プラグイン

承認および質問/プランのプロンプトに対するネイティブ OS 通知。トーストにワークスペース名を表示し、クリックでそこにジャンプ、中国語(簡体/繁体)/英語のバイリンガル対応、チャイム音付き。

スキルと MCP 設定をスキャンし、プロンプトインジェクション、同形文字、隠れた Unicode 文字、危険なシェルコマンド、認証情報の漏洩を検出します。

型付きで保護されたコンテナ操作。ps/logs/inspect/exec/start/stop と compose up/down を JSON 出力付きで提供し、プロジェクトを意識したターゲット指定と、破壊的操作への承認ゲートに対応します。

Web Components 対応。

Claude-style composer header bar: shows working-tree diff counters, quick branch switcher, native diff drawer integration, and adaptive PR creation with Actions CI status.

Subagent model control: a Jev classifier labels each turn, and the subagent's own request is rewritten to the provider, model and reasoning effort that label maps to; per-session inherit/auto/manual selection, one prompt per role injected ahead of the task, and a ledger of recent dispatches.

输入框提示词联想插件：助手回复结束后预测你的下一句话，以灰色 ghost text 浮在输入框里，Tab 采纳、Esc 忽略 ｜ Codex-style composer prompt predictions for DeepSeek Harness: your next message ghosted into the composer, accepted with Tab.

Image generation for DeepSeek Harness through an OpenAI-compatible relay (configured for `api.ykh.ai` / `gpt-image-2`).

Drive the desktop and Chrome from DeepSeek Harness using the computer-use runtime inside the ChatGPT desktop application.

Remote companion for dsh-remote-desktop iframe control.

Cross-session memory for your dsh agent: remembered, recalled, and re-verified instead of assumed.

Removes sandbox_permissions / justification arguments that cannot widen the call's current sandbox mode, so calls no longer fail with 'sandbox escalation to "workspace-write" is not strictly wider than this call's current "danger-full-access" mode'. GPT models tend to fill these optional fields on every call and pick workspace-write, which is narrower than danger-full-access. Runs in tools/pre-execute: compares the requested mode with the mode the session's sandbox policy resolves, and drops the fields when the request is the same or narrower (also drops a lone justification). Also understands the values GPT carries over from Codex's own shell tool: null, empty and use_default are treated as no request, and in a danger-full-access session any value (including require_escalated) is dropped because nothing is wider. Real widening requests, unknown modes and tools that do not advertise DSH's escalation schema are left to DSH core. Never widens permissions. Configurable tool list (default bash, pwsh, write, edit, run_code). Zero dependencies.

Pushes DSH session events to phone IM and lets you reply straight under that message, injecting the text back into the right session. Covers nine event kinds: task completion, execution error, execution blocked, manual abort, token limit reached, abnormal interruption, waiting for your answer, permission request, and waiting for plan confirmation. Channels are QQ single-chat bots and Feishu custom apps, both over WebSocket long connections — no public IP, domain or tunneling needed. Several bots can be configured at once, each subscribing to the sessions it cares about. Approvals and questions arrive with tappable buttons, and replies route home through three layers (button, quoted reply, explicit short-id prefix), falling back to the most recent intervention-needed notification and echoing which session it went to.

Five task-state reminders for DeepSeek Harness (completion, approval, question, block, error) with four synthesized browser sound presets, system notifications that open the right session, and a terminal-BEL fallback when no browser is ready.

Windows toast notifications for DeepSeek Harness covering approval requests, questions, run completion, errors and sign-in prompts, with the conversation name as the first line of every notification.

Gated four-stage video pipeline: brief, script, assets and compose, turning one sentence into a narrated explainer with ComfyUI workflows or image/video APIs and FFmpeg assembly.

Session-scoped delivery receipts for local artifacts: compare current file hashes with a recorded baseline, keep agent claims separate from explicit user acceptance, flag changed or unavailable files, and export a Markdown receipt through a tool, slash command, and conversation panel.

Ports jcode's auto-poke so an idle agent keeps working while its session still has incomplete todos.

Compiles a rough need into a versioned task book (goal / context / constraints / acceptance / decisions / open gaps, all numbered) and hands it to any AI window losslessly: the receiver must pass a read-back handshake — restate, list gaps, declare READY — before work starts; /answer closes gaps with an automatic version bump, /forge-list tracks which window holds which version.

Skill browser and switchboard for the DSH web GUI: a sidebar entry lists skills from configurable source directories as cards, clicking a card opens the full SKILL.md, and the per-card switch writes disable-model-invocation and registers or removes that skill in the agent skill catalog, so the model can load exactly the skills that are switched on. It also recognises WorkBuddy expert-team folders and shows avatar, tags, quick prompts and members, registering its lead prompt as a skill when switched on. Source directories are editable in the panel.

Speaker button left of the model selector in the composer tool row — one click scrolls to the start of your newest question, marks it with a blinking caret and reads from there through the newest agent reply (dsh-tts, browser voice as fallback); press-and-hold the icon and then click anywhere on the page to pick another reading start position; press-and-drag-up opens a vertical mixer for in-page media volume and system output volume.

Adds an agnes_image tool that calls the Agnes Image Flash models (2.5, 2.1, 2.0) for text-to-image, image-to-image and multi-image composition, and ships a settings-page console for the active model, default size and aspect ratio, output folder, API key and generation history.

Adds a "Check updates" tab to the Built-in plugins settings: scans every installed bundle for the latest published version and DSH-runtime compatibility, with a per-plugin update action.

Mounts the hosted Reaudit MCP server (https://mcp.reaudit.io/mcp) through the in-box @deepseek-ai/dsh-mcp-client bridge with a REAUDIT_API_KEY bearer token: 238 mcp__reaudit__* tools for brand visibility in AI answers (ChatGPT, Perplexity, Gemini, Google AI Overviews), competitor and citation analysis, site audits, content generation and social scheduling.