_make_tool() — langchain Function Reference

Architecture documentation for the _make_tool() function in test_responses_spec.py from the langchain codebase.

Function python LangChainCore MessageInterface called by 1

Entity Profile

LangChainCore→ MessageInterface→ _make_tool() — langchain Function Reference

Dependency Diagram

graph TD
  99d8fafd_9703_0e81_2299_11884efd897a["_make_tool()"]
  e8aafd1b_21af_e716_6b31_14e1cb032faa["test_responses_spec.py"]
  99d8fafd_9703_0e81_2299_11884efd897a -->|defined in| e8aafd1b_21af_e716_6b31_14e1cb032faa
  7f729c04_c50c_2eea_c486_67a2676c7829["test_responses_integration_matrix()"]
  7f729c04_c50c_2eea_c486_67a2676c7829 -->|calls| 99d8fafd_9703_0e81_2299_11884efd897a
  style 99d8fafd_9703_0e81_2299_11884efd897a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/test_responses_spec.py lines 70–78

def _make_tool(fn: Callable[..., str | None], *, name: str, description: str) -> dict[str, Any]:
    mock = MagicMock(side_effect=lambda *, name: fn(name=name))
    input_model = create_model(f"{name}_input", name=(str, ...))

    @tool(name, description=description, args_schema=input_model)
    def _wrapped(name: str) -> Any:
        return mock(name=name)

    return {"tool": _wrapped, "mock": mock}