Xinyuan Wang
24fbad9015
Merge pull request #264 from yuanmengqi/main
...
Improve the parallel logic
2025-07-17 12:28:48 +08:00
yuanmengqi
fe40011b5d
Improve the parallel logic
2025-07-17 04:21:42 +00:00
yuanmengqi
6788c58aa3
Improve the parallel logic
2025-07-17 04:20:59 +00:00
yuanmengqi
bb8b0b2582
Improve the parallel logic
2025-07-17 04:19:44 +00:00
Zilong Zhou
dc164d5269
feat&fix: update configuration management to save model arguments and enhance UI display for model args ( #262 )
2025-07-16 21:46:35 +08:00
yuanmengqi
cb070307ee
merge code
2025-07-15 14:57:14 +00:00
yuanmengqi
90c4e894a4
Merge remote-tracking branch 'upstream/main' into fix_chrome
2025-07-14 07:14:19 +00:00
yuanmengqi
5d90faa548
run operagor
2025-07-14 07:13:17 +00:00
Zilong Zhou
74b7c189af
Feat/monitor ( #254 )
...
* feat: add claude support
* feat: add script for end-to-end evaluation with logging and task distribution
* feat&fix: add tool result handling and update model default in evaluation script
* chore: remove run_test_env.py script
* feat&fix: implement action parsing for tool calls and update default action space
* fix: update text formatting in action parsing and replace logger import
* feat&fix: implement action parsing for tool calls and add screen size handling
* feat: add setup instructions for Anthropic API integration
* feat: add notice about image size limitations for Anthropic API
* Delete test_env/logger.py
* Delete test_env/utils.py
* fix: update logger usage to use global logger and improve error handling
* feat&fix: add configuration management API endpoints and update UI for configuration selection
* feat&fix: update environment configuration, enhance task statistics, and improve UI responsiveness
* feat&fix: add configuration toggle button in UI and improve task loading performance
* feat&fix: add accuracy percentage display to score and style updates for UI
2025-07-14 13:43:41 +08:00
yuanmengqi
572a94b6df
Merge branch 'main' into fix_chrome
2025-07-13 10:16:08 +00:00
yuanmengqi
ea51f5264a
fix chrome
2025-06-30 08:07:24 +00:00
yuanmengqi
7315aec6e6
clean code
2025-06-10 04:06:54 +00:00
yuanmengqi
aee1207fff
fix error
2025-06-09 04:20:59 +00:00
yuanmengqi
d8872634ee
edit prompt
2025-06-08 03:59:31 +00:00
yuanmengqi
f48d80002f
Merge remote-tracking branch 'upstream/feat/aws-provider-support'
2025-06-07 13:22:53 +00:00
yuanmengqi
c57b1d4e7a
eval update
2025-06-07 13:19:22 +00:00
adlsdztony
7d25f902a4
refactor&fix: update README and main.py for improved configuration and task status handling
2025-06-06 12:55:13 +00:00
yuanmengqi
64177045b5
Merge remote-tracking branch 'upstream/feat/aws-provider-support'
2025-06-06 10:22:56 +00:00
yuanmengqi
4ea24ddfd3
add proxy
2025-06-06 09:41:22 +00:00
adlsdztony
2ad48f04d7
feat&fix: update environment configuration for Docker compatibility and enhance result path handling
2025-06-06 02:53:20 +00:00
yuanmengqi
a6300e05c9
Merge remote-tracking branch 'upstream/feat/aws-provider-support'
2025-06-05 13:31:42 +00:00
adlsdztony
6acb8a2d1f
feat&fix: implement task status caching for improved performance and add cache handling in brief status retrieval
2025-06-05 12:42:59 +00:00
adlsdztony
3b1540ed23
feat&fix: enhance task status handling and update logging configuration
2025-06-05 09:33:36 +00:00
adlsdztony
2bfb4af8b5
feat&fix: add score display banner and update task status with animation
2025-06-05 05:07:45 +00:00
adlsdztony
2d5cee3f5c
feat&fix: add brief task status retrieval and improve task status update mechanism
2025-06-05 03:41:43 +00:00
adlsdztony
80e4ec75de
fix&docs: update FLASK_DEBUG setting to false in .env and README
2025-06-04 19:58:47 +08:00
yuanmengqi
b211df3385
fix timeout
2025-06-04 10:23:45 +00:00
yuanmengqi
b87cbe69e5
add monitor
2025-06-02 13:34:20 +00:00
adlsdztony
e363da2fd7
docs: update README with important execution note & fix: fix auto-refresh logic
2025-06-02 21:11:38 +08:00
adlsdztony
2b36860a03
refactor&fix: remove unused no-transition styles and simplify refresh logic
2025-06-01 09:36:46 +00:00
adlsdztony
37505f4c3b
feat&fix: implement auto-refresh functionality and disable animation when refresh
2025-06-01 08:45:58 +00:00
adlsdztony
e48bd6b059
feat: add .env configuration file and update README with configuration details
2025-06-01 07:07:47 +00:00
adlsdztony
41e9e86379
fix: update task rendering to correctly display error count
2025-06-01 06:58:05 +00:00
adlsdztony
b5efb82172
feat&fix: add task recording endpoint, enhance video player support, and improve mobile responsiveness
2025-06-01 06:50:02 +00:00
adlsdztony
cb62b3c877
feat&fix: update paths in configuration, enhance error handling, and improve UI elements
2025-06-01 04:48:50 +00:00
adlsdztony
d1a001b2b7
fix&refactor: correct port mapping in docker-compose and set fixed port in main.py
2025-06-01 10:57:14 +08:00
adlsdztony
60a2b495b9
feat: add README for OSWorld Monitor with configuration and usage instructions
2025-06-01 10:48:14 +08:00
adlsdztony
53c4106c5b
feat: Implement task monitoring web application
2025-06-01 10:31:27 +08:00
