* 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
310 lines
9.2 KiB
Go
310 lines
9.2 KiB
Go
package oairesponses
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
|
|
"context"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/relayconvert/convmeta"
|
|
relaymedia "github.com/QuantumNous/new-api/relaykit/relayconvert/internal/media"
|
|
sharedgemini "github.com/QuantumNous/new-api/relaykit/relayconvert/internal/shared/gemini"
|
|
kitutil "github.com/QuantumNous/new-api/relaykit/relayconvert/kitutil"
|
|
)
|
|
|
|
func convertOpenAIResponsesRequestToGeminiChat(c context.Context, info convmeta.Meta, request any) (any, error) {
|
|
responsesRequest, err := OpenAIResponsesRequestFromAny(request)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
prepared, err := PrepareOpenAIResponsesRequest(*responsesRequest)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
return OpenAIResponsesRequestToGeminiChat(c, &prepared, info)
|
|
}
|
|
|
|
func OpenAIResponsesRequestToGeminiChat(c context.Context, req *dto.OpenAIResponsesRequest, info convmeta.Meta) (*dto.GeminiChatRequest, error) {
|
|
opts := convmeta.OptionsOf(info)
|
|
if req == nil {
|
|
return nil, fmt.Errorf("request is nil")
|
|
}
|
|
if req.Model == "" {
|
|
return nil, fmt.Errorf("model is required")
|
|
}
|
|
if err := ValidateRequestChatUnsupportedFields(req); err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
geminiRequest := &dto.GeminiChatRequest{
|
|
GenerationConfig: dto.GeminiChatGenerationConfig{
|
|
Temperature: req.Temperature,
|
|
},
|
|
}
|
|
if req.TopP != nil && *req.TopP > 0 {
|
|
geminiRequest.GenerationConfig.TopP = kitutil.GetPointer(*req.TopP)
|
|
}
|
|
if req.MaxOutputTokens != nil && *req.MaxOutputTokens > 0 {
|
|
geminiRequest.GenerationConfig.MaxOutputTokens = kitutil.GetPointer(*req.MaxOutputTokens)
|
|
}
|
|
|
|
upstreamModelName := req.Model
|
|
if modelName := convmeta.UpstreamModelName(info); modelName != "" {
|
|
upstreamModelName = modelName
|
|
}
|
|
if opts.Gemini.SupportsImagineModel(upstreamModelName) {
|
|
geminiRequest.GenerationConfig.ResponseModalities = []string{"TEXT", "IMAGE"}
|
|
}
|
|
if err := applyResponsesTextToGemini(req.Text, geminiRequest); err != nil {
|
|
return nil, err
|
|
}
|
|
sharedgemini.ApplyThinkingConfig(geminiRequest, info, dto.GeneralOpenAIRequest{
|
|
Model: req.Model,
|
|
MaxCompletionTokens: req.MaxOutputTokens,
|
|
ReasoningEffort: ReasoningEffort(req),
|
|
})
|
|
|
|
var safetySettings []dto.GeminiChatSafetySettings
|
|
for _, category := range sharedgemini.SafetySettingCategories {
|
|
threshold := opts.Gemini.SafetySettingFor(category)
|
|
if threshold == "" {
|
|
continue
|
|
}
|
|
safetySettings = append(safetySettings, dto.GeminiChatSafetySettings{
|
|
Category: category,
|
|
Threshold: threshold,
|
|
})
|
|
}
|
|
if len(safetySettings) > 0 {
|
|
geminiRequest.SafetySettings = safetySettings
|
|
}
|
|
|
|
functions, err := RequestFunctionDeclarations(req.Tools)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
for i := range functions {
|
|
if params, ok := functions[i].Parameters.(map[string]interface{}); ok {
|
|
if props, hasProps := params["properties"].(map[string]interface{}); hasProps && len(props) == 0 {
|
|
functions[i].Parameters = nil
|
|
continue
|
|
}
|
|
}
|
|
functions[i].Parameters = sharedgemini.CleanFunctionParameters(functions[i].Parameters)
|
|
}
|
|
if len(functions) > 0 {
|
|
