research: 影子交易器落在 Hummingbot 上,并修掉 Bitget 连接器的换根延迟

1m 腿的滑点余量只有几个 bp,所以要测的必须是生产路径的滑点——换个运行时
测出来的数就不作数。框架因此从「滑点已知后再定」提前到测量阶段就定为
Hummingbot(Spot/Perp 连接器均 v2.0,Bitget 是 Foundation Partner)。

新增 research/live/。前置测量:

- bench_compute.py 本机算力,1m 单币 0.318s、三币串行 1.38s
- venue_parity.py Binance 与 Bitget 同根信号重合仅 14.6~42.6%
- signal_sensitivity.py 0.25bp 扰动就换掉一半信号
- aggregate_robustness.py 但总体期望不降——脆的是信号身份,不是 alpha
- bitget_baseline.py 因此改用 Bitget 原生基线定预算:余量 BTC -0.13bp、
  ETH +4.02bp、SOL +2.92bp。BTC 本就为负,只作延迟测量的参照物

运行时选型:

- parity_env.py 容器与本机信号逐一相同(下标、中枢数、checksum 全等),
  容器内 0.26s/币反而更快。故 chanlun 直接挂载进容器,不必另起信号服务。
  装进现有 .venv 那条路走不通:Hummingbot 要 numba>=0.61.2 与
  aiohttp<3.14,与本机 Python 3.14 冲突
- latency_ccxt.py / latency_hummingbot.py / latency_compare.py 初测显示
  Hummingbot 比 ccxt.pro 慢约 1030ms,90 根逐根配对里 80~97% 更慢
- probe_ws_action.py 否掉「丢弃 snapshot」的猜测:换根首条就是 update
- probe_hb_vs_raw.py 与 latency_attribute.py 四路归因——容器网络 2~18ms、
  Hummingbot 处理 -10~-30ms,1350~1480ms 全落在解析方式上
- probe_ws_payload.py 定位根因:Bitget 换根会推一条带两根的消息
  [上一根, 新一根],而上游取 data["data"][0] 拿到的是上一根,新一根要等
  下一条单元素消息

修复:

- patched_candles.py 处理消息里的全部元素。不能简单改成 [-1]——那样上一根
  的收盘价会永远停在换根前约 1 秒的那次推送上,而信号对 0.25bp 都敏感
- verify_patch.py 60 根配对验证:拿回 1060~1090ms,与原始 WS 只差 5~14ms
  已贴理论下限,19 根已收盘 K 线 OHLCV 逐根未变。折算 ETH 省 0.54bp、
  SOL 省 0.42bp。此 bug 值得向上游反馈

影子交易器:

- shadow_hb.py 不下单,读连接器真实盘口按仓位吃单深度算成交价,与次根开盘价
  (回测 entry_delay=1 的口径)相减,分解成延迟漂移、盘口价差、深度冲击。
  盘口 10Hz 滚动缓冲 30 秒,把延迟变成自变量:每个信号记 0.5/1/2/5s 与实际
  算完时刻各一个滑点值,本机算得慢也不影响能读出的曲线
- shadow_signal.py 信号计算隔离到子进程。0.26s 是纯 CPU 且 chanlun 受 GIL
  限制,放进 asyncio 循环会把行情处理一起卡住
- shadow_report.py 首日延迟门槛与滑点曲线报表

