phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-09 21:18:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions
llama-stack-mirror/tests/integration/recordings
History
Ashwin Bharambe 3f36bfaeaa
chore(tests): normalize recording IDs and timestamps to reduce git diff noise (#3676) 
IDs are now deterministic hashes based on request content, and
timestamps are normalized to constants, eliminating spurious changes
when re-recording tests.

## Changes
- Updated `inference_recorder.py` to normalize IDs and timestamps during
recording
- Added `scripts/normalize_recordings.py` utility to re-normalize
existing recordings
- Created documentation in `tests/integration/recordings/README.md`
- Normalized 350 existing recording files
2025-10-03 17:26:11 -07:00
..
responses chore(tests): normalize recording IDs and timestamps to reduce git diff noise (#3676) 2025-10-03 17:26:11 -07:00
README.md chore(tests): normalize recording IDs and timestamps to reduce git diff noise (#3676) 2025-10-03 17:26:11 -07:00
test.txt feat(ci): add support for running vision inference tests (#2972) 2025-07-31 11:50:42 -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

Recording mode

Set LLAMA_STACK_TEST_INFERENCE_MODE=record to capture new responses:

LLAMA_STACK_TEST_INFERENCE_MODE=record pytest tests/integration/

Replay mode (default)

Responses are replayed from recordings:

LLAMA_STACK_TEST_INFERENCE_MODE=replay 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.