mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-11 14:41:21 +00:00
* 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
291 lines
8.2 KiB
Go
291 lines
8.2 KiB
Go
package oairesponses
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
kitutil "github.com/QuantumNous/new-api/relaykit/relayconvert/kitutil"
|
|
)
|
|
|
|
const (
|
|
responsesEventCreated = "response.created"
|
|
responsesEventCompleted = "response.completed"
|
|
responsesEventDone = "response.done"
|
|
responsesEventIncomplete = "response.incomplete"
|
|
responsesEventFailed = "response.failed"
|
|
responsesEventError = "response.error"
|
|
responsesEventOutputTextDelta = "response.output_text.delta"
|
|
responsesEventOutputItemAdded = "response.output_item.added"
|
|
responsesEventOutputItemDone = "response.output_item.done"
|
|
responsesEventFunctionArgsDelta = "response.function_call_arguments.delta"
|
|
responsesEventFunctionArgsDone = "response.function_call_arguments.done"
|
|
responsesEventCustomToolInputDelta = "response.custom_tool_call_input.delta"
|
|
responsesEventCustomToolInputDone = "response.custom_tool_call_input.done"
|
|
responsesEventReasoningSummaryDelta = "response.reasoning_summary_text.delta"
|
|
responsesEventReasoningSummaryDone = "response.reasoning_summary_text.done"
|
|
responsesEventReasoningTextDelta = "response.reasoning_text.delta"
|
|
responsesEventReasoningTextDone = "response.reasoning_text.done"
|
|
responsesOutputTypeFunctionCall = "function_call"
|
|
responsesOutputTypeCustomToolCall = "custom_tool_call"
|
|
responsesOutputTypeMessage = "message"
|
|
responsesOutputTypeReasoning = "reasoning"
|
|
responsesIncompleteReasonContentFilter = "content_filter"
|
|
responsesIncompleteReasonMaxTokens = "max_output_tokens"
|
|
)
|
|
|
|
func ResponsesFinishReasonFromStatus(resp *dto.OpenAIResponsesResponse) (string, bool) {
|
|
if resp == nil {
|
|
return "", false
|
|
}
|
|
|
|
status := responseStatusString(resp)
|
|
if status != "incomplete" {
|
|
return "", false
|
|
}
|
|
|
|
reason := ""
|
|
if resp.IncompleteDetails != nil {
|
|
reason = strings.TrimSpace(resp.IncompleteDetails.Reason)
|
|
}
|
|
if reason == responsesIncompleteReasonContentFilter {
|
|
return "content_filter", true
|
|
}
|
|
return "length", true
|
|
}
|
|
|
|
func ResponsesResponseToChatCompletionsResponse(resp *dto.OpenAIResponsesResponse, id string) (*dto.OpenAITextResponse, *dto.Usage, error) {
|
|
if resp == nil {
|
|
return nil, nil, errors.New("response is nil")
|
|
}
|
|
|
|
text := ExtractOutputTextFromResponses(resp)
|
|
reasoning := ExtractReasoningTextFromResponses(resp)
|
|
|
|
usage := UsageFromResponsesUsage(resp.Usage)
|
|
|
|
created := resp.CreatedAt
|
|
|
|
var toolCalls []dto.ToolCallResponse
|
|
if len(resp.Output) > 0 {
|
|
for _, out := range resp.Output {
|
|
if !isResponsesToolOutputType(out.Type) {
|
|
continue
|
|
}
|
|
name := strings.TrimSpace(out.Name)
|
|
if name == "" {
|
|
continue
|
|
}
|
|
callId := strings.TrimSpace(out.CallId)
|
|
if callId == "" {
|
|
callId = strings.TrimSpace(out.ID)
|
|
}
|
|
toolCalls = append(toolCalls, dto.ToolCallResponse{
|
|
ID: callId,
|
|
Type: "function",
|
|
