* 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
134 lines
4.1 KiB
Go
134 lines
4.1 KiB
Go
package openai
|
|
|
|
import (
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
)
|
|
|
|
func applyUsagePostProcessing(info *relaycommon.RelayInfo, usage *dto.Usage, responseBody []byte) {
|
|
if info == nil || usage == nil {
|
|
return
|
|
}
|
|
|
|
switch info.ChannelType {
|
|
case constant.ChannelTypeDeepSeek:
|
|
if usage.PromptTokensDetails.CachedTokens == 0 && usage.PromptCacheHitTokens != 0 {
|
|
usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
|
|
}
|
|
case constant.ChannelTypeZhipu_v4:
|
|
// 智普的cached_tokens在标准位置: usage.prompt_tokens_details.cached_tokens
|
|
if usage.PromptTokensDetails.CachedTokens == 0 {
|
|
if usage.InputTokensDetails != nil && usage.InputTokensDetails.CachedTokens > 0 {
|
|
usage.PromptTokensDetails.CachedTokens = usage.InputTokensDetails.CachedTokens
|
|
} else if cachedTokens, ok := extractCachedTokensFromBody(responseBody); ok {
|
|
usage.PromptTokensDetails.CachedTokens = cachedTokens
|
|
} else if usage.PromptCacheHitTokens > 0 {
|
|
usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
|
|
}
|
|
}
|
|
case constant.ChannelTypeMoonshot:
|
|
// Moonshot的cached_tokens在非标准位置: choices[].usage.cached_tokens
|
|
if usage.PromptTokensDetails.CachedTokens == 0 {
|
|
if usage.InputTokensDetails != nil && usage.InputTokensDetails.CachedTokens > 0 {
|
|
usage.PromptTokensDetails.CachedTokens = usage.InputTokensDetails.CachedTokens
|
|
} else if cachedTokens, ok := extractMoonshotCachedTokensFromBody(responseBody); ok {
|
|
usage.PromptTokensDetails.CachedTokens = cachedTokens
|
|
} else if cachedTokens, ok := extractCachedTokensFromBody(responseBody); ok {
|
|
usage.PromptTokensDetails.CachedTokens = cachedTokens
|
|
} else if usage.PromptCacheHitTokens > 0 {
|
|
usage.PromptTokensDetails.CachedTokens = usage.PromptCacheHitTokens
|
|
}
|
|
}
|
|
case constant.ChannelTypeOpenAI:
|
|
if usage.PromptTokensDetails.CachedTokens == 0 {
|
|
if cachedTokens, ok := extractLlamaCachedTokensFromBody(responseBody); ok {
|
|
usage.PromptTokensDetails.CachedTokens = cachedTokens
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func extractCachedTokensFromBody(body []byte) (int, bool) {
|
|
if len(body) == 0 {
|
|
return 0, false
|
|
}
|
|
|
|
var payload struct {
|
|
Usage struct {
|
|
PromptTokensDetails struct {
|
|
CachedTokens *int `json:"cached_tokens"`
|
|
} `json:"prompt_tokens_details"`
|
|
CachedTokens *int `json:"cached_tokens"`
|
|
PromptCacheHitTokens *int `json:"prompt_cache_hit_tokens"`
|
|
} `json:"usage"`
|
|
}
|
|
|
|
if err := common.Unmarshal(body, &payload); err != nil {
|
|
return 0, false
|
|
}
|
|
|
|
if payload.Usage.PromptTokensDetails.CachedTokens != nil {
|
|
return *payload.Usage.PromptTokensDetails.CachedTokens, true
|
|
}
|
|
if payload.Usage.CachedTokens != nil {
|
|
return *payload.Usage.CachedTokens, true
|
|
}
|
|
if payload.Usage.PromptCacheHitTokens != nil {
|
|
return *payload.Usage.PromptCacheHitTokens, true
|
|
}
|
|
return 0, false
|
|
}
|
|
|
|
// extractMoonshotCachedTokensFromBody 从Moonshot的非标准位置提取cached_tokens
|
|
// Moonshot的流式响应格式: {"choices":[{"usage":{"cached_tokens":111}}]}
|
|
func extractMoonshotCachedTokensFromBody(body []byte) (int, bool) {
|
|
if len(body) == 0 {
|
|
return 0, false
|
|
}
|
|
|
|
var payload struct {
|
|
Choices []struct {
|
|
Usage struct {
|
|
CachedTokens *int `json:"cached_tokens"`
|
|
} `json:"usage"`
|
|
} `json:"choices"`
|
|
}
|
|
|
|
if err := common.Unmarshal(body, &payload); err != nil {
|
|
return 0, false
|
|
}
|
|
|
|
// 遍历choices查找cached_tokens
|
|
for _, choice := range payload.Choices {
|
|
if choice.Usage.CachedTokens != nil && *choice.Usage.CachedTokens > 0 {
|
|
return *choice.Usage.CachedTokens, true
|
|
}
|
|
}
|
|
|
|
return 0, false
|
|
}
|
|
|
|
// extractLlamaCachedTokensFromBody 从llama.cpp的非标准位置提取cache_n
|
|
func extractLlamaCachedTokensFromBody(body []byte) (int, bool) {
|
|
if len(body) == 0 {
|
|
return 0, false
|
|
}
|
|
|
|
var payload struct {
|
|
Timings struct {
|
|
CachedTokens *int `json:"cache_n"`
|
|
} `json:"timings"`
|
|
}
|
|
|
|
if err := common.Unmarshal(body, &payload); err != nil {
|
|
return 0, false
|
|
}
|
|
|
|
if payload.Timings.CachedTokens == nil {
|
|
return 0, false
|
|
}
|
|
return *payload.Timings.CachedTokens, true
|
|
}
|