#!/bin/bash
# ============================================================
# homelab-brain Auto-Sync Script
# Läuft alle 15 Min auf pve-hetzner
# Aktualisiert STATE.md Dateien, pushed nach GitHub
# und sendet Telegram-Alerts bei Service-Ausfällen
#
# Setup (einmalig auf pve-hetzner):
#   git clone https://<TOKEN>@github.com/Orbitalo/homelab-brain.git /opt/homelab-brain
#   chmod +x /opt/homelab-brain/scripts/sync-state.sh
#   echo "*/15 * * * * root /opt/homelab-brain/scripts/sync-state.sh >> /var/log/homelab-sync.log 2>&1" >> /etc/crontab
# ============================================================

set -euo pipefail
REPO="/opt/homelab-brain"
GH_TOKEN="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"
TG_TOKEN="8551565940:AAHIUpZND-tCNGv9yEoNPRyPt4GxEPYBJdE"
TG_CHAT="674951792"
DEBOUNCE_DIR="/tmp/homelab_watchdog"
DATE=$(date '+%Y-%m-%d %H:%M')
CHANGED=0

mkdir -p "$DEBOUNCE_DIR"
log() { echo "[$(date '+%H:%M:%S')] $1"; }

# Telegram Alert mit Debounce (10 Min pro Alert-Typ)
tg_alert() {
    local key="$1" msg="$2"
    local lockfile="$DEBOUNCE_DIR/${key}.lock"
    local now=$(date +%s)
    if [ -f "$lockfile" ]; then
        local last=$(cat "$lockfile")
        if [ $((now - last)) -lt 600 ]; then
            return  # Debounce aktiv
        fi
    fi
    curl -s -X POST "https://api.telegram.org/bot${TG_TOKEN}/sendMessage" \
        -d "chat_id=${TG_CHAT}" \
        -d "text=🚨 Homelab Watchdog%0A%0A${msg}" \
        -d "parse_mode=Markdown" > /dev/null 2>&1
    echo "$now" > "$lockfile"
    log "Alert gesendet: $key"
}

# Service-Watchdog: prüft ob ein CT-Service läuft
check_service() {
    local ct="$1" service="$2" name="$3"
    local status
    status=$(pct exec "$ct" -- systemctl is-active "$service" 2>/dev/null || echo "unknown")
    if [ "$status" != "active" ]; then
        tg_alert "service_${service}" "⚠️ *${name}* ist DOWN%0AService: ${service}%0ACT: ${ct}%0AStatus: ${status}"
        echo "DOWN"
    else
        # Wenn vorheriger Alert vorhanden → Recovery-Meldung
        if [ -f "$DEBOUNCE_DIR/service_${service}.lock" ]; then
            curl -s -X POST "https://api.telegram.org/bot${TG_TOKEN}/sendMessage" \
                -d "chat_id=${TG_CHAT}" \
                -d "text=✅ *${name}* wieder online" \
                -d "parse_mode=Markdown" > /dev/null 2>&1
            rm -f "$DEBOUNCE_DIR/service_${service}.lock"
        fi
        echo "active"
    fi
}

cd "$REPO"
git pull --quiet

# ─────────────────────────────────────────────────────
# 0. SERVICE WATCHDOG
# ─────────────────────────────────────────────────────
log "Watchdog läuft..."
RSS_LIVE=$(check_service 109 rss-manager "RSS Manager")
WP_LIVE=$(pct exec 101 -- docker inspect --format='{{.State.Status}}' wordpress-app 2>/dev/null || echo "unknown")
if [ "$WP_LIVE" != "running" ]; then
    tg_alert "wordpress" "⚠️ *WordPress Docker* ist DOWN%0AStatus: ${WP_LIVE}%0ACT: 101"
fi

# ─────────────────────────────────────────────────────
# 1. ARAKAVA NEWS STATE
# ─────────────────────────────────────────────────────
log "Sammle Arakava News Status..."

