remove: drop support for claude-2 and claude-1 series models

- Remove claude-instant-1.2, claude-2, claude-2.0, claude-2.1 from model lists
- Remove /v1/complete endpoint support (legacy completion API)
- Remove RequestModeCompletion and related code paths
- Simplify handler functions by removing requestMode parameter
- Update all channel adaptors that referenced claude handlers

relay/channel/claude/relay-claude.go

@@ -41,37 +41,6 @@ func maybeMarkClaudeRefusal(c *gin.Context, stopReason string) {
 	}
 }
 
-func RequestOpenAI2ClaudeComplete(textRequest dto.GeneralOpenAIRequest) *dto.ClaudeRequest {
-
-	claudeRequest := dto.ClaudeRequest{
-		Model:         textRequest.Model,
-		Prompt:        "",
-		StopSequences: nil,
-		Temperature:   textRequest.Temperature,
-		TopP:          textRequest.TopP,
-		TopK:          textRequest.TopK,
-		Stream:        textRequest.Stream,
-	}
-	if claudeRequest.MaxTokensToSample == 0 {
-		claudeRequest.MaxTokensToSample = 4096
-	}
-	prompt := ""
-	for _, message := range textRequest.Messages {
-		if message.Role == "user" {
-			prompt += fmt.Sprintf("\n\nHuman: %s", message.StringContent())
-		} else if message.Role == "assistant" {
-			prompt += fmt.Sprintf("\n\nAssistant: %s", message.StringContent())
-		} else if message.Role == "system" {
-			if prompt == "" {
-				prompt = message.StringContent()
-			}
-		}
-	}
-	prompt += "\n\nAssistant:"
-	claudeRequest.Prompt = prompt
-	return &claudeRequest
-}
-
 func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRequest) (*dto.ClaudeRequest, error) {
 	claudeTools := make([]any, 0, len(textRequest.Tools))
 
@@ -411,7 +380,7 @@ func RequestOpenAI2ClaudeMessage(c *gin.Context, textRequest dto.GeneralOpenAIRe
 	return &claudeRequest, nil
 }
 
