* 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
254 lines
7.4 KiB
Go
254 lines
7.4 KiB
Go
package cohere
|
|
|
|
import (
|
|
"encoding/json"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
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/gin-gonic/gin"
|
|
"github.com/samber/lo"
|
|
)
|
|
|
|
func requestOpenAI2Cohere(textRequest dto.GeneralOpenAIRequest) *CohereRequest {
|
|
cohereReq := CohereRequest{
|
|
Model: textRequest.Model,
|
|
ChatHistory: []ChatHistory{},
|
|
Message: "",
|
|
Stream: lo.FromPtrOr(textRequest.Stream, false),
|
|
MaxTokens: textRequest.GetMaxTokens(),
|
|
}
|
|
if common.CohereSafetySetting != "NONE" {
|
|
cohereReq.SafetyMode = common.CohereSafetySetting
|
|
}
|
|
if cohereReq.MaxTokens == 0 {
|
|
cohereReq.MaxTokens = 4000
|
|
}
|
|
for _, msg := range textRequest.Messages {
|
|
if msg.Role == "user" {
|
|
cohereReq.Message = msg.StringContent()
|
|
} else {
|
|
var role string
|
|
if msg.Role == "assistant" {
|
|
role = "CHATBOT"
|
|
} else if msg.Role == "system" {
|
|
role = "SYSTEM"
|
|
} else {
|
|
role = "USER"
|
|
}
|
|
cohereReq.ChatHistory = append(cohereReq.ChatHistory, ChatHistory{
|
|
Role: role,
|
|
Message: msg.StringContent(),
|
|
})
|
|
}
|
|
}
|
|
|
|
return &cohereReq
|
|
}
|
|
|
|
func requestConvertRerank2Cohere(rerankRequest dto.RerankRequest) *CohereRerankRequest {
|
|
topN := lo.FromPtrOr(rerankRequest.TopN, 1)
|
|
if topN <= 0 {
|
|
topN = 1
|
|
}
|
|
cohereReq := CohereRerankRequest{
|
|
Query: rerankRequest.Query,
|
|
Documents: rerankRequest.Documents,
|
|
Model: rerankRequest.Model,
|
|
TopN: topN,
|
|
ReturnDocuments: true,
|
|
}
|
|
return &cohereReq
|
|
}
|
|
|
|
func stopReasonCohere2OpenAI(reason string) string {
|
|
switch reason {
|
|
case "COMPLETE":
|
|
return "stop"
|
|
case "MAX_TOKENS":
|
|
return "max_tokens"
|
|
default:
|
|
return reason
|
|
}
|
|
}
|
|
|
|
func cohereStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
responseId := helper.GetResponseID(c)
|
|
createdTime := common.GetTimestamp()
|
|
usage := &dto.Usage{}
|
|
responseText := ""
|
|
scanner := helper.NewStreamScanner(resp.Body)
|
|
scanner.Split(func(data []byte, atEOF bool) (advance int, token []byte, err error) {
|
|
if atEOF && len(data) == 0 {
|
|
return 0, nil, nil
|
|
}
|
|
if i := strings.Index(string(data), "\n"); i >= 0 {
|
|
return i + 1, data[0:i], nil
|
|
}
|
|
if atEOF {
|
|
return len(data), data, nil
|
|
}
|
|
return 0, nil, nil
|
|
})
|
|
dataChan := make(chan string)
|
|
stopChan := make(chan bool)
|
|
go func() {
|
|
for scanner.Scan() {
|
|
data := scanner.Text()
|
|
dataChan <- data
|
|
}
|
|
if err := scanner.Err(); err != nil {
|
|
common.SysLog("error reading stream: " + err.Error())
|
|
}
|
|
stopChan <- true
|
|
}()
|
|
helper.SetEventStreamHeaders(c)
|
|
isFirst := true
|
|
c.Stream(func(w io.Writer) bool {
|
|
select {
|
|
case data := <-dataChan:
|
|
if isFirst {
|
|
isFirst = false
|
|
info.FirstResponseTime = time.Now()
|
|
}
|
|
data = strings.TrimSuffix(data, "\r")
|
|
var cohereResp CohereResponse
|
|
err := json.Unmarshal([]byte(data), &cohereResp)
|
|
if err != nil {
|
|
common.SysLog("error unmarshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
var openaiResp dto.ChatCompletionsStreamResponse
|
|
openaiResp.Id = responseId
|
|
openaiResp.Created = createdTime
|
|
openaiResp.Object = "chat.completion.chunk"
|
|
openaiResp.Model = info.UpstreamModelName
|
|
if cohereResp.IsFinished {
|
|
finishReason := stopReasonCohere2OpenAI(cohereResp.FinishReason)
