vyndr/tests/unit/calibrationGuards.test.js

'use strict';

/**
 * The two ways a calibration measurement lies.
 *
 * Both produced a confident, plausible, completely wrong number in the
 * settlement session, and neither was visible in the output. These lock them out.
 */

const g = require('../../src/services/model/calibrationGuards');
const cal = require('../../src/services/model/calibration');

/** A population carrying BOTH sides of each prop, as the snapshot table does. */
function bothSides(n) {
  const rows = [];
  for (let i = 0; i < n; i += 1) {
    const p = 0.55 + (i % 7) * 0.05;
    rows.push({ propKey: `prop${i}`, side: 'over', p });
    rows.push({ propKey: `prop${i}`, side: 'under', p: 1 - p });
  }
  return rows;
}

describe('GUARD 1 — the both-sides tell', () => {
  it('catches the 0.4998 signature: both sides present AND mean pinned at 0.5', () => {
    const rows = bothSides(200);
    const r = g.checkPickedSideDedup(rows);
    expect(r.violated).toBe(true);
    expect(r.both_sides_share).toBe(1);
    expect(Math.abs(r.mean_p - 0.5)).toBeLessThanOrEqual(g.BALANCED_TOLERANCE);
    expect(r.reason).toMatch(/balanced by construction/);
  });

  it('assert form REFUSES rather than returning a number', () => {
    expect(() => g.assertPickedSideDedup(bothSides(100))).toThrow(/CALIBRATION GUARD/);
  });

  it('passes once deduped to the model-picked side', () => {
    // The picked side is the one the model favoured, so the mean sits well
    // above 0.5 — which is what a real forecaster's book looks like.
    const picked = bothSides(200).filter((r) => r.p > 0.5);
    const r = g.checkPickedSideDedup(picked);
    expect(r.violated).toBe(false);
    expect(r.mean_p).toBeGreaterThan(0.5 + g.BALANCED_TOLERANCE);
  });

  it('does NOT fire on a genuinely balanced one-sided book', () => {
    // Either condition alone is unremarkable. A book of one-sided picks that
    // happens to average 0.5 is honest, and flagging it would be a false alarm.
    const rows = Array.from({ length: 300 }, (_, i) => ({
      propKey: `p${i}`, side: 'over', p: i % 2 ? 0.45 : 0.55,
    }));
    const r = g.checkPickedSideDedup(rows);
    expect(r.both_sides_props).toBe(0);
    expect(r.violated).toBe(false);
  });

  it('does NOT fire when both sides are present but the mean is skewed', () => {
    const rows = bothSides(50).concat(
      Array.from({ length: 400 }, (_, i) => ({ propKey: `x${i}`, side: 'over', p: 0.8 })));
    const r = g.checkPickedSideDedup(rows);
    expect(r.both_sides_props).toBeGreaterThan(0);
    expect(r.violated).toBe(false);          // already deduped elsewhere
  });
});

describe('GUARD 2 — a null must never score itself', () => {
  it('(null-1)**2 can no longer pass as a metric', () => {
    // This is the exact breach: JS scores null as 1 against a win and 0 against
    // a loss, so the "Brier" silently equals the win rate.
    const outcomes = [1, 1, 0, 1, 0];
    const naive = outcomes.reduce((s, y, i) => s + ((null - y) ** 2), 0) / outcomes.length;
    const winRate = outcomes.reduce((a, b) => a + b, 0) / outcomes.length;
    expect(naive).toBeCloseTo(winRate, 10);          // the trap, demonstrated

    expect(g.safeBrier([null, null, null, null, null], outcomes)).toBeNull();
  });

  it('refuses when ANY single prediction is null', () => {
    expect(g.safeBrier([0.6, 0.4, null], [1, 0, 1])).toBeNull();
  });

  it('can be made to hard-fail instead of refusing', () => {
    expect(() => g.safeBrier([0.6, null], [1, 0], { onNull: 'throw' }))
      .toThrow(/null prediction reached a Brier term/);
  });

  it('scores normally when every prediction is real', () => {
    expect(g.safeBrier([1, 0], [1, 0])).toBe(0);
    expect(g.safeBrier([0.5, 0.5], [1, 0])).toBeCloseTo(0.25, 10);
  });

  it('an unfittable map refuses instead of producing null predictions', () => {
    // fitIsotonic returns null below its minimum; this is what must happen next.
    const map = cal.fitIsotonic([{ p: 0.6, won: 1 }, { p: 0.4, won: 0 }]);
    expect(map).toBeNull();
    const out = g.applyOrRefuse(map, [{ p: 0.6 }], cal.applyIsotonic);
    expect(out.ok).toBe(false);
    expect(out.reason).toMatch(/no calibration map/);
    expect(out.rows).toEqual([]);
  });

  it('drops unmappable rows rather than passing nulls downstream', () => {
    const fit = [];
    for (let i = 0; i < 400; i += 1) fit.push({ p: 0.3 + (i % 60) / 100, won: i % 3 === 0 ? 1 : 0 });
    const map = cal.fitIsotonic(fit);
    expect(map).not.toBeNull();
    const out = g.applyOrRefuse(map, [{ p: 0.5 }, { p: null }], cal.applyIsotonic);
    expect(out.rows.length).toBe(1);
    expect(out.dropped).toBe(1);
  });
});