test_reasoning_aggregation() — langchain Function Reference

Architecture documentation for the test_reasoning_aggregation() function in test_llms.py from the langchain codebase.

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test_reasoning_aggregation() — langchain Function Reference

Dependency Diagram

graph TD
  8cb149d9_e5ca_328b_8c35_264f19425c18["test_reasoning_aggregation()"]
  92c74082_b175_00d9_ee08_72212a280d77["test_llms.py"]
  8cb149d9_e5ca_328b_8c35_264f19425c18 -->|defined in| 92c74082_b175_00d9_ee08_72212a280d77
  style 8cb149d9_e5ca_328b_8c35_264f19425c18 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/ollama/tests/unit_tests/test_llms.py lines 49–67

def test_reasoning_aggregation() -> None:
    """Test that reasoning chunks are aggregated into final response."""
    llm = OllamaLLM(model=MODEL_NAME, reasoning=True)
    prompts = ["some prompt"]
    mock_stream = [
        {"thinking": "I am thinking.", "done": False},
        {"thinking": " Still thinking.", "done": False},
        {"response": "Final Answer.", "done": True},
    ]

    with patch.object(llm, "_create_generate_stream") as mock_stream_method:
        mock_stream_method.return_value = iter(mock_stream)
        result = llm.generate(prompts)

    assert result.generations[0][0].generation_info is not None
    assert (
        result.generations[0][0].generation_info["thinking"]
        == "I am thinking. Still thinking."
    )