vyndr/tests/unit/chain.test.js

'use strict';

/**
 * The portable chain + the calibration gate that guards it.
 *
 * The failure these exist to prevent is specific: compounding probabilities that
 * are individually survivable and jointly catastrophic. A 4-leg ticket of "90%"
 * legs whose realized rate is 63% is a 4.4x overstatement, in the direction the
 * user pays for.
 */

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

const atom = (id, p, extra = {}) => ({ id, p, calibrated: true, gameId: `g${id}`, ...extra });

describe('CHAIN ACROSS — the calibration gate is structural', () => {
  it('REFUSES to compound an uncalibrated atom', () => {
    const out = chain.chainAcross([atom('a', 0.9), { ...atom('b', 0.9), calibrated: false }]);
    expect(out.ok).toBe(false);
    expect(out.reason).toBe('uncalibrated_atoms');
    expect(out.uncalibrated).toEqual(['b']);
  });

  it('the refusal is the feature — this is the 4.4x case, made unbuildable', () => {
    // Model 0.91^4 = 0.686; realized 0.63^4 = 0.157.
    const legs = ['a', 'b', 'c', 'd'].map((k) => ({ ...atom(k, 0.91), calibrated: false }));
    expect(chain.chainAcross(legs).ok).toBe(false);
    // And the same legs, once genuinely calibrated, DO compound.
    const ok = chain.chainAcross(legs.map((l) => ({ ...l, calibrated: true })));
    expect(ok.ok).toBe(true);
    expect(ok.compound_probability).toBeCloseTo(0.91 ** 4, 3);
  });

  it('independent cross-game legs multiply', () => {
    const out = chain.chainAcross([atom('a', 0.8), atom('b', 0.5)]);
    expect(out.independent_probability).toBeCloseTo(0.4, 6);
    expect(out.cross_game_legs).toBe(2);
  });

  it('correlated same-game legs are NOT treated as independent', () => {
    const legs = [atom('a', 0.7, { gameId: 'G1' }), atom('b', 0.7, { gameId: 'G1' })];
    const indep = chain.chainAcross(legs);
    const corr = chain.chainAcross(legs, { correlation: () => 0.6 });
    // Shared pitcher/park/weather makes them land together more often than
    // independence implies — and independence is the FLATTERING error here.
    expect(corr.compound_probability).toBeGreaterThan(indep.compound_probability);
    expect(corr.cross_game_legs).toBe(1);
  });

  it('an unreadable atom is dropped, never counted as probability zero', () => {
    const out = chain.chainAcross([atom('a', 0.8), { id: 'b', p: null, calibrated: true }]);
    expect(out.ok).toBe(true);
    expect(out.legs).toBe(1);           // a p=0 leg would have zeroed the ticket
    expect(out.compound_probability).toBeCloseTo(0.8, 6);
  });

  it('no usable atoms is an explicit refusal, not a zero', () => {
    expect(chain.chainAcross([]).ok).toBe(false);
    expect(chain.chainAcross([{ id: 'x', p: null }]).reason).toBe('no_usable_atoms');
  });
});

describe('CHAIN UP — same atoms, team reading', () => {
  it('sums atoms into an expected value', () => {
    const out = chain.chainUp([atom('a', 0.3), atom('b', 0.4), atom('c', 0.5)]);
    expect(out.expected_value).toBeCloseTo(1.2, 6);
    expect(out.contributors).toBe(3);
  });

  it('respects weights, and an absent weight contributes ONCE not zero', () => {
    const out = chain.chainUp([atom('a', 0.5, { weight: 4 }), atom('b', 0.5)]);
    expect(out.expected_value).toBeCloseTo(2.5, 6);
  });

  it('the archetype-redistribution HOOK is dormant unless supplied', () => {
    const legs = [atom('star', 0.6), atom('bench', 0.1)];
    expect(chain.chainUp(legs).redistributed).toBe(false);
  });

