Continuous ETA model retraining pipeline

Design a continuous (automated) retraining pipeline for a food-delivery ETA model that must adapt to changing conditions, new restaurants, traffic patterns, weather, seasonality. The model should retrain regularly on fresh data with no human in the loop for routine retrains, but a bad model must never auto-deploy. Design the pipeline from raw data to a safely-promoted production model, and explain the gates that prevent a corrupted dataset or a regressed model from shipping automatically.