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 -1
View File
@@ -243,7 +243,7 @@ async function registered(scenario:'accept'|'uncertain'|'missing source'|'missin
navigateToModeAskUserQuestion:async()=>({modeIndex:3,visibleAtMode:'captured mode',question:{nativeCall:mode(f)}}),
planCountQuestionInput:(_v:string,q:any)=>q.nativeCall.toolUseId===modeId?'3':'1',selectPtyNumberedOption:async()=>{throw Error('unexpected legacy key');},
hasNativePostAnswerCeoPosture:scenario==='lexical pass'||scenario==='expansion'?()=>true:hasNativePostAnswerCeoPosture,
ceoModeSubmissionInput:()=>null,ceoExpansionPacingReady:()=>false,ceoExpansionPacingChoice:()=>null,holdDeferKeepIndex,
ceoModeSubmissionInput:()=>null,ceoModePacketTabAnswer:()=>null,ceoExpansionPacingReady:()=>false,ceoExpansionPacingChoice:()=>null,holdDeferKeepIndex,
nextCeoPostureContinuation:(_a:any,_b:any,_c:any,_d:any,_e:any,continued:boolean)=>continued?null:'question',
capturePlanCountQuestion:()=>({nativeCall:pending}),isPlanReadyVisible:()=>false,isNumberedOptionListVisible:()=>false,
buildCeoHoldPostureReview,evaluateCeoHoldPostureReview:async(review:PlanReviewDecisionInput)=>{