Files
msd-core/tests/install-update-marker.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

199 lines
7.4 KiB
JavaScript

'use strict';
/**
* Tests for marker-driven profile re-application on `gsd update` (Deviation 2).
*
* Verifies:
* 1. resolveEffectiveProfile returns the marker's profile when no explicit flag given.
* 2. Explicit --profile flag overrides the marker.
* 3. Multi-runtime marker disagreement resolves to the most-restrictive profile.
* 4. Missing marker falls back to 'full'.
* 5. stageSkillsForProfile is called with the resolved profile (not 'full') on updates.
*/
const { test, describe } = require('node:test');
const assert = require('node:assert/strict');
const fs = require('fs');
const path = require('path');
const os = require('os');
const { cleanup } = require('./helpers.cjs');
const {
resolveEffectiveProfile,
mostRestrictiveProfile,
writeActiveProfile,
readActiveProfile,
resolveProfile,
loadSkillsManifest,
stageSkillsForProfile,
cleanupStagedSkills,
} = require('../get-shit-done/bin/lib/install-profiles.cjs');
const REAL_COMMANDS_DIR = path.join(__dirname, '..', 'commands', 'gsd');
describe('resolveEffectiveProfile', () => {
test('no explicit flag and no marker → returns "full"', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
const result = resolveEffectiveProfile({ requestedProfileName: null, targetDir: dir });
assert.strictEqual(result, 'full');
} finally {
cleanup(dir);
}
});
test('no explicit flag but marker exists → returns marker profile', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
writeActiveProfile(dir, 'standard');
const result = resolveEffectiveProfile({ requestedProfileName: null, targetDir: dir });
assert.strictEqual(result, 'standard');
} finally {
cleanup(dir);
}
});
test('no explicit flag but core marker exists → returns "core"', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
writeActiveProfile(dir, 'core');
const result = resolveEffectiveProfile({ requestedProfileName: null, targetDir: dir });
assert.strictEqual(result, 'core');
} finally {
cleanup(dir);
}
});
test('explicit --profile=full overrides a non-full marker', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
writeActiveProfile(dir, 'core');
const result = resolveEffectiveProfile({ requestedProfileName: 'full', targetDir: dir });
assert.strictEqual(result, 'full');
} finally {
cleanup(dir);
}
});
test('explicit --profile=standard overrides a core marker', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
writeActiveProfile(dir, 'core');
const result = resolveEffectiveProfile({ requestedProfileName: 'standard', targetDir: dir });
assert.strictEqual(result, 'standard');
} finally {
cleanup(dir);
}
});
test('full marker falls back to "full" (not recorded as a restriction)', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-reu-'));
try {
writeActiveProfile(dir, 'full');
const result = resolveEffectiveProfile({ requestedProfileName: null, targetDir: dir });
assert.strictEqual(result, 'full');
} finally {
cleanup(dir);
}
});
});
describe('mostRestrictiveProfile', () => {
test('returns "core" over "standard" (core is smaller)', () => {
const result = mostRestrictiveProfile(['standard', 'core']);
assert.strictEqual(result, 'core');
});
test('returns "core" over "full"', () => {
const result = mostRestrictiveProfile(['full', 'core']);
assert.strictEqual(result, 'core');
});
test('returns "standard" over "full"', () => {
const result = mostRestrictiveProfile(['full', 'standard']);
assert.strictEqual(result, 'standard');
});
test('single profile returns that profile', () => {
assert.strictEqual(mostRestrictiveProfile(['standard']), 'standard');
assert.strictEqual(mostRestrictiveProfile(['full']), 'full');
assert.strictEqual(mostRestrictiveProfile(['core']), 'core');
});
test('empty array returns "full" (no restriction)', () => {
assert.strictEqual(mostRestrictiveProfile([]), 'full');
});
test('all same profile returns that profile', () => {
assert.strictEqual(mostRestrictiveProfile(['standard', 'standard', 'standard']), 'standard');
});
});
describe('marker-driven profile resolution end-to-end', () => {
test('fresh install with --profile=standard writes marker, re-read resolves standard', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-e2e-'));
try {
// Simulate: fresh install with --profile=standard
writeActiveProfile(dir, 'standard');
// Simulate: re-run without flags (e.g. `gsd update`)
const effective = resolveEffectiveProfile({ requestedProfileName: null, targetDir: dir });
assert.strictEqual(effective, 'standard');
// Verify the staged output contains only standard's skills
const manifest = loadSkillsManifest(REAL_COMMANDS_DIR);
const resolved = resolveProfile({ modes: [effective], manifest });
assert.ok(resolved.skills instanceof Set, 'skills should be a Set for standard');
assert.ok(resolved.skills.has('plan-phase'), 'standard should include plan-phase');
// plan-phase should be staged
let staged;
try {
staged = stageSkillsForProfile(REAL_COMMANDS_DIR, resolved);
assert.notStrictEqual(staged, REAL_COMMANDS_DIR, 'should be a staged dir, not srcDir');
const stagedFiles = fs.readdirSync(staged).map(f => f.slice(0, -3)); // strip .md
assert.ok(stagedFiles.includes('plan-phase'), 'plan-phase.md should be staged');
// full-only skills must NOT be staged
const allFiles = fs.readdirSync(REAL_COMMANDS_DIR).map(f => f.slice(0, -3));
const notInStandard = allFiles.filter(s => !resolved.skills.has(s));
for (const stem of notInStandard) {
assert.ok(!stagedFiles.includes(stem),
`${stem} should not be staged in standard profile`);
}
} finally {
if (staged) cleanupStagedSkills();
}
} finally {
cleanup(dir);
}
});
test('marker disagreement across runtimes → mostRestrictiveProfile picks smaller set', () => {
const dirA = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-rtA-'));
const dirB = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-rtB-'));
try {
writeActiveProfile(dirA, 'standard');
writeActiveProfile(dirB, 'core');
const profileA = readActiveProfile(dirA) || 'full';
const profileB = readActiveProfile(dirB) || 'full';
const resolved = mostRestrictiveProfile([profileA, profileB]);
assert.strictEqual(resolved, 'core',
'core is smaller than standard — most-restrictive wins');
} finally {
cleanup(dirA);
cleanup(dirB);
}
});
test('explicit --profile=full overrides restrictive marker (no narrowing)', () => {
const dir = fs.mkdtempSync(path.join(os.tmpdir(), 'gsd-override-'));
try {
writeActiveProfile(dir, 'core');
const effective = resolveEffectiveProfile({ requestedProfileName: 'full', targetDir: dir });
assert.strictEqual(effective, 'full');
const manifest = loadSkillsManifest(REAL_COMMANDS_DIR);
const resolved = resolveProfile({ modes: [effective], manifest });
assert.strictEqual(resolved.skills, '*', 'full profile should be sentinel');
} finally {
cleanup(dir);
}
});
});