[management] Rework Agent Network endpoint identity and settings bootstrap (#7085)

Store the per-account gateway endpoint as {domain, proxy_address} with a
global unique index on the full hostname; dedicated = (domain ==
proxy_address). Bootstrap becomes an explicit POST carrying exactly one
of proxy_address (server allocates an adjective-noun label beneath it)
or endpoint (claimed verbatim, address-first); provider create loses its
bootstrap side effect. PUT is a full replace with every field required —
the immutable identity fields must be echoed unchanged and a mismatch is
rejected with 422. A guarded DELETE releases the endpoint: refused with
412 while providers exist or a proxy is actively serving the endpoint
hostname (matched case-insensitively); re-creating bootstraps fresh. A
self-addressed pin excludes its address from the account's cluster allow
list, and the live mapping update path now addresses the serving proxy
from the synthesized service. Existing rows are migrated on all three
store engines.

management/internals/modules/reverseproxy/domain/manager/manager.go

@@ -2,24 +2,28 @@ package manager
 
 import (
 	"context"
+	"errors"
 	"fmt"
 	"net"
 	"strings"
 
 	log "github.com/sirupsen/logrus"
 
+	agentnetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
 	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
 	"github.com/netbirdio/netbird/management/server/account"
 	"github.com/netbirdio/netbird/management/server/activity"
 	"github.com/netbirdio/netbird/management/server/permissions"
 	"github.com/netbirdio/netbird/management/server/permissions/modules"
 	"github.com/netbirdio/netbird/management/server/permissions/operations"
+	nbstore "github.com/netbirdio/netbird/management/server/store"
 	"github.com/netbirdio/netbird/management/server/types"
 	"github.com/netbirdio/netbird/shared/management/status"
 )
 
 type store interface {
 	GetAccount(ctx context.Context, accountID string) (*types.Account, error)
+	GetAgentNetworkSettings(ctx context.Context, lockStrength nbstore.LockingStrength, accountID string) (*agentnetworkTypes.Settings, error)
 
 	GetCustomDomain(ctx context.Context, accountID string, domainID string) (*domain.Domain, error)
 	ListFreeDomains(ctx context.Context, accountID string) ([]string, error)
@@ -311,17 +315,21 @@ func (m Manager) getClusterAllowList(ctx context.Context, accountID string) ([]s
 	if err != nil {
 		return nil, fmt.Errorf("get public cluster addresses: %w", err)
 	}
+	reserved, err := m.reservedGatewayAddress(ctx, accountID)
+	if err != nil {
+		return nil, err
+	}
 	seen := make(map[string]struct{}, len(byopAddresses)+len(publicAddresses))
 	merged := make([]string, 0, len(byopAddresses)+len(publicAddresses))
 	for _, addr := range byopAddresses {
-		if _, ok := seen[addr]; ok {
+		if _, ok := seen[addr]; ok || addr == reserved {
 			continue
 		}
 		seen[addr] = struct{}{}
 		merged = append(merged, addr)
 	}
 	for _, addr := range publicAddresses {
-		if _, ok := seen[addr]; ok {
+		if _, ok := seen[addr]; ok || addr == reserved {
 			continue
 		}
 		seen[addr] = struct{}{}
@@ -330,6 +338,31 @@ func (m Manager) getClusterAllowList(ctx context.Context, accountID string) ([]s
 	return merged, nil
 }
 
