backend/scripts/test_colossus_integration.py

#!/usr/bin/env python3
"""
SAAP colossus Server Integration Test Script
Quick-Test für colossus Server Integration und Performance-Benchmark

Usage:
python test_colossus_integration.py

Author: Hanan Wandji Danga
"""

import asyncio
import sys
import os
import json
import time
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# Add parent directory to path for imports
sys.path.append(os.path.dirname(os.path.dirname(os.path.abspath(__file__))))

from agents.colossus_saap_agent import ColossusSAAPAgent, ColossusBenchmark, create_saap_colossus_agents

# colossus Server Configuration
API_KEY = os.getenv("COLOSSUS_API_KEY", "")
BASE_URL = "https://ai.adrian-schupp.de"
MODEL_NAME = "mistral-small3.2:24b-instruct-2506"

async def test_colossus_connection():
    """
    Test 1: Grundlegende Konnektivität und API-Funktionalität
    """
    print("🔗 TEST 1: colossus Server Connection Test")
    print("=" * 50)
    
    agent = ColossusSAAPAgent("test_coordinator", "Coordinator", API_KEY, BASE_URL)
    
    # Health Check
    print("📊 Running health check...")
    health = await agent.health_check()
    
    print(f"Status: {health['colossus_status']}")
    print(f"Response Time: {health.get('response_time', 'N/A')}s")
    
    if health.get('error'):
        print(f"❌ Error: {health['error']}")
        return False
    
    print("✅ colossus Server is healthy and reachable")
    return True

async def test_saap_agent_roles():
    """
    Test 2: SAAP Agent Rollen-spezifische Responses
    """
    print("\n🤖 TEST 2: SAAP Agent Role-Specific Responses")
    print("=" * 50)
    
    # Erstelle die 3 Basis-Agenten aus dem Plan
    agents = create_saap_colossus_agents(API_KEY)
    
    test_questions = [
        {
            "agent": "agent_coordinator",
            "role": "Coordinator", 
            "question": "Wie koordinierst du mehrere Agenten in einem SAAP-System?"
        },
        {
            "agent": "agent_developer", 
            "role": "Developer",
            "question": "Welche Python-Bibliotheken empfiehlst du für Multi-Agent-Systeme?"
        },
        {
            "agent": "agent_analyst",
            "role": "Analyst", 
            "question": "Analysiere die Performance-Vorteile von On-Premise vs Cloud AI."
        }
    ]
    
    for test in test_questions:
        print(f"\n👤 Testing {test['role']} Agent...")
        
        # Find entsprechenden Agent
        agent = next((a for a in agents if a.agent_name == test['agent']), None)
        if not agent:
            print(f"❌ Agent {test['agent']} not found")
            continue
        
        # Sende Anfrage
        result = await agent.send_request_to_colossus(test['question'])
        
        if result['success']:
            print(f"✅ Response Time: {result['response_time']}s")
            print(f"📝 Response: {result['response'][:200]}...")
            print(f"🔢 Tokens: {result['token_count']}")
        else:
            print(f"❌ Failed: {result.get('error')}")

async def test_performance_benchmark():
    """
    Test 3: Performance Benchmark für < 2s Response-Zeit Ziel
    """
    print("\n⚡ TEST 3: Performance Benchmark (Target: < 2s)")
    print("=" * 50)
    
    benchmark = ColossusBenchmark(API_KEY)
    
    # SAAP-spezifische Test-Prompts
    test_prompts = [
        "Was ist SAAP?",
        "Erkläre Multi-Agent Systeme kurz.",
        "Vorteile von On-Premise AI?", 
        "Wie funktioniert Agent-Koordination?",
        "Python für AI-Entwicklung?"
    ]
    
    print(f"🧪 Running {len(test_prompts)} performance tests...")
    results = await benchmark.run_performance_benchmark(test_prompts)
    
    print(f"\n📊 BENCHMARK RESULTS:")
    print(f"Total Tests: {results['total_tests']}")
    print(f"Successful Tests: {results['successful_tests']}")
    print(f"Success Rate: {results['success_rate']:.1f}%")
    
    if results.get('average_response_time'):
        print(f"Average Response Time: {results['average_response_time']}s")
        print(f"Average Token Count: {results['average_token_count']}")
        
