feat: Enhance GeminiChatHandler to include RelayInfo

- Updated the GeminiChatHandler function to accept an additional parameter, RelayInfo, allowing for better context handling during chat operations.
- Modified the DoResponse method in the Adaptor to pass RelayInfo to GeminiChatHandler, ensuring consistent usage of upstream model information.
- Enhanced the GeminiChatStreamHandler to utilize the upstream model name from RelayInfo, improving response accuracy and data representation in Gemini requests.

relay/channel/gemini/adaptor.go

@@ -76,7 +76,7 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 	if info.IsStream {
 		err, usage = GeminiChatStreamHandler(c, resp, info)
 	} else {
-		err, usage = GeminiChatHandler(c, resp)
+		err, usage = GeminiChatHandler(c, resp, info)
 	}
 	return
 }

relay/channel/gemini/relay-gemini.go

@@ -355,6 +355,7 @@ func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 		}
 		response.Id = id
 		response.Created = createAt
+		response.Model = info.UpstreamModelName
 		responseText += response.Choices[0].Delta.GetContentString()
 		if geminiResponse.UsageMetadata.TotalTokenCount != 0 {
 			usage.PromptTokens = geminiResponse.UsageMetadata.PromptTokenCount
@@ -383,7 +384,7 @@ func GeminiChatStreamHandler(c *gin.Context, resp *http.Response, info *relaycom
 	return nil, usage
 }
 
-func GeminiChatHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
+func GeminiChatHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
 	responseBody, err := io.ReadAll(resp.Body)
 	if err != nil {
 		return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
@@ -409,6 +410,7 @@ func GeminiChatHandler(c *gin.Context, resp *http.Response) (*dto.OpenAIErrorWit
 		}, nil
 	}
 	fullTextResponse := responseGeminiChat2OpenAI(&geminiResponse)
+	fullTextResponse.Model = info.UpstreamModelName
 	usage := dto.Usage{
 		PromptTokens:     geminiResponse.UsageMetadata.PromptTokenCount,
 		CompletionTokens: geminiResponse.UsageMetadata.CandidatesTokenCount,

relay/channel/vertex/adaptor.go

@@ -170,7 +170,7 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
 		case RequestModeClaude:
 			err, usage = claude.ClaudeHandler(c, resp, claude.RequestModeMessage, info)
 		case RequestModeGemini:
-			err, usage = gemini.GeminiChatHandler(c, resp)
+			err, usage = gemini.GeminiChatHandler(c, resp, info)
 		case RequestModeLlama:
 			err, usage = openai.OpenaiHandler(c, resp, info.PromptTokens, info.OriginModelName)
 		}