Hello Simplification of the eval workflow 1. software-agent-sdk https://github.com/OpenHands/software-agent-sdk/pull/1267 2. evaluation https://github.com/OpenHands/evaluation/pull/55 They have been tested and they work! Only remaining issue is the URLs readability but that's a gcloud issue @chilly-france-44439 @calm-artist-7206

LGTM on 2! Very excited to see this comming together