Plugins

Qwen Token Plan CN Responses provider for DeepSeek Harness via the OpenAI Responses API, with Qwen server-side tools, DSH local function tools, text/reasoning/tool-call multi-turn history, persisted image attachments, and a per-release official model catalog snapshot.

Classic Macintosh (System 7) pixel theme: desktop pattern canvas, Finder sidebar, monochrome buttons and dialogs, light/dark support.

Real-time token estimates for the DSH conversation composer, combining the current context baseline with the draft and showing exact or heuristic counts.

Shows MiniMax Token Plan usage beside the DSH Web UI model selector with compact 5h/7d bars, click-to-refresh, automatic idle and heartbeat refreshes, and endpoint fallback. Reuses subscription keys configured under Settings → Model and appears only for MiniMax Token Plan providers.

One-click update for the self-built Linux dsh-desktop: check fork releases, download the deb, swap the app and restart.

Provider balance and quota status bar for DSH Web, with model capability settings, external JSON health monitoring, visual field binding, and per-model status details.

Shows DeepSeek API balance and tells whether the current moment is peak or off-peak pricing time, with a live countdown to the next switch.

Local-first personal usage insights in Settings, with 1/7/30-day token heatmaps and a 30-day calendar, token composition, model mix, and skill-call status.

Aipx toolkit: skills plus a Hub Console that fronts every MCP server with ~4 meta tools — server pool health, per-tool enable/disable, a tool catalog, and a search playground showing exactly what mcp_search hands the model.

A Codex-style right side panel for the DSH Web UI — session artifacts browser (live file tree, scan include, preview, reveal) plus a side chat that forks the current session with a model picker, human-pacing scheduled runs and smart send-to-bottom scrolling.

Renders local audio/video paths as inline, playable previews in DSH chat: replaces paths with <audio>/<video> players backed by same-origin /api/media-preview/* route, with explicit error statuses.

Composer button that opens a panel listing every skill available to the current session with Chinese titles, purposes and usage examples, and lets you catalogue newly installed skills in one click (saved locally).

Layered syntax highlighting for bash/pwsh command and read code output in the DSH web GUI (VS Code Dark+ palette: keywords/strings/numbers/functions/comments each get a color); colors only what it recognizes, keeps tables/logs plain; pure frontend, zero token overhead.

All-in-one inline media previewer for mip-img/mip-video/mip-audio fences with streaming playback, ffmpeg transcoding fallback, lightbox, and trust-fenced LAN/mobile access.

Right-side message navigation rail for DeepSeek Harness: per-message tick marks, hover-to-expand preview drawer, smooth jump to any historical message, star bookmarks, realtime slide animation with interrupt support, full session index with virtualization, dynamic panel avoidance, official --dsw-* token styling.

DSH Desktop enhancement: one-click update checker, DeepSeek balance & API key viewer, and import other AI tools.

Version badge above the sidebar settings button: shows the current dsh version, expands to list every core package version, and checks npm for updates with one-click deploy.

Durable, reversible installer that patches DSH Desktop session-reference UX — workspace-prioritized @ candidates, title-first display, two-line menu layout, and sidebar drag-to-composer session references.

Manchester United 2026/27 fixtures in the sidebar with kickoff times in your local timezone, finished matches with W/L/D results.

Full workbench fork of dsh-better-sidebar: explorer, editor, terminal, Git, browser and split panes, plus a VSCode-like shell refactor with a full-width compact header and activity rail; publishes as @all3cn/dsh-better-sidebar-n23 on npm.

Provider health dashboard as a Settings page: read-only per-provider status, health (time-decayed from recent errors), thinking capability, max tokens and latest error, sourced from the llm-pi-ai config and the compat-healer error log.

Keeps a local model's context at a size the GPU handles well: measures prefill speed on every request and, before each step, warns or compacts early on a hard token ceiling, an observed time-to-first-token budget, or a predicted cold-prefill budget; /context-budget shows the numbers and the cost of compacting now.

Git Ship Done (opengsd-core) reimplemented as host-plane Cordis plugins: replaces the default agent loop with a spec/discuss/plan/execute/verify/ship phase loop.

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).