command output not shown in Copilot CLI batch mode

[lopuhin]

Select Topic Area

Product Feedback

Copilot Feature Area

Copilot Coding Agent

Body

When Copilot CLI is run in batch mode, the output of the commands is not shown, for example:

% copilot --log-level all -p "run ls -lha and stop"
● I'll run the ls -lha command for you.

✓ List all files with details in current directory
   $ ls -lha
   ↪ 10 lines...

● Done. The directory contains 8 items including Docker configuration, Python scripts, and
   documentation files.

This makes it hard to understand what happened, e.g. why did an agent decide to do a certain action based on the command output. I'd suggest an option to show full, or at least reasonably full, command output, and same for any other cases of when "↪ X lines..." is shown.

[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. ⭐

[sadiapeerzada]

Workaround: Use Interactive Mode for Full Output

While batch mode is designed for automation and may limit output for brevity, you can switch to interactive mode to receive complete command outputs. In interactive mode, Copilot provides detailed responses, including full outputs, which can help in understanding the agent's decisions.

To enter interactive mode:

Run copilot in your terminal without the -p flag.

Interact with Copilot by typing your prompts directly.

This mode allows for a more conversational interaction, where Copilot can explain its actions in detail.

[lopuhin]

@sadiapeerzada interactive mode is not better in that regard, see below

% copilot
 Welcome to GitHub Copilot CLI
 Version 0.0.346 · Commit 74e4d22

 ...

 > run ls -lha and stop

 ✓ List all files with details
   $ ls -lha
   ↪ 10 lines...

 ● Done. The directory contains 8 items including 5 Python scripts, a Dockerfile,
   README, and YAML config file.

besides that, I'd like to use the batch mode, because copilot agent is run remotely. Although if batch mode did provide the output I suppose I could simulate user interactions programmatically, but unfortunately it does not provide the output still.

For comparison, other agent tools and environments do provide output, e.g. when it's run in VSCode, or in GitHub.

[otto-gebb]

Looks like AI slop.