predictions ON CONFLICT: overwrite xgb/lstm/confidence/ensemble too

After cutting HeatWavePredictor, pipeline started writing NULL for
trigger_probability_7d on conflict. But the ON CONFLICT clause only
listed 5 columns for update -- xgb_probability, lstm_probability,
prediction_confidence, and ensemble_method were left out, so every
existing predictions row kept the last XGBoost-era values forever
(e.g. DAR-JAN on 04-21 was still carrying xgb_probability=0.0403
from a pre-cut run).

Expanded UPDATE SET to overwrite all of those plus predicted_at=NOW()
so next run fully heals the stale fields.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

src/database/crud.py

@@ -500,10 +500,15 @@ def insert_prediction(conn, record: dict) -> Optional[int]:
         VALUES (%s, %s, %s, %s, %s, %s, %s, %s, %s, %s, %s)
         ON CONFLICT (zone_id, date) DO UPDATE SET
             trigger_probability_7d = EXCLUDED.trigger_probability_7d,
+            prediction_confidence = EXCLUDED.prediction_confidence,
             model_tier = EXCLUDED.model_tier,
+            xgb_probability = EXCLUDED.xgb_probability,
+            lstm_probability = EXCLUDED.lstm_probability,
+            ensemble_method = EXCLUDED.ensemble_method,
             annual_cost_per_worker = EXCLUDED.annual_cost_per_worker,
             payout_factor = EXCLUDED.payout_factor,
-            learned_frequency = EXCLUDED.learned_frequency
+            learned_frequency = EXCLUDED.learned_frequency,
+            predicted_at = NOW()
         RETURNING id
         """,
         (record["zone_id"], _to_date(record["date"]),