Files
new-api/service/log_info_generate.go
T
Calcium-Ion 0ed497f066 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
2026-09-01 21:53:35 +08:00

333 lines
12 KiB
Go

package service
import (
"encoding/base64"
"fmt"
"strings"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/logger"
"github.com/QuantumNous/new-api/pkg/billingexpr"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/QuantumNous/new-api/relaykit/types"
hosttypes "github.com/QuantumNous/new-api/types"
"github.com/gin-gonic/gin"
)
// attachQuotaSaturationToOther nests a quota saturation marker under
// other.admin_info.quota_saturation. Nesting under admin_info makes it
// admin-only for free, since model.formatUserLogs strips the whole admin_info
// object for non-admin viewers. Creates admin_info if absent. No-op when the
// clamp is nil (the common case: no saturation happened).
func attachQuotaSaturationToOther(other map[string]interface{}, clamp *common.QuotaClamp) {
if clamp == nil || other == nil {
return
}
adminInfo, ok := other["admin_info"].(map[string]interface{})
if !ok || adminInfo == nil {
adminInfo = map[string]interface{}{}
other["admin_info"] = adminInfo
}
adminInfo["quota_saturation"] = clamp.AuditMap()
}
// attachQuotaSaturation records the request's quota clamp (if any) onto the
// consume log's other.admin_info and emits a request-correlated backend audit
// line. Called right before RecordConsumeLog on the text/audio/wss paths.
func attachQuotaSaturation(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil {
return
}
clamp := relayInfo.QuotaClamp
if clamp == nil {
return
}
attachQuotaSaturationToOther(other, clamp)
logger.LogWarn(ctx, fmt.Sprintf("quota saturation on consume log: op=%s kind=%s original=%g clamped=%d user=%d model=%s",
clamp.Op, clamp.Kind, clamp.Original, clamp.Clamped, relayInfo.UserId, relayInfo.GetBillingModelName()))
}
func appendRequestPath(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if other == nil {
return
}
if ctx != nil && ctx.Request != nil && ctx.Request.URL != nil {
if path := ctx.Request.URL.Path; path != "" {
other["request_path"] = path
return
}
}
if relayInfo != nil && relayInfo.RequestURLPath != "" {
path := relayInfo.RequestURLPath
if idx := strings.Index(path, "?"); idx != -1 {
path = path[:idx]
}
other["request_path"] = path
}
}
func GenerateTextOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelRatio, groupRatio, completionRatio float64,
cacheTokens int, cacheRatio float64, modelPrice float64, userGroupRatio float64) map[string]interface{} {
other := make(map[string]interface{})
other["model_ratio"] = modelRatio
other["group_ratio"] = groupRatio
other["completion_ratio"] = completionRatio
other["cache_tokens"] = cacheTokens
other["cache_ratio"] = cacheRatio
other["model_price"] = modelPrice
other["user_group_ratio"] = userGroupRatio
other["frt"] = float64(relayInfo.FirstResponseTime.UnixMilli() - relayInfo.StartTime.UnixMilli())
if relayInfo.ReasoningEffort != "" {
other["reasoning_effort"] = relayInfo.ReasoningEffort
}
if relayInfo.IsModelMapped {
other["is_model_mapped"] = true
other["upstream_model_name"] = relayInfo.UpstreamModelName
}
isSystemPromptOverwritten := common.GetContextKeyBool(ctx, constant.ContextKeySystemPromptOverride)
if isSystemPromptOverwritten {
other["is_system_prompt_overwritten"] = true
}
adminInfo := make(map[string]interface{})
adminInfo["use_channel"] = ctx.GetStringSlice("use_channel")
if billingModel := relayInfo.GetBillingModelName(); billingModel != "" && billingModel != relayInfo.OriginModelName {
adminInfo["billing_model"] = billingModel
}
if diagnostics := relayInfo.ConversionDiagnostics(); len(diagnostics) > 0 {
adminInfo["conversion_diagnostics"] = diagnostics
}
if relayInfo.ConversionDiagnosticsTruncated() {
adminInfo["conversion_diagnostics_truncated"] = true
}
isMultiKey := common.GetContextKeyBool(ctx, constant.ContextKeyChannelIsMultiKey)
if isMultiKey {
adminInfo["is_multi_key"] = true
adminInfo["multi_key_index"] = common.GetContextKeyInt(ctx, constant.ContextKeyChannelMultiKeyIndex)
}
isLocalCountTokens := common.GetContextKeyBool(ctx, constant.ContextKeyLocalCountTokens)
