Merge branch 'main' into embedded-vnc

shared/management/client/client_test.go

@@ -8,7 +8,7 @@ import (
 	"testing"
 	"time"
 
-	"github.com/golang/mock/gomock"
+	"go.uber.org/mock/gomock"
 	log "github.com/sirupsen/logrus"
 	"github.com/stretchr/testify/assert"
 	"github.com/stretchr/testify/require"
@@ -591,7 +591,7 @@ func Test_GetPKCEAuthorizationFlow(t *testing.T) {
 	expectedFlowInfo := &mgmtProto.PKCEAuthorizationFlow{
 		ProviderConfig: &mgmtProto.ProviderConfig{
 			ClientID:     "client",
-			ClientSecret: "secret",
+			ClientSecret: "secret", //nolint:staticcheck
 		},
 	}
 

shared/management/client/grpc.go

@@ -21,6 +21,8 @@ import (
 	"google.golang.org/grpc/connectivity"
 
 	nbgrpc "github.com/netbirdio/netbird/client/grpc"
+	"github.com/netbirdio/netbird/client/netstate"
+	"github.com/netbirdio/netbird/client/netsweep"
 	"github.com/netbirdio/netbird/client/system"
 	"github.com/netbirdio/netbird/encryption"
 	"github.com/netbirdio/netbird/shared/management/domain"
@@ -62,6 +64,13 @@ type GrpcClient struct {
 	connStateCallbackLock sync.RWMutex
 	serverURL             string
 
+	// netState gates the stream retry loop on OS-reported network
+	// availability; nil (the default) disables gating.
+	netState *netstate.State
+
+	// sweeper cuts the transport connections on network change; nil disables it.
+	sweeper *netsweep.Sweeper
+
 	// syncStreamErr holds the last Sync stream error, or nil while the stream
 	// is established and healthy. GetServerKey succeeds even when the peer
 	// cannot sync (e.g. the server returns "settings not found"), so the
@@ -111,16 +120,43 @@ func MaxRecvMsgSize() int {
 	return size
 }
 
+// Option configures optional GrpcClient behavior.
+type Option func(*GrpcClient)
+
+// WithNetworkState injects the OS network availability state that gates the
+// stream retry loop; without it gating is disabled.
+func WithNetworkState(netState *netstate.State) Option {
+	return func(c *GrpcClient) { c.netState = netState }
+}
+
+// WithSweeper injects the network change sweeper.
+func WithSweeper(sweeper *netsweep.Sweeper) Option {
+	return func(c *GrpcClient) { c.sweeper = sweeper }
+}
+
 // NewClient creates a new client to Management service
-func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool) (*GrpcClient, error) {
-	var conn *grpc.ClientConn
+func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsEnabled bool, opts ...Option) (*GrpcClient, error) {
+	// Options apply before dialing: the sweeper must wrap the first connection too.
+	c := &GrpcClient{
+		key:                   ourPrivateKey,
+		ctx:                   ctx,
+		connStateCallbackLock: sync.RWMutex{},
+		serverURL:             addr,
+	}
+	for _, opt := range opts {
+		opt(c)
+	}
 
 	var extraOpts []grpc.DialOption
 	if maxSize := MaxRecvMsgSize(); maxSize > 0 {
 		extraOpts = append(extraOpts, grpc.WithDefaultCallOptions(grpc.MaxCallRecvMsgSize(maxSize)))
 		log.Infof("management gRPC max receive message size set to %d bytes", maxSize)
 	}
+	if c.sweeper != nil {
+		extraOpts = append(extraOpts, nbgrpc.WithSweeper(c.sweeper))
+	}
 
+	var conn *grpc.ClientConn
 	operation := func() error {
 		var err error
 		conn, err = nbgrpc.CreateConnection(ctx, addr, tlsEnabled, wsproxy.ManagementComponent, extraOpts...)
@@ -136,16 +172,9 @@ func NewClient(ctx context.Context, addr string, ourPrivateKey wgtypes.Key, tlsE
 		return nil, err
 	}
 
