Files
new-api/service/relayconvert/chat_to_responses_response.go
T
Calcium-Ion 2d5a041639 feat: support Responses to Chat (#5787)
* fix(openai): harden Chat-to-Responses compatibility

Add a shared Responses-to-Chat stream state machine and use it from the OpenAI relay path. Preserve assistant text alongside tool calls, bind tool argument deltas by output_index, map incomplete finish reasons, support reasoning/custom tool events, and buffer upstream SSE for non-stream Chat clients.

Add deterministic service tests and relay SSE tests for the conversion path.

Related to #5745.

* refactor: rename openaicompat to relayconvert for improved clarity

* feat(gemini): support responses request conversion

* feat: add responses to chat conversion support

* fix: harden responses chat conversion edge cases
2026-06-28 14:25:47 +08:00

606 lines
17 KiB
Go

package relayconvert
import (
"errors"
"fmt"
"sort"
"strings"
"time"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/dto"
)
const (
chatFinishReasonLength = "length"
chatFinishReasonContentFilter = "content_filter"
)
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
}
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.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
}
return usage
}
type ChatToResponsesStreamEvent struct {
Type string
Payload dto.ResponsesStreamResponse
}
type ChatToResponsesStreamState struct {
ID string
Model string
Created int64
Usage *dto.Usage
status string
incompleteDetails *dto.IncompleteDetails
sentCreated bool
textOutputIndex int
textStarted bool
textDone bool
reasoningIndex int
reasoningStarted bool
reasoningDone bool
finalized bool
nextOutputIndex int
toolsByIndex map[int]*chatToResponsesStreamTool
outputOrder []chatToResponsesOutputRef
text strings.Builder
reasoning strings.Builder
}
type chatToResponsesStreamTool struct {
ChatIndex int
OutputIndex int
ID string
Name string
Arguments strings.Builder
Done bool
}
type chatToResponsesOutputRef struct {
Kind string
ToolIndex int
}
func NewChatToResponsesStreamState(id string, model string) *ChatToResponsesStreamState {
return &ChatToResponsesStreamState{
ID: id,
Model: model,
Created: time.Now().Unix(),
Usage: &dto.Usage{},
status: "completed",
textOutputIndex: -1,
reasoningIndex: -1,
toolsByIndex: make(map[int]*chatToResponsesStreamTool),
}
}
func ChatCompletionsStreamChunkToResponsesEvents(chunk *dto.ChatCompletionsStreamResponse, state *ChatToResponsesStreamState) ([]ChatToResponsesStreamEvent, error) {
if chunk == nil || state == nil {
return nil, nil
}
if state.ID == "" {
state.ID = chunk.Id
}
if state.Model == "" {
state.Model = chunk.Model
}
if state.Created == 0 {
state.Created = chunk.Created
}
if chunk.Usage != nil {
state.Usage = UsageFromChatUsage(chunk.Usage)
}
events := make([]ChatToResponsesStreamEvent, 0)
if !state.sentCreated {
state.sentCreated = true
events = append(events, responsesStreamEvent(responsesEventCreated, dto.ResponsesStreamResponse{
Type: responsesEventCreated,
Response: state.createdResponse(),
}))
}
for _, choice := range chunk.Choices {
if choice.Delta.GetReasoningContent() != "" {
events = append(events, state.appendReasoningDelta(choice.Delta.GetReasoningContent())...)
}
if choice.Delta.GetContentString() != "" {
events = append(events, state.appendTextDelta(choice.Delta.GetContentString())...)
}
for _, toolCall := range choice.Delta.ToolCalls {
toolEvents, err := state.appendToolCallDelta(toolCall)
if err != nil {
return nil, err
}
events = append(events, toolEvents...)
}
if choice.FinishReason != nil && strings.TrimSpace(*choice.FinishReason) != "" {
state.applyFinishReason(*choice.FinishReason)
events = append(events, state.doneDeltaEvents()...)
}
}
return events, nil
}
func FinalizeChatCompletionsStreamToResponses(state *ChatToResponsesStreamState) []ChatToResponsesStreamEvent {
if state == nil || state.finalized {
return nil
}
events := state.doneDeltaEvents()
state.finalized = true
resp := state.finalResponse()
eventType := responsesEventCompleted
if state.status == "incomplete" {
eventType = responsesEventIncomplete
}
events = append(events, responsesStreamEvent(eventType, dto.ResponsesStreamResponse{
Type: eventType,
Response: resp,
}))
return events
}
func (s *ChatToResponsesStreamState) UsageText() string {
if s == nil {
return ""
