import os
import asyncio
from pathlib import Path
from typing import List

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

# --------------------------- 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 ---------------------------
PERSIST_DIR = Path("./chroma_db")
PERSIST_DIR.mkdir(parents=True, exist_ok=True)

embeddings = OllamaEmbeddings(model="nomic-embed-text")
vectorstore = Chroma(persist_directory=str(PERSIST_DIR), embedding_function=embeddings)

# Load documents from ./documents if not already loaded
DOCS_DIR = Path("./documents")
if DOCS_DIR.exists():
    for file in DOCS_DIR.glob("**/*.*"):
        if file.suffix.lower() in {".txt", ".md"}:
            text = file.read_text(encoding="utf-8")
            splitter = RecursiveCharacterTextSplitter(chunk_size=1000, chunk_overlap=200)
            docs = splitter.split_text(text)
            vectorstore.add_texts(docs, metadatas=[{"source": str(file)} for _ in docs])
    vectorstore.persist()

# --------------------------- Tools ---------------------------
@tool
def search_local_kb(query: str, top_k: int = 3) -> str:
    """Semantic search in the local ChromaDB knowledge base."""
    retriever = vectorstore.as_retriever(search_kwargs={"k": top_k})
    docs = retriever.invoke(query)
    if not docs:
        return "No local knowledge found."
    return "\n---\n".join([f"{d.page_content[:500]}..." for d in docs])

@tool
def web_search(query: str) -> str:
    """Web search using Tavily."""
    tavily = TavilySearchResults(api_key=os.getenv("TAVILY_API_KEY"))
    results = tavily.invoke(query)
    if not results:
        return "No web results found."
    return "\n---\n".join([f"{r['title']}: {r['content'][:500]}..." for r in results])

# --------------------------- Agent ---------------------------
SYSTEM_PROMPT = (
    "You are an AI assistant that can answer questions using either a local knowledge base or the web. "
    "If the answer can be found in the local documents, use the `search_local_kb` tool and prefix the response with `[Local KB]`. "
    "If the answer requires up‑to‑date information, use the `web_search` tool and prefix the response with `[Web Search]`. "
    "Always indicate the source in the response."
)

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

# --------------------------- CLI ---------------------------
async def main():
    print("RAG Agent ready. Type 'exit' to quit.")
    while True:
        user_input = input("\nЗапрос: ")
        if user_input.lower() in {"exit", "quit"}:
            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(f"\n{reply}")

if __name__ == "__main__":
    asyncio.run(main())