phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-11 05:38:38 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Merge branch 'main' into resp_to_ci

Browse source
This commit is contained in:
Ashwin Bharambe 2025-09-04 15:14:15 -07:00 • committed by GitHub
commit b54f10150e
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
9 changed files with 96 additions and 17 deletions
Download patch file Download diff file Expand all files Collapse all files

25
tests/integration/inference/test_openai_completion.py
View file

@ -5,6 +5,8 @@
# the root directory of this source tree.
import time
import pytest
from ..test_cases.test_case import TestCase
@ -323,8 +325,15 @@ def test_inference_store(compat_client, client_with_models, text_model_id, strea
response_id = response.id
content = response.choices[0].message.content
responses = client.chat.completions.list(limit=1000)
assert response_id in [r.id for r in responses.data]
tries = 0
while tries < 10:
responses = client.chat.completions.list(limit=1000)
if response_id in [r.id for r in responses.data]:
break
else:
tries += 1
time.sleep(0.1)
assert tries < 10, f"Response {response_id} not found after 1 second"
retrieved_response = client.chat.completions.retrieve(response_id)
assert retrieved_response.id == response_id
@ -388,6 +397,18 @@ def test_inference_store_tool_calls(compat_client, client_with_models, text_mode
response_id = response.id
content = response.choices[0].message.content
# wait for the response to be stored
tries = 0
while tries < 10:
responses = client.chat.completions.list(limit=1000)
if response_id in [r.id for r in responses.data]:
break
else:
tries += 1
time.sleep(0.1)
assert tries < 10, f"Response {response_id} not found after 1 second"
responses = client.chat.completions.list(limit=1000)
assert response_id in [r.id for r in responses.data]