Files
new-api/router/relay-router.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

230 lines
8.4 KiB
Go
Raw Blame History

This file contains ambiguous Unicode characters
This file contains Unicode characters that might be confused with other characters. If you think that this is intentional, you can safely ignore this warning. Use the Escape button to reveal them.
package router
import (
"github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/controller"
"github.com/QuantumNous/new-api/middleware"
"github.com/QuantumNous/new-api/relay"
"github.com/QuantumNous/new-api/relaykit/types"
"github.com/gin-gonic/gin"
)
func SetRelayRouter(router *gin.Engine) {
router.Use(middleware.CORS())
router.Use(middleware.DecompressRequestMiddleware())
router.Use(middleware.BodyStorageCleanup()) // 清理请求体存储
router.Use(middleware.StatsMiddleware())
// https://platform.openai.com/docs/api-reference/introduction
modelsRouter := router.Group("/v1/models")
modelsRouter.Use(middleware.RouteTag("relay"))
modelsRouter.Use(middleware.TokenAuth())
{
modelsRouter.GET("", func(c *gin.Context) {
switch {
case c.GetHeader("x-api-key") != "" && c.GetHeader("anthropic-version") != "":
controller.ListModels(c, constant.ChannelTypeAnthropic)
case c.GetHeader("x-goog-api-key") != "" || c.Query("key") != "": // 单独的适配
controller.RetrieveModel(c, constant.ChannelTypeGemini)
default:
controller.ListModels(c, constant.ChannelTypeOpenAI)
}
})
modelsRouter.GET("/:model", func(c *gin.Context) {
switch {
case c.GetHeader("x-api-key") != "" && c.GetHeader("anthropic-version") != "":
controller.RetrieveModel(c, constant.ChannelTypeAnthropic)
default:
controller.RetrieveModel(c, constant.ChannelTypeOpenAI)
}
})
}
geminiRouter := router.Group("/v1beta/models")
geminiRouter.Use(middleware.RouteTag("relay"))
geminiRouter.Use(middleware.TokenAuth())
{
geminiRouter.GET("", func(c *gin.Context) {
controller.ListModels(c, constant.ChannelTypeGemini)
})
}
geminiCompatibleRouter := router.Group("/v1beta/openai/models")
geminiCompatibleRouter.Use(middleware.RouteTag("relay"))
geminiCompatibleRouter.Use(middleware.TokenAuth())
{
geminiCompatibleRouter.GET("", func(c *gin.Context) {
controller.ListModels(c, constant.ChannelTypeOpenAI)
})
}
playgroundRouter := router.Group("/pg")
playgroundRouter.Use(middleware.RouteTag("relay"))
playgroundRouter.Use(middleware.SystemPerformanceCheck())
playgroundRouter.Use(middleware.UserAuth(), middleware.Distribute())
{
playgroundRouter.POST("/chat/completions", controller.Playground)
}
relayV1Router := router.Group("/v1")
relayV1Router.Use(middleware.RouteTag("relay"))
relayV1Router.Use(middleware.SystemPerformanceCheck())
relayV1Router.Use(middleware.TokenAuth())
relayV1Router.Use(middleware.ModelRequestRateLimit())
{
// WebSocket 路由(统一到 Relay
wsRouter := relayV1Router.Group("")
wsRouter.Use(middleware.Distribute())
wsRouter.GET("/realtime", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIRealtime)
})
}
{
//http router
httpRouter := relayV1Router.Group("")
httpRouter.Use(middleware.Distribute())
// claude related routes
httpRouter.POST("/messages", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatClaude)
})
// chat related routes
httpRouter.POST("/completions", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAI)
})
httpRouter.POST("/chat/completions", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAI)
})
// response related routes
httpRouter.POST("/responses", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIResponses)
})
httpRouter.POST("/responses/compact", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIResponsesCompaction)
})
// alpha search related routes (Codex standalone web search)
httpRouter.POST("/alpha/search", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIAlphaSearch)
})
// image related routes
httpRouter.POST("/edits", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIImage)
})
httpRouter.POST("/images/generations", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIImage)
})
httpRouter.POST("/images/edits", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIImage)
})
// embedding related routes
httpRouter.POST("/embeddings", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatEmbedding)
