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.

docs/scenarios.md

@@ -54,6 +54,8 @@ These scenarios test the business rule validations inside `validate_train_params
 | `test_scenario_2_1_5_unknown_model_type` | `model_type = 'totally_unknown_model'` | `'totally_unknown_model'` |
 | `test_scenario_2_1_6_missing_target_variable` | `target_variable = ''` | `'target_variable'` |
 | `test_scenario_2_1_7_missing_experiment_run_id` | Missing `experiment_run_id` | N/A (raises ValueError immediately) |
+| `test_scenario_2_1_8_missing_date_column` | Missing `date_column` | N/A (raises ValueError immediately) |
+| `test_scenario_2_1_9_whitespace_date_column` | `date_column = '   '` | `'date_column'` |
 
 ## 3. CleanupFiles Workflow (`test_cleanup_files_workflow.py`)
 

e2e/conftest.py

@@ -17,6 +17,7 @@ from concurrent.futures import ThreadPoolExecutor
 import base64
 import csv
 import io
+import os
 import shutil
 import tempfile
 import time
@@ -27,10 +28,10 @@ import pytest_asyncio
 import requests
 from minio import Minio
 from sqlalchemy import create_engine, text
-from testcontainers.core.container import DockerContainer
-from testcontainers.minio import MinioContainer
-from testcontainers.mongodb import MongoDbContainer
-from testcontainers.postgres import PostgresContainer
+from testcontainers.core.container import DockerContainer  # type: ignore[import-untyped]
+from testcontainers.minio import MinioContainer  # type: ignore[import-untyped]
+from testcontainers.mongodb import MongoDbContainer  # type: ignore[import-untyped]
+from testcontainers.postgres import PostgresContainer  # type: ignore[import-untyped]
 from temporalio.testing import WorkflowEnvironment
 from temporalio.worker import Worker
 
@@ -288,6 +289,12 @@ class DummyTransformer:
         pass
 """
 
+    # requirements.txt required by current model packaging path in training activity.
+    requirements_txt = """
+pandas
+numpy
+"""
+
     def push_file(path: str, content: str):
         encoded = base64.b64encode(content.encode()).decode()
         _gitea_api(
@@ -307,6 +314,7 @@ class DummyTransformer:
         push_file(f'{prefix}/schemas.yaml', schemas_yaml)
         push_file(f'{prefix}/wrapper.py', wrapper_py)
         push_file(f'{prefix}/model_logic.py', model_logic_py)
+        push_file(f'{prefix}/requirements.txt', requirements_txt.strip() + '\n')
         push_file(f'{prefix}/__init__.py', "")
 
     # Push runtime
@@ -317,7 +325,7 @@ class DummyTransformer:
 # Session-scoped containers
 # ---------------------------------------------------------------------------
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def postgres_container():
     """PostgreSQL 15 container for experiment_run table."""
     container = PostgresContainer('postgres:15')
@@ -326,7 +334,7 @@ def postgres_container():
     container.stop()
 
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def minio_container():
     """MinIO container for training CSV storage."""
     container = MinioContainer()
@@ -335,7 +343,7 @@ def minio_container():
     container.stop()
 
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def mongodb_container():
     """MongoDB container for CoreNotificationHandler."""
     container = MongoDbContainer('mongo:7')
@@ -344,7 +352,7 @@ def mongodb_container():
     container.stop()
 
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def gitea_container():
     """
     Gitea container with a ``model-store`` repo seeded via REST API
@@ -397,7 +405,7 @@ def gitea_container():
     container.stop()
 
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def mlflow_tracking_dir():
     """Local MLflow filesystem tracking directory (no network needed)."""
     tmpdir = tempfile.mkdtemp(prefix='mlflow-e2e-')
@@ -406,11 +414,51 @@ def mlflow_tracking_dir():
     shutil.rmtree(tmpdir, ignore_errors=True)
 