+// reservedGatewayAddress returns the account's agent-network gateway address
+// when its settings pin is self-addressed — a proxy dedicated to serving
+// exactly the gateway. Dropping that address from the cluster allow list keeps
+// it from being offered as a cluster for ordinary services, and because the
+// free-domain suffix match is depth-independent, dropping the address rejects
+// every name beneath it as well as the bare one. Only the account's own
+// gateway address can ever appear in its allow list (another tenant's gateway
+// proxy is account-scoped to them), so this single-address exclusion is
+// sufficient. Returns "" when the account has no settings row or a labeled
+// (shared-cluster) pin.
+func (m Manager) reservedGatewayAddress(ctx context.Context, accountID string) (string, error) {
+	settings, err := m.store.GetAgentNetworkSettings(ctx, nbstore.LockingStrengthNone, accountID)
+	if err != nil {
+		var sErr *status.Error
+		if errors.As(err, &sErr) && sErr.Type() == status.NotFound {
+			return "", nil
+		}
+		return "", fmt.Errorf("get agent network settings: %w", err)
+	}
+	if settings == nil || !settings.Dedicated() {
+		return "", nil
+	}
+	return settings.ProxyAddress, nil
+}
+
 func extractClusterFromCustomDomains(serviceDomain string, customDomains []*domain.Domain) (string, bool) {
 	bestCluster := ""
 	bestLen := -1

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

@@ -7,6 +7,12 @@ import (
 
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
+
+	agentnetworkTypes "github.com/netbirdio/netbird/management/internals/modules/agentnetwork/types"
+	"github.com/netbirdio/netbird/management/internals/modules/reverseproxy/domain"
+	nbstore "github.com/netbirdio/netbird/management/server/store"
+	"github.com/netbirdio/netbird/management/server/types"
+	"github.com/netbirdio/netbird/shared/management/status"
 )
 
 type mockProxyManager struct {
@@ -55,7 +61,7 @@ func TestGetClusterAllowList_BYOPMergedWithPublic(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
 	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result)
@@ -71,7 +77,7 @@ func TestGetClusterAllowList_DeduplicatesBYOPAndPublic(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
 	assert.Equal(t, []string{"shared.example.com", "byop.example.com", "eu.proxy.netbird.io"}, result)
@@ -87,7 +93,7 @@ func TestGetClusterAllowList_NoBYOP_FallbackToShared(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
 	assert.Equal(t, []string{"eu.proxy.netbird.io", "us.proxy.netbird.io"}, result)
@@ -100,7 +106,7 @@ func TestGetClusterAllowList_BYOPError_ReturnsError(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.Error(t, err)
 	assert.Nil(t, result)
@@ -117,7 +123,7 @@ func TestGetClusterAllowList_PublicError_ReturnsError(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.Error(t, err)
 	assert.Nil(t, result)
@@ -134,7 +140,7 @@ func TestGetClusterAllowList_BYOPEmptySlice_FallbackToShared(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
 	assert.Equal(t, []string{"eu.proxy.netbird.io"}, result)
@@ -150,8 +156,138 @@ func TestGetClusterAllowList_PublicEmpty_BYOPOnly(t *testing.T) {
 		},
 	}
 
