dsh-openai-gateway：把 DSH Agent 暴露为 OpenAI 兼容 API
dsh-openai-gateway 是 DSH 的插件，旨在将 DeepSeek Harness（DSH）Agent 暴露为标准的 OpenAI 兼容 API 服务端。该插件支持 `POST /v1/chat/completions`、`GET /v1/models` 等端点，每次调用背后均为带有工具和工作区的真实 DSH Agent 会话。用户只需安装插件并重启服务，即可通过配置 `base_url` 和 API key 使用任何 OpenAI 客户端进行接入。 插件默认监听本地回环地址端口 41540，提供无状态和粘性两种会话模式。粘性会话支持多轮连续任务，需通过特定头或字段维持会话 I
Read Moredsh-plugin-codex-bridge：将 OpenAI Codex 的 skills、instructions 和 configuration 接入 DeepSeek H
dsh-plugin-codex-bridge 是一款由 YYTbit 维护、基于 MIT 许可证的 DSH 插件，旨在解决 OpenAI Codex 本地文件难以复用的问题。该插件实现“零迁移”，通过将 Codex 的 skills、instructions 和 configuration 自动桥接至 DeepSeek Harness，避免用户手动搬运或调整分散的文件。具体功能包括：将 ~/.codex/skills 下的文件注入为可用技能，将 instructions.md 注入系统提示词，以及从 config.toml 注入模型上下文。用户可通过 dsh 命令在指定 profile 中安
Read Moredsh-draw-router：给 DeepSeek Harness 增加统一绘图路由
`dsh-draw-router` 是 DeepSeek Harness (DSH) 的统一绘图路由插件，旨在解决不同 OpenAI 兼容图像生成服务接口不一致的问题。该插件通过注册 `draw_image` 和 `draw_list_sources` 两个 Agent 工具，允许 DSH Agent 在对话中直接调用绘图功能，并支持自动发现可用图像模型，无需依赖固定模型清单。它兼容 SenseNova、StepFun、Qwen、Hunyuan 等多种提供商，配置时只需指定 API Root 即可自动适配路径。除 Agent 集成外，插件还提供 REST API 用于管理绘图来源及发起绘图请求
Read Moredeepseek-vl-support：为 DeepSeek 文本模型接入视觉的 DSH 插件
`deepseek-vl-support` 是一个 MIT 许可的插件，旨在解决 DeepSeek 文本模型无法直接读取图片的痛点。该插件通过拦截图片读取请求，将其发送至选定的 OpenAI 兼容视觉服务（如 OpenRouter、SiliconFlow、DashScope 等），并将返回的文字描述以固定格式回传给模型，从而实现图片理解。 该工具支持多种 Agent 环境，包括 Claude Code、Codex、DeepSeek Harness、Cursor、VS Code 等，并提供一次性安装向导、按 Agent 安装命令及 `doctor` 健康检查功能。用户只需具备 Node.js 1
Read Moredsh-polyglot: Providing OpenAI-Compatible Endpoint Switching and Automatic Fallback for DSH
dsh-polyglot is an MIT-licensed DSH plugin developed by Jesse-njx, designed to address challenges in DSH when invoking external models, including multi-endpoint management, unstable free quotas, and rate limiting. This plugin consolidates multiple OpenAI-compatible providers into a single virtual provider, `polyglot`, utilizing a universal adapter to handle streaming, tool calls, and usage extraction, while employing declarative configuration to accommodate variations across different services. At its core is an automatic fallback router that, upon encountering 429 rate limits, quota exhaustion, 5xx errors, or missing API keys, automatically switches to the next available provider in the chain, implementing exponential backoff and retry strategies for cooldown. The plugin maintains provider information through JSON preset files and records the service source, status, and token usage for each request in session logs.
Read Moredsh-llm-newapi: Adding NewAPI Provider to DeepSeek Harness
dsh-llm-newapi is an LLM Provider plugin based on the MIT license, designed to add a NewAPI provider to DeepSeek Harness (dsh), enabling integration with OpenAI-compatible gateways without any code modifications. The plugin implements the `LlmAdapter` interface, utilizes the `POST /chat/completions` and `GET /models` endpoints to provide model services, and automatically filters out models that only support chat functionality. Users can install the plugin via npm or GitHub, and need to add the package name to the `bundles` array in the dsh web configuration, then restart the service. The API Key is not read from environment variables and must be configured through the settings page of dsh web.
Read MoreAdd DeepSeek V4 protocol adaptation for OpenAI client using deepseek-harness
HenryZ838978-maintained deepseek-harness provides protocol-aware adaptation for DeepSeek V4-Pro / V4-Flash, recording 16 protocol features, 10 contracts and 12 probes. This article verifies the access methods including pip, dsh CLI, MCP and SKILL.md, as well as precautions such as reasoning_content 400, prefix caching and the same-name conflict with the official dsh, based on the community directory and GitHub README.
Read More