pm2-self-heal: migrate alerts from Zulip to Telegram
- abiba-zulip PM2 process decommissioned (2026-07-04) - Replace Zulip stream alerts (agent-hub > alerts-pm2) with Telegram DM - Remove stale abiba-zulip monitoring block (process no longer exists) - Retain abiba-telegram auto-restart (critical — sole communication bridge) - Token sourced from extension .env, not hardcoded
This commit is contained in:
+22
-32
@@ -1,29 +1,26 @@
|
||||
#!/bin/bash
|
||||
# pm2-self-heal — hourly PM2 process check
|
||||
# Part of the pm2-self-heal prose contract
|
||||
# Only sends Zulip DM when action is taken or escalation needed
|
||||
# Alerts via Telegram (abiba-zulip decommissioned 2026-07-04)
|
||||
# Field positions (awk -F'│'): $7=pid $8=uptime $9=restarts $10=status
|
||||
|
||||
ZULIP_BOT="abiba-bot@chat.sysloggh.net"
|
||||
ZULIP_KEY="cKTDMZAPW08dk3zl05sStzO7HRztzyn8"
|
||||
ZULIP_SITE="https://chat.sysloggh.net"
|
||||
OWNER_ID=9
|
||||
LOG="/tmp/pm2-self-heal.log"
|
||||
TELEGRAM_BOT_TOKEN="$(grep TELEGRAM_BOT_TOKEN /root/.pi/agent/extensions/telegram/.env 2>/dev/null | cut -d= -f2 || echo '')"
|
||||
TELEGRAM_CHAT_ID="5822977936"
|
||||
|
||||
send_alert() {
|
||||
notify_tg() {
|
||||
local subject="$1"
|
||||
local body="$2"
|
||||
curl -s -X POST "$ZULIP_SITE/api/v1/messages" \
|
||||
-u "$ZULIP_BOT:$ZULIP_KEY" \
|
||||
-d "type=stream" \
|
||||
-d "to=agent-hub" \
|
||||
-d "subject=alerts-pm2" \
|
||||
-d "content=$subject\n$body" > /dev/null 2>&1
|
||||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] Alert sent to #agent-hub > alerts-pm2" >> "$LOG"
|
||||
local msg="${subject}\n${body}"
|
||||
curl -sf -X POST "https://api.telegram.org/bot${TELEGRAM_BOT_TOKEN}/sendMessage" \
|
||||
-d "chat_id=${TELEGRAM_CHAT_ID}" \
|
||||
-d "text=${msg}" \
|
||||
-d "parse_mode=HTML" > /dev/null 2>&1 || true
|
||||
}
|
||||
ALERTS="${ALERTS}$msg"
|
||||
}
|
||||
|
||||
# Log-only mode: replaced by prose contract pm2-self-heal.prose.md
|
||||
# Only sends DM on actual failure (status != online), not just high restarts
|
||||
# Only alerts Telegram on actual failure (status != online)
|
||||
# This prevents the process from receiving alerts about itself
|
||||
|
||||
# Parse PM2 status (--no-color to avoid ANSI escape codes in awk columns)
|
||||
@@ -42,28 +39,21 @@ if [ "$TEL_STATUS" != "online" ]; then
|
||||
TEL_LINE2=$(pm2 status --no-color 2>/dev/null | grep "abiba-telegram")
|
||||
TEL_STATUS2=$(echo "$TEL_LINE2" | awk -F'│' '{print $10}' | xargs)
|
||||
if [ "$TEL_STATUS2" = "online" ]; then
|
||||
ALERTS="${ALERTS}⚠️ abiba-telegram was **$TEL_STATUS** → restarted to online\n"
|
||||
msg="⚠️ abiba-telegram was **$TEL_STATUS** → restarted to online"
|
||||
ALERTS="${ALERTS}${msg}\n"
|
||||
else
|
||||
ALERTS="${ALERTS}🚨 abiba-telegram **failed restart** (was $TEL_STATUS, still $TEL_STATUS2)\n"
|
||||
msg="🚨 abiba-telegram **failed restart** (was $TEL_STATUS, still $TEL_STATUS2)"
|
||||
ALERTS="${ALERTS}${msg}\n"
|
||||
fi
|
||||
fi
|
||||
|
||||
# Check abiba-zulip (read-only — never restart)
|
||||
ZUL_LINE=$(echo "$STATUS" | grep "abiba-zulip")
|
||||
ZUL_STATUS=$(echo "$ZUL_LINE" | awk -F'│' '{print $10}' | xargs)
|
||||
ZUL_RESTARTS=$(echo "$ZUL_LINE" | awk -F'│' '{print $9}' | xargs)
|
||||
|
||||
if [ "$ZUL_STATUS" != "online" ]; then
|
||||
ALERTS="${ALERTS}🚨 **abiba-zulip is $ZUL_STATUS** — needs investigation!\n"
|
||||
ALERTS="${ALERTS} NOT auto-restarting (runs this contract)\n"
|
||||
elif [ "$ZUL_RESTARTS" -gt 30 ] 2>/dev/null; then
|
||||
ALERTS="${ALERTS}⚠️ abiba-zulip has **$ZUL_RESTARTS restarts** — may need attention\n"
|
||||
fi
|
||||
|
||||
# Log check
|
||||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] tel=$TEL_STATUS zul=$ZUL_STATUS alerts=${ALERTS:+yes}" >> "$LOG"
|
||||
{
|
||||
echo "[$(date '+%Y-%m-%d %H:%M:%S')] tel=$TEL_STATUS alerts=${ALERTS:+yes}"
|
||||
[ -n "$ALERTS" ] && echo "$ALERTS"
|
||||
} >> "$LOG"
|
||||
|
||||
# Only DM when there's something to report
|
||||
# Only Telegram DM when there's something to report
|
||||
if [ -n "$ALERTS" ]; then
|
||||
send_alert "**PM2 Self-Heal — $(date '+%H:%M UTC')**" "$ALERTS"
|
||||
notify_tg "PM2 Self-Heal — $(date '+%H:%M UTC')" "$ALERTS"
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user