mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-15 01:15:29 +02:00
test: registries, budgets and suite reconciled for Aside-first with the $B fallback
Touchfiles + E2E tiers gain the Aside keys, coverage matrix and eval baselines updated, size budget re-baselined to parity-baseline-v1.80.0.0.json (the contract plus fallback ride in every browsing skill), parity ceilings ratcheted with measured values, LLM-judge prompts and the E2E fixtures speak Aside-first, browse-fallback. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Sina
@@ -25,6 +25,14 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'browse-basic': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
|
||||
'browse-snapshot': ['browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-bws.test.ts'],
|
||||
|
||||
// Aside-driven browsing skills — live E2E against the Aside AI browser, the
|
||||
// primary browser (test/skill-e2e-aside.test.ts self-skips without a running Aside)
|
||||
'aside-browse-basic': ['browse/**', 'scripts/resolvers/browse.ts', 'scripts/resolvers/aside.ts', 'browse/test/test-server.ts', 'browse/test/fixtures/basic.html', 'test/helpers/aside-available.ts', 'test/skill-e2e-aside.test.ts'],
|
||||
'aside-browse-flow': ['browse/**', 'scripts/resolvers/browse.ts', 'scripts/resolvers/aside.ts', 'browse/test/test-server.ts', 'browse/test/fixtures/forms.html', 'test/helpers/aside-available.ts', 'test/skill-e2e-aside.test.ts'],
|
||||
'aside-qa-quick': ['qa/**', 'scripts/resolvers/browse.ts', 'scripts/resolvers/aside.ts', 'browse/test/test-server.ts', 'browse/test/fixtures/basic.html', 'test/helpers/aside-available.ts', 'test/skill-e2e-aside.test.ts'],
|
||||
'aside-scrape-json': ['scrape/**', 'scripts/resolvers/aside.ts', 'browse/test/test-server.ts', 'browse/test/fixtures/basic.html', 'test/helpers/aside-available.ts', 'test/skill-e2e-aside.test.ts'],
|
||||
'aside-canary-quick': ['canary/**', 'scripts/resolvers/aside.ts', 'browse/test/test-server.ts', 'browse/test/fixtures/basic.html', 'test/helpers/aside-available.ts', 'test/skill-e2e-aside.test.ts'],
|
||||
|
||||
// Hermetic isolation canaries (hermetic-env.ts is also a GLOBAL touchfile;
|
||||
// these entries exist so the canaries themselves stay tier-classified)
|
||||
'hermetic-canary': ['test/helpers/hermetic-env.ts', 'test/helpers/session-runner.ts', 'test/skill-e2e-hermetic-canary.test.ts', 'lib/conductor-env-shim.ts'],
|
||||
@@ -44,13 +52,14 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'session-awareness': ['SKILL.md', 'SKILL.md.tmpl', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-bws.test.ts'],
|
||||
'operational-learning': ['scripts/resolvers/preamble.ts', 'bin/gstack-learnings-log', 'test/skill-e2e-bws.test.ts'],
|
||||
|
||||
// QA (+ test-server dependency)
|
||||
'qa-quick': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
'qa-b6-static': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-b7-spa': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-b8-checkout': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-only-no-fix': ['qa-only/**', 'qa/templates/**', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
'qa-fix-loop': ['qa/**', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
// QA (+ test-server dependency). /qa drives Aside first (the resolver) and
|
||||
// the browse binary as fallback (browse/src), so both are deps.
|
||||
'qa-quick': ['qa/**', 'scripts/resolvers/browse.ts', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
'qa-b6-static': ['qa/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval.html', 'test/fixtures/qa-eval-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-b7-spa': ['qa/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-spa.html', 'test/fixtures/qa-eval-spa-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-b8-checkout': ['qa/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/helpers/llm-judge.ts', 'browse/test/fixtures/qa-eval-checkout.html', 'test/fixtures/qa-eval-checkout-ground-truth.json', 'test/skill-e2e-qa-bugs.test.ts'],
|
||||
'qa-only-no-fix': ['qa-only/**', 'qa/templates/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
'qa-fix-loop': ['qa/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'browse/test/test-server.ts', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
'qa-bootstrap': ['qa/**', 'ship/**', 'test/skill-e2e-qa-workflow.test.ts'],
|
||||
|
||||
// Review
|
||||
@@ -298,15 +307,19 @@ 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-research': ['design-consultation/**', '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/**', 'browse/src/**', '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'],
|
||||
|
||||
// /diagram (diagram-render bundle consumers). Triplet = deterministic
|
||||
// functional (gate); authoring quality = LLM-judged benchmark (periodic).
|
||||
'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'browse/src/write-commands.ts', 'browse/src/read-commands.ts', 'test/skill-e2e-diagram.test.ts'],
|
||||
'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'],
|
||||
// Both render the triplet through gstack-render (lib/aside-render.ts +
|
||||
// bin/gstack-render.ts): Aside when it is running, the browse daemon
|
||||
// otherwise — so both engines are deps. Triplet = deterministic functional
|
||||
// (gate); authoring quality = LLM-judged benchmark (periodic).
