* 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
302 lines
9.0 KiB
Go
302 lines
9.0 KiB
Go
package dify
|
||
|
||
import (
|
||
"bytes"
|
||
"encoding/base64"
|
||
"encoding/json"
|
||
"fmt"
|
||
"io"
|
||
"mime/multipart"
|
||
"net/http"
|
||
"os"
|
||
"strings"
|
||
|
||
"github.com/QuantumNous/new-api/common"
|
||
"github.com/QuantumNous/new-api/constant"
|
||
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
||
"github.com/QuantumNous/new-api/relay/helper"
|
||
"github.com/QuantumNous/new-api/relaykit/dto"
|
||
"github.com/QuantumNous/new-api/relaykit/types"
|
||
"github.com/QuantumNous/new-api/service"
|
||
"github.com/samber/lo"
|
||
|
||
"github.com/gin-gonic/gin"
|
||
)
|
||
|
||
func uploadDifyFile(c *gin.Context, info *relaycommon.RelayInfo, user string, media dto.MediaContent) *DifyFile {
|
||
uploadUrl := fmt.Sprintf("%s/v1/files/upload", info.ChannelBaseUrl)
|
||
switch media.Type {
|
||
case dto.ContentTypeImageURL:
|
||
// Decode base64 data
|
||
imageMedia := media.GetImageMedia()
|
||
base64Data := imageMedia.Url
|
||
// Remove base64 prefix if exists (e.g., "data:image/jpeg;base64,")
|
||
if idx := strings.Index(base64Data, ","); idx != -1 {
|
||
base64Data = base64Data[idx+1:]
|
||
}
|
||
|
||
// Decode base64 string
|
||
decodedData, err := base64.StdEncoding.DecodeString(base64Data)
|
||
if err != nil {
|
||
common.SysLog("failed to decode base64: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
// Create temporary file
|
||
tempFile, err := os.CreateTemp("", "dify-upload-*")
|
||
if err != nil {
|
||
common.SysLog("failed to create temp file: " + err.Error())
|
||
return nil
|
||
}
|
||
defer tempFile.Close()
|
||
defer os.Remove(tempFile.Name())
|
||
|
||
// Write decoded data to temp file
|
||
if _, err := tempFile.Write(decodedData); err != nil {
|
||
common.SysLog("failed to write to temp file: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
// Create multipart form
|
||
body := &bytes.Buffer{}
|
||
writer := multipart.NewWriter(body)
|
||
|
||
// Add user field
|
||
if err := writer.WriteField("user", user); err != nil {
|
||
common.SysLog("failed to add user field: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
// Create form file with proper mime type
|
||
mimeType := imageMedia.MimeType
|
||
if mimeType == "" {
|
||
mimeType = "image/jpeg" // default mime type
|
||
}
|
||
|
||
// Create form file
|
||
part, err := writer.CreateFormFile("file", fmt.Sprintf("image.%s", strings.TrimPrefix(mimeType, "image/")))
|
||
if err != nil {
|
||
common.SysLog("failed to create form file: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
// Copy file content to form
|
||
if _, err = io.Copy(part, bytes.NewReader(decodedData)); err != nil {
|
||
common.SysLog("failed to copy file content: " + err.Error())
|
||
return nil
|
||
}
|
||
writer.Close()
|
||
|
||
// Create HTTP request
|
||
req, err := http.NewRequest("POST", uploadUrl, body)
|
||
if err != nil {
|
||
common.SysLog("failed to create request: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
req.Header.Set("Content-Type", writer.FormDataContentType())
|
||
req.Header.Set("Authorization", fmt.Sprintf("Bearer %s", info.ApiKey))
|
||
|
||
// Send request
|
||
client := service.GetHttpClient()
|
||
resp, err := client.Do(req)
|
||
