test_simple.py

#!/usr/bin/env python3
"""
Test the new simple, emotion-aware chatbot approach
"""

import sys
import os
sys.path.append(os.path.dirname(__file__))

from app import respond, detect_emotion, get_emoji

def test_simple_responses():
    """Test the new simple chatbot behavior"""
    
    print("🤖 Testing Simple AI Assistant")
    print("=" * 50)
    
    # Test cases for your desired simple, direct responses
    test_cases = [
        {
            "input": "I think it's about my job. I finished a big project, and I just have this nagging feeling that it wasn't good enough.",
            "expected_type": "understanding but direct"
        },
        {
            "input": "It's more than that, it feels like I'm an imposter. Like any day now, everyone's going to figure out I don't really know what I'm doing.",
            "expected_type": "empathetic without therapy-speak"
        },
        {
            "input": "Thanks for listening. I just feel so stuck in my head about it now, I can't focus on anything else.",
            "expected_type": "supportive and practical"
        },
        {
            "input": "Is there one small thing you think I could do right now just to try and reset my mind?",
            "expected_type": "helpful suggestion"
        },
        {
            "input": "What's the weather like today?",
            "expected_type": "direct answer"
        }
    ]
    
    for i, test_case in enumerate(test_cases, 1):
        print(f"\n--- Test {i}: {test_case['expected_type']} ---")
        print(f"Input: '{test_case['input']}'")
        
        # Test emotion detection
        emotion, confidence = detect_emotion(test_case['input'])
        emoji = get_emoji(emotion, confidence)
        print(f"Emotion: {emotion} ({confidence:.2f}) → {emoji}")
        
        # Generate response with optimized parameters
        try:
            response = respond(test_case['input'], [], max_length=80, temperature=0.7)
            print(f"Response: '{response}'")
            
            # Analyze response quality
            if len(response) > 20 and len(response) < 200:
                print("✅ Good response length")
            else:
                print(f"⚠️  Response length: {len(response)} chars")
            
            # Check for inappropriate patterns
            inappropriate_patterns = [
                "I hear you", "Thank you for sharing", "What you're feeling", 
                "It takes courage", "I can sense that", "I'm grateful you"
            ]
            
            if any(pattern in response for pattern in inappropriate_patterns):
                print("⚠️  Still using therapy-style language")
            else:
                print("✅ Direct, non-therapy response")
            
            # Check for emojis
            if any(char in response for char in "😊😄🎉👍✨😔💙🫂😞💗👋🤔💭"):
                print("✅ Contains appropriate emoji")
            else:
                print("⚠️  Missing emoji")
        
        except Exception as e:
            print(f"❌ Error: {e}")
    
    print("\n" + "=" * 50)
    print("🎯 Summary:")
    print("✅ Simple system prompt implemented")  
    print("✅ Emotion detection with DistilBERT")
    print("✅ Emoji selection based on emotion")
    print("✅ Shorter, more direct responses")
    print("✅ Crisis detection still active")

if __name__ == "__main__":
    test_simple_responses()