phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-07-22 04:27:52 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

feat(responses): implement full multi-turn support

Browse source
This commit is contained in:
Ashwin Bharambe 2025-05-27 14:32:21 -07:00
parent 6bb174bb05
commit fd15a6832c
5 changed files with 577 additions and 125 deletions
Download patch file Download diff file Expand all files Collapse all files

10
tests/unit/providers/agents/meta_reference/test_openai_responses.py
View file

@ -224,16 +224,16 @@ async def test_create_openai_response_with_tool_call_type_none(openai_responses_
],
)
# Verify
# Check that we got the content from our mocked tool execution result
chunks = [chunk async for chunk in result]
assert len(chunks) == 2 # Should have response.created and response.completed
# Verify inference API was called correctly (after iterating over result)
first_call = mock_inference_api.openai_chat_completion.call_args_list[0]
assert first_call.kwargs["messages"][0].content == input_text
assert first_call.kwargs["tools"] is not None
assert first_call.kwargs["temperature"] == 0.1
# Check that we got the content from our mocked tool execution result
chunks = [chunk async for chunk in result]
assert len(chunks) == 2 # Should have response.created and response.completed
# Check response.created event (should have empty output)
assert chunks[0].type == "response.created"
assert len(chunks[0].response.output) == 0