mirror of
https://github.com/QuantumNous/new-api.git
synced 2026-09-13 15:54:34 +00:00
* 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
252 lines
7.1 KiB
Go
252 lines
7.1 KiB
Go
package zhipu
|
|
|
|
import (
|
|
"bufio"
|
|
"encoding/json"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
"sync"
|
|
"time"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/constant"
|
|
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"
|
|
"github.com/golang-jwt/jwt/v5"
|
|
)
|
|
|
|
// https://open.bigmodel.cn/doc/api#chatglm_std
|
|
// chatglm_std, chatglm_lite
|
|
// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/invoke
|
|
// https://open.bigmodel.cn/api/paas/v3/model-api/chatglm_std/sse-invoke
|
|
|
|
var zhipuTokens sync.Map
|
|
var expSeconds int64 = 24 * 3600
|
|
|
|
func getZhipuToken(apikey string) string {
|
|
data, ok := zhipuTokens.Load(apikey)
|
|
if ok {
|
|
tokenData := data.(zhipuTokenData)
|
|
if time.Now().Before(tokenData.ExpiryTime) {
|
|
return tokenData.Token
|
|
}
|
|
}
|
|
|
|
split := strings.Split(apikey, ".")
|
|
if len(split) != 2 {
|
|
common.SysLog("invalid zhipu key: " + apikey)
|
|
return ""
|
|
}
|
|
|
|
id := split[0]
|
|
secret := split[1]
|
|
|
|
expMillis := time.Now().Add(time.Duration(expSeconds)*time.Second).UnixNano() / 1e6
|
|
expiryTime := time.Now().Add(time.Duration(expSeconds) * time.Second)
|
|
|
|
timestamp := time.Now().UnixNano() / 1e6
|
|
|
|
payload := jwt.MapClaims{
|
|
"api_key": id,
|
|
"exp": expMillis,
|
|
"timestamp": timestamp,
|
|
}
|
|
|
|
token := jwt.NewWithClaims(jwt.SigningMethodHS256, payload)
|
|
|
|
token.Header["alg"] = "HS256"
|
|
token.Header["sign_type"] = "SIGN"
|
|
|
|
tokenString, err := token.SignedString([]byte(secret))
|
|
if err != nil {
|
|
return ""
|
|
}
|
|
|
|
zhipuTokens.Store(apikey, zhipuTokenData{
|
|
Token: tokenString,
|
|
ExpiryTime: expiryTime,
|
|
})
|
|
|
|
return tokenString
|
|
}
|
|
|
|
func requestOpenAI2Zhipu(request dto.GeneralOpenAIRequest) *ZhipuRequest {
|
|
messages := make([]ZhipuMessage, 0, len(request.Messages))
|
|
for _, message := range request.Messages {
|
|
if message.Role == "system" {
|
|
messages = append(messages, ZhipuMessage{
|
|
Role: "system",
|
|
Content: message.StringContent(),
|
|
})
|
|
messages = append(messages, ZhipuMessage{
|
|
Role: "user",
|
|
Content: "Okay",
|
|
})
|
|
} else {
|
|
messages = append(messages, ZhipuMessage{
|
|
Role: message.Role,
|
|
Content: message.StringContent(),
|
|
})
|
|
}
|
|
}
|
|
return &ZhipuRequest{
|
|
Prompt: messages,
|
|
Temperature: request.Temperature,
|
|
TopP: lo.FromPtrOr(request.TopP, 0),
|
|
Incremental: false,
|
|
}
|
|
}
|
|
|
|
func responseZhipu2OpenAI(response *ZhipuResponse) *dto.OpenAITextResponse {
|
|
fullTextResponse := dto.OpenAITextResponse{
|
|
Id: response.Data.TaskId,
|
|
Object: "chat.completion",
|
|
Created: common.GetTimestamp(),
|
|
Choices: make([]dto.OpenAITextResponseChoice, 0, len(response.Data.Choices)),
|
|
Usage: response.Data.Usage,
|
|
}
|
|
for i, choice := range response.Data.Choices {
|
|
openaiChoice := dto.OpenAITextResponseChoice{
|
|
Index: i,
|
|
Message: dto.Message{
|
|
Role: choice.Role,
|
|
Content: strings.Trim(choice.Content, "\""),
|
|
},
|
|
FinishReason: "",
|
|
}
|
|
if i == len(response.Data.Choices)-1 {
|
|
openaiChoice.FinishReason = "stop"
|
|
}
|
|
fullTextResponse.Choices = append(fullTextResponse.Choices, openaiChoice)
|
|
}
|
|
return &fullTextResponse
|
|
}
|
|
|
|
func streamResponseZhipu2OpenAI(zhipuResponse string) *dto.ChatCompletionsStreamResponse {
