config-audit/tests/scanners/cli-humanizer.test.mjs
Kjell Tore Guttormsen 4027cdcf54 fix(scanners): retire the autoMode GAP dimension, a /doctor duplicate (D1)
CC 2.1.226's /doctor Check 8 covers auto mode with usage-weighted judgement.
The binding positioning forbids carrying a feature whose whole value is
duplicating a /doctor check, so the "adopt this feature" nudge goes. The
deterministic side stays: SET still validates autoMode structure and still
flags it as dead config in shared project settings. GAP dimensions 25 -> 24.

The title lived in FOUR tables, not the two the removal was scoped against:
the dimension list, scoring TITLE_TO_ID, the humanizer's static translations,
and the scoring denominators (TIER_COUNTS t3 8->7, TOTAL_DIMENSIONS 25->24,
MAX_WEIGHTED 42->41) -- the one that moves a user-visible number. findGapId
falls back to 'unknown' silently, so a partial removal would have degraded
without failing. A blanket sync invariant now asserts all four against
GAP_CHECKS instead of comparing occurrences pairwise; each arm was verified
red against its own defect (denominator drift, orphaned humanizer entry,
resurrected dimension).

Frozen tests/snapshots/v5.0.0/ stays untouched. strip-retired-gap.mjs is the
removal twin of strip-added-scanner.mjs: it strips the retired dimension from
whichever side still carries it and re-derives GAP IDs, since retiring a
dimension from mid-list shifts every later ID by one. Derived utilization
figures are dropped from comparison rather than recomputed -- recomputing them
in a test helper would assert the new arithmetic against itself, and
scoring.test.mjs already pins them exactly. Re-seeding was rejected: it would
silently bake in any other drift across every scanner those four files cover.

risk_score, risk_band, verdict, overallGrade, maturity and segment are
byte-identical across the change (severity info carries zero risk weight; GAP
is excluded from the overall grade). Utilization shifts 43 -> 44 on the fixture.

D2 (CA-SKL-002) is NOT removed. Verified against the primary source first: the
CC changelog carries exactly one budget-fraction statement (L3786, 2.1.32) and
nothing supersedes it, so our 2% is current and 002 is not a duplicate with a
stale figure. /doctor's ~1% could not be reconciled from the changelog and it
discloses its own numbers as disk estimates, so it is recorded, not adopted.
Left explicitly unverified in a code note: L3786 says "character budget" while
we express tokens -- a 4x difference nobody can settle from the wording.

Suite 1531 -> 1535, all green.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01RsfPGxgwbR3MY54wDC6hat
2026-08-09 22:43:04 +02:00

