Vision tools · DeepSeek Harness plugins — Page 3

Sidebar plugin: session multi-level tree, search, grouping, state dots

Web skill references and the dedicated skill tool row

Slot registry pure core: SlotMap declaration merging, single register composition API, four-share props types, store-seat types, renderer install seam

Subagent conversation catalog, continuation routing UI, and '@' reference source

Theme plugin: Host bootstrap for the pre-plugin palette; DOM-free ThemeRuntime for light/dark/system state; --dsw-* token styles and Appearance settings row

Client Tool call-tree renderer and keyed per-tool presentation slot

Trajectory event ledger with an interactive timing overview: pure-consumer plugin registering into the conversation ViewMap (no service)

Web ask_user_question feature: host tool mount plus composer-takeover question UI

Durable workflow-run Conversation Node and nested member disclosure for dsh web

Immutable command-line handoff from a dsh launcher to any app plugin that injects cmdlineArgs

The dsh one-shot bundle: a direct core Agent/Session runner over dsh-base with no Host, HTTP, or browser layer

The dsh browser-surface bundle: the web patch layer over dsh-base plus the runtime glue plugin (frontend dist serving, web-surface prompt, bash runtime variables, URL line)

Bridge plugin: token-authenticated WebSocket carrier for the browser extension plus text-only browser_* tools that drive the user's Chrome via that extension

Model-facing describe_image tool for the dsh web GUI: gives a text-only model image understanding by asking a vision-language model at an OpenAI-compatible endpoint to describe one image (local path, http(s) URL, or attachment reference). Hot-pluggable — mounted via ~/.dsh/cordis.patch.yml + a profile node_modules symlink, no dsh source changes.

Eyes for text-only DeepSeek Harness agents: built-in free vision chain (no key) + pixel-level vision tools (Q&A, grounding, crop, pixel diff, colors, OCR, SVG trace, cutout, screenshots). One-command install, no Python, image turns work like ordinary tool-calling turns.

Local IMAP invoice download, OCR, archive, and Excel summary bundle for DeepSeek Harness

Bring ChatGPT-like image generation to DeepSeek Harness — Gemini, OpenAI, Seedream, DashScope, local ComfyUI & more.

DSH 界面综合增强插件：复刻 pi-web-ui 经典底部状态指标条（Token/运行状态）、输入框快捷指令芯片栏、轻量随手记便签与现代视觉主题优化。

Unofficial DeepSeek Harness LLM provider plugin for Command Code, ported from pi-commandcode-provider (MIT). Registers the 'commandcode' provider route with a Models-page card and live model catalog.

DeepSeek Harness plugin for the iOS Simulator — build, run, and interact with a live simulator stream inside a conversation. Tested with DSH 0.1.5-rc.1.

DSH 启动动画与屏保：全屏短片片尾交叉溶解进界面；闲置后全屏盖住界面，点击或按键收回。支持视频/图片/动图/Live2D，设置全在界面里。不改 DSH 本体源码。

Pure React attachment atoms for the dsh web UI: draft-image rail, message image gallery, and original-image lightbox (zero cordis)

Dynamic attachment presentation plugin for conversation input, message-image, and trajectory image slots

ChatGPT OAuth and Codex models for DeepSeek Harness.