GitHub Copilot Chat: Oops, you reached the rate limit. Please try again later.
Answered
I frequently get those errors using JetBrains Rider, with any mode and model, but it tends to happen more often in agent mode.
This can be very disruptive and sometimes lead to context loss, confusing the agent and leading to incomplete work.
The error never happens when using the same account on VSCode for example, it seems it's able to deal with that better, or simply better deal with request rates and limits.
Please sign in to leave a comment.
I am having the same issue. The same account in VSCode does not produce any errors related to rate limiting. This seems to be a bug in the plugin.
The message “Oops, you reached the rate limit. Please try again later. Request ID: …” indicates that the AI service rejected the request due to rate limiting. We understand this is disruptive, especially if it interrupts agent work.
To investigate why it happens so frequently in Rider (and compare it with your VS Code experience), please share:
Rider version/build and AI Assistant plugin version
The Request ID(s) shown in the message (if available)
Approximate time (with timezone) when it occurred
Rider logs collected right after reproducing: Help → Collect Logs and Diagnostic Data (you can upload the archive and post the upload id here)
With that information we can verify the cause and escalate to the AI Assistant team if needed.
Hi! Thanks for reaching out and sorry for the confusion in the last message.
The “Oops, you reached the rate limit” message comes from GitHub Copilot Chat, which is provided and maintained by a third party via the GitHub Copilot JetBrains plugin:
https://plugins.jetbrains.com/plugin/17718-github-copilot--your-ai-pair-programmer
Since it’s a third‑party plugin, JetBrains can’t directly investigate or change its rate-limiting behavior. Please report the issue to the Copilot JetBrains plugin issue tracker here (including the Request ID and timestamps if available):
https://github.com/microsoft/copilot-intellij-feedback/issues
You should change the agent max request, by default it's 25, as always it's a matter of tokens, you'll consume more for larger task but will have a lesser number of occurence for the Oops, you reached the rate limit. Please try again later. issue. Solved the problem for me!
Please see:
https://github.com/microsoft/copilot-intellij-feedback/issues/1334