gitea_admin/sientia-dataops-laborious-legacy
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity
Files
e4fc12e5292529e9528c12b227a5089fe3fd78d9
sientia-dataops-laborious-l…/tests/laborious/activities/test_api.py
vitor-aignosi e4fc12e529 QTZPOC-20 
QTZPOC-20: Enhance system robustness and test coverage across bundle processing, activity error handling, and worker operations.

*   Strengthen bundle reader validation with new tests for archive integrity, security vulnerabilities (e.g., path traversal, duplicate entries, special file types), and I/O error resilience.
*   Improve error handling and status propagation in PI Web API, MLflow, and OPC activities, including partial write scenarios and OPC session management.
*   Add comprehensive tests for worker startup, configuration, graceful shutdown, and Prometheus metrics server initialization.
*   Introduce a new utility for intelligent DataFrame debugging, summarizing large dataframes for concise logging, and refine exception chain summarization.
*   Update code coverage configuration to exclude @overload decorator lines.
2026-09-08 09:42:23 -03:00

531 lines
17 KiB
Python
Raw Blame History

from unittest.mock import ANY, AsyncMock, MagicMock, call, patch
import pytest_asyncio
from pytest import fixture, mark
from sientia_do.notifications.models import NotificationLevel
from laborious.activities.api import API, PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
metadata = {
'metadata': {
'model_id': 'test_model',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'schema_name': 'test_schedule',
},
}
def _create_mock_dataframe(to_dict_return=None):
"""Helper function to create a mocked DataFrame for testing."""
mock_df = MagicMock()
mock_head = MagicMock()
def get_column_values(key):
if key == 'prediction':
return MagicMock(values=[0.75])
elif key == 'prediction_confidence':
return MagicMock(values=[0.95])
else:
return MagicMock(values=['2024-01-01T00:00:00+00:00'])
mock_head.__getitem__.side_effect = get_column_values
mock_df.head.return_value = mock_head
if to_dict_return is None:
to_dict_return = {
'prediction': [0.75],
'prediction_confidence': [0.95],
'timestamp': ['2024-01-01T00:00:00+00:00'],
}
mock_df.to_dict.return_value = to_dict_return
return mock_df
@fixture
def base_input_data():
"""Base input data for PI Web API tests."""
return {
**metadata,
'data': {
'prediction': [0.75],
'prediction_confidence': [0.95],
'timestamp': ['2024-01-01T00:00:00+00:00'],
},
'pi_web_api_output_config': {
'endpoint': 'https://test-pi-server.com/piwebapi',
'prediction_tags': {'tag1': 'web_id_1'},
'confidence_tags': {'tag2': 'web_id_2'},
},
}
@patch('laborious.activities.api.PIWebAPIClient')
def test_get_pi_web_api_core_labels_without_operation_type(mock_pi_web_api_client):
from sientia_do.observability.sientia_monitoring import SientiaMonitoring
api_instance = API(
base_url='https://test-pi-server.com',
auth_type='bearer',
auth_token='test_token',
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
with patch.object(
SientiaMonitoring,
'get_core_labels',
return_value={
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'operation_type': 'write_pi_web_api_data',
},
):
labels = api_instance.get_pi_web_api_core_labels(metadata=metadata['metadata'])
assert labels['operation_type'] == 'write_pi_web_api_data'
