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
233 lines
6.8 KiB
Go
233 lines
6.8 KiB
Go
package oaichat
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
kitutil "github.com/QuantumNous/new-api/relaykit/relayconvert/kitutil"
|
|
)
|
|
|
|
const (
|
|
chatFinishReasonLength = "length"
|
|
chatFinishReasonContentFilter = "content_filter"
|
|
|
|
responsesEventCreated = "response.created"
|
|
responsesEventCompleted = "response.completed"
|
|
responsesEventIncomplete = "response.incomplete"
|
|
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"
|
|
responsesEventReasoningSummaryDelta = "response.reasoning_summary_text.delta"
|
|
responsesEventReasoningSummaryDone = "response.reasoning_summary_text.done"
|
|
responsesOutputTypeFunctionCall = "function_call"
|
|
responsesOutputTypeMessage = "message"
|
|
responsesOutputTypeReasoning = "reasoning"
|
|
responsesIncompleteReasonContentFilter = "content_filter"
|
|
responsesIncompleteReasonMaxTokens = "max_output_tokens"
|
|
)
|
|
|
|
func ChatCompletionsResponseToResponsesResponse(resp *dto.OpenAITextResponse, id string) (*dto.OpenAIResponsesResponse, *dto.Usage, error) {
|
|
if resp == nil {
|
|
return nil, nil, errors.New("response is nil")
|
|
}
|
|
|
|
usage := UsageFromChatUsage(&resp.Usage)
|
|
out := &dto.OpenAIResponsesResponse{
|
|
ID: id,
|
|
Object: "response",
|
|
CreatedAt: chatCreatedAt(resp.Created),
|
|
Status: []byte(`"completed"`),
|
|
Model: resp.Model,
|
|
Output: make([]dto.ResponsesOutput, 0),
|
|
Usage: usage,
|
|
}
|
|
|
|
if len(resp.Choices) == 0 {
|
|
return out, usage, nil
|
|
}
|
|
|
|
choice := resp.Choices[0]
|
|
if status, details := ResponsesStatusFromChatFinishReason(choice.FinishReason); status != "" {
|
|
out.Status = []byte(fmt.Sprintf("%q", status))
|
|
out.IncompleteDetails = details
|
|
}
|
|
|
|
if text := choice.Message.StringContent(); text != "" {
|
|
out.Output = append(out.Output, dto.ResponsesOutput{
|
|
Type: responsesOutputTypeMessage,
|
|
ID: fmt.Sprintf("%s_msg_0", id),
|
|
Status: responseOutputStatus(out),
|
|
Role: "assistant",
|
|
Content: []dto.ResponsesOutputContent{
|
|
{
|
|
Type: "output_text",
|
|
Text: text,
|
|
Annotations: []interface{}{},
|
|
},
|
|
},
|
|
})
|
|
}
|
|
if reasoning := choice.Message.GetReasoningContent(); reasoning != "" {
|
|
out.Output = append(out.Output, dto.ResponsesOutput{
|
|
Type: responsesOutputTypeReasoning,
|
|
ID: fmt.Sprintf("%s_reasoning_0", id),
|
|
Status: responseOutputStatus(out),
|
|
Content: []dto.ResponsesOutputContent{
|
|
{
|
|
Type: "summary_text",
|
|
Text: reasoning,
|
|
},
|
|
},
|
|
})
|
|
}
|
|
|
|
for i, toolCall := range choice.Message.ParseToolCalls() {
|
|
toolOutput, err := chatToolCallToResponsesOutput(toolCall, id, i, responseOutputStatus(out))
|
|
if err != nil {
|
|
return nil, nil, err
|
|
}
|
|
out.Output = append(out.Output, toolOutput)
|
|
}
|
|
|
|
return out, usage, nil
|
|
}
|
|
|
|
func ResponsesStatusFromChatFinishReason(finishReason string) (string, *dto.IncompleteDetails) {
|
|
switch strings.TrimSpace(finishReason) {
|
|
case chatFinishReasonLength:
|
|
return "incomplete", &dto.IncompleteDetails{Reason: responsesIncompleteReasonMaxTokens}
|
|
case chatFinishReasonContentFilter:
|
|
return "incomplete", &dto.IncompleteDetails{Reason: responsesIncompleteReasonContentFilter}