  it('and LIVE when a sport supplies it — a blowout fades the star, feeds the bench', () => {
    // Dormant in baseball (a nine-run lead does not change who bats next);
    // this is the basketball case the hook exists for.
    const legs = [atom('star', 0.6), atom('bench', 0.1)];
    const out = chain.chainUp(legs, {
      context: { blowout: true },
      redistribute: (as, ctx) => (ctx.blowout
        ? as.map((a) => (a.id === 'star' ? { ...a, p: a.p * 0.6 } : { ...a, p: a.p * 2 }))
        : as),
    });
    expect(out.redistributed).toBe(true);
    expect(out.expected_value).toBeCloseTo(0.6 * 0.6 + 0.1 * 2, 6);
  });
});

describe('SELF-CHECK — the model flagging its own suspect calls', () => {
  it('flags an internal inconsistency as LOW CONFIDENCE, without guessing which side is wrong', () => {
    const out = chain.selfCheck({
      perEntity: [{ p: 0.5 }, { p: 0.5 }, { p: 0.5 }],   // sums to 1.5
      teamRead: 4.0,
    });
    expect(out.confidence).toBe('LOW');
    expect(out.flags.map((f) => f.flag)).toContain('INTERNAL_INCONSISTENCY');
    expect(out.flags[0].consequence).toMatch(/do not know which/);
  });

  it('agreement is NORMAL confidence', () => {
    const out = chain.selfCheck({ perEntity: [{ p: 1.0 }, { p: 1.1 }], teamRead: 2.05 });
    expect(out.confidence).toBe('NORMAL');
    expect(out.flags).toEqual([]);
  });

  it('market divergence FLAGS the script but never claims we are right', () => {
    const out = chain.selfCheck({ perEntity: [{ p: 5.5 }], teamRead: 5.5, marketRead: 3.5 });
    const f = out.flags.find((x) => x.flag === 'SCRIPT_DIVERGES_FROM_MARKET');
    expect(f).toBeTruthy();
    expect(f.consequence).toMatch(/either the best or the worst/);
    // Divergence is not an error signal, so it does not downgrade confidence.
    expect(out.confidence).toBe('NORMAL');
  });
});

describe('PROPAGATION — one settled result improves every reading that shares the atom', () => {
  it('moves a thin atom a lot and a heavy atom barely at all', () => {
    const thin = chain.propagate({ id: 'a', p: 0.5, n: 4 }, { won: 1 });
    const heavy = chain.propagate({ id: 'a', p: 0.5, n: 400 }, { won: 1 });
    expect(thin.p - 0.5).toBeGreaterThan((heavy.p - 0.5) * 10);
    // That gap is the difference between learning and chasing noise.
    expect(heavy.n).toBe(401);
  });

  it('an unreadable observation changes nothing', () => {
    const before = { id: 'a', p: 0.5, n: 10 };
    expect(chain.propagate(before, { won: null })).toEqual(before);
    expect(chain.propagate(before, null)).toEqual(before);
  });
});

describe('CALIBRATION SERVICE — fit past, apply forward, certify by band', () => {
  const svc = require('../../src/services/model/calibrationService');

  /** Rows dated so the time-split is meaningful. */
  const hist = (specs) => {
    const out = [];
    let day = 1;
    for (const [p, n, rate] of specs) {
      for (let i = 0; i < n; i += 1) {
        // Wins are INTERLEAVED, not front-loaded. Front-loading makes the
        // outcome correlate with the date, so a time-split would train on the
        // wins and certify on the losses — the generator would be creating the
        // very leakage the split exists to prevent.
        const won = Math.floor((i + 1) * rate) > Math.floor(i * rate) ? 1 : 0;
        out.push({ p, won, date: `2026-07-${String(day).padStart(2, '0')}` });
        if (out.length % 40 === 0) day = Math.min(28, day + 1);
      }
    }
    return out;
  };

  it('refuses to build on thin history rather than passing raw numbers through', () => {
    // "No calibrator" must mean nothing is stackable, never "trust the model".
    expect(svc.build(hist([[0.6, 50, 0.5]]))).toBeNull();
    expect(svc.build([])).toBeNull();
  });

