@databricks/sdk-modelserving 0.1.0-dev.1 → 0.1.0-dev.3

package/src/v1/client.ts

@@ -1,13 +1,12 @@
 // Code generated from API definition by Databricks SDK Generator. DO NOT EDIT.
 
 import {VERSION as AUTH_VERSION} from '@databricks/sdk-auth';
-import type {Call} from '@databricks/sdk-core/api';
-import {retryOn} from '@databricks/sdk-core/api';
 import {createDefault} from '@databricks/sdk-core/clientinfo';
 import type {Logger} from '@databricks/sdk-core/logger';
 import {NoOpLogger} from '@databricks/sdk-core/logger';
 import type {CallOptions} from '@databricks/sdk-options/call';
 import type {ClientOptions} from '@databricks/sdk-options/client';
+import type {LroOptions} from '@databricks/sdk-options/lro';
 import type {HttpClient} from '@databricks/sdk-core/http';
 import {newHttpClient} from './transport';
 import {
@@ -17,13 +16,15 @@ import {
   sendAndCheckError,
   marshalRequest,
   parseResponse,
+  executeWait,
+  StillRunningError,
 } from './utils';
 import pkgJson from '../../package.json' with {type: 'json'};
 import type {
   CreateInferenceEndpointRequest,
   CreatePtEndpointRequest,
   DeleteInferenceEndpointRequest,
-  DeleteInferenceEndpointRequest_Response,
+  DeleteInferenceEndpointResponse,
   ExportMetricsResponse,
   ExternalFunctionRequest,
   ExternalFunctionResponse,
@@ -32,22 +33,22 @@ import type {
   GetInferenceEndpointSchemaRequest,
   GetOpenApiResponse,
   GetServedModelBuildLogsRequest,
-  GetServedModelBuildLogsRequest_Response,
+  GetServedModelBuildLogsResponse,
   GetServedModelLogsRequest,
-  GetServedModelLogsRequest_Response,
+  GetServedModelLogsResponse,
   InferenceEndpointDetailed,
   ListInferenceEndpointsRequest,
-  ListInferenceEndpointsRequest_Response,
+  ListInferenceEndpointsResponse,
   PatchInferenceEndpointTagsRequest,
-  PatchInferenceEndpointTagsRequest_Response,
+  PatchInferenceEndpointTagsResponse,
   PutInferenceEndpointAiGatewayRequest,
-  PutInferenceEndpointAiGatewayRequest_Response,
+  PutInferenceEndpointAiGatewayResponse,
   PutInferenceEndpointConfigRequest,
   PutInferenceEndpointRateLimitsRequest,
-  PutInferenceEndpointRateLimitsRequest_Response,
+  PutInferenceEndpointRateLimitsResponse,
   PutPtEndpointConfigRequest,
   UpdateInferenceEndpointNotificationsRequest,
-  UpdateInferenceEndpointNotificationsRequest_Response,
+  UpdateInferenceEndpointNotificationsResponse,
 } from './model';
 import {
   InferenceEndpointState_ConfigUpdateState,
@@ -60,15 +61,15 @@ import {
   marshalPutInferenceEndpointRateLimitsRequestSchema,
   marshalPutPtEndpointConfigRequestSchema,
   marshalUpdateInferenceEndpointNotificationsRequestSchema,
-  unmarshalDeleteInferenceEndpointRequest_ResponseSchema,
-  unmarshalGetServedModelBuildLogsRequest_ResponseSchema,
-  unmarshalGetServedModelLogsRequest_ResponseSchema,
+  unmarshalDeleteInferenceEndpointResponseSchema,
+  unmarshalGetServedModelBuildLogsResponseSchema,
+  unmarshalGetServedModelLogsResponseSchema,
   unmarshalInferenceEndpointDetailedSchema,
-  unmarshalListInferenceEndpointsRequest_ResponseSchema,
-  unmarshalPatchInferenceEndpointTagsRequest_ResponseSchema,
-  unmarshalPutInferenceEndpointAiGatewayRequest_ResponseSchema,
-  unmarshalPutInferenceEndpointRateLimitsRequest_ResponseSchema,
-  unmarshalUpdateInferenceEndpointNotificationsRequest_ResponseSchema,
+  unmarshalListInferenceEndpointsResponseSchema,
+  unmarshalPatchInferenceEndpointTagsResponseSchema,
+  unmarshalPutInferenceEndpointAiGatewayResponseSchema,
+  unmarshalPutInferenceEndpointRateLimitsResponseSchema,
+  unmarshalUpdateInferenceEndpointNotificationsResponseSchema,
 } from './model';
 
