yunke/yunke-server/app/db/models.py

"""Core ORM models for the yunke data-mirror system.

Every model maps an entity observed in the yunke CRM API (see
``docs/superpowers/specs/2026-08-01-yunke-data-dictionary.md``) to a SQL table.
Models target **MySQL in production** but keep column types portable so the
suite can exercise them on **in-memory SQLite** (see ``tests/test_models.py``).

Conventions
-----------
* SQLAlchemy 2.0 ``Mapped``/``mapped_column`` style; all classes extend
  ``app.db.base.Base``.
* API field names are mapped to ``snake_case`` columns; the original payload is
  preserved verbatim in ``raw_json`` (``sa.JSON``).
* Common audit columns on every source-mirrored table:
    - ``version``    — source update stamp (string when the API gives a version
                       token, BigInteger when it is a ms timestamp).
    - ``raw_json``   — the original API record (``sa.JSON``).
    - ``fetched_at`` — when we pulled the row (server default ``now()``).
    - ``updated_at`` — when the row was last written (server default + onupdate).
* ``channel`` is only added where it is *meaningful*:
    - Communication tables (``Customer``, ``Message``, ``Media``, ``ChatGroup``,
      ``GroupMember``, ``Sms``) use ``channel`` in {``wechat``, ``whatsapp``,
      ``sms``}.
    - ``PhoneCall`` uses ``channel`` to mean call-type in {``phone_call``,
      ``voice_call``} (calls are not tied to a messaging channel).
    - ``SyncState`` uses ``channel`` to scope a sync cursor (together with
      ``entity_type``).
    - ``Staff``, ``Department``, ``WechatAccount``, ``WhatsappAccount``,
      ``YkAccount``, ``SyncRun``, ``MomentsPost`` carry no ``channel`` column.
* Primary keys use the natural source id where one exists; otherwise an
  integer surrogate PK is used (``SyncState``, ``YkAccount``, ``SyncRun``).
* ``GroupMember`` uses a composite PK ``(channel, room_id, member_id)``.

The ``Message`` model currently maps to a single physical ``message`` table.
Real-world volume is expected at millions of rows/month, so the long-term plan
is time-sharded physical tables named via :func:`message_table_name`. That
sharding is a LATER task — for now every message row lives in ``message`` and
the helper below is provided so call-sites can already agree on the naming
convention.
"""

from __future__ import annotations

import datetime as dt
from typing import Any

import sqlalchemy as sa
from sqlalchemy.dialects.mysql import MEDIUMTEXT  # noqa: E402
from sqlalchemy import BigInteger, Boolean, DateTime, Index, Integer, String, Text
from sqlalchemy.orm import Mapped, mapped_column
from sqlalchemy.types import JSON

from app.db.base import Base

# ---------------------------------------------------------------------------
# Helpers
# ---------------------------------------------------------------------------


def message_table_name(channel: str, timestamp: int | dt.datetime) -> str:
    """Return the conventional sharded table name for a message.

    Format: ``message_<channel>_<YYYYMM>`` where ``YYYYMM`` is derived from the
    message timestamp. ``timestamp`` may be either:

    * a Unix epoch in **milliseconds** (``int``) — the form used by the
      ``Message.timestamp`` column and the yunke API, or
    * a ``datetime.datetime`` instance (any tz).

    Examples
    --------
    >>> import datetime as dt
    >>> message_table_name("wechat", 1_700_000_000_000)
    'message_wechat_202311'
    >>> message_table_name("whatsapp", dt.datetime(2024, 1, 5))
    'message_whatsapp_202401'
    """
    if isinstance(timestamp, dt.datetime):
        ts = timestamp
    else:
        # Treat int as ms-since-epoch (UTC). ``float`` also tolerated.
        ts = dt.datetime.fromtimestamp(int(timestamp) / 1000, tz=dt.UTC)
    return f"message_{channel}_{ts.strftime('%Y%m')}"


# ---------------------------------------------------------------------------
# Shared column defaults
# ---------------------------------------------------------------------------


def _fetched_at() -> Mapped[dt.datetime]:
    return mapped_column(
        DateTime, server_default=sa.func.now(), nullable=False
    )


def _updated_at() -> Mapped[dt.datetime]:
    return mapped_column(
        DateTime,
        server_default=sa.func.now(),
        onupdate=sa.func.now(),
        nullable=False,
    )


# ===========================================================================
# 1. Organization & people
# ===========================================================================


class Department(Base):
    """云客 部门/分组 — source: ``POST /usercenter/dept/tree``."""

