Get automated code review on your own pull requests
A user used Copilot code review on PRs in their private repo, but reviews hung for hours and ended in errors.
Done withGitHub Copilot
- What they did
- The user paid for an individual Copilot subscription and had Copilot review PRs they opened against their own private repo. It worked at first, then failed about half the time and later over 90%. Runners hung for up to 6 hours. Commenters suggested checking the repo contents, cancelling stuck jobs, and testing another repo.
- How it went
- The cause turned out to be a 20-megabyte binary disk image checked into the repo. After the user deleted it, reviews worked again. Copilot gave no error naming the file.
- Worth knowing
- Look for large binary files committed to the repo if reviews hang. The user also found that cancelling stuck runs in Actions sometimes made them produce output anyway.
Try it yourself with GitHub Copilot
Please review my pull request [PR number] in [owner/repo] as a code reviewer. Leave inline comments on bugs, risky changes, missing tests, and unclear naming, and finish with a short summary of the most important things to fix. If the review can't complete, tell me the error so I can retry instead of leaving it hanging.
Want help getting this working? Join the Vibe Coding Academy ↗ Run by Alex Finn, who also runs this site.
Source: github.com · Undated
Related use cases
Run a solo company with eight agent departments
A founder set up CEO, CFO, COO, lawyer, accountant, marketing, CTO, and improver agents that share memory and consult each other.
Add a filtered report page to a Razor Pages app
The poster used Copilot agent mode in Visual Studio 2022 to build a charges summary report page with date and status filters, add a menu option, and write the git commit steps.
Have Copilot write all of a day's pushed code
A commenter had Copilot write every line pushed in a day; it mostly worked but one wrong change needed human review.
Build a C compiler with a team of parallel agents
Anthropic's engineering write-up on tasking Opus 4.6 agent teams with building a C compiler.
Test Devin on integrations, migration and security review
Answer.AI tried Devin on an observability integration, an nbdev migration and a vulnerability review; it found some real issues, hallucinated others, and failed the migration.
Find bugs with property-testing agent swarms
Agent swarms doing property testing found about 30 bugs in the author's work code, then ~100 bugs across open-source projects like uv, with many fixes merged.
Get 5 like this every morning
The best things people got an AI agent to do, each with the prompt to try it.