import os
import asyncio
from pathlib import Path
from langchain_openai import ChatOpenAI, OpenAIEmbeddings
from langchain_chroma import Chroma
from langchain_core.documents import Document
from langchain.tools import tool
from deepagents import create_deep_agent
from deepagents.backends import FilesystemBackend, LocalShellBackend, CompositeBackend
from langchain_core.messages import HumanMessage

# ---------------------------
# Configuration
# ---------------------------
OPENAI_API_KEY = os.getenv("OPENAI_API_KEY")
if not OPENAI_API_KEY:
    raise RuntimeError("OPENAI_API_KEY not set in environment")

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

# Embeddings via OpenRouter
embeddings = OpenAIEmbeddings(
    model="text-embedding-3-small",
    base_url="https://openrouter.ai/api/v1",
    api_key=OPENAI_API_KEY,
)

# Chroma vector store (persisted)
CHROMA_PATH = Path("./chroma_faq")
vector_store = Chroma(
    collection_name="faq_collection",
    embedding_function=embeddings,
    persist_directory=str(CHROMA_PATH),
)

# ---------------------------
# Data loading
# ---------------------------

def load_faq_to_chroma(md_folder: str = "data"):
    """Load all .md files from md_folder into ChromaDB.
    Each file is split into chunks and added to the vector store.
    """
    md_path = Path(md_folder)
    if not md_path.exists():
        raise FileNotFoundError(f"Markdown folder {md_folder} not found")
    docs = []
    for md_file in md_path.glob("*.md"):
        text = md_file.read_text(encoding="utf-8")
        # Simple chunking: split by double newlines
        chunks = [c.strip() for c in text.split("\n\n") if c.strip()]
        for i, chunk in enumerate(chunks):
            docs.append(Document(page_content=chunk, metadata={"source": md_file.name, "chunk": i}))
    if docs:
        vector_store.add_documents(docs)
        vector_store.persist()
    else:
        print("No markdown files found to load.")

# ---------------------------
# Tools
# ---------------------------
@tool
def search_course_docs(query: str, k: int = 3) -> str:
    """Search the FAQ knowledge base for relevant information."""
    docs = vector_store.similarity_search(query, k=k)
    if not docs:
        return "No relevant information found in the course materials."
    return "\n\n---\n\n".join(f"**{doc.metadata.get('source')}** (chunk {doc.metadata.get('chunk')}):\n{doc.page_content}" for doc in docs)

@tool
def fetch_course_meta(query: str) -> str:
    """Mock MCP-style tool that returns course metadata.
    In production this would perform an HTTP GET to an MCP server.
    Here we return a static JSON-like string for simplicity.
    """
    # Static mock data
    meta = {
        "schedule": {
            "Monday": "Lecture 1: Introduction",
            "Wednesday": "Lecture 2: Advanced Topics",
            "Friday": "Lab Session"
        },
        "instructor": "Dr. Jane Doe",
        "credits": 3
    }
    return f"Course metadata: {meta}"

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

# ---------------------------
# Agent creation
# ---------------------------
agent = create_deep_agent(
    model=llm,
    tools=[search_course_docs, fetch_course_meta],
    backend=backend,
    system_prompt="You are a helpful FAQ bot for the course. Use the search_course_docs tool for questions about lecture materials, and fetch_course_meta for questions about schedule or metadata. In your answer, clearly indicate the source: either 'chroma' or 'mcp_meta'. Do not use both tools unless necessary.",
)

# ---------------------------
# CLI
# ---------------------------
PRESET_QUESTIONS = [
    "What topics are covered in Lecture 1?",  # should hit chroma
    "Explain the concept of tokenization in NLP.",  # chroma
    "When is the next lab session?",  # should hit mcp_meta
]

async def run_agent(question: str, thread_id: str = "session-1"):
    result = await agent.ainvoke(
        {"messages": [HumanMessage(content=question)]},
        {"configurable": {"thread_id": thread_id}},
    )
    # The last message is the agent's reply
    reply = result["messages"][-1].content
    print(f"\nQ: {question}\nA: {reply}\n")

async def main():
    # Load data if not already loaded
    if not CHROMA_PATH.exists() or not any(CHROMA_PATH.iterdir()):
        print("Loading FAQ data into Chroma...")
        load_faq_to_chroma()
    else:
        print("Chroma database already loaded.")

    # Run preset questions
    for i, q in enumerate(PRESET_QUESTIONS, 1):
        await run_agent(q, thread_id=f"preset-{i}")

    # Interactive mode
    print("Enter your own questions (type 'exit' to quit):")
    while True:
        user_input = input("> ")
        if user_input.lower() in {"exit", "quit"}:
            break
        await run_agent(user_input, thread_id="interactive")

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