From 3e75b69e05d239e48bd8842cdc9338ebefd77e79 Mon Sep 17 00:00:00 2001 From: Dotta Date: Tue, 27 Oct 2026 00:25:11 -0500 Subject: [PATCH] test(evals): return verified gateway prerequisite receipt --- tests/runner-e2e/chat-catalog-domains/external-gateway-error.ts | 1 + 1 file changed, 1 insertion(+) diff --git a/tests/runner-e2e/chat-catalog-domains/external-gateway-error.ts b/tests/runner-e2e/chat-catalog-domains/external-gateway-error.ts index c5f1c05f11b..fcfaca44f5f 100644 --- a/tests/runner-e2e/chat-catalog-domains/external-gateway-error.ts +++ b/tests/runner-e2e/chat-catalog-domains/external-gateway-error.ts @@ -76,6 +76,7 @@ export const gatewayErrorExternalCases=[definition("gateways-profiles.inspect-ga const rows=await Promise.all([state.morganRunId,state.ownRunId].map(id=>ctx.input.api.get(`${root(ctx)}/tools/runs/${id}/decisions`))); if(!failedInvocation(rows,state.morganRunId,state.morganId,state.morganTaskId,state)||!failedInvocation(rows,state.ownRunId,ctx.input.fixtures.agent.id,state.ownTaskId,state))throw new Error("Setup blocker: two distinct actual native provider-error receipts are required before diagnostic chat"); if(state.agentAuditStatus!==403||state.agentDecisionStatus!==403)throw new Error("Setup blocker: company audit and board receipt lookup must deny the ordinary agent"); + return {passed:true,checks:[{id:"distinct-native-provider-receipts-and-board-boundary",passed:true,detail:"Two independently observed provider tool_error invocations bind separate agent/task native reports; company audit and decision lookup deny the ordinary agent."}]}; }, async observe(ctx,state){ const provider=providers.get(ctx)!;state.decisions=await Promise.all((await ctx.allRuns()).map(run=>ctx.input.api.get(`${root(ctx)}/tools/runs/${run.id}/decisions`)));