|
|
var choice dto.ChatCompletionsStreamResponseChoice
|
|
choice.Delta.SetContentString(zhipuResponse)
|
|
response := dto.ChatCompletionsStreamResponse{
|
|
Object: "chat.completion.chunk",
|
|
Created: common.GetTimestamp(),
|
|
Model: "chatglm",
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
|
|
}
|
|
return &response
|
|
}
|
|
|
|
func streamMetaResponseZhipu2OpenAI(zhipuResponse *ZhipuStreamMetaResponse) (*dto.ChatCompletionsStreamResponse, *dto.Usage) {
|
|
var choice dto.ChatCompletionsStreamResponseChoice
|
|
choice.Delta.SetContentString("")
|
|
choice.FinishReason = &constant.FinishReasonStop
|
|
response := dto.ChatCompletionsStreamResponse{
|
|
Id: zhipuResponse.RequestId,
|
|
Object: "chat.completion.chunk",
|
|
Created: common.GetTimestamp(),
|
|
Model: "chatglm",
|
|
Choices: []dto.ChatCompletionsStreamResponseChoice{choice},
|
|
}
|
|
return &response, &zhipuResponse.Usage
|
|
}
|
|
|
|
func zhipuStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
var usage *dto.Usage
|
|
scanner := helper.NewStreamScanner(resp.Body)
|
|
scanner.Split(bufio.ScanLines)
|
|
dataChan := make(chan string)
|
|
metaChan := make(chan string)
|
|
stopChan := make(chan bool)
|
|
go func() {
|
|
for scanner.Scan() {
|
|
data := scanner.Text()
|
|
lines := strings.Split(data, "\n")
|
|
for i, line := range lines {
|
|
if len(line) < 5 {
|
|
continue
|
|
}
|
|
if line[:5] == "data:" {
|
|
dataChan <- line[5:]
|
|
if i != len(lines)-1 {
|
|
dataChan <- "\n"
|
|
}
|
|
} else if line[:5] == "meta:" {
|
|
metaChan <- line[5:]
|
|
}
|
|
}
|
|
}
|
|
if err := scanner.Err(); err != nil {
|
|
common.SysLog("error reading stream: " + err.Error())
|
|
}
|
|
stopChan <- true
|
|
}()
|
|
helper.SetEventStreamHeaders(c)
|
|
c.Stream(func(w io.Writer) bool {
|
|
select {
|
|
case data := <-dataChan:
|
|
response := streamResponseZhipu2OpenAI(data)
|
|
jsonResponse, err := json.Marshal(response)
|
|
if err != nil {
|
|
common.SysLog("error marshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
|
|
return true
|
|
case data := <-metaChan:
|
|
var zhipuResponse ZhipuStreamMetaResponse
|
|
err := json.Unmarshal([]byte(data), &zhipuResponse)
|
|
if err != nil {
|
|
common.SysLog("error unmarshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
response, zhipuUsage := streamMetaResponseZhipu2OpenAI(&zhipuResponse)
|
|
jsonResponse, err := json.Marshal(response)
|
|
if err != nil {
|
|
common.SysLog("error marshalling stream response: " + err.Error())
|
|
return true
|
|
}
|
|
usage = zhipuUsage
|
|
c.Render(-1, common.CustomEvent{Data: "data: " + string(jsonResponse)})
|
|
return true
|
|
case <-stopChan:
|
|
c.Render(-1, common.CustomEvent{Data: "data: [DONE]"})
|
|
return false
|
|
}
|
|
})
|
|
service.CloseResponseBodyGracefully(resp)
|
|
return usage, nil
|
|
}
|
|
|
|
func zhipuHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
var zhipuResponse ZhipuResponse
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
|
|
}
|
|
service.CloseResponseBodyGracefully(resp)
|
|
err = json.Unmarshal(responseBody, &zhipuResponse)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
if !zhipuResponse.Success {
|
|
return nil, types.WithOpenAIError(types.OpenAIError{
|
|
Message: zhipuResponse.Msg,
|
|
Code: zhipuResponse.Code,
|
|
}, resp.StatusCode)
|
|
}
|
|
fullTextResponse := responseZhipu2OpenAI(&zhipuResponse)
|
|
jsonResponse, err := json.Marshal(fullTextResponse)
|
|
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 &fullTextResponse.Usage, nil
|
|
}
|