Files
new-api/relay/channel/zhipu_4v/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

128 lines
3.4 KiB
Go

package zhipu_4v
import (
"io"
"net/http"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/logger"
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 zhipuImageRequest struct {
Model string `json:"model"`
Prompt string `json:"prompt"`
Quality string `json:"quality,omitempty"`
Size string `json:"size,omitempty"`
WatermarkEnabled *bool `json:"watermark_enabled,omitempty"`
UserID string `json:"user_id,omitempty"`
}
type zhipuImageResponse struct {
Created *int64 `json:"created,omitempty"`
Data []zhipuImageData `json:"data,omitempty"`
ContentFilter any `json:"content_filter,omitempty"`
Usage *dto.Usage `json:"usage,omitempty"`
Error *zhipuImageError `json:"error,omitempty"`
RequestID string `json:"request_id,omitempty"`
ExtendParam map[string]string `json:"extendParam,omitempty"`
}
type zhipuImageError struct {
Code string `json:"code"`
Message string `json:"message"`
}
type zhipuImageData struct {
Url string `json:"url,omitempty"`
ImageUrl string `json:"image_url,omitempty"`
B64Json string `json:"b64_json,omitempty"`
B64Image string `json:"b64_image,omitempty"`
}
type openAIImagePayload struct {
Created int64 `json:"created"`
Data []openAIImageData `json:"data"`
}
type openAIImageData struct {
B64Json string `json:"b64_json"`
}
func zhipu4vImageHandler(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 zhipuResp zhipuImageResponse
if err := common.Unmarshal(responseBody, &zhipuResp); err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
if zhipuResp.Error != nil && zhipuResp.Error.Message != "" {
return nil, types.WithOpenAIError(types.OpenAIError{
Message: zhipuResp.Error.Message,
Type: "zhipu_image_error",
Code: zhipuResp.Error.Code,
}, resp.StatusCode)
}
payload := openAIImagePayload{}
if zhipuResp.Created != nil && *zhipuResp.Created != 0 {
payload.Created = *zhipuResp.Created
} else {
payload.Created = info.StartTime.Unix()
}
for _, data := range zhipuResp.Data {
url := data.Url
if url == "" {
url = data.ImageUrl
}
if url == "" {
logger.LogWarn(c, "zhipu_image_missing_url")
continue
}
var b64 string
switch {
case data.B64Json != "":
b64 = data.B64Json
case data.B64Image != "":
b64 = data.B64Image
default:
_, downloaded, err := service.GetImageFromUrl(url)
if err != nil {
logger.LogError(c, "zhipu_image_get_b64_failed: "+err.Error())
continue
}
b64 = downloaded
}
if b64 == "" {
logger.LogWarn(c, "zhipu_image_empty_b64")
continue
}
imageData := openAIImageData{
B64Json: b64,
}
payload.Data = append(payload.Data, imageData)
}
jsonResp, err := common.Marshal(payload)
if err != nil {
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
}
service.IOCopyBytesGracefully(c, resp, jsonResp)
return &dto.Usage{}, nil
}