Ashwin Bharambe f70aa99c97 fix(models)!: always prefix models with provider_id when registering (#3822) ... **!!BREAKING CHANGE!!** The lookup is also straightforward -- we always look for this identifier and don't try to find a match for something without the provider_id prefix. Note that, this ideally means we need to update the `register_model()` API also (we should kill "identifier" from there) but I am not doing that as part of this PR. ## Test Plan Existing unit tests		2025-10-16 06:47:39 -07:00
..
agent	feat: Add support for Conversations in Responses API (#3743)	2025-10-10 11:57:40 -07:00
agents	feat: Add responses and safety impl extra_body (#3781)	2025-10-15 15:01:37 -07:00
batches	feat: Add /v1/embeddings endpoint to batches API (#3384)	2025-10-10 13:25:58 -07:00
files	feat(files): fix expires_after API shape (#3604)	2025-09-29 21:29:15 -07:00
inference	feat(api)!: BREAKING CHANGE: support passing extra_body through to providers (#3777)	2025-10-10 16:21:44 -07:00
inline	feat: Add responses and safety impl extra_body (#3781)	2025-10-15 15:01:37 -07:00
nvidia	feat: add static embedding metadata to dynamic model listings for providers using OpenAIMixin (#3547)	2025-09-25 17:17:00 -04:00
utils	fix(models)!: always prefix models with provider_id when registering (#3822)	2025-10-16 06:47:39 -07:00
vector_io	fix(vector-io): handle missing document_id in insert_chunks (#3521)	2025-10-15 11:02:48 -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