Files
new-api/relay/channel/tencent/relay-tencent.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

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
}