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

service/convert.go

@@ -628,12 +628,14 @@ func ResponseOpenAI2Claude(openAIResponse *dto.OpenAITextResponse, info *relayco
 			claudeContent.Type = "tool_use"
 			claudeContent.Id = toolUse.ID
 			claudeContent.Name = toolUse.Function.Name
-			var mapParams map[string]interface{}
-			if err := common.Unmarshal([]byte(toolUse.Function.Arguments), &mapParams); err == nil {
-				claudeContent.Input = mapParams
-			} else {
-				claudeContent.Input = toolUse.Function.Arguments
+			mapParams := map[string]interface{}{}
+			if strings.TrimSpace(toolUse.Function.Arguments) != "" {
+				var parsed map[string]interface{}
+				if err := common.Unmarshal([]byte(toolUse.Function.Arguments), &parsed); err == nil && parsed != nil {
+					mapParams = parsed
+				}
 			}
+			claudeContent.Input = mapParams
 			contents = append(contents, claudeContent)
 		}
 	}

service/openai_chat_responses_compat.go

@@ -2,21 +2,29 @@ package service
 
 import (
 	"github.com/QuantumNous/new-api/dto"
-	"github.com/QuantumNous/new-api/service/openaicompat"
+	"github.com/QuantumNous/new-api/service/relayconvert"
 )
 
 func ChatCompletionsRequestToResponsesRequest(req *dto.GeneralOpenAIRequest) (*dto.OpenAIResponsesRequest, error) {
-	return openaicompat.ChatCompletionsRequestToResponsesRequest(req)
+	return relayconvert.ChatCompletionsRequestToResponsesRequest(req)
+}
+
+func ResponsesRequestToChatCompletionsRequest(req *dto.OpenAIResponsesRequest) (*dto.GeneralOpenAIRequest, error) {
+	return relayconvert.ResponsesRequestToChatCompletionsRequest(req)
+}
+
+func ChatCompletionsResponseToResponsesResponse(resp *dto.OpenAITextResponse, id string) (*dto.OpenAIResponsesResponse, *dto.Usage, error) {
+	return relayconvert.ChatCompletionsResponseToResponsesResponse(resp, id)
 }
 
 func ResponsesResponseToChatCompletionsResponse(resp *dto.OpenAIResponsesResponse, id string) (*dto.OpenAITextResponse, *dto.Usage, error) {
-	return openaicompat.ResponsesResponseToChatCompletionsResponse(resp, id)
+	return relayconvert.ResponsesResponseToChatCompletionsResponse(resp, id)
 }
 
 func ResponsesFinishReasonFromStatus(resp *dto.OpenAIResponsesResponse) (string, bool) {
-	return openaicompat.ResponsesFinishReasonFromStatus(resp)
+	return relayconvert.ResponsesFinishReasonFromStatus(resp)
 }
 
 func ExtractOutputTextFromResponses(resp *dto.OpenAIResponsesResponse) string {
-	return openaicompat.ExtractOutputTextFromResponses(resp)
+	return relayconvert.ExtractOutputTextFromResponses(resp)
 }

service/openai_chat_responses_mode.go

@@ -1,14 +1,14 @@
 package service
 
 import (
-	"github.com/QuantumNous/new-api/service/openaicompat"
+	"github.com/QuantumNous/new-api/service/relayconvert"
 	"github.com/QuantumNous/new-api/setting/model_setting"
 )
 
 func ShouldChatCompletionsUseResponsesPolicy(policy model_setting.ChatCompletionsToResponsesPolicy, channelID int, channelType int, model string) bool {
-	return openaicompat.ShouldChatCompletionsUseResponsesPolicy(policy, channelID, channelType, model)
+	return relayconvert.ShouldChatCompletionsUseResponsesPolicy(policy, channelID, channelType, model)
 }
 
 func ShouldChatCompletionsUseResponsesGlobal(channelID int, channelType int, model string) bool {
-	return openaicompat.ShouldChatCompletionsUseResponsesGlobal(channelID, channelType, model)
+	return relayconvert.ShouldChatCompletionsUseResponsesGlobal(channelID, channelType, model)
 }

service/relayconvert/chat_responses_compat_test.go

@@ -1,4 +1,4 @@
-package openaicompat
+package relayconvert
 
 import (
 	"testing"
@@ -182,6 +182,70 @@ func TestResponsesStreamEventToChatChunksUsesOutputIndexForToolArguments(t *test
 	assert.Equal(t, 3, state.Usage.TotalTokens)
 }
 