geminiRequest.SetTools([]dto.GeminiChatTool{
|
|
{FunctionDeclarations: functions},
|
|
})
|
|
}
|
|
|
|
toolChoice, err := RequestToolChoiceToChat(req.ToolChoice)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if toolChoice != nil {
|
|
geminiRequest.ToolConfig = sharedgemini.OpenAIToolChoiceToConfig(toolChoice)
|
|
}
|
|
|
|
systemTexts := make([]string, 0)
|
|
if RawJSONPresent(req.Instructions) {
|
|
instructions, err := JSONString(req.Instructions)
|
|
if err != nil {
|
|
return nil, fmt.Errorf("invalid instructions: %w", err)
|
|
}
|
|
if strings.TrimSpace(instructions) != "" {
|
|
systemTexts = append(systemTexts, instructions)
|
|
}
|
|
}
|
|
|
|
inputItems, err := InputItems(req.Input)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
callNames := make(map[string]string)
|
|
for _, item := range inputItems {
|
|
itemType := strings.TrimSpace(kitutil.Interface2String(item["type"]))
|
|
switch itemType {
|
|
case ResponsesInputTypeFunctionCall:
|
|
part, callID, err := responsesFunctionCallItemToGeminiPart(item)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
sharedgemini.AttachFunctionCallThoughtSignature(opts, &part)
|
|
if callID != "" {
|
|
callNames[callID] = part.FunctionCall.FunctionName
|
|
}
|
|
appendGeminiContentPart(geminiRequest, "model", part)
|
|
case ResponsesInputTypeFunctionCallOutput:
|
|
part := responsesFunctionOutputItemToGeminiPart(item, callNames)
|
|
appendGeminiContentPart(geminiRequest, "user", part)
|
|
default:
|
|
role := responsesGeminiRole(item)
|
|
parts, err := responsesInputContentToGeminiParts(c, item["content"])
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
if role == "system" {
|
|
for _, part := range parts {
|
|
if part.Text != "" {
|
|
systemTexts = append(systemTexts, part.Text)
|
|
}
|
|
}
|
|
continue
|
|
}
|
|
if len(parts) > 0 {
|
|
geminiRequest.Contents = append(geminiRequest.Contents, dto.GeminiChatContent{
|
|
Role: role,
|
|
Parts: parts,
|
|
})
|
|
}
|
|
}
|
|
}
|
|
|
|
if len(systemTexts) > 0 {
|
|
geminiRequest.SystemInstructions = &dto.GeminiChatContent{
|
|
Parts: []dto.GeminiPart{{Text: strings.Join(systemTexts, "\n")}},
|
|
}
|
|
}
|
|
|
|
return geminiRequest, nil
|
|
}
|
|
|
|
func applyResponsesTextToGemini(raw []byte, geminiRequest *dto.GeminiChatRequest) error {
|
|
responseFormat, err := RequestTextToChatResponseFormat(raw)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
if responseFormat == nil || (responseFormat.Type != "json_schema" && responseFormat.Type != "json_object") {
|
|
return nil
|
|
}
|
|
|
|
geminiRequest.GenerationConfig.ResponseMimeType = "application/json"
|
|
if len(responseFormat.JsonSchema) == 0 {
|
|
return nil
|
|
}
|
|
|
|
var jsonSchema dto.FormatJsonSchema
|
|
if err := kitutil.Unmarshal(responseFormat.JsonSchema, &jsonSchema); err != nil {
|
|
return nil
|
|
}
|
|
geminiRequest.GenerationConfig.ResponseSchema = sharedgemini.RemoveAdditionalProperties(jsonSchema.Schema, 0)
|
|
return nil
|
|
}
|
|
|
|
func responsesInputContentToGeminiParts(c context.Context, content any) ([]dto.GeminiPart, error) {
|
|
contentParts, err := ContentParts(content)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
parts := make([]dto.GeminiPart, 0, len(contentParts))
|
|
for _, contentPart := range contentParts {
|
|
nextParts, err := responsesContentPartToGeminiParts(c, contentPart)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
parts = append(parts, nextParts...)