-	realClient := proto.NewManagementServiceClient(conn)
-
-	return &GrpcClient{
-		key:                   ourPrivateKey,
-		realClient:            realClient,
-		ctx:                   ctx,
-		conn:                  conn,
-		connStateCallbackLock: sync.RWMutex{},
-		serverURL:             addr,
-	}, nil
+	c.conn = conn
+	c.realClient = proto.NewManagementServiceClient(conn)
+	return c, nil
 }
 
 // GetServerURL returns the management server URL
@@ -206,16 +235,33 @@ func (c *GrpcClient) withMgmtStream(
 	ctx context.Context,
 	handler func(ctx context.Context, serverPubKey wgtypes.Key, backOff backoff.BackOff) error,
 ) error {
-	backOff := defaultBackoff(ctx)
+	backOff := c.sweeper.QuickRetryBackoff(ctx, defaultBackoff(ctx), c.netState)
 	operation := func() error {
-		log.Debugf("management connection state %v", c.conn.GetState())
-		connState := c.conn.GetState()
+		// suspend reconnect attempts while the OS reports no usable network.
+		// Wait only errors on a cancelled context, which means shutdown, so
+		// stop the loop without reporting a failure.
+		if waited, err := c.netState.Wait(ctx); err != nil {
+			log.Debugf("management connection context has been canceled while offline, this usually indicates shutdown")
+			return nil //nolint:nilerr // a cancelled context means shutdown, not a retryable failure
+		} else if waited {
+			backOff.Reset()
+		}
 
+		connState := c.conn.GetState()
+		log.Debugf("management connection state %v", connState)
 		if connState == connectivity.Shutdown {
 			return backoff.Permanent(fmt.Errorf("connection to management has been shut down"))
-		} else if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+		}
+		if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+			// A dial may already be in flight (e.g. the other stream triggered
+			// it after a network change); wait for it to settle and proceed if
+			// the channel became usable, instead of burning a backoff round on
+			// a successful dial. A failed dial errors out as before.
 			c.conn.WaitForStateChange(ctx, connState)
-			return fmt.Errorf("connection to management is not ready and in %s state", connState)
+			connState = c.conn.GetState()
+			if !(connState == connectivity.Ready || connState == connectivity.Idle) {
+				return fmt.Errorf("connection to management is not ready and in %s state", connState)
+			}
 		}
 
 		serverPubKey, err := c.getServerPublicKey()
@@ -227,7 +273,7 @@ func (c *GrpcClient) withMgmtStream(
 		return handler(ctx, *serverPubKey, backOff)
 	}
 
-	err := backoff.Retry(operation, backOff)
+	err := nbgrpc.Retry(ctx, operation, backOff, c.netState)
 	if err != nil {
 		log.Warnf("exiting the Management service connection retry loop due to the unrecoverable error: %s", err)
 	}

shared/management/client/rest/agentnetwork.go

@@ -57,10 +57,9 @@ func (a *AgentNetworkAPI) GetProvider(ctx context.Context, providerID string) (*
 	return &ret, err
 }
 
-// CreateProvider creates a new Agent Network provider. Set
-// request.BootstrapCluster on the account's first provider to bootstrap the
-// per-account gateway endpoint (alternatively bootstrap via UpdateSettings
-// with a cluster).
+// CreateProvider creates a new Agent Network provider. Providers have no
+// settings side effects — bootstrap the account's gateway endpoint separately
+// via CreateSettings.
 func (a *AgentNetworkAPI) CreateProvider(ctx context.Context, request api.PostApiAgentNetworkProvidersJSONRequestBody) (*api.AgentNetworkProvider, error) {
 	requestBytes, err := json.Marshal(request)
 	if err != nil {
@@ -329,14 +328,13 @@ func (a *AgentNetworkAPI) DeleteBudgetRule(ctx context.Context, ruleID string) e
 	return nil
 }
 