+func TestResponsesStreamEventToChatChunksDoesNotDuplicatePendingArgsWithOutputIndexAndItemID(t *testing.T) {
+	state := newTestResponsesStreamState()
+	outputIndex := 1
+
+	var chunks []dto.ChatCompletionsStreamResponse
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{Type: responsesEventCreated})...)
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{
+		Type:        responsesEventFunctionArgsDelta,
+		OutputIndex: &outputIndex,
+		ItemID:      "fc_1",
+		Delta:       `{"q":"x"}`,
+	})...)
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{
+		Type:        responsesEventOutputItemAdded,
+		OutputIndex: &outputIndex,
+		ItemID:      "fc_1",
+		Item: &dto.ResponsesOutput{
+			Type:   responsesOutputTypeFunctionCall,
+			ID:     "fc_1",
+			CallId: "call_1",
+			Name:   "lookup",
+		},
+	})...)
+
+	require.Len(t, chunks, 2)
+	tool := chunks[1].Choices[0].Delta.ToolCalls[0]
+	assert.Equal(t, "call_1", tool.ID)
+	assert.Equal(t, "lookup", tool.Function.Name)
+	assert.Equal(t, `{"q":"x"}`, tool.Function.Arguments)
+	assert.Empty(t, state.pendingArgsByOutputIndex)
+	assert.Empty(t, state.pendingArgsByItemID)
+}
+
+func TestResponsesStreamEventToChatChunksDrainsItemOnlyPendingArgsWhenOutputIndexArrives(t *testing.T) {
+	state := newTestResponsesStreamState()
+	outputIndex := 1
+
+	var chunks []dto.ChatCompletionsStreamResponse
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{Type: responsesEventCreated})...)
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{
+		Type:   responsesEventFunctionArgsDelta,
+		ItemID: "fc_1",
+		Delta:  `{"q":"x"}`,
+	})...)
+	chunks = append(chunks, mustStreamChunks(t, state, &dto.ResponsesStreamResponse{
+		Type:        responsesEventOutputItemAdded,
+		OutputIndex: &outputIndex,
+		ItemID:      "fc_1",
+		Item: &dto.ResponsesOutput{
+			Type:   responsesOutputTypeFunctionCall,
+			CallId: "call_1",
+			Name:   "lookup",
+		},
+	})...)
+
+	require.Len(t, chunks, 2)
+	tool := chunks[1].Choices[0].Delta.ToolCalls[0]
+	assert.Equal(t, "call_1", tool.ID)
+	assert.Equal(t, "lookup", tool.Function.Name)
+	assert.Equal(t, `{"q":"x"}`, tool.Function.Arguments)
+	assert.Empty(t, state.pendingArgsByOutputIndex)
+	assert.Empty(t, state.pendingArgsByItemID)
+}
+
 func TestResponsesStreamEventToChatChunksCustomToolAndReasoning(t *testing.T) {
 	state := newTestResponsesStreamState()
 	outputIndex := 0
@@ -313,6 +377,165 @@ func TestResponsesBufferedAccumulatorSupplementsEmptyTerminalOutput(t *testing.T
 	assert.Equal(t, `{"q":"x"}`, toolCalls[0].Function.Arguments)
 }
 
+func TestResponsesBufferedAccumulatorDoesNotDuplicatePendingArgsWithOutputIndexAndItemID(t *testing.T) {
+	acc := NewResponsesBufferedAccumulator()
+	outputIndex := 1
+	acc.ProcessEvent(&dto.ResponsesStreamResponse{
+		Type:        responsesEventFunctionArgsDelta,
+		OutputIndex: &outputIndex,
+		ItemID:      "fc_1",
+		Delta:       `{"q":"x"}`,
+	})
+	acc.ProcessEvent(&dto.ResponsesStreamResponse{
+		Type:        responsesEventOutputItemAdded,
+		OutputIndex: &outputIndex,
+		ItemID:      "fc_1",
+		Item: &dto.ResponsesOutput{
+			Type:   responsesOutputTypeFunctionCall,
+			ID:     "fc_1",
+			CallId: "call_1",
+			Name:   "lookup",
+		},
+	})
+
+	resp := &dto.OpenAIResponsesResponse{
+		Status: []byte(`"completed"`),
+		Model:  "gpt-test",
+	}
+	acc.SupplementResponseOutput(resp)
+
+	chat, _, err := ResponsesResponseToChatCompletionsResponse(resp, "chatcmpl_1")
+	require.NoError(t, err)
+	toolCalls := chat.Choices[0].Message.ParseToolCalls()
+	require.Len(t, toolCalls, 1)
+	assert.Equal(t, `{"q":"x"}`, toolCalls[0].Function.Arguments)
+	assert.Empty(t, acc.pendingByOutputIndex)
+	assert.Empty(t, acc.pendingByItemID)
+}
+
+func TestChatCompletionsResponseToResponsesPreservesTextToolCallsAndUsage(t *testing.T) {
+	chat := &dto.OpenAITextResponse{
+		Id:      "chatcmpl_1",
+		Model:   "gpt-test",
+		Created: 456,
+		Choices: []dto.OpenAITextResponseChoice{
+			{
+				Message:      assistantMessageWithTool("I will call.", "call_1", "lookup", `{"q":"x"}`),
+				FinishReason: "tool_calls",
+			},
+		},
+		Usage: dto.Usage{PromptTokens: 3, CompletionTokens: 5, TotalTokens: 8},
+	}
+
+	resp, usage, err := ChatCompletionsResponseToResponsesResponse(chat, "resp_1")
+	require.NoError(t, err)
+	require.NotNil(t, usage)
+
+	assert.Equal(t, "resp_1", resp.ID)
+	assert.Equal(t, "response", resp.Object)
+	assert.Equal(t, `"completed"`, string(resp.Status))
+	assert.Equal(t, 3, resp.Usage.InputTokens)
+	assert.Equal(t, 5, resp.Usage.OutputTokens)
+	require.Len(t, resp.Output, 2)
+	assert.Equal(t, responsesOutputTypeMessage, resp.Output[0].Type)
+	assert.Equal(t, "I will call.", resp.Output[0].Content[0].Text)
+	assert.Equal(t, responsesOutputTypeFunctionCall, resp.Output[1].Type)
+	assert.Equal(t, "call_1", resp.Output[1].CallId)
+	assert.Equal(t, "lookup", resp.Output[1].Name)
+	assert.Equal(t, `"{\"q\":\"x\"}"`, string(resp.Output[1].Arguments))
+}
+
+func TestChatCompletionsResponseToResponsesMapsIncompleteFinishReasons(t *testing.T) {
+	tests := []struct {
+		name         string
+		finishReason string
+		wantReason   string
+	}{
+		{name: "length", finishReason: "length", wantReason: responsesIncompleteReasonMaxTokens},
+		{name: "content filter", finishReason: "content_filter", wantReason: responsesIncompleteReasonContentFilter},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			resp, _, err := ChatCompletionsResponseToResponsesResponse(&dto.OpenAITextResponse{
+				Id:    "chatcmpl_1",
+				Model: "gpt-test",
+				Choices: []dto.OpenAITextResponseChoice{
+					{
+						Message:      dto.Message{Role: "assistant", Content: "partial"},
+						FinishReason: tt.finishReason,
+					},
+				},
+			}, "resp_1")
+			require.NoError(t, err)
+
+			assert.Equal(t, `"incomplete"`, string(resp.Status))
+			require.NotNil(t, resp.IncompleteDetails)
+			assert.Equal(t, tt.wantReason, resp.IncompleteDetails.Reason)
+			require.Len(t, resp.Output, 1)
+			assert.Equal(t, "incomplete", resp.Output[0].Status)
+		})
+	}
+}
+
+func TestChatCompletionsStreamToResponsesEventsAggregatesUsageAndToolArgs(t *testing.T) {
+	state := NewChatToResponsesStreamState("resp_1", "gpt-test")
+	state.Created = 123
+	toolIndex := 0
+
+	var events []ChatToResponsesStreamEvent
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Id:      "chatcmpl_1",
+		Model:   "gpt-test",
+		Created: 123,
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{Index: 0, Delta: dto.ChatCompletionsStreamResponseChoiceDelta{Role: "assistant"}},
+		},
+	})...)
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{Index: 0, Delta: dto.ChatCompletionsStreamResponseChoiceDelta{Content: lo.ToPtr("hello")}},
+		},
+	})...)
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{Index: 0, Delta: dto.ChatCompletionsStreamResponseChoiceDelta{ToolCalls: []dto.ToolCallResponse{
+				{Index: &toolIndex, ID: "call_1", Type: "function", Function: dto.FunctionResponse{Name: "lookup"}},
+			}}},
+		},
+	})...)
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{Index: 0, Delta: dto.ChatCompletionsStreamResponseChoiceDelta{ToolCalls: []dto.ToolCallResponse{
+				{Index: &toolIndex, Function: dto.FunctionResponse{Arguments: `{"q":"x"}`}},
+			}}},
+		},
+	})...)
+	finishReason := "tool_calls"
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Choices: []dto.ChatCompletionsStreamResponseChoice{
+			{Index: 0, FinishReason: &finishReason},
+		},
+	})...)
+	events = append(events, mustResponsesEventsFromChatChunk(t, state, &dto.ChatCompletionsStreamResponse{
+		Usage: &dto.Usage{PromptTokens: 2, CompletionTokens: 4, TotalTokens: 6},
+	})...)
+	events = append(events, FinalizeChatCompletionsStreamToResponses(state)...)
+
+	require.Len(t, events, 10)
+	assert.Equal(t, responsesEventCreated, events[0].Type)
+	assert.Equal(t, responsesEventOutputTextDelta, events[2].Type)
+	assert.Equal(t, "hello", events[2].Payload.Delta)
+	assert.Equal(t, responsesEventFunctionArgsDelta, events[4].Type)
+	assert.Equal(t, `{"q":"x"}`, events[4].Payload.Delta)
+	assert.Equal(t, responsesEventCompleted, events[9].Type)
+	require.NotNil(t, events[9].Payload.Response)
+	assert.Equal(t, 6, events[9].Payload.Response.Usage.TotalTokens)
+	require.Len(t, events[9].Payload.Response.Output, 2)
+	assert.Equal(t, "hello", events[9].Payload.Response.Output[0].Content[0].Text)
+	assert.Equal(t, `"{\"q\":\"x\"}"`, string(events[9].Payload.Response.Output[1].Arguments))
+}
+
 func assistantMessageWithTool(content string, id string, name string, args string) dto.Message {
 	msg := dto.Message{Role: "assistant", Content: content}
 	msg.SetToolCalls([]dto.ToolCallRequest{
@@ -341,3 +564,10 @@ func mustStreamChunks(t *testing.T, state *ResponsesToChatStreamState, event *dt
 	require.NoError(t, err)
 	return chunks
 }
+
+func mustResponsesEventsFromChatChunk(t *testing.T, state *ChatToResponsesStreamState, chunk *dto.ChatCompletionsStreamResponse) []ChatToResponsesStreamEvent {
+	t.Helper()
+	events, err := ChatCompletionsStreamChunkToResponsesEvents(chunk, state)
+	require.NoError(t, err)
+	return events
+}