Function: dto.FunctionResponse{
|
|
Name: name,
|
|
Arguments: out.ArgumentsString(),
|
|
},
|
|
})
|
|
}
|
|
}
|
|
|
|
finishReason := "stop"
|
|
if mappedReason, ok := ResponsesFinishReasonFromStatus(resp); ok {
|
|
finishReason = mappedReason
|
|
} else if len(toolCalls) > 0 {
|
|
finishReason = "tool_calls"
|
|
}
|
|
|
|
msg := dto.Message{
|
|
Role: "assistant",
|
|
Content: text,
|
|
}
|
|
if reasoning != "" {
|
|
msg.ReasoningContent = &reasoning
|
|
}
|
|
if len(toolCalls) > 0 {
|
|
msg.SetToolCalls(toolCalls)
|
|
}
|
|
|
|
out := &dto.OpenAITextResponse{
|
|
Id: id,
|
|
Object: "chat.completion",
|
|
Created: created,
|
|
Model: resp.Model,
|
|
Choices: []dto.OpenAITextResponseChoice{
|
|
{
|
|
Index: 0,
|
|
Message: msg,
|
|
FinishReason: finishReason,
|
|
},
|
|
},
|
|
Usage: *usage,
|
|
}
|
|
|
|
return out, usage, nil
|
|
}
|
|
|
|
func UsageFromResponsesUsage(src *dto.Usage) *dto.Usage {
|
|
usage := &dto.Usage{}
|
|
if src == nil {
|
|
return usage
|
|
}
|
|
usage.UsageSemantic = src.UsageSemantic
|
|
usage.UsageSource = src.UsageSource
|
|
usage.BillingUsage = dto.CloneBillingUsage(src.BillingUsage)
|
|
if usage.BillingUsage == nil {
|
|
usage.BillingUsage = dto.NewOpenAIResponsesBillingUsage(src)
|
|
}
|
|
usage.Cost = src.Cost
|
|
if src.InputTokens != 0 {
|
|
usage.PromptTokens = src.InputTokens
|
|
usage.InputTokens = src.InputTokens
|
|
}
|
|
if src.OutputTokens != 0 {
|
|
usage.CompletionTokens = src.OutputTokens
|
|
usage.OutputTokens = src.OutputTokens
|
|
}
|
|
if src.TotalTokens != 0 {
|
|
usage.TotalTokens = src.TotalTokens
|
|
} else {
|
|
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
|
|
}
|
|
if src.InputTokensDetails != nil {
|
|
usage.PromptTokensDetails.CachedTokens = src.InputTokensDetails.CachedTokens
|
|
usage.PromptTokensDetails.CachedCreationTokens = src.InputTokensDetails.CachedCreationTokens
|
|
usage.PromptTokensDetails.CacheWriteTokens = src.InputTokensDetails.CacheWriteTokens
|
|
usage.PromptTokensDetails.TextTokens = src.InputTokensDetails.TextTokens
|
|
usage.PromptTokensDetails.ImageTokens = src.InputTokensDetails.ImageTokens
|
|
usage.PromptTokensDetails.AudioTokens = src.InputTokensDetails.AudioTokens
|
|
}
|
|
if src.CompletionTokenDetails.ReasoningTokens != 0 ||
|
|
src.CompletionTokenDetails.TextTokens != 0 ||
|
|
src.CompletionTokenDetails.AudioTokens != 0 ||
|
|
src.CompletionTokenDetails.ImageTokens != 0 {
|
|
usage.CompletionTokenDetails.ReasoningTokens = src.CompletionTokenDetails.ReasoningTokens
|
|
usage.CompletionTokenDetails.TextTokens = src.CompletionTokenDetails.TextTokens
|
|
usage.CompletionTokenDetails.AudioTokens = src.CompletionTokenDetails.AudioTokens
|
|
usage.CompletionTokenDetails.ImageTokens = src.CompletionTokenDetails.ImageTokens
|
|
}
|
|
usage.ClaudeCacheCreation5mTokens = src.ClaudeCacheCreation5mTokens
|
|
usage.ClaudeCacheCreation1hTokens = src.ClaudeCacheCreation1hTokens
|
|
return usage
|
|
}
|
|
|
|
func ExtractOutputTextFromResponses(resp *dto.OpenAIResponsesResponse) string {
|
|
if resp == nil || len(resp.Output) == 0 {
|
|
return ""
|
|
}
|
|
|
|
var sb strings.Builder
|
|
|
|
// Prefer assistant message outputs.