-// GetSettings gets the account's Agent Network gateway settings (cluster,
-// subdomain, endpoint, collection toggles). An account that has not been
-// bootstrapped yet — via UpdateSettings with a cluster, or by creating the
-// first provider with bootstrap_cluster set — reads as the defaults with an
-// empty Cluster, Subdomain and Endpoint. Management servers prior to that
-// contract answered 200 with a JSON null body instead; that legacy shape is
-// translated to an APIError matchable via IsNotFound rather than fabricating
-// defaults the server never stated.
+// GetSettings gets the account's Agent Network gateway settings (endpoint,
+// proxy address, collection toggles). An account that has not been
+// bootstrapped yet — via CreateSettings — reads as the defaults with an empty
+// Endpoint and ProxyAddress. Management servers prior to that contract
+// answered 200 with a JSON null body instead; that legacy shape is translated
+// to an APIError matchable via IsNotFound rather than fabricating defaults
+// the server never stated.
 func (a *AgentNetworkAPI) GetSettings(ctx context.Context) (*api.AgentNetworkSettings, error) {
 	resp, err := a.c.NewRequest(ctx, "GET", "/api/agent-network/settings", nil, nil)
 	if err != nil {
@@ -359,11 +357,33 @@ func (a *AgentNetworkAPI) GetSettings(ctx context.Context) (*api.AgentNetworkSet
 	return &ret, nil
 }
 
+// CreateSettings bootstraps the account's Agent Network settings row,
+// assigning the immutable endpoint. Exactly one of request.ProxyAddress
+// (labeled endpoint beneath that cluster; the server allocates the label) and
+// request.Endpoint (self-addressed dedicated endpoint, claimed verbatim) must
+// be set. Returns a conflict when the account already has a settings row.
+func (a *AgentNetworkAPI) CreateSettings(ctx context.Context, request api.PostApiAgentNetworkSettingsJSONRequestBody) (*api.AgentNetworkSettings, error) {
+	requestBytes, err := json.Marshal(request)
+	if err != nil {
+		return nil, err
+	}
+	resp, err := a.c.NewRequest(ctx, "POST", "/api/agent-network/settings", bytes.NewReader(requestBytes), nil)
+	if err != nil {
+		return nil, err
+	}
+	if resp.Body != nil {
+		defer resp.Body.Close()
+	}
+	ret, err := parseResponse[api.AgentNetworkSettings](resp)
+	return &ret, err
+}
+
 // UpdateSettings updates the account's Agent Network settings; the request
-// replaces every mutable field (collection toggles and retention). Setting
-// request.Cluster bootstraps the settings row when the account does not have
-// one yet; on a bootstrapped account it must match the assigned cluster (or
-// be nil) and any other value is rejected — the cluster is immutable.
+// carries every field, replacing the mutable ones (collection toggles and
+// retention). The endpoint and proxy address are assigned at bootstrap
+// (CreateSettings) and immutable — the request must echo them unchanged, and
+// a request carrying different values is rejected. Returns not-found until
+// the account is bootstrapped.
 func (a *AgentNetworkAPI) UpdateSettings(ctx context.Context, request api.PutApiAgentNetworkSettingsJSONRequestBody) (*api.AgentNetworkSettings, error) {
 	requestBytes, err := json.Marshal(request)
 	if err != nil {
@@ -379,3 +399,19 @@ func (a *AgentNetworkAPI) UpdateSettings(ctx context.Context, request api.PutApi
 	ret, err := parseResponse[api.AgentNetworkSettings](resp)
 	return &ret, err
 }
+
+// DeleteSettings deletes the account's Agent Network settings row, releasing
+// the endpoint. The server refuses (precondition failed) while any provider
+// exists for the account or while a proxy is actively serving the endpoint.
+// Bootstrapping again afterwards allocates a new endpoint.
+func (a *AgentNetworkAPI) DeleteSettings(ctx context.Context) error {
+	resp, err := a.c.NewRequest(ctx, "DELETE", "/api/agent-network/settings", nil, nil)
+	if err != nil {
+		return err
+	}
+	if resp.Body != nil {
+		defer resp.Body.Close()
+	}
+
+	return nil
+}

