Plugins

Tripo 3D skills for DeepSeek Harness — generate engine-ready 3D assets from a text prompt or a reference image via tripo-cli, with texturing, rigging, retopology and format conversion in one pass.

Claude Code CLI as an LLM provider for dsh: live model list, per-session resume, approval relay, images, a memory/rewind/changes panel, and workspaces on remote SSH boxes.

Tripo 3D generation skills driving the tripo-cli through the shell: text-to-3D, image-to-3D, rigging with locomotion clips, decimation and LOD chains, and export to GLB/FBX/OBJ/STL/USDZ/3MF, with headless device login for both China-mainland and international accounts; installable as `tripo-dsh`.

Adds ChatGPT-style stop, edit-and-resend, native quote annotations, and an independent sidebar follow-up chat with model and image input for DeepSeek Harness Desktop.

Live token stats under the DSH Web composer: streamed tokens/s, output token and first-byte latency, plus per-step estimate-vs-actual reconciliation using the official BPE tokenizer, to tell a slow stream from a stalled one.

Give DeepSeek (text-only) models vision in Claude Code, Codex, and Agent Plugins clients: describe images via any OpenAI-compatible vision endpoint.

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.

Drag-and-drop file upload for PDF, Word, Excel and images: dropped files are saved to a local directory and referenced by path, no base64 bloat in the chat.

Inline preview for \[图片: path] image bridge markers: after the marker renders, the image shows in chat automatically, keeping long instructions out of the conversation.

Adds selectable animated skins to the "Deep diving..." status row, with configurable size and optional status-text replacement.

Requires DSH 0.1.5-alpha.1. Annotate selected text in finished assistant messages, then submit multiple drafts with official composer text, images, and files as one Session user message; the model answers each annotation in order with hoverable reply chips.

Image viewer for the dock workbench: PNG, JPEG, GIF, WebP, BMP, SVG, ICO and AVIF, with SVG rendered as image data only.

File explorer for the dock workbench: tree browsing of the session workspace with create/rename/copy-paste/delete, drag-and-drop import and paste of local files and clipboard images.

Two-way WeChat bridge for DeepSeek Harness via the iLink protocol: bind your personal WeChat with a QR scan and chat with a local DSH agent from the chat box (text, images, voice-to-text, files); a web settings panel handles binding/start/stop/status, project-session binding continues the conversation on desktop, proactive wechat_notify pushes include throttling, and the pure-Node daemon runs on Windows/macOS/Linux.

Codex-style `@file` mentions for the web GUI: search and reference workspace files of every format (.java, .vue, PDF, images, extension-less, hidden) with no index truncation. Replaces dsh-at-file.

Lets text-only models handle pasted chat images, with a native vision experience, batch image viewing, and a built-in OpenAI-compatible analyze_image tool; vision-capable models are unaffected.

DeepSeek Harness 原生视觉 Bundle：粘贴或拖入图片，通过托管的 deepseek-vision-mcp 调用 OpenAI 兼容视觉模型。

Desktop pet drawn from the official whale outline: pure-SVG animation follows agent state (thinking, working, celebrating, error), with poke and double-click flip interactions, cursor avoidance, 7 palettes, light/dark theme sync, and a playable web preview.

Unified image generation router for DeepSeek Harness (DSH): auto-discovers image models from any OpenAI-compatible endpoint, provides draw_image and draw_list_sources tools, supports SenseNova, StepFun, Agnes, Qwen, Flux, SD, Imagen and more.

Fully-local image understanding & OCR via macOS Vision Framework: `ocr_image` (text, table layout + coordinates) and `view_image` (scene, faces, QR) — paste multiple images into the web input box or pass path/URL/base64; images never leave your Mac.

Vision MCP and DSH bundle for text-only DeepSeek: analyze_image, analyze_clipboard, compare_images and vision_status tools, a visual settings page, free GLM-4.6V-Flash by default, result caching and rate-limit tolerance; keys stay out of logs.

Adds ChatGPT/Codex OAuth-backed Codex models and gpt-image-2 generation/editing to DSH without requiring an OpenAI Platform API key.

DeepSeek account balance and current-session spend estimate in a top-bar chip and settings card, with pause-aware auto-refresh, an editable official price table, a `deepseek_balance` model tool, and a bilingual UI.