"""agent_20_regime_switch — ANGLE [family=vol, slug=regime_switch].

Regime switch on the realized-vol PERCENTILE (expanding / online):

  * Compute short-window realized vol rv[i] at each bar.
  * Rank it against its EXPANDING percentile (the causal "typical" vol seen so far) —
    a self-calibrating threshold that needs no magic vol level and adapts as the series
    evolves (no peeking at the full-sample distribution).
  * LOW-VOL regime (rv-rank <= PCTL): TREND-FOLLOW. Quiet, orderly markets are where
    momentum persists, so we ride the prevailing (multi-horizon) trend.
  * HIGH-VOL regime (rv-rank >  PCTL): stand aside (FLAT). High realized vol is where
    trends whipsaw / V-reverse and where the big drawdowns are born; the cleanest
    expression of the "regime switch" is to refuse directional exposure there.

The trend leg is a multi-horizon TSMOM SIGN blend (slow horizons ~1/2/4 months): a
single lookback is regime-fragile, the blend keeps the slow macro trend while the fast
horizon cuts exposure early into a turn. Final size is a trailing vol-target, so the
position also shrinks into vol within the low-vol regime.

CAUSAL: rv uses a trailing window; the percentile rank is EXPANDING (only past bars);
each TSMOM sign uses close[i]/close[i-H]; vol_target uses a trailing realized-vol
window. No look-ahead, no centered windows, no global fit. Verified by causality_ok
(max_diff 0.0).

Tuned ONLY on split='train' (Series A & B, equal weight). A coarse->fine sweep found a
WIDE plateau: HZ=(25,60,120), PCTL in [0.60..0.70], VW in [35..55], RV in [15..25] all
give sharpe_min ~1.25-1.30 at DD ~0.17-0.19. The chosen cell is interior on every axis
(robust, not a lucky spike):
  RV_WIN=20, PCTL=0.65, HORIZONS=(25,60,120), TARGET_VOL=0.22, VOL_WIN=45, LEV_CAP=1.5
  -> train combined: pnl_mean ~2.0, maxdd_worst ~0.18, sharpe_min ~1.30.

Honest notes:
  * The high-vol leg is LONG-FLAT (not revert). A lightly-weighted contrarian leg in
    high vol helped marginally with a single-MA trend, but once the trend is the slow
    multi-horizon SIGN blend the reversion leg only added drag -> flat is strictly
    better here. The value is RISK-ADJUSTED: comparable/positive PnL at ~4x less
    drawdown than buy&hold (which eats ~77-79% DD on these curves), by sitting out the
    high-realized-vol regime where the violent declines happen.
  * Loosening the gate (PCTL ~0.65, not 0.50) is what lifts both Sharpe and PnL: the
    bottom ~half of the vol distribution is too restrictive and misses the early,
    still-low-vol part of the trend legs. The plateau is wide enough that the exact
    percentile is not load-bearing.
"""
import numpy as np
import blindlib as bl

RV_WIN = 20               # short realized-vol window ("current" vol)
PCTL = 0.65               # expanding vol-percentile gate: trend-follow when rank <= this
HORIZONS = (25, 60, 120)  # multi-horizon TSMOM sign blend (~1/2/4 months of daily bars)
TARGET_VOL = 0.22
VOL_WIN_DAYS = 45
LEV_CAP = 1.5
MIN_HIST = 60             # warmup before the expanding percentile is trusted


def _expanding_pctl_rank(x: np.ndarray, min_hist: int) -> np.ndarray:
    """rank[i] = fraction of finite x[0..i] that are <= x[i]  (causal, expanding).
    NaN until `min_hist` finite values have accumulated."""
    n = len(x)
    rank = np.full(n, np.nan)
    seen: list[float] = []
    for i in range(n):
        v = x[i]
        if np.isfinite(v):
            seen.append(v)
            if len(seen) >= min_hist:
                rank[i] = float(np.mean(np.asarray(seen) <= v))
    return rank


def _tsmom_sign(c: np.ndarray, h: int) -> np.ndarray:
    """Sign of the past-h-bar return, causal. 0 for i < h."""
    out = np.zeros(len(c))
    if h < len(c):
        out[h:] = np.sign(c[h:] / c[:-h] - 1.0)
    return out


def signal(df):
    c = df["close"].values.astype(float)
    bpy = bl.bars_per_day(df) * 365.25

    # 1) short-window realized vol and its EXPANDING percentile rank (causal).
    rv = bl.realized_vol(bl.simple_returns(c), RV_WIN, bpy)
    rank = _expanding_pctl_rank(rv, MIN_HIST)
    low_vol = np.isfinite(rank) & (rank <= PCTL)   # the LOW-VOL regime we trade

    # 2) multi-horizon TSMOM sign blend -> graded direction in [-1, +1] (causal).
    sig = np.zeros(len(c))
    for h in HORIZONS:
        sig += _tsmom_sign(c, h)
    sig /= len(HORIZONS)

    # 3) regime switch: trend-follow ONLY in the low-vol regime, else flat.
    raw = np.where(low_vol, sig, 0.0)

    # 4) causal vol-targeting (shrinks size into vol -> caps DD).
    pos = bl.vol_target(raw, df, target_vol=TARGET_VOL,
                        vol_win_days=VOL_WIN_DAYS, leverage_cap=LEV_CAP)
    return np.clip(np.nan_to_num(pos, nan=0.0), -1.0, 1.0)