Plugins

DSH plugin: auto-fill metadata (context length, output cap, display name, input modalities) for custom-provider models from the Model Metadata Registry (models.dev).

Terminal front door for DeepSeek Harness (dsh): an out-of-tree TUI mode bundle over dsh-base

Health checks for DSH plugins: manifest/patch/entry/build/pack/install verification, model-callable plugin_check, profile host-shadowing + BOM detection, environment diagnostics, and poison preflight.

Continual self-refinement loop: persistent memory, periodic review-and-refine, cross-session shared knowledge, and automatic rollback through a model-callable harness_refine tool.

Desktop notifications for run completion, model questions, and approval requests with per-platform system sounds, zero runtime dependencies.

Task board for DSH: create tasks with project and model assignment, run them manually or on cron schedules; new sessions in a project automatically pick up its todo tasks and move them to in-review when done.

MiniMax-powered multimodal plugin: real-time voice call mode (streaming conversation, floating dock UI), voice mode and mic voice input, plus image/video/music/speech generation and vision inspection tools.

Zero-dependency browser control: drive a real headless Edge/Chrome over CDP with 8 `pilot_*` tools (navigate/click/type/keys/eval/screenshot) plus a live draggable cockpit panel in the Web GUI - text-first snapshots for text-only models, no Playwright, no API key.

Optimize a raw instruction into a professional prompt through the harness llm service — four-section (Role / Task / Context / Format) or a headerless plain-text style. Context-aware by default: the recent conversation is injected as background and may enrich the ## Context section. Long outputs resume from the truncation point with auto-expanded budgets; validated results are cached (identical requests cost zero model calls); a unified call budget bounds worst-case cost. Composer ✨ one-click optimize, undo, cancel and a token-cost hint; prompt_optimize tool (optimize + iterate), auto-optimize hook, auto-detected zh/en role document.

Dedicated model routes, tools, and system guidance for vision, compaction, reviews, subagents, titles, and image generation.

Learning Mode agent preset: a coding agent that teaches while coding — concrete scenario-grounded explanations, Socratic guidance, and TODO(你) practice blanks, modeled on Claude Code's Learning output style; installable via dsh plugin add (dsh-learning-mode on npm).

Knowledge-base-driven agent preset: wiki long-term memory, a web KB UI, a management page and optional UI polish.

In-place conversation rewind in the same session window without forking (Claude Code /rewind semantics): a per-message ↶ button cuts the model context back to any user message, with an optional Claude-Code-style file restore from disk-persisted before-backups.

Codex App Server model provider using a local Codex login, with session reuse, Harness tool bridging, native action traces, and durable generated-image projection.

Simulates a Codex environment for selected model routes to improve GPT-family model tool-call success.

Use third-party subscription accounts in DeepSeek Harness: chat, image understanding, image generation, and image editing with the models your subscription covers, with available models and reasoning levels synced from your account; currently supports OpenAI/ChatGPT subscriptions, more providers planned.

Two-tier model routing: a strong tier plans, advises and reviews while a cheap tier implements, with plan-mode-aware auto routing, a high-impact escalation guard, failure auto-escalation, and subagent tiering.

Usage tiers and shareable stats cards: 🐟→🐳 ranks by monthly token burn with a locally-computed estimated percentile, precise pricing for 46 models across 6 vendors (including size-tiered Chinese pricing), backfill of pre-install sessions, and old-vs-new comparison across the 2026-08-17 rate change. Local-only, no telemetry.

Telemetría de ejecución sin intervención para DSH: cada sesión escribe automáticamente tarea, nivel de modelo, herramientas, fallos, duración y estado en un diario legible con una sección de estadísticas (puro observador: sin herramientas, sin llamadas a LLM, sin inyección).

Usa un Codex App Server local como proveedor de modelo en DeepSeek Harness

Un plugin de dsh que permite a la IA invocar automáticamente VLM (modelos multimodales) para el análisis visual.

Sidecar de visión gratuito y alojado para DeepSeek Harness, con evidencia de sesión duradera

Un HUD en la esquina para DeepSeek Harness que muestra de un vistazo la presión de tokens de tu sesión, el coste por modelo y el uso diario/mensual, con un presupuesto y saldo editables que registran tu gasto.

Proveedor de LLM de DeepSeek Harness para modelos Codex usando OAuth gestionado de ChatGPT