* 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
228 lines
6.1 KiB
Go
228 lines
6.1 KiB
Go
package helper
|
|
|
|
import (
|
|
"errors"
|
|
"fmt"
|
|
"net/http"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/logger"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
"github.com/gorilla/websocket"
|
|
)
|
|
|
|
func FlushWriter(c *gin.Context) (err error) {
|
|
defer func() {
|
|
if r := recover(); r != nil {
|
|
err = fmt.Errorf("flush panic recovered: %v", r)
|
|
}
|
|
}()
|
|
|
|
if c == nil || c.Writer == nil {
|
|
return nil
|
|
}
|
|
|
|
if requestContextDone(c) {
|
|
return fmt.Errorf("request context done: %w", c.Request.Context().Err())
|
|
}
|
|
|
|
flusher, ok := c.Writer.(http.Flusher)
|
|
if !ok {
|
|
return errors.New("streaming error: flusher not found")
|
|
}
|
|
|
|
flusher.Flush()
|
|
return nil
|
|
}
|
|
|
|
func requestContextDone(c *gin.Context) bool {
|
|
return c != nil && c.Request != nil && c.Request.Context().Err() != nil
|
|
}
|
|
|
|
func SetEventStreamHeaders(c *gin.Context) {
|
|
// 检查是否已经设置过头部
|
|
if _, exists := c.Get("event_stream_headers_set"); exists {
|
|
return
|
|
}
|
|
|
|
// 设置标志,表示头部已经设置过
|
|
c.Set("event_stream_headers_set", true)
|
|
|
|
c.Writer.Header().Set("Content-Type", "text/event-stream")
|
|
c.Writer.Header().Set("Cache-Control", "no-cache")
|
|
c.Writer.Header().Set("Connection", "keep-alive")
|
|
c.Writer.Header().Set("Transfer-Encoding", "chunked")
|
|
c.Writer.Header().Set("X-Accel-Buffering", "no")
|
|
}
|
|
|
|
func ClaudeData(c *gin.Context, resp dto.ClaudeResponse) error {
|
|
if requestContextDone(c) {
|
|
return nil
|
|
}
|
|
|
|
jsonData, err := common.Marshal(resp)
|
|
if err != nil {
|
|
common.SysError("error marshalling stream response: " + err.Error())
|
|
} else {
|
|
c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("event: %s\n", resp.Type)})
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonData)})
|
|
}
|
|
_ = FlushWriter(c)
|
|
return nil
|
|
}
|
|
|
|
func ClaudeChunkData(c *gin.Context, resp dto.ClaudeResponse, data string) {
|
|
if requestContextDone(c) {
|
|
return
|
|
}
|
|
|
|
c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("event: %s\n", resp.Type)})
|
|
c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("data: %s\n", data)})
|
|
_ = FlushWriter(c)
|
|
}
|
|
|
|
func ResponseChunkData(c *gin.Context, resp dto.ResponsesStreamResponse, data string) error {
|
|
if requestContextDone(c) {
|
|
return fmt.Errorf("request context done: %w", c.Request.Context().Err())
|
|
}
|
|
|
|
c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("event: %s\n", resp.Type)})
|
|
c.Render(-1, common.CustomEvent{Data: fmt.Sprintf("data: %s", data)})
|
|
return FlushWriter(c)
|
|
}
|
|
|
|
func StringData(c *gin.Context, str string) error {
|
|
if c == nil || c.Writer == nil {
|
|
return errors.New("context or writer is nil")
|
|
}
|
|
|
|
if requestContextDone(c) {
|
|
return fmt.Errorf("request context done: %w", c.Request.Context().Err())
|
|
}
|
|
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + str})
|
|
return FlushWriter(c)
|
|
}
|
|
|
|
func PingData(c *gin.Context) error {
|
|
if c == nil || c.Writer == nil {
|
|
return errors.New("context or writer is nil")
|
|
}
|
|
|
|
if requestContextDone(c) {
|
|
return fmt.Errorf("request context done: %w", c.Request.Context().Err())
