fix(api): correct some Responses types

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 81
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-c8579861bc21d4d2155a5b9e8e7d54faee8083730673c4d32cbbe573d7fb4116.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-f763c1a35c8b9b02f1e31b9b2e09e21f98bfe8413e5079c86cbb07da2dd7779b.yml

src/resources/batches.ts

@@ -220,11 +220,11 @@ export interface BatchCreateParams {
 
   /**
    * The endpoint to be used for all requests in the batch. Currently
-   * `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions` are supported.
-   * Note that `/v1/embeddings` batches are also restricted to a maximum of 50,000
-   * embedding inputs across all requests in the batch.
+   * `/v1/responses`, `/v1/chat/completions`, `/v1/embeddings`, and `/v1/completions`
+   * are supported. Note that `/v1/embeddings` batches are also restricted to a
+   * maximum of 50,000 embedding inputs across all requests in the batch.
    */
-  endpoint: '/v1/chat/completions' | '/v1/embeddings' | '/v1/completions';
+  endpoint: '/v1/responses' | '/v1/chat/completions' | '/v1/embeddings' | '/v1/completions';
 
   /**
    * The ID of an uploaded file that contains requests for the new batch.

src/resources/chat/completions/completions.ts

@@ -377,10 +377,13 @@ export interface ChatCompletionChunk {
   /**
    * An optional field that will only be present when you set
    * `stream_options: {"include_usage": true}` in your request. When present, it
-   * contains a null value except for the last chunk which contains the token usage
-   * statistics for the entire request.
+   * contains a null value **except for the last chunk** which contains the token
+   * usage statistics for the entire request.
+   *
+   * **NOTE:** If the stream is interrupted or cancelled, you may not receive the
+   * final usage chunk which contains the total token usage for the request.
    */
-  usage?: CompletionsAPI.CompletionUsage | null;
+  usage?: CompletionsAPI.CompletionUsage;
 }
 
 export namespace ChatCompletionChunk {
@@ -551,7 +554,7 @@ export namespace ChatCompletionContentPart {
       /**
        * The name of the file, used when passing the file to the model as a string.
        */
-      file_name?: string;
+      filename?: string;
     }
   }
 }
@@ -930,8 +933,11 @@ export interface ChatCompletionStreamOptions {
   /**
    * If set, an additional chunk will be streamed before the `data: [DONE]` message.
    * The `usage` field on this chunk shows the token usage statistics for the entire
-   * request, and the `choices` field will always be an empty array. All other chunks
-   * will also include a `usage` field, but with a null value.
+   * request, and the `choices` field will always be an empty array.
+   *
+   * All other chunks will also include a `usage` field, but with a null value.
+   * **NOTE:** If the stream is interrupted, you may not receive the final usage
+   * chunk which contains the total token usage for the request.
    */
   include_usage?: boolean;
 }

src/resources/responses/responses.ts

@@ -1298,11 +1298,6 @@ export interface ResponseFunctionCallArgumentsDoneEvent {
  * for more information.
  */
 export interface ResponseFunctionToolCall {
-  /**
-   * The unique ID of the function tool call.
-   */
-  id: string;
-
   /**
    * A JSON string of the arguments to pass to the function.
    */
@@ -1323,6 +1318,11 @@ export interface ResponseFunctionToolCall {
    */
   type: 'function_call';
 
+  /**
+   * The unique ID of the function tool call.
+   */
+  id?: string;
+
   /**
    * The status of the item. One of `in_progress`, `completed`, or `incomplete`.
    * Populated when items are returned via API.
@@ -2241,6 +2241,11 @@ export interface ResponseUsage {
    */
   input_tokens: number;
 
+  /**
+   * A detailed breakdown of the input tokens.
+   */
+  input_tokens_details: ResponseUsage.InputTokensDetails;
+
   /**
    * The number of output tokens.
    */
@@ -2258,6 +2263,17 @@ export interface ResponseUsage {
 }
 
 export namespace ResponseUsage {
+  /**
+   * A detailed breakdown of the input tokens.
+   */
+  export interface InputTokensDetails {
+    /**
+     * The number of tokens that were retrieved from the cache.
+     * [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching).
+     */
+    cached_tokens: number;
+  }
+
   /**
    * A detailed breakdown of the output tokens.
    */

src/resources/shared.ts

@@ -171,10 +171,10 @@ export interface Reasoning {
    * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
    * result in faster responses and fewer tokens used on reasoning in a response.
    */
-  effort: ReasoningEffort | null;
+  effort?: ReasoningEffort | null;
 
   /**
-   * **o-series models only**
+   * **computer_use_preview only**
    *
    * A summary of the reasoning performed by the model. This can be useful for
    * debugging and understanding the model's reasoning process. One of `concise` or

tests/api-resources/batches.test.ts

@@ -12,7 +12,7 @@ describe('resource batches', () => {
   test('create: only required params', async () => {
     const responsePromise = client.batches.create({
       completion_window: '24h',
-      endpoint: '/v1/chat/completions',
+      endpoint: '/v1/responses',
       input_file_id: 'input_file_id',
     });
     const rawResponse = await responsePromise.asResponse();
@@ -27,7 +27,7 @@ describe('resource batches', () => {
   test('create: required and optional params', async () => {
     const response = await client.batches.create({
       completion_window: '24h',
-      endpoint: '/v1/chat/completions',
+      endpoint: '/v1/responses',
       input_file_id: 'input_file_id',
       metadata: { foo: 'string' },
     });