Files
new-api/relay/channel/aws/dto.go
T
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

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
}