vyndr/tests/unit/canonicalParticipant.test.js

'use strict';

/**
 * CANONICAL MLB PARTICIPANT IDENTITY.
 *
 * VYNDR had three definitions of "same player": raw `p.player` (dedupe),
 * `utils/normalize.normalizeName` (features, NO nickname handling), and
 * `utils/playerName.nameKey` (retention, WITH nicknames). Retention was the
 * first layer to notice they disagreed, and all it could do was discard the
 * loser — 28 collisions in the blocked controlled cohort.
 *
 * The fix is not a better spelling. The event-scoped roster already carries the
 * StatsAPI personId; it was being thrown away. Scope is load-bearing: measured
 * on the real 2026-08-28 league rosters, `max muncy`, `jose fermin` and
 * `luis garcia` each resolve to TWO different people, so a bare name key is NOT
 * globally unique. Within one game's two rosters, all 33 real events tested
 * (including the verified doubleheader date) resolved uniquely.
 */

const fs = require('fs');
const path = require('path');
const evid = require('../../src/services/event/eventIdentity');
const { nameKey } = require('../../src/utils/playerName');
const { normalizeName: featNorm } = require('../../src/utils/normalize');
const { __internals } = require('../../src/services/gradeSlateService');
const ROOT = path.resolve(__dirname, '..', '..');

const G = (pk, home, away) => ({ gamePk: pk, home: { team: home }, away: { team: away } });
const personsOf = (rows) => {
  const m = new Map();
  for (const r of rows) {
    const k = nameKey(r.canonicalName);
    if (!m.has(k)) m.set(k, []);
    m.get(k).push(r);
  }
  return m;
};
const prop = (o = {}) => ({ player: 'P', stat_type: 'hits', line: 0.5, book: 'draftkings', ...o });

describe('SCOPE IS LOAD-BEARING — a name key is not a player id', () => {
  // Real league data: two different humans, one normalized key.
  const persons = personsOf([
    { personId: 691777, canonicalName: 'Max Muncy', abbr: 'ATH' },
    { personId: 571970, canonicalName: 'Max Muncy', abbr: 'LAD' },
  ]);
  const games = [G(1, 'Los Angeles Dodgers', 'San Diego Padres'), G(2, 'Athletics', 'Los Angeles Dodgers')];

  test('one team in the event -> resolves to that team’s person', () => {
    const r = evid.resolveParticipant(prop({ player: 'Max Muncy', canonical_event_id: 'mlb:gamepk:1' }), games, persons);
    expect(r.personId).toBe(571970);
    expect(r.teamAbbr).toBe('LAD');
  });

  test('BOTH Muncys in the same event -> REFUSES, never guesses', () => {
    expect(evid.resolveParticipant(prop({ player: 'Max Muncy', canonical_event_id: 'mlb:gamepk:2' }), games, persons)).toBeNull();
  });

  test('no event, no game, or unknown player -> null (fails closed)', () => {
    expect(evid.resolveParticipant(prop({ player: 'Max Muncy' }), games, persons)).toBeNull();
    expect(evid.resolveParticipant(prop({ player: 'Max Muncy', canonical_event_id: 'mlb:gamepk:99' }), games, persons)).toBeNull();
    expect(evid.resolveParticipant(prop({ player: 'Nobody Here', canonical_event_id: 'mlb:gamepk:1' }), games, persons)).toBeNull();
  });

  test('an empty persons index never resolves', () => {
    expect(evid.resolveParticipant(prop({ player: 'Max Muncy', canonical_event_id: 'mlb:gamepk:1' }), games, new Map())).toBeNull();
  });
});

