ms-ai-architect/tests/kb-update/test-user-data.test.mjs

// tests/kb-update/test-user-data.test.mjs
// Spor C fase C2.1: user-owned storage + ambient org-context injection (#1 + #2).
//
// lib/user-data.mjs is the PURE resolver every later C2 sub-session builds on.
// It NEVER writes — it only resolves user-owned paths and builds a compact,
// deterministic org-context summary from file contents handed to it. This suite
// proves:
//   (A) the resolvers point at ~/.claude/ms-ai-architect/ (a USER-owned dir,
//       independent of pluginRoot => survives plugin reinstall — acceptance K2),
//       and the config filename matches C1's so loadScheduleConfig stays compat,
//   (B) buildOrgSummary is deterministic, length-capped, tolerant, and pure
//       (no fs) so the SessionStart hook can inject it ambiently (K1).

import { test } from 'node:test';
import assert from 'node:assert/strict';
import { join } from 'node:path';
import { homedir } from 'node:os';
import {
  USER_DATA_DIRNAME,
  CONFIG_FILENAME,
  ORG_FILES,
  FREE_CONTEXT_FILE,
  resolveUserDataDir,
  resolveOrgDir,
  resolveConfigPath,
  buildOrgSummary,
  orderOrgFiles,
} from '../../scripts/kb-update/lib/user-data.mjs';

// ===========================================================================
// (A) Resolvers — pure, homedir-injectable, user-owned (survives reinstall)
// ===========================================================================

test('USER_DATA_DIRNAME — the plugin folder under ~/.claude', () => {
  assert.equal(USER_DATA_DIRNAME, 'ms-ai-architect');
});

test('resolveUserDataDir — user-owned dir under ~/.claude, independent of pluginRoot (K2)', () => {
  assert.equal(resolveUserDataDir('/Users/x'), join('/Users/x', '.claude', 'ms-ai-architect'));
});

test('resolveUserDataDir — defaults to os.homedir()', () => {
  assert.equal(resolveUserDataDir(), join(homedir(), '.claude', 'ms-ai-architect'));
});

test('resolveOrgDir — org/ under the user data dir', () => {
  assert.equal(resolveOrgDir('/Users/x'), join('/Users/x', '.claude', 'ms-ai-architect', 'org'));
});

test('resolveConfigPath — config under user data dir; filename matches C1 (backward-compat)', () => {
  assert.equal(
    resolveConfigPath('/Users/x'),
    join('/Users/x', '.claude', 'ms-ai-architect', CONFIG_FILENAME),
  );
  assert.equal(CONFIG_FILENAME, 'ms-ai-architect.local.md', 'must match detection-schedule CONFIG_FILENAME');
});

test('ORG_FILES — the five canonical onboarding files in deterministic order', () => {
  assert.deepEqual([...ORG_FILES], [
    'organization-profile.md',
    'technology-stack.md',
    'security-compliance.md',
    'architecture-decisions.md',
    'business-references.md',
  ]);
});

// ===========================================================================
// (B) buildOrgSummary — deterministic, capped, pure
// ===========================================================================

const PROFILE = [
  '---',
  'category: organization-profile',
  'completed: true',
  'last_updated: 2026-06-22',
  '---',
  '',
  '# Virksomhetsprofil',
  '',
  '## Sektortype',
  'Offentlig sektor',
  '',
  '## Sektor',
  'Statlig',
  '',
  '## Virksomhet',
  'Statens vegvesen — nasjonal veiforvaltning',
  '',
  '## Størrelse',
  '2000-10000',
  '',
  '## Regulatoriske krav',
  'Personopplysningsloven/GDPR, Arkivloven, Forvaltningsloven',
  '',
].join('\n');

test('buildOrgSummary — no files / null content => empty string', () => {
  assert.equal(buildOrgSummary({}), '');
  assert.equal(buildOrgSummary({ 'organization-profile.md': null }), '');
});

test('buildOrgSummary — null/undefined/garbage input is tolerated (returns "")', () => {
  assert.equal(buildOrgSummary(null), '');
  assert.equal(buildOrgSummary(undefined), '');
  assert.equal(buildOrgSummary({ 'organization-profile.md': 12345 }), '');
});

