* 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
199 lines
6.5 KiB
Go
199 lines
6.5 KiB
Go
package codex
|
|
|
|
import (
|
|
"encoding/json"
|
|
"errors"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/relay/channel"
|
|
"github.com/QuantumNous/new-api/relay/channel/openai"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
relayconstant "github.com/QuantumNous/new-api/relay/constant"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
type Adaptor struct {
|
|
}
|
|
|
|
func (a *Adaptor) ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeminiChatRequest) (any, error) {
|
|
return nil, errors.New("codex channel: endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertClaudeRequest(*gin.Context, *relaycommon.RelayInfo, *dto.ClaudeRequest) (any, error) {
|
|
return nil, errors.New("codex channel: /v1/messages endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error) {
|
|
return nil, errors.New("codex channel: endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error) {
|
|
return nil, errors.New("codex channel: endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) Init(info *relaycommon.RelayInfo) {
|
|
}
|
|
|
|
func (a *Adaptor) ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error) {
|
|
return nil, errors.New("codex channel: /v1/chat/completions endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error) {
|
|
return nil, errors.New("codex channel: /v1/rerank endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error) {
|
|
return nil, errors.New("codex channel: /v1/embeddings endpoint not supported")
|
|
}
|
|
|
|
func (a *Adaptor) ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error) {
|
|
isCompact := info != nil && info.RelayMode == relayconstant.RelayModeResponsesCompact
|
|
|
|
if info != nil && info.ChannelSetting.SystemPrompt != "" {
|
|
systemPrompt := info.ChannelSetting.SystemPrompt
|
|
|
|
if len(request.Instructions) == 0 {
|
|
if b, err := common.Marshal(systemPrompt); err == nil {
|
|
request.Instructions = b
|
|
} else {
|
|
return nil, err
|
|
}
|
|
} else if info.ChannelSetting.SystemPromptOverride {
|
|
var existing string
|
|
if err := common.Unmarshal(request.Instructions, &existing); err == nil {
|
|
existing = strings.TrimSpace(existing)
|
|
if existing == "" {
|
|
if b, err := common.Marshal(systemPrompt); err == nil {
|
|
request.Instructions = b
|
|
} else {
|
|
return nil, err
|
|
}
|
|
} else {
|
|
if b, err := common.Marshal(systemPrompt + "\n" + existing); err == nil {
|
|
request.Instructions = b
|
|
} else {
|
|
return nil, err
|
|
}
|
|
}
|
|
} else {
|
|
if b, err := common.Marshal(systemPrompt); err == nil {
|
|
request.Instructions = b
|
|
} else {
|
|
return nil, err
|
|
}
|
|
}
|
|
}
|
|
}
|
|
// Codex backend requires the `instructions` field to be present.
|
|
// Keep it consistent with Codex CLI behavior by defaulting to an empty string.
|
|
if len(request.Instructions) == 0 {
|
|
request.Instructions = json.RawMessage(`""`)
|
|
}
|
|
|
|
if isCompact {
|
|
return request, nil
|
|
}
|
|
// codex: store must be false
|
|
request.Store = json.RawMessage("false")
|
|
// rm max_output_tokens
|
|
request.MaxOutputTokens = nil
|
|
request.Temperature = nil
|
|
return request, nil
|
|
}
|
|
|
|
func (a *Adaptor) DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error) {
|
|
return channel.DoApiRequest(a, c, info, requestBody)
|
|
}
|
|
|
|
func (a *Adaptor) DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError) {
|
|
switch info.RelayMode {
|
|
case relayconstant.RelayModeAlphaSearch:
|
|
// Alpha search responses are handled by relay.AlphaSearchHelper.
|
|
return nil, types.NewError(errors.New("codex channel: alpha search response should be handled by AlphaSearchHelper"), types.ErrorCodeInvalidRequest)
|
|
case relayconstant.RelayModeResponsesCompact:
|
|
return openai.OaiResponsesCompactionHandler(c, resp)
|
|
case relayconstant.RelayModeResponses:
|
|
if info.IsStream {
|
|
return openai.OaiResponsesStreamHandler(c, info, resp)
|
|
}
|
|
return openai.OaiResponsesHandler(c, info, resp)
|
|
default:
|
|
return nil, types.NewError(errors.New("codex channel: endpoint not supported"), types.ErrorCodeInvalidRequest)
|
|
}
|
|
}
|
|
|
|
func (a *Adaptor) GetModelList() []string {
|
|
return ModelList
|
|
}
|
|
|
|
func (a *Adaptor) GetChannelName() string {
|
|
return ChannelName
|
|
}
|
|
|
|
func (a *Adaptor) GetRequestURL(info *relaycommon.RelayInfo) (string, error) {
|
|
var path string
|
|
switch info.RelayMode {
|
|
case relayconstant.RelayModeResponses:
|
|
path = "/backend-api/codex/responses"
|
|
case relayconstant.RelayModeResponsesCompact:
|
|
path = "/backend-api/codex/responses/compact"
|
|
case relayconstant.RelayModeAlphaSearch:
|
|
path = "/backend-api/codex/alpha/search"
|
|
default:
|
|
return "", errors.New("codex channel: only /v1/responses, /v1/responses/compact and /v1/alpha/search are supported")
|
|
}
|
|
return relaycommon.GetFullRequestURL(info.ChannelBaseUrl, path, info.ChannelType), nil
|
|
}
|
|
|
|
func (a *Adaptor) SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error {
|
|
channel.SetupApiRequestHeader(info, c, req)
|
|
|
|
key := strings.TrimSpace(info.ApiKey)
|
|
if !strings.HasPrefix(key, "{") {
|
|
return errors.New("codex channel: key must be a JSON object")
|
|
}
|
|
|
|
oauthKey, err := ParseOAuthKey(key)
|
|
if err != nil {
|
|
return err
|
|
}
|
|
|
|
accessToken := strings.TrimSpace(oauthKey.AccessToken)
|
|
accountID := strings.TrimSpace(oauthKey.AccountID)
|
|
|
|
if accessToken == "" {
|
|
return errors.New("codex channel: access_token is required")
|
|
}
|
|
if accountID == "" {
|
|
return errors.New("codex channel: account_id is required")
|
|
}
|
|
|
|
req.Set("Authorization", "Bearer "+accessToken)
|
|
req.Set("chatgpt-account-id", accountID)
|
|
|
|
if req.Get("OpenAI-Beta") == "" {
|
|
req.Set("OpenAI-Beta", "responses=experimental")
|
|
}
|
|
if req.Get("originator") == "" {
|
|
req.Set("originator", "codex_cli_rs")
|
|
}
|
|
|
|
// chatgpt.com/backend-api/codex/responses is strict about Content-Type.
|
|
// Clients may omit it or include parameters like `application/json; charset=utf-8`,
|
|
// which can be rejected by the upstream. Force the exact media type.
|
|
req.Set("Content-Type", "application/json")
|
|
if info.IsStream {
|
|
req.Set("Accept", "text/event-stream")
|
|
} else if req.Get("Accept") == "" {
|
|
req.Set("Accept", "application/json")
|
|
}
|
|
|
|
return nil
|
|
}
|