Plugins

Adds free model lanes to DeepSeek Harness — DeepSeek V4.1 Flash, Kimi K3 and others — with no login, sign-up or API key, plus a local OpenAI-compatible gateway, fallback routing and a usage dashboard.

A `describe_image` vision tool for text-only models: images (local path, URL, attachment) go to a configurable OpenAI-compatible vision endpoint and only the returned text enters the session.

在 dsh 里装上这个插件即可，无需登录、注册或填 API Key，就能使用包括 Muse Spark 1.3、MiMo V2.6 在内的前沿模型——完全免费，不限量。 All you do is install this plugin in dsh: no login, no sign-up, no API key — the frontier models are just there, Muse Spark 1.3 and MiMo V2.6 among them. Completely free, with no usage cap.

AI image generation for the DSH Web GUI: text-to-image and image-to-image through a configurable OpenAI-compatible endpoint (gpt-image-2 / gpt-image-1 / dall-e-3), with an api_url/api_key settings card and a sidebar split-pane generation studio.

Signs in and manages accounts for 16 AI coding providers, plus a cross-provider rotation channel: multi-account pools, automatic credential refresh, credit claiming where the provider offers it, and a local OpenAI-compatible gateway.

Runs Midscene on the models already configured in DeepSeek Harness instead of separate third-party API keys: hosts an OpenAI-compatible bridge on 127.0.0.1 (default port 8787, automatically skipping occupied ports) that proxies chat completions, streaming and non-streaming, to the DSH host model layer, so DeepSeek official routing, CodeBuddy, Codex and custom OpenAI/Anthropic endpoints all become available to Midscene agents while credentials stay inside the provider plugins and the bridge never touches them. A `/v1/midscene-env` endpoint generates the four MIDSCENE_MODEL_* environment lines with the model family inferred, and seven built-in skills — browser, desktop, Android, iOS and HarmonyOS automation plus a Vitest E2E skill and a Midscene knowledge reference — appear in the session skill catalog without `npx skills add`. Install from npm with `dsh plugin --profile web add @tnnevol/dsh-midscene`.

Adds account login, API and custom Provider setup, model switching, image fallback for text-only models, and token/cost attribution to DeepSeek Harness 47f.

Registers a local OpenAI-compatible bridge as a native dsh model provider: reuses the models already signed in on the desktop app on this machine, manages the bridge and its local dashboard process, and adds five tools, a /workbuddy command and a nine-tab settings panel. Requires the desktop app to be installed and signed in on the same machine; the bridge binds 127.0.0.1 only.

One DSH plugin that aggregates the models of WorkBuddy (personal multi-account, enterprise and the WorkBuddy AI international edition), Qoder CN and Trae CN into a single model picker with a shared conversation history, live credit multipliers, per-model reasoning effort, the largest context window the international edition declares, and daily check-in where the channel offers one.

Puts the Markdown documents, source files, images and video that already exist anywhere in the session workspace into the DSH sidebar, ranked by relevance to the current conversation. The default lexical mode matches your recent messages against title, summary and body locally with IDF weighting (BM25) — no model calls, no network, nothing leaves the machine. The list comes from scanning the workspace rather than from a recent-files list, so restarting DSH or opening a new session does not empty it. Results are organised into a three-tier reading order (primary / supporting / related) with a verifiable reason on every row — which field matched, which document cites this one — and one click opens an in-place preview: Markdown as rendered text, relative-path images actually drawn, source code with the host's own syntax highlighting, video streamed over HTTP Range. The same Context Pack is exposed to the agent as a knit_docs tool. Later versions added read evidence and lifecycle tracking (attribution is frozen at the moment of reading), pin / exclude (exclusion applies before retrieval, and is undoable), relation evidence (references / imports / tests, with line numbers) and an incremental index reused across restarts. Since v0.23 there is also an optional hybrid mode: it is off by default and only runs once you configure an Ollama or OpenAI-compatible embedding provider yourself. When it runs, what leaves the machine is your query text plus each candidate file's title and summary — a Markdown summary is an excerpt of the body's first paragraph (at most 60 characters), a code file's summary is its workspace-relative directory, and an image or video contributes its file name; full bodies and absolute paths are not sent, and a loopback provider keeps everything on this machine. Since v0.24 it also associates uncommitted changes: a read-only git status (fixed argv, no shell, whitelisted child-process environment) combined with the same reference / import / test / mention evidence shows which files a change is likely to drag along, and it is off by default. The benefit of semantic retrieval still awaits a real-provider run, so no recall improvement is claimed.

