Files
msd-core/tests/enh-2789-description-budget.test.cjs
Tom Boucher a28dcec981 chore(#597): replace count-based ratchet guards with AST lint + named-set allowlists (#603)
The windows-test-parity ratchet greps test source for fs.rmSync-without-
maxRetries (and six other Windows-portability anti-patterns), failing when an
integer offender COUNT exceeds a frozen baseline (rmSync: 95). A count ratchet
is a Goodhart metric: fixing one offender and adding another keeps the count
constant, so a new defect slips through green. Replace it — and every other
count ratchet in the repo — with a layered, masking-proof design.

Behavioral seam test
- tests/helpers-cleanup.test.cjs proves helpers.cleanup() carries the Windows
  EBUSY retry budget. cleanup() delegates retries to Node's fs.rmSync via
  maxRetries (it owns no loop), so the test asserts the option contract
  (recursive/force/maxRetries>0/retryDelay>0) + real-FS removal + the cwd-guard,
  rather than a loop that does not exist. The EBUSY risk is now tested ONCE at
  the helper, not approximated textually at every call site.

Write-time ESLint rule (AST-accurate, replaces the grep)
- eslint-rules/no-raw-rmsync-in-tests.cjs (error in tests/**/*.test.cjs) bans
  raw fs.rmSync, steering to cleanup(). Catches member, computed (fs['rmSync']),
  destructured and aliased forms; escape hatch is inline
  `// eslint-disable-next-line local/no-raw-rmsync-in-tests -- <reason>` only.
- Migrated 336 raw fs.rmSync teardown calls across ~116 test files to cleanup().
  ~18 genuinely load-bearing sites (mid-test SUT/fault-injection removals,
  error-swallowing or name-colliding local teardown helpers) keep the raw call
  with an inline eslint-disable + reason.

Shared anti-ratchet primitive
- scripts/lib/allowlist-ratchet.cjs:
  - assertWithinAllowlist: fails on NOVEL ids (new offender introduced) AND on
    STALE ids (a known offender was fixed but not pruned) — identity, not count,
    and a ratchet DOWN toward zero.
  - assertTightCeiling: a size/length budget whose ceiling must stay within a
    grace band of the high-water mark, so budgets may only tighten, never creep.

Ratchets converted onto the primitive
- windows-test-parity-guard.test.cjs: rmSync rule deleted (now ESLint-enforced);
  the remaining six patterns moved from integer baselines to named-set
  allowlists with ratchet-down.
- scripts/lint-test-file-count.{cjs,allowlist.json}: per-module integer counts →
  named filename sets (closes the swap-a-file-keep-the-count blind spot); a
  module dropping under cap now FAILS to force pruning its allowlist entry.
- enh-2790 skill-count `<= 63` → named skill allowlist (ratchets toward ~58).

Size budgets hardened (tighten-only)
- agent-size / workflow-size / feat-3039 help-tiered: ceilings lowered to the
  current high-water mark and an assertTightCeiling anti-creep check added per
  tier. Fixed external-contract limits (description ≤100 chars, agent ≤100 KB)
  are intentionally left as-is — they are not grandfathered creeping budgets.

No user-facing behavior change (tests + tooling only); no USER_FACING_PREFIXES
touched, so no changeset fragment is required.

Co-authored-by: Claude Opus 4.8 <noreply@anthropic.com>
2026-06-01 22:43:49 -04:00

