#!/usr/bin/env node
// check-cosmo-gate.mjs — the RATIFIED R13 persona gate (operator 2026-09-12, alt. A).
//
// Replaces the roadmap's `grep -rl "Cosmo" skills/*/references | wc -l -> 0`, which was
// measured false twice over (it would delete 451 Azure Cosmos DB occurrences, and it is
// unreachable under a heading-only scope because 132 persona occurrences live in prose,
// tables and dialogue). Full derivation: lib/cosmo-persona.mjs header.
//
// THREE CLAUSES
//   G1  persona occurrences on markdown heading lines in the reference corpus = 0
//   G2  every fragment link resolves to a real heading slug, except the anchors on the
//       committed exemption list (pre-existing, not caused by R13)
//   G3  product occurrences unchanged from the committed baseline, and each product-only
//       file still carries zero persona
//
// USAGE
//   node scripts/kb-update/check-cosmo-gate.mjs                  # check (exit 1 on fail)
//   node scripts/kb-update/check-cosmo-gate.mjs --emit-baseline  # write the baseline JSON
//   node scripts/kb-update/check-cosmo-gate.mjs --validate-net   # prove the net both ways
//
// --validate-net is not decoration. A gate whose null result has never been forced to
// the other answer is not a measurement (memory decision-gate-must-be-validated-both-
// ways): it injects a known-positive persona heading into a copy of a real corpus file
// and asserts G1 FAILS, then asserts the known-negative product-only files PASS.
import { readFileSync, writeFileSync, existsSync } from 'node:fs';
import { join, dirname, relative } from 'node:path';
import { fileURLToPath } from 'node:url';
import { globSync } from 'node:fs';
import {
  classifyCosmo, findDeadAnchors, classifyPersonaSites, neutralizeLabels,
} from './lib/cosmo-persona.mjs';

const __dirname = dirname(fileURLToPath(import.meta.url));
const PLUGIN_ROOT = join(__dirname, '..', '..');
const BASELINE_PATH = join(__dirname, 'data', 'cosmo-gate-baseline.json');
// R13b lives in its OWN baseline file. The R13 one records pre-transform reference points
// (personaHeadings 401) that regenerating would destroy — never build over a reference-point
// artefact, so R13b adds a file rather than re-emitting that one.
const LABELS_BASELINE_PATH = join(__dirname, 'data', 'cosmo-labels-baseline.json');

/** Every reference file in the corpus, as repo-relative paths, sorted. */
function refFiles() {
  return globSync('skills/*/references/**/*.md', { cwd: PLUGIN_ROOT }).sort();
}

/** Measure the whole corpus: persona buckets, product total, per-file detail. */
function measure() {
  const files = refFiles();
  const totals = { heading: 0, toc: 0, prose: 0, product: 0 };
  const headingFiles = new Set();
  const perFile = {};
  const deadAnchors = [];
  for (const rel of files) {
    const src = readFileSync(join(PLUGIN_ROOT, rel), 'utf8');
    const c = classifyCosmo(src);
    totals.heading += c.persona.heading;
    totals.toc += c.persona.toc;
    totals.prose += c.persona.prose;
    totals.product += c.product;
    if (c.persona.heading > 0) headingFiles.add(rel);
    perFile[rel] = { persona: c.personaTotal, product: c.product };
    for (const d of findDeadAnchors(src)) deadAnchors.push(`${rel}#${d.anchor}`);
  }
  return { files, totals, headingFiles: [...headingFiles].sort(), perFile, deadAnchors };
}

/** Files carrying Azure Cosmos DB but no persona at all — must stay untouched. */
function productOnlyFiles(m) {
  return m.files.filter((f) => m.perFile[f].product > 0 && m.perFile[f].persona === 0);
}

function emitBaseline() {
  const m = measure();
  const pof = productOnlyFiles(m);
  const baseline = {
    _comment: 'Ratified R13 persona-gate baseline. Measured before the heading transform; '
      + 'G1 drives personaHeadings to 0, G2 and G3 must not move. Regenerate ONLY with a '
      + 'ratified scope change — a silently moved baseline is a gate that proves nothing.',
    measured: new Date().toISOString().slice(0, 10),
    refFiles: m.files.length,
    personaHeadings: m.totals.heading,
    personaHeadingFiles: m.headingFiles.length,
    personaTocOccurrences: m.totals.toc,
    personaProseOccurrences: m.totals.prose,
    productOccurrences: m.totals.product,
    productOnlyFiles: pof,
    productOnlyFileCounts: Object.fromEntries(pof.map((f) => [f, m.perFile[f].product])),
    deadAnchorsExempt: m.deadAnchors,
  };
  writeFileSync(BASELINE_PATH, `${JSON.stringify(baseline, null, 2)}\n`, 'utf8');
  console.log(`baseline skrevet: ${relative(PLUGIN_ROOT, BASELINE_PATH)}`);
  console.log(JSON.stringify(baseline, null, 2));
}

