chaos/chaos-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge branch 'origin/main' into nightly

Browse Source 
Resolve 4 conflicts:
- relay/compatible_handler.go: accept main's refactor (postConsumeQuota -> service.PostTextConsumeQuota)
- service/quota.go: accept main's PostClaudeConsumeQuota deletion, keep nightly's tiered billing in PostWssConsumeQuota and PostAudioConsumeQuota
- web/src/i18n/locales/{en,zh-CN}.json: merge both sets of translation keys

Post-merge integration:
- Add tiered billing (TryTieredSettle, InjectTieredBillingInfo) to PostTextConsumeQuota
- Update tool pricing calls to use nightly's generic GetToolPriceForModel/GetToolPrice API
This commit is contained in:
CaIon
2026-04-02 00:39:13 +08:00
parent d385d7abfe a706f00287
commit 35d0704640
122 changed files with 8307 additions and 3923 deletions
Download Patch File Download Diff File Expand all files Collapse all files
service/quota.go
-118
View File
@@ -251,124 +251,6 @@ func PostWssConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, mod
})
}
func PostClaudeConsumeQuota(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage) {
if usage != nil {
ObserveChannelAffinityUsageCacheByRelayFormat(ctx, usage, relayInfo.GetFinalRequestRelayFormat())
}
var tieredUsedVars map[string]bool
if snap := relayInfo.TieredBillingSnapshot; snap != nil {
tieredUsedVars = billingexpr.UsedVars(snap.ExprString)
}
var tieredResult *billingexpr.TieredResult
tieredOk, tieredQuota, tieredRes := TryTieredSettle(relayInfo, BuildTieredTokenParams(usage, true, tieredUsedVars))
if tieredOk {
tieredResult = tieredRes
}
useTimeSeconds := time.Now().Unix() - relayInfo.StartTime.Unix()
promptTokens := usage.PromptTokens
completionTokens := usage.CompletionTokens
modelName := relayInfo.OriginModelName
tokenName := ctx.GetString("token_name")
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 := relayInfo.PriceData.CacheCreationRatio
cacheCreationRatio5m := relayInfo.PriceData.CacheCreation5mRatio
cacheCreationRatio1h := relayInfo.PriceData.CacheCreation1hRatio
cacheCreationTokens := usage.PromptTokensDetails.CachedCreationTokens
cacheCreationTokens5m := usage.ClaudeCacheCreation5mTokens
cacheCreationTokens1h := usage.ClaudeCacheCreation1hTokens
if relayInfo.ChannelType == constant.ChannelTypeOpenRouter {
promptTokens -= cacheTokens
isUsingCustomSettings := relayInfo.PriceData.UsePrice || hasCustomModelRatio(modelName, relayInfo.PriceData.ModelRatio)
if cacheCreationTokens == 0 && relayInfo.PriceData.CacheCreationRatio != 1 && usage.Cost != 0 && !isUsingCustomSettings {
maybeCacheCreationTokens := CalcOpenRouterCacheCreateTokens(*usage, relayInfo.PriceData)
if maybeCacheCreationTokens >= 0 && promptTokens >= maybeCacheCreationTokens {
cacheCreationTokens = maybeCacheCreationTokens
}
}
promptTokens -= cacheCreationTokens
}
calculateQuota := 0.0
if !relayInfo.PriceData.UsePrice {
calculateQuota = float64(promptTokens)
calculateQuota += float64(cacheTokens) * cacheRatio
calculateQuota += float64(cacheCreationTokens5m) * cacheCreationRatio5m
calculateQuota += float64(cacheCreationTokens1h) * cacheCreationRatio1h
remainingCacheCreationTokens := cacheCreationTokens - cacheCreationTokens5m - cacheCreationTokens1h
if remainingCacheCreationTokens > 0 {
calculateQuota += float64(remainingCacheCreationTokens) * cacheCreationRatio
}
calculateQuota += float64(completionTokens) * completionRatio
calculateQuota = calculateQuota * groupRatio * modelRatio
} else {
calculateQuota = modelPrice * common.QuotaPerUnit * groupRatio
}
if modelRatio != 0 && calculateQuota <= 0 {
calculateQuota = 1
}
quota := int(calculateQuota)
if tieredOk {
quota = tieredQuota
}
totalTokens := promptTokens + completionTokens
var logContent string
// record all the consume log even if quota is 0
if totalTokens == 0 {
// in this case, must be some error happened
// 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）")
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)
}
if err := SettleBilling(ctx, relayInfo, quota); err != nil {
logger.LogError(ctx, "error settling billing: "+err.Error())
}
other := GenerateClaudeOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio,
cacheTokens, cacheRatio,
cacheCreationTokens, cacheCreationRatio,
cacheCreationTokens5m, cacheCreationRatio5m,
cacheCreationTokens1h, cacheCreationRatio1h,
modelPrice, relayInfo.PriceData.GroupRatioInfo.GroupSpecialRatio)
if tieredResult != nil {
InjectTieredBillingInfo(other, relayInfo, tieredResult)
}
model.RecordConsumeLog(ctx, relayInfo.UserId, model.RecordConsumeLogParams{
ChannelId: relayInfo.ChannelId,
PromptTokens: promptTokens,
CompletionTokens: completionTokens,
ModelName: modelName,
TokenName: tokenName,
Quota: quota,
Content: logContent,
TokenId: relayInfo.TokenId,
UseTimeSeconds: int(useTimeSeconds),
IsStream: relayInfo.IsStream,
Group: relayInfo.UsingGroup,
Other: other,
})
}
func CalcOpenRouterCacheCreateTokens(usage dto.Usage, priceData types.PriceData) int {
if priceData.CacheCreationRatio == 1 {
return 0