removeWgPeer bool) {
 	conn.mu.Lock()
 	defer conn.wgWatcherWg.Wait()
 	defer conn.mu.Unlock()
@@ -329,8 +341,12 @@ func (conn *Conn) Close(signalToRemote bool) {
 		conn.wgProxyICE = nil
 	}
 
-	if err := conn.endpointUpdater.RemoveWgPeer(); err != nil {
-		conn.Log.Errorf("failed to remove wg endpoint: %v", err)
+	if removeWgPeer {
+		if err := conn.endpointUpdater.RemoveWgPeer(); err != nil {
+			conn.Log.Errorf("failed to remove wg endpoint: %v", err)
+		}
+	} else {
+		conn.endpointUpdater.CancelPendingUpdates()
 	}
 
 	if conn.evalStatus() == StatusConnected && conn.onDisconnected != nil {

client/internal/peer/endpoint.go

@@ -65,6 +65,16 @@ func (e *EndpointUpdater) RemoveWgPeer() error {
 	return e.wgConfig.WgInterface.RemovePeer(e.wgConfig.RemoteKey)
 }
 
+// CancelPendingUpdates stops a scheduled delayed endpoint update without touching the
+// WireGuard peer. Used on the idle transition where the peer is kept so a pending
+// responder-side update cannot overwrite the wake endpoint later.
+func (e *EndpointUpdater) CancelPendingUpdates() {
+	e.mu.Lock()
+	defer e.mu.Unlock()
+
+	e.waitForCloseTheDelayedUpdate()
+}
+
 func (e *EndpointUpdater) RemoveEndpointAddress() error {
 	e.mu.Lock()
 	defer e.mu.Unlock()

client/internal/peer/endpoint_test.go

@@ -0,0 +1,101 @@
+package peer
+
+import (
+	"net"
+	"net/netip"
+	"sync"
+	"testing"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"golang.zx2c4.com/wireguard/wgctrl/wgtypes"
+
+	"github.com/netbirdio/netbird/client/iface/configurer"
+	"github.com/netbirdio/netbird/client/iface/wgaddr"
+	"github.com/netbirdio/netbird/client/iface/wgproxy"
+)
+
+type endpointTestWGIface struct {
+	mu          sync.Mutex
+	updateCalls int
+	removeCalls int
+}
+
+func (m *endpointTestWGIface) UpdatePeer(string, []netip.Prefix, time.Duration, *net.UDPAddr, *wgtypes.Key) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.updateCalls++
+	return nil
+}
+
+func (m *endpointTestWGIface) RemovePeer(string) error {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	m.removeCalls++
+	return nil
+}
+
+func (m *endpointTestWGIface) GetStats() (map[string]configurer.WGStats, error) {
+	return map[string]configurer.WGStats{}, nil
+}
+
+func (m *endpointTestWGIface) GetProxy() wgproxy.Proxy { return nil }
+
+func (m *endpointTestWGIface) Address() wgaddr.Address { return wgaddr.Address{} }
+
+func (m *endpointTestWGIface) RemoveEndpointAddress(string) error { return nil }
+
+func (m *endpointTestWGIface) counts() (updates, removes int) {
+	m.mu.Lock()
+	defer m.mu.Unlock()
+	return m.updateCalls, m.removeCalls
+}
+
+func newTestEndpointUpdater(iface *endpointTestWGIface, initiator bool) *EndpointUpdater {
+	cfg := WgConfig{
+		RemoteKey:   "remoteKey",
+		WgInterface: iface,
+		AllowedIps:  []netip.Prefix{netip.MustParsePrefix("100.64.0.5/32")},
+	}
+	return NewEndpointUpdater(log.WithField("peer", "test"), cfg, initiator)
+}
+
+// TestEndpointUpdater_CancelPendingUpdates ensures a scheduled responder-side delayed
+// update is stopped without removing the WireGuard peer, so an idle transition cannot
+// be overwritten later by a stale endpoint update.
+func TestEndpointUpdater_CancelPendingUpdates(t *testing.T) {
+	iface := &endpointTestWGIface{}
+	e := newTestEndpointUpdater(iface, false)
+
+	addr := &net.UDPAddr{IP: net.ParseIP("127.0.0.1"), Port: 51820}
+	require.NoError(t, e.ConfigureWGEndpoint(addr, nil))
+
+	updates, _ := iface.counts()
+	require.Equal(t, 1, updates, "responder must apply the immediate nil-endpoint update")
+
+	// CancelPendingUpdates waits for the delayed-update goroutine to exit, so the
+	// call counts below are final: the 5s fallback update can never fire anymore.
+	e.CancelPendingUpdates()
+
+	updates, removes := iface.counts()
+	assert.Equal(t, 1, updates, "delayed endpoint update must not fire after cancellation")
+	assert.Equal(t, 0, removes, "cancellation must not remove the WireGuard peer")
+}
+
+// TestEndpointUpdater_CancelPendingUpdatesNoPending ensures cancellation is a safe no-op
+// when no delayed update is scheduled (initiator path).
+func TestEndpointUpdater_CancelPendingUpdatesNoPending(t *testing.T) {
+	iface := &endpointTestWGIface{}
+	e := newTestEndpointUpdater(iface, true)
+
+	addr := &net.UDPAddr{IP: net.ParseIP("127.0.0.1"), Port: 51820}
+	require.NoError(t, e.ConfigureWGEndpoint(addr, nil))
+
+	e.CancelPendingUpdates()
+
+	updates, removes := iface.counts()
+	assert.Equal(t, 1, updates, "initiator applies exactly one direct update")
+	assert.Equal(t, 0, removes, "cancellation must not remove the WireGuard peer")
+}

client/internal/peerstore/store.go

@@ -108,7 +108,10 @@ func (s *Store) PeerConnOpenWithFirstPacket(ctx context.Context, pubKey string,
 	}
 }
 
-func (s *Store) PeerConnIdle(pubKey string) {
+// PeerConnIdle transitions the peer connection to the lazy idle state, keeping the
+// WireGuard peer and its AllowedIPs in place. signalToRemote indicates whether the
+// remote peer should be notified (false when the remote initiated the idle via GOAWAY).
+func (s *Store) PeerConnIdle(pubKey string, signalToRemote bool) {
 	s.peerConnsMu.RLock()
 	defer s.peerConnsMu.RUnlock()
 
@@ -116,18 +119,7 @@ func (s *Store) PeerConnIdle(pubKey string) {
 	if !ok {
 		return
 	}
-	p.Close(true)
-}
-
-func (s *Store) PeerConnClose(pubKey string) {
-	s.peerConnsMu.RLock()
-	defer s.peerConnsMu.RUnlock()
-
-	p, ok := s.peerConns[pubKey]
-	if !ok {
-		return
-	}
-	p.Close(false)
+	p.Idle(signalToRemote)
 }
 
 func (s *Store) PeersPubKey() []string {

client/ui/i18n/locales/_index.json

@@ -8,7 +8,6 @@
         {"code": "fr", "displayName": "Français", "englishName": "French"},
         {"code": "it", "displayName": "Italiano", "englishName": "Italian"},
         {"code": "pt", "displayName": "Português", "englishName": "Portuguese"},
-        {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"},
-        {"code": "ja", "displayName": "日本語", "englishName": "Japanese"}
+        {"code": "zh-CN", "displayName": "简体中文", "englishName": "Simplified Chinese"}
     ]
 }

combined/cmd/root.go

@@ -226,7 +226,7 @@ func (s *serverInstances) createRelayServer(cfg *CombinedConfig, tlsSupport bool
 	}
 
 	hashedSecret := sha256.Sum256([]byte(cfg.Relay.AuthSecret))
-	authenticator := auth.NewTimedHMACValidator(hashedSecret[:])
+	authenticator := auth.NewTimedHMACValidator(hashedSecret[:], 24*time.Hour)
 
 	relayCfg := relayServer.Config{
 		Meter:          s.metricsServer.Meter,

management/internals/modules/agentnetwork/catalog/catalog.go

@@ -197,12 +197,6 @@ type JSONMetadataInjection struct {
 	// enforces a 128-char limit per value; oversized values are
 	// truncated rather than failing the request. 0 disables the cap.
 	MaxValueLength int
-	// Sanitize, when true, replaces characters outside the destination's
-	// accepted set with '_' before emitting each value. AWS Bedrock's
-	// X-Amzn-Bedrock-Request-Metadata restricts values to a limited character
-	// class, so unsanitized group display names (e.g. containing spaces) would
-	// make Bedrock reject the request with 400.
-	Sanitize bool
 }
 
