Plugins

Agent-agnostic skill that turns task input files into reusable structural briefs and a per-task searchable index (OpenAI Codex, Claude Code, DeepSeek Harness)

科研收敛驾驶舱 (developer preview): hard-gated research convergence loop for DSH agents - 7 conv_* tools + host session projection + turn-tail card (conversation.chat.turnTail) + cockpit strip (conversation.input.dock) + settings section. 零 npm 依赖 (node builtins

Neural Ledger · 神经账本 — turn your DSH collaboration sessions into a visual work ledger: token analytics, smart insights, trend forecasting, and one-click daily/weekly/monthly Markdown reports.

dsh（DeepSeek Harness）→ ZapMomo 桌宠任务事件桥：监听 agent/status 与 turn/end，把任务开始/完成/失败/中断推给 ZapMomo 的 loopback 桥，桌宠以气泡 + 语音播报。

Turns code review into a hard gate: deterministic severity rules, LLM-assisted findings, a team approval quorum and a durable compliance audit trail that must pass before a merge proceeds.

Desktop notification plugin for the DeepSeek Harness (dsh): shows a native OS toast when the agent finishes a conversation turn. Zero runtime dependencies; works on Windows (native WinRT toast), macOS (osascript) and Linux (notify-send).

A pouch of practical micro-plugins for DSH: per-turn wall-clock time injection, safe restart, session ID header badge, Tavily search provider, configurable LLM request-header routes, and an MCP server console managing the official @deepseek-ai/dsh-mcp-client at runtime — add/edit/enable/disable/reconnect, per-tool switches, live status over SSE, mcpServers JSON import, and auto-migration of profile-YAML MCP entries.

Antigravity-style run_command for DSH: short commands return inline within a configurable wait window (default 10s) while longer ones auto-promote into ctx.jobs for later collection and completion notices — executed via ctx.shell under the session sandbox and approval pipeline.

Turns each produced-file chip into a per-file menu: open the file, copy its path, reveal it in the native file browser, or open a terminal cd-ed into its directory.

Un-clamps the composer stats footer: long turn and token stats lines span the full composer width instead of truncating with an ellipsis.

Feishu/Lark channel that drives DeepSeek Harness agents from chats: streaming rich cards with live thinking and tool steps, per-turn cost metering at DeepSeek peak/off-peak rates, one-tap approval cards, model-gated image intake, and QR onboarding without a public endpoint.

Displays and copies absolute paths for files produced by DSH turns in remote Web.

Conversation-map rail down the left edge of the transcript: one tick per user turn, read from the full session log on the host rather than from the rendered page, so long sessions are covered end to end. Hovering fans the neighbouring ticks open by pixel distance and floats a scrollable preview of that turn prompt and its last reply; clicking scrolls to the turn, paging older history in first when it has not been rendered yet; the tick for the visible turn stays highlighted while you scroll.

Codex-style message timeline navigation for DSH web clients: hover to preview a message, click to jump to it, and the currently-read turn stays highlighted.

Adds a Settings card that pops a system notification and optional chime when a conversation turn completes.

像 Claude Code 一样，DeepSeek Harness 现在也允许您自定义等待 AI 回复时的状态提示语。您可以根据不同轮次或场景，灵活替换占位文案，让开发助手在“思考”时也能传递您想要的信息。

DeepSeek Harness (dsh) plugin: turn one idea into a narrated video cut from your own asset folder, stopping four times to ask you first.

Adds read-only, scriptable playback to native DSH conversations, with simulated user typing, forward and reverse playback, event stepping, speed control, idle-gap compression, and direct seeking by event, turn, or recorded time.

DeepSeek-Harness (dsh) plugin that streams sessions, turns, and tool activity to a JARVIS Mission Control board

Persistent memory for DeepSeek Harness: memory read/write/retrieve tools, per-turn auto-recording, project-scoped recall injection and a management UI, with non-destructive Claude Code memory import.

Langfuse observability for DeepSeek Harness (DSH): per-turn trace trees aggregated by session id, with prompt versioning and evaluation.

Replay real DeepSeek Harness turns against Standard, Minimal, Anchored, or plugin candidates with frozen request-surface evidence

Human-in-the-loop tools (`human_task` / `human_task_ready_check`): pause the agent until the user performs a real-world action or returns an observation (GUI operation, game testing, visual verification, hardware checks), gated by session consent and an AFK presence check, returning a structured JSON result via a web task dialog.

Rotates the model status line through a 53-phrase English/Chinese deep-theme pool: a random pick at turn start, event-driven switching on new thinking segments or tool calls (3s throttle), and a click on the status line toggles the language.