let5sne.win10 b97d3f3a9f Improve Video Learning Agent with action-based detection and analysis toggle ...

- Change video detection from screenshot hash to action-based (Swipe detection)
- Add enable_analysis toggle to disable VLM screenshot analysis
- Improve task prompt to prevent VLM from stopping prematurely
- Add debug logging for action detection troubleshooting
- Fix ModelResponse attribute error (content -> raw_content)

Co-Authored-By: Claude <noreply@anthropic.com>

2026-01-10 01:47:09 +08:00

..

actions

Merge pull request #143 from gekowa/ios-support-3

2025-12-19 18:15:50 +08:00

adb

解决issue154中的model_output有换行的问题以及多行文本输出。解决subprocessing编码问题

2025-12-15 18:10:46 +08:00

config

Merge pull request #143 from gekowa/ios-support-3

2025-12-19 18:15:50 +08:00

hdc

修复hdc的get_current_app函数

2025-12-22 10:29:57 +08:00

model

fix format

2025-12-14 14:03:41 +08:00

xctest

feat: Added iOS support

2025-12-12 17:58:20 +08:00

__init__.py

Add Video Learning Agent for short video platforms

2026-01-09 22:54:57 +08:00

agent_ios.py

Add Web Dashboard with multi-device control and callback hooks

2026-01-09 02:20:06 +08:00

agent.py

Add Web Dashboard with multi-device control and callback hooks

2026-01-09 02:20:06 +08:00

device_factory.py

fix format

2025-12-19 18:56:43 +08:00

video_learning.py

Improve Video Learning Agent with action-based detection and analysis toggle

2026-01-10 01:47:09 +08:00