feat: enhance E2E testing setup and model reporting

- Added a new fixture to manage runtime report artifacts in a writable temp directory during E2E tests, addressing permission issues in local CI/dev environments.
- Updated `conftest.py` to include a requirements.txt file in the model packaging path for training activities.
- Refactored existing fixtures to use `pytest.fixture` instead of `pytest_asyncio.fixture` for better compatibility.
- Enhanced the `Reports` class to include a target alias for report metrics, ensuring compatibility with Evidently's reporting requirements.
- Introduced new test scenarios to validate the handling of missing and whitespace-only `date_column` inputs in the training workflow.

These changes improve the robustness of the E2E testing framework and enhance the clarity of model reporting metrics.

model_manager/sientia/reports.py

@@ -111,8 +111,14 @@ class Reports:
         ]
         self.metrics.extend(metrics)
         if run:
+            mapping = ColumnMapping()
+            mapping.target = self.target_name
             report = Report(metrics=metrics, options=self.options)
-            report.run(reference_data=self.ref_data, current_data=self.cur_data)
+            report.run(
+                reference_data=self.ref_data,
+                current_data=self.cur_data,
+                column_mapping=mapping,
+            )
             self.sections['data_quality'] = report.as_dict()
             if self.base_path:
                 # Note: Relies on Evidently's save_html() to properly manage file I/O
@@ -128,8 +134,14 @@ class Reports:
         """
         self.metrics.append(DataDriftPreset(columns=columns))
         if run:
+            mapping = ColumnMapping()
+            mapping.target = self.target_name
             report = Report(metrics=[DataDriftPreset(columns=columns)], options=self.options)
-            report.run(reference_data=self.ref_data, current_data=self.cur_data)
+            report.run(
+                reference_data=self.ref_data,
+                current_data=self.cur_data,
+                column_mapping=mapping,
+            )
             self.sections['data_drift'] = report.as_dict()
             if self.base_path:
                 # Note: Relies on Evidently's save_html() to properly manage file I/O

model_manager/utils/repository/data_manager_repository.py

@@ -565,6 +565,13 @@ class DataManagerRepository(SientiaMonitoring):
         current_data = y_val_pred[['prediction']].join(data.val_data, how='inner')
         current_data_float = current_data.astype(np.float64)
 
+        # Evidently's ConflictTargetMetric expects a literal `target` column name.
+        # Keep the original target column and provide this alias for report metrics.
+        target_col = data.params.target_variable
+
+        reference_data_float['target'] = reference_data_float[target_col]
+        current_data_float['target'] = current_data_float[target_col]
+
         # Initialize report generator
         base_path = self._get_reports_directory()
         data.run_dir = self._create_run_directory(base_path, data.run_name)
@@ -581,7 +588,6 @@ class DataManagerRepository(SientiaMonitoring):
         )
 
         # Generate report sections
-        target_col = data.params.target_variable
         feature_and_target_cols = data.params.variable_columns + [target_col]
         report.add_data_quality_section(columns=feature_and_target_cols)
         report.add_data_drift_section(columns=feature_and_target_cols)

model_manager/workflows/cleanup_files.py

@@ -17,6 +17,7 @@ with workflow.unsafe.imports_passed_through():
     from model_manager.workflows.train_model import no_retry_policy
 
     TIMEOUT_CLEANUP_LOCAL = int(os.getenv('TIMEOUT_CLEANUP_LOCAL', '120'))
+    POD_ID = os.getenv('POD_ID')
 
 
 @workflow.defn(name='cleanup_files')
@@ -46,7 +47,7 @@ class CleanupFiles:
         # Metadata for tracking
         metadata = {
             'metadata': {
-                'pod_id': os.getenv('POD_ID'),
+                'pod_id': POD_ID,
                 'workflow_name': 'cleanup_files',
             }
         }

model_manager/workflows/train_model.py

@@ -17,6 +17,7 @@ with workflow.unsafe.imports_passed_through():
     from typing import Any
 
     from temporalio.common import RetryPolicy
+    from temporalio.exceptions import ApplicationError
 
     from model_manager.activities.activities import Activities
     from model_manager.activities.experiment_tracking import UpdateType
@@ -95,7 +96,11 @@ class TrainModel:
         """
         workflow.logger.info(f'Starting train_model workflow for {input_data}')
 
-        experiment_run_id = self._validate_experiment_run_id(input_data)
+        try:
+            experiment_run_id = self._validate_experiment_run_id(input_data)
+        except ValueError as exc:
+            # Prevent workflow-task retries on deterministic input contract violations.
+            raise ApplicationError(str(exc), non_retryable=True) from exc
         input_data = {**input_data, 'experiment_run_id': experiment_run_id}
 
         model_name = input_data.get('model_name')