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

feat: Migrate OSWorld files to HuggingFace cache with comprehensive documentation

Browse Source 
- Add detailed README for file cache repository
- Implement migration script with retry logic and browser simulation
- Support automatic file type detection and deduplication
- Ensure reliable hosting for OSWorld evaluation files
This commit is contained in:
Timothyxxx
2025-05-28 04:29:37 +08:00
parent a845824f06
commit 34748567a5
317 changed files with 12630 additions and 12008 deletions
Download Patch File Download Diff File Expand all files Collapse all files

194
evaluation_examples/examples/thunderbird/15c3b339-88f7-4a86-ab16-e71c58dcb01e.json
View File

@@ -1,99 +1,99 @@
{
"id": "15c3b339-88f7-4a86-ab16-e71c58dcb01e",
"snapshot": "thunderbird",
"instruction": "Help me access my outlook account with address \"anonym-x2024@outlook.com\" and password 'Wlv(z._6y|a,rrjfQuQhIi\\$;' (without ')",
"source": "https://www.wikihow.com/Access-Gmail-With-Mozilla-Thunderbird",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://drive.usercontent.google.com/download?id=1hSVXjep_RBaN2VN039sKCkFM5NB32wn9&export=download&authuser=0&confirm=t&uuid=90be5a47-f360-4460-8706-628ae555e52b&at=APZUnTV7JqHDhcQJjWKJL_2jO1vj:1705411196058",
"path": "/home/user/Desktop/thunderbird-profile-blank.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"-f",
"/home/user/Desktop/thunderbird-profile-blank.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://raw.githubusercontent.com/unode/firefox_decrypt/3f1a6dce63056c1f64d845ff077fc1e653e757c6/firefox_decrypt.py",
"path": "/home/user/Desktop/firefox_decrypt.py"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python3",
"/home/user/Desktop/firefox_decrypt.py",
"/home/user/.thunderbird",
"-n",
"-c",
"2",
"-f",
"csv",
"-d",
","
],
"stdout": "thunderbird-accounts.csv"
}
}
],
"func": "check_csv",
"result": {
"type": "cache_file",
"path": "thunderbird-accounts.csv"
},
"expected": {
"type": "rule",
"rules": {
"expect": [
{
"url": "imap://outlook.office365.com",
"user": "anonym-x2024@outlook.com",
"password": "Wlv(z._6y|a,rrjfQuQhIi\\$;"
},
{
"url": "smtp://smtp.office365.com",
"user": "anonym-x2024@outlook.com",
"password": "Wlv(z._6y|a,rrjfQuQhIi\\$;"
}
]
}
}
"id": "15c3b339-88f7-4a86-ab16-e71c58dcb01e",
"snapshot": "thunderbird",
"instruction": "Help me access my outlook account with address \"anonym-x2024@outlook.com\" and password 'Wlv(z._6y|a,rrjfQuQhIi\\$;' (without ')",
"source": "https://www.wikihow.com/Access-Gmail-With-Mozilla-Thunderbird",
"config": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://huggingface.co/datasets/xlangai/ubuntu_osworld_file_cache/resolve/main/thunderbird/15c3b339-88f7-4a86-ab16-e71c58dcb01e/thunderbird-profile-blank.tar.gz",
"path": "/home/user/Desktop/thunderbird-profile-blank.tar.gz"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"tar",
"-xzv",
"-f",
"/home/user/Desktop/thunderbird-profile-blank.tar.gz",
"-C",
"/home/user/"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"/usr/bin/thunderbird"
]
}
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"thunderbird"
],
"evaluator": {
"postconfig": [
{
"type": "download",
"parameters": {
"files": [
{
"url": "https://raw.githubusercontent.com/unode/firefox_decrypt/3f1a6dce63056c1f64d845ff077fc1e653e757c6/firefox_decrypt.py",
"path": "/home/user/Desktop/firefox_decrypt.py"
}
]
}
},
{
"type": "execute",
"parameters": {
"command": [
"python3",
"/home/user/Desktop/firefox_decrypt.py",
"/home/user/.thunderbird",
"-n",
"-c",
"2",
"-f",
"csv",
"-d",
","
],
"stdout": "thunderbird-accounts.csv"
}
}
],
"func": "check_csv",
"result": {
"type": "cache_file",
"path": "thunderbird-accounts.csv"
},
"expected": {
"type": "rule",
"rules": {
"expect": [
{
"url": "imap://outlook.office365.com",
"user": "anonym-x2024@outlook.com",
"password": "Wlv(z._6y|a,rrjfQuQhIi\\$;"
},
{
"url": "smtp://smtp.office365.com",
"user": "anonym-x2024@outlook.com",
"password": "Wlv(z._6y|a,rrjfQuQhIi\\$;"
}
]
}
}
}
}