comprehensive_server_test.py

#!/usr/bin/env python3
"""
Comprehensive server functionality test
Tests all endpoints and core features
"""
import requests
import json
import time
import sys

def test_endpoint(name, url, method="GET", data=None, headers=None):
    """Test a single endpoint"""
    try:
        print(f"\n🔍 Testing {name}...")
        print(f"   URL: {url}")
        
        if method == "POST":
            response = requests.post(url, json=data, headers=headers, timeout=30)
        else:
            response = requests.get(url, timeout=10)
        
        print(f"   Status: {response.status_code}")
        
        if response.status_code == 200:
            try:
                result = response.json()
                print(f"   ✅ SUCCESS")
                return True, result
            except:
                print(f"   ✅ SUCCESS (Non-JSON response)")
                return True, response.text[:200]
        else:
            print(f"   ❌ FAILED: {response.text[:200]}")
            return False, response.text
            
    except requests.exceptions.ConnectionError:
        print(f"   ❌ CONNECTION FAILED - Server not running?")
        return False, "Connection failed"
    except Exception as e:
        print(f"   ❌ ERROR: {str(e)}")
        return False, str(e)

def comprehensive_server_test():
    """Run comprehensive server tests"""
    
    base_url = "http://localhost:8000"
    print("🚀 COMPREHENSIVE SERVER FUNCTIONALITY TEST")
    print("=" * 60)
    
    results = {}
    
    # 1. Test Status/Health Endpoint
    success, data = test_endpoint("Health Check", f"{base_url}/api/status")
    results["health"] = success
    
    # 2. Test Main Landing Page
    success, data = test_endpoint("Main Page", f"{base_url}/")
    results["main_page"] = success
    
    # 3. Test Dashboard
    success, data = test_endpoint("Dashboard", f"{base_url}/dashboard")
    results["dashboard"] = success
    
    # 4. Test API Documentation
    success, data = test_endpoint("API Docs", f"{base_url}/docs")
    results["api_docs"] = success
    
    # 5. Test Playground
    success, data = test_endpoint("Playground", f"{base_url}/playground")
    results["playground"] = success
    
    # 6. Test CORE PREDICTION - Valid Response (No Hallucination)
    test_data_valid = {
        "prompt": "iPhone 15 Pro: A17 Pro chip",
        "response": "iPhone 15 Pro has A17 Pro chip",
        "question": "iPhone 15 Pro: A17 Pro chip"
    }
    success, data = test_endpoint(
        "Prediction API - Valid Response", 
        f"{base_url}/api/predict",
        "POST",
        test_data_valid,
        {"Content-Type": "application/json"}
    )
    results["prediction_valid"] = success
    if success:
        print(f"   Result: is_hallucination={data.get('is_hallucination')}, confidence={data.get('confidence_score')}")
    
    # 7. Test CORE PREDICTION - Hallucination Detection
    test_data_invalid = {
        "prompt": "iPhone 15 Pro: A17 Pro chip",
        "response": "iPhone 15 Pro has M1 chip",  # Wrong chip = hallucination
        "question": "iPhone 15 Pro: A17 Pro chip"
    }
    success, data = test_endpoint(
        "Prediction API - Hallucination Detection", 
        f"{base_url}/api/predict",
        "POST",
        test_data_invalid,
        {"Content-Type": "application/json"}
    )
    results["prediction_hallucination"] = success
    if success:
        print(f"   Result: is_hallucination={data.get('is_hallucination')}, confidence={data.get('confidence_score')}")
    
    # 8. Test Batch Prediction
    batch_data = {
        "items": [
            {
                "prompt": "iPhone 15 Pro: A17 Pro chip",
                "response": "iPhone 15 Pro has A17 Pro chip",
                "question": "iPhone 15 Pro: A17 Pro chip"
            },
            {
                "prompt": "iPhone 14: A16 Bionic chip", 
                "response": "iPhone 14 features A16 Bionic processor",
                "question": "iPhone 14: A16 Bionic chip"
            }
        ]
    }
    success, data = test_endpoint(
        "Batch Prediction API",
        f"{base_url}/api/batch_predict", 
        "POST",
        batch_data,
        {"Content-Type": "application/json"}
    )
    results["batch_prediction"] = success
    
    # 9. Test Model Training Status
    success, data = test_endpoint("Training Status", f"{base_url}/api/train/status")
    results["training_status"] = success
    
    # 10. Test Monitor/Metrics
    success, data = test_endpoint("Monitor/Metrics", f"{base_url}/api/monitor/metrics")
    results["monitor"] = success
    
    # Summary
    print("\n" + "=" * 60)
    print("📊 TEST RESULTS SUMMARY")
    print("=" * 60)
    
    passed = sum(1 for result in results.values() if result)
    total = len(results)
    
    for test_name, result in results.items():
        status = "✅ PASS" if result else "❌ FAIL"
        print(f"{test_name:25} : {status}")
    
    print(f"\n🎯 OVERALL RESULT: {passed}/{total} tests passed")
    
    if passed == total:
        print("🎉 ALL TESTS PASSED - SERVER IS FULLY FUNCTIONAL!")
        return True
    elif passed >= total * 0.8:  # 80% pass rate
        print("⚠️  MOSTLY FUNCTIONAL - Some minor issues")
        return True
    else:
        print("❌ MAJOR ISSUES DETECTED - Server needs attention")
        return False

if __name__ == "__main__":
    comprehensive_server_test()