host
89a918b543
Deploy: deploy.sh builds tarball, backs up current code (keep 3), deploys, restarts, health-gates 60s (ok/backend=postgres/db_ok), auto-rolls back on failure; rollback.sh restores latest backup. Rollback is code-only, DB migrations are additive-only so old code can still read new columns. Backup: restore_postgres refuses to restore into the production DB name unless explicitly allowed (drill never allows it); restore-drill.sh backs up fresh, restores to a test DB, compares tasks/projects/users/audit row counts, drops the test DB. Monitoring: worker writes heartbeat file every loop (atomic replace, failure only logged); GET /health adds worker_last_seen_seconds_ago + worker_ok (180s default, env tunable, still HTTP 200 when worker is stale); monitor.sh checks server/worker/health/pg_isready/docker-postgres/disk/ app dir as one JSON line, exit non-zero on any fail, plus systemd timer every 5 minutes. Push alerting to chat still needs a separate channel decision (SSH key or webhook URL). Multi-user: verify-multiuser.py creates test users/projects in memory-key only, checks RBAC via real HTTP API (owner/ maintainer/contributor/viewer, cross-project isolation, merge 200/403/409, no-key 401), test tasks carry a never- satisfiable dependency so the production worker never claims them, cleanup deletes only multiuser-test- rows (audit log is append-only and keeps test entries by design). Tests: host 27 pass, cloud 298 pass (8 skipped are environment-dependent real-Postgres tests).
80 lines
2.5 KiB
Bash
Executable File
80 lines
2.5 KiB
Bash
Executable File
#!/bin/sh
|
||
# 回滚：VM 侧运行，把主机恢复到最近一份代码备份包并重启验证。
|
||
#
|
||
# 用法：deploy/rollback.sh <host> [user]
|
||
# host：主机 IP 或域名（必填）；user：SSH 用户（默认 root）。
|
||
#
|
||
# 密码：与 deploy.sh 同款规则——绝不接受密码参数、不读 env 文件、
|
||
# 不打印任何密钥；SSH 密码由交互提示或调用方通道提供；需要代理时
|
||
# 用环境变量 SSH_PROXY_CMD 传入 ProxyCommand，未设则直连。
|
||
#
|
||
# 回滚边界：只回代码，不回数据库（理由见 deploy.sh 头注释与
|
||
# deploy/README.md：数据库迁移是只加列的幂等操作，老代码仍能读新列）。
|
||
# 备份包来自 deploy.sh 每次部署前在主机上打的
|
||
# /opt/codex-app-server-backups/codex-app-server-<时间戳>.tar.gz，
|
||
# 本脚本恢复其中最新的一份；主机上没有备份包时直接报错退出，不编造。
|
||
set -eu
|
||
|
||
HOST=${1:-}
|
||
USER_ARG=${2:-root}
|
||
if [ -z "$HOST" ]; then
|
||
echo "用法：deploy/rollback.sh <host> [user]" >&2
|
||
exit 2
|
||
fi
|
||
|
||
ssh_cmd() {
|
||
if [ -n "${SSH_PROXY_CMD:-}" ]; then
|
||
ssh -o "ProxyCommand $SSH_PROXY_CMD" -o StrictHostKeyChecking=no \
|
||
-o UserKnownHostsFile=/dev/null "$@"
|
||
else
|
||
ssh -o StrictHostKeyChecking=no -o UserKnownHostsFile=/dev/null "$@"
|
||
fi
|
||
}
|
||
|
||
ssh_cmd "$USER_ARG@$HOST" 'sh -s' <<'HOST_SCRIPT'
|
||
set -eu
|
||
APP_DIR=/opt/codex-app-server
|
||
BACKUP_DIR=/opt/codex-app-server-backups
|
||
|
||
check_health() {
|
||
OUT=$(curl -s --max-time 5 http://127.0.0.1:8765/health || true)
|
||
[ -n "$OUT" ] && printf '%s' "$OUT" | python3 -c '
|
||
import json, sys
|
||
try:
|
||
d = json.load(sys.stdin)
|
||
except Exception:
|
||
sys.exit(1)
|
||
sys.exit(0 if (d.get("ok") is True and d.get("backend") == "postgres"
|
||
and d.get("db_ok") is True) else 1)
|
||
'
|
||
}
|
||
|
||
wait_health() {
|
||
i=0
|
||
while [ "$i" -lt 12 ]; do
|
||
if check_health; then return 0; fi
|
||
sleep 5
|
||
i=$((i + 1))
|
||
done
|
||
return 1
|
||
}
|
||
|
||
BACKUP_FILE=$(ls -t "$BACKUP_DIR"/codex-app-server-*.tar.gz 2>/dev/null \
|
||
| head -n 1 || true)
|
||
if [ -z "$BACKUP_FILE" ]; then
|
||
echo "主机上没有代码备份包，无法回滚：$BACKUP_DIR" >&2
|
||
exit 1
|
||
fi
|
||
echo "将恢复备份包：$BACKUP_FILE"
|
||
systemctl stop codex-cloud-worker codex-cloud-server || true
|
||
tar -xzf "$BACKUP_FILE" -C /opt
|
||
chown -R codexsvc:codexsvc "$APP_DIR"
|
||
systemctl start codex-cloud-server codex-cloud-worker
|
||
if wait_health; then
|
||
echo "回滚成功，health 通过，当前代码为备份包：$BACKUP_FILE"
|
||
exit 0
|
||
fi
|
||
echo "回滚后 health 仍失败，需人工介入" >&2
|
||
exit 1
|
||
HOST_SCRIPT
|