Plugins
Explora, filtra e instala plugins de DeepSeek-Harness.
122 plugins encontrados
dsh-think-any-lang
lco117/dsh-think-any-lang
Plugin de DeepSeek Harness (DSH): un selector de «idioma de razonamiento» en Ajustes → General que indica al modelo en qué idioma razonar (cadena de pensamiento) mediante una sección del system prompt. Sin llamadas adicionales, sin latencia extra, 12 idiomas.
dsh-thinking-slider
mufeng262/dsh-thinking-slider
Replaces the composer model selector with a "model · reasoning level" trigger that opens a card holding the model-switch entry and a gradient particle slider for changing reasoning effort, and shows the model name alone when a model reports no reasoning levels.
dsh-dynamic-thinking-chain
lovelydazai/dsh-dynamic-thinking-chain
Allows deepseek harness to think dynamically like human,automatically judge the difficulty of tasks with suitable thinking chain.
dsh-pixelwhale
lkrain821/dsh-pixelwhale
Pixel-font "deep seeking" thinking status with an animated DeepSeek blue whale (20 spout frames and 32 tail-wag frames).
dsh-model-router
neptune810/dsh-model-router
Keeps a pool of models and routes every agent step to one of them with its reasoning effort set — configured by clicking in the composer, no JSON needed. The router takes over the composer's model cell, so one control shows the session's model and reasoning effort alongside the router's own settings. Three authorization scopes (model / effort / full) where a manual pick only counts in the scope that owns it, and in effort scope the router is bound to the one model you choose. Task presets with per-model weights, vision routing for image steps, session signals (active todo, context pressure, token budget, subagent depth), and an optional semantic task classifier. Thinking stays on, because DeepSeek rejects a thinking-enabled request whose history contains a tool call made with thinking off.
dsh-bailian-models
croissantts/dsh-bailian-models
Alibaba Bailian (DashScope) model catalog preset + auto-adapter for DeepSeek Harness — reasoning effort levels, thinking budgets, context windows, auto-adaptation of existing Bailian routes, a configurable context ceiling
dsh-thinking-token-stat
six6strings/dsh-thinking-token-stat
A lightweight plugin that adds model thinking token statistics to the bottom Dock.
dsh-agent-lang
kannakuron/dsh-agent-lang
Three independent language channels for model output — tool-call descriptions (every tool-call card title, including run_code in PTC-style presets), thinking, and replies — each set to follow the web GUI language, force a specific language, or turn off (default: only descriptions, following the GUI). One global runtime-context prompt directive on the host; the client half reports the GUI language; a Settings plugin card switches the modes.
dsh-llm-openai-completions
drscrewdriver/dsh-llm-openai-completions
OpenAI-completions-compatible adapter for custom gateways (vLLM / LM Studio / self-hosted proxies): always role:"system", thinking driven by the model config, Qwen-style response split, and vision-model image input (single / multiple).
dsh-client-ui-thinking-stats
six6strings/dsh-client-ui-thinking-stats
A lightweight plugin that adds model thinking token statistics to the bottom Dock and the end of each conversation.
dsh-btw
wlv-zedd/dsh-btw
Interactive Side-Assistant Dock to ask quick side questions via /btw with real-time thinking status and history pagination without interrupting the active agent loop.
dsh-fetch-timeouts
d3vmeh/dsh-fetch-timeouts
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.
dsh-ask-in-sidebar
ruiming-cn/dsh-ask-in-sidebar
Ask a sidebar assistant about selected assistant text: an ephemeral right-side panel answers from a snapshot of the main conversation's LLM history with streaming Markdown, collapsible thinking and multi-turn follow-ups, without touching the main conversation.
dsh-feishu-channel
whoisjiahao/dsh-feishu-channel
Canal de Feishu/Lark que dirige agentes de DeepSeek Harness desde los chats: tarjetas enriquecidas en streaming con razonamiento en vivo y pasos de herramientas, medición del coste por turno con tarifas de DeepSeek en hora punta/fuera de punta, tarjetas de aprobación con un toque, entrada de imágenes restringida por modelo y alta mediante código QR sin endpoint público.
dsh-wrapped
rand0wn/dsh-wrapped
Registra /wrapped, que lee las estadísticas de la propia sesión y renderiza una tarjeta resumen en SVG oscuro para compartir: tiempo de herramientas frente a tiempo de razonamiento, velocidad de decodificación y un veredicto sobre la proporción herramienta/razonamiento.
dsh-gap-feed
faukwaa/dsh-gap-feed
Durante largos periodos de reflexión del agente, publica un mensaje de noticias de última hora o un recordatorio directamente en el flujo de la conversación.
dsh-deep-verbs
winter-and-you-gone/dsh-deep-verbs
Rota la línea de estado del modelo a través de un grupo de 53 frases en inglés/chino de temas profundos: selección aleatoria al inicio del turno, cambio basado en eventos ante nuevos segmentos de pensamiento o llamadas a herramientas (limitador de 3 s) y un clic en la línea de estado alterna el idioma.
dsh-plugin-dit
cuboteam/dsh-plugin-dit
Paquete de proveedor DIT.ai para DeepSeek Harness: instala 29 modelos OpenAI Chat Completions y 10 modelos Anthropic Messages desde una única DIT_API_KEY, con configuración de pensamiento específica del protocolo.
dsh-deepseek-pet
txlznbzsdj-collab/dsh-deepseek-pet
Mascota de escritorio animada de ballena azul DeepSeek flotando en la página web de DSH: arrastrable, con burbujas de diálogo y poses de ánimo, una herramienta pet_say para que el modelo la haga hablar, y estados de pensamiento y celebración al inicio/final de turno.
dsh-process-fold
uigdwunm/dsh-process-fold
Pliega el pensamiento, las llamadas a herramientas y el contexto de cada turno de DSH Web en cajas de proceso con borde, cortadas en cada fragmento de texto del modelo; una caja contraída muestra sus dos últimos elementos, las líneas apiladas sobre su borde abren esa caja, el propio borde la vuelve a plegar, y el diálogo del usuario, las preguntas interactivas y el texto del modelo quedan fuera.
dsh-pi-tui
lqhl/dsh-pi-tui
Interfaz frontal Pi TUI (framework de terminal con renderizado diferencial): markdown en streaming, colapso de pensamiento, tarjetas de herramientas, comandos de barra, superposiciones de aprobación/pregunta y almacén de sesión de dsh compartido.
dsh-plugin-thinking-mode
lovedheart/dsh-plugin-thinking-mode
Plugin de DeepSeek Harness: interruptor de modo de pensamiento por solicitud (enable_thinking) para los modelos de la familia Qwen3 en endpoints compatibles con OpenAI
dsh-radeon-cloud-patcher
zhz8888/dsh-radeon-cloud-patcher
Adds AMD Radeon Cloud as a model provider in DeepSeek Harness, with reasoning-effort levels declared per model. The provider definition ships in the plugin's own patch layer rather than in your profile.
dsh-model-control
uio-o/dsh-model-control
Replaces the composer model seat with a search-first picker and adds a model management page: create and edit llm-pi-ai channels, choose which of an endpoint's models exist, and declare per-model thinking ladders and capabilities.