Files
gstack/test/design-detect-contract.test.ts
T
Garry TanandClaude Fable 5.1 3522073ef0 feat(design): {{DESIGN_DETECTOR}} wired into design-review, ship review-lite, review army, design-html
The user-installed impeccable engine becomes a deterministic pre-pass in four
skills, through one resolver with three renders: {{DESIGN_DETECTOR}} (the probe
block and how to read every sentinel), {{DESIGN_DETECTOR:phase0}} (design-
review's mechanical scan), {{DESIGN_DETECTOR:gate}} (design-html's bounded slop
gate). Every rendered invocation is `bun --no-env-file run <bin>/gstack-design-
detect.ts ... --host <host>` and every scan ends with the DETECT_EXIT_CODE echo
so exit 2 (findings) never aborts a block.

design-review: probe in Setup; Phase 0 picks DOM mode (URL target) or source
mode (diff-aware, no URL) once; source mode scans the changed frontend files in
Setup, DOM mode never reads source (Rule 4). Phase 3 gains a DOM-dump step per
page: both browser engines load the shared script from lib/dom-dump.js (Aside
splices it into a double-quoted repl script; the fallback engine copies it into
a temp dir for `$B eval --out --raw`), the dump is size-capped, run through
gstack-redact (a HIGH finding skips the page), and persisted under
$REPORT_DIR/dom/$RUN_ID/; one scan runs after the last page, labeled "static
scan of the rendered DOM; cross-origin CSS not resolved". REPORT_DIR honors
GSTACK_HOME so the wrapper's allow-list and the report dir agree; RUN_ID is set
once in Setup. design-baseline.json is schemaVersion 2 with runId, targetSet,
base, and a detector block (mode, engine, byRule, byPage), written temp+rename
with a per-run copy; Regression Output diffs ids only when mode and target set
match, caveats an engine change, and calls live-page count deltas advisory.
Phase 7 hands deferred detector findings to the `handoff=` command the scan
printed; Phase 9 recomputes the same way and deletes the dumps unless
--keep-dom; Phase 10 reports `Detector: N → M`.

ship review-lite gains step 0 (probe, `scan --changed <base>`, tier buckets,
detector + checklist dedupe, advisory and ignored never count) and a
`detector` count in its log payload; the PR body gets a Detector line (rule
ids and counts only). The Review Army Design specialist runs the mechanical
pass at the top of review/design-checklist.md, which now carries it. design-
html probes after DESIGN_SETUP and runs the one-pass gate before screenshots.

lib/dom-dump.js is generated by gen-skill-docs from lib/dom-dump-script.ts
(Claude host, --out-dir aware, dry-run freshness) and pinned byte-equal, so the
prose never carries the script. The contract gains DETECT_JSON, DOM_DUMP_OK,
and the self-describing set; its test now checks both directions.

Budget: design-review eager 25.6K → 28.5K. The plan's target was +2.5K; after
the levers it named (ids-only detector rules, no inline script, trimmed prose)
it lands at +2.87K, and the remainder is doctrine and detector wiring, so the
ceiling moves to the captured 31,319 for design-review only (the full capture
would also have loosened 21 ceilings this branch never touched; those stay).
design-html skeleton re-baselined to 54,000 (measured 53,592). Codex and
Factory ship goldens refreshed (review-lite step 0 and the PR-body line render
inline there).

