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

Improve code logic for password & resolution (#252)

Browse Source 
* fix chrome

* fix: fix proxy setup

* feat&fix: add proxy support in setup and remove hardcoded proxy from example

* fix tasks

* fix chrome finished

* fix

* clean chrome_fix code

* clean chrome_fix code

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix multiapps

* fix chrome 2888b4e6-5b47-4b57-8bf5-c73827890774

* fix some multi_apps tasks

* fix some multi_apps tasks

* fix password&resolution

* fix password&resolution

* Improve code logic for password & resolution

* edit

* Merge branch 'main' into fix_chrome

* fix chrome tasks

---------

Co-authored-by: adlsdztony <zzl0712@connect.hku.hk>
This commit is contained in:
Yuan Mengqi
2025-07-13 21:04:07 +08:00
committed by GitHub
parent 97ed6f99b0
commit 38a30734a6
16 changed files with 98 additions and 55 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
evaluation_examples/examples/chrome/3299584d-8f11-4457-bf4c-ce98f7600250.json
View File

@@ -7,7 +7,7 @@
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S apt update -y && echo password | sudo -S apt install jq -y",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt update -y && echo {CLIENT_PASSWORD} | sudo -S apt install jq -y",
"shell": true
}
},

2
evaluation_examples/examples/chrome/6766f2b8-8a72-417f-a9e5-56fcaa735837.json
View File

@@ -18,7 +18,7 @@
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S apt-get update -y && echo password | sudo -S apt-get install unzip -y && unzip /home/user/Desktop/helloExtension.zip -d /home/user/Desktop/ && rm /home/user/Desktop/helloExtension.zip",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt-get update -y && echo {CLIENT_PASSWORD} | sudo -S apt-get install unzip -y && unzip /home/user/Desktop/helloExtension.zip -d /home/user/Desktop/ && rm /home/user/Desktop/helloExtension.zip",
"shell": true
}
},

2
evaluation_examples/examples/chrome/6c4c23a1-42a4-43cc-9db1-2f86ff3738cc.json
View File

@@ -74,5 +74,5 @@
}
}
},
"proxy": true
"proxy": false
}

2
evaluation_examples/examples/chrome/b4f95342-463e-4179-8c3f-193cd7241fb2.json
View File

@@ -1,7 +1,7 @@
{
"id": "b4f95342-463e-4179-8c3f-193cd7241fb2",
"snapshot": "chrome",
"instruction": "Find the next available date for Diamond.",
"instruction": "List as many of the next available dates for Diamond Campground as possible.",
"source": "test_task_1",
"config": [
{

8
evaluation_examples/examples/chrome/fc6d8143-9452-4171-9459-7f515143419a.json
View File

@@ -1,7 +1,7 @@
{
"id": "fc6d8143-9452-4171-9459-7f515143419a",
"snapshot": "chrome",
"instruction": "Find the status of tomorrow flights from New York airports to Columbus in Ohio.",
"instruction": "Find the status of tomorrow flights from New York-Kennedy airport to Chicago-O'Hare airport.",
"source": "test_task_0",
"config": [
{
@@ -65,12 +65,12 @@
"from": "tomorrow"
},
"expected": {
"start": "NYC",
"end": "CMH",
"start": "JFK",
"end": "ORD",
"time": "{DoW}, {Month} {Day0D}, {Year}"
}
}
}
},
"proxy": true
"proxy": false
}

2
evaluation_examples/examples/multi_apps/2373b66a-092d-44cb-bfd7-82e86e7a3b4d.json
View File

@@ -7,7 +7,7 @@
{
"type": "command",
"parameters": {
"command": "echo password | sudo -S apt-get update && echo password | sudo -S apt-get install sysstat",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt-get update && echo {CLIENT_PASSWORD} | sudo -S apt-get install sysstat",
"shell": "true"
}
}

2
evaluation_examples/examples/multi_apps/716a6079-22da-47f1-ba73-c9d58f986a38.json
View File

@@ -25,7 +25,7 @@
{
"type": "command",
"parameters": {
"command": "echo password | sudo -S apt install xsel && xsel -bc",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt install xsel && xsel -bc",
"shell": "true"
}
}

9
evaluation_examples/examples/multi_apps/9f3bb592-209d-43bc-bb47-d77d9df56504.json
View File

@@ -61,14 +61,7 @@
{
"type": "command",
"parameters": {
"command": "echo password | sudo -S pip install pysrt",
"shell": "true"
}
},
{
"type": "command",
"parameters": {
"command": "echo osworld-public-evaluation | sudo -S pip install pysrt",
"command": "echo {CLIENT_PASSWORD} | sudo -S pip install pysrt",
"shell": "true"
}
}

2
evaluation_examples/examples/multi_apps/a74b607e-6bb5-4ea8-8a7c-5d97c7bbcd2a.json
View File

@@ -18,7 +18,7 @@
{
"type": "execute",
"parameters": {
"command": "echo password | sudo -S apt-get update -y && echo password | sudo -S apt-get install unzip -y && unzip /home/user/Desktop/helloExtension.zip -d /home/user/Desktop/ && rm /home/user/Desktop/helloExtension.zip",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt-get update -y && echo {CLIENT_PASSWORD} | sudo -S apt-get install unzip -y && unzip /home/user/Desktop/helloExtension.zip -d /home/user/Desktop/ && rm /home/user/Desktop/helloExtension.zip",
"shell": true
}
},

2
evaluation_examples/examples/os/5812b315-e7bd-4265-b51f-863c02174c28.json
View File

@@ -21,7 +21,7 @@
{
"type": "execute",
"parameters": {
"command": "echo 'password' | sudo -S apt-get install -y expect",
"command": "echo {CLIENT_PASSWORD} | sudo -S apt-get install -y expect",
"shell": true
}
},

2
evaluation_examples/examples/os/e0df059f-28a6-4169-924f-b9623e7184cc.json
View File

@@ -8,7 +8,7 @@
{
"type": "execute",
"parameters": {
"command": "echo 'password' | sudo -S mkdir ~/Desktop/todo_list_Jan_1",
"command": "echo {CLIENT_PASSWORD} | sudo -S mkdir ~/Desktop/todo_list_Jan_1",
"shell": true
}
},