|
||||
'diagram-triplet': ['diagram/**', 'lib/diagram-render/**', 'lib/aside-render.ts', 'bin/gstack-render.ts', 'test/helpers/aside-available.ts', 'browse/src/**', 'test/skill-e2e-diagram.test.ts'],
|
||||
'diagram-authoring-quality': ['diagram/**', 'lib/diagram-render/**', 'lib/aside-render.ts', 'bin/gstack-render.ts', 'test/helpers/aside-available.ts', 'browse/src/**', 'test/helpers/llm-judge.ts', 'test/skill-e2e-diagram.test.ts'],
|
||||
|
||||
// gstack-upgrade
|
||||
'gstack-upgrade-happy-path': ['gstack-upgrade/**', 'test/skill-e2e-workflow.test.ts'],
|
||||
@@ -315,8 +328,8 @@ export const E2E_TOUCHFILES: Record<string, string[]> = {
|
||||
'land-and-deploy-workflow': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
|
||||
'land-and-deploy-first-run': ['land-and-deploy/**', 'scripts/gen-skill-docs.ts', 'bin/gstack-slug', 'test/skill-e2e-deploy.test.ts'],
|
||||
'land-and-deploy-review-gate': ['land-and-deploy/**', 'bin/gstack-review-read', 'test/skill-e2e-deploy.test.ts'],
|
||||
'canary-workflow': ['canary/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
|
||||
'benchmark-workflow': ['benchmark/**', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
|
||||
'canary-workflow': ['canary/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
|
||||
'benchmark-workflow': ['benchmark/**', 'scripts/resolvers/aside.ts', 'browse/src/**', 'test/skill-e2e-deploy.test.ts'],
|
||||
'setup-deploy-workflow': ['setup-deploy/**', 'scripts/gen-skill-docs.ts', 'test/skill-e2e-deploy.test.ts'],
|
||||
|
||||
|
||||
@@ -483,6 +496,14 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
'browse-basic': 'gate',
|
||||
'browse-snapshot': 'gate',
|
||||
|
||||
// Aside-driven browsing — periodic (external app: the Aside browser; the
|
||||
// file self-gates on 'periodic' and skips without a live Aside)
|
||||
'aside-browse-basic': 'periodic',
|
||||
'aside-browse-flow': 'periodic',
|
||||
'aside-qa-quick': 'periodic',
|
||||
'aside-scrape-json': 'periodic',
|
||||
'aside-canary-quick': 'periodic',
|
||||
|
||||
// Hermetic isolation — gate (deterministic env/config assertions; if the
|
||||
// clean room breaks, every other eval's signal is contaminated)
|
||||
'hermetic-canary': 'gate',
|
||||
@@ -718,7 +739,8 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
'plan-design-review-no-ui-scope': 'gate',
|
||||
'design-review-fix': 'periodic',
|
||||
|
||||
// /diagram — triplet is deterministic functional, judge is a quality benchmark
|
||||
// /diagram — triplet is deterministic functional (gstack-render falls back
|
||||
// to the browse daemon, so CI runs it); judge is a quality benchmark
|
||||
'diagram-triplet': 'gate',
|
||||
'diagram-authoring-quality': 'periodic',
|
||||
|
||||
@@ -740,9 +762,14 @@ export const E2E_TIERS: Record<string, 'gate' | 'periodic'> = {
|
||||
// Multi-provider benchmark — periodic (requires external CLIs + auth, paid)
|
||||
'benchmark-providers-live': 'periodic',
|
||||
|
||||
// Browser-skills Phase 2a — gate (D1/D3 contracts must not silently break)
|
||||
'scrape-match-path': 'gate',
|
||||
'scrape-prototype-path': 'gate',
|
||||
// Browser-skills Phase 2a — skillify keys gate (D1/D3 contracts must not
|
||||
// silently break). The two scrape keys are periodic: /scrape is Aside-first
|
||||
// and its fallback no longer prescribes the `$B skill list` / `skill run`
|
||||
// match + prototype flow the tests assert, so a pass rides on prompt
|
||||
// compliance (non-deterministic). Flip back to gate when scrape's fallback
|
||||
// carries the browser-skills flow again.
|
||||
'scrape-match-path': 'periodic',
|
||||
'scrape-prototype-path': 'periodic',
|
||||
'skillify-happy-path': 'gate',
|
||||
'skillify-provenance-refusal': 'gate',
|
||||
'skillify-approval-reject': 'gate',
|
||||
@@ -796,7 +823,7 @@ export const LLM_JUDGE_TOUCHFILES: Record<string, string[]> = {
|
||||
'command reference table': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/skill-llm-eval.test.ts'],
|
||||
'snapshot flags reference': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/snapshot.ts', 'test/skill-llm-eval.test.ts'],
|
||||
'browse/SKILL.md reference': ['browse/sections/**', 'browse/SKILL.md', 'browse/SKILL.md.tmpl', 'browse/src/**', 'test/skill-llm-eval.test.ts'],
|
||||
'setup block': ['SKILL.md', 'SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
|
||||
'setup block': ['browse/SKILL.md', 'browse/SKILL.md.tmpl', 'scripts/resolvers/aside.ts', 'scripts/resolvers/browse.ts', 'test/skill-llm-eval.test.ts'],
|
||||
'regression vs baseline': ['browse/sections/**', 'SKILL.md', 'SKILL.md.tmpl', 'browse/src/commands.ts', 'test/fixtures/eval-baselines.json', 'test/skill-llm-eval.test.ts'],
|
||||
'qa/SKILL.md workflow': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
|
||||
'qa/SKILL.md health rubric': ['qa/sections/**', 'qa/SKILL.md', 'qa/SKILL.md.tmpl', 'test/skill-llm-eval.test.ts'],
|
||||
|
||||
Reference in New Issue
Block a user