if isLocalCountTokens {
adminInfo["local_count_tokens"] = isLocalCountTokens
}
AppendChannelAffinityAdminInfo(ctx, adminInfo)
other["admin_info"] = adminInfo
appendRequestPath(ctx, relayInfo, other)
appendRequestConversionChain(relayInfo, other)
appendFinalRequestFormat(relayInfo, other)
appendBillingInfo(relayInfo, other)
appendParamOverrideInfo(relayInfo, other)
appendStreamStatus(relayInfo, other)
return other
}
func appendParamOverrideInfo(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil || other == nil || len(relayInfo.ParamOverrideAudit) == 0 {
return
}
other["po"] = relayInfo.ParamOverrideAudit
}
func appendStreamStatus(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil || other == nil || !relayInfo.IsStream || relayInfo.StreamStatus == nil {
return
}
ss := relayInfo.StreamStatus
status := "ok"
if !ss.IsNormalEnd() || ss.HasErrors() {
status = "error"
}
streamInfo := map[string]interface{}{
"status": status,
"end_reason": string(ss.EndReason),
}
if ss.EndError != nil {
streamInfo["end_error"] = ss.EndError.Error()
}
if ss.ErrorCount > 0 {
streamInfo["error_count"] = ss.ErrorCount
messages := make([]string, 0, len(ss.Errors))
for _, e := range ss.Errors {
messages = append(messages, e.Message)
}
streamInfo["errors"] = messages
}
other["stream_status"] = streamInfo
}
func appendBillingInfo(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil || other == nil {
return
}
// billing_source: "wallet" or "subscription"
if relayInfo.BillingSource != "" {
other["billing_source"] = relayInfo.BillingSource
}
if relayInfo.UserSetting.BillingPreference != "" {
other["billing_preference"] = relayInfo.UserSetting.BillingPreference
}
if relayInfo.BillingSource == "subscription" {
if relayInfo.SubscriptionId != 0 {
other["subscription_id"] = relayInfo.SubscriptionId
}
if relayInfo.SubscriptionPreConsumed > 0 {
other["subscription_pre_consumed"] = relayInfo.SubscriptionPreConsumed
}
// post_delta: settlement delta applied after actual usage is known (can be negative for refund)
if relayInfo.SubscriptionPostDelta != 0 {
other["subscription_post_delta"] = relayInfo.SubscriptionPostDelta
}
if relayInfo.SubscriptionPlanId != 0 {
other["subscription_plan_id"] = relayInfo.SubscriptionPlanId
}
if relayInfo.SubscriptionPlanTitle != "" {
other["subscription_plan_title"] = relayInfo.SubscriptionPlanTitle
}
// Compute "this request" subscription consumed + remaining
consumed := relayInfo.SubscriptionPreConsumed + relayInfo.SubscriptionPostDelta
usedFinal := relayInfo.SubscriptionAmountUsedAfterPreConsume + relayInfo.SubscriptionPostDelta
if consumed < 0 {
consumed = 0
}
if usedFinal < 0 {
usedFinal = 0
}
if relayInfo.SubscriptionAmountTotal > 0 {
remain := relayInfo.SubscriptionAmountTotal - usedFinal
if remain < 0 {
remain = 0
}
other["subscription_total"] = relayInfo.SubscriptionAmountTotal
other["subscription_used"] = usedFinal
other["subscription_remain"] = remain
}
if consumed > 0 {
other["subscription_consumed"] = consumed
}
// Wallet quota is not deducted when billed from subscription.
other["wallet_quota_deducted"] = 0
}
}
func appendRequestConversionChain(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil || other == nil {
return
}
if len(relayInfo.RequestConversionChain) == 0 {
return
}
chain := make([]string, 0, len(relayInfo.RequestConversionChain))
for _, f := range relayInfo.RequestConversionChain {
switch f {
case types.RelayFormatOpenAI:
chain = append(chain, "OpenAI Compatible")
case types.RelayFormatClaude:
chain = append(chain, "Claude Messages")
case types.RelayFormatGemini:
chain = append(chain, "Google Gemini")
case types.RelayFormatOpenAIResponses:
chain = append(chain, "OpenAI Responses")
default:
chain = append(chain, string(f))
}
}
if len(chain) == 0 {
return
}
other["request_conversion"] = chain
}
func appendFinalRequestFormat(relayInfo *relaycommon.RelayInfo, other map[string]interface{}) {
if relayInfo == nil || other == nil {
return
}
if relayInfo.GetFinalRequestRelayFormat() == types.RelayFormatClaude {
// claude indicates the final upstream request format is Claude Messages.
