miku-discord/bot/utils/core.py

# utils/core.py

import asyncio
import aiohttp
import re

import globals
from langchain_community.vectorstores import FAISS
from langchain_text_splitters import CharacterTextSplitter, RecursiveCharacterTextSplitter
from langchain_core.documents import Document
from utils.logger import get_logger

logger = get_logger('core')


# switch_model() removed - llama-swap handles model switching automatically


async def is_miku_addressed(message) -> bool:
    # Check if this is a DM (no guild)
    if message.guild is None:
        # In DMs, always respond to every message
        return True
    
    # Safety check: ensure guild and guild.me exist
    if not message.guild or not message.guild.me:
        logger.warning(f"Invalid guild or guild.me in message from {message.author}")
        return False
    
    # If message contains a ping for Miku, return true
    if message.guild.me in message.mentions:
        return True

    # If message is a reply, check the referenced message author
    if message.reference:
        try:
            referenced_msg = await message.channel.fetch_message(message.reference.message_id)
            if referenced_msg.author == message.guild.me:
                return True
        except Exception as e:
            logger.warning(f"Could not fetch referenced message: {e}")

    cleaned = message.content.strip()

    return bool(re.search(
        r'(?<![\w\(])(?:[^\w\s]{0,2}\s*)?miku(?:\s*[^\w\s]{0,2})?(?=,|\s*,|[!\.?\s]*$)',
        cleaned,
        re.IGNORECASE
    ))

# Vectorstore functionality disabled - not needed with current structured context approach
# If you need embeddings in the future, you can use a different embedding provider
# For now, the bot uses structured prompts from context_manager.py

# def load_miku_knowledge():
#     with open("miku_lore.txt", "r", encoding="utf-8") as f:
#         text = f.read()
#     
#     from langchain_text_splitters import RecursiveCharacterTextSplitter
#     
#     text_splitter = RecursiveCharacterTextSplitter(
#         chunk_size=520,
#         chunk_overlap=50,
#         separators=["\n\n", "\n", ".", "!", "?", ",", " ", ""]
#     )
#     
#     docs = [Document(page_content=chunk) for chunk in text_splitter.split_text(text)]
#     
#     vectorstore = FAISS.from_documents(docs, embeddings)
#     return vectorstore
# 
# def load_miku_lyrics():
#     with open("miku_lyrics.txt", "r", encoding="utf-8") as f:
#         lyrics_text = f.read()
#     
#     text_splitter = CharacterTextSplitter(chunk_size=520, chunk_overlap=50)
#     docs = [Document(page_content=chunk) for chunk in text_splitter.split_text(lyrics_text)]
#     
#     vectorstore = FAISS.from_documents(docs, embeddings)
#     return vectorstore
# 
# miku_vectorstore = load_miku_knowledge()
# miku_lyrics_vectorstore = load_miku_lyrics()