lzy/sci-gui-agent-benchmark
1
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

3
evaluation_examples/examples/gimp/045bf3ff-9077-4b86-b483-a1040a949cff.json
View File

@@ -31,5 +31,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/06ca5602-62ca-47f6-ad4f-da151cde54cc.json
View File

@@ -91,5 +91,6 @@
"path": "/home/user/Desktop/palette_computer.png",
"dest": "palette_computer.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/2a729ded-3296-423d-aec4-7dd55ed5fbb3.json
View File

@@ -95,5 +95,6 @@
"path": "/home/user/Desktop/dog_without_background.png",
"dest": "dog_without_background.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/2e6f678f-472d-4c55-99cc-8e7c5c402a71.json
View File

@@ -38,5 +38,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/38f48d40-764e-4e77-a7cf-51dfce880291.json
View File

@@ -22,5 +22,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/554785e9-4523-4e7a-b8e1-8016f565f56a.json
View File

@@ -91,5 +91,6 @@
"path": "/home/user/Desktop/edited_colorful.png",
"dest": "edited_colorful.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/58d3eeeb-e9d0-499f-962e-fd0db2a744d8.json
View File

@@ -31,5 +31,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

8
evaluation_examples/examples/gimp/5ca86c6f-f317-49d8-b6a7-b527541caae8.json
View File

@@ -3,13 +3,13 @@
"snapshot": "gimp",
"instruction": "Could you help me download the logo of the University of Hong Kong in \".png\" format within GIMP?",
"source": "",
"config": [
],
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"func": "infeasible"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/62f7fd55-0687-4a43-b6e1-3eda16fc6252.json
View File

@@ -22,5 +22,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/72f83cdc-bf76-4531-9a1b-eb893a13f8aa.json
View File

@@ -91,5 +91,6 @@
"path": "/home/user/Desktop/berry_mirror.png",
"dest": "berry_mirror.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/734d6579-c07d-47a8-9ae2-13339795476b.json
View File

@@ -95,5 +95,6 @@
"path": "/home/user/Desktop/green_background_with_object.png",
"dest": "green_background_with_object.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/7767eef2-56a3-4cea-8c9f-48c070c7d65b.json
View File

@@ -50,5 +50,6 @@
"file_name": "gimprc",
"dest": "gimprc"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/77b8ab4d-994f-43ac-8930-8ca087d7c4b4.json
View File

@@ -41,5 +41,6 @@
"path": "/home/user/Desktop/export.jpg",
"dest": "export.jpg"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/7a4deb26-d57d-4ea9-9a73-630f66a7b568.json
View File

@@ -91,5 +91,6 @@
"path": "/home/user/Desktop/edited_darker.png",
"dest": "edited_darker.png"
}
}
},
"proxy": false
}

103
evaluation_examples/examples/gimp/7b7617bd-57cc-468e-9c91-40c4ec2bcb3d.json
View File

@@ -1,54 +1,55 @@
{
"id": "7b7617bd-57cc-468e-9c91-40c4ec2bcb3d",
"snapshot": "gimp",
"instruction": "Set the minimum number of undo steps to 100.",
"source": "https://www.youtube.com/watch?v=G_PjQAy0iiU",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"gimp"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import pyautogui; pyautogui.hotkey([\"ctrl\", \"q\"]);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_config_status",
"expected": {
"type": "rule",
"rules": {
"type:": "key-value",
"key": "undo-levels",
"value": "100"
}
},
"result": {
"type": "gimp_config_file",
"file_name": "gimprc",
"dest": "gimprc"
}
"id": "7b7617bd-57cc-468e-9c91-40c4ec2bcb3d",
"snapshot": "gimp",
"instruction": "Set the minimum number of undo steps to 100.",
"source": "https://www.youtube.com/watch?v=G_PjQAy0iiU",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"gimp"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import pyautogui; pyautogui.hotkey([\"ctrl\", \"q\"]);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_config_status",
"expected": {
"type": "rule",
"rules": {
"type:": "key-value",
"key": "undo-levels",
"value": "100"
}
},
"result": {
"type": "gimp_config_file",
"file_name": "gimprc",
"dest": "gimprc"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/8ea73f6f-9689-42ad-8c60-195bbf06a7ba.json
View File

