128 lines
4.9 KiB
Python
128 lines
4.9 KiB
Python
"""一次性迁移:把已有的 taskId 会商记录从个人草稿表搬进独立的 task 存储。
|
|
|
|
背景
|
|
====
|
|
早期 taskId 深链会商记录混存在按用户分权的 ``roundtable_drafts`` 表里(带一个
|
|
``task_id`` 列 + 放开归属校验)。现在 taskId 聊天记录有了独立、不分权的存储
|
|
``roundtable_task_drafts``(只按 ``task_id`` 区分,跨用户共享)。本脚本把历史数据搬过去:
|
|
|
|
1. ``roundtable_drafts`` 中 ``task_id`` 非空的每一行 → 在 ``roundtable_task_drafts``
|
|
建同 id 的记录(``created_by`` = 原 ``user_id``,审计用);
|
|
2. 这些草稿对应的 ``roundtable_jobs`` 行(``draft_id`` 匹配且 ``task_id`` 为空)补上
|
|
``task_id``,使其转为「task 作业」(按 task 共享);
|
|
3. 从 ``roundtable_drafts`` 删除已迁走的行,使个人历史不再混入 task 记录。
|
|
|
|
幂等:目标表已存在同 id 记录则跳过;可重复运行。alembic 自动升级在运行时是关闭的
|
|
(见 ``persistence/engine.py``),所以这步数据搬迁用本脚本手动执行。
|
|
|
|
用法(在 backend 目录)
|
|
======================
|
|
::
|
|
|
|
# 预览(不写盘)
|
|
PYTHONPATH=. uv run python scripts/migrate_roundtable_task_drafts.py --dry-run
|
|
|
|
# 执行
|
|
PYTHONPATH=. uv run python scripts/migrate_roundtable_task_drafts.py
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
import argparse
|
|
import asyncio
|
|
import logging
|
|
import sys
|
|
|
|
logging.basicConfig(level=logging.INFO, format="%(message)s")
|
|
logger = logging.getLogger("migrate_roundtable_task_drafts")
|
|
|
|
|
|
async def _run(dry_run: bool) -> int:
|
|
from sqlalchemy import select, update
|
|
|
|
from deerflow.config import get_app_config
|
|
from deerflow.persistence.engine import close_engine, get_session_factory, init_engine_from_config
|
|
from deerflow.persistence.roundtable_drafts.model import RoundtableDraftRow
|
|
from deerflow.persistence.roundtable_jobs.model import RoundtableJobRow
|
|
from deerflow.persistence.roundtable_task_drafts.model import RoundtableTaskDraftRow
|
|
|
|
config = get_app_config()
|
|
await init_engine_from_config(config.database)
|
|
sf = get_session_factory()
|
|
|
|
moved = 0
|
|
skipped = 0
|
|
jobs_tagged = 0
|
|
try:
|
|
async with sf() as session:
|
|
rows = (
|
|
await session.execute(
|
|
select(RoundtableDraftRow).where(RoundtableDraftRow.task_id.is_not(None))
|
|
)
|
|
).scalars().all()
|
|
logger.info("发现 %d 条带 task_id 的个人草稿待迁移。", len(rows))
|
|
|
|
for row in rows:
|
|
# 幂等:目标已存在同 id → 跳过(仍尝试给作业补 task_id + 删源行)。
|
|
exists = await session.get(RoundtableTaskDraftRow, row.id)
|
|
if exists is None:
|
|
if not dry_run:
|
|
session.add(
|
|
RoundtableTaskDraftRow(
|
|
id=row.id,
|
|
task_id=row.task_id,
|
|
created_by=row.user_id,
|
|
title=row.title or "",
|
|
furthest_step=row.furthest_step or 1,
|
|
step1=row.step1,
|
|
step2=row.step2,
|
|
step3=row.step3,
|
|
created_at=row.created_at,
|
|
updated_at=row.updated_at,
|
|
)
|
|
)
|
|
moved += 1
|
|
logger.info(" 迁移 draft %s (task_id=%s)", row.id, row.task_id)
|
|
else:
|
|
skipped += 1
|
|
logger.info(" 跳过 draft %s (目标已存在)", row.id)
|
|
|
|
# 关联后台作业补 task_id(未标记的才动)。
|
|
if not dry_run:
|
|
res = await session.execute(
|
|
update(RoundtableJobRow)
|
|
.where(RoundtableJobRow.draft_id == row.id)
|
|
.where(RoundtableJobRow.task_id.is_(None))
|
|
.values(task_id=row.task_id)
|
|
)
|
|
jobs_tagged += int(res.rowcount or 0)
|
|
|
|
# 删除源行(task 记录不再留在个人表)。
|
|
if not dry_run:
|
|
await session.delete(row)
|
|
|
|
if not dry_run:
|
|
await session.commit()
|
|
|
|
logger.info(
|
|
"完成%s:迁移 %d 条,跳过 %d 条,关联作业打标 %d 条。",
|
|
"(dry-run,未写盘)" if dry_run else "",
|
|
moved,
|
|
skipped,
|
|
jobs_tagged,
|
|
)
|
|
return 0
|
|
finally:
|
|
await close_engine()
|
|
|
|
|
|
def main() -> int:
|
|
parser = argparse.ArgumentParser(description="迁移 taskId 会商记录到独立 task 存储")
|
|
parser.add_argument("--dry-run", action="store_true", help="只预览,不写盘")
|
|
args = parser.parse_args()
|
|
return asyncio.run(_run(args.dry_run))
|
|
|
|
|
|
if __name__ == "__main__":
|
|
sys.exit(main())
|