if err != nil {
|
||
common.SysLog("failed to send request: " + err.Error())
|
||
return nil
|
||
}
|
||
defer resp.Body.Close()
|
||
|
||
// Parse response
|
||
var result struct {
|
||
Id string `json:"id"`
|
||
}
|
||
if err := json.NewDecoder(resp.Body).Decode(&result); err != nil {
|
||
common.SysLog("failed to decode response: " + err.Error())
|
||
return nil
|
||
}
|
||
|
||
return &DifyFile{
|
||
UploadFileId: result.Id,
|
||
Type: "image",
|
||
TransferMode: "local_file",
|
||
}
|
||
}
|
||
return nil
|
||
}
|
||
|
||
func requestOpenAI2Dify(c *gin.Context, info *relaycommon.RelayInfo, request dto.GeneralOpenAIRequest) *DifyChatRequest {
|
||
difyReq := DifyChatRequest{
|
||
Inputs: make(map[string]interface{}),
|
||
AutoGenerateName: false,
|
||
}
|
||
|
||
user := request.User
|
||
if len(user) == 0 {
|
||
user = json.RawMessage(helper.GetResponseID(c))
|
||
}
|
||
var stringUser string
|
||
err := json.Unmarshal(user, &stringUser)
|
||
if err != nil {
|
||
common.SysLog("failed to unmarshal user: " + err.Error())
|
||
stringUser = helper.GetResponseID(c)
|
||
}
|
||
difyReq.User = stringUser
|
||
|
||
files := make([]DifyFile, 0)
|
||
var content strings.Builder
|
||
for _, message := range request.Messages {
|
||
if message.Role == "system" {
|
||
content.WriteString("SYSTEM: \n" + message.StringContent() + "\n")
|
||
} else if message.Role == "assistant" {
|
||
content.WriteString("ASSISTANT: \n" + message.StringContent() + "\n")
|
||
} else {
|
||
parseContent := message.ParseContent()
|
||
for _, mediaContent := range parseContent {
|
||
switch mediaContent.Type {
|
||
case dto.ContentTypeText:
|
||
content.WriteString("USER: \n" + mediaContent.Text + "\n")
|
||
case dto.ContentTypeImageURL:
|
||
media := mediaContent.GetImageMedia()
|
||
var file *DifyFile
|
||
if media.IsRemoteImage() {
|
||
// 修复 #2083: 远程图片分支此前未初始化 file,
|
||
// 导致 file.Type = ... 触发 nil pointer dereference
|
||
// 而 panic(500: "invalid memory address or nil pointer dereference")。
|
||
file = &DifyFile{
|
||
Type: media.MimeType,
|
||
TransferMode: "remote_url",
|
||
URL: media.Url,
|
||
}
|
||
} else {
|
||
file = uploadDifyFile(c, info, difyReq.User, mediaContent)
|
||
}
|
||
if file != nil {
|
||
files = append(files, *file)
|
||
}
|
||
}
|
||
}
|
||
}
|
||
}
|
||
difyReq.Query = content.String()
|
||
difyReq.Files = files
|
||
mode := "blocking"
|
||
if lo.FromPtrOr(request.Stream, false) {
|
||
mode = "streaming"
|
||
}
|
||
difyReq.ResponseMode = mode
|
||
return &difyReq
|
||
}
|
||
|
||
func streamResponseDify2OpenAI(difyResponse DifyChunkChatCompletionResponse) *dto.ChatCompletionsStreamResponse {
|
||
response := dto.ChatCompletionsStreamResponse{
|
||
Object: "chat.completion.chunk",
|
||
Created: common.GetTimestamp(),
|
||
Model: "dify",
|
||
}
|
||
var choice dto.ChatCompletionsStreamResponseChoice
|
||
if strings.HasPrefix(difyResponse.Event, "workflow_") {
|
||
if constant.DifyDebug {
|
||
text := "Workflow: " + difyResponse.Data.WorkflowId
|
||
if difyResponse.Event == "workflow_finished" {
|
||
text += " " + difyResponse.Data.Status
|
||
}
|
||
choice.Delta.SetReasoningContent(text + "\n")
|
||
}
|
||
} else if strings.HasPrefix(difyResponse.Event, "node_") {
|
||
if constant.DifyDebug {
|
||
text := "Node: " + difyResponse.Data.NodeType