function check() {
  if (!existsSync(BASELINE_PATH)) {
    console.error('FEIL: ingen baseline. Kjoer --emit-baseline foer transformen.');
    process.exit(2);
  }
  const b = JSON.parse(readFileSync(BASELINE_PATH, 'utf8'));
  const m = measure();
  const fails = [];

  // --- G1: no persona left on any heading line ---
  if (m.totals.heading !== 0) {
    fails.push(`G1: ${m.totals.heading} persona-forekomster staar fortsatt paa heading-linjer `
      + `i ${m.headingFiles.length} filer (baseline var ${b.personaHeadings})`);
  }

  // --- G2: no dead fragment links beyond the committed exemptions ---
  const exempt = new Set(b.deadAnchorsExempt);
  const newDead = m.deadAnchors.filter((d) => !exempt.has(d));
  if (newDead.length) {
    fails.push(`G2: ${newDead.length} NYE doede fragmentlenker: ${newDead.slice(0, 10).join(', ')}`);
  }
  const healed = b.deadAnchorsExempt.filter((d) => !m.deadAnchors.includes(d));

  // --- G3: product untouched ---
  if (m.totals.product !== b.productOccurrences) {
    fails.push(`G3: produkt-forekomster ${m.totals.product} != baseline ${b.productOccurrences} `
      + `(differanse ${m.totals.product - b.productOccurrences})`);
  }
  for (const [f, n] of Object.entries(b.productOnlyFileCounts)) {
    const now = m.perFile[f];
    if (!now) { fails.push(`G3: kun-produkt-fila ${f} finnes ikke lenger`); continue; }
    if (now.product !== n) fails.push(`G3: ${f} produkt ${now.product} != baseline ${n}`);
    if (now.persona !== 0) fails.push(`G3: ${f} har faatt ${now.persona} persona-forekomst(er)`);
  }

  const labelLines = checkLabels(fails);

  console.log('=== R13 persona-gate (ratifisert 2026-09-12, alt. A) ===');
  console.log(`ref-filer                        : ${m.files.length} (baseline ${b.refFiles})`);
  console.log(`G1 persona paa heading-linjer     : ${m.totals.heading}  (baseline ${b.personaHeadings})`);
  console.log(`   persona i TOC-linjer           : ${m.totals.toc}  (baseline ${b.personaTocOccurrences})`);
  console.log(`   persona i proesa/tabell        : ${m.totals.prose}  (baseline ${b.personaProseOccurrences}) `
    + '— UTENFOR R13-scope, bokfoert til R13b/R14');
  console.log(`G2 doede fragmentlenker           : ${m.deadAnchors.length} `
    + `(${exempt.size} unntatt, ${newDead.length} nye, ${healed.length} forsvunnet)`);
  console.log(`G3 produkt-forekomster            : ${m.totals.product}  (baseline ${b.productOccurrences})`);
  console.log(`   kun-produkt-filer urørt        : ${Object.keys(b.productOnlyFileCounts).length}`);
  console.log('--- R13b etikett/celle-gate (ratifisert 2026-09-15, alt. A) ---');
  for (const l of labelLines) console.log(l);
  if (fails.length) {
    console.log('\nGATE FAILED');
    for (const f of fails) console.log(`  x ${f}`);
    process.exit(1);
  }
  console.log('\nGATE PASSED');
}

/** Force the gate to the other answer — a null result nobody could falsify is not one. */
function validateNet() {
  const m = measure();
  let bad = 0;

  // Known-positive: inject a persona heading into a real corpus file's content and
  // assert the classifier sees it. If this cannot fail the gate, the gate is blind.
  const victim = m.files[0];
  const injected = `${readFileSync(join(PLUGIN_ROOT, victim), 'utf8')}\n## For Cosmo\n`;
  const ic = classifyCosmo(injected);
  const base = classifyCosmo(readFileSync(join(PLUGIN_ROOT, victim), 'utf8'));
  if (ic.persona.heading !== base.persona.heading + 1) {
    console.log(`x KJENT-POSITIV: injisert "## For Cosmo" ble IKKE sett `
      + `(${base.persona.heading} -> ${ic.persona.heading})`); bad++;
  } else {
    console.log(`ok KJENT-POSITIV: injisert "## For Cosmo" felte G1 `
      + `(${base.persona.heading} -> ${ic.persona.heading}) i ${victim}`);
  }

