feat: enhance test scenarios and configuration for regression models

- Updated `pyproject.toml` to include new linting rules for end-to-end tests.
- Modified `requirements-dev.txt` to add dependencies for E2E testing with `testcontainers` and `requests`.
- Refactored multiple JSON test scenario files to standardize structure, including new fields for `experiment_run_id`, `bucket_name`, and `file_name`.
- Improved model training parameters in `train_model_params.py` to use `experiment_name` directly.
- Adjusted `data_manager_repository.py` to utilize the updated `experiment_name` for logging.

These changes improve the organization and clarity of regression model tests and enhance the overall testing framework.
This commit is contained in:
2026-05-04 11:11:16 -03:00
parent 50d0ea6f32
commit 6bd30e3328
26 changed files with 2024 additions and 397 deletions

View File

@@ -0,0 +1,109 @@
"""
End-to-end tests for CleanupFiles workflow.
Covers scenarios 3.x: cleanup of temporary local directories.
"""
import os
import shutil
import tempfile
import pytest
import pytest_asyncio
from temporalio.testing import WorkflowEnvironment
from temporalio.worker import Worker
from e2e.helpers import make_workflow_id, start_and_await_workflow
from model_manager.workflows.cleanup_files import CleanupFiles
@pytest.mark.asyncio
@pytest.mark.integration
async def test_scenario_3_1_1_cleanup_with_no_temp_dirs(
temporal_test_env: WorkflowEnvironment,
temporal_worker: Worker,
tmp_path,
):
"""Scenario 3.1.1 – Cleanup when the temp directory is empty.
The cleanup_temp_directories activity should complete without error
and the workflow should finish successfully.
"""
# Use an empty temp directory as the reports path
empty_dir = tmp_path / 'reports_temp'
empty_dir.mkdir()
result = await start_and_await_workflow(
temporal_test_env.client,
CleanupFiles.run,
{'temp_path': str(empty_dir)},
make_workflow_id('test-s3-1-1'),
)
# Workflow returns None on success
assert result is None
@pytest.mark.asyncio
@pytest.mark.integration
async def test_scenario_3_1_2_cleanup_removes_old_temp_dirs(
temporal_test_env: WorkflowEnvironment,
temporal_worker: Worker,
tmp_path,
):
"""Scenario 3.1.2 – Cleanup removes stale subdirectories from the temp dir.
Creates two subdirectories with timestamp suffixes inside the reports
temp directory and verifies the activity removes them.
"""
reports_dir = tmp_path / 'reports_temp'
reports_dir.mkdir()
# Create two stale run directories
stale1 = reports_dir / 'run-1234567890'
stale2 = reports_dir / 'run-9876543210'
stale1.mkdir()
stale2.mkdir()
(stale1 / 'model.pkl').write_bytes(b'fake-model-data')
(stale2 / 'report.json').write_bytes(b'{"status": "old"}')
result = await start_and_await_workflow(
temporal_test_env.client,
CleanupFiles.run,
{'temp_path': str(reports_dir)},
make_workflow_id('test-s3-1-2'),
)
assert result is None
# The activity should have cleaned up the stale directories
remaining = list(reports_dir.iterdir())
assert len(remaining) == 0, (
f'Expected all stale dirs to be removed, but found: {remaining}'
)
@pytest.mark.asyncio
@pytest.mark.integration
async def test_scenario_3_1_3_cleanup_nonexistent_temp_path(
temporal_test_env: WorkflowEnvironment,
temporal_worker: Worker,
tmp_path,
):
"""Scenario 3.1.3 – Cleanup with a temp_path that does not exist.
The activity must handle a missing directory gracefully without
raising an unhandled exception, since the directory may have already
been cleaned by a previous run.
"""
nonexistent = str(tmp_path / 'does_not_exist' / 'reports')
# Should not raise — the activity is expected to handle a missing path
result = await start_and_await_workflow(
temporal_test_env.client,
CleanupFiles.run,
{'temp_path': nonexistent},
make_workflow_id('test-s3-1-3'),
)
assert result is None