"""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__`` 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 ``@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, ``@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 CustomerAccountLink(Base): """账号↔客户 多对多关联(customer_account_link,2026-09-08)。 ``customer`` 表 PK=``friend_id`` 全局一客户一行,归属=最后抓取员工 (last-wins)——共享客户(同一人加多个员工)在其他员工名下「消失」: 实测 Lily 云客好友 36 vs 镜像页面 12,24 个全在别的员工名下。云客 的口径是**每个账号各算一个**(per-employee 列表连备注/收发计数都按 关系各存一份);本表每个「渠道×账号×客户」一行,由 :func:`app.storage.repos.upsert_customer` 随档案同事务维护,员工维度 的列表/计数(`/api/customers?owner_account_id=`)读这里。 快照列为员工客户页所需(昵称/备注/头像 per-relation);全字段档案 (raw_json/60 列)仍在 ``customer`` 表按 friend_id 关联。 """ __tablename__ = "customer_account_link" channel: Mapped[str] = mapped_column(String(16), primary_key=True) owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True) friend_id: Mapped[str] = mapped_column(String(128), primary_key=True) # per-relation 展示快照(云客好友记录按员工各一份;备注是员工自己的) friend_nickname: Mapped[str | None] = mapped_column(String(255), nullable=True) friend_remark: Mapped[str | None] = mapped_column(String(255), nullable=True) head_image_url: Mapped[str | None] = mapped_column(String(1024), nullable=True) real_name: Mapped[str | None] = mapped_column(String(64), nullable=True) phone: Mapped[str | None] = mapped_column(String(64), nullable=True) last_chat_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True) add_time: Mapped[int | None] = mapped_column(BigInteger, nullable=True) 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) # 云客 fromType 代码(数据来源列;int,前端 fromTypeLabel 映射) from_type: Mapped[int | None] = mapped_column(Integer, nullable=True) # 同 customer.delete_flag 口径(int 0/1) delete_flag: Mapped[int | None] = mapped_column(Integer, nullable=True) fetched_at: Mapped[dt.datetime] = _fetched_at() updated_at: Mapped[dt.datetime] = _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 # 群备注(微信群统计页「群备注」列;getChatroomList.remark / # friend_list/es 的 friendWxRemark,2026-09-09) group_remark: 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_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 ChatGroupMemberStats(Base): """群成员进出按天统计(chat_group_member_stats,2026-09-09)。 云客「微信群统计」的新增/退出成员数是 ``getChatroomList`` 按 ``startTime~endTime`` 任意窗实时算的;本地无成员进出事件流,改为每夜 抓一次「当日窗」的 addMembers/lossMembers 落一行,页面任意日窗=按天 求和。**上线日起积累**(历史日期无数据;chat_group.add_members/ loss_members 旧列保留作最近一次抓取窗的快照)。 """ __tablename__ = "chat_group_member_stats" channel: Mapped[str] = mapped_column(String(16), primary_key=True) owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True) room_id: Mapped[str] = mapped_column(String(128), primary_key=True) # yyyymmdd(上海自然日,同 msg_daily_stats 口径) day: Mapped[int] = mapped_column(Integer, primary_key=True) added: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) lost: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) fetched_at: Mapped[dt.datetime] = _fetched_at() updated_at: Mapped[dt.datetime] = _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__`` 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", ), # 群聊消息窗实际查询形如 ``channel=? AND room_id=? ORDER BY timestamp`` # (不带 owner——chat_group 按 room 去重后 owner 与消息归属错位,见 # ChatMain queryFor)。上面的索引被 owner 挡住前缀用不上,优化器退化到 # room 单列索引 + filter + filesort:2026-09-07 服务器实测 4 万条群 # count 4.7s / 首页 5.1s / 末页 10.7s,串行撞前端 15s 超时 # (ECONNABORTED)。此索引让群查询与单聊同享 seek+排序直达。 # 「模型+迁移双声明」防 alembic autogenerate 反 DROP。 