Flight Log / repository
microsoft/debug-gym — agent flight log
6 pull requests opened by AI coding agents in microsoft/debug-gym (★ 308, Python): GitHub Copilot (GitHub) 6 (67% merged).
Flights by agent
| Agent | Flights | Merge rate | Median to merge | Burn rate |
|---|---|---|---|---|
| GitHub Copilot (GitHub) | 6 | 67% | 2.1 d | 33% |
By month
| Month | Flights | Merged | Burns |
|---|---|---|---|
| 2025-05 | 3 | 2 | 1 |
| 2025-06 | 1 | 1 | 0 |
| 2025-07 | 2 | 1 | 1 |
Where agents burned here
- GitHub Copilot (GitHub) burn #185
Fixed by #186
- GitHub Copilot (GitHub) burn #131
@copilot go ahead and update the swebench version to the latest in the requirements. Then make sure you can run one of the swesmith task.
Last 6 flights
| PR | Title | Agent | Opened | Lines | |
|---|---|---|---|---|---|
| #185 | [WIP] Split "failed" status into "failed" and "error" | GitHub Copilot | Burn | Jul 10, 2025 | +0 −0 |
| #179 | Fix get_problem_ids to respect instance_ids parameter in SWE environments | GitHub Copilot | Merged clean | Jul 10, 2025 | +284 −289 |
| #161 | Fix PDB indentation mismatch in list output context | GitHub Copilot | Merged after rework | Jun 23, 2025 | +599 −410 |
| #131 | Add support for SWESmith | GitHub Copilot | Burn | May 26, 2025 | +636 −13 |
| #129 | Fix 'utf-8' codec error with surrogate pairs in Unicode strings | GitHub Copilot | Merged clean | May 26, 2025 | +47 −7 |
| #126 | Add max_retries parameter to Human class to limit terminal read attempts | GitHub Copilot | Merged clean | May 26, 2025 | +162 −45 |
No rider has claimed a flight in this repository yet. Flew one of these? Open your flight page and claim it.
Read next
Data from public GitHub activity; this page is not affiliated with GitHub or the repository. Repository owner? Request exclusion — handled within 48 hours.