kubernetes-sigs / kubernetes-sigs/devops-bench
feat(tasks): add four tasks with deterministic verification specs
Open
- Dominant language
- Python
- Stars
- 29
- Forks
- 15
- Avg merge
- 6d 3h
- Merged PRs (30d)
- 15
Description
New benchmark tasks, each with a prompt and a `verification_spec` rather than judged prose alone. Owner: @jessie1111101.
- [ ] #105 `cve-remediation` and its kind stack
- [ ] #106 `spot-rebalancing` and its kind stack
- [ ] #107 `migration-and-upgrade` and its stack
- [ ] #108 grade what the agent broke on `opa-remediation`
Related: #110 hardening `cve-remediation` with layered failure modes.
Contributor guide
Assessment
This issue has not been assessed yet.