ms-ai-architect/scripts/kb-update/backfill-last-updated.mjs

104 lines
5.6 KiB
JavaScript

#!/usr/bin/env node
// Backfill **Last updated:** on the ONE advisor reference file that carries no date label at
// all — decision-trees.md (Enhet 4, ⊥ R7). Ground truth (2026-07-16): it is the only
// skills/**/*.md whose header lacks an English **Last updated:**. Sister driver to
// backfill-status.mjs / backfill-category.mjs — same manifest-driven shape over the tested
// insertMetaField primitive.
//
// Value derivation — git "content-commit" heuristic (NEVER "today"):
// The date is the authored date of the last commit that changed decision-trees.md's BODY,
// EXCLUDING the R20/R21 metadata passes (which inserted only a **Category:** / **Status:**
// header line — no body change). Measured 2026-07-16 against `git log -- <file>`:
// 5a0e8d7 2026-07-06 R21 Status-backfill — header-only insert → metadata → EXCLUDED
// a583599 2026-07-06 R20 Category-backfill — header-only insert → metadata → EXCLUDED
// 03d596e 2026-06-23 KB-refresh Foundry namesweep — 3 BODY table rows changed → CONTENT ✓
// baa2d02 2026-04-08 file birth (plugin add)
// ⇒ last content commit = 03d596e (2026-06-23). Full YYYY-MM-DD dialect (dominant among the
// architecture/ siblings). The date is FROZEN below with this provenance; re-measure against
// git before re-running on a mutated history. "today" (MEASURED_TODAY) is asserted-against so
// a naive last-commit / metadata-pass date can never leak in.
//
// This applier writes ONLY the derived bold **Last updated:** line — reuses insertMetaField,
// with a hard per-file invariant asserted BEFORE any write (exactly one line inserted, it is the
// Last updated line with the frozen date byte-exact, body byte-identical). Idempotent: a file
// already carrying **Last updated:** in its header window is skipped. atomicWriteSync
// (crash-safe: tmp+rename — a reader sees the old file or the new one, never a partial; an
// interrupted run recovers by re-running). Aborts and writes nothing on any drift or breach.
//
// Usage: node scripts/kb-update/backfill-last-updated.mjs [--dry]
import { readFileSync, existsSync, realpathSync } from 'node:fs';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { insertMetaField } from './lib/transform.mjs';
import { atomicWriteSync } from './lib/atomic-write.mjs';
const __dirname = dirname(fileURLToPath(import.meta.url));
const PLUGIN_ROOT = join(__dirname, '..', '..');
// The session date the manifest was measured on. A manifest date equal to this means the
// heuristic fell back to a metadata-pass / naive last-commit date — the never-today guard rejects it.
export const MEASURED_TODAY = '2026-07-16';
// Frozen manifest — the single dateless advisor file + its git-content-commit date (03d596e).
// Value is a YYYY-MM-DD string; provenance in the header comment above.
export const MANIFEST = [
{ path: 'skills/ms-ai-advisor/references/architecture/decision-trees.md', lastUpdated: '2026-06-23' },
];
const RE_ISO_DATE = /^\d{4}-\d{2}-\d{2}$/;
// Presence of a dated **Last updated:** in the header window — mirrors audit-corpus-headers.mjs
// RE_LAST_UPDATED (the guard the header audit reads), used here for idempotency.
const RE_LAST_UPDATED = /\*\*Last updated:\*\*\s*[\d-]+/i;
function run({ dry }) {
const planned = [];
const skipped = [];
const missing = [];
for (const { path: rel, lastUpdated } of MANIFEST) {
if (!RE_ISO_DATE.test(lastUpdated)) throw new Error(`ABORT ${rel}: date '${lastUpdated}' not YYYY-MM-DD`);
if (lastUpdated === MEASURED_TODAY) throw new Error(`ABORT ${rel}: date equals measured 'today' — never-today guard`);
const abs = join(PLUGIN_ROOT, rel);
if (!existsSync(abs)) { missing.push(rel); continue; }
const old = readFileSync(abs, 'utf8');
if (RE_LAST_UPDATED.test(old.slice(0, 500))) { skipped.push(rel); continue; } // idempotent
const out = insertMetaField(old, 'Last updated', lastUpdated);
// Hard invariant: exactly one line inserted (the Last updated line), body byte-identical.
const o = old.split('\n');
const n = out.split('\n');
if (n.length !== o.length + 1) throw new Error(`ABORT ${rel}: not exactly one line inserted`);
let d = 0;
while (d < o.length && o[d] === n[d]) d++;
if (n[d] !== `**Last updated:** ${lastUpdated}`) throw new Error(`ABORT ${rel}: inserted line mismatch → ${JSON.stringify(n[d])}`);
if (o.slice(d).join('\n') !== n.slice(d + 1).join('\n')) throw new Error(`ABORT ${rel}: body not byte-identical below the insertion`);
planned.push({ rel, lastUpdated, out });
}
if (missing.length) {
console.error(`ABORT — ${missing.length} manifest target(s) not found (corpus drift):`);
missing.forEach((m) => console.error(' ' + m));
process.exit(1);
}
if (planned.length + skipped.length !== MANIFEST.length) {
throw new Error(`ABORT — accounted ${planned.length + skipped.length} ≠ manifest ${MANIFEST.length}`);
}
console.log(`Manifest: ${MANIFEST.length} | to insert: ${planned.length} | already present (skipped): ${skipped.length}`);
if (dry) {
console.log('\n(dry run — no writes)');
for (const p of planned) console.log(` + ${p.rel} → **Last updated:** ${p.lastUpdated}`);
return;
}
for (const p of planned) atomicWriteSync(join(PLUGIN_ROOT, p.rel), p.out);
console.log(`\nWrote ${planned.length} files.`);
}
const isMain = (() => {
try {
return realpathSync(process.argv[1]) === realpathSync(fileURLToPath(import.meta.url));
} catch {
return false;
}
})();
if (isMain) run({ dry: process.argv.includes('--dry') });