test('buildOrgSummary — strips frontmatter + H1, extracts H2 section => value lines', () => {
  const s = buildOrgSummary({ 'organization-profile.md': PROFILE });
  assert.doesNotMatch(s, /category:/, 'frontmatter stripped');
  assert.doesNotMatch(s, /completed:/, 'frontmatter stripped');
  assert.doesNotMatch(s, /Virksomhetsprofil/, 'H1 not included');
  assert.match(s, /Sektortype: Offentlig sektor/);
  assert.match(s, /Sektor: Statlig/);
  assert.match(s, /Virksomhet: Statens vegvesen/);
  assert.match(s, /Størrelse: 2000-10000/);
  assert.match(s, /Regulatoriske krav: .*Arkivloven/);
});

test('buildOrgSummary — deterministic order follows ORG_FILES regardless of input key order', () => {
  const TECH = '---\ncategory: technology-stack\n---\n## Lisenstype\nE5\n';
  const out = buildOrgSummary({ 'technology-stack.md': TECH, 'organization-profile.md': PROFILE });
  assert.ok(
    out.indexOf('Sektortype') < out.indexOf('Lisenstype'),
    'organization-profile sections precede technology-stack sections',
  );
});

test('buildOrgSummary — non-.md keys and non-string values contribute nothing', () => {
  assert.equal(buildOrgSummary({ 'notater.txt': '## Hemmelig\nverdi' }), '');
  assert.equal(buildOrgSummary({ 'ekstra.md': 12345 }), '');
});

test('buildOrgSummary — skips empty sections (header with no body)', () => {
  const c = '## Sektor\n\n## Størrelse\n500-2000\n';
  const s = buildOrgSummary({ 'organization-profile.md': c });
  assert.doesNotMatch(s, /Sektor:/, 'empty section omitted');
  assert.match(s, /Størrelse: 500-2000/);
});

test('buildOrgSummary — collapses a multi-line section body to one line', () => {
  const c = '## Virksomhet\nLinje en\nLinje to\n';
  const s = buildOrgSummary({ 'organization-profile.md': c });
  assert.match(s, /Virksomhet: Linje en Linje to/);
});

test('buildOrgSummary — caps a long free-text value with an ellipsis (budget guard)', () => {
  const long = 'x'.repeat(500);
  const s = buildOrgSummary(
    { 'business-references.md': `## Referansearkitektur\n${long}\n` },
    { maxTotalLen: 80 },
  );
  const line = s.split('\n').find((l) => l.includes('Referansearkitektur'));
  assert.ok(line, 'value line present');
  assert.match(line, /…$/, 'truncation marker appended');
  // label "Referansearkitektur: " + value(<=80)
  assert.ok(line.length <= 'Referansearkitektur: '.length + 80, `line too long: ${line.length}`);
});

test('buildOrgSummary — caps total line count and marks omitted fields', () => {
  const many = Array.from({ length: 40 }, (_, i) => `## Felt${i}\nverdi${i}`).join('\n\n');
  const s = buildOrgSummary({ 'organization-profile.md': many }, { cap: 10 });
  const lines = s.split('\n').filter(Boolean);
  assert.ok(lines.length <= 10, `capped to 10, got ${lines.length}`);
  assert.match(s, /flere/, 'truncation marker indicates omitted fields');
});

test('buildOrgSummary — default cap keeps the summary compact (<= 25 lines)', () => {
  const all = {};
  for (const f of ORG_FILES) {
    all[f] = Array.from({ length: 8 }, (_, i) => `## ${f}-Felt${i}\nverdi${i}`).join('\n\n');
  }
  const s = buildOrgSummary(all); // default cap
  const lines = s.split('\n').filter(Boolean);
  assert.ok(lines.length <= 25, `default cap should keep <=25 lines, got ${lines.length}`);
});

// ===========================================================================
// (C) Free-prose context (C2.2) — the optional sixth file (#3, acceptance K3)
// ===========================================================================

test('FREE_CONTEXT_FILE — optional free-prose filename, NOT part of ORG_FILES', () => {
  assert.equal(FREE_CONTEXT_FILE, 'free-context.md');
  assert.ok(
    !ORG_FILES.includes(FREE_CONTEXT_FILE),
    'free-context is optional and must not count toward onboarding completeness',
  );
});

const FREE = [
  '---',
  'category: free-context',
  'completed: true',
  'last_updated: 2026-06-22',
  '---',
  '',
  '# Fri kontekst',
  '',
  '## Fri kontekst',
  'Vi migrerer fra on-prem til Azure i 2026.',
  '',
].join('\n');