// Frontend log rendering uses this to keep the original Claude input display.
other["claude"] = true
}
}
func GenerateWssOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.RealtimeUsage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice, userGroupRatio float64) map[string]interface{} {
info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, 0, 0.0, modelPrice, userGroupRatio)
info["ws"] = true
info["audio_input"] = usage.InputTokenDetails.AudioTokens
info["audio_output"] = usage.OutputTokenDetails.AudioTokens
info["text_input"] = usage.InputTokenDetails.TextTokens
info["text_output"] = usage.OutputTokenDetails.TextTokens
info["audio_ratio"] = audioRatio
info["audio_completion_ratio"] = audioCompletionRatio
return info
}
func GenerateAudioOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, usage *dto.Usage, modelRatio, groupRatio, completionRatio, audioRatio, audioCompletionRatio, modelPrice, userGroupRatio float64) map[string]interface{} {
info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, 0, 0.0, modelPrice, userGroupRatio)
info["audio"] = true
info["audio_input"] = usage.PromptTokensDetails.AudioTokens
info["audio_output"] = usage.CompletionTokenDetails.AudioTokens
info["text_input"] = usage.PromptTokensDetails.TextTokens
info["text_output"] = usage.CompletionTokenDetails.TextTokens
info["audio_ratio"] = audioRatio
info["audio_completion_ratio"] = audioCompletionRatio
return info
}
func GenerateClaudeOtherInfo(ctx *gin.Context, relayInfo *relaycommon.RelayInfo, modelRatio, groupRatio, completionRatio float64,
cacheTokens int, cacheRatio float64,
cacheCreationTokens int, cacheCreationRatio float64,
cacheCreationTokens5m int, cacheCreationRatio5m float64,
cacheCreationTokens1h int, cacheCreationRatio1h float64,
modelPrice float64, userGroupRatio float64) map[string]interface{} {
info := GenerateTextOtherInfo(ctx, relayInfo, modelRatio, groupRatio, completionRatio, cacheTokens, cacheRatio, modelPrice, userGroupRatio)
info["claude"] = true
info["cache_creation_tokens"] = cacheCreationTokens
info["cache_creation_ratio"] = cacheCreationRatio
if cacheCreationTokens5m != 0 {
info["cache_creation_tokens_5m"] = cacheCreationTokens5m
info["cache_creation_ratio_5m"] = cacheCreationRatio5m
}
if cacheCreationTokens1h != 0 {
info["cache_creation_tokens_1h"] = cacheCreationTokens1h
info["cache_creation_ratio_1h"] = cacheCreationRatio1h
}
return info
}
func GenerateMjOtherInfo(relayInfo *relaycommon.RelayInfo, priceData hosttypes.PriceData) map[string]interface{} {
other := make(map[string]interface{})
other["model_price"] = priceData.ModelPrice
other["group_ratio"] = priceData.GroupRatioInfo.GroupRatio
if priceData.GroupRatioInfo.HasSpecialRatio {
other["user_group_ratio"] = priceData.GroupRatioInfo.GroupSpecialRatio
}
appendRequestPath(nil, relayInfo, other)
return other
}
// InjectTieredBillingInfo overlays tiered billing fields onto an existing
// module-specific other map. Call this after GenerateTextOtherInfo /
// GenerateClaudeOtherInfo / etc. when the request used tiered_expr billing.
func InjectTieredBillingInfo(other map[string]interface{}, relayInfo *relaycommon.RelayInfo, result *billingexpr.TieredResult) {
if relayInfo == nil || other == nil {
return
}
snap := relayInfo.TieredBillingSnapshot
if snap == nil {
return
}
other["billing_mode"] = "tiered_expr"
other["expr_b64"] = base64.StdEncoding.EncodeToString([]byte(snap.ExprString))
if result != nil {
other["matched_tier"] = result.MatchedTier
if len(result.RequestRules) > 0 {
other["request_rules"] = result.RequestRules
}
}
}