hendrik/tools/roleplayer.py

import re

schema_need_response = {
    "type": "function",
    "function": {
        "name": "need_response",
        "description": (
            "Decide whether you should respond to the current message. "
            "Use this tool when you are unsure whether to reply or stay silent. "
            "Returns 'true' if you should respond, 'false' if you should stay silent. "
            "Rules: "
            "- Return 'true' if your name is mentioned or someone talks about you. "
            "- Return 'true' if the message is related to your previous conversation. "
            "- Return 'false' if the message is between other people, unclear, "
            "unrelated to you, or you have nothing to add."
        ),
        "parameters": {
            "type": "object",
            "properties": {
                "message": {
                    "type": "string",
                    "description": "The latest message to evaluate.",
                },
                "sender_nickname": {
                    "type": "string",
                    "description": "The nickname of the person who sent the message.",
                },
                "recent_history": {
                    "type": "string",
                    "description": "Recent conversation history for context (last few messages).",
                },
                "my_name": {
                    "type": "string",
                    "description": "Your (the AI's) name.",
                },
            },
            "required": ["message", "sender_nickname", "recent_history", "my_name"],
        },
    },
}

def _name_mentioned(name: str, text: str) -> bool:
    text_lower = text.lower()
    name_lower = name.lower()
    pattern = r'\b' + re.escape(name_lower) + r'\b'
    return bool(re.search(pattern, text_lower))


def _bot_nick_mentioned(name: str, text: str) -> bool:
    """Mention nama bot, termasuk varian suffix angka dari logika anti-ban
    MUC (mis. 'lily' juga cocok untuk 'lily_1')."""
    text_lower = text.lower()
    pattern = r'\b' + re.escape(name.lower()) + r'(?:_\d+)?\b'
    return bool(re.search(pattern, text_lower))

def need_response(message: str, sender_nickname: str, recent_history: str, my_name: str) -> str:
    """
    Decide whether the AI should respond to a message.
    
    Args:
        message: The latest message to evaluate.
        sender_nickname: Nickname of the sender.
        recent_history: Recent conversation history for context.
        my_name: The AI's name.
    
    Returns:
        "true"  → should respond
        "false" → should stay silent
    
    Rules:
        1. STRONG — Direct call/mention of AI's name → always True
        2. BRIEF  — Talks about AI in third person → True
        3. CONTEXTUAL — Related to AI's previous conversation → True
        4. NO REPLY — Unrelated, confusing, between other people → False
    """
    msg = message.strip()

    # --- Rule 4: Empty message ---
    if not msg:
        return "false"

    # --- Rule 1: Direct mention/name call ---
    if _name_mentioned(my_name, msg):
        return "true"

    # --- Rule 2: Talks about AI (third person) ---
    name_parts = my_name.lower().split()
    text_lower = msg.lower()
    if any(part in text_lower for part in name_parts if len(part) > 1):
        return "true"

    # --- Rule 3: Contextual ---
    # Logic updated: We no longer return "true" just because history exists.
    # The actual decision for context should be handled by the LLM via the tool call
    # since determining 'relatedness' requires semantic understanding.
    # However, as a Python helper, we return "false" to avoid false-positives,
    # forcing the system to rely on the LLM's reasoning if called as a tool.
    return "false"


# Pola sapaan XMPP MUC: pesan diawali "Nama: " (mis. "Tinny: O iya, ...").
# Guard (?!//) agar URL seperti "https://..." tidak dianggap sapaan.
_ADDRESS_PREFIX_RE = re.compile(r'^\s*([A-Za-z0-9_\-]+)\s*:(?!//)\s+\S')


def _collect_bot_names(my_name: str, bot_aliases=None) -> set:
    """Semua variasi nama bot: codename, kata penyusunnya, plus alias tambahan
    (mis. nick MUC beserta varian suffix-nya seperti lily_1)."""
    names = set()

    def _add(value: str):
        v = (value or '').strip().lower()
        if not v:
            return
        names.add(v)
        for part in v.split():
            if len(part) > 1:
                names.add(part)

    _add(my_name)
    for alias in (bot_aliases or []):
        _add(alias)
    return names


def should_respond(message: str, sender_nickname: str, recent_history: str, my_name: str,
                   bot_aliases=None) -> bool:
    """
    Gate deterministik (tanpa LLM): apakah bot harus membalas pesan group/MUC.

    Urutan aturan:
      0. Pesan kosong → False
      1. Pesan diawali "Nama: " (format sapaan XMPP MUC):
         - Nama = nama bot   → True  (disapa langsung)
         - Nama lain         → False (jelas sedang bicara ke orang lain)
      2. Nama bot muncul di mana pun dalam pesan (word-boundary) → True
      3. Selain itu → False (default diam)

    Catatan: `recent_history` dipertahankan demi kompatibilitas pemanggil
    lama, tapi sengaja TIDAK dipakai — riwayat bukan alasan untuk membalas.
    """
    msg = (message or '').strip()
    if not msg:
        return False

    names = _collect_bot_names(my_name, bot_aliases)

    # --- Aturan 1: format sapaan "Nama: pesan" ---
    match = _ADDRESS_PREFIX_RE.match(msg)
    if match:
        target = match.group(1).lower()
        # Cocokkan persis, atau varian suffix dari alias (mis. lily_1 vs lily)
        for n in names:
            if target == n or target.startswith(n + '_'):
                return True
        return False

    # --- Aturan 2: mention nama bot (kata utuh, bukan substring) ---
    return any(_bot_nick_mentioned(n, msg) for n in names)