describe('ALIAS CLASSES — generic, with the seven as regression evidence', () => {
  const CASES = [
    ['accent',    'Heriberto Hernández', 'Heriberto Hernandez', 681715, 'MIA', 'Miami Marlins'],
    ['suffix',    'Luis Robert Jr.',     'Luis Robert',         673357, 'NYM', 'New York Mets'],
    ['case',      'Jonny DeLuca',        'Jonny Deluca',        676356, 'TB',  'Tampa Bay Rays'],
    ['suffix II', 'Michael Harris II',   'Michael Harris',      671739, 'ATL', 'Atlanta Braves'],
    ['nickname',  'Mickey Gasper',       'Michael Gasper',      681508, 'BOS', 'Boston Red Sox'],
    ['formal',    'Joshua Báez',    'Josh Baez',           695491, 'STL', 'St. Louis Cardinals'],
    ['nick+suf',  'Jimmy Crooks',        'Jimmy Crooks III',    699625, 'STL', 'St. Louis Cardinals'],
  ];
  for (const [label, canonical, alias, personId, abbr, teamName] of CASES) {
    test(`${label}: "${alias}" resolves to the same person as "${canonical}"`, () => {
      const persons = personsOf([{ personId, canonicalName: canonical, abbr }]);
      const games = [G(7, teamName, 'Chicago Cubs')];
      const a = evid.resolveParticipant(prop({ player: alias, canonical_event_id: 'mlb:gamepk:7' }), games, persons);
      const c = evid.resolveParticipant(prop({ player: canonical, canonical_event_id: 'mlb:gamepk:7' }), games, persons);
      expect(a).not.toBeNull();
      expect(a.personId).toBe(personId);
      expect(c.personId).toBe(personId);
      expect(a.canonicalName).toBe(canonical);
    });
  }

  test('the fix is GENERIC — no player name is hardcoded in production code', () => {
    for (const f of ['src/services/event/eventIdentity.js', 'src/services/gradeSlateService.js',
      'src/services/intelligence/computeFeatures.js', 'src/services/snapshotService.js']) {
      const src = fs.readFileSync(path.join(ROOT, f), 'utf8')
        .replace(/\/\*[\s\S]*?\*\//g, '').replace(/(^|[^:])\/\/.*$/gm, '$1');
      for (const name of ['Gasper', 'Hernández', 'Hernandez', 'Baez', 'Crooks', 'DeLuca', 'Muncy']) {
        expect(src).not.toContain(name);
      }
    }
  });
});

describe('DEDUPE BY PARTICIPANT, NOT DISPLAY NAME', () => {
  const dd = (rows) => __internals.dedupeProps(rows, 1000);
  const base = { stat_type: 'hits', line: 0.5, book: 'draftkings', canonical_event_id: 'mlb:gamepk:7' };

  test('two aliases of ONE proven participant collapse to ONE proposition', () => {
    const out = dd([
      { ...base, player: 'Michael Gasper', mlb_person_id: 681508 },
      { ...base, player: 'Mickey Gasper', mlb_person_id: 681508 },
    ]);
    expect(out).toHaveLength(1);
  });

  test('the SAME person in TWO events stays TWO propositions', () => {
    const out = dd([
      { ...base, player: 'Mickey Gasper', mlb_person_id: 681508, canonical_event_id: 'mlb:gamepk:824514' },
      { ...base, player: 'Mickey Gasper', mlb_person_id: 681508, canonical_event_id: 'mlb:gamepk:824478' },
    ]);
    expect(out).toHaveLength(2);
  });

  test('same person, different STAT stays two', () => {
    expect(dd([
      { ...base, player: 'A', mlb_person_id: 1 },
      { ...base, player: 'A', mlb_person_id: 1, stat_type: 'total_bases' },
    ])).toHaveLength(2);
  });

  test('same person, different LINE stays two', () => {
    expect(dd([
      { ...base, player: 'A', mlb_person_id: 1 },
      { ...base, player: 'A', mlb_person_id: 1, line: 1.5 },
    ])).toHaveLength(2);
  });

  test('DIFFERENT people are never merged, even with one lossy name key', () => {
    const out = dd([
      { ...base, player: 'Max Muncy', mlb_person_id: 691777 },
      { ...base, player: 'Max Muncy', mlb_person_id: 571970 },
    ]);
    expect(out).toHaveLength(2);
  });

