* test(relayconvert): add golden snapshot matrix and relaykit boundary guard Phase 0 of the relaykit extraction plan: pin byte-level output of every registered (from,to) request/response/stream conversion route, and forbid kit-bound packages from growing host-only imports. * wip(relayconvert): drop gin.Context from converter signatures; add convmeta draft Phase 1 in progress: relayconvert now takes context.Context; host media resolver adapts gin.Context back at the service boundary. * refactor(relayconvert): decouple converters from RelayInfo, gin, and settings Phase 1 of the relaykit extraction plan: - converters now depend on convmeta.Meta (implemented by RelayInfo) instead of *relaycommon.RelayInfo; ClaudeConvertInfo and the format guesser move to convmeta with aliases left behind - host settings reach converters via a convmeta.Options snapshot built in RelayInfo.ConvOptions; no more model_setting/reasoning global reads inside the conversion layer - effort-suffix helpers move to service/relayconvert/reasoning (old package forwards); chat-to-responses upgrade policy moves to service (host routing logic, not conversion) - golden conversion matrix unchanged * test(relayconvert): tighten boundary — kit packages now free of gin/setting imports * refactor(dto): drop gin and logger dependencies Phase 2 (part 1): dto.Request.IsStream now takes *http.Request instead of *gin.Context (Gemini's impl reads query/path off the std request); dto's three logger calls become common.SysError. Boundary test allowlist is now empty — kit-bound packages import no gin/setting/logger/model. * refactor(kit): extract dependency-free kitutil; dto/types/relayconvert stop importing common Phase 2 of the relaykit extraction plan: - new service/relayconvert/kitutil holds the pure helpers the kit needs (JSON wrappers, pointer/string/uuid/timestamp utils, MaskSensitiveInfo, pluggable LogInfo/LogError hooks, Debug flag) - dto, types, and all relayconvert packages now use kitutil; their only remaining internal deps are dto/types/constant - common keeps every original symbol (MaskSensitiveInfo delegates to kitutil) so host code is untouched; main.go routes kit logging into common.SysLog/SysError and mirrors DebugEnabled - golden conversion matrix unchanged * refactor(kit): move EndpointType/FinishReason to types; OpenRouter dialect via Options Kit packages (dto/types/relayconvert/reasonmap) no longer import constant: - EndpointType and finish-reason values live in types; constant re-exports - the OpenRouter special-case in claude->openai request conversion reads Options.OpenRouterDialect, set by the host from the channel type; InitChannelMeta invalidates the cached snapshot on channel switch * refactor: extract relaykit submodule (dto/types/relayconvert/reasonmap) Phase 3 of the relaykit extraction plan: - new go module github.com/QuantumNous/new-api/relaykit containing dto (minus task family), types, relayconvert (with convmeta/kitutil/reasoning), and reasonmap; host consumes it via require + replace, go.work for dev - task-family dto (task/suno/midjourney/video) stays in the host dto package; dual-consumer host files alias it as taskdto - relaykit builds and tests standalone (GOWORK=off): no host imports, no gin, no DB, no settings - golden conversion matrix unchanged * build(docker): copy relaykit/go.mod before go mod download The local-replace submodule's go.mod must exist inside the build context for the main module graph to resolve. * fix: address relaykit extraction regressions * fix: address relaykit review regressions * docs: document Meta nil receiver contract * fix(relaykit): fail OpenAI→Claude conversion without max_tokens; reject negative default_max_tokens The Claude Messages API requires max_tokens (omitting it is a 400 "Field required"), but with a nil Options.Claude.DefaultMaxTokens hook the converters silently emitted a request the upstream is guaranteed to reject. Both OpenAI Chat and Responses → Claude conversions now return sharedclaude.ErrMissingMaxTokens when no path (client value, default hook, thinking-adapter floor) supplied one. Unreachable in the host, which always configures the hook. Host side, claude.default_max_tokens now rejects negative values at the option API before persisting — they would wrap into huge unsigned values during conversion. Zero stays allowed: the current API treats max_tokens: 0 as cache pre-warming. * fix: make Gemini safety settings read path race-free