service/relayconvert/chat_to_responses.go

@@ -1,4 +1,4 @@
-package openaicompat
+package relayconvert
 
 import (
 	"encoding/json"

service/relayconvert/chat_to_responses_response.go

@@ -0,0 +1,605 @@
+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
+}

service/relayconvert/policy.go

@@ -1,4 +1,4 @@
-package openaicompat
+package relayconvert
 
 import "github.com/QuantumNous/new-api/setting/model_setting"
 

service/relayconvert/regex.go

@@ -1,4 +1,4 @@
-package openaicompat
+package relayconvert
 
 import (
 	"regexp"

service/relayconvert/responses_request_to_chat.go

@@ -0,0 +1,521 @@
+package relayconvert
+
+import (
+	"encoding/json"
+	"errors"
+	"fmt"
+	"strings"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+)
+
+const (
+	responsesInputTypeFunctionCall       = "function_call"
+	responsesInputTypeFunctionCallOutput = "function_call_output"
+	responsesInputTypeCustomToolCall     = "custom_tool_call"
+)
+
+func ResponsesRequestToChatCompletionsRequest(req *dto.OpenAIResponsesRequest) (*dto.GeneralOpenAIRequest, error) {
+	if req == nil {
+		return nil, errors.New("request is nil")
+	}
+	if req.Model == "" {
+		return nil, errors.New("model is required")
+	}
+	if err := validateResponsesRequestChatUnsupportedFields(req); err != nil {
+		return nil, err
+	}
+
+	messages, err := responsesRequestMessagesToChat(req)
+	if err != nil {
+		return nil, err
+	}
+
+	tools, err := responsesRequestToolsToChat(req.Tools)
+	if err != nil {
+		return nil, err
+	}
+
+	toolChoice, err := responsesRequestToolChoiceToChat(req.ToolChoice)
+	if err != nil {
+		return nil, err
+	}
+
+	responseFormat, err := responsesRequestTextToChatResponseFormat(req.Text)
+	if err != nil {
+		return nil, err
+	}
+
+	out := &dto.GeneralOpenAIRequest{
+		Model:                req.Model,
+		Messages:             messages,
+		Stream:               req.Stream,
+		StreamOptions:        req.StreamOptions,
+		MaxCompletionTokens:  req.MaxOutputTokens,
+		Temperature:          req.Temperature,
+		TopP:                 req.TopP,
+		TopLogProbs:          req.TopLogProbs,
+		ResponseFormat:       responseFormat,
+		Tools:                tools,
+		ToolChoice:           toolChoice,
+		User:                 req.User,
+		Store:                req.Store,
+		Metadata:             req.Metadata,
+		SafetyIdentifier:     req.SafetyIdentifier,
+		PromptCacheRetention: req.PromptCacheRetention,
+		EnableThinking:       req.EnableThinking,
+	}
+
+	if req.Reasoning != nil {
+		out.ReasoningEffort = req.Reasoning.Effort
+	}
+	if req.ServiceTier != "" {
+		out.ServiceTier, _ = common.Marshal(req.ServiceTier)
+	}
+	if len(req.ParallelToolCalls) > 0 && common.GetJsonType(req.ParallelToolCalls) == "boolean" {
+		var parallelToolCalls bool
+		if err := common.Unmarshal(req.ParallelToolCalls, &parallelToolCalls); err == nil {
+			out.ParallelTooCalls = &parallelToolCalls
+		}
+	}
+	if len(req.PromptCacheKey) > 0 && common.GetJsonType(req.PromptCacheKey) == "string" {
+		var promptCacheKey string
+		if err := common.Unmarshal(req.PromptCacheKey, &promptCacheKey); err == nil {
+			out.PromptCacheKey = promptCacheKey
+		}
+	}
+
+	return out, nil
+}
+
+func validateResponsesRequestChatUnsupportedFields(req *dto.OpenAIResponsesRequest) error {
+	unsupported := make([]string, 0, 4)
+	if rawJSONPresent(req.Conversation) {
+		unsupported = append(unsupported, "conversation")
+	}
+	if strings.TrimSpace(req.PreviousResponseID) != "" {
+		unsupported = append(unsupported, "previous_response_id")
+	}
+	if rawJSONPresent(req.Prompt) {
+		unsupported = append(unsupported, "prompt")
+	}
+	if rawJSONPresent(req.ContextManagement) {
+		unsupported = append(unsupported, "context_management")
+	}
+	if len(unsupported) > 0 {
+		return fmt.Errorf("responses to chat conversion does not support stateful fields: %s", strings.Join(unsupported, ", "))
+	}
+	return nil
+}
+
+func responsesRequestMessagesToChat(req *dto.OpenAIResponsesRequest) ([]dto.Message, error) {
+	messages := make([]dto.Message, 0)
+	if rawJSONPresent(req.Instructions) {
+		instructions, err := responsesJSONString(req.Instructions)
+		if err != nil {
+			return nil, fmt.Errorf("invalid instructions: %w", err)
+		}
+		if strings.TrimSpace(instructions) != "" {
+			messages = append(messages, dto.Message{Role: "system", Content: instructions})
+		}
+	}
+
+	if !rawJSONPresent(req.Input) {
+		return messages, nil
+	}
+
+	switch common.GetJsonType(req.Input) {
+	case "string":
+		input, err := responsesJSONString(req.Input)
+		if err != nil {
+			return nil, fmt.Errorf("invalid input string: %w", err)
+		}
+		messages = append(messages, dto.Message{Role: "user", Content: input})
+		return messages, nil
+	case "array":
+		var items []map[string]any
+		if err := common.Unmarshal(req.Input, &items); err != nil {
+			return nil, fmt.Errorf("invalid input array: %w", err)
+		}
+		for _, item := range items {
+			nextMessages, err := responsesInputItemToChatMessages(item, messages)
+			if err != nil {
+				return nil, err
+			}
