Every time I try to interact with an agent, it gets stuck on summarizing chat context. even a simple hi is not processing
request id-
Request ID: c6776a16-10cf-46fd-8a67-cb16f288d080
An unexpected error occurred.
[internal] Failed to run step, exceeded max retries
aae: [internal] Failed to run step, exceeded max retries
at rK_ (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:28926:24637)
at nK_ (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:28926:23543)
at dK_ (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:28927:6487)
at h8u.run (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:28927:11285)
at async xDn.runAgentLoop (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41235:11960)
at async W1d.streamFromAgentBackend (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41305:12151)
at async W1d.getAgentStreamResponse (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:41305:18486)
at async N3e.submitChatMaybeAbortCurrent (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:29033:16809)
at async giC.submitMessage (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:44688:94906)
at async T_C.submitMessage (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:45709:10241)
at async vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.desktop.main.js:42968:88647
Thanks for the report @Abhijeet_Patil! This matches a known issue we’re tracking when conversation context grows significantly beyond the model’s token limit., and I’ve added your report.
Starting a new chat should let you continue working with the agent. Is that the case?
Hi Colin, thanks for the response. Although starting new chat is of no use, switching AI model worked for me. Currently using it that way and will wait for a fix from the team. Thanks !
Hi @Colin , I am getting this issue again after the latest update. PSB the details:
Request ID: e7339d18-b575-4325-889b-03d9512f1cb3
An unexpected error occurred.
[internal] Failed to run step, exceeded max retries
RetriableError: [internal] Failed to run step, exceeded max retries
at zCE (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11938:27797)
at cNh (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11938:26526)
at g5S (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11939:11430)
at Object.classify (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11939:15949)
at KCE (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11939:5709)
at async iWg.runWithSharedTurnRunner (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:11939:15300)
at async gue.runAgentLoop (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:21292:3043)
at async eLv.streamFromAgentBackend (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:24470:13921)
at async eLv.getAgentStreamResponse (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:24470:22774)
at async Fpt.submitChatMaybeAbortCurrent (vscode-file://vscode-app/c:/Users/patilabh/AppData/Local/Programs/cursor/resources/app/out/vs/workbench/workbench.glass.main.js:12056:1967)
This time opening new chat or changing the AI model is also not working.
If it’s persisting on new chats, perhaps you have some context bloat that needs to be addressed. In the latest versions of Cursor, you can see what’s taking up your agent’s context here!
We’ve made a change on our side to how this is handled. When a chat grows past what the model can hold, even after summarizing, Cursor no longer gets stuck cycling through “Summarizing chat context” and retrying until it fails with “exceeded max retries”. It now stops quickly and shows a “Conversation Too Long” message with options to start a new chat, send a shorter message, or switch to a model with a larger context window.
