插件

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

Same-runtime cross-Session discovery and communication for DeepSeek Harness

The missing companion CLI for DeepSeek Harness (dsh): manage MCP servers with one command — add/list/remove/test with dry-run connection checks, plus one-shot import from Claude Code / Codex. Also mounts as a dsh plugin so the agent can manage MCP itself.

DeepSeek Harness plugin: live DeepSeek official service status (status.deepseek.com) in the sidebar — overall status, component statuses, incidents, and uptime.

Vision toolkit for DeepSeek Harness -- glance, ground, detect, crop CLI tools for text-only agents to understand images

DeepSeek-Harness 图像生成插件。申请 Yali AI API Key：https://api.yaliai.com/

MCP server manager for DeepSeek Harness: manage MCP servers from the Web settings page, stored globally in $DSH_HOME/mcp-servers.json, connected/disconnected at runtime.

DSH skin plugin: Alphacoders popular wallpapers as the DeepSeek Harness Web GUI background (gallery, search, local image upload, light/dark mask)

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

A dsh status plugin with host-plane and browser halves: harness runtime health (process, listener, API-key presence, memory, uptime, plugin inventory) as JSON plus server-pushed SSE alerts, surfaced as a header badge with an expanded panel in the Web UI

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.

/repro 导出最小可复现问题包：去 secret 的会话日志、失败命令与 git diff。

强制痛点检查：同一问题连续 2 个实验未收敛后注入三问、拦截非调查类工具调用直到答出、阻止同方向重试。

审批与选择方案的系统级桌面通知：通知显示所属工作区、点击跳转到对应工作区，多语言（简中/繁中/英文），附提示音。

定时 Agent：按 cron 计划运行 prompt，把摘要送到你已有的地方，内置重叠/漏跑/超时安全策略。

将 SVG 路径与关键帧参数编译成自包含的 Lottie JSON 动画文件。

全局知识库桥：kb_add/kb_search/kb_show/kb_timeline 读写与 Codex 共享的 D:\knowledge（格式逐字节兼容）。

Labnana image generation for DeepSeek Harness: text-to-image / image-to-image / precise editing (NanoBanana Pro, Gemini 3.1 Flash Image, GPT-Image-2, Wan2.7, Seedream).

Vision browser tool: drives real Chrome over CDP with browser-use and reads the page with deepseek-v4-flash-vision-exp, so canvas text, text baked into images and values in rendered charts are readable; returns JSON validated against a caller-supplied schema and reports per-run token cost.

Peak/valley billing dock and usage analytics: token/cost/model stats, trend and token-mix charts, latest-20-turns records, global time/session/model filters.

DSH plugin: safe auto-continue-once recovery for native continuable subagents that end with explicit max-tokens termination. No timers, no polling, no private APIs.

DeepSeek Harness 余额与开销插件：状态栏显示 DeepSeek/MiMo 余额与花费（本会话/本次活跃/最近一次/上次对话），逐请求按模型+峰谷时段计价，支持花费超线提醒（点击设置）

Image generation for DeepSeek Harness: a generate_image tool with pluggable providers — the FAL queue, any OpenAI-compatible images API, or a ChatGPT/Grok subscription with no API key at all. The picture is shown inline in the conversation; the model rece

A floating whale desktop pet for the DeepSeek Harness Web UI: 94 categorized animations, event-aware actions, custom uploads, click reactions, dragging and screen wandering.