Summarize conversation results in additional burning of premium requests

[MarkWard0110]

Select Topic Area

Product Feedback

Copilot Feature Area

Copilot Agent Mode

Body

The agent has to perform additional premium requests after a summary has been generated to restore knowledge or information lost after the summary. This reduces the number of premium requests for actual work.

After a summary conversation, the agent sometimes repeats work or research they did before. This is likely due to this information not carrying through the summarization, which is going to burn through premium requests.

The quality of the summarization will affect the agent's actions. A summary might contextualize what is happening in the agent session, but this might be biased to a specific context. Sometimes, the agent needs to be reminded of details that were covered very early in the session, resulting in using more premium requests. Other times, the agent, based upon the summary, will need to look at files again before it resumes the tasks it was working on.

Perhaps using the thumbs down can help provide feedback that some responses are perceived to be negatively impacting users' premium request budgets.

The agent can burn through the premium requests by getting enough information to understand the task. Some tasks require the agent to understand details from many different files, which must be repeated each new agent session. Using a README.md does help; it reduces the agent's search for all files, but it does not provide the details that the actual code offers. In some projects, there are several premium requests the agent must perform to start a task, which significantly limits their ability to be used.

I have a project where almost every task begins with informing the agent about a file that provides an overview and details about the project. However, the agent still has to access the source code of various components to have enough working knowledge to be functional. It also has to request and read other files to understand how to use other classes.

[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. ⭐