Plugins

Minimal-anchored agent preset: request #1 keeps the real bash + str_replace_editor pair with auto-injected context stripped, then promotion unlocks the full Standard catalog and posts a one-shot background-jobs notice against sleep-polling habits.

Give text-only models vision: a describe_image tool that delegates images to a vision model from your dsh model list over the harness's own LLM runtime.

Lets a text-only DeepSeek agent read images in the same session by delegating to a vision-capable subagent, with send-time image-to-path conversion.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a locally running Unsloth Desktop (Unsloth Studio) server through unsloth_run and unsloth_vision tools; pure HTTP client, never spawns or owns processes.

Hands repetitive text and vision labor (OCR, image analysis, comparison) to a local KoboldCpp (llama.cpp) server through koboldcpp_run and koboldcpp_vision tools, with on-demand server lifecycle management.

Local OCR for attached images via the built-in Windows engine (Windows.Media.Ocr): only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Local OCR for attached images via Tesseract: only the recognized text is sent to the model, never the image bytes; vision passthrough is opt-in.

Give your text-only model eyes - chat image attachments are auto-described via a vision model (default prompt), with iterative re-parsing through model-generated prompts when details are missing; system/custom model modes + GUI config panel, key-safe secret handling, and a small host patch for DSH 0.1.0-rc.6 (see repo README).

Two-tier image reading for text-only models: fast local OCR (RapidOCR, offline) first, vision-model fallback (modlens).

Transparent image guard for text-only routes: paste images without the 400 session deadlock, plus a vision_analyze tool for OCR/PDF/docx/pptx/video.

Image-to-text input for the Web UI: paste or drag an image and it is transcribed into structured text and sent, giving text-only LLMs image-input takeover (OpenAI-compatible vision API).

Give DSH text-only models vision: an image/OCR/document recognition skill (race pool → custom channels → local) plus an idempotent host patch so image messages reach the model.

Turn any SVG logo into a motion video inside DSH: an `animate_svg` tool renders a transparent 30fps assembly animation (parts fly in, or the whole mark settles) and synthesizes an MP4 with ffmpeg.

Observational file-mutation rollback for the fs tools: write/edit pre-images are checkpointed as git blobs or snapshots and restored through a model-facing rollback_files tool or a /rollback command.

Nexterm fleet maintenance in a DSH session: 6 agent tools (auth with password/TOTP/device-code login, fleet listing, single-host exec, parallel batch exec, preset health checks, CPU/memory/disk monitoring) over the Nexterm REST API, plus a minimal settings page; no SSH private keys needed on the DSH machine.

Turns markdown into a WeChat Official Account (微信公众号) draft: inlines every CSS rule onto its element because the editor discards `<style>` blocks and class names, uploads each local image through WeChat's own endpoint so it is not filtered out, and creates the draft; it never broadcasts.

Animated wallpaper plugin with 8 canvas backgrounds (particles, meteors, starfield, waves, rain, bubbles, matrix, aurora) plus custom video import, and speed/density/opacity/blur sliders with localStorage persistence.

DSH usage and balance panel with official live balance, per-event official peak/off-peak pricing, all-channel spend estimates from daily balance snapshots, and a Codex-style 12-month token activity timeline. Fork of Ychris12138/dsh-usage-stats.

Real-time cost tracking for the current DSH conversation: a composer-dock line showing the running token usage and DeepSeek official price estimate (base and peak/valley pricing).

Upload files and folders straight into the conversation — images attach as real message blocks, text content is written into the composer draft, folders land by directory structure.

Floating workspace file-preview window for the Web client: lazy file tree, CodeMirror preview and in-window edit with save, Markdown and image preview, Quick Open search, and opening paths clicked in the conversation.

Input history switcher for the DSH composer that locally persists every submitted prompt (text plus attachments, max 50) and re-fills the empty composer with ArrowUp/ArrowDown, re-attaching file references and image previews.

Drag & drop or click to attach any non-image file (PDF/Word/Excel/ZIP/text) into the composer: in the desktop shell it resolves the real Finder path instantly; otherwise it uploads to the workspace and inserts the path.

Vision for text-only LLMs: image description / OCR / VQA via free Gemini and GLM vision APIs.