mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
chore: unbreak inference store test
# What does this PR do? The inference store writes were moved to asyncio.create_task and not await anymore ## Test Plan ❯ OLLAMA_URL=http://localhost:11434 LLAMA_STACK_CONFIG=server:starter uv run --with pytest-repeat pytest tests/integration/inference --text-model="ollama/llama3.2:3b-instruct-fp16" -vvs -k "test_inference_store_tool_calls and 3b-instruct-fp16-True" --count=10 Uninstalled 2 packages in 102ms Installed 2 packages in 138ms INFO 2025-09-04 14:10:17,775 tests.integration.conftest:66 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS ========================================================================================================== test session starts =========================================================================================================== platform darwin -- Python 3.12.3, pytest-8.4.1, pluggy-1.6.0 -- /Users/erichuang/.cache/uv/builds-v0/.tmpSGMlgt/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.3', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1', 'pluggy': '1.6.0'}, 'Plugins': {'repeat': '0.9.4', 'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0'}} rootdir: /Users/erichuang/projects/llama-stack-git configfile: pyproject.toml plugins: repeat-0.9.4, anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 970 items / 950 deselected / 20 selected tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-1-10] instantiating llama_stack_client Starting llama stack server with config 'starter' on port 8321... Waiting for server at http://localhost:8321... (0.0s elapsed) Waiting for server at http://localhost:8321... (0.5s elapsed) Waiting for server at http://localhost:8321... (5.1s elapsed) Waiting for server at http://localhost:8321... (5.6s elapsed) Waiting for server at http://localhost:8321... (10.1s elapsed) Waiting for server at http://localhost:8321... (10.6s elapsed) Waiting for server at http://localhost:8321... (15.2s elapsed) Waiting for server at http://localhost:8321... (15.7s elapsed) Server is ready at http://localhost:8321 llama_stack_client instantiated in 20.583s PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-2-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-3-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-4-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-5-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-6-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-7-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-8-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-9-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-10-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-1-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-2-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-3-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-4-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-5-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-6-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-7-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-8-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-9-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-10-10] PASSEDTerminating llama stack server process... Terminating process 53307 and its group... Server process and children terminated gracefully
This commit is contained in:
Eric Huang
parent
55a8c5f439
commit
b40e100a17
1 changed files with 23 additions and 2 deletions
|
|
@ -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
|
||||
|
||||
tries = 0
|
||||
while tries < 10:
|
||||
responses = client.chat.completions.list(limit=1000)
|
||||
assert response_id in [r.id for r in responses.data]
|
||||
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]
|
||||
|
||||
|
|
|
|||
Loading…
Add table
Add a link
Reference in a new issue