206 lines
7.4 KiB
Go
206 lines
7.4 KiB
Go
package service
|
|
|
|
import (
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
)
|
|
|
|
const (
|
|
usageBillingPathLocal = "local"
|
|
usageBillingPathUpstream = "upstream"
|
|
usageBillingPathOpenAI = "billing-usage-openai"
|
|
usageBillingPathOpenAIEstimated = "billing-usage-openai-estimated"
|
|
usageBillingPathAnthropic = "billing-usage-anthropic"
|
|
usageBillingPathAnthropicEstimated = "billing-usage-anthropic-estimated"
|
|
usageBillingPathGemini = "billing-usage-gemini"
|
|
usageBillingPathGeminiEstimated = "billing-usage-gemini-estimated"
|
|
)
|
|
|
|
func effectiveBillingUsage(usage *dto.Usage) *dto.Usage {
|
|
if billingUsage, ok := usageFromBillingUsage(usage); ok {
|
|
return billingUsage
|
|
}
|
|
return usage
|
|
}
|
|
|
|
func usageBillingPathForLog(isLocalCountTokens bool, usage *dto.Usage) string {
|
|
if isLocalCountTokens {
|
|
return usageBillingPathLocal
|
|
}
|
|
if usage == nil || usage.BillingUsage == nil {
|
|
return usageBillingPathUpstream
|
|
}
|
|
source := strings.TrimSpace(usage.BillingUsage.Source)
|
|
semantic := strings.TrimSpace(usage.BillingUsage.Semantic)
|
|
if strings.EqualFold(source, dto.BillingUsageSourceOAIChat) ||
|
|
strings.EqualFold(source, dto.BillingUsageSourceOAIResponses) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticOpenAI) {
|
|
if usage.BillingUsage.Estimated {
|
|
return usageBillingPathOpenAIEstimated
|
|
}
|
|
return usageBillingPathOpenAI
|
|
}
|
|
if strings.EqualFold(source, dto.BillingUsageSourceClaudeMessages) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticAnthropic) {
|
|
if usage.BillingUsage.Estimated {
|
|
return usageBillingPathAnthropicEstimated
|
|
}
|
|
return usageBillingPathAnthropic
|
|
}
|
|
if strings.EqualFold(source, dto.BillingUsageSourceGeminiChat) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticGemini) {
|
|
if usage.BillingUsage.Estimated {
|
|
return usageBillingPathGeminiEstimated
|
|
}
|
|
return usageBillingPathGemini
|
|
}
|
|
return usageBillingPathUpstream
|
|
}
|
|
|
|
func appendUsageBillingPathForLog(other map[string]interface{}, isLocalCountTokens bool, usage *dto.Usage) {
|
|
if other == nil {
|
|
return
|
|
}
|
|
adminInfo, ok := other["admin_info"].(map[string]interface{})
|
|
if !ok || adminInfo == nil {
|
|
adminInfo = make(map[string]interface{})
|
|
other["admin_info"] = adminInfo
|
|
}
|
|
adminInfo["usage_billing_path"] = usageBillingPathForLog(isLocalCountTokens, usage)
|
|
}
|
|
|
|
func usageFromBillingUsage(usage *dto.Usage) (*dto.Usage, bool) {
|
|
if usage == nil || usage.BillingUsage == nil {
|
|
return nil, false
|
|
}
|
|
billingUsage := usage.BillingUsage
|
|
source := strings.TrimSpace(billingUsage.Source)
|
|
semantic := strings.TrimSpace(billingUsage.Semantic)
|
|
|
|
if billingUsage.OpenAIUsage != nil &&
|
|
(strings.EqualFold(source, dto.BillingUsageSourceOAIChat) ||
|
|
strings.EqualFold(source, dto.BillingUsageSourceOAIResponses) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticOpenAI)) {
|
|
return usageFromOpenAIBillingUsage(billingUsage), true
|
|
}
|
|
|
|
if billingUsage.ClaudeUsage != nil &&
|
|
(strings.EqualFold(source, dto.BillingUsageSourceClaudeMessages) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticAnthropic)) {
|
|
return usageFromClaudeBillingUsage(billingUsage), true
|
|
}
|
|
|
|
if billingUsage.GeminiUsageMetadata != nil &&
|
|
(strings.EqualFold(source, dto.BillingUsageSourceGeminiChat) ||
|
|
strings.EqualFold(semantic, dto.BillingUsageSemanticGemini)) {
|
|
return usageFromGeminiBillingUsage(billingUsage), true
|
|
}
|
|
|
|
return nil, false
|
|
}
|
|
|
|
func usageFromOpenAIBillingUsage(billingUsage *dto.BillingUsage) *dto.Usage {
|
|
usage := *billingUsage.OpenAIUsage
