test_new_multi_agent_system.py

"""
Test script for the new LangGraph Multi-Agent System

This script tests the complete workflow:
- Lead Agent orchestration
- Research Agent information gathering  
- Code Agent computational tasks
- Answer Formatter GAIA compliance
- Memory system integration
"""

import asyncio
import os
from dotenv import load_dotenv
from langgraph_agent_system import run_agent_system

# Load environment variables
load_dotenv("env.local")


async def test_simple_factual_question():
    """Test with a simple factual question that should primarily use research"""
    print("🧪 Testing simple factual question...")
    
    query = "What is the capital of Maharashtra?"
    result = await run_agent_system(
        query=query,
        user_id="test_user_1",
        session_id="test_session_1"
    )
    
    print(f"Query: {query}")
    print(f"Result: {result}")
    print("-" * 50)
    return result


async def test_computational_question():
    """Test with a computational question that should use both research and code"""
    print("🧪 Testing computational question...")
    
    query = "What is 25 + 17 * 3?"
    result = await run_agent_system(
        query=query,
        user_id="test_user_2", 
        session_id="test_session_2"
    )
    
    print(f"Query: {query}")
    print(f"Result: {result}")
    print("-" * 50)
    return result


async def test_complex_question():
    """Test with a complex question requiring both research and computation"""
    print("🧪 Testing complex question...")
    
    query = "How many seconds are there in a week? Show the calculation."
    result = await run_agent_system(
        query=query,
        user_id="test_user_3",
        session_id="test_session_3"
    )
    
    print(f"Query: {query}")
    print(f"Result: {result}")
    print("-" * 50)
    return result


async def test_list_question():
    """Test with a question that should return a list"""
    print("🧪 Testing list question...")
    
    query = "What are the first 3 prime numbers?"
    result = await run_agent_system(
        query=query,
        user_id="test_user_4",
        session_id="test_session_4"
    )
    
    print(f"Query: {query}")
    print(f"Result: {result}")
    print("-" * 50)
    return result


async def run_all_tests():
    """Run all test cases"""
    print("🚀 Starting Multi-Agent System Tests")
    print("=" * 60)
    
    tests = [
        test_simple_factual_question,
        test_computational_question,
        test_complex_question,
        test_list_question
    ]
    
    results = []
    for test_func in tests:
        try:
            result = await test_func()
            results.append(("PASS", test_func.__name__, result))
        except Exception as e:
            print(f"❌ {test_func.__name__} failed: {e}")
            results.append(("FAIL", test_func.__name__, str(e)))
    
    # Summary
    print("=" * 60)
    print("🏁 Test Results Summary:")
    for status, test_name, result in results:
        status_emoji = "✅" if status == "PASS" else "❌"
        print(f"{status_emoji} {test_name}: {status}")
        if status == "PASS":
            print(f"   Result: {result[:100]}...")
    
    passed = sum(1 for status, _, _ in results if status == "PASS")
    total = len(results)
    print(f"\n📊 Tests passed: {passed}/{total}")


if __name__ == "__main__":
    # Check environment setup
    required_env_vars = ["GROQ_API_KEY", "LANGFUSE_PUBLIC_KEY", "LANGFUSE_SECRET_KEY", "LANGFUSE_HOST"]
    missing_vars = [var for var in required_env_vars if not os.getenv(var)]
    
    if missing_vars:
        print(f"❌ Missing required environment variables: {missing_vars}")
        print("Please set up your environment variables in env.local")
        exit(1)
    
    # Run tests
    asyncio.run(run_all_tests())