fix: error on failed job, do not wait for timeout (#2945)

# What does this PR do?

cause post training integration test to error when job fails.

## Test Plan

ci
This commit is contained in:
Matthew Farrellee 2025-07-29 14:07:51 -04:00 committed by GitHub
parent 870a37ff4b
commit c7dc0f21b4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194

View file

@ -38,9 +38,8 @@ sys.stdout.reconfigure(line_buffering=True)
# How to run this test:
#
# pytest llama_stack/providers/tests/post_training/test_post_training.py
# -m "torchtune_post_training_huggingface_datasetio"
# -v -s --tb=short --disable-warnings
# LLAMA_STACK_CONFIG=ci-tests uv run --dev pytest tests/integration/post_training/test_post_training.py
#
class TestPostTraining:
@ -113,6 +112,7 @@ class TestPostTraining:
break
logger.info(f"Current status: {status}")
assert status.status in ["scheduled", "in_progress", "completed"]
if status.status == "completed":
break