langchain Architecture Docs
Home / Function/ test_usage_metadata_standardization() — langchain Function Reference

test_usage_metadata_standardization() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

Dependency Diagram

graph TD
  830f5232_cbf7_415c_45ac_36a68c3f176f["test_usage_metadata_standardization()"]
  18428dc5_a41b_90c6_88ad_615296ee3311["test_chat_models.py"]
  830f5232_cbf7_415c_45ac_36a68c3f176f -->|defined in| 18428dc5_a41b_90c6_88ad_615296ee3311
  style 830f5232_cbf7_415c_45ac_36a68c3f176f fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/anthropic/tests/unit_tests/test_chat_models.py lines 1387–1423

def test_usage_metadata_standardization() -> None:
    class UsageModel(BaseModel):
        input_tokens: int = 10
        output_tokens: int = 5
        cache_read_input_tokens: int = 3
        cache_creation_input_tokens: int = 2

    # Happy path
    usage = UsageModel()
    result = _create_usage_metadata(usage)
    assert result["input_tokens"] == 15  # 10 + 3 + 2
    assert result["output_tokens"] == 5
    assert result["total_tokens"] == 20
    assert result.get("input_token_details") == {"cache_read": 3, "cache_creation": 2}

    # Null input and output tokens
    class UsageModelNulls(BaseModel):
        input_tokens: int | None = None
        output_tokens: int | None = None
        cache_read_input_tokens: int | None = None
        cache_creation_input_tokens: int | None = None

    usage_nulls = UsageModelNulls()
    result = _create_usage_metadata(usage_nulls)
    assert result["input_tokens"] == 0
    assert result["output_tokens"] == 0
    assert result["total_tokens"] == 0

    # Test missing fields
    class UsageModelMissing(BaseModel):
        pass

    usage_missing = UsageModelMissing()
    result = _create_usage_metadata(usage_missing)
    assert result["input_tokens"] == 0
    assert result["output_tokens"] == 0
    assert result["total_tokens"] == 0

Domain

Subdomains

Defined In

Source

Frequently Asked Questions

What does test_usage_metadata_standardization() do?
test_usage_metadata_standardization() is a function in the langchain codebase, defined in libs/partners/anthropic/tests/unit_tests/test_chat_models.py.
Where is test_usage_metadata_standardization() defined?
test_usage_metadata_standardization() is defined in libs/partners/anthropic/tests/unit_tests/test_chat_models.py at line 1387.

Analyze Your Own Codebase

Get architecture documentation, dependency graphs, and domain analysis for your codebase in minutes.

Try Supermodel Free