YES/NO arbitrage

• ✓When your view of the odds differs from the market's pricing
• ⚠Liquidity thins near resolution; binary outcomes can go to zero

Binary prediction-market simulation (YES/NO, settles YES after 180 steps) — not a promise of future returns.

"""YES/NO 套利（YES/NO arbitrage）—— 两腿总价 < 1 的无风险价差。

思路：二元市场的 YES 与 NO 结算时必有一腿兑付 1、另一腿 0，故一对（1 YES + 1 NO）到期恰好价值 1。
当此刻 YES + NO 的买入成本 < 1 时，同时买入两腿即锁定 (1 - 成本) 的无风险价差，持有至结算兑付。
纸面回测按中间价成交，故 edge = 1 - (yes_mid + no_mid)（真实场馆应按 best_ask 计，见下）。

适用性：instrument="event"、venues=["POLYMARKET"]。仅做多（买 token），不涉及做空。
降级：feed 不提供配对腿（complement_token 为 None）时保持空仓。
"""
from __future__ import annotations

from ..base import StrategyBase
from ..context import StrategyContext
from ..registry import register


@register("YES/NO 套利")
class PmYesNoArb(StrategyBase):
    description = "YES+NO 两腿总价低于 1 时同时买入锁定无风险价差，结算兑付。"
    params = {"size": 20.0, "min_edge": 0.01}
    venues = ["POLYMARKET"]
    symbols: list = []
    instrument = "event"

    def __init__(self, size: float = 20.0, min_edge: float = 0.01) -> None:
        self.size = float(size)
        self.min_edge = float(min_edge)

    async def on_tick(self, ctx: StrategyContext) -> None:
        yes = ctx.conn_symbol()
        no = ctx.complement_token(yes)
        if no is None:
            return  # 非二元市场：不建仓
        ym = await ctx.price(yes)
        nm = await ctx.price(no)
        edge = 1.0 - (ym + nm)  # 一对 YES+NO 的买入成本相对结算价值 1 的价差
        band = self.size * 0.1
        if edge >= self.min_edge:
            await ctx.target(yes, self.size, band=band)  # 两腿等量买入锁定
            await ctx.target(no, self.size, band=band)

The full SDK and all strategies are MIT-licensed open source — backtest, paper-trade, or fork them directly.