refactor: unify data preparations and research input snapshots
Deploy production / deploy (push) Successful in 53s

This commit is contained in:
yuxuanhui
2026-09-12 01:24:02 +08:00
parent 849f86fef7
commit 394438e753
82 changed files with 4146 additions and 2076 deletions
+69
View File
@@ -3,6 +3,7 @@
import argparse
import asyncio
import getpass
import math
from sqlalchemy import delete, update
@@ -59,6 +60,63 @@ async def token_command(args):
await engine.dispose()
async def catalog_sync_command(args):
"""Enqueue on the existing runner, then observe without owning the upstream session."""
import json
import time
from fastapi import HTTPException
from .business import Business
from .catalog.contracts import CatalogJobInput, Scope
from .catalog.service import Catalog
from .models import Job
engine, sessions = create_database(Settings().database_url)
try:
async with sessions.begin() as db:
if args.resume_job:
if args.region or args.universe or args.delay is not None:
raise ValueError("--resume-job 不能同时指定新范围")
job = await db.get(Job, args.resume_job)
if not job or job.kind != "catalog_full_sync":
raise ValueError("只能恢复已有全量目录任务")
result = await Business(db).retry_job(job.id)
job_id = result["id"]
else:
if not args.region or not args.universe or args.delay is None:
raise ValueError("需要 --region、--universe 和 --delay")
scope = Scope(instrument_type=args.instrument_type, region=args.region,
universe=args.universe, delay=args.delay)
job = await Catalog(db).create_job(CatalogJobInput(scope=scope), full=True)
job_id = job.id
deadline, previous = time.monotonic() + args.wait_timeout, None
while True:
async with sessions() as db:
job = await db.get(Job, job_id)
data = dict(job_id=job.id, status=job.status, processed=job.processed,
total=job.total, failed=job.failed, checkpoint=job.checkpoint, error=job.error)
current = json.dumps(data, ensure_ascii=False, sort_keys=True)
if current != previous:
print(current, flush=True)
previous = current
if job.status == "completed":
return 0
if job.status in ("failed", "completed_with_errors", "cancelled"):
return 2 if job.checkpoint.get("error_code") == "invalid_scope" else 1
if job.status in ("waiting_auth", "waiting_connection"):
return 3
if time.monotonic() >= deadline:
print(f"等待超时;后台任务 {job_id} 继续执行", flush=True)
return 4
await asyncio.sleep(min(5, max(0, deadline - time.monotonic())))
except HTTPException as exc:
print(str(exc.detail), flush=True)
return 3 if exc.status_code == 409 else 1
finally:
await engine.dispose()
if __name__ == "__main__":
parser = argparse.ArgumentParser()
commands = parser.add_subparsers(dest="command", required=True)
@@ -70,8 +128,19 @@ if __name__ == "__main__":
commands.add_parser("mcp-token-list")
revoke = commands.add_parser("mcp-token-revoke")
revoke.add_argument("token_id")
sync = commands.add_parser("catalog-sync", help="全量同步一个范围的数据集及全部字段")
sync.add_argument("--region")
sync.add_argument("--universe")
sync.add_argument("--delay", type=int, choices=range(0, 10))
sync.add_argument("--instrument-type", default="EQUITY")
sync.add_argument("--resume-job")
sync.add_argument("--wait-timeout", type=float, default=21600)
args = parser.parse_args()
if args.command == "catalog-sync" and (not math.isfinite(args.wait_timeout) or args.wait_timeout <= 0):
parser.error("--wait-timeout 必须大于 0")
try:
if args.command == "catalog-sync":
raise SystemExit(asyncio.run(catalog_sync_command(args)))
asyncio.run(reset_password() if args.command == "reset-password" else token_command(args))
except ValueError as exc:
parser.error(str(exc))