phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-12-27 23:22:01 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

fix

Browse source
This commit is contained in:
Ashwin Bharambe 2025-05-25 19:08:36 -07:00
parent cad1c9b4c9
commit 12dfcd11d9
3 changed files with 21 additions and 9 deletions
Download patch file Download diff file Expand all files Collapse all files

7
tests/verifications/openai_api/test_responses.py
View file

@ -84,7 +84,7 @@ def test_response_streaming_basic(request, openai_client, model, provider, verif
if chunk.type == "response.created":
# Verify response.created is emitted first and immediately
assert len(events) == 1, "response.created should be the first event"
assert event_times[0] < 0.1, "response.created should be emitted immediately (< 100ms)"
assert event_times[0] < 0.1, "response.created should be emitted immediately"
assert chunk.response.status == "in_progress"
response_id = chunk.response.id
@ -109,11 +109,6 @@ def test_response_streaming_basic(request, openai_client, model, provider, verif
completed_index = event_types.index("response.completed")
assert created_index < completed_index, "response.created should come before response.completed"
# Verify timing - there should be some delay between events (indicating real processing)
if len(event_times) >= 2:
time_between_events = event_times[-1] - event_times[0]
assert time_between_events > 0.01, "There should be measurable time between events (indicating real processing)"
# Verify stored response matches streamed response
retrieved_response = openai_client.responses.retrieve(response_id=response_id)
final_event = events[-1]