不用 paper trade 测滑点:它的成交由 Hummingbot 自己的撮合模型模拟,
测出来是模型行为而非市场行为。

Co-authored-by: Cursor <cursoragent@cursor.com>
This commit is contained in:
Ubuntu
2026-08-27 23:51:57 +08:00
co-authored by Cursor
parent 66061f79a1
commit 7e339d2a54
44 changed files with 11946 additions and 0 deletions
+179
View File
@@ -0,0 +1,179 @@
"""验证补丁是否真把那 1.1 秒拿回来了。
容器内同一进程并行跑三条路径,共用时钟与网络:
stock 上游 BitgetPerpetualCandles(取 data[0]
patched PatchedBitgetPerpetualCandles(处理全部元素)
raw 原始 aiohttp WS,按 data[-1] 判断换根(理论最快)
预期:patched ≈ raw,且比 stock 早约 1.1 秒。
同时校验补丁没有破坏数据:两条 feed 的历史 K 线应逐根相等(补丁只影响
最新一根的到达时刻与收盘价更新时机,不该改动已收盘的历史)。
docker run --rm -v $PWD:/repo:ro -v $PWD/research/out:/out \
-w /home/hummingbot -e PYTHONPATH=/home/hummingbot:/repo/research/live \
--entrypoint /opt/conda/envs/hummingbot/bin/python \
hummingbot/hummingbot:latest /repo/research/live/verify_patch.py --minutes 20
"""
from __future__ import annotations
import argparse
import asyncio
import csv
import json
import time
from pathlib import Path
SYMS = ("BTC", "ETH", "SOL")
WSS = "wss://ws.bitget.com/v2/ws/public"
def out_dir() -> Path:
p = Path("/out")
return p if p.is_dir() else Path(__file__).resolve().parents[1] / "out"
async def raw_ws(rec: dict, stop: asyncio.Event) -> None:
import aiohttp
payload = {"op": "subscribe",
"args": [{"instType": "USDT-FUTURES", "channel": "candle1m",
"instId": f"{s}USDT"} for s in SYMS]}
while not stop.is_set():
try:
async with aiohttp.ClientSession() as sess, \
sess.ws_connect(WSS, heartbeat=20) as ws:
await ws.send_str(json.dumps(payload))
last: dict[str, int] = {}
while not stop.is_set():
msg = await ws.receive()
if msg.type is not aiohttp.WSMsgType.TEXT:
break
if msg.data == "pong":
continue
d = json.loads(msg.data)
if "data" not in d or "arg" not in d or not d["data"]:
continue
sym = d["arg"]["instId"].replace("USDT", "")
kts = int(d["data"][-1][0]) # 关键:取末元素
if last.get(sym) is not None and kts > last[sym]:
rec.setdefault((sym, kts), {})["raw"] = \
int(time.time() * 1000)
last[sym] = max(kts, last.get(sym, 0))
except asyncio.CancelledError:
raise
except Exception as e:
print(f" [raw] {type(e).__name__}: {e}", flush=True)
# 正常跳出与异常都要歇一下再重连,避免服务端持续拒绝时打成风暴
if not stop.is_set():
await asyncio.sleep(1)
async def poll_feeds(feeds: dict, key: str, rec: dict,
stop: asyncio.Event) -> None:
last = {s: (int(f._candles[-1][0]) if len(f._candles) else None)
for s, f in feeds.items()}
while not stop.is_set():
for s, f in feeds.items():
if not len(f._candles):
continue
newest = int(f._candles[-1][0])
if last[s] is not None and newest > last[s]:
kts = newest * 1000 if newest < 1e12 else newest
rec.setdefault((s, kts), {})[key] = int(time.time() * 1000)
last[s] = newest
await asyncio.sleep(0.01)
async def main_async(minutes: int) -> None:
from hummingbot.data_feed.candles_feed.bitget_perpetual_candles import (
BitgetPerpetualCandles,
)
from patched_candles import PatchedBitgetPerpetualCandles
stock, patched = {}, {}
for s in SYMS:
stock[s] = BitgetPerpetualCandles(f"{s}-USDT", "1m", 20)
patched[s] = PatchedBitgetPerpetualCandles(f"{s}-USDT", "1m", 20)
for d in (stock, patched):
for f in d.values():
f.start()
print(f"[补丁验证] {SYMS} · 跑 {minutes} 分钟", flush=True)
t0 = time.time()
while time.time() - t0 < 120:
if all(f.ready for d in (stock, patched) for f in d.values()):
break
await asyncio.sleep(0.5)
print(f" 回填完成 {time.time() - t0:.1f}s", flush=True)
rec: dict = {}
stop = asyncio.Event()
tasks = [asyncio.create_task(raw_ws(rec, stop)),
asyncio.create_task(poll_feeds(stock, "stock", rec, stop)),
asyncio.create_task(poll_feeds(patched, "patched", rec, stop))]
deadline = time.time() + minutes * 60
seen = set()
while time.time() < deadline:
await asyncio.sleep(2)
for k, v in rec.items():
if k in seen or not {"stock", "patched", "raw"} <= v.keys():
continue
seen.add(k)
print(f" {k[0]}: patched 比 stock 早 "
f"{v['stock'] - v['patched']}ms · 距 raw "
f"{v['patched'] - v['raw']}ms", flush=True)
stop.set()
for t in tasks:
t.cancel()
await asyncio.gather(*tasks, return_exceptions=True)
# 数据一致性:两条 feed 的已收盘历史必须逐根相同
print("\n########## 补丁是否改动了已收盘 K 线 ##########")
for s in SYMS:
a = [list(map(float, r)) for r in list(stock[s]._candles)[:-1]]
b = [list(map(float, r)) for r in list(patched[s]._candles)[:-1]]
n = min(len(a), len(b))
ta = {int(r[0]): r for r in a[-n:]}
tb = {int(r[0]): r for r in b[-n:]}
common = sorted(set(ta) & set(tb))
diff = [t for t in common if ta[t][1:6] != tb[t][1:6]]
print(f" {s}: 共有 {len(common)} 根,OHLCV 不同 {len(diff)}"
+ (f"(示例 ts={diff[:3]}" if diff else ""))
for d in (stock, patched):
for f in d.values():
f.stop()
full = [(s, k, v) for (s, k), v in rec.items()
if {"stock", "patched", "raw"} <= v.keys()]
f = out_dir() / "verify_patch.csv"
with f.open("w", newline="") as fh:
w = csv.writer(fh)
w.writerow(["sym", "kline_ts", "raw", "patched", "stock",
"gain_ms", "patched_minus_raw_ms"])
for s, k, v in sorted(full, key=lambda x: x[1]):
w.writerow([s, k, v["raw"], v["patched"], v["stock"],
v["stock"] - v["patched"], v["patched"] - v["raw"]])
print(f"\n########## 补丁收益(配对 {len(full)} 根)##########")
print(f"{'':<5}{'n':>5}{'早于stock中位':>14}{'距raw中位':>12}")
for s in SYMS:
g = [v for ss, _, v in full if ss == s]
if not g:
print(f" {s}: 无样本")
continue
gain = sorted(v["stock"] - v["patched"] for v in g)
dr = sorted(v["patched"] - v["raw"] for v in g)
print(f"{s:<5}{len(g):>5}{gain[len(gain) // 2]:>14}"
f"{dr[len(dr) // 2]:>12}")
print(f"\n产物写入 {f}")
def main() -> None:
ap = argparse.ArgumentParser()
ap.add_argument("--minutes", type=int, default=20)
asyncio.run(main_async(ap.parse_args().minutes))
if __name__ == "__main__":
main()