Files
sci-gui-agent-benchmark/evaluation_examples/examples/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c.json
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

89 lines
2.9 KiB
JSON

{
"id": "3680a5ee-6870-426a-a997-eba929a0d25c",
"snapshot": "libreoffice_calc",
"instruction": "I have file1.xlsx and file2.ods on my Desktop, each containing a single column. Using only the command line, help me merge these two columns into a single column by concatenating the strings from both rows, save the result as ~/Desktop/output.csv, and open it in LibreOffice Calc from the terminal",
"source": "https://unix.stackexchange.com/questions/510850/how-to-open-calc-from-terminal-and-insert-files",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/file1.xlsx",
"path": "/home/user/Desktop/file1.xlsx"
},
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/file2.ods",
"path": "/home/user/Desktop/file2.ods"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": "export DBUS_SESSION_BUS_ADDRESS='unix:path=/run/user/1000/bus'\ngnome-terminal --maximize --working-directory=/home/user/Desktop",
"shell": true
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"libreoffice_calc",
"terminal"
],
"evaluator": {
"func": [
"check_include_exclude",
"compare_csv"
],
"conj": "and",
"result": [
{
"type": "vm_command_line",
"command": [
"/bin/bash",
"-c",
"output=$(ps aux | grep \"[s]office\" | awk '{print $7}' | grep -E \"pts/|tty\"); if [ -z \"$output\" ]; then echo \"use no terminal\"; else echo \"use terminal\"; fi;"
]
},
{
"type": "vm_file",
"path": "/home/user/Desktop/output.csv",
"dest": "output.csv"
}
],
"expected": [
{
"type": "rule",
"rules": {
"include": [
"use terminal"
]
}
},
{
"type": "cloud_file",
"multi": true,
"path": [
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output.csv",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output_gold2.csv",
"https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/multi_apps/3680a5ee-6870-426a-a997-eba929a0d25c/output_gold3.csv"
],
"dest": [
"output_gold.csv",
"output_gold2.csv",
"output_gold3.csv"
],
"gives": [
0,
1,
2
]
}
]
},
"proxy": false,
"fixed_ip": false,
"possibility_of_env_change": "low"
}