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

feat: enhance evaluator configuration for Chrome with post-execution commands

Browse Source 
- Added postconfig commands to multiple JSON files for Chrome evaluation examples.
- Included commands to terminate existing Chrome processes, launch Chrome with remote debugging, and introduce sleep intervals for timing.
- Updated logging messages in the AWS manager to improve clarity and user experience.

These changes enhance the automation and usability of the evaluation examples while preserving existing logic.
This commit is contained in:
yuanmengqi
2025-07-17 10:50:10 +00:00
parent 24fbad9015
commit 2c51950e73
12 changed files with 172 additions and 59 deletions
Download Patch File Download Diff File Expand all files Collapse all files

26
evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json
View File

@@ -29,6 +29,32 @@
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "launch",
"parameters": {
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "exact_match",
"result": {
"type": "enable_do_not_track"

26
evaluation_examples/examples/chrome/2ad9387a-65d8-4e33-ad5b-7580065a27ca.json
View File

@@ -29,6 +29,32 @@
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "launch",
"parameters": {
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "is_expected_bookmarks",
"result": {
"type": "bookmarks"

6
evaluation_examples/examples/chrome/2ae9ba84-3a0d-4d4c-8338-3a1478dc5fe3.json
View File

@@ -47,6 +47,12 @@
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "exact_match",

6
evaluation_examples/examples/chrome/44ee5668-ecd5-4366-a6ce-c1c9b8d4e938.json
View File

@@ -254,6 +254,12 @@
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "check_history_deleted",

6
evaluation_examples/examples/chrome/480bcfea-d68f-4aaa-a0a9-2589ef319381.json
View File

@@ -47,6 +47,12 @@
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "check_enabled_experiments",

26
evaluation_examples/examples/chrome/7a5a7856-f1b6-42a4-ade9-1ca81ca0f263.json
View File

@@ -38,6 +38,32 @@
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "launch",
"parameters": {
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "is_expected_bookmarks",
"result": {
"type": "bookmarks"

26
evaluation_examples/examples/chrome/7b6c7e24-c58a-49fc-a5bb-d57b80e5b4c3.json
View File

@@ -38,6 +38,32 @@
"chrome"
],
"evaluator": {
"postconfig": [
{
"type": "launch",
"parameters": {
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "is_cookie_deleted",
"result": {
"type": "cookie_data",

23
evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json
View File

@@ -31,10 +31,27 @@
"evaluator": {
"postconfig": [
{
"type": "execute",
"type": "launch",
"parameters": {
"command": "pkill chrome",
"shell": "true"
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],

23
evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json
View File

@@ -31,10 +31,27 @@
"evaluator": {
"postconfig": [
{
"type": "execute",
"type": "launch",
"parameters": {
"command": "pkill chrome",
"shell": "true"
"command": [
"pkill",
"chrome"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],

6
evaluation_examples/examples/chrome/af630914-714e-4a24-a7bb-f9af687d3b91.json
View File

@@ -47,6 +47,12 @@
"--remote-debugging-port=1337"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
}
],
"func": "check_font_size",

52
evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json
View File

@@ -31,28 +31,11 @@
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import pyautogui; pyautogui.press('f5')"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
},
{
"type": "execute",
"type": "launch",
"parameters": {
"command": [
"pkill",
"-f",
"google-chrome"
"chrome"
]
}
},
@@ -65,37 +48,6 @@
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
},
{
"type": "chrome_open_tabs",
"parameters": {
"urls_to_open": [
"chrome://settings/search",
"chrome://settings"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 3
}
},
{
"type": "execute",
"parameters": {
"command": ["pkill", "-SIGHUP", "-f", "google-chrome"]
}
},
{
"type": "sleep",
"parameters": {