tests/test_enhanced_narrator_agent.py

#!/usr/bin/env python3
"""
Test script for the enhanced narrator analyzer agent that uses Shamela scraper.
"""

import asyncio
import os
import sys
from pathlib import Path

# Add the project root to Python path
project_root = Path(__file__).parent
sys.path.insert(0, str(project_root))

from app.agent.services import LLMService
from pprint import pprint


async def test_single_narrator():
    """Test analyzing a single narrator."""
    print("🔍 Testing Single Narrator Analysis")
    print("=" * 50)
    
    llm_service = LLMService()
    
    # Test with a well-known narrator
    narrator_name = "زرارة بن أعين"
    print(f"Analyzing: {narrator_name}")
    
    result = await llm_service.analyze_narrator(narrator_name)
    
    print(f"\n📊 Results for {narrator_name}:")
    print(f"Name: {result.narrator_name}")
    print(f"Grade: {result.reliability_grade}")
    print(f"Confidence: {result.confidence_level}")
    print(f"Success: {result.success}")
    print(f"Message: {result.message}")
    print(f"\nReasoning:\n{result.reasoning}")
    print(f"\nScholarly Consensus:\n{result.scholarly_consensus}")
    print(f"\nBiographical Info:\n{result.biographical_info}")
    if result.known_issues:
        print(f"\nKnown Issues:\n{result.known_issues}")
    print(f"\nRecommendation:\n{result.recommendation}")


async def test_narrator_chain():
    """Test analyzing a chain of narrators."""
    print("\n\n🔗 Testing Narrator Chain Analysis")
    print("=" * 50)
    
    llm_service = LLMService()
    
    # Test with a sample chain
    narrator_chain = [
        "زرارة بن أعين",
        "أبو جعفر الباقر",
        "جابر بن عبد الله"
    ]
    
    print(f"Analyzing chain: {' ← '.join(narrator_chain)}")
    
    # Analyze individual narrators
    chain_results = await llm_service.analyze_narrator_chain(narrator_chain)
    
    print("\n📋 Individual Results:")
    for narrator, result in chain_results.items():
        print(f"\n{narrator}:")
        print(f"  Grade: {result.reliability_grade}")
        print(f"  Confidence: {result.confidence_level}")
        print(f"  Success: {result.success}")
        if not result.success:
            print(f"  Error: {result.message}")
    
    # Synthesize chain analysis
    synthesis = await llm_service.synthesize_chain_analysis(chain_results)
    
    print("\n🔬 Chain Synthesis:")
    print(f"Success: {synthesis['success']}")
    print(f"Chain Length: {synthesis['chain_length']}")
    print(f"\nOverall Assessment:\n{synthesis['overall_assessment']}")


async def test_unknown_narrator():
    """Test analyzing an unknown/obscure narrator."""
    print("\n\n❓ Testing Unknown Narrator Analysis")
    print("=" * 50)
    
    llm_service = LLMService()
    
    # Test with an unknown narrator
    narrator_name = "محمد بن غير مشهور"  # A made-up name
    print(f"Analyzing unknown narrator: {narrator_name}")
    
    result = await llm_service.analyze_narrator(narrator_name)
    
    print(f"\n📊 Results for {narrator_name}:")
    print(f"Grade: {result.reliability_grade}")
    print(f"Confidence: {result.confidence_level}")
    print(f"Success: {result.success}")
    print(f"Message: {result.message}")
    print(f"\nReasoning:\n{result.reasoning}")


async def main():
    """Run all tests."""
    print("🤖 Enhanced Narrator Analyzer Agent Test Suite")
    print("=" * 60)
    print("This agent combines Shamela.ws scraping with LLM analysis")
    print("=" * 60)
    
    try:
        # Check if Google API key is available
        if not os.getenv("GOOGLE_API_KEY"):
            print("❌ Warning: GOOGLE_API_KEY not found in environment")
            print("   Make sure you have set up your .env file with the API key")
            return
        
        # Run tests
        await test_single_narrator()
        await test_narrator_chain()
        await test_unknown_narrator()
        
        print("\n✅ All tests completed!")
        print("\n💡 The enhanced agent now:")
        print("   • Scrapes data from Shamela.ws automatically")
        print("   • Combines scraped data with LLM knowledge")
        print("   • Provides detailed reasoning and analysis")
        print("   • Can analyze complete chains of narrators")
        print("   • Synthesizes chain-level assessments")
        
    except Exception as e:
        print(f"❌ Test failed: {str(e)}")
        import traceback
        traceback.print_exc()


if __name__ == "__main__":
    asyncio.run(main())