feat(ms-ai-architect): RX-KB1b — deterministisk footer-dato-avvik-deteksjon + label-whitelist i corpus-audit (flag-to-human, 3 flagg) [skip-docs]

scripts/kb-update/audit-corpus-headers.mjs

@@ -53,6 +53,49 @@ const RE_CLEAN_DATE = /^\d{4}-\d{2}(-\d{2})?$/;
 // pipe.mjs removes the current 87; this detects any reappearance within the non-advisor scope).
 const RE_PLAIN_VERIFIED = /(?:^|[^*])Verified:/m;
 
+// ── RX-KB1b: footer date-conflict + label-whitelist ────────────────────────
+// A file that carries a header **Last updated:** date AND a norsk footer date under a
+// last-updated-EQUIVALENT label ("Sist oppdatert") with a different value contradicts
+// itself — it asserts two distinct last-updated dates. That is the only norsk footer
+// label that can conflict with the header. LABEL WHITELIST: "Verifisert"/"Sist
+// verifisert" record an INDEPENDENT axis (when content was last checked against source,
+// not when the file was edited), so a differing date there is expected and is never a
+// conflict. Detection is read-only and flag-to-human: the audit reports, the operator
+// resolves per file against git/source (aldri-auto-fiks — a footer date can be right and
+// the header stale, or vice versa; only a human can adjudicate which).
+
+// Header **Last updated:** DATE — captured value (RE_LAST_UPDATED above only tests presence).
+const RE_HEADER_LAST_UPDATED_DATE = /\*\*Last updated:\*\*\s*(\d{4}-\d{2}(?:-\d{2})?)/i;
+
+// Any norsk footer meta-line carrying a date: "**Label:** DATE", "*Label: DATE", "Label: DATE".
+// A valid month (01-12) is required, which also excludes template placeholders ([Dato],
+// YYYY-MM-DD — they never match \d{4}-(0[1-9]|1[0-2])). Whole-file scan: footers live well
+// outside the 500-byte header window. Group 1 = label, group 2 = date.
+const RE_FOOTER_META =
+  /(?:^|\n)[ \t>*_-]*\*{0,2}\s*(Sist oppdatert|Sist verifisert|Verifisert)\s*:?\**\s*(\d{4}-(?:0[1-9]|1[0-2])(?:-\d{2})?)/gi;
+
+// Only this label is last-updated-equivalent (conflict-bearing). Everything else the
+// RE_FOOTER_META captures ("sist verifisert", "verifisert") is on the whitelist.
+const FOOTER_LABEL_LAST_UPDATED = 'sist oppdatert';
+
+/**
+ * Footer date-conflict for one file's full content. Returns null when there is no header
+ * Last-updated date, no last-updated-equivalent footer, or all such footers agree on the
+ * YYYY-MM prefix. Otherwise returns the header date and the conflicting footer date(s). Pure.
+ */
+function detectFooterConflict(content, headerLastUpdated) {
+  if (!headerLastUpdated) return null;
+  const footerDates = [];
+  for (const m of content.matchAll(RE_FOOTER_META)) {
+    if (m[1].toLowerCase() === FOOTER_LABEL_LAST_UPDATED) footerDates.push(m[2]);
+  }
+  if (footerDates.length === 0) return null;
+  const headerPrefix = headerLastUpdated.slice(0, 7);
+  const conflicting = footerDates.filter((d) => d.slice(0, 7) !== headerPrefix);
+  if (conflicting.length === 0) return null;
+  return { headerLastUpdated, footerDates: conflicting };
+}
+
 /** Audit a single file's content. Pure. */
 function auditContent(content) {
   const head = content.slice(0, HEADER_REGION_BYTES);
@@ -76,6 +119,9 @@ function auditContent(content) {
   else if (/\*\*Category:\*\*/i.test(head)) dialect = 'category';
   else if (/\*\*Kategori:\*\*/i.test(head)) dialect = 'kategori';
 
+  const headerLuMatch = head.match(RE_HEADER_LAST_UPDATED_DATE);
+  const footerConflict = detectFooterConflict(content, headerLuMatch ? headerLuMatch[1] : null);
+
   return {
     title: RE_TITLE.test(content),
     status: RE_STATUS.test(content),
@@ -83,6 +129,7 @@ function auditContent(content) {
     dialect,
     verified,
     plainVerified: RE_PLAIN_VERIFIED.test(head),
+    footerConflict,
   };
 }
 
@@ -105,6 +152,7 @@ export function auditHeaders(paths, readFile = (p) => readFileSync(p, 'utf8')) {
     verifiedPipe: 0,
     verifiedDuplicate: 0,
     plainVerifiedPipe: 0,
+    footerConflicts: 0,
     missingTitle: 0,
     missingStatus: 0,
     missingEnglishLastUpdated: 0,
@@ -131,6 +179,7 @@ export function auditHeaders(paths, readFile = (p) => readFileSync(p, 'utf8')) {
       if (r.verified.duplicateWithinHeaderRegion) aggregate.verifiedDuplicate++;
     }
     if (r.plainVerified) aggregate.plainVerifiedPipe++;
+    if (r.footerConflict) aggregate.footerConflicts++;
     if (!r.title) aggregate.missingTitle++;
     if (!r.status) aggregate.missingStatus++;
     if (!r.lastUpdatedEnglish) aggregate.missingEnglishLastUpdated++;
@@ -184,6 +233,11 @@ function main(argv) {
     console.log(`  Verified header present: ${a.verifiedPresent} (date: ${a.verifiedDate}, stale non-date: ${a.verifiedNonDate})`);
     console.log(`  Verified pipe rows: ${a.verifiedPipe}, duplicates within 500B: ${a.verifiedDuplicate}`);
     console.log(`  Plain (non-bold) Verified tails (RX-KB1 poison class): ${a.plainVerifiedPipe}`);
+    console.log(`  Footer "Sist oppdatert" ≠ header Last updated (RX-KB1b, flag-to-human): ${a.footerConflicts}`);
+    for (const [abs, r] of Object.entries(report.files)) {
+      if (!r.footerConflict) continue;
+      console.log(`    FLAG ${relative(PLUGIN_ROOT, abs)} — header ${r.footerConflict.headerLastUpdated} vs footer ${r.footerConflict.footerDates.join(', ')}`);
+    }
     console.log(`  Missing English Last updated: ${a.missingEnglishLastUpdated}`);
     console.log(`  Missing Status: ${a.missingStatus}`);
     console.log(`  Missing title: ${a.missingTitle}`);