  // Known-positive #2: the Norwegian genitive must also be caught, since it is the
  // case the letter-s heuristic gets wrong in BOTH directions.
  const gen = classifyCosmo('### Cosmos tonalitet\n');
  if (gen.persona.heading !== 1) { console.log('x KJENT-POSITIV: genitiv "### Cosmos tonalitet" ikke sett'); bad++; }
  else console.log('ok KJENT-POSITIV: genitiv "### Cosmos tonalitet" felte G1');

  // Known-negative: a product heading must NOT trip the gate.
  const prod = classifyCosmo('### Azure Cosmos DB for GraphRAG\n');
  if (prod.personaTotal !== 0 || prod.product !== 1) {
    console.log(`x KJENT-NEGATIV: produkt-heading feilklassifisert `
      + `(persona ${prod.personaTotal}, produkt ${prod.product})`); bad++;
  } else console.log('ok KJENT-NEGATIV: "### Azure Cosmos DB for GraphRAG" gir 0 persona, 1 produkt');

  // Known-negative #2: the real product-only files must be clean of persona.
  for (const f of productOnlyFiles(m)) {
    const c = classifyCosmo(readFileSync(join(PLUGIN_ROOT, f), 'utf8'));
    if (c.personaTotal !== 0) { console.log(`x KJENT-NEGATIV: ${f} klassifisert med persona`); bad++; }
    else console.log(`ok KJENT-NEGATIV: ${f} — 0 persona, ${c.product} produkt`);
  }

  console.log('--- R13b klausulene, begge veier ---');
  bad += validateLabelsNet();

  console.log(bad === 0 ? '\nNETTET VALIDERT BEGGE VEIER' : `\nNETT-VALIDERING FEILET (${bad})`);
  process.exit(bad === 0 ? 0 : 1);
}


// ================================ R13b: the three decomposed clauses ========================
//
//   R1  REFERENT     — has the search string more than one referent? Zero persona in
//                      MECHANICAL bold labels and table cells, while product stays untouched.
//   R2  REKKEVIDDE   — does the operation reach every occurrence it claims? An in-class site
//                      in neither ratified table must be REPORTED, never silently skipped.
//   R3  HVA SOM STAAR — the 70 editorial occurrences unchanged in count AND content, product
//                      451 unchanged, R13's headings and TOC still zero (not regraded).
//
// Each clause carries BOTH a known-positive and a known-negative in --validate-net. A gate
// never forced to the other answer is not a measurement.

/** Per-corpus measurement of the R13b sites. */
function measureLabels() {
  const files = refFiles();
  const t = {
    mechLabel: 0, mechCell: 0, edLabel: 0, edCell: 0, prose: 0, product: 0,
    unmapped: [], mechFiles: [], unreachable: [],
  };
  for (const rel of files) {
    const src = readFileSync(join(PLUGIN_ROOT, rel), 'utf8');
    const s = classifyPersonaSites(src);
    t.mechLabel += s.label.mechanical;
    t.mechCell += s.table.mechanical;
    t.edLabel += s.label.editorial;
    t.edCell += s.table.editorial;
    for (const u of s.unmapped) t.unmapped.push(`${rel}: ${u}`);
    const c = classifyCosmo(src);
    t.prose += c.persona.prose;
    t.product += c.product;
    // R2: a site the tables know but the transform does not actually rewrite is out of reach.
    if (s.label.mechanical + s.table.mechanical > 0) {
      t.mechFiles.push(rel);
      let after;
      try { after = neutralizeLabels(src, { relPath: rel }).content; } catch (e) {
        t.unreachable.push(`${rel}: ${e.message}`); continue;
      }
      const a = classifyPersonaSites(after);
      const left = a.label.mechanical + a.table.mechanical;
      if (left) t.unreachable.push(`${rel}: ${left} site(r) utenfor transformens rekkevidde`);
    }
  }
  return t;
}

