* 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
195 lines
5.2 KiB
Go
195 lines
5.2 KiB
Go
package common
|
|
|
|
import (
|
|
"crypto/sha256"
|
|
"encoding/hex"
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/setting/operation_setting"
|
|
)
|
|
|
|
var reservedBillableToolNames = map[string]struct{}{
|
|
dto.BuildInToolWebSearchPreview: {},
|
|
dto.BuildInToolWebSearch: {},
|
|
dto.BuildInToolFileSearch: {},
|
|
dto.BuildInToolGoogleSearch: {},
|
|
dto.BuildInToolImageGeneration: {},
|
|
}
|
|
|
|
// CountBillableToolCall is the single entry point for per-call tool billing counts.
|
|
// Built-in call types always count; custom function/tool_use names only count when priced.
|
|
func (info *RelayInfo) CountBillableToolCall(itemType string, functionName string) {
|
|
if info == nil {
|
|
return
|
|
}
|
|
if info.ResponsesUsageInfo == nil {
|
|
info.ResponsesUsageInfo = &ResponsesUsageInfo{
|
|
BuiltInTools: make(map[string]*BuildInToolInfo),
|
|
}
|
|
}
|
|
if info.ResponsesUsageInfo.BuiltInTools == nil {
|
|
info.ResponsesUsageInfo.BuiltInTools = make(map[string]*BuildInToolInfo)
|
|
}
|
|
|
|
switch itemType {
|
|
case dto.BuildInCallWebSearchCall:
|
|
info.incrementBillableToolCall(resolveWebSearchToolName(info.ResponsesUsageInfo.BuiltInTools))
|
|
case dto.BuildInCallFileSearchCall:
|
|
info.incrementBillableToolCall(dto.BuildInToolFileSearch)
|
|
case dto.BuildInCallFunctionCall, dto.BuildInCallToolUse:
|
|
if functionName == "" {
|
|
return
|
|
}
|
|
if _, reserved := reservedBillableToolNames[functionName]; reserved {
|
|
return
|
|
}
|
|
if operation_setting.GetToolPriceForModel(functionName, info.OriginModelName) <= 0 {
|
|
return
|
|
}
|
|
info.incrementBillableToolCall(functionName)
|
|
}
|
|
}
|
|
|
|
func resolveWebSearchToolName(tools map[string]*BuildInToolInfo) string {
|
|
if _, ok := tools[dto.BuildInToolWebSearchPreview]; ok {
|
|
return dto.BuildInToolWebSearchPreview
|
|
}
|
|
if _, ok := tools[dto.BuildInToolWebSearch]; ok {
|
|
return dto.BuildInToolWebSearch
|
|
}
|
|
return dto.BuildInToolWebSearchPreview
|
|
}
|
|
|
|
func (info *RelayInfo) incrementBillableToolCall(name string) {
|
|
if existing, ok := info.ResponsesUsageInfo.BuiltInTools[name]; ok && existing != nil {
|
|
existing.CallCount++
|
|
return
|
|
}
|
|
info.ResponsesUsageInfo.BuiltInTools[name] = &BuildInToolInfo{
|
|
ToolName: name,
|
|
CallCount: 1,
|
|
}
|
|
}
|
|
|
|
// ImageGenerationCallCounter counts completed Responses image_generation_call
|
|
// outputs with stream-safe identity deduplication.
|
|
type ImageGenerationCallCounter struct {
|
|
seen map[string]struct{}
|
|
count int
|
|
}
|
|
|
|
// Observe records one completed final image output when billable.
|
|
// outputIndex may be nil; when set and nonnegative it participates in dedup.
|
|
func (c *ImageGenerationCallCounter) Observe(item *dto.ResponsesOutput, outputIndex *int) {
|
|
if c == nil || item == nil {
|
|
return
|
|
}
|
|
if item.Type != dto.ResponsesOutputTypeImageGenerationCall {
|
|
return
|
|
}
|
|
if strings.TrimSpace(item.Result) == "" {
|
|
return
|
|
}
|
|
switch strings.ToLower(strings.TrimSpace(item.Status)) {
|
|
case "failed", "cancelled", "canceled", "incomplete", "partial":
|
|
return
|
|
}
|
|
|
|
aliases := make([]string, 0, 4)
|
|
if item.ID != "" {
|
|
aliases = append(aliases, "id:"+item.ID)
|
|
}
|
|
if item.CallId != "" {
|
|
aliases = append(aliases, "call:"+item.CallId)
|
|
}
|
|
if outputIndex != nil && *outputIndex >= 0 {
|
|
aliases = append(aliases, fmt.Sprintf("index:%d", *outputIndex))
|
|
}
|
|
sum := sha256.Sum256([]byte(item.Result))
|
|
aliases = append(aliases, "result:"+hex.EncodeToString(sum[:]))
|
|
|
|
if c.seen == nil {
|
|
c.seen = make(map[string]struct{})
|
|
}
|
|
for _, alias := range aliases {
|
|
if _, ok := c.seen[alias]; ok {
|
|
return
|
|
}
|
|
}
|
|
for _, alias := range aliases {
|
|
c.seen[alias] = struct{}{}
|
|
}
|
|
c.count++
|
|
}
|
|
|
|
// Reset clears pending observations (used when a terminal response fails).
|
|
func (c *ImageGenerationCallCounter) Reset() {
|
|
if c == nil {
|
|
return
|
|
}
|
|
c.seen = nil
|
|
c.count = 0
|
|
}
|
|
|
|
// Count returns the deduplicated completed image output count before commit capping.
|
|
func (c *ImageGenerationCallCounter) Count() int {
|
|
if c == nil {
|
|
return 0
|
|
}
|
|
return c.count
|
|
}
|
|
|
|
// Commit writes the capped completed-output count into RelayInfo once.
|
|
// Request tool declarations alone must not become billable calls.
|
|
func (c *ImageGenerationCallCounter) Commit(info *RelayInfo) {
|
|
if info == nil {
|
|
return
|
|
}
|
|
if info.ResponsesUsageInfo == nil {
|
|
info.ResponsesUsageInfo = &ResponsesUsageInfo{
|
|
BuiltInTools: make(map[string]*BuildInToolInfo),
|
|
}
|
|
}
|
|
if info.ResponsesUsageInfo.BuiltInTools == nil {
|
|
info.ResponsesUsageInfo.BuiltInTools = make(map[string]*BuildInToolInfo)
|
|
}
|
|
|
|
count := 0
|
|
if c != nil {
|
|
count = c.count
|
|
}
|
|
if count > dto.MaxImageN {
|
|
count = dto.MaxImageN
|
|
}
|
|
|
|
if existing, ok := info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration]; ok && existing != nil {
|
|
existing.CallCount = count
|
|
return
|
|
}
|
|
info.ResponsesUsageInfo.BuiltInTools[dto.BuildInToolImageGeneration] = &BuildInToolInfo{
|
|
ToolName: dto.BuildInToolImageGeneration,
|
|
CallCount: count,
|
|
}
|
|
}
|
|
|
|
// IsNonBillableResponsesStatus reports terminal response statuses that must not
|
|
// bill pending image_generation observations.
|
|
func IsNonBillableResponsesStatus(status []byte) bool {
|
|
if len(status) == 0 {
|
|
return false
|
|
}
|
|
var s string
|
|
if err := common.Unmarshal(status, &s); err != nil {
|
|
return false
|
|
}
|
|
switch strings.ToLower(strings.TrimSpace(s)) {
|
|
case "failed", "cancelled", "canceled", "incomplete":
|
|
return true
|
|
default:
|
|
return false
|
|
}
|
|
}
|