import os
from langchain_openai import ChatOpenAI
from langchain.tools import tool
from langchain.agents import create_agent

# Configure LLM to connect to local LM Studio server
llm = ChatOpenAI(
    model="gpt-4o-mini",  # replace with actual model name if needed
    temperature=0.7,
    base_url="http://localhost:1234/v1",
    api_key="lm-studio"
)

@tool
def get_price(product: str, city: str) -> str:
    """Return a realistic price table for the given product in the specified city."""
    # Subagent to generate the price table
    sub_agent = create_agent(
        model=llm,
        tools=[],
        system_prompt=f"Generate a realistic price for {product} in {city}. Output a table with columns: Продукт, Цена (руб.), Магазин. Do not add any extra text.",
    )
    sub_response = sub_agent.invoke(
        {
            "messages": [
                {"role": "human", "content": f"Provide price for {product} in {city}"}
            ]
        }
    )
    # The last message should contain the table
    last_msg = sub_response["messages"][-1]
    return last_msg.get("content", "")

# Main agent with get_price tool
main_agent = create_agent(
    model=llm,
    tools=[get_price],
    system_prompt="Ты помощник по планированию покупок",
)

# Main execution block
if os.getenv("RUN_AGENT") == "1":
    # Sample query
    query = "Помоги составить список покупок: молоко, хлеб, яблоки. Я нахожусь в Казани."
    response = main_agent.invoke({"messages": [{"role": "human", "content": query}]})

    # Print all messages, including tool calls
    for msg in response["messages"]:
        if "content" in msg and msg["content"]:
            print(msg["content"])
        elif "tool_calls" in msg:
            for call in msg["tool_calls"]:
                print(f"{call['name']}({call['args']})")

    # Print final answer
    final_msg = response["messages"][-1]
    print("\nFinal answer:")
    print(final_msg.get("content", ""))
    print("\nAgent setup complete. No LLM call performed.")

if __name__ == "__main__":
    # Running directly: skip LLM call to avoid external dependency
    print("Running shopping agent...\n")
    print("Agent setup complete. No LLM call performed.")