test_agent_tool_return_direct() — langchain Function Reference

Architecture documentation for the test_agent_tool_return_direct() function in test_agent.py from the langchain codebase.

Function python LangChainCore Runnables

Entity Profile

LangChainCore→ Runnables→ test_agent_tool_return_direct() — langchain Function Reference

Dependency Diagram

graph TD
  ca756be3_835d_6412_c888_717773e675a1["test_agent_tool_return_direct()"]
  47a7b285_8e60_f78f_282d_429958c446fa["test_agent.py"]
  ca756be3_835d_6412_c888_717773e675a1 -->|defined in| 47a7b285_8e60_f78f_282d_429958c446fa
  style ca756be3_835d_6412_c888_717773e675a1 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain/tests/unit_tests/agents/test_agent.py lines 316–339

def test_agent_tool_return_direct() -> None:
    """Test agent using tools that return directly."""
    tool = "Search"
    responses = [
        f"FooBarBaz\nAction: {tool}\nAction Input: misalignment",
        "Oh well\nFinal Answer: curses foiled again",
    ]
    fake_llm = FakeListLLM(responses=responses)
    tools = [
        Tool(
            name="Search",
            func=lambda x: x,
            description="Useful for searching",
            return_direct=True,
        ),
    ]
    agent = initialize_agent(
        tools,
        fake_llm,
        agent=AgentType.ZERO_SHOT_REACT_DESCRIPTION,
    )

    output = agent.run("when was langchain made")
    assert output == "misalignment"