(async) Update the system prompt and filter tools based on backend capabilities.
Also evicts oversized HumanMessages to the filesystem. See
wrap_model_call for full documentation.
awrap_model_call(
self,
request: ModelRequest[ContextT],
handler: Callable[[ModelRequest[ContextT]], Awaitable[ModelResponse[ResponseT]]]
) -> ModelResponse[ResponseT] | ExtendedModelResponse| Name | Type | Description |
|---|---|---|
request* | ModelRequest[ContextT] | The model request being processed. |
handler* | Callable[[ModelRequest[ContextT]], Awaitable[ModelResponse[ResponseT]]] | The handler function to call with the modified request. |