test('buildOrgSummary — surfaces free-context as a "Fri kontekst" field', () => {
  const s = buildOrgSummary({ 'free-context.md': FREE });
  assert.match(s, /Fri kontekst: Vi migrerer fra on-prem til Azure i 2026\./);
});

test('buildOrgSummary — free-context is robust to raw prose without any H2 (K3: no silent drop)', () => {
  // The whole point of #3 is a single free field; it must surface even when the
  // agent writes a plain paragraph with no markdown structure at all.
  const s = buildOrgSummary({
    'free-context.md': 'Vi har hatt en hendelse med Copilot som lekket interne dokumenter.',
  });
  assert.match(s, /Fri kontekst: Vi har hatt en hendelse med Copilot/);
});

test('buildOrgSummary — free-context strips frontmatter and all header lines', () => {
  const s = buildOrgSummary({
    'free-context.md': '---\ncategory: free-context\n---\n# Fri kontekst\n## Fri kontekst\nKun prosaen skal vises.\n',
  });
  assert.doesNotMatch(s, /category:/, 'frontmatter stripped');
  assert.equal(s, 'Fri kontekst: Kun prosaen skal vises.');
});

test('buildOrgSummary — free-context appears AFTER the structured fields', () => {
  const out = buildOrgSummary({
    'free-context.md': '## Fri kontekst\nTilleggsnotat.',
    'organization-profile.md': PROFILE,
  });
  assert.ok(
    out.indexOf('Sektortype') < out.indexOf('Fri kontekst'),
    'structured context leads; free prose trails',
  );
});

test('buildOrgSummary — long free-context is capped with an ellipsis (budget guard)', () => {
  const s = buildOrgSummary({ 'free-context.md': 'y'.repeat(500) }, { maxTotalLen: 80 });
  const line = s.split('\n').find((l) => l.startsWith('Fri kontekst:'));
  assert.ok(line, 'free-context line present');
  assert.match(line, /…$/, 'truncation marker appended');
  assert.ok(line.length <= 'Fri kontekst: '.length + 80, `line too long: ${line.length}`);
});

test('buildOrgSummary — empty/whitespace/header-only free-context yields no field', () => {
  assert.equal(buildOrgSummary({ 'free-context.md': '   \n\n' }), '');
  assert.equal(
    buildOrgSummary({ 'free-context.md': '---\ncategory: free-context\n---\n# Fri kontekst\n' }),
    '',
    'frontmatter + bare H1 (no prose) => nothing',
  );
});

test('buildOrgSummary — free-context absent leaves the structured summary unchanged (back-compat)', () => {
  const s = buildOrgSummary({ 'organization-profile.md': PROFILE });
  assert.doesNotMatch(s, /Fri kontekst/);
});

test('buildOrgSummary — realistic full onboarding keeps free-context visible (K3)', () => {
  const all = {};
  for (const f of ORG_FILES) all[f] = `## ${f}-felt\nverdi for ${f}`;
  all['free-context.md'] = '## Fri kontekst\nViktig tilleggskontekst som må være synlig.';
  const s = buildOrgSummary(all); // default cap 25
  assert.match(s, /Fri kontekst: Viktig tilleggskontekst/, 'free-context visible within default budget');
});

// ===========================================================================
// (D) Reduksjon — the total value budget replaces the per-field cap, and the
//     file set is no longer frozen to ORG_FILES (measured 2026-08-26: a 160-
//     char per-field cap threw away 47 % of a 300-char answer and 92 % of a
//     2000-char one while most of the budget stood unspent, and a seventh file
//     in org/ never reached the model at all).
// ===========================================================================

test('buildOrgSummary — a long field survives whole while the total budget is unspent', () => {
  const long = 'x'.repeat(1500);
  const s = buildOrgSummary({
    'organization-profile.md': '## Sektor\noffentlig',
    'free-context.md': long,
  });
  assert.ok(s.includes(long), 'a single long answer must survive uncut when the budget allows it');
});

test('buildOrgSummary — unspent budget is redistributed, so every field beats the old 160 cap', () => {
  const all = {};
  for (const f of ORG_FILES) {
    all[f] = Array.from({ length: 4 }, (_, i) => `## ${f}-Felt${i}\n${'x'.repeat(1000)}`).join('\n\n');
  }
  const s = buildOrgSummary(all); // 20 fields, default budget 4000 => 200 each
  const values = s.split('\n').map((l) => l.slice(l.indexOf(': ') + 2));
  for (const v of values) {
    assert.ok(v.length >= 200, `fair share of 4000 over 20 fields is 200, got ${v.length}`);
  }
});

