From fffdd60dd845db8fa1caf60a86f52efc8549d131 Mon Sep 17 00:00:00 2001 From: Dotta Date: Mon, 12 Oct 2026 16:12:36 -0500 Subject: [PATCH] test(evals): record four qualified Claude onboarding default targets Advance the first-task definition while keeping historical result identities intact. Co-Authored-By: Paperclip --- tests/runner-e2e/catalog.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/runner-e2e/catalog.ts b/tests/runner-e2e/catalog.ts index b00500d41db..f187f68af7a 100644 --- a/tests/runner-e2e/catalog.ts +++ b/tests/runner-e2e/catalog.ts @@ -1431,7 +1431,7 @@ export const runnerSuites: readonly RunnerSuiteFixture[] = [ groups: ["onboarding"], profiles: runnerProfiles.filter(profile => ["legacy-codex", "legacy-claude", "runner-codex", "runner-acpx-claude"].includes(profile.id)), environments: [localEnvironment], tasks: firstTaskTasks, expectedMatrixSize: 52, - definitionMetadata: { version: 7, runGrading: "evidenced-nonexecution-and-refusal", credentialPersistenceCheck: false, questionChoiceMinimum: 2, nativeSetup: "qualified-platform-wizard-saved-default", claudeDefaultTarget: "darwin-arm64", legacySetup: "explicit-advanced-runner-choice", productionInstructions: true, qualityGrading: "informational" }, + definitionMetadata: { version: 8, runGrading: "evidenced-nonexecution-and-refusal", credentialPersistenceCheck: false, questionChoiceMinimum: 2, nativeSetup: "qualified-platform-wizard-saved-default", claudeDefaultTargets: ["darwin-arm64", "darwin-x64", "linux-x64", "linux-arm64"], legacySetup: "explicit-advanced-runner-choice", productionInstructions: true, qualityGrading: "informational" }, }, { id: "agent-chat", label: "Persistent Agent Chat",