|
|
openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
|
|
{
|
|
Delta: dto.ChatCompletionsStreamResponseChoiceDelta{},
|
|
Index: 0,
|
|
FinishReason: &finishReason,
|
|
},
|
|
}
|
|
if cohereResp.Response != nil {
|
|
usage.PromptTokens = cohereResp.Response.Meta.BilledUnits.InputTokens
|
|
usage.CompletionTokens = cohereResp.Response.Meta.BilledUnits.OutputTokens
|
|
}
|
|
} else {
|
|
openaiResp.Choices = []dto.ChatCompletionsStreamResponseChoice{
|
|
{
|
|
Delta: dto.ChatCompletionsStreamResponseChoiceDelta{
|
|
Role: "assistant",
|
|
Content: &cohereResp.Text,
|
|
},
|
|
Index: 0,
|
|
},
|
|
}
|
|
responseText += cohereResp.Text
|
|
}
|
|
jsonStr, err := json.Marshal(openaiResp)
|
|
if err != nil {
|
|
common.SysLog("error marshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonStr)})
|
|
return true
|
|
case <-stopChan:
|
|
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
|
return false
|
|
}
|
|
})
|
|
if usage.PromptTokens == 0 {
|
|
usage = service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens())
|
|
}
|
|
return usage, nil
|
|
}
|
|
|
|
func cohereHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
createdTime := common.GetTimestamp()
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
service.CloseResponseBodyGracefully(resp)
|
|
var cohereResp CohereResponseResult
|
|
err = json.Unmarshal(responseBody, &cohereResp)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
usage := dto.Usage{}
|
|
usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
|
|
usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
|
|
usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
|
|
|
|
var openaiResp dto.TextResponse
|
|
openaiResp.Id = cohereResp.ResponseId
|
|
openaiResp.Created = createdTime
|
|
openaiResp.Object = "chat.completion"
|
|
openaiResp.Model = info.UpstreamModelName
|
|
openaiResp.Usage = usage
|
|
|
|
openaiResp.Choices = []dto.OpenAITextResponseChoice{
|
|
{
|
|
Index: 0,
|
|
Message: dto.Message{Content: cohereResp.Text, Role: "assistant"},
|
|
FinishReason: stopReasonCohere2OpenAI(cohereResp.FinishReason),
|
|
},
|
|
}
|
|
|
|
jsonResponse, err := json.Marshal(openaiResp)
|
|
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 &usage, nil
|
|
}
|
|
|
|
func cohereRerankHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.Usage, *types.NewAPIError) {
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
service.CloseResponseBodyGracefully(resp)
|
|
var cohereResp CohereRerankResponseResult
|
|
err = json.Unmarshal(responseBody, &cohereResp)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
usage := dto.Usage{}
|
|
if cohereResp.Meta.BilledUnits.InputTokens == 0 {
|
|
usage.PromptTokens = info.GetEstimatePromptTokens()
|
|
usage.CompletionTokens = 0
|
|
usage.TotalTokens = info.GetEstimatePromptTokens()
|
|
} else {
|
|
usage.PromptTokens = cohereResp.Meta.BilledUnits.InputTokens
|
|
usage.CompletionTokens = cohereResp.Meta.BilledUnits.OutputTokens
|
|
usage.TotalTokens = cohereResp.Meta.BilledUnits.InputTokens + cohereResp.Meta.BilledUnits.OutputTokens
|
|
}
|
|
|
|
var rerankResp dto.RerankResponse
|
|
rerankResp.Results = cohereResp.Results
|
|
rerankResp.Usage = usage
|
|
|
|
jsonResponse, err := json.Marshal(rerankResp)
|
|
if err != nil {
|
|
return nil, types.NewError(err, types.ErrorCodeBadResponseBody)
|
|
}
|
|
c.Writer.Header().Set("Content-Type", "application/json")
|
|
c.Writer.WriteHeader(resp.StatusCode)
|
|
_, err = c.Writer.Write(jsonResponse)
|
|
return &usage, nil
|
|
}
|