mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-11 14:41:21 +00:00
* 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
402 lines
12 KiB
Go
402 lines
12 KiB
Go
package oaichat
|
|
|
|
import (
|
|
"encoding/json"
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/dto"
|
|
relaymedia "github.com/QuantumNous/new-api/service/relayconvert/internal/media"
|
|
sharedclaude "github.com/QuantumNous/new-api/service/relayconvert/internal/shared/claude"
|
|
"github.com/QuantumNous/new-api/setting/model_setting"
|
|
"github.com/QuantumNous/new-api/setting/reasoning"
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
const (
|
|
webSearchMaxUsesLow = 1
|
|
webSearchMaxUsesMedium = 5
|
|
webSearchMaxUsesHigh = 10
|
|
)
|
|
|
|
type openRouterRequestReasoning struct {
|
|
Enabled bool `json:"enabled"`
|
|
Effort string `json:"effort,omitempty"`
|
|
MaxTokens int `json:"max_tokens,omitempty"`
|
|
Exclude bool `json:"exclude,omitempty"`
|
|
}
|
|
|
|
func OpenAIChatRequestToClaudeMessages(c *gin.Context, textRequest dto.GeneralOpenAIRequest) (*dto.ClaudeRequest, error) {
|
|
claudeTools := make([]any, 0, len(textRequest.Tools))
|
|
|
|
for _, tool := range textRequest.Tools {
|
|
if params, ok := tool.Function.Parameters.(map[string]any); ok {
|
|
claudeTool := dto.Tool{
|
|
Name: tool.Function.Name,
|
|
Description: tool.Function.Description,
|
|
}
|
|
claudeTool.InputSchema = make(map[string]interface{})
|
|
if params["type"] != nil {
|
|
claudeTool.InputSchema["type"] = params["type"].(string)
|
|
}
|
|
claudeTool.InputSchema["properties"] = params["properties"]
|
|
claudeTool.InputSchema["required"] = params["required"]
|
|
for key, value := range params {
|
|
if key == "type" || key == "properties" || key == "required" {
|
|
continue
|
|
}
|
|
claudeTool.InputSchema[key] = value
|
|
}
|
|
claudeTools = append(claudeTools, &claudeTool)
|
|
}
|
|
}
|
|
|
|
if textRequest.WebSearchOptions != nil {
|
|
webSearchTool := dto.ClaudeWebSearchTool{
|
|
Type: "web_search_20250305",
|
|
Name: "web_search",
|
|
}
|
|
|
|
if textRequest.WebSearchOptions.UserLocation != nil {
|
|
anthropicUserLocation := &dto.ClaudeWebSearchUserLocation{
|
|
Type: "approximate",
|
|
}
|
|
|
|
var userLocationMap map[string]interface{}
|
|
if err := common.Unmarshal(textRequest.WebSearchOptions.UserLocation, &userLocationMap); err == nil {
|
|
if approximateData, ok := userLocationMap["approximate"].(map[string]interface{}); ok {
|
|
if timezone, ok := approximateData["timezone"].(string); ok && timezone != "" {
|
|
anthropicUserLocation.Timezone = timezone
|
|
}
|
|
if country, ok := approximateData["country"].(string); ok && country != "" {
|
|
anthropicUserLocation.Country = country
|
|
}
|
|
if region, ok := approximateData["region"].(string); ok && region != "" {
|
|
anthropicUserLocation.Region = region
|
|
}
|
|
if city, ok := approximateData["city"].(string); ok && city != "" {
|
|
anthropicUserLocation.City = city
|
|
}
|
|
}
|
|
}
|
|
|
|
webSearchTool.UserLocation = anthropicUserLocation
|
|
}
|
|
|
|
switch textRequest.WebSearchOptions.SearchContextSize {
|
|
case "low":
|
|
webSearchTool.MaxUses = webSearchMaxUsesLow
|
|
case "medium":
|
|
webSearchTool.MaxUses = webSearchMaxUsesMedium
|
|
case "high":
|
|
