Files
new-api/relay/channel/minimax/image.go
T
Calcium-Ion 86ac0f7745 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
2026-07-27 15:56:21 +08:00

214 lines
5.6 KiB
Go

package minimax
import (
"fmt"
"io"
"net/http"
"strconv"
"strings"
"github.com/QuantumNous/new-api/common"
relaycommon "github.com/QuantumNous/new-api/relay/common"
"github.com/QuantumNous/new-api/relaykit/dto"
"github.com/QuantumNous/new-api/relaykit/types"
"github.com/QuantumNous/new-api/service"
"github.com/gin-gonic/gin"
)
type MiniMaxImageRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
AspectRatio string `json:"aspect_ratio,omitempty"`
ResponseFormat string `json:"response_format,omitempty"`
N int `json:"n,omitempty"`
PromptOptimizer *bool `json:"prompt_optimizer,omitempty"`
AigcWatermark *bool `json:"aigc_watermark,omitempty"`
}
type MiniMaxImageResponse struct {
ID string `json:"id"`
Data struct {
ImageURLs []string `json:"image_urls"`
ImageBase64 []string `json:"image_base64"`
} `json:"data"`
Metadata map[string]any `json:"metadata"`
BaseResp struct {
StatusCode int `json:"status_code"`
StatusMsg string `json:"status_msg"`
} `json:"base_resp"`
}
func oaiImage2MiniMaxImageRequest(request dto.ImageRequest) MiniMaxImageRequest {
responseFormat := normalizeMiniMaxResponseFormat(request.ResponseFormat)
minimaxRequest := MiniMaxImageRequest{
Model: request.Model,
Prompt: request.Prompt,
ResponseFormat: responseFormat,
N: 1,
AigcWatermark: request.Watermark,
}
if request.Model == "" {
minimaxRequest.Model = "image-01"
}
if request.N != nil && *request.N > 0 {
minimaxRequest.N = int(*request.N)
}
if aspectRatio := aspectRatioFromImageRequest(request); aspectRatio != "" {
minimaxRequest.AspectRatio = aspectRatio
}
if raw, ok := request.Extra["prompt_optimizer"]; ok {
var promptOptimizer bool
if err := common.Unmarshal(raw, &promptOptimizer); err == nil {
minimaxRequest.PromptOptimizer = &promptOptimizer
}
}
return minimaxRequest
}
func aspectRatioFromImageRequest(request dto.ImageRequest) string {
if raw, ok := request.Extra["aspect_ratio"]; ok {
var aspectRatio string
if err := common.Unmarshal(raw, &aspectRatio); err == nil && aspectRatio != "" {
return aspectRatio
}
}
switch request.Size {
case "1024x1024":
return "1:1"
case "1792x1024":
return "16:9"
case "1024x1792":
return "9:16"
case "1536x1024", "1248x832":
return "3:2"
case "1024x1536", "832x1248":
return "2:3"
case "1152x864":
return "4:3"
case "864x1152":
return "3:4"
case "1344x576":
return "21:9"
}
width, height, ok := parseImageSize(request.Size)
if !ok {
return ""
}
ratio := reduceAspectRatio(width, height)
switch ratio {
case "1:1", "16:9", "4:3", "3:2", "2:3", "3:4", "9:16", "21:9":
return ratio
default:
return ""
}
}
func parseImageSize(size string) (int, int, bool) {
parts := strings.Split(size, "x")
if len(parts) != 2 {
return 0, 0, false
}
width, err := strconv.Atoi(parts[0])
if err != nil {
return 0, 0, false
}
height, err := strconv.Atoi(parts[1])
if err != nil {
return 0, 0, false
}
if width <= 0 || height <= 0 {
return 0, 0, false
}
return width, height, true
}
func reduceAspectRatio(width, height int) string {
divisor := gcd(width, height)
return fmt.Sprintf("%d:%d", width/divisor, height/divisor)
}
func gcd(a, b int) int {
for b != 0 {
a, b = b, a%b
}
if a == 0 {
return 1
}
return a
}
func normalizeMiniMaxResponseFormat(responseFormat string) string {
switch strings.ToLower(responseFormat) {
case "", "url":
return "url"
case "b64_json", "base64":
return "base64"
default:
return responseFormat
}
}
func responseMiniMax2OpenAIImage(response *MiniMaxImageResponse, info *relaycommon.RelayInfo) (*dto.ImageResponse, error) {
imageResponse := &dto.ImageResponse{
Created: info.StartTime.Unix(),
}
for _, imageURL := range response.Data.ImageURLs {
imageResponse.Data = append(imageResponse.Data, dto.ImageData{Url: imageURL})
}
for _, imageBase64 := range response.Data.ImageBase64 {
imageResponse.Data = append(imageResponse.Data, dto.ImageData{B64Json: imageBase64})
}
if len(response.Metadata) > 0 {
metadata, err := common.Marshal(response.Metadata)
if err != nil {
return nil, err
}
imageResponse.Metadata = metadata
}
return imageResponse, nil
}
func miniMaxImageHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.Usage, *types.NewAPIError) {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
}
service.CloseResponseBodyGracefully(resp)
var minimaxResponse MiniMaxImageResponse
if err := common.Unmarshal(responseBody, &minimaxResponse); err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
if minimaxResponse.BaseResp.StatusCode != 0 {
return nil, types.WithOpenAIError(types.OpenAIError{
Message: minimaxResponse.BaseResp.StatusMsg,
Type: "minimax_image_error",
Code: fmt.Sprintf("%d", minimaxResponse.BaseResp.StatusCode),
}, resp.StatusCode)
}
openAIResponse, err := responseMiniMax2OpenAIImage(&minimaxResponse, info)
if err != nil {
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
}
jsonResponse, err := common.Marshal(openAIResponse)
if err != nil {
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
if _, err := c.Writer.Write(jsonResponse); err != nil {
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
}
return &dto.Usage{}, nil
}