I am unable to login after installing on Windows. I click "Sign in to GitHub". The application states "Opening GitHub.com to authorize..." and provides an 8 digit code. The web browser never opens, so I navigate manually to https://github.com/login/device/ to enter the code. After submitting the code I get the message "Uh oh, we couldn't find anything Please make sure you entered the user code correctly."

I pulled the Appimage to one of our RHEL8.8 systems with no luck. Can you build on as old a system as possible so that those of us in the corporate space have a prayer of running it without having to go virtual?

ETA: Yes I know that there are dinosaurs younger than RHEL8.8 but still, at least sharing what the system requirements are would help.

Need the ability to have the "commit" button use a custom commit message syntax with a given model - much like VSCode provides: https://code.visualstudio.com/docs/sourcecontrol/staging-commits. Bonus points if you can select the model and provide specific instructions for commit messages.

Having to leave the GitHub App just to commit and push changes seems a bit silly. Alternative is to just have my instructions set to commit changes, but then at that point, the button is useless :)

With this UI, it really takes Copilot CLI to the next level, IMO (beyond the CLI, as it were :)

Idea that could be exceedingly useful in many enterprises - support UI navigation of GitHub Copilot marketplaces (https://docs.github.com/en/copilot/how-tos/copilot-cli/customize-copilot/plugins-marketplace)

Keeping the marketplace experience inside one cohesive UI would be brilliant - install plugins, skills, agents, etc - all without leaving the app.

Any plans to support transcribing or dictation?

How can we edit our message just like in VS Code GHC agent.

Chat mode: the PR status icon is wrong. It returned a list of "open PRs/color" that were already merged.

Please add automated workflows running on Copilot Cloud Agent instead of only locally

I'd like to see the Chat Debug View feature ported here as well.

It is awesome that we can have our team-specific custom workflow as a template here. We were in the verge of building something similar for the entire org. Super cool, we can improve on this.

The browser don´t allow us to open different domains. For exemple, .test domains cannot be open. Forcing us to use localhost:port.

First of all. Thank you very much!

1. What have you tried doing with the app so far (e.g., start a new project, review a PR, write code, etc.), and why?

I have used three sessions for maintenance tasks on an existing project. For more details, see my newsletter post https://www.linkedin.com/pulse/episode-7-first-look-new-github-copilot-app-dr-matthias-liebeck-yniue

1. What has been most useful about this app? What tasks is it particularly suited for?

Very smooth UI experience. I love switching between the sessions, the progress indicator and the sound. I'm not sure if you prioritized my sessions since they were through the App, but they felt very very fast, like 5x from what I'm used to.

1. How does this experience compare to other tools you use today (e.g., Copilot in your IDE, Claude Code, Codex)? What does the GitHub App do better or worse?

The UI was very smooth. Still in early stages, but I can see myself switch to the GitHub Copilot App as main development environment for agentic coding in the next couple of months, if the issues from point 4 (see blow) are addressed.

1. What is missing, or confusing, if anything?

The most confusing what the Git commit behaviour. At first, I only managed to get automatic commits working, #419. Then, I guess I can't find a commit button or a way to specify a commit message #423

Maybe it's already there, but confusing since I can't find it.

#421
#422

1. What type of tasks do you still feel like you need to go to github.com or other tools for?

Right now, manual commits feel like I need to switch out of the GitHub App into a Git UI like Fork.

I'm also not sure how to use multiple sessions that from my local docker test setup in parallel. Usually, I would run my full E2E PlayWright test suite, but I have no idea how I would have three sessions that access the same docker container or at least something like "okay I need to access containers that session A uses. I wait until session A is done to spin up my own containers".

1. If you had a magic wand to make this app just right for you, what would you change?

See 4)

I've got some feedback and a question from the Bing team.

I switched from copilot cli to the copilot app since you left. it's pretty crazy I feel like there's no reason to use the CLI anymore after using it exclusively for development the last couple of months.

Yay!

Is the copilot app using the same SDK as the CLI?

This is the question I'm trying to answer. I assume yes?

Where is the best place to talk directly with the team? I've got dual access and have access to Slack.

The right side "Files" cannot select the text to copy-paste. and it's hard to drag the file/folder path to the chat to tell the agent which files it needs to read.

Is there a way to bring my own model? I have a paid Claude Max sub, and I'd love to use it in this app...

Few comments:

1. whenever I open the apps, it doesn't load like an app that has already been installed. It always open the installation wizard and reinstalls the app. It delays opening by a few minutes, but all the previous content (i.e., chats) is still there.

2. There should be a setting to limit which directories github copilot has access to. I currently don't find the settings and it has access to information it should not have access to. I am being careful with my instructions for now.

3. When it is executing a task and you need to provide additional instructions there should be a way to interrupt the execution with the new text. Right now the new prompt stays in a "queue", but it would be nice if there was a button next to the queued chat that allowed me to "send" the message and interrupt the current execution with this new information.

Poor WSL integration — agent runs in Windows context, not WSL shell

When the project repository lives inside WSL (e.g. \\wsl.localhost\Ubuntu-24.04\...), the Copilot CLI agent operates in a Windows PowerShell context rather than the WSL Linux environment. This causes several practical problems:

Issues encountered

1. Built-in tools (grep, glob, view) reject UNC paths

Any file under \\wsl.localhost\... is blocked with "UNC path not permitted", making these core tools unusable on WSL-hosted repos.

2. Shell commands run in PowerShell, not bash

The agent spawns powershell.exe instead of a WSL shell. Linux-native tools (rg, find, awk, etc.) are only available if installed on Windows separately — not from the WSL distro.

3. Traversal over UNC is extremely slow

Select-String / Get-ChildItem -Recurse over \\wsl.localhost\... is orders of magnitude slower than native filesystem access, causing frequent timeouts on medium-to-large repos.

4. rg (ripgrep) works inconsistently

Even when available on Windows, scanning a large WSL repo via UNC frequently hits timeouts and returns incomplete results.

5. No way to explicitly configure the shell to WSL bash

There is no configuration option to tell the agent "this project lives in WSL, use wsl.exe as the shell."

Expected behavior

When the workspace path resolves to a WSL filesystem, the agent should detect this and spawn commands via:

wsl.exe -- bash -c "..."

This would give the agent access to the full Linux toolchain and native filesystem performance.

Environment

1. with model costs increasing dramatically (not faulting github for this), we need ability to use cheaper models or bring our own models
2. I'm a bit confused what the workflow is supposed to be with the separate worktrees being checked out for every context. An example - I test mobile app features in a simulator. Before when I was using the Github CLI it worked on my local directory and I just reloaded the simulator to visually see any changes that it made. Now I have to relaunch the simulator from each new worktree? I'm probably missing something in the workflow

is GitHub Copilot app made in WinUI, web app or a different framework and what framework is it?

Need granular breakdown of token usage. It's great that I can view the input/output token traffic per session (see attached image). Can we also maybe get some clickable on-hover links that opens up a panel with trace data on:

• agent discovery phase (loaded instructions, loaded skills, triggered hooks etc)
• model turns,
• tool calls,
• input/output tokens,
• cache tokens