RSS_STATUS=$(pct exec 109 -- systemctl is-active rss-manager 2>/dev/null || echo "unknown")
WP_STATUS=$(pct exec 101 -- docker inspect --format='{{.State.Status}}' wordpress-app 2>/dev/null || echo "unknown")

# Letzte Feed-Aktivität aus SQLite
FEED_ACTIVITY=$(pct exec 109 -- python3 -c "
import sqlite3, json
db = sqlite3.connect('/opt/rss-manager/rss_manager.db')
rows = db.execute(\"SELECT name, last_run FROM feeds WHERE enabled=1 ORDER BY last_run DESC LIMIT 5\").fetchall()
for r in rows: print(f'  {r[0]}: {r[1] or \"nie\"}')
" 2>/dev/null || echo "  (nicht abrufbar)")

# Letzte Fehler (letzte 24h)
ERRORS=$(pct exec 109 -- bash -c "grep -c 'ERROR' /opt/rss-manager/logs/service.log 2>/dev/null || echo 0")
LAST_ERROR=$(pct exec 109 -- bash -c "grep 'ERROR' /opt/rss-manager/logs/service.log 2>/dev/null | tail -1 || echo 'keine'")

# OpenRouter Balance
OR_BALANCE=$(pct exec 109 -- python3 -c "
import requests, sys
try:
    r = requests.get('https://openrouter.ai/api/v1/auth/key',
        headers={'Authorization': 'Bearer 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'},
        timeout=5)
    d = r.json().get('data', {})
    remaining = float(d.get('limit', 20)) - float(d.get('usage', 0))
    print(f'\${remaining:.2f} verbleibend')
except Exception as e:
    print(f'(nicht abrufbar: {e})')
" 2>/dev/null || echo "(nicht abrufbar)")

cat > "$REPO/arakava-news/STATE.md" << EOF
# Arakava News — Live State
> Auto-generiert: $DATE | Manueller Abschnitt am Ende.

## Service Status
| Service | Status |
|---|---|
| rss-manager (CT 109) | $RSS_STATUS |
| WordPress Docker (CT 101) | $WP_STATUS |
| n8n Workflows | ⛔ deaktiviert |

## Letzte Feed-Aktivität (Top 5)
$FEED_ACTIVITY

## Fehler (letzte 24h)
- Fehler gesamt: $ERRORS
- Letzter Fehler: $LAST_ERROR

## OpenRouter Guthaben
$OR_BALANCE

## Credentials
- WordPress: https://arakava-news-2.orbitalo.net | admin / eJIyhW0p5PFacjvvKGufKeXS
- RSS Manager: http://<CT109-IP>:8080
- OpenRouter: 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

## Feeds (17 aktiv)
| ID | Name | Kategorie | Schedule |
|---|---|---|---|
| 1 | Dr. Bines Substack | 13 | 08/14/20 Uhr |
| 3 | NachDenkSeiten | 5 | 07/13/19 Uhr |
| 4 | Tichys Einblick | 6 | 07:30/13:30/19:30 |
| 5 | Junge Freiheit | 7 | 08/14/20 Uhr |
| 6 | PAZ | 8 | 08:30/14:30/20:30 |
| 7 | Apollo News | 9 | 09/15/21 Uhr |
| 8 | Apolut | 10 | 09:30/15:30/21:30 |
| 9 | Achgut.com | 15 | 10/16/22 Uhr |
| 10 | Heise Security | 11 | alle 4h |
| 11 | Golem.de | 12 | alle 2h |
| 12 | Heise Online | 3 | alle 3h |
| 13 | Rubikon.news | 17 | alle 3h |
| 14 | Corona-Transition | 18 | alle 4h |
| 15 | Photon.info (KI) | 3 | alle 6h |
| 16 | Antispiegel | 20 | 08:30/14:30/20:30 |
| 17 | Riehle News | 21 | 09:00 Uhr |

## Code (CT 109: /opt/rss-manager/)
- poster.py, scheduler.py, app.py, db.py, github_researcher.py
- Vollcode: github.com/Orbitalo/Wordpress-V3-MCP-Projekt

## Offene Aufgaben v3
- [ ] CT 112 anlegen, Docker Compose v3
- [ ] Retry-Logik in poster.py
- [ ] Telegram Alerting bei Feed-Fehlern

## Notizen (manuell)
EOF
CHANGED=1
log "Arakava News STATE.md aktualisiert"

# ─────────────────────────────────────────────────────
# 2. INFRASTRUKTUR STATE
# ─────────────────────────────────────────────────────
log "Sammle Infrastruktur Status..."