|
|
default:
|
|
return "completed", nil
|
|
}
|
|
}
|
|
|
|
func UsageFromChatUsage(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.NewOpenAIChatBillingUsage(src)
|
|
}
|
|
usage.Cost = src.Cost
|
|
if src.PromptTokens != 0 {
|
|
usage.PromptTokens = src.PromptTokens
|
|
usage.InputTokens = src.PromptTokens
|
|
}
|
|
if src.CompletionTokens != 0 {
|
|
usage.CompletionTokens = src.CompletionTokens
|
|
usage.OutputTokens = src.CompletionTokens
|
|
}
|
|
if src.TotalTokens != 0 {
|
|
usage.TotalTokens = src.TotalTokens
|
|
} else {
|
|
usage.TotalTokens = usage.InputTokens + usage.OutputTokens
|
|
}
|
|
if src.PromptTokensDetails.CachedTokens != 0 ||
|
|
src.PromptTokensDetails.ImageTokens != 0 ||
|
|
src.PromptTokensDetails.AudioTokens != 0 ||
|
|
src.PromptTokensDetails.CachedCreationTokens != 0 ||
|
|
src.PromptTokensDetails.CacheWriteTokens != 0 ||
|
|
src.PromptTokensDetails.TextTokens != 0 {
|
|
details := src.PromptTokensDetails
|
|
usage.InputTokensDetails = &details
|
|
}
|
|
if src.CompletionTokenDetails.ReasoningTokens != 0 ||
|
|
src.CompletionTokenDetails.TextTokens != 0 ||
|
|
src.CompletionTokenDetails.AudioTokens != 0 ||
|
|
src.CompletionTokenDetails.ImageTokens != 0 {
|
|
usage.CompletionTokenDetails = src.CompletionTokenDetails
|
|
}
|
|
usage.ClaudeCacheCreation5mTokens = src.ClaudeCacheCreation5mTokens
|
|
usage.ClaudeCacheCreation1hTokens = src.ClaudeCacheCreation1hTokens
|
|
return usage
|
|
}
|
|
|
|
func responseOutputStatus(resp *dto.OpenAIResponsesResponse) string {
|
|
if resp == nil || responseStatusString(resp) != "incomplete" {
|
|
return "completed"
|
|
}
|
|
return "incomplete"
|
|
}
|
|
|
|
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 chatToolCallToResponsesOutput(toolCall dto.ToolCallRequest, responseID string, index int, status string) (dto.ResponsesOutput, error) {
|
|
callID := strings.TrimSpace(toolCall.ID)
|
|
if callID == "" {
|
|
callID = fmt.Sprintf("%s_call_%d", responseID, index)
|
|
}
|
|
if toolCall.Type == "" || toolCall.Type == "function" {
|
|
return dto.ResponsesOutput{
|
|
Type: responsesOutputTypeFunctionCall,
|
|
ID: callID,
|
|
Status: status,
|
|
CallId: callID,
|
|
Name: toolCall.Function.Name,
|
|
Arguments: chatArgumentsRawMessage(toolCall.Function.Arguments),
|
|
}, nil
|
|
}
|
|
return dto.ResponsesOutput{
|
|
Type: toolCall.Type,
|
|
ID: callID,
|
|
Status: status,
|
|
CallId: callID,
|
|
Arguments: toolCall.Custom,
|
|
}, nil
|
|
}
|
|
|
|
func chatArgumentsRawMessage(arguments string) []byte {
|
|
raw, err := kitutil.Marshal(arguments)
|
|
if err != nil {
|
|
return []byte(`""`)
|
|
}
|
|
return raw
|
|
}
|
|
|
|
func chatCreatedAt(created any) int {
|
|
switch v := created.(type) {
|
|
case int:
|
|
return v
|
|
case int64:
|
|
return int(v)
|
|
case float64:
|
|
return int(v)
|
|
case float32:
|
|
return int(v)
|
|
case string:
|
|
if parsed := kitutil.String2Int(v); parsed != 0 {
|
|
return parsed
|
|
}
|
|
}
|
|
return int(time.Now().Unix())
|
|
}
|
|
|
|
func responsesStreamEvent(eventType string, payload dto.ResponsesStreamResponse) ChatToResponsesStreamEvent {
|
|
payload.Type = eventType
|
|
return ChatToResponsesStreamEvent{
|
|
Type: eventType,
|
|
Payload: payload,
|
|
}
|
|
}
|
|
|
|
func intPtr(v int) *int {
|
|
return &v
|
|
}
|