-	mgr := Manager{proxyManager: pm}
+	mgr := Manager{store: &stubStore{}, proxyManager: pm}
 	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
 	require.NoError(t, err)
 	assert.Equal(t, []string{"byop.example.com"}, result)
 }
+
+// stubStore satisfies the manager's narrow store interface for allow-list
+// tests. Only the agent-network settings lookup participates; the default (a
+// nil func) reads as "no settings row", the state most accounts are in.
+type stubStore struct {
+	getAgentNetworkSettingsFunc func(ctx context.Context, accountID string) (*agentnetworkTypes.Settings, error)
+}
+
+func (s *stubStore) GetAccount(context.Context, string) (*types.Account, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) GetAgentNetworkSettings(ctx context.Context, _ nbstore.LockingStrength, accountID string) (*agentnetworkTypes.Settings, error) {
+	if s.getAgentNetworkSettingsFunc != nil {
+		return s.getAgentNetworkSettingsFunc(ctx, accountID)
+	}
+	return nil, status.Errorf(status.NotFound, "agent network settings for account %s not found", accountID)
+}
+
+func (s *stubStore) GetCustomDomain(context.Context, string, string) (*domain.Domain, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) ListFreeDomains(context.Context, string) ([]string, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) ListCustomDomains(context.Context, string) ([]*domain.Domain, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) CreateCustomDomain(context.Context, string, string, string, bool) (*domain.Domain, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) UpdateCustomDomain(context.Context, string, *domain.Domain) (*domain.Domain, error) {
+	panic("not used in allow-list tests")
+}
+
+func (s *stubStore) DeleteCustomDomain(context.Context, string, string) error {
+	panic("not used in allow-list tests")
+}
+
+// TestGetClusterAllowList_DedicatedGatewayAddressExcluded pins invariant (B)'s
+// chokepoint: a self-addressed settings pin reserves the account's gateway
+// address, so it is dropped from the allow list — which, because the
+// free-domain suffix match is depth-independent, rejects every name beneath
+// it as well as the bare one. Other addresses are unaffected.
+func TestGetClusterAllowList_DedicatedGatewayAddressExcluded(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"brave-otter.gateway.example.com", "byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return []string{"eu.proxy.netbird.io"}, nil
+		},
+	}
+	st := &stubStore{
+		getAgentNetworkSettingsFunc: func(_ context.Context, accountID string) (*agentnetworkTypes.Settings, error) {
+			assert.Equal(t, "acc-123", accountID,
+				"the exclusion must look up the requesting account's own settings")
+			return &agentnetworkTypes.Settings{
+				AccountID:    accountID,
+				Domain:       "brave-otter.gateway.example.com",
+				ProxyAddress: "brave-otter.gateway.example.com",
+			}, nil
+		},
+	}
+
+	mgr := Manager{store: st, proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result,
+		"the dedicated gateway address must be reserved from cluster selection")
+}
+
+// TestGetClusterAllowList_LabeledPinDoesNotExclude pins the counterpart: a
+// labeled pin means the gateway rides on a shared cluster serving ordinary
+// services too, so nothing is reserved.
+func TestGetClusterAllowList_LabeledPinDoesNotExclude(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return []string{"eu.proxy.netbird.io"}, nil
+		},
+	}
+	st := &stubStore{
+		getAgentNetworkSettingsFunc: func(_ context.Context, accountID string) (*agentnetworkTypes.Settings, error) {
+			return &agentnetworkTypes.Settings{
+				AccountID:    accountID,
+				Domain:       "violet.eu.proxy.netbird.io",
+				ProxyAddress: "eu.proxy.netbird.io",
+			}, nil
+		},
+	}
+
+	mgr := Manager{store: st, proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.NoError(t, err)
+	assert.Equal(t, []string{"byop.example.com", "eu.proxy.netbird.io"}, result,
+		"a labeled pin reserves nothing")
+}
+
+// TestGetClusterAllowList_SettingsLookupError_ReturnsError pins that a store
+// outage is surfaced rather than silently treated as "nothing reserved" —
+// failing open here would offer a reserved gateway address for ordinary
+// services.
+func TestGetClusterAllowList_SettingsLookupError_ReturnsError(t *testing.T) {
+	pm := &mockProxyManager{
+		getActiveClusterAddressesForAccountFunc: func(_ context.Context, _ string) ([]string, error) {
+			return []string{"byop.example.com"}, nil
+		},
+		getActiveClusterAddressesFunc: func(_ context.Context) ([]string, error) {
+			return []string{"eu.proxy.netbird.io"}, nil
+		},
+	}
+	st := &stubStore{
+		getAgentNetworkSettingsFunc: func(_ context.Context, _ string) (*agentnetworkTypes.Settings, error) {
+			return nil, status.Errorf(status.Internal, "store outage")
+		},
+	}
+
+	mgr := Manager{store: st, proxyManager: pm}
+	result, err := mgr.getClusterAllowList(context.Background(), "acc-123")
+	require.Error(t, err)
+	assert.Nil(t, result)
+	assert.Contains(t, err.Error(), "agent network settings")
+}