CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-13 08:29:04 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: touchfiles, tiers, shim E2E, real-engine fixture

Browse Source 
Touchfiles: the catalog, contract, detector bin, checklist resolver, review-
army resolver, and DESIGN.md lib join the dep lists of review-design-lite,
design-review-fix, the design-consultation cases, and plan-design-review-no-
ui-scope, so editing any of them re-selects the tests that read their output.
Three new E2E keys: design-review-detector-shim (gate; source mode on a
feature-branch diff), design-review-detector-shim-dom (gate; DOM mode: the
slop fixture served on loopback, dumped through the browse binary with
lib/dom-dump.js, persisted under a GSTACK_HOME-scoped REPORT_DIR, scanned once;
self-skips when browse/dist/browse is absent), and design-html-slop-gate
(periodic; one fix pass, at most two scans, remaining findings accepted with
reason). Every case reaches the engine through test/fixtures/fake-impeccable.ts
via IMPECCABLE_BIN from outside the temp repo, reads extracted skill sections
(never a whole SKILL.md) with the installed bin path rewritten to this
checkout, and asserts the probe ran, the right scan verb ran, `npx impeccable`
never did, and the output carries FINDING rows tagged [ai-color-palette] and
[low-contrast]. review-design-lite gets the fake engine and an eighth tally
signal for a detector row; its 4-hit threshold is unchanged.

test/gstack-design-detect.test.ts evaluates design-review's REPORT_DIR
expression with GSTACK_HOME set and proves a dump under it is accepted by the
wrapper's allow-list. The sample fixtures were real captures from commit 1
(engine 0.1.3), so there is nothing hand-written left to swap.

Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
2026-09-08 16:38:46 +00:00
co-authored by Claude Fable 5.1
parent f1ce46eb8b
commit 9a03aa5e4a
6 changed files with 289 additions and 11 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/touchfiles-data.ts
+12 -5
View File
@@ -66,7 +66,7 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
'review-sql-injection': ['review/**', 'test/fixtures/review-eval-vuln.rb', 'test/skill-e2e-review.test.ts'],
'review-enum-completeness': ['review/**', 'test/fixtures/review-eval-enum*.rb', 'test/skill-e2e-review.test.ts'],
'review-base-branch': ['review/**', 'test/skill-e2e-review-attribution.test.ts'],
'review-design-lite': ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-review.test.ts'],
'review-design-lite': ['review/**', 'test/fixtures/review-eval-design-slop.*', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'lib/design-catalog.ts', 'lib/design-detect-contract.ts', 'bin/gstack-design-detect.ts', 'scripts/resolvers/design-checklist.ts', 'scripts/resolvers/review-army.ts', 'test/skill-e2e-review.test.ts'],
// Review Army (specialist dispatch)
'review-army-migration-safety': ['review/**', 'scripts/resolvers/review-army.ts', 'bin/gstack-diff-scope', 'test/skill-e2e-review-army.test.ts'],
@@ -305,12 +305,16 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
],
// Design
'design-consultation-core': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-existing': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-core': ['design-consultation/**', 'lib/design-catalog.ts', 'lib/design-md.ts', 'scripts/gen-skill-docs.ts', 'test/helpers/llm-judge.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-existing': ['design-consultation/**', 'lib/design-md.ts', 'bin/gstack-design-md.ts', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-research': ['design-consultation/**', 'scripts/resolvers/aside.ts', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-consultation-preview': ['design-consultation/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-review-fix': ['design-review/**', 'scripts/resolvers/aside.ts', 'scripts/resolvers/design.ts', 'browse/src/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'plan-design-review-no-ui-scope': ['plan-design-review/**', 'lib/design-catalog.ts', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
'design-review-fix': ['design-review/**', 'scripts/resolvers/aside.ts', 'scripts/resolvers/design.ts', 'lib/design-catalog.ts', 'browse/src/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-design.test.ts'],
// Design detector (user-installed impeccable engine) through the fake engine shim: source mode on a diff and DOM mode on a served page.
'design-review-detector-shim': ['design-review/**', 'scripts/resolvers/design.ts', 'lib/design-catalog.ts', 'lib/design-detect-contract.ts', 'lib/dom-dump-script.ts', 'lib/dom-dump.js', 'bin/gstack-design-detect.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-design.test.ts'],
'design-review-detector-shim-dom': ['design-review/**', 'scripts/resolvers/design.ts', 'lib/design-detect-contract.ts', 'lib/dom-dump-script.ts', 'lib/dom-dump.js', 'bin/gstack-design-detect.ts', 'browse/src/**', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/fixtures/review-eval-design-slop.*', 'test/skill-e2e-design.test.ts'],
'design-html-slop-gate': ['design-html/**', 'scripts/resolvers/design.ts', 'lib/design-detect-contract.ts', 'bin/gstack-design-detect.ts', 'test/fixtures/fake-impeccable.ts', 'test/fixtures/impeccable-detect-sample.json', 'test/skill-e2e-design.test.ts'],
// /diagram (diagram-render bundle consumers). Triplet = deterministic
// functional (gate); authoring quality = LLM-judged benchmark (periodic).
@@ -738,6 +742,9 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
'design-consultation-preview': 'periodic', // D2a demotion 2026-08 ($0.89/481s)
'plan-design-review-no-ui-scope': 'gate',
'design-review-fix': 'periodic',
'design-review-detector-shim': 'gate', // deterministic sentinels from the fake engine (source mode on a diff)
'design-review-detector-shim-dom': 'gate', // same shim, DOM mode through the browse binary's dump; self-skips when the binary is absent
'design-html-slop-gate': 'periodic', // one-pass gate behavior is a judgment call on a fake engine's fixed output
// /diagram — triplet is deterministic functional (gstack-render falls back
// to the browse daemon, so CI runs it); judge is a quality benchmark