Add reverse mappings for original tool names and improve error logging

- Introduced reverse mapping logic for tool names in translators to restore original names when shortened.
- Enhanced error handling by logging API response errors consistently across handlers.
- Refactored request and response loggers to include API error details, improving debugging capabilities.
- Integrated robust tool name shortening and uniqueness mechanisms for OpenAI, Gemini, and Claude requests.
- Improved handler retry logic to properly capture and respond to errors.

internal/api/handlers/claude/code_handlers.go

@@ -139,12 +139,13 @@ func (h *ClaudeCodeAPIHandler) handleStreamingResponse(c *gin.Context, rawJSON [
 			}
 		}
 	}()
+
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	// Main client rotation loop with quota management
 	// This loop implements a sophisticated load balancing and failover mechanism
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -185,6 +186,8 @@ outLoop:
 			// This manages various error conditions and implements retry logic
 			case errInfo, okError := <-errChan:
 				if okError {
+					errorResponse = errInfo
+					h.LoggingAPIResponseError(cliCtx, errInfo)
 					// Special handling for quota exceeded errors
 					// If configured, attempt to switch to a different project/client
 					switch errInfo.StatusCode {
@@ -221,4 +224,12 @@ outLoop:
 			}
 		}
 	}
+
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }

internal/api/handlers/gemini/gemini-cli_handlers.go

@@ -169,10 +169,10 @@ func (h *GeminiCLIAPIHandler) handleInternalStreamGenerateContent(c *gin.Context
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -208,6 +208,9 @@ outLoop:
 			// Handle errors from the backend.
 			case err, okError := <-errChan:
 				if okError {
+					errorResponse = err
+					h.LoggingAPIResponseError(cliCtx, err)
+
 					switch err.StatusCode {
 					case 429:
 						if h.Cfg.QuotaExceeded.SwitchProject {
@@ -232,6 +235,13 @@ outLoop:
 			}
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }
 
 // handleInternalGenerateContent handles non-streaming content generation requests.
@@ -252,9 +262,9 @@ func (h *GeminiCLIAPIHandler) handleInternalGenerateContent(c *gin.Context, rawJ
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -265,6 +275,9 @@ func (h *GeminiCLIAPIHandler) handleInternalGenerateContent(c *gin.Context, rawJ
 
 		resp, err := cliClient.SendRawMessage(cliCtx, modelName, rawJSON, "")
 		if err != nil {
+			errorResponse = err
+			h.LoggingAPIResponseError(cliCtx, err)
+
 			switch err.StatusCode {
 			case 429:
 				if h.Cfg.QuotaExceeded.SwitchProject {
@@ -296,4 +309,11 @@ func (h *GeminiCLIAPIHandler) handleInternalGenerateContent(c *gin.Context, rawJ
 			break
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = c.Writer.Write([]byte(errorResponse.Error.Error()))
+		cliCancel(errorResponse.Error)
+		return
+	}
+
 }

internal/api/handlers/gemini/gemini_handlers.go

@@ -221,10 +221,10 @@ func (h *GeminiAPIHandler) handleStreamGenerateContent(c *gin.Context, modelName
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -263,6 +263,9 @@ outLoop:
 			// Handle errors from the backend.
 			case err, okError := <-errChan:
 				if okError {
+					errorResponse = err
+					h.LoggingAPIResponseError(cliCtx, err)
+
 					switch err.StatusCode {
 					case 429:
 						if h.Cfg.QuotaExceeded.SwitchProject {
@@ -287,6 +290,13 @@ outLoop:
 			}
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }
 
 // handleCountTokens handles token counting requests for Gemini models.
@@ -365,9 +375,9 @@ func (h *GeminiAPIHandler) handleGenerateContent(c *gin.Context, modelName strin
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -378,6 +388,9 @@ func (h *GeminiAPIHandler) handleGenerateContent(c *gin.Context, modelName strin
 
 		resp, err := cliClient.SendRawMessage(cliCtx, modelName, rawJSON, alt)
 		if err != nil {
+			errorResponse = err
+			h.LoggingAPIResponseError(cliCtx, err)
+
 			switch err.StatusCode {
 			case 429:
 				if h.Cfg.QuotaExceeded.SwitchProject {
@@ -409,4 +422,10 @@ func (h *GeminiAPIHandler) handleGenerateContent(c *gin.Context, modelName strin
 			break
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = c.Writer.Write([]byte(errorResponse.Error.Error()))
+		cliCancel(errorResponse.Error)
+		return
+	}
 }

internal/api/handlers/handlers.go

@@ -235,6 +235,22 @@ func (h *BaseAPIHandler) GetContextWithCancel(handler interfaces.APIHandler, c *
 	}
 }
 
+func (h *BaseAPIHandler) LoggingAPIResponseError(ctx context.Context, err *interfaces.ErrorMessage) {
+	if h.Cfg.RequestLog {
+		if ginContext, ok := ctx.Value("gin").(*gin.Context); ok {
+			if apiResponseErrors, isExist := ginContext.Get("API_RESPONSE_ERROR"); isExist {
+				if slicesAPIResponseError, isOk := apiResponseErrors.([]*interfaces.ErrorMessage); isOk {
+					slicesAPIResponseError = append(slicesAPIResponseError, err)
+					ginContext.Set("API_RESPONSE_ERROR", slicesAPIResponseError)
+				}
+			} else {
+				// Create new response data entry
+				ginContext.Set("API_RESPONSE_ERROR", []*interfaces.ErrorMessage{err})
+			}
+		}
+	}
+}
+
 // APIHandlerCancelFunc is a function type for canceling an API handler's context.
 // It can optionally accept parameters, which are used for logging the response.
 type APIHandlerCancelFunc func(params ...interface{})

