perf(api): 会话/5数字弹窗超时修复——日粒度汇总层 msg_daily_stats
根因(服务器实测):sessions 对 owner 全量 message GROUP BY,重账号 5.2万条 3~5s;staff-chat-stats 全时段窗 6.9s——128MB buffer pool 下被推过前端 15s 超时(ECONNABORTED)。EXPLAIN ANALYZE 证实最优 covering 索引也要 18.9s,瓶颈是磁盘不是查询形状。 修复(预聚合,云客同款思路): - msg_daily_stats 表:每「渠道×账号×会话×上海自然日」一行(收发计数/ 当日最后时间与方向);迁移 a7d3e9f1c2b4(幂等建表) - 写路径:repos.upsert_messages 落库自动重算本批触及的会话×天(所有 抓取路径汇到该函数,一处挂全;失败不阻塞写入) - 读路径:sessions/staff-chat-stats 表有行时读汇总(namedtuple 同形, 端点主体零改动),空表守卫回退旧聚合(部署回填前不空白) - 自愈:CLI daily-stats 全量重建(幂等);full_sync_all.sh 夜间追加第 11 步——顺带修掉尾部 sqlite3 直连 smoke.db 的硬编码(服务器 MySQL 上会炸) - 口径统一:day 一律 Asia/Shanghai Python 计算(旧 from_unixtime 跟随 DB 会话时区与今日数割裂);统计窗口对齐自然日(文档化语义变化) 测试:12 新增(汇总层 8 + 端点判别/对拍 4,判别手法=回填后删光 message 仍出完整数据),全量 512 绿。 Co-Authored-By: Claude Code <noreply@anthropic.com>
This commit is contained in:
浅念
@@ -1,10 +1,17 @@
|
||||
"""GET /api/sessions — 账号会话列表(好友+群,今日消息数+最近联系时间),全本地 message 聚合。
|
||||
"""GET /api/sessions — 账号会话列表(好友+群,今日消息数+最近联系时间)。
|
||||
|
||||
镜像 staff_chat_stats 聚合模式(GROUP BY + case 计数 + Python 侧合并昵称/头像)。
|
||||
today_start 钉死 Asia/Shanghai(UTC+8)当日 0 点,不依赖服务器时区。
|
||||
**双路径(2026-09-03 会话列表超时修复)**:
|
||||
- ``msg_daily_stats`` 有行 → 读日粒度汇总(每会话「今日行 + MAX(last_ts)」,
|
||||
毫秒级;旧实时全量聚合在重账号上实测 3~5s,128MB buffer pool 下更被推过
|
||||
前端 15s 超时)。
|
||||
- 空表(部署回填前守卫)→ 回退旧实时聚合,行为不变。
|
||||
|
||||
today_start 钉死 Asia/Shanghai(UTC+8)当日 0 点,不依赖服务器时区;汇总层
|
||||
``day_key`` 同口径。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
from collections import namedtuple
|
||||
from datetime import datetime
|
||||
from typing import Annotated
|
||||
from zoneinfo import ZoneInfo
|
||||
@@ -15,7 +22,8 @@ from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.api.deps import get_session
|
||||
from app.api.schemas import SessionListOut, SessionOut
|
||||
from app.db.models import ChatGroup, Customer, Message
|
||||
from app.db.models import ChatGroup, Customer, Message, MsgDailyStats
|
||||
from app.storage.summary import day_key, has_rows as _summary_has_rows
|
||||
|
||||
router = APIRouter(prefix="/api", tags=["sessions"])
|
||||
|
||||
@@ -63,6 +71,51 @@ async def _group_rows(session: AsyncSession, owner: str, channel: str, today_sta
|
||||
return (await session.execute(stmt)).all()
|
||||
|
||||
|
||||
# ── 汇总路径:msg_daily_stats 日行(namedtuple 与旧 Row 同形,端点主体零改动)── #
|
||||
|
||||
_FriendRow = namedtuple("_FriendRow", ["talker_id", "last_chat_time", "today_count"])
|
||||
_GroupRow = namedtuple("_GroupRow", ["room_id", "last_chat_time", "today_count"])
|
||||
|
||||
|
||||
async def _summary_rows(
|
||||
session: AsyncSession, owner: str, channel: str, kind: str, today: int
|
||||
) -> dict[str, tuple[int | None, int]]:
|
||||
"""peer → (last_chat_time, today_count),来自日行聚合。
|
||||
|
||||
last = MAX(last_ts)(日行内时间单调,跨日最大即全史最后一条);
|
||||
today = 当日行的 send+recv。
|
||||
"""
|
||||
base = (
|
||||
MsgDailyStats.channel == channel,
|
||||
MsgDailyStats.owner_account_id == owner,
|
||||
MsgDailyStats.peer_kind == kind,
|
||||
)
|
||||
last = {
|
||||
peer: last_ts
|
||||
