💬 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. ⭐

Thanks for the quick acknowledgment! I appreciate the transparency about how feedback gets triaged.

I'd be glad to help move this forward directly — I've been building out multi-agent AI workflows and automation tooling around Copilot CLI (see my profile for recent contributions across Grafana, Prowler, and Career Ops), so I have a solid handle on how Copilot sessions behave in practice. Happy to collaborate on design/scope for session continuity between GitHub Mobile and Copilot CLI/VS Code, or just submit a fix/PR directly if there's an existing issue or component to work from.

Let me know where it'd be most useful and I'll follow whatever process works best (RFC, linked issue, PR, etc.).

Thanks to @4Raisan for collaborating and jumping on this so quickly!

The proposal to separate session identity from the client via durable session IDs is a sound architectural move; it effectively solves the hand-off problem between VS Code and Mobile. We particularly like the idea of starting with a read-only status pilot to validate the event-flow without the overhead of full state synchronization.
One consideration: for the 'waiting for approval' flow to feel responsive, we'd likely need a robust event-bridge (e.g., a server-sent events or webhook model) so the mobile client can trigger the agent's local event loop in real-time, rather than relying on a polled status view. We're aligned with the session-based approach but suggest focusing the pilot on the latency and reliability of these 'approval triggers' to ensure the cross-client experience feels seamless.

To the GitHub team: we would be happy to coordinate our efforts or partner on a resolution for this that aligns with your existing product roadmap and technical preferences. Let us know how you'd prefer to proceed!

for the finished-notification part, in the meantime: copilot cli can run MCP servers, so you can have the agent reach you when a long run is done or stuck. im the dev of callmemcp.com, it places a real call to your iphone, reads out what the agent wants to say, and your spoken answer goes back to it as text. it can also text progress. no session view or link back into the run though, and its a paid iphone only app.