Design-fidelity QA for text-only models: a `deepseek_vision` tool borrows an eye from any OpenAI-compatible vision route, so the model can judge whether an implementation matches its mock — shipped with the benchmark behind that judgement (four fixtures, 23 injected defects, raw transcripts) and the questioning discipline it depends on.

Voice input for the DSH web UI: tap or hold Alt to dictate into the composer. Local SenseVoice ASR by default — offline, zero config, zero key; auto-fallback to browser Web Speech, optional OpenAI-compatible ASR chain, polish through DSH-configured models, settings UI.

Adds image_generate and image_library tools that pick reference images from four local libraries (characters, outfits, scenes, props), expand situation, expression, pose, shot and light keyword presets into the prompt, and call the 65535 async task API or any OpenAI-compatible images API, showing the result in the conversation; a settings page manages the libraries and turns an uploaded image or a text description into a three-view reference sheet. With dsh-daily-schedule installed, an image without a specified outfit uses what the character is wearing in the current schedule entry.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Gives text-only models vision: forwards user images to an OpenAI-compatible vision model and shows the descriptions in a Web UI right panel.

DeepSeek brain + automatic image transcription: attach images in the GUI and each one is transcribed via the official deepseek-v4-flash-vision-exp by default (a pure-text V4-Pro brain can see images), with any OpenAI-compatible VLM or local Ollama as alternatives.

Voice input for the web UI: dictation chunked by pauses and voice messages, each with its own provider fallback chain (Deepgram, Groq, HuggingFace, local whisper.cpp, or an OpenAI-compatible endpoint).

An AI routing gateway that runs as a DSH plugin. Adds a Routing System sidebar panel for suppliers, account pool, fallback combos and API keys, and serves an OpenAI-compatible endpoint at http://localhost:3080/v1.

Adds a generate_image tool backed by the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription, and shows the result inline in the conversation.

Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.

Media and vision workspace for DeepSeek Harness: image, video and speech generation, image Q&A and element locating, long-image OCR, pixel diff, HTML-screenshot verification and video summarization, with DashScope and OpenAI-compatible providers, model pools and a workbench client.

All-media (video/audio/image) sibling of liustack/modlens: turns local media into structured evidence (timeline / transcript / layout regions) injected into the conversation so text-only models can cite concrete frames, seconds and speakers — Evidence, not imagination. One failover chain per media, recorded hop-by-hop in meta.attempts (a fallback is never silent): host-registered multimodal models first, then a configured OpenAI-compatible endpoint (comma-separated multi-key rotation), then local ffmpeg frame-sampling / a local ASR CLI, degrading to metadata-only as a last resort. Absorbs modlens battle-tested rules — cooldown keyed only on auth/quota failures and softened to chain-tail (never dropped), redact-before-clip error text, magic-byte sniff that never trusts file extensions. Optional vision-bridge registers a media-lens wrapper into the host model selector so a pure-text model gains image/audio/video sight. Registering / authenticating multimodal models and true inline audio-video upload lean on two companion plugins, declared as optional peers (absence auto-degrades, never errors): dsh-thinking-levels fronts the model config / registration surface, dsh-llm-openai-completions takes over the OpenAI-compatible transport that serializes file blocks into video_url / input_audio. Privacy: media goes to remote providers by default; strictLocalOnly keeps content on-machine. Prerequisites not shipped with the package: ffmpeg/ffprobe on PATH (frame sampling / reencode / duration probe; degrades to metadata when missing) and a user-configured local ASR CLI for the audio fallback. Hosts 0.1.7 / 0.2.0 / 0.2.1 (6 rc, exact engines.dsh enum). npm: dsh-media-lens.

Unofficial upstream bundle for DeepSeek Harness. CodeBuddy gateway with a runtime-synced model catalogue, per-model reasoning efforts, web search/fetch, image generation and a streaming credential bridge, plus TraeWork CN and Qoder CN subscription channels via local translation gateways and a key-type OpenAI-compatible provider registry, all managed from an accordion settings card.

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.