"""
Base configuration and utilities for LangChain agents in FinRyver
"""
import os
from typing import Optional
from langchain_openai import ChatOpenAI
from langchain.agents import AgentExecutor, create_openai_tools_agent
from langchain_core.prompts import ChatPromptTemplate, MessagesPlaceholder
from langchain.tools import Tool
from langchain_core.messages import HumanMessage, SystemMessage
import logging

# Load environment variables
try:
    from dotenv import load_dotenv
    load_dotenv()
except ImportError:
    pass  # dotenv is optional

logger = logging.getLogger(__name__)

class FinRyverAgentConfig:
    """Configuration class for FinRyver agents"""
    
    def __init__(self):
        self.openrouter_api_key = os.getenv("OPENROUTER_API_KEY")
        self.model_name = os.getenv("AGENT_MODEL", "gpt-3.5-turbo")
        self.temperature = float(os.getenv("AGENT_TEMPERATURE", "0.1"))
        self.max_tokens = int(os.getenv("AGENT_MAX_TOKENS", "2000"))
        
    def get_llm(self) -> ChatOpenAI:
        """Get configured LLM instance"""
        if not self.openrouter_api_key:
            logger.warning("OPENROUTER_API_KEY not found. Agent functionality may be limited.")
            return None
            
        return ChatOpenAI(
            api_key=self.openrouter_api_key,
            base_url="https://openrouter.ai/api/v1",
            model=self.model_name,
            temperature=self.temperature,
            max_tokens=self.max_tokens
        )

def create_financial_agent_prompt(role: str, goal: str, context: str = "") -> ChatPromptTemplate:
    """Create a standardized prompt template for financial agents"""
    
    system_message = f"""
    You are a {role} working with financial data analysis and reporting.
    
    Your primary goal: {goal}
    
    Context: {context}
    
    You have access to various tools to help you analyze financial data, generate reports, 
    and ensure compliance with accounting standards. Always provide clear, accurate, and 
    professional responses.
    
    When working with financial data:
    - Ensure all calculations are accurate
    - Follow GAAP/IFRS standards where applicable
    - Provide clear explanations for your analysis
    - Flag any anomalies or inconsistencies
    - Always validate data before proceeding
    
    If you need clarification or additional information, ask specific questions.
    """
    
    return ChatPromptTemplate.from_messages([
        ("system", system_message),
        MessagesPlaceholder(variable_name="chat_history", optional=True),
        ("human", "{input}"),
        MessagesPlaceholder(variable_name="agent_scratchpad")
    ])

def create_agent_executor(
    role: str, 
    goal: str, 
    tools: list, 
    context: str = "",
    llm: Optional[ChatOpenAI] = None
) -> AgentExecutor:
    """Create a configured agent executor"""
    
    if llm is None:
        config = FinRyverAgentConfig()
        llm = config.get_llm()
        
    if llm is None:
        raise ValueError("LLM configuration failed. Check your API keys.")
    
    prompt = create_financial_agent_prompt(role, goal, context)
    
    agent = create_openai_tools_agent(
        llm=llm,
        tools=tools,
        prompt=prompt
    )
    
    return AgentExecutor(
        agent=agent,
        tools=tools,
        verbose=True,
        max_iterations=5,
        early_stopping_method="generate"
    )