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.

laborious/activities/gates.py

@@ -3,8 +3,6 @@ from temporalio import activity, workflow
 with workflow.unsafe.imports_passed_through():
     import traceback
     from collections.abc import Callable, Mapping
-    from os import path
-    from shutil import rmtree
     from typing import Any
 
     from pandas import DataFrame
@@ -628,19 +626,3 @@ class Gates(BaseActivity):
         ).observe(response_time)
 
         self.info(f'Metrics written for model {metadata["model_name"]}', metadata)
-
-    @activity.defn(name='clean_tmp_files')
-    async def clean_tmp_files(self, input_data: dict[str, Any]):
-        """
-        Clean temporary files in the tmp directory.
-        """
-        model_name = input_data['model_name']
-        metadata = input_data['metadata']
-        self.info(f'Cleaning tmp files for model {model_name}...', metadata)
-
-        if path.exists(f'tmp/retrain_data/{model_name}'):
-            rmtree(f'tmp/retrain_data/{model_name}')
-        if path.exists(f'tmp/artifacts/{model_name}'):
-            rmtree(f'tmp/artifacts/{model_name}')
-
-        self.info('Tmp files cleaned', metadata)

laborious/utils/repository/model_repository.py

@@ -304,7 +304,7 @@ class MLFlowRepository:
             if model_type == 'predict':
                 model = self.load_predict_model(model_name, flavor)
 
-            elif model_type == 'transform':
+            else:
                 model = self.load_transform_model(model_name, flavor)
 
         return model, artifact_path

laborious/utils/repository/opc_repository.py

@@ -92,14 +92,11 @@ class OpcRepository:
             - Session Timeout: 10,000,000 ms
         """
 
-        if not all([self.cert_path, self.private_key_path]):
+        if self.cert_path is None or self.private_key_path is None:
             raise ValueError(
                 'Certificate and private key paths must be provided for secure connection.'
             )
 
-        if self.cert_path is None or self.private_key_path is None:
-            raise ValueError('Certificate and private key paths cannot be None')
-
         cert = Path(self.cert_path)
         private_key = Path(self.private_key_path)
         server_cert = Path(self.server_cert_path) if self.server_cert_path else None
@@ -316,14 +313,8 @@ class OpcRepository:
         start_time = time.time()
 
         try:
-            if self.client is None:
-                return False, {
-                    'notification_id': f'OPC_WRITE_GET_NODE_ERROR_{self.id}',
-                    'message': 'Client is not initialized',
-                    'block': 'opc_repository',
-                    'level': NotificationLevel.ERROR,
-                }
-            node_obj = self.client.get_node(node)
+            # ignored because self.validate_connection is called before, so we know self.client is not None
+            node_obj = self.client.get_node(node)  # type: ignore[union-attr]
         except Exception as e:
             trace = traceback.format_exc()
             logger.custom_error(trace, metadata.get('schedule_name', 'N/A'))

laborious/workflows/minimal_retrain.py

@@ -116,6 +116,7 @@ class MinimalRetrain:
                 **metadata,
                 'experiment_response': experiment_response,
                 'model_name': model_name,
+                'model_id': input_data['model_id'],
                 'update_report': update_report,
             },
             retry_policy=retry_policy,