Plugins

Retoma automaticamente requisições interrompidas na Web do DSH: envia um 「继续」 (continuar) enfileirado após falhas de rede, timeout ou crash do host, com classificação de erros, backoff adaptativo, texto de continuação baseado em templates e notificações no navegador.

Converte artigos DSH em diagramas Excalidraw da sessão: diagram_create, edição com salvamento automático, exportação PNG/SVG/.excalidraw e leitura com diagram_read. 0.6 adiciona visão editável e índice para árvores grandes de três níveis.

Guarda e monitor de concorrência para DeepSeek Harness: fila FIFO quando requisições simultâneas de modelos atingem o limite, estatísticas persistidas por dia com classificação por tipo de erro, e detecção de interrupção para fluxos abandonados.

Toolbox de visão aprimorada: 14 ferramentas de visão em nível de pixel (describe, ground, detect, crop, pixel-diff, OCR, OCR de long-screenshot, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) acionadas por um endpoint compatível com OpenAI, com marcadores de bridge [图片: path] limpos, classificação de segurança de conteúdo e retry automático de rate-limit.

Plugin de previsão bursátil bayesiana que funde MACD, RSI, médias móveis, volume e outros sinais técnicos em uma probabilidade posterior de alta, com comparação multi-horizonte, classificação do estado de tendência e métricas de risco de posição para ações A e dos EUA.

Memória de projeto DSH: cria PROJECT.md, DECISIONS.md e SESSIONS.md no primeiro passo de cada sessão do workspace; relê do disco e só reinjeta se mudar ou se a compactação remover. memory_checkpoint classifica dados; lembrete limitado para trabalho sem registro. memory_read lê log e arquivo; memory_search pesquisa com BM25 sem dependências. Limite 200: excedentes em SESSIONS-archive.md nunca são injetados, mas podem ser lidos, pesquisados e restaurados um a um. Ajustes: filtro workspace/caminho, abas somente leitura, recarga, JSON import/export por workspace, exclusão em duas etapas, editar/remover bloco AGENTS.md e aviso PROJECT.md desatualizado. Indicador de sincronização; cria ao clicar. Sem dependências, vetores, embeddings ou chamadas de modelo.

Verifiable issue-to-PR delivery chain: an 11-stage pipeline (analysis, search, code understanding, hypothesis, planning, implementation, patch ledger, tests, review, failure classification, PR build) with 4 human review gates, GitHub/GitLab/CodeArts credential connections, a 5-page workbench and a draggable AI assistant panel.

Organiza a navegação de configurações do DSH: agrupa entradas de plugins de terceiros sob linhas de grupo recolhíveis, com grupos personalizados no estilo de favoritos, um botão de recolhimento e classificação automática (tags do mercado → regras de nome → seu modelo de IA).

Roteamento adaptativo de modelos: classificação de complexidade por requisição com roteamento automático de provedor

Turns DSH permissions into 9 selectable presets (3 sandbox modes x 4 approval tiers), with rule plus LLM risk classification across four risk levels, password-gated approval for high-risk operations, and a JSONL audit log.

DSH agent tools for local Ollama System One decision models: classify, answer yes/no, and score against a rubric in one batched request.

Hands secrets and PII to the agent without them entering its context, with checksum-validated extraction and masked content classification.

Sorts every loaded skill into one or more user-owned workspaces in a right-sidebar tab: each workspace is its own category list plus where every skill sits, categories are created, renamed, reordered and deleted in place, and skills are dragged or picked between them. A first run can let the profile model build the first classification, or place skills into categories the user built first; clicking a row copies its /skill-name and hovering unfolds the description the skill ships.

Lightweight crash-recovery for dsh: after a restart, it detects sessions whose last turn was killed mid-flight and re-injects a continuation prompt that first demands the agent verify real-world state before acting, so side-effecting operations are not blindly repeated. It only reacts to the genuine crash marker (turn/end reason 'interrupted', synthesized on cold read by session repair), so it never misfires on user cancels, rate limits or model errors - which is why it needs no error classification, backoff or configuration UI. Unlike general-purpose auto-continue plugins, it also covers the case where a subagent was interrupted mid-run: the parent turn has already ended normally while it waits, so a naive check sees nothing to resume and the whole subagent tree dies silently; this plugin detects the interrupted child and wakes the parent instead. Single host file, zero external dependencies, seven config constants.

Grouped skill picker for the composer. A button beside the input box opens a panel that browses every installed skill by scene (research, office, data, writing, media, dev), with auto-classification for new skills, Chinese annotations, search and drill-down; picking one inserts the /skill-name gesture.

Zero-UI-overhead DeepSeek Harness plugin that automatically classifies conversation intents and names sessions with clean emoji prefixes (optimize, fix, feature, explore, etc.).

Replaces the chat model picker with a collapsible provider-grouped list (640x720 max) that shows each model name, provider name, provider ID and exact model ID, plus a manually managed uncommon list and a separate favorites list. Classification is user-driven only: no usage tracking and no auto-sorting. Search covers model name, model ID, provider name, provider ID and account notes.

Connects TypeSafe/Jev, Cloudflare/Clef, Nace/Drex, self-hosted Laya, and custom decision providers through one interface for agent and plugin classification, filtering, scoring, and image-object localization with structured results.

session_health for DeepSeek Harness — health intelligence (outcome classification, tool-health signals, prompt heuristics, context pressure, A–F grade) computed in-process from the session store, plus a standalone CLI over the same engine.

Auto-adjust model reasoning effort per task (off/low/high/max): task classification, \[effort=...] markers, in-turn error escalation, DeepSeek peak-pricing-period capping with countdown notices, and manual-selection priority.

Apple on-device Vision tools for text-only dsh models: local OCR (zh-Hans + 30 langs), image classification, face detection, document layout, and a combined describe — 100% offline, no API key, tall-screenshot slicing.

Cross-border commerce: HS codes, customs invoices, mainland reachability. HS/HTS code lookup and classification, commercial invoices, live exchange rates, IBAN and EAN/UPC checks, amount-in-English for documents, and whether your site is actually reachabl

Chemical safety intelligence through the hosted MSDS Chain MCP endpoint: 23 tools for compatibility and mixing order, GHS hazards, PPE, storage, waste disposal, exposure limits, transport classification, multi-region regulatory compliance, SDS lookup and version diffs, and signed audit reports, each answer citing the supplier SDS and revision date it is grounded in.