test: PTY harness handles clipped reviews and bundled setup tabs; AUQ judge uses structured output; design-consultation carve declines optional outside voices

- ceo mode routing: a Submit review taller than the viewport, a setup tab
  bundled after the mode tab, and a clip through the mode question each hung
  or misread the run; the native answer is still verified after Submit.
- judgeRecommendation requests a 1-5 enum schema; a malformed Haiku reply had
  scored substance 0 for a 4/5 brief. Judge failures now propagate.
- carve section-loading for design-consultation declines the optional outside
  voices (a supported path) and treats DESIGN.md as the report; timeout unchanged.
The Step 0E handoff defect is not fixed (0/15 samples across four wordings,
none shipped) and is filed in TODOS.
This commit is contained in:
garrytan committed 2026-09-30 12:52:56 +00:00
1 parent dfe5e733fb
commit a27365bffe
16 files changed
+893 -28

No files matched your search

+1
View File
@@ -52,6 +52,7 @@ mock.module(path.join(root,'test/helpers/ceo-mode-option.ts'),()=>({
ceoExpansionPacingChoice:()=>{current.pacingChoices++;return scenario.startsWith('pacing')&&(!current.pacingSent||scenario==='pacing-repeated')?{call:{questions:[]},index:scenario==='pacing-unsupported'?0:1}:null;},
ceoExpansionPacingReady:()=>{current.pacingChecks++;return (scenario==='pacing'||scenario==='pacing-repeated')&&current.pacingChecks>=3;},
ceoModeSubmissionInput:()=>scenario==='mode-submit'&&!current.submitted?'\\r':null,
ceoModePacketTabAnswer:()=>null,
holdDeferKeepIndex:()=>null,
nextCeoModeNavigation:(_visible,target)=>{
if(scenario==='navigation')throw new Error('fixture navigation failed');