Copilot Failing to work on Assigned issue #199259
Replies: 1 comment
-
|
💬 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 ⏩
Where to look to see what's shipping 👀
What you can do in the meantime 💻
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. ⭐ |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
🏷️ Discussion Type
Bug
💬 Feature/Topic Area
Copilot in GitHub
Body
Hello,
For the past week, our entire organization has been unable to utilize the Copilot Coding/Workspace Agent when automating workflows. Specifically, when we assign a GitHub issue to Copilot via MCP (Model Context Protocol) or the GraphQL API, the assignment mutation itself is successful, but the Copilot agent immediately crashes when attempting to initiate the work.
Error Message Received (via UI/Agent output):
The agent encountered an error and was unable to start working on this issue: Please try again later, or contact support if the problem persists. (Request id: A000:3E7F70:26EEE1A:9003BF1:6A322642)
Steps to Reproduce:
Authenticate and initiate an API request via MCP or GraphQL to assign a specific GitHub issue to the Copilot Agent.
Observe that the API request completes successfully (e.g., HTTP 200 / successful mutation) and the issue reflects the assignment.
Observe the Copilot Agent's state: It fails to bootstrap the workspace/task.
The agent throws the error: unable to start working on this issue with the request ID mentioned above.
Previously we have observed this issue but after 2 days it was resolved and working on similar issue assignments
Duration of issue: ~1 week (ongoing)
Feedback & Impact:
Because the API assignment succeeds but the worker fails asynchronously, this breaks our automated triaging and coding pipelines. We have no visibility into why the worker node is crashing. It is unclear if this is a sudden token permission scope issue (e.g., the API token can assign the issue, but the backend agent lacks the scope to read the repository to start working), or a backend degradation in the Copilot Workspace routing.
Questions:
Has there been a recent change to the required OAuth/PAT scopes for API-driven Copilot Agent assignments?
Is the Request id: A000:3E7F70:26EEE1A:9003BF1:6A322642 indicative of a rate limit, a repository context size limit, or an internal server error (500)?
Are there any known issues with MCP integrations failing to hand off the required context to the Copilot backend workers?
Beta Was this translation helpful? Give feedback.
All reactions