Index( "ix_message_channel_room_time", "channel", "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。 - 首响/回复率三列(2026-09-07 批1)按「消息串」口径,见 :func:`app.storage.summary._thread_stats`:串=客户连续消息不被员工 消息打断的段(is_send=NULL 不参与串判定);日切近似——日末未闭合 串计 threads 不计 answered,跨夜的串在次日段重新起算。 """ __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) # 当日客户串数(串=客户连续消息不被员工消息打断的段;NULL 方向不参与) cust_threads: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) # 被员工回复的串数 ≡ 首响样本数 fr_cnt(fr_cnt=threads_answered 不单列) threads_answered: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) # 首响样本时长和(ms):展示用首响时长 = fr_sum_ms / threads_answered fr_sum_ms: Mapped[int] = mapped_column( sa.BigInteger, nullable=False, default=0, server_default=sa.text("0") ) 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") ) # 首响/回复率三列(2026-09-07 批1):msg_daily_stats 同义列按账号→员工 # 累加。回复率=Σanswered/Σthreads;首响时长=Σfr_sum_ms/Σanswered。 cust_threads: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) threads_answered: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) fr_sum_ms: Mapped[int] = mapped_column( sa.BigInteger, 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() # ========================================================================== # 经营管理后台(2026-09-08 v2 spec,批次A)——fact/宽表/通话小表 + 三张业务表 # ========================================================================== class FirstReplyFact(Base): """首响事实表(管理域)——一行 = 一个被回的 1:1 客户消息串(v2 §3.1)。 跨日精确串口径:按会话**全历史**计算,fr_ms = 员工首条回复 ts − 串末条 客户消息 ts,day = 串末条所在上海自然日。区别于 msg_daily_stats 首响 三列的日切近似(跨夜串整条丢失,v2 §1.1 #1)。只写 1:1(friend)会话 ——群串语义不成立。由回填 CLI / 4h 滚动 / 夜间全量重算,**不挂写钩子** (写钩子零改动)。用途:精确 P50/P90、2h/24h 回复率分子、下钻证据。 """ __tablename__ = "first_reply_fact" channel: Mapped[str] = mapped_column(String(16), primary_key=True) owner_account_id: Mapped[str] = mapped_column(String(128), primary_key=True) peer_id: Mapped[str] = mapped_column(String(128), primary_key=True) thread_end_ts: Mapped[int] = mapped_column(BigInteger, primary_key=True) reply_ts: Mapped[int] = mapped_column(BigInteger, primary_key=True) # 回复消息 msg_id:同毫秒 F,T,F,T 交换的 (thread_end_ts, reply_ts) 并列 # 去重(一条回复恰好闭合一个串);兼作下钻证据定位回复消息 reply_msg_id: Mapped[str] = mapped_column(String(64), primary_key=True) # 串末条所在上海自然日 yyyymmdd(冗余物化,窗口/趋势索引) day: Mapped[int] = mapped_column(Integer, nullable=False) fr_ms: Mapped[int] = mapped_column(BigInteger, nullable=False) __table_args__ = (Index("ix_fr_fact_day_channel", "day", "channel"),) class EmployeeMetricDaily(Base): """员工×日管理指标宽表(v2 §3.2)——1:1 口径,管理域专用。 列来源(v2 §1.1 #2/#5):消息计数/负载列自 msg_daily_stats (peer_kind='friend' 过滤 + account_map 归并);串类三列与首响日值由 first_reply_facts.compute_conversation 同源输出(串末条归属日)—— 回复率分子分母同口径。metric_version 只影响派生列(生命周期), 默认 'v1'。account_map 映射不上或不在 staff 的 owner(幽灵员工) 过滤不落表(v2 §1.3 #11)。通话在 employee_call_daily(无渠道维)。 """ __tablename__ = "employee_metric_daily" 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) metric_version: Mapped[str] = mapped_column( String(16), primary_key=True, default="v1", server_default="v1" ) # 消息计数列(1:1 口径) 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") ) # 负载列(active_rooms 为群负载,唯一计入宽表的群维度) 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") ) # 串类列(与 first_reply_fact 同源,按串末条归属日) cust_threads: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) threads_answered: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) fr_sum_ms: Mapped[int] = mapped_column( BigInteger, nullable=False, default=0, server_default=sa.text("0") ) # 