Plugins

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

QwenWork (千问办公) model provider for dsh: signs in through the desktop device flow and then calls the official OpenAI-compatible gateway, so tool calls, image input and usage pass through; adds the tiers of the plan as a qwenwork provider, keeps the credential in a local file that a refresh rewrites in place, and shows the remaining credits of the account.

Stops session lockups from OpenAI-compatible gateways that stream empty tool-call ids: intercepts llm/stream chunks in memory to synthesize consistent call_<sha256> ids across tool-call-delta and block-end, plus offline session repair/verify scripts under tools/.

Continuous voice conversation for DSH: auto sentence splitting, a 2-second confirm window before sending, and spoken replies you can interrupt by speaking. Speech is recognised by DSH's own speech service by default (a local Whisper bridge or an OpenAI-compatible endpoint can be set instead), the recognised text is corrected by a DSH model call, and replies are read aloud through Microsoft Edge's online text-to-speech service, so reply text is sent to Microsoft. A daily check of PyPI and Hugging Face for faster-whisper updates is on by default; settings and any API keys are stored in plain text in ~/.dsh/voice-tutor-config.json. Its /voice-tutor routes require an authenticated DSH session (admission is checked per request), API keys are never returned, and applying an update needs a one-time confirmation token.

Generates video through the user's own OpenAI-style asynchronous endpoint and plays the finished clip in the conversation, with live progress and cancel.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Generate a persona appearance image from hair, outfit, accessory and expression text, then save it to a local gallery. Works with any OpenAI-compatible images API and also reports the composed prompt and backend status. Needs an images API key: it defaults to SiliconFlow (Qwen/Qwen-Image) and you set baseUrl, model and apiKey in the plugin config.

Account-based access to the ToTonAI gateway inside DeepSeek Harness: sign in or register in the settings panel, use 65 mainstream models (GPT, Claude, Gemini, DeepSeek, Doubao, Grok, GLM), and pick a plan then pay by QR code in the same panel. Upstream API keys stay on the server.

Provider pool for DeepSeek Harness. It runs a local OpenAI-compatible proxy that tries configured LLM providers in priority order and falls back on authentication, quota, rate-limit or server errors, with per-provider usage statistics.

Explains Chinese internet memes to an agent: registers a meme_explain tool that returns the meaning, tone, origin and lifecycle of a sticker, which memes can and cannot be combined, occasions to avoid, and both a meme-version and a plain-version reply. Answers come from a local memory store with spacing-effect decay, falling back to a user-configured OpenAI-compatible vision endpoint (BYOK).

ModelScope connector: OpenAI-compatible chat models, a Models-page provider entry, and a composer magicube balance while a ModelScope model is selected.

Ask a vision-capable model about a local image from any session, including sessions whose own model is text-only. On the default path the plugin calls the host's route in-process with ctx.llm.stream(), so the host's credentials stay inside its provider adapters; only the optional direct/custom OpenAI-compatible routes read one key (from the plugin config or an apiKeyRef into ~/.dsh/.credentials.yaml).

Image generation and editing with configurable APIs, reference images, and an on-demand annotation canvas. Requires your own OpenAI-compatible image API endpoint and key.

Signs in to ima.qq.com (Tencent IMA) with a WeChat QR code and runs a localhost OpenAI-compatible relay in front of its SSE chat endpoint, so the four models behind it appear in the picker.

Connect multiple OpenAI-compatible providers to DeepSeek Harness: discover their models, pick the ones to expose, and generate images and videos with them from a DSH session.

A OneShot-themed desktop pet (World Machine) with the original game-style dialogue window, per-turn token usage , an optional OpenAI-compatible chat API, lightweight memory and a customizable persona card.

Logic-risk review before rewriting: audit the source, decide each fix, generate several drafts in parallel, and export with a per-draft audit report. Bring your own OpenAI-compatible API endpoint and key - the plugin ships no model and returns 403 until one is configured.

Emotion, energy and per-user portrait engine for AI characters: a 303-word emotion library scored in two steps (pick one of 6 categories first, then choose within it), novelty reward and same-word cooldown for diversity, a spirit meter with easter-egg state transitions (excited / suppressed / angry), and per-user portraits. File mode works with any AI; the optional OneBot mode reads friend message history from a OneBot 11 endpoint such as NapCat. Requires your own OpenAI-compatible LLM endpoint and API key (EMOTION_LLM_KEY or emotion/config.json).

Talks to the two public Hugging Face Spaces (MiniMax-VL-01 and Llama-2-7B-Chat) that grok3ai.org only embeds in an iframe, presenting them as OpenAI-compatible models.

Runs a local OpenAI-compatible relay that forwards DSH chat requests to grok.online, exposing its two chat models in the model picker without an API key.

Keeps a DSH agent turn open when the model ends it by narrating work it has not done: on agent/turn-stopping the guard replays the turn log and classifies the trailing message with regexes — in the default mode wait / ask / done / gray end the turn with no model call, and only a promise of pending work reaches the judge — then has a judge chain of four dialect kinds (System One three-question noul, OpenAI-compatible, OpenAI Decisions, or the session LLM) rule on whether the turn is really over, and steers the same turn with agent.steer when it is not.

Character-chat memory layer that keeps persona, voice and relationship state separate from summaries, archives every raw message for retrieval, and ships a SillyTavern card importer plus an OpenAI-compatible gateway.

Use your own OpenAI-compatible vision model in DeepSeek Harness: images are described before the main model sees the request, plus an image_understand tool for reading charts, screenshots, UI and OCR.

Runs the local nanobot CLI agent as a DSH subagent through a nanobot_run tool: each call carries one self-contained task and returns only the agent's final answer, either as a fresh process or through a persistent OpenAI-compatible server.