 // providers is the canonical list of supported Agent Network providers.
@@ -335,18 +329,6 @@ var providers = []Provider{
 			{ID: "amazon.nova-lite", Label: "Amazon Nova Lite (Bedrock)", InputPer1k: 0.00006, OutputPer1k: 0.00024, ContextWindow: 300000},
 			{ID: "amazon.nova-micro", Label: "Amazon Nova Micro (Bedrock)", InputPer1k: 0.000035, OutputPer1k: 0.00014, ContextWindow: 128000},
 		},
-		// Bedrock accepts a cost-allocation metadata header; stamp the caller's
-		// user + authorizing group so spend can be attributed in AWS Cost
-		// Management. Sanitized because Bedrock restricts the value character set.
-		IdentityInjection: &IdentityInjection{
-			JSONMetadata: &JSONMetadataInjection{
-				Header:         "X-Amzn-Bedrock-Request-Metadata",
-				UserKey:        "user",
-				GroupsKey:      "group",
-				MaxValueLength: 256,
-				Sanitize:       true,
-			},
-		},
 	},
 	{
 		ID:                 "vertex_ai_api",

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

@@ -3,10 +3,9 @@ package labelgen
 
 import (
 	"fmt"
+	"math/rand"
 	"sort"
 	"sync"
-
-	"github.com/netbirdio/netbird/management/server/util"
 )
 
 // pickAttempts caps the random retries before falling back to the
@@ -41,15 +40,16 @@ func uniqueWords() []string {
 // PickUnique selects a label not already in `taken`. It tries up to
 // pickAttempts random picks; on exhaustion it scans the deduplicated
 // wordlist for any remaining free entry, and if none is left appends
-// `-<fallbackSuffix>` to a random word and returns.
-func PickUnique(taken map[string]struct{}, fallbackSuffix string) string {
+// `-<fallbackSuffix>` to a deterministic word and returns. The caller
+// is responsible for seeding rng (math/rand).
+func PickUnique(rng *rand.Rand, taken map[string]struct{}, fallbackSuffix string) string {
 	pool := uniqueWords()
 	if len(pool) == 0 {
 		return fallbackSuffix
 	}
 
 	for i := 0; i < pickAttempts; i++ {
-		w := pool[util.RandIntn(len(pool))]
+		w := pool[rng.Intn(len(pool))]
 		if _, ok := taken[w]; !ok {
 			return w
 		}
@@ -61,6 +61,6 @@ func PickUnique(taken map[string]struct{}, fallbackSuffix string) string {
 		}
 	}
 
-	w := pool[util.RandIntn(len(pool))]
+	w := pool[rng.Intn(len(pool))]
 	return fmt.Sprintf("%s-%s", w, fallbackSuffix)
 }

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

@@ -1,7 +1,7 @@
 package labelgen
 
 import (
-	"slices"
+	"math/rand"
 	"strings"
 	"testing"
 
@@ -9,12 +9,19 @@ import (
 	"github.com/stretchr/testify/require"
 )
 
-// TestPickUnique_ReturnsWordFromPool confirms a pick against an empty
-// taken set is always drawn verbatim from the wordlist.
-func TestPickUnique_ReturnsWordFromPool(t *testing.T) {
-	got := PickUnique(map[string]struct{}{}, "abcd")
+// TestPickUnique_DeterministicWithSeededRng locks the property the
+// caller relies on: same seed + same taken set → same pick. Without
+// that, the bootstrap flow can't reproduce a label across retries.
+func TestPickUnique_DeterministicWithSeededRng(t *testing.T) {
+	taken := map[string]struct{}{}
 
-	assert.True(t, slices.Contains(uniqueWords(), got), "Pick %q must be drawn from the wordlist", got)
+	rngA := rand.New(rand.NewSource(42))
+	rngB := rand.New(rand.NewSource(42))
+
+	a := PickUnique(rngA, taken, "abcd")
+	b := PickUnique(rngB, taken, "abcd")
+
+	assert.Equal(t, a, b, "Same seed and taken set must produce identical pick")
 }
 
 // TestPickUnique_AvoidsTakenWordsWhenMostAreReserved seeds taken with
@@ -39,7 +46,8 @@ func TestPickUnique_AvoidsTakenWordsWhenMostAreReserved(t *testing.T) {
 		taken[w] = struct{}{}
 	}
 
-	got := PickUnique(taken, "abcd")
+	rng := rand.New(rand.NewSource(7))
+	got := PickUnique(rng, taken, "abcd")
 
 	_, isFree := free[got]
 	assert.True(t, isFree, "PickUnique must return one of the free words; got %q", got)
@@ -57,7 +65,8 @@ func TestPickUnique_FallsBackWhenAllReserved(t *testing.T) {
 		taken[w] = struct{}{}
 	}
 
-	got := PickUnique(taken, "abcd")
+	rng := rand.New(rand.NewSource(99))
+	got := PickUnique(rng, taken, "abcd")
 
 	assert.True(t, strings.HasSuffix(got, "-abcd"), "Exhausted pool must produce <word>-<suffix>; got %q", got)
 

management/internals/modules/agentnetwork/manager.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"math/rand"
 	"slices"
 	"strings"
 	"sync"
@@ -122,6 +123,11 @@ type managerImpl struct {
 	// accountID, then by synthesised service ID.
 	reconcileMu    sync.Mutex
 	reconcileCache map[string]map[string]*proto.ProxyMapping
+
+	// labelRngMu guards labelRng. PickUnique consumes math/rand.Source
+	// state; concurrent provider creates would otherwise race.
+	labelRngMu sync.Mutex
+	labelRng   *rand.Rand
 }
 
 // NewManager constructs the persistent Agent Network manager. The
@@ -141,6 +147,7 @@ func NewManager(
 		permissionsManager: permissionsManager,
 		proxyController:    proxyController,
 		reconcileCache:     make(map[string]map[string]*proto.ProxyMapping),
+		labelRng:           rand.New(rand.NewSource(time.Now().UnixNano())),
 	}
 }
 
@@ -646,7 +653,9 @@ func (m *managerImpl) bootstrapSettingsIfNeeded(ctx context.Context, accountID,
 		suffix = suffix[:4]
 	}
 
-	subdomain := labelgen.PickUnique(taken, suffix)
+	m.labelRngMu.Lock()
+	subdomain := labelgen.PickUnique(m.labelRng, taken, suffix)
+	m.labelRngMu.Unlock()
 
 	now := time.Now().UTC()
 	settings := &types.Settings{

management/internals/modules/agentnetwork/synthesizer.go

@@ -540,7 +540,6 @@ type identityInjectJSONMetadata struct {
 	UserKey        string `json:"user_key,omitempty"`
 	GroupsKey      string `json:"groups_key,omitempty"`
 	MaxValueLength int    `json:"max_value_length,omitempty"`
-	Sanitize       bool   `json:"sanitize,omitempty"`
 }
 