webSearchTool.MaxUses = webSearchMaxUsesHigh
|
|
}
|
|
|
|
claudeTools = append(claudeTools, &webSearchTool)
|
|
}
|
|
|
|
claudeRequest := dto.ClaudeRequest{
|
|
Model: textRequest.Model,
|
|
StopSequences: nil,
|
|
Temperature: textRequest.Temperature,
|
|
Tools: claudeTools,
|
|
}
|
|
if maxTokens := textRequest.GetMaxTokens(); maxTokens > 0 {
|
|
claudeRequest.MaxTokens = common.GetPointer(maxTokens)
|
|
}
|
|
if textRequest.TopP != nil {
|
|
claudeRequest.TopP = common.GetPointer(*textRequest.TopP)
|
|
}
|
|
if textRequest.TopK != nil {
|
|
claudeRequest.TopK = common.GetPointer(*textRequest.TopK)
|
|
}
|
|
if textRequest.IsStream(nil) {
|
|
claudeRequest.Stream = common.GetPointer(true)
|
|
}
|
|
|
|
if textRequest.ToolChoice != nil || textRequest.ParallelTooCalls != nil {
|
|
claudeToolChoice := sharedclaude.MapOpenAIToolChoice(textRequest.ToolChoice, textRequest.ParallelTooCalls)
|
|
if claudeToolChoice != nil {
|
|
claudeRequest.ToolChoice = claudeToolChoice
|
|
}
|
|
}
|
|
|
|
if claudeRequest.MaxTokens == nil || *claudeRequest.MaxTokens == 0 {
|
|
defaultMaxTokens := uint(model_setting.GetClaudeSettings().GetDefaultMaxTokens(textRequest.Model))
|
|
claudeRequest.MaxTokens = &defaultMaxTokens
|
|
}
|
|
|
|
if baseModel, effortLevel, ok := reasoning.TrimEffortSuffix(textRequest.Model); ok && effortLevel != "" &&
|
|
(strings.HasPrefix(textRequest.Model, "claude-opus-4-6") ||
|
|
strings.HasPrefix(textRequest.Model, "claude-opus-4-7") ||
|
|
strings.HasPrefix(textRequest.Model, "claude-opus-4-8")) {
|
|
claudeRequest.Model = baseModel
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "adaptive",
|
|
}
|
|
claudeRequest.OutputConfig = json.RawMessage(fmt.Sprintf(`{"effort":"%s"}`, effortLevel))
|
|
if strings.HasPrefix(baseModel, "claude-opus-4-7") ||
|
|
strings.HasPrefix(baseModel, "claude-opus-4-8") {
|
|
claudeRequest.Thinking.Display = "summarized"
|
|
claudeRequest.Temperature = nil
|
|
claudeRequest.TopP = nil
|
|
claudeRequest.TopK = nil
|
|
} else {
|
|
claudeRequest.TopP = nil
|
|
claudeRequest.Temperature = common.GetPointer[float64](1.0)
|
|
}
|
|
} else if model_setting.GetClaudeSettings().ThinkingAdapterEnabled &&
|
|
strings.HasSuffix(textRequest.Model, "-thinking") {
|
|
|
|
trimmedModel := strings.TrimSuffix(textRequest.Model, "-thinking")
|
|
if strings.HasPrefix(trimmedModel, "claude-opus-4-7") ||
|
|
strings.HasPrefix(trimmedModel, "claude-opus-4-8") {
|
|
claudeRequest.Thinking = &dto.Thinking{Type: "adaptive", Display: "summarized"}
|
|
claudeRequest.OutputConfig = json.RawMessage(`{"effort":"high"}`)
|
|
claudeRequest.Temperature = nil
|
|
claudeRequest.TopP = nil
|
|
claudeRequest.TopK = nil
|
|
} else {
|
|
if claudeRequest.MaxTokens == nil || *claudeRequest.MaxTokens < 1280 {
|
|
claudeRequest.MaxTokens = common.GetPointer[uint](1280)
|
|
}
|
|
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: common.GetPointer[int](int(float64(*claudeRequest.MaxTokens) * model_setting.GetClaudeSettings().ThinkingAdapterBudgetTokensPercentage)),
|
|
}
|
|
claudeRequest.TopP = nil
|
|
claudeRequest.Temperature = common.GetPointer[float64](1.0)
|
|
}
|
|
if !model_setting.ShouldPreserveThinkingSuffix(textRequest.Model) {
|
|
claudeRequest.Model = trimmedModel
|
|
}
|
|
}
|
|
|
|
if textRequest.ReasoningEffort != "" {
