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
..
__init__.py	chore: enable pyupgrade fixes (#1806)	2025-05-01 14:23:50 -07:00
embedding_mixin.py	fix(inference): enable routing of models with provider_data alone (backport #3928) (#4142)	2025-11-12 13:41:27 -08:00
inference_store.py	fix: harden storage semantics (backport #4118) (#4138)	2025-11-12 13:01:21 -08:00
litellm_openai_mixin.py	feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794)	2025-10-12 19:01:52 -07:00
model_registry.py	feat: use SecretStr for inference provider auth credentials (#3724)	2025-10-10 07:32:50 -07:00
openai_compat.py	fix: Update watsonx.ai provider to use LiteLLM mixin and list all models (#3674)	2025-10-08 07:29:43 -04:00
openai_mixin.py	fix: enforce allowed_models during inference requests (#4197)	2025-11-24 19:05:08 +00:00
prompt_adapter.py	chore!: Safety api refactoring to use OpenAIMessageParam (#3796)	2025-10-12 08:01:00 -07:00