プラグイン

System Duo for DeepSeek Harness. Make your agent think fast and slow: System One decision models triage, guard, shield, mask and check your agent loop beside System Two (vllm-sr/auto), with a free app.vllm-sr.ai key.

Interactive physics lab in the DSH sidebar — 24 parameter-driven animations (mechanics, electromagnetism, optics, thermodynamics) grouped by grade, each with a knowledge-point lesson whose steps follow the animation, a quiz with answer checking, and a draggable 3D view for four field models. Pure client side: analytic solutions computed locally, no LLM calls, no network, no telemetry.

Off-peak task queue: typing /闲时任务 in a conversation queues a task with no model call at queue time, and DSH runs it in that same conversation during the off-peak hours of the model that conversation uses (DeepSeek off-peak half price, GLM Coding Plan half credits).

Skill catalog with independent model and user manual invocation controls for file-backed Skills, live source reads, read-only non-file Providers, and safe cleanup of missing policies.

One-line song cover: fetch a track or take a local file, split stems, derive a key shift, run RVC conversion through Applio, align the vocal, mix three variants and gate the master — nine stages across three tools, zero npm dependencies. Requires a local Applio install (Python, ffmpeg, yt-dlp), a voice model and a CUDA GPU.

Text-to-speech for the dsh-go native phone UI: long-press an assistant reply to read it aloud through Xiaomi MiMo TTS or ByteDance Doubao Seed TTS. The reply is segmented and pre-synthesized in the background after each turn, so one tap hands the app a single continuous MP3 instead of one short chunk per tap; playback has a stable lease so stop works, a status strip and progress bar give live feedback, and audio can be exported to phone storage. Keys stay on the device (0600) and are never rendered, committed, or sent to the model.

Turn rough ideas into precise prompts for 19 image/video generation, writing, code and text models, with multi-model enhancement, prompt scoring, image-to-prompt and a periodic self-updating knowledge base.

Recap a session from dsh, Claude Code, Codex or OpenCode saved on this machine: the intent, key decisions and why, what changed, open threads and where to resume. Adds the session_recap tool, the /recap command and a right-sidebar panel that lists a project's sessions across agents. Uses the session's own model route, removes keys and tokens from transcripts before sending, and caches recaps locally. Needs python3 and zstd.

Routes subagent delegations once at spawn time by keyword rules over the delegation label and prompt: the first matching rule sets the child's provider/model/reasoningEffort, explicit caller routes are kept unless a rule opts in, and unmatched delegations pass through unchanged.

OpenCode Go subscription, model allowance, usage meter, and per-million-token rate panel for the DeepSeek Harness sidebar.

Delegates mechanical text work (translate, summarize, extract, classify, rewrite) to an Ollama-native or OpenAI-compatible endpoint by file path, so the source text never enters the main model's context. Registers local_transform, local_batch and local_health; per-workspace local-AI levels (none/light/default/high/max) add a local_worker subagent and a plan-only mode; an opt-in SlaveAgentTeams switch discovers mounted model routes, runs parallel child agents with node-level failover, and registers the endpoint chain as llm-pi-ai routes. Configured from the Web GUI; requires a reachable endpoint.

Sidebar sticky-note wall with colour-coded notes, checklists, folding, a trash drawer that restores deleted notes, drag and resize, and five sticky_wall_* model tools for writing and restoring notes from chat.

Translation and refinement workspace with topic memory, revision history, and main-model coordination; Normal mode uses the companion Composer extension.

Preview FBX, OBJ, glTF/GLB, and STL models in the right sidebar with orbit controls, PBR materials, four built-in HDRI environments, and animation playback.

Runs shell commands on machines you have paired with eXe, over its relay, and reads images back from them as image blocks for the model: three model tools (device list, shell, image — take a screenshot with the shell tool, then read the file), plus a sidebar page that shows the caller address of this machine, edits the device and trusted-caller lists with labels, and times a real call to each device on demand. Needs the eXe client running on those machines and a caller key from `exe mcp init` on this machine.

An IDE inside DeepSeek Harness with a file tree, multi-tab editor, AI assistant with model picker and API-key setup, Git panel, PTY terminal, and Python/TypeScript LSP.

Project workspaces for multi-session collaboration, conversation handoffs, searchable chat records, and editable shared memory; automatic memory curation and handoff judgment require two background models (memoryModel and sessionManagerModel) configured in the plugin config.

Second-model gate on the assistant turn, installed in two parts: copy engine/ into ~/.dsh/plugins/ and mount it by absolute path in the profile patch (the bundle itself only installs the settings panel), then switch off the default dry-run mode that only logs verdicts. Once active, a separate judge call scores the draft against the numbered criteria (0-10 each); any criterion under 6 fails the turn and sends it back for a rewrite, up to 3 rounds by default. The web panel edits criteria and thresholds, and every verdict is appended to an audit log.

Restarts the DSH desktop host on macOS when a change needs it, then hands the conversation back to the same session with a note the model writes about why it restarted and what comes next.

Registers 12 CatPaw (妙手) models as a DeepSeek Harness provider, with per-model reasoning effort, harness-executed tool calls, and QR-code login. The bundled catpaw-cli is a macOS arm64 binary (other platforms must supply their own copy), and calls use the signed-in CatPaw account quota.

Usage panel for the provider account behind the current model: quota windows, credit balance and token usage, following the model automatically. It renders as a full page, plus a sidebar entry and a per-session usage chip in the conversation header.

Follow list above the sidebar conversation list: a status dot per conversation (unread, waiting for you, running, failed), newest reply first, running ones last, and a follow toggle beside the model selector.

Redacts secrets, cookies and personal data in every model request at the host process undici dispatcher and restores the placeholders in the reply, so one interception covers every provider, adapters that plugins add included; per-kind actions mask / warn / block, an optional same-shape fake key, records written to disk by the day and a statistics card.

Adds a { } button under each assistant reply in the DSH Web GUI that opens the exact request sent to the model for that reply: model, call parameters, messages, tools, and provider-reported token usage.