llama-stack-mirror/llama_stack/testing
Matthew Farrellee b0364572b2 chore(replay): improve replay robustness with un-validated construction
some providers do not produce spec compliant outputs. when this happens
the replay infra will fail to construct the proper types and will return
a dict to the client. the client likely does not expect a dict.

this was discovered with tgi, which returns finish_reason="" when valid
values are "stop", "length" or "content_filter"
2025-09-11 01:01:01 -04:00
..
__init__.py feat(tests): introduce inference record/replay to increase test reliability (#2941) 2025-07-29 12:41:31 -07:00
inference_recorder.py chore(replay): improve replay robustness with un-validated construction 2025-09-11 01:01:01 -04:00