#!/usr/bin/env python3
"""
Debug Adaptive Beta Bug

Quick test to reproduce the bug where word count decreases when beta is relaxed.
"""

import os
import sys
import logging

# Configure logging to see the debug messages
logging.basicConfig(level=logging.INFO, format='%(asctime)s - %(message)s')

def setup_environment():
    """Setup environment and add src to path"""
    # Set cache directory to root cache-dir folder
    cache_dir = os.path.join(os.path.dirname(__file__), '..', 'cache-dir')
    cache_dir = os.path.abspath(cache_dir)
    os.environ['HF_HOME'] = cache_dir
    os.environ['TRANSFORMERS_CACHE'] = cache_dir
    os.environ['SENTENCE_TRANSFORMERS_HOME'] = cache_dir
    
    # Add backend source to path
    backend_path = os.path.join(os.path.dirname(__file__), '..', 'crossword-app', 'backend-py', 'src')
    backend_path = os.path.abspath(backend_path)
    if backend_path not in sys.path:
        sys.path.insert(0, backend_path)
    
    print(f"Using cache directory: {cache_dir}")

def test_debug_adaptive_beta():
    """Test the problematic case with debug logging"""
    
    setup_environment()
    
    print("🐛 Debug Adaptive Beta Bug")
    print("=" * 50)
    
    # Set environment variables for soft minimum with debug
    os.environ['MULTI_TOPIC_METHOD'] = 'soft_minimum'
    os.environ['SOFT_MIN_BETA'] = '10.0'
    os.environ['SOFT_MIN_ADAPTIVE'] = 'true'
    os.environ['SOFT_MIN_MIN_WORDS'] = '15'
    os.environ['SOFT_MIN_MAX_RETRIES'] = '5'
    os.environ['SOFT_MIN_BETA_DECAY'] = '0.7'
    os.environ['THEMATIC_VOCAB_SIZE_LIMIT'] = '1000'  # Small for faster testing
    
    try:
        from services.thematic_word_service import ThematicWordService
        
        print("Creating ThematicWordService...")
        service = ThematicWordService()
        service.initialize()
        
        # Test the problematic case
        inputs = ["universe", "movies", "languages"]
        print(f"\\nTesting problematic case: {inputs}")
        print(f"Expected: Word count should INCREASE as beta decreases")
        print("-" * 50)
        
        results = service.generate_thematic_words(
            inputs,
            num_words=50,
            min_similarity=0.3,
            multi_theme=False  # Force single theme processing
        )
        
        print(f"\\n✅ Final result: {len(results)} words generated")
        if len(results) > 0:
            print(f"Top 5 words:")
            for i, (word, similarity, tier) in enumerate(results[:5], 1):
                print(f"   {i}. {word}: {similarity:.4f}")
        else:
            print("   ⚠️ No words generated!")
    
    except Exception as e:
        print(f"❌ Test failed: {e}")
        import traceback
        traceback.print_exc()

def main():
    print("🧪 Debugging Adaptive Beta Bug")
    print("This will show detailed score statistics at each beta level")
    print("=" * 60)
    
    test_debug_adaptive_beta()
    
    print("\\n" + "=" * 60)
    print("🔍 Look for patterns in the debug output:")
    print("1. Do score ranges change as expected?")
    print("2. Is the threshold comparison working correctly?")
    print("3. Are scores getting more permissive with lower beta?")
    print("=" * 60)

if __name__ == "__main__":
    main()