-func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse) *dto.ChatCompletionsStreamResponse {
+func StreamResponseClaude2OpenAI(claudeResponse *dto.ClaudeResponse) *dto.ChatCompletionsStreamResponse {
 	var response dto.ChatCompletionsStreamResponse
 	response.Object = "chat.completion.chunk"
 	response.Model = claudeResponse.Model
@@ -425,74 +394,66 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse
 		}
 	}
 	var choice dto.ChatCompletionsStreamResponseChoice
-	if reqMode == RequestModeCompletion {
-		choice.Delta.SetContentString(claudeResponse.Completion)
-		finishReason := stopReasonClaude2OpenAI(claudeResponse.StopReason)
-		if finishReason != "null" {
-			choice.FinishReason = &finishReason
+	if claudeResponse.Type == "message_start" {
+		if claudeResponse.Message != nil {
+			response.Id = claudeResponse.Message.Id
+			response.Model = claudeResponse.Message.Model
 		}
-	} else {
-		if claudeResponse.Type == "message_start" {
-			if claudeResponse.Message != nil {
-				response.Id = claudeResponse.Message.Id
-				response.Model = claudeResponse.Message.Model
+		//claudeUsage = &claudeResponse.Message.Usage
+		choice.Delta.SetContentString("")
+		choice.Delta.Role = "assistant"
+	} else if claudeResponse.Type == "content_block_start" {
+		if claudeResponse.ContentBlock != nil {
+			// 如果是文本块，尽可能发送首段文本（若存在）
+			if claudeResponse.ContentBlock.Type == "text" && claudeResponse.ContentBlock.Text != nil {
+				choice.Delta.SetContentString(*claudeResponse.ContentBlock.Text)
 			}
-			//claudeUsage = &claudeResponse.Message.Usage
-			choice.Delta.SetContentString("")
-			choice.Delta.Role = "assistant"
-		} else if claudeResponse.Type == "content_block_start" {
-			if claudeResponse.ContentBlock != nil {
-				// 如果是文本块，尽可能发送首段文本（若存在）
-				if claudeResponse.ContentBlock.Type == "text" && claudeResponse.ContentBlock.Text != nil {
-					choice.Delta.SetContentString(*claudeResponse.ContentBlock.Text)
-				}
-				if claudeResponse.ContentBlock.Type == "tool_use" {
-					tools = append(tools, dto.ToolCallResponse{
-						Index: common.GetPointer(fcIdx),
-						ID:    claudeResponse.ContentBlock.Id,
-						Type:  "function",
-						Function: dto.FunctionResponse{
-							Name:      claudeResponse.ContentBlock.Name,
-							Arguments: "",
-						},
-					})
-				}
-			} else {
-				return nil
+			if claudeResponse.ContentBlock.Type == "tool_use" {
+				tools = append(tools, dto.ToolCallResponse{
+					Index: common.GetPointer(fcIdx),
+					ID:    claudeResponse.ContentBlock.Id,
+					Type:  "function",
+					Function: dto.FunctionResponse{
+						Name:      claudeResponse.ContentBlock.Name,
+						Arguments: "",
+					},
+				})
 			}
-		} else if claudeResponse.Type == "content_block_delta" {
-			if claudeResponse.Delta != nil {
-				choice.Delta.Content = claudeResponse.Delta.Text
-				switch claudeResponse.Delta.Type {
-				case "input_json_delta":
-					tools = append(tools, dto.ToolCallResponse{
-						Type:  "function",
-						Index: common.GetPointer(fcIdx),
-						Function: dto.FunctionResponse{
-							Arguments: *claudeResponse.Delta.PartialJson,
-						},
-					})
-				case "signature_delta":
-					// 加密的不处理
-					signatureContent := "\n"
-					choice.Delta.ReasoningContent = &signatureContent
-				case "thinking_delta":
-					choice.Delta.ReasoningContent = claudeResponse.Delta.Thinking
-				}
-			}
-		} else if claudeResponse.Type == "message_delta" {
-			if claudeResponse.Delta != nil && claudeResponse.Delta.StopReason != nil {
-				finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
-				if finishReason != "null" {
-					choice.FinishReason = &finishReason
-				}
-			}
-			//claudeUsage = &claudeResponse.Usage
-		} else if claudeResponse.Type == "message_stop" {
-			return nil
 		} else {
 			return nil
 		}
+	} else if claudeResponse.Type == "content_block_delta" {
+		if claudeResponse.Delta != nil {
+			choice.Delta.Content = claudeResponse.Delta.Text
+			switch claudeResponse.Delta.Type {
+			case "input_json_delta":
+				tools = append(tools, dto.ToolCallResponse{
+					Type:  "function",
+					Index: common.GetPointer(fcIdx),
+					Function: dto.FunctionResponse{
+						Arguments: *claudeResponse.Delta.PartialJson,
+					},
+				})
+			case "signature_delta":
+				// 加密的不处理
+				signatureContent := "\n"
+				choice.Delta.ReasoningContent = &signatureContent
+			case "thinking_delta":
+				choice.Delta.ReasoningContent = claudeResponse.Delta.Thinking
+			}
+		}
+	} else if claudeResponse.Type == "message_delta" {
+		if claudeResponse.Delta != nil && claudeResponse.Delta.StopReason != nil {
+			finishReason := stopReasonClaude2OpenAI(*claudeResponse.Delta.StopReason)
+			if finishReason != "null" {
+				choice.FinishReason = &finishReason
+			}
+		}
+		//claudeUsage = &claudeResponse.Usage
+	} else if claudeResponse.Type == "message_stop" {
+		return nil
+	} else {
+		return nil
 	}
 	if len(tools) > 0 {
 		choice.Delta.Content = nil // compatible with other OpenAI derivative applications, like LobeOpenAICompatibleFactory ...
@@ -503,7 +464,7 @@ func StreamResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse
 	return &response
 }
 