 
+@pytest.fixture(scope='session', autouse=True)
+def e2e_runtime_reports_dir():
+    """
+    Route runtime report artifacts to a writable temp directory during E2E.
+
+    Production defaults point to /var/lib/model-manager; in local CI/dev runs this
+    path may be unavailable. This fixture keeps the same code paths while avoiding
+    host permission issues.
+    """
+    import model_manager.runtime_paths as runtime_paths
+    import model_manager.utils.repository.data_manager_repository as data_repo_module
+
+    base_dir = tempfile.mkdtemp(prefix='model-manager-e2e-runtime-')
+    reports_root = f'{base_dir}/reports'
+    reports_temp_dir = f'{reports_root}/temp'
+    project_base_path = os.path.abspath(os.path.join(os.path.dirname(__file__), '..', 'model_manager'))
+
+    old_runtime_reports_root = runtime_paths.REPORTS_ROOT
+    old_runtime_reports_temp = runtime_paths.REPORTS_TEMP_DIR
+    old_runtime_project_base = runtime_paths.PROJECT_BASE_PATH
+    old_repo_reports_root = data_repo_module.REPORTS_ROOT
+    old_repo_project_base = data_repo_module.PROJECT_BASE_PATH
+
+    runtime_paths.REPORTS_ROOT = reports_root
+    runtime_paths.REPORTS_TEMP_DIR = reports_temp_dir
+    runtime_paths.PROJECT_BASE_PATH = project_base_path
+    data_repo_module.REPORTS_ROOT = reports_root
+    data_repo_module.PROJECT_BASE_PATH = project_base_path
+
+    try:
+        yield reports_root
+    finally:
+        runtime_paths.REPORTS_ROOT = old_runtime_reports_root
+        runtime_paths.REPORTS_TEMP_DIR = old_runtime_reports_temp
+        runtime_paths.PROJECT_BASE_PATH = old_runtime_project_base
+        data_repo_module.REPORTS_ROOT = old_repo_reports_root
+        data_repo_module.PROJECT_BASE_PATH = old_repo_project_base
+        shutil.rmtree(base_dir, ignore_errors=True)
+
+
 # ---------------------------------------------------------------------------
 # Session-scoped: seed MinIO with training CSV
 # ---------------------------------------------------------------------------
 
-@pytest_asyncio.fixture(scope='session', autouse=True)
+@pytest.fixture(scope='session', autouse=True)
 def upload_training_csv(minio_container, mlflow_tracking_dir):  # noqa: ARG001
     """
     Upload training CSV files to the MinIO container before any test runs.
@@ -479,7 +527,7 @@ def upload_training_csv(minio_container, mlflow_tracking_dir):  # noqa: ARG001
 # Function-scoped: database engine + schema setup
 # ---------------------------------------------------------------------------
 
-@pytest_asyncio.fixture
+@pytest.fixture
 def postgres_engine(postgres_container):
     """SQLAlchemy engine connected to the test PostgreSQL container."""
     engine = create_engine(postgres_container.get_connection_url())
@@ -487,7 +535,7 @@ def postgres_engine(postgres_container):
     engine.dispose()
 
 
-@pytest_asyncio.fixture(autouse=True)
+@pytest.fixture(autouse=True)
 def setup_experiment_run_table(postgres_engine):
     """
     Create the experiment_run table before each test and drop it afterwards
@@ -517,13 +565,13 @@ def setup_experiment_run_table(postgres_engine):
 # Observability (real sientia_do implementations)
 # ---------------------------------------------------------------------------
 
-@pytest_asyncio.fixture(scope='session')
+@pytest.fixture(scope='session')
 def e2e_logger():
     """Shared production-style Logger for the whole E2E session."""
     return get_logger('model-manager-e2e')
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 def metrics_controller(e2e_logger):
     """MetricsController bound to the E2E logger (fresh instance per test)."""
     return MetricsController(logger=e2e_logger)
@@ -533,7 +581,7 @@ def metrics_controller(e2e_logger):
 # Application fixtures
 # ---------------------------------------------------------------------------
 
-@pytest_asyncio.fixture
+@pytest.fixture
 def notification_handler(mongodb_container, e2e_logger):
     """
     Real CoreNotificationHandler connected to the MongoDB testcontainer.
@@ -549,7 +597,7 @@ def notification_handler(mongodb_container, e2e_logger):
     handler.shutdown()
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 def plugin_store(gitea_container, e2e_logger, metrics_controller, notification_handler):
     """
     Real PluginStore pointed at the Gitea testcontainer.
@@ -569,7 +617,7 @@ def plugin_store(gitea_container, e2e_logger, metrics_controller, notification_h
     yield store
 
