fix: reject unprovenanced ML artifacts

ml/optimizer.py

@@ -26,7 +26,8 @@ from sklearn.metrics import (
 from sklearn.model_selection import TimeSeriesSplit
 from sklearn.preprocessing import StandardScaler
 
-from scoring.policy import SCORE_BRACKETS, score_in_bracket
+from scoring.policy import SCORE_BRACKETS, SCORE_VERSION, score_in_bracket
+from ml.artifacts import ML_ARTIFACT_SCHEMA_VERSION
 
 logging.basicConfig(
     level=logging.INFO,
@@ -478,8 +479,12 @@ def train_model(rows):
     comparison = run_comparison(rows, weights)
     out_of_sample_comparison = run_out_of_sample_comparison(labeled, fold_results)
 
-    # Build output
+    # Build output. Final weights are fitted on all labeled history for live use;
+    # only the fold weights below are valid for OOS comparisons.
+    trained_at = datetime.now(tz=__import__('datetime').timezone.utc).isoformat()
     result = {
+        "artifact_schema_version": ML_ARTIFACT_SCHEMA_VERSION,
+        "score_version": SCORE_VERSION,
         "weights": weights,
         "feature_importances": {name: round(float(imp), 6) for name, imp in feat_imp},
         "cv_results": {
@@ -501,9 +506,19 @@ def train_model(rows):
             "date_range": f"{labeled[0]['date']} to {labeled[-1]['date']}",
             "model": "GradientBoostingClassifier",
         },
+        "provenance": {
+            "validation_method": "purged_expanding_window",
+            "label_horizon_days": LABEL_HORIZON_DAYS,
+            "weight_scope": "full_history_fit",
+            "training_date_range": {
+                "start": labeled[0]["date"],
+                "end": labeled[-1]["date"],
+            },
+            "trained_at": trained_at,
+        },
         "comparison": comparison,
         "out_of_sample_comparison": out_of_sample_comparison,
-        "trained_at": datetime.now(tz=__import__('datetime').timezone.utc).isoformat(),
+        "trained_at": trained_at,
     }
 
     return result