mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-14 00:49:00 +02:00
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>
This commit is contained in:
co-authored by
Claude Fable 5.1
parent
3867dae355
commit
3522073ef0
@@ -11,7 +11,7 @@ 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 } from '../lib/design-detect-contract';
|
||||
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';
|
||||
|
||||
@@ -69,11 +69,27 @@ describe('contract shape', () => {
|
||||
});
|
||||
});
|
||||
|
||||
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];
|
||||
|
||||
Reference in New Issue
Block a user