Commit Graph

1126 Commits

Author SHA1 Message Date
Yan98
0a5058342d init (#246) 2025-07-10 00:29:42 +08:00
Yuan Mengqi
093679b90d fix some multi_apps task (#243)
* fix chrome

* fix: fix proxy setup

* feat&fix: add proxy support in setup and remove hardcoded proxy from example

* fix tasks

* fix chrome finished

* fix

* clean chrome_fix code

* clean chrome_fix code

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix multiapps

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix some multi_apps tasks

* fix some multi_apps tasks

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-08 18:59:00 +08:00
Zeyi Sun
b6d9a804fa fix compare_videos in vlc.py (#242)
fix result in the same format of float number.
2025-07-08 16:25:00 +08:00
yuanmengqi
7d0ad02706 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-07-06 19:38:26 +00:00
yuanmengqi
a68d6f7ab6 Enhance GIMP metrics evaluator with logging and transparency handling
- Replaced print statements with logging for better traceability in gimp.py.
- Added handling for transparent images in structure checks and size evaluations.
- Updated JSON examples to include delays in pyautogui commands for improved execution reliability.
- Changed image URL in example to a more accessible source.
2025-07-06 19:38:22 +00:00
shuyhere
3afc01f1fe fix chrome examples (#240) 2025-07-07 02:25:59 +08:00
MillanK
8facb285a1 VS Code Task Fix (#237)
* vscode fix

* vscode task fix
2025-07-06 16:47:23 +08:00
yuanmengqi
a1891f7d88 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-07-06 07:52:42 +00:00
yuanmengqi
9be6fcd688 Check and fix on Chrome tasks
- Added `pytz` dependency to `requirements.txt` for timezone handling.
- Introduced `get_macys_product_url_parse` function to replace the old `get_url_path_parse` for better clarity and maintain backward compatibility.
- Enhanced logging throughout the `get_active_tab_html_parse` and `get_rule_relativeTime` functions for improved debugging and traceability.
- Updated JSON examples to reflect changes in expected keys and added new fields for better evaluation context.
- Removed deprecated execution commands from JSON examples to streamline the evaluation process.
2025-07-06 07:52:37 +00:00
Danyang Zhang
30a346eb68 Merge pull request #239 from xlang-ai/thbd_eval_fix
Thbd eval fix
fix w.r.t. a11y tree check function
2025-07-04 23:24:33 +08:00
zdy023
690f6ed6e7 ver Jul4th
fixed check_accessibility_tree function, updated the namespace
definitons according the values defined in server/main.py
2025-07-04 23:20:51 +08:00
zdy023
bfa796dc45 Merge branch 'main' into thbd_eval_fix 2025-07-04 23:14:00 +08:00
XXZ
c8a6a22aad Fix VLC task design (#238)
* fix: fix multiapp tasks

* fix: update instructions for VLC evaluation examples

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-04 20:39:48 +08:00
Shenzhennan
1b40a458de Impress eval fix (#226)
* fix compare_pptx

* Fix impress-4ed5abd0-8b5d-47bd-839f-cacfa15ca37a eval script:Fix temporarily by ignoring the contaminated  To fix completely, compare source file needs to be updated

* fix impress domain

* fix a53 by changing gold

* fix impress a53

* fix impress b8d origin file

* add table font color check

* fix left pane check

---------

Co-authored-by: chenjix <3107760494@qq.com>
Co-authored-by: moonshot <moonshot@moonshotznshenMacBook-Pro.local>
Co-authored-by: Shen Zhennan <shenzhennan@moonshot.cn>
2025-07-04 13:32:02 +08:00
Zilong Zhou
587f929567 fix: proxy setup (#234) 2025-07-04 13:31:51 +08:00
Zilong Zhou
1308a80029 Update 5990457f-2adb-467b-a4af-5c857c92d762.json (#235) 2025-07-04 13:31:18 +08:00
yuanmengqi
3cd79c9830 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-07-03 16:57:49 +00:00
yuanmengqi
a651b04e49 Update AWS AMI ID, enhance directory creation logic in file upload, modify osworld service configuration, and refine JSON evaluation examples for improved clarity and functionality. 2025-07-03 16:57:41 +00:00
Danyang Zhang
adc9ad88c2 Thunderbird eval fix (#233)
* ver Jul2nd

updated task requiring set up new email account

* ver Jul3rd

fixed several tasks
2025-07-03 21:55:55 +08:00
XXZ
ac24ccce99 fix: fix multiapp tasks (#229)
Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-03 21:53:58 +08:00
yuanmengqi
7b2120c843 Merge branch 'main' of github.com:xlang-ai/OSWorld 2025-07-03 13:50:35 +00:00
yuanmengqi
cb4bed20a0 Refactor compare_python_pure_text function for improved normalization and error handling. Update JSON example to clarify instruction for extracting Python code from Colab, changing output file names for consistency. 2025-07-03 13:50:21 +00:00
Yuan Mengqi
b2fb8b4222 fix chrome tasks (#230)
* fix chrome

