"""Locks the marginal-vs-TP01 scorer (altlib) — the harness fix from the 2026-06-20 sweep.

The point: absolute Sharpe is not enough to earn a portfolio slot. A candidate must
IMPROVE the TP01 baseline out-of-sample. These tests pin the invariants:
  * the TP01 baseline reproduces the canonical ~1.30 full Sharpe,
  * TP01-vs-itself is REDUNDANT (zero marginal),
  * a flat (do-nothing) sleeve never earns a slot.
"""
import sys
from pathlib import Path

import numpy as np

ROOT = Path(__file__).resolve().parents[1]
sys.path.insert(0, str(ROOT / "scripts" / "research" / "alt"))

import altlib as al  # noqa: E402
from src.strategies.trend_portfolio import CANONICAL, TrendPortfolio  # noqa: E402


def test_tp01_baseline_reproduces_canonical():
    r = al.tp01_baseline_daily().values
    sharpe = float(np.mean(r) / np.std(r) * np.sqrt(365.25))
    assert 1.1 < sharpe < 1.5, f"TP01 baseline Sharpe {sharpe:.2f} off canonical ~1.30"


def test_tp01_vs_itself_is_redundant():
    cand = al.candidate_daily(lambda df: TrendPortfolio(**CANONICAL).target_series(df))
    m = al.marginal_vs_tp01(cand)
    assert m["corr_full"] > 0.95
    assert abs(m["blends"]["w25"]["uplift_full"]) < 0.05
    assert m["marginal_verdict"] == "REDUNDANT"
    assert al.study_marginal("tp01-self", lambda df: TrendPortfolio(**CANONICAL).target_series(df))["earns_slot"] is False


def test_flat_sleeve_earns_no_slot():
    m = al.marginal_vs_tp01(al.candidate_daily(lambda df: np.zeros(len(df))))
    assert m["marginal_verdict"] != "ADDS"


def test_call_target_passes_asset_when_accepted():
    seen = {}

    def two_arg(df, asset):
        seen[asset] = True
        return np.zeros(len(df))

    al.candidate_daily(two_arg)
    assert seen == {"BTC": True, "ETH": True}


# --- hardening gates (2026-06-21 ortho wave) -------------------------------------------
# A low-corr asset adds ~+0.03 Sharpe by pure diversification MATH; a sleeve that only
# pays when TP01 is weak is a HEDGE; an edge living in one late window is NOT robust.
# These pin that the scorer rejects all three, but still PASSES a real high-Sharpe
# uncorrelated sleeve (the diversification of a genuine return stream IS value).
import pandas as pd  # noqa: E402


def _tp01_index():
    return al.tp01_baseline_daily().index


def test_noise_sleeve_is_not_adds():
    """Near-zero-Sharpe, zero-corr asset = diversification math, not signal -> not ADDS."""
    idx = _tp01_index()
    rng = np.random.default_rng(1)
    c = pd.Series(rng.normal(0.0001, 0.02, len(idx)), index=idx)
    m = al.marginal_vs_tp01(c)
    assert m["marginal_verdict"] != "ADDS"
    assert m["beats_noise_null"] is False


def test_high_sharpe_uncorrelated_is_not_rejected_as_noise():
    """A genuine Sharpe~1.3 uncorrelated sleeve (XS01-like) must NOT be called NOISE."""
    idx = _tp01_index()
    rng = np.random.default_rng(2)
    c = pd.Series(rng.normal(0.0011, 0.013, len(idx)), index=idx)
    m = al.marginal_vs_tp01(c)
    assert m["beats_noise_null"] is True
    assert m["marginal_verdict"] == "ADDS"


def test_hedge_only_when_tp01_weak_is_flagged():
    """A sleeve that pays only when TP01 trails down is a HEDGE, not alpha -> no slot."""
    B = al.tp01_baseline_daily()
    trail = B.rolling(60, min_periods=20).sum().shift(1)
    base = np.where(trail.values <= 0, 0.004, -0.001)
    rng = np.random.default_rng(4)
    c = pd.Series(base + rng.normal(0, 0.004, len(B)), index=B.index)
    m = al.marginal_vs_tp01(c)
    assert m["is_hedge"] is True
    assert m["marginal_verdict"] == "HEDGE"


def test_flat_in_sample_late_edge_earns_no_slot():
    """An edge FLAT in-sample that only appears in the recent window has NO standalone
    in-sample merit -> NOISE (not ADDS), no slot. This is the ortho 2025-window pattern."""
    B = al.tp01_baseline_daily()
    rng = np.random.default_rng(3)
    c = pd.Series(0.0, index=B.index)                 # exactly flat in-sample
    hold = B.index >= al.HOLDOUT
    c[hold] = 0.004 + rng.normal(0, 0.002, int(hold.sum()))   # edge only in the hold-out
    m = al.marginal_vs_tp01(c)
    assert m["has_insample_edge"] is False
    assert m["marginal_verdict"] == "NOISE"
    assert al.marginal_vs_tp01(c)["marginal_verdict"] != "ADDS"


def test_pre_holdout_underperformer_earns_no_slot():
    """A sleeve with no real in-sample standalone edge (it bleeds before the hold-out and
    only wins in the recent window) never earns a slot — the 2025-only ortho pattern."""
    B = al.tp01_baseline_daily()
    early = B.index < al.HOLDOUT
    rng = np.random.default_rng(5)
    c = pd.Series(0.0, index=B.index)
    c[early] = -0.0008 + rng.normal(0, 0.012, int(early.sum()))   # weak/negative in-sample
    c[~early] = 0.010 + rng.normal(0, 0.012, int((~early).sum()))  # strong only post-hold-out
    m = al.marginal_vs_tp01(c)
    assert m["cand_insample_sharpe"] < 0.5
    assert m["has_insample_edge"] is False
    assert m["marginal_verdict"] != "ADDS"