Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/aad10cd7-9337-4b62-b704-a857848cedf2.json
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

74 lines
1.9 KiB
JSON

{
"id": "aad10cd7-9337-4b62-b704-a857848cedf2",
"snapshot": "chrome",
"instruction": "I want to obtain a local file version of the content from the blog at https://developer.apple.com/design/human-interface-guidelines/searching to facilitate my own revision. Please retain the primary content on this page, specifically from 'searching' to just before 'resources.' Assist me in saving this blog as \"notes.docx\" on the desktop.",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/aad10cd7-9337-4b62-b704-a857848cedf2",
"related_apps": [
"os",
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "notes.docx - LibreOffice Writer",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; import time; pyautogui.hotkey('ctrl', 's'); time.sleep(0.5); "
]
}
}
],
"func": "compare_docx_files",
"expected": {
"type": "cloud_file",
"path": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/aad10cd7-9337-4b62-b704-a857848cedf2/notes.docx",
"dest": "notes_Gold.docx"
},
"result": {
"type": "vm_file",
"path": "/home/user/Desktop/notes.docx",
"dest": "notes.docx"
},
"options": {
"fuzzy_match": true
}
},
"proxy": false
}