Плагины

Upgrades DSH image viewing with pointer-centered zoom, pan, galleries, downloads, keyboard support, and inline region notes.

A permanent DSH plugin that bundles a developer workbench, an in-session conversation tree, and a plugin manager: build and run an LVAL project, browse its code, and keep per-program version snapshots with rollback; edit, retry, or branch any message in place, with message micro-versions; a feature manager plus a global-plugin library whose entries each carry an enable tier; cross-dialogue memory, one-shot temporary chats, and model collaboration; five network-permission tiers, mixed-model routing, a security audit, and browser control through a companion extension.

LLM approval answerer for sandbox escalations beyond workspace-write: a deterministic regex filter first, then a clean-context reviewer model; humans are asked only when it is unsure. Requires the bundled core patches.

Независимый ревьюер подтверждений в стиле Codex Guardian для DSH.

Fail-closed рецензент одобрения с помощью LLM для DeepSeek Harness

Режим разрешений автоматического ревью в стиле Codex: добавляет предустановку авто-ревью, которая автоматически одобряет безопасные эскалации песочницы, запрашивает подтверждение для рискованных или неоднозначных и отклоняет критичные неподтверждённые операции.

Рендерер диаграмм Mermaid для веб-интерфейса беседы: превращает блоки кода mermaid в интерактивные карточки (масштаб, подгонка по ширине, полноэкранный просмотр, переключение предпросмотра и кода) на официальных примитивах интерфейса и сохраняет исходный блок кода с встроенной плашкой ошибки, если рендеринг не удался.

Headless-консультации Claude Code с ролями советника, рецензента и проектировщика, возвращаемые как справочные ответы.

Плавающий обозреватель дерева файлов рабочего пространства для веб-интерфейса с нумерованной подсветкой синтаксиса и Markdown-предпросмотром.

Инкрементальный diff-ревьюер для DSH: после одобрения пакета показываются только изменения после контрольной точки, с веб-панелью ревью и командой `/review`, возвращающей обратную связь агенту.

Escalation-only LLM reviewer: reviews sandbox escapes only, keeps the sandbox, fails closed.

Wire-level LLM inspector: captures the raw HTTP request and response bodies of model provider calls and attributes each capture to the session that caused it through the llm/stream waterfall. The request pane renders the body as a collapsible tree with per-node sizes — one measured request was 98.6% a single 973-entry array — and the response pane reassembles the OpenAI-style SSE chunk stream into reasoning, content, tool calls and usage. Shown in a Conversation View tab and a loopback viewer page.

A continuation of simon300000/dsh-auto: the Auto Approve permission preset for the DSH Web UI reviews each approval with one single-shot model call instead of a reviewer subagent, auto-approves only the actions that pass and hands the rest to human approval, and remembers confirmed decisions as project- and global-scope allow/deny lists, with an approval timeline in the right sidebar.

Automatically orchestrates complex DeepSeek Harness requests. It detects when delegation is useful, builds a dependency-aware plan, assigns bounded researcher, architect, backend, frontend, tester, and documentation workers, collects structured evidence, and sends the results to a final reviewer. The bundle atomically enables the workflow engine and model-facing subagent tools; disabling the plugin disables its complete tool group as well.

Memory archive and prompt viewer for DeepSeek Harness: read back what compaction folded out of context - browse past sessions or Tavern playthrough archives (summary, original text, state) with full-text search - and inspect the prompt each turn actually sent, listing every assembled system section with its order, character count, offset, hash and mutability, plus an assembly map, registry export, and honest diagnostics when a section is empty or its log cannot be read. Optionally provisions a roleplay agent preset.

Multi-provider quota panel for DeepSeek Harness: DeepSeek official balance, jojo code, SCNet and Ark Coding Plan usage windows in the sidebar footer, with 90 days of local history and trend charts.

A draw.io editor as a .drawio file viewer in the DSH sidebar: diagrams are ordinary workspace files (new ones default to docs/diagrams/), edits autosave, and a file changed outside the editor is refused with a conflict bar instead of being overwritten; the editor is downloaded once from a pinned upstream release with a SHA-256 check and then runs fully offline.

Adds an "approve for me" access mode whose approval requests are answered by an independent reviewer model instead of a person: the reviewer can read the workspace read-only, a reviewer that cannot run hands the request back to the human, and every decision is recorded with its rationale in an Approvals tab.

Session messages viewer: a keyboard-driven overlay for listing and jumping to messages within the current session.

DSH 日志分析插件：选择本机 Java 服务文本日志，分析 ERROR/异常堆栈，提供 AI 工具与 Web 仪表盘

Plugin inventory manager for DeepSeek Harness Web: table view of installed plugins with status filters, enable/disable switches applied via HMR, config viewer/copy, uninstall and npm update reminders.

DeepSeek Harness plugin: a model-facing show_image tool that presents a local image to the human viewer in the conversation.

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.

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