+			messages = nextMessages
+		}
+		return messages, nil
+	default:
+		return nil, fmt.Errorf("unsupported responses input type %q", common.GetJsonType(req.Input))
+	}
+}
+
+func responsesInputItemToChatMessages(item map[string]any, messages []dto.Message) ([]dto.Message, error) {
+	itemType := strings.TrimSpace(common.Interface2String(item["type"]))
+	switch itemType {
+	case responsesInputTypeFunctionCall:
+		toolCall, err := responsesFunctionCallItemToChatToolCall(item)
+		if err != nil {
+			return nil, err
+		}
+		return appendToolCallToLastAssistant(messages, toolCall), nil
+	case responsesInputTypeCustomToolCall:
+		toolCall, err := responsesCustomToolCallItemToChatToolCall(item)
+		if err != nil {
+			return nil, err
+		}
+		return appendToolCallToLastAssistant(messages, toolCall), nil
+	case responsesInputTypeFunctionCallOutput:
+		callID := strings.TrimSpace(common.Interface2String(item["call_id"]))
+		content := responseToolOutputToChatContent(item["output"])
+		return append(messages, dto.Message{Role: "tool", ToolCallId: callID, Content: content}), nil
+	}
+
+	role := strings.TrimSpace(common.Interface2String(item["role"]))
+	if role == "" {
+		role = "user"
+	}
+	content, err := responsesInputContentToChatContent(item["content"])
+	if err != nil {
+		return nil, err
+	}
+	return append(messages, dto.Message{Role: role, Content: content}), nil
+}
+
+func responsesInputContentToChatContent(content any) (any, error) {
+	if content == nil {
+		return "", nil
+	}
+
+	switch value := content.(type) {
+	case string:
+		return value, nil
+	case []any:
+		return responsesContentPartsToChatContent(value)
+	case []map[string]any:
+		parts := make([]any, 0, len(value))
+		for _, part := range value {
+			parts = append(parts, part)
+		}
+		return responsesContentPartsToChatContent(parts)
+	default:
+		return content, nil
+	}
+}
+
+func responsesContentPartsToChatContent(parts []any) (any, error) {
+	chatParts := make([]any, 0, len(parts))
+	var textOnly strings.Builder
+	onlyText := true
+
+	for _, rawPart := range parts {
+		part, ok := rawPart.(map[string]any)
+		if !ok {
+			onlyText = false
+			chatParts = append(chatParts, rawPart)
+			continue
+		}
+
+		partType := strings.TrimSpace(common.Interface2String(part["type"]))
+		switch partType {
+		case "input_text", "output_text", "text":
+			text := common.Interface2String(part["text"])
+			textOnly.WriteString(text)
+			chatParts = append(chatParts, map[string]any{
+				"type": dto.ContentTypeText,
+				"text": text,
+			})
+		case "input_image":
+			onlyText = false
+			chatParts = append(chatParts, map[string]any{
+				"type":      dto.ContentTypeImageURL,
+				"image_url": responsesImagePartToChatImageURL(part),
+			})
+		case "input_file":
+			onlyText = false
+			chatParts = append(chatParts, map[string]any{
+				"type": dto.ContentTypeFile,
+				"file": responsesFilePartToChatFile(part),
+			})
+		case "input_audio":
+			onlyText = false
+			chatParts = append(chatParts, map[string]any{
+				"type":        dto.ContentTypeInputAudio,
+				"input_audio": responsesPartPayload(part, "input_audio"),
+			})
+		case "input_video":
+			onlyText = false
+			chatParts = append(chatParts, map[string]any{
+				"type":      dto.ContentTypeVideoUrl,
+				"video_url": responsesVideoPartToChatVideoURL(part),
+			})
+		default:
+			onlyText = false
+			chatParts = append(chatParts, part)
+		}
+	}
+
+	if onlyText {
+		return textOnly.String(), nil
+	}
+	return chatParts, nil
+}
+
+func responsesFunctionCallItemToChatToolCall(item map[string]any) (dto.ToolCallRequest, error) {
+	name := strings.TrimSpace(common.Interface2String(item["name"]))
+	if name == "" {
+		return dto.ToolCallRequest{}, errors.New("function_call item is missing name")
+	}
+	return dto.ToolCallRequest{
+		ID:   responsesCallID(item),
+		Type: "function",
+		Function: dto.FunctionRequest{
+			Name:      name,
+			Arguments: responsesArgumentsString(item["arguments"]),
+		},
+	}, nil
+}
+
+func responsesCustomToolCallItemToChatToolCall(item map[string]any) (dto.ToolCallRequest, error) {
+	raw, err := common.Marshal(item)
+	if err != nil {
+		return dto.ToolCallRequest{}, err
+	}
+	return dto.ToolCallRequest{
+		ID:     responsesCallID(item),
+		Type:   dto.CustomType,
+		Custom: raw,
+		Function: dto.FunctionRequest{
+			Name:      strings.TrimSpace(common.Interface2String(item["name"])),
+			Arguments: responsesArgumentsString(item["input"]),
+		},
+	}, nil
+}
+
+func appendToolCallToLastAssistant(messages []dto.Message, toolCall dto.ToolCallRequest) []dto.Message {
+	if len(messages) == 0 || messages[len(messages)-1].Role != "assistant" {
+		messages = append(messages, dto.Message{Role: "assistant"})
+	}
+
+	idx := len(messages) - 1
+	toolCalls := messages[idx].ParseToolCalls()
+	toolCalls = append(toolCalls, toolCall)
+	toolCallsRaw, _ := common.Marshal(toolCalls)
+	messages[idx].ToolCalls = toolCallsRaw
+	return messages
+}
+
+func responsesRequestToolsToChat(raw json.RawMessage) ([]dto.ToolCallRequest, error) {
