#!/bin/bash
# 部署自适应阈值的 watchdog（只换脚本，不动隧道）
set -u

RELAY=/root/lanremote-relay
cp -a "$RELAY/watchdog.sh" "$RELAY/watchdog.sh.bak.$(date +%s)"

echo "════════ 1. 装上（已经是新版了，这里复核）════════"
bash -n "$RELAY/watchdog.sh" && echo "  语法 OK"
echo "  行数: $(wc -l < "$RELAY/watchdog.sh")"
echo "  关键参数:"
grep -E '^THRESHOLD=|^THRESHOLD_HEALTHY=|^GRACE=|^MIN_RESTART_GAP=|^BUILT_MIN=' "$RELAY/watchdog.sh" | sed 's/^/    /'

echo
echo "════════ 2. 预演（当前一切正常，应该无动作）════════"
DRY_RUN=1 bash "$RELAY/watchdog.sh" 2>&1 | sed 's/^/    /'
echo "  （无输出 = 正常）"

echo
echo "════════ 3. 真跑一次 ════════"
bash "$RELAY/watchdog.sh" 2>&1 | sed 's/^/    /'
echo "  退出码 $?"
echo "  状态文件: $(cat "$RELAY/watchdog.state" 2>/dev/null | tr '\n' ' ')"

echo
echo "════════ 4. 当前隧道状态（确认没被影响）════════"
for port in 20241 20242; do
    n=$(curl -s --max-time 4 "http://127.0.0.1:$port/metrics" 2>/dev/null \
        | grep '^cloudflared_tunnel_ha_connections' | awk '{print $2}')
    echo "  端口 $port: ${n:-无响应}"
done

echo
echo "════════ 5. 长测进度（确认没被打断）════════"
echo "  健康样本: $(wc -l < /root/long2h_health.tsv 2>/dev/null || echo 0)"
echo "  轮询: $(wc -l < /root/rp_poll30.tsv 2>/dev/null || echo 0) / 30"
echo "  测试进程:"
pgrep -af 'rp_long2h|rpp30' | sed 's/^/    /'