}
return s.text.String()
}
func (s *ChatToResponsesStreamState) appendTextDelta(delta string) []ChatToResponsesStreamEvent {
events := make([]ChatToResponsesStreamEvent, 0, 2)
if !s.textStarted {
s.textStarted = true
s.textOutputIndex = s.nextIndex("message", -1)
events = append(events, responsesStreamEvent(responsesEventOutputItemAdded, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemAdded,
OutputIndex: intPtr(s.textOutputIndex),
Item: &dto.ResponsesOutput{
Type: responsesOutputTypeMessage,
ID: s.messageID(),
Status: "in_progress",
Role: "assistant",
Content: []dto.ResponsesOutputContent{},
},
}))
}
s.text.WriteString(delta)
events = append(events, responsesStreamEvent(responsesEventOutputTextDelta, dto.ResponsesStreamResponse{
Type: responsesEventOutputTextDelta,
OutputIndex: intPtr(s.textOutputIndex),
ContentIndex: intPtr(0),
Delta: delta,
ItemID: s.messageID(),
}))
return events
}
func (s *ChatToResponsesStreamState) appendReasoningDelta(delta string) []ChatToResponsesStreamEvent {
events := make([]ChatToResponsesStreamEvent, 0, 2)
if !s.reasoningStarted {
s.reasoningStarted = true
s.reasoningIndex = s.nextIndex("reasoning", -1)
events = append(events, responsesStreamEvent(responsesEventOutputItemAdded, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemAdded,
OutputIndex: intPtr(s.reasoningIndex),
Item: &dto.ResponsesOutput{
Type: responsesOutputTypeReasoning,
ID: s.reasoningID(),
Status: "in_progress",
Content: []dto.ResponsesOutputContent{},
},
}))
}
s.reasoning.WriteString(delta)
events = append(events, responsesStreamEvent(responsesEventReasoningSummaryDelta, dto.ResponsesStreamResponse{
Type: responsesEventReasoningSummaryDelta,
OutputIndex: intPtr(s.reasoningIndex),
SummaryIndex: intPtr(0),
Delta: delta,
ItemID: s.reasoningID(),
}))
return events
}
func (s *ChatToResponsesStreamState) appendToolCallDelta(toolCall dto.ToolCallResponse) ([]ChatToResponsesStreamEvent, error) {
chatIndex := 0
if toolCall.Index != nil {
chatIndex = *toolCall.Index
}
tool := s.toolsByIndex[chatIndex]
events := make([]ChatToResponsesStreamEvent, 0, 2)
if tool == nil {
tool = &chatToResponsesStreamTool{
ChatIndex: chatIndex,
OutputIndex: s.nextIndex("tool", chatIndex),
ID: strings.TrimSpace(toolCall.ID),
Name: strings.TrimSpace(toolCall.Function.Name),
}
if tool.ID == "" {
tool.ID = fmt.Sprintf("%s_call_%d", s.ID, chatIndex)
}
s.toolsByIndex[chatIndex] = tool
events = append(events, responsesStreamEvent(responsesEventOutputItemAdded, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemAdded,
OutputIndex: intPtr(tool.OutputIndex),
ItemID: tool.ID,
Item: &dto.ResponsesOutput{
Type: responsesOutputTypeFunctionCall,
ID: tool.ID,
Status: "in_progress",
CallId: tool.ID,
Name: tool.Name,
Arguments: []byte(`""`),
},
}))
}
if strings.TrimSpace(toolCall.ID) != "" {
tool.ID = strings.TrimSpace(toolCall.ID)
}
if strings.TrimSpace(toolCall.Function.Name) != "" {
tool.Name = strings.TrimSpace(toolCall.Function.Name)
}
if toolCall.Function.Arguments != "" {
tool.Arguments.WriteString(toolCall.Function.Arguments)
events = append(events, responsesStreamEvent(responsesEventFunctionArgsDelta, dto.ResponsesStreamResponse{
Type: responsesEventFunctionArgsDelta,
OutputIndex: intPtr(tool.OutputIndex),
ItemID: tool.ID,
Delta: toolCall.Function.Arguments,
}))
}
return events, nil
}
func (s *ChatToResponsesStreamState) doneDeltaEvents() []ChatToResponsesStreamEvent {
events := make([]ChatToResponsesStreamEvent, 0)
status := s.outputStatus()
if s.textStarted && !s.textDone {
s.textDone = true
events = append(events, responsesStreamEvent("response.output_text.done", dto.ResponsesStreamResponse{
Type: "response.output_text.done",
OutputIndex: intPtr(s.textOutputIndex),
ContentIndex: intPtr(0),
ItemID: s.messageID(),
}))
events = append(events, responsesStreamEvent(responsesEventOutputItemDone, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemDone,
OutputIndex: intPtr(s.textOutputIndex),
Item: s.messageOutput(status),
}))
}
if s.reasoningStarted && !s.reasoningDone {
s.reasoningDone = true
events = append(events, responsesStreamEvent(responsesEventReasoningSummaryDone, dto.ResponsesStreamResponse{
Type: responsesEventReasoningSummaryDone,
OutputIndex: intPtr(s.reasoningIndex),
SummaryIndex: intPtr(0),
ItemID: s.reasoningID(),