test('buildOrgSummary — the total value budget is enforced across all fields', () => {
  const all = {};
  for (const f of ORG_FILES) {
    all[f] = Array.from({ length: 4 }, (_, i) => `## ${f}-Felt${i}\n${'x'.repeat(5000)}`).join('\n\n');
  }
  const s = buildOrgSummary(all);
  const total = s
    .split('\n')
    .reduce((sum, l) => sum + l.slice(l.indexOf(': ') + 2).length, 0);
  assert.ok(total <= 4000, `total value chars must stay within the 4000 budget, got ${total}`);
});

test('buildOrgSummary — a short field is never padded away from its own length', () => {
  const s = buildOrgSummary({
    'organization-profile.md': '## Sektor\noffentlig',
    'technology-stack.md': `## Stack\n${'x'.repeat(9000)}`,
  });
  assert.match(s, /^Sektor: offentlig$/m, 'a short field is kept whole, never trimmed to its share');
});

test('buildOrgSummary — maxTotalLen is overridable', () => {
  const s = buildOrgSummary({ 'organization-profile.md': `## Sektor\n${'x'.repeat(500)}` }, { maxTotalLen: 50 });
  const value = s.slice(s.indexOf(': ') + 2);
  assert.equal(value.length, 50, `explicit budget must bind, got ${value.length}`);
});

test('buildOrgSummary — an extra .md file beyond ORG_FILES contributes its sections', () => {
  const s = buildOrgSummary({ 'kundeportefolje.md': '## Kunder\nStore offentlige etater' });
  assert.match(s, /Kunder: Store offentlige etater/);
});

test('buildOrgSummary — extra files come after ORG_FILES, before free-context, sorted by name', () => {
  const s = buildOrgSummary({
    'zeta.md': '## Zeta\nz',
    'alfa.md': '## Alfa\na',
    'organization-profile.md': '## Sektor\noffentlig',
    'free-context.md': 'fritekst',
  });
  assert.deepEqual(
    s.split('\n').map((l) => l.slice(0, l.indexOf(':'))),
    ['Sektor', 'Alfa', 'Zeta', 'Fri kontekst'],
  );
});

test('orderOrgFiles — ORG_FILES first in canonical order, then extra .md sorted by name', () => {
  assert.deepEqual(
    orderOrgFiles(['zeta.md', 'technology-stack.md', 'alfa.md', 'organization-profile.md']),
    ['organization-profile.md', 'technology-stack.md', 'alfa.md', 'zeta.md'],
  );
});

test('orderOrgFiles — free-context is excluded (callers append it last, labelled)', () => {
  assert.deepEqual(orderOrgFiles([FREE_CONTEXT_FILE, 'alfa.md']), ['alfa.md']);
});

test('orderOrgFiles — non-.md entries and garbage input are dropped', () => {
  assert.deepEqual(orderOrgFiles(['notater.txt', '.DS_Store', 'alfa.md']), ['alfa.md']);
  assert.deepEqual(orderOrgFiles(null), []);
});

test('buildOrgSummary — Fri kontekst survives the overflow cut (it is added last, not least)', () => {
  const many = Array.from({ length: 40 }, (_, i) => `## Felt${i}\nverdi${i}`).join('\n\n');
  const s = buildOrgSummary({
    'organization-profile.md': many,
    'free-context.md': 'Den ene sloten der brukeren skriver fritt.',
  });
  const lines = s.split('\n');
  assert.ok(lines.length <= 25, `line budget still binds, got ${lines.length}`);
  assert.match(s, /Fri kontekst: Den ene sloten/, 'free-context must not be the first field dropped');
  assert.match(lines[lines.length - 1], /flere felt/, 'marker still last');
  assert.match(lines[lines.length - 2], /^Fri kontekst:/, 'free-context kept as the last field');
});

test('buildOrgSummary — overflow without free-context is unchanged (back-compat)', () => {
  const many = Array.from({ length: 40 }, (_, i) => `## Felt${i}\nverdi${i}`).join('\n\n');
  const lines = buildOrgSummary({ 'organization-profile.md': many }, { cap: 10 }).split('\n');
  assert.equal(lines.length, 10);
  assert.equal(lines[0], 'Felt0: verdi0');
  assert.equal(lines[8], 'Felt8: verdi8');
  assert.match(lines[9], /flere felt/);
});

