流式请求中 client_gone 导致 New API 计费为 0，但上游已正常扣费且客户端收到完整响应

Deployment source

Repository release / official image (self-hosted)

Your current newapi version

v1.0.0-rc.25

Submission Checks

• Non-duplicate issue: I have searched existing Issues and confirmed there are no similar issues.
• Read this first: I have fully read the section above, reviewed the docs at https://docs.newapi.ai/ and the project README, and asked AI first, confirming this is not a usage, configuration, or integration question.
• Supported version: I have provided an exact version, commit, or image tag (not latest or unknown) and confirmed that the issue reproduces on an unmodified, supported version from this repository.
• Not a third-party service: I confirm that this issue is not exclusive to a third-party hosting site, relay, API service, or fork that has not been verified against the unmodified repository. Third-party instance issues must be reported to their operator.
• Issue attribution: I have provided evidence that distinguishes the client, new-api, and upstream layers. For relay issues, I compared equivalent redacted requests sent directly upstream and through new-api, confirming that new-api introduces or changes the error rather than merely forwarding the upstream error unchanged.
• Channel and protocol boundary: I confirm that the issue is not caused by a Coding Plan service, reverse-engineered channel, third-party API wrapper, Codex reverse-proxy endpoint, or behavior specific to the Codex API. If first observed through such an interface, I have reproduced it using a standard API protocol supported by this repository.
• Maintainer time: I understand that maintainers have limited time and issues that do not follow this template may be ignored or closed directly.

Issue Description

当流式请求（stream: true）在首字已成功返回给客户端后，因网络波动、客户端超时或用户主动取消等原因导致连接断开时，New API 记录 client_gone 并立即取消上游请求（终止向上游 Sub2API 的读取）。由于上游响应被中断，New API 无法获取最终的 usage 信息，便将本次请求标记为失败，退还预扣配额，因此消费记录中显示 费用为 $0，Tokens 为 0。
但上游 Sub2API 已经完整处理了该请求，生成了完整响应，并已按实际用量计费（可从 Sub2API 后台账单核对）。客户端在断开前通常已收到大部分甚至全部内容，导致用户认为服务已正常提供，而 New API 却显示未计费，造成账目不一致。

影响范围

• 财务对账困难：用户未在 New API 内扣费，但上游 Sub2API 实打实花了钱，需要人工逐一核对。
• 影响流式长回复场景，在网络不稳定的环境下触发频率较高。
• 从截图可见，多条请求 New API 显示 $0，而客户端显示了正数的 token 和费用。

发生频率
[请填写：例如"在响应长度超过500 tokens的流式请求中，约5%~10%出现此情况"]

证明问题出在 New API 层的证据

1. 直接上游对比：将相同请求直接发往 Sub2API（绕过 New API），使用同样的客户端，Sub2API 在完整处理后记录用量并扣费，其后台账单可查。
2. 经 New API 后：同样条件下，New API 日志出现 client_gone，上游被取消，消费记录显示 $0，relay 日志中无 usage 信息。
3. 客户端侧证据：截图显示客户端成功显示了每条请求的 token 数和费用，而 New API 列表却显示同样时间点的多条请求费用为 $0。

Steps to Reproduce

启动 New API v1.0.0-rc.25，配置 Sub2API 为上游渠道。 使用Codex客户端并使用gpt-5.6-sol模型进行开发到有较大上下文时new api后台概率出现0 token计费 同时查看sub2api可见正常扣费

Expected Result

当客户端在首字已返回后New API 不应立即取消上游请求，而应继续读取直到上游流正常结束，获取 usage 后按实际用量扣费；或设置合理超时（如 30 秒）后仍无 usage 再退款。这样消费记录才能与上游 Sub2API 账单保持一致。

Related Screenshots