@@ -31,5 +31,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/a746add2-cab0-4740-ac36-c3769d9bfb46.json
View File

@@ -65,5 +65,6 @@
"file_name": "action-history",
"dest": "action-history"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/b148e375-fe0b-4bec-90e7-38632b0d73c2.json
View File

@@ -62,5 +62,6 @@
"file_name": "gimprc",
"dest": "gimprc"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/d16c99dc-2a1e-46f2-b350-d97c86c85c15.json
View File

@@ -113,5 +113,6 @@
"dest": "resized.png"
}
]
}
},
"proxy": false
}

103
evaluation_examples/examples/gimp/d52d6308-ec58-42b7-a2c9-de80e4837b2b.json
View File

@@ -1,54 +1,55 @@
{
"id": "d52d6308-ec58-42b7-a2c9-de80e4837b2b",
"snapshot": "gimp",
"instruction": "Could you help me remove the dock on the left side of the screen?",
"source": "https://superuser.com/questions/1447106/how-to-get-rid-of-the-gimp-tool-options-box",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"gimp"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import pyautogui; pyautogui.hotkey([\"ctrl\", \"q\"]);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_config_status",
"expected": {
"type": "rule",
"rules": {
"type:": "key-value",
"key": "hide-docks",
"value": "yes"
}
},
"result": {
"type": "gimp_config_file",
"file_name": "sessionrc",
"dest": "sessionrc"
}
"id": "d52d6308-ec58-42b7-a2c9-de80e4837b2b",
"snapshot": "gimp",
"instruction": "Could you help me remove the dock on the left side of the screen?",
"source": "https://superuser.com/questions/1447106/how-to-get-rid-of-the-gimp-tool-options-box",
"config": [
{
"type": "launch",
"parameters": {
"command": [
"gimp"
]
}
}
],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"postconfig": [
{
"type": "execute",
"parameters": {
"command": [
"python3",
"-c",
"import pyautogui; pyautogui.hotkey([\"ctrl\", \"q\"]);"
]
}
},
{
"type": "sleep",
"parameters": {
"seconds": 0.5
}
}
],
"func": "check_config_status",
"expected": {
"type": "rule",
"rules": {
"type:": "key-value",
"key": "hide-docks",
"value": "yes"
}
},
"result": {
"type": "gimp_config_file",
"file_name": "sessionrc",
"dest": "sessionrc"
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/dbbf4b99-2253-4b10-9274-45f246af2466.json
View File

@@ -31,5 +31,6 @@
],
"evaluator": {
"func": "infeasible"
}
},
"proxy": false
}

8
evaluation_examples/examples/gimp/e19bd559-633b-4b02-940f-d946248f088e.json
View File

@@ -3,13 +3,13 @@
"snapshot": "gimp",
"instruction": "Could you tone down the brightness of my photo at desktop?",
"source": "https://www.quora.com/How-do-I-edit-a-photo-in-GIMP",
"config": [
],
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"func": "infeasible"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/e2dd0213-26db-4349-abe5-d5667bfd725c.json
View File

@@ -86,5 +86,6 @@
"path": "/home/user/Desktop/leftside_textbox.png",
"dest": "leftside_textbox.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/f4aec372-4fb0-4df5-a52b-79e0e2a5d6ce.json
View File

@@ -90,5 +90,6 @@
"path": "/home/user/Desktop/Triangle_In_The_Middle.png",
"dest": "Triangle_In_The_Middle.png"
}
}
},
"proxy": false
}

3
evaluation_examples/examples/gimp/f723c744-e62c-4ae6-98d1-750d3cd7d79d.json
View File

@@ -91,5 +91,6 @@
"path": "/home/user/Desktop/berries_contrast.png",
"dest": "berries_contrast.png"
}
}
},
"proxy": false
}

8
evaluation_examples/examples/gimp/fbb548ca-c2a6-4601-9204-e39a2efc507b.json
View File

@@ -3,13 +3,13 @@
"snapshot": "gimp",
"instruction": "Blue is my favorite color, so could you help me change the color theme of GIMP to \"Blue\"?",
"source": "",
"config": [
],
"config": [],
"trajectory": "trajectories/",
"related_apps": [
"gimp"
],
"evaluator": {
"func": "infeasible"
}
}
},
"proxy": false
}