SIENTIAPDE-1231

Enhance validation script and refactor code in various modules

- Updated the validation script to include automatic code formatting and linting fixes using Ruff.
- Removed the `clean_tmp_files` method from the Gates class to streamline functionality.
- Simplified conditional checks in the OpcRepository for better clarity and error handling.
- Added model ID to the minimal retrain workflow for improved tracking.
- Introduced new test cases for error handling in MLFlow and storage operations, ensuring robustness in repository interactions.

tests/laborious/activities/test_gates.py

@@ -117,6 +117,24 @@ async def test_input_gate_with_filter(gates_activity):
     gates_activity.debug.assert_called()
 
 
+@mark.asyncio
+async def test_input_gate_with_filter_not_caught(gates_activity):
+    # Arrange
+    input_data = {
+        **metadata,
+        'filters': {'EMPTY_DATA': {'policy': 'STOP', 'config': {}}},
+        '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.debug.assert_called()
+
+
 @mark.asyncio
 async def test_mlflow_response_gate_invalid_filter(gates_activity):
     # Arrange
@@ -210,13 +228,38 @@ async def test_mlflow_response_gate_with_filter(gates_activity):
     gates_activity.send_notification.assert_called()
 
 
+@mark.asyncio
+async def test_mlflow_response_gate_with_filter_not_caught(gates_activity):
+    # Arrange
+    input_data = {
+        **metadata,
+        'filters': {'API_ERROR': {'policy': 'STOP'}},
+        'data': {
+            'success': True,
+            '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.debug.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]},
+        'data': {
+            'success': True,
+            'content': {'message': 'success'},
+        },
         'type': 'test',
         'path_priority': ['STOP', 'CONTINUE', 'REPEAT'],
     }
@@ -304,6 +347,25 @@ async def test_mlflow_content_gate_with_filter(gates_activity):
     gates_activity.send_notification.assert_called()
 
 
+@mark.asyncio
+async def test_mlflow_content_gate_with_filter_not_caught(gates_activity):
+    # Arrange
+    input_data = {
+        **metadata,
+        'filters': {'API_ERROR': {'POLICY': 'STOP'}},
+        'data': {'content': {'message': 'success'}},
+        '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()
+
+
 def test_get_prediction_store_policy_invalid_policy(gates_activity):
     # Arrange
     prediction_store_policy = 'INVALID_POLICY'
@@ -506,6 +568,38 @@ async def test_format_default_prediction(gates_activity):
     gates_activity.debug.assert_called()
 
 
+@mark.asyncio
+async def test_format_retrain_report(gates_activity):
+    # Arrange
+    input_data = {
+        **metadata,
+        'experiment_response': {
+            'success': True,
+            'timestamp': '2023-05-26 11:12:27',
+            'message': 'success',
+        },
+        'update_report': {
+            'version': '1.0.0',
+            'mlflow_run_id': 'test_mlflow_run_id',
+            'mlflow_experiment_id': 'test_mlflow_experiment_id',
+        },
+        'model_id': 'test_model',
+        'model_name': 'test_model',
+    }
+
+    # Act
+    result = await gates_activity.format_retrain_report(input_data)
+
+    # Assert
+    assert result['model_id'] == {0: 'test_model'}
+    assert result['model_name'] == {0: 'test_model'}
+    assert result['timestamp'] == {0: '2023-05-26 11:12:27'}
+    assert result['status'] == {0: 'success'}
+    assert result['version'] == {0: '1.0.0'}
+    assert result['mlflow_run_id'] == {0: 'test_mlflow_run_id'}
+    assert result['mlflow_experiment_id'] == {0: 'test_mlflow_experiment_id'}
+
+
 @mark.asyncio
 async def test_get_last_timestamp_with_data(gates_activity):
     # Arrange

tests/laborious/activities/test_mlflow.py

@@ -1,7 +1,7 @@
 from unittest.mock import ANY, MagicMock, call, patch
 
 import numpy as np
-from pytest import fixture, mark
+from pytest import fixture, mark, raises
 from sientia_do.notifications.models import NotificationLevel
 from sientia_do.temporal.constants import DATETIME_FORMAT, DATETIME_FORMAT_WITH_TZ
 
@@ -396,6 +396,27 @@ async def test_retrain_model_data_error(mlflow):
     }
 
 
+@mark.asyncio
+async def test_retrain_model_data_error_no_minio_repository(mlflow):
+    mlflow.minio_repository = None
+
+    with raises(ValueError) as e:
+        await mlflow.retrain_model(
+            {
+                **metadata,
+                'object_key': 'test_object_key',
+                'model_name': 'test_model',
+                'model_config': {
+                    'target': 'target',
+                    'transform_flavor': 'sklearn',
+                    'predict_flavor': 'pyfunc',
+                },
+            }
+        )
+
+        assert str(e.value) == 'Minio repository not initialized'
+
+
 @mark.asyncio
 async def test_update_production_model(mlflow):
     input_data = {

tests/laborious/activities/test_storage.py

@@ -1,7 +1,7 @@
 import datetime
 from unittest.mock import ANY, AsyncMock, MagicMock, patch
 
-from pytest import fixture, mark
+from pytest import fixture, mark, raises
 from sientia_do.notifications.models import NotificationLevel
 from sientia_do.temporal.activities.postgres import Postgres
 
@@ -135,6 +135,16 @@ def test___init___done_repository(mock_minio_repository, storage):
     assert storage.minio_repository is not None
 
 
+@mark.asyncio
+async def test_query_to_minio_minio_repository_not_initialized(storage):
+    storage.minio_repository = None
+
+    with raises(ValueError) as e:
+        await storage.query_to_minio({})
+
+        assert str(e.value) == 'Minio repository not initialized'
+
+
 @mark.asyncio
 async def test_query_to_minio_not_data(storage):
     storage.load_custom_query = AsyncMock(return_value=None)