phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-08-16 06:27:58 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

chore(tests): fix responses and vector_io tests (#3119)

Browse source 
Some fixes to MCP tests. And a bunch of fixes for Vector providers.

I also enabled a bunch of Vector IO tests to be used with
`LlamaStackLibraryClient`

## Test Plan

Run Responses tests with llama stack library client:
```
pytest -s -v tests/integration/non_ci/responses/ --stack-config=server:starter \
   --text-model openai/gpt-4o \
  --embedding-model=sentence-transformers/all-MiniLM-L6-v2 \
  -k "client_with_models"
```

Do the same with `-k openai_client`

The rest should be taken care of by CI.
This commit is contained in:
Ashwin Bharambe 2025-08-12 16:15:53 -07:00 • committed by GitHub
parent 1721aafc1f
commit 3d90117891
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
25 changed files with 175 additions and 112 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/core/routers/inference.py
View file

@ -65,7 +65,7 @@ from llama_stack.providers.datatypes import HealthResponse, HealthStatus, Routin
from llama_stack.providers.utils.inference.inference_store import InferenceStore
from llama_stack.providers.utils.telemetry.tracing import get_current_span
logger = get_logger(name=__name__, category="core")
logger = get_logger(name=__name__, category="inference")
class InferenceRouter(Inference):
@ -854,4 +854,5 @@ class InferenceRouter(Inference):
model=model.identifier,
object="chat.completion",
)
logger.debug(f"InferenceRouter.completion_response: {final_response}")
await self.store.store_chat_completion(final_response, messages)