// ===========================================================================
// (E) Reduksjon ved SKALA — the unit of reduction is the DOCUMENT, not the
//     field. Measured 2026-08-26 (bake-off arm A2b, flat org/, n=55 corpus
//     docs): 61 files and 183 fields went in, 24 fields came out, and those 24
//     came from 8 files — 53 files were invisible while 1013 of the 4000 value
//     chars stood unspent. What remained was selection by FIXED ORDER, which is
//     relevance-blind, and the summary is built ambiently at session start —
//     before any question exists — so there is no relevance signal to rank
//     against. The honest substitute for ranking is COVERAGE.
// ===========================================================================

test('buildOrgSummary — every file contributes at least one field when the budget allows it', () => {
  const all = {};
  for (let f = 0; f < 40; f++) {
    all[`fil${String(f).padStart(2, '0')}.md`] = Array.from(
      { length: 3 },
      (_, i) => `## F${f}H${i}\nverdi fra fil ${f} felt ${i}`,
    ).join('\n\n');
  }
  const s = buildOrgSummary(all);
  const missing = [];
  for (let f = 0; f < 40; f++) {
    if (!new RegExp(`^F${f}H\\d: `, 'm').test(s)) missing.push(f);
  }
  assert.deepEqual(missing, [], `every file must reach the summary; ${missing.length}/40 did not`);
});

test('buildOrgSummary — selection is breadth-first across files, not fixed order within one', () => {
  const all = {
    'organization-profile.md': '## A0\na0\n\n## A1\na1\n\n## A2\na2',
    'technology-stack.md': '## B0\nb0\n\n## B1\nb1\n\n## B2\nb2',
    'security-compliance.md': '## C0\nc0\n\n## C1\nc1\n\n## C2\nc2',
  };
  // cap 4 => 3 field lines + marker. Fixed order would spend all three on the
  // first file; coverage spends one on each.
  const lines = buildOrgSummary(all, { cap: 4 }).split('\n');
  assert.deepEqual(lines.slice(0, 3), ['A0: a0', 'B0: b0', 'C0: c0']);
  assert.match(lines[3], /flere felt/);
});

test('buildOrgSummary — the overflow marker reports how many FILES were cut, not only fields', () => {
  const all = {};
  for (let f = 0; f < 200; f++) all[`fil${String(f).padStart(3, '0')}.md`] = `## H${f}\nverdi ${f}`;
  const s = buildOrgSummary(all);
  const marker = s.split('\n').at(-1);
  assert.match(marker, /flere felt/, 'field residue still reported');
  assert.match(marker, /\d+ filer/, 'file residue must be named — a silent drop is the defect');
});

test('buildOrgSummary — coverage yields to the char budget, never starving lines to fragments', () => {
  const all = {};
  for (let f = 0; f < 200; f++) all[`fil${String(f).padStart(3, '0')}.md`] = `## H${f}\n${'x'.repeat(400)}`;
  const s = buildOrgSummary(all);
  const values = s.split('\n').filter((l) => /^H\d+: /.test(l)).map((l) => l.slice(l.indexOf(': ') + 2));
  assert.ok(values.length > 0, 'fields emitted');
  for (const v of values) {
    assert.ok(v.length >= 60, `a coverage line must stay readable, got ${v.length}`);
  }
  assert.ok(
    values.reduce((a, v) => a + v.length, 0) <= 4000,
    'the total value budget still binds at scale',
  );
});

test('buildOrgSummary — the designed onboarding size is untouched by the coverage rule', () => {
  const all = {};
  for (const f of ORG_FILES) {
    all[f] = Array.from({ length: 4 }, (_, i) => `## ${f}-Felt${i}\nverdi${i}`).join('\n\n');
  }
  const lines = buildOrgSummary(all).split('\n');
  assert.equal(lines.length, 20, '20 fields over 5 files fit; no marker, no reordering');
  assert.equal(lines[0], 'organization-profile.md-Felt0: verdi0');
  assert.equal(lines[3], 'organization-profile.md-Felt3: verdi3');
});

test('buildOrgSummary — Fri kontekst still survives the cut at scale', () => {
  const all = {};
  for (let f = 0; f < 40; f++) all[`fil${String(f).padStart(2, '0')}.md`] = `## H${f}\nverdi ${f}`;
  all['free-context.md'] = 'Den ene sloten der brukeren skriver fritt.';
  const s = buildOrgSummary(all, { cap: 10 });
  assert.match(s, /Fri kontekst: Den ene sloten/, 'free-context must not be the first field dropped');
});