Chan/research/live/latency_hummingbot.py

"""延迟基准 B：Hummingbot 侧的数据到手时刻。

在 Hummingbot 容器内运行，测的事件与 latency_ccxt.py 完全相同：
**我们在什么时候得知第 N 根 1m 已经收盘**。

为什么必须在 Hummingbot 里测而不是复用 ccxt 的数字：如果最终执行走
Hummingbot，那决定成交价的是它的 WS 处理与事件循环延迟。用别的运行时测出
的滑点，换到 Hummingbot 上就不成立了。

用 max_records=20 让历史回填快速完成——这里只关心增量推送的时刻，不需要
2000 根窗口。

输出 out/latency_hummingbot.csv，字段与 A 侧一致，事后按 kline_ts join。
"""
from __future__ import annotations

import argparse
import asyncio
import csv
import time
from pathlib import Path

SYMS = ("BTC", "ETH", "SOL")
CONNECTOR = "bitget_perpetual"
OUT = Path("/out/latency_hummingbot.csv")


async def main_async(minutes: int) -> None:
    from hummingbot.data_feed.candles_feed.candles_factory import CandlesFactory
    from hummingbot.data_feed.candles_feed.data_types import CandlesConfig

    feeds = {}
    for s in SYMS:
        cfg = CandlesConfig(connector=CONNECTOR, trading_pair=f"{s}-USDT",
                            interval="1m", max_records=20)
        feeds[s] = CandlesFactory.get_candle(cfg)

    print(f"[Hummingbot 延迟] {SYMS} · connector={CONNECTOR} · "
          f"计划跑 {minutes} 分钟", flush=True)
    for s, f in feeds.items():
        if hasattr(f, "start"):
            f.start()
        else:
            await f.start_network()
        print(f"  {s} 已启动订阅", flush=True)

    # 等历史回填完成，否则 deque 尾部时间戳还在跳变
    t0 = time.time()
    while time.time() - t0 < 120:
        if all(f.ready for f in feeds.values()):
            break
        await asyncio.sleep(0.5)
    ready = {s: f.ready for s, f in feeds.items()}
    print(f"  回填状态 {ready}（{time.time() - t0:.1f}s）", flush=True)

    OUT.parent.mkdir(parents=True, exist_ok=True)
    fh = OUT.open("w", newline="")
    writer = csv.DictWriter(fh, fieldnames=["kline_ts", "sym", "t_data_ms", "lag_ms"])
    writer.writeheader()

    last = {}
    for s, f in feeds.items():
        c = f._candles
        last[s] = int(c[-1][0]) if len(c) else None

    stats: dict = {}
    deadline = time.time() + minutes * 60
    while time.time() < deadline:
        for s, f in feeds.items():
            c = f._candles
            if not len(c):
                continue
            newest = int(c[-1][0])
            if last[s] is None:
                last[s] = newest
                continue
            if newest > last[s]:
                now_ms = int(time.time() * 1000)
                # Hummingbot 的时间戳是秒，统一成毫秒后再与本地钟相减
                closed_ms = newest * 1000 if newest < 1e12 else newest
                lag_ms = now_ms - closed_ms
                writer.writerow({"kline_ts": closed_ms, "sym": s,
                                 "t_data_ms": now_ms, "lag_ms": lag_ms})
                fh.flush()
                stats.setdefault(s, []).append(lag_ms)
                n = len(stats[s])
                if n % 5 == 1:
                    med = sorted(stats[s])[n // 2]
                    print(f"  {s}: 第 {n} 根，本次 lag {lag_ms}ms，中位 {med}ms",
                          flush=True)
                last[s] = newest
        await asyncio.sleep(0.01)

    for f in feeds.values():
        f.stop()
    fh.close()

    print("\n########## t_data − t_close（ms）##########")
    for s in SYMS:
        v = sorted(stats.get(s, []))
        if not v:
            print(f"  {s}: 无样本")
            continue
        print(f"  {s}: n={len(v)} 中位 {v[len(v) // 2]}ms "
              f"P90 {v[int(len(v) * .9)]}ms 最大 {v[-1]}ms")
    print(f"\n产物写入 {OUT}")


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--minutes", type=int, default=20)
    args = ap.parse_args()
    asyncio.run(main_async(args.minutes))


if __name__ == "__main__":
    main()