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

fix chrome tasks

Browse Source
This commit is contained in:
yuanmengqi
2025-07-13 12:41:27 +00:00
parent 572a94b6df
commit 7279469d23
3 changed files with 6 additions and 8 deletions
Download Patch File Download Diff File Expand all files Collapse all files

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

@@ -1,7 +1,7 @@
{ {
"id": "b4f95342-463e-4179-8c3f-193cd7241fb2", "id": "b4f95342-463e-4179-8c3f-193cd7241fb2",
"snapshot": "chrome", "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", "source": "test_task_1",
"config": [ "config": [
{ {

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

@@ -1,7 +1,7 @@
{ {
"id": "fc6d8143-9452-4171-9459-7f515143419a", "id": "fc6d8143-9452-4171-9459-7f515143419a",
"snapshot": "chrome", "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", "source": "test_task_0",
"config": [ "config": [
{ {
@@ -65,12 +65,12 @@
"from": "tomorrow" "from": "tomorrow"
}, },
"expected": { "expected": {
"start": "NYC", "start": "JFK",
"end": "CMH", "end": "ORD",
"time": "{DoW}, {Month} {Day0D}, {Year}" "time": "{DoW}, {Month} {Day0D}, {Year}"
} }
} }
} }
}, },
"proxy": true "proxy": false
} }

4
manual_examine.py
View File

@@ -275,9 +275,7 @@ def main():
os_type="Ubuntu", os_type="Ubuntu",
require_a11y_tree=args.observation_type in ["a11y_tree", "screenshot_a11y_tree", "som"], require_a11y_tree=args.observation_type in ["a11y_tree", "screenshot_a11y_tree", "som"],
enable_proxy=True, enable_proxy=True,
client_password=args.client_password, client_password=args.client_password
screen_width=args.screen_width,
screen_height=args.screen_height
) )
# 执行手动检查 # 执行手动检查