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

.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/openai/resources/beta/assistants.py

@@ -61,6 +61,7 @@ def create(
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_create_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -97,6 +98,13 @@ def create(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -155,6 +163,7 @@ def create(
                     "instructions": instructions,
                     "metadata": metadata,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -210,8 +219,42 @@ def update(
         description: Optional[str] | NotGiven = NOT_GIVEN,
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
-        model: str | NotGiven = NOT_GIVEN,
+        model: Union[
+            str,
+            Literal[
+                "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",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -249,6 +292,13 @@ def update(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -309,6 +359,7 @@ def update(
                     "metadata": metadata,
                     "model": model,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -451,6 +502,7 @@ async def create(
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_create_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -487,6 +539,13 @@ async def create(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -545,6 +604,7 @@ async def create(
                     "instructions": instructions,
                     "metadata": metadata,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,
@@ -600,8 +660,42 @@ async def update(
         description: Optional[str] | NotGiven = NOT_GIVEN,
         instructions: Optional[str] | NotGiven = NOT_GIVEN,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
-        model: str | NotGiven = NOT_GIVEN,
+        model: Union[
+            str,
+            Literal[
+                "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",
+            ],
+        ]
+        | NotGiven = NOT_GIVEN,
         name: Optional[str] | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_resources: Optional[assistant_update_params.ToolResources] | NotGiven = NOT_GIVEN,
@@ -639,6 +733,13 @@ async def update(
 
           name: The name of the assistant. The maximum length is 256 characters.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -699,6 +800,7 @@ async def update(
                     "metadata": metadata,
                     "model": model,
                     "name": name,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "temperature": temperature,
                     "tool_resources": tool_resources,

src/openai/resources/beta/threads/runs/runs.py

@@ -85,6 +85,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -153,6 +154,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -228,6 +236,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -299,6 +308,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -370,6 +386,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -441,6 +458,13 @@ def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -511,6 +535,7 @@ def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -541,6 +566,7 @@ def create(
                     "metadata": metadata,
                     "model": model,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "stream": stream,
                     "temperature": temperature,
@@ -941,6 +967,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -1009,6 +1036,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1084,6 +1118,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -1155,6 +1190,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1226,6 +1268,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
         tool_choice: Optional[AssistantToolChoiceOptionParam] | NotGiven = NOT_GIVEN,
@@ -1297,6 +1340,13 @@ async def create(
               [parallel function calling](https://platform.openai.com/docs/guides/function-calling#configuring-parallel-function-calling)
               during tool use.
 
+          reasoning_effort: **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.
+
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
               [GPT-4 Turbo](https://platform.openai.com/docs/models#gpt-4-turbo-and-gpt-4),
@@ -1367,6 +1417,7 @@ async def create(
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         model: Union[str, ChatModel, None] | NotGiven = NOT_GIVEN,
         parallel_tool_calls: bool | NotGiven = NOT_GIVEN,
+        reasoning_effort: Optional[Literal["low", "medium", "high"]] | NotGiven = NOT_GIVEN,
         response_format: Optional[AssistantResponseFormatOptionParam] | NotGiven = NOT_GIVEN,
         stream: Optional[Literal[False]] | Literal[True] | NotGiven = NOT_GIVEN,
         temperature: Optional[float] | NotGiven = NOT_GIVEN,
@@ -1397,6 +1448,7 @@ async def create(
                     "metadata": metadata,
                     "model": model,
                     "parallel_tool_calls": parallel_tool_calls,
+                    "reasoning_effort": reasoning_effort,
                     "response_format": response_format,
                     "stream": stream,
                     "temperature": temperature,