Effi/scripts/beszel_client.py

#!/usr/bin/env python3
# Beszel API Client - Pour qu'Effi interroge les métriques Beszel
# Usage: python3 beszel_client.py [--system SYSTEM_ID] [--check CHECK_TYPE]

import requests
import argparse
import sys
import os
import json
from datetime import datetime

BESZEL_URL = os.getenv("BESZEL_URL", "http://192.168.1.25:8090")

class BeszelClient:
    def __init__(self, username=None, password=None):
        self.url = BESZEL_URL
        self.token = None
        self.username = username or os.getenv("BESZEL_USER", "admin")
        self.password = password or os.getenv("BESZEL_PASSWORD", "")
    
    def login(self):
        try:
            response = requests.post(f"{self.url}/api/auth/login", json={
                "identity": self.username,
                "password": self.password
            }, timeout=10)
            if response.status_code == 200:
                self.token = response.json().get("token")
                return True
            return False
        except Exception as e:
            print(f"Erreur login: {e}")
            return False
    
    def get_systems(self):
        if not self.token:
            return None
        try:
            headers = {"Authorization": f"Bearer {self.token}"}
            response = requests.get(f"{self.url}/api/systems", headers=headers, timeout=10)
            if response.status_code == 200:
                return response.json()
            return None
        except Exception as e:
            print(f"Erreur get_systems: {e}")
            return None
    
    def get_system_stats(self, system_id):
        if not self.token:
            return None
        try:
            headers = {"Authorization": f"Bearer {self.token}"}
            response = requests.get(f"{self.url}/api/systems/{system_id}/stats", 
                                  headers=headers, timeout=10)
            if response.status_code == 200:
                return response.json()
            return None
        except Exception as e:
            print(f"Erreur get_stats: {e}")
            return None
    
    def get_system_info(self, system_id):
        if not self.token:
            return None
        try:
            headers = {"Authorization": f"Bearer {self.token}"}
            response = requests.get(f"{self.url}/api/systems/{system_id}", 
                                  headers=headers, timeout=10)
            if response.status_code == 200:
                return response.json()
            return None
        except Exception as e:
            print(f"Erreur get_info: {e}")
            return None
    
    def format_stats_text(self, stats, system_name="System"):
        lines = []
        lines.append(f"=== {system_name} ===")
        lines.append(f"CPU: {stats.get('cpu', 0):.1f}%")
        lines.append(f"Mémoire: {stats.get('memory', 0):.1f}%")
        
        if 'swap' in stats:
            lines.append(f"Swap: {stats.get('swap', 0):.1f}%")
        
        if 'disk' in stats:
            for disk, info in stats['disk'].items():
                lines.append(f"Disque {disk}: {info.get('used_percent', 0):.1f}%")
        
        if 'load' in stats:
            load = stats['load']
            lines.append(f"Load: {load[0]:.2f} {load[1]:.2f} {load[2]:.2f}")
        
        if 'gpu' in stats and stats['gpu']:
            lines.append("")
            lines.append("GPU:")
            for gpu_name, gpu_data in stats['gpu'].items():
                vram_used = gpu_data.get('memory_used', 0) / (1024**3)
                vram_total = gpu_data.get('memory_total', 0) / (1024**3)
                vram_pct = (gpu_data.get('memory_used', 0) / gpu_data.get('memory_total', 1)) * 100
                lines.append(f"  {gpu_name}:")
                lines.append(f"    VRAM: {vram_used:.2f}GB / {vram_total:.2f}GB ({vram_pct:.1f}%)")
                lines.append(f"    Utilisation GPU: {gpu_data.get('utilization_gpu', 0)}%")
                if 'temperature' in gpu_data:
                    lines.append(f"    Température: {gpu_data.get('temperature', 0)}°C")
                if 'power_draw' in gpu_data:
                    lines.append(f"    Consommation: {gpu_data.get('power_draw', 0)}W")
        
