token limit exceeded

[NaiSaikChan]

Select Topic Area

Product Feedback

Copilot Feature Area

Copilot Agent Mode

Body

I using the GitHub Copilot for Xcode (0.43.0) Language Server Version: 1.362.0.
In my issue, I always get the warning Oops, the token limit exceeded. Try to shorten your prompt or start a new conversation. Even though I start a new conversation.

[github-actions[bot]]

💬 Your Product Feedback Has Been Submitted 🎉

Thank you for taking the time to share your insights with us! Your feedback is invaluable as we build a better GitHub experience for all our users.

Here's what you can expect moving forward ⏩

• Your input will be carefully reviewed and cataloged by members of our product teams. 
  • Due to the high volume of submissions, we may not always be able to provide individual responses.
  • Rest assured, your feedback will help chart our course for product improvements.
• Other users may engage with your post, sharing their own perspectives or experiences. 
• GitHub staff may reach out for further clarification or insight. 
  • We may 'Answer' your discussion if there is a current solution, workaround, or roadmap/changelog post related to the feedback.

Where to look to see what's shipping 👀

• Read the Changelog for real-time updates on the latest GitHub features, enhancements, and calls for feedback.
• Explore our Product Roadmap, which details upcoming major releases and initiatives.

What you can do in the meantime 💻

• Upvote and comment on other user feedback Discussions that resonate with you.
• Add more information at any point! Useful details include: use cases, relevant labels, desired outcomes, and any accompanying screenshots.

As a member of the GitHub community, your participation is essential. While we can't promise that every suggestion will be implemented, we want to emphasize that your feedback is instrumental in guiding our decisions and priorities.

Thank you once again for your contribution to making GitHub even better! We're grateful for your ongoing support and collaboration in shaping the future of our platform. ⭐

[cauanrricardo]

Hello there!

I'm sorry to hear you're running into this. I actually faced the same issue in an older version of the Copilot extension, and it was incredibly frustrating!

My Personal Workaround (The Simple Solution)

For me, the immediate fix was to drastically reduce the code context and, simultaneously, "mix" my AI usage while waiting for the bug to be fixed.

Strict Context Reduction: As others have suggested, the key is to be extremely aggressive about context. I would close all unrelated files and, often, copy the code I was working on into a scratch file/gist to completely isolate the problem area from the main project.

Use a Second AI Tool: If I hit the token limit error in Copilot, I would copy the same prompt and code block and use another free AI tool (like an external LLM chat) to get the answer. This allowed me to keep my workflow moving and understand the code logic without constantly being blocked by the bug. I then used that external answer to guide my coding in Xcode.

This back-and-forth approach isn't ideal, but it allowed me to bypass the bug and keep working until the issue was officially patched in a later release.

I hope this helps you out while the GitHub team works on a fix!

[sunni198]

While I understand the necessity for the token limit, this is a major experience issue. Here is what I observe: I have a working solution but I need to fix something. While fixing I get the token issue, but there is no warning when I am approaching it. Copilot just hits an error in the middle of updating code and fails showing the retry that never works. I have an implementation summary file to get it back up to speed when I reset the chat, but it often loses so much context it then attempts to fix by revising ALL my files and puts me in a broken state. Then I end up spending my token limit to get my solution back to working state, and only have a few chats until it reaches limit again. Please introduce some warning that we are reaching the limit. It would also be helpful if it were to save some sort of context for a new chat where it keeps the last revisions it was making as it has repeatedly cut off code and broke files. If it is near limit, it should not be making file edits and get stopped in the middle. I also notice when it does this that all the progress it made since last chat is just removed, so I cannot see what it did up until it failed. I have had this vicious cycle multiple times and it is incredibly frustrating. I should not have to consume the limits to get my app back to working state after it breaks everything trying to resume after chat reset.

I will try smaller fixes, and try to reduce token usage but the user experience could use some care.