339 lines
13 KiB
JavaScript

import { describe, it } from 'node:test';
import assert from 'node:assert/strict';
import { resolve, dirname } from 'node:path';
import { fileURLToPath } from 'node:url';
import { execFile } from 'node:child_process';
import { promisify } from 'node:util';
import { readFile, writeFile, unlink, mkdir, access } from 'node:fs/promises';
import { hermeticEnv, HERMETIC_HOME } from '../helpers/hermetic-home.mjs';
import { stripHotspotLoadPattern } from '../helpers/strip-hotspot-load-pattern.mjs';
import { stripRetiredGap } from '../helpers/strip-retired-gap.mjs';
const exec = promisify(execFile);
const __dirname = dirname(fileURLToPath(import.meta.url));
const REPO = resolve(__dirname, '../..');
const FIXTURE = resolve(REPO, 'tests/fixtures/marketplace-medium');
const BROKEN_PLUGIN = resolve(REPO, 'tests/fixtures/broken-plugin');
const BASELINE_DIR = resolve(HERMETIC_HOME, '.config-audit/baselines');
const DEFAULT_BASELINE = resolve(BASELINE_DIR, 'default.json');
/**
* Run a CLI subprocess and return stdout/stderr regardless of exit code
* (some CLIs exit non-zero on findings — we still need their output).
*/
async function runCli(cliPath, args, env = {}) {
try {
const { stdout, stderr } = await exec('node', [cliPath, ...args], {
timeout: 60000,
cwd: REPO,
env: hermeticEnv(env),
maxBuffer: 10 * 1024 * 1024,
});
return { stdout: stdout || '', stderr: stderr || '', code: 0 };
} catch (err) {
return {
stdout: err.stdout || '',
stderr: err.stderr || '',
code: err.code ?? 1,
};
}
}
/** Strip time-varying duration_ms / Xms occurrences for snapshot comparison. */
function normalizeTokenHotspotsPayload(p) {
const out = JSON.parse(JSON.stringify(p));
out.duration_ms = 0;
return stripRetiredGap(stripHotspotLoadPattern(out));
}
function normalizeManifestOutput(o) {
const out = JSON.parse(JSON.stringify(o));
if (out.meta) {
out.meta.repoPath = '<TARGET>';
out.meta.generatedAt = '<TIMESTAMP>';
out.meta.durationMs = 0;
}
return out;
}
function normalizeWhatsActiveOutput(o) {
const out = JSON.parse(JSON.stringify(o));
if (out.meta) {
out.meta.repoPath = '<TARGET>';
out.meta.generatedAt = '<TIMESTAMP>';
out.meta.durationMs = 0;
if (out.meta.gitRoot) out.meta.gitRoot = '<GITROOT>';
if (out.meta.projectKey) out.meta.projectKey = '<PROJECTKEY>';
}
return out;
}
function normalizePluginHealthOutput(o) {
const out = JSON.parse(JSON.stringify(o));
out.duration_ms = 0;
return out;
}
function normalizeDriftOutput(o) {
// Drift result has no time fields; just round-trip through JSON.
return stripRetiredGap(JSON.parse(JSON.stringify(o)));
}
// ============================================================================
// token-hotspots-cli
// ============================================================================
describe('token-hotspots-cli humanizer (Step 7)', () => {
const CLI = resolve(REPO, 'scanners/token-hotspots-cli.mjs');
const SNAPSHOT = resolve(REPO, 'tests/snapshots/v5.0.0/token-hotspots.json');
it('--json: payload.findings byte-equal v5.0.0 snapshot', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(
normalizeTokenHotspotsPayload(actual),
normalizeTokenHotspotsPayload(expected),
);
});
it('--raw: payload.findings byte-equal v5.0.0 snapshot', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--raw']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(
normalizeTokenHotspotsPayload(actual),
normalizeTokenHotspotsPayload(expected),
);
});
it('default: payload.findings include humanizer fields when findings exist', async () => {
const { stdout } = await runCli(CLI, [FIXTURE]);
const actual = JSON.parse(stdout);
if (actual.findings.length === 0) return;
for (const f of actual.findings) {
assert.equal(typeof f.userImpactCategory, 'string',
`${f.id}: default mode must add userImpactCategory`);
assert.equal(typeof f.userActionLanguage, 'string',
`${f.id}: default mode must add userActionLanguage`);
assert.equal(typeof f.relevanceContext, 'string',
`${f.id}: default mode must add relevanceContext`);
}
});
it('--json: payload.findings do NOT carry humanizer fields', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const actual = JSON.parse(stdout);
for (const f of actual.findings) {
assert.equal(f.userImpactCategory, undefined,
`${f.id}: --json must not add userImpactCategory`);
}
});
});
// ============================================================================
// plugin-health-scanner
//
// NOTE: plugin-health scans the plugin root (not the fixture path), so its
// findings reflect the current marketplace state — snapshot frozen at Wave 0
// no longer matches as new plugins are added. We verify mode-equivalence
// (--json == --raw) instead.
// ============================================================================
describe('plugin-health-scanner humanizer (Step 7)', () => {
const CLI = resolve(REPO, 'scanners/plugin-health-scanner.mjs');
it('--json and --raw produce byte-identical stdout (both bypass humanizer)', async () => {
const { stdout: jsonOut } = await runCli(CLI, [FIXTURE, '--json']);
const { stdout: rawOut } = await runCli(CLI, [FIXTURE, '--raw']);
assert.deepStrictEqual(
normalizePluginHealthOutput(JSON.parse(jsonOut)),
normalizePluginHealthOutput(JSON.parse(rawOut)),
);
});
it('--json output preserves v5.0.0 finding shape (no humanizer fields)', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const actual = JSON.parse(stdout);
for (const f of actual.findings || []) {
assert.equal(f.userImpactCategory, undefined,
`${f.id}: --json must not add userImpactCategory`);
}
});
it('default mode renders to stderr (humanized when findings exist)', async () => {
const { stderr: defaultStderr } = await runCli(CLI, [BROKEN_PLUGIN]);
const { stderr: rawStderr } = await runCli(CLI, [BROKEN_PLUGIN, '--raw']);
// --raw suppresses prose stderr (machine mode); default emits humanized prose.
// Just verify both run without crash; humanization assertion is best-effort
// because broken-plugin may produce no PLH-translated findings.
