Plugins

88API Image Studio for DSH: four Image2 and Nano Banana models for text-to-image, multi-reference editing, 2K/4K output, and sequential batches.

Windows computer-use capability for DeepSeek Harness: screenshot → vision model → simulated mouse/keyboard input, with self-evolving knowledge base.

DeepSeek Harness 的 MCP 服务管理器：在 设置 → 插件 → MCP 标签页中发现 GitHub 上的 MCP 服务仓库（topic:mcp-server / modelcontextprotocol），探测 npm / PyPI 发布状态与 README 启动线索，详情查看后一键安装 / 移除。服务以 @deepseek-ai/dsh-mcp-client 行登记进 cordis.patch.yml，HMR 热重载，无需重启。支持 GitHub 代理。

The `debug` tool for DeepSeek Harness — a model-facing Debug Adapter Protocol tool with 28 operations (launch/attach, breakpoints, continue/pause/step, threads/stackTrace/scopes/variables/evaluate, disassembly, memory, modules, output, terminate) over the

LLM compatibility auto-healer: detects 400 errors from incorrectly declared model capabilities (thinking/reasoning) on transit/gateway providers, then idempotently patches `llm-pi-ai` config and suppresses thinking on the next request — no restart needed. Full settings UI for every pi-ai compat field.

LiteLLM /v1/search-backed web search provider for the DeepSeek Harness web capability seam (ctx.web). One search is one HTTP request — no model turn.

DeepSeek Harness plugin for Readproof: stable readproof:// identity, freshness policy, snapshots, per-run manifests, diff, byte-exact replay, and evidence bundles as model-callable tools.

LLM-as-a-Verifier for dsh with the Best-of-N conversation mode built in: rank N candidates with a fine-grained verifier (expected grade over the logprob distribution), on demand via the verify tool or automatically on every turn of a Best-of-N session. In

Browser Web Speech dictation for the Composer: recognition needs no dedicated ASR server, key, or model download; reuses Session text and a configured DSH model for contextual phrase hints and optional transcript polishing.

Runs one coding prompt across multiple configured models in isolated Git worktrees, streams side-by-side tool traces and results, and commits the candidate the user adopts for later rounds.

Use OpenCode models inside DeepSeek Harness without a separate provider API key.

Rate-limit plugin for DeepSeek Harness: FIFO queue per provider/model bucket with minIntervalMs and maxConcurrent

Switch DSH between localhost (127.0.0.1) and LAN (0.0.0.0) bind from the Settings page (LAN access off by default), with a crypto.randomUUID polyfill for non-secure LAN origins.

DeepSeek Harness web plugin for model usage, balance quota, and daily token display

领域建模：主动构建并打磨项目的领域模型（CONTEXT.md 术语表 + ADR 决策记录），挑战模糊术语、推敲边界场景。受 mattpocock/skills（223k★ MIT）启发。

Organize DSH sidebar sessions by configurable last-updated activity groups with attention-first sorting and Focus mode.

DSH Tool Router — deterministically shrink model-visible tool schemas per step with a safe fallback

Host-anchored provider, authentication, catalog, policy, and model-selection extension for DeepSeek Harness.

Let text-only models see images in DeepSeek Harness: intercepts the llm/stream waterfall and transparently substitutes each image with a vision model's description.

DeepSeek Harness plugin: creates a Windows desktop shortcut that launches dsh web in a Chrome app-mode window (auto-detects Chrome, waits for the port, no duplicate windows).

Lightweight, route-preserving vision link for DSH: a configured vision model sees while the selected text model stays in control.

Configure model input capabilities and reasoning efforts for DeepSeek Harness

New API OAuth provider, account configuration, model discovery, and model adapter for DeepSeek Harness

Local eyes for text-only models: eyes_render draws text/shapes/Mermaid onto a canvas in the Web GUI, eyes_paste captures pasted images, eyes_ocr reads text via the built-in Windows OCR (offline), and eyes_analyze inspects pixels as structured data — no vision model required.