 // Package identity segment for this client to be used in the User-Agent header.
@@ -77,9 +78,7 @@ const PACKAGE_SEGMENT = {
   value: pkgJson.version,
 };
 
-class StillRunningError extends Error {}
-
-export class ModelservingClient {
+export class ModelServingClient {
   private readonly host: string;
   // Workspace ID used to route workspace-level calls on unified hosts (SPOG).
   // When set, workspace-level methods send X-Databricks-Org-Id on every
@@ -108,7 +107,7 @@ export class ModelservingClient {
   }
 
   /** Create a new serving endpoint. */
-  async createInferenceEndpoint(
+  private async createInferenceEndpoint(
     req: CreateInferenceEndpointRequest,
     options?: CallOptions
   ): Promise<InferenceEndpointDetailed> {
@@ -118,7 +117,7 @@ export class ModelservingClient {
       marshalCreateInferenceEndpointRequestSchema
     );
     let resp: InferenceEndpointDetailed | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -134,7 +133,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -151,14 +150,14 @@ export class ModelservingClient {
   }
 
   /** Create a new PT serving endpoint. */
-  async createProvisionedThroughputInferenceEndpoint(
+  private async createProvisionedThroughputInferenceEndpoint(
     req: CreatePtEndpointRequest,
     options?: CallOptions
   ): Promise<InferenceEndpointDetailed> {
     const url = `${this.host}/api/2.0/serving-endpoints/pt`;
     const body = marshalRequest(req, marshalCreatePtEndpointRequestSchema);
     let resp: InferenceEndpointDetailed | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -174,7 +173,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -197,10 +196,10 @@ export class ModelservingClient {
   async deleteInferenceEndpoint(
     req: DeleteInferenceEndpointRequest,
     options?: CallOptions
-  ): Promise<DeleteInferenceEndpointRequest_Response> {
+  ): Promise<DeleteInferenceEndpointResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}`;
-    let resp: DeleteInferenceEndpointRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: DeleteInferenceEndpointResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -214,12 +213,12 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalDeleteInferenceEndpointRequest_ResponseSchema
+        unmarshalDeleteInferenceEndpointResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -231,7 +230,7 @@ export class ModelservingClient {
   ): Promise<ExportMetricsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/metrics`;
     let resp: ExportMetricsResponse | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -249,7 +248,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -261,7 +260,7 @@ export class ModelservingClient {
   ): Promise<InferenceEndpointDetailed> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}`;
     let resp: InferenceEndpointDetailed | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -277,7 +276,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -289,7 +288,7 @@ export class ModelservingClient {
   ): Promise<GetOpenApiResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/openapi`;
     let resp: GetOpenApiResponse | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -307,7 +306,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -316,10 +315,10 @@ export class ModelservingClient {
   async getServedModelBuildLogs(
     req: GetServedModelBuildLogsRequest,
     options?: CallOptions
-  ): Promise<GetServedModelBuildLogsRequest_Response> {
+  ): Promise<GetServedModelBuildLogsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/served-models/${req.servedModelName ?? ''}/build-logs`;
-    let resp: GetServedModelBuildLogsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: GetServedModelBuildLogsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -333,12 +332,12 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalGetServedModelBuildLogsRequest_ResponseSchema
+        unmarshalGetServedModelBuildLogsResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -347,10 +346,10 @@ export class ModelservingClient {
   async getServedModelLogs(
     req: GetServedModelLogsRequest,
     options?: CallOptions
-  ): Promise<GetServedModelLogsRequest_Response> {
+  ): Promise<GetServedModelLogsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/served-models/${req.servedModelName ?? ''}/logs`;
-    let resp: GetServedModelLogsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: GetServedModelLogsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -362,14 +361,11 @@ export class ModelservingClient {
