Plugins

Reanuda automáticamente las solicitudes interrumpidas de DSH Web: envía un «继续» (continuar) en cola tras fallos de red, tiempo de espera o caída del host, con clasificación de errores, backoff adaptativo, texto de continuación con plantillas y notificaciones del navegador.

Convierte artículos de DSH en diagramas Excalidraw de sesión: diagram_create, edición con guardado automático, exportación PNG/SVG/.excalidraw y lectura con diagram_read. 0.6 añade resumen editable e índice para árboles grandes de tres niveles.

Guardia y monitor de concurrencia para DeepSeek Harness: cola FIFO cuando las solicitudes concurrentes de modelos alcanzan el límite, estadísticas persistidas por día con clasificación por tipo de error, y detección de interrupciones para transmisiones abandonadas.

Caja de herramientas de visión mejorada: 14 herramientas de visión a nivel de píxel (describe, ground, detect, crop, pixel-diff, OCR, OCR de captura larga, vectorize, colors, cutout, screenshot, present, materialize, html-screenshot) impulsadas por un endpoint compatible con OpenAI, con marcadores de puente limpios [图片: path], clasificación de seguridad de contenido y auto-retry por límite de tasa.

Plugin de predicción bursátil bayesiana que fusiona MACD, RSI, medias móviles, volumen y otras señales técnicas en una probabilidad posterior de subida con comparación multihorizonte, clasificación del estado de tendencia y métricas de riesgo de posición para acciones A y de EE. UU.

Memoria por proyecto de DeepSeek Harness: en el primer paso de cada sesión del workspace crea PROJECT.md, DECISIONS.md y SESSIONS.md; los relee del disco y solo reinyecta si cambian o la compactación los elimina. memory_checkpoint guarda datos clasificados; aviso final limitado si hubo trabajo sin registrar. memory_read lee el log y el archivo; memory_search busca con BM25 sin dependencias. Tope 200 entradas: excedente a SESSIONS-archive.md, nunca inyectado, pero consultable, buscable y restaurable uno a uno. Ajustes: filtro workspace/ruta, vistas solo lectura, recarga, JSON importar/exportar por workspace, borrado en dos pasos, editar/quitar bloque AGENTS.md y aviso PROJECT.md obsoleto. Chip de sync; clic crea archivos. Sin dependencias, vectores, embeddings ni llamadas al 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.

Ordena la navegación de ajustes de DSH: agrupa las entradas de plugins de terceros bajo filas de grupo plegables, con grupos personalizados estilo marcador, un interruptor de plegado y clasificación automática (etiquetas del mercado → reglas de nombre → tu modelo de IA).

Enrutamiento adaptativo de modelos: clasificación de complejidad por solicitud con enrutamiento automático de proveedores.

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.