test__format_output_cached() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

LangChainCore→ LanguageModelBase→ test__format_output_cached() — langchain Function Reference

Dependency Diagram

graph TD
  e8f16cbb_279d_6f62_63eb_b2487d32cb0d["test__format_output_cached()"]
  18428dc5_a41b_90c6_88ad_615296ee3311["test_chat_models.py"]
  e8f16cbb_279d_6f62_63eb_b2487d32cb0d -->|defined in| 18428dc5_a41b_90c6_88ad_615296ee3311
  style e8f16cbb_279d_6f62_63eb_b2487d32cb0d fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/tests/unit_tests/test_chat_models.py lines 223–252

def test__format_output_cached() -> None:
    anthropic_msg = Message(
        id="foo",
        content=[TextBlock(type="text", text="bar")],
        model="baz",
        role="assistant",
        stop_reason=None,
        stop_sequence=None,
        usage=Usage(
            input_tokens=2,
            output_tokens=1,
            cache_creation_input_tokens=3,
            cache_read_input_tokens=4,
        ),
        type="message",
    )
    expected = AIMessage(  # type: ignore[misc]
        "bar",
        usage_metadata={
            "input_tokens": 9,
            "output_tokens": 1,
            "total_tokens": 10,
            "input_token_details": {"cache_creation": 3, "cache_read": 4},
        },
        response_metadata={"model_provider": "anthropic"},
    )

    llm = ChatAnthropic(model=MODEL_NAME, anthropic_api_key="test")  # type: ignore[call-arg, call-arg]
    actual = llm._format_output(anthropic_msg)
    assert actual.generations[0].message == expected