    __tablename__ = "department"

    dept_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    parent_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    path: Mapped[str | None] = mapped_column(String(512), nullable=True)

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()


class Staff(Base):
    """员工 — embedded in account lists (``userId`` + ``userName``)."""

    __tablename__ = "staff"

    user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sale_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    dept_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    is_on_job: Mapped[bool | None] = mapped_column(Boolean, nullable=True)

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()


# ===========================================================================
# 2. Staff messaging accounts (channel identity, so no `channel` column)
# ===========================================================================


class WechatAccount(Base):
    """员工微信号 — source: ``POST /wechatweb/wxUser/list`` (wechatId PK)."""

    __tablename__ = "wechat_account"

    wx_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    nick_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    alias: Mapped[str | None] = mapped_column(String(255), nullable=True)
    phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    user_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    contacts_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    group_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    send_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    receive_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    is_on_job: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
    db_size: Mapped[int | None] = mapped_column(BigInteger, nullable=True)  # 字节数可超 32 位 INT(实测 2.17GB,2026-08-21)
    online_status: Mapped[str | None] = mapped_column(String(32), nullable=True)
    last_update: Mapped[int | None] = mapped_column(BigInteger, nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    # 云客 wxUser/list 返回顺序(对齐云客员工列表排列;NULL=未回填按 wx_id 排)
    list_order: Mapped[int | None] = mapped_column(Integer, nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()


class WhatsappAccount(Base):
    """员工 WhatsApp 账号 — source: ``POST /qqweb/WhatsAppUser/businessSalesList``.

    PK is ``uid`` of the form ``<phone>@s.whatsapp.net``.
    """

    __tablename__ = "whatsapp_account"

    uid: Mapped[str] = mapped_column(String(128), primary_key=True)
    user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    user_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    nick_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sale_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sales_bind_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    contacts_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    group_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    talker_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    friend_add_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    is_on_job: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
    last_update: Mapped[int | None] = mapped_column(BigInteger, nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()


# ===========================================================================
# 3. Communication entities (carry a meaningful `channel` column)
# ===========================================================================


class Customer(Base):
    """客户/好友 (WeChat friend OR WhatsApp contact OR SMS peer).

    Source: ``POST /wechatweb/wxFriends/friend_list/es`` (WeChat) or
    ``POST /qqweb/WhatsAppUser/businessFriendList`` (WhatsApp). PK is the
    source friend id: ``friendWxId`` for WeChat, ``<phone>@s.whatsapp.net``
    for WhatsApp.
    """

    __tablename__ = "customer"

    friend_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)
    owner_account_id: Mapped[str | None] = mapped_column(
        String(128), nullable=True
    )  # wxId (WeChat) / uid (WhatsApp) — owning staff account
    friend_nickname: Mapped[str | None] = mapped_column(String(255), nullable=True)
    friend_remark: Mapped[str | None] = mapped_column(String(255), nullable=True)
    real_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    wechat_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    gender: Mapped[int | None] = mapped_column(Integer, nullable=True)
    region: Mapped[str | None] = mapped_column(String(255), nullable=True)
    description: Mapped[str | None] = mapped_column(Text, nullable=True)
    sale_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    dept_route: Mapped[str | None] = mapped_column(String(255), nullable=True)
    dept_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    head_image_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    last_chat_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    add_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)  # ms epoch; from raw_json.addTime
    send_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    receive_num: Mapped[int | None] = mapped_column(Integer, nullable=True)
    message_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    delete_flag: Mapped[int | None] = mapped_column(Integer, nullable=True)
    is_block: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
    friend_state: Mapped[int | None] = mapped_column(Integer, nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index(
            "ix_customer_owner_friend",
            "channel",
            "owner_account_id",
            "friend_id",
        ),
        # /api/analytics/health MAX(updated_at) 新鲜度探针;无索引时全表扫。
        # 「模型+迁移双声明」防 alembic autogenerate 反 DROP(c3d4e5f6a7b8)。
        Index("ix_customer_updated_at", "updated_at"),
    )


class ChatGroup(Base):
    """聊天群 — source: ``POST /wechatweb/chatroom/getChatroomList``.

