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.
This commit is contained in:
CaIon
@@ -5,35 +5,14 @@ import (
|
||||
"one-api/common"
|
||||
relaycommon "one-api/relay/common"
|
||||
"one-api/setting/ratio_setting"
|
||||
"one-api/types"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
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
|
||||
}
|
||||
|
||||
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)
|
||||
}
|
||||
|
||||
// HandleGroupRatio checks for "auto_group" in the context and updates the group ratio and relayInfo.UsingGroup if present
|
||||
func HandleGroupRatio(ctx *gin.Context, relayInfo *relaycommon.RelayInfo) GroupRatioInfo {
|
||||
groupRatioInfo := GroupRatioInfo{
|
||||
func HandleGroupRatio(ctx *gin.Context, relayInfo *relaycommon.RelayInfo) types.GroupRatioInfo {
|
||||
groupRatioInfo := types.GroupRatioInfo{
|
||||
GroupRatio: 1.0, // default ratio
|
||||
GroupSpecialRatio: -1,
|
||||
}
|
||||
@@ -62,7 +41,7 @@ func HandleGroupRatio(ctx *gin.Context, relayInfo *relaycommon.RelayInfo) GroupR
|
||||
return groupRatioInfo
|
||||
}
|
||||
|
||||
func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens int, maxTokens int) (PriceData, error) {
|
||||
func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens int, meta *types.TokenCountMeta) (types.PriceData, error) {
|
||||
modelPrice, usePrice := ratio_setting.GetModelPrice(info.OriginModelName, false)
|
||||
|
||||
groupRatioInfo := HandleGroupRatio(c, info)
|
||||
@@ -75,8 +54,8 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
|
||||
var cacheCreationRatio float64
|
||||
if !usePrice {
|
||||
preConsumedTokens := common.PreConsumedQuota
|
||||
if maxTokens != 0 {
|
||||
preConsumedTokens = promptTokens + maxTokens
|
||||
if meta.MaxTokens != 0 {
|
||||
preConsumedTokens = promptTokens + meta.MaxTokens
|
||||
}
|
||||
var success bool
|
||||
var matchName string
|
||||
@@ -87,7 +66,7 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
|
||||
acceptUnsetRatio = true
|
||||
}
|
||||
if !acceptUnsetRatio {
|
||||
return PriceData{}, fmt.Errorf("模型 %s 倍率或价格未配置，请联系管理员设置或开始自用模式；Model %s ratio or price not set, please set or start self-use mode", matchName, matchName)
|
||||
return types.PriceData{}, fmt.Errorf("模型 %s 倍率或价格未配置，请联系管理员设置或开始自用模式；Model %s ratio or price not set, please set or start self-use mode", matchName, matchName)
|
||||
}
|
||||
}
|
||||
completionRatio = ratio_setting.GetCompletionRatio(info.OriginModelName)
|
||||
@@ -97,10 +76,13 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
|
||||
ratio := modelRatio * groupRatioInfo.GroupRatio
|
||||
preConsumedQuota = int(float64(preConsumedTokens) * ratio)
|
||||
} else {
|
||||
if meta.ImagePriceRatio != 0 {
|
||||
modelPrice = modelPrice * meta.ImagePriceRatio
|
||||
}
|
||||
preConsumedQuota = int(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
}
|
||||
|
||||
priceData := PriceData{
|
||||
priceData := types.PriceData{
|
||||
ModelPrice: modelPrice,
|
||||
ModelRatio: modelRatio,
|
||||
CompletionRatio: completionRatio,
|
||||
@@ -115,38 +97,32 @@ func ModelPriceHelper(c *gin.Context, info *relaycommon.RelayInfo, promptTokens
|
||||
if common.DebugEnabled {
|
||||
println(fmt.Sprintf("model_price_helper result: %s", priceData.ToSetting()))
|
||||
}
|
||||
|
||||
info.PriceData = priceData
|
||||
return priceData, nil
|
||||
}
|
||||
|
||||
type PerCallPriceData struct {
|
||||
ModelPrice float64
|
||||
Quota int
|
||||
GroupRatioInfo GroupRatioInfo
|
||||
}
|
||||
|
||||
// ModelPriceHelperPerCall 按次计费的 PriceHelper (MJ、Task)
|
||||
func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) PerCallPriceData {
|
||||
groupRatioInfo := HandleGroupRatio(c, info)
|
||||
|
||||
modelPrice, success := ratio_setting.GetModelPrice(info.OriginModelName, true)
|
||||
// 如果没有配置价格，则使用默认价格
|
||||
if !success {
|
||||
defaultPrice, ok := ratio_setting.GetDefaultModelRatioMap()[info.OriginModelName]
|
||||
if !ok {
|
||||
modelPrice = 0.1
|
||||
} else {
|
||||
modelPrice = defaultPrice
|
||||
}
|
||||
}
|
||||
quota := int(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
priceData := PerCallPriceData{
|
||||
ModelPrice: modelPrice,
|
||||
Quota: quota,
|
||||
GroupRatioInfo: groupRatioInfo,
|
||||
}
|
||||
return priceData
|
||||
}
|
||||
//func ModelPriceHelperPerCall(c *gin.Context, info *relaycommon.RelayInfo) types.PerCallPriceData {
|
||||
// groupRatioInfo := HandleGroupRatio(c, info)
|
||||
//
|
||||
// modelPrice, success := ratio_setting.GetModelPrice(info.OriginModelName, true)
|
||||
// // 如果没有配置价格，则使用默认价格
|
||||
// if !success {
|
||||
// defaultPrice, ok := ratio_setting.GetDefaultModelRatioMap()[info.OriginModelName]
|
||||
// if !ok {
|
||||
// modelPrice = 0.1
|
||||
// } else {
|
||||
// modelPrice = defaultPrice
|
||||
// }
|
||||
// }
|
||||
// quota := int(modelPrice * common.QuotaPerUnit * groupRatioInfo.GroupRatio)
|
||||
// priceData := types.PerCallPriceData{
|
||||
// ModelPrice: modelPrice,
|
||||
// Quota: quota,
|
||||
// GroupRatioInfo: groupRatioInfo,
|
||||
// }
|
||||
// return priceData
|
||||
//}
|
||||
|
||||
func ContainPriceOrRatio(modelName string) bool {
|
||||
_, ok := ratio_setting.GetModelPrice(modelName, false)
|
||||
|
||||
Reference in New Issue
Block a user