phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-06-28 02:53:30 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(responses): implement full multi-turn support (#2295)

Browse source 
I think the implementation needs more simplification. Spent way too much
time trying to get the tests pass with models not co-operating :(
Finally had to switch claude-sonnet to get things to pass reliably.

### Test Plan

```
export TAVILY_SEARCH_API_KEY=...
export OPENAI_API_KEY=...

uv run pytest -p no:warnings \
   -s -v tests/verifications/openai_api/test_responses.py \
 --provider=stack:starter \
  --model openai/gpt-4o
```
This commit is contained in:
Ashwin Bharambe 2025-06-02 15:35:49 -07:00 • committed by GitHub
parent cac7d404a2
commit dbe4e84aca
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 593 additions and 136 deletions
Download patch file Download diff file Expand all files Collapse all files

3
llama_stack/providers/inline/agents/meta_reference/agents.py
View file

@ -325,9 +325,10 @@ class MetaReferenceAgentsImpl(Agents):
stream: bool | None = False,
temperature: float | None = None,
tools: list[OpenAIResponseInputTool] | None = None,
max_infer_iters: int | None = 10,
) -> OpenAIResponseObject:
return await self.openai_responses_impl.create_openai_response(
input, model, instructions, previous_response_id, store, stream, temperature, tools
input, model, instructions, previous_response_id, store, stream, temperature, tools, max_infer_iters
)
async def list_openai_responses(