Plugins

Floating translucent DeepSeek whale elf on the DSH page that opens a draggable, minimizable temporary chat window using the session model or a custom OpenAI-compatible endpoint, with real-time streaming.

Persona wardrobe for DeepSeek Harness: save multiple personas, apply them globally or per workspace, with a master switch, an adjustable API balance guard, and a lazy token-loving tired mode that speaks on the agent's behalf when quota runs out. Files-as-config, hot reload, zero dependencies.

Design mode for DeepSeek Harness: the design-loop agent preset plus design-principles and design-qa skill packs

Small file memory for DeepSeek Harness. The model writes markdown, the host injects it.

Prevent the computer from sleeping while Harness is running. Toggle at runtime through a model-facing tool.

Native DeepSeek Harness plugin for IsingQ guided QUBO modeling and solving

DeepSeek Harness status-light plugin: character expressions follow the model state, chat-bubble notifications, and a Windows always-on-top mini-window. 状态灯插件：角色表情跟随模型状态 + 聊天框气泡 + 系统级置顶小窗。

DSH web plugin: full-page static/video wallpaper with live opacity / blur / contrast sliders, glass-panel transparency controls, folder-loop rotation with cross-fade, model-select and permission-chip flowing-border styling. State persists to ~/.dsh/dsh-bg

Windows multi-bash plugin for dsh: git_bash / wsl_bash model tools plus a shell-select executor routing the single ctx.shell seat across Git Bash, WSL and pwsh (pwsh stays the default).

DSH 模型收藏插件:收藏的模型置顶显示、同名模型标注 provider、模型/推理等级双按钮、每模型 effort 记忆

Model-facing accurate_vision tool: precise image spatial reasoning via a vision model

DeepSeek Harness plugin with two default model-and-reasoning shortcuts above the composer and optional Settings customization.

Evidence-first multi-model coding comparison workbench for DeepSeek Harness

FriendliAI serverless LLM adapter for DeepSeek Harness — OpenAI-compatible chat completions with dynamic model discovery and reasoning support

Paste images into DeepSeek Harness chat and have them read by a free local backend (macOS Vision / Tesseract) before the text-only DeepSeek model answers

Workflow Studio for the DeepSeek Harness (dsh) - browse workflow sessions per project, manage workflow definitions, start sessions in workflow mode, and visualize run details.

A DeepSeek Harness plugin that mounts one subagent delegation tool per configured role and model, each bound to its own model provider route.

DSH plugin: connect to MCP servers, discover tools, and register them for direct model invocation with retry logic and statistics

Taints the agent when tool results carry untrusted content, gates the privileged calls that follow, and refuses credentials passed to network-capable tools in every mode.

Auto Mode for DSH: a flash-model router that auto-picks the best agent preset (standard/code/minimal/cordis) for each new session and executes immediately, no confirmation.

Per-project LLM token usage and RMB cost in the DSH Web sidebar, split by input (cache miss), cache hit, and output with model price auto-pricing.

One-click Windows/WSL2 environment switcher for DSH (coexistence mode): both environments run simultaneously on separate ports and switch from the web UI without killing any process.

Alternative WorkflowEngine provider for DSH 0.1.0-rc.7 that runs model-written orchestration in fresh QuickJS/WASM runtimes with a JSON-only host bridge and bounded memory, execution time, and child-agent fan-out.

Smart provider routing: composer-button one-click enable/disable, any channel error (including 4xx) auto-falls-back to the next channel, chain names shown in the model selector without exposing internal channels/models, multi-chain management with settings UI.