phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-18 15:27:16 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix(models)!: always prefix models with provider_id when registering (#3822)

Browse source 
**!!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
This commit is contained in:
Ashwin Bharambe 2025-10-16 06:47:39 -07:00 • committed by GitHub
parent f205ab6f6c
commit f70aa99c97
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
10 changed files with 53 additions and 124 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/utils/inference/openai_mixin.py
View file

@ -435,7 +435,8 @@ class OpenAIMixin(NeedsRequestProviderData, ABC, BaseModel):
"""
# First check if the model is pre-registered in the model store
if hasattr(self, "model_store") and self.model_store:
if await self.model_store.has_model(model):
qualified_model = f"{self.__provider_id__}/{model}" # type: ignore[attr-defined]
if await self.model_store.has_model(qualified_model):
return True
# Then check the provider's dynamic model cache