function emitLabelsBaseline() {
  const t = measureLabels();
  const baseline = {
    _comment: 'Ratified R13b label/cell baseline (operator 2026-09-15, alt. A). Measured BEFORE '
      + 'the label transform. R1 drives mechanical -> 0; R3 pins editorial and product as '
      + 'immovable. The 85/47 split the dispatching order carried was re-measured to 62/70 — '
      + 'the classifier was wrong, not the count. Regenerate ONLY on a ratified scope change.',
    measured: new Date().toISOString().slice(0, 10),
    refFiles: refFiles().length,
    mechanicalLabels: t.mechLabel,
    mechanicalCells: t.mechCell,
    mechanicalTotal: t.mechLabel + t.mechCell,
    mechanicalFiles: t.mechFiles.length,
    editorialLabels: t.edLabel,
    editorialCells: t.edCell,
    editorialTotal: 70,
    personaProseBefore: t.prose,
    personaProseAfter: t.prose - (t.mechLabel + t.mechCell),
    productOccurrences: t.product,
    mixedLines: [
      'skills/ms-ai-advisor/references/prompt-engineering/reasoning-models-o1-o3-optimization.md:549',
    ],
  };
  writeFileSync(LABELS_BASELINE_PATH, `${JSON.stringify(baseline, null, 2)}\n`, 'utf8');
  console.log(`R13b-baseline skrevet: ${relative(PLUGIN_ROOT, LABELS_BASELINE_PATH)}`);
  console.log(JSON.stringify(baseline, null, 2));
}

/** Evaluate R1-R3, pushing onto the shared fails list; returns the printable lines. */
function checkLabels(fails) {
  if (!existsSync(LABELS_BASELINE_PATH)) return ['(R13b: ingen baseline — klausulene hoppes over)'];
  const b = JSON.parse(readFileSync(LABELS_BASELINE_PATH, 'utf8'));
  const t = measureLabels();
  const mech = t.mechLabel + t.mechCell;

  // --- R1 REFERENT ---
  if (mech !== 0) {
    fails.push(`R1: ${mech} mekanisk(e) persona-site(r) staar igjen `
      + `(${t.mechLabel} etiketter, ${t.mechCell} celler; baseline ${b.mechanicalTotal})`);
  }
  if (t.product !== b.productOccurrences) {
    fails.push(`R1/R3: produkt ${t.product} != baseline ${b.productOccurrences}`);
  }

  // --- R2 REKKEVIDDE ---
  if (t.unmapped.length) {
    fails.push(`R2: ${t.unmapped.length} persona-site(r) i INGEN ratifisert tabell — `
      + `umaalt variant: ${t.unmapped.slice(0, 5).join(' | ')}`);
  }
  if (t.unreachable.length) {
    fails.push(`R2: ${t.unreachable.length} site(r) utenfor transformens rekkevidde: `
      + `${t.unreachable.slice(0, 5).join(' | ')}`);
  }

  // --- R3 HVA SOM SKAL STAA ---
  if (t.edLabel !== b.editorialLabels || t.edCell !== b.editorialCells) {
    fails.push(`R3: REDAKSJONELT scope roert — etiketter ${t.edLabel} `
      + `(baseline ${b.editorialLabels}), celler ${t.edCell} (baseline ${b.editorialCells})`);
  }
  if (t.prose !== b.personaProseAfter && t.prose !== b.personaProseBefore) {
    fails.push(`R3: persona i proesa/tabell ${t.prose} er hverken foer-verdien `
      + `${b.personaProseBefore} eller etter-verdien ${b.personaProseAfter}`);
  }

  const done = mech === 0;
  return [
    `R1 mekaniske sites (etikett+celle) : ${mech}  (baseline ${b.mechanicalTotal} `
      + `= ${b.mechanicalLabels}+${b.mechanicalCells} i ${b.mechanicalFiles} filer)`,
    `R2 umaalte varianter / utenfor rekkevidde : ${t.unmapped.length} / ${t.unreachable.length}`,
    `R3 redaksjonelt holdt for R14      : ${t.edLabel} etiketter + ${t.edCell} celler `
      + `(baseline ${b.editorialLabels} + ${b.editorialCells})`,
    `   persona i proesa/tabell          : ${t.prose}  (${b.personaProseBefore} foer R13b, `
      + `${b.personaProseAfter} etter)${done ? ' — R13b UTFOERT' : ' — R13b IKKE kjoert'}`,
  ];
}

/** Force each R13b clause to the other answer. */
function validateLabelsNet() {
  let bad = 0;
  const ok = (msg) => console.log(`ok ${msg}`);
  const no = (msg) => { console.log(`x ${msg}`); bad++; };

