DeepSeek Harness gate - per-turn persistent-operation counter: remind, instruct the model to stop, then ask for confirmation. Steps aside under sandbox/read-only modes; follows a live permission switch without restart. Verified on real hardware (full -> workspace-write -> read-only -> full). Crafted on an estimated 0.27 USD of model spend.
The Feishu UI for DeepSeek Harness — a panel-driven control console: every slash command a button on the ⚙️ control-panel card, in-card approvals & questions, live streaming cards, one-QR setup. | DeepSeek Harness 的飞书 UI:面板驱动控制台——每个命令都是卡片按钮,卡内审批与提问,流式卡片,扫码一键配置。
Keep DSH plugins working across host upgrades: reads official upgrade guides directly, scans plugin code for breaking changes, smoke-tests in memory, scaffolds five plugin forms. Agent-native skill, zero dependencies
A prompt-enhancement plugin for DeepSeek Harness: an ✨ Enhance composer button that rewrites prompts with first-principles thinking using session context, and asks clarifying questions when key info is missing.
Hold-to-talk voice input for the DeepSeek Harness web composer: hold the mouse on the input box, speak, release to insert the text into the draft. Local SenseVoice ASR via sherpa-onnx: no API key, offline, audio never leaves the machine. | DSH 长按说话语音输入插件:输入框上按住鼠标说话,浮层边说边出字,松手把文字写进输入框,上滑取消;识别在本机跑,免密钥、离线、音频不出本机。
Turn Sieve (回合筛) — DeepSeek Harness 插件:在对话里原位筛除低价值问答或单条消息,可随时撤销。Prune low-value parts of a DSH chat in place — whole turns, single messages or just your own prompt — and undo any time.
Detects verbatim reasoning loops in DSH LLM streams and cuts them early. Zero-dependency Cordis plugin with a fire journal and a reasoning_loop_log tool.