builtbykev/vyndr
1
0
Fork 0
Code Issues 1 Pull Requests Actions 6 Packages Projects Releases Wiki Activity

Read integrity, as-of context, and the shadow matchup resolve (A1-A7)

Browse Source 
Seven orders of measurement-first repair. The served grade does not move.

A0/A1 — the unordered page walk returned the right COUNT and the wrong ROWS:
410-617 of 2,490 duplicated with an equal number never returned, while
rows.length matched the server exactly. safePaginate orders on a real unique
key, verifies the tuple at runtime, and THROWS on a query error instead of
treating it as end-of-data. Both hits PROVES are withdrawn: they were drawn
through that reader, and defense_by_direction's distinct-n was likely below
the gate floor all along.

A2/A2b — rolled across every reader: 11 FAIL -> 0. Composite keys pulled from
pg_index (the context tables are dated-composite and had no single unique
column). The unordered helper is deleted, not parked.

A3 — ledgerService and retentionService defaulted the SAME env var to
DIFFERENT versions, so no ledger row ever carried the marker eligibility
requires. One source now. model_snapshots settlement moved onto the cron:
15,484 -> 28,894 settled, repaired-champion 0 -> 7,556.

A4 — hitsFactorContext takes an as-of cutoff. Refusal over reconstruction: no
row at-or-before the date means the factor does not apply, never the nearest
row. Live path unchanged, proven 400/400 on real rows.

A5 — factor_inputs freezes what the factor READ, never the multiplier, so an
audit can recompute and check. It also recorded the finding: the three hits
factors have NEVER fired. prop.opponent and prop.opposing_pitcher are read by
the resolver and written by nothing.

A6/A7 — matchupKeys resolves those keys from the posted lineup plus the
schedule's probable pitchers, and fires the factors into a SHADOW freeze:
248 fires on 308 props, 245 of which would move the grade. The served
forecast is untouched. specs/a8-shadow-factor-gate.md pre-registers the test
that decides whether they ever go live.