首响日值(趋势图用;评分用周期值从 fact 表窗口函数精确计算) first_reply_p50_ms: Mapped[int | None] = mapped_column(BigInteger, nullable=True) first_reply_p90_ms: Mapped[int | None] = mapped_column(BigInteger, nullable=True) # 生命周期 4 列(距今天数口径,当日持有客户状态分布,当前归属) new_customer_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) cooling_customer_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) dormant_customer_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) reactivated_customer_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) # 预留完整性标记:宽表生成当前恒写 True(串类列与 fact 同一算法直算, # 不读 fact 表)——真实语义(如校验 fact 覆盖/同步完整)由批次B定义 data_complete: Mapped[bool] = mapped_column( Boolean, nullable=False, default=False, server_default=sa.text("0") ) computed_at: Mapped[dt.datetime] = mapped_column( sa.DateTime, nullable=False, server_default=sa.func.now() ) class EmployeeCallDaily(Base): """员工×日通话小表(v2 §1.2 #9)——通话无消息渠道维度,独立于宽表。 phone_call.channel 是通话类型(实测值 voice_call/wa_voice_call, 无蜂窝 phone_call 行)非消息渠道,塞进 (day,channel,user) 宽表会在 channel=all 聚合时双计。接通 = call_duration > 0;followup = 通话后 24h 内该员工任一账号对该客户 有消息(Task 0 已核实:1:1 通话可匹配率 100%,@chatroom 群通话除外)。 """ __tablename__ = "employee_call_daily" day: Mapped[int] = mapped_column(Integer, primary_key=True) user_id: Mapped[str] = mapped_column(String(64), primary_key=True) call_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) call_seconds: Mapped[int] = mapped_column( BigInteger, nullable=False, default=0, server_default=sa.text("0") ) answered_call_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) call_followup_count: Mapped[int] = mapped_column( Integer, nullable=False, default=0, server_default=sa.text("0") ) computed_at: Mapped[dt.datetime] = mapped_column( sa.DateTime, nullable=False, server_default=sa.func.now() ) class EmployeeScoreConfig(Base): """评分配置版本(v1 §10.4/v2 §3.3)——config_json 存维度/指标/权重/ 方向/阈值/样本门槛;激活前须过权重总和与阈值校验(批次B scoring 实现)。 MVP 无可视化编辑器,受控 CLI 种子维护。 JSON 列(config_json 等)修改须整列重赋值,原地修改不会提交。""" __tablename__ = "employee_score_config" id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) version: Mapped[str] = mapped_column(String(32), unique=True, nullable=False) name: Mapped[str] = mapped_column(String(128), nullable=False) # draft | active | retired status: Mapped[str] = mapped_column( String(16), nullable=False, default="draft", server_default="draft" ) effective_from: Mapped[int | None] = mapped_column(Integer, nullable=True) effective_to: Mapped[int | None] = mapped_column(Integer, nullable=True) config_json: Mapped[dict[str, Any]] = mapped_column(JSON, nullable=False) created_by: Mapped[str | None] = mapped_column(String(64), nullable=True) approved_by: Mapped[str | None] = mapped_column(String(64), nullable=True) created_at: Mapped[dt.datetime] = mapped_column( sa.DateTime, nullable=False, server_default=sa.func.now() ) activated_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True) class EmployeeScoreSnapshot(Base): """周/月考核快照(v1 §8/v2 §3.3)——不可变:冻结后业务层禁改评分字段; 重算走 supersedes_id 替代链。