vyndr/tests/unit/retentionIdentity.test.js

'use strict';

/**
 * SEMANTIC RETENTION PROPOSITION IDENTITY, and the database enforcement of it.
 *
 * The semantic question comes FIRST: when are two outbound rows the same
 * retention proposition within one cycle? Answer — same cycle, same EVENT, same
 * participant, same stat, same line, same side. Provider/book is deliberately
 * absent: collapsing books is `dedupeProps`'s job and the price anchor is
 * chosen later.
 *
 * The database index is ENFORCEMENT of that answer, never the definition of it.
 * `model_snapshots_cycle_prop_uniq` carried no event component, so a real MLB
 * doubleheader collapsed to one identity — verified on production: 2026-08-17
 * St. Louis @ Cincinnati holds 1,738 retained rows under a single game_id, and
 * replaying 1,000 real propositions across both real gamePks materialized 1,000
 * of 2,000 rows under the old index and 2,000 of 2,000 under the new one.
 */

const fs = require('fs');
const path = require('path');
const retention = require('../../src/services/retentionService');

const ROOT = path.resolve(__dirname, '..', '..');
const SNAP = '11111111-1111-1111-1111-111111111111';
const G1 = 'mlb:gamepk:824514';
const G2 = 'mlb:gamepk:824478';

const row = (o = {}) => ({
  snapshot_id: SNAP, game_id: 'mlb:2026-08-17:St.LouisCardinals@CincinnatiReds',
  canonical_event_id: G1, player_key: 'nolan arenado', stat: 'hits', line: 0.5,
  side: 'over', sport: 'mlb', ...o,
});

describe('SEMANTIC IDENTITY — the contract, stated before the schema', () => {
  test('the conflict target names cycle, event, participant, stat, line, side', () => {
    expect(retention.RETENTION_CONFLICT.split(',')).toEqual(
      ['snapshot_id', 'game_id', 'canonical_event_id', 'player_key', 'stat', 'line', 'side']);
  });

  test('BOOK is deliberately NOT part of identity', () => {
    expect(retention.RETENTION_CONFLICT).not.toMatch(/book/);
    // …and that is upstream's documented job, not an oversight.
    const gs = fs.readFileSync(path.join(ROOT, 'src/services/gradeSlateService.js'), 'utf8');
    expect(gs).toMatch(/Provider is collapsed on\s+\* purpose/);
  });

  test('SAME proposition -> same identity', () => {
    expect(retention.rowIdentity(row())).toBe(retention.rowIdentity(row()));
  });

  test('DIFFERENT EVENT -> DISTINCT (the doubleheader)', () => {
    expect(retention.rowIdentity(row({ canonical_event_id: G1 })))
      .not.toBe(retention.rowIdentity(row({ canonical_event_id: G2 })));
  });

  for (const [what, patch] of [
    ['LINE', { line: 1.5 }],
    ['SIDE', { side: 'under' }],
    ['STAT', { stat: 'total_bases' }],
    ['PARTICIPANT', { player_key: 'paul goldschmidt' }],
    ['CYCLE', { snapshot_id: '22222222-2222-2222-2222-222222222222' }],
    ['GAME (no canonical)', { canonical_event_id: null, game_id: 'nba:2026-08-27:LAL@NYK' }],
  ]) {
    test(`DIFFERENT ${what} -> DISTINCT`, () => {
      expect(retention.rowIdentity(row())).not.toBe(retention.rowIdentity(row(patch)));
    });
  }
});

describe('SEMANTIC IDENTITY <=> DATABASE CONFLICT IDENTITY', () => {
  test('the JS identity uses EXACTLY the columns the DB conflict target names', () => {
    expect(retention.CONFLICT_IDENTITY).toEqual(retention.RETENTION_CONFLICT.split(','));
  });

  test('the migration creates an index on exactly those columns', () => {
    const sql = fs.readFileSync(path.join(ROOT,
      'supabase/migrations/048_retention_event_aware_identity_expand.sql'), 'utf8');
    const stmt = sql.slice(sql.indexOf('create unique index'));
    const cols = stmt.slice(stmt.indexOf('(snapshot_id'), stmt.indexOf('nulls not distinct'))
      .replace(/[()\s]/g, '');
    expect(cols.replace(/,$/, '')).toBe(retention.RETENTION_CONFLICT);
  });

