SIENTIAPDE-1646

Enhance MLFlow reference data handling and testing

- Updated the artifact handling in MLFlow to prioritize 'retrain_input.csv' over 'train_data.csv' when resolving reference data.
- Introduced new methods for resolving artifact names and locating downloaded CSV files.
- Modified the `get_reference_data` method to improve artifact resolution and error handling.
- Expanded unit tests to cover scenarios for missing artifacts and preference logic between retrain and train data CSVs.

e2e/test_drift.py

@@ -142,7 +142,7 @@ def _recent_minute_timestamps(count: int, offset_minutes: int = 6) -> list[str]:
 def _configure_reference_csv(mlflow_repository_stub, reference_rows: pd.DataFrame) -> None:
     """
     Wire ``mlflow_repository_stub`` so ``get_reference_data`` returns
-    ``reference_rows`` by writing them to ``dst_path/evaluation_data.csv``.
+    ``reference_rows`` by writing them to ``dst_path/retrain_input.csv``.
 
     Args:
      - mlflow_repository_stub: External MLflow repository fixture.
@@ -150,12 +150,16 @@ def _configure_reference_csv(mlflow_repository_stub, reference_rows: pd.DataFram
     """
 
     def _download(run_id: str, artifact_path: str, dst_path: str, metadata=None):
-        target = Path(dst_path) / 'evaluation_data.csv'
+        target = Path(dst_path) / artifact_path
+        target.parent.mkdir(parents=True, exist_ok=True)
         reference_rows.to_csv(target, index=False)
 
     mlflow_repository_stub._client.get_model_version_by_alias.return_value = MagicMock(
         run_id='fake-reference-run'
     )
+    file_info = MagicMock()
+    file_info.path = 'retrain_input.csv'
+    mlflow_repository_stub._client.list_artifacts.return_value = [file_info]
     mlflow_repository_stub.download_artifacts.side_effect = _download