vyndr/tests/unit/retentionSchemaContract.test.js

'use strict';

/**
 * RETENTION SCHEMA CONTRACT — the guard that would have caught the outage.
 *
 * WHAT HAPPENED. `createCollector.onPublished` set `published_side` alongside
 * `published`. `published_side` is not a `model_snapshots` column, supabase-js
 * declares the UNION of row keys in the `columns=` parameter, and PostgREST
 * rejected the entire batch with a 400 — for every sport, silently, because
 * retention is best-effort. Verified in production edge logs.
 *
 * WHY 381 GREEN SUITES MISSED IT. Every retention test injects a permissive
 * fake client — `{ from: () => ({ upsert: async () => ({ error: null }) }) }` —
 * which accepts any column set. The suite proved the logic and never once
 * compared a row against the database contract.
 *
 * WHY THE FIRST MANUAL CHECK ALSO MISSED IT. It sampled the collector after
 * `onGraded` only and never called `onPublished`, so the offending key was not
 * yet on the row. It inspected a PRE-PUBLICATION shape and reported the FINAL
 * outbound shape as clean.
 *
 * So this test does two things the old ones could not:
 *   1. it validates the payload ACTUALLY HANDED TO `.upsert()`, captured by a
 *      spy, after the full production call order including `onPublished`;
 *   2. it validates against a contract DERIVED from the migration chain, not a
 *      hand-maintained list.
 */

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

const ROOT = path.resolve(__dirname, '..', '..');
const CONTRACT = JSON.parse(fs.readFileSync(
  path.join(ROOT, 'supabase/schema/model_snapshots.columns.json'), 'utf8',
));

/** Captures the exact array supabase-js would send. */
function spyClient() {
  const seen = [];
  return {
    seen,
    client: {
      from: (table) => ({
        upsert: async (rows, opts) => { seen.push({ table, rows, opts }); return { error: null }; },
      }),
    },
  };
}

const CTX = {
  snapshotId: '00000000-0000-0000-0000-000000000000',
  capturedAt: '2026-08-27T22:00:00Z',
  gameDate: '2026-08-27',
  gameIdFor: () => 'mlb:2026-08-27:BostonRedSox@MiamiMarlins',
};
const BASE = {
  player: 'Aaron Judge', stat_type: 'hits', line: 0.5, sport: 'mlb', book: 'draftkings',
  canonical_event_id: 'mlb:gamepk:823825', event_identity_source: 'MLB_STATSAPI_GAMEPK',
  event_identity_method: 'CANONICAL', event_identity_version: 'evid@1', event_occurrence: 1,
};
const OVER = { ...BASE, direction: 'over', grade: 'B', confidence: 61, p_win: 0.61 };
const UNDER = { ...BASE, direction: 'under', grade: 'C', confidence: 39, p_win: 0.39 };

/** The FULL production call order — onGraded for both sides, then onPublished. */
function finalOutboundRows() {
  const c = retention.createCollector(CTX);
  c.onGraded(BASE, [OVER, UNDER]);
  c.onPublished(BASE, OVER);
  return c.rows;
}

describe('the contract itself is derived, not hand-written', () => {
  test('it declares its generator and its derivation', () => {
    expect(CONTRACT.table).toBe('model_snapshots');
    expect(CONTRACT.generated_by).toBe('scripts/generate-schema-contract.js');
    expect(CONTRACT.derived_from).toMatch(/supabase\/migrations/);
    expect(fs.existsSync(path.join(ROOT, 'scripts/generate-schema-contract.js'))).toBe(true);
    expect(fs.existsSync(path.join(ROOT, 'scripts/verify-schema-contract.js'))).toBe(true);
  });

  test('it is non-trivial and self-consistent', () => {
    expect(CONTRACT.columns.length).toBe(CONTRACT.column_count);
    expect(CONTRACT.columns.length).toBeGreaterThan(50);
    expect(CONTRACT.columns).toContain('published');
    expect(CONTRACT.columns).toContain('canonical_event_id');
    // The offending field must NOT be in the contract — that is the fact.
    expect(CONTRACT.columns).not.toContain('published_side');
  });

  test('known production drift is recorded rather than hidden', () => {
    const d = CONTRACT.known_production_drift;
    expect(d.columns_in_production_not_in_migrations).toEqual(
      expect.arrayContaining(['quarantine_reason', 're_settled_at', 'settlement_source']),
    );
    // The migration-derived set is the stricter of the two, so a writer inside
    // it is valid against production as well.
    expect(d.explanation).toMatch(/stricter/);
  });
});

describe('FINAL OUTBOUND payload is within the schema contract', () => {
  test('the captured upsert payload uses only real columns', async () => {
    const spy = spyClient();
    await retention.persist(finalOutboundRows(), { getClient: () => spy.client });

    expect(spy.seen.length).toBeGreaterThan(0);
    const call = spy.seen[0];
    expect(call.table).toBe('model_snapshots');

