Files
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

179 lines
6.3 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/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 := dto.Usage{}
if responsesResponse.Usage != nil {
usage.PromptTokens = responsesResponse.Usage.InputTokens
usage.CompletionTokens = responsesResponse.Usage.OutputTokens
usage.TotalTokens = responsesResponse.Usage.TotalTokens
if responsesResponse.Usage.InputTokensDetails != nil {
usage.PromptTokensDetails.CachedTokens = responsesResponse.Usage.InputTokensDetails.CachedTokens
usage.PromptTokensDetails.CacheWriteTokens = responsesResponse.Usage.InputTokensDetails.CacheWriteTokens
}
}
// 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 {
if streamResponse.Response.Usage.InputTokens != 0 {
usage.PromptTokens = streamResponse.Response.Usage.InputTokens
}
if streamResponse.Response.Usage.OutputTokens != 0 {
usage.CompletionTokens = streamResponse.Response.Usage.OutputTokens
}
if streamResponse.Response.Usage.TotalTokens != 0 {
usage.TotalTokens = streamResponse.Response.Usage.TotalTokens
}
if streamResponse.Response.Usage.InputTokensDetails != nil {
usage.PromptTokensDetails.CachedTokens = streamResponse.Response.Usage.InputTokensDetails.CachedTokens
usage.PromptTokensDetails.CacheWriteTokens = streamResponse.Response.Usage.InputTokensDetails.CacheWriteTokens
}
}
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
return usage, nil
}