Plugins

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.

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.

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.

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.

Memory that outlives the session, kept as plain daily log files: one markdown file per day plus a generated index the agent greps instead of re-reading. Registers the annals skill, injects the write-it-down rules into the system prompt, and exposes three tools — annals_init builds the log directory, the index generator and a separate Git repository in one call; annals_query full-text searches past entries and returns them with file and line anchors; annals_links resolves which entry cites which. Reminds the agent once per turn when it changed files but wrote no log that day, and once more when the log was updated but the index was not. Adds a settings page for the six switches.

Deletes a whole DSH session or one completed turn from the session log: confirmation dialog, live-agent teardown, path and identity checks, pre-rewrite backup, and later turns renumbered.

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.

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.

Per-model API price table with Peak and Off-Peak rates in USD or CNY, the DeepSeek account balance and live session spend under the composer, an all-time total, a collapsible source URL and check date per model, and optional per-model Peak schedules.

Tree-style questioning for DSH: click "Ask in tree" on a selection to add a node to the right-sidebar tree and ask inline under it; clicking another node makes it the current parent, so later selections nest there, Alt+click opens a root node, Ctrl+click appends another passage to the same node, double-click jumps back to the quoted text, a red/green dot marks each node as understood or not, and the panel switches between a list view and a horizontal branch graph. "Add to composer" instead puts the quote into the input box as a reference chip, without creating a node. Nodes live in localStorage and nothing is injected into the prompt.

Rewrites the New Session hero headline with a short greeting written by the model the session already uses, from the local time, the current city and the live weather; falls back to a local time-based greeting when no model is reachable.

A to-do list that lives in the right sidebar instead of the conversation: add an item, tick it off, delete it, and drag rows to reorder them. Items are kept only in the browser's localStorage, and the plugin registers no model-facing tools; a button in the conversation header opens the panel.

Shows a Live2D character in the bottom-right corner of the DSH web UI: blinking, breathing, lip-sync while talking, seven moods, and a speech bubble with its own chat, memory, corpus and stickers. Models are never bundled; every user drops in their own folder.

Adds a full-screen dialog for writing long messages: Markdown on the left rendered live by marked on the right, with a draggable splitter that remembers its ratio. Confirming writes the text back to the composer draft, keeping command tokens and @-reference chips as a fixed prefix; Esc asks whether to discard or write back before closing.

Bilibili live multiview page for DeepSeek Harness with Niri-style horizontal windows, vertical stacking, danmaku, focus-following solo, and focus ducking.

Live per-session cost badge in the DeepSeek Harness conversation header (top-right), with peak/off-peak (峰谷分时) pricing.

Web mascot that acts out each live tool call (read, write, edit, search, run, plan, sub-agent, wait, error) with matching step cards in chat; ships two swappable character packs.

Bridges a OneBot QQ bot into DSH: the owner's direct messages open a session on the same home, answers go back to QQ, and files named with \[SEND_FILE: path] are delivered. Needs a OneBot v11 implementation with a forward WebSocket (such as NapCat) and ownerId set in the config, otherwise every message is ignored. The home it shares with the main session is provided by the separately installed dsh-wakeup plugin. It also runs an unauthenticated local status endpoint on 127.0.0.1:3002 with open CORS that returns the owner QQ number, the login QR code and recent log lines (including the first 60 characters of incoming messages).

Bundles 61 specialist workflows and a Chief of Staff coordinator in one plugin, with local intake, delivery, recovery, and evidence tools.

Adds one-click permanent Session deletion to the DeepSeek Harness Workspace sidebar: a row-hover trash button, a menu item, a confirmation dialog, live-Session protection, cascade deletion for derived Sessions, and cleanup of the session log directory, projection cache and workspace bookkeeping.

Shows the DeepSeek API account balance and live round-trip latency to the configured inference provider in one sidebar widget, with a configurable low-balance alert threshold. The balance needs DEEPSEEK_API_KEY configured in DSH credentials, otherwise the widget shows a missing-key notice.

White kitten accountant on the window sill: shows the tokens and money for each answer and for the whole session, the money the prompt cache saved, the context size against the model window, the next peak/off-peak price change and the live DeepSeek balance; it purrs when stroked, reacts while the agent works and synthesizes all of its sounds.

Live done/now/next card above the composer while the agent is still working.