mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-06-29 19:34:19 +00:00
07a992ef90
Summary: 1. The `tools` parameter we construct to pass the inference API is non-deterministic. As a result, our recordable mocks is flaky as the ordering change sometimes. This PR makes it so that `tools` ordering is deterministic and aligned with the order user specified. 2. In recordable mock key generation, client tool's parameter type was 'str' and now is 'string' for some reason. I didn't dig into exactly why, but just regenerated the fixtures. Test Plan: Regenerate mocks: ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B --record-responses ``` Rerun tests without --record-responses: ``` LLAMA_STACK_CONFIG=fireworks pytest -s -v tests/client-sdk/agents/test_agents.py --safety-shield meta-llama/Llama-Guard-3-8B ``` |
||
|---|---|---|
| .. | ||
| agents | ||
| datasetio | ||
| eval | ||
| inference | ||
| ios/inference | ||
| post_training | ||
| safety | ||
| scoring | ||
| telemetry | ||
| tool_runtime | ||
| vector_io | ||
| __init__.py | ||