* 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
147 lines
4.8 KiB
Go
147 lines
4.8 KiB
Go
package aws
|
|
|
|
import (
|
|
"context"
|
|
"encoding/json"
|
|
"io"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/logger"
|
|
"github.com/QuantumNous/new-api/relaykit/dto"
|
|
)
|
|
|
|
type AwsClaudeRequest struct {
|
|
// AnthropicVersion should be "bedrock-2023-05-31"
|
|
AnthropicVersion string `json:"anthropic_version"`
|
|
AnthropicBeta json.RawMessage `json:"anthropic_beta,omitempty"`
|
|
System any `json:"system,omitempty"`
|
|
Messages []dto.ClaudeMessage `json:"messages"`
|
|
MaxTokens *uint `json:"max_tokens,omitempty"`
|
|
Temperature *float64 `json:"temperature,omitempty"`
|
|
TopP *float64 `json:"top_p,omitempty"`
|
|
TopK *int `json:"top_k,omitempty"`
|
|
StopSequences []string `json:"stop_sequences,omitempty"`
|
|
Tools any `json:"tools,omitempty"`
|
|
ToolChoice any `json:"tool_choice,omitempty"`
|
|
ContextManagement json.RawMessage `json:"context_management,omitempty"`
|
|
Thinking *dto.Thinking `json:"thinking,omitempty"`
|
|
OutputConfig json.RawMessage `json:"output_config,omitempty"`
|
|
//Metadata json.RawMessage `json:"metadata,omitempty"`
|
|
}
|
|
|
|
func formatRequest(requestBody io.Reader, requestHeader http.Header) (*AwsClaudeRequest, error) {
|
|
var awsClaudeRequest AwsClaudeRequest
|
|
err := common.DecodeJson(requestBody, &awsClaudeRequest)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
awsClaudeRequest.AnthropicVersion = "bedrock-2023-05-31"
|
|
|
|
// check header anthropic-beta
|
|
anthropicBetaValues := requestHeader.Get("anthropic-beta")
|
|
if len(anthropicBetaValues) > 0 {
|
|
var tempArray []string
|
|
tempArray = strings.Split(anthropicBetaValues, ",")
|
|
if len(tempArray) > 0 {
|
|
betaJson, err := json.Marshal(tempArray)
|
|
if err != nil {
|
|
return nil, err
|
|
}
|
|
awsClaudeRequest.AnthropicBeta = betaJson
|
|
}
|
|
}
|
|
logger.LogJson(context.Background(), "json", awsClaudeRequest)
|
|
return &awsClaudeRequest, nil
|
|
}
|
|
|
|
// NovaMessage Nova模型使用messages-v1格式
|
|
type NovaMessage struct {
|
|
Role string `json:"role"`
|
|
Content []NovaContent `json:"content"`
|
|
}
|
|
|
|
type NovaContent struct {
|
|
Text string `json:"text"`
|
|
}
|
|
|
|
type NovaRequest struct {
|
|
SchemaVersion string `json:"schemaVersion"` // 请求版本,例如 "1.0"
|
|
Messages []NovaMessage `json:"messages"` // 对话消息列表
|
|
InferenceConfig *NovaInferenceConfig `json:"inferenceConfig,omitempty"` // 推理配置,可选
|
|
}
|
|
|
|
type NovaInferenceConfig struct {
|
|
MaxTokens int `json:"maxTokens,omitempty"` // 最大生成的 token 数
|
|
Temperature float64 `json:"temperature,omitempty"` // 随机性 (默认 0.7, 范围 0-1)
|
|
TopP float64 `json:"topP,omitempty"` // nucleus sampling (默认 0.9, 范围 0-1)
|
|
TopK int `json:"topK,omitempty"` // 限制候选 token 数 (默认 50, 范围 0-128)
|
|
StopSequences []string `json:"stopSequences,omitempty"` // 停止生成的序列
|
|
}
|
|
|
|
// 转换OpenAI请求为Nova格式
|
|
func convertToNovaRequest(req *dto.GeneralOpenAIRequest) *NovaRequest {
|
|
novaMessages := make([]NovaMessage, len(req.Messages))
|
|
for i, msg := range req.Messages {
|
|
novaMessages[i] = NovaMessage{
|
|
Role: msg.Role,
|
|
Content: []NovaContent{{Text: msg.StringContent()}},
|
|
}
|
|
}
|
|
|
|
novaReq := &NovaRequest{
|
|
SchemaVersion: "messages-v1",
|
|
Messages: novaMessages,
|
|
}
|
|
|
|
// 设置推理配置
|
|
if (req.MaxTokens != nil && *req.MaxTokens != 0) || (req.Temperature != nil && *req.Temperature != 0) || (req.TopP != nil && *req.TopP != 0) || (req.TopK != nil && *req.TopK != 0) || req.Stop != nil {
|
|
novaReq.InferenceConfig = &NovaInferenceConfig{}
|
|
if req.MaxTokens != nil && *req.MaxTokens != 0 {
|
|
novaReq.InferenceConfig.MaxTokens = int(*req.MaxTokens)
|
|
}
|
|
if req.Temperature != nil && *req.Temperature != 0 {
|
|
novaReq.InferenceConfig.Temperature = *req.Temperature
|
|
}
|
|
if req.TopP != nil && *req.TopP != 0 {
|
|
novaReq.InferenceConfig.TopP = *req.TopP
|
|
}
|
|
if req.TopK != nil && *req.TopK != 0 {
|
|
novaReq.InferenceConfig.TopK = *req.TopK
|
|
}
|
|
if req.Stop != nil {
|
|
if stopSequences := parseStopSequences(req.Stop); len(stopSequences) > 0 {
|
|
novaReq.InferenceConfig.StopSequences = stopSequences
|
|
}
|
|
}
|
|
}
|
|
|
|
return novaReq
|
|
}
|
|
|
|
// parseStopSequences 解析停止序列,支持字符串或字符串数组
|
|
func parseStopSequences(stop any) []string {
|
|
if stop == nil {
|
|
return nil
|
|
}
|
|
|
|
switch v := stop.(type) {
|
|
case string:
|
|
if v != "" {
|
|
return []string{v}
|
|
}
|
|
case []string:
|
|
return v
|
|
case []interface{}:
|
|
var sequences []string
|
|
for _, item := range v {
|
|
if str, ok := item.(string); ok && str != "" {
|
|
sequences = append(sequences, str)
|
|
}
|
|
}
|
|
return sequences
|
|
}
|
|
return nil
|
|
}
|