feat: support /v1/responses API
This commit is contained in:
@@ -25,8 +25,9 @@ import (
|
||||
"path/filepath"
|
||||
"strings"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
"net/textproto"
|
||||
|
||||
"github.com/gin-gonic/gin"
|
||||
)
|
||||
|
||||
type Adaptor struct {
|
||||
@@ -67,6 +68,9 @@ func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
|
||||
if info.RelayFormat == relaycommon.RelayFormatClaude {
|
||||
return fmt.Sprintf("%s/v1/chat/completions", info.BaseUrl), nil
|
||||
}
|
||||
if info.RelayMode == constant.RelayModeResponses {
|
||||
return fmt.Sprintf("%s/v1/responses", info.BaseUrl), nil
|
||||
}
|
||||
if info.RelayMode == constant.RelayModeRealtime {
|
||||
if strings.HasPrefix(info.BaseUrl, "https://") {
|
||||
baseUrl := strings.TrimPrefix(info.BaseUrl, "https://")
|
||||
@@ -380,6 +384,21 @@ func detectImageMimeType(filename string) string {
|
||||
}
|
||||
}
|
||||
|
||||
func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
|
||||
// 模型后缀转换 reasoning effort
|
||||
if strings.HasSuffix(request.Model, "-high") {
|
||||
request.Reasoning.Effort = "high"
|
||||
request.Model = strings.TrimSuffix(request.Model, "-high")
|
||||
} else if strings.HasSuffix(request.Model, "-low") {
|
||||
request.Reasoning.Effort = "low"
|
||||
request.Model = strings.TrimSuffix(request.Model, "-low")
|
||||
} else if strings.HasSuffix(request.Model, "-medium") {
|
||||
request.Reasoning.Effort = "medium"
|
||||
request.Model = strings.TrimSuffix(request.Model, "-medium")
|
||||
}
|
||||
return request, nil
|
||||
}
|
||||
|
||||
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
|
||||
if info.RelayMode == constant.RelayModeAudioTranscription ||
|
||||
info.RelayMode == constant.RelayModeAudioTranslation ||
|
||||
@@ -406,6 +425,12 @@ func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycom
|
||||
err, usage = OpenaiHandlerWithUsage(c, resp, info)
|
||||
case constant.RelayModeRerank:
|
||||
err, usage = common_handler.RerankHandler(c, info, resp)
|
||||
case constant.RelayModeResponses:
|
||||
if info.IsStream {
|
||||
err, usage = OaiStreamHandler(c, resp, info)
|
||||
} else {
|
||||
err, usage = OpenaiResponsesHandler(c, resp, info)
|
||||
}
|
||||
default:
|
||||
if info.IsStream {
|
||||
err, usage = OaiStreamHandler(c, resp, info)
|
||||
|
||||
@@ -644,3 +644,53 @@ func OpenaiHandlerWithUsage(c *gin.Context, resp *http.Response, info *relaycomm
|
||||
}
|
||||
return nil, &usageResp.Usage
|
||||
}
|
||||
|
||||
func OpenaiResponsesHandler(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (*dto.OpenAIErrorWithStatusCode, *dto.Usage) {
|
||||
// read response body
|
||||
var responsesResponse dto.OpenAIResponsesResponse
|
||||
responseBody, err := io.ReadAll(resp.Body)
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapper(err, "read_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
err = resp.Body.Close()
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapper(err, "close_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
err = common.DecodeJson(responseBody, &responsesResponse)
|
||||
if err != nil {
|
||||
return service.OpenAIErrorWrapper(err, "unmarshal_response_body_failed", http.StatusInternalServerError), nil
|
||||
}
|
||||
if responsesResponse.Error != nil {
|
||||
return &dto.OpenAIErrorWithStatusCode{
|
||||
Error: dto.OpenAIError{
|
||||
Message: responsesResponse.Error.Message,
|
||||
Type: "openai_error",
|
||||
Code: responsesResponse.Error.Code,
|
||||
},
|
||||
StatusCode: resp.StatusCode,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// reset response body
|
||||
resp.Body = io.NopCloser(bytes.NewBuffer(responseBody))
|
||||
// We shouldn't set the header before we parse the response body, because the parse part may fail.
|
||||
// And then we will have to send an error response, but in this case, the header has already been set.
|
||||
// So the httpClient will be confused by the response.
|
||||
// For example, Postman will report error, and we cannot check the response at all.
|
||||
for k, v := range resp.Header {
|
||||
c.Writer.Header().Set(k, v[0])
|
||||
}
|
||||
c.Writer.WriteHeader(resp.StatusCode)
|
||||
// copy response body
|
||||
_, err = io.Copy(c.Writer, resp.Body)
|
||||
if err != nil {
|
||||
common.SysError("error copying response body: " + err.Error())
|
||||
}
|
||||
resp.Body.Close()
|
||||
// compute usage
|
||||
usage := dto.Usage{}
|
||||
usage.PromptTokens = responsesResponse.Usage.InputTokens
|
||||
usage.CompletionTokens = responsesResponse.Usage.OutputTokens
|
||||
usage.TotalTokens = responsesResponse.Usage.TotalTokens
|
||||
return nil, &usage
|
||||
}
|
||||
|
||||
Reference in New Issue
Block a user