+	if !rawJSONPresent(raw) {
+		return nil, nil
+	}
+
+	var tools []map[string]any
+	if err := common.Unmarshal(raw, &tools); err != nil {
+		return nil, fmt.Errorf("invalid tools: %w", err)
+	}
+
+	out := make([]dto.ToolCallRequest, 0, len(tools))
+	for _, tool := range tools {
+		toolType := strings.TrimSpace(common.Interface2String(tool["type"]))
+		if toolType == "function" {
+			out = append(out, dto.ToolCallRequest{
+				Type: "function",
+				Function: dto.FunctionRequest{
+					Name:        strings.TrimSpace(common.Interface2String(tool["name"])),
+					Description: common.Interface2String(tool["description"]),
+					Parameters:  tool["parameters"],
+				},
+			})
+			continue
+		}
+
+		rawTool, err := common.Marshal(tool)
+		if err != nil {
+			return nil, err
+		}
+		out = append(out, dto.ToolCallRequest{
+			Type:   toolType,
+			Custom: rawTool,
+		})
+	}
+	return out, nil
+}
+
+func responsesRequestToolChoiceToChat(raw json.RawMessage) (any, error) {
+	if !rawJSONPresent(raw) {
+		return nil, nil
+	}
+	if common.GetJsonType(raw) == "string" {
+		var choice string
+		if err := common.Unmarshal(raw, &choice); err != nil {
+			return nil, fmt.Errorf("invalid tool_choice: %w", err)
+		}
+		return choice, nil
+	}
+
+	var choice map[string]any
+	if err := common.Unmarshal(raw, &choice); err != nil {
+		return nil, fmt.Errorf("invalid tool_choice: %w", err)
+	}
+	if common.Interface2String(choice["type"]) == "function" {
+		name := strings.TrimSpace(common.Interface2String(choice["name"]))
+		if name != "" {
+			return map[string]any{
+				"type": "function",
+				"function": map[string]any{
+					"name": name,
+				},
+			}, nil
+		}
+	}
+	return choice, nil
+}
+
+func responsesRequestTextToChatResponseFormat(raw json.RawMessage) (*dto.ResponseFormat, error) {
+	if !rawJSONPresent(raw) {
+		return nil, nil
+	}
+
+	var textConfig map[string]any
+	if err := common.Unmarshal(raw, &textConfig); err != nil {
+		return nil, fmt.Errorf("invalid text config: %w", err)
+	}
+	format, ok := textConfig["format"].(map[string]any)
+	if !ok {
+		return nil, nil
+	}
+
+	formatType := strings.TrimSpace(common.Interface2String(format["type"]))
+	if formatType == "" {
+		return nil, nil
+	}
+
+	out := &dto.ResponseFormat{Type: formatType}
+	if formatType == "json_schema" {
+		schemaRaw, err := common.Marshal(format)
+		if err != nil {
+			return nil, err
+		}
+		out.JsonSchema = schemaRaw
+	}
+	return out, nil
+}
+
+func responsesImagePartToChatImageURL(part map[string]any) any {
+	if imageURL, ok := part["image_url"]; ok {
+		return imageURL
+	}
+	imageURL := map[string]any{}
+	for _, key := range []string{"url", "file_id", "detail"} {
+		if value, ok := part[key]; ok {
+			imageURL[key] = value
+		}
+	}
+	if len(imageURL) == 0 {
+		return part
+	}
+	return imageURL
+}
+
+func responsesFilePartToChatFile(part map[string]any) any {
+	if file, ok := part["file"]; ok {
+		return file
+	}
+	file := map[string]any{}
+	for _, key := range []string{"file_id", "file_data", "filename", "file_url"} {
+		if value, ok := part[key]; ok {
+			file[key] = value
+		}
+	}
+	if len(file) == 0 {
+		return part
+	}
+	return file
+}
+
+func responsesVideoPartToChatVideoURL(part map[string]any) any {
+	if videoURL, ok := part["video_url"]; ok {
+		if videoURLMap, ok := videoURL.(map[string]any); ok {
+			if url := common.Interface2String(videoURLMap["url"]); url != "" {
+				return url
+			}
+		}
+		return videoURL
+	}
+	if url := common.Interface2String(part["url"]); url != "" {
+		return url
+	}
+	return responsesPartPayload(part, "video_url")
+}
+
+func responsesPartPayload(part map[string]any, key string) any {
+	if value, ok := part[key]; ok {
+		return value
+	}
+	payload := make(map[string]any, len(part))
+	for k, value := range part {
+		if k == "type" {
+			continue
+		}
+		payload[k] = value
+	}
+	return payload
+}
+
+func responsesCallID(item map[string]any) string {
+	callID := strings.TrimSpace(common.Interface2String(item["call_id"]))
+	if callID != "" {
+		return callID
+	}
+	return strings.TrimSpace(common.Interface2String(item["id"]))
+}
+
+func responsesArgumentsString(value any) string {
+	switch v := value.(type) {
+	case nil:
+		return ""
+	case string:
+		return v
+	default:
+		raw, err := common.Marshal(v)
+		if err != nil {
+			return common.Interface2String(v)
+		}
+		return string(raw)
+	}
+}
+
+func responseToolOutputToChatContent(value any) any {
+	switch v := value.(type) {
+	case nil:
+		return ""
+	case string:
+		return v
+	default:
+		raw, err := common.Marshal(v)
+		if err != nil {
+			return fmt.Sprintf("%v", v)
+		}
+		return string(raw)
+	}
+}
+
+func responsesJSONString(raw json.RawMessage) (string, error) {
+	if common.GetJsonType(raw) != "string" {
+		return string(raw), nil
+	}
+	var value string
+	if err := common.Unmarshal(raw, &value); err != nil {
+		return "", err
+	}
+	return value, nil
+}
+
+func rawJSONPresent(raw json.RawMessage) bool {
+	if len(raw) == 0 {
+		return false
+	}
+	return common.GetJsonType(raw) != "null"
+}