    PK is composite (``room_id``, ``channel``, ``owner_account_id``) — the
    same room mirrors to one row per owning staff account; ``room_id`` is the
    source ``chatRoomId`` (ends with ``@chatroom``). The raw ``memberIds``
    (semicolon-joined wxids) is kept verbatim in ``member_ids``; the parsed
    members are mirrored into :class:`GroupMember`.
    """

    __tablename__ = "chat_group"

    # 复合主键(channel, owner, room):同一群在每个员工名下各一行(2026-08-24)
    # 原按 room_id 单列 PK 会把多员工同群去重(云客张士蓓 64 群 vs 我们 42)
    room_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
    owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    room_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    owner_account_nickname: Mapped[str | None] = mapped_column(
        String(255), nullable=True
    )
    member_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    member_ids: Mapped[str | None] = mapped_column(Text, nullable=True)
    head_image_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    owner_user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    owner_user_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    message_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    own_message_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    loss_members: Mapped[int | None] = mapped_column(Integer, nullable=True)
    add_members: Mapped[int | None] = mapped_column(Integer, nullable=True)
    last_chat_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    update_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)

    # 通讯录·微信群 tab 对齐云客的补充列（2026-08-25，从 raw_json 提取：
    # ownerName/ownerWchatId/ownerAlias/ownerImage/friendCount/createTime；
    # createTime 兼容 ms-int 与 'YYYY-MM-DD HH:mm:SS' 两种上游形态，归一为 ms）
    owner_name: Mapped[str | None] = mapped_column(String(255), nullable=True)  # 群主昵称(上游脱敏)
    owner_wxid: Mapped[str | None] = mapped_column(String(128), nullable=True)
    owner_alias: Mapped[str | None] = mapped_column(String(255), nullable=True)  # 群主微信号
    owner_avatar: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    friend_count: Mapped[int | None] = mapped_column(Integer, nullable=True)  # 群成员中员工好友数
    create_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)  # 建群时间 ms epoch

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index(
            "ix_chat_group_owner",
            "channel",
            "owner_account_id",
            "room_id",
        ),
        # /api/analytics/health MAX(updated_at) 新鲜度探针(c3d4e5f6a7b8)。
        Index("ix_chat_group_updated_at", "updated_at"),
    )


class GroupMember(Base):
    """群成员 — composite PK (channel, room_id, member_id).

    Source: the ``memberIds`` field of a chatroom payload, parsed into one row
    per member. Per-member nickname/avatar may require a separate API call
    (see data-dictionary §9.6) and are therefore nullable.
    """

    __tablename__ = "group_member"

    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
    room_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    member_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    nickname: Mapped[str | None] = mapped_column(String(255), nullable=True)
    avatar: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    display_name: Mapped[str | None] = mapped_column(String(255), nullable=True)

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()


class Message(Base):
    """聊天消息 — WeChat ``msgSvrId`` / WhatsApp ``keyId`` as natural PK.

    Sources:
      * WeChat: ``POST /wechatweb/msg/chats``
      * WhatsApp: ``POST /qqweb/WhatsAppUser/chatRecords``

    The model currently maps to a **single** ``message`` table. The real
    sharding across ``message_<channel>_<YYYYMM>`` physical tables (see
    :func:`message_table_name`) is a LATER task; this single-table mapping is
    sufficient for ingestion v1.
    """

    __tablename__ = "message"

    msg_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)
    owner_account_id: Mapped[str | None] = mapped_column(
        String(128), nullable=True
    )  # wechatId / uid of sender staff account
    talker_id: Mapped[str | None] = mapped_column(
        String(128), nullable=True
    )  # talker / friendUid — the other party
    ori_talker: Mapped[str | None] = mapped_column(String(128), nullable=True)
    room_id: Mapped[str | None] = mapped_column(
        String(128), nullable=True
    )  # @chatroom id; NULL/empty = direct message
    is_send: Mapped[bool | None] = mapped_column(Boolean, nullable=True)  # mine/isSend
    type: Mapped[str | None] = mapped_column(
        String(32), nullable=True
    )  # normalized enum label (text/image/voice/.../unknown); see design §4.3
    type_raw: Mapped[int | None] = mapped_column(
        Integer, nullable=True
    )  # original upstream type code (e.g. WeChat 1=text, -2=divider)
    # MEDIUMTEXT(16MB):MySQL TEXT 上限 64KB 字节,实测车源清单消息最长
    # 20.8万字符(≈800KB utf8mb4)超限(2026-08-21 迁移踩坑)
    text: Mapped[str | None] = mapped_column(
        Text().with_variant(MEDIUMTEXT(), "mysql"), nullable=True
    )  # content/text
    file_url: Mapped[str | None] = mapped_column(sa.Text, nullable=True)  # 分享链接可超1KB(实测,2026-08-21)
    file_th_url: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
    file_hd_url: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
    md5: Mapped[str | None] = mapped_column(String(64), nullable=True)
    md5_th: Mapped[str | None] = mapped_column(String(64), nullable=True)
    md5_hd: Mapped[str | None] = mapped_column(String(64), nullable=True)
    duration: Mapped[int | None] = mapped_column(Integer, nullable=True)
    transcription_text: Mapped[str | None] = mapped_column(Text, nullable=True)
    img_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    original_image: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    pic_type: Mapped[int | None] = mapped_column(Integer, nullable=True)
    pay_msg_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    refer_msg: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    sender_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    sender_head_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    timestamp: Mapped[int | None] = mapped_column(BigInteger, nullable=True)  # ms epoch
    is_del: Mapped[bool | None] = mapped_column(Boolean, nullable=True)

