test_reasoning_effort_streaming() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_reasoning_effort_streaming() — langchain Function Reference

Dependency Diagram

graph TD
  cd20eeee_6d11_6b67_ea94_1d447708ca85["test_reasoning_effort_streaming()"]
  af57ae60_607e_c138_9ab0_fb8bb1c5916a["test_chat_models.py"]
  cd20eeee_6d11_6b67_ea94_1d447708ca85 -->|defined in| af57ae60_607e_c138_9ab0_fb8bb1c5916a
  style cd20eeee_6d11_6b67_ea94_1d447708ca85 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/groq/tests/integration_tests/test_chat_models.py lines 341–360

def test_reasoning_effort_streaming() -> None:
    """Test that reasoning_effort is captured in streaming response metadata."""
    chat = ChatGroq(
        model=DEFAULT_MODEL_NAME,
        reasoning_effort="medium",
    )
    message = HumanMessage(content="What is the capital of France?")

    chunks = list(chat.stream([message]))
    assert len(chunks) > 0

    # Find the final chunk with finish_reason
    final_chunk = None
    for chunk in chunks:
        if chunk.response_metadata.get("finish_reason"):
            final_chunk = chunk
            break

    assert final_chunk is not None
    assert final_chunk.response_metadata.get("reasoning_effort") == "medium"