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

// tests/kb-update/test-dedup-plain-header.test.mjs
// TDD for Enhet 3 Op B — the dual-header plain→bold dedup on the 4 ms-ai-governance
// ai-act-* files. Those files carry an authored, PLAIN-TEXT block
//     Last updated: <date>
//     Status: GA
//     Category: <value>            ← redundant: a bold **Category:** <same value> already exists
// (R20 inserted the bold Category; the plain block is the original dual header). This is NOT a
// derive-a-value backfill (backfill-status.mjs owns that) — the authored values are PRESERVED
// byte-exact; only their label decoration is normalized to bold, and the provably-redundant
// plain Category line is removed. Two new pure primitives + a pure composition are pinned here.

import { test } from 'node:test';
import assert from 'node:assert/strict';
import { boldifyPlainField, dropRedundantPlainField } from '../../scripts/kb-update/lib/transform.mjs';
import { dedupPlainHeader, MANIFEST } from '../../scripts/kb-update/dedup-plain-header.mjs';

// An ai-act-shaped fixture: bold Type+Category (Category from R20), then the plain block,
// then a body that itself mentions "Status:" in prose (must never be touched).
const FIXTURE = [
  '# EU AI Act — Systematisk Klassifiseringsmetodikk',
  '**Type:** regulatory',
  '**Category:** Responsible AI & Governance',
  '',
  'Last updated: 2026-06-18',
  'Status: GA',
  'Category: Responsible AI & Governance',
  '',
  '---',
  '',
  '## Innhold',
  '',
  'A body paragraph that says Status: draft in prose — must be left alone.',
  '',
].join('\n');

// ── boldifyPlainField ────────────────────────────────────────────────────────
test('boldifyPlainField: plain header field → bold, value preserved byte-exact', () => {
  const out = boldifyPlainField(FIXTURE, 'Last updated');
  assert.ok(out.includes('**Last updated:** 2026-06-18'), 'bold line present');
  assert.ok(!/^Last updated:/m.test(out.split('\n---')[0]), 'plain header line gone');
});

test('boldifyPlainField: idempotent — a bold field already present is unchanged', () => {
  const once = boldifyPlainField(FIXTURE, 'Status');
  const twice = boldifyPlainField(once, 'Status');
  assert.equal(twice, once);
});

test('boldifyPlainField: no plain field in header → unchanged', () => {
  assert.equal(boldifyPlainField(FIXTURE, 'Nonexistent'), FIXTURE);
});

test('boldifyPlainField: never touches a match in the body (below the header region)', () => {
  const out = boldifyPlainField(FIXTURE, 'Status');
  assert.ok(out.includes('says Status: draft in prose'), 'body prose untouched');
  // exactly one bold Status inserted (the header one), body "Status:" not bolded
  assert.equal((out.match(/\*\*Status:\*\*/g) || []).length, 1);
});

test('boldifyPlainField: body byte-identical (only the header line changes)', () => {
  const out = boldifyPlainField(FIXTURE, 'Status');
  const bodyOf = (c) => c.slice(c.indexOf('\n---'));
  assert.equal(bodyOf(out), bodyOf(FIXTURE));
});

// ── dropRedundantPlainField ──────────────────────────────────────────────────
test('dropRedundantPlainField: drops the plain line when a bold field with the same value exists', () => {
  const out = dropRedundantPlainField(FIXTURE, 'Category');
  const header = out.split('\n---')[0];
  assert.ok(/\*\*Category:\*\* Responsible AI & Governance/.test(header), 'bold Category kept');
  assert.ok(!/^Category:/m.test(header), 'plain Category removed');
  assert.equal(out.split('\n').length, FIXTURE.split('\n').length - 1, 'exactly one line removed');
});

test('dropRedundantPlainField: throws when plain value ≠ bold value (not redundant, human decision)', () => {
  const mismatched = FIXTURE.replace('Category: Responsible AI & Governance', 'Category: Something Else');
  assert.throws(() => dropRedundantPlainField(mismatched, 'Category'), /not redundant|≠/);
});

test('dropRedundantPlainField: throws when no bold field exists to prove redundancy', () => {
  const noBold = FIXTURE.replace('**Category:** Responsible AI & Governance\n', '');
  assert.throws(() => dropRedundantPlainField(noBold, 'Category'), /no bold/i);
});

test('dropRedundantPlainField: no-op when the plain line is absent (idempotent)', () => {
  const once = dropRedundantPlainField(FIXTURE, 'Category');
  assert.equal(dropRedundantPlainField(once, 'Category'), once);
});

// ── dedupPlainHeader (full composition) ──────────────────────────────────────
test('dedupPlainHeader: boldifies Last updated + Status, drops redundant plain Category', () => {
  const out = dedupPlainHeader(FIXTURE);
  const header = out.split('\n---')[0];
  assert.ok(/\*\*Last updated:\*\* 2026-06-18/.test(header), 'Last updated bolded, value preserved');
  assert.ok(/\*\*Status:\*\* GA/.test(header), 'Status bolded, GA preserved');
  assert.equal((header.match(/\*\*Category:\*\*/g) || []).length, 1, 'exactly one bold Category');
  assert.ok(!/^(Last updated|Status|Category):/m.test(header), 'no plain header fields remain');
});

test('dedupPlainHeader: net one line removed, body byte-identical', () => {
  const out = dedupPlainHeader(FIXTURE);
  assert.equal(out.split('\n').length, FIXTURE.split('\n').length - 1);
  const bodyOf = (c) => c.slice(c.indexOf('\n---'));
  assert.equal(bodyOf(out), bodyOf(FIXTURE));
});

test('dedupPlainHeader: idempotent — a second pass is a no-op', () => {
  const once = dedupPlainHeader(FIXTURE);
  assert.equal(dedupPlainHeader(once), once);
});

// ── MANIFEST ─────────────────────────────────────────────────────────────────
test('MANIFEST: exactly the 4 dual-header ai-act-* files', () => {
  assert.equal(MANIFEST.length, 4);
  assert.equal(new Set(MANIFEST).size, 4, 'no duplicates');
  const expected = [
    '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',
  ];
  for (const p of expected) assert.ok(MANIFEST.includes(p), `missing ${p}`);
});