  test('unresolved props fall back to the raw name — prior behaviour exactly', () => {
    expect(dd([{ ...base, player: 'Michael Gasper' }, { ...base, player: 'Mickey Gasper' }])).toHaveLength(2);
    expect(dd([{ ...base, player: 'Same Guy' }, { ...base, player: 'Same Guy' }])).toHaveLength(1);
  });

  test('the dedupe key uses the participant when present, the raw name otherwise', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/gradeSlateService.js'), 'utf8');
    expect(src).toMatch(/const who = p\.mlb_person_id != null \? `mlb:\$\{p\.mlb_person_id\}` : p\.player;/);
    expect(src).toMatch(/\$\{propositionEventKey\(p\)\}::\$\{who\}::\$\{p\.stat_type\}::\$\{p\.line\}/);
  });
});

describe('FEATURE IDENTITY IS CANONICAL, NOT THE SURVIVING ALIAS', () => {
  const src = fs.readFileSync(path.join(ROOT, 'src/services/intelligence/computeFeatures.js'), 'utf8');

  test('the lookup consumes the canonical roster name when proven', () => {
    expect(src).toMatch(/const featurePlayer = rawProp\.canonical_player_name \|\| player;/);
    expect(src).toMatch(/lookupPlayer\(\{ player: featurePlayer, sport \}\)/);
    expect(src).toMatch(/getStatRows\(featurePlayer, sport, statType\)/);
  });

  test('this is exactly why raw spelling could not be trusted', () => {
    // player_id_map holds `mickey gasper`, NOT `michael gasper` (verified in
    // production). Under the raw name the lookup outcome depended on which
    // alias survived dedupe.
    expect(featNorm('Mickey Gasper')).toBe('mickey gasper');
    expect(featNorm('Michael Gasper')).toBe('michael gasper');
    expect(featNorm('Mickey Gasper')).not.toBe(featNorm('Michael Gasper'));
    // The retention normalizer DOES unify them — that disagreement is the bug.
    expect(nameKey('Mickey Gasper')).toBe(nameKey('Michael Gasper'));
  });

  test('no canonical name -> the raw name, unchanged from before', () => {
    expect(src).toMatch(/rawProp\.canonical_player_name \|\| player/);
  });
});

describe('SOURCE PROVENANCE IS PRESERVED', () => {
  test('the raw provider name is never overwritten', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/snapshotService.js'), 'utf8');
    const i = src.indexOf('CANONICAL PARTICIPANT. Resolved AFTER event identity');
    const block = src.slice(i, i + 900);
    expect(block).toMatch(/pr\.mlb_person_id = who\.personId;/);
    expect(block).toMatch(/pr\.canonical_player_name = who\.canonicalName;/);
    expect(block).not.toMatch(/pr\.player\s*=/);
  });

  test('retention still stores the SOURCE name', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8');
    expect(src).toMatch(/player_name: normalizeName\(player\)\.display \|\| player/);
  });

  /**
   * This assertion used to grep for `player_key: nameKey(player)`.
   *
   * That expression was standing in for a PROPERTY — that retention's collision
   * counter is an independent detector of the producer failing to collapse a
   * human — and a grep verifies the spelling instead of the property. The
   * semantic key now prefers the league's own record when the participant is
   * PROVEN, which is what stops one human becoming two identities. The property
   * the grep was protecting is asserted directly below, in both modes, and it
   * survives: when the producer emits two rows for one human, retention still
   * files them under one identity and still reports the collision.
   */
  test('retention still catches the producer under-collapsing — participant PROVEN', () => {
    const retention = require('../../src/services/retentionService');
    const rows = retention.rowsFromSides(
      { player: 'Mickey Gasper', stat_type: 'hits', line: 0.5, mlb_person_id: 681508, canonical_player_name: 'Mickey Gasper' },
      [{ direction: 'over', grade: 'C' }], { snapshotId: 's', sport: 'mlb', gameDate: '2026-08-30', gameIdFor: () => 'g' },
    ).concat(retention.rowsFromSides(
      { player: 'Michael Gasper', stat_type: 'hits', line: 0.5, mlb_person_id: 681508, canonical_player_name: 'Mickey Gasper' },
      [{ direction: 'over', grade: 'C' }], { snapshotId: 's', sport: 'mlb', gameDate: '2026-08-30', gameIdFor: () => 'g' },
    ));
    expect(retention.expectedMaterialization(rows).collision_count).toBe(1);
  });

