gateway-config：DSH 智能体网关配置插件
`gateway-config` 插件旨在通过可视化和命令行工具，简化 DeepSeek Harness (DSH) 生态中 LLM 网关的配置。它支持通过 `GET /models` 接口自动发现模型，管理 API Key，并映射推理能力。该插件提供 Web 设置面板和 Host 工具，支持 OpenAI 兼容网关及原生 ChatGPT OAuth 登录。安装后需在配置文件中添加条目并重启。所有凭据由 DSH 本地管理，安全性高，适用于管理各类私有或公共网关。
Read MoreDeepSeek Harness Thinking Loop Guard Plugin: dsh-loop-guard
`mrweicodes/dsh-loop-guard` is a plugin that resolves the “thinking-only, no-action” infinite loop in DeepSeek Harness agents. Through a five-layer detection mechanism, it accurately identifies pure reasoning loops or repeated spamming, directly interrupts calls within the stream, and injects corrective prompts. The plugin does not interrupt the session, supports offline analysis, has a very low false positive rate, and requires DSH version 0.1.2 or higher. After installation, automatic resumption can be configured for unattended operation.
Read MoreIntroducing the DeepSeek Harness Plugin: dsh-llm-provider
`dsh-llm-provider` is the LLM provider plugin for DeepSeek Harness (DSH), designed to address issues such as delayed updates to built-in entries, lack of quota visibility, and limited selection flexibility. The plugin takes over the relevant entries and provides a self-maintained pi-ai bridge, a visual model selector, quota querying, and provider management. After installation, a process restart is required for it to take effect, and it currently supports only the Chinese interface.
Read Moredsh-cooldown-retry: Upstream 429 Cooldown Wait and Fault-Tolerant Retries for DeepSeek Harness
dsh-cooldown-retry is a plugin for DeepSeek Harness that addresses the issue where, when a shared gateway returns a 429 error, the built-in mechanism only falls back to local backoff, causing requests to fail. It provides a more patient automatic retry mechanism by reading delay hints such as `retry_after_seconds` from the response body. In addition, the plugin can absorb 400 errors incorrectly labeled as “audio modality not supported,” manage retry budgets, and perform cancellation-aware waiting. After installation, the plugin entry should be configured after the `llm-retry` entry, and it supports customizing parameters such as the maximum retry count and delay window to improve workflow availability in unstable gateway environments.
Read Moredsh-llm-balance: Display API balances of each LLM provider under the DSH chat input box.
dsh-llm-balance is by JonyChan839
Read More