fix: remove ClaudeMax references not yet in upstream/main

Remove SimulateClaudeMaxEnabled field and related logic from
admin_service.go, and remove applyClaudeMaxCacheBillingPolicyToUsage,
applyClaudeMaxNonStreamingRewrite, setupClaudeMaxStreamingHook calls
from antigravity_gateway_service.go. These symbols are not yet
available in upstream/main.

backend/internal/service/admin_service.go

@@ -145,8 +145,7 @@ type CreateGroupInput struct {
 	// 模型路由配置（仅 anthropic 平台使用）
 	ModelRouting             map[string][]int64
 	ModelRoutingEnabled      bool // 是否启用模型路由
-	MCPXMLInject             *bool
-	SimulateClaudeMaxEnabled *bool
+	MCPXMLInject *bool
 	// 支持的模型系列（仅 antigravity 平台使用）
 	SupportedModelScopes []string
 	// Sora 存储配额
@@ -185,8 +184,7 @@ type UpdateGroupInput struct {
 	// 模型路由配置（仅 anthropic 平台使用）
 	ModelRouting             map[string][]int64
 	ModelRoutingEnabled      *bool // 是否启用模型路由
-	MCPXMLInject             *bool
-	SimulateClaudeMaxEnabled *bool
+	MCPXMLInject *bool
 	// 支持的模型系列（仅 antigravity 平台使用）
 	SupportedModelScopes *[]string
 	// Sora 存储配额
@@ -870,13 +868,6 @@ func (s *adminServiceImpl) CreateGroup(ctx context.Context, input *CreateGroupIn
 	if input.MCPXMLInject != nil {
 		mcpXMLInject = *input.MCPXMLInject
 	}
-	simulateClaudeMaxEnabled := false
-	if input.SimulateClaudeMaxEnabled != nil {
-		if platform != PlatformAnthropic && *input.SimulateClaudeMaxEnabled {
-			return nil, fmt.Errorf("simulate_claude_max_enabled only supported for anthropic groups")
-		}
-		simulateClaudeMaxEnabled = *input.SimulateClaudeMaxEnabled
-	}
 
 	// 如果指定了复制账号的源分组，先获取账号 ID 列表
 	var accountIDsToCopy []int64
@@ -933,7 +924,6 @@ func (s *adminServiceImpl) CreateGroup(ctx context.Context, input *CreateGroupIn
 		FallbackGroupIDOnInvalidRequest: fallbackOnInvalidRequest,
 		ModelRouting:                    input.ModelRouting,
 		MCPXMLInject:                    mcpXMLInject,
-		SimulateClaudeMaxEnabled:        simulateClaudeMaxEnabled,
 		SupportedModelScopes:            input.SupportedModelScopes,
 		SoraStorageQuotaBytes:           input.SoraStorageQuotaBytes,
 		AllowMessagesDispatch:           input.AllowMessagesDispatch,
@@ -1140,15 +1130,6 @@ func (s *adminServiceImpl) UpdateGroup(ctx context.Context, id int64, input *Upd
 	if input.MCPXMLInject != nil {
 		group.MCPXMLInject = *input.MCPXMLInject
 	}
-	if input.SimulateClaudeMaxEnabled != nil {
-		if group.Platform != PlatformAnthropic && *input.SimulateClaudeMaxEnabled {
-			return nil, fmt.Errorf("simulate_claude_max_enabled only supported for anthropic groups")
-		}
-		group.SimulateClaudeMaxEnabled = *input.SimulateClaudeMaxEnabled
-	}
-	if group.Platform != PlatformAnthropic {
-		group.SimulateClaudeMaxEnabled = false
-	}
 