* fix: fix proxy setup

* feat&fix: add proxy support in setup and remove hardcoded proxy from example

* fix tasks

* fix chrome finished

* fix

* clean chrome_fix code

* clean chrome_fix code

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
2025-07-03 21:32:41 +08:00
zdy023
3cf80eaab8 ver Jul3rd
fixed several tasks
2025-07-03 20:55:30 +08:00
ChenYXxxx
bdaf37e0e5 fix_os&gimp (#220)
* Update ec4e3f68-9ea4-4c18-a5c9-69f89d1178b3.json

* Update c288e301-e626-4b98-a1ab-159dcb162af5.json

* Update 3ce045a0-877b-42aa-8d2c-b4a863336ab8.json

* Update b3d4a89c-53f2-4d6b-8b6a-541fb5d205fa.json

* Update 2e6f678f-472d-4c55-99cc-8e7c5c402a71.json

Please batch process all images on the desktop by increasing their brightness to 50, instead of adjusting them individually.

* Update 5ca86c6f-f317-49d8-b6a7-b527541caae8.json

* Update a746add2-cab0-4740-ac36-c3769d9bfb46.json

* Update a746add2-cab0-4740-ac36-c3769d9bfb46.json

* Update 62f7fd55-0687-4a43-b6e1-3eda16fc6252.json

* Update d52d6308-ec58-42b7-a2c9-de80e4837b2b.json

* Update d16c99dc-2a1e-46f2-b350-d97c86c85c15.json

* Update d16c99dc-2a1e-46f2-b350-d97c86c85c15.json

* Update 58d3eeeb-e9d0-499f-962e-fd0db2a744d8.json
2025-07-03 16:59:05 +08:00
Tianbao Xie
bba367b8bc fix: fix multiapps tasks (#231)
* Update JSON example for multi_apps: change snapshot name and specify presenter in instructions for clarity.

* Enhance PDF image comparison in chrome.py by adding existence checks for input files and improving image extraction logic. Introduce image hashing for similarity scoring with a configurable threshold. Update docs.py to support fuzzy matching in DOCX file comparisons, allowing for similarity scoring based on text content. Modify example JSON to enable fuzzy matching option.

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-07-03 16:58:43 +08:00
Tianbao Xie
e9c657b714 fix: Libreoffice writer fix (#232)
* Refactor LibreOffice Writer example JSON to support multiple expected and result files for line spacing comparison, enhancing evaluation flexibility. Updated function calls and added additional expected file paths.

* Update source link in LibreOffice Writer example JSON to a more relevant help page for inserting tables, improving instructional clarity.

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-07-03 16:58:08 +08:00
zdy023
c4b47886d9 ver Jul2nd
updated task requiring set up new email account
2025-07-02 20:46:04 +08:00
Zilong Zhou
4d9528f208 feat&fix: add proxy support in get_info_from_website function (#228) 2025-07-02 18:13:15 +08:00
Zilong Zhou
595a704aff fix: fix proxy setup (#227)
* fix: fix proxy setup

* feat&fix: add proxy support in setup and remove hardcoded proxy from example
2025-07-02 01:36:32 +08:00
Danyang Zhang
d4273d992e Calc eval fix (#225)
* ver Jun17th

updating annotations

* ver Jun17th

corrected annotation of 1d17
added check for cell merge

* ver Jun17th

updated several annotations

* ver Jun20th

fixed set-up config of 2bd59342-0664-4ccb-ba87-79379096cc08

* fix: Enhance instructions in LibreOffice Calc examples for clarity and specificity, including details on using Pivot Tables, column placements, and revenue calculations.

* ver Jun21st

updating calc evals

* ver Jun22nd

fixed an impress task

* ver Jun22ndv2

adjusted several calc tasks

* Clean scalfolds

---------

Co-authored-by: BowenBryanWang <bryanwang.nlp@connect.hku.hk>
Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-30 18:23:09 +08:00
Tianbao Xie
30138c5db1 VLC fix (#224)
* Enhance SetupController with improved logging and error handling during setup and file upload processes. Update instance type to t3.xlarge and AMI ID for AWS configuration. Add download progress logging and exception handling for better debugging.

* Enhance VLC status evaluation by adding multiple paths for file and URL information extraction, improving robustness against varying VLC XML structures. Implement detailed logging for better debugging and error handling in case of mismatches or missing data. Update example JSON for VLC evaluation to use a valid HLS stream URL.

