Vision tools · DeepSeek Harness plugins — Page 3

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)

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.

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.

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

DeepSeek Harness plugin for the iOS Simulator — build, run, and interact with a live simulator stream inside a conversation. Tested with DSH 0.1.0-rc.6.

Local image-code knowledge library with native macOS and local Web clients, plus MCP and Skill for Pi, DeepSeek Harness (dsh), Claude, Codex, Cursor, and Wisp.

An open-source, agent-native platform for multimodal AI generation, built on DeepSeek Harness. Every interaction lives in agent conversations and an infinite canvas, unifying creation, generation, and editing.

Near-native image understanding for text-only DeepSeek Harness models

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

Use ChatGPT and Codex subscriptions in DeepSeek Harness with OAuth, quota, safe resets, web search, images, and Fast mode