  it('corrects an over-confident model and marks the corrected value calibrated', () => {
    // Claims 0.9, realises 0.6 — the shape measured on real hits.
    const c = svc.build(hist([[0.5, 300, 0.5], [0.9, 300, 0.6]]), { minBin: 30 });
    expect(c).not.toBeNull();
    const out = c.calibrate(0.9);
    expect(out.p_calibrated).toBeLessThan(0.75);   // the 0.9 claim is corrected down
    expect(out.p_raw).toBe(0.9);
  });

  it('a probability OUTSIDE a certified band is not stackable', () => {
    const c = svc.build(hist([[0.5, 300, 0.5], [0.9, 300, 0.6]]), { minBin: 30 });
    const far = c.calibrate(0.02);
    // Whatever it maps to, if the band was never certified it cannot compound.
    if (!far.calibrated) expect(far.reason).toBe('outside_certified_band');
  });

  it('an absent probability is absent, never 0', () => {
    const c = svc.build(hist([[0.5, 300, 0.5], [0.9, 300, 0.6]]), { minBin: 30 });
    const out = c.calibrate(null);
    expect(out.p_calibrated).toBeNull();
    expect(out.calibrated).toBe(false);
  });

  it('splits by TIME — the certification window is later than the fit window', () => {
    const c = svc.build(hist([[0.5, 300, 0.5], [0.9, 300, 0.6]]), { minBin: 30 });
    expect(c.certified_through >= c.fitted_through).toBe(true);
    expect(c.fit_n).toBeGreaterThan(0);
    expect(c.certify_n).toBeGreaterThan(0);
  });

  it('END TO END: uncalibrated legs are refused; calibrated ones compound', () => {
    const c = svc.build(hist([[0.5, 300, 0.5], [0.9, 300, 0.6]]), { minBin: 30 });
    const legs = ['a', 'b'].map((id) => {
      const v = c.calibrate(0.5);
      return { id, p: v.p_calibrated, calibrated: v.calibrated, gameId: `g${id}` };
    });
    const out = chain.chainAcross(legs);
    if (legs.every((l) => l.calibrated)) {
      expect(out.ok).toBe(true);
      expect(out.compound_probability).toBeCloseTo(legs[0].p * legs[1].p, 3);
    } else {
      expect(out.reason).toBe('uncalibrated_atoms');
    }
  });
});

describe('CALIBRATION — the gate itself', () => {
  const rows = (spec) => spec.flatMap(([p, n, hitRate]) =>
    Array.from({ length: n }, (_, i) => ({ p, won: i < Math.round(n * hitRate) ? 1 : 0 })));

  it('passes a model whose stated probabilities are its realized rates', () => {
    const out = cal.isCalibrated(rows([[0.3, 100, 0.30], [0.5, 100, 0.50], [0.9, 100, 0.90]]));
    expect(out.calibrated).toBe(true);
  });

  it('FAILS the real hits curve — over-confident exactly where a parlay stacks', () => {
    const out = cal.isCalibrated(rows([[0.45, 152, 0.49], [0.75, 152, 0.605], [0.91, 100, 0.63]]));
    expect(out.calibrated).toBe(false);
    expect(out.reason).toBe('bin_error_exceeds_tolerance');
    expect(out.worst_high_confidence_bin.error).toBeGreaterThan(0.15);
  });

  it('refuses to judge on too little data rather than guessing', () => {
    expect(cal.isCalibrated(rows([[0.5, 20, 0.5]])).reason).toBe('insufficient_sample');
  });

  it('isotonic fitting corrects the numbers while PRESERVING the ordering', () => {
    const map = cal.fitIsotonic(rows([[0.45, 152, 0.49], [0.75, 152, 0.605], [0.91, 100, 0.63]]));
    expect(map).not.toBeNull();
    const lo = cal.applyIsotonic(map, 0.45);
    const hi = cal.applyIsotonic(map, 0.91);
    expect(hi).toBeGreaterThanOrEqual(lo);      // ordering survives
    expect(hi).toBeLessThan(0.75);              // the 0.91 claim is corrected down hard
  });
});