Files

111 lines
4.0 KiB
Python

#!/usr/bin/env python3
"""Inspect retention candidates and optionally clean verified managed jobs.
Default mode is a safe dry-run. Metadata-less workspaces are reported for
manual investigation but are never removed by ``--apply``.
"""
from __future__ import annotations
import argparse
import json
import os
from datetime import datetime, timezone
from pathlib import Path
from .cleanup_service import CleanupService
from .metadata_store import MetadataStore
from .product_archive_store import ProductArchiveStore
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"
PRODUCTS_DIR = PROJECT_ROOT / "service_products"
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=30)
parser.add_argument(
"--apply",
action="store_true",
help="Delete only CleanupService-verified candidates; orphan workspaces remain report-only",
)
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)
product_store = ProductArchiveStore(PRODUCTS_DIR / "metadata")
cleanup = CleanupService(storage, store, product_store)
known_job_ids = store.job_ids() if store.db_path.exists() else set()
asset_referenced = referenced_job_ids()
archive_protected = cleanup.archive_protected_job_ids()
orphaned = storage.stale_job_dirs(
referenced_job_ids=archive_protected,
exclude_job_ids=known_job_ids,
max_age_days=args.max_age_days,
)
cleanup_report = cleanup.preview(datetime.now(timezone.utc))
reclaimable = cleanup_report.reclaimable_bytes + sum(item["size_bytes"] for item in orphaned)
report = {
"scanned_at": datetime.now(timezone.utc).isoformat(),
"job_dir_count": len(storage.list_job_ids()),
"referenced_job_ids": len(asset_referenced),
"asset_referenced_job_ids": sorted(asset_referenced),
"archive_protected_job_ids": sorted(archive_protected),
"known_job_ids": len(known_job_ids),
"temporary_jobs": [item.model_dump(mode="json") for item in cleanup_report.temporary_jobs],
"pending_product_ids": [item.product_id for item in cleanup_report.pending_products],
"failed_product_ids": [item.product_id for item in cleanup_report.failed_products],
"reminder_job_ids": cleanup_report.reminder_job_ids,
"stale_job_count": len(orphaned),
"reclaimable_bytes": reclaimable,
"max_age_days": args.max_age_days,
"apply": args.apply,
"stale_jobs": orphaned[: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:
if os.environ.get("CLEANUP_APPLY_ENABLED", "false").strip().lower() != "true":
parser.error("--apply requires CLEANUP_APPLY_ENABLED=true")
applied = cleanup.apply(datetime.now(timezone.utc))
freed = sum(
item.size_bytes
for item in applied.temporary_jobs
if item.job_id in applied.deleted_job_ids
)
print(
"freed_bytes="
f"{freed} deleted_job_ids={applied.deleted_job_ids} "
f"deleted_product_ids={applied.deleted_product_ids}"
)
if __name__ == "__main__":
main()