-func ResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse) *dto.OpenAITextResponse {
+func ResponseClaude2OpenAI(claudeResponse *dto.ClaudeResponse) *dto.OpenAITextResponse {
 	choices := make([]dto.OpenAITextResponseChoice, 0)
 	fullTextResponse := dto.OpenAITextResponse{
 		Id:      fmt.Sprintf("chatcmpl-%s", common.GetUUID()),
@@ -521,39 +482,26 @@ func ResponseClaude2OpenAI(reqMode int, claudeResponse *dto.ClaudeResponse) *dto
 	tools := make([]dto.ToolCallResponse, 0)
 	thinkingContent := ""
 
-	if reqMode == RequestModeCompletion {
-		choice := dto.OpenAITextResponseChoice{
-			Index: 0,
-			Message: dto.Message{
-				Role:    "assistant",
-				Content: strings.TrimPrefix(claudeResponse.Completion, " "),
-				Name:    nil,
-			},
-			FinishReason: stopReasonClaude2OpenAI(claudeResponse.StopReason),
-		}
-		choices = append(choices, choice)
-	} else {
-		fullTextResponse.Id = claudeResponse.Id
-		for _, message := range claudeResponse.Content {
-			switch message.Type {
-			case "tool_use":
-				args, _ := json.Marshal(message.Input)
-				tools = append(tools, dto.ToolCallResponse{
-					ID:   message.Id,
-					Type: "function", // compatible with other OpenAI derivative applications
-					Function: dto.FunctionResponse{
-						Name:      message.Name,
-						Arguments: string(args),
-					},
-				})
-			case "thinking":
-				// 加密的不管， 只输出明文的推理过程
-				if message.Thinking != nil {
-					thinkingContent = *message.Thinking
-				}
-			case "text":
-				responseText = message.GetText()
+	fullTextResponse.Id = claudeResponse.Id
+	for _, message := range claudeResponse.Content {
+		switch message.Type {
+		case "tool_use":
+			args, _ := json.Marshal(message.Input)
+			tools = append(tools, dto.ToolCallResponse{
+				ID:   message.Id,
+				Type: "function", // compatible with other OpenAI derivative applications
+				Function: dto.FunctionResponse{
+					Name:      message.Name,
+					Arguments: string(args),
+				},
+			})
+		case "thinking":
+			// 加密的不管， 只输出明文的推理过程
+			if message.Thinking != nil {
+				thinkingContent = *message.Thinking
 			}
+		case "text":
+			responseText = message.GetText()
 		}
 	}
 	choice := dto.OpenAITextResponseChoice{
@@ -586,71 +534,67 @@ type ClaudeResponseInfo struct {
 	Done         bool
 }
 