    // supabase-js sends the UNION of keys across the batch — validate the union.
    const union = new Set();
    for (const r of call.rows) for (const k of Object.keys(r)) union.add(k);
    const invalid = [...union].filter((k) => !CONTRACT.columns.includes(k)).sort();
    expect(invalid).toEqual([]);
  });

  test('the payload is captured AFTER onPublished, not before', async () => {
    // The pre-publication shape is what the earlier manual check inspected.
    const pre = retention.createCollector(CTX);
    pre.onGraded(BASE, [OVER, UNDER]);
    const preKeys = new Set(pre.rows.flatMap((r) => Object.keys(r)));

    const post = finalOutboundRows();
    const postKeys = new Set(post.flatMap((r) => Object.keys(r)));

    // Both must be valid; the point is that this test exercises the later one.
    for (const set of [preKeys, postKeys]) {
      expect([...set].filter((k) => !CONTRACT.columns.includes(k))).toEqual([]);
    }
    // And onPublished must actually have marked a row, or the test is vacuous.
    expect(post.filter((r) => r.published === true)).toHaveLength(1);
    expect(post.filter((r) => r.published === false)).toHaveLength(1);
  });

  test('every declared key is present on EVERY row', async () => {
    // A key on only some rows is dropped for the whole batch by PostgREST, so
    // a ragged batch is its own defect class.
    const rows = finalOutboundRows();
    const union = new Set(rows.flatMap((r) => Object.keys(r)));
    for (const r of rows) {
      expect(new Set(Object.keys(r))).toEqual(union);
    }
  });

  test('published_side is gone from the source entirely', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8')
      .replace(/\/\*[\s\S]*?\*\//g, '')
      .replace(/(^|[^:])\/\/.*$/gm, '$1');
    expect(src).not.toMatch(/published_side/);
  });
});

describe('RETENTION FAILURE IS NOT SILENT', () => {
  test('a PostgREST 400 is reported, never swallowed as success', async () => {
    const failing = {
      from: () => ({
        upsert: async () => ({
          error: { message: "Could not find the 'published_side' column of 'model_snapshots'", code: 'PGRST204' },
        }),
      }),
    };
    const out = await retention.persist(finalOutboundRows(), { getClient: () => failing });
    expect(out.written).toBe(0);
    expect(out.error).toMatch(/published_side/);
    // Never reported as a success.
    expect(out.skipped).toBe(false);
  });

  test('the pipeline emits a high-severity structured event on that failure', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/snapshotService.js'), 'utf8');
    const block = src.slice(src.indexOf('Retention write FAILED') - 400,
      src.indexOf('Retention write FAILED') + 700);
    for (const field of ['stage=model_snapshots', 'snapshot_id=', 'code_sha=', 'at=', 'error=']) {
      expect(block).toContain(field);
    }
    expect(block).toMatch(/priority: 'high'/);
    // Best-effort semantics preserved: the product is explicitly unaffected.
    expect(block).toMatch(/product is unaffected/);
  });

  test('a skipped write (no database configured) is NOT alerted', async () => {
    const out = await retention.persist(finalOutboundRows(), { getClient: () => null });
    expect(out.skipped).toBe(true);
    expect(out.error).toBeNull();
    const src = fs.readFileSync(path.join(ROOT, 'src/services/snapshotService.js'), 'utf8');
    expect(src).toMatch(/!r\.skipped/);
  });

  test('zero rows written with candidates present also alerts', () => {
    const src = fs.readFileSync(path.join(ROOT, 'src/services/snapshotService.js'), 'utf8');
    expect(src).toMatch(/r\.attempted > 0 && r\.written === 0/);
  });
});

describe('CYCLE PERSISTENCE MECHANISM', () => {
  test('a cycle is written in chunks, and a failed chunk aborts the rest', async () => {
    // Documented for the dark-cycle gate: persistence is CHUNKED (250), so a
    // partial cycle is possible in principle — the loop breaks on the first
    // error rather than continuing. There is no terminal completion marker.
    const src = fs.readFileSync(path.join(ROOT, 'src/services/retentionService.js'), 'utf8');
    const body = src.slice(src.indexOf('async function persist('));
    expect(body).toMatch(/const CHUNK = 250/);
    expect(body).toMatch(/if \(error\) \{ out\.error = error\.message; break; \}/);
    // `written` is the exact count of rows in successfully committed chunks, so
    // written === attempted is the completion signal available today.
    expect(body).toMatch(/out\.written \+= chunk\.length/);
  });

  test('written vs attempted distinguishes a complete cycle from a partial one', async () => {
    const spy = spyClient();
    const rows = finalOutboundRows();
    const out = await retention.persist(rows, { getClient: () => spy.client });
    expect(out.attempted).toBe(rows.length);
    expect(out.written).toBe(rows.length);
  });
});