phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 20:14:13 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(replay): improve replay robustness with un-validated construction

Browse source 
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"
This commit is contained in:
Matthew Farrellee 2025-09-11 01:01:01 -04:00
parent c04f1c1e8c
commit b0364572b2
1 changed files with 6 additions and 2 deletions
Download patch file Download diff file Expand all files Collapse all files

8
llama_stack/testing/inference_recorder.py
View file

@ -105,8 +105,12 @@ def _deserialize_response(data: dict[str, Any]) -> Any:
return cls.model_validate(data["__data__"]) return cls.model_validate(data["__data__"])
except (ImportError, AttributeError, TypeError, ValueError) as e: except (ImportError, AttributeError, TypeError, ValueError) as e:
logger.warning(f"Failed to deserialize object of type {data['__type__']}: {e}") logger.warning(f"Failed to deserialize object of type {data['__type__']} with model_validate: {e}")
return data["__data__"] try:
return cls.model_construct(**data["__data__"])
except Exception as e:
logger.warning(f"Failed to deserialize object of type {data['__type__']} with model_construct: {e}")
return data["__data__"]
return data return data