mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-13 15:54:34 +00:00
refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
This commit is contained in:
Calcium-Ion
@@ -0,0 +1,192 @@
|
||||
package dto
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"net/http"
|
||||
"reflect"
|
||||
"strings"
|
||||
|
||||
kitutil "github.com/QuantumNous/new-api/relaykit/relayconvert/kitutil"
|
||||
"github.com/QuantumNous/new-api/relaykit/types"
|
||||
)
|
||||
|
||||
// MaxImageN caps the image generation count. Without this bound a huge or
|
||||
// wrapped-negative n overflows quota calculation into a negative charge.
|
||||
const MaxImageN = 128
|
||||
|
||||
type ImageRequest struct {
|
||||
Model string `json:"model"`
|
||||
Prompt string `json:"prompt" binding:"required"`
|
||||
N *uint `json:"n,omitempty"`
|
||||
Size string `json:"size,omitempty"`
|
||||
Quality string `json:"quality,omitempty"`
|
||||
ResponseFormat string `json:"response_format,omitempty"`
|
||||
Style json.RawMessage `json:"style,omitempty"`
|
||||
User json.RawMessage `json:"user,omitempty"`
|
||||
ExtraFields json.RawMessage `json:"extra_fields,omitempty"`
|
||||
Background json.RawMessage `json:"background,omitempty"`
|
||||
Moderation json.RawMessage `json:"moderation,omitempty"`
|
||||
OutputFormat json.RawMessage `json:"output_format,omitempty"`
|
||||
OutputCompression json.RawMessage `json:"output_compression,omitempty"`
|
||||
PartialImages json.RawMessage `json:"partial_images,omitempty"`
|
||||
Stream *bool `json:"stream,omitempty"`
|
||||
Images json.RawMessage `json:"images,omitempty"`
|
||||
Mask json.RawMessage `json:"mask,omitempty"`
|
||||
InputFidelity json.RawMessage `json:"input_fidelity,omitempty"`
|
||||
Watermark *bool `json:"watermark,omitempty"`
|
||||
// zhipu 4v
|
||||
WatermarkEnabled json.RawMessage `json:"watermark_enabled,omitempty"`
|
||||
UserId json.RawMessage `json:"user_id,omitempty"`
|
||||
Image json.RawMessage `json:"image,omitempty"`
|
||||
// 用匿名参数接收额外参数
|
||||
Extra map[string]json.RawMessage `json:"-"`
|
||||
}
|
||||
|
||||
func (i *ImageRequest) UnmarshalJSON(data []byte) error {
|
||||
// 先解析成 map[string]interface{}
|
||||
var rawMap map[string]json.RawMessage
|
||||
if err := kitutil.Unmarshal(data, &rawMap); err != nil {
|
||||
return err
|
||||
}
|
||||
|
||||
// 用 struct tag 获取所有已定义字段名
|
||||
knownFields := GetJSONFieldNames(reflect.TypeOf(*i))
|
||||
|
||||
// 再正常解析已定义字段
|
||||
type Alias ImageRequest
|
||||
var known Alias
|
||||
if err := kitutil.Unmarshal(data, &known); err != nil {
|
||||
return err
|
||||
}
|
||||
*i = ImageRequest(known)
|
||||
|
||||
// 提取多余字段
|
||||
i.Extra = make(map[string]json.RawMessage)
|
||||
for k, v := range rawMap {
|
||||
if _, ok := knownFields[k]; !ok {
|
||||
i.Extra[k] = v
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// 序列化时需要重新把字段平铺
|
||||
func (r ImageRequest) MarshalJSON() ([]byte, error) {
|
||||
// 将已定义字段转为 map
|
||||
type Alias ImageRequest
|
||||
alias := Alias(r)
|
||||
base, err := kitutil.Marshal(alias)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
