Plugins

Full-duplex Chinese voice interaction for DSH Web: dictate and edit tasks, submit requests, manage sessions, answer DSH questions, and hear concise task-completion announcements.

Work reports for DeepSeek Harness: gathers Git commits and local agent conversations (DeepSeek/Claude/Codex) and renders daily, weekly or monthly reports from your own templates; the agent tool is injected on demand.

Adds a /simplify command that asks the agent to simplify code within a selected Git change scope, including staged changes, commits, and untracked files.

Connects DeepSeek Harness to Busabase: search workspace knowledge, work with structured records and apps, submit writes as reviewable ChangeRequests, and inspect results in live cards.

Auto-resume for interrupted agent sessions: an ordered rule table routes by failure type (rate limit, quota, auth, context overflow, crashed orphan) to automatic backoff retry, model switch, resume after context compaction, or a stop-loss notification, with a visual rule editor and a full activity log.

A whale-maid with a jar, sitting in the corner of your DSH window. She goes exploring on Bilibili for whatever you are into, ranks by like, coin and favourite rate rather than view count, and brings back pickled snacks that suit your taste. When a term runs dry she takes another route. Five picks go into the jar, and she tells you what each video is about. News-type axes keep only the last two weeks; game guides and music have no limit, and each axis decides for itself.

DSH plugin bundling the kimi-ppt skill: create, edit and export presentations as a locally generated .pptx with Pillow-rendered previews. Derived from the MIT open-kimi-ppt-skill.

Runs TiddlyWiki 5 as the DSH persistent knowledge base: ten tiddlywiki_* agent tools (filtered search, read/write/batch/rename/delete, recent, tags, git sync with conflict resolve), a full TiddlyWiki editor embedded in the GUI center column over a same-origin proxy, a right-side wiki tab, a per-session tab summarizing the notes a session read or wrote, a quick-note card with draft auto-save, and an optional clip bookmarklet with image attachment — all backed by an auto-committing git repository.

During Beijing working-day peak hours (default 09:00-12:00 and 14:00-18:00) it blocks official DeepSeek requests or reroutes them to a configured target provider; off-peak traffic flows to official as usual.

For the DeepSeek Harness native vision model deepseek-v4-flash-vision-exp, raises image admission limits to 32 MiB / 8192 px / 600 images and adds a highres_read tool that tiles large images, then returns the whole image plus 800x800 tiles through the host read_image tool.

Six-player no-limit Texas Hold'em for the dsh Web GUI. One human plays against five LLM agents that each see only their own hole cards. Adds a dedicated tab plus a draggable mini-window over the conversation area, per-browser sessions with CSRF protection, pot-relative raise sizing, three rebuys before elimination, and showdown reveals with board-card deal animations.

Voice input for DeepSeek Harness: speak into the microphone and the recognized text is submitted as a normal chat message, via local or browser speech recognition.

ChatGPT Codex subscription chat: official OAuth, a Sol/Terra/Luna catalog with Fast rows, live usage limits, and optional search and view_image tools.

One shared Obsidian vault for every agent: dependency-free Python core (search/promote/adjudicate/forget), vault template, dsh plugin (memory_search/show/submit/status).

Let text-only models see images: when a picture arrives with a placeholder like \[image omitted because this model accepts text only], the model calls the vision_describe tool and the plugin forwards the image reference plus the question to a multimodal model, retrying with a fallback model on failure. Configured in the settings page and persisted via the official settings API.

Rotates configured LLM API keys after quota, rate-limit, or authentication failures.

Adjust Agent Team's member count, task count, message size and teardown timeout.

Rotifer Protocol skills plus the Rotifer MCP server, configured as instances of DSH's own skill provider and MCP client: search Genes, compare them on Arena rankings, install or roll back Genes in the local project, and create and run local Agents. The MCP server is version-pinned and limited to its evolve tool set, which leaves out publishing and login.

Brings the WorkBuddy, Trae and Qoder desktop logins on this machine into DeepSeek Harness as OpenAI-compatible local endpoints, with an account pool, automatic account switching when WorkBuddy is rate limited, and a settings panel.

Keeps plugins you have edited (third-party or built-in) as local git repos: deploys an exact commit only after it builds and passes checks, reverts a change that crashes dsh right after it is applied, merges origin updates (npm or git) into your edits, and can open an agent session that squashes your edits into one commit on top of the original release (backup branch first).

OpenViking in the DSH web GUI: a Studio panel, a per-session memory-commit status pill with its commit timeline, and a right-sidebar tab showing what the current session retrieves.

DeepSeek Harness port of Claude Code Game Studios (CCGS v1.1.2, MIT): 76 skills, 49 agents, hook bridge.

One-tap connect SenseNova Token Plan language and image models into DSH (off by default), with image recognition and thinking level filled in automatically. On a rate limit it backs off and retries on its own instead of misreading it as an exhausted quota. After signing in to the SenseNova console you can see the usage pill, credit pools and per-model consumption. Xiaohuanxiong can also be signed in by QR code, bringing in its models and their consumption multipliers, and taking over DSH web search.

Use your logged-in web AI (DeepSeek, GLM, Kimi, Qwen, Doubao...) as model providers in DeepSeek Harness. Web models emit tool calls, DSH runs them under its native permission system, and results return to the same web session. No API keys.