"""查 Bitget candle1m 每条推送里到底带几根 K 线、最新的在哪一端。

归因结果显示 ccxt.pro 比原始 WS 快约 1.4 秒，而两者订阅的是同一条频道。
Hummingbot 的解析取 data["data"][0]，我的探针也取 [0]，两者一致地慢——
若 Bitget 一条消息里带多根、最新在末尾，取 [0] 就会系统性落后一个滑动窗口。

对每条消息记录：元素个数、首末元素的时间戳、以及首末之差。
若普遍 len>1 且末元素更新，则 [0] 就是那 1.4 秒的来源，且可用一行覆盖修好。

    .venv/bin/python research/live/probe_ws_payload.py --minutes 4
"""
from __future__ import annotations

import argparse
import asyncio
import json
import time
from collections import Counter, defaultdict

WSS = "wss://ws.bitget.com/v2/ws/public"
SYMS = ("BTCUSDT", "ETHUSDT", "SOLUSDT")


async def run(minutes: int) -> None:
    import aiohttp

    payload = {"op": "subscribe",
               "args": [{"instType": "USDT-FUTURES", "channel": "candle1m",
                         "instId": s} for s in SYMS]}

    n_elems = Counter()
    action_elems = Counter()
    # 取 [0] 相对取 [-1] 的落后量：同一根 K 线，两种读法各自首次见到的时刻
    first_seen_head: dict = {}
    first_seen_tail: dict = {}
    n_msg = 0

    print(f"[载荷探针] {SYMS} · 跑 {minutes} 分钟", flush=True)
    deadline = time.time() + minutes * 60
    while time.time() < deadline:
        try:
            async with aiohttp.ClientSession() as sess, \
                    sess.ws_connect(WSS, heartbeat=20) as ws:
                await ws.send_str(json.dumps(payload))
                while time.time() < deadline:
                    msg = await ws.receive(timeout=30)
                    # 断开后 receive() 立刻返回 CLOSED，只 continue 会变成空转
                    if msg.type is not aiohttp.WSMsgType.TEXT:
                        print(f"  非文本消息 {msg.type}，重连", flush=True)
                        break
                    if msg.data == "pong":
                        continue
                    d = json.loads(msg.data)
                    if "data" not in d or "arg" not in d:
                        continue
                    arr = d["data"]
                    if not arr:
                        continue
                    n_msg += 1
                    sym = d["arg"]["instId"].replace("USDT", "")
                    act = d.get("action")
                    n_elems[len(arr)] += 1
                    action_elems[(act, len(arr))] += 1

                    now_ms = int(time.time() * 1000)
                    head_ts, tail_ts = int(arr[0][0]), int(arr[-1][0])
                    first_seen_head.setdefault((sym, head_ts), now_ms)
                    first_seen_tail.setdefault((sym, tail_ts), now_ms)

                    if n_msg <= 6 or len(arr) > 1:
                        print(f"  {sym} action={act} 元素数={len(arr)} "
                              f"首ts={head_ts} 末ts={tail_ts} "
                              f"跨度={(tail_ts - head_ts) // 1000}s", flush=True)
        except asyncio.CancelledError:
            raise
        except Exception as e:
            print(f"  连接异常 {type(e).__name__}: {e}，1s 后重连", flush=True)
        if time.time() < deadline:
            await asyncio.sleep(1)

    print(f"\n########## 每条消息的元素个数分布（共 {n_msg} 条）##########")
    for k in sorted(n_elems):
        print(f"  {k} 根: {n_elems[k]} 条")
    print("\n按 action 拆分：")
    for k in sorted(action_elems, key=lambda x: (str(x[0]), x[1])):
        print(f"  action={k[0]} 元素数={k[1]}: {action_elems[k]} 条")

    # 同一根 K 线，用 [-1] 读比用 [0] 读早多少
    lead = defaultdict(list)
    for (sym, ts), t_tail in first_seen_tail.items():
        t_head = first_seen_head.get((sym, ts))
        if t_head is not None:
            lead[sym].append(t_head - t_tail)
    print("\n########## 取 [-1] 比取 [0] 提前多少（ms）##########")
    for s in SYMS:
        v = sorted(lead[s.replace("USDT", "")])
        if not v:
            print(f"  {s}: 无配对")
            continue
        print(f"  {s}: n={len(v)} 中位 {v[len(v) // 2]}ms 最大 {v[-1]}ms")


def main() -> None:
    ap = argparse.ArgumentParser()
    ap.add_argument("--minutes", type=int, default=4)
    asyncio.run(run(ap.parse_args().minutes))


if __name__ == "__main__":
    main()