feat(provenance): govern source snapshots and data inputs

scripts/refine_yolo_labels_with_sam.py

@@ -10,8 +10,20 @@ import json
 import math
 import os
 import shutil
+import sys
 from pathlib import Path
-from typing import Any
+
+
+SCRIPT_DIR = Path(__file__).resolve().parent
+if str(SCRIPT_DIR) not in sys.path:
+    sys.path.insert(0, str(SCRIPT_DIR))
+
+from training_release_manifest import (  # noqa: E402
+    TrainingReleaseError,
+    assert_yolo_summary_bound_to_training_release,
+    file_sha256,
+    training_release_paths,
+)
 
 
 def sha256(path: Path) -> str:
@@ -97,6 +109,8 @@ def link_or_copy(source: Path, target: Path) -> None:
 def main() -> int:
     parser = argparse.ArgumentParser()
     parser.add_argument("--summary", type=Path, required=True)
+    parser.add_argument("--train-yaml", type=Path, required=True)
+    parser.add_argument("--corpus-manifest", type=Path, required=True)
     parser.add_argument("--model", type=Path, required=True)
     parser.add_argument("--output-dir", type=Path, required=True)
     parser.add_argument("--device", default="cuda:0")
@@ -110,7 +124,21 @@ def main() -> int:
     parser.add_argument("--max-prompts-per-pass", type=int, default=96)
     parser.add_argument("--fallback-policy", choices=("retain", "drop"), default="retain")
     parser.add_argument("--force", action="store_true")
+    parser.add_argument(
+        "--fixture-mode",
+        action="store_true",
+        help="Accept only an explicitly fixture-only source release; refined labels remain non-trainable.",
+    )
     args = parser.parse_args()
+    try:
+        source_release = assert_yolo_summary_bound_to_training_release(
+            summary_path=args.summary,
+            train_yaml=args.train_yaml,
+            corpus_manifest=args.corpus_manifest,
+            fixture_mode=args.fixture_mode,
+        )
+    except TrainingReleaseError as exc:
+        raise SystemExit(str(exc)) from exc
     if args.output_dir.exists():
         if not args.force:
             raise SystemExit(f"Output exists: {args.output_dir}")
@@ -194,6 +222,16 @@ def main() -> int:
         print(f"{index}/{len(summary['tiles'])} {tile['sample_slug']}: {len(source_boxes)}", flush=True)
 
     output_summary = dict(summary)
+    # SAM changes label bytes and semantics. It therefore cannot inherit the
+    # source release; keep the parent evidence separately and require a new
+    # governed corpus/review/release before any training consumer can use it.
+    for field_name in (
+        "training_release_manifest",
+        "training_release_manifest_sha256",
+        "training_release_freeze",
+        "training_asset_manifest",
+    ):
+        output_summary.pop(field_name, None)
     output_summary.update(
         {
             "output_dir": str(args.output_dir),
@@ -207,6 +245,10 @@ def main() -> int:
             "label_count": refined_count if args.fallback_policy == "drop" else summary["label_count"],
             "positive_tile_count": sum(not tile["is_negative"] for tile in output_tiles),
             "negative_tile_count": sum(tile["is_negative"] for tile in output_tiles),
+            "training_eligible": False,
+            "training_eligibility_reason": (
+                "SAM-refined labels require a new governed corpus, validation report, human review and immutable training release."
+            ),
         }
     )
     summary_path = args.output_dir / "yolo_tile_dataset_summary.json"
@@ -220,6 +262,11 @@ def main() -> int:
         "status": "ok",
         "source_summary": str(args.summary),
         "source_summary_sha256": sha256(args.summary),
+        "source_training_release": str(training_release_paths(args.train_yaml)["release_manifest"]),
+        "source_training_release_sha256": file_sha256(
+            training_release_paths(args.train_yaml)["release_manifest"]
+        ),
+        "source_corpus_manifest_sha256": source_release["corpus"]["manifest_sha256"],
         "sam_model": str(args.model),
         "sam_model_sha256": sha256(args.model),
         "device": args.device,
@@ -236,6 +283,8 @@ def main() -> int:
         "fallback_label_count": fallback_count,
         "dropped_fallback_label_count": fallback_count if args.fallback_policy == "drop" else 0,
         "fallback_reason_counts": reason_counts,
+        "training_eligible": False,
+        "fixture_mode": bool(args.fixture_mode),
     }
     (args.output_dir / "sam-refinement.json").write_text(json.dumps(evidence, indent=2), encoding="utf-8")
     print(json.dumps(evidence, indent=2))