  test('retention still catches the producer under-collapsing — participant UNPROVEN', () => {
    const retention = require('../../src/services/retentionService');
    const mk = (player) => retention.rowsFromSides(
      { player, stat_type: 'hits', line: 0.5 },
      [{ direction: 'over', grade: 'C' }], { snapshotId: 's', sport: 'mlb', gameDate: '2026-08-30', gameIdFor: () => 'g' },
    );
    // No personId anywhere: the key falls back to the raw spelling exactly as
    // it always did, and the two spellings still meet on one identity.
    expect(retention.expectedMaterialization(mk('Mickey Gasper').concat(mk('Michael Gasper'))).collision_count).toBe(1);
  });
});

describe('RETENTION REMAINS AN INDEPENDENT CHECK', () => {
  const src = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8');

  test('the conflict identity is unchanged and carries NO raw spelling', () => {
    const retention = require('../../src/services/retentionService');
    expect(retention.RETENTION_CONFLICT.split(',')).toEqual(
      ['snapshot_id', 'game_id', 'canonical_event_id', 'player_key', 'stat', 'line', 'side']);
    expect(retention.RETENTION_CONFLICT).not.toMatch(/player_name|mlb_person_id/);
  });

  test('the collision counter still exists and still disqualifies', () => {
    const retention = require('../../src/services/retentionService');
    const rows = [
      { snapshot_id: 's', game_id: 'g', canonical_event_id: 'e', player_key: 'a', stat: 'hits', line: 0.5, side: 'over' },
      { snapshot_id: 's', game_id: 'g', canonical_event_id: 'e', player_key: 'a', stat: 'hits', line: 0.5, side: 'over' },
    ];
    const exp = retention.expectedMaterialization(rows);
    expect(exp.collision_count).toBe(1);
    expect(retention.reconcileMaterialization({
      expected: exp, actualIdentities: exp.identities, transportStatus: retention.TERMINAL.COMPLETE,
    }).status).toBe(retention.MATERIALIZATION.COLLISION);
    expect(src).toMatch(/collision_count/);
  });
});

describe('THE THREE-NORMALIZER CONTRACT', () => {
  test('semantic participant identity is independent of every name normalizer', () => {
    const persons = personsOf([{ personId: 681508, canonicalName: 'Mickey Gasper', abbr: 'BOS' }]);
    const games = [G(7, 'Boston Red Sox', 'New York Yankees')];
    const a = evid.resolveParticipant(prop({ player: 'Michael Gasper', canonical_event_id: 'mlb:gamepk:7' }), games, persons);
    const b = evid.resolveParticipant(prop({ player: 'Mickey Gasper', canonical_event_id: 'mlb:gamepk:7' }), games, persons);
    // Same identity despite the raw strings differing AND the feature
    // normalizer disagreeing about them.
    expect(a.personId).toBe(b.personId);
    expect(featNorm('Michael Gasper')).not.toBe(featNorm('Mickey Gasper'));
    // And the id is not derived from a name at all.
    expect(typeof a.personId).toBe('number');
  });

  test('the normalizers keep their existing narrow purposes', () => {
    const rs = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8');
    expect(rs).toMatch(/nameKey/);
    const cf = fs.readFileSync(path.join(ROOT, 'src/services/intelligence/computeFeatures.js'), 'utf8');
    expect(cf).toMatch(/normalizeName/);
    // Neither was globally replaced by the other.
    expect(cf).not.toMatch(/require\(.*playerName.*\)/);
  });
});

describe('THE GAME-DATE REPAIR IS UNTOUCHED', () => {
  test('the fast-path date assignment is still present', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/gameBinder.js'), 'utf8');
    expect(src).toMatch(/if \(!p\.game_date\) p\.game_date = etFast;/);
    expect(src).toMatch(/const etFast = p\.game_time \? etDate\(p\.game_time\) : null;/);
  });
});