perf: use max_tokens to reduce token consuming

controller/channel.go

@@ -211,10 +211,11 @@ func buildTestRequest(c *gin.Context) *ChatRequest {
 	model_ := c.Query("model")
 	model_ := c.Query("model")
 	testRequest := &ChatRequest{
 	testRequest := &ChatRequest{
 		Model:     model_,
 		Model:     model_,
+		MaxTokens: 1,
 	}
 	}
 	testMessage := Message{
 	testMessage := Message{
 		Role:    "user",
 		Role:    "user",
-		Content: "echo hi",
+		Content: "hi",
 	}
 	}
 	testRequest.Messages = append(testRequest.Messages, testMessage)
 	testRequest.Messages = append(testRequest.Messages, testMessage)
 	return testRequest
 	return testRequest

controller/relay.go

@@ -23,6 +23,7 @@ type Message struct {
 type ChatRequest struct {
 type ChatRequest struct {
 	Model     string    `json:"model"`
 	Model     string    `json:"model"`
 	Messages  []Message `json:"messages"`
 	Messages  []Message `json:"messages"`
+	MaxTokens int       `json:"max_tokens"`
 }
 }
 
 
 type TextRequest struct {
 type TextRequest struct {