Add Video Learning Agent for short video platforms
Features: - VideoLearningAgent for automated video watching on Douyin/Kuaishou/TikTok - Web dashboard UI for video learning sessions - Real-time progress tracking with screenshot capture - App detection using get_current_app() for accurate recording - Session management with pause/resume/stop controls Technical improvements: - Simplified video detection logic using direct app detection - Full base64 hash for sensitive screenshot change detection - Immediate stop when target video count is reached - Fixed circular import issues with ModelConfig Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>
This commit is contained in:
13
.env.example
13
.env.example
@@ -108,3 +108,16 @@ SCREENSHOT_THROTTLE_MS=500
|
||||
|
||||
# Maximum task history to keep / 保留的最大任务历史数
|
||||
MAX_TASK_HISTORY=100
|
||||
|
||||
# ============================================================================
|
||||
# Video Learning Configuration / 视频学习配置
|
||||
# ============================================================================
|
||||
|
||||
# Output directory for video learning data / 视频学习数据输出目录
|
||||
VIDEO_LEARNING_OUTPUT_DIR=./video_learning_data
|
||||
|
||||
# Model parameters for video learning / 视频学习模型参数
|
||||
PHONE_AGENT_MAX_TOKENS=3000
|
||||
PHONE_AGENT_TEMPERATURE=0.0
|
||||
PHONE_AGENT_TOP_P=0.85
|
||||
PHONE_AGENT_FREQUENCY_PENALTY=0.2
|
||||
|
||||
Reference in New Issue
Block a user