service/relayconvert/responses_request_to_chat_test.go

@@ -0,0 +1,270 @@
+package relayconvert
+
+import (
+	"testing"
+
+	"github.com/QuantumNous/new-api/common"
+	"github.com/QuantumNous/new-api/dto"
+	"github.com/samber/lo"
+	"github.com/stretchr/testify/assert"
+	"github.com/stretchr/testify/require"
+	"github.com/tidwall/gjson"
+)
+
+func TestResponsesRequestToChatCompletionsRequestInstructionsAndScalarInput(t *testing.T) {
+	stream := true
+	temperature := 0.0
+	topP := 0.9
+	maxOutputTokens := uint(128)
+	parallelToolCalls := true
+
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model:                "gpt-test",
+		Instructions:         mustRawMessage(t, "system rules"),
+		Input:                mustRawMessage(t, "hello"),
+		Stream:               &stream,
+		StreamOptions:        &dto.StreamOptions{IncludeUsage: true},
+		MaxOutputTokens:      &maxOutputTokens,
+		Temperature:          &temperature,
+		TopP:                 &topP,
+		User:                 mustRawMessage(t, "user-1"),
+		Store:                mustRawMessage(t, false),
+		Metadata:             mustRawMessage(t, map[string]any{"trace": "abc"}),
+		ParallelToolCalls:    mustRawMessage(t, parallelToolCalls),
+		PromptCacheKey:       mustRawMessage(t, "cache-key"),
+		PromptCacheRetention: mustRawMessage(t, "24h"),
+		Reasoning:            &dto.Reasoning{Effort: "medium"},
+	})
+	require.NoError(t, err)
+
+	assert.Equal(t, "gpt-test", got.Model)
+	require.Len(t, got.Messages, 2)
+	assert.Equal(t, dto.Message{Role: "system", Content: "system rules"}, got.Messages[0])
+	assert.Equal(t, dto.Message{Role: "user", Content: "hello"}, got.Messages[1])
+	assert.Same(t, &stream, got.Stream)
+	require.NotNil(t, got.StreamOptions)
+	assert.True(t, got.StreamOptions.IncludeUsage)
+	assert.Equal(t, maxOutputTokens, lo.FromPtr(got.MaxCompletionTokens))
+	assert.Equal(t, 0.0, lo.FromPtr(got.Temperature))
+	assert.Equal(t, 0.9, lo.FromPtr(got.TopP))
+	assert.True(t, lo.FromPtr(got.ParallelTooCalls))
+	assert.Equal(t, "cache-key", got.PromptCacheKey)
+	assert.Equal(t, "medium", got.ReasoningEffort)
+	assert.Equal(t, `"user-1"`, string(got.User))
+	assert.Equal(t, `false`, string(got.Store))
+	assert.Equal(t, "abc", gjson.GetBytes(got.Metadata, "trace").String())
+}
+
+func TestResponsesRequestToChatCompletionsRequestMultimodalInput(t *testing.T) {
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model: "gpt-test",
+		Input: mustRawMessage(t, []map[string]any{
+			{
+				"role": "user",
+				"content": []map[string]any{
+					{"type": "input_text", "text": "look"},
+					{"type": "input_image", "image_url": "https://example.test/a.png", "detail": "low"},
+					{"type": "input_file", "file_id": "file_1", "filename": "a.txt"},
+					{"type": "input_audio", "input_audio": map[string]any{"data": "abc", "format": "wav"}},
+					{"type": "input_video", "video_url": map[string]any{"url": "https://example.test/v.mp4"}},
+				},
+			},
+		}),
+	})
+	require.NoError(t, err)
+
+	require.Len(t, got.Messages, 1)
+	assert.Equal(t, "user", got.Messages[0].Role)
+	parts := got.Messages[0].ParseContent()
+	require.Len(t, parts, 5)
+	assert.Equal(t, dto.ContentTypeText, parts[0].Type)
+	assert.Equal(t, "look", parts[0].Text)
+	assert.Equal(t, dto.ContentTypeImageURL, parts[1].Type)
+	assert.Equal(t, "https://example.test/a.png", parts[1].GetImageMedia().Url)
+	assert.Equal(t, dto.ContentTypeFile, parts[2].Type)
+	assert.Equal(t, "file_1", parts[2].GetFile().FileId)
+	assert.Equal(t, dto.ContentTypeInputAudio, parts[3].Type)
+	assert.Equal(t, "wav", parts[3].GetInputAudio().Format)
+	assert.Equal(t, dto.ContentTypeVideoUrl, parts[4].Type)
+	assert.Equal(t, "https://example.test/v.mp4", parts[4].GetVideoUrl().Url)
+}
+
+func TestResponsesRequestToChatCompletionsRequestAssistantTextAndFunctionCallCoexist(t *testing.T) {
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model: "gpt-test",
+		Input: mustRawMessage(t, []map[string]any{
+			{
+				"role": "assistant",
+				"content": []map[string]any{
+					{"type": "output_text", "text": "I will call."},
+				},
+			},
+			{
+				"type":      "function_call",
+				"call_id":   "call_1",
+				"name":      "lookup",
+				"arguments": map[string]any{"q": "x"},
+			},
+			{
+				"type":    "function_call_output",
+				"call_id": "call_1",
+				"output":  map[string]any{"ok": true},
+			},
+		}),
+	})
+	require.NoError(t, err)
+
+	require.Len(t, got.Messages, 2)
+	assert.Equal(t, "assistant", got.Messages[0].Role)
+	assert.Equal(t, "I will call.", got.Messages[0].StringContent())
+	toolCalls := got.Messages[0].ParseToolCalls()
+	require.Len(t, toolCalls, 1)
+	assert.Equal(t, "call_1", toolCalls[0].ID)
+	assert.Equal(t, "function", toolCalls[0].Type)
+	assert.Equal(t, "lookup", toolCalls[0].Function.Name)
