From dd6c5df76a12369ab7a660157632c3f0918f0f23 Mon Sep 17 00:00:00 2001 From: Dotta Date: Sat, 7 Nov 2026 22:27:00 -0600 Subject: [PATCH] test(evals): give archive-card's Research card a real blocker to summarize The unrelated Research card asks for the project's biggest blockers, but its only task was a backlog follow-up. The summarizer searched for blockers that did not exist, and its pre-query generation took 171-182s against the 180s limit, failing setup in 2 of 4 runs. The Research project now has one blocked task, as Launch does. Co-Authored-By: Claude Opus 5.5 --- .../chat-catalog-domains/integrator-status-cards.ts | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/tests/runner-e2e/chat-catalog-domains/integrator-status-cards.ts b/tests/runner-e2e/chat-catalog-domains/integrator-status-cards.ts index 17ae1258d7b..3abe51f7ae7 100644 --- a/tests/runner-e2e/chat-catalog-domains/integrator-status-cards.ts +++ b/tests/runner-e2e/chat-catalog-domains/integrator-status-cards.ts @@ -223,7 +223,10 @@ function define(id: string, seed: "none" | "ceo" | "morgan", extra: Partial ctx.allRuns(), accept: rows => rows.length === 2 && rows.every(row => row.status === "succeeded") }); }