Plugins

Provider-tabbed model picker for the dsh web composer: left provider column and right model list, both independently scrollable, with cross-provider search.

File-browser web app for DSH: React frontend and REST API served by the host webserver, a /dsh-agfs command that opens at the current session workspace, and a browse_files model tool.

Installs an image-input checkbox into the Models catalog so a custom model can declare image input and receive images directly; includes an optional BYO vision relay.

Adds a strip above the composer to recall sent-but-unread (steering) text messages before the model reads them.

PBR 3D model preview for game art: GLB/GLTF with textures, IBL environment lighting, orbit controls, and a material channel inspector (baseColor/normal/roughness/metallic/AO/emissive/wireframe); scalar channels shown as grayscale per PBR spec, via the pbr3d fence and pbr_render tool.

Focus mode with a full-screen reading overlay that hides the header and composer and folds AI tool calls into summaries.

Structured test runner tool (test_run): auto-detect Vitest/Jest/pytest/node:test, run tests, parse failure summaries for the model.

Pin assistant replies from the Web action strip and recall them into the next model turn (`/pin` `/recall`, with optional wake).

Capture every upstream model API payload to JSON (debug & observability).

DSH port of TaskPlane: dependency-ordered waves run in parallel git-worktree lanes, with task packets, cross-model review, and crash recovery.

Two-tier model router for DeepSeek Harness — LLM-Judge routing, multi-model fallback chains, exponential-backoff failover, and task-level orchestration (DSH adaptation of pi-shift-router)

view modes for deepseek harness, including Verbose, Normal, Summary Mode

deepseek harness manim数学插件

DeepSeek Harness plugin: per-request thinking-mode switch (enable_thinking) for Qwen3-family models on OpenAI-compatible endpoints

SearXNG-backed web search provider for the DeepSeek Harness web capability seam (ctx.web) — self-hosted metasearch, no API key, no model turn per search

Recurring/scheduled tasks (轮询任务/定时任务) plugin for DeepSeek Harness: cron-driven polling jobs as real sessions, natural-language creation, model tools (polling_create/list/edit/delete/trigger) and a web UI. Install-and-go via `dsh plugin add`.

DeepSeek usage monitor for DeepSeek Harness: account balance query and token usage summary as model-callable tools.

A DeepSeek Harness plugin: model-facing reload_plugin tool that restarts one Cordis Loader entry (by entry id, module name, or MCP serverName) without touching sibling entries — respawns mcp-client server processes

DeepSeek Harness plugin bundle: qwen_vision (Qwen-VL image understanding) and qwen_generate (Qwen-Image text-to-image) tools for text-only models

Inspect and manage the live instruction chain and project skills for the current dsh session, with in-place creation and editing — what you see is what the model gets

Request Context Profiler for DeepSeek Harness — see what changed between model requests, and how cache reuse changed with it.

DeepSee: DeepSeek Harness vision, multi-model routing, and Gemini visual self-checks before delivery

Plug-in vision for text-only DeepSeek Harness (dsh) models: a `vision` tool with built-in cheap/free VLM presets, multi-image batch analysis, paste-to-hint image admission, and a web settings page with hot-reload.

Browser Web Speech API voice input: zero server, zero keys, zero model downloads (Edge=Azure, Chrome=Google speech).