+	assert.JSONEq(t, `{"q":"x"}`, toolCalls[0].Function.Arguments)
+	assert.Equal(t, "tool", got.Messages[1].Role)
+	assert.Equal(t, "call_1", got.Messages[1].ToolCallId)
+	assert.JSONEq(t, `{"ok":true}`, got.Messages[1].StringContent())
+}
+
+func TestResponsesRequestToChatCompletionsRequestOnlyFunctionCallCreatesAssistant(t *testing.T) {
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model: "gpt-test",
+		Input: mustRawMessage(t, []map[string]any{
+			{
+				"type":      "function_call",
+				"call_id":   "call_1",
+				"name":      "lookup",
+				"arguments": `{"q":"x"}`,
+			},
+		}),
+	})
+	require.NoError(t, err)
+
+	require.Len(t, got.Messages, 1)
+	assert.Equal(t, "assistant", got.Messages[0].Role)
+	assert.Nil(t, got.Messages[0].Content)
+	toolCalls := got.Messages[0].ParseToolCalls()
+	require.Len(t, toolCalls, 1)
+	assert.Equal(t, `{"q":"x"}`, toolCalls[0].Function.Arguments)
+}
+
+func TestResponsesRequestToChatCompletionsRequestToolsToolChoiceAndTextFormat(t *testing.T) {
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model: "gpt-test",
+		Input: mustRawMessage(t, "hello"),
+		Tools: mustRawMessage(t, []map[string]any{
+			{
+				"type":        "function",
+				"name":        "lookup",
+				"description": "Lookup data",
+				"parameters": map[string]any{
+					"type": "object",
+					"properties": map[string]any{
+						"q": map[string]any{"type": "string"},
+					},
+				},
+			},
+		}),
+		ToolChoice: mustRawMessage(t, map[string]any{
+			"type": "function",
+			"name": "lookup",
+		}),
+		Text: mustRawMessage(t, map[string]any{
+			"format": map[string]any{
+				"type":   "json_schema",
+				"name":   "answer",
+				"schema": map[string]any{"type": "object"},
+				"strict": true,
+			},
+		}),
+	})
+	require.NoError(t, err)
+
+	require.Len(t, got.Tools, 1)
+	assert.Equal(t, "function", got.Tools[0].Type)
+	assert.Equal(t, "lookup", got.Tools[0].Function.Name)
+	assert.Equal(t, "Lookup data", got.Tools[0].Function.Description)
+	assert.Equal(t, "object", got.Tools[0].Function.Parameters.(map[string]any)["type"])
+	assert.Equal(t, map[string]any{
+		"type": "function",
+		"function": map[string]any{
+			"name": "lookup",
+		},
+	}, got.ToolChoice)
+	require.NotNil(t, got.ResponseFormat)
+	assert.Equal(t, "json_schema", got.ResponseFormat.Type)
+	assert.Equal(t, "answer", gjson.GetBytes(got.ResponseFormat.JsonSchema, "name").String())
+	assert.True(t, gjson.GetBytes(got.ResponseFormat.JsonSchema, "strict").Bool())
+}
+
+func TestResponsesRequestToChatCompletionsRequestCustomToolCallPreservesRawShape(t *testing.T) {
+	got, err := ResponsesRequestToChatCompletionsRequest(&dto.OpenAIResponsesRequest{
+		Model: "gpt-test",
+		Input: mustRawMessage(t, []map[string]any{
+			{
+				"type":    "custom_tool_call",
+				"call_id": "call_custom",
+				"name":    "apply_patch",
+				"input":   "patch body",
+			},
+		}),
+	})
+	require.NoError(t, err)
+
+	require.Len(t, got.Messages, 1)
+	toolCalls := got.Messages[0].ParseToolCalls()
+	require.Len(t, toolCalls, 1)
+	assert.Equal(t, dto.CustomType, toolCalls[0].Type)
+	assert.Equal(t, "call_custom", toolCalls[0].ID)
+	assert.Equal(t, "apply_patch", toolCalls[0].Function.Name)
+	assert.Equal(t, "patch body", toolCalls[0].Function.Arguments)
+	assert.Equal(t, "custom_tool_call", gjson.GetBytes(toolCalls[0].Custom, "type").String())
+	assert.Equal(t, "patch body", gjson.GetBytes(toolCalls[0].Custom, "input").String())
+}
+
+func TestResponsesRequestToChatCompletionsRequestRejectsStatefulFields(t *testing.T) {
+	tests := []struct {
+		name string
+		req  *dto.OpenAIResponsesRequest
+		want string
+	}{
+		{
+			name: "conversation",
+			req:  &dto.OpenAIResponsesRequest{Model: "gpt-test", Conversation: mustRawMessage(t, "conv_1")},
+			want: "conversation",
+		},
+		{
+			name: "previous response",
+			req:  &dto.OpenAIResponsesRequest{Model: "gpt-test", PreviousResponseID: "resp_1"},
+			want: "previous_response_id",
+		},
+		{
+			name: "prompt",
+			req:  &dto.OpenAIResponsesRequest{Model: "gpt-test", Prompt: mustRawMessage(t, map[string]any{"id": "pmpt_1"})},
+			want: "prompt",
+		},
+		{
+			name: "context management",
+			req:  &dto.OpenAIResponsesRequest{Model: "gpt-test", ContextManagement: mustRawMessage(t, map[string]any{"type": "auto"})},
+			want: "context_management",
+		},
+	}
+
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			_, err := ResponsesRequestToChatCompletionsRequest(tt.req)
+			require.Error(t, err)
+			assert.Contains(t, err.Error(), tt.want)
+			assert.Contains(t, err.Error(), "stateful fields")
+		})
+	}
+}
+
+func mustRawMessage(t *testing.T, value any) []byte {
+	t.Helper()
+	raw, err := common.Marshal(value)
+	require.NoError(t, err)
+	return raw
+}

