vyndr/src/utils/gradeRanking.js

'use strict';

/**
 * gradeRanking (2026-07-29, specs/top-graded-selector.md) — THE ONE definition of
 * how a board of graded props is ordered. Extracted so the hero, the server
 * selector, and the client board cannot drift apart.
 *
 * WHO USES THIS:
 *   - `services/heroPropService`   — imports `takeablePWin` (its "top READ" rule
 *     is p_win-FIRST, so it uses the primitive, not `rankGrades`).
 *   - `services/topGradedService`  — imports `rankGrades` (its "top GRADES" board
 *     is grade-FIRST). Those two leading picks may legitimately differ; they
 *     agree WITHIN the leading grade tier.
 *   - `web/src/lib/slateAdapter.selectTopGrades` — a MIRROR, because the browser
 *     cannot import `src/` (the Session-25 rule). `tests/unit/gradeBoardSort`
 *     cross-checks the two on identical fixtures — the `playerName.js` precedent.
 *     If you change the order here, change it there IN THE SAME COMMIT.
 *
 * WHY p_win AND NOT ev_pct/edge_pct: ev_pct is NULL on served grades and
 * `Number(null) === 0` made every prop tie at 0 (the hero bug); edge_pct is a
 * price-free (proj−line)/line artifact whose scale is a function of line size.
 * p_win is the only signal whose takeable-MLB-over CLV survived the skew audit.
 */

const { isTakeable } = require('../config/valueEngine');

const GRADE_RANK = Object.freeze({
  'A+': 0, A: 1, 'A-': 2, 'B+': 3, B: 4, 'B-': 5, 'C+': 6, C: 7, 'C-': 8, D: 9, F: 10,
});

/** Grade letter → sortable tier rank (lower = better). Unknown → 99. */
function gradeRankOf(g) {
  const k = String(g == null ? '' : g).trim().toUpperCase();
  return GRADE_RANK[k] !== undefined ? GRADE_RANK[k] : 99;
}

/** Strict numeric read — `Number(null) === 0` is the recurring fabrication bug. */
function strictNum(v) {
  if (v == null || v === '') return null;
  const n = Number(v);
  return Number.isFinite(n) ? n : null;
}

/**
 * The takeable-gated champion probability for one grade row, or null.
 *
 * The takeable filter is MANDATORY: raw p_win crowns −300 chalk, which is not
 * the product. Band = `config/valueEngine.isTakeable` (−160..+200), the same
 * definition the takeable-edge proof and the over-side skew audit used.
 * Price falls back to the LOCKED odds (`gradedAt.odds`) when `book_odds` is absent.
 */
function takeablePWin(g) {
  const p = strictNum(g && g.p_win);
  if (p == null) return null;
  const price = strictNum(g && g.book_odds) ?? strictNum(g && g.gradedAt && g.gradedAt.odds);
  if (price == null || !isTakeable(price)) return null;
  return p;
}

/** Descending comparator that always sorts a null signal LAST (never first). */
function descNullsLast(a, b) {
  if (a == null && b == null) return 0;
  if (a == null) return 1;
  if (b == null) return -1;
  return b - a;
}

/**
 * rankGrades — "top GRADES" order: grade tier → confidence → takeable-gated
 * p_win → stable input order.
 *
 * EDGE KEY REMOVED 2026-08-01. It used to be the 4th key. Measured on n=200
 * settled MLB rows, corr(edge, outcome) = -0.010 under the incumbent ruler and
 * -0.022 under the consensus ruler — it does not predict, so it must not break
 * ties either. Removing it is safe for EVERY sport: it takes a non-predictive
 * signal out, it does not put p_win in front (that is `rankByForecast`, gated
 * to sports whose own model has passed).
 *
 * Rows without a grade are dropped (a board of ungraded rows is not a board).
 * `limit` omitted → the whole ranked list (callers slice).
 */
function rankGrades(grades, limit) {
  const arr = (Array.isArray(grades) ? grades : []).filter((g) => g && g.grade);
  const scored = arr.map((g, idx) => ({
    g,
    idx,
    rank: gradeRankOf(g.grade),
    conf: strictNum(g.confidence) == null ? -1 : strictNum(g.confidence),
    pWin: takeablePWin(g),
  }));
  scored.sort((a, b) => a.rank - b.rank
    || b.conf - a.conf
    || descNullsLast(a.pWin, b.pWin)
    || a.idx - b.idx);
  const out = scored.map((s) => s.g);
  return limit == null ? out : out.slice(0, Math.max(0, limit));
}


