Plugins

Workspace checkpoints per tool call: records every file mutation inside the workspace (excluding .git and node_modules by default), including changes made by shell commands rather than by write/edit, and stores the previous content of each changed path in a content-addressed store kept outside the workspace. Restores have two modes — undo one record, or return to a point in time — with a line-level diff preview, a dry run by default, and a rescue record written before every restore so the restore itself can be undone.

Model-callable compact_agents tool that force-compacts context in every live session (main session, ordinary sub-agents and AgentTeams members alike), queues busy targets and compacts them when the turn ends, reports the shadowed node count and estimated tokens per target, and ships a browser form for the trigger ratio, retained ratio, controlled-phase output budget, auto-continue budget and an end-of-turn pre-compaction ratio that compacts near the trigger line once a turn ends, so a reply no longer opens with a wait for the summarizer.

Long-form novel writing plugin: each book is a git repository of frontmatter files, with 39 DSH domain tools and a web writing UI. Deep import drafts candidates, AI adoption into canonical assets requires DSH approval, and deterministic continuity checks ship with a report-only benchmark. Independent open source (MIT), not an official DeepSeek product; requires Node >= 24.11.0 and currently targets DSH 0.1.2-rc.1.

Layered memory for DSH whose agent-facing surface is 10 tools: high-privilege writes (memory_add, memory_delete, memory_import), rumination controls (memory_ruminate, _cancel, _status), and a memory graph (memory_search_graph, memory_expand_graph_node), built over an L0-L3 distillation pipeline that recalls and injects relevant memories before each model step.

dsh (DeepSeek Harness) 跨 agent 信箱插件：让 dsh 会话内的 agent 通过 agent-mailbox 与本机其他 agent（Claude Code / OpenCode / Hermes…）互发消息、收任务卡、卡动即唤醒。零 npm 依赖，Node 22 即装即用。

Ollama 监控与测评平台：node 半侧提供 DSH 工具，web 半侧提供设置页内的交互面板

Opens the dsh web GUI in a dedicated Edge/Chrome app-mode window on its own browser profile and gracefully stops the server when that window is closed.

Per-session question index for the DSH Web UI: a time-proportional dot rail on the right edge and an expandable chain panel showing every user question with its time, including branch/subagent sessions; clicking a node jumps to that message and highlights it.

Share the DSH workspace over the local network: phones, tablets and other computers browse, download and upload files via browser with no DSH login. Token gate, path boundary, read-only mode and rate limit. Zero-dependency (node:http).

Browse local image, video, and SVGA artifacts from conversation nodes in a Finder-style column view.

Raises Node's HTTP headers/body timeouts for the whole DSH process (default 30 min, proxy-aware) so Ollama and LM Studio models that stay silent while thinking or generating a large tool call are not cut off at 5 minutes; replaces the node_modules undici patch.

Clean Architecture reference library for DSH: 8 pinned reference repos (Go, Java, C#, Python) indexed into a local FTS5 database, with assertion rules, a review ledger, and a read-only observation panel.

科研收敛驾驶舱 (developer preview): hard-gated research convergence loop for DSH agents - 7 conv_* tools + host session projection + turn-tail card (conversation.chat.turnTail) + cockpit strip (conversation.input.dock) + settings section. 零 npm 依赖 (node builtins

Conversation history panel: per-exchange delete, in-place restore and a built-in node rail, with no leftover tool-call cards after deletion.

SOP-driven business Agent Teams for DeepSeek Harness: configurable captain/member agents, human- or agent-defined SOP workflows (nodes, dependencies, quality gates, manual gates), event-driven task scheduling, and a web dashboard (SOP canvas, run board, a

Workflow One - Orquestrador visual de fluxos de trabalho de IA para DeepSeek Harness (dsh), com DAGs multiagentes, execução ao vivo, recuperação e integração com Feishu

Sistema de memória leve da GUI Web do DSH: quatro arquivos Markdown em maiúsculas (USER.md / PROJECT.md / WORKLOG.md / CONVENTION.md) + duas ações (append de fluxo / distill de sedimentação). Zero dependências externas, usando apenas módulos nativos do Node; arquivos visualizáveis, com diff e gerenciáveis via git.

RPC bidirecional entre o DSH Host e o Client através da Connection nativa e do Typert Gateway, com chamadas de peer direcionadas, cancelamento e tratamento do ciclo de vida da conexão.

Plugin de verificação de atualizações do DSH (bundle estático): verifica automaticamente novas versões do DSH na primeira abertura (obtém a maior versão real do npm), exibe um pop-up no canto inferior esquerdo com um botão [Atualizar para] que executa automaticamente uma atualização verificada; a UI usa tokens semânticos de tema do DSH; raiz de instalação/versão do DSH e node/npm são detectados em runtime, sem caminhos hardcoded.

Plugin do DeepSeek Harness (dsh) para @tabilo/ai-code-review: registra a ferramenta ai_code_review (review | context) que reusa o engine Node.js para coletar diffs, rodar testes/cobertura, fazer análise de impacto e alimentar habilidades pack ao modelo.

A ferramenta run_kernel_code para o DeepSeek Harness: kernels persistentes de Python e JavaScript (um subprocess python3/node de longa duração por sessão, compartilhando um driver host central) — um plugin autônomo sem necessidade de mudanças no harness upstream.

Respondedor de aprovações do DeepSeek Harness (dsh) apoiado pelo sidecar agent-governance — toda aprovação/requisição é decidida pelo gate de negação por padrão, pelas regras L0–L4 e pela cadeia de auditoria organizacional.

Plugin de terminal local para a GUI web do DeepSeek Harness: um painel xterm.js com várias abas sobre shells node-pty reais, transmitido por uma rota WebSocket no processo host. Conectável a quente — montado pela lista de bundles do perfil web, sem alterações no código-fonte do dsh.

Detecção da stack do projeto e recomendações de capacidades para o DeepSeek Harness.