ms-ai-architect/scripts/kb-update/dedup-plain-header.mjs

#!/usr/bin/env node
// dedup-plain-header.mjs — Enhet 3 Op B (2026-07-07, ⊥ R7). Normalize the dual-header block on
// the 4 ms-ai-governance/responsible-ai/ai-act-* files.
//
// Those files carry, below the bold header, an authored PLAIN-TEXT block:
//     Last updated: <date>
//     Status: GA
//     Category: <value>            ← redundant with a bold **Category:** <same value> (R20)
// This driver, per file:
//   1. boldifyPlainField('Last updated')  — plain → **Last updated:**, date PRESERVED byte-exact
//   2. boldifyPlainField('Status')        — plain → **Status:** GA, GA PRESERVED (authored, not
//                                           the derived {Reference|Established Practice} vocab)
//   3. dropRedundantPlainField('Category')— delete the plain Category iff a bold **Category:**
//                                           with the IDENTICAL value proves it redundant
// It NEVER derives a value and NEVER deletes a field it cannot prove redundant (the primitive
// throws on a value mismatch or a missing bold field). A hard per-file invariant is asserted
// BEFORE any write: exactly one line removed net, both target fields now bold with the authored
// value, no plain header field remains, and the body (from the first `## `/`---`) is byte-
// identical. Idempotent: a re-run finds the plain fields gone and is a no-op. Aborts, writing
// nothing, on any drift or invariant breach.
//
// Closes the last 4 of the corpus's Missing-Status and all 4 Missing-English-Last-updated.
//
// Recovery contract: writes are crash-safe (atomicWriteSync tmp+rename — a reader sees the old
// file or the new one, never a partial); an interrupted run is recovered by re-running (idempotent).
//
// Usage:  node scripts/kb-update/dedup-plain-header.mjs [--dry]
import { readFileSync, existsSync, realpathSync } from 'node:fs';
import { join, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { boldifyPlainField, dropRedundantPlainField } from './lib/transform.mjs';
import { atomicWriteSync } from './lib/atomic-write.mjs';

const __dirname = dirname(fileURLToPath(import.meta.url));
const PLUGIN_ROOT = join(__dirname, '..', '..');

// Frozen manifest — the 4 dual-header ai-act-* files (ground truth 2026-07-07: the only
// non-advisor files carrying a plain-text Status/Last updated block).
export const MANIFEST = [
  'skills/ms-ai-governance/references/responsible-ai/ai-act-classification-methodology.md',
  'skills/ms-ai-governance/references/responsible-ai/ai-act-deployer-obligations.md',
  'skills/ms-ai-governance/references/responsible-ai/ai-act-fria-template.md',
  'skills/ms-ai-governance/references/responsible-ai/ai-act-provider-obligations.md',
];

/**
 * The pure Op-B composition: boldify the plain Last updated + Status, then drop the redundant
 * plain Category. Order-independent for these files (distinct labels). Pure — no I/O.
 * @param {string} content
 * @returns {string}
 */
export function dedupPlainHeader(content) {
  let out = boldifyPlainField(content, 'Last updated');
  out = boldifyPlainField(out, 'Status');
  out = dropRedundantPlainField(out, 'Category');
  return out;
}

// Header region = lines above the first `## `/`---` (mirrors transform.mjs headerEndIndex).
function splitHeaderBody(content) {
  const lines = content.split('\n');
  let i = 0;
  for (; i < lines.length; i++) {
    if (/^##\s/.test(lines[i]) || /^---\s*$/.test(lines[i])) break;
  }
  return { header: lines.slice(0, i).join('\n'), body: lines.slice(i).join('\n') };
}

const RE_PLAIN_META = /^(Last updated|Status|Category):\s*\S/im;

// Assert the hard per-file invariant. Throws (aborting the run) on any breach.
function assertInvariant(rel, oldC, newC) {
  const o = oldC.split('\n');
  const n = newC.split('\n');
  if (n.length !== o.length - 1) {
    throw new Error(`ABORT ${rel}: expected exactly one line removed net (was ${o.length}, now ${n.length})`);
  }
  const oldH = splitHeaderBody(oldC);
  const newH = splitHeaderBody(newC);
  if (oldH.body !== newH.body) throw new Error(`ABORT ${rel}: body not byte-identical`);
  if (RE_PLAIN_META.test(newH.header)) throw new Error(`ABORT ${rel}: a plain header field remains`);
  if (!/\*\*Last updated:\*\*\s*\S/.test(newH.header)) throw new Error(`ABORT ${rel}: **Last updated:** missing after dedup`);
  if (!/\*\*Status:\*\*\s*\S/.test(newH.header)) throw new Error(`ABORT ${rel}: **Status:** missing after dedup`);
  if ((newH.header.match(/\*\*Category:\*\*/g) || []).length !== 1) {
    throw new Error(`ABORT ${rel}: expected exactly one bold **Category:** after dedup`);
  }
  // Value preservation: the authored plain values must survive verbatim in the bold lines.
  const oldPlain = (label) => {
    const m = new RegExp('^' + label.replace(/ /g, '\\ ') + ':\\s*(\\S.*?)\\s*$', 'im').exec(oldH.header);
    return m ? m[1] : null;
  };
  for (const label of ['Last updated', 'Status']) {
    const want = oldPlain(label);
    const boldRe = new RegExp('\\*\\*' + label + ':\\*\\*\\s*(\\S.*?)\\s*$', 'im');
    const got = boldRe.exec(newH.header);
    if (!want || !got || got[1] !== want) {
      throw new Error(`ABORT ${rel}: value for '${label}' not preserved (want ${JSON.stringify(want)}, got ${JSON.stringify(got && got[1])})`);
    }
  }
}

function run({ dry }) {
  const planned = [];
  const skipped = [];
  const missing = [];

  for (const rel of MANIFEST) {
    const abs = join(PLUGIN_ROOT, rel);
    if (!existsSync(abs)) { missing.push(rel); continue; }
    const old = readFileSync(abs, 'utf8');
    const out = dedupPlainHeader(old);
    if (out === old) { skipped.push(rel); continue; } // idempotent: already deduped
    assertInvariant(rel, old, out);
    planned.push({ rel, 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 dedup: ${planned.length} | already deduped (skipped): ${skipped.length}`);
  if (dry) {
    console.log('\n(dry run — no writes)');
    for (const p of planned) console.log(`  ~ ${p.rel}`);
    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') });