assert labels == {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'operation_type': 'write_pi_web_api_data',
}
@patch('laborious.activities.api.PIWebAPIClient')
def test_get_pi_web_api_core_labels_with_operation_type(mock_pi_web_api_client):
from sientia_do.observability.sientia_monitoring import SientiaMonitoring
api_instance = API(
base_url='https://test-pi-server.com',
auth_type='bearer',
auth_token='test_token',
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
with patch.object(
SientiaMonitoring,
'get_core_labels',
return_value={
'pod_id': 'test_pod',
'runtime': 'k8s',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
'operation_type': 'write',
},
):
labels = api_instance.get_pi_web_api_core_labels(
metadata=metadata['metadata'], operation_type='write'
)
assert labels['operation_type'] == 'write'
assert labels['runtime'] == 'k8s'
def test__init__():
api = API(
base_url='https://test-pi-server.com',
auth_type='bearer',
auth_token='test_token',
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
assert api.pi_web_api_client is not None
@pytest_asyncio.fixture
@patch('laborious.activities.api.PIWebAPIClient')
def api(mock_pi_web_api_client):
mock_client = MagicMock()
mock_client.write_value = AsyncMock()
mock_client.close = MagicMock()
mock_client.base_url = 'https://test-pi-server.com'
mock_pi_web_api_client.return_value = mock_client
api_instance = API(
base_url='https://test-pi-server.com',
auth_type='bearer',
auth_token='test_token',
logger=MagicMock(),
notification_handler=MagicMock(),
metrics_controller=AsyncMock(),
)
api_instance.send_notification_async = AsyncMock()
api_instance.info = MagicMock()
api_instance.error = MagicMock()
api_instance.emit_metric = AsyncMock()
api_instance.get_core_labels = MagicMock(
return_value={
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
)
return api_instance
@mark.asyncio
@patch('laborious.activities.api.DataFrame')
async def test_write_pi_web_api_data_success(mock_dataframe, api, base_input_data):
input_data = {
**base_input_data,
'pi_web_api_output_config': {
'endpoint': 'https://test-pi-server.com/piwebapi',
'prediction_tags': {'tag1': 'web_id_1', 'tag2': 'web_id_2'},
'confidence_tags': {'tag3': 'web_id_3', 'tag4': 'web_id_4'},
},
}
mock_dataframe.return_value = _create_mock_dataframe()
# Mock successful responses
api.pi_web_api_client.write_value.side_effect = [
[{'WebId': 'web_id_1', 'Errors': []}, {'WebId': 'web_id_2', 'Errors': []}],
[{'WebId': 'web_id_3', 'Errors': []}, {'WebId': 'web_id_4', 'Errors': []}],
]
result = await api.write_pi_web_api_data(input_data)
api.pi_web_api_client.write_value.assert_has_calls(
[
call(
web_ids=['web_id_1', 'web_id_2'],
value={
'Timestamp': '2024-01-01T00:00:00+00:00',
'Value': 0.75,
},
metadata=metadata['metadata'],
),
call(
web_ids=['web_id_3', 'web_id_4'],
value={
'Timestamp': '2024-01-01T00:00:00+00:00',
'Value': 0.95,
},
metadata=metadata['metadata'],
),
]
)
assert result == {
'prediction': [0.75],
'prediction_confidence': [0.95],
'timestamp': ['2024-01-01T00:00:00+00:00'],
}
@mark.asyncio
@patch('laborious.activities.api.DataFrame')
async def test_write_pi_web_api_data_partial_prediction_mismatch_downgrades_confidence(
mock_dataframe, api, base_input_data
):
"""A partial write (some tags report Errors) doesn't raise — it's caught by the tag-count
mismatch check, which still must downgrade confidence and attach the mismatch message."""
