Unreleased
Changes on main that aren't in a PyPI release yet.
- OSWorld computer-use tasks:
scripts/import_osworld.pyimports 16 of OSWorld’s (Apache-2.0) LibreOffice Calc and Writer tasks as computer-use environments, each with a reference episode, and writes OSWorld’s license and a NOTICE next to them. They boot the Daytona snapshotdeepgym-osworld-libreoffice(--build-snapshotcreates it), since Daytona’s default image has no LibreOffice;metadata.jsontakes asnapshot. The verifier scores the saved file with the task’s owncompare_tablerules (ported into the shared_checks.py, standard library only) or its reference text, never a screenshot. Rules the starting file already holds, or holds once an empty sheet is added, are guards, so an untouched file or a blank sheet scores 0; a saved file the readers can’t read (missing, corrupt, not a regular file, too large) scores 0, and reading and scoring run in a time- and memory-limited child whose failure also scores 0, so nothing in the file can crash or stall the verifier.deepgym checkasks a computer-use folder forreference_actions.jsoninstead ofreference_solution.*, and is inconclusive on one off Daytona.