Plugins

Mini-juego de tiempo de espera con cuadrícula Schulte dinámica: haz clic en 1..N en orden sobre una cuadrícula estática o una ruleta giratoria mientras el modelo piensa.

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.

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

Moves reasoning that a provider leaks into the visible text channel back into the reasoning channel, and emits a text block when a whole turn of answer text lands only in the reasoning channel. Catches three shapes: `<thinking>`-tagged text, text that continues a reasoning tail which ended mid-token, and an answer-only reasoning turn that stops. Healthy streams pass through unchanged, block order is preserved, and each of the four rules can be switched off in one JSON config.

Qwen mode for DSH: manages local GenieX and Alibaba Cloud QwenCloud providers, normalizes thinking and sampling, detects model capabilities, and shows per-turn latency and decode speed. Its bundle patch replaces the permission plugin's preset table with reply-only, read-only, workspace-write and danger-full-access (the last two as in stock), so any custom presets are overridden.

Connect a locally installed agy CLI to DeepSeek Harness 0.2.2-rc.1, with separate thinking levels, quota display, and Harness-owned tools. Community fork of dannndouglas/dsh-antigravity-acp, beta, verified on Windows x64 only. Needs the agy CLI signed in with your own Google account; installing makes new chats default to Agy models (messages go through agy to Google), switches web search to the agy provider and replaces the built-in compaction. Do not enable it alongside other forks that register the agy-local-acp provider.

The row that is running expands itself and folds back when it settles. A running turn keeps its whole procedure in one height-capped window that scrolls itself; a finished turn merges into the built-in finished header, leaving only the final answer. It works by driving the official disclosure rows rather than drawing its own panel, leaves rows you opened by hand alone, and restores the official settings on uninstall.

Delivers one required user-role runtime context that makes the agent reason in Simplified Chinese and keep a whale-loli in-thinking persona (calls itself 本鱼, lazy-arrogant tone) in both reasoning and the final reply, while proper nouns, identifiers, paths, commands, URLs and error text stay verbatim; persona, extra proper nouns and context order are configurable. Enabled by default for every agent in the profile, subagents included.

Imports chats captured from chat.deepseek.com by the repo's companion Edge extension (loaded unpacked in Edge) into DeepSeek Harness as new sessions; thinking is saved as a sidecar thinking.md, and trimmed, branched or very long chats also get the full transcript.md.

Per-turn reasoning-effort routing that keeps the current provider/model: judges each user message (retry or correction, explicit intent, length, code blocks, errors, task scope) and sets reasoningEffort to a level the model actually declares, so Magpie and other OpenAI-compatible models work too. Ships a composer chip with an auto/manual switch and per-session decision history.

Replaces the composer model picker with a model + thinking-effort picker and an Auto level; Auto scores each turn by how far the conversation has drifted from the main objective and by repeated failures (one extra small judge call per turn), picks the effort from that score, and labels every finished turn with the effort it sent.

Turns scattered thinking notes into a growing constellation of themes, claims, relations and open questions, plus a written synthesis of the argument.

Injects a Chinese-thinking reminder around the system prompt and the per-step runtime snapshot, so the agent reasons in Simplified Chinese instead of drifting back to English as the transcript grows.

Replaces the composer Effort switch with a Claude Desktop-style five-level slider (Low/Medium/High/Max/Ultracode): a pill opens a popover above the composer, dragging snaps with a spring and writes once, and Ultracode maps to the model's maximum reasoning effort. Ships the Ultracode WebGL2 energy grid, a per-session Ultracode mode, and passes modifier-click through to the shipped level list.

Proveedor de SAP AI Core con OAuth compartido, cinco opciones de modelos Qwen, presupuestos de razonamiento, streaming y llamadas a herramientas; validado en cn40.

[LLM] Permite que DSH sincronice las modalidades de entrada y el nivel de razonamiento desde el upstream de magpie.

Plugin para DeepSeek Harness: indica a cada agente que redacte su razonamiento privado en chino simplificado.

Slider del composer inspirado en Claude Desktop para ajustar el esfuerzo de razonamiento del modelo con clic, arrastre o teclado.

Paquete Windows x64 con el runtime ACP oficial de Antigravity incluido. Delega tareas de texto de una sola ejecución con autenticación, modelo y nivel de pensamiento seleccionables. Usa host peers para Harness >=0.2.1-rc.3 <0.2.2-0, incluidas las RC posteriores de 0.2.1 y la versión estable 0.2.1.

El historial del composer restaura todo el estado de entrada: contenido, adjuntos de imagen/archivo, referencias @ y comandos slash, además del modelo, esfuerzo de razonamiento, permiso y preset de agente usados.

Menú de tres puntos en el encabezado de sesión: descarga el log, cambia cada transcripción entre Normal y Verbose y define qué expande Verbose (bloques de razonamiento, llamadas a herramientas y salida del terminal).

Proveedor de modelos Cohere para DSH: usa por defecto el protocolo compatible con OpenAI y el canal nativo v2 de Cohere para citas/RAG/presupuesto de razonamiento. Adaptador directo, sin proxy.

Interfaz DSH monocroma y serena con acentos lavanda, animaciones de inicio y cambio, workspace de pensamiento, skills con ámbito y conexiones locales opcionales de voz y mascota.