Update analytics/recommendation_engine.py

analytics/recommendation_engine.py

@@ -29,7 +29,11 @@ def build_upcoming_hitter_recommendations(
 ) -> list[dict]:
     """
     Decision-layer wrapper.
-    Uses simulated fair rows, then adds confidence + recommendation tier.
+    Uses simulated fair rows, then adds:
+    1) opportunity adjustment
+    2) confidence
+    3) recommendation tier
+
     Suppresses low-value PASS rows unless nothing else exists.
     """
     rows = build_upcoming_simulated_rows(
@@ -41,6 +45,31 @@ def build_upcoming_hitter_recommendations(
     recommendations: list[dict] = []
 
     for row in rows:
+        slot = row.get("slot", "current")
+        lineup_distance = _lineup_distance_from_slot(slot)
+
+        opportunity = estimate_plate_appearance_probability(
+            outs=game_row.get("outs", 0),
+            lineup_distance=lineup_distance,
+        )
+
+        expected_pa = float(opportunity.get("expected_pa", 1.0) or 1.0)
+
+        # Apply opportunity adjustment to downstream probabilities
+        for prob_col in ["hit_prob", "hr_prob", "tb2p_prob"]:
+            if prob_col in row and row.get(prob_col) is not None:
+                try:
+                    raw_prob = float(row.get(prob_col))
+                    row[prob_col] = min(0.95, max(0.001, raw_prob * expected_pa))
+                except Exception:
+                    pass
+
+        # Carry opportunity diagnostics forward for debugging/auditing
+        row["lineup_distance"] = lineup_distance
+        row["pa_prob_this_inning"] = opportunity.get("pa_prob_this_inning")
+        row["pa_prob_next_two_innings"] = opportunity.get("pa_prob_next_two_innings")
+        row["expected_pa"] = expected_pa
+
         confidence_block = compute_confidence(row, game_row=game_row)
         row.update(confidence_block)