Plugins

Mic button in the composer tool row: Web Speech API speech-to-text (Chrome/Edge), language switching, and optional auto-send, zero dependencies.

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.

Gives a text-only model image understanding via a vision-language model, exposed as a `describe_image` tool.

Zotero library tools via the local API (no API key): search items/collections, read metadata and abstracts, list attachments, read full text (parses PDFs on the fly when Zotero cache misses), download PDFs, and manage notes.

Neumorphic DSH Web theme with light and dark palettes, ambient lighting, material shadows, grain texture, frosted-glass surfaces, and micro-interactions.

Configurable DSH usage statistics: a sidebar text/card widget plus a detail dialog with per-provider and per-model breakdowns, cache-hit rates, token trends, and latency details (TTFT and duration).

PBR 3D model preview for game art: GLB/GLTF with textures, IBL environment lighting, orbit controls, and a material channel inspector (baseColor/normal/roughness/metallic/AO/emissive/wireframe); scalar channels shown as grayscale per PBR spec, via the pbr3d fence and pbr_render tool.

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.

Four-module session companion: smart conversation export (Markdown/PDF/JSON/PNG long-image with privacy redaction and batch ZIP), context handoff summaries with template save/import, API cost optimization (live official pricing, peak/off-peak scheduling, daily/monthly budgets, model routing), and global conversation search with in-chat find (Ctrl+F, CSS Custom Highlight API).

WeCom AI Bot text and image bridge for DeepSeek Harness

Bridges session images to configurable vision providers and returns text-only analysis to eligible DeepSeek Harness model routes.

Inject rules when needed, without wasting context. DSH port of opencode-stream-rules.

Appends local hash-chained JSONL receipts for tool results and session events without storing prompts, tool arguments, result text, or raw session IDs.

Writes local JSONL summaries of per-turn tool counts and coarse verification signals without storing prompts, tool arguments, or result text.

Session execution analytics: steps, tool calls, failures, repeated actions, token usage and verification signals, rendered as text/Markdown/JSON reports.

Structured comparison and unified diffs for text/JSON/CSV/Markdown.

Native LLM-provider vision bridge: images pasted in the chat are described by a vision model (Qwen3-VL via pi-ai/llama.cpp) and the text description is fed to text-only DeepSeek for the reply — image admission, routing and compaction all run through harness-native mechanisms, with an LRU description cache and 503 retry.

Draggable grid-aligned workbench of 28 mini-cards in the margins of the conversation (API balance, token usage, cost, context pressure, todos, goal, usage heatmap, GitHub repo, image relay), with S/M/L/XL size tiers.

Select text in a committed DSH response to open an independent, persistent, read-only multi-turn Topic bound to source-session evidence and project files while the source Agent keeps running.

Presents DSH Web as a playable, full-screen first-person Minecraft-style voxel interface—not a color-only skin: users walk through a persistent Three.js block world and access native workspaces, sessions, conversations, tools, model selection, permissions, context information, and the composer through in-world facilities and a workbench.

A retro macOS System 7-style workstation UI for DeepSeek Harness with desktop windows, Workspace and Agent management, Finder, Terminal, Monitor, context tools, and desk accessories.

Read-only Web client file-preview panel with image, PDF, CSV/TSV, text, source-code, Markdown, JSON and YAML renderers, large-file range loading, and a provider API for non-local content.

Cute token-usage pet in the session header: live context occupancy, per-session usage and breakdown, plus date/weekday, weather, 3-day forecast and severe-weather alerts, all theme-aware.

Animated mood icon: swaps the favicon, sidebar wordmark and hero headline for bloub expression animations that follow session state (working / awaiting input / done / idle), with 8 shapes, 12 colors and custom wordmark texts configurable in Settings.