Home / Function/ test_no_max_tools_uses_all_selected() — langchain Function Reference

test_no_max_tools_uses_all_selected() — langchain Function Reference

Architecture documentation for the test_no_max_tools_uses_all_selected() function in test_tool_selection.py from the langchain codebase.

Entity Profile

Dependency Diagram

graph TD
  6bb118a7_e9ab_3138_028a_96ace800c797["test_no_max_tools_uses_all_selected()"]
  f414d4bb_d578_5e97_a076_b6127f4f90dd["TestMaxToolsLimiting"]
  6bb118a7_e9ab_3138_028a_96ace800c797 -->|defined in| f414d4bb_d578_5e97_a076_b6127f4f90dd
  style 6bb118a7_e9ab_3138_028a_96ace800c797 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_tool_selection.py lines 273–334

    def test_no_max_tools_uses_all_selected(self) -> None:
        """Test that when max_tools is None, all selected tools are used."""
        model_requests = []

        @wrap_model_call
        def trace_model_requests(
            request: ModelRequest, handler: Callable[[ModelRequest], ModelResponse]
        ) -> ModelResponse:
            model_requests.append(request)
            return handler(request)

        tool_selection_model = FakeModel(
            messages=cycle(
                [
                    AIMessage(
                        content="",
                        tool_calls=[
                            {
                                "name": "ToolSelectionResponse",
                                "id": "1",
                                "args": {
                                    "tools": [
                                        "get_weather",
                                        "search_web",
                                        "calculate",
                                        "get_stock_price",
                                    ]
                                },
                            }
                        ],
                    ),
                ]
            )
        )

        model = FakeModel(messages=iter([AIMessage(content="Done")]))

        # No max_tools specified
        tool_selector = LLMToolSelectorMiddleware(model=tool_selection_model)

        agent = create_agent(
            model=model,
            tools=[get_weather, search_web, calculate, send_email, get_stock_price],
            middleware=[tool_selector, trace_model_requests],
        )

        agent.invoke({"messages": [HumanMessage("test")]})

        # All 4 selected tools should be present
        assert len(model_requests) > 0
        for request in model_requests:
            assert len(request.tools) == 4
            tool_names = []
            for tool_ in request.tools:
                assert isinstance(tool_, BaseTool)
                tool_names.append(tool_.name)
            assert set(tool_names) == {
                "get_weather",
                "search_web",
                "calculate",
                "get_stock_price",
            }

Domain

Subdomains

Frequently Asked Questions

What does test_no_max_tools_uses_all_selected() do?
test_no_max_tools_uses_all_selected() is a function in the langchain codebase, defined in libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_tool_selection.py.
Where is test_no_max_tools_uses_all_selected() defined?
test_no_max_tools_uses_all_selected() is defined in libs/langchain_v1/tests/unit_tests/agents/middleware/implementations/test_tool_selection.py at line 273.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free