Plugins

Quote any message of the current conversation into the composer: pick one from the @ menu, click the quote button on a user or assistant message, or select text and use Quote in the right-click menu. Quotes show as numbered chips in the composer and as summary bubbles above it; after sending, each quote becomes a fenced block so the model can tell quoted text from new text.

Live2D character stage for the DeepSeek Harness Web UI: chat-column background, foreground overlay and sidebar seats, same-origin model serving, LLM emotion control with a cross-session director, SillyTavern-style character cards and world books, and a se

Plugin Steward adds a plugin panel to the chat composer for managing the installed DeepSeek Harness plugins: list them, switch them on or off, edit a plugin's settings, hide one plugin's tools or MCP servers from a single conversation, and have the model write short Chinese labels for installed plugins by reading their own README and package files.

Audit how each turn's context budget is spent. Breaks down what a turn pays for AGENTS.md, the skill catalog, tool schemas and runtime context; flags repeated injection of unchanged content as pure waste; ranks skill-catalog bloat (with 60+ skills installed, how many tokens of descriptions does the model read every turn) and tool-schema inflation per plugin. Deterministic — no LLM, so a wrong answer is a rule bug with a name. Four tools including a cross-session sweep.

QQbot, QQ机器人 — watches chosen QQ groups over OneBot 11, batches messages by a count threshold, summarizes each batch with a model already configured in DSH, and sends the per-group report to chosen friends as a QQ private message. Messages can be filtered by keyword and by sender; ships a settings page, a local web console and a summary archive.

IDEA-style Git workbench for the Web UI: commit graph with lanes and ref labels, log filters, commit details, split and unified diffs with per-hunk staging, a fine-grained zero-context mode, local changes with amend and sign-off, rename-following file history, per-line annotate, stash, branch operations, compare, tags, an interactive rebase planner and conflict resolution. Records which model produced a commit by stamping an Assisted-by trailer from the live session, and renders any existing commit trailers as chips, so AI-authored history stays traceable.

Reflex arc for DS Bot: runs as a sibling DSH plugin with no change to ds-bot, collects facts in cheap layers, scores them with a local decision model, and wakes a Bot only when something crosses a threshold.

Parent-agent dispatch with review: split a task into work orders, hand each to a contractor you picked (its own provider, model, and reasoning effort), then pass or fail every delivery — failed ones are re-dispatched with your feedback.

ZenTao work panel in the DSH left sidebar: lists tasks, bugs and stories assigned to you (web-login protocol, so instances where the RESTful v2 API is unavailable are supported — verified on ZenTao 18.13 open-source) with search, smart sort, overdue / due-today filters and a flow-board view; opens a new chat pre-filled with the card's description, recent comments and screenshots (or a blank one), or dispatches it to a new background session with workspace, model, reasoning-effort and optional-instruction selection (single or multi-select batch), turns screenshots inside ticket descriptions into real image attachments, reads back the linked session's latest reply once a card is done and lets you answer the agent from the panel while it waits on you, and tracks each card with live running / needs-decision / done status plus manual overrides and a manually-marked finished state, with a deep link to ZenTao's finish / resolve page. Multi-account; read-only, no writes back to ZenTao.

Standalone Skills page for dsh: lists every skill with an enable switch at global, project or session scope, keeps unchecked skills out of the model catalog, and sorts them into named categories.

Cite Lens for dsh: select text in a PDF in the Files tab to quote or ask about it in the current chat, and turn the model's \[main.pdf p.7 "exact words"] citations into links that open the PDF and highlight the passage; /cite-links makes a chat cite every claim.

Reads a video or audio file into metadata, sampled stills, subtitles and a multilingual speech transcript with speaker labels, captures the live desktop as frames or a recording, and installs its ffmpeg/whisper.cpp/sherpa-onnx toolchain on first use with per-file sha256 checks; all processing stays local. Automatic toolchain install and desktop capture currently support Windows x64 only, so elsewhere ffmpeg and model paths must be set manually.

Nine model-facing tools over the qBittorrent WebAPI v2, with confirm-gated mutations and an orphan-torrent diagnostic.

Connects a ComfyUI server to the agent through five draw_* tools (status, workflows, models, generate, reverse) and a sidebar panel. It ships no workflows and assumes nothing about your models: every API-format JSON you drop into the workflow directory is inspected to find where prompt, negative, width, height, steps, cfg, seed and LoRA live, and a sidecar file can override what was detected. LoRA injection splices into any graph. All paths are configuration, editable from the panel and saved to a settings file, so it works against a remote or already-running ComfyUI. Headless auto-start and idle shutdown are opt-in and off by default.

Run Blender headless from DeepSeek Harness: execute bpy scripts, render scenes and export glTF assets, with modeling cookbook, 5.x pitfall list and asset-pipeline playbooks bundled as skills so the agent self-checks geometry before handing assets back.

Read-only CNKI bibliographic search for DSH: four MCP tools (search, detail, export, status) drive your own Edge/Chrome through a native-messaging bridge, with no PDF downloads, a 3-second minimum interval and a 300-action daily cap. Requires pip install wensu plus wensu setup and loading the browser extension before the four tools appear.

Port of the V2 memory pipeline from OpenAI Codex to DeepSeek Harness: a background agent extracts each idle session, consolidation folds the extractions into one memory_summary.md behind a git baseline diff, new sessions get that summary injected, and cited memory flows back as usage counts. A Settings page chooses the model, each stage's reasoning effort, and the idle, age, concurrency and timeout limits.

Adds a Timestamp toggle to the composer; while it is on, each message you submit is followed by a hidden context message carrying the current local time, so the model knows when you sent it. The switch is remembered per conversation.

Adds Tako chat models to the official llm-pi-ai provider list from Tako's public catalog, with live refresh, context windows from size tags, and browser one-click sign-in writing a cr_ key into DSH credentials.

Rates how hard the current message is and shows the cheapest model and reasoning effort that still fits, above the composer, before you send.

Adds a Claude Pro/Max OAuth provider with multiple accounts, optional account failover, cached quota reporting, live model catalogs, and quota UI in settings and conversations. Uses the Claude Code client identity; quota reporting uses an experimental endpoint.

Bailian (DashScope / Model Studio) model catalog in the DSH settings page: lists every model the configured API key can reach, groups them by model family, probes whether a model is actually callable (an unopened model answers 403, which DSH reports as an invalid key), refuses to add models that fail the probe, and shows the active session's context window and remaining budget. An sk- key has no balance endpoint, so quota here means context quota.

Official-style model + reasoning-effort control for the composer. Reuses the official picker and always offers Off/Low/High/Max — exactly like the official DeepSeek control — even when a gateway model declares no reasoning effort, with a small hint at the panel bottom when upstream does not natively support it.