增加环绕侦察场景适配

backend_service/venv/lib/python3.13/site-packages/openai/_base_client.py

@@ -1264,9 +1264,12 @@ class SyncAPIClient(BaseClient[httpx.Client, Stream[Any]]):
         *,
         cast_to: Type[ResponseT],
         body: Body | None = None,
+        files: RequestFiles | None = None,
         options: RequestOptions = {},
     ) -> ResponseT:
-        opts = FinalRequestOptions.construct(method="patch", url=path, json_data=body, **options)
+        opts = FinalRequestOptions.construct(
+            method="patch", url=path, json_data=body, files=to_httpx_files(files), **options
+        )
         return self.request(cast_to, opts)
 
     def put(
@@ -1799,9 +1802,12 @@ class AsyncAPIClient(BaseClient[httpx.AsyncClient, AsyncStream[Any]]):
         *,
         cast_to: Type[ResponseT],
         body: Body | None = None,
+        files: RequestFiles | None = None,
         options: RequestOptions = {},
     ) -> ResponseT:
-        opts = FinalRequestOptions.construct(method="patch", url=path, json_data=body, **options)
+        opts = FinalRequestOptions.construct(
+            method="patch", url=path, json_data=body, files=await async_to_httpx_files(files), **options
+        )
         return await self.request(cast_to, opts)
 
     async def put(

backend_service/venv/lib/python3.13/site-packages/openai/_streaming.py

@@ -55,49 +55,51 @@ class Stream(Generic[_T]):
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
+        try:
+            for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
 
-            # we have to special case the Assistants `thread.` events since we won't have an "event" key in the data
-            if sse.event and sse.event.startswith("thread."):
-                data = sse.json()
+                # we have to special case the Assistants `thread.` events since we won't have an "event" key in the data
+                if sse.event and sse.event.startswith("thread."):
+                    data = sse.json()
 
-                if sse.event == "error" and is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
+                    if sse.event == "error" and is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
 
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
 
-                yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
-            else:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
+                    yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
+                else:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
 
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
 
-                yield process_data(data=data, cast_to=cast_to, response=response)
+                    yield process_data(data=data, cast_to=cast_to, response=response)
 
-        # As we might not fully consume the response stream, we need to close it explicitly
-        response.close()
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            response.close()
 
     def __enter__(self) -> Self:
         return self
@@ -156,49 +158,51 @@ class AsyncStream(Generic[_T]):
         process_data = self._client._process_response_data
         iterator = self._iter_events()
 
-        async for sse in iterator:
-            if sse.data.startswith("[DONE]"):
-                break
+        try:
+            async for sse in iterator:
+                if sse.data.startswith("[DONE]"):
+                    break
 
-            # we have to special case the Assistants `thread.` events since we won't have an "event" key in the data
-            if sse.event and sse.event.startswith("thread."):
-                data = sse.json()
+                # we have to special case the Assistants `thread.` events since we won't have an "event" key in the data
+                if sse.event and sse.event.startswith("thread."):
+                    data = sse.json()
 
-                if sse.event == "error" and is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
+                    if sse.event == "error" and is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
 
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
 
-                yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
-            else:
-                data = sse.json()
-                if is_mapping(data) and data.get("error"):
-                    message = None
-                    error = data.get("error")
-                    if is_mapping(error):
-                        message = error.get("message")
-                    if not message or not isinstance(message, str):
-                        message = "An error occurred during streaming"
+                    yield process_data(data={"data": data, "event": sse.event}, cast_to=cast_to, response=response)
+                else:
+                    data = sse.json()
+                    if is_mapping(data) and data.get("error"):
+                        message = None
+                        error = data.get("error")
+                        if is_mapping(error):
+                            message = error.get("message")
+                        if not message or not isinstance(message, str):
+                            message = "An error occurred during streaming"
 
