Plugins

DSH Session Fork Tree Arrangement: forked sessions sit under their parent with an indent and a rounded connector, sessions that own forks carry a green "+" that collapses by default and expands level by level, and hovering a child highlights its ancestor chain.

Connect Huawei CodeArts and OfficeAce models to DeepSeek Harness: it reuses existing logins (a logged-in CodeArts desktop client or dsh-codearts; the OfficeAce desktop app running and logged in on Windows), shows each account's remaining credits, toggles models per platform, and shapes requests like the official clients.

Adds a browserless deepseek-web provider that drives chat.deepseek.com, with an account pool (rotation, cooldown, auto-failover), in-panel login (browser, or email + password with MFA) and token usage stats.

Automatically retries model failures (drops, timeouts, rate limits, 5xx) in-turn. Retry count, delays, backoff, fallback and more are configurable. Rate-limit backoff is capped and jittered, server retry hints are honored, and optional retry-until-success keeps going within a time ceiling. Every option is editable from the plugin config or the sidebar panel: retry count, initial and max delay, backoff factor and jitter, rate-limit delay window, retry-until-success ceiling, fallback trigger and switch cap, dead-route blacklist TTL, log file. When a route keeps failing it can switch to a pinned, allowlist-filtered, or catalog-picked alternate model route, with a 30-minute dead-route blacklist (auth failure, subscription expired, billing) and a stale-assembly guard that keeps retried requests on the switched route. Ships a right-sidebar panel with live retry state, route labels and incident counters, Chinese and English locale, and memory-only logging by default.

Saves tokens in DeepSeek Harness sessions by reading any file by line range or symbol mention instead of whole, and by bounding oversized tool results while keeping a recovery path. Pruning happens at the source, not after content reaches the context. Measured 43.9% fewer prompt tokens in a modelled 30-step session.

Sidebar badge and panel showing the balance, daily spend and remaining runway of a New API relay, with a top-up link.

Alibaba Cloud coupon balance, used amount and expiry in the sidebar footer, read through the read-only BSS OpenAPI.

Tokenrhythm billing center for DeepSeek Harness: account balance and expiring quota, model price cards, a 30-day usage heat calendar, connectivity checks and platform API-key management, with credentials kept on the local host. A single-channel fork of 162568316/dsh-tokenrhythm-bill; the package name, Cordis id and route prefix all differ, so the two can be installed side by side.

Token usage dashboard for DeepSeek Harness. A dedicated settings page shows cumulative input / output / cache-read / cache-write token totals, a green GitHub-style daily heatmap colored by usage, and a pie / bar chart toggle for per-model (provider/model) usage shares — all read from local session logs, no upstream API calls.

VS Code style 44px icon rails for the side panels DSH collapses: the left rail keeps the sidebar navigation and the bottom action rows, the right rail lists the sidebarRightTabs ledger so third-party tabs appear on their own, and the right panel is drag-resizable between 300px and 60% of the window. Two switches under Settings → Activity Bar, saved in this browser.

Lets the model turn an answer into a web page that lives right inside the chat. The show_page tool either fills one of 8 built-in templates (report, compare, checklist, dashboard, timeline, flashcards, quiz, flow), where the model writes only the content and the plugin does layout, interaction and saving, or saves a full page the model wrote itself (calculators, games, custom layouts). Hand-written pages get the same design as base styles inside a CSS @layer, so the page's own CSS still wins. The page appears under the reply at its content height, interactive and following DSH's light/dark theme. The page's localStorage is stored in DSH per page, so what users tick or type survives reopening and new versions, and the same page open in the chat and the right sidebar stays in sync. Each edit is saved as a new version you can flip back to. After saving, the page is checked in a hidden local Chrome or Edge (script errors, horizontal overflow, dark mode not applied) and problems go back to the model. The right sidebar shows the page full-size with versions, a gallery of all pages and export to PNG, PDF or HTML. Pages run in a sandboxed, separate-origin frame with a strict CSP: no access to DSH data and no fetch, XHR or WebSocket. Works on phones with dsh-mobile.

Rewrites the composer draft into a tighter prompt in one click and restores the exact original in another, running on Harness's own models by default or any OpenAI-compatible endpoint, with an editable polishing prompt.

Uncle Sam — answers through chat.deepseek.com in a real browser tab instead of the metered API. Switch between the API and the web account from the composer; web replies are signed so you always know which route answered.

KuroWhale is an unofficial dark-themed whale-girl desktop companion for Windows x64, inspired by the DeepSeek Harness icon, with nine animations that react to DSH Agent activity. Requires WebView2; the first launch downloads the official Neutralino 6.9.0 runtime and artwork over the network and verifies them by SHA-256.