         httpClient: this.httpClient,
         logger: this.logger,
       });
-      resp = parseResponse(
-        respBody,
-        unmarshalGetServedModelLogsRequest_ResponseSchema
-      );
+      resp = parseResponse(respBody, unmarshalGetServedModelLogsResponseSchema);
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -378,10 +374,10 @@ export class ModelservingClient {
   async listInferenceEndpoints(
     _req: ListInferenceEndpointsRequest,
     options?: CallOptions
-  ): Promise<ListInferenceEndpointsRequest_Response> {
+  ): Promise<ListInferenceEndpointsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints`;
-    let resp: ListInferenceEndpointsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: ListInferenceEndpointsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers();
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -395,12 +391,12 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalListInferenceEndpointsRequest_ResponseSchema
+        unmarshalListInferenceEndpointsResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -409,14 +405,14 @@ export class ModelservingClient {
   async patchInferenceEndpointTags(
     req: PatchInferenceEndpointTagsRequest,
     options?: CallOptions
-  ): Promise<PatchInferenceEndpointTagsRequest_Response> {
+  ): Promise<PatchInferenceEndpointTagsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/tags`;
     const body = marshalRequest(
       req,
       marshalPatchInferenceEndpointTagsRequestSchema
     );
-    let resp: PatchInferenceEndpointTagsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: PatchInferenceEndpointTagsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -430,12 +426,12 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalPatchInferenceEndpointTagsRequest_ResponseSchema
+        unmarshalPatchInferenceEndpointTagsResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -444,14 +440,14 @@ export class ModelservingClient {
   async putInferenceEndpointAiGateway(
     req: PutInferenceEndpointAiGatewayRequest,
     options?: CallOptions
-  ): Promise<PutInferenceEndpointAiGatewayRequest_Response> {
+  ): Promise<PutInferenceEndpointAiGatewayResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/ai-gateway`;
     const body = marshalRequest(
       req,
       marshalPutInferenceEndpointAiGatewayRequestSchema
     );
-    let resp: PutInferenceEndpointAiGatewayRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: PutInferenceEndpointAiGatewayResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -465,18 +461,18 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalPutInferenceEndpointAiGatewayRequest_ResponseSchema
+        unmarshalPutInferenceEndpointAiGatewayResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
 
   /** Updates any combination of the serving endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. An endpoint that already has an update in progress can not be updated until the current update completes or fails. */
-  async putInferenceEndpointConfig(
+  private async putInferenceEndpointConfig(
     req: PutInferenceEndpointConfigRequest,
     options?: CallOptions
   ): Promise<InferenceEndpointDetailed> {
@@ -486,7 +482,7 @@ export class ModelservingClient {
       marshalPutInferenceEndpointConfigRequestSchema
     );
     let resp: InferenceEndpointDetailed | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -502,7 +498,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -522,14 +518,14 @@ export class ModelservingClient {
   async putInferenceEndpointRateLimits(
     req: PutInferenceEndpointRateLimitsRequest,
     options?: CallOptions
-  ): Promise<PutInferenceEndpointRateLimitsRequest_Response> {
+  ): Promise<PutInferenceEndpointRateLimitsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/rate-limits`;
     const body = marshalRequest(
       req,
       marshalPutInferenceEndpointRateLimitsRequestSchema
     );
-    let resp: PutInferenceEndpointRateLimitsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: PutInferenceEndpointRateLimitsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -543,25 +539,25 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalPutInferenceEndpointRateLimitsRequest_ResponseSchema
+        unmarshalPutInferenceEndpointRateLimitsResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
 