for peer, last_ts in (
|
||||
await session.execute(
|
||||
sa.select(MsgDailyStats.peer_id, sa.func.max(MsgDailyStats.last_ts))
|
||||
.where(*base)
|
||||
.group_by(MsgDailyStats.peer_id)
|
||||
)
|
||||
).all()
|
||||
}
|
||||
today_counts = {
|
||||
peer: int(cnt or 0)
|
||||
for peer, cnt in (
|
||||
await session.execute(
|
||||
sa.select(
|
||||
MsgDailyStats.peer_id,
|
||||
sa.func.coalesce(sa.func.sum(MsgDailyStats.send_cnt + MsgDailyStats.recv_cnt), 0),
|
||||
)
|
||||
.where(*base, MsgDailyStats.day == today)
|
||||
.group_by(MsgDailyStats.peer_id)
|
||||
)
|
||||
).all()
|
||||
}
|
||||
return {peer: (last_ts, today_counts.get(peer, 0)) for peer, last_ts in last.items()}
|
||||
|
||||
|
||||
async def _meta(session: AsyncSession, owner: str, channel: str, friend_ids: list[str], room_ids: list[str]):
|
||||
"""查 customer/chat_group 表合并昵称/头像;好友行额外带 delete_flag(is_del 过滤用)。
|
||||
|
||||
@@ -105,8 +158,14 @@ async def list_sessions(
|
||||
``pinned``:filehelper 会话置顶标记(对齐云客置顶区),其余好友/群恒 False。
|
||||
"""
|
||||
today_start = _today_start_ms()
|
||||
f_rows = await _friend_rows(session, owner_account_id, channel, today_start)
|
||||
g_rows = await _group_rows(session, owner_account_id, channel, today_start)
|
||||
if await _summary_has_rows(session):
|
||||
f_map = await _summary_rows(session, owner_account_id, channel, "friend", day_key(today_start))
|
||||
g_map = await _summary_rows(session, owner_account_id, channel, "room", day_key(today_start))
|
||||
f_rows = [_FriendRow(talker_id=p, last_chat_time=t, today_count=c) for p, (t, c) in f_map.items()]
|
||||
g_rows = [_GroupRow(room_id=p, last_chat_time=t, today_count=c) for p, (t, c) in g_map.items()]
|
||||
else:
|
||||
f_rows = await _friend_rows(session, owner_account_id, channel, today_start)
|
||||
g_rows = await _group_rows(session, owner_account_id, channel, today_start)
|
||||
fnames, gnames = await _meta(
|
||||
session, owner_account_id, channel, [r.talker_id for r in f_rows], [r.room_id for r in g_rows]
|
||||
)
|
||||
|
||||
@@ -1,12 +1,17 @@
|
||||
"""GET /api/staff-chat-stats — 微信员工 5 数字 + 客户明细（本地 message 表实时聚合）。
|
||||
"""GET /api/staff-chat-stats — 微信员工 5 数字 + 客户明细。
|
||||
|
||||
**双路径(2026-09-03 全时段窗 6.9s 超时修复)**:``msg_daily_stats`` 有行时
|
||||
读日粒度汇总(窗口对齐到自然日,毫秒级);空表回退旧实时聚合,行为不变。
|
||||
窗口语义随之统一为「上海自然日」(旧 SQL 日期函数跟随 DB 会话时区,UTC
|
||||
容器下与今日数口径割裂——顺带修复)。
|
||||
|
||||
数据全本地：按 员工微信 wxid × ms-epoch 日期窗 聚合 1:1 私聊（room_id 过滤），
|
||||
不访问云客。5 汇总数从 customers 在 Python 侧派生（spec §5）。
|
||||
跨库日期提取（codebase 首例）镜像 app/storage/repos.py 的方言检测写法。
|
||||
"""
|
||||
from __future__ import annotations
|
||||
|
||||
import time
|
||||
from collections import namedtuple
|
||||
from typing import Annotated
|
||||
|
||||
import sqlalchemy as sa
|
||||
@@ -15,7 +20,8 @@ from sqlalchemy.ext.asyncio import AsyncSession
|
||||
|
||||
from app.api.deps import get_session
|
||||
from app.api.schemas import StaffChatCustomerOut, StaffChatStatsOut, StaffChatStatsSummary
|
||||
from app.db.models import Customer, Message
|
||||