input_data = {
**base_input_data,
'pi_web_api_output_config': {
'endpoint': 'https://test-pi-server.com/piwebapi',
'prediction_tags': {'tag1': 'web_id_1', 'tag2': 'web_id_2'},
'confidence_tags': {'tag3': 'web_id_3'},
},
}
mock_df = _create_mock_dataframe()
mock_dataframe.return_value = mock_df
api.pi_web_api_client.write_value.side_effect = [
[{'WebId': 'web_id_1', 'Errors': []}, {'WebId': 'web_id_2', 'Errors': ['bad tag']}],
[{'WebId': 'web_id_3', 'Errors': []}],
]
await api.write_pi_web_api_data(input_data)
mock_df.__setitem__.assert_any_call(
'prediction_confidence', PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
)
mock_df.__setitem__.assert_any_call('comments', ANY)
api.send_notification_async.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='WRITE_PI_WEB_API_PREDICTION_ERROR',
message=ANY,
block='write_pi_web_api_data',
level=NotificationLevel.ERROR,
)
@mark.asyncio
@patch('laborious.activities.api.DataFrame')
async def test_write_pi_web_api_data_prediction_error(mock_dataframe, api, base_input_data):
mock_dataframe.return_value = _create_mock_dataframe(
{
'prediction': [0.75],
'prediction_confidence': [PI_WEB_API_PREDICTION_ERROR_CONFIDENCE],
'timestamp': ['2024-01-01T00:00:00+00:00'],
}
)
api.pi_web_api_client.write_value.side_effect = Exception('Prediction write failed')
result = await api.write_pi_web_api_data(base_input_data)
api.send_notification_async.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='WRITE_PI_WEB_API_PREDICTION_ERROR',
message="Error writing prediction data to PI Web API: Prediction write failed\n Tags: {'tag1': 'web_id_1'}",
block='write_pi_web_api_data',
level=NotificationLevel.ERROR,
attachment_content=ANY,
)
assert result['prediction_confidence'][0] == PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
assert api.pi_web_api_client.write_value.call_count == 1
@mark.asyncio
@patch('laborious.activities.api.DataFrame')
async def test_write_pi_web_api_data_confidence_error(mock_dataframe, api, base_input_data):
mock_dataframe.return_value = _create_mock_dataframe()
# First call succeeds, second fails
api.pi_web_api_client.write_value.side_effect = [
[{'WebId': 'web_id_1', 'Errors': []}],
Exception('Confidence write failed'),
]
result = await api.write_pi_web_api_data(base_input_data)
api.send_notification_async.assert_called_once_with(
metadata=metadata['metadata'],
notification_id='WRITE_PI_WEB_API_CONFIDENCE_ERROR',
message="Error writing confidence data to PI Web API: Confidence write failed\n Tags: {'tag2': 'web_id_2'}",
block='write_pi_web_api_data',
level=NotificationLevel.ERROR,
attachment_content=ANY,
)
assert result == {
'prediction': [0.75],
'prediction_confidence': [0.95],
'timestamp': ['2024-01-01T00:00:00+00:00'],
}
assert api.pi_web_api_client.write_value.call_count == 2
@mark.asyncio
@patch('laborious.activities.api.DataFrame')
async def test_write_pi_web_api_data_empty_tags(mock_dataframe, api, base_input_data):
input_data = {
**base_input_data,
'pi_web_api_output_config': {
'endpoint': 'https://test-pi-server.com/piwebapi',
'prediction_tags': {},
'confidence_tags': {},
},
}
mock_dataframe.return_value = _create_mock_dataframe()
# Mock empty responses
api.pi_web_api_client.write_value.side_effect = [
[],
[],
]
result = await api.write_pi_web_api_data(input_data)
api.pi_web_api_client.write_value.assert_has_calls(
[
call(
web_ids=[],
value={
'Timestamp': '2024-01-01T00:00:00+00:00',
'Value': 0.75,
},
metadata=metadata['metadata'],
),
call(
web_ids=[],
value={
'Timestamp': '2024-01-01T00:00:00+00:00',
'Value': 0.95,
},
metadata=metadata['metadata'],
),
]
)
assert result == {
'prediction': [0.75],
'prediction_confidence': [0.95],
'timestamp': ['2024-01-01T00:00:00+00:00'],
}
@mark.asyncio
async def test_close(api):
api.close()
api.pi_web_api_client.close.assert_called_once()
@mark.asyncio
async def test_process_pi_web_api_response_success(api):
"""Test successful processing of PI Web API response with all tags written."""
