浅念
165 lines
6.0 KiB
Python
165 lines
6.0 KiB
Python
"""first_reply_fact 维护层(管理域,批次A)——跨日精确串算法。
|
||
|
||
区别于 app.storage.summary._thread_stats 的日切近似(v2 §1.1 #1):
|
||
按会话**全历史**计算,跨夜串(客户 23:00 → 员工次日 9:00 回)不再丢失。
|
||
**不挂写钩子**(v2 §3.1):由回填 CLI / 4h 滚动 / 夜间全量重算,写钩子
|
||
零改动。只处理 1:1(friend)会话——群串语义不成立。
|
||
|
||
compute_conversation 同时输出每日串聚合(threads/answered/fr_sum_ms,
|
||
按串末条归属日)——employee_metric_daily 的串类列与 fact 行**同源**
|
||
(回复率分子分母一致,v2 §1.1 #5)。
|
||
"""
|
||
from __future__ import annotations
|
||
|
||
import logging
|
||
from collections import namedtuple
|
||
|
||
import sqlalchemy as sa
|
||
from sqlalchemy.ext.asyncio import AsyncSession
|
||
|
||
from app.db.models import FirstReplyFact, Message, MsgDailyStats
|
||
from app.storage.summary import day_key
|
||
|
||
logger = logging.getLogger(__name__)
|
||
|
||
# 一个被回串的首响样本;day = 串末条客户消息所在上海自然日
|
||
FactSample = namedtuple("FactSample", "thread_end_ts reply_ts fr_ms day")
|
||
# 某会话某日的串聚合(分子分母同源)
|
||
DayAgg = namedtuple("DayAgg", "threads answered fr_sum_ms")
|
||
|
||
|
||
class _DayAcc:
|
||
__slots__ = ("answered", "fr_sum_ms", "threads")
|
||
|
||
def __init__(self) -> None:
|
||
self.threads = 0
|
||
self.answered = 0
|
||
self.fr_sum_ms = 0
|
||
|
||
|
||
def compute_conversation(rows: list) -> tuple[list[FactSample], dict[int, DayAgg]]:
|
||
"""跨日精确串算法。rows = [(ts, is_send)] 该会话全历史,**须按 ts 升序**。
|
||
|
||
- 串 = 客户连续消息(is_send=False)不被员工消息(is_send=True)打断的
|
||
段;is_send=None 跳过(不打断也不起串)——与 _thread_stats 判定一致。
|
||
- 每个被回串一个样本:fr_ms = 员工首条回复 ts − 串**末条**客户消息 ts,
|
||
归属 day = 串末条所在上海自然日(跨夜串不再丢失)。
|
||
- 会话末尾仍未闭合的串:计入当日 threads(回复率分母),不产生样本。
|
||
"""
|
||
facts: list[FactSample] = []
|
||
acc: dict[int, _DayAcc] = {}
|
||
in_thread = False
|
||
end_ts: int | None = None
|
||
for ts, is_send in rows:
|
||
if is_send is False:
|
||
in_thread = True
|
||
end_ts = int(ts)
|
||
elif is_send is True:
|
||
if in_thread and end_ts is not None:
|
||
fr = int(ts) - end_ts
|
||
d = day_key(end_ts)
|
||
facts.append(FactSample(end_ts, int(ts), fr, d))
|
||
a = acc.setdefault(d, _DayAcc())
|
||
a.threads += 1
|
||
a.answered += 1
|
||
a.fr_sum_ms += fr
|
||
in_thread = False
|
||
end_ts = None
|
||
# is_send=None:跳过
|
||
if in_thread and end_ts is not None: # 会话末尾未闭合串
|
||
a = acc.setdefault(day_key(end_ts), _DayAcc())
|
||
a.threads += 1
|
||
return facts, {d: DayAgg(a.threads, a.answered, a.fr_sum_ms)
|
||
for d, a in acc.items()}
|
||
|
||
|
||
async def load_conversation(
|
||
session: AsyncSession, channel: str, owner: str, peer: str
|
||
) -> list:
|
||
"""拉取该 1:1 会话全历史 (timestamp, is_send),Python 侧排序(串算法
|
||
需严格时序——与 summary.recompute_days 同惯例,避免依赖 SQL 排序)。
|
||
|
||
公有命名:employee_metrics 宽表生成复用同一加载口径(同源原则)。"""
|
||
rows = (
|
||
await session.execute(
|
||
sa.select(Message.timestamp, Message.is_send).where(
|
||
Message.channel == channel,
|
||
Message.owner_account_id == owner,
|
||
Message.talker_id == peer,
|
||
sa.or_(Message.room_id.is_(None), Message.room_id == ""),
|
||
Message.timestamp.is_not(None),
|
||
)
|
||
)
|
||
).all()
|
||
return sorted(rows, key=lambda r: r[0])
|
||
|
||
|
||
async def recompute_pairs(
|
||
session: AsyncSession, pairs: list[tuple[str, str, str]]
|
||
) -> int:
|
||
"""重算给定 friend 会话的 fact 行:按会话 delete+insert,幂等。
|
||
|
||
pairs = [(channel, owner_account_id, peer_id)]。返回会话数。
|
||
"""
|
||
for channel, owner, peer in sorted(pairs):
|
||
rows = await load_conversation(session, channel, owner, peer)
|
||
facts, _agg = compute_conversation(rows)
|
||
await session.execute(
|
||
sa.delete(FirstReplyFact).where(
|
||
FirstReplyFact.channel == channel,
|
||
FirstReplyFact.owner_account_id == owner,
|
||
FirstReplyFact.peer_id == peer,
|
||
)
|
||
)
|
||
for f in facts:
|
||
session.add(
|
||
FirstReplyFact(
|
||
channel=channel,
|
||
owner_account_id=owner,
|
||
peer_id=peer,
|
||
thread_end_ts=f.thread_end_ts,
|
||
reply_ts=f.reply_ts,
|
||
day=f.day,
|
||
fr_ms=f.fr_ms,
|
||
)
|
||
)
|
||
return len(pairs)
|
||
|
||
|
||
async def all_friend_pairs(session: AsyncSession) -> list[tuple[str, str, str]]:
|
||
"""全部 1:1 会话(friend 行 distinct)——全量回填用。"""
|
||
rows = (
|
||
await session.execute(
|
||
sa.select(
|
||
MsgDailyStats.channel,
|
||
MsgDailyStats.owner_account_id,
|
||
MsgDailyStats.peer_id,
|
||
).where(MsgDailyStats.peer_kind == "friend")
|
||
)
|
||
).all()
|
||
return sorted({(r[0], r[1], r[2]) for r in rows})
|
||
|
||
|
||
async def pairs_active_in_days(
|
||
session: AsyncSession, days
|
||
) -> list[tuple[str, str, str]]:
|
||
"""窗口内有消息的 friend 会话(4h 滚动重算用;批次F 接调度)。"""
|
||
rows = (
|
||
await session.execute(
|
||
sa.select(
|
||
MsgDailyStats.channel,
|
||
MsgDailyStats.owner_account_id,
|
||
MsgDailyStats.peer_id,
|
||
).where(
|
||
MsgDailyStats.peer_kind == "friend",
|
||
MsgDailyStats.day.in_(list(days)),
|
||
)
|
||
)
|
||
).all()
|
||
return sorted({(r[0], r[1], r[2]) for r in rows})
|
||
|
||
|
||
async def recompute_all(session: AsyncSession) -> int:
|
||
"""全量重建(回填/夜间自愈,幂等)。"""
|
||
return await recompute_pairs(session, await all_friend_pairs(session))
|