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 ---------------------
BASE_DIR = Path(__file__).parent
DATA_DIR = BASE_DIR / "data"
CHROMA_DIR = BASE_DIR / "chroma_faq"
MOCK_META_FILE = BASE_DIR / "course_meta.json"

# --------------------- LLM and Embeddings ---------------------
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,
)

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

# --------------------- Chroma Vector Store ---------------------
vector_store = Chroma(
    collection_name="faq_collection",
    embedding_function=embeddings,
    persist_directory=str(CHROMA_DIR),
)

# --------------------- Tools ---------------------
@tool
def search_course_docs(query: str, k: int = 3) -> str:
    """Search the local FAQ collection for relevant passages."""
    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('title', 'Document')}**\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 be an HTTP call to an MCP server.
    Here we read a local JSON file for simplicity.
    """
    import json
    if not MOCK_META_FILE.exists():
        return "Metadata source not available."
    with open(MOCK_META_FILE, "r", encoding="utf-8") as f:
        data = json.load(f)
    # Simple keyword search in the metadata
    results = [f"{k}: {v}" for k, v in data.items() if query.lower() in k.lower() or query.lower() in str(v).lower()]
    return "\n".join(results) if results else "No metadata matches your query."

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

# --------------------- Agent ---------------------
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.\n"
        "Use the search_course_docs tool for questions about lecture materials.\n"
        "Use the fetch_course_meta tool for questions about schedule or metadata.\n"
        "Do not call both tools unless absolutely necessary.\n"
        "In your final answer, prefix the source with 'source: chroma' or 'source: mcp_meta'."
    ),
)

# --------------------- Data Loading ---------------------
async def load_faq_to_chroma():
    """Load all .md files from data/ into the Chroma collection."""
    if not DATA_DIR.exists():
        print("Data directory not found.")
        return
    docs = []
    for md_file in DATA_DIR.glob("*.md"):
        text = md_file.read_text(encoding="utf-8")
        docs.append(Document(page_content=text, metadata={"title": md_file.stem}))
    if docs:
        vector_store.add_documents(docs)
        vector_store.persist()
        print(f"Loaded {len(docs)} documents into Chroma.")
    else:
        print("No markdown files found in data/.")

# --------------------- CLI ---------------------
PRESET_QUESTIONS = [
    "What is the deadline for the final project?",  # chroma
    "Explain the concept of tokenization in NLP.",  # chroma
    "When is the next lecture scheduled?",  # mcp_meta
]

async def run_cli():
    await load_faq_to_chroma()
    print("\n--- FAQ Bot CLI ---\n")
    for i, q in enumerate(PRESET_QUESTIONS, 1):
        print(f"{i}. {q}")
    print("\nEnter your own question (or 'exit' to quit):")
    while True:
        user_input = input("> ")
        if user_input.lower() in {"exit", "quit"}:
            break
        result = await agent.ainvoke(
            {"messages": [HumanMessage(content=user_input)]},
            {"configurable": {"thread_id": "session-1"}},
        )
        print(result["messages"][-1].content)

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