* refactor: consolidate relay protocol converters * refactor relayconvert text converters * feat: refine relay converters and advanced custom routing * refactor: enhance logging and add thought signature handling for Gemini requests * refactor: enhance channel cache and pricing endpoint handling for advanced custom models * feat: preserve billing usage semantics * feat: add protocol-aware billing usage * Delete useless files * chore: update action versions in workflow files * chore: update Docker action versions in workflow files * fix: harden billing usage settlement and hot-path route matching - estimate Gemini completion tokens locally when billable usageMetadata is prompt-only but output content was received (e.g. client aborts the stream before the final chunk), and rebuild the attached billing_usage as estimated so settlement does not bill zero output tokens - guard NewClaudeMessagesBillingUsage against all-zero ClaudeUsage, matching the OpenAI/Gemini constructors, so a zero billing_usage cannot override a non-zero top-level usage during settlement - cache compiled advanced-custom route model regexes; they run on the request hot path and were recompiled per request - move the effectiveBillingUsage remap to PostTextConsumeQuota only, and document that calculateTextQuotaSummary expects remapped usage - document the updatePricingLock -> channelSyncLock lock ordering that InitChannelCache/CacheUpdateChannel rely on, and the aux-struct pitfall in GeminiChatResponse.UnmarshalJSON
305 lines
9.2 KiB
Go
305 lines
9.2 KiB
Go
package oairesponses
|
|
|
|
import (
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/dto"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
relaymedia "github.com/QuantumNous/new-api/service/relayconvert/internal/media"
|
|
relaymeta "github.com/QuantumNous/new-api/service/relayconvert/internal/meta"
|
|
sharedgemini "github.com/QuantumNous/new-api/service/relayconvert/internal/shared/gemini"
|
|
"github.com/QuantumNous/new-api/setting/model_setting"
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
func convertOpenAIResponsesRequestToGeminiChat(c *gin.Context, info *relaycommon.RelayInfo, 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 *gin.Context, req *dto.OpenAIResponsesRequest, info *relaycommon.RelayInfo) (*dto.GeminiChatRequest, error) {
|
|
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 = common.GetPointer(*req.TopP)
|
|
}
|
|
if req.MaxOutputTokens != nil && *req.MaxOutputTokens > 0 {
|
|
geminiRequest.GenerationConfig.MaxOutputTokens = common.GetPointer(*req.MaxOutputTokens)
|
|
}
|
|
|
|
upstreamModelName := req.Model
|
|
if modelName := relaymeta.RelayInfoUpstreamModelName(info); modelName != "" {
|
|
upstreamModelName = modelName
|
|
}
|
|
if model_setting.IsGeminiModelSupportImagine(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),
|
|
})
|
|
|
|
safetySettings := make([]dto.GeminiChatSafetySettings, 0, len(sharedgemini.SafetySettingCategories))
|
|
for _, category := range sharedgemini.SafetySettingCategories {
|
|
safetySettings = append(safetySettings, dto.GeminiChatSafetySettings{
|
|
Category: category,
|
|
Threshold: model_setting.GetGeminiSafetySetting(category),
|
|
})
|
|
}
|
|
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(common.Interface2String(item["type"]))
|
|
switch itemType {
|
|
case ResponsesInputTypeFunctionCall:
|
|
part, callID, err := responsesFunctionCallItemToGeminiPart(item)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
sharedgemini.AttachFunctionCallThoughtSignature(&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 := common.Unmarshal(responseFormat.JsonSchema, &jsonSchema); err != nil {
|
|
return nil
|
|
}
|
|
geminiRequest.GenerationConfig.ResponseSchema = sharedgemini.RemoveAdditionalProperties(jsonSchema.Schema, 0)
|
|
return nil
|
|
}
|
|
|
|
func responsesInputContentToGeminiParts(c *gin.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 *gin.Context, part map[string]any) ([]dto.GeminiPart, error) {
|
|
partType := strings.TrimSpace(common.Interface2String(part["type"]))
|
|
switch partType {
|
|
case "input_text", "output_text", "text":
|
|
text := common.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(common.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(common.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(common.Interface2String(item["role"])) {
|
|
case "assistant":
|
|
return "model"
|
|
case "system", "developer":
|
|
return "system"
|
|
case "model":
|
|
return "model"
|
|
default:
|
|
return "user"
|
|
}
|
|
}
|