   /** Updates any combination of the pt endpoint's served entities, the compute configuration of those served entities, and the endpoint's traffic config. Updates are instantaneous and endpoint should be updated instantly */
-  async putProvisionedThroughputInferenceEndpointConfig(
+  private async putProvisionedThroughputInferenceEndpointConfig(
     req: PutPtEndpointConfigRequest,
     options?: CallOptions
   ): Promise<InferenceEndpointDetailed> {
     const url = `${this.host}/api/2.0/serving-endpoints/pt/${req.name ?? ''}/config`;
     const body = marshalRequest(req, marshalPutPtEndpointConfigRequestSchema);
     let resp: InferenceEndpointDetailed | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -577,7 +573,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -600,14 +596,14 @@ export class ModelservingClient {
   async updateInferenceEndpointNotifications(
     req: UpdateInferenceEndpointNotificationsRequest,
     options?: CallOptions
-  ): Promise<UpdateInferenceEndpointNotificationsRequest_Response> {
+  ): Promise<UpdateInferenceEndpointNotificationsResponse> {
     const url = `${this.host}/api/2.0/serving-endpoints/${req.name ?? ''}/notifications`;
     const body = marshalRequest(
       req,
       marshalUpdateInferenceEndpointNotificationsRequestSchema
     );
-    let resp: UpdateInferenceEndpointNotificationsRequest_Response | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    let resp: UpdateInferenceEndpointNotificationsResponse | undefined;
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -621,12 +617,12 @@ export class ModelservingClient {
       });
       resp = parseResponse(
         respBody,
-        unmarshalUpdateInferenceEndpointNotificationsRequest_ResponseSchema
+        unmarshalUpdateInferenceEndpointNotificationsResponseSchema
       );
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -639,7 +635,7 @@ export class ModelservingClient {
     const url = `${this.host}/api/2.0/external-function`;
     const body = marshalRequest(req, marshalExternalFunctionRequestSchema);
     let resp: ExternalFunctionResponse | undefined;
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const headers = new Headers({'Content-Type': 'application/json'});
       if (this.workspaceId !== undefined) {
         headers.set('X-Databricks-Org-Id', this.workspaceId);
@@ -657,7 +653,7 @@ export class ModelservingClient {
     };
     await executeCall(call, options);
     if (resp === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return resp;
   }
@@ -665,7 +661,7 @@ export class ModelservingClient {
 
 export class CreateInferenceEndpointWaiter {
   constructor(
-    private readonly client: ModelservingClient,
+    private readonly client: ModelServingClient,
     readonly name: string
   ) {}
 
@@ -674,15 +670,15 @@ export class CreateInferenceEndpointWaiter {
    *
    * Throws if a failure state is reached.
    */
-  async wait(options?: CallOptions): Promise<InferenceEndpointDetailed> {
+  async wait(options?: LroOptions): Promise<InferenceEndpointDetailed> {
     let result: InferenceEndpointDetailed | undefined;
 
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const pollResp = await this.client.getInferenceEndpoint(
         {
           name: this.name,
         },
-        {...options, ...(callSignal !== undefined && {signal: callSignal})}
+        callSignal !== undefined ? {signal: callSignal} : undefined
       );
 
       const status = pollResp.state?.configUpdate;
@@ -704,16 +700,9 @@ export class CreateInferenceEndpointWaiter {
       }
     };
 
-    const retryOptions: CallOptions = {
-      ...(options?.signal !== undefined && {signal: options.signal}),
-      retrier: () =>
-        retryOn({}, (err: Error) => {
-          return err instanceof StillRunningError;
-        }),
-    };
-    await executeCall(call, retryOptions);
+    await executeWait(call, options);
     if (result === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return result;
   }
@@ -745,7 +734,7 @@ export class CreateInferenceEndpointWaiter {
 
 export class CreateProvisionedThroughputInferenceEndpointWaiter {
   constructor(
-    private readonly client: ModelservingClient,
+    private readonly client: ModelServingClient,
     readonly name: string
   ) {}
 
@@ -754,15 +743,15 @@ export class CreateProvisionedThroughputInferenceEndpointWaiter {
    *
    * Throws if a failure state is reached.
    */
-  async wait(options?: CallOptions): Promise<InferenceEndpointDetailed> {
+  async wait(options?: LroOptions): Promise<InferenceEndpointDetailed> {
     let result: InferenceEndpointDetailed | undefined;
 