-func FormatClaudeResponseInfo(requestMode int, claudeResponse *dto.ClaudeResponse, oaiResponse *dto.ChatCompletionsStreamResponse, claudeInfo *ClaudeResponseInfo) bool {
+func FormatClaudeResponseInfo(claudeResponse *dto.ClaudeResponse, oaiResponse *dto.ChatCompletionsStreamResponse, claudeInfo *ClaudeResponseInfo) bool {
 	if claudeInfo == nil {
 		return false
 	}
 	if claudeInfo.Usage == nil {
 		claudeInfo.Usage = &dto.Usage{}
 	}
-	if requestMode == RequestModeCompletion {
-		claudeInfo.ResponseText.WriteString(claudeResponse.Completion)
-	} else {
-		if claudeResponse.Type == "message_start" {
-			if claudeResponse.Message != nil {
-				claudeInfo.ResponseId = claudeResponse.Message.Id
-				claudeInfo.Model = claudeResponse.Message.Model
-			}
-
-			// message_start, 获取usage
-			if claudeResponse.Message != nil && claudeResponse.Message.Usage != nil {
-				claudeInfo.Usage.PromptTokens = claudeResponse.Message.Usage.InputTokens
-				claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Message.Usage.CacheReadInputTokens
-				claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Message.Usage.CacheCreationInputTokens
-				claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Message.Usage.GetCacheCreation5mTokens()
-				claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Message.Usage.GetCacheCreation1hTokens()
-				claudeInfo.Usage.CompletionTokens = claudeResponse.Message.Usage.OutputTokens
-			}
-		} else if claudeResponse.Type == "content_block_delta" {
-			if claudeResponse.Delta != nil {
-				if claudeResponse.Delta.Text != nil {
-					claudeInfo.ResponseText.WriteString(*claudeResponse.Delta.Text)
-				}
-				if claudeResponse.Delta.Thinking != nil {
-					claudeInfo.ResponseText.WriteString(*claudeResponse.Delta.Thinking)
-				}
-			}
-		} else if claudeResponse.Type == "message_delta" {
-			// 最终的usage获取
-			if claudeResponse.Usage != nil {
-				if claudeResponse.Usage.InputTokens > 0 {
-					// 不叠加，只取最新的
-					claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
-				}
-				if claudeResponse.Usage.CacheReadInputTokens > 0 {
-					claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
-				}
-				if claudeResponse.Usage.CacheCreationInputTokens > 0 {
-					claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
-				}
-				if cacheCreation5m := claudeResponse.Usage.GetCacheCreation5mTokens(); cacheCreation5m > 0 {
-					claudeInfo.Usage.ClaudeCacheCreation5mTokens = cacheCreation5m
-				}
-				if cacheCreation1h := claudeResponse.Usage.GetCacheCreation1hTokens(); cacheCreation1h > 0 {
-					claudeInfo.Usage.ClaudeCacheCreation1hTokens = cacheCreation1h
-				}
-				if claudeResponse.Usage.OutputTokens > 0 {
-					claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens
-				}
-				claudeInfo.Usage.TotalTokens = claudeInfo.Usage.PromptTokens + claudeInfo.Usage.CompletionTokens
-			}
-
-			// 判断是否完整
-			claudeInfo.Done = true
-		} else if claudeResponse.Type == "content_block_start" {
-		} else {
-			return false
+	if claudeResponse.Type == "message_start" {
+		if claudeResponse.Message != nil {
+			claudeInfo.ResponseId = claudeResponse.Message.Id
+			claudeInfo.Model = claudeResponse.Message.Model
 		}
+
+		// message_start, 获取usage
+		if claudeResponse.Message != nil && claudeResponse.Message.Usage != nil {
+			claudeInfo.Usage.PromptTokens = claudeResponse.Message.Usage.InputTokens
+			claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Message.Usage.CacheReadInputTokens
+			claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Message.Usage.CacheCreationInputTokens
+			claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Message.Usage.GetCacheCreation5mTokens()
+			claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Message.Usage.GetCacheCreation1hTokens()
+			claudeInfo.Usage.CompletionTokens = claudeResponse.Message.Usage.OutputTokens
+		}
+	} else if claudeResponse.Type == "content_block_delta" {
+		if claudeResponse.Delta != nil {
+			if claudeResponse.Delta.Text != nil {
+				claudeInfo.ResponseText.WriteString(*claudeResponse.Delta.Text)
+			}
+			if claudeResponse.Delta.Thinking != nil {
+				claudeInfo.ResponseText.WriteString(*claudeResponse.Delta.Thinking)
+			}
+		}
+	} else if claudeResponse.Type == "message_delta" {
+		// 最终的usage获取
+		if claudeResponse.Usage != nil {
+			if claudeResponse.Usage.InputTokens > 0 {
+				// 不叠加，只取最新的
+				claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
+			}
+			if claudeResponse.Usage.CacheReadInputTokens > 0 {
+				claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
+			}
+			if claudeResponse.Usage.CacheCreationInputTokens > 0 {
+				claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
+			}
+			if cacheCreation5m := claudeResponse.Usage.GetCacheCreation5mTokens(); cacheCreation5m > 0 {
+				claudeInfo.Usage.ClaudeCacheCreation5mTokens = cacheCreation5m
+			}
+			if cacheCreation1h := claudeResponse.Usage.GetCacheCreation1hTokens(); cacheCreation1h > 0 {
+				claudeInfo.Usage.ClaudeCacheCreation1hTokens = cacheCreation1h
+			}
+			if claudeResponse.Usage.OutputTokens > 0 {
+				claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens
+			}
+			claudeInfo.Usage.TotalTokens = claudeInfo.Usage.PromptTokens + claudeInfo.Usage.CompletionTokens
+		}
+
+		// 判断是否完整
+		claudeInfo.Done = true
+	} else if claudeResponse.Type == "content_block_start" {
+	} else {
+		return false
 	}
 	if oaiResponse != nil {
 		oaiResponse.Id = claudeInfo.ResponseId
@@ -660,7 +604,7 @@ func FormatClaudeResponseInfo(requestMode int, claudeResponse *dto.ClaudeRespons
 	return true
 }
 
