PythagorasGoal/tests/test_harness_realism.py

"""Locks the two harness-realism gates codified from the 2026-06-21 intraday wave:
  * day_boundary_robust — a calendar/session/hour signal whose marginal uplift INVERTS when
    the UTC day boundary is shifted is a labeling ARTIFACT (this killed open_drive). A price
    signal that ignores the calendar is INVARIANT; a genuine calendar effect is ROBUST.
  * eval_weights_smallcap — at ~$600 a sub-min_order rebalance can't execute; the modeled
    proportional fee on thousands of sub-dollar moves is a fiction. The realistic evaluator
    skips them.
"""
import sys
from pathlib import Path

import numpy as np
import pandas as pd

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "scripts" / "research" / "alt"))
import altlib as al  # noqa: E402


# --- LESSON 1: day-boundary robustness -------------------------------------------------
def test_day_boundary_invariant_for_price_signal():
    """A signal that never reads the calendar is INVARIANT to the day-boundary shift."""
    def mom(df):
        c = df["close"].values
        return np.tanh(3 * (c / al.sma(c, 200) - 1))
    r = al.day_boundary_robust(mom, offsets=(0, 6, 12, 18))
    assert r["verdict"] == "INVARIANT"
    assert r["spread"] == 0.0
    assert r["calendar_sensitive"] is False


def test_day_boundary_flags_calendar_artifact():
    """A pure hour-of-day bias is calendar-sensitive: its uplift swings with the boundary
    (the open_drive failure mode). It must be flagged, never INVARIANT."""
    def hourbias(df):
        h = pd.to_datetime(df["datetime"], utc=True).dt.hour.values
        return np.where(h < 8, 1.0, 0.0)
    r = al.day_boundary_robust(hourbias, offsets=(0, 6, 12, 18))
    assert r["calendar_sensitive"] is True
    assert r["spread"] > 0.05
    assert r["verdict"] != "INVARIANT"


# --- LESSON 2: small-capital fill realism ----------------------------------------------
def test_smallcap_skips_subdollar_rebalances():
    """Thousands of sub-min_order wiggles (a vol-target overlay's fiction) do NOT execute."""
    df = al.get("BTC", "1h")
    rng = np.random.default_rng(0)
    micro = 0.5 + 0.001 * rng.standard_normal(len(df))     # tiny drift around 0.5
    r = al.eval_weights_smallcap(df, micro, capital=600.0, min_order=5.0)
    modeled_turn = al.eval_weights(df, micro)["turnover_per_year"]
    assert r["executed_turnover_per_year"] < modeled_turn * 0.2
    assert r["n_executed_trades"] < len(df) * 0.05


def test_smallcap_keeps_real_trades():
    """A low-turnover signal with genuine large moves executes them, ~no Sharpe haircut."""
    df = al.get("BTC", "1h")
    step = np.zeros(len(df)); step[: len(df) // 2] = 0.5; step[len(df) // 2:] = -0.5
    r = al.eval_weights_smallcap(df, step, capital=600.0, min_order=5.0)
    assert r["n_executed_trades"] >= 2
    assert abs(r["sharpe_haircut"]) < 0.2


# --- LESSON 3: look-ahead (online-consistency) guard -----------------------------------
def test_causality_passes_causal_signal():
    """A causal signal recomputed on a prefix matches the full run on its tail."""
    def mom(df):
        c = df["close"].values
        return np.tanh(3 * (c / al.sma(c, 200) - 1))
    r = al.causality_ok(mom, tf="1h")
    assert r["ok"] is True
    assert r["max_tail_diff"] == 0.0


def test_causality_flags_lookahead():
    """A signal that reads tomorrow's move (future peek) is disqualified."""
    def leaky(df):
        c = df["close"].values
        f = np.zeros(len(c)); f[:-1] = np.sign(c[1:] - c[:-1])   # uses close[i+1]
        return f
    r = al.causality_ok(leaky, tf="1h")
    assert r["ok"] is False


# --- LESSON 4: selection-on-holdout gate (codified 2026-06-29, filone B) ----------------
def _mom_factory():
    """Tiny continuous momentum factory parametrized by SMA lookback (for grid tests)."""
    def factory(tf, win):
        def fn(df):
            c = df["close"].values.astype(float)
            return al.vol_target(np.tanh(3 * (c / al.sma(c, win) - 1)), df, 0.20, 30, 2.0)
        return fn
    return factory


def test_deflated_sharpe_penalizes_multiple_testing():
    """The SAME Sharpe deflates toward 0 when it was the best of MANY wide-dispersion trials,
    but survives when it stood alone among a few tight ones (Bailey & Lopez de Prado)."""
    rng = np.random.default_rng(0)
    T = 1500
    idx = pd.date_range("2020-01-01", periods=T, freq="D", tz="UTC")
    sr_target = 1.0
    ret = pd.Series(0.01 * (sr_target / np.sqrt(365.25) + rng.standard_normal(T)), index=idx)
    sr_ann = al._sh(ret)
    many = list(np.linspace(-3.0, 2.5, 120))                 # 120 wide-spread trials
    few = [0.1, 0.0, -0.1, 0.05]                             # 4 tight trials
    dsr_many, sr0_many = al.deflated_sharpe(sr_ann, many, ret)
    dsr_few, sr0_few = al.deflated_sharpe(sr_ann, few, ret)
    assert sr0_many > sr0_few                                # more/wider search -> higher null max
    assert dsr_many < dsr_few                                # multiple-testing is penalized
    assert dsr_many < 0.5 and dsr_few > 0.8
    assert 0.0 <= dsr_many <= 1.0 and 0.0 <= dsr_few <= 1.0


def test_select_cell_insample_ranks_by_insample_only():
    """The cell chosen must be the IN-SAMPLE (<HOLDOUT) Sharpe leader — never the hold-out's —
    and every searched cell's FULL Sharpe is returned for deflation."""
    factory = _mom_factory()
    grid = [dict(win=50), dict(win=150)]
    sel = al.select_cell_insample(factory, grid, ("12h",))
    assert sel["chosen"] is not None
    assert len(sel["all_full_sharpe"]) == len(grid)          # one trial per (tf,cell)
    best_is = max(r["insample_sharpe"] for r in sel["rows"])
    assert sel["chosen"]["insample_sharpe"] == best_is       # picked by in-sample, not hold-out


def test_study_family_honest_contract():
    """earns_slot_honest is exactly (in-sample-picked cell earns_slot) AND (deflated-Sharpe PASS).
    Both sub-gates must be enforced; the combined flag is their conjunction."""
    factory = _mom_factory()
    grid = [dict(win=50), dict(win=150)]
    rep = al.study_family_honest("MOMTEST", factory, grid, ("12h",))
    for k in ("chosen", "earns_slot_marginal", "deflated_sharpe", "dsr_pass", "earns_slot_honest"):
        assert k in rep
    assert rep["n_cells"] == len(grid)
    assert isinstance(rep["earns_slot_honest"], bool)
    assert rep["earns_slot_honest"] == bool(rep["earns_slot_marginal"] and rep["dsr_pass"])