import re


def remove_markdown(text: str) -> str:
    text = re.sub(r"\*\*(.+?)\*\*", r"\1", text)
    text = re.sub(r"\*(.+?)\*", r"\1", text)
    text = re.sub(r"__(.+?)__", r"\1", text)
    text = re.sub(r"_(.+?)_", r"\1", text)
    text = re.sub(r"~~(.+?)~~", r"\1", text)
    text = re.sub(r"```[\s\S]*?```", "", text)
    text = re.sub(r"`{1,3}[^`]*`{1,3}", "", text)
    text = re.sub(r"\[([^\]]*)\]\([^)]*\)", r"\1", text)
    text = re.sub(r"!\[.*?\]\(.*?\)", "[图片]", text)
    text = re.sub(r"^#+ (.*?)$", r"\1", text, flags=re.MULTILINE)
    text = re.sub(r"^[*-] (.*?)$", r"· \1", text, flags=re.MULTILINE)
    text = re.sub(r"^> (.*?)$", r"  \1", text, flags=re.MULTILINE)
    text = re.sub(r"\n{3,}", "\n\n", text)
    return text.strip()


def split_utf8_safe(text: str, max_len: int) -> list[str]:
    if len(text) <= max_len:
        return [text]
    chunks = []
    while text:
        if len(text) <= max_len:
            chunks.append(text)
            break
        split_at = text.rfind("\n", 0, max_len)
        if split_at == -1 or split_at < max_len // 2:
            split_at = max_len
        chunks.append(text[:split_at])
        text = text[split_at:].lstrip()
    return chunks