#!/bin/bash
# pm2-self-heal — hourly PM2 process check
# Part of the pm2-self-heal prose contract
# Alerts via Telegram (abiba-zulip decommissioned 2026-07-04)
# Field positions (awk -F'│'): $7=pid $8=uptime $9=restarts $10=status

TELEGRAM_BOT_TOKEN="$(grep TELEGRAM_BOT_TOKEN /root/.pi/agent/extensions/telegram/.env 2>/dev/null | cut -d= -f2 || echo '')"
TELEGRAM_CHAT_ID="5822977936"

notify_tg() {
    local subject="$1"
    local body="$2"
    local msg="${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 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)
STATUS=$(pm2 status --no-color 2>/dev/null)

ALERTS=""

# Check abiba-telegram (safe to auto-restart)
TEL_LINE=$(echo "$STATUS" | grep "abiba-telegram")
TEL_STATUS=$(echo "$TEL_LINE" | awk -F'│' '{print $10}' | xargs)
TEL_RESTARTS=$(echo "$TEL_LINE" | awk -F'│' '{print $9}' | xargs)

if [ "$TEL_STATUS" != "online" ]; then
    pm2 restart abiba-telegram > /dev/null 2>&1
    sleep 3
    TEL_LINE2=$(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
        msg="⚠️ abiba-telegram was **$TEL_STATUS** → restarted to online"
        ALERTS="${ALERTS}${msg}\n"
    else
        msg="🚨 abiba-telegram **failed restart** (was $TEL_STATUS, still $TEL_STATUS2)"
        ALERTS="${ALERTS}${msg}\n"
    fi
fi

# Log check
{
    echo "[$(date '+%Y-%m-%d %H:%M:%S')] tel=$TEL_STATUS alerts=${ALERTS:+yes}"
    [ -n "$ALERTS" ] && echo "$ALERTS"
} >> "$LOG"

# Only Telegram DM when there's something to report
if [ -n "$ALERTS" ]; then
    notify_tg "PM2 Self-Heal — $(date '+%H:%M UTC')" "$ALERTS"
fi