CalvinBackup/gstack
1
0
Fork 0
mirror of https://github.com/garrytan/gstack.git synced 2026-09-19 11:22:21 +02:00
Code Issues Packages Projects Releases Wiki Activity

test: registries, budgets and suite reconciled for Aside-first with the $B fallback

Browse Source 
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
2026-09-05 16:48:38 -04:00
co-authored by Claude Fable 5.1
parent 993692cd54
commit 886217894f
21 changed files with 1281 additions and 166 deletions
Download Patch File Download Diff File Expand all files Collapse all files
test/helpers/carve-guards.ts
+28 -24
View File
@@ -150,7 +150,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
},
behavioral: 'external',
externalTest: 'test/skill-e2e-ship-section-loading.test.ts',
maxSkeletonBytes: 77_650, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 77_236
maxSkeletonBytes: 79_300, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 78_275
minUnionBytes: 181_000, // token-reduction Phases 1-2 (v1.69.x branch); measured union 201,464
mustContain: ['VERSION', 'CHANGELOG', 'review', 'merge', 'PR'],
// v1.58.5.0: pre-push-guard install (#2077) stacks on the shared first-run-guidance preamble.
@@ -181,7 +181,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// v1.65 merge: provisional larger-of-both-waves budget; re-measured below.
// Fork port wave 2 (#703): the repo-doc-preference block in the design
// check grew every plan-review skeleton ~0.7KB. Measured values noted.
maxSkeletonBytes: 76_000, // + v1.78 AUQ objectivity + v1.79 foreground-dispatch sweep (merged); measured 75_586
maxSkeletonBytes: 79_000, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 77_657
minUnionBytes: 123_600, // token-reduction Phases 1-2 (v1.69.x branch): preamble bash -> bin/gstack-skill-start, onboarding -> gated emission; measured union 137,346
mustContain: ['SCOPE EXPANSION', 'SELECTIVE EXPANSION', 'HOLD SCOPE', 'SCOPE REDUCTION'],
// Default-on Codex outside-voice (codexPreflight block + CODEX_MODE branch
@@ -207,7 +207,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// check grew every plan-review skeleton ~0.7KB. Measured values noted.
// #2499 project-scope MCP jq in the brain-sync block grew every tier-2+
// skeleton ~1.5KB (entry resolution emitted once per SKILL.md).
maxSkeletonBytes: 54_200, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 53_773
maxSkeletonBytes: 56_500, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 55_457
minUnionBytes: 99_800, // token-reduction Phases 1-2 (v1.69.x branch); measured union 110,910
mustContain: ['Architecture', 'Code Quality', 'Test', 'Performance'],
// Cross-cutting preamble growth (v1.57.2.0 AUQ-failure prose fallback + the
@@ -264,7 +264,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// check grew every plan-review skeleton ~0.7KB. Measured values noted.
// #2499 project-scope MCP jq in the brain-sync block grew every tier-2+
// skeleton ~1.5KB (entry resolution emitted once per SKILL.md).
maxSkeletonBytes: 65_900, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 65_486
maxSkeletonBytes: 68_500, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 67_129
minUnionBytes: 99_700, // token-reduction Phases 1-2 (v1.69.x branch); measured union 110,833
mustContain: ['developer experience', 'Getting Started'],
// Default-on Codex outside-voice (codexPreflight block + CODEX_MODE branch
@@ -295,7 +295,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// the #538 opt-out + D1 evidence directive — ratio 1.104 measured.
// #2499 project-scope MCP jq in the brain-sync block grew every tier-2+
// skeleton ~1.5KB (entry resolution emitted once per SKILL.md).
maxSkeletonBytes: 73_450, // + v1.78 AUQ objectivity + v1.79 foreground-dispatch sweep (merged); measured 73_040
maxSkeletonBytes: 76_800, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 75_804
minUnionBytes: 115_800, // Phase 4 wave 4; measured union 118,175
mustContain: ['design doc', 'problem statement'],
maxSizeRatio: 1.12,
@@ -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: 53_750, // + v1.78 AUQ objectivity + v1.79 foreground-dispatch sweep (merged); measured 53_342
maxSkeletonBytes: 66_500, // + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} for the research phase; measured 65_506
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 +
@@ -387,7 +387,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
// +Conductor AUQ-default-prose rule + one-way/continuation safety in the
// always-loaded AskUserQuestion Format section.