  test('NULLS NOT DISTINCT is present, and it is load-bearing', () => {
    // canonical_event_id is NULL for every non-MLB row. Under PostgreSQL's
    // DEFAULT semantics two NULLs are DISTINCT, so the same NBA proposition
    // would insert again on every retry — measured: 2 rows. NULLS NOT DISTINCT
    // makes it 1.
    const sql = fs.readFileSync(path.join(ROOT,
      'supabase/migrations/048_retention_event_aware_identity_expand.sql'), 'utf8');
    expect(sql).toMatch(/nulls not distinct/i);
  });
});

describe('CANONICAL EVENT AVAILABILITY BY ROW CLASS', () => {
  const gs = fs.readFileSync(path.join(ROOT, 'src/services/gradeSlateService.js'), 'utf8');

  test('MLB: only RESOLVED rows WITH a canonical id are admitted', () => {
    expect(gs).toMatch(/status === 'RESOLVED' && p\.canonical_event_id/);
  });

  test('UNRESOLVED / AMBIGUOUS / CONTRADICTED never reach retention at all', () => {
    // They are rejected BEFORE grading, and onGraded is what feeds retention.
    expect(gs).toMatch(/const gate = admitForGrading\(props, sport\)/);
    expect(gs).toMatch(/dedupeProps\(gate\.admitted, limit\)/);
    expect(gs).not.toMatch(/dedupeProps\(gate\.rejected/);
  });

  test('a sport with no resolver is admitted unchanged — canonical stays NULL', () => {
    expect(gs).toMatch(/!status \|\| status === 'UNSUPPORTED'/);
  });

  test('game_id is the always-present fallback, so identity is never NULL-only', () => {
    // NOT NULL in the schema; measured 0 nulls / 0 empties across 328,262 rows.
    const contract = JSON.parse(fs.readFileSync(path.join(ROOT,
      'supabase/schema/model_snapshots.columns.json'), 'utf8'));
    expect(contract.columns).toContain('game_id');
    expect(retention.RETENTION_CONFLICT).toMatch(/game_id/);
  });
});

describe('MIXED-FLEET BRIDGE', () => {
  const err = (code, message) => ({ code, message });

  test('a missing new index (pre-EXPAND) is bridged', () => {
    expect(retention.isLegacyConflictBlock(
      err('42P10', 'there is no unique or exclusion constraint matching the ON CONFLICT specification'))).toBe(true);
  });

  test('the LEGACY index rejecting a doubleheader row is bridged', () => {
    expect(retention.isLegacyConflictBlock(
      err('23505', 'duplicate key value violates unique constraint "model_snapshots_cycle_prop_uniq"'))).toBe(true);
  });

  test('a SUPERSEDES conflict is NOT bridged — the fork guard must still fire', () => {
    // Also a 23505. Swallowing it would destroy the forked-history guard, which
    // is why the bridge requires the legacy index to be NAMED.
    expect(retention.isLegacyConflictBlock(
      err('23505', 'duplicate key value violates unique constraint "model_snapshots_supersedes_unique"'))).toBe(false);
  });

  test('unrelated errors are never bridged', () => {
    expect(retention.isLegacyConflictBlock(err('23502', 'null value in column "captured_at"'))).toBe(false);
    expect(retention.isLegacyConflictBlock(err('PGRST204', "Could not find the 'x' column"))).toBe(false);
    expect(retention.isLegacyConflictBlock(null)).toBe(false);
  });

  test('it targets the event-aware identity FIRST', async () => {
    const seen = [];
    const sb = { from: () => ({ upsert: async (rows, o) => { seen.push(o.onConflict); return { error: null }; } }) };
    const res = await retention.upsertSnapshotChunk(sb, [row()], { ignoreDuplicates: true });
    expect(seen).toEqual([retention.RETENTION_CONFLICT]);
    expect(res.fellBack).toBe(false);
  });

  test('it retries the SAME chunk on the legacy target when bridged', async () => {
    const seen = [];
    const sb = {
      from: () => ({
        upsert: async (rows, o) => {
          seen.push({ target: o.onConflict, n: rows.length });
          return seen.length === 1
            ? { error: err('23505', 'duplicate key value violates unique constraint "model_snapshots_cycle_prop_uniq"') }
            : { error: null };
        },
      }),
    };
    const chunk = [row({ canonical_event_id: G1 }), row({ canonical_event_id: G2 })];
    const res = await retention.upsertSnapshotChunk(sb, chunk, { ignoreDuplicates: true });
    expect(seen.map((s) => s.target)).toEqual([retention.RETENTION_CONFLICT, retention.LEGACY_CONFLICT]);
    expect(seen[1].n).toBe(chunk.length);      // the SAME chunk, whole
    expect(res.error).toBeNull();
    expect(res.fellBack).toBe(true);
  });

