Plugins

Session-scoped Markdown writing pad docked beside the conversation, with edit/preview modes, selection-based AI rewrites, diff review, undo, and draft recovery.

Zero-token online status indicator for the DeepSeek Harness web UI: an always-visible online/offline dot in the conversation header, auto-refreshed every 15 seconds with no LLM calls.

Incremental file mounting with read dedupe: mounted line ranges are never re-sent to the model, on-disk changes invalidate and remount, with a Mounted Files tab and token-savings accounting.

DeepSeek Harness (DSH) plugin: a "Thinking Language" selector under Settings → General that tells the model which language to reason in (chain of thought) via a system-prompt section. Zero extra calls, zero latency, 12 languages.

Skill manager for the dsh web GUI: a sidebar entry plus a panel listing the skills visible to the current session (split into global / local groups) with per-skill on/off switches, create / import / edit / delete. Disabling a skill removes it from the mod

OpenAI Codex OAuth provider and native settings UI for DeepSeek Harness

Command Code Go provider adapter for dsh: scan the Go-plan model catalog dynamically and serve /alpha/generate through the harness LLM seam

A Symphony-compatible multi-provider task orchestrator and dashboard for DeepSeek Harness

Lightweight usage analytics for DeepSeek Harness — token trends, activity heatmaps, model breakdowns, and exports.

A model-native meta-agent plugin for DeepSeek Harness: the model synthesizes task-specific workflows at runtime from five agentic workflow patterns (prompt chaining, parallel workers, router, supervisor, evaluation loop) and coordinates tools and subagent

Native interactive Git diff review for DeepSeek Harness with structured annotations sent back to the current Agent session.

Adaptive model routing: per-request complexity classification with automatic provider routing.

Puts the agent on the Muretai network: its own identity, invite-based introductions, signed end-to-end encrypted messaging with agents owned by other people, and an inbound-mail wake that lets it reply on its own.

Extends dsh-subagent-tools with a per-call cwd for subagents, shipped with the two in-process provider patches it requires.

Per-call model, provider, persona, and toolFilter overrides for subagent delegation, with @preset: references and provider/model composite ids.

Project .pack.json/.pack.zip into .agent-pack/modpacks/ and expose skills via a workspace allow-list.

Composer-attached images are transcribed to text by an OpenAI-compatible vision model before reaching text-only DeepSeek models.

Bounded, privacy-safe local scanner for Codex, Claude Code, WorkBuddy, and CodeBuddy metadata: atomically aggregates keyed evidence and deterministically advises built-in DSH presets and optional capabilities—without content retention, network access, or preset mutation.

Edit user and built-in system-prompt sections with live preview.

Expose DeepSeek Harness sessions to Google Antigravity (Gemini) through a local, token-guarded HTTP bridge.

AI 浏览器模式：在会话右侧打开应用内浏览器（多窗口），AI 可读取页面、点击/输入/滚动、截图和下载文件；提供每窗口四级浏览器权限、风险警告、主动授权越权，下载支持断点续传与进度/速度面板。

Adds OpenCode Go's required x-opencode-session header to model requests of the configured OpenCode routes (including auto-review and hand-declared routes), with a live on/off switch.

Local Russian speech-to-text for DeepSeek Harness voice input: GigaAM v3 (ONNX int8) on CPU via sherpa-onnx

JetBrains Junie CLI as a one-shot DeepSeek Harness subagent provider over the Agent Client Protocol, with a settings page for model and thinking depth.