|
|
}
|
|
return parts, nil
|
|
}
|
|
|
|
func responsesContentPartToGeminiParts(c context.Context, part map[string]any) ([]dto.GeminiPart, error) {
|
|
partType := strings.TrimSpace(kitutil.Interface2String(part["type"]))
|
|
switch partType {
|
|
case "input_text", "output_text", "text":
|
|
text := kitutil.Interface2String(part["text"])
|
|
if text == "" {
|
|
return nil, nil
|
|
}
|
|
return []dto.GeminiPart{{Text: text}}, nil
|
|
case "input_image", "input_file", "input_audio", "input_video":
|
|
source := ContentPartToFileSource(part)
|
|
if source == nil {
|
|
return nil, nil
|
|
}
|
|
base64Data, mimeType, err := relaymedia.ResolveBase64Data(c, source, "formatting Responses input for Gemini")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("get file data from '%s' failed: %w", source.GetIdentifier(), err)
|
|
}
|
|
if _, ok := sharedgemini.SupportedMimeTypes[strings.ToLower(mimeType)]; !ok {
|
|
return nil, fmt.Errorf("mime type is not supported by Gemini: '%s', url: '%s', supported types are: %v", mimeType, source.GetIdentifier(), sharedgemini.SupportedMimeTypesList())
|
|
}
|
|
return []dto.GeminiPart{
|
|
{
|
|
InlineData: &dto.GeminiInlineData{
|
|
MimeType: mimeType,
|
|
Data: base64Data,
|
|
},
|
|
},
|
|
}, nil
|
|
default:
|
|
return nil, nil
|
|
}
|
|
}
|
|
|
|
func responsesFunctionCallItemToGeminiPart(item map[string]any) (dto.GeminiPart, string, error) {
|
|
name := strings.TrimSpace(kitutil.Interface2String(item["name"]))
|
|
if name == "" {
|
|
return dto.GeminiPart{}, "", fmt.Errorf("function_call item is missing name")
|
|
}
|
|
callID := CallID(item)
|
|
return dto.GeminiPart{
|
|
FunctionCall: &dto.FunctionCall{
|
|
FunctionName: name,
|
|
Arguments: ObjectValue(item["arguments"], "arguments"),
|
|
},
|
|
}, callID, nil
|
|
}
|
|
|
|
func responsesFunctionOutputItemToGeminiPart(item map[string]any, callNames map[string]string) dto.GeminiPart {
|
|
callID := CallID(item)
|
|
name := strings.TrimSpace(kitutil.Interface2String(item["name"]))
|
|
if name == "" {
|
|
name = callNames[callID]
|
|
}
|
|
return dto.GeminiPart{
|
|
FunctionResponse: &dto.GeminiFunctionResponse{
|
|
Name: name,
|
|
Response: GeminiResponseMap(item["output"]),
|
|
},
|
|
}
|
|
}
|
|
|
|
func appendGeminiContentPart(req *dto.GeminiChatRequest, role string, part dto.GeminiPart) {
|
|
if len(req.Contents) > 0 && req.Contents[len(req.Contents)-1].Role == role {
|
|
if role == "model" && part.FunctionCall != nil {
|
|
parts := req.Contents[len(req.Contents)-1].Parts
|
|
insertAt := 0
|
|
for insertAt < len(parts) && parts[insertAt].FunctionCall != nil {
|
|
insertAt++
|
|
}
|
|
parts = append(parts, dto.GeminiPart{})
|
|
copy(parts[insertAt+1:], parts[insertAt:])
|
|
parts[insertAt] = part
|
|
req.Contents[len(req.Contents)-1].Parts = parts
|
|
return
|
|
}
|
|
req.Contents[len(req.Contents)-1].Parts = append(req.Contents[len(req.Contents)-1].Parts, part)
|
|
return
|
|
}
|
|
req.Contents = append(req.Contents, dto.GeminiChatContent{
|
|
Role: role,
|
|
Parts: []dto.GeminiPart{part},
|
|
})
|
|
}
|
|
|
|
func responsesGeminiRole(item map[string]any) string {
|
|
switch strings.TrimSpace(kitutil.Interface2String(item["role"])) {
|
|
case "assistant":
|
|
return "model"
|
|
case "system", "developer":
|
|
return "system"
|
|
case "model":
|
|
return "model"
|
|
default:
|
|
return "user"
|
|
}
|
|
}
|