internal/api/handlers/openai/openai_handlers.go

@@ -387,9 +387,9 @@ func (h *OpenAIAPIHandler) handleNonStreamingResponse(c *gin.Context, rawJSON []
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -400,6 +400,9 @@ func (h *OpenAIAPIHandler) handleNonStreamingResponse(c *gin.Context, rawJSON []
 
 		resp, err := cliClient.SendRawMessage(cliCtx, modelName, rawJSON, "")
 		if err != nil {
+			errorResponse = err
+			h.LoggingAPIResponseError(cliCtx, err)
+
 			switch err.StatusCode {
 			case 429:
 				if h.Cfg.QuotaExceeded.SwitchProject {
@@ -431,6 +434,12 @@ func (h *OpenAIAPIHandler) handleNonStreamingResponse(c *gin.Context, rawJSON []
 			break
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = c.Writer.Write([]byte(errorResponse.Error.Error()))
+		cliCancel(errorResponse.Error)
+		return
+	}
 }
 
 // handleStreamingResponse handles streaming responses for Gemini models.
@@ -471,10 +480,10 @@ func (h *OpenAIAPIHandler) handleStreamingResponse(c *gin.Context, rawJSON []byt
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -511,6 +520,9 @@ outLoop:
 			// Handle errors from the backend.
 			case err, okError := <-errChan:
 				if okError {
+					errorResponse = err
+					h.LoggingAPIResponseError(cliCtx, err)
+
 					switch err.StatusCode {
 					case 429:
 						if h.Cfg.QuotaExceeded.SwitchProject {
@@ -535,6 +547,13 @@ outLoop:
 			}
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }
 
 // handleCompletionsNonStreamingResponse handles non-streaming completions responses.
@@ -562,9 +581,9 @@ func (h *OpenAIAPIHandler) handleCompletionsNonStreamingResponse(c *gin.Context,
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -576,6 +595,9 @@ func (h *OpenAIAPIHandler) handleCompletionsNonStreamingResponse(c *gin.Context,
 		// Send the converted chat completions request
 		resp, err := cliClient.SendRawMessage(cliCtx, modelName, chatCompletionsJSON, "")
 		if err != nil {
+			errorResponse = err
+			h.LoggingAPIResponseError(cliCtx, err)
+
 			switch err.StatusCode {
 			case 429:
 				if h.Cfg.QuotaExceeded.SwitchProject {
@@ -601,6 +623,13 @@ func (h *OpenAIAPIHandler) handleCompletionsNonStreamingResponse(c *gin.Context,
 			break
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = c.Writer.Write([]byte(errorResponse.Error.Error()))
+		cliCancel(errorResponse.Error)
+		return
+	}
+
 }
 
 // handleCompletionsStreamingResponse handles streaming completions responses.
@@ -644,10 +673,10 @@ func (h *OpenAIAPIHandler) handleCompletionsStreamingResponse(c *gin.Context, ra
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -689,6 +718,9 @@ outLoop:
 			// Handle errors from the backend.
 			case err, okError := <-errChan:
 				if okError {
+					errorResponse = err
+					h.LoggingAPIResponseError(cliCtx, err)
+
 					switch err.StatusCode {
 					case 429:
 						if h.Cfg.QuotaExceeded.SwitchProject {
@@ -713,4 +745,11 @@ outLoop:
 			}
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }

internal/api/handlers/openai/openai_responses_handlers.go

@@ -115,9 +115,9 @@ func (h *OpenAIResponsesAPIHandler) handleNonStreamingResponse(c *gin.Context, r
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -128,6 +128,9 @@ func (h *OpenAIResponsesAPIHandler) handleNonStreamingResponse(c *gin.Context, r
 
 		resp, err := cliClient.SendRawMessage(cliCtx, modelName, rawJSON, "")
 		if err != nil {
+			errorResponse = err
+			h.LoggingAPIResponseError(cliCtx, err)
+
 			switch err.StatusCode {
 			case 429:
 				if h.Cfg.QuotaExceeded.SwitchProject {
@@ -159,6 +162,13 @@ func (h *OpenAIResponsesAPIHandler) handleNonStreamingResponse(c *gin.Context, r
 			break
 		}
 	}
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = c.Writer.Write([]byte(errorResponse.Error.Error()))
+		cliCancel(errorResponse.Error)
+		return
+	}
+
 }
 
 // handleStreamingResponse handles streaming responses for Gemini models.
@@ -199,10 +209,10 @@ func (h *OpenAIResponsesAPIHandler) handleStreamingResponse(c *gin.Context, rawJ
 		}
 	}()
 
+	var errorResponse *interfaces.ErrorMessage
 	retryCount := 0
 outLoop:
 	for retryCount <= h.Cfg.RequestRetry {
-		var errorResponse *interfaces.ErrorMessage
 		cliClient, errorResponse = h.GetClient(modelName)
 		if errorResponse != nil {
 			c.Status(errorResponse.StatusCode)
@@ -238,6 +248,8 @@ outLoop:
 			// Handle errors from the backend.
 			case err, okError := <-errChan:
 				if okError {
+					errorResponse = err
+					h.LoggingAPIResponseError(cliCtx, err)
 					switch err.StatusCode {
 					case 429:
 						if h.Cfg.QuotaExceeded.SwitchProject {
@@ -262,4 +274,12 @@ outLoop:
 			}
 		}
 	}
+
+	if errorResponse != nil {
+		c.Status(errorResponse.StatusCode)
+		_, _ = fmt.Fprint(c.Writer, errorResponse.Error.Error())
+		flusher.Flush()
+		cliCancel(errorResponse.Error)
+		return
+	}
 }