fix(api): add missing reasoning effort + model enums (#1302)

.stats.yml

@@ -1,2 +1,2 @@
 configured_endpoints: 69
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-fc5dbc19505b0035f9e7f88868619f4fb519b048bde011f6154f3132d4be71fb.yml
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai-7c699d4503077d06a4a44f52c0c1f902d19a87c766b8be75b97c8dfd484ad4aa.yml

src/resources/beta/assistants.ts

@@ -1133,6 +1133,16 @@ export interface AssistantCreateParams {
    */
   name?: string | null;
 
+  /**
+   * **o1 and o3-mini models only**
+   *
+   * Constrains effort on reasoning for
+   * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+   * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+   * result in faster responses and fewer tokens used on reasoning in a response.
+   */
+  reasoning_effort?: 'low' | 'medium' | 'high' | null;
+
   /**
    * Specifies the format that the model must output. Compatible with
    * [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -1288,13 +1298,52 @@ export interface AssistantUpdateParams {
    * [Model overview](https://platform.openai.com/docs/models) for descriptions of
    * them.
    */
-  model?: string;
+  model?:
+    | (string & {})
+    | 'o3-mini'
+    | 'o3-mini-2025-01-31'
+    | 'o1'
+    | 'o1-2024-12-17'
+    | 'gpt-4o'
+    | 'gpt-4o-2024-11-20'
+    | 'gpt-4o-2024-08-06'
+    | 'gpt-4o-2024-05-13'
+    | 'gpt-4o-mini'
+    | 'gpt-4o-mini-2024-07-18'
+    | 'gpt-4-turbo'
+    | 'gpt-4-turbo-2024-04-09'
+    | 'gpt-4-0125-preview'
+    | 'gpt-4-turbo-preview'
+    | 'gpt-4-1106-preview'
+    | 'gpt-4-vision-preview'
+    | 'gpt-4'
+    | 'gpt-4-0314'
+    | 'gpt-4-0613'
+    | 'gpt-4-32k'
+    | 'gpt-4-32k-0314'
+    | 'gpt-4-32k-0613'
+    | 'gpt-3.5-turbo'
+    | 'gpt-3.5-turbo-16k'
+    | 'gpt-3.5-turbo-0613'
+    | 'gpt-3.5-turbo-1106'
+    | 'gpt-3.5-turbo-0125'
+    | 'gpt-3.5-turbo-16k-0613';
 
   /**
    * The name of the assistant. The maximum length is 256 characters.
    */
   name?: string | null;
 
+  /**
+   * **o1 and o3-mini models only**
+   *
+   * Constrains effort on reasoning for
+   * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+   * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+   * result in faster responses and fewer tokens used on reasoning in a response.
+   */
+  reasoning_effort?: 'low' | 'medium' | 'high' | null;
+
   /**
    * Specifies the format that the model must output. Compatible with
    * [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),

src/resources/beta/threads/runs/runs.ts

@@ -731,6 +731,16 @@ export interface RunCreateParamsBase {
    */
   parallel_tool_calls?: boolean;
 
+  /**
+   * Body param: **o1 and o3-mini models only**
+   *
+   * Constrains effort on reasoning for
+   * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
+   * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
+   * result in faster responses and fewer tokens used on reasoning in a response.
+   */
+  reasoning_effort?: 'low' | 'medium' | 'high' | null;
+
   /**
    * Body param: Specifies the format that the model must output. Compatible with
    * [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),

src/resources/chat/completions.ts

@@ -744,14 +744,14 @@ export interface ChatCompletionPredictionContent {
 }
 
 /**
- * **o1 models only**
+ * **o1 and o3-mini models only**
  *
  * Constrains effort on reasoning for
  * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
  * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
  * result in faster responses and fewer tokens used on reasoning in a response.
  */
-export type ChatCompletionReasoningEffort = 'low' | 'medium' | 'high';
+export type ChatCompletionReasoningEffort = 'low' | 'medium' | 'high' | null;
 
 /**
  * The role of the author of a message
@@ -1063,14 +1063,14 @@ export interface ChatCompletionCreateParamsBase {
   presence_penalty?: number | null;
 
   /**
-   * **o1 models only**
+   * **o1 and o3-mini models only**
    *
    * Constrains effort on reasoning for
    * [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
    * supported values are `low`, `medium`, and `high`. Reducing reasoning effort can
    * result in faster responses and fewer tokens used on reasoning in a response.
    */
-  reasoning_effort?: ChatCompletionReasoningEffort;
+  reasoning_effort?: ChatCompletionReasoningEffort | null;
 
   /**
    * An object specifying the format that the model must output.

tests/api-resources/beta/assistants.test.ts

@@ -27,6 +27,7 @@ describe('resource assistants', () => {
       instructions: 'instructions',
       metadata: { foo: 'string' },
       name: 'name',
+      reasoning_effort: 'low',
       response_format: 'auto',
       temperature: 1,
       tool_resources: {

tests/api-resources/beta/threads/runs/runs.test.ts

@@ -39,6 +39,7 @@ describe('resource runs', () => {
       metadata: { foo: 'string' },
       model: 'gpt-4o',
       parallel_tool_calls: true,
+      reasoning_effort: 'low',
       response_format: 'auto',
       stream: false,
       temperature: 1,