373 results
Restart recovery for dsh web: after a crash/restart, an interrupted agent turn continues automatically (host-side agent/created listener — no browser timing races). Pairs with the dsh-web-guard skill (which auto-relaunches the web process); together they
DeepSeek Harness plugin: Nocturne Memory client — automated long-term memory (boot/read/search/create/update) backed by your own Nocturne MCP server.
Turn a structured outline into a presentation for DeepSeek Harness (dsh): a self-contained HTML deck that presents offline with speaker notes and prints to PDF, plus optional editable .pptx export. Five committed themes.
Animate any photo into a responsive virtual girl. She talks, turns, smiles, and moves naturally in sync with your conversation. Low-lag, high-detail.
Conversation lineage for DeepSeek Harness: fork at a completed turn and show the family tree. Does not rewind files or merge logs.
Native DeepSeek Harness plugin: a turn that states a verdict without evidence does not end — it is steered back for proof.
Turn any composed dsh plugin on or off from the web UI. Switches take effect live and survive a restart, because they are written as `disabled:` rows into the profile's own cordis.patch.yml.
DeepSeek Harness (DSH) 插件：可逆时间旅行与审计。为工具副作用建立「前状态快照 → 执行 → 补偿」链路，提供 rewindTo(turnId) 按轮次倒序恢复工作区，内置审计规则引擎。
dsh-voice — turn-based voice loop for DeepSeek Harness: pluggable Qwen / MiMo / local ASR+TTS engines, agent-driven speak/listen tools and browser PTT UI, built for interviewer presets
会话地图 for DeepSeek Harness — turn the conversation waterfall into a navigable map: one complete turn per card, branchable DAG, live growth, docked turn inspector. Pure map, no context-graph extras.
Data → interactive chart lab for DeepSeek Harness: turn local CSV, Excel, or DuckDB data into zoomable, filterable, groupable interactive charts.
DeepSeek Harness plugin: connect a Telegram bot to your dsh agent via long polling. One agent per chat, multi-turn context, whitelist access, and agent-preset mounting so the bot gets the same tools as a Web GUI session.
Collapses each settled turn's process rows into one disclosure in the DeepSeek Harness Web conversation
Code collector for DeepSeek Harness: a composer-side panel that gathers every code block the model produced in the current session, with by-language / by-file views, version history, live search, one-click copy, download-all, and click-to-jump back to the exact turn.
DSH 断点续接插件：模型回复因网络中断/超时半途失败时，自动把已生成的部分输出带进下一轮，让模型从中断处继续，而不是从零全量重跑。DSH plugin: on a mid-stream network failure, auto-resume the turn from its partial output instead of restarting from scratch.
DSH web plugin: play a chime when a turn completes or your input (approval / question / plan review) is needed — foreground or background.
DeepSeek Harness plugin: turn lines of narration into a finished vertical reel. Free neural voice-over, burned-in captions, no API keys.
Model Capability Facade for DSH: a plugin author declares one semantic capability (a few model-facing operations), the facade turns them into typed tools that run a declared pipeline of existing tools through the normal tool pipeline.
mycel working modes: a switch_mode tool returning one selected mindset as an ordinary tool result, plus a shared core-behavior system-prompt section
DSH 思考增强插件（EAC 定制版）：思考与回复强制中文（system-prompt 注入）+ 界面硬编码英文中文化。已移除全部接管对话渲染器的显示功能，不再与折叠类插件（dsh-auto-collapse / dsh-turn-fold）抢占 assistant-step 座位。DSH web plugin (EAC fork): force Chinese agent thinking/replies + localize hard-coded UI labels, with all renderer-hijacking display features removed.
DeepSeek Harness web plugin: when a task (conversation turn) completes, open the Genshin Impact official site matching the computer's Windows display language. · DSH Web 插件：任务完成后按电脑显示语言跳转对应语言的《原神》官方站点。
Mechanically stops unfounded "done" claims from coding agents — a zero-LLM, pure-regex turn-boundary hook that demands verification evidence before sign-off.
Limit concurrent DeepSeek Harness subagent turns and delegation runs
DSH Web plugin: play a chime when the agent finishes a turn, with a settings page to enable it, pick the volume and upload your own audio file. Host-stored configuration, no core changes.