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.

service/quota.go

@@ -8,11 +8,12 @@ import (
 	"one-api/common"
 	"one-api/constant"
 	"one-api/dto"
+	"one-api/logger"
 	"one-api/model"
 	relaycommon "one-api/relay/common"
-	"one-api/relay/helper"
 	"one-api/setting"
 	"one-api/setting/ratio_setting"
+	"one-api/types"
 	"strings"
 	"time"
 
@@ -129,23 +130,23 @@ func PreWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usag
 	quota := calculateAudioQuota(quotaInfo)
 
 	if userQuota < quota {
-		return fmt.Errorf("user quota is not enough, user quota: %s, need quota: %s", common.FormatQuota(userQuota), common.FormatQuota(quota))
+		return fmt.Errorf("user quota is not enough, user quota: %s, need quota: %s", logger.FormatQuota(userQuota), logger.FormatQuota(quota))
 	}
 
 	if !token.UnlimitedQuota && token.RemainQuota < quota {
-		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", common.FormatQuota(token.RemainQuota), common.FormatQuota(quota))
+		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", logger.FormatQuota(token.RemainQuota), logger.FormatQuota(quota))
 	}
 
 	err = PostConsumeQuota(relayInfo, quota, 0, false)
 	if err != nil {
 		return err
 	}
-	common.LogInfo(ctx, "realtime streaming consume quota success, quota: "+fmt.Sprintf("%d", quota))
+	logger.LogInfo(ctx, "realtime streaming consume quota success, quota: "+fmt.Sprintf("%d", quota))
 	return nil
 }
 
 func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelName string,
-	usage *dto.RealtimeUsage, preConsumedQuota int, userQuota int, priceData helper.PriceData, extraContent string) {
+	usage *dto.RealtimeUsage, extraContent string) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	textInputTokens := usage.InputTokenDetails.TextTokens
@@ -159,10 +160,10 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 	audioRatio := decimal.NewFromFloat(ratio_setting.GetAudioRatio(relayInfo.OriginModelName))
 	audioCompletionRatio := decimal.NewFromFloat(ratio_setting.GetAudioCompletionRatio(modelName))
 
-	modelRatio := priceData.ModelRatio
-	groupRatio := priceData.GroupRatioInfo.GroupRatio
-	modelPrice := priceData.ModelPrice
-	usePrice := priceData.UsePrice
+	modelRatio := relayInfo.PriceData.ModelRatio
+	groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
+	modelPrice := relayInfo.PriceData.ModelPrice
+	usePrice := relayInfo.PriceData.UsePrice
 
 	quotaInfo := QuotaInfo{
 		InputDetails: TokenDetails{
@@ -196,8 +197,8 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		// we cannot just return, because we may have to return the pre-consumed quota
 		quota = 0
 		logContent += fmt.Sprintf("（可能是上游超时）")
-		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
+		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, relayInfo.FinalPreConsumedQuota))
 	} else {
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
@@ -208,7 +209,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		logContent += ", " + extraContent
 	}
 	other := GenerateWssOtherInfo(ctx, relayInfo, usage, modelRatio, groupRatio,
-		completionRatio.InexactFloat64(), audioRatio.InexactFloat64(), audioCompletionRatio.InexactFloat64(), modelPrice, priceData.GroupRatioInfo.GroupSpecialRatio)
+		completionRatio.InexactFloat64(), audioRatio.InexactFloat64(), audioCompletionRatio.InexactFloat64(), modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
 	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
 		ChannelId:        relayInfo.ChannelId,
 		PromptTokens:     usage.InputTokens,
@@ -218,7 +219,6 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 		Quota:            quota,
 		Content:          logContent,
 		TokenId:          relayInfo.TokenId,
-		UserQuota:        userQuota,
 		UseTimeSeconds:   int(useTimeSeconds),
 		IsStream:         relayInfo.IsStream,
 		Group:            relayInfo.UsingGroup,
@@ -226,8 +226,7 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
 	})
 }
 
-func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
-	usage *dto.Usage, preConsumedQuota int, userQuota int, priceData helper.PriceData, extraContent string) {
+func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	promptTokens := usage.PromptTokens
@@ -235,20 +234,20 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	modelName := relayInfo.OriginModelName
 
 	tokenName := ctx.GetString("token_name")
-	completionRatio := priceData.CompletionRatio
-	modelRatio := priceData.ModelRatio
-	groupRatio := priceData.GroupRatioInfo.GroupRatio
-	modelPrice := priceData.ModelPrice
-	cacheRatio := priceData.CacheRatio
+	completionRatio := relayInfo.PriceData.CompletionRatio
+	modelRatio := relayInfo.PriceData.ModelRatio
+	groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
+	modelPrice := relayInfo.PriceData.ModelPrice
+	cacheRatio := relayInfo.PriceData.CacheRatio
 	cacheTokens := usage.PromptTokensDetails.CachedTokens
 
