Production-grade: webhook execution, Postgres backup, rate limit, worker timeout/retry

GitHub webhook: delivery-id dedup persisted in webhook_deliveries,
/fix-review creates a queued task with audit (no model run in the
webhook itself), check_run/check_suite parsing without mutating
task state (CI backfill still via pr-checks).
Control plane: Postgres pg_dump backup branch + POST /admin/backup
(maintainer+, password only via PGPASSWORD env), per-key/IP rate
limit (default 120/min, 429), health returns backend + db_ok,
metrics by_status always has all seven status keys.
Worker: per-task timeout (default 1800s, --task-timeout), timeout
is failed not interrupted, limited retries (default 1, backoff,
fallback failures not re-retried), stale codex- container cleanup
on loop/CLI start.
Tests: cloud 271 (267 pass, 4 skipped are pre-existing real-
Postgres tests), host 27 pass.
This commit is contained in:
host committed 2026-10-26 03:55:07 +08:00
1 parent 86160ad175
commit 33841355b5
9 files changed
+1366 -52

No files matched your search

+63 -2
View File
@@ -15,7 +15,9 @@
import argparse
import glob
import os
import shutil
import sqlite3
import subprocess
import time
from cloud.db import connect as _db_connect
@@ -50,13 +52,72 @@ def backup_db(db_path, out_dir, keep=3, timestamp=None):
return dest
def backup_postgres(out_dir, keep=3, timestamp=None, runner=None,
pg_dump_cmd="pg_dump"):
"""Postgres 备份:调 pg_dump 写出 .sql 文件并轮转,返回文件路径。
连接参数只走 CLOUD_DB_* 环境变量(host/port/dbname/user/
password),密码只以 PGPASSWORD 环境变量传给子进程,绝不
出现在命令行参数、返回值或日志里。runner 可注入(单测用假
runner):调用约定 runner(cmd, env) -> 具 returncode/stdout/
stderr 的对象;未注入时用 subprocess.run。pg_dump 不存在时
明确报错;pg_dump 非零退出时明确报错(stderr 截断,不含密码)。
轮转规则与 SQLite 分支一致:只留最近 keep 份,keep < 1 报错。
SQLite 分支原样不动,本函数不碰任何 .db 文件。
"""
if keep < 1:
raise ValueError("keep 必须 >= 1,否则会删光所有备份")
host = os.environ.get("CLOUD_DB_HOST") or "127.0.0.1"
port = os.environ.get("CLOUD_DB_PORT") or "5432"
dbname = os.environ.get("CLOUD_DB_NAME")
user = os.environ.get("CLOUD_DB_USER")
password = os.environ.get("CLOUD_DB_PASSWORD")
if not dbname or not user:
raise RuntimeError(
"Postgres 备份需要 CLOUD_DB_NAME 与 CLOUD_DB_USER")
if shutil.which(pg_dump_cmd) is None and runner is None:
raise RuntimeError("pg_dump 不可用:本机找不到 %s" % pg_dump_cmd)
os.makedirs(out_dir, exist_ok=True)
stamp = timestamp or time.strftime("%Y%m%d%H%M%S", time.localtime())
dest = os.path.join(out_dir, "cloud-backup-%s.sql" % stamp)
cmd = [pg_dump_cmd, "-h", host, "-p", str(port), "-U", user,
"-d", dbname, "-f", dest]
env = dict(os.environ)
if password:
env["PGPASSWORD"] = password
if runner is not None:
result = runner(cmd, env)
else:
result = subprocess.run(cmd, capture_output=True, text=True,
env=env)
if getattr(result, "returncode", 1) != 0:
err = (getattr(result, "stderr", "") or "")[:500]
raise RuntimeError("pg_dump 失败:%s" % err)
if not os.path.exists(dest):
raise RuntimeError("pg_dump 未生成备份文件:%s" % dest)
backups = sorted(glob.glob(os.path.join(out_dir, "cloud-backup-*.sql")))
for old in backups[:-keep] if len(backups) > keep else []:
os.remove(old)
return dest
def main(argv=None):
parser = argparse.ArgumentParser(description="cloud control-plane backup")
parser.add_argument("--db", required=True)
parser.add_argument("--db", default=None,
help="SQLite 库路径;postgres 模式可省略")
parser.add_argument("--out", required=True)
parser.add_argument("--keep", type=int, default=3)
parser.add_argument("--backend", default="sqlite",
choices=["sqlite", "postgres"],
help="sqlite 时 --db 必填;postgres 时忽略 --db,"
"连接参数走 CLOUD_DB_* 环境变量")
args = parser.parse_args(argv)
dest = backup_db(args.db, args.out, keep=args.keep)
if args.backend == "postgres":
dest = backup_postgres(args.out, keep=args.keep)
else:
if not args.db:
parser.error("sqlite 模式需要 --db")
dest = backup_db(args.db, args.out, keep=args.keep)
print(dest)