dsh-model-sync:把推理端模型列表自动写进 DSH 设置

dsh-model-sync 是 mpetruc 维护的 DSH 模型推理类插件(v0.7.1,MIT)。它通过 llm 服务的 discoverModels,把各 llm-pi-ai provider 公布的模型镜像到 Settings → Models,减少手填 model id。激活或 Plugins 页重开 model-sync 约 1.5 s 后同步;可配置 intervalMinutes 与 prune,并用 owner 标记区分手填与自动项。同步摘要写入 lastSync 并在插件卡片展示;rejected 状态存于 storages/model-sync/state.json。endpoint 异常时跳过并告警,不拖垮整插件。

Read More
dsh-model-sync: Automatic Synchronization of DeepSeek Harness Model Catalog

`dsh-model-sync` is an automation plugin for DeepSeek Harness, built around an "everything is a plugin" philosophy to eliminate the burden of manually maintaining model configurations. Maintained by GooDAnDReaDY, it can connect to 25+ upstream providers to automatically discover model lists, context windows, and pricing information, and supports quota monitoring, smart virtual aliases, and fallback chain management. It supports numerous platforms, including OpenAI, Anthropic, Groq, and Ollama, with audit logging. Installation requires Node.js 20+, and the plugin runs under DSH process permissions. It is ideal for administrators who need to efficiently manage multi-provider model catalogs.

Read More
dsh-model-sync: Integrate the latest model lists and quota readings from all Providers into DSH.

# Introduction If you use multiple providers—such as openai-codex, kimi-coding, and deepseek-official—simultaneously in DSH, you have likely encountered two issues: first, when a provider releases a new model, you have to manually add the model ID to `llm-pi-ai.providers.<id>.models` by referencing the documentation; and second, the quotas are scattered across different provider consoles, requiring you to switch pages to check how much remains in the 5-hour window or if your pay-as-you-go balance is sufficient. dsh-model-sync brings these two tasks into the DSH settings page: one page to synchronize the model list, one page to monitor quotas, and a ring indicator next to the input box that updates based on the current session model. Below, we introduce its features, installation, and usage.

Read More