# Container-Status auf pve-hetzner
CT_STATUS=$(pvesh get /nodes/pve-hetzner/lxc --output-format=text 2>/dev/null | \
    awk '{print $1, $2}' | grep -v "^vmid" || echo "(nicht abrufbar)")

# Disk-Auslastung
DISK_ROOT=$(df -h / | awk 'NR==2{print $5 " von " $2}')
DISK_DATA=$(df -h /var/lib/vz | awk 'NR==2{print $5 " von " $2}' 2>/dev/null || echo "n/a")

cat > "$REPO/infrastructure/STATE.md" << EOF
# Infrastruktur — Live State
> Auto-generiert: $DATE

## pve-hetzner Disk
| Mount | Belegt |
|---|---|
| / (root) | $DISK_ROOT |
| /var/lib/vz (VMs) | $DISK_DATA |

## Container auf pve-hetzner
| CT | Name | Tailscale IP | Dienste |
|---|---|---|---|
| 100 | traefik | 100.78.77.115 | Traefik, Pangolin, Uptime-Kuma |
| 101 | moltbot | 100.91.212.19 | @MutterbotAI_bot |
| 102 | dify | 100.113.136.30 | Dify RAG + @DifyRagBot |
| 103 | seafile | 100.75.247.60 | Seafile (seafile.orbitalo.net) |
| 104 | n8n | 100.125.102.93 | n8n (Workflows deaktiviert) |
| 107 | ragflow | 100.116.125.12 | RAGFlow (in Einrichtung) |
| 109 | rss-manager | — | RSS Manager + KI |
| 110 | portainer | 100.109.206.43 | Portainer UI |
| 144 | muldenstein-backup | — | Backup-Archiv |
| 999 | cluster-docu | 100.79.8.49 | Dokumentation |

## Container auf pve1 Kambodscha
| CT | Name | IP | Dienste |
|---|---|---|---|
| 135 | edelmetall | 192.168.0.219 | Streamlit Gold/Silber |
| 888 | MCP-Proxmox | 192.168.0.116 | Proxmox MCP |
| 999 | cluster-docu | 192.168.0.209 | Doku-Mirror |

## Container auf pve3 Muldenstein
| CT | Name | IP | Dienste |
|---|---|---|---|
| 134 | gold-silber-de | 100.69.161.128 | Dashboard DE (blei.orbitalo.info) |
| 143 | raspi-broker | 192.168.178.36 | InfluxDB, Grafana, ioBroker |

## Zugangsdaten
- pve-hetzner: root / Astral-Proxmox!2026
- pve1: root / astral66
- Alle lokalen CTs: root / astral66
- Seafile: admin@orbitalo.net / astral66
- n8n: wuttig@gmx.de / Astral66
- Dify: admin@orbitalo.net / astral66

## Notizen (manuell)
EOF
CHANGED=1
log "Infrastruktur STATE.md aktualisiert"

# ─────────────────────────────────────────────────────
# 3. SMART HOME STATE
# ─────────────────────────────────────────────────────
log "Sammle Smart Home Status..."

# Backup-Status
LAST_BACKUP=$(ls -t /home/backup-muldenstein/backups/*.tar.gz 2>/dev/null | head -1 | xargs ls -lh 2>/dev/null | awk '{print $5, $6, $7, $8}' || echo "nicht abrufbar")
BACKUP_COUNT=$(ls /home/backup-muldenstein/backups/*.tar.gz 2>/dev/null | wc -l || echo "0")

cat > "$REPO/smart-home/STATE.md" << EOF
# Smart Home Muldenstein — Live State
> Auto-generiert: $DATE

## Backup-Status
- Letztes Backup: $LAST_BACKUP
- Backups gesamt: $BACKUP_COUNT
- Ziel: /home/backup-muldenstein/backups/ (CT 144)

## Services (CT 143: 192.168.178.36)
| Dienst | URL |
|---|---|
| Grafana | https://grafana.orbitalo.net |
| ioBroker | http://192.168.178.36:8081 |
| InfluxDB | http://192.168.178.36:8086 |

## Grafana Alerts → Telegram 674951792
- Promtail DOWN (> 5 Min keine Daten)
- CPU > 70%
- Memory > 80%
- Disk > 90%

## Backup-Zeitplan
- täglich 04:00 → Script: /root/backup-to-hetzner.sh (auf pve3)
- Retention: 30d tägl, 90d wöchl, unbegrenzt monatl

## Notizen (manuell)
EOF
CHANGED=1
log "Smart Home STATE.md aktualisiert"

# ─────────────────────────────────────────────────────
# 4. GIT COMMIT & PUSH
# ─────────────────────────────────────────────────────
if [ "$CHANGED" -eq 1 ]; then
    log "Committe Änderungen..."
    git -C "$REPO" add -A
    git -C "$REPO" -c user.email="sync@homelab" -c user.name="Auto-Sync" \
        commit -m "Auto-Sync: $DATE" --quiet || true
    git -C "$REPO" push \
        "https://${GH_TOKEN}@github.com/Orbitalo/homelab-brain.git" main --quiet
    log "Push erfolgreich"
else
    log "Keine Änderungen"
fi

log "Sync abgeschlossen"