Plugins

DeepSeek Harness plugin: a Task Instructions button beside the input box pins reusable task requirements to a session, and the instruction survives context compression.

Sidebar DeepSeek peak/off-peak pricing hint with a Beijing-time countdown, Chinese public holidays and make-up workdays, daily pricing-rule refresh, official top-up offer status, and your account balance converted to input tokens (read with the DeepSeek platform sign-in already stored in DSH).

Imports DeepSeek usage exports (ZIP, CSV, JSON) locally and renders token and cost trends, per-model and per-API-key breakdowns, cache savings, input/output composition and usage spikes. The interface is Chinese only.

Select text in a conversation and park it as a quote card above the composer; the input box keeps only your question, and the quoted text rides along with the message you send. Package name: dsh-quote-tray.

Super input suite — model and effort picker, prompt enhancer, follow-up suggestion chips, a full cost engine with daily heatmap and Coding Plan quotas, voice-input light effects and transcript cleanup (needs the built-in voice-input bundle enabled), prompt templates, selection reference chips with comments, a compaction ring and a settings hub. Bundles the author's standalone dsh-cost, dsh-power-picker, dsh-prompt-enhancer, dsh-followup, dsh-siri-voice and dsh-compaction-control; uninstall those before installing.

A reading layer for long DeepSeek Harness sessions. A fixed enlarge button on every answer opens a two-pane view with 80-300% type, an outline of every turn in the session (turns not yet loaded are fetched on demand), and a composer that fills the real DSH input without sending. Formulas, tables and code stay exactly as rendered; over-wide formulas shrink to fit, failed ones degrade quietly, and turns whose answer was cut off are labelled as truncated.

macOS companion window for DSH Desktop: todos, reminders, live session messages, approval handling and quick input. The first open downloads Electron 43.3.0 to ~/.dsh/electron; after installing or updating, press ⌘Q (Command + Q) to quit DSH completely and reopen. macOS only. Tested on DSH 0.2.2-rc.1 and macOS 27 arm64.

任务通知台：任务完成或中断时响提示音并弹系统/浏览器通知，侧边栏「任务」面板可筛选待回复、进行中与未读结果（含退出、欠费中断）。Task-completion chime + system/browser notifications, plus a Tasks sidebar panel that surfaces sessions waiting on your input, running, and unread results, including interruptions.

Voice dictation scratchpad: realtime speech-to-text into timestamped, per-session blocks, with one-click insert into the conversation composer. Requires the official DSH voice-input bundle (@deepseek-ai/dsh-experimental-voice-input-bundle); the speech model downloads on first use.

Before closing a coding session or the DSH app itself, checks what would be lost — uncommitted work, unpushed commits, scratch files, missing handoff notes, pending restarts, broken profile bundles — and prints a three-level verdict; when a handoff is needed it writes the seven-section handoff file into the workspace ledger. Read-only by default.

Lands the chat viewport on your most recent own message when you open a finished session, instead of the bottom of the conversation; running sessions still follow the bottom. Client-only: it reads the viewport and never touches files, credentials, subprocesses, or the network.

Turns the chat composer into an auto-playing mini-game arcade while a task runs — snake, pong, flappy, ecology, horse race, runner, number rush and maze all play themselves with no input; focusing the composer restores the normal editor.

Native desktop notifications for DSH on Windows, macOS and Linux. While the DSH window is in the background, permission requests arrive as system notifications; where the platform supports notification actions, Reject and Allow-once buttons return the decision to the host approval waterfall, and returning focus or a timeout hands the request back to the in-app panel. Approvals and questions also play a separate input cue that is independent of window focus. Turn-end, question and error reminders, notification sounds and the cue are configured on a Notifications settings page.

Reports DSH session token usage from the local session logs as a host-side tool: totals, input, output and cache-read split, a per-day timeline, usage grouped by day or session and optional cost estimates.

Opens STEP/STP/STL/GLB/GLTF models in a sidebar 3D viewer: STEP is tessellated in the browser with OpenCASCADE WASM; the toolbar offers fit/front/top/side/iso orthographic views and a PNG screenshot; inputs are capped at 64 MiB and .gltf files that reference external buffers or textures are rejected.

A named-agent-team chat workbench for DSH: per-member model routes with fallback and 3D mascot avatars; private and group chats with mention relay and bounded parallel lanes; a whole department as one agent whose lead dispatches sub-agents that run in parallel on their own models before the lead synthesizes; record search with hit highlighting and today/yesterday/earlier buckets; a four-layer memory system (raw chats → atomic facts → scene summary → user persona) recalled by hybrid BM25 + embedding RRF; plus an avatar library and local/cloud speech input. Hybrid recall needs an embedding endpoint (default: local Ollama qwen3-embedding:0.6b; otherwise BM25 only); speech input needs a local jianchang512/stt service or a cloud ASR key, otherwise it falls back to the browser speech API.

Composer tweaks for the DSH input box: a Markdown source/view toggle, Markdown rendering for user messages, one mixed file-and-folder picker backed by the macOS open panel, a GenUI prompt switch inside the plus menu, an open-in-new-window action on sidebar Session rows (needs the separate `dsh-popout-window` host plugin), and a collapsible subagent tree. Requires DSH 0.2.x.

Windows companion window for DSH Desktop: todos, reminders, live session messages, approval handling and quick input. The standalone window reuses the Electron binary at %USERPROFILE%\.dsh\electron\electron.exe (usually installed by dsh-pet) and fails to open when it is missing.

A Feishu/Lark channel for DeepSeek Harness: WebSocket inbound messaging, Markdown tables rendered as native Feishu table components, 13 Feishu tools, a web settings page, voice input/output, media upload and a model fallback chain.

Screen frames, log lines and (on Windows) key/mouse input on one millisecond timeline: record, mark the failing seconds, box the problem on the frame, then hand the agent a keyframe strip, an animated GIF and the aligned log slice.

Hold Space to record and release to transcribe and send, without focusing the composer first. Esc cancels and window blur auto-cancels. Requires the official voice-input bundle (`@deepseek-ai/dsh-experimental-voice-input-bundle`) enabled with its speech model downloaded; otherwise Space is left alone.

Image understanding for DSH: describe an image and read the text in it through Zhipu GLM-4V (needs a Zhipu API key, free tier), with optional person identification through Volcengine Ark and anime-only reverse image search through SauceNAO or trace.moe (each needs its own key); ffmpeg must be installed for GIF/WebP input. Keys and the ffmpeg path are set on the plugin's own settings page.

Local video understanding for agents: extracts keyframes adaptively based on motion and pauses, inspects any timestamp at full resolution, and aligns visuals with dialogue from embedded subtitles or configured ASR. Requires ffmpeg and ffprobe; clips without subtitles also need a transcription engine for dialogue (a ~190 MB local whisper model, a cloud API key, or the official voice-input model).

macOS computer use with eight computer_* tools: accessibility-tree and Vision OCR screen reading, actions by element index or visible label that also reach background windows, and CoreGraphics mouse and keyboard events with a resident low-latency daemon for game-grade input sequences; its Swift helpers compile on first use, so there is no runtime dependency.