* 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
330 lines
11 KiB
Go
330 lines
11 KiB
Go
package model
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"math/rand"
|
|
"sort"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
"github.com/QuantumNous/new-api/logger"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/setting/ratio_setting"
|
|
)
|
|
|
|
var group2model2channels map[string]map[string][]int // enabled channel
|
|
var channelsIDM map[int]*Channel // all channels include disabled
|
|
// channel2advancedCustomConfig caches parsed Advanced Custom (type 58) configs so
|
|
// path-aware selection avoids re-parsing JSON per request. Refreshed on full sync.
|
|
var channel2advancedCustomConfig map[int]*dto.AdvancedCustomConfig
|
|
var channelSyncLock sync.RWMutex
|
|
|
|
func InitChannelCache() {
|
|
if !common.MemoryCacheEnabled {
|
|
InvalidatePricingCache()
|
|
return
|
|
}
|
|
newChannelId2channel := make(map[int]*Channel)
|
|
newChannel2advancedCustomConfig := make(map[int]*dto.AdvancedCustomConfig)
|
|
var channels []*Channel
|
|
DB.Find(&channels)
|
|
for _, channel := range channels {
|
|
newChannelId2channel[channel.Id] = channel
|
|
if channel.Type == constant.ChannelTypeAdvancedCustom {
|
|
if config := channel.GetOtherSettings().AdvancedCustom; config != nil {
|
|
newChannel2advancedCustomConfig[channel.Id] = config
|
|
}
|
|
}
|
|
}
|
|
var abilities []*Ability
|
|
DB.Find(&abilities)
|
|
groups := make(map[string]bool)
|
|
for _, ability := range abilities {
|
|
groups[ability.Group] = true
|
|
}
|
|
newGroup2model2channels := make(map[string]map[string][]int)
|
|
for group := range groups {
|
|
newGroup2model2channels[group] = make(map[string][]int)
|
|
}
|
|
for _, channel := range channels {
|
|
if channel.Status != common.ChannelStatusEnabled {
|
|
continue // skip disabled channels
|
|
}
|
|
groups := strings.Split(channel.Group, ",")
|
|
for _, group := range groups {
|
|
models := strings.Split(channel.Models, ",")
|
|
for _, model := range models {
|
|
if _, ok := newGroup2model2channels[group][model]; !ok {
|
|
newGroup2model2channels[group][model] = make([]int, 0)
|
|
}
|
|
newGroup2model2channels[group][model] = append(newGroup2model2channels[group][model], channel.Id)
|
|
}
|
|
}
|
|
}
|
|
|
|
// sort by priority
|
|
for group, model2channels := range newGroup2model2channels {
|
|
for model, channels := range model2channels {
|
|
sort.Slice(channels, func(i, j int) bool {
|
|
return newChannelId2channel[channels[i]].GetPriority() > newChannelId2channel[channels[j]].GetPriority()
|
|
})
|
|
newGroup2model2channels[group][model] = channels
|
|
}
|
|
}
|
|
|
|
channelSyncLock.Lock()
|
|
group2model2channels = newGroup2model2channels
|
|
//channelsIDM = newChannelId2channel
|
|
for i, channel := range newChannelId2channel {
|
|
if channel.ChannelInfo.IsMultiKey {
|
|
channel.Keys = channel.GetKeys()
|
|
if channel.ChannelInfo.MultiKeyMode == constant.MultiKeyModePolling {
|
|
if oldChannel, ok := channelsIDM[i]; ok {
|
|
// 存在旧的渠道,如果是多key且轮询,保留轮询索引信息
|
|
if oldChannel.ChannelInfo.IsMultiKey && oldChannel.ChannelInfo.MultiKeyMode == constant.MultiKeyModePolling {
|
|
channel.ChannelInfo.MultiKeyPollingIndex = oldChannel.ChannelInfo.MultiKeyPollingIndex
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
channelsIDM = newChannelId2channel
|
|
channel2advancedCustomConfig = newChannel2advancedCustomConfig
|
|
channelSyncLock.Unlock()
|
|
// Lock ordering: InvalidatePricingCache acquires updatePricingLock, and
|
|
// GetPricing (holding updatePricingLock) nests channelSyncLock.RLock via
|
|
// loadPricingAdvancedCustomConfigs. channelSyncLock MUST be released before
|
|
// invalidating the pricing cache, otherwise the reversed order deadlocks.