from app.db.models import Customer, Message, MsgDailyStats
|
||||
from app.storage.summary import day_key, has_rows as _summary_has_rows
|
||||
|
||||
router = APIRouter(prefix="/api", tags=["staff-chat-stats"])
|
||||
|
||||
@@ -81,6 +87,62 @@ async def _aggregate(session: AsyncSession, owner: str, start: int, end: int) ->
|
||||
return agg_rows, last_map
|
||||
|
||||
|
||||
# ── 汇总路径:msg_daily_stats 日行(namedtuple 与旧 Row 同形)────────────── #
|
||||
|
||||
_AggRow = namedtuple(
|
||||
"_AggRow", ["talker_id", "send_count", "receive_count", "interaction_days", "last_time"]
|
||||
)
|
||||
|
||||
|
||||
async def _aggregate_summary(
|
||||
session: AsyncSession, owner: str, start: int, end: int
|
||||
) -> tuple[list, dict[str, bool | None]]:
|
||||
"""窗口 → [day_key(start), day_key(end)] 自然日区间,按日行 Python 聚合。
|
||||
|
||||
interaction_days = 窗内有消息的自然日数;last_time/last_is_send 取窗内
|
||||
最后一条(last_ts 最大的日行)。窗口对齐自然日是文档化的语义变化
|
||||
(前端日期选择器本就按天取值)。
|
||||
"""
|
||||
rows = (
|
||||
await session.execute(
|
||||
sa.select(
|
||||
MsgDailyStats.peer_id,
|
||||
MsgDailyStats.day,
|
||||
MsgDailyStats.send_cnt,
|
||||
MsgDailyStats.recv_cnt,
|
||||
MsgDailyStats.last_ts,
|
||||
MsgDailyStats.last_is_send,
|
||||
).where(
|
||||
MsgDailyStats.channel == "wechat",
|
||||
MsgDailyStats.owner_account_id == owner,
|
||||
MsgDailyStats.peer_kind == "friend",
|
||||
MsgDailyStats.day >= day_key(start),
|
||||
MsgDailyStats.day <= day_key(end),
|
||||
)
|
||||
)
|
||||
).all()
|
||||
|
||||
per: dict[str, dict] = {}
|
||||
for peer, _day, send, recv, last_ts, last_is in rows:
|
||||
acc = per.setdefault(
|
||||
peer, {"send": 0, "recv": 0, "days": 0, "last_ts": None, "last_is": None}
|
||||
)
|
||||
acc["send"] += int(send or 0)
|
||||
acc["recv"] += int(recv or 0)
|
||||
acc["days"] += 1
|
||||
if acc["last_ts"] is None or (last_ts is not None and last_ts >= acc["last_ts"]):
|
||||
acc["last_ts"] = last_ts
|
||||
acc["last_is"] = last_is
|
||||
|
||||
agg_rows = [
|
||||
_AggRow(talker_id=p, send_count=a["send"], receive_count=a["recv"],
|
||||
interaction_days=a["days"], last_time=a["last_ts"])
|
||||
for p, a in per.items()
|
||||
]
|
||||
last_map = {p: a["last_is"] for p, a in per.items()}
|
||||
return agg_rows, last_map
|
||||
|
||||
|
||||
async def _customer_names(session: AsyncSession, owner: str, talker_ids: list[str]) -> dict[str, tuple[str, str, str]]:
|
||||
if not talker_ids:
|
||||
return {}
|
||||
@@ -114,7 +176,10 @@ async def get_staff_chat_stats(
|
||||
if start is None:
|
||||
start = end - 3 * _MS_PER_DAY # 默认近 3 天
|
||||
|
||||
agg_rows, last_map = await _aggregate(session, owner_account_id, start, end)
|
||||
if await _summary_has_rows(session):
|
||||
agg_rows, last_map = await _aggregate_summary(session, owner_account_id, start, end)
|
||||
else:
|
||||
agg_rows, last_map = await _aggregate(session, owner_account_id, start, end)
|
||||
talker_ids = [r.talker_id for r in agg_rows]
|
||||
names = await _customer_names(session, owner_account_id, talker_ids)
|
||||
|
||||
|
||||
Reference in New Issue
Block a user