mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-14 00:01:53 +00:00
feat(relay): hosted-tool conversion fidelity, reasoning normalization, and billing usage integrity (#7137)
* feat(relaykit): preserve hosted tools across conversions - add protocol-neutral hosted-tool DTOs, conversion metadata, and loss policies - bridge citations, grounding metadata, and hosted-tool stream lifecycles - document the public conversion behavior and channel policy controls * refactor(relaykit): normalize reasoning and thinking intent - centralize provider-neutral reasoning intent, effort, and budget mappings - parse model suffixes at the host entry boundary while preserving provider-owned tails - keep adaptive Claude thinking and explicit zero-token compatibility consistent * fix(billing): preserve authoritative usage across relay hops - carry native BillingUsage sidecars through direct and streamed protocol bridges - merge partial and terminal usage monotonically with safe fallback settlement - retain cache metadata, penultimate usage, and per-call Gemini tool surcharges * feat(relay): bridge Responses with Claude and Gemini protocols - add direct request, response, and stream converters across supported relay formats - expose Claude count_tokens and Chat-to-Responses compatibility endpoints - carry conversion diagnostics through the host while retaining the curated public goldens * fix(relay): wire relaykit conversions into host channels - connect handlers, adaptors, and channel settings to the standalone conversion layer - keep model mapping, pricing identity, retries, and provider-specific suffix behavior aligned - ignore local audit artifacts and retain focused public regression coverage
This commit is contained in:
Calcium-Ion
+2
-156
@@ -1,10 +1,6 @@
|
||||
package service
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/QuantumNous/new-api/relaykit/dto"
|
||||
)
|
||||
import "github.com/QuantumNous/new-api/relaykit/dto"
|
||||
|
||||
const (
|
||||
usageBillingPathLocal = "local"
|
||||
@@ -70,155 +66,5 @@ 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
|
||||
}
|
||||
if inputDetails := usage.InputTokensDetails; inputDetails != nil {
|
||||
if usage.PromptTokensDetails.CachedTokens == 0 && inputDetails.CachedTokens > 0 {
|
||||
usage.PromptTokensDetails.CachedTokens = inputDetails.CachedTokens
|
||||
}
|
||||
if usage.PromptTokensDetails.CachedCreationTokens == 0 && inputDetails.CachedCreationTokens > 0 {
|
||||
usage.PromptTokensDetails.CachedCreationTokens = inputDetails.CachedCreationTokens
|
||||
}
|
||||
if usage.PromptTokensDetails.CacheWriteTokens == 0 && inputDetails.CacheWriteTokens > 0 {
|
||||
usage.PromptTokensDetails.CacheWriteTokens = inputDetails.CacheWriteTokens
|
||||
}
|
||||
if usage.PromptTokensDetails.TextTokens == 0 && inputDetails.TextTokens > 0 {
|
||||
usage.PromptTokensDetails.TextTokens = inputDetails.TextTokens
|
||||
}
|
||||
if usage.PromptTokensDetails.ImageTokens == 0 && inputDetails.ImageTokens > 0 {
|
||||
usage.PromptTokensDetails.ImageTokens = inputDetails.ImageTokens
|
||||
}
|
||||
if usage.PromptTokensDetails.AudioTokens == 0 && inputDetails.AudioTokens > 0 {
|
||||
usage.PromptTokensDetails.AudioTokens = inputDetails.AudioTokens
|
||||
}
|
||||
}
|
||||
if usage.PromptTokensDetails.CachedTokens == 0 && usage.PromptCacheHitTokens > 0 {
|
||||
usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
|
||||
}
|
||||
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
|
||||
}
|
||||
return usage.BillingUsage.CanonicalUsage()
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user