 // buildIdentityInjectConfigJSON walks the enabled providers and emits
@@ -584,11 +583,9 @@ func buildIdentityInjectConfigJSON(providers []*types.Provider, groupIndex map[s
 func buildIdentityInjectRule(p *types.Provider, entry catalog.Provider) (identityInjectProvider, bool) {
 	rule := identityInjectProvider{ProviderID: p.ID}
 	// Identity-stamping shape (one of HeaderPair / JSONMetadata). Skip the
-	// shape silently when the catalog entry doesn't declare one, or when the
-	// operator disabled metadata for this provider — extras can still apply,
-	// see below. MetadataDisabled suppresses only the identity dimensions
-	// (user + authorizing group), not the catalog's routing ExtraHeaders.
-	if !p.MetadataDisabled && entry.IdentityInjection != nil {
+	// shape silently when the catalog entry doesn't declare one — extras
+	// can still apply, see below.
+	if entry.IdentityInjection != nil {
 		switch {
 		case entry.IdentityInjection.HeaderPair != nil:
 			rule.HeaderPair = buildIdentityHeaderPair(p, entry.IdentityInjection.HeaderPair)
@@ -654,7 +651,6 @@ func buildIdentityJSONMetadata(p *types.Provider, jm *catalog.JSONMetadataInject
 		UserKey:        userKey,
 		GroupsKey:      groupsKey,
 		MaxValueLength: jm.MaxValueLength,
-		Sanitize:       jm.Sanitize,
 	}
 }
 

management/internals/modules/agentnetwork/synthesizer_test.go

@@ -698,94 +698,6 @@ func TestSynthesizeServices_IdentityInject_Portkey_NotCustomizable(t *testing.T)
 		"same fixed-schema guarantee for the groups dimension")
 }
 
-// TestSynthesizeServices_IdentityInject_Bedrock pins Bedrock's cost-allocation
-// metadata: a JSONMetadata shape emitting X-Amzn-Bedrock-Request-Metadata with
-// the reserved user/group keys, sanitized to Bedrock's accepted charset.
-func TestSynthesizeServices_IdentityInject_Bedrock(t *testing.T) {
-	ctx := context.Background()
-	ctrl := gomock.NewController(t)
-	defer ctrl.Finish()
-	mockStore := store.NewMockStore(ctrl)
-
-	br := newSynthTestProvider()
-	br.ID = "prov-bedrock"
-	br.ProviderID = "bedrock_api"
-	br.UpstreamURL = "https://bedrock-runtime.us-east-1.amazonaws.com"
-	br.APIKey = "bedrock-bearer"
-	br.CreatedAt = time.Date(2026, 4, 2, 0, 0, 0, 0, time.UTC)
-
-	policy := newSynthTestPolicy(br.ID, "grp-eng", "")
-	policy.ID = "pol-bedrock"
-
-	expectSynthBaseInputs(mockStore, ctx, newSynthTestSettings(),
-		[]*types.Provider{br},
-		[]*types.Policy{policy},
-		[]*types.Guardrail{})
-
-	services, err := SynthesizeServices(ctx, mockStore, testAccountID)
-	require.NoError(t, err)
-	require.Len(t, services, 1)
-
-	var injectCfg identityInjectConfig
-	for _, m := range services[0].Targets[0].Options.Middlewares {
-		if m.ID == middlewareIDLLMIdentityInject {
-			require.NoError(t, json.Unmarshal(m.ConfigJSON, &injectCfg))
-			break
-		}
-	}
-	require.Len(t, injectCfg.Providers, 1)
-	entry := injectCfg.Providers[0]
-	require.NotNil(t, entry.JSONMetadata, "Bedrock uses the JSONMetadata shape for cost-allocation metadata")
-	assert.Nil(t, entry.HeaderPair, "shapes are mutually exclusive")
-	assert.Equal(t, "X-Amzn-Bedrock-Request-Metadata", entry.JSONMetadata.Header,
-		"the caller identity lands in Bedrock's cost-allocation metadata header")
-	assert.Equal(t, "user", entry.JSONMetadata.UserKey)
-	assert.Equal(t, "group", entry.JSONMetadata.GroupsKey)
-	assert.True(t, entry.JSONMetadata.Sanitize,
-		"Bedrock restricts the metadata value charset, so values must be sanitized")
-}
-
-// TestSynthesizeServices_MetadataDisabled_SuppressesInjection verifies the
-// per-provider opt-out: a provider with MetadataDisabled set emits no
-// identity-inject entry (Bedrock has no catalog ExtraHeaders, so the whole
-// entry is dropped).
-func TestSynthesizeServices_MetadataDisabled_SuppressesInjection(t *testing.T) {
-	ctx := context.Background()
-	ctrl := gomock.NewController(t)
-	defer ctrl.Finish()
-	mockStore := store.NewMockStore(ctrl)
-
-	br := newSynthTestProvider()
-	br.ID = "prov-bedrock"
-	br.ProviderID = "bedrock_api"
-	br.UpstreamURL = "https://bedrock-runtime.us-east-1.amazonaws.com"
-	br.APIKey = "bedrock-bearer"
-	br.MetadataDisabled = true
-	br.CreatedAt = time.Date(2026, 4, 2, 0, 0, 0, 0, time.UTC)
-
-	policy := newSynthTestPolicy(br.ID, "grp-eng", "")
-	policy.ID = "pol-bedrock"
-
-	expectSynthBaseInputs(mockStore, ctx, newSynthTestSettings(),
-		[]*types.Provider{br},
-		[]*types.Policy{policy},
-		[]*types.Guardrail{})
-
-	services, err := SynthesizeServices(ctx, mockStore, testAccountID)
-	require.NoError(t, err)
-	require.Len(t, services, 1)
-
-	var injectCfg identityInjectConfig
-	for _, m := range services[0].Targets[0].Options.Middlewares {
-		if m.ID == middlewareIDLLMIdentityInject {
-			require.NoError(t, json.Unmarshal(m.ConfigJSON, &injectCfg))
-			break
-		}
-	}
-	assert.Empty(t, injectCfg.Providers,
-		"metadata_disabled must drop the provider's identity-inject entry")
-}
-
 // TestSynthesizeServices_IdentityInject_Vercel pins Vercel AI
 // Gateway's wiring: HeaderPair shape with fixed wire names dictated
 // by Vercel's Custom Reporting API (ai-reporting-user /

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

@@ -51,12 +51,6 @@ type Provider struct {
 	// private or self-signed certificate. The synthesiser propagates it into
 	// the router route so the proxy dials that provider's upstream insecurely.
 	SkipTLSVerification bool `gorm:"column:skip_tls_verification"`
-	// MetadataDisabled suppresses identity metadata injection for this provider.
-	// Metadata (the caller's user + authorizing group) is injected by default;
-	// when true the synthesiser omits the provider's identity-inject shape, so no
-	// user/group headers (e.g. Bedrock's X-Amzn-Bedrock-Request-Metadata) are
-	// stamped. Catalog ExtraHeaders (routing config) are unaffected.
-	MetadataDisabled bool `gorm:"column:metadata_disabled"`
 	// SessionPrivateKey + SessionPublicKey are the ed25519 keypair the
 	// synthesised reverse-proxy service uses to sign / verify session
 	// JWTs after a successful OIDC handshake. Generated once on
@@ -143,9 +137,6 @@ func (p *Provider) FromAPIRequest(req *api.AgentNetworkProviderRequest) {
 	if req.SkipTlsVerification != nil {
 		p.SkipTLSVerification = *req.SkipTlsVerification
 	}
-	if req.MetadataDisabled != nil {
-		p.MetadataDisabled = *req.MetadataDisabled
-	}
 	// Identity-header overrides for catalogs flagged Customizable.
 	// nil pointer = "field omitted on the wire" → leave the stored
 	// value untouched (per the openapi description). Empty string is
@@ -179,7 +170,6 @@ func (p *Provider) ToAPIResponse() *api.AgentNetworkProvider {
 		Models:              models,
 		Enabled:             p.Enabled,
 		SkipTlsVerification: p.SkipTLSVerification,
-		MetadataDisabled:    p.MetadataDisabled,
 		CreatedAt:           &created,
 		UpdatedAt:           &updated,
 	}

