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
+7 -6
View File
@@ -52,16 +52,17 @@ pub(crate) use self::planner::{
build_standard_family_sync_plan_and_reports, build_standard_stream_plan_from_decision,
build_standard_sync_plan_from_decision, candidate_auth_channel_skip_reason,
codex_model_capabilities_for_transport, extract_pool_sticky_session_token,
maybe_build_stream_decision_payload, maybe_build_stream_plan_payload,
maybe_build_sync_decision_payload, maybe_build_sync_plan_payload,
planner_is_matching_stream_request, provider_key_pool_score_id, provider_key_pool_score_scope,
read_candidate_transport_snapshot, record_local_runtime_candidate_skip_reason,
resolve_tunnel_scheduler_affinity_context, resolve_upstream_is_stream_for_provider,
set_local_openai_chat_execution_exhausted_diagnostic,
maybe_build_responses_websocket_decision, maybe_build_stream_decision_payload,
maybe_build_stream_plan_payload, maybe_build_sync_decision_payload,
maybe_build_sync_plan_payload, planner_is_matching_stream_request, provider_key_pool_score_id,
provider_key_pool_score_scope, read_candidate_transport_snapshot,
record_local_runtime_candidate_skip_reason, resolve_tunnel_scheduler_affinity_context,
resolve_upstream_is_stream_for_provider, set_local_openai_chat_execution_exhausted_diagnostic,
set_local_openai_image_execution_exhausted_diagnostic, validate_final_openai_provider_request,
CandidateFailureDiagnostic, CandidateFailureDiagnosticKind, EligibleLocalExecutionCandidate,
GatewayAuthApiKeySnapshot, GatewayProviderTransportSnapshot, LocalExecutionAttemptSource,
LocalExecutionCandidateKind, LocalResolvedOAuthRequestAuth, PlannerAppState,
ResponsesWebSocketBodyNormalization, ResponsesWebSocketDecision,
SkippedLocalExecutionCandidate,
};
pub(crate) use self::pure::*;