From d2826233b3d2a3cbc9732f819b5cac75249953a9 Mon Sep 17 00:00:00 2001 From: Dotta Date: Mon, 2 Nov 2026 20:19:55 -0600 Subject: [PATCH] test(evals): align goal link calibration with UI evidence Keep the aggregate no-chat-link expectation consistent with the reviewed v2 normal Goals UI/readback oracle. Missing hierarchy inspection remains a failing negative control. Co-Authored-By: Paperclip --- tests/runner-e2e/chat-catalog-domains/internal.test.ts | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tests/runner-e2e/chat-catalog-domains/internal.test.ts b/tests/runner-e2e/chat-catalog-domains/internal.test.ts index 07d003efb7e..283d0fc9dd8 100644 --- a/tests/runner-e2e/chat-catalog-domains/internal.test.ts +++ b/tests/runner-e2e/chat-catalog-domains/internal.test.ts @@ -382,7 +382,7 @@ describe("internal chat scenario independent oracles", () => { expect(gradeInternal(wrong).passed).toBe(false); expect(gradeInternal(undefined).passed).toBe(false); const noLinks = structuredClone(good); noLinks.links = []; - expect(gradeInternal(noLinks).passed).toBe(["goals.align-existing-work", "projects.archive-project", "projects.add-repository", "projects.replace-repository", "tasks.completion-with-gate", "documents-artifacts.private-download", "inbox-search.archive-done", "inbox-search.restore-archive", "inbox-search.archive-without-grant", "documents-artifacts.restore-document"].includes(definition.scenarioId)); + expect(gradeInternal(noLinks).passed).toBe(["goals.create-goal-tree", "goals.align-existing-work", "projects.archive-project", "projects.add-repository", "projects.replace-repository", "tasks.completion-with-gate", "documents-artifacts.private-download", "inbox-search.archive-done", "inbox-search.restore-archive", "inbox-search.archive-without-grant", "documents-artifacts.restore-document"].includes(definition.scenarioId)); }); } it("never treats an unimplemented scenario as passing", () => expect(gradeInternal(base("inbox-search.archive-partial-failure")).passed).toBe(false));