// v1.2.0 activation lift: first-run-guidance section in the shared preamble.
maxSkeletonBytes: 58_800, // + v1.78 AUQ objectivity + v1.79 foreground-dispatch sweep (merged); measured 58_364
maxSkeletonBytes: 61_800, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 60_628
minUnionBytes: 64_200, // token-reduction Phases 1-2 (v1.69.x branch); measured union 71,379
mustContain: ['OWASP', 'STRIDE', 'daily', 'comprehensive', 'verif'],
// cso keeps its mode-dispatch + FP-filtering phases always-loaded, so the
@@ -424,7 +424,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
gateAfterStop: undefined, // operational multi-STOP skill, like ship
},
behavioral: 'plan',
maxSkeletonBytes: 59_150, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 58_722
maxSkeletonBytes: 61_500, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 60_309
minUnionBytes: 89_000, // Phase 4 wave 1; measured union 93,357
mustContain: ['confidence', 'P1', 'P2', 'Review Army', 'adversarial'],
},
@@ -477,7 +477,8 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
gateAfterStop: undefined, // operational skill
},
behavioral: 'prompt',
maxSkeletonBytes: 62_450, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 62_021
maxSkeletonBytes: 74_500, // + Aside browser contract for Step 7 canary ({{ASIDE_SETUP}}); measured 73_523
maxSizeRatio: 1.10, // + v1.80 Aside contract + gstack-browser fallback block; measured 1.077
minUnionBytes: 91_000, // Phase 4 wave 1; estimated union ~94.9KB
mustContain: ['readiness', 'merge', 'canary', 'revert', 'staging'],
},
@@ -541,7 +542,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
gateAfterStop: undefined,
},
behavioral: 'prompt',
maxSkeletonBytes: 57_100, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 56_697
maxSkeletonBytes: 58_400, // + v2.0 {{ASIDE_RESEARCH}} (Aside first, WebSearch fallback); measured 57_356
minUnionBytes: 64_500, // measured union 67,430
mustContain: ['HARD GATE', 'dedupe', 'quality gate', 'acceptance criteria', 'archive'],
},
@@ -581,11 +582,11 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
expectedSections: ['test-bootstrap.md', 'qa-patterns.md'],
requiredReads: ['qa-patterns.md'],
scenario:
'Walk /qa in SIMULATION — do not launch a browser, run any $B command, or execute bash; treat the working tree as clean, the tier as Quick, and the target app as http://localhost:3000 with a small feature-branch diff touching one page. Skip the test-framework bootstrap (assume CLAUDE.md documents the test command). Read each pointed section before doing its step, then produce the QA plan as the report: the mode you selected and why, the Phase 1-6 steps you would run, and a worked health-score computation from the rubric. Do NOT use AskUserQuestion.',
'Walk /qa in SIMULATION — do not launch a browser, run any aside command, or execute bash; treat the working tree as clean, the tier as Quick, and the target app as http://localhost:3000 with a small feature-branch diff touching one page. Skip the test-framework bootstrap (assume CLAUDE.md documents the test command). Read each pointed section before doing its step, then produce the QA plan as the report: the mode you selected and why, the Phase 1-6 steps you would run, and a worked health-score computation from the rubric. Do NOT use AskUserQuestion.',
staticInvariants: {
mustStayInSkeleton: [
'## Setup',
'## SETUP (run this check BEFORE any browse command)',
'## BROWSER SETUP (Aside',
'## Phases 1-6: QA Baseline',
'## Phase 7: Triage',
'## Phase 8: Fix Loop',
@@ -605,29 +606,32 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
gateAfterStop: undefined,
},
behavioral: 'prompt',
maxSkeletonBytes: 52_550, // + v1.78 AUQ spawned-trigger objectivity (explicit declaration + interactive fence); measured 52_150
maxSkeletonBytes: 63_500, // + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} (replaces the browse setup block); measured 61_253
maxSizeRatio: 1.08, // + v1.80 Aside contract + gstack-browser fallback block; measured 1.063
minUnionBytes: 69_500, // measured union 70,385
mustContain: ['bug', 'browse', 'fix', 'Health Score Rubric', 'regression'],
// 'aside repl' pins the Aside contract; '$B goto' pins the fallback block in the always-loaded skeleton.