})
// audio related routes
httpRouter.POST("/audio/transcriptions", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIAudio)
})
httpRouter.POST("/audio/translations", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIAudio)
})
httpRouter.POST("/audio/speech", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAIAudio)
})
// rerank related routes
httpRouter.POST("/rerank", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatRerank)
})
// gemini relay routes
httpRouter.POST("/engines/:model/embeddings", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatGemini)
})
httpRouter.POST("/models/*path", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatGemini)
})
// other relay routes
httpRouter.POST("/moderations", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatOpenAI)
})
// not implemented
httpRouter.POST("/images/variations", controller.RelayNotImplemented)
httpRouter.GET("/files", controller.RelayNotImplemented)
httpRouter.POST("/files", controller.RelayNotImplemented)
httpRouter.DELETE("/files/:id", controller.RelayNotImplemented)
httpRouter.GET("/files/:id", controller.RelayNotImplemented)
httpRouter.GET("/files/:id/content", controller.RelayNotImplemented)
httpRouter.POST("/fine-tunes", controller.RelayNotImplemented)
httpRouter.GET("/fine-tunes", controller.RelayNotImplemented)
httpRouter.GET("/fine-tunes/:id", controller.RelayNotImplemented)
httpRouter.POST("/fine-tunes/:id/cancel", controller.RelayNotImplemented)
httpRouter.GET("/fine-tunes/:id/events", controller.RelayNotImplemented)
httpRouter.DELETE("/models/:model", controller.RelayNotImplemented)
}
relayMjRouter := router.Group("/mj")
relayMjRouter.Use(middleware.RouteTag("relay"))
relayMjRouter.Use(middleware.SystemPerformanceCheck())
registerMjRouterGroup(relayMjRouter)
relayMjModeRouter := router.Group("/:mode/mj")
relayMjModeRouter.Use(middleware.RouteTag("relay"))
relayMjModeRouter.Use(middleware.SystemPerformanceCheck())
registerMjRouterGroup(relayMjModeRouter)
//relayMjRouter.Use()
relaySunoRouter := router.Group("/suno")
relaySunoRouter.Use(middleware.RouteTag("relay"))
relaySunoRouter.Use(middleware.SystemPerformanceCheck())
relaySunoRouter.Use(middleware.TokenAuth(), middleware.Distribute())
{
relaySunoRouter.POST("/submit/:action", controller.RelayTask)
relaySunoRouter.POST("/fetch", controller.RelayTaskFetch)
relaySunoRouter.GET("/fetch/:id", controller.RelayTaskFetch)
}
relayGeminiRouter := router.Group("/v1beta")
relayGeminiRouter.Use(middleware.RouteTag("relay"))
relayGeminiRouter.Use(middleware.SystemPerformanceCheck())
relayGeminiRouter.Use(middleware.TokenAuth())
relayGeminiRouter.Use(middleware.ModelRequestRateLimit())
relayGeminiRouter.Use(middleware.Distribute())
{
// Gemini API 路径格式: /v1beta/models/{model_name}:{action}
relayGeminiRouter.POST("/models/*path", func(c *gin.Context) {
controller.Relay(c, types.RelayFormatGemini)
})
}
}
func registerMjRouterGroup(relayMjRouter *gin.RouterGroup) {
relayMjRouter.GET("/image/:id", relay.RelayMidjourneyImage)
relayMjRouter.Use(middleware.TokenAuth(), middleware.Distribute())
{
relayMjRouter.POST("/submit/action", controller.RelayMidjourney)
relayMjRouter.POST("/submit/shorten", controller.RelayMidjourney)
relayMjRouter.POST("/submit/modal", controller.RelayMidjourney)
relayMjRouter.POST("/submit/imagine", controller.RelayMidjourney)
relayMjRouter.POST("/submit/change", controller.RelayMidjourney)
relayMjRouter.POST("/submit/simple-change", controller.RelayMidjourney)
relayMjRouter.POST("/submit/describe", controller.RelayMidjourney)
relayMjRouter.POST("/submit/blend", controller.RelayMidjourney)
relayMjRouter.POST("/submit/edits", controller.RelayMidjourney)
relayMjRouter.POST("/submit/video", controller.RelayMidjourney)
//relayMjRouter.POST("/notify", controller.RelayMidjourney)
relayMjRouter.GET("/task/:id/fetch", controller.RelayMidjourney)
relayMjRouter.GET("/task/:id/image-seed", controller.RelayMidjourney)
relayMjRouter.POST("/task/list-by-condition", controller.RelayMidjourney)
relayMjRouter.POST("/insight-face/swap", controller.RelayMidjourney)
relayMjRouter.POST("/submit/upload-discord-images", controller.RelayMidjourney)
}
}