import os
import asyncio
from pathlib import Path
from langchain_openai import ChatOpenAI
from langchain_core.messages import HumanMessage
from langchain.tools import tool
from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
from langchain_chroma import Chroma
from langchain_ollama import OllamaEmbeddings
from langchain_text_splitters import RecursiveCharacterTextSplitter
from langchain_ollama import OllamaEmbeddings
from langchain_tavily import TavilySearchResults

# ---------- LLM ----------
llm = ChatOpenAI(
    model="openai/gpt-oss-20b:free",
    base_url="https://openrouter.ai/api/v1",
    api_key=os.getenv("OPENAI_API_KEY"),
    temperature=0.0,
)

# ---------- Backend ----------
backend = CompositeBackend([
    LocalShellBackend(workspace_dir="./workspace"),
    FilesystemBackend(),
])

# ---------- Vectorstore utilities ----------
PERSIST_DIR = Path("./chroma_db")

def create_vectorstore(persist_directory: str = "./chroma_db"):
    embeddings = OllamaEmbeddings(model="nomic-embed-text")
    return Chroma(persist_directory=persist_directory, embedding_function=embeddings)


def load_documents(directory: str, vectorstore):
    splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
    docs = []
    for file in Path(directory).glob("**/*"):
        if file.suffix.lower() in {".txt", ".md"}:
            text = file.read_text(encoding="utf-8")
            docs.extend(splitter.split_text(text))
    # Convert to Document objects
    from langchain_core.documents import Document
    documents = [Document(page_content=chunk) for chunk in docs]
    vectorstore.add_documents(documents)
    vectorstore.persist()

# ---------- Tools ----------
@tool
def search_local_kb(query: str, top_k: int = 3) -> str:
    """Semantic search in the local ChromaDB knowledge base."""
    vectorstore = create_vectorstore(PERSIST_DIR)
    retriever = vectorstore.as_retriever(search_kwargs={"k": top_k})
    docs = retriever.invoke(query)
    if not docs:
        return "No relevant local documents found."
    return "\n---\n".join(doc.page_content for doc in docs) + "\n[Source: chromadb]"

@tool
def web_search(query: str) -> str:
    """Web search using Tavily."""
    tavily = TavilySearchResults(api_key=os.getenv("TAVILY_API_KEY"))
    results = tavily.run(query)
    if not results:
        return "No web results found."
    snippets = [f"{r['title']}\n{r['content']}" for r in results]
    return "\n---\n".join(snippets) + "\n[Source: tavily]"

# ---------- Agent ----------
SYSTEM_PROMPT = (
    "You are an AI assistant that can answer questions using either a local knowledge base or the web. "
    "If the question refers to documents in the local folder, use the `search_local_kb` tool. "
    "If the question is about recent events or requires up‑to‑date information, use the `web_search` tool. "
    "Always include the source tag (`[Source: chromadb]` or `[Source: tavily]`) in your answer."
)

agent = create_deep_agent(
    model=llm,
    tools=[search_local_kb, web_search],
    backend=backend,
    system_prompt=SYSTEM_PROMPT,
)

# ---------- CLI ----------
async def chat_loop():
    print("RAG Agent ready. Type 'exit' to quit.")
    while True:
        user_input = input("\nЗапрос: ")
        if user_input.strip().lower() == "exit":
            print("Goodbye!")
            break
        result = await agent.ainvoke(
            {"messages": [HumanMessage(content=user_input)]},
            {"configurable": {"thread_id": "session-1"}},
        )
        # The last message is the assistant's reply
        reply = result["messages"][-1].content
        print(reply)

# ---------- Initialization ----------
if __name__ == "__main__":
    # Ensure vectorstore exists and load documents if empty
    vectorstore = create_vectorstore(PERSIST_DIR)
    if not vectorstore.get_all_documents():
        print("Loading documents into ChromaDB...")
        load_documents("./documents", vectorstore)
        print("Documents loaded.")
    asyncio.run(chat_loop())