shared/management/client/rest/agentnetwork_test.go

@@ -47,9 +47,9 @@ var (
 	}
 
 	testAgentNetworkSettings = api.AgentNetworkSettings{
-		Cluster:                "eu.proxy.netbird.io",
-		Subdomain:              "violet",
 		Endpoint:               "violet.eu.proxy.netbird.io",
+		ProxyAddress:           "eu.proxy.netbird.io",
+		Dedicated:              false,
 		EnableLogCollection:    true,
 		AccessLogRetentionDays: ptr(30),
 	}
@@ -120,18 +120,15 @@ func TestAgentNetwork_CreateProvider_200(t *testing.T) {
 			var req api.PostApiAgentNetworkProvidersJSONRequestBody
 			require.NoError(t, json.Unmarshal(reqBytes, &req))
 			assert.Equal(t, "OpenAI", req.Name)
-			require.NotNil(t, req.BootstrapCluster)
-			assert.Equal(t, "eu.proxy.netbird.io", *req.BootstrapCluster)
 			retBytes, _ := json.Marshal(testAgentNetworkProvider)
 			_, err = w.Write(retBytes)
 			require.NoError(t, err)
 		})
 		ret, err := c.AgentNetwork.CreateProvider(context.Background(), api.PostApiAgentNetworkProvidersJSONRequestBody{
-			ProviderId:       "openai_api",
-			Name:             "OpenAI",
-			UpstreamUrl:      "https://api.openai.com",
-			ApiKey:           ptr("sk-test"),
-			BootstrapCluster: ptr("eu.proxy.netbird.io"),
+			ProviderId:  "openai_api",
+			Name:        "OpenAI",
+			UpstreamUrl: "https://api.openai.com",
+			ApiKey:      ptr("sk-test"),
 		})
 		require.NoError(t, err)
 		assert.Equal(t, testAgentNetworkProvider, *ret)
@@ -456,6 +453,45 @@ func TestAgentNetwork_GetSettings_LegacyNullBody(t *testing.T) {
 	})
 }
 
