feat(gateway): Codex/OpenAI Responses WebSocket 代理模式

在 /v1/responses 上支持 WebSocket 升级,把客户端帧中继到上游 Codex /
OpenAI Responses WebSocket 端点,同时保持既有的路由、鉴权、配额与用量
语义:

- 路由与准入:control/route/ai.rs 识别 WebSocket 升级请求;
  websocket/ingress.rs 复用 API Key 鉴权、IP 规则与并发许可,并引入
  独立的 WebSocket 连接许可
- 中继:websocket/responses/* 按 connection / session / turn 分层,
  帧解析归一化、socket 写入有界、continuation 保持调度亲和性
- 配额:orchestration/codex_quota_breaker.rs 在账号配额耗尽时熔断并
  自动恢复,不再直接断开客户端连接
- 用量:每个 turn 的终态用量落库,request_metadata 记录
  websocket_mode / websocket_transport,管理端与 usage 视图暴露
  is_websocket
- 管理端:provider 可配置 Responses WebSocket 开关
This commit is contained in:
AAEE86
2026-08-17 14:50:33 +08:00
committed by ZheFox
parent 9a0d346ff3
commit 71b54070e8
72 changed files with 10441 additions and 108 deletions
@@ -1216,6 +1216,7 @@ fn admin_usage_active_request_json(
"api_key_name": api_key_name,
"provider_key_name": provider_key_name,
"is_stream": item.is_stream,
"is_websocket": item.is_websocket(),
"upstream_is_stream": upstream_is_stream,
"client_requested_stream": client_is_stream,
"client_is_stream": client_is_stream,
@@ -1348,6 +1349,7 @@ pub fn admin_usage_record_json(
"end_to_end_first_byte_time_ms"
)),
);
object.insert("is_websocket".to_string(), json!(item.is_websocket()));
object.insert("is_stream".to_string(), json!(item.is_stream));
object.insert(
UPSTREAM_IS_STREAM_KEY.to_string(),
@@ -2697,6 +2699,30 @@ mod tests {
}
}
#[test]
fn admin_usage_payloads_expose_websocket_transport() {
let item = StoredRequestUsageAudit {
request_metadata: Some(json!({
"websocket_mode": true,
"websocket_transport": "responses",
})),
..sample_usage("completed", Some(200), None)
};
let record = admin_usage_record_json(
&item,
&BTreeMap::new(),
&BTreeMap::new(),
false,
false,
None,
);
let active = admin_usage_active_request_json(&item, None, None, None);
assert_eq!(record["is_websocket"], true);
assert_eq!(active["is_websocket"], true);
}
#[test]
fn admin_usage_record_infers_client_family_from_user_agent() {
let item = StoredRequestUsageAudit {