 
-@pytest_asyncio.fixture
+@pytest.fixture
 def test_activities(
     postgres_container,
     minio_container,

e2e/test_train_model_validation.py

@@ -246,3 +246,53 @@ async def test_scenario_2_1_7_missing_experiment_run_id(
         )
     combined = _exception_chain_text(excinfo.value)
     assert 'experiment_run_id' in combined
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_8_missing_date_column(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+):
+    """Scenario 2.1.8 – date_column missing in payload raises before workflow business validation."""
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {k: v for k, v in scenario.items() if k != 'date_column'}
+
+    with pytest.raises(WorkflowFailureError) as excinfo:
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-8'),
+        )
+    combined = _exception_chain_text(excinfo.value)
+    assert 'date_column' in combined
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_scenario_2_1_9_whitespace_date_column(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    postgres_engine,
+):
+    """Scenario 2.1.9 – date_column='   ' must produce ORCHESTRATOR_VALIDATION_ERROR."""
+    experiment_run_id = _VALIDATION_ID_BASE + 9
+    scenario = load_scenario('01-linear-regression-basic.json')
+    scenario = {**scenario, 'experiment_run_id': experiment_run_id, 'date_column': '   '}
+    insert_experiment_run(postgres_engine, experiment_run_id)
+
+    with pytest.raises(Exception):
+        await start_and_await_workflow(
+            temporal_test_env.client,
+            TrainModel.run,
+            scenario,
+            make_workflow_id('test-s2-1-9'),
+        )
+
+    assert_experiment_error(
+        postgres_engine,
+        experiment_run_id,
+        expected_status='ORCHESTRATOR_VALIDATION_ERROR',
+        error_substr='date_column',
+    )

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}')
 
+        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')

models/linear_regression/.cache_updated_at

@@ -1 +0,0 @@
-1777925550

models/linear_regression/index.yaml

@@ -1,14 +0,0 @@
-
-name: "linear_regression"
-version: 1
-runtime: "basic"
-path: "wrapper.py"
-class: "DummyWrapper"
-model:
-  class: "DummyModel"
-  path: "model_logic.py"
-  external: false
-data_model:
-  class: "DummyTransformer"
-  path: "model_logic.py"
-  external: false

models/linear_regression/model_logic.py

@@ -1,8 +0,0 @@
-
-class DummyModel:
-    def __init__(self, **kwargs):
-        pass
-
-class DummyTransformer:
-    def __init__(self, **kwargs):
-        pass

models/linear_regression/schemas.yaml

@@ -1,10 +0,0 @@
-
-model:
-  type: object
-  properties: {}
-data_model:
-  type: object
-  properties: {}
-opt_params:
-  type: object
-  properties: {}

models/linear_regression/wrapper.py

@@ -1,27 +0,0 @@
-
-from sientia_model.wrappers.sientia_model import SientiaModel
-import pandas as pd
-import numpy as np
-from typing import Any
-
-class DummyWrapper(SientiaModel):
-    def _predict(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
-        self._log("info", f"Predicting dummy model for {self.model_type}")
-        # Return a simple prediction (mean or 0.5) to allow metrics computation
-        preds = pd.DataFrame({self.target: [0.5] * len(data)}, index=data.index)
-        return preds, {}
-        
-    def _transform(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
-        return data, {}
-        
-    def _train_transformer(self, train_data: pd.DataFrame, val_data: pd.DataFrame) -> None:
-        pass
-        
-    def _train_model(self, x: pd.DataFrame, y: pd.DataFrame, x_val: pd.DataFrame | None = None, y_val: pd.DataFrame | None = None) -> None:
-        self.target = y.columns[0]
-        
-    def _retrain_transformer(self, data: pd.DataFrame) -> None:
-        pass
-        
-    def _retrain_model(self, x: pd.DataFrame, y: pd.DataFrame | None) -> None:
-        pass

models/polynomial_regression/.cache_updated_at

@@ -1 +0,0 @@
-1777925551

models/polynomial_regression/index.yaml

@@ -1,14 +0,0 @@
-
-name: "polynomial_regression"
-version: 1
-runtime: "basic"
-path: "wrapper.py"
-class: "DummyWrapper"
-model:
-  class: "DummyModel"
-  path: "model_logic.py"
-  external: false
-data_model:
-  class: "DummyTransformer"
-  path: "model_logic.py"
-  external: false

models/polynomial_regression/model_logic.py

@@ -1,8 +0,0 @@
-
-class DummyModel:
-    def __init__(self, **kwargs):
-        pass
-
-class DummyTransformer:
-    def __init__(self, **kwargs):
-        pass