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

@@ -42,38 +42,3 @@ func TestProvider_SkipTLSVerification_RoundTrip(t *testing.T) {
 	assert.False(t, p.SkipTLSVerification, "explicit false must clear skip_tls_verification")
 	assert.False(t, p.ToAPIResponse().SkipTlsVerification, "response must reflect the cleared value")
 }
-
-// TestProvider_MetadataDisabled_RoundTrip covers the request→provider→response
-// mapping of metadata_disabled, with the same update semantics: nil preserves,
-// explicit false clears.
-func TestProvider_MetadataDisabled_RoundTrip(t *testing.T) {
-	enable := true
-	disable := false
-
-	base := func() *api.AgentNetworkProviderRequest {
-		return &api.AgentNetworkProviderRequest{
-			ProviderId:  "bedrock_api",
-			Name:        "bedrock",
-			UpstreamUrl: "https://bedrock-runtime.us-east-1.amazonaws.com",
-		}
-	}
-
-	p := NewProvider("acc-1")
-
-	req := base()
-	req.MetadataDisabled = &enable
-	p.FromAPIRequest(req)
-	assert.True(t, p.MetadataDisabled, "create with metadata_disabled=true must set the field")
-	assert.True(t, p.ToAPIResponse().MetadataDisabled, "response must surface metadata_disabled")
-
-	// Omitting the field on update leaves the stored value untouched.
-	p.FromAPIRequest(base())
-	assert.True(t, p.MetadataDisabled, "omitting metadata_disabled on update must preserve it")
-
-	// Explicit false clears it (re-enables metadata).
-	req = base()
-	req.MetadataDisabled = &disable
-	p.FromAPIRequest(req)
-	assert.False(t, p.MetadataDisabled, "explicit false must clear metadata_disabled")
-	assert.False(t, p.ToAPIResponse().MetadataDisabled, "response must reflect the cleared value")
-}

management/server/account.go

@@ -4,6 +4,7 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"math/rand"
 	"net"
 	"net/netip"
 	"os"
@@ -62,7 +63,7 @@ const (
 type userLoggedInOnce bool
 
 func cacheEntryExpiration() time.Duration {
-	r := util.RandIntn(int(nbcache.DefaultIDPCacheExpirationMax.Milliseconds()-nbcache.DefaultIDPCacheExpirationMin.Milliseconds())) + int(nbcache.DefaultIDPCacheExpirationMin.Milliseconds())
+	r := rand.Intn(int(nbcache.DefaultIDPCacheExpirationMax.Milliseconds()-nbcache.DefaultIDPCacheExpirationMin.Milliseconds())) + int(nbcache.DefaultIDPCacheExpirationMin.Milliseconds())
 	return time.Duration(r) * time.Millisecond
 }
 
@@ -2454,7 +2455,8 @@ func (am *DefaultAccountManager) ensureIPv6Subnet(ctx context.Context, transacti
 		return transaction.UpdateAccountNetworkV6(ctx, accountID, network.NetV6)
 	}
 	if network.NetV6.IP == nil {
-		network.NetV6 = types.AllocateIPv6Subnet()
+		r := rand.New(rand.NewSource(time.Now().UnixNano()))
+		network.NetV6 = types.AllocateIPv6Subnet(r)
 
 		// Sync settings to match the allocated subnet so SaveAccountSettings persists it.
 		ones, _ := network.NetV6.Mask.Size()

management/server/group_ipv6_test.go

@@ -2,6 +2,7 @@ package server
 
 import (
 	"context"
+	"math/rand"
 	"testing"
 	"time"
 
@@ -27,7 +28,7 @@ func TestGroupIPv6Assignment(t *testing.T) {
 	require.NoError(t, err)
 
 	// Allocate IPv6 subnet for the account
-	account.Network.NetV6 = types.AllocateIPv6Subnet()
+	account.Network.NetV6 = types.AllocateIPv6Subnet(rand.New(rand.NewSource(time.Now().UnixNano())))
 	require.NoError(t, am.Store.SaveAccount(ctx, account))
 
 	// Create setup key

management/server/idp/util.go

@@ -2,12 +2,11 @@ package idp
 
 import (
 	"encoding/json"
+	"math/rand"
 	"net/url"
 	"os"
 	"strings"
 	"time"
-
-	"github.com/netbirdio/netbird/management/server/util"
 )
 
 var (
@@ -34,32 +33,31 @@ func GeneratePassword(passwordLength, minSpecialChar, minNum, minUpperCase int)
 
 	//Set special character
 	for i := 0; i < minSpecialChar; i++ {
-		random := util.RandIntn(len(specialCharSet))
+		random := rand.Intn(len(specialCharSet))
 		password.WriteString(string(specialCharSet[random]))
 	}
 
 	//Set numeric
 	for i := 0; i < minNum; i++ {
-		random := util.RandIntn(len(numberSet))
+		random := rand.Intn(len(numberSet))
 		password.WriteString(string(numberSet[random]))
 	}
 
 	//Set uppercase
 	for i := 0; i < minUpperCase; i++ {
-		random := util.RandIntn(len(upperCharSet))
+		random := rand.Intn(len(upperCharSet))
 		password.WriteString(string(upperCharSet[random]))
 	}
 
 	remainingLength := passwordLength - minSpecialChar - minNum - minUpperCase
 	for i := 0; i < remainingLength; i++ {
-		random := util.RandIntn(len(allCharSet))
+		random := rand.Intn(len(allCharSet))
 		password.WriteString(string(allCharSet[random]))
 	}
 	inRune := []rune(password.String())
-	for i := len(inRune) - 1; i > 0; i-- {
-		j := util.RandIntn(i + 1)
+	rand.Shuffle(len(inRune), func(i, j int) {
 		inRune[i], inRune[j] = inRune[j], inRune[i]
-	}
+	})
 	return string(inRune)
 }
 

management/server/types/network.go

@@ -1,13 +1,14 @@
 package types
 
 import (
-	"crypto/rand"
 	"encoding/binary"
 	"fmt"
+	"math/rand"
 	"net"
 	"net/netip"
 	"slices"
 	"sync"
+	"time"
 
 	"github.com/c-robinson/iplib"
 	"github.com/rs/xid"
@@ -136,12 +137,14 @@ func NewNetwork() *Network {
 	n := iplib.NewNet4(net.ParseIP("100.64.0.0"), NetSize)
 	sub, _ := n.Subnet(SubnetSize)
 