    # sha256 media_hash of the localized media blob (FK -> Media.media_hash);
    # NULL until sync_message_images downloads it. Populated by the
    # message_images sync pass; rendering prefers /api/media/{this} over the
    # OSS file_url / file_th_url / file_hd_url URLs. For image messages the
    # localized blob is typically the thumbnail (file_th_url) — small + fast
    # + sufficient for chat-timeline display.
    media_hash: Mapped[str | None] = mapped_column(String(64), nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        # Hot query path: per-account, per-talker, time-ordered pagination.
        Index(
            "ix_message_channel_owner_talker_time",
            "channel",
            "owner_account_id",
            "talker_id",
            "timestamp",
        ),
        # Group-chat hot path: per-account, per-room, time-ordered pagination.
        # Group messages filter on room_id (not talker_id, which is the *other
        # party* in a DM); without this index MySQL scans the talker index then
        # refilters on room_id, which on high-volume accounts degrades fast.
        Index(
            "ix_message_channel_owner_room_time",
            "channel",
            "owner_account_id",
            "room_id",
            "timestamp",
        ),
        # 今日收发聚合热路径:channel= + owner IN + timestamp>= 定位当天消息
        # (customer 列表行内 send_today/receive_today)。上面两个索引把
        # timestamp 排在 talker/room 之后,时间范围无法直接 seek;MySQL 预编译
        # 语句(asyncmy 走服务端 prepare)优化器弃索引转全表扫 86 万含大文本
        # 的行,实测 7.7s/次(2026-08-27),裸字面量也要 0.23s 扫 92 万索引项。
        # 此索引让 (channel, owner) 前缀下按 timestamp 直接落入当天几百行。
        Index(
            "ix_message_channel_owner_time",
            "channel",
            "owner_account_id",
            "timestamp",
        ),
        # C1 敏感词增量扫描水位:MAX(fetched_at) / fetched_at > 水位 定位新入库
        # 消息(按消息 timestamp 做水位会永久漏扫增量拉回的历史消息,spec §3.6)。
        # 「模型+迁移双声明」防 alembic autogenerate 反 DROP。
        Index(
            "ix_message_fetched_at",
            "fetched_at",
        ),
    )


class Media(Base):
    """Locally cached media (image / voice / video / file) — keyed by hash.

    Deduplicates downloads across messages that reference the same file (via
    ``md5``). ``local_path`` is set once the blob has been fetched into the
    local media store.
    """

    __tablename__ = "media"

    media_hash: Mapped[str] = mapped_column(String(64), primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)
    media_type: Mapped[str | None] = mapped_column(
        String(32), nullable=True
    )  # image|voice|video|file|...
    original_url: Mapped[str | None] = mapped_column(sa.Text, nullable=True)
    original_th_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    original_hd_url: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    local_path: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    size_bytes: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    mime_type: Mapped[str | None] = mapped_column(String(128), nullable=True)
    duration: Mapped[int | None] = mapped_column(Integer, nullable=True)

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index("ix_media_type_channel", "media_type", "channel"),
        # /api/analytics/health MAX(updated_at) 新鲜度探针——media 5 万宽行
        # (多个 TEXT/JSON 列)在 128MB buffer pool 下最伤(c3d4e5f6a7b8)。
        Index("ix_media_updated_at", "updated_at"),
    )


# ===========================================================================
# 4. Phone calls & SMS (prefix /pc/)
# ===========================================================================


class PhoneCall(Base):
    """电话/语音通话记录 — source: ``POST /pc/callLog/list`` (phone calls) and
    ``POST /wechatweb/callRecord/queryWeChatVoiceList`` (voice calls).

