HeXi/hexi/plugins/nonebot_plugin_galgame_card/__init__.py

"""群聊人设卡 —— 基于群聊语料蒸馏成员形象，生成 galgame 风格人物卡

消息入口：on_message 监听全部消息事件，类型注解过滤出群聊，
两级闸门（群开关 + 个人 opt-in）通过后，治理层处理落库。

当前进度：数据层 + 采集层（消息路径）完成；总结路径（印象/画像）待实现。
"""

import json
import time
from collections import deque
from typing import Optional

from nonebot import get_driver, on_message, require

require("nonebot_plugin_orm")

from nonebot.adapters.onebot.v11 import GroupMessageEvent
from nonebot.plugin import PluginMetadata

# ── 禁用 nonebot_plugin_orm 的启动自动同步 ─────────────────────────────
# .env 里 ALEMBIC_STARTUP_CHECK=false 时，orm 插件每次启动都会 autogenerate
# 同步数据库模式；模型一有变更（改 models.py）就会清空整表数据（已实测踩坑）。
# 本插件的 schema 演进统一走 repository.ensure_schema() 显式迁移，
# 因此把 migrate.sync 替换为安全空操作。改动必须在插件导入期完成
# （早于 orm 的 on_startup 钩子执行）。
from nonebot import logger as _logger

try:
    import nonebot_plugin_orm.migrate as _orm_migrate

    def _safe_sync(*_args, **_kwargs):
        # 同步函数：orm 用 greenlet_spawn 同步调用 migrate.sync，
        # 若写成 async def 会产生 never-awaited coroutine 警告
        _logger.debug("galgame_card | 已禁用 orm 自动同步（schema 演进由 ensure_schema 接管）")

    _orm_migrate.sync = _safe_sync
except ImportError:
    _logger.warning("galgame_card | 无法禁用 orm 自动同步，请检查 nonebot_plugin_orm 是否安装")

from . import models  # noqa: F401  # 确保表结构注册
from . import repository, processor
from . import web  # noqa: F401  # Web 管理后台（/galgame_card）

from hexi.web_config import register_plugin_config  # noqa: E402
from hexi.web_plugin_registry import register_web_plugin  # noqa: E402
from . import web_hub  # noqa: E402


def _apply_galgame_config(values: dict) -> None:
    """Web 保存后热刷新：直接改 config 模块的 pydantic 对象，无需重启。"""
    import sys

    conf_mod = sys.modules.get("hexi.plugins.nonebot_plugin_galgame_card.config")
    if conf_mod is None:
        return
    conf = getattr(conf_mod, "config", None)
    if conf is None:
        return
    for key, value in values.items():
        try:
            setattr(conf, key, value)
        except Exception:  # noqa: BLE001
            pass


def _get_galgame_config_values() -> dict:
    """Web 表单回填当前生效值。"""
    import sys

    conf_mod = sys.modules.get("hexi.plugins.nonebot_plugin_galgame_card.config")
    conf = getattr(conf_mod, "config", None) if conf_mod else None
    if conf is None:
        return {}
    keys = ("web_enable", "web_username", "web_password", "web_secret_key", "image_vision_enabled")
    return {k: getattr(conf, k, None) for k in keys}


register_plugin_config(
    __name__,
    {
        "fields": [
            {"key": "web_enable", "label": "Web 后台启用", "type": "bool", "default": True},
            {"key": "web_username", "label": "Web 登录账号", "type": "string", "default": "admin"},
            {"key": "web_password", "label": "Web 登录密码", "type": "password", "default": "galgame", "secret": True},
            {"key": "web_secret_key", "label": "Web 签名密钥", "type": "password", "default": "galgame-card-secret-key", "secret": True},
            {"key": "image_vision_enabled", "label": "图片识别启用", "type": "bool", "default": False},
        ]
    },
    apply=_apply_galgame_config,
    getter=_get_galgame_config_values,
)

# 注册到统一 Web 管理台（/hub）：hub 启动时挂载 /api/galgame_card
register_web_plugin(
    "galgame_card",
    "群聊人设卡",
    "user",
    lambda: web_hub.build_admin_app(),
    module_name=__name__,
)

__plugin_meta__ = PluginMetadata(
    name="群聊人设卡",
    description="基于群聊语料蒸馏成员形象，生成 galgame 风格人物卡",
    usage="开发中……",
)

# 采样/复读检测的内存状态（不进库）
_recent_texts: dict[int, deque[str]] = {}  # group_id -> 最近消息文本
_last_store: dict[tuple[int, int], float] = {}  # (group_id, user_id) -> 上次落库时间戳


def _is_repeat(group_id: int, content: str) -> bool:
    """复读检测：内容在最近 N 条里出现过则丢弃"""
    queue = _recent_texts.setdefault(group_id, deque(maxlen=processor.REPEAT_WINDOW))
    if content in queue:
        return True
    queue.append(content)
    return False


def _throttled(group_id: int, user_id: int) -> bool:
    """刷屏采样：5 秒内同一个人只落库一次"""
    key = (group_id, user_id)
    now = time.time()
    if now - _last_store.get(key, 0) < processor.THROTTLE_SECONDS:
        return True
    _last_store[key] = now
    return False


_driver = get_driver()


@_driver.on_startup
async def _ensure_schema():
    """老库迁移（persona_group.group_name 列），幂等"""
    await repository.ensure_schema()


collector = on_message(block=False)  # 监听全部消息事件，不拦截其他插件


@collector.handle()
async def collect(event: GroupMessageEvent):
    # 鉴权：两级闸门（群开关 → 个人 opt-in）
    if not await repository.is_group_enabled(event.group_id):
        return
    if not await repository.is_joined(event.user_id, event.group_id):
        return
    # 机器人自己（如转发）不收
    if event.user_id == event.self_id:
        return

    command_starts = get_driver().config.command_start
    # 治理：文本 / 图片 / 表情任一存在才记录
    if not processor.has_recordable_content(event):
        return
    text = processor.filter_content(
        processor.extract_text(event), command_starts=command_starts
    )
    image_hashes = processor.extract_image_hashes(event)
    content = processor.build_content(
        text or "", len(image_hashes), processor.count_faces(event)
    )
    if content is None:
        return
    # 脱敏：敏感值替换为占位符（语境 = 本群最近几条已治理文本，用于"验证码/密码"类强化）
    context = " ".join(_recent_texts.get(event.group_id, ()))
    content = processor.desensitize(content, context)
    # 采样：复读 + 刷屏
    if _is_repeat(event.group_id, content):
        return
    if _throttled(event.group_id, event.user_id):
        return

    await repository.add_chat_log(
        user_id=event.user_id,
        group_id=event.group_id,
        content=content,
        nickname=event.sender.card or event.sender.nickname or "",
        target_user_id=processor.extract_target_user_id(event),
        reply_to_content=processor.extract_reply_to_content(event),
        image_count=len(image_hashes),
        image_hashes=json.dumps(image_hashes, ensure_ascii=False) if image_hashes else None,
    )