langgraph_agent_toolkit.agents.components.middlewares.immediate_generation module

Middleware that requests a direct answer near the model-call limit.

class langgraph_agent_toolkit.agents.components.middlewares.immediate_generation.ImmediateGenerationMiddleware(model_call_limit=None, instruction=None)

Bases: AgentMiddleware

Request a direct answer on the last allowed model call.

The middleware removes tools and adds an instruction to the system message. It keeps tool results so the model can use collected data. The budget counts AI messages after the latest human message.

Parameters:

• model_call_limit (int | None)

• instruction (str | None)

__init__(model_call_limit=None, instruction=None)

Parameters:

• model_call_limit (int | None)

• instruction (str | None)

Return type:

None

wrap_model_call(request, handler)

Parameters:

• request (ModelRequest)

• handler (Callable[[ModelRequest], ModelResponse])

Return type:

ModelResponse

async awrap_model_call(request, handler)

Parameters:

• request (ModelRequest)

• handler (Callable[[ModelRequest], Awaitable[ModelResponse]])

Return type:

ModelResponse