    ``channel`` here means **call-type** in {``phone_call``, ``voice_call``}
    (calls are not tied to a messaging channel). PK is the source ``id``.
    """

    __tablename__ = "phone_call"

    call_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)
    start_call_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    call_duration: Mapped[int | None] = mapped_column(Integer, nullable=True)
    ring_time: Mapped[int | None] = mapped_column(Integer, nullable=True)
    call_status: Mapped[int | None] = mapped_column(Integer, nullable=True)
    incoming_call: Mapped[int | None] = mapped_column(Integer, nullable=True)
    user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    user_id_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    department_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    call_number: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sim_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sim_number: Mapped[str | None] = mapped_column(String(64), nullable=True)
    imei: Mapped[str | None] = mapped_column(String(128), nullable=True)
    record_file: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    # sha256 media_hash of the localized recording blob (FK -> Media.media_hash);
    # NULL until sync_call_recordings downloads it. Populated by the
    # call_recordings sync pass; playback prefers /api/media/{this} over the
    # OSS record_file URL.
    record_media_hash: Mapped[str | None] = mapped_column(String(64), nullable=True)
    is_upload: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
    download_count: Mapped[int | None] = mapped_column(Integer, nullable=True)
    ai_asr: Mapped[str | None] = mapped_column(Text, nullable=True)
    qc_status: Mapped[int | None] = mapped_column(Integer, nullable=True)
    plan_customer_name: Mapped[str | None] = mapped_column(String(255), nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index("ix_phone_call_user_time", "user_id", "start_call_time"),
        # /api/analytics/health MAX(updated_at) 新鲜度探针(c3d4e5f6a7b8)。
        Index("ix_phone_call_updated_at", "updated_at"),
    )


class VoiceClip(Base):
    """长语音片段 — source: ``POST /wechatweb/call/list`` (WeChat + WhatsApp
    share the same endpoint, distinguished by the employee's channel).

    Distinct from :class:`PhoneCall` (which holds ``callLog/list`` phone calls
    and ``queryWeChatVoiceList`` voice-call records): a voice_clip is one of the
    long audio segments listed in the 云客 微信长语音 / WA wavoicecalllist modals.
    PK is the source ``id`` (a cross-employee-globally-unique bigint).

    ``channel`` here is the **messaging channel** in {``wechat``, ``whatsapp``}
    — stamped LOCALLY by the sync orchestrator based on which staff-account
    table owns the scraped ``user_id`` (WechatAccount -> ``wechat``,
    WhatsappAccount -> ``whatsapp``). The upstream endpoint is shared and does
    NOT distinguish the channel in its response, so the channel must come from
    the employee mapping, not the record.

    ``start_time`` / ``end_time`` arrive as ms-epoch **strings** (e.g.
    ``"1786072733378"``); the scraper normalizes them to ``int``.
    """

    __tablename__ = "voice_clip"

    voice_clip_id: Mapped[int] = mapped_column(
        BigInteger, primary_key=True, autoincrement=False
    )
    user_id: Mapped[str] = mapped_column(String(64), nullable=False)
    user_real_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    wx_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    talker: Mapped[str | None] = mapped_column(String(128), nullable=True)
    status: Mapped[str | None] = mapped_column(String(32), nullable=True)
    is_send: Mapped[bool | None] = mapped_column(Boolean, nullable=True)
    company_code: Mapped[str | None] = mapped_column(String(64), nullable=True)
    start_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    end_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    oss_file_name: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    mp3_duration: Mapped[int | None] = mapped_column(Integer, nullable=True)
    duration_format: Mapped[str | None] = mapped_column(String(32), nullable=True)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)

    # sha256 media_hash of the localized audio blob (FK -> Media.media_hash);
    # NULL until sync_voice_clip_audio downloads it. Populated by the
    # voice_clip_audio sync pass; playback prefers /api/media/{this} over the
    # OSS oss_file_name URL.
    media_hash: Mapped[str | None] = mapped_column(String(64), nullable=True)

    # LOCAL-only manual match: references customer.friend_id when an operator
    # has associated this clip with a specific customer (好友). NULL = unmatched.
    # The mirror never pushes this back to 云客 — it's our own bookkeeping for
    # the 手动匹配 UI (spec §7). Read paths resolve the customer name via join.
    matched_friend_id: Mapped[str | None] = mapped_column(String(128), nullable=True)

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (Index("ix_voice_clip_user_time", "user_id", "start_time"),)


class Sms(Base):
    """短信记录 — source: ``POST /pc/customer/smsLogsList``."""

