Plugins

Windows plugin that swaps the host shell executor for Git for Windows bash across every agent mode, materializes Git Bash variants of the standard, minimal, PTC and Cordis presets (per-file sha256-marked, user edits preserved), and exposes a gitBash capability so companion presets pick Git Bash automatically; when dsh-better-sidebar is installed it also adopts that sidebar's terminal shell (UI tabs and the model-facing terminal_* tools) through its official settings seam.

Adds an `auto` permission preset between workspace-write and danger-full-access: a classifier grants routine sandbox escalations once, while dangerous or uncertain requests still go to a human.

SillyTavern-compatible roleplay with character cards, presets, world books, and swipe branches that restore their continuations alongside native DSH conversations.

DeepSeek Harness universal preset enhancement plugin: an editable preset editor (system/user/assistant entries + camouflage model output prepopulation)

Wallpaper plus optional Liquid Glass islands for the DSH Web UI: Ice/Deepwater presets, import, wallpaper opacity, and per-island blur on official light/dark/system.

IMAP/SMTP email tools (list/read/search/send/folders/attachment/health/watch/mark/reply) with since/until date-range filters, email_mark for read/unread/star/move, email_reply for reply/reply-all/forward with threading headers, QQ/163/126/Sina/Aliyun/Gmail/Outlook/iCloud presets, multi-account support, a send-approval gate, a web settings page and a whale-girl new-mail popup driven by the incremental email_watch checker. Outlook OAuth2 device-code login works out of the box through a built-in community client, and an account can still supply its own clientId instead.

Expert-mode agent preset for DeepSeek Harness (v0.9.2, npm dsh-expert-mode, bilingual EN/ZH): a chief coordinator plus 17 domain-expert subagents with automatic task delegation. Features: taskboard scheduler (file-system task state machine pending/ready/running/done/failed, dependency DAG, atomic claim, retry, crash recovery), quality gates (5-stage pipeline for high-risk tasks: requirement clarity, implementation, verification, independent review, integration, with 2-round rework limit), Five-Anchor constraint (review/convergence/anti-drift/collaboration-check/resource-awareness per turn), Near-distance Guidance (identity/task/output template per expert), progressive disclosure (~28% token savings), expert persistence, inter-expert file message bus (direct P2P comm, zero coordinator relay), cross review, experience pool, fast-track for simple tasks, fault recovery with auto-retry. Experts: data analyst, copywriter, legal review, product manager, frontend, UI/UX, architect, social media ops, growth hacker, quant finance, finance, backend, DevOps, database, QA, security.

Match your models and token budgets to each role, then let DSH delegate specialized subagents by task type. Covers architecture analysis, UI/UX, code implementation, codebase exploration, and documentation research, with automatic setup plus per-role reasoning effort and tool permissions.

DSH bundle 插件：V4 Flash 神模式（opencode-go）agent preset 分发包，dsh plugin add 安装后自动同步 router-flash preset。DSH agent preset bundle for DeepSeek V4 Flash godmode.

Unified anchored agent preset for DeepSeek V4 Pro/Flash on the official API and opencode-go: Minimal-exact two-tool first-request bootstrap, model-aware Pro/Flash paths, and epoch-aware catalog management for long-session stability.

DSH Web session manager: delete, archive, move across workspaces, migrate preset; favorites, review-later, search, sort, priority, add tags and notes (manual / semi-automated). Suggestions are welcome on GitHub.

DSH-native integration layer for the Minta memory engine: composes the official dsh-mcp-client row, registers the minta-memory-governance skill plus a session-start memory prewarm, and ships a Minta agent preset; requires the separately deployed Minta engine (Python/Docker) to provide the 19 MCP tools - not usable without it.

Seven agent-preset modes for DeepSeek Harness, each with a fixed tool boundary, per-mode model routing and fast/deep omd_task delegation tiers, plus a plan-to-execute loop (/mode, /start-work, goal-backed /ulw) and a settings page that remaps models per mode and per tier.

LLM-assisted auto approval with countdown fallback for the Auto permission preset: static rules, risk tiers, breaker and file audit.

OpenCode Go subscription usage (rolling/weekly/monthly windows with reset countdowns) in the composer dock, with a built-in credential editor.

Programming Mode agent preset bundle: the standard coding agent with its persona mandating the Superpowers discipline (skills first, brainstorming before building, plans before code, TDD, systematic debugging, verification before completion) plus an always-on Ponytail code-volume discipline (7-rung minimal-code ladder, default full); ships all twenty skills bundled (14 superpowers + 6 ponytail) and mechanically injects the full using-superpowers skill into every new session's first request.

A gated math-modeling skill suite for DeepSeek Harness: a five-stage pipeline with stage gates, award-paper writing patterns, sensitivity analysis, statistical diagnosis, and a contest preset.

Multi-engine text-to-image generation (OpenAI Images and Zhipu CogView presets) with per-session quota tracking, engine failover, credential-safe config, and a result card with regenerate.

Global Chinese mode: a compact pill switch beside the composer that injects a language requirement into any preset's system prompt (complete personas excepted); reply, thinking and tool output each toggle between Chinese and English, and anchored presets are supported.

Manage DSH MCP, skills, scenes, memories, subagents, presets & archived sessions in one panel; per-domain context injection with visible adoption stats, and scene locking.

MySQL connector for DeepSeek Harness: configure multiple connections in the settings page with per-connection table allowlist and write permission, switch the active connection from the composer, and expose mysql_query / mysql_tables / mysql_execute tools to every agent preset.

Per-round thinking-level (reasoning_effort) control for DeepSeek Harness: pick Auto and it schedules low/high/max from the recent tool-call history, or fix a wire level (off/on/minimal/low/medium/high/xhigh/max) manually, with custom wire mapping, a model-aware capability guard, and context-window presets (64K–1M); its per-model capability card pairs with a separate plugin, [dsh-llm-openai-completions](https://github.com/drscrewdriver/dsh-llm-openai-completions) (installable from dsh-market), so custom OpenAI-compatible gateways (vLLM / LM Studio / self-hosted) can try reasoning — the card writes llm-pi-ai capabilities, the adapter drives the wire (compat.thinkingFormat), and this plugin auto-maintains the takeover list.

Header quota badge plus a usage-monitoring tab: live balance/quota remaining and reset countdown per provider, with requests, tokens (input/output/cache-read/cache-write), cache hit rate, estimated cost and average latency tracked per session, provider, model and client, stored locally in SQLite with cross-device import/export.

Adds Xiaomi MiMo text-to-speech controls for finalized assistant messages, with preset voices and custom voice design.