Ashwin Bharambe 4645182789 fix: enforce allowed_models during inference requests (#4197) ... The `allowed_models` configuration was only being applied when listing models via the `/v1/models` endpoint, but the actual inference requests weren't checking this restriction. This meant users could directly request any model the provider supports by specifying it in their inference call, completely bypassing the intended cost controls. The fix adds validation to all three inference methods (chat completions, completions, and embeddings) that checks the requested model against the allowed_models list before making the provider API call. ### Test plan Added unit tests (cherry picked from commit d649c3663e) # Conflicts: # llama_stack/providers/utils/inference/openai_mixin.py # tests/unit/providers/utils/inference/test_openai_mixin.py		2025-11-24 19:05:08 +00:00
..
agent	feat(stores)!: use backend storage references instead of configs (#3697)	2025-10-20 13:20:09 -07:00
agents	feat(stores)!: use backend storage references instead of configs (#3697)	2025-10-20 13:20:09 -07:00
batches	feat(stores)!: use backend storage references instead of configs (#3697)	2025-10-20 13:20:09 -07:00
files	feat(stores)!: use backend storage references instead of configs (#3697)	2025-10-20 13:20:09 -07:00
inference	fix(tests): reduce some test noise (#3825)	2025-10-16 09:52:16 -07:00
inline	feat: Add responses and safety impl extra_body (#3781)	2025-10-15 15:01:37 -07:00
nvidia	fix(tests): reduce some test noise (#3825)	2025-10-16 09:52:16 -07:00
utils	fix: enforce allowed_models during inference requests (#4197)	2025-11-24 19:05:08 +00:00
vector_io	fix: remove consistency checks (#3881)	2025-10-21 14:40:14 -07:00
test_bedrock.py	fix: AWS Bedrock inference profile ID conversion for region-specific endpoints (#3386)	2025-09-11 11:41:53 +02:00
test_configs.py	chore(rename): move llama_stack.distribution to llama_stack.core (#2975)	2025-07-30 23:30:53 -07:00