Nothing is turned on. CALIBRATION_DEPLOYED stays []. Both verdicts stay
withdrawn. 4,772 tests / 371 suites green, web build exit 0, read-integrity
harness 34/34.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
This commit is contained in:
Kev
2026-08-11 22:49:56 -04:00
parent 387ae4d54e
commit f61ec6b391
49 changed files with 4874 additions and 308 deletions
Download Patch File Download Diff File Expand all files Collapse all files
scripts/prove-tb-factors.js
+45 -23
View File
@@ -38,6 +38,8 @@ const { nameKey } = require('../src/utils/playerName');
const sd = require('../src/services/model/sprayDefense');
const pss = require('../src/services/model/platoonSeverity');
const pw = require('../src/services/model/parkWeather');
const { paginate } = require('../src/utils/safePaginate');
const { uniqueKeyFor } = require('../src/utils/tableKeys');
/** League-typical hit-type shares; the atom reshapes these and TB follows. */
const BASE_SHARES = { single: 0.655, double: 0.195, triple: 0.017, home_run: 0.133 };
@@ -48,18 +50,37 @@ const SB_KEY = process.env.SUPABASE_SERVICE_ROLE_KEY || process.env.SUPABASE_SER
const PAGE = 1000;
const ARCHS = (process.env.TB_ARCHETYPES || 'ALL,BOMBER,GHOST,BRUSH,DRIVER').split(',');
async function page(sb, table, select, apply) {
const out = [];
for (let from = 0; ; from += PAGE) {
const { data, error } = await apply(sb.from(table).select(select)).range(from, from + PAGE - 1);
if (error) throw error;
if (!data || data.length === 0) break;
out.push(...data);
if (data.length < PAGE) break;
}
return out;
// ── FIX A2 (2026-08-09) — THE SAFE WALK ───────────────────────────────────
// `page()` above walks with no ORDER BY. Measured on production, that returned
// the correct row COUNT and the wrong ROWS: up to 33.6% of a read came back
// twice while an equal share never came back at all. `pageSafe` routes the same
// call through `src/utils/safePaginate`, which orders on a UNIQUE key on every
// page, verifies uniqueness at runtime, and THROWS on a query error instead of
// treating it as end-of-data.
//
// `page()` SURVIVES only for the context tables (statcast_aggregates,
// batter_spray, team_defense, platoon_splits, park_dimensions, game_context...).
// Those have COMPOSITE primary keys with no single unique column, so
// safePaginate cannot express them. They measure 0% corruption today; making
// them safe needs a composite-key ordering the helper does not yet have. Do not
// use `page()` for ledger_entries or model_snapshots.
async function pageSafe(sb, table, select, apply, key = uniqueKeyFor(table)) {
return paginate(() => apply(sb.from(table).select(select)),
{ key, pageSize: PAGE, label: `${table}` });
}
/** THE MEASURED READS — main() and the harness call the same functions. */
const READS = {
parks: (sb) => pageSafe(sb, 'park_dimensions', '*', (q) => q.eq('sport', 'mlb')),
gameCtx: (sb) => pageSafe(sb, 'game_context', 'game_id, venue_id, wx_temp_f, wx_wind_speed_mph, wx_wind_direction_deg', (q) => q),
snaps: (sb) => pageSafe(sb, 'model_snapshots', 'id, player_key, game_date, archetype, stat',
(q) => q.eq('sport', 'mlb').eq('stat', 'total_bases').not('archetype', 'is', null)),
ledger: (sb) => pageSafe(sb, 'ledger_entries',
'id, game_id, player_key, player_name, line, side, outcome, game_date, p_win, quarantine_reason, env_park_base',
(q) => q.eq('sport', 'mlb').is('user_id', null).eq('stat', 'total_bases')
.in('outcome', ['hit', 'miss']).not('p_win', 'is', null)),
};
/**
* THE FACTORS. Each returns a MULTIPLIER on the base rate, or null when the
* input is absent — an absent factor must leave the baseline untouched rather
@@ -112,14 +133,14 @@ async function main() {
if (!SB_URL || !SB_KEY) throw new Error('SUPABASE_URL / service key required');
const sb = createClient(SB_URL, SB_KEY, { auth: { persistSession: false } });
const statcast = await page(sb, 'statcast_aggregates', '*', (q) => q.eq('sport', 'mlb'));
const statcast = await pageSafe(sb, 'statcast_aggregates', '*', (q) => q.eq('sport', 'mlb'));
const batters = new Map(); const pitchersById = new Map();
for (const r of statcast) {
const prof = sk.fromStatcastRow(r);
if (r.role === 'pitcher' && r.source_id != null) pitchersById.set(Number(r.source_id), prof);
if (r.role === 'batter' && r.player_key) batters.set(r.player_key, prof);
}
const sprayRows = await page(sb, 'batter_spray', '*', (q) => q.eq('sport', 'mlb'));
const sprayRows = await pageSafe(sb, 'batter_spray', '*', (q) => q.eq('sport', 'mlb'));
const sprayByKey = new Map();
for (const r of sprayRows) {
if (!r.player_key) continue;
@@ -127,7 +148,7 @@ async function main() {
if (!prev || String(r.as_of_date) > String(prev.as_of_date)) sprayByKey.set(r.player_key, r);
}
const platRows = await page(sb, 'platoon_splits', '*', (q) => q.eq('sport', 'mlb'));
const platRows = await pageSafe(sb, 'platoon_splits', '*', (q) => q.eq('sport', 'mlb'));
const platByKey = new Map();
for (const r of platRows) {
if (!r.player_key) continue;
@@ -135,26 +156,22 @@ async function main() {
if (!prev || String(r.as_of_date) > String(prev.as_of_date)) platByKey.set(r.player_key, r);
}
const parkRows = await page(sb, 'park_dimensions', '*', (q) => q.eq('sport', 'mlb'));
const parkRows = await pageSafe(sb, 'park_dimensions', '*', (q) => q.eq('sport', 'mlb'));
const parkByVenue = new Map();
for (const p of parkRows) if (!parkByVenue.has(p.venue_id)) parkByVenue.set(p.venue_id, p);
const parkLeague = pw.leagueGeometry([...parkByVenue.values()]);
const ctxRows = await page(sb, 'game_context', 'game_id, venue_id, wx_temp_f, wx_wind_speed_mph, wx_wind_direction_deg', (q) => q);
const ctxRows = await pageSafe(sb, 'game_context', 'game_id, venue_id, wx_temp_f, wx_wind_speed_mph, wx_wind_direction_deg', (q) => q);
const ctxBy = new Map(ctxRows.map((c) => [c.game_id, c]));
const defRows = await page(sb, 'team_defense', '*', (q) => q.eq('sport', 'mlb'));
const defRows = await pageSafe(sb, 'team_defense', '*', (q) => q.eq('sport', 'mlb'));
const defByTeam = new Map();
for (const d of defRows) defByTeam.set(d.team, d);
const snaps = await page(sb, 'model_snapshots', 'player_key, game_date, archetype, stat',
(q) => q.eq('sport', 'mlb').eq('stat', 'total_bases').not('archetype', 'is', null));
const snaps = await READS.snaps(sb);
const archOf = new Map();
for (const s of snaps) archOf.set(`${s.player_key}|${s.game_date}`, s.archetype);
const led = await page(sb, 'ledger_entries',
'id, game_id, player_key, player_name, line, side, outcome, game_date, p_win, quarantine_reason, env_park_base',
(q) => q.eq('sport', 'mlb').is('user_id', null).eq('stat', 'total_bases')
.in('outcome', ['hit', 'miss']).not('p_win', 'is', null));
const led = await READS.ledger(sb);
const clean = led.filter((r) => !(r.quarantine_reason || '').startsWith('nontakeable_book'));
// Opponent faced, from each hitter's own game log.
@@ -342,4 +359,9 @@ async function main() {
process.exit(0);
}
main().catch((e) => { console.error(e); process.exit(1); });
if (require.main === module) {
main().catch((e) => { console.error(e); process.exit(1); });
}
// Exported so the read-integrity harness measures THE REAL FUNCTION.
module.exports = { READS };