var baseMap map[string]json.RawMessage
|
||||
if err := kitutil.Unmarshal(base, &baseMap); err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
// 不能合并ExtraFields！！！！！！！！
|
||||
// 合并 ExtraFields
|
||||
//for k, v := range r.Extra {
|
||||
// if _, exists := baseMap[k]; !exists {
|
||||
// baseMap[k] = v
|
||||
// }
|
||||
//}
|
||||
|
||||
return kitutil.Marshal(baseMap)
|
||||
}
|
||||
|
||||
func GetJSONFieldNames(t reflect.Type) map[string]struct{} {
|
||||
fields := make(map[string]struct{})
|
||||
for i := 0; i < t.NumField(); i++ {
|
||||
field := t.Field(i)
|
||||
|
||||
// 跳过匿名字段（例如 ExtraFields）
|
||||
if field.Anonymous {
|
||||
continue
|
||||
}
|
||||
|
||||
tag := field.Tag.Get("json")
|
||||
if tag == "-" || tag == "" {
|
||||
continue
|
||||
}
|
||||
|
||||
// 取逗号前字段名（排除 omitempty 等）
|
||||
name := tag
|
||||
if commaIdx := indexComma(tag); commaIdx != -1 {
|
||||
name = tag[:commaIdx]
|
||||
}
|
||||
fields[name] = struct{}{}
|
||||
}
|
||||
return fields
|
||||
}
|
||||
|
||||
func indexComma(s string) int {
|
||||
for i := 0; i < len(s); i++ {
|
||||
if s[i] == ',' {
|
||||
return i
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
func (i *ImageRequest) GetTokenCountMeta() *types.TokenCountMeta {
|
||||
var sizeRatio = 1.0
|
||||
var qualityRatio = 1.0
|
||||
|
||||
if strings.HasPrefix(i.Model, "dall-e") {
|
||||
// Size
|
||||
if i.Size == "256x256" {
|
||||
sizeRatio = 0.4
|
||||
} else if i.Size == "512x512" {
|
||||
sizeRatio = 0.45
|
||||
} else if i.Size == "1024x1024" {
|
||||
sizeRatio = 1
|
||||
} else if i.Size == "1024x1792" || i.Size == "1792x1024" {
|
||||
sizeRatio = 2
|
||||
}
|
||||
|
||||
if i.Model == "dall-e-3" && i.Quality == "hd" {
|
||||
qualityRatio = 2.0
|
||||
if i.Size == "1024x1792" || i.Size == "1792x1024" {
|
||||
qualityRatio = 1.5
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
imageN := uint(1)
|
||||
if i.N != nil && *i.N > 0 {
|
||||
imageN = *i.N
|
||||
}
|
||||
|
||||
// Keep n separate from ImagePriceRatio so size/quality and count remain
|
||||
// independent billing dimensions. Fixed-price pre-consume stores this on
|
||||
// PriceData, and image settlement reuses or replaces the same "n" ratio.
|
||||
return &types.TokenCountMeta{
|
||||
CombineText: i.Prompt,
|
||||
MaxTokens: 1584,
|
||||
ImagePriceRatio: sizeRatio * qualityRatio,
|
||||
BillingRatios: map[string]float64{"n": float64(imageN)},
|
||||
}
|
||||
}
|
||||
|
||||
func (i *ImageRequest) IsStream(c *http.Request) bool {
|
||||
return i.Stream != nil && *i.Stream
|
||||
}
|
||||
|
||||
func (i *ImageRequest) SetModelName(modelName string) {
|
||||
if modelName != "" {
|
||||
i.Model = modelName
|
||||
}
|
||||
}
|
||||
|
||||
type ImageResponse struct {
|
||||
Data []ImageData `json:"data"`
|
||||
Created int64 `json:"created"`
|
||||
Metadata json.RawMessage `json:"metadata,omitempty"`
|
||||
}
|
||||
type ImageData struct {
|
||||
Url string `json:"url"`
|
||||
B64Json string `json:"b64_json"`
|
||||
RevisedPrompt string `json:"revised_prompt"`
|
||||
}
|
||||
Reference in New Issue
Block a user