test_reasoning_effort_none() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_reasoning_effort_none() — langchain Function Reference

Dependency Diagram

graph TD
  a0681f7f_ab9b_0d1a_bb8c_fc63f85815e0["test_reasoning_effort_none()"]
  af57ae60_607e_c138_9ab0_fb8bb1c5916a["test_chat_models.py"]
  a0681f7f_ab9b_0d1a_bb8c_fc63f85815e0 -->|defined in| af57ae60_607e_c138_9ab0_fb8bb1c5916a
  style a0681f7f_ab9b_0d1a_bb8c_fc63f85815e0 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/groq/tests/integration_tests/test_chat_models.py lines 276–287

def test_reasoning_effort_none() -> None:
    """Test that no reasoning output is returned if effort is set to none."""
    chat = ChatGroq(
        model="qwen/qwen3-32b",  # Only qwen3 currently supports reasoning_effort = none
        reasoning_effort="none",
    )
    message = HumanMessage(content="What is the capital of France?")
    response = chat.invoke([message])
    assert isinstance(response, AIMessage)
    assert "reasoning_content" not in response.additional_kwargs
    assert "<think>" not in response.content
    assert "<think/>" not in response.content