  test('a non-bridgeable error is returned, never retried', async () => {
    const seen = [];
    const sb = { from: () => ({ upsert: async (r, o) => { seen.push(o.onConflict); return { error: err('23502', 'null value') }; } }) };
    const res = await retention.upsertSnapshotChunk(sb, [row()], {});
    expect(seen).toHaveLength(1);
    expect(res.error.code).toBe('23502');
    expect(res.fellBack).toBe(false);
  });

  test('persist reports when the bridge fired — it is a bridge, not a resting place', async () => {
    let first = true;
    const sb = {
      from: () => ({
        upsert: async () => (first
          ? (first = false, { error: err('23505', 'duplicate key value violates unique constraint "model_snapshots_cycle_prop_uniq"') })
          : { error: null }),
      }),
    };
    const out = await retention.persist([row()], { getClient: () => sb });
    expect(out.legacy_conflict_fallback).toBe(true);
    expect(out.written).toBe(1);
  });

  test('EVERY model_snapshots write goes through the bridge', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8')
      .replace(/\/\*[\s\S]*?\*\//g, '').replace(/(^|[^:])\/\/.*$/gm, '$1');
    // No hardcoded legacy target may survive outside the constant itself.
    const hard = src.match(/onConflict: 'snapshot_id,player_key,stat,line,side'/g) || [];
    expect(hard).toHaveLength(0);
    const upserts = src.match(/\.upsert\(/g) || [];
    const bridged = src.match(/upsertSnapshotChunk\(/g) || [];
    // One .upsert lives inside the bridge helper (two calls: primary + fallback).
    expect(upserts.length).toBe(2);
    expect(bridged.length).toBeGreaterThanOrEqual(4);   // definition + 3 call sites
  });
});

describe('MIGRATION SAFETY', () => {
  const expand = fs.readFileSync(path.join(ROOT,
    'supabase/migrations/048_retention_event_aware_identity_expand.sql'), 'utf8');
  const contract = fs.readFileSync(path.join(ROOT,
    'supabase/migrations/049_retention_event_aware_identity_contract.sql'), 'utf8');

  test('EXPAND is additive and idempotent, and retires nothing', () => {
    expect(expand).toMatch(/create unique index if not exists/i);
    expect(expand).not.toMatch(/drop\s+index/i);
    expect(expand).not.toMatch(/alter table/i);
  });

  test('EXPAND performs no backfill', () => {
    expect(expand).not.toMatch(/\bupdate\b/i);
    expect(expand).not.toMatch(/\binsert\b/i);
  });

  test('CONTRACT only drops the legacy index, and documents its rollback', () => {
    expect(contract).toMatch(/drop index if exists public\.model_snapshots_cycle_prop_uniq/i);
    expect(contract).not.toMatch(/\bupdate\b/i);
    expect(contract).toMatch(/ROLLBACK/);
    expect(contract).toMatch(/APPLY THIS ONLY AFTER FLEET CONVERGENCE IS PROVEN/);
  });

  test('the two phases are separate files — they must not land together', () => {
    expect(expand).not.toMatch(/drop index if exists public\.model_snapshots_cycle_prop_uniq/i);
  });
});

describe('MATERIALIZATION DEFENCE SURVIVES THE REPAIR', () => {
  test('the collision detector is still wired and still disqualifies a cohort', () => {
    const rows = [row({ canonical_event_id: G1 }), row({ canonical_event_id: G2 })];
    // Under the NEW identity these are two propositions, so no collision.
    const exp = retention.expectedMaterialization(rows);
    expect(exp.expected_identities).toBe(2);
    expect(exp.collision_count).toBe(0);
    // And a genuine duplicate still collides.
    const dup = retention.expectedMaterialization([row(), row()]);
    expect(dup.collision_count).toBe(1);
    expect(retention.reconcileMaterialization({
      expected: dup, actualIdentities: dup.identities, transportStatus: retention.TERMINAL.COMPLETE,
    }).status).toBe(retention.MATERIALIZATION.COLLISION);
  });

  test('transport vs materialization, and per-sport evidence, are intact', () => {
    expect(typeof retention.classifyPersist).toBe('function');
    expect(typeof retention.reconcileMaterialization).toBe('function');
    expect(typeof retention.lastRetention).toBe('function');
    expect(retention.TERMINAL.FAILED_PARTIAL).toBeTruthy();
  });
});