chore(internal): codegen related update (#2222)

Author: stainless-app[bot]

.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/openai/resources/batches.py

@@ -49,7 +49,7 @@ def create(
         self,
         *,
         completion_window: Literal["24h"],
-        endpoint: Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
+        endpoint: Literal["/v1/responses", "/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
         input_file_id: str,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -67,9 +67,9 @@ def create(
               is supported.
 
           endpoint: 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.
 
           input_file_id: The ID of an uploaded file that contains requests for the new batch.
 
@@ -259,7 +259,7 @@ async def create(
         self,
         *,
         completion_window: Literal["24h"],
-        endpoint: Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
+        endpoint: Literal["/v1/responses", "/v1/chat/completions", "/v1/embeddings", "/v1/completions"],
         input_file_id: str,
         metadata: Optional[Metadata] | NotGiven = NOT_GIVEN,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
@@ -277,9 +277,9 @@ async def create(
               is supported.
 
           endpoint: 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.
 
           input_file_id: The ID of an uploaded file that contains requests for the new batch.
 

src/openai/types/batch_create_params.py

@@ -17,12 +17,13 @@ class BatchCreateParams(TypedDict, total=False):
     Currently only `24h` is supported.
     """
 
-    endpoint: Required[Literal["/v1/chat/completions", "/v1/embeddings", "/v1/completions"]]
+    endpoint: Required[Literal["/v1/responses", "/v1/chat/completions", "/v1/embeddings", "/v1/completions"]]
     """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.
+    Currently `/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.
     """
 
     input_file_id: Required[str]

src/openai/types/chat/chat_completion_chunk.py

@@ -142,6 +142,9 @@ class ChatCompletionChunk(BaseModel):
     """
     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.
     """

src/openai/types/chat/chat_completion_content_part_param.py

@@ -22,7 +22,7 @@ class FileFile(TypedDict, total=False):
     file_id: str
     """The ID of an uploaded file to use as input."""
 
-    file_name: str
+    filename: str
     """The name of the file, used when passing the file to the model as a string."""
 
 

src/openai/types/chat/chat_completion_stream_options_param.py

@@ -12,6 +12,9 @@ class ChatCompletionStreamOptionsParam(TypedDict, total=False):
     """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.
     """

src/openai/types/responses/response_function_tool_call.py

@@ -9,9 +9,6 @@
 
 
 class ResponseFunctionToolCall(BaseModel):
-    id: str
-    """The unique ID of the function tool call."""
-
     arguments: str
     """A JSON string of the arguments to pass to the function."""
 
@@ -24,6 +21,9 @@ class ResponseFunctionToolCall(BaseModel):
     type: Literal["function_call"]
     """The type of the function tool call. Always `function_call`."""
 
+    id: Optional[str] = None
+    """The unique ID of the function tool call."""
+
     status: Optional[Literal["in_progress", "completed", "incomplete"]] = None
     """The status of the item.
 

src/openai/types/responses/response_function_tool_call_param.py

@@ -8,9 +8,6 @@
 
 
 class ResponseFunctionToolCallParam(TypedDict, total=False):
-    id: Required[str]
-    """The unique ID of the function tool call."""
-
     arguments: Required[str]
     """A JSON string of the arguments to pass to the function."""
 
@@ -23,6 +20,9 @@ class ResponseFunctionToolCallParam(TypedDict, total=False):
     type: Required[Literal["function_call"]]
     """The type of the function tool call. Always `function_call`."""
 
+    id: str
+    """The unique ID of the function tool call."""
+
     status: Literal["in_progress", "completed", "incomplete"]
     """The status of the item.
 

src/openai/types/responses/response_usage.py

@@ -3,7 +3,15 @@
 
 from ..._models import BaseModel
 
-__all__ = ["ResponseUsage", "OutputTokensDetails"]
+__all__ = ["ResponseUsage", "InputTokensDetails", "OutputTokensDetails"]
+
+
+class InputTokensDetails(BaseModel):
+    cached_tokens: int
+    """The number of tokens that were retrieved from the cache.
+
+    [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching).
+    """
 
 
 class OutputTokensDetails(BaseModel):
@@ -15,6 +23,9 @@ class ResponseUsage(BaseModel):
     input_tokens: int
     """The number of input tokens."""
 
+    input_tokens_details: InputTokensDetails
+    """A detailed breakdown of the input tokens."""
+
     output_tokens: int
     """The number of output tokens."""
 

src/openai/types/shared/reasoning.py

@@ -20,7 +20,7 @@ class Reasoning(BaseModel):
     """
 
     generate_summary: Optional[Literal["concise", "detailed"]] = None
-    """**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

src/openai/types/shared_params/reasoning.py

@@ -3,15 +3,15 @@
 from __future__ import annotations
 
 from typing import Optional
-from typing_extensions import Literal, Required, TypedDict
+from typing_extensions import Literal, TypedDict
 
 from ..shared.reasoning_effort import ReasoningEffort
 
 __all__ = ["Reasoning"]
 
 
 class Reasoning(TypedDict, total=False):
-    effort: Required[Optional[ReasoningEffort]]
+    effort: Optional[ReasoningEffort]
     """**o-series models only**
 
     Constrains effort on reasoning for
@@ -21,7 +21,7 @@ class Reasoning(TypedDict, total=False):
     """
 
     generate_summary: Optional[Literal["concise", "detailed"]]
-    """**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/test_batches.py

@@ -22,7 +22,7 @@ class TestBatches:
     def test_method_create(self, client: OpenAI) -> None:
         batch = client.batches.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         )
         assert_matches_type(Batch, batch, path=["response"])
@@ -31,7 +31,7 @@ def test_method_create(self, client: OpenAI) -> None:
     def test_method_create_with_all_params(self, client: OpenAI) -> None:
         batch = client.batches.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
             metadata={"foo": "string"},
         )
@@ -41,7 +41,7 @@ def test_method_create_with_all_params(self, client: OpenAI) -> None:
     def test_raw_response_create(self, client: OpenAI) -> None:
         response = client.batches.with_raw_response.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         )
 
@@ -54,7 +54,7 @@ def test_raw_response_create(self, client: OpenAI) -> None:
     def test_streaming_response_create(self, client: OpenAI) -> None:
         with client.batches.with_streaming_response.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         ) as response:
             assert not response.is_closed
@@ -182,7 +182,7 @@ class TestAsyncBatches:
     async def test_method_create(self, async_client: AsyncOpenAI) -> None:
         batch = await async_client.batches.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         )
         assert_matches_type(Batch, batch, path=["response"])
@@ -191,7 +191,7 @@ async def test_method_create(self, async_client: AsyncOpenAI) -> None:
     async def test_method_create_with_all_params(self, async_client: AsyncOpenAI) -> None:
         batch = await async_client.batches.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
             metadata={"foo": "string"},
         )
@@ -201,7 +201,7 @@ async def test_method_create_with_all_params(self, async_client: AsyncOpenAI) ->
     async def test_raw_response_create(self, async_client: AsyncOpenAI) -> None:
         response = await async_client.batches.with_raw_response.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         )
 
@@ -214,7 +214,7 @@ async def test_raw_response_create(self, async_client: AsyncOpenAI) -> None:
     async def test_streaming_response_create(self, async_client: AsyncOpenAI) -> None:
         async with async_client.batches.with_streaming_response.create(
             completion_window="24h",
-            endpoint="/v1/chat/completions",
+            endpoint="/v1/responses",
             input_file_id="string",
         ) as response:
             assert not response.is_closed