perf: trim persisted ML fold metadata

ml/optimizer.py

@@ -164,6 +164,14 @@ def viable_classification_splits(y, splits):
         yield train_idx, val_idx
 
 
+def artifact_fold_results(fold_results):
+    """Strip training-only row indexes from the persisted ML artifact."""
+    return [
+        {key: value for key, value in fold.items() if key not in {"train_idx", "val_idx"}}
+        for fold in fold_results
+    ]
+
+
 def _build_model():
     return GradientBoostingClassifier(
         n_estimators=300,
@@ -503,7 +511,7 @@ def train_model(rows):
             "mean_recall": round(float(np.mean(cv_recall)), 4),
             "validation_method": "purged_expanding_window",
             "label_horizon_days": LABEL_HORIZON_DAYS,
-            "folds": fold_results,
+            "folds": artifact_fold_results(fold_results),
         },
         "training_info": {
             "n_samples": len(labeled),

tests/test_ml_optimizer_validation.py

@@ -87,3 +87,21 @@ def test_classification_splits_skip_training_windows_with_one_class():
 
     assert len(viable) == 1
     assert viable[0][0].tolist() == [0, 1, 3, 4]
+
+
+def test_artifact_folds_omit_large_internal_index_arrays():
+    folds = [{
+        "fold": 1,
+        "train_idx": [0, 1],
+        "val_idx": [2, 3],
+        "weights": {"fear_greed": 1.0},
+        "date_ranges": {"validation": "2024-01-01 to 2024-01-02"},
+    }]
+
+    saved = optimizer.artifact_fold_results(folds)
+
+    assert saved == [{
+        "fold": 1,
+        "weights": {"fear_greed": 1.0},
+        "date_ranges": {"validation": "2024-01-01 to 2024-01-02"},
+    }]