        if 'containers' in stats and stats['containers']:
            lines.append("")
            lines.append("Containers Docker:")
            for container in stats['containers']:
                name = container.get('name', 'unknown')
                cpu = container.get('cpu_percent', 0)
                mem = container.get('memory_percent', 0)
                lines.append(f"  {name}: CPU {cpu:.1f}% MEM {mem:.1f}%")
        
        return "\n".join(lines)
    
    def check_thresholds(self, stats, thresholds=None):
        if thresholds is None:
            thresholds = {
                'cpu': 80,
                'memory': 90,
                'vram': 90
            }
        
        alerts = []
        
        cpu = stats.get('cpu', 0)
        if cpu > thresholds['cpu']:
            alerts.append(f"⚠️ CPU elevated: {cpu:.1f}%")
        
        memory = stats.get('memory', 0)
        if memory > thresholds['memory']:
            alerts.append(f"⚠️ Memory elevated: {memory:.1f}%")
        
        if 'gpu' in stats and stats['gpu']:
            for gpu_name, gpu_data in stats['gpu'].items():
                vram_pct = (gpu_data.get('memory_used', 0) / gpu_data.get('memory_total', 1)) * 100
                if vram_pct > thresholds['vram']:
                    alerts.append(f"⚠️ VRAM {gpu_name} elevated: {vram_pct:.1f}%")
                
                util = gpu_data.get('utilization_gpu', 0)
                if util > thresholds['vram']:
                    alerts.append(f"⚠️ GPU {gpu_name} utilization elevated: {util}%")
        
        return alerts


def main():
    parser = argparse.ArgumentParser(description="Beszel API Client")
    parser.add_argument("--system", "-s", help="System ID to query")
    parser.add_argument("--list-systems", "-l", action="store_true", help="List all systems")
    parser.add_argument("--check", "-c", choices=["stats", "alerts", "full"], 
                       default="stats", help="Type of check")
    parser.add_argument("--json", "-j", action="store_true", help="Output JSON")
    parser.add_argument("--user", "-u", help="Beszel username")
    parser.add_argument("--password", "-p", help="Beszel password")
    
    args = parser.parse_args()
    
    client = BeszelClient(username=args.user, password=args.password)
    
    if not client.login():
        print("❌ Échec de connexion à Beszel")
        sys.exit(1)
    
    if args.list_systems:
        systems = client.get_systems()
        if systems:
            print("=== Systèmes surveillés ===")
            for sys in systems.get('items', []):
                print(f"  - {sys.get('name')} (ID: {sys.get('id')})")
        return
    
    if args.system:
        if args.check == "stats":
            stats = client.get_system_stats(args.system)
            if stats:
                if args.json:
                    print(json.dumps(stats, indent=2))
                else:
                    info = client.get_system_info(args.system)
                    name = info.get('name', args.system) if info else args.system
                    print(client.format_stats_text(stats, name))
        
        elif args.check == "alerts":
            stats = client.get_system_stats(args.system)
            if stats:
                alerts = client.check_thresholds(stats)
                if alerts:
                    print("\n".join(alerts))
                else:
                    print("✅ Tout est normal")
        
        elif args.check == "full":
            stats = client.get_system_stats(args.system)
            info = client.get_system_info(args.system)
            if stats and info:
                if args.json:
                    print(json.dumps({'info': info, 'stats': stats}, indent=2, default=str))
                else:
                    name = info.get('name', args.system)
                    print(f"=== {name} ===")
                    print(client.format_stats_text(stats, name))
                    alerts = client.check_thresholds(stats)
                    if alerts:
                        print("\n" + "\n".join(alerts))
    else:
        systems = client.get_systems()
        if systems:
            print("Systèmes disponibles (utiliser --system ID):")
            for sys in systems.get('items', []):
                print(f"  - {sys.get('name')} (ID: {sys.get('id')})")


if __name__ == "__main__":
    main()