chaos/chaos-api
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

feat: openai response /v1/response/compact (#2644)

Browse Source 
* feat: openai response /v1/response/compact

* feat: /v1/response/compact bill

* feat: /v1/response/compact

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: /v1/responses/compact -> codex channel

* feat: codex channel default models

* feat: compact model price

* feat: /v1/responses/comapct test
This commit is contained in:
Seefs
2026-01-26 20:20:16 +08:00
committed by GitHub
parent d9321b7da3
commit cf114ca7d6
25 changed files with 483 additions and 42 deletions
Download Patch File Download Diff File Expand all files Collapse all files
relay/responses_handler.go
+52 -5
View File
@@ -8,8 +8,10 @@ import (
"strings"
"github.com/QuantumNous/new-api/common"
appconstant "github.com/QuantumNous/new-api/constant"
"github.com/QuantumNous/new-api/dto"
relaycommon "github.com/QuantumNous/new-api/relay/common"
relayconstant "github.com/QuantumNous/new-api/relay/constant"
"github.com/QuantumNous/new-api/relay/helper"
"github.com/QuantumNous/new-api/service"
"github.com/QuantumNous/new-api/setting/model_setting"
@@ -20,10 +22,37 @@ import (
func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *types.NewAPIError) {
info.InitChannelMeta(c)
if info.RelayMode == relayconstant.RelayModeResponsesCompact {
switch info.ApiType {
case appconstant.APITypeOpenAI, appconstant.APITypeCodex:
default:
return types.NewErrorWithStatusCode(
fmt.Errorf("unsupported endpoint %q for api type %d", "/v1/responses/compact", info.ApiType),
types.ErrorCodeInvalidRequest,
http.StatusBadRequest,
types.ErrOptionWithSkipRetry(),
)
}
}
responsesReq, ok := info.Request.(*dto.OpenAIResponsesRequest)
if !ok {
return types.NewErrorWithStatusCode(fmt.Errorf("invalid request type, expected dto.OpenAIResponsesRequest, got %T", info.Request), types.ErrorCodeInvalidRequest, http.StatusBadRequest, types.ErrOptionWithSkipRetry())
var responsesReq *dto.OpenAIResponsesRequest
switch req := info.Request.(type) {
case *dto.OpenAIResponsesRequest:
responsesReq = req
case *dto.OpenAIResponsesCompactionRequest:
responsesReq = &dto.OpenAIResponsesRequest{
Model: req.Model,
Input: req.Input,
Instructions: req.Instructions,
PreviousResponseID: req.PreviousResponseID,
}
default:
return types.NewErrorWithStatusCode(
fmt.Errorf("invalid request type, expected dto.OpenAIResponsesRequest or dto.OpenAIResponsesCompactionRequest, got %T", info.Request),
types.ErrorCodeInvalidRequest,
http.StatusBadRequest,
types.ErrOptionWithSkipRetry(),
)
}
request, err := common.DeepCopy(responsesReq)
@@ -105,10 +134,28 @@ func ResponsesHelper(c *gin.Context, info *relaycommon.RelayInfo) (newAPIError *
return newAPIError
}
usageDto := usage.(*dto.Usage)
if info.RelayMode == relayconstant.RelayModeResponsesCompact {
originModelName := info.OriginModelName
originPriceData := info.PriceData
_, err := helper.ModelPriceHelper(c, info, info.GetEstimatePromptTokens(), &types.TokenCountMeta{})
if err != nil {
info.OriginModelName = originModelName
info.PriceData = originPriceData
return types.NewError(err, types.ErrorCodeModelPriceError, types.ErrOptionWithSkipRetry())
}
postConsumeQuota(c, info, usageDto)
info.OriginModelName = originModelName
info.PriceData = originPriceData
return nil
}
if strings.HasPrefix(info.OriginModelName, "gpt-4o-audio") {
service.PostAudioConsumeQuota(c, info, usage.(*dto.Usage), "")
service.PostAudioConsumeQuota(c, info, usageDto, "")
} else {
postConsumeQuota(c, info, usage.(*dto.Usage))
postConsumeQuota(c, info, usageDto)
}
return nil
}