Files
sci-gui-agent-benchmark/evaluation_examples/examples/gimp/a746add2-cab0-4740-ac36-c3769d9bfb46.json
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

83 lines
2.4 KiB
JSON

{
"id": "a746add2-cab0-4740-ac36-c3769d9bfb46",
"snapshot": "gimp",
"instruction": "Help me open up the Vignette filter window.",
"source": "https://www.youtube.com/watch?v=_L_MMU22bAw",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/gimp/a746add2-cab0-4740-ac36-c3769d9bfb46/dog_with_background.png",
"path": "/home/user/Desktop/dog_with_background.png"
}
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"gimp",
"/home/user/Desktop/dog_with_background.png"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import time; import pyautogui; pyautogui.press([\"esc\"]);time.sleep(1);pyautogui.hotkey([\"ctrl\", \"q\"]);time.sleep(1);"
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import time; import pyautogui; pyautogui.press([\"right\"]);time.sleep(1);pyautogui.press([\"enter\"])"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_include_exclude",
"result": {
"type": "vm_command_line",
"command": "cat /home/user/.config/GIMP/2.10/action-history",
"shell": true
},
"expected": {
"type": "rule",
"rules": {
"include": [
"filters-vignette"
],
"exclude": [
"error",
"failed",
"not found"
]
}
}
},
"proxy": false
}