models/polynomial_regression/schemas.yaml

@@ -1,10 +0,0 @@
-
-model:
-  type: object
-  properties: {}
-data_model:
-  type: object
-  properties: {}
-opt_params:
-  type: object
-  properties: {}

models/polynomial_regression/wrapper.py

@@ -1,27 +0,0 @@
-
-from sientia_model.wrappers.sientia_model import SientiaModel
-import pandas as pd
-import numpy as np
-from typing import Any
-
-class DummyWrapper(SientiaModel):
-    def _predict(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
-        self._log("info", f"Predicting dummy model for {self.model_type}")
-        # Return a simple prediction (mean or 0.5) to allow metrics computation
-        preds = pd.DataFrame({self.target: [0.5] * len(data)}, index=data.index)
-        return preds, {}
-        
-    def _transform(self, data: pd.DataFrame) -> tuple[pd.DataFrame, dict[str, Any]]:
-        return data, {}
-        
-    def _train_transformer(self, train_data: pd.DataFrame, val_data: pd.DataFrame) -> None:
-        pass
-        
-    def _train_model(self, x: pd.DataFrame, y: pd.DataFrame, x_val: pd.DataFrame | None = None, y_val: pd.DataFrame | None = None) -> None:
-        self.target = y.columns[0]
-        
-    def _retrain_transformer(self, data: pd.DataFrame) -> None:
-        pass
-        
-    def _retrain_model(self, x: pd.DataFrame, y: pd.DataFrame | None) -> None:
-        pass

tests/activities/test_cleanup.py

@@ -125,7 +125,7 @@ def test_cleanup_temp_directories_nonexistent_path(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
     cleanup.warning = MagicMock()
 
     cleanup.cleanup_temp_directories({'temp_path': '/nonexistent/path', 'metadata': {}})
@@ -152,7 +152,7 @@ def test_cleanup_temp_directories_success_with_deletions(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
 
     old_time = (datetime.now() - timedelta(hours=48)).strftime('%Y%m%d_%H%M%S_000000')
     old_dir = os.path.join(temp_dir, f'old_dir_{old_time}')
@@ -187,7 +187,7 @@ def test_cleanup_temp_directories_dry_run(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
 
     old_time = (datetime.now() - timedelta(hours=48)).strftime('%Y%m%d_%H%M%S_000000')
     old_dir = os.path.join(temp_dir, f'old_dir_{old_time}')
@@ -217,7 +217,7 @@ def test_cleanup_temp_directories_delete_error(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
     cleanup.error = MagicMock()
 
     old_time = (datetime.now() - timedelta(hours=48)).strftime('%Y%m%d_%H%M%S_000000')
@@ -276,7 +276,7 @@ def test_cleanup_temp_directories_with_files_and_unmatched_dirs(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
     cleanup.debug = MagicMock()
 
     # Create a file and a directory with a non-matching name
@@ -310,7 +310,7 @@ def test_cleanup_temp_directories_invalid_timestamp_format(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
     cleanup.error = MagicMock()
 
     # Create a directory with a malformed timestamp that matches the regex but fails parsing
@@ -340,7 +340,7 @@ def test_cleanup_temp_directories_generic_exception(
         notification_handler=mock_notification_handler,
         metrics_controller=mock_metrics_controller,
     )
-    cleanup._emit_metrics = MagicMock()
+    cleanup._emit_metrics = MagicMock()  # type: ignore[method-assign]
     cleanup.send_notification = MagicMock()
 
     with patch('os.listdir', side_effect=Exception('Unexpected OS Error')):

tests/activities/test_experiment_tracking.py

@@ -136,6 +136,11 @@ def test_experiment_tracking_del_with_engine_exception(
     et.engine = MagicMock()
 
     class MockSuperWithError:
+        _should_raise: bool
+
+        def __init__(self) -> None:
+            self._should_raise = False
+
         def __del__(self):
             # Only raise error if not being cleaned up by garbage collector
             # This prevents the PytestUnraisableExceptionWarning
@@ -215,7 +220,7 @@ def test_update_experiment_run_status_success(
         mock_execute(*args, **kwargs)
         return {'rowcount': 1}
 
-    et._execute_update = mock_execute_update
+    et._execute_update = mock_execute_update  # type: ignore[method-assign]
     et.info = MagicMock()
 
     input_data = {
@@ -293,7 +298,7 @@ def test_update_experiment_run_status_with_error_success(
         mock_execute(*args, **kwargs)
         return {'rowcount': 1}
 
