Plugins

Publish an HTML document as a shareable link that opens in one tap and previews as a card in chat apps; publish, update, and export to PNG/PDF/Word.

Mermaid diagram renderer for the Web UI conversation: renders mermaid code blocks into interactive cards (zoom, fit-width, fullscreen viewer, preview/code toggle) with official UI primitives, and keeps the original code block with an inline error banner when rendering fails.

Analyze a codebase and generate architecture documentation: module responsibilities, dependencies, entry points and run methods.

Rappels sonores avec saut en un clic pour les sessions simultanées : la session courante reçoit des tonalités nettes dang/dang-dang, les autres un doux ding/ding-ding plus une carte en haut à droite qui saute directement vers la conversation qui répond.

Pont de pièces jointes d'images dans le chat avec un outil view_image pour tout VLM compatible OpenAI (Ollama local ou cloud) : les images collées/déposées deviennent des marqueurs de chemin view_image avant d'atteindre les modèles DeepSeek texte uniquement.

`describe_image` tool: a vision bridge that sends images to mimo-v2.5 through the opencode Zen API (credential `OPENCODE_GO_API_KEY`, free route first with paid fallback) and returns text descriptions for text-only models, with native passthrough and ImageMagick transcoding of SVG/TIFF/HEIC formats.

Outil image_describe (识图) côté modèle sur l'API compatible OpenAI de DashScope (qwen3.7-flash), plus un pont de collage : sur les sessions texte uniquement, les images collées se convertissent automatiquement en chemins de fichiers à l'envoi et se réaffichent dans la transcription, sans jamais déclencher l'admission d'images. Apportez votre propre DASHSCOPE_API_KEY ; endpoint/modèle/budgets configurables, client HTTP anti-redirection, fonctionne dans tous les agent presets.

Vision for any DSH route: paste images in the Web composer with intent-aware auto-analysis, delegate workspace image reads to a Kimi/MiniMax vision subagent, and materialize pasted originals for editing.

Auto-discovery vision bridge for text-only DeepSeek Harness agents: automatically finds an image-capable model from your configured providers and returns picture descriptions as plain text via a vision tool.

Vision-augmented DeepSeek adapter: a vision-capable model describes image input, then a text-only DeepSeek model reasons over the description.

On-demand vision for text-only DeepSeek models: upload images, and the model calls a view_image tool backed by any OpenAI-compatible vision endpoint (Qwen/DashScope by default).

Plug-in vision for text-only models on DSH, with native interaction for image understanding and generation, GUI automation, through layered evidence memory and cache.

Local-first structured vision for text-only agents: images go to a local OpenAI-compatible VLM and come back as JSON evidence (summary, verbatim OCR, layout regions, entities/relations, colors, explicit uncertainty), with anti-hallucination fallback and an optional paste/upload bridge; zero cloud cost, images never leave the machine.

Synesthesia Encoder for DSH: a vision model translates images into compact structured spatial text (canvas/elements/percentage coordinates), giving text-only LLMs pixel-level image understanding via the `mm_vision` tool.

Reuses DeepSeek web's built-in vision mode for text-only models: the deepseek_vision tool drives the local deepseek-vision-cli browser automation (manual login helper, deep-think enabled, auto-closes browser) and returns image descriptions as text.

Routes chat images to a fixed OpenAI-compatible vision model, returns factual observations to the selected main model, and reuses session-scoped observations across replay, compaction, and restarts.

CDP bridge to an already-running Chrome/Edge for DSH: screenshots, pixel assertions, DOM/CSS checks, and page JS evaluation over HTTP + WebSocket, with zero child processes, zero npm dependencies, and zero per-use approval.

Drive Jiey Browser from DeepSeek Harness over MCP: navigate, snapshot, act, read, screenshot, and manage tabs in a real Chromium profile.

Exact-profile control of your real logged-in Chrome browser: an MCP server plus MV3 extension and authenticated localhost bridge for tabs, locators, file injection, media export, and durable scroll capture, with no debug profile or remote-debugging port.

Deep-collaboration writing agent for DSH: per-user writing-style learning from edit pairs, clarify→outline→section-writing→red-team→reader-gallery flow, project-to-report synthesis (lab report / product intro / survey / README), 41 MCP tools, and web selection-improve UI with in-app file preview.

Fournit l'outil bili_summary : métadonnées de vidéos Bilibili, chronologie des sous-titres et capture d'images avec sharp, avec gestion d'erreurs et dégradation gracieuse intégrées.

Créez un raccourci de bureau Windows en un clic depuis la page de réglages : un lanceur .cmd + icône de bureau pour DeepSeek Harness ou tout serveur local, ouverture automatique du navigateur, avec astuces d'épinglage à la barre des tâches.

Ingestion-time tool-output curation: keeps error and warning lines plus head and tail, spills the full text to disk with a pointer the model can read back; covers every text tool, small results pass through untouched.

Trending-topics collector aggregating Baidu / Toutiao / Douyin / Weibo hot lists in one call (Weibo optional cookie), returning titles with heat values for content creators — tool: `sxs_news_hot`.