"""meta_ortho — the orchestrator's decisive read on the ortho fleet.

17/18 books "earn a slot". That cannot be 17 alphas. This asks the three questions that
decide whether ANY of it is deployable:

  1. ARE THEY ONE BET?  Mutual correlation of the books' daily returns. Relative-momentum
     variants will cluster ~1; we collapse them to de-correlated representatives.
  2. IS THE UPLIFT PERSISTENT OR JUST THE 2025-26 WINDOW?  altlib.marginal_vs_tp01 fixes
     the hold-out at 2025-01-01 — exactly the window where ETH bled vs BTC and TP01 was
     weak. We re-measure the blend uplift at SEVERAL cut dates (2022/2023/2024/2025). A
     real orthogonal premium adds at every cut; a regime artifact only adds at 2025.
  3. WHAT DOES A SINGLE COMBINED SLEEVE LOOK LIKE?  Equal-weight the representatives into
     one relative-value sleeve and score THAT vs TP01 (full + per-cut).

  uv run python scripts/research/ortho/meta_ortho.py
"""
from __future__ import annotations

import importlib.util
import sys
from pathlib import Path

import numpy as np
import pandas as pd

HERE = Path(__file__).resolve().parent
sys.path.insert(0, str(HERE))
sys.path.insert(0, "/opt/docker/PythagorasGoal/scripts/research/alt")
import ortholib as ol  # noqa: E402
import altlib as al    # noqa: E402

AGENTS = HERE / "agents"
CUTS = ["2022-01-01", "2023-01-01", "2024-01-01", "2025-01-01"]


def _book(path: Path):
    spec = importlib.util.spec_from_file_location(path.stem, path)
    mod = importlib.util.module_from_spec(spec)
    spec.loader.exec_module(mod)
    return mod.book


def _sh(s: pd.Series) -> float:
    r = np.asarray(s.dropna().values, float)
    return float(np.mean(r) / np.std(r) * np.sqrt(365.25)) if len(r) > 2 and np.std(r) > 0 else 0.0


def uplift_at(cand: pd.Series, B: pd.Series, cut: str, w: float = 0.25) -> float:
    J = pd.concat({"B": B, "C": cand}, axis=1, join="inner").dropna()
    J = J[J.index >= pd.Timestamp(cut, tz="UTC")]
    if len(J) < 30:
        return float("nan")
    return _sh((1 - w) * J["B"] + w * J["C"]) - _sh(J["B"])


def main():
    B = al.tp01_baseline_daily()
    dailies = {}
    for p in sorted(AGENTS.glob("agent_*.py")):
        try:
            ev = ol.eval_book(_book(p))
            d = ev["daily"]
            if d.std() > 0:
                dailies[p.stem.replace("agent_", "")] = d
        except Exception as e:
            print(f"  skip {p.stem}: {e}")

    names = list(dailies)
    M = pd.concat(dailies, axis=1, join="inner").dropna()
    C = M.corr()

    # greedy de-correlation: order by full-sample uplift, keep if corr<0.6 to all kept
    upf = {n: uplift_at(dailies[n], B, "2018-01-01") for n in names}
    order = sorted(names, key=lambda n: upf[n], reverse=True)
    reps = []
    for n in order:
        if all(abs(C.loc[n, r]) < 0.6 for r in reps):
            reps.append(n)

    print(f"\n  ORTHO META — {len(names)} books, mutual-corr clusters -> {len(reps)} de-correlated reps")
    print(f"  mean |corr| among all books = {C.abs().values[np.triu_indices(len(names),1)].mean():.2f}")
    print(f"\n  DE-CORRELATED REPRESENTATIVES (corr<0.6 to each other):")
    print(f"  {'book':<20}{'up_full':>8}  uplift at cut: " + "  ".join(c[:7] for c in CUTS))
    for n in reps:
        ups = [uplift_at(dailies[n], B, c) for c in CUTS]
        print(f"  {n:<20}{upf[n]:>8.3f}   " + "  ".join(f"{u:>+6.2f}" for u in ups))

    # combined sleeve = equal-weight of representatives
    combo = M[reps].mean(axis=1)
    print(f"\n  COMBINED relative-value sleeve (equal-weight of {len(reps)} reps):")
    print(f"  {'':<20}{'up_full':>8}  uplift at cut: " + "  ".join(c[:7] for c in CUTS))
    ups = [uplift_at(combo, B, c) for c in CUTS]
    print(f"  {'COMBO':<20}{uplift_at(combo,B,'2018-01-01'):>8.3f}   " + "  ".join(f"{u:>+6.2f}" for u in ups))
    print(f"  combo standalone: Sharpe {_sh(combo):.2f}  corr->TP01 {M[reps].mean(axis=1).corr(pd.concat({'b':B},axis=1).reindex(combo.index)['b']):.2f}")

    # also: ALL ADDS equal-weight (what 'just deploy everything' would be)
    allc = M.mean(axis=1)
    ups = [uplift_at(allc, B, c) for c in CUTS]
    print(f"\n  ALL-{len(names)} equal-weight sleeve:")
    print(f"  {'ALL':<20}{uplift_at(allc,B,'2018-01-01'):>8.3f}   " + "  ".join(f"{u:>+6.2f}" for u in ups))
    print("\n  READ: a column that is +ve at 2022/2023/2024 cuts (not only 2025) = persistent.")
    print("       all-positive-only-at-2025 = the ETH/BTC-bleed regime, not a standing premium.")


if __name__ == "__main__":
    main()