#!/bin/bash
# WEVIA Proactive Monitor v1.0 — */5 cron
# Auto-check Docker + disk + RAM + services → auto-restart if needed

LOG="/var/log/proactive-monitor.log"
TS=$(date '+%Y-%m-%d %H:%M')

echo "[$TS] PROACTIVE CHECK" >> $LOG

# 1. Docker check — restart stopped containers
STOPPED=$(docker ps -a --filter "status=exited" --format "{{.Names}}" | grep -v "chatwoot" | head -5)
if [ -n "$STOPPED" ]; then
    for C in $STOPPED; do
        docker restart "$C" >> $LOG 2>&1
        echo "[$TS] RESTARTED: $C" >> $LOG
    done
fi

# 2. Disk check — alert if > 90%
DISK=$(df / | tail -1 | awk '{print $5}' | tr -d '%')
if [ "$DISK" -gt 90 ]; then
    echo "[$TS] DISK ALERT: ${DISK}%" >> $LOG
    # Auto-clean old logs
    find /var/log -name "*.log" -size +50M -mtime +3 -delete 2>/dev/null
    docker system prune -f --filter "until=72h" >> $LOG 2>&1
    echo "[$TS] AUTO-CLEAN done" >> $LOG
fi

# 3. RAM check — clear cache if > 85%
RAM_PCT=$(free | grep Mem | awk '{printf "%.0f", $3/$2*100}')
if [ "$RAM_PCT" -gt 85 ]; then
    sync && echo 3 > /proc/sys/vm/drop_caches
    echo "[$TS] RAM CLEAR: was ${RAM_PCT}%" >> $LOG
fi

# 4. Critical services check
for SVC in "ollama:11434" "qdrant:6333" "searxng:8888" "mattermost:8065"; do
    NAME=$(echo $SVC | cut -d: -f1)
    PORT=$(echo $SVC | cut -d: -f2)
    if ! curl -s --max-time 2 "http://127.0.0.1:$PORT/" > /dev/null 2>&1; then
        echo "[$TS] DOWN: $NAME:$PORT — attempting restart" >> $LOG
        docker restart "$NAME" >> $LOG 2>&1 || true
    fi
done

# 5. Nginx check
if ! nginx -t 2>/dev/null; then
    echo "[$TS] NGINX CONFIG ERROR" >> $LOG
fi

echo "[$TS] CHECK DONE — disk=${DISK}% ram=${RAM_PCT}%" >> $LOG