Plugins

ChatGPT-style composer predictions for DeepSeek Harness: after each assistant turn, suggest the user's next message as ghost text in the composer. Tab accepts, Escape dismisses.

Agent persona: gives DSH one global persona (name, language, persona prompt) that every new session carries at the front of its system prompt, plus a long-term memory you grow from any chat in one click; three built-in presets ship with it, and a Big fat fish persona is active right after install; chat sessions can also be deleted from the sidebar row menu.

Agent Memory plugin for DeepSeek Harness: local, file-per-memory long-term memory with human approval.

A separate narrow-screen web surface for DeepSeek Harness rather than the desktop GUI scaled down: it serves its own session list and chat stream behind a random access token over LAN, a tunnel (cloudflared, localtunnel or localhost.run) or an SSH reverse forward through a server you own. On the phone it streams assistant text, thinking, tool calls and results, sends prompts, stops the running turn, answers blocking questions and tool approvals (including ones waiting in other sessions), switches model, thinking level and permission preset, sends up to four photos compressed on the device, and keeps the computer awake.

Mirrors assistant streaming frames (deltas, blocks, commits, turn fences) to a configurable NDJSON sink for external consumers.

Original CSS gold and purple glass theme with local avatar upload, crop controls, assistant naming and reading styles; no bundled game media.

Token usage dashboard for the whole harness: billed tokens from every session are rolled up per session and turn (uncached input, cache read, cache write and output) with a peak/off-peak CNY cost estimate, and a "Token 用量" entry above Settings in the sidebar opens the dashboard at /token-stats, in a new tab on the web and in an in-app popup on the Desktop. The page recollects and repaints every 60 seconds while the tab is visible. Usage is read from the same session event stream dsh-token-meter consumes, accepting 0.1.x assistant/chunk and 0.2.x assistant/message and assistant/attempt, and counting an attempt repeated after an llm retry as its own billed call; cold history is seeded once from a persisted rollup file and afterwards only logs whose mtime or size changed are re-parsed. Host half and client half ship in the one package.

A right-sidebar assistant that knows the main session's finished turns, follows the main agent's running steps and background jobs, and answers in the panel; its model, context budget and answer style are configurable.

Keeps quotes out of the message body: quoting any passage from an assistant turn opens an editable quote tray above the composer, the quotes are injected into the next turn as system-prompt context (attributed with source and time), and an expandable quote row under that turn shows exactly which quotes were used. Quotes persist across page reloads and are claimed per turn; the host and client halves hand-shake on version and report a compatibility verdict.

Pins a selected passage of a finished user or assistant message as source text and keeps it in the model input across context compaction: each pin is recall-on-demand by default, or can be moved to a neutral resident system-prompt section or an emphasised highlighted one. Selections are aligned back to the source text with source-exact, source-normalized or rendered fidelity, and each of the three levels has its own character budget.

Adds a configurable bubble behind assistant replies, with an optional liquid-glass material and matching chrome for process, tool-call and reasoning rows.

Input prediction: the likely continuation of your draft appears as grey ghost text after the caret and Tab accepts it, and after each assistant turn 1-3 clickable follow-up suggestions appear above the input box and send on click. Ghost completion, suggestions and the suggestion count can be toggled in Settings, Built-in plugins.

Shows what each assistant turn cost under every reply, priced from the token usage of that turn at the official peak and off-peak CNY rates, together with the account and bonus balances; when a turn cannot be priced it states the reason instead of guessing.

A secret store for DSH Desktop that keeps API keys in one place and injects them into the assistant's shell as $DSH_* variables.

Personal coding assistant that schedules, follows up on and verifies local Codex or Claude Code tasks from DSH, with WeChat, WeCom and Feishu remote channels.

Live2D session view with realtime voice: continuous voice input, streaming TTS, subtitle translation, multi-model catalog, standalone entry / Live2D 实时语音会话视图：连续语音输入、流式 TTS、字幕翻译、多模型目录、独立入口

Execution flow chart: renders the current session's execution as a vertical node flow (turns, user, assistant, tools, approvals, retries, compaction), appended in real time over SSE with auto-follow scrolling — the chart draws wherever the session executes.

Email notifications for DSH with an away-mode switch: mails you when a turn ends, a tool waits for approval, or the assistant asks a question. Title and body are editable templates.

Adds a speaker button immediately right of the Like button on every finalized assistant reply; click it to hear the reply through the browser speech engine, and hover it for a speed and voice panel. Text is sent to an unofficial Edge TTS endpoint.

Automatically highlights key points, definitions, warnings, and questions in completed assistant answers using one separate model call.

Local-first voice conversations for DSH, with local speech recognition and synthesis and optional external providers.

Personalization plugin for the DeepSeek Harness (dsh): teach your assistant who you are, who it is, and how it should behave. Adds a Personalization page to dsh settings (custom instructions, nicknames, persona) and injects the content into every agent tu

MiniMax 语音识别（asr-1.0）+ 语音合成（speech-2.8-hd）的 DeepSeek Harness 全局插件：转写工具、任务结束后用喇叭念一句的播报、实时免手对话、303 个音色可选

Persistent project intelligence and memory plugin for DSH: architecture analysis, cross-session context, TODOs, and optional hybrid retrieval