Calcium-Ion
86ac0f7745
* 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
85 lines
4.4 KiB
Go
85 lines
4.4 KiB
Go
package channel
|
|
|
|
import (
|
|
"io"
|
|
"net/http"
|
|
|
|
taskdto "github.com/QuantumNous/new-api/dto"
|
|
"github.com/QuantumNous/new-api/model"
|
|
relaycommon "github.com/QuantumNous/new-api/relay/common"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
"github.com/QuantumNous/new-api/relaykit/types"
|
|
|
|
"github.com/gin-gonic/gin"
|
|
)
|
|
|
|
type Adaptor interface {
|
|
// Init IsStream bool
|
|
Init(info *relaycommon.RelayInfo)
|
|
GetRequestURL(info *relaycommon.RelayInfo) (string, error)
|
|
SetupRequestHeader(c *gin.Context, req *http.Header, info *relaycommon.RelayInfo) error
|
|
ConvertOpenAIRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeneralOpenAIRequest) (any, error)
|
|
ConvertRerankRequest(c *gin.Context, relayMode int, request dto.RerankRequest) (any, error)
|
|
ConvertEmbeddingRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.EmbeddingRequest) (any, error)
|
|
ConvertAudioRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.AudioRequest) (io.Reader, error)
|
|
ConvertImageRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.ImageRequest) (any, error)
|
|
ConvertOpenAIResponsesRequest(c *gin.Context, info *relaycommon.RelayInfo, request dto.OpenAIResponsesRequest) (any, error)
|
|
DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (any, error)
|
|
DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (usage any, err *types.NewAPIError)
|
|
GetModelList() []string
|
|
GetChannelName() string
|
|
ConvertClaudeRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.ClaudeRequest) (any, error)
|
|
ConvertGeminiRequest(c *gin.Context, info *relaycommon.RelayInfo, request *dto.GeminiChatRequest) (any, error)
|
|
}
|
|
|
|
type TaskAdaptor interface {
|
|
Init(info *relaycommon.RelayInfo)
|
|
|
|
ValidateRequestAndSetAction(c *gin.Context, info *relaycommon.RelayInfo) *taskdto.TaskError
|
|
|
|
// ── Billing ──────────────────────────────────────────────────────
|
|
|
|
// EstimateBilling returns OtherRatios for pre-charge based on user request.
|
|
// Called after ValidateRequestAndSetAction, before price calculation.
|
|
// Adaptors should extract duration, resolution, etc. from the parsed request
|
|
// and return them as ratio multipliers (e.g. {"seconds": 5, "size": 1.666}).
|
|
// Return nil to use the base model price without extra ratios.
|
|
EstimateBilling(c *gin.Context, info *relaycommon.RelayInfo) map[string]float64
|
|
|
|
// AdjustBillingOnSubmit returns adjusted OtherRatios from the upstream
|
|
// submit response. Called after a successful DoResponse.
|
|
// If the upstream returned actual parameters that differ from the estimate
|
|
// (e.g. actual seconds), return updated ratios so the caller can recalculate
|
|
// the quota and settle the delta with the pre-charge.
|
|
// Return nil if no adjustment is needed.
|
|
AdjustBillingOnSubmit(info *relaycommon.RelayInfo, taskData []byte) map[string]float64
|
|
|
|
// AdjustBillingOnComplete returns the actual quota when a task reaches a
|
|
// terminal state (success/failure) during polling.
|
|
// Called by the polling loop after ParseTaskResult.
|
|
// Return a positive value to trigger delta settlement (supplement / refund).
|
|
// Return 0 to keep the pre-charged amount unchanged.
|
|
AdjustBillingOnComplete(task *model.Task, taskResult *relaycommon.TaskInfo) int
|
|
|
|
// ── Request / Response ───────────────────────────────────────────
|
|
|
|
BuildRequestURL(info *relaycommon.RelayInfo) (string, error)
|
|
BuildRequestHeader(c *gin.Context, req *http.Request, info *relaycommon.RelayInfo) error
|
|
BuildRequestBody(c *gin.Context, info *relaycommon.RelayInfo) (io.Reader, error)
|
|
|
|
DoRequest(c *gin.Context, info *relaycommon.RelayInfo, requestBody io.Reader) (*http.Response, error)
|
|
DoResponse(c *gin.Context, resp *http.Response, info *relaycommon.RelayInfo) (taskID string, taskData []byte, err *taskdto.TaskError)
|
|
|
|
GetModelList() []string
|
|
GetChannelName() string
|
|
|
|
// ── Polling ──────────────────────────────────────────────────────
|
|
|
|
FetchTask(baseUrl, key string, body map[string]any, proxy string) (*http.Response, error)
|
|
ParseTaskResult(respBody []byte) (*relaycommon.TaskInfo, error)
|
|
}
|
|
|
|
type OpenAIVideoConverter interface {
|
|
ConvertToOpenAIVideo(originTask *model.Task) ([]byte, error)
|
|
}
|