- Gemini stream: 捕获 promptFeedback.blockReason 后停止流并返回 OpenAPI 错误
- OpenAI stream: 检测 SSE 帧中的 error 响应，在首帧写入前转换为 API 错误
- Responses stream: 处理 response.error / response.failed / error 类型帧
- 新增 ClearEventStreamHeadersIfNotWritten 工具方法，错误转换时清除流式头
- 新增 streamOpenAIErrorFromData，从 SSE data 帧提取 OpenAPI 错误结构
- 上游错误体会截断后存入 UpstreamBody 供排障

Co-Authored-By: Claude <noreply@anthropic.com>

gpt-5.4 returns `arguments` as a JSON object for some tools (e.g.
apply_patch, tool_search), but ResponsesOutput.Arguments was typed as
string, causing json.Unmarshal to fail on every such SSE event.

The failure silently dropped all output_item events and the
response.completed event from the forwarded stream, so:
- the client never received tool call content
- usage/token counts could not be extracted (billed as 0)
- client reported "stream closed before response.completed"

Fix: change Arguments to json.RawMessage and add GetArguments() which
normalises both forms to a plain string (unescapes JSON strings,
returns raw bytes for objects).

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

- Claude 和 OpenAI Responses 转发中设置 RelayChatID
- 日志查询使用 URLSearchParams 替代手动字符串拼接
- 日志查询日期范围改为可选，不再强制默认今天

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

- 前端用户列表：synced 用户显式取 synced_quota 字段作为剩余额度
- 各 OpenAI handler 中记录 relayChatID 用于日志追踪

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

- 提取 TruncateBody 公共函数，截断到 2KB 避免日志过大
- 新增 handleResponsesStreamError 统一 SSE 错误提取逻辑
- 流式/非流式 Responses API 错误路径均捕获 UpstreamBody
- 添加 upstream_body 和 truncate_body 单元测试

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>