+func TestAgentNetwork_CreateSettings_200(t *testing.T) {
+	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
+		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
+			assert.Equal(t, "POST", r.Method)
+			reqBytes, err := io.ReadAll(r.Body)
+			require.NoError(t, err)
+			var req api.PostApiAgentNetworkSettingsJSONRequestBody
+			require.NoError(t, json.Unmarshal(reqBytes, &req))
+			require.NotNil(t, req.ProxyAddress, "proxy address must be on the wire")
+			assert.Equal(t, "eu.proxy.netbird.io", *req.ProxyAddress)
+			assert.Nil(t, req.Endpoint, "endpoint must stay off the wire for a labeled bootstrap")
+			retBytes, _ := json.Marshal(testAgentNetworkSettings)
+			_, err = w.Write(retBytes)
+			require.NoError(t, err)
+		})
+		ret, err := c.AgentNetwork.CreateSettings(context.Background(), api.PostApiAgentNetworkSettingsJSONRequestBody{
+			ProxyAddress: ptr("eu.proxy.netbird.io"),
+		})
+		require.NoError(t, err)
+		assert.Equal(t, testAgentNetworkSettings, *ret)
+	})
+}
+
+func TestAgentNetwork_CreateSettings_Conflict(t *testing.T) {
+	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
+		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
+			retBytes, _ := json.Marshal(util.ErrorResponse{Message: "agent network settings already bootstrapped for account acct1", Code: 409})
+			w.WriteHeader(409)
+			_, err := w.Write(retBytes)
+			require.NoError(t, err)
+		})
+		_, err := c.AgentNetwork.CreateSettings(context.Background(), api.PostApiAgentNetworkSettingsJSONRequestBody{
+			Endpoint: ptr("gw.example.com"),
+		})
+		require.Error(t, err)
+		assert.Contains(t, err.Error(), "already bootstrapped")
+	})
+}
+
 func TestAgentNetwork_UpdateSettings_200(t *testing.T) {
 	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
 		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
@@ -464,15 +500,18 @@ func TestAgentNetwork_UpdateSettings_200(t *testing.T) {
 			require.NoError(t, err)
 			var req api.PutApiAgentNetworkSettingsJSONRequestBody
 			require.NoError(t, json.Unmarshal(reqBytes, &req))
-			require.NotNil(t, req.Cluster, "bootstrap cluster must be on the wire")
-			assert.Equal(t, "eu.proxy.netbird.io", *req.Cluster)
 			assert.True(t, req.EnableLogCollection)
+			assert.Equal(t, "brave-otter.eu.proxy.netbird.io", req.Endpoint,
+				"the identity echo must be on the wire")
+			assert.Equal(t, "eu.proxy.netbird.io", req.ProxyAddress,
+				"the identity echo must be on the wire")
 			retBytes, _ := json.Marshal(testAgentNetworkSettings)
 			_, err = w.Write(retBytes)
 			require.NoError(t, err)
 		})
 		ret, err := c.AgentNetwork.UpdateSettings(context.Background(), api.PutApiAgentNetworkSettingsJSONRequestBody{
-			Cluster:             ptr("eu.proxy.netbird.io"),
+			Endpoint:            "brave-otter.eu.proxy.netbird.io",
+			ProxyAddress:        "eu.proxy.netbird.io",
 			EnableLogCollection: true,
 		})
 		require.NoError(t, err)
@@ -483,15 +522,40 @@ func TestAgentNetwork_UpdateSettings_200(t *testing.T) {
 func TestAgentNetwork_UpdateSettings_Err(t *testing.T) {
 	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
 		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
-			retBytes, _ := json.Marshal(util.ErrorResponse{Message: "cluster is immutable once assigned (current: eu.proxy.netbird.io)", Code: 422})
-			w.WriteHeader(422)
+			retBytes, _ := json.Marshal(util.ErrorResponse{Message: "agent network settings have not been bootstrapped yet; POST /api/agent-network/settings to bootstrap them", Code: 404})
+			w.WriteHeader(404)
 			_, err := w.Write(retBytes)
 			require.NoError(t, err)
 		})
 		_, err := c.AgentNetwork.UpdateSettings(context.Background(), api.PutApiAgentNetworkSettingsJSONRequestBody{
-			Cluster: ptr("us.proxy.netbird.io"),
+			EnableLogCollection: true,
 		})
 		require.Error(t, err)
-		assert.Contains(t, err.Error(), "immutable")
+		assert.True(t, rest.IsNotFound(err), "an unbootstrapped account must surface as IsNotFound")
+	})
+}
+
+func TestAgentNetwork_DeleteSettings_200(t *testing.T) {
+	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
+		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
+			assert.Equal(t, "DELETE", r.Method)
+			_, err := w.Write([]byte("{}"))
+			require.NoError(t, err)
+		})
+		require.NoError(t, c.AgentNetwork.DeleteSettings(context.Background()))
+	})
+}
+
+func TestAgentNetwork_DeleteSettings_Guarded(t *testing.T) {
+	withMockClient(func(c *rest.Client, mux *http.ServeMux) {
+		mux.HandleFunc("/api/agent-network/settings", func(w http.ResponseWriter, r *http.Request) {
+			retBytes, _ := json.Marshal(util.ErrorResponse{Message: "agent network settings cannot be deleted while 2 provider(s) exist; delete the providers first", Code: 412})
+			w.WriteHeader(412)
+			_, err := w.Write(retBytes)
+			require.NoError(t, err)
+		})
+		err := c.AgentNetwork.DeleteSettings(context.Background())
+		require.Error(t, err)
+		assert.Contains(t, err.Error(), "cannot be deleted")
 	})
 }