Files
new-api/relay/helper/common.go
T
Calcium-Ion 86ac0f7745 refactor: extract protocol conversion layer into standalone relaykit module (#6369)
* 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
2026-07-27 15:56:21 +08:00

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,
}
}