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

add new chrome examples and change port from 9222 to 1337

Browse Source
This commit is contained in:
Jason Lee
2024-02-22 16:31:25 +08:00
parent e31e1dacde
commit e2745d8b1b
8 changed files with 121 additions and 7 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
evaluation_examples/examples/chrome/030eeff7-b492-4218-b312-701ec99ee0cc.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=9222"
"--remote-debugging-port=1337"
]
}
},

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

@@ -23,7 +23,7 @@
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=9222"
"--remote-debugging-port=1337"
]
}
},

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

@@ -27,7 +27,7 @@
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=9222"
"--remote-debugging-port=1337"
]
}
},

2
evaluation_examples/examples/chrome/9656a811-9b5b-4ddf-99c7-5117bcef0626.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=9222"
"--remote-debugging-port=1337"
]
}
},

29
evaluation_examples/examples/chrome/99146c54-4f37-4ab8-9327-5f3291665e1e.json
View File

@@ -3,16 +3,41 @@
"snapshot": "chrome",
"instruction": "Please help me set Chrome to delete my browsing history automatically every time I close the browser.",
"source": "https://www.youtube.com/watch?v=v0kxqB7Xa6I",
"config": [],
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func": "",
"func": "exact_match",
"result": {
"type": "data_delete_automacally"
},
"expected": {
"type": "rule",
"rules": {
"expected": "Crashed"
}
}
}
}

45
evaluation_examples/examples/chrome/a96b564e-dbe9-42c3-9ccf-b4498073438a.json Normal file
View File

@@ -0,0 +1,45 @@
{
"id": "a96b564e-dbe9-42c3-9ccf-b4498073438a",
"snapshot": "chrome",
"instruction": "Find discussions of community and open one with most replies.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_active_tab",
"result": {
"type": "active_tab_info"
},
"expected":{
"type": "rule",
"rules":{
"type": "url",
"url": "https://discussions.flightaware.com/t/graphs-for-dump1090-my-version-with-install-script/46263"
}
}
}
}

2
evaluation_examples/examples/chrome/bb5e4c0d-f964-439c-97b6-bdb9747de3f4.json
View File

@@ -9,7 +9,7 @@
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=9222"
"--remote-debugging-port=1337"
]
}
},

44
evaluation_examples/examples/chrome/f3b19d1e-2d48-44e9-b4e1-defcae1a0197.json Normal file
View File

@@ -0,0 +1,44 @@
{
"id": "f3b19d1e-2d48-44e9-b4e1-defcae1a0197",
"snapshot": "chrome",
"instruction": "Find help page about buying tickets.",
"source": "test_task_0",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"google-chrome",
"--remote-debugging-port=1337"
]
}
},
{
"type": "launch",
"parameters": {
"command": [
"socat",
"tcp-listen:9222,fork",
"tcp:localhost:1337"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"chrome"
],
"evaluator": {
"func":"is_expected_url_pattern_match",
"result": {
"type": "active_tab_info"
},
"expected":{
"type": "rule",
"rules":{
"expected": "https://seatgeek\\.com/help/articles/\\d+-Buying-Tickets"
}
}
}
}