SIENTIAPDE-1243: Initial commit of the model manager project, adding core files and configurations.

This commit introduces the initial project structure, including:
- .env.example: Example environment configuration.
- .github/workflows/quality-gate.yml: CI workflow for quality checks.
- .gitignore: Specifies intentionally untracked files that Git should ignore.
- Makefile: Automation of tasks like docker builds.
- README.md: Project documentation.
- Source code for model management, activities, utils, worker and workflows.
- Test suite.
- Dockerfile for the simulator.
- sonar-project.properties: SonarQube configuration file.
- values.yaml: Helm chart values for deployment.
This commit is contained in:
Bruno Domingues
2025-09-30 14:55:38 -03:00
parent e79b35a1fb
commit 93d0849c80
51 changed files with 8171 additions and 3 deletions

View File

@@ -0,0 +1,597 @@
from unittest.mock import MagicMock, ANY, patch
from pytest import fixture, mark
from sientia_do.notifications.models import NotificationLevel
from laborious.activities.gates import Gates
@fixture
def gates_activity():
gates = Gates(
logger=MagicMock(),
notification_handler=MagicMock(),
)
gates.error = MagicMock()
gates.debug = MagicMock()
gates.info = MagicMock()
gates.warning = MagicMock()
gates.critical = MagicMock()
gates.send_notification = MagicMock()
return gates
metadata = {
"metadata": {
"model_id": "test_model",
"model_name": "test_model",
"workflow_name": "test_workflow",
"schema_name": "test_schedule",
},
}
@mark.asyncio
async def test_input_gate_invalid_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'INVALID_FILTER': {'POLICY': 'STOP'}
},
'data': {'value': [1, 2, 3]},
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.input_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.error.assert_called_once_with(
"Filter INVALID_FILTER not found", metadata['metadata']
)
@mark.asyncio
@patch('laborious.activities.gates.input_filter_functions')
async def test_input_gate_filter_exception(mock_input_filter_functions, gates_activity):
# Arrange
mock_input_filter_functions.__contains__.return_value = True
mock_input_filter_functions.__getitem__.return_value = MagicMock(
side_effect=Exception("Test error"))
input_data = {
**metadata,
'filters': {
'EMPTY_DATA': {'policy': 'STOP', 'config': {}}
},
'data': {'value': []},
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.input_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.send_notification.assert_called_once_with(
metadata=metadata['metadata'],
notification_id="INTPUT_GATE_ERROR__EMPTY_DATA",
message="Error in filter EMPTY_DATA:{'policy': 'STOP', 'config': {}}: \n Test error",
block="input_gate",
level=NotificationLevel.ERROR,
attachment_content=ANY
)
@mark.asyncio
async def test_input_gate_no_filters(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {},
'data': {'value': [1, 2, 3]},
'path_priority': ['CONTINUE', 'STOP', 'REPEAT']
}
# Act
result = await gates_activity.input_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.debug.assert_called()
@mark.asyncio
async def test_input_gate_with_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'EMPTY_DATA': {'policy': 'STOP', 'config': {}}
},
'data': {'value': []},
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.input_gate(input_data)
# Assert
assert result == ('STOP', -1, "Input data with bad quality")
gates_activity.debug.assert_called()
@mark.asyncio
async def test_mlflow_response_gate_invalid_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'INVALID_FILTER': {'POLICY': 'STOP'}
},
'data': {'content': {'message': 'success'}},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_response_gate(input_data)