-func HandleStreamResponseData(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, data string, requestMode int) *types.NewAPIError {
+func HandleStreamResponseData(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, data string) *types.NewAPIError {
 	var claudeResponse dto.ClaudeResponse
 	err := common.UnmarshalJsonStr(data, &claudeResponse)
 	if err != nil {
@@ -677,24 +621,19 @@ func HandleStreamResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 		maybeMarkClaudeRefusal(c, *claudeResponse.Delta.StopReason)
 	}
 	if info.RelayFormat == types.RelayFormatClaude {
-		FormatClaudeResponseInfo(requestMode, &claudeResponse, nil, claudeInfo)
+		FormatClaudeResponseInfo(&claudeResponse, nil, claudeInfo)
 
-		if requestMode == RequestModeCompletion {
-		} else {
-			if claudeResponse.Type == "message_start" {
-				// message_start, 获取usage
-				if claudeResponse.Message != nil {
-					info.UpstreamModelName = claudeResponse.Message.Model
-				}
-			} else if claudeResponse.Type == "content_block_delta" {
-			} else if claudeResponse.Type == "message_delta" {
+		if claudeResponse.Type == "message_start" {
+			// message_start, 获取usage
+			if claudeResponse.Message != nil {
+				info.UpstreamModelName = claudeResponse.Message.Model
 			}
 		}
 		helper.ClaudeChunkData(c, claudeResponse, data)
 	} else if info.RelayFormat == types.RelayFormatOpenAI {
-		response := StreamResponseClaude2OpenAI(requestMode, &claudeResponse)
+		response := StreamResponseClaude2OpenAI(&claudeResponse)
 
-		if !FormatClaudeResponseInfo(requestMode, &claudeResponse, response, claudeInfo) {
+		if !FormatClaudeResponseInfo(&claudeResponse, response, claudeInfo) {
 			return nil
 		}
 
@@ -706,20 +645,15 @@ func HandleStreamResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 	return nil
 }
 
-func HandleStreamFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, requestMode int) {
-
-	if requestMode == RequestModeCompletion {
-		claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, info.GetEstimatePromptTokens())
-	} else {
-		if claudeInfo.Usage.PromptTokens == 0 {
-			//上游出错
-		}
-		if claudeInfo.Usage.CompletionTokens == 0 || !claudeInfo.Done {
-			if common.DebugEnabled {
-				common.SysLog("claude response usage is not complete, maybe upstream error")
-			}
-			claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, claudeInfo.Usage.PromptTokens)
+func HandleStreamFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo) {
+	if claudeInfo.Usage.PromptTokens == 0 {
+		//上游出错
+	}
+	if claudeInfo.Usage.CompletionTokens == 0 || !claudeInfo.Done {
+		if common.DebugEnabled {
+			common.SysLog("claude response usage is not complete, maybe upstream error")
 		}
+		claudeInfo.Usage = service.ResponseText2Usage(c, claudeInfo.ResponseText.String(), info.UpstreamModelName, claudeInfo.Usage.PromptTokens)
 	}
 
 	if info.RelayFormat == types.RelayFormatClaude {
@@ -736,7 +670,7 @@ func HandleStreamFinalResponse(c *gin.Context, info *relaycommon.RelayInfo, clau
 	}
 }
 
-func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.Usage, *types.NewAPIError) {
+func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.Usage, *types.NewAPIError) {
 	claudeInfo := &ClaudeResponseInfo{
 		ResponseId:   helper.GetResponseID(c),
 		Created:      common.GetTimestamp(),
@@ -746,7 +680,7 @@ func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 	}
 	var err *types.NewAPIError
 	helper.StreamScannerHandler(c, resp, info, func(data string) bool {
-		err = HandleStreamResponseData(c, info, claudeInfo, data, requestMode)
+		err = HandleStreamResponseData(c, info, claudeInfo, data)
 		if err != nil {
 			return false
 		}
@@ -756,11 +690,11 @@ func ClaudeStreamHandler(c *gin.Context, resp *http.Response, info *relaycommon.
 		return nil, err
 	}
 
