letta-client 0.1.233__py3-none-any.whl → 0.1.234__py3-none-any.whl

letta_client/agents/messages/raw_client.py

@@ -0,0 +1,1384 @@
+# This file was auto-generated by Fern from our API Definition.
+
+import contextlib
+import json
+import typing
+from json.decoder import JSONDecodeError
+
+import httpx_sse
+from ...core.api_error import ApiError
+from ...core.client_wrapper import AsyncClientWrapper, SyncClientWrapper
+from ...core.http_response import AsyncHttpResponse, HttpResponse
+from ...core.jsonable_encoder import jsonable_encoder
+from ...core.request_options import RequestOptions
+from ...core.serialization import convert_and_respect_annotation_metadata
+from ...core.unchecked_base_model import construct_type
+from ...errors.unprocessable_entity_error import UnprocessableEntityError
+from ...types.agent_state import AgentState
+from ...types.http_validation_error import HttpValidationError
+from ...types.letta_message_union import LettaMessageUnion
+from ...types.letta_response import LettaResponse
+from ...types.message_create import MessageCreate
+from ...types.message_type import MessageType
+from ...types.run import Run
+from .types.letta_streaming_response import LettaStreamingResponse
+from .types.messages_modify_request import MessagesModifyRequest
+from .types.messages_modify_response import MessagesModifyResponse
+from .types.messages_preview_raw_payload_request import MessagesPreviewRawPayloadRequest
+
+# this is used as the default value for optional parameters
+OMIT = typing.cast(typing.Any, ...)
+
+
+class RawMessagesClient:
+    def __init__(self, *, client_wrapper: SyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    def list(
+        self,
+        agent_id: str,
+        *,
+        after: typing.Optional[str] = None,
+        before: typing.Optional[str] = None,
+        limit: typing.Optional[int] = None,
+        group_id: typing.Optional[str] = None,
+        use_assistant_message: typing.Optional[bool] = None,
+        assistant_message_tool_name: typing.Optional[str] = None,
+        assistant_message_tool_kwarg: typing.Optional[str] = None,
+        include_err: typing.Optional[bool] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[typing.List[LettaMessageUnion]]:
+        """
+        Retrieve message history for an agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        after : typing.Optional[str]
+            Message after which to retrieve the returned messages.
+
+        before : typing.Optional[str]
+            Message before which to retrieve the returned messages.
+
+        limit : typing.Optional[int]
+            Maximum number of messages to retrieve.
+
+        group_id : typing.Optional[str]
+            Group ID to filter messages by.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether to use assistant messages
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument.
+
+        include_err : typing.Optional[bool]
+            Whether to include error messages and error statuses. For debugging purposes only.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[typing.List[LettaMessageUnion]]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages",
+            method="GET",
+            params={
+                "after": after,
+                "before": before,
+                "limit": limit,
+                "group_id": group_id,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_err": include_err,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.List[LettaMessageUnion],
+                    construct_type(
+                        type_=typing.List[LettaMessageUnion],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def create(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[LettaResponse]:
+        """
+        Process a user message and return the agent's response.
+        This endpoint accepts a message from a user and processes it through the agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[LettaResponse]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    LettaResponse,
+                    construct_type(
+                        type_=LettaResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def modify(
+        self,
+        agent_id: str,
+        message_id: str,
+        *,
+        request: MessagesModifyRequest,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[MessagesModifyResponse]:
+        """
+        Update the details of a message associated with an agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        message_id : str
+
+        request : MessagesModifyRequest
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[MessagesModifyResponse]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/{jsonable_encoder(message_id)}",
+            method="PATCH",
+            json=convert_and_respect_annotation_metadata(
+                object_=request, annotation=MessagesModifyRequest, direction="write"
+            ),
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    MessagesModifyResponse,
+                    construct_type(
+                        type_=MessagesModifyResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.contextmanager
+    def create_stream(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        stream_tokens: typing.Optional[bool] = OMIT,
+        include_pings: typing.Optional[bool] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.Iterator[HttpResponse[typing.Iterator[LettaStreamingResponse]]]:
+        """
+        Process a user message and return the agent's response.
+        This endpoint accepts a message from a user and processes it through the agent.
+        It will stream the steps of the response always, and stream the tokens if 'stream_tokens' is set to True.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        stream_tokens : typing.Optional[bool]
+            Flag to determine if individual tokens should be streamed. Set to True for token streaming (requires stream_steps = True).
