refactor: Introduce pre-consume quota and unify relay handlers

This commit introduces a major architectural refactoring to improve quota management, centralize logging, and streamline the relay handling logic.

Key changes:
- **Pre-consume Quota:** Implements a new mechanism to check and reserve user quota *before* making the request to the upstream provider. This ensures more accurate quota deduction and prevents users from exceeding their limits due to concurrent requests.

- **Unified Relay Handlers:** Refactors the relay logic to use generic handlers (e.g., `ChatHandler`, `ImageHandler`) instead of provider-specific implementations. This significantly reduces code duplication and simplifies adding new channels.

- **Centralized Logger:** A new dedicated `logger` package is introduced, and all system logging calls are migrated to use it, moving this responsibility out of the `common` package.

- **Code Reorganization:** DTOs are generalized (e.g., `dalle.go` -> `openai_image.go`) and utility code is moved to more appropriate packages (e.g., `common/http.go` -> `service/http.go`) for better code structure.

types/error.go

@@ -39,12 +39,13 @@ const (
 	ErrorCodeSensitiveWordsDetected ErrorCode = "sensitive_words_detected"
 
 	// new api error
-	ErrorCodeCountTokenFailed  ErrorCode = "count_token_failed"
-	ErrorCodeModelPriceError   ErrorCode = "model_price_error"
-	ErrorCodeInvalidApiType    ErrorCode = "invalid_api_type"
-	ErrorCodeJsonMarshalFailed ErrorCode = "json_marshal_failed"
-	ErrorCodeDoRequestFailed   ErrorCode = "do_request_failed"
-	ErrorCodeGetChannelFailed  ErrorCode = "get_channel_failed"
+	ErrorCodeCountTokenFailed   ErrorCode = "count_token_failed"
+	ErrorCodeModelPriceError    ErrorCode = "model_price_error"
+	ErrorCodeInvalidApiType     ErrorCode = "invalid_api_type"
+	ErrorCodeJsonMarshalFailed  ErrorCode = "json_marshal_failed"
+	ErrorCodeDoRequestFailed    ErrorCode = "do_request_failed"
+	ErrorCodeGetChannelFailed   ErrorCode = "get_channel_failed"
+	ErrorCodeGenRelayInfoFailed ErrorCode = "gen_relay_info_failed"
 
 	// channel error
 	ErrorCodeChannelNoAvailableKey       ErrorCode = "channel:no_available_key"

types/price_data.go

@@ -0,0 +1,31 @@
+package types
+
+import "fmt"
+
+type GroupRatioInfo struct {
+	GroupRatio        float64
+	GroupSpecialRatio float64
+	HasSpecialRatio   bool
+}
+
+type PriceData struct {
+	ModelPrice             float64
+	ModelRatio             float64
+	CompletionRatio        float64
+	CacheRatio             float64
+	CacheCreationRatio     float64
+	ImageRatio             float64
+	UsePrice               bool
+	ShouldPreConsumedQuota int
+	GroupRatioInfo         GroupRatioInfo
+}
+
+type PerCallPriceData struct {
+	ModelPrice     float64
+	Quota          int
+	GroupRatioInfo GroupRatioInfo
+}
+
+func (p PriceData) ToSetting() string {
+	return fmt.Sprintf("ModelPrice: %f, ModelRatio: %f, CompletionRatio: %f, CacheRatio: %f, GroupRatio: %f, UsePrice: %t, CacheCreationRatio: %f, ShouldPreConsumedQuota: %d, ImageRatio: %f", p.ModelPrice, p.ModelRatio, p.CompletionRatio, p.CacheRatio, p.GroupRatioInfo.GroupRatio, p.UsePrice, p.CacheCreationRatio, p.ShouldPreConsumedQuota, p.ImageRatio)
+}

types/relay_format.go

@@ -0,0 +1,15 @@
+package types
+
+type RelayFormat string
+
+const (
+	RelayFormatOpenAI          RelayFormat = "openai"
+	RelayFormatClaude                      = "claude"
+	RelayFormatGemini                      = "gemini"
+	RelayFormatOpenAIResponses             = "openai_responses"
+	RelayFormatOpenAIAudio                 = "openai_audio"
+	RelayFormatOpenAIImage                 = "openai_image"
+	RelayFormatOpenAIRealtime              = "openai_realtime"
+	RelayFormatRerank                      = "rerank"
+	RelayFormatEmbedding                   = "embedding"
+)

types/relay_request.go

@@ -0,0 +1,27 @@
+package types
+
+type RelayRequest struct {
+	OriginRequest    any
+	Format           RelayFormat
+	PromptTokenCount int
+}
+
+func (r *RelayRequest) CopyOriginRequest() any {
+	if r.OriginRequest == nil {
+		return nil
+	}
+	switch v := r.OriginRequest.(type) {
+	case *GeneralOpenAIRequest:
+		return v.Copy()
+	case *GeneralClaudeRequest:
+		return v.Copy()
+	case *GeneralGeminiRequest:
+		return v.Copy()
+	case *GeneralRerankRequest:
+		return v.Copy()
+	case *GeneralEmbeddingRequest:
+		return v.Copy()
+	default:
+		return nil
+	}
+}

types/request_meta.go

@@ -0,0 +1,45 @@
+package types
+
+type FileType string
+
+const (
+	FileTypeImage FileType = "image" // Image file type
+	FileTypeAudio FileType = "audio" // Audio file type
+	FileTypeVideo FileType = "video" // Video file type
+	FileTypeFile  FileType = "file"  // Generic file type
+)
+
+type TokenType string
+
+const (
+	TokenTypeTextNumber TokenType = "text_number" // Text or number tokens
+	TokenTypeTokenizer  TokenType = "tokenizer"   // Tokenizer tokens
+	TokenTypeImage      TokenType = "image"       // Image tokens
+)
+
+type TokenCountMeta struct {
+	TokenType     TokenType   `json:"token_type,omitempty"`     // Type of tokens used in the request
+	CombineText   string      `json:"combine_text,omitempty"`   // Combined text from all messages
+	ToolsCount    int         `json:"tools_count,omitempty"`    // Number of tools used
+	NameCount     int         `json:"name_count,omitempty"`     // Number of names in the request
+	MessagesCount int         `json:"messages_count,omitempty"` // Number of messages in the request
+	Files         []*FileMeta `json:"files,omitempty"`          // List of files, each with type and content
+	MaxTokens     int         `json:"max_tokens,omitempty"`     // Maximum tokens allowed in the request
+
+	ImagePriceRatio float64 `json:"image_ratio,omitempty"` // Ratio for image size, if applicable
+	//IsStreaming   bool        `json:"is_streaming,omitempty"`   // Indicates if the request is streaming
+}
+
+type FileMeta struct {
+	FileType
+	MimeType string
+	Data     string
+	Detail   string
+}
+
+type RequestMeta struct {
+	OriginalModelName string `json:"original_model_name"`
+	UserUsingGroup    string `json:"user_using_group"`
+	PromptTokens      int    `json:"prompt_tokens"`
+	PreConsumedQuota  int    `json:"pre_consumed_quota"`
+}