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const pollResp = await this.client.getInferenceEndpoint(
         {
           name: this.name,
         },
-        {...options, ...(callSignal !== undefined && {signal: callSignal})}
+        callSignal !== undefined ? {signal: callSignal} : undefined
       );
 
       const status = pollResp.state?.configUpdate;
@@ -784,16 +773,9 @@ export class CreateProvisionedThroughputInferenceEndpointWaiter {
       }
     };
 
-    const retryOptions: CallOptions = {
-      ...(options?.signal !== undefined && {signal: options.signal}),
-      retrier: () =>
-        retryOn({}, (err: Error) => {
-          return err instanceof StillRunningError;
-        }),
-    };
-    await executeCall(call, retryOptions);
+    await executeWait(call, options);
     if (result === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return result;
   }
@@ -825,7 +807,7 @@ export class CreateProvisionedThroughputInferenceEndpointWaiter {
 
 export class PutInferenceEndpointConfigWaiter {
   constructor(
-    private readonly client: ModelservingClient,
+    private readonly client: ModelServingClient,
     readonly name: string
   ) {}
 
@@ -834,15 +816,15 @@ export class PutInferenceEndpointConfigWaiter {
    *
    * Throws if a failure state is reached.
    */
-  async wait(options?: CallOptions): Promise<InferenceEndpointDetailed> {
+  async wait(options?: LroOptions): Promise<InferenceEndpointDetailed> {
     let result: InferenceEndpointDetailed | undefined;
 
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const pollResp = await this.client.getInferenceEndpoint(
         {
           name: this.name,
         },
-        {...options, ...(callSignal !== undefined && {signal: callSignal})}
+        callSignal !== undefined ? {signal: callSignal} : undefined
       );
 
       const status = pollResp.state?.configUpdate;
@@ -864,16 +846,9 @@ export class PutInferenceEndpointConfigWaiter {
       }
     };
 
-    const retryOptions: CallOptions = {
-      ...(options?.signal !== undefined && {signal: options.signal}),
-      retrier: () =>
-        retryOn({}, (err: Error) => {
-          return err instanceof StillRunningError;
-        }),
-    };
-    await executeCall(call, retryOptions);
+    await executeWait(call, options);
     if (result === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return result;
   }
@@ -905,7 +880,7 @@ export class PutInferenceEndpointConfigWaiter {
 
 export class PutProvisionedThroughputInferenceEndpointConfigWaiter {
   constructor(
-    private readonly client: ModelservingClient,
+    private readonly client: ModelServingClient,
     readonly name: string
   ) {}
 
@@ -914,15 +889,15 @@ export class PutProvisionedThroughputInferenceEndpointConfigWaiter {
    *
    * Throws if a failure state is reached.
    */
-  async wait(options?: CallOptions): Promise<InferenceEndpointDetailed> {
+  async wait(options?: LroOptions): Promise<InferenceEndpointDetailed> {
     let result: InferenceEndpointDetailed | undefined;
 
-    const call: Call = async (callSignal?: AbortSignal): Promise<void> => {
+    const call = async (callSignal?: AbortSignal): Promise<void> => {
       const pollResp = await this.client.getInferenceEndpoint(
         {
           name: this.name,
         },
-        {...options, ...(callSignal !== undefined && {signal: callSignal})}
+        callSignal !== undefined ? {signal: callSignal} : undefined
       );
 
       const status = pollResp.state?.configUpdate;
@@ -944,16 +919,9 @@ export class PutProvisionedThroughputInferenceEndpointConfigWaiter {
       }
     };
 
-    const retryOptions: CallOptions = {
-      ...(options?.signal !== undefined && {signal: options.signal}),
-      retrier: () =>
-        retryOn({}, (err: Error) => {
-          return err instanceof StillRunningError;
-        }),
-    };
-    await executeCall(call, retryOptions);
+    await executeWait(call, options);
     if (result === undefined) {
-      throw new Error('API call completed without a result.');
+      throw new Error('operation completed without a result.');
     }
     return result;
   }