-	cacheCreationRatio := priceData.CacheCreationRatio
+	cacheCreationRatio := relayInfo.PriceData.CacheCreationRatio
 	cacheCreationTokens := usage.PromptTokensDetails.CachedCreationTokens
 
 	if relayInfo.ChannelType == constant.ChannelTypeOpenRouter {
 		promptTokens -= cacheTokens
-		if cacheCreationTokens == 0 && priceData.CacheCreationRatio != 1 && usage.Cost != 0 {
-			maybeCacheCreationTokens := CalcOpenRouterCacheCreateTokens(*usage, priceData)
+		if cacheCreationTokens == 0 && relayInfo.PriceData.CacheCreationRatio != 1 && usage.Cost != 0 {
+			maybeCacheCreationTokens := CalcOpenRouterCacheCreateTokens(*usage, relayInfo.PriceData)
 			if promptTokens >= maybeCacheCreationTokens {
 				cacheCreationTokens = maybeCacheCreationTokens
 			}
@@ -257,7 +256,7 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	}
 
 	calculateQuota := 0.0
-	if !priceData.UsePrice {
+	if !relayInfo.PriceData.UsePrice {
 		calculateQuota = float64(promptTokens)
 		calculateQuota += float64(cacheTokens) * cacheRatio
 		calculateQuota += float64(cacheCreationTokens) * cacheCreationRatio
@@ -282,23 +281,23 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		// we cannot just return, because we may have to return the pre-consumed quota
 		quota = 0
 		logContent += fmt.Sprintf("（可能是上游出错）")
-		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, preConsumedQuota))
+		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, modelName, relayInfo.FinalPreConsumedQuota))
 	} else {
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	quotaDelta := quota - preConsumedQuota
+	quotaDelta := quota - relayInfo.FinalPreConsumedQuota
 	if quotaDelta != 0 {
-		err := PostConsumeQuota(relayInfo, quotaDelta, preConsumedQuota, true)
+		err := PostConsumeQuota(relayInfo, quotaDelta, relayInfo.FinalPreConsumedQuota, true)
 		if err != nil {
-			common.LogError(ctx, "error consuming token remain quota: "+err.Error())
+			logger.LogError(ctx, "error consuming token remain quota: "+err.Error())
 		}
 	}
 
 	other := GenerateClaudeOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio,
-		cacheTokens, cacheRatio, cacheCreationTokens, cacheCreationRatio, modelPrice, priceData.GroupRatioInfo.GroupSpecialRatio)
+		cacheTokens, cacheRatio, cacheCreationTokens, cacheCreationRatio, modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
 	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
 		ChannelId:        relayInfo.ChannelId,
 		PromptTokens:     promptTokens,
@@ -308,7 +307,6 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		Quota:            quota,
 		Content:          logContent,
 		TokenId:          relayInfo.TokenId,
-		UserQuota:        userQuota,
 		UseTimeSeconds:   int(useTimeSeconds),
 		IsStream:         relayInfo.IsStream,
 		Group:            relayInfo.UsingGroup,
@@ -317,7 +315,7 @@ func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 
 }
 
-func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData helper.PriceData) int {
+func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData types.PriceData) int {
 	if priceData.CacheCreationRatio == 1 {
 		return 0
 	}
@@ -338,8 +336,7 @@ func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData helper.PriceData
 		(promptCacheCreatePrice - quotaPrice)))
 }
 
-func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
-	usage *dto.Usage, preConsumedQuota int, userQuota int, priceData helper.PriceData, extraContent string) {
+func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, extraContent string) {
 
 	useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
 	textInputTokens := usage.PromptTokensDetails.TextTokens
@@ -353,10 +350,10 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 	audioRatio := decimal.NewFromFloat(ratio_setting.GetAudioRatio(relayInfo.OriginModelName))
 	audioCompletionRatio := decimal.NewFromFloat(ratio_setting.GetAudioCompletionRatio(relayInfo.OriginModelName))
 
