Commit graph

2 commits

Author SHA1 Message Date
Copilot
dedf05565d
feat(frontier): add replay variability suite and token-cost telemetry (#66)
Agent-Logs-Url: https://github.com/AssetOverflow/core/sessions/f88b48fa-0c2a-4f9d-a42b-d275596e43b8

Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com>
Co-authored-by: AssetOverflow <109810776+AssetOverflow@users.noreply.github.com>
2026-05-20 15:04:34 -07:00
Shay
e64ec578eb
feat(evals): frontier comparison benchmark wave 1 (#52)
* feat(evals): add frontier comparison benchmark wave one scaffold

* feat(evals): add frontier comparison runner package

* feat(evals): implement frontier comparison wave one suites

* feat(evals): add frontier comparison CLI entrypoint

* feat(evals): add static frontier benchmark report viewer

* test(evals): cover frontier comparison wave one benchmarks

* fix(evals): record runtime observation failures instead of aborting suites

* docs(evals): document frontier comparison recording UI
2026-05-20 06:27:32 -07:00