|
|
InvalidatePricingCache()
|
|
common.SysLog("channels synced from database")
|
|
}
|
|
|
|
func SyncChannelCache(frequency int) {
|
|
for {
|
|
time.Sleep(time.Duration(frequency) * time.Second)
|
|
common.SysLog("syncing channels from database")
|
|
InitChannelCache()
|
|
}
|
|
}
|
|
|
|
func GetRandomSatisfiedChannel(group string, model string, retry int, requestPath string) (*Channel, error) {
|
|
// if memory cache is disabled, get channel directly from database
|
|
if !common.MemoryCacheEnabled {
|
|
return GetChannel(group, model, retry, requestPath)
|
|
}
|
|
|
|
channelSyncLock.RLock()
|
|
defer channelSyncLock.RUnlock()
|
|
|
|
// First, try to find channels with the exact model name.
|
|
channels := filterChannelsByRequestPathAndModel(group2model2channels[group][model], requestPath, model)
|
|
|
|
// If no channels found, try to find channels with the normalized model name.
|
|
if len(channels) == 0 {
|
|
normalizedModel := ratio_setting.FormatMatchingModelName(model)
|
|
channels = filterChannelsByRequestPathAndModel(group2model2channels[group][normalizedModel], requestPath, model)
|
|
}
|
|
|
|
if len(channels) == 0 {
|
|
return nil, nil
|
|
}
|
|
|
|
if len(channels) == 1 {
|
|
if channel, ok := channelsIDM[channels[0]]; ok {
|
|
return channel, nil
|
|
}
|
|
return nil, fmt.Errorf("数据库一致性错误,渠道# %d 不存在,请联系管理员修复", channels[0])
|
|
}
|
|
|
|
uniquePriorities := make(map[int]bool)
|
|
for _, channelId := range channels {
|
|
if channel, ok := channelsIDM[channelId]; ok {
|
|
uniquePriorities[int(channel.GetPriority())] = true
|
|
} else {
|
|
return nil, fmt.Errorf("数据库一致性错误,渠道# %d 不存在,请联系管理员修复", channelId)
|
|
}
|
|
}
|
|
var sortedUniquePriorities []int
|
|
for priority := range uniquePriorities {
|
|
sortedUniquePriorities = append(sortedUniquePriorities, priority)
|
|
}
|
|
sort.Sort(sort.Reverse(sort.IntSlice(sortedUniquePriorities)))
|
|
|
|
if retry >= len(uniquePriorities) {
|
|
retry = len(uniquePriorities) - 1
|
|
}
|
|
targetPriority := int64(sortedUniquePriorities[retry])
|
|
|
|
// get the priority for the given retry number
|
|
var sumWeight = 0
|
|
var targetChannels []*Channel
|
|
for _, channelId := range channels {
|
|
if channel, ok := channelsIDM[channelId]; ok {
|
|
if channel.GetPriority() == targetPriority {
|
|
sumWeight += channel.GetWeight()
|
|
targetChannels = append(targetChannels, channel)
|
|
}
|
|
} else {
|
|
return nil, fmt.Errorf("数据库一致性错误,渠道# %d 不存在,请联系管理员修复", channelId)
|
|
}
|
|
}
|
|
|
|
if len(targetChannels) == 0 {
|
|
return nil, errors.New(fmt.Sprintf("no channel found, group: %s, model: %s, priority: %d", group, model, targetPriority))
|
|
}
|
|
|
|
// smoothing factor and adjustment
|
|
smoothingFactor := 1
|
|
smoothingAdjustment := 0
|
|
|
|
if sumWeight == 0 {
|
|
// when all channels have weight 0, set sumWeight to the number of channels and set smoothing adjustment to 100
|
|
// each channel's effective weight = 100
|
|
sumWeight = len(targetChannels) * 100
|
|
smoothingAdjustment = 100
|
|
} else if sumWeight/len(targetChannels) < 10 {
|
|
// when the average weight is less than 10, set smoothing factor to 100
|
|
smoothingFactor = 100
|
|
}
|
|
|
|
// Calculate the total weight of all channels up to endIdx
|
|
totalWeight := sumWeight * smoothingFactor
|
|
|
|
// Generate a random value in the range [0, totalWeight)
|
|
randomWeight := rand.Intn(totalWeight)
|
|
|
|
// Find a channel based on its weight
|
|
for _, channel := range targetChannels {
|
|
randomWeight -= channel.GetWeight()*smoothingFactor + smoothingAdjustment
|
|
if randomWeight < 0 {
|
|
return channel, nil
|
|
}
|
|
}
|
|
// return null if no channel is not found
|
|
return nil, errors.New("channel not found")
|
|
}
|
|
|
|
// filterChannelsByRequestPathAndModel restricts candidates by request path and
|
|
// model. Only Advanced Custom (type 58) channels are path-checked: they are kept
|
|
// only when one of their configured routes matches requestPath and model. All
|
|
// other channel types always pass. When requestPath is empty, filtering is skipped.
|
|
// Caller must hold channelSyncLock (read lock). The cached slice is never mutated.