+
+        include_pings : typing.Optional[bool]
+            Whether to include periodic keepalive ping messages in the stream to prevent connection timeouts.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.Iterator[HttpResponse[typing.Iterator[LettaStreamingResponse]]]
+            Successful response
+        """
+        with self._client_wrapper.httpx_client.stream(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/stream",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+                "stream_tokens": stream_tokens,
+                "include_pings": include_pings,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            def _stream() -> HttpResponse[typing.Iterator[LettaStreamingResponse]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        def _iter():
+                            _event_source = httpx_sse.EventSource(_response)
+                            for _sse in _event_source.iter_sse():
+                                if _sse.data == None:
+                                    return
+                                try:
+                                    yield typing.cast(
+                                        LettaStreamingResponse,
+                                        construct_type(
+                                            type_=LettaStreamingResponse,  # type: ignore
+                                            object_=json.loads(_sse.data),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return HttpResponse(response=_response, data=_iter())
+                    _response.read()
+                    if _response.status_code == 422:
+                        raise UnprocessableEntityError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                HttpValidationError,
+                                construct_type(
+                                    type_=HttpValidationError,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    _response_json = _response.json()
+                except JSONDecodeError:
+                    raise ApiError(
+                        status_code=_response.status_code, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield _stream()
+
+    def cancel(
+        self,
+        agent_id: str,
+        *,
+        request: typing.Optional[typing.Sequence[str]] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]:
+        """
+        Cancel runs associated with an agent. If run_ids are passed in, cancel those in particular.
+
+        Note to cancel active runs associated with an agent, redis is required.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        request : typing.Optional[typing.Sequence[str]]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/cancel",
+            method="POST",
+            json=request,
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.Dict[str, typing.Optional[typing.Any]],
+                    construct_type(
+                        type_=typing.Dict[str, typing.Optional[typing.Any]],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def create_async(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        callback_url: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[Run]:
+        """
+        Asynchronously process a user message and return a run object.
+        The actual processing happens in the background, and the status can be checked using the run ID.
+
+        This is "asynchronous" in the sense that it's a background job and explicitly must be fetched by the run ID.
+        This is more like `send_message_job`
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        callback_url : typing.Optional[str]
+            Optional callback URL to POST to when the job completes
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[Run]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/async",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+                "callback_url": callback_url,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    Run,
+                    construct_type(
+                        type_=Run,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def reset(
+        self,
+        agent_id: str,
+        *,
+        add_default_initial_messages: typing.Optional[bool] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[AgentState]:
+        """
+        Resets the messages for an agent
+
+        Parameters
+        ----------
+        agent_id : str
+
+        add_default_initial_messages : typing.Optional[bool]
+            If true, adds the default initial messages after resetting.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[AgentState]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/reset-messages",
+            method="PATCH",
+            params={
+                "add_default_initial_messages": add_default_initial_messages,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    AgentState,
+                    construct_type(
+                        type_=AgentState,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    def preview_raw_payload(
+        self,
+        agent_id: str,
+        *,
+        request: MessagesPreviewRawPayloadRequest,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> HttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]:
+        """
+        Inspect the raw LLM request payload without sending it.
+
+        This endpoint processes the message through the agent loop up until
+        the LLM request, then returns the raw request payload that would
+        be sent to the LLM provider. Useful for debugging and inspection.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        request : MessagesPreviewRawPayloadRequest
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        HttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]
+            Successful Response
+        """
+        _response = self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/preview-raw-payload",
+            method="POST",
+            json=convert_and_respect_annotation_metadata(
+                object_=request, annotation=MessagesPreviewRawPayloadRequest, direction="write"
+            ),
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.Dict[str, typing.Optional[typing.Any]],
+                    construct_type(
+                        type_=typing.Dict[str, typing.Optional[typing.Any]],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return HttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+
+class AsyncRawMessagesClient:
+    def __init__(self, *, client_wrapper: AsyncClientWrapper):
+        self._client_wrapper = client_wrapper
+
+    async def list(
+        self,
+        agent_id: str,
+        *,
+        after: typing.Optional[str] = None,
+        before: typing.Optional[str] = None,
+        limit: typing.Optional[int] = None,
+        group_id: typing.Optional[str] = None,
+        use_assistant_message: typing.Optional[bool] = None,
+        assistant_message_tool_name: typing.Optional[str] = None,
+        assistant_message_tool_kwarg: typing.Optional[str] = None,
+        include_err: typing.Optional[bool] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[typing.List[LettaMessageUnion]]:
+        """
+        Retrieve message history for an agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        after : typing.Optional[str]
+            Message after which to retrieve the returned messages.
+
+        before : typing.Optional[str]
+            Message before which to retrieve the returned messages.
+
+        limit : typing.Optional[int]
+            Maximum number of messages to retrieve.
+
+        group_id : typing.Optional[str]
+            Group ID to filter messages by.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether to use assistant messages
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument.
