fix: 使用openai兼容接口调用部分渠道在最终端点为claude原生端点下还是走了openai扣减input_token的逻辑

relay/channel/ali/adaptor.go

@@ -223,11 +223,8 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	switch info.RelayFormat {
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
 	case types.RelayFormatClaude:
 		if supportsAliAnthropicMessages(info.UpstreamModelName) {
 		if supportsAliAnthropicMessages(info.UpstreamModelName) {
-			if info.IsStream {
-				return claude.ClaudeStreamHandler(c, resp, info)
-			}
-
-			return claude.ClaudeHandler(c, resp, info)
+			adaptor := claude.Adaptor{}
+			return adaptor.DoResponse(c, resp, info)
 		}
 		}
 
 
 		adaptor := openai.Adaptor{}
 		adaptor := openai.Adaptor{}

relay/channel/claude/adaptor.go

@@ -95,6 +95,7 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 }
 }
 
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	info.FinalRequestRelayFormat = types.RelayFormatClaude
 	if info.IsStream {
 	if info.IsStream {
 		return ClaudeStreamHandler(c, resp, info)
 		return ClaudeStreamHandler(c, resp, info)
 	} else {
 	} else {

relay/channel/codex/adaptor.go

@@ -26,7 +26,7 @@ func (a *Adaptor) ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayIn
 }
 }
 
 
 func (a *Adaptor) ConvertClaudeRequest(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
 func (a *Adaptor) ConvertClaudeRequest(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
-	return nil, errors.New("codex channel: endpoint not supported")
+	return nil, errors.New("codex channel: /v1/messages endpoint not supported")
 }
 }
 
 
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
 func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
@@ -41,15 +41,15 @@ func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
 }
 }
 
 
 func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
 func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
-	return nil, errors.New("codex channel: endpoint not supported")
+	return nil, errors.New("codex channel: /v1/chat/completions endpoint not supported")
 }
 }
 
 
 func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
 func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
-	return nil, errors.New("codex channel: endpoint not supported")
+	return nil, errors.New("codex channel: /v1/rerank endpoint not supported")
 }
 }
 
 
 func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
 func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
-	return nil, errors.New("codex channel: endpoint not supported")
+	return nil, errors.New("codex channel: /v1/embeddings endpoint not supported")
 }
 }
 
 
 func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
 func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {

relay/channel/deepseek/adaptor.go

@@ -95,11 +95,8 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 	switch info.RelayFormat {
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
 	case types.RelayFormatClaude:
-		if info.IsStream {
-			return claude.ClaudeStreamHandler(c, resp, info)
-		} else {
-			return claude.ClaudeHandler(c, resp, info)
-		}
+		adaptor := claude.Adaptor{}
+		return adaptor.DoResponse(c, resp, info)
 	default:
 	default:
 		adaptor := openai.Adaptor{}
 		adaptor := openai.Adaptor{}
 		return adaptor.DoResponse(c, resp, info)
 		return adaptor.DoResponse(c, resp, info)

relay/channel/moonshot/adaptor.go

@@ -102,11 +102,8 @@ func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.Rela
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 	switch info.RelayFormat {
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
 	case types.RelayFormatClaude:
-		if info.IsStream {
-			return claude.ClaudeStreamHandler(c, resp, info)
-		} else {
-			return claude.ClaudeHandler(c, resp, info)
-		}
+		adaptor := claude.Adaptor{}
+		return adaptor.DoResponse(c, resp, info)
 	default:
 	default:
 		adaptor := openai.Adaptor{}
 		adaptor := openai.Adaptor{}
 		return adaptor.DoResponse(c, resp, info)
 		return adaptor.DoResponse(c, resp, info)

