#!/usr/bin/env python3
"""
Test Enhanced RL Fix - Verify comprehensive state building and reward calculation
"""

import sys
from pathlib import Path
project_root = Path(__file__).parent
sys.path.insert(0, str(project_root))

def test_enhanced_orchestrator():
    """Test enhanced orchestrator methods"""
    print("=== TESTING ENHANCED RL FIXES ===")
    
    try:
        from core.enhanced_orchestrator import EnhancedTradingOrchestrator  
        from core.data_provider import DataProvider
        print("✓ Enhanced orchestrator imported successfully")
        
        # Create orchestrator with enhanced RL enabled
        dp = DataProvider()
        eo = EnhancedTradingOrchestrator(
            data_provider=dp, 
            enhanced_rl_training=True,
            symbols=['ETH/USDT', 'BTC/USDT']
        )
        print("✓ Enhanced orchestrator created")
        
        # Test method availability
        methods = ['build_comprehensive_rl_state', 'calculate_enhanced_pivot_reward', '_get_symbol_correlation']
        print("\nMethod availability:")
        for method in methods:
            available = hasattr(eo, method)
            print(f"  {method}: {'✓' if available else '✗'}")
        
        # Test comprehensive state building
        print("\nTesting comprehensive state building...")
        state = eo.build_comprehensive_rl_state('ETH/USDT')
        if state is not None:
            print(f"✓ Comprehensive state built: {len(state)} features")
            print(f"  State type: {type(state)}")
            print(f"  State shape: {state.shape if hasattr(state, 'shape') else 'No shape'}")
        else:
            print("✗ Comprehensive state returned None")
            
            # Debug why state is None
            print("\nDEBUGGING STATE BUILDING...")
            print(f"  Williams enabled: {hasattr(eo, 'williams_enabled')}")
            print(f"  COB integration active: {hasattr(eo, 'cob_integration_active')}")
            print(f"  Enhanced RL training: {getattr(eo, 'enhanced_rl_training', 'Not set')}")
            
        # Test enhanced reward calculation
        print("\nTesting enhanced reward calculation...")
        trade_decision = {
            'action': 'BUY',
            'confidence': 0.75,
            'price': 2500.0,
            'timestamp': '2023-01-01 00:00:00'
        }
        trade_outcome = {
            'net_pnl': 50.0,
            'exit_price': 2550.0,
            'duration': '00:15:00'
        }
        market_data = {'symbol': 'ETH/USDT'}
        
        try:
            reward = eo.calculate_enhanced_pivot_reward(trade_decision, market_data, trade_outcome)
            print(f"✓ Enhanced reward calculated: {reward}")
        except Exception as e:
            print(f"✗ Enhanced reward failed: {e}")
            import traceback
            traceback.print_exc()
            
        print("\n=== TEST COMPLETE ===")
        
    except Exception as e:
        print(f"✗ Test failed: {e}")
        import traceback
        traceback.print_exc()

if __name__ == "__main__":
    test_enhanced_orchestrator()