+
+        include_err : typing.Optional[bool]
+            Whether to include error messages and error statuses. For debugging purposes only.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[typing.List[LettaMessageUnion]]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages",
+            method="GET",
+            params={
+                "after": after,
+                "before": before,
+                "limit": limit,
+                "group_id": group_id,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_err": include_err,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.List[LettaMessageUnion],
+                    construct_type(
+                        type_=typing.List[LettaMessageUnion],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def create(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[LettaResponse]:
+        """
+        Process a user message and return the agent's response.
+        This endpoint accepts a message from a user and processes it through the agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[LettaResponse]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    LettaResponse,
+                    construct_type(
+                        type_=LettaResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def modify(
+        self,
+        agent_id: str,
+        message_id: str,
+        *,
+        request: MessagesModifyRequest,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[MessagesModifyResponse]:
+        """
+        Update the details of a message associated with an agent.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        message_id : str
+
+        request : MessagesModifyRequest
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[MessagesModifyResponse]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/{jsonable_encoder(message_id)}",
+            method="PATCH",
+            json=convert_and_respect_annotation_metadata(
+                object_=request, annotation=MessagesModifyRequest, direction="write"
+            ),
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    MessagesModifyResponse,
+                    construct_type(
+                        type_=MessagesModifyResponse,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    @contextlib.asynccontextmanager
+    async def create_stream(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        stream_tokens: typing.Optional[bool] = OMIT,
+        include_pings: typing.Optional[bool] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[LettaStreamingResponse]]]:
+        """
+        Process a user message and return the agent's response.
+        This endpoint accepts a message from a user and processes it through the agent.
+        It will stream the steps of the response always, and stream the tokens if 'stream_tokens' is set to True.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        stream_tokens : typing.Optional[bool]
+            Flag to determine if individual tokens should be streamed. Set to True for token streaming (requires stream_steps = True).
+
+        include_pings : typing.Optional[bool]
+            Whether to include periodic keepalive ping messages in the stream to prevent connection timeouts.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Yields
+        ------
+        typing.AsyncIterator[AsyncHttpResponse[typing.AsyncIterator[LettaStreamingResponse]]]
+            Successful response
+        """
+        async with self._client_wrapper.httpx_client.stream(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/stream",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+                "stream_tokens": stream_tokens,
+                "include_pings": include_pings,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        ) as _response:
+
+            async def _stream() -> AsyncHttpResponse[typing.AsyncIterator[LettaStreamingResponse]]:
+                try:
+                    if 200 <= _response.status_code < 300:
+
+                        async def _iter():
+                            _event_source = httpx_sse.EventSource(_response)
+                            async for _sse in _event_source.aiter_sse():
+                                if _sse.data == None:
+                                    return
+                                try:
+                                    yield typing.cast(
+                                        LettaStreamingResponse,
+                                        construct_type(
+                                            type_=LettaStreamingResponse,  # type: ignore
+                                            object_=json.loads(_sse.data),
+                                        ),
+                                    )
+                                except Exception:
+                                    pass
+                            return
+
+                        return AsyncHttpResponse(response=_response, data=_iter())
+                    await _response.aread()
+                    if _response.status_code == 422:
+                        raise UnprocessableEntityError(
+                            headers=dict(_response.headers),
+                            body=typing.cast(
+                                HttpValidationError,
+                                construct_type(
+                                    type_=HttpValidationError,  # type: ignore
+                                    object_=_response.json(),
+                                ),
+                            ),
+                        )
+                    _response_json = _response.json()
+                except JSONDecodeError:
+                    raise ApiError(
+                        status_code=_response.status_code, headers=dict(_response.headers), body=_response.text
+                    )
+                raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+            yield await _stream()
+
+    async def cancel(
+        self,
+        agent_id: str,
+        *,
+        request: typing.Optional[typing.Sequence[str]] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]:
+        """
+        Cancel runs associated with an agent. If run_ids are passed in, cancel those in particular.
+
+        Note to cancel active runs associated with an agent, redis is required.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        request : typing.Optional[typing.Sequence[str]]
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/cancel",
+            method="POST",
+            json=request,
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.Dict[str, typing.Optional[typing.Any]],
+                    construct_type(
+                        type_=typing.Dict[str, typing.Optional[typing.Any]],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def create_async(
+        self,
+        agent_id: str,
+        *,
+        messages: typing.Sequence[MessageCreate],
+        max_steps: typing.Optional[int] = OMIT,
+        use_assistant_message: typing.Optional[bool] = OMIT,
+        assistant_message_tool_name: typing.Optional[str] = OMIT,
+        assistant_message_tool_kwarg: typing.Optional[str] = OMIT,
+        include_return_message_types: typing.Optional[typing.Sequence[MessageType]] = OMIT,
+        enable_thinking: typing.Optional[str] = OMIT,
+        callback_url: typing.Optional[str] = OMIT,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[Run]:
+        """
+        Asynchronously process a user message and return a run object.
