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

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 Both hits PROVES are withdrawn: they were drawn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withdrawn. 4,772 tests / 371 suites green, web build exit 0, read-integrity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>

scripts/calibrate-hits.js

@@ -29,6 +29,8 @@
 require('dotenv').config();
 const { createClient } = require('@supabase/supabase-js');
 const cal = require('../src/services/model/calibration');
+const { paginate } = require('../src/utils/safePaginate');
+const { uniqueKeyFor } = require('../src/utils/tableKeys');
 
 const SB_URL = process.env.SUPABASE_URL;
 const SB_KEY = process.env.SUPABASE_SERVICE_ROLE_KEY || process.env.SUPABASE_SERVICE_KEY;
@@ -37,19 +39,24 @@ const PAGE = 1000;
 
 const r3 = (v) => (v == null || !Number.isFinite(v) ? null : Math.round(v * 1000) / 1000);
 
-async function page(sb, apply) {
-  const out = [];
-  for (let from = 0; ; from += PAGE) {
-    const { data, error } = await apply(sb.from('ledger_entries')
-      .select('p_win, outcome, game_date, quarantine_reason')).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;
+// ── THE SAFE WALK (Fix A2b) ───────────────────────────────────────────────
+// This walked pages with no ORDER BY and measured 24.7% corrupt on production —
+// 616 of 2,490 rows returned twice, an equal share never returned — while
+// `rows.length` matched the server count exactly. It fits the calibration
+// reliability curve, so a fifth of the history was double-weighted and another
+// fifth absent from every bin.
+async function pageSafe(sb, apply) {
+  return paginate(() => apply(sb.from('ledger_entries')
+    .select('id, p_win, outcome, game_date, quarantine_reason')),
+  { key: uniqueKeyFor('ledger_entries'), pageSize: PAGE, label: 'calibrate-hits' });
 }
 
+/** THE MEASURED READ — main() and the harness call the same function. */
+const READS = {
+  ledger: (sb) => pageSafe(sb, (q) => q.eq('sport', 'mlb').is('user_id', null).eq('stat', 'hits')
+    .in('outcome', ['hit', 'miss']).not('p_win', 'is', null)),
+};
+
 /** Reliability rendered per bin with n — the only honest way to read this. */
 function curve(rows, label) {
   return cal.reliability(rows, 10)
@@ -67,8 +74,7 @@ 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 raw = await page(sb, (q) => q.eq('sport', 'mlb').is('user_id', null)
-    .eq('stat', 'hits').in('outcome', ['hit', 'miss']).not('p_win', 'is', null));
+  const raw = await READS.ledger(sb);
   const all = raw
     .filter((r) => !(r.quarantine_reason || '').startsWith('nontakeable_book'))
     .map((r) => ({ p: Number(r.p_win), won: r.outcome === 'hit' ? 1 : 0, d: String(r.game_date) }));
@@ -133,4 +139,10 @@ 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 };
+