[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.
2026-09-28 09:39:05 +02:00 · 2026-08-10 19:06:55 +02:00
parent e8671a811d
commit ebfdf7d7b8
46 changed files with 2392 additions and 688 deletions
@@ -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
+}
@@ -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")
 	})
 }