|
|
}
|
|
|
|
if _, err := c.Writer.Write([]byte(": PING\n\n")); err != nil {
|
|
return fmt.Errorf("write ping data failed: %w", err)
|
|
}
|
|
return FlushWriter(c)
|
|
}
|
|
|
|
func ObjectData(c *gin.Context, object interface{}) error {
|
|
if object == nil {
|
|
return errors.New("object is nil")
|
|
}
|
|
jsonData, err := common.Marshal(object)
|
|
if err != nil {
|
|
return fmt.Errorf("error marshalling object: %w", err)
|
|
}
|
|
return StringData(c, string(jsonData))
|
|
}
|
|
|
|
func Done(c *gin.Context) {
|
|
_ = StringData(c, "[DONE]")
|
|
}
|
|
|
|
func WssString(c *gin.Context, ws *websocket.Conn, str string) error {
|
|
if ws == nil {
|
|
logger.LogError(c, "websocket connection is nil")
|
|
return errors.New("websocket connection is nil")
|
|
}
|
|
//common.LogInfo(c, fmt.Sprintf("sending message: %s", str))
|
|
return ws.WriteMessage(1, []byte(str))
|
|
}
|
|
|
|
func WssObject(c *gin.Context, ws *websocket.Conn, object interface{}) error {
|
|
jsonData, err := common.Marshal(object)
|
|
if err != nil {
|
|
return fmt.Errorf("error marshalling object: %w", err)
|
|
}
|
|
if ws == nil {
|
|
logger.LogError(c, "websocket connection is nil")
|
|
return errors.New("websocket connection is nil")
|
|
}
|
|
//common.LogInfo(c, fmt.Sprintf("sending message: %s", jsonData))
|
|
return ws.WriteMessage(1, jsonData)
|
|
}
|
|
|
|
func WssError(c *gin.Context, ws *websocket.Conn, openaiError types.OpenAIError) {
|
|
if ws == nil {
|
|
return
|
|
}
|
|
errorObj := &dto.RealtimeEvent{
|
|
Type: "error",
|
|
EventId: GetLocalRealtimeID(c),
|
|
Error: &openaiError,
|
|
}
|
|
_ = WssObject(c, ws, errorObj)
|
|
}
|
|
|
|
func GetResponseID(c *gin.Context) string {
|
|
logID := c.GetString(common.RequestIdKey)
|
|
return fmt.Sprintf("chatcmpl-%s", logID)
|
|
}
|
|
|
|
func GetLocalRealtimeID(c *gin.Context) string {
|
|
logID := c.GetString(common.RequestIdKey)
|
|
return fmt.Sprintf("evt_%s", logID)
|
|
}
|
|
|
|
func GenerateStartEmptyResponse(id string, createAt int64, model string, systemFingerprint *string) *dto.ChatCompletionsStreamResponse {
|
|
return &dto.ChatCompletionsStreamResponse{
|
|
Id: id,
|
|
Object: "chat.completion.chunk",
|
|
Created: createAt,
|
|
Model: model,
|
|
SystemFingerprint: systemFingerprint,
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{
|
|
{
|
|
Delta: dto.ChatCompletionsStreamResponseChoiceDelta{
|
|
Role: "assistant",
|
|
Content: common.GetPointer(""),
|
|
},
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
func GenerateStopResponse(id string, createAt int64, model string, finishReason string) *dto.ChatCompletionsStreamResponse {
|
|
return &dto.ChatCompletionsStreamResponse{
|
|
Id: id,
|
|
Object: "chat.completion.chunk",
|
|
Created: createAt,
|
|
Model: model,
|
|
SystemFingerprint: nil,
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{
|
|
{
|
|
FinishReason: &finishReason,
|
|
},
|
|
},
|
|
}
|
|
}
|
|
|
|
func GenerateFinalUsageResponse(id string, createAt int64, model string, usage dto.Usage) *dto.ChatCompletionsStreamResponse {
|
|
return &dto.ChatCompletionsStreamResponse{
|
|
Id: id,
|
|
Object: "chat.completion.chunk",
|
|
Created: createAt,
|
|
Model: model,
|
|
SystemFingerprint: nil,
|
|
Choices: make([]dto.ChatCompletionsStreamResponseChoice, 0),
|
|
Usage: &usage,
|
|
}
|
|
}
|