        # Performance Target Check
        target_met = results['performance_target_met']
        target_symbol = "✅" if target_met else "❌"
        print(f"{target_symbol} Performance Target (< 2s): {'MET' if target_met else 'NOT MET'}")
        
        if not target_met:
            print("💡 Optimization suggestions will be provided for performance improvement")
    else:
        print("❌ No successful tests - check connection and API key")
    
    return results

async def test_multi_agent_communication():
    """
    Test 4: Multi-Agent Kommunikation via Redis
    """
    print("\n💬 TEST 4: Multi-Agent Communication Test") 
    print("=" * 50)
    
    try:
        import redis
        redis_client = redis.Redis(host='localhost', port=6379, decode_responses=True)
        
        # Test Redis connection
        redis_client.ping()
        print("✅ Redis connection successful")
        
        # Erstelle 2 Test-Agenten
        coordinator = ColossusSAAPAgent("test_coordinator", "Coordinator", API_KEY)
        developer = ColossusSAAPAgent("test_developer", "Developer", API_KEY)
        
        # Sende Nachricht von Coordinator zu Developer
        test_message = "Entwickle ein Python-Script für Agent-Kommunikation"
        print(f"📤 Coordinator → Developer: {test_message}")
        
        coordinator.send_message_to_agent("test_developer", test_message)
        
        # Simuliere Developer Response
        print("🔄 Developer processing message...")
        await asyncio.sleep(1)
        
        # Check Redis queue
        queue_length = redis_client.llen("saap_agent_test_developer")
        print(f"📊 Developer message queue length: {queue_length}")
        
        if queue_length > 0:
            print("✅ Multi-Agent communication working")
        else:
            print("⚠️ No messages in queue - check Redis setup")
            
    except ImportError:
        print("❌ Redis not available - install with: pip install redis")
    except Exception as e:
        print(f"❌ Redis connection failed: {e}")
        print("💡 Make sure Redis/Valkey is running: systemctl start valkey")

def print_next_steps(performance_results):
    """
    Druckt Next Steps basierend auf Test-Ergebnissen
    """
    print("\n🎯 NEXT STEPS - Week 1-2 Infrastructure Foundation")
    print("=" * 60)
    
    if performance_results and performance_results.get('success_rate', 0) > 80:
        print("✅ colossus Integration erfolgreich!")
        print("🚀 Ready für Phase 1 Implementation:")
        print("   1. Integriere colossus Agents in bestehendes SAAP-System")
        print("   2. Update Vue.js Dashboard für colossus Agent-Monitoring")
        print("   3. Teste 3 Basis-Agenten (Coordinator, Developer, Analyst)")
        print("   4. OpenRouter GLM 4.5 Air als Fallback konfigurieren")
        print("   5. Performance-Optimierung wenn Response-Zeit > 2s")
        
        print(f"\n📊 Performance Status:")
        avg_time = performance_results.get('average_response_time', 0)
        if avg_time < 2.0:
            print(f"   ✅ Target erfüllt: {avg_time}s < 2s")
        else:
            print(f"   ⚠️ Optimierung nötig: {avg_time}s > 2s")
            print("   💡 Optimierungen: Model-Caching, Connection-Pooling, Prompt-Optimization")
    else:
        print("❌ colossus Integration needs fixes:")
        print("   1. Check API Key and URL")
        print("   2. Verify network connectivity") 
        print("   3. Test model availability")
        print("   4. Check server status")

async def main():
    """
    Hauptfunktion - führt alle Tests sequentiell durch
    """
    print("🚀 SAAP colossus Server Integration Tests")
    print("=" * 60)
    print(f"Target: {BASE_URL}")
    print(f"Model: {MODEL_NAME}")
    print(f"Performance Goal: < 2s response time")
    print("")
    
    # Validate API key
    if not API_KEY:
        print("❌ Error: COLOSSUS_API_KEY environment variable not set")
        print("Please add COLOSSUS_API_KEY to backend/.env file")
        return
    
    # Test 1: Basic Connectivity
    connection_ok = await test_colossus_connection()
    
    if not connection_ok:
        print("\n❌ Basic connection failed. Check server and API key.")
        return
    
    # Test 2: Role-specific responses
    await test_saap_agent_roles()
    
    # Test 3: Performance benchmark
    performance_results = await test_performance_benchmark()
    
    # Test 4: Multi-Agent communication  
    await test_multi_agent_communication()
    
    # Summary and next steps
    print_next_steps(performance_results)
    
    print(f"\n🎓 Integration Status: Ready for SAAP Phase 1 Development")
    print("📚 Master Thesis Progress: Infrastructure Foundation Complete")

if __name__ == "__main__":
    # Run all tests
    asyncio.run(main())