194 lines
6.2 KiB
JavaScript

'use strict';
// allow-test-rule: source-text-is-the-product
// commands/gsd/*.md text IS what the runtime loads — testing description
// length tests the deployed system-prompt contract.
/**
* Tests for #2789 — Trim skill description anti-patterns; enforce 100-char budget
*
* Verifies:
* 1. All skill descriptions in commands/gsd/*.md are <= 100 chars
* 2. No descriptions contain flag documentation anti-patterns (Use --)
* 3. No descriptions contain "Triggers:" keyword stuffing
* 4. lint-descriptions.cjs rejects descriptions over 100 chars
* 5. lint-descriptions.cjs accepts descriptions under 100 chars
*/
const { test, describe, beforeEach, afterEach } = require('node:test');
const assert = require('node:assert/strict');
const fs = require('node:fs');
const path = require('node:path');
const { spawnSync } = require('node:child_process');
const os = require('node:os');
const { cleanup } = require('./helpers.cjs');
const COMMANDS_DIR = path.join(__dirname, '../commands/gsd');
const LINT_SCRIPT = path.join(__dirname, '../scripts/lint-descriptions.cjs');
const MAX_DESCRIPTION_LENGTH = 100;
/**
* Parse the description field from a frontmatter block in a .md file.
* Returns null if no description is found.
*/
function parseDescription(content) {
// Extract frontmatter block between --- markers
const fmMatch = content.match(/^---\r?\n([\s\S]*?)\r?\n---/);
if (!fmMatch) return null;
const fm = fmMatch[1];
// Handle multi-line or quoted values: description: "..." or description: plain text
// Match: description: "value" or description: value (to end of line)
const quoted = fm.match(/^description:\s+"((?:[^"\\]|\\.)*)"\s*$/m);
if (quoted) return quoted[1];
const plain = fm.match(/^description:\s+(.+)$/m);
if (plain) return plain[1].trim();
return null;
}
/**
* Get all .md files in commands/gsd/ with their descriptions.
*/
function getAllCommandDescriptions() {
const files = fs.readdirSync(COMMANDS_DIR).filter(f => f.endsWith('.md'));
return files.map(file => {
const filePath = path.join(COMMANDS_DIR, file);
const content = fs.readFileSync(filePath, 'utf-8');
const description = parseDescription(content);
return { file, filePath, description };
});
}
// ── Test 1: All descriptions <= 100 chars ────────────────────────────────────
describe('description length budget', () => {
test('all commands/gsd/*.md descriptions are <= 100 chars', () => {
const commands = getAllCommandDescriptions();
const violators = commands
.filter(c => c.description !== null && c.description.length > MAX_DESCRIPTION_LENGTH)
.map(c => [
'length=' + c.description.length,
'file=' + c.file,
'desc=' + c.description,
].join(' | '));
assert.strictEqual(
violators.length,
0,
[
`${violators.length} description(s) exceed ${MAX_DESCRIPTION_LENGTH} chars:`,
...violators.map(v => ' ' + v),
].join('\n')
);
});
});
// ── Test 2: No flag documentation anti-patterns ──────────────────────────────
describe('description anti-patterns', () => {
test('no descriptions contain flag documentation (Use --, use --, via --)', () => {
const commands = getAllCommandDescriptions();
const FLAG_PATTERNS = ['Use --', 'use --', 'via --'];
const violators = commands
.filter(c => {
if (!c.description) return false;
return FLAG_PATTERNS.some(p => c.description.includes(p));
})
.map(c => 'file=' + c.file + ' | desc=' + c.description);
assert.strictEqual(
violators.length,
0,
[
`${violators.length} description(s) contain flag documentation anti-patterns:`,
...violators.map(v => ' ' + v),
].join('\n')
);
});
// ── Test 3: No Triggers: keyword stuffing ─────────────────────────────────
test('no descriptions contain "Triggers:" keyword stuffing', () => {
const commands = getAllCommandDescriptions();
const violators = commands
.filter(c => c.description && /triggers:/i.test(c.description))
.map(c => 'file=' + c.file + ' | desc=' + c.description);
assert.strictEqual(
violators.length,
0,
[
`${violators.length} description(s) contain "Triggers:" keyword stuffing:`,
...violators.map(v => ' ' + v),
].join('\n')
);
});
});
// ── Test 4 & 5: lint-descriptions.cjs script ─────────────────────────────────
describe('lint-descriptions.cjs', () => {
let tmpDir;
beforeEach(() => {
tmpDir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-lint-desc-test-'));
});
afterEach(() => {
cleanup(tmpDir);
});
test('rejects a command file with a description over 100 chars', () => {
const longDesc = 'A'.repeat(101);
const content = [
'---',
'name: gsd:test-long',
'description: ' + longDesc,
'---',
'',
'Body text.',
].join('\n');
const tmpFile = path.join(tmpDir, 'long-desc.md');
fs.writeFileSync(tmpFile, content, 'utf-8');
const result = spawnSync(process.execPath, [LINT_SCRIPT, tmpFile], {
encoding: 'utf-8',
});
assert.notStrictEqual(result.status, 0, [
'lint-descriptions.cjs should exit non-zero for description > 100 chars',
'stdout: ' + result.stdout,
'stderr: ' + result.stderr,
].join('\n'));
});
test('accepts a command file with a description under 100 chars', () => {
const shortDesc = 'Short routing description for this skill.';
const content = [
'---',
'name: gsd:test-short',
'description: ' + shortDesc,
'---',
'',
'Body text.',
].join('\n');
const tmpFile = path.join(tmpDir, 'short-desc.md');
fs.writeFileSync(tmpFile, content, 'utf-8');
const result = spawnSync(process.execPath, [LINT_SCRIPT, tmpFile], {
encoding: 'utf-8',
});
assert.strictEqual(result.status, 0, [
'lint-descriptions.cjs should exit 0 for description <= 100 chars',
'stdout: ' + result.stdout,
'stderr: ' + result.stderr,
].join('\n'));
});
});