CaIon
48068ce923
Parse OpenAI's native cache_write_tokens (chat prompt_tokens_details / responses input_tokens_details), bill it at the cache-creation ratio, and clamp the uncached prompt remainder at zero since cached + cache-write can exceed prompt_tokens. Propagate the field through chat/responses/claude format conversions and tiered expression billing (cc variable).
46 lines
1.5 KiB
Go
46 lines
1.5 KiB
Go
package openai
|
|
|
|
import (
|
|
"io"
|
|
"net/http"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/dto"
|
|
"github.com/QuantumNous/new-api/service"
|
|
"github.com/QuantumNous/new-api/types"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
func OaiResponsesCompactionHandler(c *gin.Context, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
|
|
defer service.CloseResponseBodyGracefully(resp)
|
|
|
|
responseBody, err := io.ReadAll(resp.Body)
|
|
if err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
|
|
}
|
|
|
|
var compactResp dto.OpenAIResponsesCompactionResponse
|
|
if err := common.Unmarshal(responseBody, &compactResp); err != nil {
|
|
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
|
|
}
|
|
if oaiError := compactResp.GetOpenAIError(); oaiError != nil && oaiError.Type != "" {
|
|
return nil, types.WithOpenAIError(*oaiError, resp.StatusCode)
|
|
}
|
|
|
|
service.IOCopyBytesGracefully(c, resp, responseBody)
|
|
|
|
usage := dto.Usage{}
|
|
if compactResp.Usage != nil {
|
|
usage.PromptTokens = compactResp.Usage.InputTokens
|
|
usage.CompletionTokens = compactResp.Usage.OutputTokens
|
|
usage.TotalTokens = compactResp.Usage.TotalTokens
|
|
if compactResp.Usage.InputTokensDetails != nil {
|
|
usage.PromptTokensDetails.CachedTokens = compactResp.Usage.InputTokensDetails.CachedTokens
|
|
usage.PromptTokensDetails.CacheWriteTokens = compactResp.Usage.InputTokensDetails.CacheWriteTokens
|
|
}
|
|
}
|
|
|
|
return &usage, nil
|
|
}
|