retry more capacity-style upstream failures
This commit is contained in:
@@ -9,7 +9,8 @@ tg群:https://t.me/AI_INPUT_IM
|
||||
- 保持 Codex 继续使用现有 `auth.json`
|
||||
- 只把 `config.toml` 的当前 provider `base_url` 改成本地网关
|
||||
- 非流式命中 `reasoning_tokens = 516` 时返回 `502`
|
||||
- 上游若返回明确的容量错误(默认匹配 `429/503` 且错误文案包含 `Selected model is at capacity. Please try a different model.`),也会转成本地 `502`
|
||||
- 上游若返回明确的容量错误(默认匹配错误文案 `Selected model is at capacity. Please try a different model.`),也会自动重试;重试耗尽后转成本地 `502`
|
||||
- 除了 `429/503` JSON 错误响应,也会识别 `200` 但返回体本质是错误、以及流式失败事件里携带同样文案的情况
|
||||
- 流式命中时默认先缓存并判断;一旦命中 `516`,统一返回 `502`
|
||||
- 默认同时拦截 root 路径和 `/v1` 路径:
|
||||
- `/responses`
|
||||
|
||||
Reference in New Issue
Block a user