#!/usr/bin/env bash
# 切换 A 步（在 47 上跑）：
#  ① 备份 /opt/dshs/lib  →  /opt/dsh/backups/lib-<ts>/
#  ② 覆盖 /opt/dshs/lib（T08 集群版代码）
#  ③ 装 **本地 Worker**（w-47，19100，无隧道 —— Manager 同机直连）
#  ④ 把既有用户（admin/guest）的归属**预置**为 w-47（否则粘性落点无处可粘、新老用户会被按容量随机调度）
#  ⑤ 在 PG 里注册 w-47 / w-106 两台 worker
set -uo pipefail
TS=$(date +%Y%m%d-%H%M%S)
W47_TOKEN="dshs-worker-47-c4b7e19f"
W106_TOKEN="dshs-worker-7f3a91c05e"
PGURL="postgres://dshs:dshs_cluster_2026@127.0.0.1:15432/dshs"
TARBALL=/tmp/dshs-lib-new.tgz

echo "=== ① 备份 /opt/dshs/lib ==="
mkdir -p "/opt/dsh/backups/lib-$TS"
cp -a /opt/dshs/lib "/opt/dsh/backups/lib-$TS/lib" && echo "  ✓ 备份到 /opt/dsh/backups/lib-$TS/lib（$(find /opt/dsh/backups/lib-$TS -type f | wc -l) 文件）"

echo "=== ② 覆盖 lib ==="
[ -f "$TARBALL" ] || { echo "  ✗ 缺少 $TARBALL"; exit 1; }
rm -rf /opt/dshs/lib && tar -xzf "$TARBALL" -C /opt/dshs
echo "  ✓ 已覆盖；cluster 特征检查: $(grep -l "DEPLOY_MODE" /opt/dshs/lib/config.js >/dev/null 2>&1 && echo '有 cluster 代码 ✓' || echo '✗ 未见 cluster 代码')"
echo "  lease/agent/tunnel: $(ls /opt/dshs/lib/supervisor/lease.js /opt/dshs/lib/worker/agent.js /opt/dshs/lib/worker/tunnel.js 2>/dev/null | wc -l)/3"

echo "=== ③ 本地 Worker 单元（w-47，无隧道） ==="
cat > /etc/dshs-worker.env <<ENV
DSHS_DATA_ROOT=/var/lib/dshs
DSHS_ISOLATION_MODE=account
DSHS_DSH_BIN=/usr/local/bin/dsh
DSHS_BASE_UID=100000
DSH_INSTANCE_NODE_OPTIONS=--max-old-space-size=160
DSH_INSTANCE_UNIVER_SOCKET=auto
DSHS_CLUSTER_AGENT_TOKEN=$W47_TOKEN
ENV
chmod 600 /etc/dshs-worker.env
cat > /etc/systemd/system/dshs-worker.service <<UNIT
[Unit]
Description=DSHS cluster worker agent (this host = 47, local users' instances)
After=network-online.target

[Service]
Type=simple
EnvironmentFile=/etc/dshs-worker.env
ExecStart=/usr/local/bin/node /opt/dshs/lib/cli.js worker --port 19100 --host 127.0.0.1 --host-id w-47 --instance-host 127.0.0.1 --log-level info
Restart=on-failure
RestartSec=3
KillMode=mixed

[Install]
WantedBy=multi-user.target
UNIT
systemctl daemon-reload; systemctl enable dshs-worker >/dev/null 2>&1
systemctl restart dshs-worker; sleep 5
echo "  dshs-worker=$(systemctl is-active dshs-worker)  healthz=$(curl -s -m 6 http://127.0.0.1:19100/healthz | head -c 120)"

echo "=== ④ 既有用户归属预置为 w-47（粘性锚点） ==="
PGPASSWORD=dshs_cluster_2026 /usr/bin/psql -h 127.0.0.1 -p 15432 -U dshs -d dshs -tAc \
 "insert into dsh_instances (id, user_id, role, status, host_id, epoch, heartbeat_at, lease_until)
  select 'dsh-'||id, id, 'main', 'stopped', 'w-47', 0, 0, 0 from users
  on conflict (id) do update set host_id='w-47', lease_until=0" 2>&1 | tail -1
PGPASSWORD=dshs_cluster_2026 /usr/bin/psql -h 127.0.0.1 -p 15432 -U dshs -d dshs -tAc \
 "select u.username||' -> '||coalesce(i.host_id,'NULL') from users u left join dsh_instances i on i.user_id=u.id" 2>&1 | sed 's/^/  /'

echo "=== ⑤ 注册两台 worker ==="
PGPASSWORD=dshs_cluster_2026 /usr/bin/psql -h 127.0.0.1 -p 15432 -U dshs -d dshs -tAc \
 "insert into dsh_hosts (id, endpoint, agent_token, capacity_mb, used_mb, status)
   values ('w-47','http://127.0.0.1:19100','$W47_TOKEN',1024,0,'up'),
          ('w-106','http://127.0.0.1:19000','$W106_TOKEN',2560,0,'up')
  on conflict (id) do update set endpoint=excluded.endpoint, agent_token=excluded.agent_token, capacity_mb=excluded.capacity_mb, status='up'" 2>&1 | tail -1
PGPASSWORD=dshs_cluster_2026 /usr/bin/psql -h 127.0.0.1 -p 15432 -U dshs -d dshs -tAc \
 "select id||' cap='||capacity_mb||' status='||status||' ep='||endpoint from dsh_hosts order by id" 2>&1 | sed 's/^/  /'

echo "=== 回滚剧本（现在就记下） ==="
echo "  rm -f /etc/systemd/system/dshs.service.d/cluster.conf && systemctl daemon-reload && \\"
echo "  systemctl restart dshs            # 回 SQLite 单机；lib 回滚 = cp -a /opt/dsh/backups/lib-$TS/lib /opt/dshs/lib"
echo "  备份时间戳: $TS"