 	// 支持的模型系列（仅 antigravity 平台使用）
 	if input.SupportedModelScopes != nil {

backend/internal/service/antigravity_gateway_service.go

@@ -1719,7 +1719,7 @@ func (s *AntigravityGatewayService) Forward(ctx context.Context, c *gin.Context,
 	var clientDisconnect bool
 	if claudeReq.Stream {
 		// 客户端要求流式，直接透传转换
-		streamRes, err := s.handleClaudeStreamingResponse(c, resp, startTime, originalModel, account.ID)
+		streamRes, err := s.handleClaudeStreamingResponse(c, resp, startTime, originalModel)
 		if err != nil {
 			logger.LegacyPrintf("service.antigravity_gateway", "%s status=stream_error error=%v", prefix, err)
 			return nil, err
@@ -1729,7 +1729,7 @@ func (s *AntigravityGatewayService) Forward(ctx context.Context, c *gin.Context,
 		clientDisconnect = streamRes.clientDisconnect
 	} else {
 		// 客户端要求非流式，收集流式响应后转换返回
-		streamRes, err := s.handleClaudeStreamToNonStreaming(c, resp, startTime, originalModel, account.ID)
+		streamRes, err := s.handleClaudeStreamToNonStreaming(c, resp, startTime, originalModel)
 		if err != nil {
 			logger.LegacyPrintf("service.antigravity_gateway", "%s status=stream_collect_error error=%v", prefix, err)
 			return nil, err
@@ -1738,9 +1738,6 @@ func (s *AntigravityGatewayService) Forward(ctx context.Context, c *gin.Context,
 		firstTokenMs = streamRes.firstTokenMs
 	}
 
-	// Claude Max cache billing: 同步 ForwardResult.Usage 与客户端响应体一致
-	applyClaudeMaxCacheBillingPolicyToUsage(usage, parsedRequestFromGinContext(c), claudeMaxGroupFromGinContext(c), originalModel, account.ID)
-
 	return &ForwardResult{
 		RequestID:        requestID,
 		Usage:            *usage,
@@ -3644,7 +3641,7 @@ func (s *AntigravityGatewayService) writeGoogleError(c *gin.Context, status int,
 
 // handleClaudeStreamToNonStreaming 收集上游流式响应，转换为 Claude 非流式格式返回
 // 用于处理客户端非流式请求但上游只支持流式的情况
-func (s *AntigravityGatewayService) handleClaudeStreamToNonStreaming(c *gin.Context, resp *http.Response, startTime time.Time, originalModel string, accountID int64) (*antigravityStreamResult, error) {
+func (s *AntigravityGatewayService) handleClaudeStreamToNonStreaming(c *gin.Context, resp *http.Response, startTime time.Time, originalModel string) (*antigravityStreamResult, error) {
 	scanner := bufio.NewScanner(resp.Body)
 	maxLineSize := defaultMaxLineSize
 	if s.settingService.cfg != nil && s.settingService.cfg.Gateway.MaxLineSize > 0 {
@@ -3802,9 +3799,6 @@ returnResponse:
 		return nil, s.writeClaudeError(c, http.StatusBadGateway, "upstream_error", "Failed to parse upstream response")
 	}
 
-	// Claude Max cache billing simulation (non-streaming)
-	claudeResp = applyClaudeMaxNonStreamingRewrite(c, claudeResp, agUsage, originalModel, accountID)
-
 	c.Data(http.StatusOK, "application/json", claudeResp)
 
 	// 转换为 service.ClaudeUsage
@@ -3819,7 +3813,7 @@ returnResponse:
 }
 
 // handleClaudeStreamingResponse 处理 Claude 流式响应（Gemini SSE → Claude SSE 转换）
-func (s *AntigravityGatewayService) handleClaudeStreamingResponse(c *gin.Context, resp *http.Response, startTime time.Time, originalModel string, accountID int64) (*antigravityStreamResult, error) {
+func (s *AntigravityGatewayService) handleClaudeStreamingResponse(c *gin.Context, resp *http.Response, startTime time.Time, originalModel string) (*antigravityStreamResult, error) {
 	c.Header("Content-Type", "text/event-stream")
 	c.Header("Cache-Control", "no-cache")
 	c.Header("Connection", "keep-alive")
@@ -3832,8 +3826,6 @@ func (s *AntigravityGatewayService) handleClaudeStreamingResponse(c *gin.Context
 	}
 
 	processor := antigravity.NewStreamingProcessor(originalModel)
-	setupClaudeMaxStreamingHook(c, processor, originalModel, accountID)
-
 	var firstTokenMs *int
 	// 使用 Scanner 并限制单行大小，避免 ReadString 无上限导致 OOM
 	scanner := bufio.NewScanner(resp.Body)