From a818a991fb63699b6af142d5022d781fb418b2ef Mon Sep 17 00:00:00 2001 From: garrytan Date: Sat, 3 Oct 2026 23:39:08 +0000 Subject: [PATCH] I1: office-hours-brain-writeback reads the long skill with Read and skips the preamble 4 of 18 trials ended error_max_turns at the unchanged 12-turn budget with a gbrain search but no gbrain put. The failing trial in 37151477069 read the 1260-line rendered SKILL.md with cat, got truncated output, spent four more turns re-reading it with sed, then ran the preamble's skill-start block. The passing trials skipped the preamble. The prompt now says to read the skill with the Read tool and skip the preamble, onboarding, telemetry and contributor sections, as the plan-eng fixtures already do. Budget unchanged. --- test/skill-e2e-office-hours-brain-writeback.test.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/test/skill-e2e-office-hours-brain-writeback.test.ts b/test/skill-e2e-office-hours-brain-writeback.test.ts index 6b073aae8..f77b34f33 100644 --- a/test/skill-e2e-office-hours-brain-writeback.test.ts +++ b/test/skill-e2e-office-hours-brain-writeback.test.ts @@ -235,7 +235,7 @@ exit 0 model: resolveEvalModel('capture'), run: (signal) => runSkillTest({ signal, - prompt: `Read office-hours/SKILL.md for the workflow. + prompt: `Read office-hours/SKILL.md for the workflow with the Read tool (it is long; Bash output truncates it). Skip its preamble bash block, onboarding, telemetry and contributor sections — go straight to the workflow. Read pitch.md — that's a founder pitch coming to office hours. Select Startup Mode. Skip any AskUserQuestion — this is non-interactive; auto-decide the recommended option for any question.