phoenix-oss/llama-stack-mirror
0
0
Fork 1
mirror of https://github.com/meta-llama/llama-stack.git synced 2025-10-04 04:04:14 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

make sure the mock method identifies as a coroutine

Browse source
This commit is contained in:
Matthew Farrellee 2025-09-12 13:13:13 -04:00
parent a14f42f1b8
commit a673484e21
1 changed files with 10 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

14
tests/unit/distribution/test_inference_recordings.py
View file

@ -6,7 +6,7 @@
import tempfile
from pathlib import Path
from unittest.mock import Mock, patch
from unittest.mock import AsyncMock, Mock, patch
import pytest
from openai import AsyncOpenAI
@ -159,7 +159,9 @@ class TestInferenceRecording:
return real_openai_chat_response
temp_storage_dir = temp_storage_dir / "test_recording_mode"
with patch("openai.resources.chat.completions.AsyncCompletions.create", side_effect=mock_create):
with patch(
"openai.resources.chat.completions.AsyncCompletions.create", new_callable=AsyncMock, side_effect=mock_create
):
with inference_recording(mode=InferenceMode.RECORD, storage_dir=str(temp_storage_dir)):
client = AsyncOpenAI(base_url="http://localhost:11434/v1", api_key="test")
@ -185,7 +187,9 @@ class TestInferenceRecording:
temp_storage_dir = temp_storage_dir / "test_replay_mode"
# First, record a response
with patch("openai.resources.chat.completions.AsyncCompletions.create", side_effect=mock_create):
with patch(
"openai.resources.chat.completions.AsyncCompletions.create", new_callable=AsyncMock, side_effect=mock_create
):
with inference_recording(mode=InferenceMode.RECORD, storage_dir=str(temp_storage_dir)):
client = AsyncOpenAI(base_url="http://localhost:11434/v1", api_key="test")
@ -277,7 +281,9 @@ class TestInferenceRecording:
temp_storage_dir = temp_storage_dir / "test_embeddings_recording"
# Record
with patch("openai.resources.embeddings.AsyncEmbeddings.create", side_effect=mock_create):
with patch(
"openai.resources.embeddings.AsyncEmbeddings.create", new_callable=AsyncMock, side_effect=mock_create
):
with inference_recording(mode=InferenceMode.RECORD, storage_dir=str(temp_storage_dir)):
client = AsyncOpenAI(base_url="http://localhost:11434/v1", api_key="test")