Copilot waste of tokens

[CarlosSilvaUk]

🏷️ Discussion Type

Product Feedback

💬 Feature/Topic Area

Copilot in GitHub

Body

Its not the first time that the agents just goes in circles doing what we told them to don't do and in the end of the day we are exactly where we start and $50 are gone from our accounts.

This is not fair, we pay for a service that was not delivered, its not fair that we need to pay for your errors. The minimum that you should do is that in these cases at least you restore the tokens that the model spent without producing anything. The time that it makes to lose is loss enough.

Its frustrating seeing the model doing the same mistakes again and again. It recognizes that it couldn't produce anything useful but it says that it can't contact github with that feedback.

I'm happy to pay for a service, but feels more like being rob.

[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. ⭐

[tanvishinde017]

I can understand the frustration. AI agents can sometimes get stuck in loops, repeatedly make the same changes, or consume a significant number of credits without producing useful results. When that happens, the lost time can be more frustrating than the credit cost itself.

At the moment, I don't believe there is an automatic refund mechanism for AI credits spent on unsuccessful interactions. However, I think your feedback raises a reasonable point: if an agent clearly fails to complete the task or repeatedly performs the same ineffective actions, there should be better safeguards and possibly a way to request credit restoration.

A few improvements that could help are:

• Detecting repetitive loops and automatically stopping the agent.
• Warning users before additional high-cost retries.
• Providing clearer progress indicators and failure reasons.
• Offering a credit refund or goodwill credit system for obvious agent failures.

In the meantime, submitting examples, logs, or conversation transcripts can help the product teams identify patterns and improve the experience for everyone.

Thank you for sharing your feedback — I'm sure many users working with agent workflows have experienced similar situations.