test_agent_loop() — langchain Function Reference

Architecture documentation for the test_agent_loop() function in chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_agent_loop() — langchain Function Reference

Dependency Diagram

graph TD
  849e274b_b44e_7cf4_2548_402b45a5fc07["test_agent_loop()"]
  971e928f_9c9b_ce7a_b93d_e762f2f5aa54["ChatModelIntegrationTests"]
  849e274b_b44e_7cf4_2548_402b45a5fc07 -->|defined in| 971e928f_9c9b_ce7a_b93d_e762f2f5aa54
  style 849e274b_b44e_7cf4_2548_402b45a5fc07 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/standard-tests/langchain_tests/integration_tests/chat_models.py lines 3233–3300

    def test_agent_loop(self, model: BaseChatModel) -> None:
        """Test that the model supports a simple ReAct agent loop.

        This test is skipped if the `has_tool_calling` property on the test class is
        set to `False`.

        This test is optional and should be skipped if the model does not support
        tool calling (see configuration below).

        ??? note "Configuration"

            To disable tool calling tests, set `has_tool_calling` to `False` in your
            test class:

            ```python
            class TestMyChatModelIntegration(ChatModelIntegrationTests):
                @property
                def has_tool_calling(self) -> bool:
                    return False
            ```

        ??? question "Troubleshooting"

            If this test fails, check that `bind_tools` is implemented to correctly
            translate LangChain tool objects into the appropriate schema for your
            chat model.

            Check also that all required information (e.g., tool calling identifiers)
            from `AIMessage` objects is propagated correctly to model payloads.

            This test may fail if the chat model does not consistently generate tool
            calls in response to an appropriate query. In these cases you can `xfail`
            the test:

            ```python
            @pytest.mark.xfail(reason=("Does not support tool_choice."))
            def test_agent_loop(self, model: BaseChatModel) -> None:
                super().test_agent_loop(model)
            ```

        """
        if not self.has_tool_calling:
            pytest.skip("Test requires tool calling.")

        @tool
        def get_weather(location: str) -> str:  # noqa: ARG001
            """Get the weather at a location."""
            return "It's sunny."

        llm_with_tools = model.bind_tools([get_weather])
        input_message = HumanMessage("What is the weather in San Francisco, CA?")
        tool_call_message = llm_with_tools.invoke([input_message])
        assert isinstance(tool_call_message, AIMessage)
        content_blocks = tool_call_message.content_blocks
        assert any(block["type"] == "tool_call" for block in content_blocks)
        tool_calls = tool_call_message.tool_calls
        assert len(tool_calls) == 1
        tool_call = tool_calls[0]
        tool_message = get_weather.invoke(tool_call)
        assert isinstance(tool_message, ToolMessage)
        response = llm_with_tools.invoke(
            [
                input_message,
                tool_call_message,
                tool_message,
            ]
        )
        assert isinstance(response, AIMessage)