|
|
func filterChannelsByRequestPathAndModel(channels []int, requestPath string, model string) []int {
|
|
if requestPath == "" || len(channels) == 0 {
|
|
return channels
|
|
}
|
|
filtered := make([]int, 0, len(channels))
|
|
for _, channelId := range channels {
|
|
channel, ok := channelsIDM[channelId]
|
|
if !ok {
|
|
// keep it so the downstream consistency error is raised as before
|
|
filtered = append(filtered, channelId)
|
|
continue
|
|
}
|
|
if channel.Type != constant.ChannelTypeAdvancedCustom {
|
|
filtered = append(filtered, channelId)
|
|
continue
|
|
}
|
|
if config := channel2advancedCustomConfig[channelId]; config != nil && config.SupportsPathForModel(requestPath, model) {
|
|
filtered = append(filtered, channelId)
|
|
}
|
|
}
|
|
return filtered
|
|
}
|
|
|
|
func CacheGetChannel(id int) (*Channel, error) {
|
|
if !common.MemoryCacheEnabled {
|
|
return GetChannelById(id, true)
|
|
}
|
|
channelSyncLock.RLock()
|
|
defer channelSyncLock.RUnlock()
|
|
|
|
c, ok := channelsIDM[id]
|
|
if !ok {
|
|
return nil, fmt.Errorf("渠道# %d,已不存在", id)
|
|
}
|
|
return c, nil
|
|
}
|
|
|
|
func CacheGetChannelInfo(id int) (*ChannelInfo, error) {
|
|
if !common.MemoryCacheEnabled {
|
|
channel, err := GetChannelById(id, true)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return &channel.ChannelInfo, nil
|
|
}
|
|
channelSyncLock.RLock()
|
|
defer channelSyncLock.RUnlock()
|
|
|
|
c, ok := channelsIDM[id]
|
|
if !ok {
|
|
return nil, fmt.Errorf("渠道# %d,已不存在", id)
|
|
}
|
|
return &c.ChannelInfo, nil
|
|
}
|
|
|
|
func CacheUpdateChannelStatus(id int, status int) {
|
|
if !common.MemoryCacheEnabled {
|
|
return
|
|
}
|
|
channelSyncLock.Lock()
|
|
defer channelSyncLock.Unlock()
|
|
if channel, ok := channelsIDM[id]; ok {
|
|
channel.Status = status
|
|
}
|
|
if status != common.ChannelStatusEnabled {
|
|
// delete the channel from group2model2channels
|
|
for group, model2channels := range group2model2channels {
|
|
for model, channels := range model2channels {
|
|
for i, channelId := range channels {
|
|
if channelId == id {
|
|
// remove the channel from the slice
|
|
group2model2channels[group][model] = append(channels[:i], channels[i+1:]...)
|
|
break
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
}
|
|
|
|
func CacheUpdateChannel(channel *Channel) {
|
|
if !common.MemoryCacheEnabled {
|
|
return
|
|
}
|
|
channelSyncLock.Lock()
|
|
if channel == nil {
|
|
channelSyncLock.Unlock()
|
|
return
|
|
}
|
|
|
|
if channelsIDM == nil {
|
|
channelsIDM = make(map[int]*Channel)
|
|
}
|
|
if oldChannel, ok := channelsIDM[channel.Id]; ok {
|
|
logger.LogDebug(nil, "CacheUpdateChannel before: id=%d, name=%s, status=%d, polling_index=%d", channel.Id, channel.Name, channel.Status, oldChannel.ChannelInfo.MultiKeyPollingIndex)
|
|
}
|
|
channelsIDM[channel.Id] = channel
|
|
if channel2advancedCustomConfig == nil {
|
|
channel2advancedCustomConfig = make(map[int]*dto.AdvancedCustomConfig)
|
|
}
|
|
delete(channel2advancedCustomConfig, channel.Id)
|
|
if channel.Type == constant.ChannelTypeAdvancedCustom {
|
|
if config := channel.GetOtherSettings().AdvancedCustom; config != nil {
|
|
channel2advancedCustomConfig[channel.Id] = config
|
|
}
|
|
}
|
|
logger.LogDebug(nil, "CacheUpdateChannel after: id=%d, name=%s, status=%d, polling_index=%d", channel.Id, channel.Name, channel.Status, channel.ChannelInfo.MultiKeyPollingIndex)
|
|
// Lock ordering: do NOT hold channelSyncLock while calling
|
|
// InvalidatePricingCache. GetPricing acquires updatePricingLock first and then
|
|
// channelSyncLock.RLock (via loadPricingAdvancedCustomConfigs); acquiring
|
|
// updatePricingLock while holding channelSyncLock would be an AB-BA deadlock.
|
|
channelSyncLock.Unlock()
|
|
InvalidatePricingCache()
|
|
}
|