#!/usr/bin/env python3
"""Test Gemini state management with automatic history inclusion."""

import asyncio
import sys
from pathlib import Path

from gemini_integration import get_integration

async def test_automatic_state():
    """Test if Gemini automatically maintains state through history."""
    print("🧪 Testing Automatic Gemini State Management")
    print("=" * 50)
    
    # Use singleton
    gemini = get_integration({
        'enabled': True,
        'cli_command': 'gemini',
        'timeout': 30,
        'include_history': True,  # This enables automatic history inclusion
        'max_history_entries': 10,
        'debug_mode': False
    })
    
    # Clear any existing history
    gemini.clear_conversation_history()
    
    print("\n1️⃣  First Question: What is 2+2?")
    print("-" * 30)
    
    try:
        response1 = await gemini.consult_gemini(
            query="What is 2+2?",
            context="",  # No context needed
            force_consult=True
        )
        
        if response1.get('status') == 'success':
            response_text = response1.get('response', '')
            print(f"✅ Success! Gemini responded.")
            
            # Find and show the answer
            lines = response_text.strip().split('\n')
            for line in lines:
                if '4' in line or 'four' in line.lower():
                    print(f"📝 Found answer: {line.strip()[:100]}...")
                    break
        else:
            print(f"❌ Error: {response1.get('error', 'Unknown error')}")
            return
            
    except Exception as e:
        print(f"❌ Exception: {e}")
        return
    
    print(f"\n📊 Conversation history size: {len(gemini.conversation_history)}")
    
    print("\n2️⃣  Second Question: What is that doubled?")
    print("   (No context provided - relying on automatic history)")
    print("-" * 30)
    
    try:
        # This time, provide NO context at all - let the history do the work
        response2 = await gemini.consult_gemini(
            query="What is that doubled?",
            context="",  # Empty context - history should provide the context
            force_consult=True
        )
        
        if response2.get('status') == 'success':
            response_text = response2.get('response', '')
            print(f"✅ Success! Gemini responded.")
            
            # Check if it understood the context
            if '8' in response_text or 'eight' in response_text.lower():
                print("🎉 STATE MAINTAINED! Gemini understood 'that' referred to 4")
                print("📝 Found reference to 8 in the response")
                
                # Find and show where 8 appears
                for line in response_text.split('\n'):
                    if '8' in line or 'eight' in line.lower():
                        print(f"📝 Context: {line.strip()[:100]}...")
                        break
            else:
                print("⚠️  Gemini may not have maintained state properly")
                print("📝 Response doesn't clearly reference 8")
                print(f"First 200 chars: {response_text[:200]}...")
                
        else:
            print(f"❌ Error: {response2.get('error', 'Unknown error')}")
            
    except Exception as e:
        print(f"❌ Exception: {e}")
    
    print(f"\n📊 Final conversation history size: {len(gemini.conversation_history)}")
    
    # Test with history disabled
    print("\n3️⃣  Testing with History Disabled")
    print("-" * 30)
    
    # Disable history
    gemini.include_history = False
    gemini.clear_conversation_history()
    
    # Ask first question
    await gemini.consult_gemini(
        query="What is 3+3?",
        context="",
        force_consult=True
    )
    
    # Ask follow-up
    response3 = await gemini.consult_gemini(
        query="What is that tripled?",
        context="",
        force_consult=True
    )
    
    if response3.get('status') == 'success':
        response_text = response3.get('response', '')
        if '18' in response_text or 'eighteen' in response_text.lower():
            print("❌ UNEXPECTED: Found 18 even without history!")
        else:
            print("✅ EXPECTED: Without history, Gemini doesn't understand 'that'")
            # Show what Gemini says when it doesn't have context
            print(f"Response preview: {response_text[:200]}...")
    
    print("\n✅ Test complete!")

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