"""LangGraph Agent"""
import os
from dotenv import load_dotenv
from langgraph.graph import START, StateGraph, MessagesState
from langgraph.prebuilt import tools_condition
from langgraph.prebuilt import ToolNode
from langchain_google_genai import ChatGoogleGenerativeAI
from langchain_groq import ChatGroq
from langchain_huggingface import ChatHuggingFace, HuggingFaceEndpoint, HuggingFaceEmbeddings
from langchain_community.tools.tavily_search import TavilySearchResults
from langchain_community.document_loaders import WikipediaLoader
from langchain_community.document_loaders import ArxivLoader
try:
    from langchain_chroma import Chroma
except ImportError:
    from langchain_community.vectorstores import Chroma
from langchain_core.messages import SystemMessage, HumanMessage
from langchain_core.tools import tool
from langchain.tools.retriever import create_retriever_tool
from deep_research_tool import deep_research

load_dotenv()

@tool
def multiply(a: int, b: int) -> int:
    """Multiply two numbers.
    Args:
        a: first int
        b: second int
    """
    return a * b

@tool
def add(a: int, b: int) -> int:
    """Add two numbers.
    Args:
        a: first int
        b: second int
    """
    return a + b

@tool
def subtract(a: int, b: int) -> int:
    """Subtract two numbers.
    Args:
        a: first int
        b: second int
    """
    return a - b

@tool
def divide(a: int, b: int) -> int:
    """Divide two numbers.
    Args:
        a: first int
        b: second int
    """
    if b == 0:
        raise ValueError("Cannot divide by zero.")
    return a / b

@tool
def modulus(a: int, b: int) -> int:
    """Get the modulus of two numbers.
    Args:
        a: first int
        b: second int
    """
    return a % b

@tool
def wiki_search(query: str) -> str:
    """Search Wikipedia for a query and return maximum 2 results.
    Args:
        query: The search query."""
    search_docs = WikipediaLoader(query=query, load_max_docs=2).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return {"wiki_results": formatted_search_docs}

@tool
def web_search(query: str) -> str:
    """Search Tavily for a query and return maximum 3 results.
    Args:
        query: The search query."""
    search_docs = TavilySearchResults(max_results=3).invoke(query=query)
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content}\n</Document>'
            for doc in search_docs
        ])
    return {"web_results": formatted_search_docs}

@tool
def arvix_search(query: str) -> str:
    """Search Arxiv for a query and return maximum 3 result.
    Args:
        query: The search query."""
    search_docs = ArxivLoader(query=query, load_max_docs=3).load()
    formatted_search_docs = "\n\n---\n\n".join(
        [
            f'<Document source="{doc.metadata["source"]}" page="{doc.metadata.get("page", "")}"/>\n{doc.page_content[:1000]}\n</Document>'
            for doc in search_docs
        ])
    return {"arvix_results": formatted_search_docs}


# load the system prompt from the file
with open("system_prompt.txt", "r", encoding="utf-8") as f:
    system_prompt = f.read()

# System message
sys_msg = SystemMessage(content=system_prompt)

# build a retriever with local ChromaDB
# Use a smaller, faster embedding model
embeddings = HuggingFaceEmbeddings(
    model_name="all-MiniLM-L6-v2",  # Smaller model, faster download (dim=384)
    model_kwargs={'device': 'cpu'},
    encode_kwargs={'normalize_embeddings': True}
)

# Use local ChromaDB instead of Supabase
vector_store = Chroma(
    collection_name="gaia_questions",
    embedding_function=embeddings,
    persist_directory="./chroma_db"  # Local storage
)

# Note: You need to populate the vector store with data from metadata.jsonl first
# This can be done separately (see setup instructions)

create_retriever_tool = create_retriever_tool(
    retriever=vector_store.as_retriever(),
    name="Question Search",
    description="A tool to retrieve similar questions from a vector store.",
)

tools = [
    multiply,
    add,
    subtract,
    divide,
    modulus,
    wiki_search,
    web_search,
    arvix_search,
    deep_research,
]

# Build graph function
def build_graph(provider: str = "google"):
    """Build the graph"""
    # Load environment variables from .env file
    if provider == "google":
        # Google Gemini
        llm = ChatGoogleGenerativeAI(model="gemini-2.0-flash", temperature=0)
    elif provider == "groq":
        # Groq https://console.groq.com/docs/models
        llm = ChatGroq(model="qwen-qwq-32b", temperature=0) # optional : qwen-qwq-32b gemma2-9b-it
    elif provider == "huggingface":
        # TODO: Add huggingface endpoint
        llm = ChatHuggingFace(
            llm=HuggingFaceEndpoint(repo_id = "Qwen/Qwen2.5-Coder-32B-Instruct"),
        )
    else:
        raise ValueError("Invalid provider. Choose 'google', 'groq' or 'huggingface'.")
    # Bind tools to LLM
    llm_with_tools = llm.bind_tools(tools)

    # Node
    def assistant(state: MessagesState):
        """Assistant node"""
        return {"messages": [llm_with_tools.invoke(state["messages"])]}
    
    def retriever(state: MessagesState):
        """Retriever node"""
        try:
            similar_question = vector_store.similarity_search(state["messages"][0].content, k=1)
            if similar_question:
                example_msg = HumanMessage(
                    content=f"Here I provide a similar question and answer for reference: \n\n{similar_question[0].page_content}",)
                return {"messages": [sys_msg] + state["messages"] + [example_msg]}
        except Exception as e:
            print(f"Retriever warning: {e}. Proceeding without similar examples.")

        # If retrieval fails or no results, just return with system message
        return {"messages": [sys_msg] + state["messages"]}

    builder = StateGraph(MessagesState)
    builder.add_node("retriever", retriever)
    builder.add_node("assistant", assistant)
    builder.add_node("tools", ToolNode(tools))
    builder.add_edge(START, "retriever")
    builder.add_edge("retriever", "assistant")
    builder.add_conditional_edges("assistant", tools_condition)
    builder.add_edge("tools", "assistant")

    # Compile graph
    return builder.compile()

# test
if __name__ == "__main__":
    # Simple test question
    question = "现在是2025年，现在因为AI带来的对于美国就业市场的冲击具体有哪些，我需要具体的数据，也需要知名机构的背书"

    print("\n" + "="*60)
    print("Testing Agent with question:")
    print(f"Q: {question}")
    print("="*60 + "\n")

    # Build the graph - using HuggingFace as default provider
    # Change to "groq" or "google" if you have those API keys
    graph = build_graph(provider="huggingface")

    # Run the graph
    messages = [HumanMessage(content=question)]
    result = graph.invoke({"messages": messages})

    print("\n" + "="*60)
    print("Agent Messages:")
    print("="*60 + "\n")
    for m in result["messages"]:
        m.pretty_print()
        print("-"*60)