Commit Graph

6 Commits

Author SHA1 Message Date
yuanmengqi
e433f35c1f feat: standardize configuration fields across all evaluation examples
- Add `fixed_ip` field to all 369 JSON files in examples directory
  - Set to `true` for 8 files listed in google_chrome.json multi_apps
  - Set to `false` for remaining 361 files
- Add `possibility_of_env_change` field to 363 JSON files missing this field
  - Set to "low" for newly added fields
  - Preserve existing values (4 medium, 2 high) for 6 files that already had this field

This ensures consistent configuration schema across all evaluation examples
while maintaining backward compatibility with existing settings.
2025-07-16 13:45:34 +00:00
Timothyxxx
fb7bafb885 feat: Add proxy configuration to all 369 evaluation examples - 55 with proxy, 314 without 2025-06-05 18:46:53 +08:00
Timothyxxx
34748567a5 feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation
- Add detailed README for file cache repository
- Implement migration script with retry logic and browser simulation
- Support automatic file type detection and deduplication
- Ensure reliable hosting for OSWorld evaluation files
2025-05-28 04:29:37 +08:00
David Chang
4897211a46 ver Jan31stv6
finished calc human evaluation
updated calc configs with an extra sleep to guarantee the integrity of
downloaded xlsx file
2024-01-31 22:55:47 +08:00
David Chang
8025bf19f0 ver Jan27th
corrected usage of pyautogui in calc postconfig
2024-01-27 19:46:06 +08:00
David Chang
93229ce98c ver Jan22ndv3
updated style metric to compare_table
2024-01-22 23:45:15 +08:00