|
|
if usage.PromptTokens == 0 && usage.InputTokens > 0 {
|
|
usage.PromptTokens = usage.InputTokens
|
|
}
|
|
if usage.CompletionTokens == 0 && usage.OutputTokens > 0 {
|
|
usage.CompletionTokens = usage.OutputTokens
|
|
}
|
|
if usage.InputTokens == 0 && usage.PromptTokens > 0 {
|
|
usage.InputTokens = usage.PromptTokens
|
|
}
|
|
if usage.OutputTokens == 0 && usage.CompletionTokens > 0 {
|
|
usage.OutputTokens = usage.CompletionTokens
|
|
}
|
|
if usage.TotalTokens == 0 {
|
|
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
|
|
}
|
|
usage.UsageSemantic = dto.BillingUsageSemanticOpenAI
|
|
usage.UsageSource = billingUsage.Source
|
|
usage.BillingUsage = dto.CloneBillingUsage(billingUsage)
|
|
return &usage
|
|
}
|
|
|
|
func usageFromClaudeBillingUsage(billingUsage *dto.BillingUsage) *dto.Usage {
|
|
claudeUsage := billingUsage.ClaudeUsage
|
|
cacheCreation5m := claudeUsage.GetCacheCreation5mTokens()
|
|
if cacheCreation5m == 0 {
|
|
cacheCreation5m = claudeUsage.ClaudeCacheCreation5mTokens
|
|
}
|
|
cacheCreation1h := claudeUsage.GetCacheCreation1hTokens()
|
|
if cacheCreation1h == 0 {
|
|
cacheCreation1h = claudeUsage.ClaudeCacheCreation1hTokens
|
|
}
|
|
|
|
usage := &dto.Usage{
|
|
PromptTokens: claudeUsage.InputTokens,
|
|
CompletionTokens: claudeUsage.OutputTokens,
|
|
TotalTokens: claudeUsage.InputTokens + claudeUsage.OutputTokens,
|
|
InputTokens: claudeUsage.InputTokens + claudeUsage.CacheReadInputTokens + claudeUsage.CacheCreationInputTokens,
|
|
OutputTokens: claudeUsage.OutputTokens,
|
|
UsageSemantic: dto.BillingUsageSemanticAnthropic,
|
|
UsageSource: dto.BillingUsageSourceClaudeMessages,
|
|
BillingUsage: dto.CloneBillingUsage(billingUsage),
|
|
ClaudeCacheCreation5mTokens: cacheCreation5m,
|
|
ClaudeCacheCreation1hTokens: cacheCreation1h,
|
|
}
|
|
usage.PromptTokensDetails.CachedTokens = claudeUsage.CacheReadInputTokens
|
|
usage.PromptTokensDetails.CachedCreationTokens = claudeUsage.CacheCreationInputTokens
|
|
return usage
|
|
}
|
|
|
|
func usageFromGeminiBillingUsage(billingUsage *dto.BillingUsage) *dto.Usage {
|
|
metadata := *billingUsage.GeminiUsageMetadata
|
|
promptTokens := metadata.PromptTokenCount + metadata.ToolUsePromptTokenCount
|
|
usage := &dto.Usage{
|
|
PromptTokens: promptTokens,
|
|
CompletionTokens: metadata.CandidatesTokenCount + metadata.ThoughtsTokenCount,
|
|
TotalTokens: metadata.TotalTokenCount,
|
|
UsageSemantic: dto.BillingUsageSemanticGemini,
|
|
UsageSource: dto.BillingUsageSourceGeminiChat,
|
|
BillingUsage: dto.CloneBillingUsage(billingUsage),
|
|
}
|
|
usage.CompletionTokenDetails.ReasoningTokens = metadata.ThoughtsTokenCount
|
|
usage.PromptTokensDetails.CachedTokens = metadata.CachedContentTokenCount
|
|
|
|
for _, detail := range metadata.PromptTokensDetails {
|
|
addGeminiInputTokenDetail(&usage.PromptTokensDetails, detail)
|
|
}
|
|
for _, detail := range metadata.ToolUsePromptTokensDetails {
|
|
addGeminiInputTokenDetail(&usage.PromptTokensDetails, detail)
|
|
}
|
|
for _, detail := range metadata.CandidatesTokensDetails {
|
|
switch detail.Modality {
|
|
case "IMAGE":
|
|
usage.CompletionTokenDetails.ImageTokens += detail.TokenCount
|
|
case "AUDIO":
|
|
usage.CompletionTokenDetails.AudioTokens += detail.TokenCount
|
|
case "TEXT":
|
|
usage.CompletionTokenDetails.TextTokens += detail.TokenCount
|
|
}
|
|
}
|
|
|
|
if usage.TotalTokens == 0 {
|
|
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
|
|
} else if usage.CompletionTokens <= 0 {
|
|
usage.CompletionTokens = usage.TotalTokens - usage.PromptTokens
|
|
}
|
|
if usage.PromptTokens > 0 && usage.PromptTokensDetails.TextTokens == 0 && usage.PromptTokensDetails.AudioTokens == 0 {
|
|
usage.PromptTokensDetails.TextTokens = usage.PromptTokens
|
|
}
|
|
return usage
|
|
}
|
|
|
|
func addGeminiInputTokenDetail(details *dto.InputTokenDetails, detail dto.GeminiPromptTokensDetails) {
|
|
switch detail.Modality {
|
|
case "AUDIO":
|
|
details.AudioTokens += detail.TokenCount
|
|
case "IMAGE":
|
|
details.ImageTokens += detail.TokenCount
|
|
case "TEXT":
|
|
details.TextTokens += detail.TokenCount
|
|
}
|
|
}
|