* 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
112 lines
3.5 KiB
Go
112 lines
3.5 KiB
Go
package model_setting
|
|
|
|
import (
|
|
"fmt"
|
|
"net/http"
|
|
"strings"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/setting/config"
|
|
)
|
|
|
|
//var claudeHeadersSettings = map[string][]string{}
|
|
//
|
|
//var ClaudeThinkingAdapterEnabled = true
|
|
//var ClaudeThinkingAdapterMaxTokens = 8192
|
|
//var ClaudeThinkingAdapterBudgetTokensPercentage = 0.8
|
|
|
|
// ClaudeSettings 定义Claude模型的配置
|
|
type ClaudeSettings struct {
|
|
HeadersSettings map[string]map[string][]string `json:"model_headers_settings"`
|
|
DefaultMaxTokens map[string]int `json:"default_max_tokens"`
|
|
ThinkingAdapterEnabled bool `json:"thinking_adapter_enabled"`
|
|
ThinkingAdapterBudgetTokensPercentage float64 `json:"thinking_adapter_budget_tokens_percentage"`
|
|
}
|
|
|
|
// 默认配置
|
|
var defaultClaudeSettings = ClaudeSettings{
|
|
HeadersSettings: map[string]map[string][]string{},
|
|
ThinkingAdapterEnabled: true,
|
|
DefaultMaxTokens: map[string]int{
|
|
"default": 8192,
|
|
},
|
|
ThinkingAdapterBudgetTokensPercentage: 0.8,
|
|
}
|
|
|
|
// 全局实例
|
|
var claudeSettings = defaultClaudeSettings
|
|
|
|
func init() {
|
|
// 注册到全局配置管理器
|
|
config.GlobalConfig.Register("claude", &claudeSettings)
|
|
}
|
|
|
|
// GetClaudeSettings 获取Claude配置
|
|
func GetClaudeSettings() *ClaudeSettings {
|
|
// check default max tokens must have default key
|
|
if _, ok := claudeSettings.DefaultMaxTokens["default"]; !ok {
|
|
claudeSettings.DefaultMaxTokens["default"] = 8192
|
|
}
|
|
return &claudeSettings
|
|
}
|
|
|
|
func (c *ClaudeSettings) WriteHeaders(originModel string, httpHeader *http.Header) {
|
|
if headers, ok := c.HeadersSettings[originModel]; ok {
|
|
for headerKey, headerValues := range headers {
|
|
mergedValues := normalizeHeaderListValues(
|
|
append(append([]string(nil), httpHeader.Values(headerKey)...), headerValues...),
|
|
)
|
|
if len(mergedValues) == 0 {
|
|
continue
|
|
}
|
|
httpHeader.Set(headerKey, strings.Join(mergedValues, ","))
|
|
}
|
|
}
|
|
}
|
|
|
|
func normalizeHeaderListValues(values []string) []string {
|
|
normalizedValues := make([]string, 0, len(values))
|
|
seenValues := make(map[string]struct{}, len(values))
|
|
for _, value := range values {
|
|
for _, item := range strings.Split(value, ",") {
|
|
normalizedItem := strings.TrimSpace(item)
|
|
if normalizedItem == "" {
|
|
continue
|
|
}
|
|
if _, exists := seenValues[normalizedItem]; exists {
|
|
continue
|
|
}
|
|
seenValues[normalizedItem] = struct{}{}
|
|
normalizedValues = append(normalizedValues, normalizedItem)
|
|
}
|
|
}
|
|
return normalizedValues
|
|
}
|
|
|
|
func (c *ClaudeSettings) GetDefaultMaxTokens(model string) int {
|
|
if maxTokens, ok := c.DefaultMaxTokens[model]; ok {
|
|
return maxTokens
|
|
}
|
|
return c.DefaultMaxTokens["default"]
|
|
}
|
|
|
|
// ValidateClaudeDefaultMaxTokens validates the JSON persisted by the option
|
|
// API. Zero stays allowed — the current Messages API accepts max_tokens: 0 as
|
|
// cache pre-warming — but negative values are rejected because they would
|
|
// wrap into huge unsigned values during request conversion.
|
|
func ValidateClaudeDefaultMaxTokens(value string) error {
|
|
var settings map[string]int
|
|
if err := common.UnmarshalJsonStr(value, &settings); err != nil {
|
|
return fmt.Errorf("Claude default max tokens must be a JSON map of model to integer: %w", err)
|
|
}
|
|
if settings == nil {
|
|
return fmt.Errorf("Claude default max tokens must be a JSON map of model to integer")
|
|
}
|
|
for model, maxTokens := range settings {
|
|
if maxTokens < 0 {
|
|
return fmt.Errorf("negative Claude default max_tokens %d for %q", maxTokens, model)
|
|
}
|
|
}
|
|
return nil
|
|
}
|