From fb759fbe6f7f2d0539ebd082a8c0b6aa438c25cb Mon Sep 17 00:00:00 2001 From: Dotta Date: Mon, 9 Nov 2026 01:57:54 -0600 Subject: [PATCH] test(evals): drop the reply-ID calibration superseded by the discovery-read check Co-Authored-By: Claude Opus 5.5 --- .../chat-catalog-domains/runtime-runs-adapters.test.ts | 1 - 1 file changed, 1 deletion(-) diff --git a/tests/runner-e2e/chat-catalog-domains/runtime-runs-adapters.test.ts b/tests/runner-e2e/chat-catalog-domains/runtime-runs-adapters.test.ts index 9e667512eb2..bb5456bcde9 100644 --- a/tests/runner-e2e/chat-catalog-domains/runtime-runs-adapters.test.ts +++ b/tests/runner-e2e/chat-catalog-domains/runtime-runs-adapters.test.ts @@ -11,7 +11,6 @@ function valid() { it("accepts an actual admitted option with account qualification distinguished", () => expect(gradeModelOptions(valid()).passed).toBe(true)); it("accepts natural qualified model-option guidance", () => { const o = valid(); o.reply = "gpt-5.6-sol appears among the model options. Whether you can use it depends on the account connection selected for this runtime and its qualification."; expect(gradeModelOptions(o).passed).toBe(true); }); it("accepts a reworded answer without account keywords", () => { const o = valid(); o.reply = "Morgan can pick gpt-5.6-sol; whether it runs is down to the key Morgan is set up with."; expect(gradeModelOptions(o).passed).toBe(true); }); -it("rejects an answer that names no discovered option", () => { const o = valid(); o.reply = "Morgan can use the usual models."; expect(gradeModelOptions(o).passed).toBe(false); }); it("rejects an answer whose run never read model discovery", () => { const o = valid(); (o.state as Record).agentDiscoveryReads = 0; expect(gradeModelOptions(o).passed).toBe(false); }); it("counts only successful model discovery results from the answering runs", () => { const ev = (runId: string, result: Record, eventType = "item.completed") => ({ eventType, payload: { prpEvent: { runId, payload: { item: { type: "tool_result", result } } } } });