lzy/sci-gui-agent-benchmark
2
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: Add proxy configuration to all 369 evaluation examples - 55 with proxy, 314 without

Browse Source
This commit is contained in:
Timothyxxx
2025-06-05 18:46:53 +08:00
parent 3b1540ed23
commit fb7bafb885
371 changed files with 2901 additions and 2028 deletions
Download Patch File Download Diff File Expand all files Collapse all files

96
evaluation_examples/examples/multi_apps/2373b66a-092d-44cb-bfd7-82e86e7a3b4d.json
View File

@@ -1,49 +1,61 @@
{
"id": "2373b66a-092d-44cb-bfd7-82e86e7a3b4d",
"snapshot": "multiapps",
"instruction": "I want to understand the resource usage of my Ubuntu system under normal workloads. Please use the `sar` command in the `sysstat` toolkit to monitor system activity, evaluate the status once every second for 30 seconds, output the results to \"System_Resources_Report.txt\" under Desktop.",
"source": "author",
"config": [
{
"type": "command",
"parameters":{
"command": "echo password | sudo -S apt-get update && echo password | sudo -S apt-get install sysstat",
"shell": "true"
}
}
"id": "2373b66a-092d-44cb-bfd7-82e86e7a3b4d",
"snapshot": "multiapps",
"instruction": "I want to understand the resource usage of my Ubuntu system under normal workloads. Please use the `sar` command in the `sysstat` toolkit to monitor system activity, evaluate the status once every second for 30 seconds, output the results to \"System_Resources_Report.txt\" under Desktop.",
"source": "author",
"config": [
{
"type": "command",
"parameters": {
"command": "echo password | sudo -S apt-get update && echo password | sudo -S apt-get install sysstat",
"shell": "true"
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"os",
"calc"
],
"evaluator": {
"func": [
"file_contains",
"check_line_number"
],
"trajectory": "trajectories/",
"related_apps": [
"os", "calc"
"result": [
{
"type": "vm_file",
"path": "/home/user/Desktop/System_Resources_Report.txt",
"dest": "System_Resources_Report.txt"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/System_Resources_Report.txt",
"dest": "System_Resources_Report.txt"
}
],
"evaluator": {
"func": ["file_contains", "check_line_number"],
"result":
[
{
"type": "vm_file",
"path": "/home/user/Desktop/System_Resources_Report.txt",
"dest": "System_Resources_Report.txt"
},
{
"type": "vm_file",
"path": "/home/user/Desktop/System_Resources_Report.txt",
"dest": "System_Resources_Report.txt"
}
],
"expected":
[
{
"type": "rule",
"rules" :{
"expected": ["CPU", "%user","%nice","%system", "%iowait", "%steal", "%idle"]
}
},
"expected": [
{
"type": "rule",
"rules": {
"expected": "31"
"expected": [
"CPU",
"%user",
"%nice",
"%system",
"%iowait",
"%steal",
"%idle"
]
}
}]
}
}
},
{
"type": "rule",
"rules": {
"expected": "31"
}
}
]
},
"proxy": false
}