archive/src/agents/critic_agent.py

"""Critic Agent - Evaluates and reviews responses for quality and accuracy"""
from typing import Dict, Any
from langchain_core.messages import SystemMessage, HumanMessage, AIMessage
from langchain_groq import ChatGroq
from src.tracing import get_langfuse_callback_handler


def load_critic_prompt() -> str:
    """Load the critic prompt from file"""
    try:
        with open("./prompts/critic_prompt.txt", "r", encoding="utf-8") as f:
            return f.read().strip()
    except FileNotFoundError:
        return """You are a specialized critic agent. Evaluate responses for accuracy, completeness, and quality."""


def critic_agent(state: Dict[str, Any]) -> Dict[str, Any]:
    """
    Critic agent that evaluates responses for quality and accuracy
    """
    print("Critic Agent: Evaluating response quality")
    
    try:
        # Get critic prompt
        critic_prompt = load_critic_prompt()
        
        # Initialize LLM for criticism
        llm = ChatGroq(model="qwen-qwq-32b", temperature=0.2)
        
        # Get callback handler for tracing
        callback_handler = get_langfuse_callback_handler()
        callbacks = [callback_handler] if callback_handler else []
        
        # Build messages
        messages = state.get("messages", [])
        
        # Get the agent response to evaluate
        agent_response = state.get("agent_response")
        if not agent_response:
            # Find the last AI message
            for msg in reversed(messages):
                if msg.type == "ai":
                    agent_response = msg
                    break
        
        if not agent_response:
            print("Critic Agent: No response to evaluate")
            return {
                **state,
                "critic_assessment": "No response found to evaluate",
                "quality_score": 0,
                "current_step": "verification"
            }
        
        # Get user query for context
        user_query = None
        for msg in reversed(messages):
            if msg.type == "human":
                user_query = msg.content
                break
        
        # Build critic messages
        critic_messages = [SystemMessage(content=critic_prompt)]
        
        # Add evaluation request
        evaluation_request = f"""
Please evaluate the following response:

Original Query: {user_query or "Unknown query"}

Response to Evaluate:
{agent_response.content}

Provide your evaluation following the format specified in your instructions.
"""
        
        critic_messages.append(HumanMessage(content=evaluation_request))
        
        # Get critic evaluation
        evaluation = llm.invoke(critic_messages, config={"callbacks": callbacks})
        
        # Parse evaluation to determine if it passes
        evaluation_text = evaluation.content.lower()
        quality_pass = True
        quality_score = 7  # Default moderate score
        
        # Simple heuristics for quality assessment
        if "fail" in evaluation_text or "poor" in evaluation_text:
            quality_pass = False
            quality_score = 3
        elif "excellent" in evaluation_text or "outstanding" in evaluation_text:
            quality_score = 9
        elif "good" in evaluation_text:
            quality_score = 7
        elif "issues" in evaluation_text or "problems" in evaluation_text:
            quality_score = 5
        
        # Add critic evaluation to messages
        updated_messages = messages + [evaluation]
        
        return {
            **state,
            "messages": updated_messages,
            "critic_assessment": evaluation.content,
            "quality_pass": quality_pass,
            "quality_score": quality_score,
            "current_step": "verification"
        }
        
    except Exception as e:
        print(f"Critic Agent Error: {e}")
        return {
            **state,
            "critic_assessment": f"Error during evaluation: {e}",
            "quality_pass": False,
            "quality_score": 0,
            "current_step": "verification"
        }