#!/usr/bin/env python3 """Operator tool: failed-job registry and SAFE explicit replay (lab5, level 4). docker compose exec worker python scripts/replay_failed.py --list docker compose exec worker python scripts/replay_failed.py --job-id --reason "ticket-123" Replay never executes a duplicate of a successful job: it requires status=failed, that the staging source still exists, and that the effect (all variants of the pipeline version) is NOT already present. Everything happens in ONE transaction (state change + audit event + outbox row), so the new attempt is delivered by the normal dispatcher path. """ import argparse import os import sys import psycopg sys.path.insert(0, os.path.dirname(os.path.dirname(os.path.abspath(__file__)))) from src import jobs # noqa: E402 def main() -> int: p = argparse.ArgumentParser() p.add_argument("--list", action="store_true") p.add_argument("--job-id") p.add_argument("--reason", default="operator replay") a = p.parse_args() with psycopg.connect(connect_timeout=5) as conn: if a.list or not a.job_id: for r in conn.execute("SELECT job_id, attachment_id, error_code, attempt, updated_at FROM attachment_jobs WHERE status='failed' ORDER BY updated_at"): print(*r, sep="\t") return 0 row = conn.execute("SELECT j.status, j.attachment_id, j.pipeline_version, a.staging_key FROM attachment_jobs j " "JOIN attachments a ON a.id=j.attachment_id WHERE j.job_id=%s FOR UPDATE OF j", (a.job_id,)).fetchone() if row is None: print("REFUSED: unknown job"); return 1 status, att_id, pv, staging_key = row if status != "failed": print(f"REFUSED: job is {status}, only failed jobs can be replayed"); return 1 done = conn.execute("SELECT count(*) FROM attachment_variants WHERE attachment_id=%s AND pipeline_version=%s", (att_id, pv)).fetchone()[0] if done >= len(jobs.VARIANT_ORDER): print("REFUSED: the effect already exists (all variants present)"); return 1 if not staging_key: print("REFUSED: staging source expired (retention), upload the file again"); return 1 conn.execute("UPDATE attachment_jobs SET status='queued', attempt=0, error_code=NULL, lease_until=NULL, next_attempt_at=now(), updated_at=now() WHERE job_id=%s", (a.job_id,)) conn.execute("UPDATE attachments SET status='queued', error_code=NULL, updated_at=now() WHERE id=%s", (att_id,)) jobs.add_event(conn, a.job_id, "replay", a.reason[:200]) jobs.enqueue(conn, a.job_id, att_id, pv, 1) print(f"REPLAYED job={a.job_id} attachment={att_id}") return 0 if __name__ == "__main__": sys.exit(main())