Plugins

Tickets entre escritorios para sesiones de una misma máquina. Una sesión indica su escritorio con un prefijo numérico en el título; cada ticket nombra un escritorio y lo toma la primera sesión de ese escritorio que empieza a trabajar. La dirección es el escritorio, por lo que no se entrega a una sesión que solo está de paso.

Prompt optimizer for the composer: a button in the tool row rewrites your draft through a model channel you already configured, streaming into a panel that floats above the composer without taking up layout. Your draft changes only when you click Accept — and Accept is refused while the answer is still streaming, so a half-finished reply can never be written back. It asks first when the draft carries @ references or attachments, which a whole-draft replace would flatten into plain text. No global keyboard shortcuts, and no API key ever reaches the browser: the host half makes the call.

A project-scoped memory plugin for DSH. Knowledge authoring and the plugin's own prompts are open to editing, so users can redesign the library structure and how the model is driven without changing a line of code. By default the library is built on one core idea: a project document you design yourself (a handoff by default) is the project entity; the plugin detects which project a session belongs to, binds captured knowledge to that project, and promotes what generalizes into theme and global layers. The most natural logic there is does the pre-filtering of knowledge, with controllable compression and archiving of context.

Model attribution panel for the dsh web chat — local, zero-network structural fingerprinting (template token leaks, glitch canaries, tokenizer usage-vector matching) that scores which of 29 AI vendors a session's responses most resemble, with a per-claim evidence ledger and a 12-probe active battery.

Panel de química para DSH Web. Dibuja estructuras en Ketcher; un script descarga la compilación y el navegador las renderiza localmente, sin backend. RDKit calcula la molécula actual sin llamar al modelo: fórmula, masas, logP, TPSA, donantes/aceptores de enlaces H, anillos, Fsp3, centros estereogénicos, reglas Lipinski y Veber, QED, alertas PAINS/BRENK y esqueleto Murcko, además de búsqueda SMARTS, similitud, conversión, estandarización y limpieza por lotes. La pestaña de retrosíntesis usa un backend intercambiable (Retro* por defecto) mediante un proceso JSON de entrada/salida y señala lo que falta si no está instalado, sin inventar rutas. Los cálculos los realiza el paquete Python del repositorio (rdkit), que se instala aparte con pip.

Herramientas de skills bajo demanda para DeepSeek Harness: skill_search / skill_load / skill_ref permiten buscar primero una biblioteca escalonada y cargar el contenido solo cuando hace falta, sin dejarla en el catálogo residente ni en cada turno del contexto. La pestaña Skills revisa toda la sesión y enumera qué skills se cargaron y en qué turno. Sin dependencias; los registros se dibujan solo en el cliente y nunca entran al contexto del modelo.

Security-audit facts AI coding agents cannot compute, plus a verdict gate: euthyna history attributes deleted lines to commits and flags those from security fixes (--origins finds the first introducer), euthyna coverage reports which changed symbols no test ever invoked, and euthyna gate checks each finding against six gates, downgrading any without evidence to an observation.

Añade Explain a la tarjeta de aprobación: una llamada al modelo devuelve exactamente tres líneas sobre la operación pendiente, los archivos o estado que lee/escribe/modifica/ejecuta y un veredicto riesgo/atención/seguro con una frase de justificación. También muestra detalles de llamadas write y edit, que el renderizador deja vacíos al leer solo el campo command.

Permisos de archivos para llamadas de shell por ruta y capacidad, no por nombre de comando. Analiza la línea de comandos para detectar lectura, escritura, creación, borrado y ejecución necesarios; si falta capacidad, muestra una tarjeta de aprobación en vez de rechazar sin más. Compila las mismas reglas en el perfil macOS Seatbelt para el proceso, sus hijos y el código oculto en sus argumentos. La pestaña Approvals muestra el registro de auditoría e indica si cada llamada la respondió una regla, el revisor automático o una persona.

Skill de actualización para autores de plugins de DeepSeek Harness. Incluye un índice que detecta la banda peer del usuario y lo dirige a la tarjeta closed corridor correspondiente (0.1.3-alpha.1→0.1.5-rc.1, tramos A+B; 0.1.5-rc.2→0.1.6-alpha.2, tramo C), además de un escáner de límites sin dependencias como skill y CLI npx.

Alcance MCP por workspace para DeepSeek Harness — decide qué servidores MCP puede ver una sesión según el directorio en el que se abrió.

Informa de la actividad de las sesiones de DeepSeek Harness a un servidor cc-monitor autoalojado, que muestra las sesiones de Claude Code y DSH como tarjetas de estado con código de color en un único panel web, y avisa a tu navegador y a tu app de Android cuando una sesión necesita atención.