  // R1 known-positive — BOTH forms, because the genitive table variant is precisely what a
  // bold-only net misses.
  const victim = refFiles()[0];
  const base = readFileSync(join(PLUGIN_ROOT, victim), 'utf8');
  const inj = classifyPersonaSites(`${base}\n**For Cosmo:** x\n\n| A | Cosmos råd |\n`);
  const pre = classifyPersonaSites(base);
  if (inj.label.mechanical !== pre.label.mechanical + 1) no('R1 KJENT-POSITIV: injisert "**For Cosmo:**" ble IKKE sett');
  else ok('R1 KJENT-POSITIV: injisert "**For Cosmo:**" felte R1');
  if (inj.table.mechanical !== pre.table.mechanical + 1) no('R1 KJENT-POSITIV: injisert "| Cosmos råd |" (genitiv) ble IKKE sett');
  else ok('R1 KJENT-POSITIV: injisert "| Cosmos råd |" (genitiv) felte R1');

  // R1 known-negative — the second case is the dangerous one: it LOOKS like a persona label.
  const prod = classifyPersonaSites('**Cosmos DB-anbefaling:** bruk autoscale\n| Azure Cosmos DB | 8000 NOK |\n');
  if (prod.label.mechanical + prod.table.mechanical !== 0 || prod.unmapped.length) {
    no(`R1 KJENT-NEGATIV: produkt feilklassifisert (${JSON.stringify(prod)})`);
  } else ok('R1 KJENT-NEGATIV: "**Cosmos DB-anbefaling:**" og "| Azure Cosmos DB |" passerer urort');

  // R2 known-positive — an in-class site the tables do not know must be REPORTED.
  const hole = classifyPersonaSites('**Cosmo-hjørnet:** noe tekst\n');
  if (hole.unmapped.length !== 1) no('R2 KJENT-POSITIV: ukjent etikettform ble IKKE rapportert');
  else ok('R2 KJENT-POSITIV: ukjent etikettform "**Cosmo-hjørnet:**" rapportert som umaalt');
  let threw = false;
  try { neutralizeLabels('**Cosmo-hjørnet:** noe tekst\n'); } catch { threw = true; }
  if (!threw) no('R2 KJENT-POSITIV: transformen hoppet STILLE over en ukjent form'); else ok('R2 KJENT-POSITIV: transformen KASTER paa ukjent form, hopper ikke stille over');

  // R2 known-negative — the editorial classes must be reported OUT of scope and left alone.
  const ed = '**Cosmo svarer:**\n| A | B | Cosmo-syntese av verified sources |\n';
  const edC = classifyPersonaSites(ed);
  if (edC.label.editorial !== 1 || edC.table.editorial !== 1) no('R2 KJENT-NEGATIV: redaksjonell form ikke bokfoert som utenfor scope');
  else if (neutralizeLabels(ed).content !== ed) no('R2 KJENT-NEGATIV: redaksjonell form ble ENDRET');
  else ok('R2 KJENT-NEGATIV: dialog + proveniens bokfoert utenfor scope OG byte-identiske');

  // R3 known-positive — break one product occurrence and the product clause must fell.
  const broken = classifyCosmo('| Azure Cosmo DB | 8000 |\n');
  const intact = classifyCosmo('| Azure Cosmos DB | 8000 |\n');
  if (!(intact.product === 1 && broken.product === 0)) no(`R3 KJENT-POSITIV: fjernet tegn i "Cosmos DB" felte IKKE produkt-differansen (${intact.product} -> ${broken.product})`);
  else ok('R3 KJENT-POSITIV: fjernet tegn i "Cosmos DB" felte produkt-differansen (1 -> 0)');

  // R3 known-negative — the product-only files must be byte-identical through the transform.
  for (const f of productOnlyFiles(measure())) {
    const src = readFileSync(join(PLUGIN_ROOT, f), 'utf8');
    if (neutralizeLabels(src, { relPath: f }).content !== src) no(`R3 KJENT-NEGATIV: kun-produkt-fila ${f} ble endret`);
    else ok(`R3 KJENT-NEGATIV: ${f} byte-identisk gjennom transformen`);
  }
  return bad;
}

const arg = process.argv[2];
if (arg === '--emit-baseline') emitBaseline();
else if (arg === '--emit-labels-baseline') emitLabelsBaseline();
else if (arg === '--validate-net') validateNet();
else check();