Files
new-api/relay/channel/openai/relay_responses.go
T
Calcium-Ion 0ed497f066 feat(relay): hosted-tool conversion fidelity, reasoning normalization, and billing usage integrity (#7137)
* feat(relaykit): preserve hosted tools across conversions

- add protocol-neutral hosted-tool DTOs, conversion metadata, and loss policies
- bridge citations, grounding metadata, and hosted-tool stream lifecycles
- document the public conversion behavior and channel policy controls

* refactor(relaykit): normalize reasoning and thinking intent

- centralize provider-neutral reasoning intent, effort, and budget mappings
- parse model suffixes at the host entry boundary while preserving provider-owned tails
- keep adaptive Claude thinking and explicit zero-token compatibility consistent

* fix(billing): preserve authoritative usage across relay hops

- carry native BillingUsage sidecars through direct and streamed protocol bridges
- merge partial and terminal usage monotonically with safe fallback settlement
- retain cache metadata, penultimate usage, and per-call Gemini tool surcharges

* feat(relay): bridge Responses with Claude and Gemini protocols

- add direct request, response, and stream converters across supported relay formats
- expose Claude count_tokens and Chat-to-Responses compatibility endpoints
- carry conversion diagnostics through the host while retaining the curated public goldens

* fix(relay): wire relaykit conversions into host channels

- connect handlers, adaptors, and channel settings to the standalone conversion layer
- keep model mapping, pricing identity, retries, and provider-specific suffix behavior aligned
- ignore local audit artifacts and retain focused public regression coverage
2026-09-01 21:53:35 +08:00

163 lines
5.5 KiB
Go

package openai
import (
"fmt"
"io"
"net/http"
"strings"
"github.com/QuantumNous/new-api/common"
"github.com/QuantumNous/new-api/logger"
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/relayconvert"
"github.com/QuantumNous/new-api/relaykit/types"
"github.com/QuantumNous/new-api/service"
"github.com/gin-gonic/gin"
)
func OaiResponsesHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
defer service.CloseResponseBodyGracefully(resp)
// read response body
var responsesResponse dto.OpenAIResponsesResponse
responseBody, err := io.ReadAll(resp.Body)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeReadResponseBodyFailed, http.StatusInternalServerError)
}
err = common.Unmarshal(responseBody, &responsesResponse)
if err != nil {
return nil, types.NewOpenAIError(err, types.ErrorCodeBadResponseBody, http.StatusInternalServerError)
}
if oaiError := responsesResponse.GetOpenAIError(); oaiError != nil && oaiError.Type != "" {
return nil, types.WithOpenAIError(*oaiError, resp.StatusCode)
}
// 写入新的 response body
service.IOCopyBytesGracefully(c, resp, responseBody)
// compute usage
usage := relayconvert.NormalizeResponsesUsage(responsesResponse.Usage)
// Count actual tool invocations from Output (not tool declarations).
for _, output := range responsesResponse.Output {
switch output.Type {
case dto.BuildInCallWebSearchCall:
info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
case dto.BuildInCallFileSearchCall:
info.CountBillableToolCall(dto.BuildInCallFileSearchCall, "")
case dto.BuildInCallFunctionCall:
info.CountBillableToolCall(dto.BuildInCallFunctionCall, output.Name)
}
}
imageCounter := &relaycommon.ImageGenerationCallCounter{}
if !relaycommon.IsNonBillableResponsesStatus(responsesResponse.Status) {
for i := range responsesResponse.Output {
idx := i
imageCounter.Observe(&responsesResponse.Output[i], &idx)
}
}
imageCounter.Commit(info)
return usage, nil
}
func OaiResponsesStreamHandler(c *gin.Context, info *relaycommon.RelayInfo, resp *http.Response) (*dto.Usage, *types.NewAPIError) {
if resp == nil || resp.Body == nil {
logger.LogError(c, "invalid response or response body")
return nil, types.NewError(fmt.Errorf("invalid response"), types.ErrorCodeBadResponse)
}
defer service.CloseResponseBodyGracefully(resp)
var usage = &dto.Usage{}
var responseTextBuilder strings.Builder
imageCounter := &relaycommon.ImageGenerationCallCounter{}
imageCommitted := false
helper.StreamScannerHandler(c, resp, info, func(data string, sr *helper.StreamResult) {
// 检查当前数据是否包含 completed 状态和 usage 信息
var streamResponse dto.ResponsesStreamResponse
if err := common.UnmarshalJsonStr(data, &streamResponse); err != nil {
logger.LogError(c, "failed to unmarshal stream response: "+err.Error())
sr.Error(err)
return
}
sendResponsesStreamData(c, streamResponse, data)
switch streamResponse.Type {
case "response.completed", "response.done":
if streamResponse.Response != nil {
if streamResponse.Response.Usage != nil {
incomingUsage := relayconvert.NormalizeResponsesUsage(streamResponse.Response.Usage)
usage = dto.MergeUsageNonZero(usage, incomingUsage)
}
if !imageCommitted {
if relaycommon.IsNonBillableResponsesStatus(streamResponse.Response.Status) {
imageCounter.Reset()
imageCounter.Commit(info)
imageCommitted = true
} else {
for i := range streamResponse.Response.Output {
idx := i
imageCounter.Observe(&streamResponse.Response.Output[i], &idx)
}
imageCounter.Commit(info)
imageCommitted = true
}
}
} else if !imageCommitted {
imageCounter.Commit(info)
imageCommitted = true
}
case "response.failed", "response.incomplete", "response.cancelled", "response.canceled":
if !imageCommitted {
imageCounter.Reset()
imageCounter.Commit(info)
imageCommitted = true
}
case "response.output_text.delta":
// 处理输出文本
responseTextBuilder.WriteString(streamResponse.Delta)
case dto.ResponsesOutputTypeItemDone:
if streamResponse.Item != nil {
switch streamResponse.Item.Type {
case dto.BuildInCallWebSearchCall:
info.CountBillableToolCall(dto.BuildInCallWebSearchCall, "")
case dto.BuildInCallFileSearchCall:
info.CountBillableToolCall(dto.BuildInCallFileSearchCall, "")
case dto.BuildInCallFunctionCall:
info.CountBillableToolCall(dto.BuildInCallFunctionCall, streamResponse.Item.Name)
case dto.ResponsesOutputTypeImageGenerationCall:
if !imageCommitted {
imageCounter.Observe(streamResponse.Item, streamResponse.OutputIndex)
}
}
}
}
})
if usage.CompletionTokens == 0 {
// 计算输出文本的 token 数量
tempStr := responseTextBuilder.String()
if len(tempStr) > 0 {
// 非正常结束,使用输出文本的 token 数量
completionTokens := service.CountTextToken(tempStr, info.UpstreamModelName)
usage.CompletionTokens = completionTokens
}
}
if usage.PromptTokens == 0 && usage.CompletionTokens != 0 {
usage.PromptTokens = info.GetEstimatePromptTokens()
}
usage.TotalTokens = usage.PromptTokens + usage.CompletionTokens
if usage.BillingUsage != nil {
usage.BillingUsage = dto.CloneBillingUsageWithEstimatedCompletion(usage.BillingUsage, usage.CompletionTokens)
}
return usage, nil
}