Entrada de voz lista para China para el compositor. Requiere un puente local en Python (pip install dashscope websockets, ejecutar bridge/voice-bridge.py); el plugin por sí solo no funciona. El micrófono del navegador transmite PCM de 16 kHz al puente, que ejecuta Alibaba Cloud DashScope ASR (paraformer-realtime-v2); el texto intermedio rellena el borrador en el cursor, parada automática por silencio y envío automático opcional.

Un interrupt button verde junto a la caja de envío: detiene en silencio un agente en ejecución, que luego resume su progreso y pide tus nuevos requisitos, con un interrupt prompt personalizable.

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.

Recursive delegation for dsh agent trees: a preset plus Host limits bound what each subagent may do, subagents work in separate _agents/ workspaces, and the parent decides which results to integrate.

Keeps a DeepSeek Harness run going on its own: continues a turn that ended abnormally, and continues a turn logged as completed while the model tool call was emitted as plain text instead, which leaves the agent silently idle. Revives a model request that stops streaming. A wait on an approval or on a question is logged and notified, never answered.

Union web search for DSH (consolidated successor of DDDMUC/dsh-free-search, which it credits): 28 engines across three tiers — keyless free (Bing/DuckDuckGo/AnySearch/SearXNG multi-instance union, plus Exa/Tavily/Keenable/Firecrawl/Parallel keyless modes), paid-with-key (Zhihu/Perplexity/Serply/DeepSeek official/You.com/Baidu/Kimi/Aliyun/Doubao/Zhipu/Bocha/Metaso), and model built-in search (OpenAI/Gemini/Claude/Grok, explicit opt-in only) — with auto smart routing, per-engine enable/disable & fallback priority, parallel top-3 merge, multi_search, failure-aware fallback, a toggle to block the system built-in search, time filtering, platform search, web_fetch and a web settings UI. Experimental free advance_fetch: whole-page GFM-Markdown or CSS-selector/fields structured extraction with no API key and no per-call billing; fetch identity configurable (custom User-Agent, Referer, per-domain cookies attached only on domain match, never leaked across cross-domain redirects). Hosts 0.1.0-rc.2 through 0.2.1-rc.2 (17-tag exact engines.dsh enum; the rc.2 search-provider takeover goes through volatile config pinning after capability probing, never version branches). Paid engines need your own API keys (optional; free engines work keyless). npm: @drscrewdriver/dsh-union-search and bare dsh-union-search.

One settings page for every MCP server on your machine. It reads the real config file of 17 other AI tools (Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, OpenCode, Trae, Trae CN, Qoder, Gemini CLI, Qwen, Zed, Roo Code, Copilot CLI, Kiro, CodeBuddy, Continue) plus DeepSeek Harness itself, groups servers by the file that declares them, probes each one over JSON-RPC to see whether it starts and which tools it exposes, and gives every server a switch that mounts or unmounts it in DeepSeek Harness without editing the other tools' own files.

Read-only assessment of whether a Dameng DM8 database can be recovered and to which point (LSN or time), across 16 recovery scenarios, with an HTML report. Needs Java 8+ and a Dameng JDBC driver jar (DmJdbcDriver8.jar) that you provide yourself.

Adds job-role prompts to the DSH composer: type - at the start of the input to pick a role, which becomes a reference chip in the draft and is then injected as a system prompt section on every turn of that conversation, so the instruction keeps applying without showing up in the transcript. Roles are added and edited on a Settings page and stored in ~/.dsh/dsh-role-prompts.md.

Predicts your next message after each completed turn and shows it as ghost text in the composer: press → to accept, or keep typing and finish it word by word with Ctrl+→, Esc to dismiss. The prediction model follows the session by default or can be picked in the settings card, which also has an on/off switch and a speed test.

Keeps quotes out of the message body: quoting any passage from an assistant turn opens an editable quote tray above the composer, the quotes are injected into the next turn as system-prompt context (attributed with source and time), and an expandable quote row under that turn shows exactly which quotes were used. Quotes persist across page reloads and are claimed per turn; the host and client halves hand-shake on version and report a compatibility verdict.

Publishes whichever model the profile has selected in chat or on the Models page as an OpenAI-compatible HTTP endpoint: /v1/models, /v1/chat/completions (streaming SSE and non-streaming), /health. A request may name any routable model; one that omits `model` gets the current chat selection, so switching model in chat switches the endpoint. Switched on, it can also lend the model the Harness tools switched on individually, run those calls through the Harness tool runtime and feed results back up to a round limit. The listener is the plugin's own, so 127.0.0.1, 0.0.0.0 and a NAT-forwarded port all behave the same with no change to the request path. Settings cover bind address, port, API key with a generator, fallback provider and model, reasoning effort, CORS origin and timeout.