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

apps/aether-gateway/src/ai_serving/planner/standard/mod.rs

@@ -42,13 +42,14 @@ pub(crate) use self::openai::{
     build_local_openai_responses_sync_attempt_source_for_kind,
     build_local_openai_responses_sync_plan_and_reports_for_kind, copy_request_number_field,
     copy_request_number_field_as, map_openai_reasoning_effort_to_claude_output,
-    map_openai_reasoning_effort_to_gemini_budget, maybe_build_stream_local_decision_payload,
+    map_openai_reasoning_effort_to_gemini_budget, maybe_build_responses_websocket_decision,
+    maybe_build_stream_local_decision_payload,
     maybe_build_stream_local_openai_responses_decision_payload,
     maybe_build_sync_local_decision_payload,
     maybe_build_sync_local_openai_embedding_decision_payload,
     maybe_build_sync_local_openai_responses_decision_payload, parse_openai_stop_sequences,
     resolve_openai_chat_max_tokens, set_local_openai_chat_execution_exhausted_diagnostic,
-    value_as_u64,
+    value_as_u64, ResponsesWebSocketBodyNormalization, ResponsesWebSocketDecision,
 };
 pub(crate) use crate::ai_serving::normalize_standard_request_to_openai_chat_request;
 pub(crate) use crate::ai_serving::{