SIENTIAPDE-1646

Update README, requirements, and E2E tests for improved configuration and functionality

- Enhanced the README with updated model configuration examples, including the addition of an alias for production.
- Removed the `requirements-light.txt` file and updated `requirements-local.txt` and `requirements.txt` to replace `asyncua` with `opcua`.
- Refactored E2E test scenarios to utilize scenario input files for better maintainability and clarity.
- Improved test coverage for MinIO offload functionality and added new helper functions for loading scenario inputs.
- Updated `values.yaml` to reflect new global configurations and environment variables for the laborious worker.

e2e/test_minio_offload.py

@@ -9,7 +9,12 @@ from sqlalchemy import text
 from temporalio.testing import WorkflowEnvironment
 from temporalio.worker import Worker
 
-from e2e.helpers import insert_sample_data, make_workflow_id, start_and_await_workflow
+from e2e.helpers import (
+    insert_sample_data,
+    load_scenario_input,
+    make_workflow_id,
+    start_and_await_workflow,
+)
 from laborious.activities.activities import Activities
 from laborious.utils.models import minio_dataframe_payload as mdp
 from laborious.workflows.predictions_batch import PredictionsBatch
@@ -32,30 +37,14 @@ async def test_load_query_with_minio_offload_writes_object_to_bucket(
         conn.execute(text(f'DELETE FROM predictions_schema.laborious_data WHERE model_id = {model_id}'))
     insert_sample_data(postgres_engine, model_id, [1.0, 2.0])
 
-    metadata = {
-        'metadata': {
-            'schedule_name': 'test-schedule',
-            'model_name': 'test_model',
-            'model_id': model_id,
-            'workflow_name': 'predictions_batch',
-        }
-    }
+    scenario_input = load_scenario_input('minio_offload_load_query.json', model_id=model_id)
+    metadata = {'metadata': scenario_input['metadata']}
     with patch.object(mdp, 'OFFLOAD_THRESHOLD_BYTES', 1):
-        payload = await test_activities_real_minio.load_query_with_minio_offload(
-            {
-                **metadata,
-                'query': (
-                    'SELECT timestamp, variable, value, created_at '
-                    f'FROM predictions_schema.laborious_data WHERE model_id = {model_id}'
-                ),
-                'model_name': 'test_model',
-                'datetime_columns': ['timestamp', 'created_at'],
-            }
-        )
+        payload = test_activities_real_minio.load_query_with_minio_offload(scenario_input)
     assert payload.object_key, 'offloaded payload must reference a MinIO object'
     assert payload.data is None or payload.data == {}, 'large payloads should not inline tabular dict'
 
-    df = await payload.retrieve(test_activities_real_minio.minio_repository, metadata['metadata'])
+    df = payload.retrieve(test_activities_real_minio.minio_repository, metadata['metadata'])
     assert len(df) >= 1
 
     client = minio_container.get_client()
@@ -82,31 +71,7 @@ async def test_predictions_batch_with_minio_offload_path(
         conn.execute(text(f'DELETE FROM predictions_schema.transformed_data WHERE model_id = {model_id}'))
     insert_sample_data(postgres_engine, model_id, [10.0, 20.0, 30.0])
 
-    input_data = {
-        'schedule_name': 'test-schedule',
-        'model_name': 'test_model',
-        'model_id': model_id,
-        'query': (
-            'SELECT timestamp, variable, value, created_at '
-            f'FROM predictions_schema.laborious_data WHERE model_id = {model_id}'
-        ),
-        'schema': 'predictions_schema',
-        'table_name': 'predictions',
-        'transform_table_name': 'transformed_data',
-        'input_filters': {'EMPTY_DATA': {'POLICY': 'STOP', 'CONFIG': {}}},
-        'mlflow_transform_filters': {'API_ERROR': {'POLICY': 'STOP', 'CONFIG': {}}},
-        'mlflow_predict_filters': {'API_ERROR': {'POLICY': 'STOP', 'CONFIG': {}}},
-        'path_priority': ['STOP', 'CONTINUE', 'REPEAT'],
-        'opc_output_config': {},
-        'pi_web_api_output_config': {},
-        'save_transform': True,
-        'prediction_store_policy': 'lts:1',
-        'model_config': {
-            'retention_minutes': 0,
-            'target': 'sensor_1',
-        },
-        'datetime_columns': ['timestamp', 'created_at'],
-    }
+    input_data = load_scenario_input('minio_offload_workflow.json', model_id=model_id)
 
     with patch.object(mdp, 'OFFLOAD_THRESHOLD_BYTES', 1):
         await start_and_await_workflow(
@@ -121,3 +86,23 @@ async def test_predictions_batch_with_minio_offload_path(
             text(f'SELECT COUNT(*) FROM predictions_schema.predictions WHERE model_id = {model_id}')
         ).scalar()
     assert count == 1
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_load_query_with_inline_payload_when_below_threshold(
+    postgres_engine,
+    test_activities_real_minio: Activities,
+):
+    """Scenario 4.2.1: payload stays inline when threshold is high enough."""
+    model_id = 503
+    with postgres_engine.begin() as conn:
+        conn.execute(text(f'DELETE FROM predictions_schema.laborious_data WHERE model_id = {model_id}'))
+    insert_sample_data(postgres_engine, model_id, [1.0, 2.0])
+
+    scenario_input = load_scenario_input('minio_offload_load_query.json', model_id=model_id)
+    with patch.object(mdp, 'OFFLOAD_THRESHOLD_BYTES', 10**9):
+        payload = test_activities_real_minio.load_query_with_minio_offload(scenario_input)
+
+    assert payload.object_key is None
+    assert payload.data is not None