Files
new-api/relay/channel/cloudflare/relay_cloudflare.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

149 lines
4.4 KiB
Go

package cloudflare
import (
"bufio"
"encoding/json"
"io"
"net/http"
"strings"
"time"
"github.com/QuantumNous/new-api/logger"
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 convertCf2CompletionsRequest(textRequest dto.GeneralOpenAIRequest) *CfRequest {
p, _ := textRequest.Prompt.(string)
return &CfRequest{
Prompt: p,
MaxTokens: textRequest.GetMaxTokens(),
Stream: lo.FromPtrOr(textRequest.Stream, false),
Temperature: textRequest.Temperature,
}
}
func cfStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
scanner := helper.NewStreamScanner(resp.Body)
scanner.Split(bufio.ScanLines)
helper.SetEventStreamHeaders(c)
id := helper.GetResponseID(c)
var responseText string
isFirst := true
for scanner.Scan() {
data := scanner.Text()
if len(data) < len("data: ") {
continue
}
data = strings.TrimPrefix(data, "data: ")
data = strings.TrimSuffix(data, "\r")
if data == "[DONE]" {
break
}
var response dto.ChatCompletionsStreamResponse
err := json.Unmarshal([]byte(data), &response)
if err != nil {
logger.LogError(c, "error_unmarshalling_stream_response: "+err.Error())
continue
}
for _, choice := range response.Choices {
choice.Delta.Role = "assistant"
responseText += choice.Delta.GetContentString()
}
response.Id = id
response.Model = info.UpstreamModelName
err = helper.ObjectData(c, response)
if isFirst {
isFirst = false
info.FirstResponseTime = time.Now()
}
if err != nil {
logger.LogError(c, "error_rendering_stream_response: "+err.Error())
}
}
if err := scanner.Err(); err != nil {
logger.LogError(c, "error_scanning_stream_response: "+err.Error())
}
usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
if info.ShouldIncludeUsage {
response := helper.GenerateFinalUsageResponse(id, info.StartTime.Unix(), info.UpstreamModelName, *usage)
err := helper.ObjectData(c, response)
if err != nil {
logger.LogError(c, "error_rendering_final_usage_response: "+err.Error())
}
}
helper.Done(c)
service.CloseResponseBodyGracefully(resp)
return nil, usage
}
func cfHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
service.CloseResponseBodyGracefully(resp)
var response dto.TextResponse
err = json.Unmarshal(responseBody, &response)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
response.Model = info.UpstreamModelName
var responseText string
for _, choice := range response.Choices {
responseText += choice.Message.StringContent()
}
usage := service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
response.Usage = *usage
response.Id = helper.GetResponseID(c)
jsonResponse, err := json.Marshal(response)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
_, _ = c.Writer.Write(jsonResponse)
return nil, usage
}
func cfSTTHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*types.NewAPIError, *dto.Usage) {
var cfResp CfAudioResponse
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
service.CloseResponseBodyGracefully(resp)
err = json.Unmarshal(responseBody, &cfResp)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
audioResp := &dto.AudioResponse{
Text: cfResp.Result.Text,
}
jsonResponse, err := json.Marshal(audioResp)
if err != nil {
return types.NewError(err, types.ErrorCodeBadResponseBody), nil
}
c.Writer.Header().Set("Content-Type", "application/json")
c.Writer.WriteHeader(resp.StatusCode)
_, _ = c.Writer.Write(jsonResponse)
usage := service.ResponseText2Usage(c, cfResp.Result.Text, info.UpstreamModelName, info.GetEstimatePromptTokens())
return nil, usage
}