-    et._execute_update = mock_execute_update
+    et._execute_update = mock_execute_update  # type: ignore[method-assign]
     et.info = MagicMock()
 
     input_data = {
@@ -339,7 +344,7 @@ def test_update_experiment_run_status_with_error_truncate_message(
         mock_execute(*args, **kwargs)
         return {'rowcount': 1}
 
-    et._execute_update = mock_execute_update
+    et._execute_update = mock_execute_update  # type: ignore[method-assign]
     et.info = MagicMock()
 
     long_error = 'x' * 2000
@@ -416,7 +421,7 @@ def test_update_experiment_run_model_saved_success(
         mock_execute(*args, **kwargs)
         return {'rowcount': 1}
 
-    et._execute_update = mock_execute_update
+    et._execute_update = mock_execute_update  # type: ignore[method-assign]
     et.info = MagicMock()
 
     input_data = {
@@ -526,7 +531,7 @@ def test_update_experiment_run_no_rows_updated(
     def mock_execute_update(*args, **kwargs):
         return {'rowcount': 0}
 
-    et._execute_update = mock_execute_update
+    et._execute_update = mock_execute_update  # type: ignore[method-assign]
     et.send_notification = MagicMock()
 
     input_data = {

tests/activities/test_training.py

@@ -131,13 +131,15 @@ def test_train_model_success_serializes_result(mock_mlflow, training):
 
     training.minio_repository.download_file = MagicMock(return_value=b'csv')
     training.data_manager_repository.prepare_training_data = MagicMock(return_value=tmr)
+
+    def _set_metrics(x, _w, **_kw):
+        x.mse_val = 0.1
+        x.mae_val = 0.2
+        x.r2_val = 0.9
+        return x
+
     training.data_manager_repository.compute_regression_metrics = MagicMock(
-        side_effect=lambda x, _w, **_kw: (
-            setattr(x, 'mse_val', 0.1),
-            setattr(x, 'mae_val', 0.2),
-            setattr(x, 'r2_val', 0.9),
-            x,
-        )[-1]
+        side_effect=_set_metrics
     )
 
     def _fill_report(x, **_kw):

tests/conftest.py

@@ -21,7 +21,7 @@ def _stub_evidently() -> None:
     sys.modules['evidently'] = ev
 
     mp = ModuleType('evidently.metric_preset')
-    mp.DataDriftPreset = _make_dummy('DataDriftPreset')
+    mp.DataDriftPreset = _make_dummy('DataDriftPreset')  # type: ignore[attr-defined]
     sys.modules['evidently.metric_preset'] = mp
 
     metrics = ModuleType('evidently.metrics')
@@ -47,22 +47,22 @@ def _stub_evidently() -> None:
     def generate_column_metrics(*_a, **_k):
         return []
 
-    base.generate_column_metrics = generate_column_metrics
+    base.generate_column_metrics = generate_column_metrics  # type: ignore[attr-defined]
     sys.modules['evidently.metrics.base_metric'] = base
 
     opt = ModuleType('evidently.options')
-    opt.ColorOptions = _make_dummy('ColorOptions')
+    opt.ColorOptions = _make_dummy('ColorOptions')  # type: ignore[attr-defined]
     sys.modules['evidently.options'] = opt
 
     pipeline = ModuleType('evidently.pipeline')
     sys.modules['evidently.pipeline'] = pipeline
 
     colmap = ModuleType('evidently.pipeline.column_mapping')
-    colmap.ColumnMapping = _make_dummy('ColumnMapping')
+    colmap.ColumnMapping = _make_dummy('ColumnMapping')  # type: ignore[attr-defined]
     sys.modules['evidently.pipeline.column_mapping'] = colmap
 
     rep = ModuleType('evidently.report')
-    rep.Report = _make_dummy('Report')
+    rep.Report = _make_dummy('Report')  # type: ignore[attr-defined]
     sys.modules['evidently.report'] = rep
 
 
@@ -82,9 +82,9 @@ def pytest_configure(config) -> None:  # noqa: ARG001
         def treat_nan(input_data, *_a, **_k):
             return input_data
 
