phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-14 04:42:41 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/tests/integration/recordings
History
Matthew Farrellee fd06717d87 chore: make OpenAIMixin maintainable, turn OpenAIMixin into a pydantic.BaseModel 
- implement get_api_key instead of relying on LiteLLMOpenAIMixin.get_api_key
 - remove use of LiteLLMOpenAIMixin
 - add default initialize/shutdown methods to OpenAIMixin
 - remove __init__s to allow proper pydantic construction
 - remove dead code from vllm adapter and associated / duplicate unit tests
 - update vllm adapter to use openaimixin for model registration
 - remove ModelRegistryHelper from fireworks & together adapters
 - remove Inference from nvidia adapter
 - complete type hints on embedding_model_metadata
 - allow extra fields on OpenAIMixin, for model_store, __provider_id__, etc
 - new recordings for ollama
 - enhance the list models error handling w/ new tests
 - update cerebras (remove cerebras-cloud-sdk) and anthropic (custom model listing) inference adapters
 - parametrized test_inference_client_caching
 - remove cerebras, databricks, fireworks, together from blanket mypy exclude
2025-10-05 07:31:19 -04:00
..
responses chore: make OpenAIMixin maintainable, turn OpenAIMixin into a pydantic.BaseModel 2025-10-05 07:31:19 -04:00
README.md feat(tests): implement test isolation for inference recordings (#3681) 2025-10-04 11:34:18 -07:00

README.md

Test Recording System

This directory contains recorded inference API responses used for deterministic testing without requiring live API access.

Structure

  • responses/ - JSON files containing request/response pairs for inference operations

Recording Format

Each JSON file contains:

  • request - The normalized request parameters (method, endpoint, body)
  • response - The response body (serialized from Pydantic models)

Normalization

To reduce noise in git diffs, the recording system automatically normalizes fields that vary between runs but don't affect test behavior:

OpenAI-style responses

  • id - Deterministic hash based on request: rec-{request_hash[:12]}
  • created - Normalized to epoch: 0

Ollama-style responses

  • created_at - Normalized to: "1970-01-01T00:00:00.000000Z"
  • total_duration - Normalized to: 0
  • load_duration - Normalized to: 0
  • prompt_eval_duration - Normalized to: 0
  • eval_duration - Normalized to: 0

These normalizations ensure that re-recording tests produces minimal git diffs, making it easier to review actual changes to test behavior.

Usage

Replay mode (default)

Responses are replayed from recordings:

LLAMA_STACK_TEST_INFERENCE_MODE=replay pytest tests/integration/

Record-if-missing mode (recommended for adding new tests)

Records only when no recording exists, otherwise replays. Use this for iterative development:

LLAMA_STACK_TEST_INFERENCE_MODE=record-if-missing pytest tests/integration/

Recording mode

Force-records all API interactions, overwriting existing recordings. Use with caution:

LLAMA_STACK_TEST_INFERENCE_MODE=record pytest tests/integration/

Live mode

Skip recordings entirely and use live APIs:

LLAMA_STACK_TEST_INFERENCE_MODE=live pytest tests/integration/

Re-normalizing Existing Recordings

If you need to apply normalization to existing recordings (e.g., after updating the normalization logic):

python scripts/normalize_recordings.py

Use --dry-run to preview changes without modifying files.