assert.ok(typeof defaultStderr === 'string');
assert.ok(typeof rawStderr === 'string');
});
});
// ============================================================================
// drift-cli
// ============================================================================
describe('drift-cli humanizer (Step 7)', () => {
const CLI = resolve(REPO, 'scanners/drift-cli.mjs');
const SNAPSHOT = resolve(REPO, 'tests/snapshots/v5.0.0/drift.json');
async function ensureBaseline() {
try {
await access(DEFAULT_BASELINE);
return true;
} catch {
// Try to save one
try {
await mkdir(BASELINE_DIR, { recursive: true });
await runCli(CLI, [FIXTURE, '--save']);
await access(DEFAULT_BASELINE);
return true;
} catch {
return false;
}
}
}
it('--json: diff byte-equal v5.0.0 snapshot', async () => {
const ok = await ensureBaseline();
if (!ok) {
// SKIP — baseline cannot be created in this environment.
return;
}
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(
normalizeDriftOutput(actual),
normalizeDriftOutput(expected),
);
});
it('--raw: diff byte-equal v5.0.0 snapshot', async () => {
const ok = await ensureBaseline();
if (!ok) return;
const { stdout } = await runCli(CLI, [FIXTURE, '--raw']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(
normalizeDriftOutput(actual),
normalizeDriftOutput(expected),
);
});
it('default: stderr report differs from --raw stderr when findings exist', async () => {
const ok = await ensureBaseline();
if (!ok) return;
const { stderr: defaultStderr } = await runCli(CLI, [FIXTURE]);
const { stderr: rawStderr } = await runCli(CLI, [FIXTURE, '--raw']);
// If there are findings whose titles get humanized, default stderr differs from raw.
// If no humanizable titles in this fixture, both can match — just verify no crash.
assert.ok(typeof defaultStderr === 'string');
assert.ok(typeof rawStderr === 'string');
});
});
// ============================================================================
// manifest
//
// NOTE: manifest scans the active config cascade (env-dependent), so the
// frozen v5.0.0 snapshot drifts as the marketplace changes. We verify
// --json == --raw == default (no-op for inventory) instead.
// ============================================================================
describe('manifest humanizer (Step 7) — no-op for --raw', () => {
const CLI = resolve(REPO, 'scanners/manifest.mjs');
it('--json and --raw produce byte-identical output', async () => {
const { stdout: jsonOut } = await runCli(CLI, [FIXTURE, '--json']);
const { stdout: rawOut } = await runCli(CLI, [FIXTURE, '--raw']);
assert.deepStrictEqual(
normalizeManifestOutput(JSON.parse(jsonOut)),
normalizeManifestOutput(JSON.parse(rawOut)),
);
});
it('default and --raw produce structurally identical output (inventory CLI)', async () => {
const { stdout: defaultOut } = await runCli(CLI, [FIXTURE]);
const { stdout: rawOut } = await runCli(CLI, [FIXTURE, '--raw']);
assert.deepStrictEqual(
normalizeManifestOutput(JSON.parse(defaultOut)),
normalizeManifestOutput(JSON.parse(rawOut)),
);
});
it('preserves v5.0.0 envelope shape', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const out = JSON.parse(stdout);
assert.ok(out.meta);
assert.ok(Array.isArray(out.sources));
assert.equal(typeof out.total, 'number');
});
});
// ============================================================================
// whats-active
//
// NOTE: whats-active scans the active config (env-dependent). Frozen snapshot
// drifts; we verify mode-equivalence instead.
// ============================================================================
describe('whats-active humanizer (Step 7) — no-op for --raw', () => {
const CLI = resolve(REPO, 'scanners/whats-active.mjs');
it('--json and --raw produce byte-identical output', async () => {
const { stdout: jsonOut } = await runCli(CLI, [FIXTURE, '--json']);
const { stdout: rawOut } = await runCli(CLI, [FIXTURE, '--raw']);
assert.deepStrictEqual(
normalizeWhatsActiveOutput(JSON.parse(jsonOut)),
normalizeWhatsActiveOutput(JSON.parse(rawOut)),
);
});
it('default and --raw produce structurally identical output (inventory CLI)', async () => {
const { stdout: defaultOut } = await runCli(CLI, [FIXTURE]);
const { stdout: rawOut } = await runCli(CLI, [FIXTURE, '--raw']);
assert.deepStrictEqual(
normalizeWhatsActiveOutput(JSON.parse(defaultOut)),
normalizeWhatsActiveOutput(JSON.parse(rawOut)),
);
});
it('preserves v5.0.0 envelope shape', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const out = JSON.parse(stdout);
assert.ok(out.meta);
assert.ok(out.claudeMd);
assert.ok(Array.isArray(out.plugins));
assert.ok(Array.isArray(out.skills));
});
});
// ============================================================================
// fix-cli
// ============================================================================
describe('fix-cli humanizer (Step 7)', () => {
const CLI = resolve(REPO, 'scanners/fix-cli.mjs');
const SNAPSHOT = resolve(REPO, 'tests/snapshots/v5.0.0/fix-cli.json');
it('--json: stdout JSON byte-equal v5.0.0 snapshot', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--json']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(stripRetiredGap(actual), stripRetiredGap(expected));
});
it('--raw: stdout JSON byte-equal v5.0.0 snapshot', async () => {
const { stdout } = await runCli(CLI, [FIXTURE, '--raw']);
const actual = JSON.parse(stdout);
const expected = JSON.parse(await readFile(SNAPSHOT, 'utf-8'));
assert.deepStrictEqual(stripRetiredGap(actual), stripRetiredGap(expected));
});
it('default mode stderr differs from --raw stderr when findings have humanizer translations', async () => {
const { stderr: defaultStderr } = await runCli(CLI, [FIXTURE]);
const { stderr: rawStderr } = await runCli(CLI, [FIXTURE, '--raw']);
// 20 manual findings in fixture; many have GAP translations → stderr differs.
assert.notEqual(defaultStderr, rawStderr,
'fix-cli default stderr must differ from --raw stderr when humanizer translates titles');
});
});