SIENTIAPDE-1646

Implement new scheduling configurations for model retraining and drift analysis in input_sample.json

- Added three new schedule configurations: `minimal-retrain-test-runtime`, `drift-test-runtime`, and `simple-metrics-test-runtime`.
- Each configuration includes parameters such as model ID, workflow type, frequency, and specific queries for data retrieval.
- Enhanced the structure to support active status and updated timestamps for better tracking of schedule states.

e2e/test_predictions_batch_prediction_process.py

@@ -3,7 +3,7 @@ End-to-end tests for PredictionsBatch workflow - Prediction Process scenarios.
 """
 
 from decimal import Decimal
-from unittest.mock import MagicMock
+from unittest.mock import MagicMock, patch
 
 import numpy as np
 import pandas as pd
@@ -15,6 +15,7 @@ from temporalio.worker import Worker
 from e2e.helpers import (
     assert_continue,
     assert_postgres_unique_violation_in_chain,
+    assert_prediction,
     assert_prediction_row_count,
     assert_repeat,
     assert_stop,
@@ -25,6 +26,7 @@ from e2e.helpers import (
     start_and_await_workflow,
 )
 from laborious.activities.activities import Activities
+from laborious.utils.models import minio_dataframe_payload as minio_payload_module
 from laborious.workflows.predictions_batch import PredictionsBatch
 
 DISTINCT_BATCH_TIMESTAMP = '2024-01-01 13:00:00+00:00'
@@ -450,3 +452,37 @@ async def test_scenario_2_4_1_priority_conflict_resolution(
         prediction_confidence=Decimal(10),
         comments='Unknown MLFlow API error',
     )
+
+
+@pytest.mark.asyncio
+@pytest.mark.integration
+async def test_e2e_request_predict_inline_minio_payload_with_datetimeindex(
+    temporal_test_env: WorkflowEnvironment,
+    temporal_worker: Worker,
+    test_activities: Activities,
+    postgres_engine,
+    mlflow_repository_stub,
+):
+    """
+    High offload threshold forces inline tabular dicts; ``DatetimeIndex`` must serialize as JSON
+    (string index keys via ``MinioDataFramePayload.from_dataframe``) so ``request_predict`` completes.
+    """
+    client = temporal_test_env.client
+    model_id = 252
+    with postgres_engine.begin() as conn:
+        conn.execute(text(f'DELETE FROM sientia_data.laborious_data WHERE model_id = {model_id}'))
+        conn.execute(text(f'DELETE FROM sientia_data.predictions WHERE model_id = {model_id}'))
+        conn.execute(text(f'DELETE FROM sientia_data.transformed_data WHERE model_id = {model_id}'))
+    insert_sample_data(postgres_engine, model_id, [60.0, 78.2])
+    input_data = get_base_input_data(model_id)
+
+    with patch.object(minio_payload_module, 'OFFLOAD_THRESHOLD_BYTES', 10**9):
+        await start_and_await_workflow(
+            client,
+            PredictionsBatch.run,
+            input_data,
+            make_workflow_id('test-predict-inline-json-datetimeindex'),
+        )
+
+    assert_prediction(postgres_engine, model_id, prediction=0.5, prediction_confidence=0)
+    mlflow_repository_stub.stub_wrapper.predict.assert_called()

laborious/activities/mlflow.py

@@ -324,8 +324,9 @@ class MLFlow(SientiaMonitoring):
 
         The activity normalizes ``NaN`` to ``None`` for JSON-friendly columns, sets the row index
         the same way as ``retrain_model`` (UTC ``DatetimeIndex`` from ``DATETIME_FORMAT_WITH_TZ``),
-        restores that index on the prediction frame, and records ``response_time``. Non-DataFrame
-        predictions are coerced to a single ``prediction`` column.
+        restores that index on the prediction frame, normalizes the prediction index to
+        ``DATETIME_FORMAT_WITH_TZ`` strings like ``request_transform``, and records ``response_time``.
+        Non-DataFrame predictions are coerced to a single ``prediction`` column.
 
         Args:
          - input_data: Same envelope as ``request_transform`` (``metadata``, ``model_name``,
@@ -381,6 +382,7 @@ class MLFlow(SientiaMonitoring):
 
             predict_data.index = input_index
             predict_data['response_time'] = (end_time - start_time).total_seconds()
+            predict_data = self._detect_and_parse_datetime_index(predict_data, metadata)
 
             response_data: dict[str, Any] = {'success': True, 'content': predict_data}
         except Exception as e:

tests/laborious/activities/test_mlflow.py

@@ -311,6 +311,7 @@ def test_request_predict(mock_to_datetime, mock_from_dataframe, mlflow):
 )
 @patch('laborious.activities.mlflow.to_datetime')
 def test_request_predict_success_dataframe_and_meta(mock_to_datetime, mock_from_dataframe, mlflow):
+    mock_to_datetime.side_effect = lambda x, **kwargs: x
     wrapper = MagicMock()
     pred_df = pd.DataFrame({'raw': [0.3]})
     wrapper.predict.return_value = (pred_df, {'m': 1})