同批次×员工唯一。""" __tablename__ = "employee_score_snapshot" id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) snapshot_batch_id: Mapped[str] = mapped_column(String(64), nullable=False) # week | month | custom period_type: Mapped[str] = mapped_column(String(8), nullable=False) period_start: Mapped[int] = mapped_column(Integer, nullable=False) period_end: Mapped[int] = mapped_column(Integer, nullable=False) user_id: Mapped[str] = mapped_column(String(64), nullable=False) score_config_version: Mapped[str] = mapped_column(String(32), nullable=False) metric_version: Mapped[str] = mapped_column(String(16), nullable=False) total_score: Mapped[int | None] = mapped_column(Integer, nullable=True) grade: Mapped[str | None] = mapped_column(String(2), nullable=True) # scored | insufficient_sample | incomplete_data score_status: Mapped[str] = mapped_column( String(24), nullable=False, default="scored", server_default="scored" ) dimension_scores_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True) metric_details_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True) data_as_of: Mapped[int] = mapped_column(Integer, nullable=False) generated_at: Mapped[dt.datetime] = mapped_column( sa.DateTime, nullable=False, server_default=sa.func.now() ) frozen_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True) frozen_by: Mapped[str | None] = mapped_column(String(64), nullable=True) supersedes_id: Mapped[int | None] = mapped_column(Integer, nullable=True) __table_args__ = ( sa.UniqueConstraint("snapshot_batch_id", "user_id", name="uq_score_snapshot_batch_user"), Index("ix_score_snapshot_period", "period_type", "period_start"), ) class ManagementFollowup(Base): """管理辅导闭环(v1 §7.3/v2 §3.3)——来源指标→问题→管理动作→结果。""" __tablename__ = "management_followup" id: Mapped[int] = mapped_column(Integer, primary_key=True, autoincrement=True) employee_user_id: Mapped[str] = mapped_column(String(64), nullable=False) # metric | anomaly | review | manual source_type: Mapped[str] = mapped_column(String(16), nullable=False) source_code: Mapped[str | None] = mapped_column(String(64), nullable=True) source_period_start: Mapped[int | None] = mapped_column(Integer, nullable=True) source_period_end: Mapped[int | None] = mapped_column(Integer, nullable=True) source_value_json: Mapped[dict[str, Any] | None] = mapped_column(JSON, nullable=True) reason: Mapped[str | None] = mapped_column(sa.Text, nullable=True) action_type: Mapped[str | None] = mapped_column(String(32), nullable=True) owner_manager_id: Mapped[str | None] = mapped_column(String(64), nullable=True) # open | in_progress | resolved | cancelled status: Mapped[str] = mapped_column( String(16), nullable=False, default="open", server_default="open" ) due_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True) result: Mapped[str | None] = mapped_column(sa.Text, nullable=True) employee_feedback: Mapped[str | None] = mapped_column(sa.Text, nullable=True) created_by: Mapped[str | None] = mapped_column(String(64), nullable=True) created_at: Mapped[dt.datetime] = mapped_column( sa.DateTime, nullable=False, server_default=sa.func.now() ) updated_at: Mapped[dt.datetime] = _updated_at() closed_at: Mapped[dt.datetime | None] = mapped_column(sa.DateTime, nullable=True) __table_args__ = ( Index("ix_followup_emp_status_due", "employee_user_id", "status", "due_at"), Index("ix_followup_owner_status", "owner_manager_id", "status"), ) __all__ = [ "ChatGroup", "Customer", "Department", "EmployeeCallDaily", "EmployeeMetricDaily", "EmployeeScoreConfig", "EmployeeScoreSnapshot", "FirstReplyFact", "GroupMember", "ManagementFollowup", "Media", "Message", "MomentsPost", "MsgDailyStats", "PhoneCall", "SensitiveHit", "SensitiveScanState", "SensitiveWord", "Sms", "Staff", "StatDailyStaff", "SyncRun", "SyncState", "VoiceClip", "WechatAccount", "WhatsappAccount", "YkAccount", "message_table_name", ]