-                    raise APIError(
-                        message=message,
-                        request=self.response.request,
-                        body=data["error"],
-                    )
+                        raise APIError(
+                            message=message,
+                            request=self.response.request,
+                            body=data["error"],
+                        )
 
-                yield process_data(data=data, cast_to=cast_to, response=response)
+                    yield process_data(data=data, cast_to=cast_to, response=response)
 
-        # As we might not fully consume the response stream, we need to close it explicitly
-        await response.aclose()
+        finally:
+            # Ensure the response is closed even if the consumer doesn't read all data
+            await response.aclose()
 
     async def __aenter__(self) -> Self:
         return self

backend_service/venv/lib/python3.13/site-packages/openai/_types.py

@@ -247,6 +247,9 @@ _T_co = TypeVar("_T_co", covariant=True)
 if TYPE_CHECKING:
     # This works because str.__contains__ does not accept object (either in typeshed or at runtime)
     # https://github.com/hauntsaninja/useful_types/blob/5e9710f3875107d068e7679fd7fec9cfab0eff3b/useful_types/__init__.py#L285
+    #
+    # Note: index() and count() methods are intentionally omitted to allow pyright to properly
+    # infer TypedDict types when dict literals are used in lists assigned to SequenceNotStr.
     class SequenceNotStr(Protocol[_T_co]):
         @overload
         def __getitem__(self, index: SupportsIndex, /) -> _T_co: ...
@@ -255,8 +258,6 @@ if TYPE_CHECKING:
         def __contains__(self, value: object, /) -> bool: ...
         def __len__(self) -> int: ...
         def __iter__(self) -> Iterator[_T_co]: ...
-        def index(self, value: Any, start: int = 0, stop: int = ..., /) -> int: ...
-        def count(self, value: Any, /) -> int: ...
         def __reversed__(self) -> Iterator[_T_co]: ...
 else:
     # just point this to a normal `Sequence` at runtime to avoid having to special case

backend_service/venv/lib/python3.13/site-packages/openai/_version.py

@@ -1,4 +1,4 @@
 # File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
 
 __title__ = "openai"
-__version__ = "2.8.0"  # x-release-please-version
+__version__ = "2.14.0"  # x-release-please-version

backend_service/venv/lib/python3.13/site-packages/openai/lib/_parsing/_responses.py

@@ -103,6 +103,7 @@ def parse_response(
             or output.type == "file_search_call"
             or output.type == "web_search_call"
             or output.type == "reasoning"
+            or output.type == "compaction"
             or output.type == "mcp_call"
             or output.type == "mcp_approval_request"
             or output.type == "image_generation_call"

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/speech.py

@@ -72,7 +72,7 @@ class Speech(SyncAPIResource):
 
           model:
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+              `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
               `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and
@@ -168,7 +168,7 @@ class AsyncSpeech(AsyncAPIResource):
 
           model:
               One of the available [TTS models](https://platform.openai.com/docs/models#tts):
-              `tts-1`, `tts-1-hd` or `gpt-4o-mini-tts`.
+              `tts-1`, `tts-1-hd`, `gpt-4o-mini-tts`, or `gpt-4o-mini-tts-2025-12-15`.
 
           voice: The voice to use when generating the audio. Supported voices are `alloy`, `ash`,
               `ballad`, `coral`, `echo`, `fable`, `onyx`, `nova`, `sage`, `shimmer`, and

backend_service/venv/lib/python3.13/site-packages/openai/resources/audio/transcriptions.py

