Plugins

Checks installed DSH plugins and previews upgrade risks, with source locations, dependency views, review records and evidence limits. Includes a panel and agent tool.

DSH Desktop 可见协作/批注层：在内建右侧 Browser 中把 Agent 的观察、操作、批注与审批可视化；不是官方 Browser Use Provider 的替代。

Mechanism-enforced discipline layer for DeepSeek Harness agent teams: role cards, quorum termination, evidence-gated reports and cost budgets.

Superpowers (obra/superpowers v6.4.2) for DeepSeek Harness: the full skill library, the session-start bootstrap, and an optional workflow gate.

The 7-7-7 execution loop for DeepSeek Harness — plan, run, capture, close, compound, with a human gate.

给小鲸鱼一双手：零依赖 CDP 直驱一个专用 Chromium，让 agent 像人一样读网页、点按钮、填表单、滚动、截图；每次操作先经用户授权，密码由用户自己输入。

Arabic-first actionable Windows notifications for DeepSeek Harness (dsh): toast buttons that continue, stop, or open the app — and approve or reject the agent's permission requests — without leaving your seat. Bilingual ar/en with RTL.

DeepSeek Harness plugin: secondary working directories for a project. The agent keeps the primary workspace as cwd, gains equal write/exec permissions on configured secondary directories under workspace-write mode, and is notified of configuration changes

DeepSeek Harness plugin: saved shortcuts (name + target agent + text) with a workspace/session/agent tree picker, a sidebar menu that delivers a shortcut's text to its target without switching sessions, and per-message capture from user bubbles

Session Fleet: model-facing tools that let one DeepSeek Harness agent discover, read, create, and message other DSH sessions.

火山方舟 Agent Plan 与 Coding Plan：OAuth 登录、账号、模型与额度管理。

Connect DeepSeek Harness to shared AgentsChat rooms over MCP and WebSocket wake bridge for cross-agent messaging, peer code review, proposals, voting, and OKRs.

Hands secrets and PII to the agent without them entering its context, with checksum-validated extraction and masked content classification.

In-app server monitor window for DSH that tunnels to a lightweight agent on your server: memory, swap, load, disk, per-container usage and QQ status, cache purge and container restarts, plus an embedded VNC desktop for manual QQ QR login and sign-out. The agent ships in the repository (server/monitor.py) and you deploy it yourself.

Phone push for DeepSeek Harness: hooks the question seam in-process so a pending question reaches your phone through an ntfy relay; an answer sent from the phone is fed back to the agent as a user message, which requires `tool-ask-user` to run in `mode: timed` — with the shipped default (`mode: legacy`) only the notification is delivered.

Sidebar todo list for DeepSeek Harness — grouped buckets, recurring tasks with weekday or month-day rules, a month-view calendar, and an agent tool that reads and writes the same JSON file.

Dictation that ends up in the repository instead of the chat log: hold the button (or import a WAV), and the plugin archives voice-memos/<id>/ with audio.wav, a rendered waveform.png, memo.md (frontmatter, per-segment timestamps, ready-to-paste quote blocks) and meta.json. Audio is resampled to 16 kHz mono in the browser before it is sent. Transcription stays local — the harness speechToText service with silence-split windows, or a command worker such as faster-whisper — and when no engine is available the memo is still filed with an explicit status and reason rather than a fabricated transcript. Ships a conversation-view 口述 tab with click-to-seek playback and per-segment quote copy, three agent tools (voice_memo_save / voice_memo_list / voice_memo_read) and HTTP routes. Zero runtime dependencies, 52 node:test cases, real screenshots in docs/.

Windows desktop control for DeepSeek Harness agents: window and UI Automation automation, local Windows OCR, direct browser reads over the Chrome DevTools Protocol (DOM text, JavaScript, selector clicks), humanised mouse and keyboard input, browser tab management, and a live control panel. It probes the machine on first run, writes its own config, and degrades gracefully when a capability is missing. Windows 10/11 only.

Version-adaptive tooling for DeepSeek Harness: it reads the running DSH version from the plugin manager, mirrors app-boot plugin-compatibility rules (engines.dsh first, then @deepseek-ai/dsh* peers, prerelease-inclusive comparison, exact-version exemptions) to score every installed plugin, and statically flags source still using APIs renamed or deprecated between v0.1.6 and v0.2.1. Ships a conversation-view panel, an agent tool and HTTP state/scan/report routes. Read-only, offline.

Restart initiated by the agent itself, not by a button. The agent calls one tool, then the plugin takes over: it waits until every agent and background job on the host is idle, runs a visible ten-second countdown that a click, a scroll, or a key press cancels, then restarts DSH and wakes the original session so the agent carries on from its last sentence. No button, no manual entry: the tool is the only way in. Works on the official desktop app and the official web client; third-party shells are not supported out of the box. Windows only. One thing to know: every launch of the DSH desktop app writes a fresh identity cookie into its own profile and never prunes the old ones, so after enough launches the cookie header outgrows the request limit and the next start dies with HTTP 431 and `Error: desktop welcome: Web authentication failed`, with no window at all. Restarting by hand runs into this too; this plugin simply restarts far more often, so it brings that day closer.

Adds a Delete action to archived Session rows that permanently removes the Session log directory, the log directories of its subagent Sessions, its Workspace membership and archive mark, its projection-cache record and its spill directory; a Session the Host still holds is staged and finished at the next start or from a cleanup dialog. It also sweeps abandoned blank placeholders, leftover subagent Sessions and orphaned projection-cache records, and keeps blank placeholders out of the @ reference list.

Per-call token meter for the DSH composer: a colour-coded pill under the input and a dashboard above it showing every model call (total versus billable input+output), sub-agent spend, tool overhead and cache-versus-fresh input, read only from local session logs.

Puts a WuwaTappo desktop pet's bubbles to work: shows the DeepSeek balance, today's spend and a per-turn cost bubble, and keeps an amber reminder bubble up while the agent waits for an answer or an approval. Talks to the pet over CDP, enabling its debug port with a one-time, revertible byte patch.

Pins an always-on-top progress bar while the agent runs a turn — the percentage is estimated from tool calls and filled to 100% when the turn ends — and badges the DeepSeek peak/off-peak pricing window so large token operations ask for confirmation only during peak hours. The bar runs as a separate Electron process and is skipped when no Electron binary is found.