-	intn := util.RandIntn(len(sub))
+	s := rand.NewSource(time.Now().UnixNano())
+	r := rand.New(s)
+	intn := r.Intn(len(sub))
 
 	return &Network{
 		Identifier: xid.New().String(),
 		Net:        sub[intn].IPNet,
-		NetV6:      AllocateIPv6Subnet(),
+		NetV6:      AllocateIPv6Subnet(r),
 		Dns:        "",
 		Serial:     0,
 	}
@@ -151,13 +154,18 @@ func NewNetwork() *Network {
 // The format follows RFC 4193 section 3.1: fd + 40-bit Global ID + 16-bit Subnet ID.
 // The Global ID and Subnet ID are randomized (simplified from the SHA-1 algorithm
 // in section 3.2.2), giving 2^56 possible /64 subnets across all accounts.
-func AllocateIPv6Subnet() net.IPNet {
+func AllocateIPv6Subnet(r *rand.Rand) net.IPNet {
 	ip := make(net.IP, 16)
 	ip[0] = 0xfd
-	// Bytes 1-5: 40-bit random Global ID, bytes 6-7: 16-bit random Subnet ID
-	if _, err := rand.Read(ip[1:8]); err != nil {
-		panic(err)
-	}
+	// Bytes 1-5: 40-bit random Global ID
+	ip[1] = byte(r.Intn(256))
+	ip[2] = byte(r.Intn(256))
+	ip[3] = byte(r.Intn(256))
+	ip[4] = byte(r.Intn(256))
+	ip[5] = byte(r.Intn(256))
+	// Bytes 6-7: 16-bit random Subnet ID
+	ip[6] = byte(r.Intn(256))
+	ip[7] = byte(r.Intn(256))
 
 	return net.IPNet{
 		IP:   ip,
@@ -209,10 +217,11 @@ func AllocatePeerIP(prefix netip.Prefix, takenIps []netip.Addr) (netip.Addr, err
 		taken[binary.BigEndian.Uint32(ab[:])] = struct{}{}
 	}
 
+	rng := rand.New(rand.NewSource(time.Now().UnixNano()))
 	maxAttempts := (int(totalIPs) - len(taken)) / 100
 
 	for i := 0; i < maxAttempts; i++ {
-		offset := uint32(util.RandIntn(int(totalIPs-2))) + 1
+		offset := uint32(rng.Intn(int(totalIPs-2))) + 1
 		candidate := baseIP + offset
 		if _, exists := taken[candidate]; !exists {
 			return uint32ToIP(candidate), nil
@@ -236,7 +245,8 @@ func AllocateRandomPeerIP(prefix netip.Prefix) (netip.Addr, error) {
 	hostBits := 32 - prefix.Bits()
 	totalIPs := uint32(1 << hostBits)
 
-	offset := uint32(util.RandIntn(int(totalIPs-2))) + 1
+	rng := rand.New(rand.NewSource(time.Now().UnixNano()))
+	offset := uint32(rng.Intn(int(totalIPs-2))) + 1
 
 	candidate := baseIP + offset
 	return uint32ToIP(candidate), nil
@@ -252,26 +262,23 @@ func AllocateRandomPeerIPv6(prefix netip.Prefix) (netip.Addr, error) {
 
 	ip := prefix.Addr().As16()
 
+	rng := rand.New(rand.NewSource(time.Now().UnixNano()))
+
 	// Determine which byte the host bits start in
 	firstHostByte := ones / 8
 	// If the prefix doesn't end on a byte boundary, handle the partial byte
 	partialBits := ones % 8
 
-	var rnd [16]byte
-	if _, err := rand.Read(rnd[firstHostByte:]); err != nil {
-		return netip.Addr{}, err
-	}
-
 	if partialBits > 0 {
 		// Keep the network bits in the partial byte, randomize the rest
 		hostMask := byte(0xff >> partialBits)
-		ip[firstHostByte] = (ip[firstHostByte] & ^hostMask) | (rnd[firstHostByte] & hostMask)
+		ip[firstHostByte] = (ip[firstHostByte] & ^hostMask) | (byte(rng.Intn(256)) & hostMask)
 		firstHostByte++
 	}
 
 	// Randomize remaining full host bytes
 	for i := firstHostByte; i < 16; i++ {
-		ip[i] = rnd[i]
+		ip[i] = byte(rng.Intn(256))
 	}
 
 	// Avoid all-zeros and all-ones host parts by checking only host bits.

management/server/util/util.go

@@ -1,20 +1,5 @@
 package util
 
-import (
-	"crypto/rand"
-	"math/big"
-)
-
-// RandIntn returns a uniformly distributed int in [0, n) sourced from
-// crypto/rand. It panics if n <= 0 or the platform randomness source fails.
-func RandIntn(n int) int {
-	v, err := rand.Int(rand.Reader, big.NewInt(int64(n)))
-	if err != nil {
-		panic(err)
-	}
-	return int(v.Int64())
-}
-
 // Difference returns the elements in `a` that aren't in `b`.
 func Difference(a, b []string) []string {
 	mb := make(map[string]struct{}, len(b))

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

@@ -64,11 +64,6 @@ type JSONMetadataRule struct {
 	UserKey        string `json:"user_key,omitempty"`
 	GroupsKey      string `json:"groups_key,omitempty"`
 	MaxValueLength int    `json:"max_value_length,omitempty"`
-	// Sanitize replaces characters outside the destination provider's accepted
-	// set with '_' before emitting each value. AWS Bedrock's
-	// X-Amzn-Bedrock-Request-Metadata restricts values to [A-Za-z0-9 +-=._:/@];
-	// group display names with other characters would otherwise 400.
-	Sanitize bool `json:"sanitize,omitempty"`
 }
 
 // Config is the on-wire configuration accepted by the factory. An

proxy/internal/middleware/builtin/llm_identity_inject/middleware.go

@@ -292,21 +292,15 @@ func applyJSONMetadata(rule *JSONMetadataRule, in *middleware.Input) *middleware
 	mutations := &middleware.Mutations{}
 	mutations.HeadersRemove = append(mutations.HeadersRemove, rule.Header)
 
-	emit := func(v string) string {
-		if rule.Sanitize {
-			v = sanitizeMetadataValue(v)
-		}
-		return truncate(v, rule.MaxValueLength)
-	}
 	payload := map[string]string{}
 	if rule.UserKey != "" {
 		if identity := identityFor(in); identity != "" {
-			payload[rule.UserKey] = emit(identity)
+			payload[rule.UserKey] = truncate(identity, rule.MaxValueLength)
 		}
 	}
 	if rule.GroupsKey != "" {
 		if csv := authorisingTagsCSV(in); csv != "" {
-			payload[rule.GroupsKey] = emit(csv)
+			payload[rule.GroupsKey] = truncate(csv, rule.MaxValueLength)
 		}
 	}
 	if len(payload) == 0 {
@@ -365,36 +359,6 @@ func truncate(s string, maxBytes int) string {
 	return s[:maxBytes]
 }
 
-// sanitizeMetadataValue replaces any character outside AWS Bedrock's accepted
-// request-metadata class — letters, digits, space, and + - = . _ : / @ — with
-// '_'. This keeps values (notably the groups CSV, whose commas are rejected, and
-// group display names with arbitrary characters) from making Bedrock reject the
-// request with 400. The result stays opaque to the gateway.
-func sanitizeMetadataValue(s string) string {
-	var b strings.Builder
-	b.Grow(len(s))
-	for _, r := range s {
-		if metadataCharAllowed(r) {
-			b.WriteRune(r)
-		} else {
-			b.WriteByte('_')
-		}
-	}
-	return b.String()
-}
-
-func metadataCharAllowed(r rune) bool {
-	switch {
-	case r >= 'a' && r <= 'z', r >= 'A' && r <= 'Z', r >= '0' && r <= '9':
-		return true
-	}
-	switch r {
-	case ' ', '+', '-', '=', '.', '_', ':', '/', '@':
-		return true
-	}
-	return false
-}
-
 // tagsIDsFromAuthorising reads llm_router's authorising-groups metadata
 // (a CSV of group ids) and returns the parsed slice. Returns nil when
 // the key is absent or empty so the caller can fall back to the full

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

@@ -304,46 +304,6 @@ func TestInject_JSONMetadata_TruncatesValues(t *testing.T) {
 		"per-value byte length must be capped at MaxValueLength")
 }
 
