lzy/sci-gui-agent-benchmark
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

ver Mar6th

Browse Source 
three new tasks
This commit is contained in:
David Chang
2024-03-06 15:06:08 +08:00
parent 459e247736
commit 5817403e2e
3 changed files with 237 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

147
evaluation_examples/examples/multi_apps/415ef462-bed3-493a-ac36-ca8c6d23bf1b.json Normal file
View File

@@ -0,0 +1,147 @@
{
"id": "415ef462-bed3-493a-ac36-ca8c6d23bf1b",
"snapshot": "thunderbird",
"instruction": "Save the AWS invoice of December from the email. I have moved that email to local \"Bills\" folder. Save it to the my receipts folder. Keep the file name pattern and update a record to my tally book.",
"source": "authors",
"config": [
{
"type": "execute",
"parameters": {
"command": ["mkdir", "-p", "/home/user/Documents/Finance/receipts", "/home/user/Documents/Projects"]
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2308.pdf", "url": "https://drive.google.com/uc?id=1azRFXf4A7fvW0S7r9upHvleMEi-92hHM&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2309.pdf", "url": "https://drive.google.com/uc?id=1x-lpHm8U4U7uRPZ74-9wq9KzW2R55ln1&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2310.pdf", "url": "https://drive.google.com/uc?id=1pcrgV9G6NO4ekMEQBiupwXtq6mmke7b_&export=download"},
{"path": "/home/user/Documents/Finance/receipts/aws-invoice-2311.pdf", "url": "https://drive.google.com/uc?id=1JzbCK_nIY8X_3QZjnkzTtb-cRoq9zNT-&export=download"},
{"path": "/home/user/Documents/Finance/receipts/X-receipt-2312.pdf", "url": "https://drive.google.com/uc?id=1QzWjNzvNosG_yQr7VVonvYb3cUYF5f3u&export=download"},
{"path": "/home/user/Documents/Finance/tally_book.xlsx", "url": "https://drive.google.com/uc?id=13yuLhBPmouoWR-DybfgaIbWUOxbY_jhL&export=download"},
{"path": "/home/user/.projects.tar.xz", "url": "https://drive.google.com/uc?id=1oJcxpjqF474Wm16i1aZc8DlCEfAvc4t_&export=download"},
{
"url": "https://drive.usercontent.google.com/download?id=1EHLRWzBCOsyERkSMUnTF2pnsR0n6ZvtR&export=download&authuser=0&confirm=t&uuid=de09bd5e-bef8-499a-b599-c642af190e10&at=APZUnTXqOsQkxl0zMSX6R1Sgp_v3:1704362491712",
"path": "/home/user/thunderbird-profile.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["tar", "-xJvf", "/home/user/.projects.tar.xz", "-C", "/home/user/Documents/Projects"]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"--recursive-unlink",
"-f",
"/home/user/thunderbird-profile.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": ["thunderbird"]
}
}
],
"trajectory": "trajectories/415ef462-bed3-493a-ac36-ca8c6d23bf1b",
"related_apps": ["thunderbird", "libreoffice_calc", "os"],
"evaluator": {
"postconfig": [
{
"type": "activate_window",
"parameters": {
"window_name": "tally_book.xlsx - LibreOffice Calc",
"strict": true
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "execute",
"parameters": {
"command": [
"python",
"-c",
"import pyautogui; pyautogui.hotkey(\"ctrl\", \"s\");"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
},
{
"type": "download",
"parameters": {
"files": [
{"path": "/home/user/.aws-invoice-2312.pdf", "url": "https://drive.google.com/uc?id=1RqbulzKG_HeYb1GZmLABOzlohlFg02UU&export=download"}
]
}
},
{
"type": "execute",
"parameters": {
"command": ["diff", ".aws-invoice-2312.pdf", "/home/user/Documents/Finance/receipts/aws-invoice-2312.pdf"],
"stdout": "diff.out"
}
}
],
"func": ["compare_table", "check_list"],
"result": [
{
"type": "vm_file",
"path": "/home/user/Documents/Finance/tally_book.xlsx",
"dest": "tally_book.xlsx"
},
{
"type": "cache_file",
"path": "diff.out"
}
],
"expected": [
{
"type": "cloud_file",
"path": "https://drive.google.com/uc?id=1x8m-korGI1PhJm8PAQVTlWYKneK4WKvn&export=download",
"dest": "tally_book_gt.xlsx"
},
{
"type": "rule",
"rules": {
"unexpect": [
".+"
]
}
}
],
"options": [
{
"rules": [
{
"type": "sheet_data",
"sheet_idx0": 0,
"sheet_idx1": "EI0"
}
]
},
{}
]
}
}

59
evaluation_examples/examples/multi_apps/e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56.json Normal file
View File

@@ -0,0 +1,59 @@
{
"id": "e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56",
"snapshot": "libreoffice_writer",
"instruction": "Install LanguageTool extension for my LibreOffice",
"source": "authors",
"config": [
{
"type": "launch",
"parameters": {
"command": ["libreoffice", "--writer"]
}
}
],
"trajectory": "trajectories/e1fc0df3-c8b9-4ee7-864c-d0b590d3aa56",
"related_apps": ["chrome", "libreoffice", "os"],
"evaluator": {
"postconfig": [
{
"type": "command",
"parameters": {
"command": ["grep", "-nHr", "languagetool", "/home/user/.config/libreoffice/4/user/uno_packages/cache/uno_packages/"],
"stdout": "grep.out"
}
},
{
"type": "command",
"parameters": {
"command": ["apt", "list", "--installed"],
"stdout": "apt.out"
}
}
],
"func": ["check_list", "check_list"],
"result": [
{
"type": "cache_file",
"path": "grep.out"
},
{
"type": "cache_file",
"path": "apt.out"
}
],
"expected": [
{
"type": "rule",
"rules": {
"expect": ["org\\.openoffice\\.languagetool\\.oxt"]
}
},
{
"type": "rule",
"rules": {
"expect": ["openjdk-\\d+-(jre|jdk)"]
}
}
]
}
}

31
evaluation_examples/examples/multi_apps/f8369178-fafe-40c2-adc4-b9b08a125456.json Normal file
View File

@@ -0,0 +1,31 @@
{
"id": "f8369178-fafe-40c2-adc4-b9b08a125456",
"snapshot": "chrome",
"instruction": "Help me to install Orchis theme from gnome-look.org and change to it for my GNOME desktop.",
"source": "https://itsfoss.com/install-switch-themes-gnome-shell",
"config": [],
"trajectory": "trajectories/f8369178-fafe-40c2-adc4-b9b08a125456",
"related_apps": ["chrome", "os"],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": ["gsettings", "get", "org.gnome.desktop.interface", "gtk-theme"],
"stdout": "gsettings.out"
}
}
],
"func": "check_list",
"result": {
"type": "cache_file",
"path": "gsettings.out"
},
"expected": {
"type": "rule",
"rules": {
"expect": ["Orchis"]
}
}
}
}