response_data = [
{'WebId': 'web_id_1', 'Errors': []},
{'WebId': 'web_id_2', 'Errors': []},
]
tags = {'tag1': 'web_id_1', 'tag2': 'web_id_2'}
core_labels = {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
confidence, message = await api.process_pi_web_api_response(
response_data=response_data,
tags=tags,
core_labels=core_labels,
metadata=metadata['metadata'],
)
assert confidence == 0
assert message == ''
assert api.emit_metric.call_count == 2
# Verify that emit_metric was called with correct tags structure
call_args_list = api.emit_metric.call_args_list
assert len(call_args_list) == 2
# Check that all calls include core_labels and tag_name
for call_args in call_args_list:
assert 'tag_name' in call_args.kwargs['tags']
assert call_args.kwargs['tags']['tag_name'] in ['tag1', 'tag2']
@mark.asyncio
async def test_process_pi_web_api_response_with_errors(api):
"""Test processing response with errors in some tags."""
response_data = [
{'WebId': 'web_id_1', 'Errors': ['Error writing tag']},
{'WebId': 'web_id_2', 'Errors': []},
]
tags = {'tag1': 'web_id_1', 'tag2': 'web_id_2'}
core_labels = {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
confidence, message = await api.process_pi_web_api_response(
response_data=response_data,
tags=tags,
core_labels=core_labels,
metadata=metadata['metadata'],
)
assert confidence == PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
assert (
message
== "The number of written tags does not match the number of tag names: Expected ['tag1', 'tag2'] tags, but ['tag2'] tags were written."
)
assert api.emit_metric.call_count == 2
@mark.asyncio
async def test_process_pi_web_api_response_missing_tags(api):
"""Test processing response when number of written tags doesn't match expected."""
response_data = [
{'WebId': 'web_id_1', 'Errors': []},
]
tags = {'tag1': 'web_id_1', 'tag2': 'web_id_2'}
core_labels = {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
confidence, message = await api.process_pi_web_api_response(
response_data=response_data,
tags=tags,
core_labels=core_labels,
metadata=metadata['metadata'],
)
assert confidence == PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
assert (
message
== "The number of written tags does not match the number of tag names: Expected ['tag1', 'tag2'] tags, but ['tag1'] tags were written."
)
api.send_notification_async.assert_called_once()
call_args = api.send_notification_async.call_args
assert call_args.kwargs['notification_id'] == 'WRITE_PI_WEB_API_PREDICTION_ERROR'
assert call_args.kwargs['level'] == NotificationLevel.ERROR
@mark.asyncio
async def test_process_pi_web_api_response_missing_webid(api):
"""Test processing response when WebId is missing in response item."""
response_data = [
{'Errors': []},
{'WebId': 'web_id_2', 'Errors': []},
]
tags = {'tag1': 'web_id_1', 'tag2': 'web_id_2'}
core_labels = {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
confidence, message = await api.process_pi_web_api_response(
response_data=response_data,
tags=tags,
core_labels=core_labels,
metadata=metadata['metadata'],
)
assert confidence == PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
assert (
message
== "The number of written tags does not match the number of tag names: Expected ['tag1', 'tag2'] tags, but ['tag2'] tags were written."
)
api.error.assert_any_call('The response did not contain some WebIds', metadata['metadata'])
@mark.asyncio
async def test_process_pi_web_api_response_missing_tag_name(api):
"""Test processing response when tag name is not found for WebId."""
response_data = [
{'WebId': 'unknown_web_id', 'Errors': []},
]
tags = {'tag1': 'web_id_1'}
core_labels = {
'pod_id': 'test_pod',
'runtime': 'local',
'model_name': 'test_model',
'workflow_name': 'test_workflow',
}
confidence, message = await api.process_pi_web_api_response(
response_data=response_data,
tags=tags,
core_labels=core_labels,
metadata=metadata['metadata'],
)
assert confidence == PI_WEB_API_PREDICTION_ERROR_CONFIDENCE
assert (
message
== "The number of written tags does not match the number of tag names: Expected ['tag1'] tags, but [] tags were written."
)
api.error.assert_any_call(
'The response did not contain the tag name for WebId unknown_web_id', metadata['metadata']
)
Reference in New Issue View Git Blame Copy Permalink