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.

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/scenarios.md

@@ -1,64 +0,0 @@
-# E2E Test Scenarios
-
-This document maps the workflow scenarios tested in the E2E suite to their corresponding JSON input files and expected behaviors.
-
-## Infrastructure (second-pass review)
-
-- **Containers:** PostgreSQL, MinIO, MongoDB, and Gitea via testcontainers; real clients and `Activities` code paths.
-- **MLflow:** `file://` tracking URI (real SDK, no remote server).
-- **Temporal:** `WorkflowEnvironment.start_time_skipping()` — official temporalio test runtime; workflows and activities are not stubbed.
-- **Logging/metrics:** `get_logger` + `MetricsController` (sientia_do); no `unittest.mock` for observability in `e2e/conftest.py`.
-- **Unit tests** under `tests/` may still use mocks where appropriate; that policy is separate from this E2E suite.
-
-## 1. TrainModel Workflow (`test_train_model_workflow.py`)
-
-### 1.1 Happy Paths (Successful execution)
-
-| Test Function | Input JSON | Expected Status | Description |
-|---|---|---|---|
-| `test_scenario_1_1_1_linear_regression_basic` | `01-linear-regression-basic.json` | `TRAINING_SUCCESS` | Basic linear regression without scaler. Verifies end-to-end pipeline. |
-| `test_scenario_1_1_2_linear_regression_with_scaler` | `02-linear-regression-with-scaler.json` | `TRAINING_SUCCESS` | Linear regression with `Standard Scaler`. |
-| `test_scenario_1_1_3_polynomial_regression_degree2_with_scaler` | `03-polynomial-regression-degree2.json` | `TRAINING_SUCCESS` | Polynomial regression (degree 2) with Standard Scaler. |
-| `test_scenario_1_1_4_polynomial_regression_degree3_with_scaler` | `04-polynomial-regression-degree3.json` | `TRAINING_SUCCESS` | Polynomial regression (degree 3) with Standard Scaler. |
-| `test_scenario_1_1_5_linear_regression_with_lags` | `05-linear-regression-with-lags.json` | `TRAINING_SUCCESS` | Linear regression with `lag_train`/`lag_val` per variable. |
-| `test_scenario_1_1_6_linear_regression_nan_interpolation` | `06-linear-regression-nan-interpolation.json` | `TRAINING_SUCCESS` | Linear regression with `nan_treatment='linear interpolation'`. |
-| `test_scenario_1_1_7_linear_regression_static_window_removal` | `07-linear-regression-static-window-removal.json` | `TRAINING_SUCCESS` | `rem_static_win=true` with default `static_threshold`. |
-| `test_scenario_1_1_8_linear_regression_with_limits` | `08-linear-regression-with-limits.json` | `TRAINING_SUCCESS` | `support_filters` with `min`/`max` per variable. |
-| `test_scenario_1_1_9_polynomial_degree2_scaler_and_lags` | `09-polynomial-degree2-with-scaler-and-lags.json` | `TRAINING_SUCCESS` | Polynomial (degree 2), Standard Scaler, and lags. |
-| `test_scenario_1_1_10_linear_regression_with_ar_opt_params` | `10-linear-regression-with-ar.json` | `TRAINING_SUCCESS` | `opt_params.include_ar=true` (placeholder for future AR behavior). |
-| `test_scenario_1_1_11_linear_regression_static_threshold_custom` | `11-linear-regression-static-threshold-custom.json` | `TRAINING_SUCCESS` | `rem_static_win=true` with custom `static_threshold`. |
-| `test_scenario_1_1_12_alternate_date_format_dd_mm_yyyy` | `12-angular-test-date-format.json` | `TRAINING_SUCCESS` | `date_column=DATA`, `dd/MM/yyyy` format, object `training_data_dd_mm_yyyy.csv`. |
-| `test_scenario_1_1_13_alternate_csv_narrow_date_window` | `13-angular-test-double-date-column.json` | `TRAINING_SUCCESS` | Same alternate CSV with a bounded `start_date`/`end_date` window. |
-| `test_scenario_1_1_14_polynomial_with_support_filters` | `14-angular-test-polynomial-support-filters.json` | `TRAINING_SUCCESS` | Polynomial (degree 4), scaler, `upper_line`/`lower_line` support filters. |
-| `test_scenario_1_1_15_linear_regression_custom_target_column_name` | `15-linear-regression-custom-target-column.json` | `TRAINING_SUCCESS` | Custom `target_variable` column name (not literal ``target``); Evidently/report columns must match. |
-| `test_scenario_1_1_16_naive_timestamp_header_column` | `16-linear-regression-naive-timestamp-header.json` | `TRAINING_SUCCESS` | `date_column`=`Timestamp`, naive CSV `training_data_timestamp_naive.csv`. |
-| `test_scenario_1_1_17_linear_regression_blank_timestamp_row_dropped` | `17-linear-regression-blank-timestamp-row.json` | `TRAINING_SUCCESS` | One empty timestamp cell; row dropped before index. |
-
-### 1.2 Error Paths
-
-| Test Function | Input JSON | Expected Status | Description |
-|---|---|---|---|
-| `test_scenario_1_2_1_minio_file_not_found` | `01-linear-regression-basic.json` | `TRAINING_ERROR` | MinIO file does not exist. Workflow fails during file download. |
-| `test_scenario_1_2_2_experiment_run_id_not_in_db` | `01-linear-regression-basic.json` | N/A (raises Exception) | `experiment_run_id` does not exist in DB. Workflow fails immediately on status update attempt. |
-
-## 2. Parameter Validation (`test_train_model_validation.py`)
-
-These scenarios test the business rule validations inside `validate_train_params`. All are expected to terminate with `ORCHESTRATOR_VALIDATION_ERROR`.
-
-| Test Function | Modification | Expected Error Substring |
-|---|---|---|
-| `test_scenario_2_1_1_train_size_out_of_range` | `train_size = 5` | `'train_size'` |
-| `test_scenario_2_1_2_empty_variable_columns` | `variable_columns = []` | `'variable_columns'` |
-| `test_scenario_2_1_3_invalid_date_format` | `date_format = 'INVALID'` | `'date_format'` |
-| `test_scenario_2_1_4_whitespace_only_model_name` | `model_name = '   '` | `'model_name'` |
-| `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) |
-
-## 3. CleanupFiles Workflow (`test_cleanup_files_workflow.py`)
-
-| Test Function | Description |
-|---|---|
-| `test_scenario_3_1_1_cleanup_with_no_temp_dirs` | Temp directory is empty. Activity completes without error. |
-| `test_scenario_3_1_2_cleanup_removes_old_temp_dirs` | Two stale directories matching `name_YYYYMMDD_HHMMSS_microseconds` are removed when older than retention. |
-| `test_scenario_3_1_3_cleanup_nonexistent_temp_path` | Target path does not exist. Handled gracefully without error. |

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',
+    )