-        df_pre.create_features = create_features
-        df_pre.limit_dataset = limit_dataset
-        df_pre.treat_nan = treat_nan
+        df_pre.create_features = create_features  # type: ignore[attr-defined]
+        df_pre.limit_dataset = limit_dataset  # type: ignore[attr-defined]
+        df_pre.treat_nan = treat_nan  # type: ignore[attr-defined]
         sys.modules['sientia_do.operations.df_preprocessor'] = df_pre
 
     sys.modules.setdefault('sientia_do.operations', ModuleType('sientia_do.operations'))
@@ -97,7 +97,7 @@ def pytest_configure(config) -> None:  # noqa: ARG001
 
             pass
 
-        ts_an.TimeSeriesDiscontinuityAnalyzer = TimeSeriesDiscontinuityAnalyzer
+        ts_an.TimeSeriesDiscontinuityAnalyzer = TimeSeriesDiscontinuityAnalyzer  # type: ignore[attr-defined]
         sys.modules['sientia_do.timeseries.analyzer'] = ts_an
 
     sys.modules.setdefault('sientia_do.timeseries', ModuleType('sientia_do.timeseries'))

tests/sientia/test_reports.py

@@ -128,7 +128,10 @@ def test_add_data_quality_section_with_run(monkeypatch, tmp_path, stub_color_opt
     ReportMock.assert_called_once_with(
         metrics=[summary, column_metrics, conflict, correlations], options=report.options
     )
-    report_instance.run.assert_called_once_with(reference_data='ref', current_data='cur')
+    run_kwargs = report_instance.run.call_args.kwargs
+    assert run_kwargs['reference_data'] == 'ref'
+    assert run_kwargs['current_data'] == 'cur'
+    assert run_kwargs['column_mapping'].target == 'target'
     report_instance.save_html.assert_called_once_with(
         os.path.join(str(tmp_path), 'data_quality.html')
     )
@@ -160,6 +163,34 @@ def test_add_data_quality_section_run_without_base_path(monkeypatch, stub_color_
     report_instance.save_html.assert_not_called()
 
 
+def test_add_data_quality_section_non_default_target_keeps_conflict_metric(
+    monkeypatch, stub_color_options
+):
+    summary = object()
+    column_metrics = object()
+    conflict = object()
+    correlations = object()
+
+    monkeypatch.setattr(reports, 'DatasetSummaryMetric', lambda: summary)
+    monkeypatch.setattr(
+        reports,
+        'generate_column_metrics',
+        lambda *args, **kwargs: column_metrics,
+    )
+    monkeypatch.setattr(reports, 'ConflictTargetMetric', lambda: conflict)
+    monkeypatch.setattr(reports, 'DatasetCorrelationsMetric', lambda: correlations)
+
+    report = reports.Reports(reference_data='ref', current_data='cur', target_name='sales')
+    report.add_data_quality_section(columns=['c1'], run=False)
+
+    assert report.metrics[-4:] == [
+        summary,
+        column_metrics,
+        conflict,
+        correlations,
+    ]
+
+
 def test_add_data_drift_section_paths(monkeypatch, tmp_path, stub_color_options):
     drift_instances = [object(), object(), object()]
     DataDriftPresetMock = MagicMock(side_effect=drift_instances)
@@ -180,7 +211,10 @@ def test_add_data_drift_section_paths(monkeypatch, tmp_path, stub_color_options)
     report.add_data_drift_section(columns=['c1'], run=True)
     assert report.sections['data_drift'] == {'result': 'data_drift'}
     ReportMock.assert_called_with(metrics=[drift_instances[2]], options=report.options)
-    report_instance.run.assert_called_with(reference_data='ref', current_data='cur')
+    run_kwargs = report_instance.run.call_args.kwargs
+    assert run_kwargs['reference_data'] == 'ref'
+    assert run_kwargs['current_data'] == 'cur'
+    assert run_kwargs['column_mapping'].target == 'target'
     report_instance.save_html.assert_called_with(os.path.join(str(tmp_path), 'data_drift.html'))
 
 
@@ -273,10 +307,12 @@ def test_set_color_options_appends(monkeypatch):
     report = reports.Reports(reference_data='ref', current_data='cur', target_name='target')
     report.set_color_options(primary_color='#111', secondary_color='#222')
 