|
|
for _, out := range resp.Output {
|
|
if out.Type != "message" {
|
|
continue
|
|
}
|
|
if out.Role != "" && out.Role != "assistant" {
|
|
continue
|
|
}
|
|
for _, c := range out.Content {
|
|
if c.Type == "output_text" && c.Text != "" {
|
|
sb.WriteString(c.Text)
|
|
}
|
|
}
|
|
}
|
|
if sb.Len() > 0 {
|
|
return sb.String()
|
|
}
|
|
for _, out := range resp.Output {
|
|
for _, c := range out.Content {
|
|
if c.Text != "" {
|
|
sb.WriteString(c.Text)
|
|
}
|
|
}
|
|
}
|
|
return sb.String()
|
|
}
|
|
|
|
func ExtractReasoningTextFromResponses(resp *dto.OpenAIResponsesResponse) string {
|
|
if resp == nil || len(resp.Output) == 0 {
|
|
return ""
|
|
}
|
|
|
|
var sb strings.Builder
|
|
for _, out := range resp.Output {
|
|
if out.Type != responsesOutputTypeReasoning {
|
|
continue
|
|
}
|
|
for _, c := range out.Content {
|
|
if c.Text != "" {
|
|
sb.WriteString(c.Text)
|
|
}
|
|
}
|
|
}
|
|
return sb.String()
|
|
}
|
|
|
|
func responseStatusString(resp *dto.OpenAIResponsesResponse) string {
|
|
if resp == nil || len(resp.Status) == 0 {
|
|
return ""
|
|
}
|
|
var status string
|
|
_ = kitutil.Unmarshal(resp.Status, &status)
|
|
return strings.TrimSpace(status)
|
|
}
|
|
|
|
func ensureIncompleteResponse(resp *dto.OpenAIResponsesResponse) *dto.OpenAIResponsesResponse {
|
|
if resp == nil {
|
|
resp = &dto.OpenAIResponsesResponse{}
|
|
}
|
|
if len(resp.Status) == 0 {
|
|
resp.Status = []byte(`"incomplete"`)
|
|
}
|
|
return resp
|
|
}
|
|
|
|
func isResponsesToolOutputType(outputType string) bool {
|
|
return outputType == responsesOutputTypeFunctionCall || outputType == responsesOutputTypeCustomToolCall
|
|
}
|
|
|
|
func responseStreamEventItemID(event *dto.ResponsesStreamResponse) string {
|
|
if event == nil {
|
|
return ""
|
|
}
|
|
if event.Item != nil {
|
|
if itemID := strings.TrimSpace(event.Item.ID); itemID != "" {
|
|
return itemID
|
|
}
|
|
}
|
|
return strings.TrimSpace(event.ItemID)
|
|
}
|
|
|
|
func fallbackToolKey(itemID string, callID string, outputIndex *int) string {
|
|
if outputIndex != nil {
|
|
return fmt.Sprintf("output:%d", *outputIndex)
|
|
}
|
|
if strings.TrimSpace(itemID) != "" {
|
|
return "item:" + strings.TrimSpace(itemID)
|
|
}
|
|
if strings.TrimSpace(callID) != "" {
|
|
return "call:" + strings.TrimSpace(callID)
|
|
}
|
|
return ""
|
|
}
|
|
|
|
func fallbackCallID(event *dto.ResponsesStreamResponse) string {
|
|
if event == nil {
|
|
return ""
|
|
}
|
|
if strings.TrimSpace(event.ItemID) != "" {
|
|
return strings.TrimSpace(event.ItemID)
|
|
}
|
|
if event.OutputIndex != nil {
|
|
return fmt.Sprintf("call_output_%d", *event.OutputIndex)
|
|
}
|
|
return ""
|
|
}
|