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
2026-09-08 16:14:03 +00:00

103 lines
5.6 KiB
TypeScript

/**
* lib/design-detect-contract.ts is the one owner of the detector vocabulary.
* Forward direction: every sentinel-shaped token (IMPECCABLE_*, DETECT_*,
* DESIGN_MD_*, DOM_DUMP_*) that appears in something the agent reads
* (generated SKILL.md files, sections, the design checklist, the resolvers)
* must be a contract constant, so prose cannot invent a sentinel the bin never
* prints. Reverse direction (every printable sentinel is mentioned somewhere
* the agent reads) lands with the DESIGN_DETECTOR resolver wiring.
*/
import { describe, test, expect } from 'bun:test';
import * as fs from 'fs';
import * as path from 'path';
import { spawnSync } from 'child_process';
import { SENTINEL, TESTED_ENGINE_VERSIONS, ADVISORY_RULE_IDS, DETECT_LIMITS, DETECT_EXIT_ECHO, SELF_DESCRIBING_SENTINELS } from '../lib/design-detect-contract';
import { ADVISORY_RULE_IDS as _a } from '../lib/design-detect-contract';
import { catalogEntry } from '../lib/design-catalog';
const ROOT = path.join(import.meta.dir, '..');
const TOKEN = /\b(IMPECCABLE_[A-Z_]+|DETECT_[A-Z_]+|DESIGN_MD_[A-Z_]+|DOM_DUMP_[A-Z_]+|DESIGN_DETECTOR_[A-Z_]+|DESIGN_DETECT_[A-Z_]+)\b/g;
// Things that look like sentinels but are env vars / flags the prose legitimately names.
const NOT_SENTINELS = new Set(['IMPECCABLE_BIN', 'IMPECCABLE_HOME', 'IMPECCABLE_HOOK_DISABLED', 'DESIGN_DETECT_TIMEOUT_MS']);
function* agentReadableFiles(): Generator<string> {
const skip = new Set(['node_modules', '.git', 'dist', 'build', 'test', 'docs', '.context', '.claude', '.agents', '.factory', '.cursor', '.kiro', '.opencode', '.openclaw', '.hermes', '.slate', '.gstack', '.gbrain', '.conductor']);
const stack = [ROOT];
while (stack.length) {
const cur = stack.pop()!;
for (const ent of fs.readdirSync(cur, { withFileTypes: true })) {
if (ent.isSymbolicLink()) continue;
const full = path.join(cur, ent.name);
if (ent.isDirectory()) { if (!skip.has(ent.name) || cur !== ROOT) { if (!skip.has(ent.name)) stack.push(full); } continue; }
if (/\.(md|tmpl|ts)$/.test(ent.name) && (full.includes(`${path.sep}scripts${path.sep}resolvers${path.sep}`) || ent.name.endsWith('.md') || ent.name.endsWith('.tmpl'))) yield full;
}
}
}
describe('contract shape', () => {
test('sentinel values are unique, uppercase, and equal their own prefix family', () => {
const values = Object.values(SENTINEL);
expect(new Set(values).size).toBe(values.length);
for (const v of values) expect(v).toMatch(/^[A-Z][A-Z_]+$/);
});
test('tested engine versions and advisory ids are consistent with the fixtures and catalog', () => {
const meta = JSON.parse(fs.readFileSync(path.join(ROOT, 'test', 'fixtures', 'impeccable-captures.meta.json'), 'utf-8'));
expect(TESTED_ENGINE_VERSIONS).toContain(meta.engine.version);
for (const id of ADVISORY_RULE_IDS) {
const e = catalogEntry(id);
expect(e).toBeDefined();
expect(e!.tier).toBe('possible');
expect(e!.impact).toBe('polish');
}
expect(_a).toBe(ADVISORY_RULE_IDS);
});
test('limits are positive and the exit echo carries the DETECT_EXIT_CODE sentinel', () => {
expect(DETECT_LIMITS.timeoutMs).toBeGreaterThan(0);
expect(DETECT_LIMITS.batch).toBeGreaterThan(0);
expect(DETECT_LIMITS.findings).toBeGreaterThan(DETECT_LIMITS.topLocations);
expect(DETECT_EXIT_ECHO).toBe(`; echo "${SENTINEL.DETECT_EXIT_CODE}=$?"`);
});
test('module is pure: no imports, loading prints nothing', () => {
const file = path.join(ROOT, 'lib', 'design-detect-contract.ts');
expect(fs.readFileSync(file, 'utf-8')).not.toMatch(/^import /m);
const r = spawnSync(process.execPath, ['--no-env-file', '-e', `await import(${JSON.stringify(file)})`], { encoding: 'utf-8', timeout: 30_000 });
expect(r.status).toBe(0);
expect(r.stdout + r.stderr).toBe('');
});
});
describe('every printable sentinel is mentioned somewhere the agent reads', () => {
// DESIGN_MD_* sentinels arrive with the DESIGN.md tool wiring; until then they are contract-only.
const PENDING = new Set<string>([SENTINEL.DESIGN_MD_FORMAT, SENTINEL.DESIGN_MD_CONVERT_REFUSED, SENTINEL.DESIGN_MD_INTERNAL_ERROR, SENTINEL.DESIGN_MD_TOKEN_REF_INVALID]);
test('generated SKILL.md files, sections, or the checklist name each one', () => {
const corpus = [...agentReadableFiles()].filter(f => !f.includes(`${path.sep}scripts${path.sep}`)).map(f => fs.readFileSync(f, 'utf-8')).join('\n');
const selfDescribing = new Set(SELF_DESCRIBING_SENTINELS);
const missing = Object.values(SENTINEL).filter(v => !PENDING.has(v) && !selfDescribing.has(v) && !corpus.includes(v));
expect(missing).toEqual([]);
// self-describing ones are still contract-owned and still printed by the bin
for (const v of SELF_DESCRIBING_SENTINELS) expect(Object.values(SENTINEL)).toContain(v);
});
});
describe('every sentinel-shaped token the agent can read exists in the contract', () => {
test('generated docs, sections, templates, resolvers, and the checklist', () => {
const known = new Set<string>(Object.values(SENTINEL));
const offenders: string[] = [];
// Resolvers are scanned for the strings they render, not their identifiers:
// an exported contract name (DETECT_EXIT_ECHO, DETECT_LIMITS) is not a sentinel.
for (const file of agentReadableFiles()) {
if (file.includes(`${path.sep}scripts${path.sep}`)) continue;
const text = fs.readFileSync(file, 'utf-8');
for (const m of text.matchAll(TOKEN)) {
const tok = m[1];
if (known.has(tok) || NOT_SENTINELS.has(tok)) continue;
offenders.push(`${path.relative(ROOT, file)}: ${tok}`);
}
}
expect(offenders).toEqual([]);
});
});