Plugins

Crie um atalho de área de trabalho do Windows com um clique na página de Configurações: um inicializador .cmd + ícone na área de trabalho para o DeepSeek Harness ou qualquer servidor local, abrindo o navegador automaticamente, com dicas de fixação na barra de tarefas.

Caixa de ferramentas pessoal para o perfil web do dsh com chaves por recurso: notificações de desktop ao concluir tarefas, reinício em um clique, exclusão de sessões, ativar/desativar plugins, checagem de atualizações e utilitários de UI.

Memória de pistas de eventos entre sessões para o DeepSeek Harness: extrai automaticamente pistas de tarefa/conversa e hábitos de linguagem do usuário de cada turno para um banco global persistente de pistas, e depois reinjeta o contexto lembrado ao detectar troca de assunto (correspondência por palavra-chave ou vetor).

Widget de custo de tokens ao vivo por tarefa: janelas de preço de pico/fora de pico, custos projetados após o aumento, tabela de custos por tarefa ordenável, multimoeada (COP/USD/CNY + ~40 outras) com taxas de câmbio e explicação LLM transmitida com um clique das tarefas caras.

Roteador de modelos em dois níveis para o DeepSeek Harness — roteamento por LLM-Judge, cadeias de fallback multimodelo, failover com backoff exponencial e orquestração em nível de tarefa (adaptação do pi-shift-router para o DSH)

Plugin de tarefas recorrentes/agendadas (轮询任务/定时任务) para o DeepSeek Harness: jobs de polling orientados por cron como sessões reais, criação em linguagem natural, ferramentas de modelo (polling_create/list/edit/delete/trigger) e uma UI web. Pronto para usar via `dsh plugin add`

Aprovações “Permitir para esta tarefa” com escopo por turno: permite automaticamente escalonamentos `danger-full-access` correspondentes apenas para a tarefa atual e depois expira

fal.ai native image generation for DSH: a FAL_KEY settings card that follows DSH's language (zh/en, English default) plus Agent tools (fal_generate_image async / fal_edit_image / fal_get_image_task / fal_list_image_models) that call queue.fal.run directly

Cut LLM costs: route routine tasks to cheap subagent models (DeepSeek Harness plugin)

树形任务流：把多步任务组织成目标→任务→子任务三级树，节点完成时由 AI 提交结果，插件随即把该节点的执行过程从上下文里折叠掉，只留下结果。

DSH 临时任务模式：为 DSH 增加「任务」分组——不绑定任何长期工作空间，自动在任务根目录下创建隔离的临时工作目录并开启会话，即开即用、用完即弃。Temporary task mode for DeepSeek Harness.

Worktree Space: puts a workspace task that spans one or more Git repositories in its own task space directory - each repository in it gets its own worktree on one shared task branch; the space is registered as a DSH Workspace so sessions start right there, and multiple tasks run side by side without interfering. Finishing a task can merge the work back into each repository's target branch, remove the worktrees, and file whatever Git does not track in an archive directory you choose.

A searchable, sortable model picker for the DeepSeek Harness Web UI — provider groups, favorites, hidden-models blacklist, live per-task cost, prices and context windows, a refresh button that re-syncs every provider model list from its live API, and the

DSH plugin: cross-session call center for agents. session_message delivers messages between DSH sessions (idle: visible full-text wake; busy: mid-turn-safe notice; plus runtime-context notes) and resolves targets by registered contact name (stale-id-proof

SDD task progress (todos) and progress ledger (sdd/progress.md) as a right-sidebar tab bound to the current session, rendered with the official MarkdownText, auto-refresh every 5s.

Chat panel for the MuChe companion with per-user backend settings, plus an outbound bridge that runs tasks on the user's local dsh.

Drives the GME Test Agent from inside Harness: three tools list interface catalogs, start and repair autonomous test generation in a local Python backend, poll the task until review, and keep PR, skip and cleanup actions behind explicit user consent.

Discover and run project tasks through Harness Jobs, inspect run receipts, and check project configuration with an Agent tool.

Personal-experience memory for DSH: turns solved tasks into sourced problem cases with condition-scoped claims, recalls them into new tasks via hidden pre-step injection, and makes corrections/deletes cascade to future recall.

Brings the Codex (ChatGPT Plus/Pro) subscription already signed in on this machine into DSH. It (1) shows the 5-hour and weekly windows with their reset times and the remaining reset credits in a sidebar panel, with one-click reset that consumes a credit; (2) registers the subscription route in llm-pi-ai (openai-codex) when the quota is read, so the Codex models appear in the model picker; (3) refreshes the OAuth access token before expiry and writes it back atomically, so no key has to be replaced by hand; and (4) adds a codex tool that delegates a task to the local Codex agent. No API key has to be entered.

Session-local scheduled tasks: inject a prompt into the current session after a delay, at a fixed time, or on a repeating interval, so the model wakes up and runs it on time. Manage them from a panel above the composer, the /schedule command, or seven model-facing tools. Timers freeze while DSH is closed and never auto-resume; pause keeps the remaining time, so resuming continues from where it stopped.

Generic idea manager for the DSH Web GUI: Host-authoritative /api/ideas ledger, capture, 4-column kanban (open / under review / archived / declined), optional TaskBoard mirror; mounted without DSH source changes.

Live progress for long-running DSH tasks: a script appends JSON lines to a per-session progress file, the Web UI draws them in a floating overlay and a right-sidebar tab that also lists background jobs which reported nothing, and `dsh-progress run -- <cmd>` wraps a command that cannot report for itself.

Google Jules as a DeepSeek Harness capability — delegate coding tasks to the remote agent, watch them in the background, approve plans, and land the diff.