Plugins

DSH Web UI workspace document vault — a “文档” tab for previewing Markdown/PDF/Excel/images/code with wikilinks, Mermaid and in-page editing.

A focused end-user QA surface backed by native DeepSeek Harness sessions

Offline voice input for the DSH Web UI: mic to local FunASR (SenseVoiceSmall), one-click install, no cloud.

BaziDIY ontology plugin: deterministic bazi/wuxing/bead/style rules as DSH tools (calculate_bazi, propose_designs, generate_design, save_design, load_design), plus bracelet SVG rendering and a bead editor; no LLM calls inside execute.

Adds an Execution graph conversation-view tab that renders each turn's prompts, replies, and tool calls/results as a foldable timeline with a detail panel and PNG export.

A calmer reading view for DeepSeek Harness with auto-collapsing process, a minimap-style message navigation rail, in-page search, unified failure cards, and generative MCP Apps (SEP-1865) in sandboxed iframes.

Deterministic loop guard: denies a tool call repeated with identical arguments and caps per-agent calls, in code outside the model; incident log lets a parent interrupt a stuck subagent.

DSH 自记忆插件（v0.3）把会话中遇到的问题、多种解决方法、脚本文件路径与模型调用全过程结构化记录下来；新会话中，「先查记录 → 有就试 → 成功标命中/失败记根因 → 无则自研 → 最后回写」的闭环自动发生，并支持外部导入解决方法。零运行时依赖、纯本地、离线可用。

Cursor 风格的 AI 代码编辑器工作台插件（DSH）：文件树、多标签页编辑、引用/备注/翻译、内嵌 AI 输入框、语法高亮

Real-time repetition guard for DeepSeek Harness (DSH): stops model generation when the same string repeats >=10 times in the streamed output. 实时检测 DSH 大模型流式输出中的重复内容，同一字符串重复十次以上立即停止生成。

Extensible AI-driven group-reaction narrative game framework for DeepSeek Harness: type one action and multiple NPCs each respond in their own chatroom message with avatar illustrations; worlds, locations, NPCs and feature extensions (e.g. a third-party drawing API for dynamic NPC expressions) are added and modified through the harness chat dialog without code.

One-click update for the local DeepSeek Harness checkout — compare versions, pull and rebuild, then restart, and roll back to any past release, all from a sidebar panel with live progress.

Brings the codebase knowledge-base capability of langchain-ai/openwiki into DSH — one-click generate/read/update of the repository Wiki, Grounded Claims (source-traced knowledge cards) and a project knowledge base built from uploaded local files, reusing the model DSH already has configured, with no second API key.

Navigation dots for DSH Web conversations — quickly jump between user messages.

Connects the Qixin Insight MCP server over OAuth 2.1 with PKCE as a single plugin entry, mounting its tools as mcp__qixin_insight__* with automatic token refresh and revocation on disconnect.

Install and call external Agent CLIs (Codex, Claude Code) from DSH without touching the system install. Each CLI gets its own Provider, model, reasoning effort and permission preset, callable directly or as a native subagent.

View and delete persistent skill memory from the DSH sidebar.

OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).

Statistiques d'utilisation des jetons par modèle, session et date dans un panneau latéral, ainsi que surveillance du quota OpenCode Go, du solde DeepSeek et du quota Z.ai.

Interactive Side-Assistant Dock to ask quick side questions via /btw with real-time thinking status and history pagination without interrupting the active agent loop.

A floating stock ticker for DeepSeek Harness: real-time quotes for Nikkei 225 and TOPIX ETF out of the box, plus worldwide markets via Yahoo Finance — Japan (.T), US, Hong Kong (.HK), China (.SS/.SZ) and any other symbol — with a customizable watchlist, display aliases and 16 UI languages.

Adds a Spawnd.gg games cabinet to the DeepSeek Harness Web sidebar with search, sorting, hover previews, embedded play, and a minimized player.

DSH 插件：可拖拽余额饼图 / 真实消耗 / 历史热力图 — balance pie with real spending & monthly heatmap for DeepSeek Harness.

Runs a parallel code review squad of read-only reviewer subagents (security, correctness, tests, style), each optionally on its own model, and aggregates one severity-grouped report from /review or a code_review tool call.