feat: integrate PluginStore and MinIO repository into model manager activities

- Added PluginStore integration for model management.
- Replaced StorageRepository with MinIORepository in Activities, Cleanup, and Training classes.
- Updated training logic to handle validation files and improved data management.
- Enhanced configuration for MinIO and PluginStore in connectors.
- Removed deprecated model repository and storage repository files.
- Updated environment variable handling for new configurations.

scripts/run_training_test.py

@@ -289,17 +289,18 @@ def run_local_pipeline(
     csv_path: Path,
     save_mlflow: bool = False,
 ) -> dict:
-    """Run the same training pipeline locally (validate + train + after_train).
+    """Run the same training pipeline locally (validate + train + metrics).
 
-    Reads CSV from disk, runs TrainingRepository.train and after_train_calculation.
-    Optionally saves to MLflow if save_mlflow is True (requires MLflow env).
+    Reads CSV from disk, runs DataManagerRepository.prepare_training_data and
+    compute_regression_metrics. Optionally saves to MLflow if save_mlflow is
+    True (requires MLflow env).
 
     Returns:
         dict: {'success': bool, 'error': str | None, 'scenario': str, ...}
     """
     from model_manager.utils.logger_helper import get_logger
     from model_manager.utils.models.train_model_params import TrainModelParams
-    from model_manager.utils.repository.training_repository import TrainingRepository
+    from model_manager.utils.repository.data_manager_repository import DataManagerRepository
 
     result = {
         'scenario': scenario_name,
@@ -327,14 +328,22 @@ def run_local_pipeline(
         return result
 
     logger = get_logger(__name__)
-    training_repository = TrainingRepository(logger)
+    data_manager_repository = DataManagerRepository(logger)
 
     with open(csv_path, 'rb') as f:
         file_content = BytesIO(f.read())
 
     try:
-        train_result = training_repository.train(file_content, train_params)
-        train_result = training_repository.after_train_calculation(train_params, train_result)
+        train_result = data_manager_repository.prepare_training_data(
+            train_file_bytes=file_content.getvalue(),
+            validation_file_bytes=None,
+            params=train_params,
+            metadata={'source': 'run_local_pipeline', 'scenario': scenario_name},
+        )
+        train_result = data_manager_repository.compute_regression_metrics(
+            train_params,
+            train_result,
+        )
     except Exception as e:
         result['error'] = str(e)
         raise  # re-raise so caller gets full traceback for diagnosis