import os
import asyncio
import json
import httpx
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

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

# --------------------- LLM & 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 DB ---------------------
vector_store = Chroma(
    collection_name="faq_collection",
    embedding_function=embeddings,
    persist_directory=str(CHROMA_DIR),
)

# Load markdown files into Chroma if not already loaded
if not CHROMA_DIR.exists() or not any(CHROMA_DIR.iterdir()):
    docs = []
    for md_file in DATA_DIR.glob("*.md"):
        text = md_file.read_text(encoding="utf-8")
        docs.append(Document(page_content=text, metadata={"source": md_file.name}))
    vector_store.add_documents(docs)
    vector_store.persist()

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

@tool
def fetch_course_meta(query: str) -> str:
    """Fetch course metadata (e.g., schedule) from a local JSON mock."""
    if not META_JSON.exists():
        return "Metadata file not found."
    data = json.loads(META_JSON.read_text(encoding="utf-8"))
    # Simple keyword search in the metadata
    matches = [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(matches) if matches else "No metadata matches the 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 assistant for the course.\n"
        "When a user asks about course content, use the search_course_docs tool.\n"
        "When a user asks about schedule, metadata, or other non‑content info, use fetch_course_meta.\n"
        "Do not use both tools unless absolutely necessary.\n"
        "In your final answer, prefix the source with 'source: chroma' or 'source: mcp_meta'."
    ),
)

# --------------------- CLI ---------------------
SAMPLE_QUESTIONS = [
    "What topics are covered in the first lecture?",  # should hit chroma
    "Explain the concept of tokenization in NLP.",  # chroma
    "When is the next class scheduled?",  # meta
]

async def run_interactive():
    print("Welcome to the Course FAQ Bot! Type 'exit' to quit.")
    while True:
        user_input = input("\nYou: ")
        if user_input.lower() in {"exit", "quit"}:
            break
        result = await agent.ainvoke(
            {"messages": [{"role": "user", "content": user_input}]},
            {"configurable": {"thread_id": "interactive-session"}},
        )
        print("\nAssistant:", result["messages"][-1]["content"])

async def run_samples():
    for q in SAMPLE_QUESTIONS:
        print("\nQuestion:", q)
        result = await agent.ainvoke(
            {"messages": [{"role": "user", "content": q}]},
            {"configurable": {"thread_id": "sample-session"}},
        )
        print("Answer:", result["messages"][-1]["content"])

async def main():
    # Run sample questions first
    await run_samples()
    # Then enter interactive mode
    await run_interactive()

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