插件

复用 DeepSeek 网页端识图模式给纯文本模型补上看图能力：deepseek_vision 工具调用本地 deepseek-vision-cli 浏览器自动化（手动登录助手、自动开启深度思考、用后自动关窗），把图片描述以文字返回给模型。

MuApi 媒体生成工具：muapi_generate 工具通过一个 x-api-key 提交并轮询 MuApi 100 多个图片、视频、音频与 3D 模型的生成任务。

把各提供方线上模型列表写进 DSH 设置，输入框圆环显示当前会话模型的 5 小时/7 天窗口或按量剩余余额。

给模型目录装上「图片输入」勾选框，自定义模型声明后可直接收图；附带可选的 BYO 视觉中继。

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

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

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.

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.

WeChat Mini Program automated testing for DeepSeek Harness (dsh): selector-addressed actions, build-freshness gates, geometry-first assertions that work on text-only models, and screenshot image blocks on vision routes. 微信小程序自动化测试 dsh 插件：选择器寻址、构建新鲜度门、面向纯文

Dynamic multimodal-to-text projection and cross-model vision bridge for DeepSeek Harness (dsh), allowing seamless hot-switching between vision models (Gemini/Claude) and text-only models (DeepSeek).

Cross-platform native desktop control tools for DeepSeek Harness (Windows first): screen_shot, screen_read (accessibility tree + pixel description for text-only models), click/type/scroll/key, and app_list/app_launch — every mutating action gated by appro

A DeepL-style translation surface for dsh: replaces the shell's root frame with a two-pane translator driven by a tool-less agent preset, keeping the shipped settings panel (models, providers, plugins) intact

Self-owned vision bridge for DeepSeek Harness: pick the vision model yourself from the available ones. Image content blocks are rewritten into text markers at the agent boundary so text-only models never fail a turn, and a describe_image tool answers via

A minimal Codex harness for GPT models that do not fit DSH's native interface, while remaining compatible with the DSH plugin ecosystem.

LLMTR AI gateway provider for the DeepSeek Harness LLM seam: 170+ chat models and Türkiye-hosted LLMs behind one OpenAI-compatible key

A minimal Codex harness for GPT models that do not fit DSH's native interface, while remaining compatible with the DSH plugin ecosystem.

Generic LLM gateway model provider plugin for DeepSeek Harness: mounts newapi / LiteLLM / Higress / any OpenAI-compatible gateway as provider routes, auto-discovers the model list, enriches every model with models.dev parameters, and dispatches each model

终端风 AI 实验室挂机游戏：攒算力、训练升级模型、发论文，一路转生到 AGI/ASI。

让纯文本模型拥有视觉：describe_image 工具调用 dsh 模型列表中的视觉模型描述图片，走 harness 自身的 LLM 运行时。

纯文本模型双层识图：优先本地快速 OCR（RapidOCR，离线），不足时回落视觉模型（modlens）。

为 DSH 纯文本模型补充视觉能力：识图技能（图片理解/OCR/文档解析，竞速池→自定义通道→本地）+ 幂等宿主补丁，让图片消息能送达模型侧。

为所有非官方（自定义）提供商的模型自动填充推理级别，数据来自 models.dev。

限流或配额耗尽时自动切换模型提供方：可按提供方配置模型，带冷却机制与永久最终兜底。

输入框右侧会话成本芯片：按官方价表（含 2026-08-17 峰谷价）逐消息计价当前会话的 DeepSeek API 花费，悬停查看计价明细、今日(DSH) 消耗与账户余额；仅 DeepSeek 模型计价，其他模型不计价不显示。