@@ -91,8 +91,9 @@ class Transcriptions(SyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, and `whisper-1` (which is powered by our open source
-              Whisper V2 model).
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           chunking_strategy: Controls how the audio is cut into chunks. When set to `"auto"`, the server
               first normalizes loudness and then uses voice activity detection (VAD) to choose
@@ -102,8 +103,9 @@ class Transcriptions(SyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           language: The language of the input audio. Supplying the input language in
               [ISO-639-1](https://en.wikipedia.org/wiki/List_of_ISO_639-1_codes) (e.g. `en`)
@@ -239,8 +241,9 @@ class Transcriptions(SyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -261,9 +264,9 @@ class Transcriptions(SyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -346,8 +349,9 @@ class Transcriptions(SyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -368,9 +372,9 @@ class Transcriptions(SyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -535,8 +539,9 @@ class AsyncTranscriptions(AsyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           chunking_strategy: Controls how the audio is cut into chunks. When set to `"auto"`, the server
               first normalizes loudness and then uses voice activity detection (VAD) to choose
@@ -548,9 +553,9 @@ class AsyncTranscriptions(AsyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -679,8 +684,9 @@ class AsyncTranscriptions(AsyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -701,9 +707,9 @@ class AsyncTranscriptions(AsyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for
@@ -786,8 +792,9 @@ class AsyncTranscriptions(AsyncAPIResource):
               flac, mp3, mp4, mpeg, mpga, m4a, ogg, wav, or webm.
 
           model: ID of the model to use. The options are `gpt-4o-transcribe`,
-              `gpt-4o-mini-transcribe`, `whisper-1` (which is powered by our open source
-              Whisper V2 model), and `gpt-4o-transcribe-diarize`.
+              `gpt-4o-mini-transcribe`, `gpt-4o-mini-transcribe-2025-12-15`, `whisper-1`
+              (which is powered by our open source Whisper V2 model), and
+              `gpt-4o-transcribe-diarize`.
 
           stream: If set to true, the model response data will be streamed to the client as it is
               generated using
@@ -808,9 +815,9 @@ class AsyncTranscriptions(AsyncAPIResource):
           include: Additional information to include in the transcription response. `logprobs` will
               return the log probabilities of the tokens in the response to understand the
               model's confidence in the transcription. `logprobs` only works with
-              response_format set to `json` and only with the models `gpt-4o-transcribe` and
-              `gpt-4o-mini-transcribe`. This field is not supported when using
-              `gpt-4o-transcribe-diarize`.
+              response_format set to `json` and only with the models `gpt-4o-transcribe`,
+              `gpt-4o-mini-transcribe`, and `gpt-4o-mini-transcribe-2025-12-15`. This field is
+              not supported when using `gpt-4o-transcribe-diarize`.
 
           known_speaker_names: Optional list of speaker names that correspond to the audio samples provided in
               `known_speaker_references[]`. Each entry should be a short identifier (for

backend_service/venv/lib/python3.13/site-packages/openai/resources/beta/assistants.py

@@ -98,9 +98,9 @@ class Assistants(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -108,6 +108,7 @@ class Assistants(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -312,9 +313,9 @@ class Assistants(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -322,6 +323,7 @@ class Assistants(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -565,9 +567,9 @@ class AsyncAssistants(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -575,6 +577,7 @@ class AsyncAssistants(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -779,9 +782,9 @@ class AsyncAssistants(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -789,6 +792,7 @@ class AsyncAssistants(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),

backend_service/venv/lib/python3.13/site-packages/openai/resources/beta/threads/runs/runs.py

@@ -169,9 +169,9 @@ class Runs(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -179,6 +179,7 @@ class Runs(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -330,9 +331,9 @@ class Runs(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -340,6 +341,7 @@ class Runs(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -487,9 +489,9 @@ class Runs(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -497,6 +499,7 @@ class Runs(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -1620,9 +1623,9 @@ class AsyncRuns(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -1630,6 +1633,7 @@ class AsyncRuns(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -1781,9 +1785,9 @@ class AsyncRuns(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -1791,6 +1795,7 @@ class AsyncRuns(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),
@@ -1938,9 +1943,9 @@ class AsyncRuns(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -1948,6 +1953,7 @@ class AsyncRuns(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: Specifies the format that the model must output. Compatible with
               [GPT-4o](https://platform.openai.com/docs/models#gpt-4o),

backend_service/venv/lib/python3.13/site-packages/openai/resources/chat/completions/completions.py

