The fastest, cheapest, most efficient open-source agent harness. Run more than 500 agents on a $10 VPS.
Rust agent-orchestrationai-agentsai-assistantdesktopllmlocal-firstmcppersonal-aiprivacyrustsecond-braintauri
test(chat): update subagent replay test wording
Steven Enamakel4b5cc7c45ffc
diff --git a/app/src/providers/__tests__/ChatRuntimeProvider.subagentReplay.test.tsx b/app/src/providers/__tests__/ChatRuntimeProvider.subagentReplay.test.tsxindex 314d1ba440..ba8d06b85d 100644--- a/app/src/providers/__tests__/ChatRuntimeProvider.subagentReplay.test.tsx+++ b/app/src/providers/__tests__/ChatRuntimeProvider.subagentReplay.test.tsx@@ -1,8 +1,8 @@/*** A redelivered `subagent_spawned` must not cancel a live sub-agent question.*- * `continue_subagent` announces a resume by republishing `subagent_spawned` for- * the same task/agent, so "a row that already exists got spawned again" is the+ * Resuming with the same task key republishes `subagent_spawned` for the same+ * task/agent, so "a row that already exists got spawned again" is the* only resume signal the frontend receives — and it is exactly what Socket.IO* redelivering the ORIGINAL spawn looks like. This socket reconnects and* replays freely (13+ times in one measured session), so the failure is not@@ -132,7 +132,7 @@ describe('ChatRuntimeProvider — replayed sub-agent spawn', () => {expect(row()?.subagent?.awaitingQuestion).toBe(QUESTION);});- it('still resumes on a real continue_subagent spawn', () => {+ it('resumes on a same-task spawn in the next parent turn', () => {const listeners = renderProvider();act(() => {