wrap_model_call() — langchain Function Reference

Architecture documentation for the wrap_model_call() function in test_tools.py from the langchain codebase.

Function python LangChainCore MessageInterface

Entity Profile

LangChainCore→ MessageInterface→ wrap_model_call() — langchain Function Reference

Dependency Diagram

graph TD
  ae17189e_bd91_c921_d9b9_73a242000716["wrap_model_call()"]
  89d098ea_5f4d_da21_9f80_e8b591806e1e["ToolFilteringMiddleware"]
  ae17189e_bd91_c921_d9b9_73a242000716 -->|defined in| 89d098ea_5f4d_da21_9f80_e8b591806e1e
  style ae17189e_bd91_c921_d9b9_73a242000716 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/middleware/core/test_tools.py lines 92–103

        def wrap_model_call(
            self,
            request: ModelRequest,
            handler: Callable[[ModelRequest], ModelResponse],
        ) -> ModelCallResult:
            # Only allow tool_a and tool_b
            filtered_tools: list[BaseTool | dict[str, Any]] = []
            for t in request.tools:
                assert isinstance(t, BaseTool)
                if t.name in {"tool_a", "tool_b"}:
                    filtered_tools.append(t)
            return handler(request.override(tools=filtered_tools))