Plugins

Adjuntos de imagen nativos para DeepSeek solo texto en la Web GUI: las imágenes pegadas o soltadas aparecen como miniaturas en la sesión y, antes del envío, el host las lee con la API de visión gratuita Zhipu GLM-4V-Flash (cadena de respaldo glm-4v-flash) y sustituye la descripción, de modo que DeepSeek responde sobre la imagen mientras el original se conserva en el historial.

Kit de visión para DeepSeek solo de texto: herramienta `vision` invocable por el modelo, adaptadores contenedores para deepseek/opencode-go (v4 flash/pro), cuota de Antigravity IDE (default, flash/pro) / cualquier VLM compatible con OpenAI / Gemini / canales locales de Ollama, memoria de evidencias con rehidratación por compactación, caché de hash de contenido y un panel de cliente bilingüe.

Herramienta `vision` invocable por el modelo para DeepSeek Harness: describe y aplica OCR a archivos de imagen llamando directamente a la API de visión gratuita Zhipu GLM (cadena de respaldo glm-4v-flash), sin necesidad de CLI externo.

Tell your deepseek-v4.1-flash: "shut up! Stop looping!"

DeepSeek Harness plugin: auto-route image-bearing requests to deepseek-v4-flash-vision-exp, then fall back to the original model.

Composer stats strip for the DSH Web UI: official CNY pricing with auto-synced peak/off-peak tiers, per-model accounting, live timers, subagent-tree merging, DeepSeek account balance, budget alerts, and streaming cost estimation.

Muestra el saldo de la API de DeepSeek y los costos de uso local de DSH Flash y Pro.

Notificación toast nativa de Windows y parpadeo de la barra de tareas para tarea completada, aprobación y ask_user_question; Win10/11, instalación con npm `dsh plugin --profile web add dsh-notify-win`.

Plugin experimental APEX para DeepSeek Harness: arranque anclado en Minimal, herramientas Standard bajo demanda, estado persistente de tareas e investigación dirigida con V4 Flash.

Herramienta image_describe (识图) orientada al modelo sobre la API compatible con OpenAI de DashScope (qwen3.7-flash), más un puente de pegado: en sesiones solo texto, las imágenes pegadas se convierten automáticamente en rutas de archivo al enviar y se vuelven a renderizar en la transcripción, para que nunca tropiecen con la admisión de imágenes. Trae tu propia DASHSCOPE_API_KEY; endpoint/modelo/presupuestos configurables, cliente HTTP a prueba de redirecciones y funciona en todos los agent presets.

Legal training workbench: three-pane academic UI that reads the "Minglü" (lawagent preset) learning profile (case dossiers, flashcards, wrong-answer book, notes) and sends instructions into a Minglü session with one click.

Shows a reminder card in the bottom-right corner of the DSH web GUI whenever the agent is waiting for your answer, and adds a desktop notification plus a flashing tab title when you are on another tab or window.

Maintained fork of feibi-mochi/deepseek-harness-control-center, which has not been updated since 2026-09-09. Pricing follows the official model pool instead of a hardcoded model prefix, so DeepSeek V4.1 Flash (`deepseek-flash`) is billed and shows its peak/off-peak clock, and the official price page is parsed structurally so a renamed or retired model no longer stops price sync. Adds an English interface beside the original Chinese. Otherwise the same plugin: balance, per-session cost and token breakdown, a 24-hour peak/off-peak clock, Z.ai plan quota, and a local usage ledger, following the host light/dark theme.

Quick Control panel for DSH Web: a docked or floating shortcut panel whose switches other plugins register through the quickControl service. Includes a theme and skin switcher plus fine-grained NO_PROXY proxy controls, and works with dock-base or standalone.

Sets the DeepSeek flash model's reasoning effort per step — thinking off for short cheap prompts, low for a plain request, high for engineering work — and raises it only on repeated tool failures. The model itself never changes; effort max is opt-in.

Quick-notes floating panel for dsh web: timestamped entries, clock, alarms with flashing reminder, API prices & balances, day/week/month/year grouping.

DeepSeek Harness 自动审批门控：Flash 模型预判写入/命令是否不可回补，安全自动批准、危险转人工（fail-safe），最小人工介入，含人工审查 UI

Reads AI replies aloud as they stream, with voiced waiting phrases while the model thinks. Edge TTS built in, any OpenAI-compatible cloud engine supported.

Vision bridge for text-only DeepSeek models: transcribes attached images with deepseek-v4-flash-vision-exp before they reach deepseek-v4-pro, with no third-party dependencies.

Twelve curated palettes, eight accent colours, a contrast slider and font/scale overrides for the DSH web UI, with an inlined first-paint script that prevents theme flash.

Auto-switch the DeepSeek route to the vision model on demand: flash main session switches (A), pro keeps deep reasoning and delegates image reading to a vision subagent (B), subagents always switch, with fatal-failure fallback. No manual model switching.

DeepSeek balance and per-session cost in the DSH web composer dock, with official peak/off-peak pricing (peak hours Mon-Fri BJT 9-12 / 14-18, weekends off-peak) and built-in deepseek-v4-flash-vision-exp vision model rates billed at flash price (images billed as tokens, max 384 tokens each).

DSH provider preset for the Memorax DeepSeek V4 Flash gateway

Self-contained vocabulary flashcards for DeepSeek Harness web sessions