Custom OpenAI Responses relay does not append /v1 when fetching models

## English ### What happened When a custom OpenAI Responses-compatible relay is configured with a root URL such as: ```text http://relay.example:3000 ``` the connection test succeeds, but updating the model catalog fails. Maka requests: ```text GET /models ``` However, the relay provides the OpenAI-compatible model list at: ```text GET /v1/models ``` Cherry Studio works with the same configuration because it automatically appends `/v1` when the base URL does not contain an API version. OpenAI's standard endpoints are also versioned: ```text GET /v1/models POST /v1/responses ``` ### Expected behavior We should clarify whether the configured URL is a host root or a complete API base URL, and use the same URL normalization rule for model discovery and Responses requests. ### Environment - Maka: 0.1.11 - Surface: Desktop - OS: Windows --- ## 中文 ### 问题描述 配置自定义 OpenAI Responses 兼容中转站时，如果服务地址填写为根地址： ```text http://relay.example:3000 ``` 连接测试可以成功，但更新模型目录失败。 Maka 当前请求： ```text GET /models ``` 而该中转站的 OpenAI 兼容模型接口为： ```text GET /v1/models ``` 相同配置在 Cherry Studio 中可以使用，因为当地址不包含 API 版本时，它会自动补充 `/v1`。OpenAI 的标准接口也包含版本前缀： ```text GET /v1/models POST /v1/responses ``` ### 期望行为 需要明确配置地址表示主机根地址还是完整 API Base URL，并让模型发现和 Responses 请求使用一致的 URL 处理规则。 ### 环境 - Maka：0.1.11 - 使用端：Desktop - 系统：Windows