* Improve audio comparison robustness in VLC evaluator by adding error handling for audio file loading and extraction. Implement detailed logging for empty or corrupt files, and normalize DTW distance calculation for more accurate similarity scoring. Remove deprecated audio fingerprint comparison function.

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-29 20:18:44 +08:00
Tianbao Xie
0cc93543a8 Environment is_used flag; OS domain fix (#219)
* Refactor evaluator structure in LibreOffice Writer example JSON to support multiple expected and result files, enhancing evaluation flexibility.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update time format in get_vm_file function to include hours, minutes, and seconds for more precise file naming with time suffix.

* More delay for 936321ce-5236-426a-9a20-e0e3c5dc536f; support one more potential solutions.

* Enhance SetupController with configurable retry limit and improved error handling for file opening requests. Introduce new function to compare unique training records, and update logging for better debugging. Adjust JSON examples for evaluation to support multiple expected and result files.

* Clean debug code

* Enhance DesktopEnv to track environment usage for optimized snapshot management. Introduce is_environment_used flag to determine if a snapshot revert is necessary based on provider type. Update setup and step methods to mark environment usage appropriately. Add new execute_with_verification method in SetupController for command execution with result verification, improving reliability. Change AWS instance type to m5.large for better performance and update AMI ID for compatibility. Update file opening logic in main.py to handle both file paths and application commands more effectively.

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-28 00:45:53 +08:00
MillanK
48ac57697a VSCode fix (#222) 2025-06-24 17:08:09 +08:00
Zilong Zhou
634e1c3d6f Reduce the startup time of the software on AWS from one minute to five seconds. (#221)
* feat: use SSD with high throughput

* fix&refactor: update AMI ID and change EBS volume type to gp3 with adjusted IOPS and throughput
2025-06-24 15:35:38 +08:00
Zilong Zhou
3d8f1779a2 feat: use SSD with high throughput (#218) 2025-06-17 18:39:42 +08:00
Tianbao Xie
4e11eafd1d Robust Evaluation, Blocking File Open, Grader Sensitivity, and LibreOffice Writer Fixes (#217)
* Refactor evaluator structure in LibreOffice Writer example JSON to support multiple expected and result files, enhancing evaluation flexibility.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update instance type to t3.large and add VNC access URL logging for allocated VMs, enhancing remote access capabilities.

* Update time format in get_vm_file function to include hours, minutes, and seconds for more precise file naming with time suffix.

* More delay for 936321ce-5236-426a-9a20-e0e3c5dc536f; support one more potential solutions.

* Enhance SetupController with configurable retry limit and improved error handling for file opening requests. Introduce new function to compare unique training records, and update logging for better debugging. Adjust JSON examples for evaluation to support multiple expected and result files.

* Clean debug code

---------

Co-authored-by: yuanmengqi <yuanmengqi@mail.ustc.edu.cn>
2025-06-16 21:37:19 +08:00
Kaixin Li
347238e17e Get VM IP again when getting screenshot fails (#215)
In rare cases, the IP of the VM changes after it launches. We can get the IP every time we retry to ensure the correct connection.
2025-06-16 02:40:40 +08:00
Yuan Mengqi
40354322e8 fix pub eval readme typo (#214)
* update clean code

* fix pub eval readme typo
2025-06-10 22:57:16 +08:00
Yuan Mengqi
362499330e update clean code (#213) 2025-06-10 22:18:03 +08:00
Yuan Mengqi
4ce05b89ae Merge pull request #212 from yuanmengqi/aws_clean
AWS OSWorld Provider Enhancement, Proxy Intergration, new Agent Operator Inplementation
2025-06-10 21:44:18 +08:00
yuanmengqi
8a1fc5c385 edit pub eval readme 2025-06-10 13:37:26 +00:00
yuanmengqi
b8d229cdb3 edit pub eval readme 2025-06-10 13:36:48 +00:00
yuanmengqi
fbe88799cf edit pub eval readme 2025-06-10 13:36:03 +00:00
yuanmengqi
3b5e4f3b15 edit pub eval readme 2025-06-10 13:34:42 +00:00
yuanmengqi
2d5439d062 edit pub eval readme 2025-06-10 13:32:24 +00:00
yuanmengqi
2d3347ca3e edit pub eval readme 2025-06-10 13:28:54 +00:00
yuanmengqi
1b09d63cb2 edit pub eval readme 2025-06-10 13:27:53 +00:00
yuanmengqi
2bae228803 merge upstream 2025-06-10 13:23:03 +00:00
yuanmengqi
7315aec6e6 clean code 2025-06-10 04:06:54 +00:00