from utils.llm import query_ollama

async def analyze_sentiment(messages: list) -> tuple[str, float]:
    """
    Analyze the sentiment of a conversation using Ollama
    Returns a tuple of (sentiment description, positivity score from 0-1)
    """
    # Combine the last few messages for context (up to 5)
    messages_to_analyze = messages[-5:] if len(messages) > 5 else messages
    conversation_text = "\n".join([
        f"{'Bot' if msg['is_bot_message'] else 'User'}: {msg['content']}"
        for msg in messages_to_analyze
    ])
    
    prompt = f"""Analyze the sentiment and tone of this conversation snippet between a user and a bot.
Focus on the overall mood, engagement level, and whether the interaction seems positive/neutral/negative.
Give a brief 1-2 sentence summary and a positivity score from 0-1 where:
0.0-0.3 = Negative/Hostile
0.3-0.7 = Neutral/Mixed
0.7-1.0 = Positive/Friendly

Conversation:
{conversation_text}

Format your response exactly like this example:
Summary: The conversation is friendly and engaging with good back-and-forth.
Score: 0.85

Response:"""
    
    try:
        response = await query_ollama(prompt)
        if not response or 'Score:' not in response:
            return "Could not analyze sentiment", 0.5
            
        # Parse the response
        lines = response.strip().split('\n')
        summary = lines[0].replace('Summary:', '').strip()
        score = float(lines[1].replace('Score:', '').strip())
        
        return summary, score
    except Exception as e:
        print(f"Error in sentiment analysis: {e}")
        return "Error analyzing sentiment", 0.5