#!/usr/bin/env python3 """Inspect and optionally clean stale job directories. Default mode is a safe dry-run that reports reclaimable bytes. Pass --apply to actually remove unreferenced job directories. """ from __future__ import annotations import argparse import json from datetime import datetime, timezone from pathlib import Path from .metadata_store import MetadataStore from .storage import Storage BACKEND_ROOT = Path(__file__).resolve().parents[1] PROJECT_ROOT = BACKEND_ROOT WORKSPACE_DIR = PROJECT_ROOT / "service_workspace" ASSETS_DIR = PROJECT_ROOT / "service_assets" METADATA_DIR = PROJECT_ROOT / "service_metadata" def read_asset_meta(path: Path) -> dict: try: return json.loads(path.read_text(encoding="utf-8")) except Exception: return {} def referenced_job_ids() -> set[str]: refs: set[str] = set() for meta_path in ASSETS_DIR.glob("*/*/meta.json"): job_id = read_asset_meta(meta_path).get("job_id") or "" if job_id: refs.add(job_id) return refs def main() -> None: parser = argparse.ArgumentParser(description=__doc__) parser.add_argument("--max-age-days", type=float, default=0) parser.add_argument("--apply", action="store_true", help="Actually delete stale job directories") parser.add_argument("--json", type=Path, default=None, help="Write JSON report") args = parser.parse_args() store = MetadataStore(METADATA_DIR / "app.db") storage = Storage(WORKSPACE_DIR) known_job_ids = store.job_ids() if store.db_path.exists() else set() referenced = referenced_job_ids() stale = storage.stale_job_dirs( referenced_job_ids=referenced, exclude_job_ids=known_job_ids, max_age_days=args.max_age_days, ) reclaimable = sum(item["size_bytes"] for item in stale) report = { "scanned_at": datetime.now(timezone.utc).isoformat(), "job_dir_count": len(storage.list_job_ids()), "referenced_job_ids": len(referenced), "known_job_ids": len(known_job_ids), "stale_job_count": len(stale), "reclaimable_bytes": reclaimable, "max_age_days": args.max_age_days, "apply": args.apply, "stale_jobs": stale[:200], } print(json.dumps(report, ensure_ascii=False, indent=2)) if args.json: args.json.write_text(json.dumps(report, ensure_ascii=False, indent=2), encoding="utf-8") if args.apply: freed = 0 for item in stale: freed += storage.remove_job_dir(item["job_id"]) store.delete_job(item["job_id"]) print(f"freed_bytes={freed}") if __name__ == "__main__": main()