Plugins

Browses checkpoints produced by dsh-checkpoint-rewind as a timeline of time nodes and shows per-file line diffs between any two of them, with trace replay from session logs (no snapshot producer needed) and preview-first workspace rollback with single-shot undo, via /diff and /rollback commands, a JSON HTTP API, and a GUI panel.

LAN / remote-access control, frpc NAT tunneling, a panel password gate, and mobile UI adaptation for the DSH Web GUI.

Feishu (Lark) bridge for DeepSeek Harness: one-command install, streaming progress cards with a tool panel, ask/approval button cards, attachments, and proactive feishu_send pushes.

Host-side Typert remote for dsh-tool-writing: serves project volumes, chapter status, corpus library, full-text search, evolution entries, and thread-graph data to the client writing panel.

Citation tools for agents: exact DOI lookup, Crossref bibliographic search, GB/T 7714 / APA / MLA / Chicago formatting, BibTeX generation, bounded-concurrency DOI validation and health self-check. A step-by-step first-run guide (3 steps) now opens inside its settings panel.

Client-side writing panel for the Web UI: project volumes and stats, corpus library, full-text search, evolution version-chain diffs, and an SVG thread graph, shown only in writing-preset sessions.

Web GUI bundle for DSH: a task board with cron scheduling, a Git branch graph, a file and change side panel, an SSH terminal with SFTP and port forwarding, QR-paired mobile remote control, a desktop companion, live token statistics, and five installable themes.

Pomodoro focus-and-break timer for DSH Web with configurable cycles, a draggable mini panel, and in-app, sound, and browser notifications.

Per-workspace persistent memory for DeepSeek Harness: a sidebar panel to manage Markdown memory files, automatic injection into every session of the workspace, and an agent tool to save new memories

Sidebar image workbench with separate Agnes / OpenAI GPT Image / Grok / OpenAI-compatible keys, text-to-image and up to five reference images, local history, an image_studio_generate tool for /image, and an in-panel GitHub update button.

Tool-use visibility for dsh: an act wrapper and guard make every ordinary tool call carry a describe field (direct calls are rejected by default), the model narrates decisions in plain text, and live act cards with thinking, purpose, status and result show in a strip under the composer and, with the optional dsh-better-sidebar plugin, in a right-side digest panel. Also adds a background event tool for long tasks.

Offline civil-service exam study panel integrating 16 upstream open-source question banks with SRS wrong-book, mock exams, essay grading, an interactive knowledge graph and whitebox observability, plus a HuaSheng-13 methodology view (25 documents) with BM25 search. The npm package ships no question-bank or corpus data: after install, the question-bank manager clones the required set (about 360 MB, needs git) from the upstream repos (all 16 are about 2.2 GB).

DeepSeek Harness (DSH) plugin: a DSH NEXT sidebar entry that embeds the dsh-superagent management panel in a same-origin iframe and starts/stops/restarts one or more services.

QQ hub for DeepSeek Harness: private and group chats over OneBot v11 (SnowLuma/NapCat), with per-chat scoped memory, per-chat persona routing, a vision helper that narrates images for text-only models, multi-platform link parsing (large videos sent as group files, image galleries sent inline or as merged-forward messages) and a web panel for models, personas and settings. Derived from aureth-labs/dsh-aurabot-qq; do not install both.

Embeds chat.deepseek.com in a DSH desktop panel and moves text both ways round by round: pick any round of the web conversation and copy it, or send it as a user message into a session of a chosen workspace; and fill any answer of the current agent session back into the web input box without sending it. The embed reuses the web session, so it spends no API quota, and asks for a web login once per app start.

Retries a model request that no other recovery layer claimed, unbounded by default with an exponential backoff ceiling, never retrying a cancellation; the policy is editable from a Settings panel.

Sidebar category groups for DSH workspaces: the flat project list becomes collapsible named sections, workspaces re-file by dragging a row onto a group or picking one from a dropdown, one toolbar button collapses every group at once, an appearance panel sets font size, text color and background tint for each of the three levels, and Ctrl+Tab cycles recently opened sessions.

Sidebar panel for Agnes image and video generation that also ships a node canvas and a short-drama mode. Canvas nodes are chained by extracting the previous shot's tail frame with ffmpeg and submitting it as the next shot's first frame; short-drama mode turns an imported script into storyboard shots. Generation and polling run in the Host process, so tasks survive a page reload or a closed panel, and results plus an 80-entry history are stored on disk.

Browses Bilibili on your behalf and actually takes part: search videos, like, coin, send danmaku, post comments, reply to other people, and keep replying when someone answers back. Reads the video's Bilibili AI subtitle (or transcribes the audio locally when there is none) so its comments talk about what the video really says, and it reads that same content before choosing whom to reply to. Instead of copying other people's sentences, it distills rules about how to sound like a person and gets less AI-ish the more it runs. Skips videos it already browsed, de-duplicates replies per thread, and after too many rounds with the same person in one comment section it reviews whether the exchange has any substance -- if it looks like two bots complimenting each other, it says one last line and stops replying to that person there. Checks whether each comment is genuinely public or only visible to your own account, can scan any time window (last hour / day / 3 days / all) and lists the ones others cannot see, warning you on the overview when replies got folded. Six-tab settings panel where every change takes effect immediately with no restart, a manual run that queues behind the background listener instead of being refused, and an environment self-check that tells you exactly what to install. Requires Python 3 for the Bilibili actions; the built-in check lists any missing packages.

JetBrains-style IDE workbench in the DSH sidebar: Project file tree, Commit panel, Git history with a swimlane graph, a real PTY terminal and an embedded editor with Markdown preview and Find in Files, plus chat file links and send-to-chat references.

A floating board over the chat for DS Bot's team: who is running and on which tool, who is waiting for another Bot to hand work back, who needs your approval or answer, and who failed, with a hand-off table grouped by sender, a per-Bot drawer showing the pending command or question, and a collapsed one-line pill. Read-only — it never writes to DS Bot's data. Needs the DS Bot plugin installed (built against 0.1.7 and 0.2.0); the panel stays hidden without it.

Fortune-telling toolkit: bazi, ziwei doushu, meihua yijing, liuyao (six-line coin oracle with najia), almanac, chenggu bone-weight, zodiac, date selection, qimen dunjia, fengshui, name scoring, compatibility, numerology, a life K-line chart, tarot and xiaoliuren — 16 tools whose ganzhi, stars, hexagrams and bone weights are all computed by deterministic local engines, with the model only interpreting results. Supports solar and lunar dates with leap months, China DST and true solar time correction, plus a ten-page read-only side panel.

Locks the model's reasoning, replies and tool-call descriptions to a chosen target language (Simplified Chinese by default) with system-prompt sections at the head, middle and tail of the prompt, offering three strength levels, an auto mode that follows the DSH interface language, a settings panel that shows the language currently in effect, and a sidebar quick switch.

Usage statistics: a usage and reference-cost panel for DeepSeek Harness with today, 7-day, 30-day, all-time and custom ranges aggregated by hour or day; a model filter and a per-model breakdown of requests, input and output tokens, cache, reference cost and share; a model-share card showing the top four models by total tokens with the rest grouped as others; a reference price list generated from opencode Zen and DeepSeek's published rates, with DeepSeek models billed by Beijing weekday peak/off-peak windows and Chinese public holidays; a pricing-match dialog to point an unmatched model at a reference model or type per-million rates by hand; reference cost switchable between ¥ and $ at a fixed 1 USD = 7 CNY; and a yearly heatmap drawn only with theme variables, with no third-party chart library.