-    assert len(report.options) == 2
+    options = report.options
+    assert options is not None
+    assert len(options) == 2
     assert calls[0]['primary_color'] == '#0F4C81'
     assert calls[1]['primary_color'] == '#111'
-    assert report.options[1]['secondary_color'] == '#222'
+    assert options[1]['secondary_color'] == '#222'
 
 
 def test_save_all_sections_html_requires_base_path(stub_color_options):

tests/utils/models/test_experiment_status.py

@@ -46,7 +46,7 @@ def test_experiment_status_comparison():
     assert ExperimentStatus.ORCHESTRATOR_VALIDATION_ERROR == 'ORCHESTRATOR_VALIDATION_ERROR'
     assert ExperimentStatus.ORCHESTRATOR_WAITING_PROC == 'ORCHESTRATOR_WAITING_PROC'
     assert ExperimentStatus.TRAINING_SUCCESS == 'TRAINING_SUCCESS'
-    assert ExperimentStatus.TRAINING_ERROR != 'TRAINING_SUCCESS'
+    assert str(ExperimentStatus.TRAINING_ERROR) != 'TRAINING_SUCCESS'
 
 
 def test_experiment_status_access_by_name():

tests/utils/repository/test_data_manager_repository.py

@@ -476,6 +476,35 @@ def test_generate_report_success(tmp_path):
             json.load(f)
 
 
+def test_generate_report_adds_target_alias_for_reports(tmp_path):
+    repo = dmr.DataManagerRepository(MagicMock())
+    p = TrainModelParams.from_dict(_minimal_dict_for_prepare())
+    tmr = TrainModelResult(
+        params=p,
+        train_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
+        val_data=pd.DataFrame({'v1': [1.0, 2.0], 't': [1.0, 2.0]}),
+        y_train_pred=pd.DataFrame({'t': [1.0, 2.0]}),
+        y_pred=pd.DataFrame({'t': [1.0, 2.0]}),
+        run_name='testrun',
+    )
+
+    with (
+        patch.object(repo, '_get_reports_directory', return_value=str(tmp_path)),
+        patch('model_manager.utils.repository.data_manager_repository.Reports') as mrep,
+    ):
+        instance = mrep.return_value
+        instance.save_all_sections_html = Mock()
+        repo.generate_report(tmr, {})
+
+        kwargs = mrep.call_args.kwargs
+        reference_data = kwargs['reference_data']
+        current_data = kwargs['current_data']
+        assert 'target' in reference_data.columns
+        assert 'target' in current_data.columns
+        assert reference_data['target'].equals(reference_data['t'])
+        assert current_data['target'].equals(current_data['t'])
+
+
 def test_generate_report_skips_equation_file_when_not_linear(tmp_path):
     repo = dmr.DataManagerRepository(MagicMock())
     p = TrainModelParams.from_dict(_minimal_dict_for_prepare())

tests/workflows/test_cleanup_files.py

@@ -1,6 +1,5 @@
 """Unit tests for the CleanupFiles workflow."""
 
-import os
 from unittest.mock import AsyncMock, patch
 
 import pytest
@@ -18,7 +17,6 @@ async def test_cleanup_files_workflow(mock_workflow_module):
 
     # Instantiate and run the workflow
     workflow_instance = CleanupFiles()
-    with patch.dict(os.environ, {'POD_ID': 'temporal-pod'}):
     await workflow_instance.run({})
 
     # Verify that the activities were called with the correct parameters
@@ -28,7 +26,5 @@ async def test_cleanup_files_workflow(mock_workflow_module):
     # Check cleanup_temp_directories call
     local_call_args = calls[0][0][1]
     assert local_call_args['temp_path'] == REPORTS_TEMP_DIR
-    assert local_call_args['metadata'] == {
-        'pod_id': 'temporal-pod',
-        'workflow_name': 'cleanup_files',
-    }
+    assert local_call_args['metadata']['workflow_name'] == 'cleanup_files'
+    assert 'pod_id' in local_call_args['metadata']

tests/workflows/test_train_model.py

@@ -3,6 +3,7 @@
 from unittest.mock import AsyncMock, Mock, patch
 
 import pytest
+from temporalio.exceptions import ApplicationError
 
 from model_manager.utils.models.experiment_status import ExperimentStatus
 from model_manager.utils.models.train_model_params import TrainModelParams
@@ -295,7 +296,7 @@ async def test_run_missing_experiment_run_id(mock_wf):
     from model_manager.workflows.train_model import TrainModel
 
     mock_wf.logger = Mock()
-    with pytest.raises(ValueError, match='experiment_run_id is required'):
+    with pytest.raises(ApplicationError, match='experiment_run_id is required'):
         await TrainModel().run({})