relay/channel/vertex/adaptor.go

@@ -365,10 +365,11 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 }
 }
 
 
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
+	claudeAdaptor := claude.Adaptor{}
 	if info.IsStream {
 	if info.IsStream {
 		switch a.RequestMode {
 		switch a.RequestMode {
 		case RequestModeClaude:
 		case RequestModeClaude:
-			return claude.ClaudeStreamHandler(c, resp, info)
+			return claudeAdaptor.DoResponse(c, resp, info)
 		case RequestModeGemini:
 		case RequestModeGemini:
 			if info.RelayMode == constant.RelayModeGemini {
 			if info.RelayMode == constant.RelayModeGemini {
 				return gemini.GeminiTextGenerationStreamHandler(c, info, resp)
 				return gemini.GeminiTextGenerationStreamHandler(c, info, resp)
@@ -381,7 +382,7 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	} else {
 	} else {
 		switch a.RequestMode {
 		switch a.RequestMode {
 		case RequestModeClaude:
 		case RequestModeClaude:
-			return claude.ClaudeHandler(c, resp, info)
+			return claudeAdaptor.DoResponse(c, resp, info)
 		case RequestModeGemini:
 		case RequestModeGemini:
 			if info.RelayMode == constant.RelayModeGemini {
 			if info.RelayMode == constant.RelayModeGemini {
 				return gemini.GeminiTextGenerationHandler(c, info, resp)
 				return gemini.GeminiTextGenerationHandler(c, info, resp)

relay/channel/volcengine/adaptor.go

@@ -347,10 +347,8 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 	if info.RelayFormat == types.RelayFormatClaude {
 	if info.RelayFormat == types.RelayFormatClaude {
 		if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
 		if _, ok := channelconstant.ChannelSpecialBases[info.ChannelBaseUrl]; ok {
-			if info.IsStream {
-				return claude.ClaudeStreamHandler(c, resp, info)
-			}
-			return claude.ClaudeHandler(c, resp, info)
+			adaptor := claude.Adaptor{}
+			return adaptor.DoResponse(c, resp, info)
 		}
 		}
 	}
 	}
 
 

relay/channel/zhipu_4v/adaptor.go

@@ -109,11 +109,8 @@ func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, request
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
 	switch info.RelayFormat {
 	switch info.RelayFormat {
 	case types.RelayFormatClaude:
 	case types.RelayFormatClaude:
-		if info.IsStream {
-			return claude.ClaudeStreamHandler(c, resp, info)
-		} else {
-			return claude.ClaudeHandler(c, resp, info)
-		}
+		adaptor := claude.Adaptor{}
+		return adaptor.DoResponse(c, resp, info)
 	default:
 	default:
 		if info.RelayMode == relayconstant.RelayModeImagesGenerations {
 		if info.RelayMode == relayconstant.RelayModeImagesGenerations {
 			return zhipu4vImageHandler(c, resp, info)
 			return zhipu4vImageHandler(c, resp, info)

relay/common/relay_info.go

@@ -145,6 +145,8 @@ type RelayInfo struct {
 	// RequestConversionChain records request format conversions in order, e.g.
 	// RequestConversionChain records request format conversions in order, e.g.
 	// ["openai", "openai_responses"] or ["openai", "claude"].
 	// ["openai", "openai_responses"] or ["openai", "claude"].
 	RequestConversionChain []types.RelayFormat
 	RequestConversionChain []types.RelayFormat
+	// 最终请求到上游的格式 TODO: 当前仅设置了Claude
+	FinalRequestRelayFormat types.RelayFormat
 
 
 	ThinkingContentInfo
 	ThinkingContentInfo
 	TokenCountMeta
 	TokenCountMeta

relay/compatible_handler.go

@@ -334,7 +334,7 @@ func postConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage
 
 
 	var audioInputQuota decimal.Decimal
 	var audioInputQuota decimal.Decimal
 	var audioInputPrice float64
 	var audioInputPrice float64
-	isClaudeUsageSemantic := relayInfo.ChannelType == constant.ChannelTypeAnthropic
+	isClaudeUsageSemantic := relayInfo.FinalRequestRelayFormat == types.RelayFormatClaude
 	if !relayInfo.PriceData.UsePrice {
 	if !relayInfo.PriceData.UsePrice {
 		baseTokens := dPromptTokens
 		baseTokens := dPromptTokens
 		// 减去 cached tokens
 		// 减去 cached tokens