-// TestInject_JSONMetadata_Sanitize pins the AWS-Bedrock sanitization path: when
-// Sanitize is set, characters outside Bedrock's accepted metadata class
-// (notably the groups CSV comma and arbitrary characters in group display
-// names) are replaced with '_' so Bedrock doesn't reject the request. Allowed
-// characters (letters, digits, spaces, and @ . _ : / + - =) pass through.
-func TestInject_JSONMetadata_Sanitize(t *testing.T) {
-	rule := ProviderInjection{
-		ProviderID: portkeyProvider,
-		JSONMetadata: &JSONMetadataRule{
-			Header:         "X-Amzn-Bedrock-Request-Metadata",
-			UserKey:        "user",
-			GroupsKey:      "group",
-			MaxValueLength: 256,
-			Sanitize:       true,
-		},
-	}
-	mw := New(Config{Providers: []ProviderInjection{rule}})
-	in := newInput(portkeyProvider, "alice", []string{"g1", "g2"})
-	in.UserEmail = "alice@example.com"
-	// Group display names carry characters Bedrock rejects (comma, '#'); the CSV
-	// join adds another comma between the two groups.
-	in.UserGroupNames = []string{"Eng,Team", "Ops#1"}
-
-	out, err := mw.Invoke(context.Background(), in)
-	require.NoError(t, err)
-	require.NotNil(t, out.Mutations)
-	require.Len(t, out.Mutations.HeadersAdd, 1)
-	added := out.Mutations.HeadersAdd[0]
-	assert.Equal(t, "X-Amzn-Bedrock-Request-Metadata", added.Key,
-		"the Bedrock cost-allocation header carries the metadata JSON")
-
-	var payload map[string]string
-	require.NoError(t, json.Unmarshal([]byte(added.Value), &payload))
-	assert.Equal(t, "alice@example.com", payload["user"],
-		"'@' and '.' are in Bedrock's accepted set and must be preserved")
-	assert.NotContains(t, payload["group"], ",", "commas must be sanitized — Bedrock rejects them")
-	assert.NotContains(t, payload["group"], "#", "disallowed characters must be sanitized")
-	assert.Contains(t, payload["group"], "Eng", "allowed characters must be preserved")
-}
-
 // TestInject_JSONMetadata_EmptyIdentity_StripsButDoesNotAdd verifies the
 // anti-spoof Remove still fires when there's nothing to stamp.
 func TestInject_JSONMetadata_EmptyIdentity_StripsButDoesNotAdd(t *testing.T) {

relay/cmd/root.go

@@ -173,7 +173,7 @@ func execute(cmd *cobra.Command, args []string) error {
 	}
 
 	hashedSecret := sha256.Sum256([]byte(cobraConfig.AuthSecret))
-	authenticator := auth.NewTimedHMACValidator(hashedSecret[:])
+	authenticator := auth.NewTimedHMACValidator(hashedSecret[:], 24*time.Hour)
 
 	cfg := server.Config{
 		Meter:          metricsServer.Meter,

relay/server/handshake.go

@@ -5,8 +5,14 @@ import (
 	"fmt"
 	"time"
 
+	log "github.com/sirupsen/logrus"
+
 	"github.com/netbirdio/netbird/relay/server/listener"
 	"github.com/netbirdio/netbird/shared/relay/messages"
+	//nolint:staticcheck
+	"github.com/netbirdio/netbird/shared/relay/messages/address"
+	//nolint:staticcheck
+	authmsg "github.com/netbirdio/netbird/shared/relay/messages/auth"
 )
 
 const (
@@ -17,30 +23,55 @@ const (
 
 type Validator interface {
 	Validate(any) error
+	// Deprecated: Use Validate instead.
+	ValidateHelloMsgType(any) error
 }
 
-// preparedMsg contains the marshalled success response message
+// preparedMsg contains the marshalled success response messages
 type preparedMsg struct {
-	responseAuthMsg []byte
+	responseHelloMsg []byte
+	responseAuthMsg  []byte
 }
 
 func newPreparedMsg(instanceURL string) (*preparedMsg, error) {
+	rhm, err := marshalResponseHelloMsg(instanceURL)
+	if err != nil {
+		return nil, err
+	}
+
 	ram, err := messages.MarshalAuthResponse(instanceURL)
 	if err != nil {
 		return nil, fmt.Errorf("failed to marshal auth response msg: %w", err)
 	}
 
 	return &preparedMsg{
-		responseAuthMsg: ram,
+		responseHelloMsg: rhm,
+		responseAuthMsg:  ram,
 	}, nil
 }
 
+func marshalResponseHelloMsg(instanceURL string) ([]byte, error) {
+	addr := &address.Address{URL: instanceURL}
+	addrData, err := addr.Marshal()
+	if err != nil {
+		return nil, fmt.Errorf("failed to marshal response address: %w", err)
+	}
+
+	//nolint:staticcheck
+	responseMsg, err := messages.MarshalHelloResponse(addrData)
+	if err != nil {
+		return nil, fmt.Errorf("failed to marshal hello response: %w", err)
+	}
+	return responseMsg, nil
+}
+
 type handshake struct {
 	conn        listener.Conn
 	validator   Validator
 	preparedMsg *preparedMsg
 
-	peerID *messages.PeerID
+	handshakeMethodAuth bool
+	peerID              *messages.PeerID
 }
 
 func (h *handshake) handshakeReceive(ctx context.Context) (*messages.PeerID, error) {
@@ -62,11 +93,17 @@ func (h *handshake) handshakeReceive(ctx context.Context) (*messages.PeerID, err
 		return nil, fmt.Errorf("determine message type from %s: %w", h.conn.RemoteAddr(), err)
 	}
 
-	if msgType != messages.MsgTypeAuth {
+	var peerID *messages.PeerID
+	switch msgType {
+	//nolint:staticcheck
+	case messages.MsgTypeHello:
+		peerID, err = h.handleHelloMsg(buf)
+	case messages.MsgTypeAuth:
+		h.handshakeMethodAuth = true
+		peerID, err = h.handleAuthMsg(buf)
+	default:
 		return nil, fmt.Errorf("invalid message type %d from %s", msgType, h.conn.RemoteAddr())
 	}
-
-	peerID, err := h.handleAuthMsg(buf)
 	if err != nil {
 		return peerID, err
 	}
@@ -75,17 +112,46 @@ func (h *handshake) handshakeReceive(ctx context.Context) (*messages.PeerID, err
 }
 
 func (h *handshake) handshakeResponse(ctx context.Context) error {
-	if _, err := h.conn.Write(ctx, h.preparedMsg.responseAuthMsg); err != nil {
+	var responseMsg []byte
+	if h.handshakeMethodAuth {
+		responseMsg = h.preparedMsg.responseAuthMsg
+	} else {
+		responseMsg = h.preparedMsg.responseHelloMsg
+	}
+
+	if _, err := h.conn.Write(ctx, responseMsg); err != nil {
 		return fmt.Errorf("handshake response write to %s (%s): %w", h.peerID, h.conn.RemoteAddr(), err)
 	}
 
 	return nil
 }
 
+func (h *handshake) handleHelloMsg(buf []byte) (*messages.PeerID, error) {
+	//nolint:staticcheck
+	peerID, authData, err := messages.UnmarshalHelloMsg(buf)
+	if err != nil {
+		return nil, fmt.Errorf("unmarshal hello message: %w", err)
+	}
+
+	log.Warnf("peer %s (%s) is using deprecated initial message type", peerID, h.conn.RemoteAddr())
+
+	authMsg, err := authmsg.UnmarshalMsg(authData)
+	if err != nil {
+		return nil, fmt.Errorf("unmarshal auth message: %w", err)
+	}
+
+	//nolint:staticcheck
+	if err := h.validator.ValidateHelloMsgType(authMsg.AdditionalData); err != nil {
+		return nil, fmt.Errorf("validate %s (%s): %w", peerID, h.conn.RemoteAddr(), err)
+	}
+
+	return peerID, nil
+}
+
 func (h *handshake) handleAuthMsg(buf []byte) (*messages.PeerID, error) {
 	rawPeerID, authPayload, err := messages.UnmarshalAuthMsg(buf)
 	if err != nil {
-		return nil, fmt.Errorf("unmarshal auth message: %w", err)
+		return nil, fmt.Errorf("unmarshal hello message: %w", err)
 	}
 