Android device workbench inside DSH (30 tools): read the UI text tree with readable role names (Text/Btn/Input/List……), measure animation motion, tap/type/swipe by text, id, ref or candidate index, mirror the screen into the right sidebar, and circle an area to send it back. Screen reading stays model-free — a colour-grid sampler, region diffing and OCR over the live stream mean typical checks cost 100–200 ms (warm frame 37 ms, 1000x600 region 121 ms) instead of a vision call. Process lifetime is bounded: reloads and crashes reclaim stray ffmpeg/recorder children instead of leaking them, and failure receipts only mention a crash that actually happened during the step. Requires adb (Android platform-tools) and ffmpeg on the host; the device-side helpers are bundled, and the OCR fallback is macOS-only.

IDEA-style Git tool window for DSH: branch tree with ahead/behind badges, commit graph with text/branch/author/date/path filters, staged and unstaged changes with a commit box, commit details with per-file line diff, stash and worktree management, a git console log, and AI commit-message drafting. Fork of KannaKuron/dsh-ide-git (MIT), reworked to register native DSH entries instead of depending on dsh-better-sidebar and extended with worktree management, undo for branch, stash and discard actions, a git console log and AI commit-message drafting. Its plugin, route and sidebar-tab ids differ from the upstream, so both can be installed, but you get two Git tool windows.

Windows only: a night-and-moon themed floating button (a sleepy DeepSeek-chan whale mascot, awake/sleeping artwork) in the bottom-right corner arms the plugin — click it to power the machine off once every root Agent session has gone idle, and click it again to disarm. The button is draggable (position remembered in localStorage), automatically dodges other plugins' corner popups, and survives the frontend re-rendering it away. When the batch finishes a 60 s cancellable countdown starts (configurable 10–600 s) with the remaining seconds on the button and a matching banner: clicking Cancel runs shutdown /a and disarms the mode, and any new session starting during the countdown aborts it. A right-click menu on the button switches the shutdown condition between only-on-success and shutdown-regardless, persisted across restarts in $DSH_HOME/deepseek-chan-sleep-shutdown.json. Zero runtime dependencies.

A workbench with a native AI assistant, task and reply tracking, Linky development workflows, knowledge, web chats, and developer/data tools. Yunzhijia messaging needs its account and CLI; web chats require the desktop app.

Durable task-decomposition plans for DeepSeek Harness: the model submits a staged plan with acceptance criteria, every work item then runs on a real department subagent, and the progress panel draws done/running/blocked subtasks as a ring, a stacked bar and per-stage steps. Ships a public security self-assessment structured on ISO/IEC 15408:2026 (Common Criteria) — security target, vulnerability analysis, SBOM and a security policy — with an explicit "no certificate claimed" line, plus a published self-correction record of where v1.8.0 documentation overstated the code (fixed in 1.8.1). Every claim is checkable by the reader instead of taken on trust. One command to install, zero runtime dependencies.

Generates complete AI songs (vocals plus full arrangement) from a theme or from provided lyrics, and instrumental BGM, through a bundled xiapan-music skill and a xiapan_music DSH tool; also queries the Xiapan API balance. Uses a user-supplied Xiapan API key (BYOK), and saves the generated mp3 files on the DSH host.

Structure-level watermark removal for PDF and Word: finds full-page Form XObject overlays drawn on every page and text blocks matching a watermark vocabulary, lists them by confidence, then excises only the drawing operators or runs — the text layer, embedded images and their resolution are not re-rendered or altered.

Hands-free voice for DSH on Windows: local wake word, local Chinese speech-to-text inserted and sent into the composer, and spoken replies that can be interrupted and resumed. Requires a one-time run of the bundled install.ps1 (Python speech dependencies plus microphone pick) and a SenseVoice model already downloaded by the DSH voice input (or placed under models/sensevoice-onnx).

Five tools for agent-driven audio: anyaudio_music renders note-level scores offline from local SoundFont banks, anyaudio_sfx offers 52 SoundFont presets plus 15 procedural generators, anyaudio_tts speaks through Edge or MiMo, anyaudio_mix ducks narration under the bed and normalizes peak level, and anyaudio_sources manages the shared sound-font library.

Long-term memory kept as plain Markdown plus git: each session opens with a generated memory-context block assembled from a global store and per-project books (role card, user profile, current focus, routing table, recent logs), the plugin records which memory files the agent read and reminds it to extract conclusions while the day's log is unextracted, personas live in roles/<role>/SOUL.md role cards, and it ships a seven-tab settings page in the sidebar plus four skills. Requires Python 3.10+.