2c51950e73
- 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.
84 lines
1.7 KiB
JSON
84 lines
1.7 KiB
JSON
{
|
|
"id": "7a5a7856-f1b6-42a4-ade9-1ca81ca0f263",
|
|
"snapshot": "chrome",
|
|
"instruction": "Can you save this webpage I'm looking at to bookmarks bar so I can come back to it later?",
|
|
"source": "https://www.youtube.com/watch?v=ZaZ8GcTxjXA",
|
|
"config": [
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"google-chrome",
|
|
"--remote-debugging-port=1337"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "launch",
|
|
"parameters": {
|
|
"command": [
|
|
"socat",
|
|
"tcp-listen:9222,fork",
|
|
"tcp:localhost:1337"
|
|
]
|
|
}
|
|
},
|
|
{
|
|
"type": "chrome_open_tabs",
|
|
"parameters": {
|
|
"urls_to_open": [
|
|
"https://blog.eleuther.ai/rotary-embeddings/",
|
|
"https://jalammar.github.io/illustrated-transformer/"
|
|
]
|
|
}
|
|
}
|
|
],
|
|
"trajectory": "trajectories/",
|
|
"related_apps": [
|
|
"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"
|
|
},
|
|
"expected": {
|
|
"type": "rule",
|
|
"rules": {
|
|
"type": "bookmark_bar_websites_urls",
|
|
"urls": [
|
|
"https://jalammar.github.io/illustrated-transformer/"
|
|
]
|
|
}
|
|
}
|
|
},
|
|
"proxy": true,
|
|
"fixed_ip": false,
|
|
"possibility_of_env_change": "low"
|
|
} |