# Assert
assert result == (None, 0, "")
@mark.asyncio
@patch('laborious.activities.gates.mlflow_response_filter_functions')
async def test_mlflow_response_gate_filter_exception(mock_mlflow_response_filter_functions,
gates_activity):
# Arrange
mock_mlflow_response_filter_functions.__contains__.return_value = True
mock_mlflow_response_filter_functions.__getitem__.return_value = MagicMock(
side_effect=Exception("Test error"))
input_data = {
**metadata,
'filters': {
'INVALID_FILTER': {'POLICY': 'STOP'}
},
'data': {'content': {'message': 'success'}},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_response_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.send_notification.assert_called_once_with(
metadata=metadata['metadata'],
notification_id="MLFLOW_GATE_RESPONSE_FILTER__INVALID_FILTER",
message="Error in filter INVALID_FILTER:{'POLICY': 'STOP'}: \n Test error",
block="mlflow_gate",
level=NotificationLevel.ERROR,
attachment_content=ANY
)
@mark.asyncio
async def test_mlflow_response_gate_no_filters(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {},
'data': {'content': {'message': 'success'}},
'type': 'test',
'path_priority': ['CONTINUE', 'STOP', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_response_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.debug.assert_called()
@mark.asyncio
async def test_mlflow_response_gate_with_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'API_ERROR': {'policy': 'STOP'}
},
'data': {
'success': False,
'content': {
'message': 'API error occurred',
'traceback': 'error trace'
}
},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_response_gate(input_data)
# Assert
assert result == ('STOP', -1, "API error occurred")
gates_activity.debug.assert_called()
gates_activity.send_notification.assert_called()
@mark.asyncio
async def test_mlflow_content_gate_invalid_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'INVALID_FILTER': {'POLICY': 'STOP'}
},
'data': {'value': [1, 2, 3]},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_content_gate(input_data)
# Assert
assert result == (None, 0, "")
@mark.asyncio
@patch('laborious.activities.gates.mlflow_content_filter_functions')
async def test_mlflow_content_gate_filter_exception(mock_mlflow_content_filter_functions,
gates_activity):
# Arrange
mock_mlflow_content_filter_functions.__contains__.return_value = True
mock_mlflow_content_filter_functions.__getitem__.return_value = MagicMock(
side_effect=Exception("Test error"))
input_data = {
**metadata,
'filters': {
'API_ERROR': {'POLICY': 'STOP'}
},
'data': {
'success': False,
'content': {
'message': 'API error occurred',
'traceback': 'error trace'
}
},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_content_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.debug.assert_called()
gates_activity.send_notification.assert_called_once_with(
metadata=metadata['metadata'],
notification_id="MLFLOW_GATE_CONTENT_FILTER__API_ERROR",
message="Error in filter API_ERROR:{'POLICY': 'STOP'}: \n Test error",
block="mlflow_gate",
level=NotificationLevel.ERROR,
attachment_content=ANY
)
@mark.asyncio
async def test_mlflow_content_gate_no_filters(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {},
'data': {'value': [1, 2, 3]},
'type': 'test',
'path_priority': ['CONTINUE', 'STOP', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_content_gate(input_data)
# Assert
assert result == (None, 0, "")
gates_activity.debug.assert_called()
@mark.asyncio
async def test_mlflow_content_gate_with_filter(gates_activity):
# Arrange
input_data = {
**metadata,
'filters': {