|
||
if difyResponse.Event == "node_finished" {
|
||
text += " " + difyResponse.Data.Status
|
||
}
|
||
choice.Delta.SetReasoningContent(text + "\n")
|
||
}
|
||
} else if difyResponse.Event == "message" || difyResponse.Event == "agent_message" {
|
||
if difyResponse.Answer == "<details style=\"color:gray;background-color: #f8f8f8;padding: 8px;border-radius: 4px;\" open> <summary> Thinking... </summary>\n" {
|
||
difyResponse.Answer = "<think>"
|
||
} else if difyResponse.Answer == "</details>" {
|
||
difyResponse.Answer = "</think>"
|
||
}
|
||
|
||
choice.Delta.SetContentString(difyResponse.Answer)
|
||
}
|
||
response.Choices = append(response.Choices, choice)
|
||
return &response
|
||
}
|
||
|
||
func difyStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
||
var responseText string
|
||
usage := &dto.Usage{}
|
||
var nodeToken int
|
||
helper.SetEventStreamHeaders(c)
|
||
helper.StreamScannerHandler(c, resp, info, func(data string, sr *helper.StreamResult) {
|
||
var difyResponse DifyChunkChatCompletionResponse
|
||
if err := json.Unmarshal([]byte(data), &difyResponse); err != nil {
|
||
common.SysLog("error unmarshalling stream response: " + err.Error())
|
||
sr.Error(err)
|
||
return
|
||
}
|
||
if difyResponse.Event == "message_end" {
|
||
usage = &difyResponse.MetaData.Usage
|
||
sr.Done()
|
||
return
|
||
} else if difyResponse.Event == "error" {
|
||
sr.Stop(fmt.Errorf("dify error event"))
|
||
return
|
||
}
|
||
openaiResponse := *streamResponseDify2OpenAI(difyResponse)
|
||
if len(openaiResponse.Choices) != 0 {
|
||
responseText += openaiResponse.Choices[0].Delta.GetContentString()
|
||
if openaiResponse.Choices[0].Delta.ReasoningContent != nil {
|
||
nodeToken += 1
|
||
}
|
||
}
|
||
if err := helper.ObjectData(c, openaiResponse); err != nil {
|
||
common.SysLog(err.Error())
|
||
sr.Error(err)
|
||
}
|
||
})
|
||
helper.Done(c)
|
||
if usage.TotalTokens == 0 {
|
||
usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
|
||
}
|
||
usage.CompletionTokens += nodeToken
|
||
return usage, nil
|
||
}
|
||
|
||
func difyHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
||
var difyResponse DifyChatCompletionResponse
|
||
responseBody, err := io.ReadAll(resp.Body)
|
||
|
||
if err != nil {
|
||
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
||
}
|
||
service.CloseResponseBodyGracefully(resp)
|
||
err = json.Unmarshal(responseBody, &difyResponse)
|
||
if err != nil {
|
||
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
||
}
|
||
fullTextResponse := dto.OpenAITextResponse{
|
||
Id: difyResponse.ConversationId,
|
||
Object: "chat.completion",
|
||
Created: common.GetTimestamp(),
|
||
Usage: difyResponse.MetaData.Usage,
|
||
}
|
||
choice := dto.OpenAITextResponseChoice{
|
||
Index: 0,
|
||
Message: dto.Message{
|
||
Role: "assistant",
|
||
Content: difyResponse.Answer,
|
||
},
|
||
FinishReason: "stop",
|
||
}
|
||
fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
|
||
jsonResponse, err := json.Marshal(fullTextResponse)
|
||
if err != nil {
|
||
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
||
}
|
||
c.Writer.Header().Set("Content-Type", "application/json")
|
||
c.Writer.WriteHeader(resp.StatusCode)
|
||
c.Writer.Write(jsonResponse)
|
||
return &difyResponse.MetaData.Usage, nil
|
||
}
|