Skip to content

SWE-agent takes a GitHub issue and tries to automatically fix it, using your LM of choice. It can also be employed for offensive cybersecurity or competitive coding challenges. [NeurIPS 2024]

399 B
Raw Blame
# Configuration for codecov
coverage:
  status:
    project:
      default:
        # If we get < 50% coverage, codecov is gonna mark it a failure
        target: 50%
        threshold: null
    patch:
      default:
        # Codecov won't mark it as a failure if a patch is not covered well
        informational: true
github_checks:
  # Don't mark lines that aren't covered
  annotations: false