'NAN_VALUES': {'policy': 'STOP', 'config': {}}
},
'data': {'value': [None, None, None]},
'type': 'test',
'path_priority': ['STOP', 'CONTINUE', 'REPEAT']
}
# Act
result = await gates_activity.mlflow_content_gate(input_data)
# Assert
assert result == (
'STOP', -1, "Transformed data not passed the content filter")
gates_activity.debug.assert_called()
gates_activity.send_notification.assert_called()
def test_get_prediction_store_policy_invalid_policy(gates_activity):
# Arrange
prediction_store_policy = 'INVALID_POLICY'
# Act
policy_type, policy_value = gates_activity.get_prediction_store_policy(
prediction_store_policy, metadata)
# Assert
assert policy_type == 'lts'
assert policy_value == 1
def test_get_prediction_store_policy_invalid_policy_value(gates_activity):
# Arrange
prediction_store_policy = 'abc:INVALID_VALUE'
# Act
policy_type, policy_value = gates_activity.get_prediction_store_policy(
prediction_store_policy, metadata)
# Assert
assert policy_type == 'lts'
assert policy_value == 1
def test_get_prediction_store_policy_valid_policy_type(gates_activity):
# Arrange
prediction_store_policy = 'abc:1'
# Act
policy_type, policy_value = gates_activity.get_prediction_store_policy(
prediction_store_policy, metadata)
# Assert
assert policy_type == 'lts'
assert policy_value == 1
def test_get_prediction_store_policy_valid_policy(gates_activity):
# Arrange
prediction_store_policy = 'erl:1'
# Act
policy_type, policy_value = gates_activity.get_prediction_store_policy(
prediction_store_policy, metadata)
# Assert
assert policy_type == 'erl'
assert policy_value == 1
@mark.asyncio
async def test_format_prediction_no_timestamp(gates_activity):
# Arrange
input_data = {
**metadata,
'data': {
'prediction': {
'2023-05-26 11:12:27': 1
},
'response_time': {
'2023-05-26 11:12:27': 0.1
}
},
'model_id': 'test_model',
'prediction_confidence': 0.9,
'prediction_store_policy': 'lts:1'
}
# Act
result = await gates_activity.format_prediction(input_data)
# Assert
assert result['prediction'] == {0: 1}
assert result['response_time'] == {0: ANY}
assert result['timestamp'] == {0: '2023-05-26 11:12:27'}
assert result['model_id'] == {0: 'test_model'}
assert result['prediction_confidence'] == {0: 0.9}
assert result['prediction_status'] == {0: 'Good'}
assert result['comments'] == {0: ""}
@mark.asyncio
async def test_format_prediction_with_timestamp_erl(gates_activity):
# Arrange
input_data = {
**metadata,
'data': {
'prediction': {
'2023-05-26 11:12:27': 1,
'2023-05-26 11:12:28': 2,
'2023-05-26 11:12:29': 3,
},
'response_time': {
'2023-05-26 11:12:27': 0.1,
'2023-05-26 11:12:28': 0.2,
'2023-05-26 11:12:29': 0.3,
}
},
'model_id': 'test_model',
'prediction_confidence': 0.9,
'prediction_store_policy': 'erl:2'
}
# Act
result = await gates_activity.format_prediction(input_data)
# Assert
assert result['prediction'] == {0: 2, 1: 1}
assert result['response_time'] == {0: 0.2, 1: 0.1}
assert result['timestamp'] == {
0: '2023-05-26 11:12:28', 1: '2023-05-26 11:12:27'}
assert result['model_id'] == {0: 'test_model', 1: 'test_model'}
assert result['prediction_confidence'] == {0: 0.9, 1: 0.9}
assert result['prediction_status'] == {0: 'Good', 1: 'Good'}
assert result['comments'] == {0: "", 1: ""}
@mark.asyncio
async def test_format_prediction_with_timestamp_lts(gates_activity):
# Arrange
input_data = {
**metadata,
'data': {
'prediction': {
'2023-05-26 11:12:27': 1,
'2023-05-26 11:12:28': 2,
'2023-05-26 11:12:29': 3,
},
'response_time': {
'2023-05-26 11:12:27': 0.1,
'2023-05-26 11:12:28': 0.2,
'2023-05-26 11:12:29': 0.3,
}
},
'model_id': 'test_model',
'prediction_confidence': 0.9,
'prediction_store_policy': 'lts:2'
}