+        The actual processing happens in the background, and the status can be checked using the run ID.
+
+        This is "asynchronous" in the sense that it's a background job and explicitly must be fetched by the run ID.
+        This is more like `send_message_job`
+
+        Parameters
+        ----------
+        agent_id : str
+
+        messages : typing.Sequence[MessageCreate]
+            The messages to be sent to the agent.
+
+        max_steps : typing.Optional[int]
+            Maximum number of steps the agent should take to process the request.
+
+        use_assistant_message : typing.Optional[bool]
+            Whether the server should parse specific tool call arguments (default `send_message`) as `AssistantMessage` objects.
+
+        assistant_message_tool_name : typing.Optional[str]
+            The name of the designated message tool.
+
+        assistant_message_tool_kwarg : typing.Optional[str]
+            The name of the message argument in the designated message tool.
+
+        include_return_message_types : typing.Optional[typing.Sequence[MessageType]]
+            Only return specified message types in the response. If `None` (default) returns all messages.
+
+        enable_thinking : typing.Optional[str]
+            If set to True, enables reasoning before responses or tool calls from the agent.
+
+        callback_url : typing.Optional[str]
+            Optional callback URL to POST to when the job completes
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[Run]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/async",
+            method="POST",
+            json={
+                "messages": convert_and_respect_annotation_metadata(
+                    object_=messages, annotation=typing.Sequence[MessageCreate], direction="write"
+                ),
+                "max_steps": max_steps,
+                "use_assistant_message": use_assistant_message,
+                "assistant_message_tool_name": assistant_message_tool_name,
+                "assistant_message_tool_kwarg": assistant_message_tool_kwarg,
+                "include_return_message_types": include_return_message_types,
+                "enable_thinking": enable_thinking,
+                "callback_url": callback_url,
+            },
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    Run,
+                    construct_type(
+                        type_=Run,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def reset(
+        self,
+        agent_id: str,
+        *,
+        add_default_initial_messages: typing.Optional[bool] = None,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[AgentState]:
+        """
+        Resets the messages for an agent
+
+        Parameters
+        ----------
+        agent_id : str
+
+        add_default_initial_messages : typing.Optional[bool]
+            If true, adds the default initial messages after resetting.
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[AgentState]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/reset-messages",
+            method="PATCH",
+            params={
+                "add_default_initial_messages": add_default_initial_messages,
+            },
+            request_options=request_options,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    AgentState,
+                    construct_type(
+                        type_=AgentState,  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)
+
+    async def preview_raw_payload(
+        self,
+        agent_id: str,
+        *,
+        request: MessagesPreviewRawPayloadRequest,
+        request_options: typing.Optional[RequestOptions] = None,
+    ) -> AsyncHttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]:
+        """
+        Inspect the raw LLM request payload without sending it.
+
+        This endpoint processes the message through the agent loop up until
+        the LLM request, then returns the raw request payload that would
+        be sent to the LLM provider. Useful for debugging and inspection.
+
+        Parameters
+        ----------
+        agent_id : str
+
+        request : MessagesPreviewRawPayloadRequest
+
+        request_options : typing.Optional[RequestOptions]
+            Request-specific configuration.
+
+        Returns
+        -------
+        AsyncHttpResponse[typing.Dict[str, typing.Optional[typing.Any]]]
+            Successful Response
+        """
+        _response = await self._client_wrapper.httpx_client.request(
+            f"v1/agents/{jsonable_encoder(agent_id)}/messages/preview-raw-payload",
+            method="POST",
+            json=convert_and_respect_annotation_metadata(
+                object_=request, annotation=MessagesPreviewRawPayloadRequest, direction="write"
+            ),
+            headers={
+                "content-type": "application/json",
+            },
+            request_options=request_options,
+            omit=OMIT,
+        )
+        try:
+            if 200 <= _response.status_code < 300:
+                _data = typing.cast(
+                    typing.Dict[str, typing.Optional[typing.Any]],
+                    construct_type(
+                        type_=typing.Dict[str, typing.Optional[typing.Any]],  # type: ignore
+                        object_=_response.json(),
+                    ),
+                )
+                return AsyncHttpResponse(response=_response, data=_data)
+            if _response.status_code == 422:
+                raise UnprocessableEntityError(
+                    headers=dict(_response.headers),
+                    body=typing.cast(
+                        HttpValidationError,
+                        construct_type(
+                            type_=HttpValidationError,  # type: ignore
+                            object_=_response.json(),
+                        ),
+                    ),
+                )
+            _response_json = _response.json()
+        except JSONDecodeError:
+            raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response.text)
+        raise ApiError(status_code=_response.status_code, headers=dict(_response.headers), body=_response_json)