mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-13 00:19:03 +02:00
Merge origin/main and advance release to v1.84.1.0
Preserve the design interoperability release and clarify ship publication sequencing under frontier evaluation. Co-authored-by: OpenAI Codex <noreply@openai.com>
This commit is contained in:
Garry Tan
@@ -347,7 +347,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
// v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
|
||||
// v1.64.1.0: shared-preamble prose from the two parallel v1.64 waves lands
|
||||
// the skeleton at 69,022 B; +~1 KB headroom.
|
||||
maxSkeletonBytes: 66_500, // + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} for the research phase; measured 65_506
|
||||
maxSkeletonBytes: 67_500, // + v1.82 open DESIGN.md format check ({{DESIGN_MD_CHECK}} in Phase 0); measured 67_014
|
||||
minUnionBytes: 65_000, // token-reduction Phases 1-2 (v1.69.x branch): preamble bash -> bin/gstack-skill-start, onboarding -> gated emission; measured union 72,252
|
||||
mustContain: ['Typography', 'Color', 'Aesthetic Direction'],
|
||||
// Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback ~2KB +
|
||||
@@ -655,7 +655,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
// (D3A: read-on-demand doctrine, requiredReads-guarded + loading eval)
|
||||
'design-html': {
|
||||
skill: 'design-html',
|
||||
expectedSections: ['doctrine.md', 'pretext-patterns.md'],
|
||||
expectedSections: ['doctrine.md', 'pretext-patterns.md', 'detector-install-offer.md'],
|
||||
requiredReads: ['doctrine.md', 'pretext-patterns.md'],
|
||||
scenario:
|
||||
'Walk /design-html in SIMULATION — do not run bash, start servers, launch a browser, or take screenshots. Treat Step 0 as already resolved: no CEO plan, no approved mockup, no variants, no DESIGN.md, no prior finalized.html — freeform mode (Case C option D), screen name "pricing", the user wants a pricing page for a developer-tools SaaS (dark, dense, three tiers, monospace-leaning). Do NOT use AskUserQuestion — proceed with the stated assumptions. Read each pointed section before doing its step, then execute Steps 1-3: produce the implementation spec, state the chosen Pretext tier and why, and generate the complete Pretext-native HTML — include the HTML in your report instead of writing files. Stop there: skip Step 3.5, Step 4, and Step 5.',
|
||||
@@ -678,7 +678,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
|
||||
gateAfterStop: undefined, // operational skill, no plan-mode gate
|
||||
},
|
||||
behavioral: 'prompt',
|
||||
maxSkeletonBytes: 52_900, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 52_492
|
||||
maxSkeletonBytes: 55_400, // measured 55,262 (2026-09-09): the detector install offer pointer + its sections-table row (the brief itself lives in sections/detector-install-offer.md); before that 54,545 for the review-cycle trust prose, the Slop Gate's Decisions-Log clause, and the blacklist header's override sentence
|
||||
minUnionBytes: 57_500, // Phase 4 wave 4; measured union 58,682
|
||||
mustContain: ["Don't make me think", "Users scan, they don't read", 'The Goodwill Reservoir', 'PRETEXT API CHEATSHEET', 'Pattern 3: Text around obstacles'],
|
||||
},
|
||||
|
||||
@@ -0,0 +1,20 @@
|
||||
/**
|
||||
* Install test/fixtures/fake-impeccable.ts as an executable `impeccable` in a
|
||||
* fresh temp dir OUTSIDE any repo (the wrapper refuses an in-repo IMPECCABLE_BIN
|
||||
* by design). Shared by the unit and E2E suites so the shim is set up one way.
|
||||
*/
|
||||
import * as fs from 'fs';
|
||||
import * as os from 'os';
|
||||
import * as path from 'path';
|
||||
|
||||
export const IMPECCABLE_FAKE_SRC = path.join(import.meta.dir, '..', 'fixtures', 'fake-impeccable.ts');
|
||||
export const DETECT_SAMPLE = path.join(import.meta.dir, '..', 'fixtures', 'impeccable-detect-sample.json');
|
||||
|
||||
export function installFakeImpeccable(prefix = 'gstack-fake-impeccable-'): { dir: string; bin: string } {
|
||||
const dir = fs.mkdtempSync(path.join(os.tmpdir(), prefix));
|
||||
const bin = path.join(dir, 'impeccable');
|
||||
fs.copyFileSync(IMPECCABLE_FAKE_SRC, bin);
|
||||
fs.chmodSync(bin, 0o755);
|
||||
fs.copyFileSync(DETECT_SAMPLE, path.join(dir, 'impeccable-detect-sample.json')); // the shim's documented default output, beside it
|
||||
return { dir, bin };
|
||||
}
|
||||
@@ -250,3 +250,16 @@ export function extractSkillHead(skillDir: string, bodyLineCount = 30): string {
|
||||
const head = bodyLines.slice(0, bodyLineCount).join('\n').trimEnd();
|
||||
return `${frontmatter}\n${head}\n\n<!-- body truncated by test/helpers/skill-fixture.ts — routing fixture needs frontmatter only -->\n`;
|
||||
}
|
||||
|
||||
/**
|
||||
* Slice a rendered skill between two literal markers. Both must exist: a
|
||||
* missing END marker would silently hand the agent the rest of the file, which
|
||||
* is exactly the "copied the whole SKILL.md" failure the E2E fixtures avoid.
|
||||
*/
|
||||
export function sliceBetween(text: string, start: string, end: string): string {
|
||||
const i = text.indexOf(start);
|
||||
if (i < 0) throw new Error(`skill fixture: start marker not found: ${start}`);
|
||||
const j = text.indexOf(end, i + start.length);
|
||||
if (j < 0) throw new Error(`skill fixture: end marker not found after start: ${end}`);
|
||||
return text.slice(i, j);
|
||||
}
|
||||
|
||||
@@ -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
|
||||
|
||||
Reference in New Issue
Block a user