mustContain: ['bug', 'aside repl', '$B goto', 'fix', 'Health Score Rubric', 'regression'],
},
browse: {
skill: 'browse',
expectedSections: ['command-list.md'],
requiredReads: ['command-list.md'],
scenario:
'QA a static page: before driving it, plan the full audit — enumerate which browse commands and snapshot flags you would use, including extraction/tab/dialog commands beyond the Most-Used table, reading the full command reference first. Do not launch the browser or run any $B command; produce the command plan as the report.',
'QA a static page: before driving it, plan the full audit — enumerate which browser steps you would run (the aside repl shapes, and the $B commands and snapshot flags the fallback would need), including extraction/tab/dialog commands beyond the basics, reading the full command reference first. Do not launch any browser or run any aside/$B command; produce the plan as the report.',
staticInvariants: {
mustStayInSkeleton: ['## SETUP', '## Core QA Patterns', '## CSS Inspector', '## Most-Used Commands'],
mustPrecedeStop: ['## SETUP'],
// Aside is the primary browser: the skeleton carries the Aside contract;
// the $B command reference + snapshot flags are the carved section.
mustStayInSkeleton: ['## BROWSER SETUP (Aside'],
mustPrecedeStop: ['## BROWSER SETUP (Aside'],
mustMoveToSection: ['## Full Command List', '## Snapshot Flags', '### Navigation'],
gateAfterStop: undefined,
},
behavioral: 'prompt',
maxSkeletonBytes: 27_500, // Phase 4 wave 3; measured 26,875
minUnionBytes: 39_500, // measured union 41,115
// 'BEGIN/END UNTRUSTED EXTERNAL' pins the untrusted-content warning; the full
// envelope phrase wraps across lines in the rendered blockquote, so the
// contiguous-substring check needs the single-line prefix form.
mustContain: ['BEGIN/END UNTRUSTED EXTERNAL', 'snapshot -i', '@e refs', 'deviceScaleFactor', 'handoff'],
maxSkeletonBytes: 32_000, // + v2.0 {{ASIDE_SETUP}}/{{BROWSE_FALLBACK}} skeleton + the STOP-Read pointer; measured 29_986
minUnionBytes: 36_000, // skeleton + command-list section (14,240); measured union ~38.5 KB
// 'BEGIN/END UNTRUSTED EXTERNAL' pins the untrusted-content warning in the
// command reference; 'aside repl' pins the Aside contract in the skeleton.
mustContain: ['BEGIN/END UNTRUSTED EXTERNAL', 'snapshot -i', '@e refs', 'aside repl'],
},
retro: {
skill: 'retro',
@@ -701,7 +705,7 @@ export const CARVE_GUARDS: Record<string, CarveGuard> = {
gateAfterStop: undefined,
},
behavioral: 'prompt',
maxSkeletonBytes: 53_100, // + v1.78 AUQ objectivity + v1.79 foreground-dispatch sweep (merged); measured 52_685
maxSkeletonBytes: 54_000, // + v2.0 preamble growth (merged); measured 52_962
minUnionBytes: 53_200, // Phase 4 wave 4; measured union 54,290
mustContain: ["Don't make me think", "Users scan, they don't read", 'trunk test', '44px minimum'],
},