llama-stack-mirror/llama_stack
Matthew Farrellee c2d281e01b
chore(replay): improve replay robustness with un-validated construction (#3414)
# What does this PR do?

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"

## Test Plan

ci
2025-09-11 13:48:19 +02:00
..
apis feat: Adding OpenAI Prompts API (#3319) 2025-09-08 11:05:13 -04:00
cli feat: include a default inference store during llama stack build (#3373) 2025-09-09 15:54:58 -07:00
core chore: introduce write queue for inference_store (#3383) 2025-09-10 11:57:42 -07:00
distributions fix: Fix locations of distrubution runtime directories (#3336) 2025-09-05 14:09:36 +02:00
models refactor(logging): rename llama_stack logger categories (#3065) 2025-08-21 17:31:04 -07:00
providers fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386) 2025-09-11 11:41:53 +02:00
strong_typing chore: enable pyupgrade fixes (#1806) 2025-05-01 14:23:50 -07:00
testing chore(replay): improve replay robustness with un-validated construction (#3414) 2025-09-11 13:48:19 +02:00
ui chore(ui-deps): bump tailwindcss from 4.1.6 to 4.1.13 in /llama_stack/ui (#3362) 2025-09-10 13:18:14 -07:00
__init__.py chore(rename): move llama_stack.distribution to llama_stack.core (#2975) 2025-07-30 23:30:53 -07:00
env.py refactor(test): move tools, evals, datasetio, scoring and post training tests (#1401) 2025-03-04 14:53:47 -08:00
log.py chore(pre-commit): add pre-commit hook to enforce llama_stack logger usage (#3061) 2025-08-20 07:15:35 -04:00
schema_utils.py feat(auth): API access control (#2822) 2025-07-24 15:30:48 -07:00