Plugins

Finder clipboard paste for macOS: Cmd+C files or folders in Finder, then Ctrl+V in the DSH composer inserts their absolute paths; ordinary text paste with Cmd+V is untouched.

Type normally; about two seconds after you pause, it rewrites your draft into a version more likely to get a good answer, leaving pasted code, links and long text untouched and keeping multi-part questions numbered.

DeepSeek Harness(DSH) web plugin: paste files into the composer, inbox storage, thumbnails. Text via read_inbox; image understanding needs your vision skill (bundled image-reader + ARK_API_KEY).

DeepSeek Harness plugin: a `deepseek-vision` route that declares image input and transcribes pasted images via the free Zhipu GLM vision models before delegating to the DeepSeek adapter.

A project-agnostic multi-agent collaboration protocol for the DeepSeek Harness: loop guards that stop runaway agent loops, a six-field handoff format, risk-tiered review routing, and a fixed verify→commit→push→review→close sequence. One skill instead of the same rules copy-pasted into every agent's instructions.

Chat image-attachment bridge with a `view_image` tool for any OpenAI-compatible VLM (local Ollama or cloud): pasted/dropped images become `view_image` path markers before reaching text-only DeepSeek models.

Model-facing image_describe (识图) tool over the DashScope OpenAI-compatible API (qwen3.7-flash), plus a paste bridge: on text-only sessions, pasted images auto-convert to file paths at send time and render back in the transcript, so they never trip image admission. Bring your own DASHSCOPE_API_KEY; endpoint/model/budgets configurable, redirect-proof HTTP client, works in every agent preset.

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.

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.

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

Computer Use for macOS desktop applications: reads any app's accessibility tree as text with element indices, then clicks, types, pastes, scrolls, drags, selects text and sets values through it, plus screenshots read back as images. Driven by a persistent JavaScript REPL — the agent gets two tools (`js`, `js_reset`) and calls an `sky` API inside them, so state survives between calls and the tool schema stays fixed as capabilities grow. Accessibility trees come back as diffs after the first read; actions address elements by index and indices from a stale read are refused rather than misapplied; typing waits for keyboard focus and reads the field back; paste restores the clipboard. Requires macOS 14.4+, Accessibility permission (Screen Recording only for screenshots) and Node 20+; ships a prebuilt native module, so nothing compiles at install time.

Drag or paste files or pictures into the DSH Web composer as one scrolling row of chips, sent as @path references.

Engineering work-tools for DeepSeek Harness: registers two model-facing Host Tools — a scoped `git` runner, and a package-manager runner (`dev`) that detects npm/pnpm/yarn/bun from the workspace lockfile and picks the right verb per manager. Both run through dsh's sandboxed shell and return structured stdout/stderr/exitCode, so the agent gets focused, reviewable results instead of raw bash, and adding another tool is a copy-paste of one register block.

Adds a file-picker 'attach image' button to the composer toolbar, since DSH's own web client only supports paste and drag-and-drop for image attachments (v1 scope, per its own upstream design notes) - a real gap for touch devices with no drag-and-drop and

Diagnose DSH home, leftover processes, ports, and oversized sessions, then write a paste-ready /doctor report.

Adds a right-click menu to DeepSeek Harness inside desktop shells that ship no context menu: cut, copy, paste and select all in the composer, copy and copy-as-plain-text on selected text elsewhere, and a search entry that opens the default browser with a configurable engine.

Adds a Long text button to the composer tool row: write or paste the body in an editor overlay, and on save it is written to <workspace>/.dsh-longtext/<timestamp>_<title>.md and an @ path reference to that file is appended to the composer, leaving the conversation free of the long text itself.

Sakura-afternoon pastel skin for the DSH Web UI: light and dark sakura token palettes, a click-through falling-petal overlay with a soft vignette, a header petal toggle and a General-settings master switch.

Toolbar picture button in the DSH Web composer: click to pick multiple images through the native file dialog — they join the same draft-image rail as drag-and-drop and paste, with the host image-format, per-message-count and per-image-size limits enforced inline.

Drag or paste any local file onto the DSH page; it resolves the real absolute path (Spotlight + size/mtime + head/tail fingerprint match) and inserts it into the composer, with a content-cache fallback.

AI-generated curiosity & trivia plugin for the dsh web GUI (Curio in the English UI): 「开始探奇」 generates a fresh batch of unexpected knowledge (excluding everything already seen), each item unfolds into two deeper layers plus similar knowledge points, and 「探奇清单」 keeps the full history (batch, items, layers, similar points) in browser storage. Reuses the host LLM channel with zero config; when no model is available, a DeepSeek API key can be pasted into the panel. Output language follows the DSH UI language (zh/en).

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.

Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers

Vision for text-only dsh models: paste an image and a configured multimodal model transcribes it to text automatically — transparent twin routing, an agent-callable read-image tool, no built-in keys or relay.