Part: &dto.ResponsesReasoningSummaryPart{
Type: "summary_text",
Text: s.reasoning.String(),
},
}))
events = append(events, responsesStreamEvent(responsesEventOutputItemDone, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemDone,
OutputIndex: intPtr(s.reasoningIndex),
Item: s.reasoningOutput(status),
}))
}
for _, tool := range s.sortedTools() {
if tool.Done {
continue
}
tool.Done = true
events = append(events, responsesStreamEvent(responsesEventFunctionArgsDone, dto.ResponsesStreamResponse{
Type: responsesEventFunctionArgsDone,
OutputIndex: intPtr(tool.OutputIndex),
ItemID: tool.ID,
}))
events = append(events, responsesStreamEvent(responsesEventOutputItemDone, dto.ResponsesStreamResponse{
Type: responsesEventOutputItemDone,
OutputIndex: intPtr(tool.OutputIndex),
Item: s.toolOutput(tool, status),
}))
}
return events
}
func (s *ChatToResponsesStreamState) applyFinishReason(finishReason string) {
if status, details := ResponsesStatusFromChatFinishReason(finishReason); status != "" {
s.status = status
s.incompleteDetails = details
}
}
func (s *ChatToResponsesStreamState) finalResponse() *dto.OpenAIResponsesResponse {
output := make([]dto.ResponsesOutput, 0, len(s.outputOrder))
status := s.outputStatus()
for _, ref := range s.outputOrder {
switch ref.Kind {
case "message":
output = append(output, *s.messageOutput(status))
case "reasoning":
output = append(output, *s.reasoningOutput(status))
case "tool":
if tool := s.toolsByIndex[ref.ToolIndex]; tool != nil {
output = append(output, *s.toolOutput(tool, status))
}
}
}
return &dto.OpenAIResponsesResponse{
ID: s.ID,
Object: "response",
CreatedAt: int(s.Created),
Status: []byte(fmt.Sprintf("%q", s.status)),
IncompleteDetails: s.incompleteDetails,
Model: s.Model,
Output: output,
Usage: s.Usage,
}
}
func (s *ChatToResponsesStreamState) createdResponse() *dto.OpenAIResponsesResponse {
return &dto.OpenAIResponsesResponse{
ID: s.ID,
Object: "response",
CreatedAt: int(s.Created),
Status: []byte(`"in_progress"`),
Model: s.Model,
Output: []dto.ResponsesOutput{},
}
}
func (s *ChatToResponsesStreamState) nextIndex(kind string, toolIndex int) int {
index := s.nextOutputIndex
s.nextOutputIndex++
s.outputOrder = append(s.outputOrder, chatToResponsesOutputRef{Kind: kind, ToolIndex: toolIndex})
return index
}
func (s *ChatToResponsesStreamState) sortedTools() []*chatToResponsesStreamTool {
indexes := make([]int, 0, len(s.toolsByIndex))
for index := range s.toolsByIndex {
indexes = append(indexes, index)
}
sort.Ints(indexes)
tools := make([]*chatToResponsesStreamTool, 0, len(indexes))
for _, index := range indexes {
tools = append(tools, s.toolsByIndex[index])
}
return tools
}
func (s *ChatToResponsesStreamState) outputStatus() string {
if s.status == "incomplete" {
return "incomplete"
}
return "completed"
}
func (s *ChatToResponsesStreamState) messageID() string {
return fmt.Sprintf("%s_msg_0", s.ID)
}
func (s *ChatToResponsesStreamState) reasoningID() string {
return fmt.Sprintf("%s_reasoning_0", s.ID)
}
func (s *ChatToResponsesStreamState) messageOutput(status string) *dto.ResponsesOutput {
return &dto.ResponsesOutput{
Type: responsesOutputTypeMessage,
ID: s.messageID(),
Status: status,
Role: "assistant",
Content: []dto.ResponsesOutputContent{
{
Type: "output_text",
Text: s.text.String(),
Annotations: []interface{}{},
},
},
}
}
func (s *ChatToResponsesStreamState) reasoningOutput(status string) *dto.ResponsesOutput {
return &dto.ResponsesOutput{
Type: responsesOutputTypeReasoning,
ID: s.reasoningID(),
Status: status,
Content: []dto.ResponsesOutputContent{
{
Type: "summary_text",
Text: s.reasoning.String(),
},
},
}
}
func (s *ChatToResponsesStreamState) toolOutput(tool *chatToResponsesStreamTool, status string) *dto.ResponsesOutput {
return &dto.ResponsesOutput{
Type: responsesOutputTypeFunctionCall,
ID: tool.ID,
Status: status,
CallId: tool.ID,
Name: tool.Name,
Arguments: chatArgumentsRawMessage(tool.Arguments.String()),
}
}
func responseOutputStatus(resp *dto.OpenAIResponsesResponse) string {
if resp == nil || responseStatusString(resp) != "incomplete" {
return "completed"
}
return "incomplete"
}
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 := common.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 := common.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
}