    __tablename__ = "sms"

    sms_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    channel: Mapped[str] = mapped_column(
        String(16), nullable=False, default="sms"
    )  # always 'sms' today; kept for symmetry
    customer_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    content: Mapped[str | None] = mapped_column(Text, nullable=True)  # full sms text
    content_preview: Mapped[str | None] = mapped_column(String(255), nullable=True)
    sender: Mapped[str | None] = mapped_column(String(128), nullable=True)
    direction: Mapped[int | None] = mapped_column(Integer, nullable=True)
    user_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sender_department: Mapped[str | None] = mapped_column(String(255), nullable=True)
    sender_department_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    receive_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    create_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    sim_phone: Mapped[str | None] = mapped_column(String(64), nullable=True)
    sim_number: Mapped[str | None] = mapped_column(String(64), nullable=True)
    source: Mapped[str | None] = mapped_column(String(64), nullable=True)

    version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (Index("ix_sms_user_time", "user_id", "create_time"),)


class MomentsPost(Base):
    """员工朋友圈帖子 — source: ``POST /wechatweb/wechatFriendster/getFriendsterInfo``.

    PK = 云客 ``data.id``。``create_time`` 统一 **ms epoch**（云客返回秒，
    scraper ×1000）。WeChat-only 实体（无 ``channel`` 列），所属员工微信号
    由 ``wechat_id`` 标识。
    """

    __tablename__ = "moments_post"

    id: Mapped[str] = mapped_column(String(64), primary_key=True)
    wechat_id: Mapped[str] = mapped_column(String(128), index=True)
    sns_id: Mapped[str | None] = mapped_column(String(64), nullable=True)
    author_name: Mapped[str | None] = mapped_column(String(255), nullable=True)
    author_wxid: Mapped[str | None] = mapped_column(String(128), nullable=True)
    author_avatar: Mapped[str | None] = mapped_column(String(1024), nullable=True)
    content: Mapped[str | None] = mapped_column(Text, nullable=True)
    type_raw: Mapped[str | None] = mapped_column(String(16), nullable=True)
    create_time: Mapped[int | None] = mapped_column(BigInteger, index=True)
    praise_json: Mapped[list[dict[str, Any]] | None] = mapped_column(JSON, nullable=True)
    comment_json: Mapped[list[dict[str, Any]] | None] = mapped_column(JSON, nullable=True)
    image_urls: Mapped[list[str] | None] = mapped_column(JSON, nullable=True)
    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    # /api/analytics/health MAX(updated_at) 新鲜度探针(c3d4e5f6a7b8)。
    __table_args__ = (Index("ix_moments_post_updated_at", "updated_at"),)


# ===========================================================================
# 5. Operational / bookkeeping tables (local; no raw_json/version)
# ===========================================================================


class SyncState(Base):
    """Resumable sync cursor — scoped by (entity_type, channel, scope_id).

    ``scope_id`` qualifies the cursor for a sub-stream (e.g. the owning staff
    account id when syncing per-account message streams). ``last_version``
    holds the opaque source update stamp; ``last_timestamp`` the ms epoch.
    """

    __tablename__ = "sync_state"

    state_id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    entity_type: Mapped[str] = mapped_column(String(32), nullable=False)
    channel: Mapped[str | None] = mapped_column(String(16), nullable=True)
    scope_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    last_version: Mapped[str | None] = mapped_column(String(64), nullable=True)
    last_timestamp: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    last_synced_at: Mapped[dt.datetime | None] = mapped_column(
        DateTime, nullable=True
    )
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index(
            "ix_sync_state_scope",
            "entity_type",
            "channel",
            "scope_id",
            unique=True,
        ),
    )


class YkAccount(Base):
    """云客 CRM login account — credentials / session for the upstream API.