 	if err := h.validator.Validate(authPayload); err != nil {

shared/management/http/api/openapi.yml

@@ -5164,10 +5164,6 @@ components:
           type: boolean
           description: Whether upstream TLS certificate verification is skipped when the proxy dials this provider's URL. Intended for self-hosted / internal gateways behind a private or self-signed certificate.
           example: false
-        metadata_disabled:
-          type: boolean
-          description: Whether identity metadata injection is disabled for this provider. When enabled (the default), the proxy stamps the caller's user and authorizing group onto upstream requests as provider-specific metadata (e.g. AWS Bedrock's X-Amzn-Bedrock-Request-Metadata header). Set true to suppress it.
-          example: false
         created_at:
           type: string
           format: date-time
@@ -5188,7 +5184,6 @@ components:
         - models
         - enabled
         - skip_tls_verification
-        - metadata_disabled
         - created_at
         - updated_at
     AgentNetworkProviderRequest:
@@ -5245,10 +5240,6 @@ components:
           type: boolean
           description: Skip upstream TLS certificate verification when the proxy dials this provider's URL. For self-hosted / internal gateways behind a private or self-signed certificate. Defaults to false. When omitted on update, the stored value is left unchanged.
           example: false
-        metadata_disabled:
-          type: boolean
-          description: Disable identity metadata injection (the caller's user + authorizing group) for this provider. Defaults to false (metadata is injected). When omitted on update, the stored value is left unchanged.
-          example: false
       required:
         - provider_id
         - name

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

@@ -2227,9 +2227,6 @@ type AgentNetworkProvider struct {
 	// IdentityHeaderUserId Wire header name the proxy stamps with the caller's display identity (user email or peer name) when the catalog entry's HeaderPair is `customizable`. Empty disables stamping for this dimension. Ignored when the catalog entry has a fixed HeaderPair (e.g. LiteLLM, Portkey). Used today by Bifrost: typical values are `x-bf-lh-netbird_user_id` (always-on log metadata) or `x-bf-dim-netbird_user_id` (Prometheus / OTEL — requires the label to be pre-declared in the gateway's `client.prometheus_labels` config).
 	IdentityHeaderUserId *string `json:"identity_header_user_id,omitempty"`
 
-	// MetadataDisabled Whether identity metadata injection is disabled for this provider. When enabled (the default), the proxy stamps the caller's user and authorizing group onto upstream requests as provider-specific metadata (e.g. AWS Bedrock's X-Amzn-Bedrock-Request-Metadata header). Set true to suppress it.
-	MetadataDisabled bool `json:"metadata_disabled"`
-
 	// Models Models exposed through this endpoint, with the operator's per-1k input/output prices. Empty means all catalog models are allowed at catalog prices.
 	Models []AgentNetworkProviderModel `json:"models"`
 
@@ -2281,9 +2278,6 @@ type AgentNetworkProviderRequest struct {
 	// IdentityHeaderUserId Wire header name for the caller's display identity. See AgentNetworkProvider.identity_header_user_id. When omitted on a request, the stored value is left unchanged; pass an empty string explicitly to clear it (which disables stamping for this dimension).
 	IdentityHeaderUserId *string `json:"identity_header_user_id,omitempty"`
 
-	// MetadataDisabled Disable identity metadata injection (the caller's user + authorizing group) for this provider. Defaults to false (metadata is injected). When omitted on update, the stored value is left unchanged.
-	MetadataDisabled *bool `json:"metadata_disabled,omitempty"`
-
 	// Models Models exposed through this endpoint, with the operator's per-1k input/output prices. Empty means all catalog models are allowed at catalog prices.
 	Models *[]AgentNetworkProviderModel `json:"models,omitempty"`
 

shared/relay/auth/allow/allow_all.go

@@ -8,3 +8,7 @@ type Auth struct {
 func (a *Auth) Validate(any) error {
 	return nil
 }
+
+func (a *Auth) ValidateHelloMsgType(any) error {
+	return nil
+}

shared/relay/auth/hmac/token.go

@@ -1,8 +1,10 @@
 package hmac
 
 import (
+	"bytes"
 	"crypto/hmac"
 	"encoding/base64"
+	"encoding/gob"
 	"fmt"
 	"hash"
 	"strconv"
@@ -16,6 +18,14 @@ type Token struct {
 	Signature string
 }
 
+func unmarshalToken(payload []byte) (Token, error) {
+	var creds Token
+	buffer := bytes.NewBuffer(payload)
+	decoder := gob.NewDecoder(buffer)
+	err := decoder.Decode(&creds)
+	return creds, err
+}
+
 // TimedHMAC generates a token with TTL and uses a pre-shared secret known to the relay server
 type TimedHMAC struct {
 	secret     string

shared/relay/auth/hmac/validator.go

@@ -0,0 +1,33 @@
+package hmac
+
+import (
+	"crypto/sha256"
+	"fmt"
+	"time"
+
+	log "github.com/sirupsen/logrus"
+)
+
+type TimedHMACValidator struct {
+	*TimedHMAC
+}
+
+func NewTimedHMACValidator(secret string, duration time.Duration) *TimedHMACValidator {
+	ta := NewTimedHMAC(secret, duration)
+	return &TimedHMACValidator{
+		ta,
+	}
+}
+
+func (a *TimedHMACValidator) Validate(credentials any) error {
+	b, ok := credentials.([]byte)
+	if !ok {
+		return fmt.Errorf("invalid credentials type")
+	}
+	c, err := unmarshalToken(b)
+	if err != nil {
+		log.Debugf("failed to unmarshal token: %s", err)
+		return err
+	}
+	return a.TimedHMAC.Validate(sha256.New, c)
+}

shared/relay/auth/validator.go

@@ -1,19 +1,28 @@
 package auth
 
 import (
+	"time"
+
+	auth "github.com/netbirdio/netbird/shared/relay/auth/hmac"
 	authv2 "github.com/netbirdio/netbird/shared/relay/auth/hmac/v2"
 )
 
 type TimedHMACValidator struct {
 	authenticatorV2 *authv2.Validator
+	authenticator   *auth.TimedHMACValidator
 }
 