@@ -411,9 +411,9 @@ class Completions(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -421,6 +421,7 @@ class Completions(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 
@@ -721,9 +722,9 @@ class Completions(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -731,6 +732,7 @@ class Completions(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 
@@ -1022,9 +1024,9 @@ class Completions(SyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -1032,6 +1034,7 @@ class Completions(SyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 
@@ -1894,9 +1897,9 @@ class AsyncCompletions(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -1904,6 +1907,7 @@ class AsyncCompletions(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 
@@ -2204,9 +2208,9 @@ class AsyncCompletions(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -2214,6 +2218,7 @@ class AsyncCompletions(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 
@@ -2505,9 +2510,9 @@ class AsyncCompletions(AsyncAPIResource):
 
           reasoning_effort: Constrains effort on reasoning for
               [reasoning models](https://platform.openai.com/docs/guides/reasoning). Currently
-              supported values are `none`, `minimal`, `low`, `medium`, and `high`. Reducing
-              reasoning effort can result in faster responses and fewer tokens used on
-              reasoning in a response.
+              supported values are `none`, `minimal`, `low`, `medium`, `high`, and `xhigh`.
+              Reducing reasoning effort can result in faster responses and fewer tokens used
+              on reasoning in a response.
 
               - `gpt-5.1` defaults to `none`, which does not perform reasoning. The supported
                 reasoning values for `gpt-5.1` are `none`, `low`, `medium`, and `high`. Tool
@@ -2515,6 +2520,7 @@ class AsyncCompletions(AsyncAPIResource):
               - All models before `gpt-5.1` default to `medium` reasoning effort, and do not
                 support `none`.
               - The `gpt-5-pro` model defaults to (and only supports) `high` reasoning effort.
+              - `xhigh` is supported for all models after `gpt-5.1-codex-max`.
 
           response_format: An object specifying the format that the model must output.
 

backend_service/venv/lib/python3.13/site-packages/openai/resources/containers/containers.py

@@ -60,6 +60,7 @@ class Containers(SyncAPIResource):
         name: str,
         expires_after: container_create_params.ExpiresAfter | Omit = omit,
         file_ids: SequenceNotStr[str] | Omit = omit,
+        memory_limit: Literal["1g", "4g", "16g", "64g"] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -77,6 +78,8 @@ class Containers(SyncAPIResource):
 
           file_ids: IDs of files to copy to the container.
 
+          memory_limit: Optional memory limit for the container. Defaults to "1g".
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -92,6 +95,7 @@ class Containers(SyncAPIResource):
                     "name": name,
                     "expires_after": expires_after,
                     "file_ids": file_ids,
+                    "memory_limit": memory_limit,
                 },
                 container_create_params.ContainerCreateParams,
             ),
@@ -256,6 +260,7 @@ class AsyncContainers(AsyncAPIResource):
         name: str,
         expires_after: container_create_params.ExpiresAfter | Omit = omit,
         file_ids: SequenceNotStr[str] | Omit = omit,
+        memory_limit: Literal["1g", "4g", "16g", "64g"] | Omit = omit,
         # Use the following arguments if you need to pass additional parameters to the API that aren't available via kwargs.
         # The extra values given here take precedence over values defined on the client or passed to this method.
         extra_headers: Headers | None = None,
@@ -273,6 +278,8 @@ class AsyncContainers(AsyncAPIResource):
 
           file_ids: IDs of files to copy to the container.
 
+          memory_limit: Optional memory limit for the container. Defaults to "1g".
+
           extra_headers: Send extra headers
 
           extra_query: Add additional query parameters to the request
@@ -288,6 +295,7 @@ class AsyncContainers(AsyncAPIResource):
                     "name": name,
                     "expires_after": expires_after,
                     "file_ids": file_ids,
+                    "memory_limit": memory_limit,
                 },
                 container_create_params.ContainerCreateParams,
             ),