|
|
switch textRequest.ReasoningEffort {
|
|
case "low":
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: common.GetPointer[int](1280),
|
|
}
|
|
case "medium":
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: common.GetPointer[int](2048),
|
|
}
|
|
case "high":
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: common.GetPointer[int](4096),
|
|
}
|
|
}
|
|
}
|
|
|
|
if textRequest.Reasoning != nil {
|
|
var reasoningConfig openRouterRequestReasoning
|
|
if err := common.Unmarshal(textRequest.Reasoning, &reasoningConfig); err != nil {
|
|
return nil, err
|
|
}
|
|
|
|
budgetTokens := reasoningConfig.MaxTokens
|
|
if budgetTokens > 0 {
|
|
claudeRequest.Thinking = &dto.Thinking{
|
|
Type: "enabled",
|
|
BudgetTokens: &budgetTokens,
|
|
}
|
|
}
|
|
}
|
|
|
|
if textRequest.Stop != nil {
|
|
switch stop := textRequest.Stop.(type) {
|
|
case string:
|
|
claudeRequest.StopSequences = []string{stop}
|
|
case []interface{}:
|
|
stopSequences := make([]string, 0)
|
|
for _, item := range stop {
|
|
stopSequences = append(stopSequences, item.(string))
|
|
}
|
|
claudeRequest.StopSequences = stopSequences
|
|
}
|
|
}
|
|
|
|
formatMessages := make([]dto.Message, 0)
|
|
lastMessage := dto.Message{
|
|
Role: "tool",
|
|
}
|
|
for i, message := range textRequest.Messages {
|
|
if message.Role == "" {
|
|
textRequest.Messages[i].Role = "user"
|
|
}
|
|
fmtMessage := dto.Message{
|
|
Role: message.Role,
|
|
Content: message.Content,
|
|
}
|
|
if message.Role == "tool" {
|
|
fmtMessage.ToolCallId = message.ToolCallId
|
|
}
|
|
if message.Role == "assistant" && message.ToolCalls != nil {
|
|
fmtMessage.ToolCalls = message.ToolCalls
|
|
}
|
|
if lastMessage.Role == message.Role && lastMessage.Role != "tool" {
|
|
if lastMessage.IsStringContent() && message.IsStringContent() {
|
|
fmtMessage.SetStringContent(strings.Trim(fmt.Sprintf("%s %s", lastMessage.StringContent(), message.StringContent()), "\""))
|
|
formatMessages = formatMessages[:len(formatMessages)-1]
|
|
}
|
|
}
|
|
if fmtMessage.Content == nil || (fmtMessage.IsStringContent() && fmtMessage.StringContent() == "") {
|
|
fmtMessage.SetStringContent("...")
|
|
}
|
|
formatMessages = append(formatMessages, fmtMessage)
|
|
lastMessage = fmtMessage
|
|
}
|
|
|
|
claudeMessages := make([]dto.ClaudeMessage, 0)
|
|
isFirstMessage := true
|
|
var systemMessages []dto.ClaudeMediaMessage
|
|
|
|
for _, message := range formatMessages {
|
|
if message.Role == "system" {
|
|
if message.IsStringContent() {
|
|
if text := message.StringContent(); text != "" {
|
|
systemMessages = append(systemMessages, dto.ClaudeMediaMessage{
|
|
Type: "text",
|
|
Text: common.GetPointer[string](text),
|
|
})
|
|
}
|
|
} else {
|
|
for _, ctx := range message.ParseContent() {
|
|
if ctx.Type == "text" && ctx.Text != "" {
|
|
systemMessages = append(systemMessages, dto.ClaudeMediaMessage{
|
|
Type: "text",
|
|
Text: common.GetPointer[string](ctx.Text),
|
|
})
|
|
}
|
|
}
|
|
}
|
|
continue
|
|
}
|
|
|
|
if isFirstMessage {
|
|
isFirstMessage = false
|
|
if message.Role != "user" {
|
|
claudeMessage := dto.ClaudeMessage{
|
|
Role: "user",
|
|
Content: []dto.ClaudeMediaMessage{
|
|
{
|
|
Type: "text",
|
|
Text: common.GetPointer[string]("..."),
|
|
},
|
|
},
|
|
}
|
|