-	modelRatio := priceData.ModelRatio
-	groupRatio := priceData.GroupRatioInfo.GroupRatio
-	modelPrice := priceData.ModelPrice
-	usePrice := priceData.UsePrice
+	modelRatio := relayInfo.PriceData.ModelRatio
+	groupRatio := relayInfo.PriceData.GroupRatioInfo.GroupRatio
+	modelPrice := relayInfo.PriceData.ModelPrice
+	usePrice := relayInfo.PriceData.UsePrice
 
 	quotaInfo := QuotaInfo{
 		InputDetails: TokenDetails{
@@ -390,18 +387,18 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		// we cannot just return, because we may have to return the pre-consumed quota
 		quota = 0
 		logContent += fmt.Sprintf("（可能是上游超时）")
-		common.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
-			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.OriginModelName, preConsumedQuota))
+		logger.LogError(ctx, fmt.Sprintf("total tokens is 0, cannot consume quota, userId %d, channelId %d, "+
+			"tokenId %d, model %s， pre-consumed quota %d", relayInfo.UserId, relayInfo.ChannelId, relayInfo.TokenId, relayInfo.OriginModelName, relayInfo.FinalPreConsumedQuota))
 	} else {
 		model.UpdateUserUsedQuotaAndRequestCount(relayInfo.UserId, quota)
 		model.UpdateChannelUsedQuota(relayInfo.ChannelId, quota)
 	}
 
-	quotaDelta := quota - preConsumedQuota
+	quotaDelta := quota - relayInfo.FinalPreConsumedQuota
 	if quotaDelta != 0 {
-		err := PostConsumeQuota(relayInfo, quotaDelta, preConsumedQuota, true)
+		err := PostConsumeQuota(relayInfo, quotaDelta, relayInfo.FinalPreConsumedQuota, true)
 		if err != nil {
-			common.LogError(ctx, "error consuming token remain quota: "+err.Error())
+			logger.LogError(ctx, "error consuming token remain quota: "+err.Error())
 		}
 	}
 
@@ -410,7 +407,7 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		logContent += ", " + extraContent
 	}
 	other := GenerateAudioOtherInfo(ctx, relayInfo, usage, modelRatio, groupRatio,
-		completionRatio.InexactFloat64(), audioRatio.InexactFloat64(), audioCompletionRatio.InexactFloat64(), modelPrice, priceData.GroupRatioInfo.GroupSpecialRatio)
+		completionRatio.InexactFloat64(), audioRatio.InexactFloat64(), audioCompletionRatio.InexactFloat64(), modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
 	model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
 		ChannelId:        relayInfo.ChannelId,
 		PromptTokens:     usage.PromptTokens,
@@ -420,7 +417,6 @@ func PostAudioConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo,
 		Quota:            quota,
 		Content:          logContent,
 		TokenId:          relayInfo.TokenId,
-		UserQuota:        userQuota,
 		UseTimeSeconds:   int(useTimeSeconds),
 		IsStream:         relayInfo.IsStream,
 		Group:            relayInfo.UsingGroup,
@@ -443,7 +439,7 @@ func PreConsumeTokenQuota(relayInfo *relaycommon.RelayInfo, quota int) error {
 		return err
 	}
 	if !relayInfo.TokenUnlimited && token.RemainQuota < quota {
-		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", common.FormatQuota(token.RemainQuota), common.FormatQuota(quota))
+		return fmt.Errorf("token quota is not enough, token remain quota: %s, need quota: %s", logger.FormatQuota(token.RemainQuota), logger.FormatQuota(quota))
 	}
 	err = model.DecreaseTokenQuota(relayInfo.TokenId, relayInfo.TokenKey, quota)
 	if err != nil {
@@ -501,7 +497,7 @@ func checkAndSendQuotaNotify(relayInfo *relaycommon.RelayInfo, quota int, preCon
 			prompt := "您的额度即将用尽"
 			topUpLink := fmt.Sprintf("%s/topup", setting.ServerAddress)
 			content := "{{value}}，当前剩余额度为 {{value}}，为了不影响您的使用，请及时充值。<br/>充值链接：<a href='{{value}}'>{{value}}</a>"
-			err := NotifyUser(relayInfo.UserId, relayInfo.UserEmail, relayInfo.UserSetting, dto.NewNotify(dto.NotifyTypeQuotaExceed, prompt, content, []interface{}{prompt, common.FormatQuota(relayInfo.UserQuota), topUpLink, topUpLink}))
+			err := NotifyUser(relayInfo.UserId, relayInfo.UserEmail, relayInfo.UserSetting, dto.NewNotify(dto.NotifyTypeQuotaExceed, prompt, content, []interface{}{prompt, logger.FormatQuota(relayInfo.UserQuota), topUpLink, topUpLink}))
 			if err != nil {
 				common.SysError(fmt.Sprintf("failed to send quota notify to user %d: %s", relayInfo.UserId, err.Error()))
 			}