From f7563a91b765e5a2aec3367160aae39a4afb7e50 Mon Sep 17 00:00:00 2001 From: Dotta Date: Sun, 8 Nov 2026 02:01:19 -0600 Subject: [PATCH] test(evals): give the open-work inventory agent room after seeding 504 tasks Run 42459254965 followed the long-list guidance: it saved all 501 open tasks as a document on the conversation (an offline grade of that document passes). The 600 s attempt ended 18 s after the final document write and before the reply. Seeding and settling the inventory takes about 2.75 minutes of each attempt, so the agent had about 7 minutes. The attempt now allows 900 s, the same budget as other large-setup chat cases. Co-Authored-By: Claude Opus 5.5 --- tests/runner-e2e/chat-catalog-descriptors.json | 2 +- .../chat-catalog-domains/internal-task-inventory.ts | 4 +++- 2 files changed, 4 insertions(+), 2 deletions(-) diff --git a/tests/runner-e2e/chat-catalog-descriptors.json b/tests/runner-e2e/chat-catalog-descriptors.json index 8393858221e..44757cbdddc 100644 --- a/tests/runner-e2e/chat-catalog-descriptors.json +++ b/tests/runner-e2e/chat-catalog-descriptors.json @@ -5886,7 +5886,7 @@ "coverageGaps": [], "expectedRunCount": 1, "turnTimeoutMs": 120000, - "attemptTimeoutMs": 600000, + "attemptTimeoutMs": 900000, "setupPolicy": { "readiness": "preserve-scenario", "invariantCheckIds": [ diff --git a/tests/runner-e2e/chat-catalog-domains/internal-task-inventory.ts b/tests/runner-e2e/chat-catalog-domains/internal-task-inventory.ts index 5f27b467585..b95c05d57ce 100644 --- a/tests/runner-e2e/chat-catalog-domains/internal-task-inventory.ts +++ b/tests/runner-e2e/chat-catalog-domains/internal-task-inventory.ts @@ -221,7 +221,9 @@ function openInventory(): ChatCatalogCase { return { project: p, originalTasks, workerIds: [worker.id, secondWorker.id], ownerPauseReceipts, ownerLabels: { [worker.id]: "Morgan", [secondWorker.id]: "Riley", unassigned: "Unassigned" } }; }, gradeOpenInventory); return { ...base, observe: observeOpenInventory, oracleVersion: "paperclip.chat-catalog.internal.organize-open-work.v6", - sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-task-inventory.ts"], attemptTimeoutMs: 600_000, + sourceFiles: [...base.sourceFiles, "chat-catalog-domains/internal-task-inventory.ts"], + // Seeding 504 tasks under paused owners takes about 2.75 minutes of the attempt; the agent keeps about 12 minutes. + attemptTimeoutMs: 900_000, setupPolicy: { readiness: "preserve-scenario", invariantCheckIds: ["inventory-owners-paused", "lead-ready", "inventory-settled"] }, async verifySetup(ctx, state) { const c = checks();