    The session cookie / password is stored encrypted with
    ``Settings.encryption_key`` (Fernet). ``user_id`` + ``company`` together
    identify a yunke session (the two ``userid`` / ``company`` request headers).
    """

    __tablename__ = "yk_account"

    account_id: Mapped[int] = mapped_column(
        Integer, primary_key=True, autoincrement=True
    )
    user_id: Mapped[str] = mapped_column(String(64), nullable=False)
    company: Mapped[str] = mapped_column(String(64), nullable=False)
    username: Mapped[str | None] = mapped_column(String(255), nullable=True)
    session_blob_enc: Mapped[str | None] = mapped_column(Text, nullable=True)
    last_login_at: Mapped[dt.datetime | None] = mapped_column(
        DateTime, nullable=True
    )
    is_active: Mapped[bool] = mapped_column(
        Boolean, nullable=False, default=True, server_default=sa.text("1")
    )

    raw_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True)
    fetched_at: Mapped[dt.datetime] = _fetched_at()
    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (
        Index("ix_yk_account_user_company", "user_id", "company", unique=True),
    )


class SyncRun(Base):
    """Audit log for one sync execution (start / end / status / counts)."""

    __tablename__ = "sync_run"

    run_id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    entity_type: Mapped[str] = mapped_column(String(32), nullable=False)
    channel: Mapped[str | None] = mapped_column(String(16), nullable=True)
    scope_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    status: Mapped[str] = mapped_column(String(16), nullable=False)  # running|success|failed
    started_at: Mapped[dt.datetime] = mapped_column(
        DateTime, server_default=sa.func.now(), nullable=False
    )
    finished_at: Mapped[dt.datetime | None] = mapped_column(DateTime, nullable=True)
    records_fetched: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    records_upserted: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    error: Mapped[str | None] = mapped_column(Text, nullable=True)

    updated_at: Mapped[dt.datetime] = _updated_at()

    __table_args__ = (Index("ix_sync_run_entity_status", "entity_type", "status"),)


class MsgDailyStats(Base):
    """日粒度会话统计:每个「渠道×账号×会话×自然日」一行(2026-09-03)。

    sessions(staff-chat 会话列表)与 staff-chat-stats(5 数字弹窗)的预聚
    合层——这两端点原先每次请求对 owner 全量 message 做 GROUP BY(重账号
    5.2 万条实测 3~7s,128MB buffer pool 下更被推过前端 15s 超时)。日行由
    写路径维护:``repos.upsert_messages`` 落库后自动重算本批触及的
    「会话×天」;夜间 ``recompute_all`` 全量重建自愈(裸 UPDATE/回填脚本
    等绕过钩子的写入由它兜底)。

    口径:
    - ``day`` 一律 Asia/Shanghai 自然日(Python 计算,不用 SQL 日期函数——
      from_unixtime 跟随 MySQL 会话时区,UTC 容器下与今日数口径割裂)。
    - ``send_cnt``/``recv_cnt`` 仅计 is_send 真/假;NULL 两边都不计(对齐
      旧聚合的 case 语义)。
    - ``last_ts``/``last_is_send`` 为该日最后一条消息的时间与方向。
    """

    __tablename__ = "msg_daily_stats"

    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
    owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    # friend = 1:1 私聊(peer=talker_id) / room = 群(peer=room_id)
    peer_kind: Mapped[str] = mapped_column(String(8), primary_key=True)
    peer_id: Mapped[str] = mapped_column(String(128), primary_key=True)
    # yyyymmdd,如 20260903(上海自然日)
    day: Mapped[int] = mapped_column(Integer, primary_key=True)
    send_cnt: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    recv_cnt: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    # 当日最后一条消息(ms);当天无有效方向计数的消息也存在(is_send=NULL)
    last_ts: Mapped[int | None] = mapped_column(sa.BigInteger, nullable=True)
    last_is_send: Mapped[bool | None] = mapped_column(Boolean, nullable=True)

    updated_at: Mapped[dt.datetime] = _updated_at()


class StatDailyStaff(Base):
    """员工×日 汇总(stat_daily_staff)— msg_daily_stats 按账号→员工映射的 rollup。

    数据分析板块 v1 地基(2026-09-04 spec §3.1):A1 员工指标直读;A2 绩效
    (二批)零基建直读。维护见 app/storage/staff_summary.py——4h 调度刷
    当日+滚动 3 天 + 夜间全量自愈,**不挂写钩子**(rollup-of-rollup 无需
    实时,滞后语义与「数据截至」角标一致)。映射不上的账号 user_id 存
    owner_account_id 原值(读侧标注未映射)。day 口径同 msg_daily_stats
    (Asia/Shanghai yyyymmdd,Python 侧计算)。
    """

