config-audit/tests/scanners/posture-grade-stability.test.mjs
Kjell Tore Guttormsen 66433fee48 feat(skill-listing): add CA-SKL-002 aggregate listing-budget check
Syklus 2 of Fase 4 Items 2+3. Flags when the sum of active skill
descriptions exceeds the listing budget (~2% of context, CC 2.1.32).

Design (operator-confirmed "fact-first, 200k anchor"):
- low severity (estimate) vs medium for the verified 1,536-char cap
- each description counted up to the 1,536 cap (what actually loads in
  the listing) — avoids double-counting the tail CA-SKL-001 flags
- fires when sum > 2% x 200k = 4000 tok; evidence leads with the measured
  sum + a calibration note that the budget scales 5x on 1M-context models
- aggregate emitted after the per-skill loop so the common case reads
  001=cap, 002=aggregate (finding IDs are a sequential counter, not stable
  semantic IDs — tests match on title, never NNN)

Also:
- tailored humanizer static entry for the aggregate title
- fix latent HOME leak in posture-grade-stability.test.mjs: it spawned
  posture.mjs without hermeticEnv(), so a real ~/.claude leaked HOME-scoped
  SKL/COL findings into the baseline grade (Token Efficiency A->B). Now
  isolated like the 8 other CLI-spawning tests.
- docs sync: test count 868->875, scanner-internals, gap-matrix, plan status

Suite 875/875, no snapshot drift, self-audit clean.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01Ter3E2JSi1Khgmuf2kady8
2026-06-18 18:06:17 +02:00

57 lines
2.3 KiB
JavaScript

import { describe, it, beforeEach } from 'node:test';
import assert from 'node:assert/strict';
import { resolve } from 'node:path';
import { fileURLToPath } from 'node:url';
import { execFile } from 'node:child_process';
import { promisify } from 'node:util';
import { hermeticEnv } from '../helpers/hermetic-home.mjs';
const exec = promisify(execFile);
const __dirname = fileURLToPath(new URL('.', import.meta.url));
const FIXTURES = resolve(__dirname, '../fixtures');
const POSTURE_BIN = resolve(__dirname, '../../scanners/posture.mjs');
async function runPostureJson(fixturePath) {
// Isolate HOME: SKL and COL are HOME-scoped (enumerateSkills/enumeratePlugins),
// so a real ~/.claude would leak the developer's installed plugins/skills into
// this baseline grade and make it machine-dependent. See tests/helpers/hermetic-home.mjs.
const { stdout } = await exec('node', [POSTURE_BIN, fixturePath, '--json'], {
timeout: 30000,
cwd: resolve(__dirname, '../..'),
env: hermeticEnv(),
});
return JSON.parse(stdout);
}
describe('posture grade stability — baseline-all-a', () => {
let result;
beforeEach(async () => {
result = await runPostureJson(resolve(FIXTURES, 'baseline-all-a'));
});
it('overallGrade is A', () => {
assert.equal(result.overallGrade, 'A');
});
it('every quality area (non-Feature Coverage) has grade A', () => {
const qualityAreas = result.areas.filter(a => a.name !== 'Feature Coverage');
for (const area of qualityAreas) {
assert.equal(area.grade, 'A', `${area.name} has grade ${area.grade}, expected A (score=${area.score})`);
}
});
it('has no critical or high findings across scanners', () => {
const scanners = result.scannerEnvelope.scanners;
for (const s of scanners) {
assert.equal(s.counts.critical, 0, `${s.scanner} has ${s.counts.critical} critical findings`);
assert.equal(s.counts.high, 0, `${s.scanner} has ${s.counts.high} high findings`);
}
});
it('Token Efficiency area scores grade A or B on baseline', () => {
const te = result.areas.find(a => a.id === 'token_efficiency');
assert.ok(te, 'expected token_efficiency area to be present');
assert.ok(['A', 'B'].includes(te.grade),
`Token Efficiency grade is ${te.grade}, expected A or B (score=${te.score})`);
});
});