# Act
result = await gates_activity.format_prediction(input_data)
# Assert
assert result['prediction'] == {0: 3, 1: 2}
assert result['response_time'] == {0: 0.3, 1: 0.2}
assert result['timestamp'] == {
0: '2023-05-26 11:12:29', 1: '2023-05-26 11:12:28'}
assert result['model_id'] == {0: 'test_model', 1: 'test_model'}
assert result['prediction_confidence'] == {0: 0.9, 1: 0.9}
assert result['prediction_status'] == {0: 'Good', 1: 'Good'}
assert result['comments'] == {0: "", 1: ""}
@mark.asyncio
async def test_format_prediction_with_timestamp_invalid_policy(gates_activity):
# Arrange
input_data = {
**metadata,
'data': {'prediction': [1, 2, 3],
'response_time': [0.1, 0.2, 0.3],
'timestamp': ['2023-05-26 11:12:27', '2023-05-26 11:12:28', '2023-05-26 11:12:29']},
'model_id': 'test_model',
'prediction_confidence': 0.9,
'prediction_store_policy': 'lts:2'
}
gates_activity.get_prediction_store_policy = MagicMock(
return_value=('invalid', 1))
try:
result = await gates_activity.format_prediction(input_data)
except ValueError as e:
assert str(e) == "Invalid policy type: invalid"
else:
assert False, "Expected ValueError"
@mark.asyncio
async def test_format_default_prediction(gates_activity):
# Arrange
input_data = {
**metadata,
'timestamp': '2023-05-26 11:12:27',
'model_id': 'test_model',
'prediction_confidence': 0.1,
'comment': 'Test comment'
}
# Act
result = await gates_activity.format_default_prediction(input_data)
# Assert
assert result['prediction'] == {0: 0}
assert result['response_time'] == {0: 0}
assert result['timestamp'] == {0: '2023-05-26 11:12:27'}
assert result['model_id'] == {0: 'test_model'}
assert result['prediction_confidence'] == {0: 0.1}
assert result['prediction_status'] == {0: 'Bad'}
assert result['comments'] == {0: 'Test comment'}
gates_activity.debug.assert_called()
@mark.asyncio
async def test_get_last_timestamp_with_data(gates_activity):
# Arrange
input_data = {
**metadata,
'data': {
'timestamp': ['2023-05-26 11:12:27', '2023-05-26 11:12:28']
}
}
# Act
result = await gates_activity.get_last_timestamp(input_data)
# Assert
assert result == '2023-05-26 11:12:28'
@mark.asyncio
async def test_get_last_timestamp_no_data(gates_activity):
# Arrange
input_data = {
'data': {},
**metadata
}
# Act
result = await gates_activity.get_last_timestamp(input_data)
# Assert
assert isinstance(result, str) # Should be a timestamp string
assert len(result) > 0
@mark.asyncio
@patch('laborious.activities.gates.metrics')
async def test_write_metrics(mock_metrics, gates_activity):
"""Test write_metrics method."""
input_data = {
**metadata,
'prediction': {
'prediction': [1, 2, 3],
'prediction_confidence': [0.9, 0.8, 0.7],
'response_time': [0.1, 0.2, 0.3]
}
}
await gates_activity.write_metrics(input_data)
mock_metrics.PREDICTIONS_WRITTEN_COUNT.labels.assert_called_once_with(
pod_id=gates_activity.pod_id,
model_name=metadata['metadata']['model_name'],
pipeline_name=metadata['metadata']['workflow_name']
)
mock_metrics.PREDICTIONS_WRITTEN_COUNT.labels.return_value.inc.assert_called_once_with()
mock_metrics.PREDICTION_CONFIDENCE_MONITOR.labels.assert_called_once_with(
pod_id=gates_activity.pod_id,
model_name=metadata['metadata']['model_name'],
pipeline_name=metadata['metadata']['workflow_name']
)
mock_metrics.PREDICTION_CONFIDENCE_MONITOR.labels.return_value.set.assert_called_once_with(
0.9
)
mock_metrics.PREDICTION_RESPONSE_TIME_MONITOR.labels.assert_called_once_with(
pod_id=gates_activity.pod_id,
model_name=metadata['metadata']['model_name'],
pipeline_name=metadata['metadata']['workflow_name']
)
mock_metrics.PREDICTION_RESPONSE_TIME_MONITOR.labels.return_value.observe.assert_called_once_with(
0.1
)