live: baked reject-marks (8) + read-only search-by-model-id precheck (已验证→60027/验证中→60028 skip, no submit); in-run marks; drop /tmp state; sync_reject_marks.py (95 tests)

scripts/sync_reject_marks.py

@@ -0,0 +1,58 @@
+#!/usr/bin/env python3
+"""Merge permanent rejects from a local live log into baked marks."""
+import argparse
+import datetime
+import json
+from pathlib import Path
+import re
+import sys
+
+sys.path.insert(0, str(Path(__file__).resolve().parents[1]))
+from src.config_params import GPU_ENUMS
+from src.live_queue import model_key
+from src.marks import PERMANENT_PAIR_CODES, REJECT_CODES, load_marks
+
+
+def main():
+    parser = argparse.ArgumentParser()
+    parser.add_argument('log')
+    parser.add_argument('--marks', default='src/data/reject-marks.json')
+    parser.add_argument('--date', default=datetime.date.today().isoformat())
+    parser.add_argument('--dry-run', action='store_true')
+    args = parser.parse_args()
+    path = Path(args.marks)
+    if path.exists():
+        load_marks(path)
+        rows = json.loads(path.read_text())['marks']
+    else:
+        rows = []
+    merged = {}
+    for row in rows:
+        merged.setdefault((model_key(row['model']), row['gpu']), row)
+    before = len(merged)
+    for line in Path(args.log).read_text().splitlines():
+        match = re.search(r'\[live\] (rejected|skip) (.*)', line)
+        if not match:
+            continue
+        fields = dict(token.split('=', 1) for token in match[2].split() if '=' in token)
+        model, gpu = fields.get('model', ''), fields.get('gpu', '')
+        raw = fields.get('code', '') if match[1] == 'rejected' else fields.get('reason', '').removeprefix('marked:precheck_')
+        if match[1] == 'skip' and not fields.get('reason', '').startswith('marked:precheck_'):
+            continue
+        try:
+            code = int(raw)
+        except ValueError:
+            continue
+        if (code not in PERMANENT_PAIR_CODES or gpu not in GPU_ENUMS.values()
+                or not re.fullmatch(r'[\w.-]+/[\w.\-]+', model)):
+            continue
+        merged.setdefault((model_key(model), gpu), dict(model=model, gpu=gpu, code=code,
+                          reason=REJECT_CODES[code], date=args.date))
+    rows = sorted(merged.values(), key=lambda r: (r['model'].lower(), r['gpu']))
+    if not args.dry_run:
+        path.write_text(json.dumps(dict(version=1, marks=rows), indent=2) + '\n')
+    print(f'added {len(rows) - before} total {len(rows)}')
+
+
+if __name__ == '__main__':
+    main()