-	HandleStreamFinalResponse(c, info, claudeInfo, requestMode)
+	HandleStreamFinalResponse(c, info, claudeInfo)
 	return claudeInfo.Usage, nil
 }
 
-func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, httpResp *http.Response, data []byte, requestMode int) *types.NewAPIError {
+func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claudeInfo *ClaudeResponseInfo, httpResp *http.Response, data []byte) *types.NewAPIError {
 	var claudeResponse dto.ClaudeResponse
 	err := common.Unmarshal(data, &claudeResponse)
 	if err != nil {
@@ -770,26 +704,22 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 		return types.WithClaudeError(*claudeError, http.StatusInternalServerError)
 	}
 	maybeMarkClaudeRefusal(c, claudeResponse.StopReason)
-	if requestMode == RequestModeCompletion {
-		claudeInfo.Usage = service.ResponseText2Usage(c, claudeResponse.Completion, info.UpstreamModelName, info.GetEstimatePromptTokens())
-	} else {
-		if claudeInfo.Usage == nil {
-			claudeInfo.Usage = &dto.Usage{}
-		}
-		if claudeResponse.Usage != nil {
-			claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
-			claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens
-			claudeInfo.Usage.TotalTokens = claudeResponse.Usage.InputTokens + claudeResponse.Usage.OutputTokens
-			claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
-			claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
-			claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Usage.GetCacheCreation5mTokens()
-			claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Usage.GetCacheCreation1hTokens()
-		}
+	if claudeInfo.Usage == nil {
+		claudeInfo.Usage = &dto.Usage{}
+	}
+	if claudeResponse.Usage != nil {
+		claudeInfo.Usage.PromptTokens = claudeResponse.Usage.InputTokens
+		claudeInfo.Usage.CompletionTokens = claudeResponse.Usage.OutputTokens
+		claudeInfo.Usage.TotalTokens = claudeResponse.Usage.InputTokens + claudeResponse.Usage.OutputTokens
+		claudeInfo.Usage.PromptTokensDetails.CachedTokens = claudeResponse.Usage.CacheReadInputTokens
+		claudeInfo.Usage.PromptTokensDetails.CachedCreationTokens = claudeResponse.Usage.CacheCreationInputTokens
+		claudeInfo.Usage.ClaudeCacheCreation5mTokens = claudeResponse.Usage.GetCacheCreation5mTokens()
+		claudeInfo.Usage.ClaudeCacheCreation1hTokens = claudeResponse.Usage.GetCacheCreation1hTokens()
 	}
 	var responseData []byte
 	switch info.RelayFormat {
 	case types.RelayFormatOpenAI:
-		openaiResponse := ResponseClaude2OpenAI(requestMode, &claudeResponse)
+		openaiResponse := ResponseClaude2OpenAI(&claudeResponse)
 		openaiResponse.Usage = *claudeInfo.Usage
 		responseData, err = json.Marshal(openaiResponse)
 		if err != nil {
@@ -807,7 +737,7 @@ func HandleClaudeResponseData(c *gin.Context, info *relaycommon.RelayInfo, claud
 	return nil
 }
 
-func ClaudeHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo, requestMode int) (*dto.Usage, *types.NewAPIError) {
+func ClaudeHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.Usage, *types.NewAPIError) {
 	defer service.CloseResponseBodyGracefully(resp)
 
 	claudeInfo := &ClaudeResponseInfo{
@@ -824,7 +754,7 @@ func ClaudeHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayI
 	if common.DebugEnabled {
 		println("responseBody: ", string(responseBody))
 	}
-	handleErr := HandleClaudeResponseData(c, info, claudeInfo, resp, responseBody, requestMode)
+	handleErr := HandleClaudeResponseData(c, info, claudeInfo, resp, responseBody)
 	if handleErr != nil {
 		return nil, handleErr
 	}