    __tablename__ = "stat_daily_staff"

    day: Mapped[int] = mapped_column(Integer, primary_key=True)
    channel: Mapped[str] = mapped_column(String(16), primary_key=True)
    user_id: Mapped[str] = mapped_column(String(64), primary_key=True)
    msg_sent: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    msg_recv: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    # 当日活跃去重数(账号合并到员工后跨账号去重 peer)
    active_friends: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    active_rooms: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    updated_at: Mapped[dt.datetime] = _updated_at()


class SensitiveWord(Base):
    """敏感词库(C1)——词库内容是高敏数据,日志禁止输出词内容。"""

    __tablename__ = "sensitive_word"

    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    word: Mapped[str] = mapped_column(String(64), unique=True)
    category: Mapped[str | None] = mapped_column(String(32), nullable=True)
    enabled: Mapped[bool] = mapped_column(
        Boolean, nullable=False, default=True, server_default=sa.text("1")
    )
    # 短于此长度不入库(防单字误报;单字词走 LIKE 回退扫描)
    min_len: Mapped[int] = mapped_column(
        Integer, nullable=False, default=2, server_default=sa.text("2")
    )
    # JSON 数组:命中行文本含任一排除词则跳过(误报抑制)
    exclude_words: Mapped[list[Any] | dict[str, Any] | None] = mapped_column(
        JSON, nullable=True
    )
    # created_at 不用 _updated_at():无 onupdate,首次落库后不被静默重写
    # (T8 改词/T10 处置命中只该动 updated_at/disposition)
    created_at: Mapped[dt.datetime] = mapped_column(
        sa.DateTime, nullable=False, server_default=sa.func.now()
    )
    updated_at: Mapped[dt.datetime] = _updated_at()


class SensitiveHit(Base):
    """敏感词命中——冗余 channel/owner/talker/room 跳转字段(不回查 message)。

    UNIQUE(word_id, msg_id) 防重扫重复膨胀;disposition ∈
    pending/confirmed/false_positive/ignored。
    """

    __tablename__ = "sensitive_hit"

    id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True)
    word_id: Mapped[int] = mapped_column(
        sa.ForeignKey("sensitive_word.id", ondelete="CASCADE"), nullable=False
    )
    msg_id: Mapped[str] = mapped_column(String(128), nullable=False)
    channel: Mapped[str] = mapped_column(String(16), nullable=False)
    owner_account_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    talker_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    room_id: Mapped[str | None] = mapped_column(String(128), nullable=True)
    ts: Mapped[int | None] = mapped_column(BigInteger, nullable=True)
    # 命中词前后文片段(不含全文,控敏)
    snippet: Mapped[str | None] = mapped_column(String(255), nullable=True)
    disposition: Mapped[str] = mapped_column(
        String(16), nullable=False, default="pending", server_default="pending"
    )
    # created_at 不用 _updated_at():无 onupdate,首次落库后不被静默重写
    # (T8 改词/T10 处置命中只该动 updated_at/disposition)
    created_at: Mapped[dt.datetime] = mapped_column(
        sa.DateTime, nullable=False, server_default=sa.func.now()
    )

    __table_args__ = (
        sa.UniqueConstraint("word_id", "msg_id", name="uq_sensitive_hit_word_msg"),
        sa.Index("ix_sensitive_hit_disp_ts", "disposition", "ts"),
    )


class SensitiveScanState(Base):
    """敏感词扫描水位——entity v1 只有 'message_text'。

    水位存 message.fetched_at(入库时间,DateTime)而非消息 timestamp:
    增量补扫拉回的历史消息 timestamp 早于水位但 fetched_at 是新的,按
    timestamp 做水位会永久漏扫(spec §3.6 P2)。
    """

    __tablename__ = "sensitive_scan_state"

    entity: Mapped[str] = mapped_column(String(32), primary_key=True)
    last_fetched_at: Mapped[dt.datetime | None] = mapped_column(
        sa.DateTime, nullable=True
    )
    last_run_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True)
    scanned: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    hits: Mapped[int] = mapped_column(
        Integer, nullable=False, default=0, server_default=sa.text("0")
    )
    updated_at: Mapped[dt.datetime] = _updated_at()


__all__ = [
    "ChatGroup",
    "Customer",
    "Department",
    "GroupMember",
    "Media",
    "Message",
    "MomentsPost",
    "MsgDailyStats",
    "PhoneCall",
    "SensitiveHit",
    "SensitiveScanState",
    "SensitiveWord",
    "Sms",
    "Staff",
    "StatDailyStaff",
    "SyncRun",
    "SyncState",
    "VoiceClip",
    "WechatAccount",
    "WhatsappAccount",
    "YkAccount",
    "message_table_name",
]