/**
 * rankByForecast — THE CHALLENGER instrument (2026-08-01).
 *
 * WHY THIS EXISTS, measured on n=200 settled MLB rows:
 *
 *     corr(p_win,               outcome) = +0.26
 *     corr(p_win - fair_prob_v1, outcome) = -0.010
 *     corr(p_win - fair_prob_v2, outcome) = -0.022
 *
 * Subtracting the market price DESTROYS the signal, under BOTH rulers. So the
 * product must rank on the thing that predicts (p_win) and must not rank on
 * market-relative edge at all. `rankGrades` (the incumbent) keeps edge as its
 * 4th key; this one has no edge term anywhere.
 *
 * ORDER: takeable-gated p_win → grade tier → confidence → stable input order.
 *
 * p_win LEADS, grade follows. That inverts the incumbent, and deliberately: the
 * grade letter measured r ~ 0.005 against outcomes and is INVERTED (B 52.4% <
 * C 56.9%), while p_win measures +0.26. Leading with the letter would sort the
 * board by the weaker signal and use the stronger one only to break ties.
 *
 * The takeable gate is mandatory and unchanged: raw p_win crowns -300 chalk,
 * which is not the product.
 *
 * ON CALIBRATION: isotonic is a MONOTONE transform, so ranking on raw p_win and
 * ranking on isotonic-calibrated p_win produce the SAME ORDER. Calibration
 * matters when p_win is displayed or thresholded — it cannot change a ranking.
 * Nothing here needs the calibrated value.
 */
function rankByForecast(grades, limit) {
  const arr = (Array.isArray(grades) ? grades : []).filter((g) => g && g.grade);
  const scored = arr.map((g, idx) => ({
    g,
    idx,
    pWin: takeablePWin(g),
    rank: gradeRankOf(g.grade),
    conf: strictNum(g.confidence) == null ? -1 : strictNum(g.confidence),
  }));
  scored.sort((a, b) => descNullsLast(a.pWin, b.pWin)
    || a.rank - b.rank
    || b.conf - a.conf
    || a.idx - b.idx);
  const out = scored.map((s) => s.g);
  return limit == null ? out : out.slice(0, Math.max(0, limit));
}

/**
 * WHICH SPORTS MAY RANK ON THE FORECAST — the per-sport doctrine, as a GATE.
 *
 *   A sport ranks on p_win ONLY once its OWN model is built and shown to
 *   predict — calibration AND resolution holding on its own holdout. MLB is the
 *   only sport that has passed. Every other sport is held out as NOT-BUILT,
 *   never as FAILED.
 *
 * WNBA IS NOT "ANTI-PREDICTIVE" AND DOES NOT "ABSTAIN" (corrected 2026-08-01).
 * The -0.12 result that produced those words was NBA-template machinery run on
 * WNBA data. WNBA has never had its own archetypes, variables, conditions or
 * calibration — it is precisely the "sport stubbed in on another sport's
 * template" that CLAUDE.md forbids. So -0.12 is the EXPECTED FAILURE OF AN
 * UNBUILT MODEL, not a verdict on the sport. Reading it as a verdict would
 * quietly retire a sport we never actually attempted.
 *
 * WNBA's own model-build is QUEUED as its own sport, after MLB is finished.
 *
 * The live consequence is identical either way — an unbuilt sport must not rank
 * on a signal that has not been shown to hold for it — which is why this set is
 * UNCHANGED. Only its meaning is corrected. A comment would not have stopped a
 * future flip from going global; this does.
 */
const FORECAST_RANKED_SPORTS = Object.freeze(new Set(['mlb']));
const ranksOnForecast = (sport) => FORECAST_RANKED_SPORTS.has(String(sport || '').toLowerCase());

/** Stable identity for a grade row, for comparing two orderings. */
function gradeKey(g) {
  if (!g) return '';
  const player = g.player_name || g.player || '';
  const stat = g.stat_type || g.stat || '';
  return `${String(player).toLowerCase()}|${String(stat).toLowerCase()}|${g.line}|${g.direction || ''}`;
}

/**
 * rankingDelta — the CHALLENGER-FIRST measurement. How far does the board move
 * if the instrument changes from `rankGrades` (grade-then-edge) to
 * `rankByForecast` (p_win-first, no edge)? Pure; changes nothing.
 */
function rankingDelta(grades, topN = 10) {
  const incumbent = rankGrades(grades);
  const challenger = rankByForecast(grades);
  const posOf = (list) => {
    const m = new Map();
    list.forEach((g, i) => m.set(gradeKey(g), i));
    return m;
  };
  const a = posOf(incumbent);
  const b = posOf(challenger);

  let moved = 0;
  let sumAbs = 0;
  let maxMove = 0;
  const moves = [];
  for (const [key, i] of a.entries()) {
    const j = b.get(key);
    if (j == null) continue;
    const d = j - i;
    if (d !== 0) moved += 1;
    sumAbs += Math.abs(d);
    if (Math.abs(d) > Math.abs(maxMove)) maxMove = d;
    moves.push({ key, from: i + 1, to: j + 1, delta: d });
  }
  const n = a.size;
  const topA = new Set(incumbent.slice(0, topN).map(gradeKey));
  const topB = new Set(challenger.slice(0, topN).map(gradeKey));
  let overlap = 0;
  for (const k of topA) if (topB.has(k)) overlap += 1;

  return {
    n,
    moved,
    moved_pct: n ? Math.round((1000 * moved) / n) / 10 : null,
    mean_abs_move: n ? Math.round((10 * sumAbs) / n) / 10 : null,
    max_move: maxMove,
    top_n: topN,
    top_n_overlap: overlap,
    top_n_overlap_pct: topN ? Math.round((1000 * overlap) / topN) / 10 : null,
    // The headline for a board: does the #1 read change?
    incumbent_top: incumbent[0] ? gradeKey(incumbent[0]) : null,
    challenger_top: challenger[0] ? gradeKey(challenger[0]) : null,
    top_changed: incumbent[0] && challenger[0] ? gradeKey(incumbent[0]) !== gradeKey(challenger[0]) : null,
    biggest_movers: moves.sort((x, y) => Math.abs(y.delta) - Math.abs(x.delta)).slice(0, 10),
  };
}

module.exports = {
  GRADE_RANK, gradeRankOf, strictNum, takeablePWin, descNullsLast, rankGrades,
  rankByForecast, rankingDelta, gradeKey,
  FORECAST_RANKED_SPORTS, ranksOnForecast,
};