Home / Function/ test_tool_runtime_with_store() — langchain Function Reference

test_tool_runtime_with_store() — langchain Function Reference

Architecture documentation for the test_tool_runtime_with_store() function in test_injected_runtime_create_agent.py from the langchain codebase.

Entity Profile

Dependency Diagram

graph TD
  9c25eccb_7873_1816_c5f7_bc0aa9488b83["test_tool_runtime_with_store()"]
  a4d83fe9_0a39_5761_b1a5_de54f81974c9["test_injected_runtime_create_agent.py"]
  9c25eccb_7873_1816_c5f7_bc0aa9488b83 -->|defined in| a4d83fe9_0a39_5761_b1a5_de54f81974c9
  style 9c25eccb_7873_1816_c5f7_bc0aa9488b83 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/langchain_v1/tests/unit_tests/agents/test_injected_runtime_create_agent.py lines 153–196

def test_tool_runtime_with_store() -> None:
    """Test ToolRuntime provides access to store."""
    # Note: create_agent doesn't currently expose a store parameter,
    # so runtime.store will be None in this test.
    # This test demonstrates the runtime injection works correctly.

    @tool
    def store_tool(key: str, value: str, runtime: ToolRuntime) -> str:
        """Tool that uses store."""
        if runtime.store is None:
            return f"No store (key={key}, value={value})"
        runtime.store.put(("test",), key, {"data": value})
        return f"Stored {key}={value}"

    @tool
    def check_runtime_tool(runtime: ToolRuntime) -> str:
        """Tool that checks runtime availability."""
        has_store = runtime.store is not None
        has_context = runtime.context is not None
        return f"Runtime: store={has_store}, context={has_context}"

    agent = create_agent(
        model=FakeToolCallingModel(
            tool_calls=[
                [{"args": {"key": "foo", "value": "bar"}, "id": "call_1", "name": "store_tool"}],
                [{"args": {}, "id": "call_2", "name": "check_runtime_tool"}],
                [],
            ]
        ),
        tools=[store_tool, check_runtime_tool],
        system_prompt="You are a helpful assistant.",
    )

    result = agent.invoke({"messages": [HumanMessage("Test store")]})

    # Find the tool messages
    tool_messages = [msg for msg in result["messages"] if isinstance(msg, ToolMessage)]
    assert len(tool_messages) == 2

    # First tool indicates no store is available (expected since create_agent doesn't expose store)
    assert "No store" in tool_messages[0].content

    # Second tool confirms runtime was injected
    assert "Runtime:" in tool_messages[1].content

Domain

Subdomains

Frequently Asked Questions

What does test_tool_runtime_with_store() do?
test_tool_runtime_with_store() is a function in the langchain codebase, defined in libs/langchain_v1/tests/unit_tests/agents/test_injected_runtime_create_agent.py.
Where is test_tool_runtime_with_store() defined?
test_tool_runtime_with_store() is defined in libs/langchain_v1/tests/unit_tests/agents/test_injected_runtime_create_agent.py at line 153.

Analyze Your Own Codebase

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

Try Supermodel Free