claudeMessages = append(claudeMessages, claudeMessage)
|
|
}
|
|
}
|
|
|
|
claudeMessage := dto.ClaudeMessage{
|
|
Role: message.Role,
|
|
}
|
|
if message.Role == "tool" {
|
|
if len(claudeMessages) > 0 && claudeMessages[len(claudeMessages)-1].Role == "user" {
|
|
lastClaudeMessage := claudeMessages[len(claudeMessages)-1]
|
|
if content, ok := lastClaudeMessage.Content.(string); ok {
|
|
lastClaudeMessage.Content = []dto.ClaudeMediaMessage{
|
|
{
|
|
Type: "text",
|
|
Text: common.GetPointer[string](content),
|
|
},
|
|
}
|
|
}
|
|
lastClaudeMessage.Content = append(lastClaudeMessage.Content.([]dto.ClaudeMediaMessage), dto.ClaudeMediaMessage{
|
|
Type: "tool_result",
|
|
ToolUseId: message.ToolCallId,
|
|
Content: message.Content,
|
|
})
|
|
claudeMessages[len(claudeMessages)-1] = lastClaudeMessage
|
|
continue
|
|
}
|
|
|
|
claudeMessage.Role = "user"
|
|
claudeMessage.Content = []dto.ClaudeMediaMessage{
|
|
{
|
|
Type: "tool_result",
|
|
ToolUseId: message.ToolCallId,
|
|
Content: message.Content,
|
|
},
|
|
}
|
|
} else if message.IsStringContent() && message.ToolCalls == nil {
|
|
text := message.StringContent()
|
|
if text == "" {
|
|
text = "..."
|
|
}
|
|
claudeMessage.Content = text
|
|
} else {
|
|
claudeMediaMessages := make([]dto.ClaudeMediaMessage, 0)
|
|
for _, mediaMessage := range message.ParseContent() {
|
|
switch mediaMessage.Type {
|
|
case "text":
|
|
if mediaMessage.Text != "" {
|
|
claudeMediaMessages = append(claudeMediaMessages, dto.ClaudeMediaMessage{
|
|
Type: "text",
|
|
Text: common.GetPointer[string](mediaMessage.Text),
|
|
})
|
|
}
|
|
default:
|
|
source := mediaMessage.ToFileSource()
|
|
if source == nil {
|
|
continue
|
|
}
|
|
base64Data, mimeType, err := relaymedia.ResolveBase64Data(c, source, "formatting image for Claude")
|
|
if err != nil {
|
|
return nil, fmt.Errorf("get file data failed: %s", err.Error())
|
|
}
|
|
claudeMediaMessage := dto.ClaudeMediaMessage{
|
|
Source: &dto.ClaudeMessageSource{
|
|
Type: "base64",
|
|
},
|
|
}
|
|
if strings.HasPrefix(mimeType, "application/pdf") {
|
|
claudeMediaMessage.Type = "document"
|
|
} else {
|
|
claudeMediaMessage.Type = "image"
|
|
}
|
|
|
|
claudeMediaMessage.Source.MediaType = mimeType
|
|
claudeMediaMessage.Source.Data = base64Data
|
|
claudeMediaMessages = append(claudeMediaMessages, claudeMediaMessage)
|
|
continue
|
|
}
|
|
}
|
|
|
|
if message.ToolCalls != nil {
|
|
for _, toolCall := range message.ParseToolCalls() {
|
|
inputObj := make(map[string]any)
|
|
if args := toolCall.Function.Arguments; args != "" {
|
|
if err := common.Unmarshal([]byte(args), &inputObj); err != nil {
|
|
common.SysLog("tool call function arguments is not a map[string]any: " + fmt.Sprintf("%v", toolCall.Function.Arguments))
|
|
}
|
|
}
|
|
claudeMediaMessages = append(claudeMediaMessages, dto.ClaudeMediaMessage{
|
|
Type: "tool_use",
|
|
Id: toolCall.ID,
|
|
Name: toolCall.Function.Name,
|
|
Input: inputObj,
|
|
})
|
|
}
|
|
}
|
|
claudeMessage.Content = claudeMediaMessages
|
|
}
|
|
claudeMessages = append(claudeMessages, claudeMessage)
|
|
}
|
|
|
|
if len(systemMessages) > 0 {
|
|
claudeRequest.System = systemMessages
|
|
}
|
|
|
|
claudeRequest.Prompt = ""
|
|
claudeRequest.Messages = claudeMessages
|
|
return &claudeRequest, nil
|
|
}
|