test_context_management() — langchain Function Reference

Architecture documentation for the test_context_management() function in test_chat_models.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_context_management() — langchain Function Reference

Dependency Diagram

graph TD
  9857cff8_6c23_436c_8b3b_346ed45d1a6a["test_context_management()"]
  f27640dd_3870_5548_d153_f9504ae1021f["test_chat_models.py"]
  9857cff8_6c23_436c_8b3b_346ed45d1a6a -->|defined in| f27640dd_3870_5548_d153_f9504ae1021f
  style 9857cff8_6c23_436c_8b3b_346ed45d1a6a fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/tests/integration_tests/test_chat_models.py lines 2046–2075

def test_context_management() -> None:
    # TODO: update example to trigger action
    llm = ChatAnthropic(
        model="claude-sonnet-4-5-20250929",  # type: ignore[call-arg]
        betas=["context-management-2025-06-27"],
        context_management={
            "edits": [
                {
                    "type": "clear_tool_uses_20250919",
                    "trigger": {"type": "input_tokens", "value": 10},
                    "clear_at_least": {"type": "input_tokens", "value": 5},
                }
            ]
        },
        max_tokens=1024,  # type: ignore[call-arg]
    )
    llm_with_tools = llm.bind_tools(
        [{"type": "web_search_20250305", "name": "web_search"}]
    )
    input_message = {"role": "user", "content": "Search for recent developments in AI"}
    response = llm_with_tools.invoke([input_message])
    assert response.response_metadata.get("context_management")

    # Test streaming
    full: BaseMessageChunk | None = None
    for chunk in llm_with_tools.stream([input_message]):
        assert isinstance(chunk, AIMessageChunk)
        full = chunk if full is None else full + chunk
    assert isinstance(full, AIMessageChunk)
    assert full.response_metadata.get("context_management")