@CAI-MH

AI response quality review for DeepSeek Harness: audits each finished assistant turn with an independent reviewer model and steers the agent to fix unreasonable output (up to 2 review rounds).

Force the DeepSeek Harness model to reply in a chosen language (default Simplified Chinese), switchable anytime via tools. 强制大模型使用指定语言回复。

Poll Feishu (Lark) chats, extract candidate tasks, two-way sync with the task-board plugin, with a floating browser panel — DeepSeek Harness bundle. 轮询飞书会话提取任务。