fix(billing): 修复 OpenAI fast 档位计费并补齐展示

- 打通 service_tier 在 OpenAI HTTP、WS、passthrough 与 usage 记录中的传递
- 修正 priority/flex 计费逻辑，并将 fast 归一化为 priority
- 在用户端和管理端补齐服务档位与计费明细展示
- 补齐前后端测试，并修复 WS 限流信号重复持久化导致的全量回归失败

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

backend/internal/service/openai_ws_v2_passthrough_adapter.go

@@ -77,6 +77,7 @@ func (s *OpenAIGatewayService) proxyResponsesWebSocketV2Passthrough(
 		return errors.New("token is empty")
 	}
 	requestModel := strings.TrimSpace(gjson.GetBytes(firstClientMessage, "model").String())
+	requestServiceTier := extractOpenAIServiceTierFromBody(firstClientMessage)
 	requestPreviousResponseID := strings.TrimSpace(gjson.GetBytes(firstClientMessage, "previous_response_id").String())
 	logOpenAIWSV2Passthrough(
 		"relay_start account_id=%d model=%s previous_response_id=%s first_message_type=%s first_message_bytes=%d",
@@ -178,6 +179,7 @@ func (s *OpenAIGatewayService) proxyResponsesWebSocketV2Passthrough(
 						CacheReadInputTokens:     turn.Usage.CacheReadInputTokens,
 					},
 					Model:           turn.RequestModel,
+					ServiceTier:     requestServiceTier,
 					Stream:          true,
 					OpenAIWSMode:    true,
 					ResponseHeaders: cloneHeader(handshakeHeaders),
@@ -225,6 +227,7 @@ func (s *OpenAIGatewayService) proxyResponsesWebSocketV2Passthrough(
 			CacheReadInputTokens:     relayResult.Usage.CacheReadInputTokens,
 		},
 		Model:           relayResult.RequestModel,
+		ServiceTier:     requestServiceTier,
 		Stream:          true,
 		OpenAIWSMode:    true,
 		ResponseHeaders: cloneHeader(handshakeHeaders),