service/relayconvert/responses_to_chat.go

@@ -1,4 +1,4 @@
-package openaicompat
+package relayconvert
 
 import (
 	"errors"
@@ -438,8 +438,7 @@ func (s *ResponsesToChatStreamState) toolArgumentsDelta(event *dto.ResponsesStre
 	if tool == nil {
 		if event.OutputIndex != nil {
 			s.pendingArgsByOutputIndex[*event.OutputIndex] += event.Delta
-		}
-		if itemID := strings.TrimSpace(event.ItemID); itemID != "" {
+		} else if itemID := strings.TrimSpace(event.ItemID); itemID != "" {
 			s.pendingArgsByItemID[itemID] += event.Delta
 		}
 		return nil
@@ -485,7 +484,7 @@ func (s *ResponsesToChatStreamState) ensureToolForEvent(event *dto.ResponsesStre
 			delete(s.pendingArgsByOutputIndex, *event.OutputIndex)
 		}
 	}
-	if itemID := strings.TrimSpace(event.Item.ID); itemID != "" {
+	if itemID := responseStreamEventItemID(event); itemID != "" {
 		tool.ItemID = itemID
 		s.itemIDToKey[itemID] = key
 		if pending := s.pendingArgsByItemID[itemID]; pending != "" {
@@ -558,7 +557,7 @@ func (s *ResponsesToChatStreamState) ensureFallbackToolForEvent(event *dto.Respo
 			delete(s.pendingArgsByOutputIndex, *event.OutputIndex)
 		}
 	}
-	if itemID := strings.TrimSpace(event.ItemID); itemID != "" {
+	if itemID := responseStreamEventItemID(event); itemID != "" {
 		tool.ItemID = itemID
 		s.itemIDToKey[itemID] = key
 		if pending := s.pendingArgsByItemID[itemID]; pending != "" {
@@ -789,8 +788,7 @@ func (a *ResponsesBufferedAccumulator) ProcessEvent(event *dto.ResponsesStreamRe
 		}
 		if event.OutputIndex != nil {
 			a.pendingByOutputIndex[*event.OutputIndex] += event.Delta
-		}
-		if itemID := strings.TrimSpace(event.ItemID); itemID != "" {
+		} else if itemID := strings.TrimSpace(event.ItemID); itemID != "" {
 			a.pendingByItemID[itemID] += event.Delta
 		}
 	}
@@ -928,6 +926,18 @@ 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)