-func NewTimedHMACValidator(secret []byte) *TimedHMACValidator {
+func NewTimedHMACValidator(secret []byte, duration time.Duration) *TimedHMACValidator {
 	return &TimedHMACValidator{
 		authenticatorV2: authv2.NewValidator(secret),
+		authenticator:   auth.NewTimedHMACValidator(string(secret), duration),
 	}
 }
 
 func (a *TimedHMACValidator) Validate(credentials any) error {
 	return a.authenticatorV2.Validate(credentials)
 }
+
+func (a *TimedHMACValidator) ValidateHelloMsgType(credentials any) error {
+	return a.authenticator.Validate(credentials)
+}

shared/relay/messages/address/address.go

@@ -0,0 +1,21 @@
+// Deprecated: This package is deprecated and will be removed in a future release.
+package address
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+)
+
+type Address struct {
+	URL string
+}
+
+func (addr *Address) Marshal() ([]byte, error) {
+	var buf bytes.Buffer
+	enc := gob.NewEncoder(&buf)
+	if err := enc.Encode(addr); err != nil {
+		return nil, fmt.Errorf("encode Address: %w", err)
+	}
+	return buf.Bytes(), nil
+}

shared/relay/messages/auth/auth.go

@@ -0,0 +1,43 @@
+// Deprecated: This package is deprecated and will be removed in a future release.
+package auth
+
+import (
+	"bytes"
+	"encoding/gob"
+	"fmt"
+)
+
+type Algorithm int
+
+const (
+	AlgoUnknown Algorithm = iota
+	AlgoHMACSHA256
+	AlgoHMACSHA512
+)
+
+func (a Algorithm) String() string {
+	switch a {
+	case AlgoHMACSHA256:
+		return "HMAC-SHA256"
+	case AlgoHMACSHA512:
+		return "HMAC-SHA512"
+	default:
+		return "Unknown"
+	}
+}
+
+type Msg struct {
+	AuthAlgorithm  Algorithm
+	AdditionalData []byte
+}
+
+func UnmarshalMsg(data []byte) (*Msg, error) {
+	var msg *Msg
+
+	buf := bytes.NewBuffer(data)
+	dec := gob.NewDecoder(buf)
+	if err := dec.Decode(&msg); err != nil {
+		return nil, fmt.Errorf("decode Msg: %w", err)
+	}
+	return msg, nil
+}

shared/relay/messages/message.go

@@ -14,10 +14,9 @@ const (
 	CurrentProtocolVersion = 1
 
 	MsgTypeUnknown MsgType = 0
-	// MsgTypeHello and MsgTypeHelloResponse are the removed legacy handshake
-	// message types. They are retained only to reserve wire values 1 and 2 so
-	// the values are never reused; the server rejects both.
-	MsgTypeHello         = 1
+	// Deprecated: Use MsgTypeAuth instead.
+	MsgTypeHello = 1
+	// Deprecated: Use MsgTypeAuthResponse instead.
 	MsgTypeHelloResponse = 2
 	MsgTypeTransport     = 3
 	MsgTypeClose         = 4
@@ -43,6 +42,10 @@ const (
 	offsetAuthPeerID    = sizeOfProtoHeader + sizeOfMagicByte
 	headerTotalSizeAuth = sizeOfProtoHeader + headerSizeAuth
 
+	// hello message
+	headerSizeHello     = sizeOfMagicByte + peerIDSize
+	headerSizeHelloResp = 0
+
 	// transport
 	headerSizeTransport      = peerIDSize
 	offsetTransportID        = sizeOfProtoHeader
@@ -110,6 +113,7 @@ func DetermineClientMessageType(msg []byte) (MsgType, error) {
 	msgType := MsgType(msg[1])
 	switch msgType {
 	case
+		MsgTypeHello,
 		MsgTypeAuth,
 		MsgTypeTransport,
 		MsgTypeClose,
@@ -131,6 +135,7 @@ func DetermineServerMessageType(msg []byte) (MsgType, error) {
 	msgType := MsgType(msg[1])
 	switch msgType {
 	case
+		MsgTypeHelloResponse,
 		MsgTypeAuthResponse,
 		MsgTypeTransport,
 		MsgTypeClose,
@@ -143,6 +148,67 @@ func DetermineServerMessageType(msg []byte) (MsgType, error) {
 	}
 }
 
+// Deprecated: Use MarshalAuthMsg instead.
+// MarshalHelloMsg initial hello message
+// The Hello message is the first message sent by a client after establishing a connection with the Relay server. This
+// message is used to authenticate the client with the server. The authentication is done using an HMAC method.
+// The protocol does not limit to use HMAC, it can be any other method. If the authentication failed the server will
+// close the network connection without any response.
+func MarshalHelloMsg(peerID PeerID, additions []byte) ([]byte, error) {
+	msg := make([]byte, sizeOfProtoHeader+sizeOfMagicByte, sizeOfProtoHeader+headerSizeHello+len(additions))
+
+	msg[0] = byte(CurrentProtocolVersion)
+	msg[1] = byte(MsgTypeHello)
+
+	copy(msg[sizeOfProtoHeader:sizeOfProtoHeader+sizeOfMagicByte], magicHeader)
+
+	msg = append(msg, peerID[:]...)
+	msg = append(msg, additions...)
+
+	return msg, nil
+}
+
+// Deprecated: Use UnmarshalAuthMsg instead.
+// UnmarshalHelloMsg extracts peerID and the additional data from the hello message. The Additional data is used to
+// authenticate the client with the server.
+func UnmarshalHelloMsg(msg []byte) (*PeerID, []byte, error) {
+	if len(msg) < sizeOfProtoHeader+headerSizeHello {
+		return nil, nil, ErrInvalidMessageLength
+	}
+	if !bytes.Equal(msg[sizeOfProtoHeader:sizeOfProtoHeader+sizeOfMagicByte], magicHeader) {
+		return nil, nil, errors.New("invalid magic header")
+	}
+
+	peerID := PeerID(msg[sizeOfProtoHeader+sizeOfMagicByte : sizeOfProtoHeader+headerSizeHello])
+
+	return &peerID, msg[headerSizeHello:], nil
+}
+
+// Deprecated: Use MarshalAuthResponse instead.
+// MarshalHelloResponse creates a response message to the hello message.
+// In case of success connection the server response with a Hello Response message. This message contains the server's
+// instance URL. This URL will be used by choose the common Relay server in case if the peers are in different Relay
+// servers.
+func MarshalHelloResponse(additionalData []byte) ([]byte, error) {
+	msg := make([]byte, sizeOfProtoHeader, sizeOfProtoHeader+headerSizeHelloResp+len(additionalData))
+
+	msg[0] = byte(CurrentProtocolVersion)
+	msg[1] = byte(MsgTypeHelloResponse)
+
+	msg = append(msg, additionalData...)
+
+	return msg, nil
+}
+
+// Deprecated: Use UnmarshalAuthResponse instead.
+// UnmarshalHelloResponse extracts the additional data from the hello response message.
+func UnmarshalHelloResponse(msg []byte) ([]byte, error) {
+	if len(msg) < sizeOfProtoHeader+headerSizeHelloResp {
+		return nil, ErrInvalidMessageLength
+	}
+	return msg, nil
+}
+
 // MarshalAuthMsg initial authentication message
 // The Auth message is the first message sent by a client after establishing a connection with the Relay server. This
 // message is used to authenticate the client with the server. The authentication is done using an HMAC method.

shared/relay/messages/message_test.go

@@ -4,11 +4,28 @@ import (
 	"testing"
 )
 
-func TestDetermineClientMessageTypeRejectsHello(t *testing.T) {
-	// The reserved legacy Hello message (type 1) must be rejected by the server.
-	msg := []byte{byte(CurrentProtocolVersion), byte(MsgTypeHello)}
-	if _, err := DetermineClientMessageType(msg); err == nil {
-		t.Fatalf("expected hello message type to be rejected")
+func TestMarshalHelloMsg(t *testing.T) {
+	peerID := HashID("abdFAaBcawquEiCMzAabYosuUaGLtSNhKxz+")
+	msg, err := MarshalHelloMsg(peerID, nil)
+	if err != nil {
+		t.Fatalf("error: %v", err)
+	}
+
+	msgType, err := DetermineClientMessageType(msg)
+	if err != nil {
+		t.Fatalf("error: %v", err)
+	}
+
+	if msgType != MsgTypeHello {
+		t.Errorf("expected %d, got %d", MsgTypeHello, msgType)
+	}
+
+	receivedPeerID, _, err := UnmarshalHelloMsg(msg)
+	if err != nil {
+		t.Fatalf("error: %v", err)
+	}
+	if receivedPeerID.String() != peerID.String() {
+		t.Errorf("expected %s, got %s", peerID, receivedPeerID)
 	}
 }