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

test_streaming_with_cached_and_reasoning_tokens() — langchain Function Reference

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

Function python LangChainCore LanguageModelBase

Entity Profile

Dependency Diagram

graph TD
  2b99fe8b_016a_0350_75fa_818b4266f917["test_streaming_with_cached_and_reasoning_tokens()"]
  5bf2e477_37e0_3e98_4042_bc609f2f7f60["test_chat_models.py"]
  2b99fe8b_016a_0350_75fa_818b4266f917 -->|defined in| 5bf2e477_37e0_3e98_4042_bc609f2f7f60
  style 2b99fe8b_016a_0350_75fa_818b4266f917 fill:#6366f1,stroke:#818cf8,color:#fff

Relationship Graph

Source Code

libs/partners/groq/tests/unit_tests/test_chat_models.py lines 801–844

def test_streaming_with_cached_and_reasoning_tokens() -> None:
    """Test that streaming includes both cached and reasoning tokens."""
    chunk = {
        "id": "chatcmpl-123",
        "object": "chat.completion.chunk",
        "created": 1234567890,
        "model": "test-model",
        "choices": [
            {
                "index": 0,
                "delta": {
                    "role": "assistant",
                    "content": "Hello",
                },
                "finish_reason": None,
            }
        ],
        "x_groq": {
            "usage": {
                "prompt_tokens": 2006,
                "completion_tokens": 450,
                "total_tokens": 2456,
                "input_tokens_details": {"cached_tokens": 1920},
                "output_tokens_details": {"reasoning_tokens": 200},
            }
        },
    }

    result = _convert_chunk_to_message_chunk(chunk, AIMessageChunk)

    assert isinstance(result, AIMessageChunk)
    assert result.content == "Hello"

    assert result.usage_metadata is not None
    assert isinstance(result.usage_metadata, dict)
    assert result.usage_metadata["input_tokens"] == 2006
    assert result.usage_metadata["output_tokens"] == 450
    assert result.usage_metadata["total_tokens"] == 2456

    assert "input_token_details" in result.usage_metadata
    assert result.usage_metadata["input_token_details"]["cache_read"] == 1920

    assert "output_token_details" in result.usage_metadata
    assert result.usage_metadata["output_token_details"]["reasoning"] == 200

Domain

Subdomains

Defined In

Source

Frequently Asked Questions

What does test_streaming_with_cached_and_reasoning_tokens() do?
test_streaming_with_cached_and_reasoning_tokens() is a function in the langchain codebase, defined in libs/partners/groq/tests/unit_tests/test_chat_models.py.
Where is test_streaming_with_cached_and_reasoning_tokens() defined?
test_streaming_with_cached_and_reasoning_tokens() is defined in libs/partners/groq/tests/unit_tests/test_chat_models.py at line 801.

Analyze Your Own Codebase

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

Try Supermodel Free