Plugins

Adds an Omni-modal settings section to DeepSeek Harness that points the harness at any OpenAI-compatible image and video endpoint: switchable config profiles with separate endpoint, API key, model, path and size for each side, free-form extra request parameters, a connectivity test that does not spend generation quota, and three model-visible tools — generate_image, generate_video and check_video — with async video tasks that survive restarts.

Removes the model-capability gate that blocks image prompts: patches llm.resolveModelInfo results and adapter model tables to declare image input, so routes with no declared input modality can send and read images. No app.asar or config-tree edits.

Adds a right-column panel that compares a set of images the user picks from the workspace — 1/2/3/4/6 per page, per-image zoom and pan, the zoom and viewed position of one image synced onto the whole set, and a reorderable filmstrip. The browser loads every image, so none of it reaches the model.

Chat with the DeepSeek web app (chat.deepseek.com) in a native DSH panel — a real browser drives the site on your existing web login, with streaming replies, deep-thinking and smart-search toggles, and image or document attachments. Conversations can be recovered from the web side, exported as Markdown, and distilled or replayed into a harness session, and the agent reaches the same web chat through six tools (dschat_status, dschat_send, dschat_stop, dschat_recover, dschat_import, dschat_transfer).

Panel for MCP servers registered by @deepseek-ai/dsh-mcp-client: toggle each server on or off with live effect, see the registered tool count and estimated context-token cost of each server, and persist the choice to the home cordis.patch.yml with a timestamped backup before every write. The panel itself can sit either as a page inside Settings or as an icon row in the left sidebar, one seat at a time, with the switcher on the plugin page in Settings. Maintained fork of dsh-mcp-toggle.

Generate images and videos directly in chat and deliver them to the conversation: generate_image / generate_video / send_media tools, a built-in Agnes free tier plus any OpenAI-compatible backend, background jobs that auto-push finished media, and inline gallery and video cards with download, lightbox, and native open.

Inlines an image block as base64 only in the one request where it first appears, and marks that same block offloaded on every later request so DSH's own image-offload projection renders it as the placeholder text carrying the read-only local path. An occurrence is keyed by session id, message id, content-tree path and attachment id, and a request is only counted after it produces its first chunk, so retries do not count as sent. Requests carrying a purpose are neither rewritten nor counted, a later read_image of the same file is a new occurrence and inlines once more, and only that request's copy is rewritten, so nothing is written back to the session.

AI provider runtime and configuration UI for shared credentials and embedding, reranking, speech, and image generation services in DSH.

OpenAI provider for language models, embeddings, text-to-speech, speech-to-text, and image generation in DSH. Requires Firefox2100/dsh-ai-providers#runtime to be installed and enabled.

Local-folder wallpaper for the DSH Web UI: it defaults to your Pictures library (C:\Users\<you>\Pictures) and the host serves those images over same-origin HTTP, rotating one every N minutes (0-1440, default 5) in a shuffled pass with no repeats; the settings page under Plugins picks a different folder through the native system dialog, and tunes image opacity (100%), darkening scrim (25%) and panel opacity (15%) with changes applied live. Dialogs, modals and menus keep the default opaque background so text stays readable. Reads .jpg .jpeg .png .webp .gif .avif .bmp straight from disk, and keeps per-user settings under $DSH_HOME so upgrades never ship your folder path.

Live estimated session spend in the composer dock, pricing each assistant step at DeepSeek's peak or off-peak rate for its own timestamp.

Shows the DeepSeek account balance and the current peak / off-peak phase in the sidebar, and estimates per-session and per-turn cost using the official peak and off-peak rates.

Workspace file tree and code editor in the DSH right sidebar: browse the workspace of the session it belongs to, create, rename and delete files and folders (to a trash folder by default), edit in place with line numbers and syntax highlighting (Ctrl+S saves, Ctrl+D duplicates the current line), preview images and play audio or video, list and unpack archives or pack a folder into a .zip through the system tar, search by file name or jump by a pasted path, and draw file rows with the icons Windows itself uses (SHGetFileInfo, Windows only).

Switches every session's thinking and answers to Chinese — terse, a little wry, plain-spoken — while keeping proper nouns in English, and adds an "answer only what was asked" interaction rule. One global system-prompt section (order 10): no UI, no binaries, no network calls. Inactive under the minimal preset, which replaces the whole prompt with its own persona.

Node-based GLSL workbench: wire a shader graph on a canvas and preview it live, compile it to Shadertoy-compatible GLSL with multi-pass buffers (BufferA–D), hot-reload as you edit, cross-compile to HLSL / MSL / SPIR-V, and keep projects, materials, snapshots and resources (images, audio, lyrics) in a local workspace. Ships 57 built-in nodes, 8 bundled examples and 11 agent tools. No runtime dependencies.

Turns the composer's reasoning-effort menu into a draggable slider and takes over the stock model-and-reasoning-level chip. Dragging follows the pointer continuously; releasing snaps to the nearest level and submits one session update per drag. The track draws its own fill, tick marks and white knob, only the highest levels (xhigh, max, ultra) get a flowing brand-colour gradient, and both ends carry the lowest and highest level names. The same card expands into the official model list. Arrow keys step one level, PageUp and PageDown two, Home and End jump to the ends, and each move submits. A generation counter on the directory object discards late responses, and reduced-motion turns the animations off. All data comes from the stock modelDirectories directory; no new capabilities are added.

Puts your own animated vector logo over the DSH brand mark in the sidebar and beside the start-page headline, taking over the three single slots sidebar.brand.mark, sidebar.brand.name and conversation.hero.brand.mark. The bundled patch only inserts the plugin into the loader — the official brand plugin (@deepseek-ai/dsh-client-ui-brand-official) holds those slots too, so you must disable it in the profile's cordis.patch.yml and restart. Ships a swimming whale that follows light and dark themes through currentColor and is tuned to stay legible at the sidebar's 24 px.

Connect multiple decision providers and models through one interface: Jev via TypeSafe, Clef via Cloudflare, Drex via Nace, Decider via meraGPT, self-hosted Laya, and compatible custom providers. Agents and plugins can classify content, filter candidates, score against criteria, or locate objects in images, then use structured results in their workflows.

Image generation for DeepSeek Harness through an OpenAI-compatible relay (configured for `api.ykh.ai` / `gpt-image-2`).

Re-encodes WebP attachment images to PNG so alpha-channel images load on LLM backends that cannot decode WebP (e.g. llama.cpp).

Talk to DeepSeek Harness from Feishu / Lark. A chat maps to a DSH session, messages become turns and answers are pushed back as cards; questions, permission requests, model switches and conversation switches are interactive cards, and inbound files and images are downloaded into the workspace.

Gated four-stage video pipeline: brief, script, assets and compose, turning one sentence into a narrated explainer with ComfyUI workflows or image/video APIs and FFmpeg assembly.

Local OCR with nothing sent to a cloud: mounts the PP-OCRv6 Medium stdio MCP server (PaddleOCR on ONNX Runtime, CPU) as mcp__ppocr__ocr_image and mcp__ppocr__ocr_pdf for images and multi-page PDFs.

Vision through NVIDIA NIM: mounts the bundled stdio MCP server as mcp__opencode_eyes_nvidia__describe_image, which describes an image with any of seven hosted vision models (MiniMax-M3 by default) and rotates several API keys.