* 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
235 lines
7.0 KiB
Go
235 lines
7.0 KiB
Go
package tencent
|
|
|
|
import (
|
|
"bufio"
|
|
"crypto/hmac"
|
|
"crypto/sha256"
|
|
"encoding/hex"
|
|
"encoding/json"
|
|
"errors"
|
|
"fmt"
|
|
"io"
|
|
"net/http"
|
|
"strconv"
|
|
"strings"
|
|
"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/gin-gonic/gin"
|
|
)
|
|
|
|
// https://cloud.tencent.com/document/product/1729/97732
|
|
|
|
func requestOpenAI2Tencent(a *Adaptor, request dto.GeneralOpenAIRequest) *TencentChatRequest {
|
|
messages := make([]*TencentMessage, 0, len(request.Messages))
|
|
for i := 0; i < len(request.Messages); i++ {
|
|
message := request.Messages[i]
|
|
messages = append(messages, &TencentMessage{
|
|
Content: message.StringContent(),
|
|
Role: message.Role,
|
|
})
|
|
}
|
|
var req = TencentChatRequest{
|
|
Stream: request.Stream,
|
|
Messages: messages,
|
|
Model: &request.Model,
|
|
}
|
|
if request.TopP != nil {
|
|
req.TopP = request.TopP
|
|
}
|
|
req.Temperature = request.Temperature
|
|
return &req
|
|
}
|
|
|
|
func responseTencent2OpenAI(response *TencentChatResponse) *dto.OpenAITextResponse {
|
|
fullTextResponse := dto.OpenAITextResponse{
|
|
Id: response.Id,
|
|
Object: "chat.completion",
|
|
Created: common.GetTimestamp(),
|
|
Usage: dto.Usage{
|
|
PromptTokens: response.Usage.PromptTokens,
|
|
CompletionTokens: response.Usage.CompletionTokens,
|
|
TotalTokens: response.Usage.TotalTokens,
|
|
},
|
|
}
|
|
if len(response.Choices) > 0 {
|
|
choice := dto.OpenAITextResponseChoice{
|
|
Index: 0,
|
|
Message: dto.Message{
|
|
Role: "assistant",
|
|
Content: response.Choices[0].Messages.Content,
|
|
},
|
|
FinishReason: response.Choices[0].FinishReason,
|
|
}
|
|
fullTextResponse.Choices = append(fullTextResponse.Choices, choice)
|
|
}
|
|
return &fullTextResponse
|
|
}
|
|
|
|
func streamResponseTencent2OpenAI(TencentResponse *TencentChatResponse) *dto.ChatCompletionsStreamResponse {
|
|
response := dto.ChatCompletionsStreamResponse{
|
|
Object: "chat.completion.chunk",
|
|
Created: common.GetTimestamp(),
|
|
Model: "tencent-hunyuan",
|
|
}
|
|
if len(TencentResponse.Choices) > 0 {
|
|
var choice dto.ChatCompletionsStreamResponseChoice
|
|
choice.Delta.SetContentString(TencentResponse.Choices[0].Delta.Content)
|
|
if TencentResponse.Choices[0].FinishReason == "stop" {
|
|
choice.FinishReason = &constant.FinishReasonStop
|
|
}
|
|
response.Choices = append(response.Choices, choice)
|
|
}
|
|
return &response
|
|
}
|
|
|
|
func tencentStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
var responseText string
|
|
scanner := helper.NewStreamScanner(resp.Body)
|
|
scanner.Split(bufio.ScanLines)
|
|
|
|
helper.SetEventStreamHeaders(c)
|
|
|
|
for scanner.Scan() {
|
|
data := scanner.Text()
|
|
if len(data) < 5 || !strings.HasPrefix(data, "data:") {
|
|
continue
|
|
}
|
|
data = strings.TrimPrefix(data, "data:")
|
|
|
|
var tencentResponse TencentChatResponse
|
|
err := common.Unmarshal([]byte(data), &tencentResponse)
|
|
if err != nil {
|
|
common.SysLog("error unmarshalling stream response: " + err.Error())
|
|
continue
|
|
}
|
|
|
|
response := streamResponseTencent2OpenAI(&tencentResponse)
|
|
if len(response.Choices) != 0 {
|
|
responseText += response.Choices[0].Delta.GetContentString()
|
|
}
|
|
|
|
err = helper.ObjectData(c, response)
|
|
if err != nil {
|
|
common.SysLog(err.Error())
|
|
}
|
|
}
|
|
|
|
if err := scanner.Err(); err != nil {
|
|
