e2037ad756
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.
46 lines
1.7 KiB
Go
46 lines
1.7 KiB
Go
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"`
|
|
}
|