common.SysLog("error reading stream: " + err.Error())
|
|
}
|
|
|
|
helper.Done(c)
|
|
|
|
service.CloseResponseBodyGracefully(resp)
|
|
|
|
return service.ResponseText2Usage(c, responseText, info.UpstreamModelName, info.GetEstimatePromptTokens()), nil
|
|
}
|
|
|
|
func tencentHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
var tencentSb TencentChatResponseSB
|
|
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, &tencentSb)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
if tencentSb.Response.Error.Code != 0 {
|
|
return nil, types.WithOpenAIError(types.OpenAIError{
|
|
Message: tencentSb.Response.Error.Message,
|
|
Code: tencentSb.Response.Error.Code,
|
|
}, resp.StatusCode)
|
|
}
|
|
fullTextResponse := responseTencent2OpenAI(&tencentSb.Response)
|
|
jsonResponse, err := common.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)
|
|
service.IOCopyBytesGracefully(c, resp, jsonResponse)
|
|
return &fullTextResponse.Usage, nil
|
|
}
|
|
|
|
func parseTencentConfig(config string) (appId int64, secretId string, secretKey string, err error) {
|
|
parts := strings.Split(config, "|")
|
|
if len(parts) != 3 {
|
|
err = errors.New("invalid tencent config")
|
|
return
|
|
}
|
|
appId, err = strconv.ParseInt(parts[0], 10, 64)
|
|
secretId = parts[1]
|
|
secretKey = parts[2]
|
|
return
|
|
}
|
|
|
|
func sha256hex(s string) string {
|
|
b := sha256.Sum256([]byte(s))
|
|
return hex.EncodeToString(b[:])
|
|
}
|
|
|
|
func hmacSha256(s, key string) string {
|
|
hashed := hmac.New(sha256.New, []byte(key))
|
|
hashed.Write([]byte(s))
|
|
return string(hashed.Sum(nil))
|
|
}
|
|
|
|
func getTencentSign(req TencentChatRequest, adaptor *Adaptor, secId, secKey string) string {
|
|
// build canonical request string
|
|
host := "hunyuan.tencentcloudapi.com"
|
|
httpRequestMethod := "POST"
|
|
canonicalURI := "/"
|
|
canonicalQueryString := ""
|
|
canonicalHeaders := fmt.Sprintf("content-type:%s\nhost:%s\nx-tc-action:%s\n",
|
|
"application/json", host, strings.ToLower(adaptor.Action))
|
|
signedHeaders := "content-type;host;x-tc-action"
|
|
payload, _ := json.Marshal(req)
|
|
hashedRequestPayload := sha256hex(string(payload))
|
|
canonicalRequest := fmt.Sprintf("%s\n%s\n%s\n%s\n%s\n%s",
|
|
httpRequestMethod,
|
|
canonicalURI,
|
|
canonicalQueryString,
|
|
canonicalHeaders,
|
|
signedHeaders,
|
|
hashedRequestPayload)
|
|
// build string to sign
|
|
algorithm := "TC3-HMAC-SHA256"
|
|
requestTimestamp := strconv.FormatInt(adaptor.Timestamp, 10)
|
|
timestamp, _ := strconv.ParseInt(requestTimestamp, 10, 64)
|
|
t := time.Unix(timestamp, 0).UTC()
|
|
// must be the format 2006-01-02, ref to package time for more info
|
|
date := t.Format("2006-01-02")
|
|
credentialScope := fmt.Sprintf("%s/%s/tc3_request", date, "hunyuan")
|
|
hashedCanonicalRequest := sha256hex(canonicalRequest)
|
|
string2sign := fmt.Sprintf("%s\n%s\n%s\n%s",
|
|
algorithm,
|
|
requestTimestamp,
|
|
credentialScope,
|
|
hashedCanonicalRequest)
|
|
|
|
// sign string
|
|
secretDate := hmacSha256(date, "TC3"+secKey)
|
|
secretService := hmacSha256("hunyuan", secretDate)
|
|
secretKey := hmacSha256("tc3_request", secretService)
|
|
signature := hex.EncodeToString([]byte(hmacSha256(string2sign, secretKey)))
|
|
|
|
// build authorization
|
|
authorization := fmt.Sprintf("%s Credential=%s/%s, SignedHeaders=%s, Signature=%s",
|
|
algorithm,
|
|
secId,
|
|
credentialScope,
|
|
signedHeaders,
|
|
signature)
|
|
return authorization
|
|
}
|