* 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
118 lines
3.6 KiB
Go
118 lines
3.6 KiB
Go
package model_setting
|
|
|
|
import (
|
|
"fmt"
|
|
|
|
"github.com/QuantumNous/new-api/common"
|
|
"github.com/QuantumNous/new-api/setting/config"
|
|
)
|
|
|
|
const defaultGeminiSafetySetting = "OFF"
|
|
|
|
var validGeminiSafetySettings = map[string]struct{}{
|
|
"OFF": {},
|
|
"BLOCK_NONE": {},
|
|
"BLOCK_ONLY_HIGH": {},
|
|
"BLOCK_MEDIUM_AND_ABOVE": {},
|
|
"BLOCK_LOW_AND_ABOVE": {},
|
|
"HARM_BLOCK_THRESHOLD_UNSPECIFIED": {},
|
|
}
|
|
|
|
// GeminiSettings defines Gemini model configuration. 注意bool要以enabled结尾才可以生效编辑
|
|
type GeminiSettings struct {
|
|
SafetySettings map[string]string `json:"safety_settings"`
|
|
VersionSettings map[string]string `json:"version_settings"`
|
|
SupportedImagineModels []string `json:"supported_imagine_models"`
|
|
ThinkingAdapterEnabled bool `json:"thinking_adapter_enabled"`
|
|
ThinkingAdapterBudgetTokensPercentage float64 `json:"thinking_adapter_budget_tokens_percentage"`
|
|
FunctionCallThoughtSignatureEnabled bool `json:"function_call_thought_signature_enabled"`
|
|
RemoveFunctionResponseIdEnabled bool `json:"remove_function_response_id_enabled"`
|
|
}
|
|
|
|
// 默认配置
|
|
var defaultGeminiSettings = GeminiSettings{
|
|
SafetySettings: map[string]string{
|
|
"default": defaultGeminiSafetySetting,
|
|
},
|
|
VersionSettings: map[string]string{
|
|
"default": "v1beta",
|
|
"gemini-1.0-pro": "v1",
|
|
},
|
|
SupportedImagineModels: []string{
|
|
"gemini-2.0-flash-exp-image-generation",
|
|
"gemini-2.0-flash-exp",
|
|
"gemini-3-pro-image-preview",
|
|
"gemini-3-pro-image",
|
|
"gemini-2.5-flash-image",
|
|
"gemini-3.1-flash-image",
|
|
"gemini-3.1-flash-image-preview",
|
|
},
|
|
ThinkingAdapterEnabled: false,
|
|
ThinkingAdapterBudgetTokensPercentage: 0.6,
|
|
FunctionCallThoughtSignatureEnabled: true,
|
|
RemoveFunctionResponseIdEnabled: true,
|
|
}
|
|
|
|
// 全局实例
|
|
var geminiSettings = defaultGeminiSettings
|
|
|
|
func init() {
|
|
// 注册到全局配置管理器
|
|
config.GlobalConfig.Register("gemini", &geminiSettings)
|
|
}
|
|
|
|
// GetGeminiSettings 获取Gemini配置
|
|
func GetGeminiSettings() *GeminiSettings {
|
|
return &geminiSettings
|
|
}
|
|
|
|
// GetGeminiSafetySetting 获取安全设置
|
|
func GetGeminiSafetySetting(key string) string {
|
|
settings := geminiSettings.SafetySettings
|
|
if value := settings[key]; value != "" {
|
|
return value
|
|
}
|
|
if value := settings["default"]; value != "" {
|
|
return value
|
|
}
|
|
return defaultGeminiSafetySetting
|
|
}
|
|
|
|
// ValidateGeminiSafetySettings validates the JSON persisted by the option API.
|
|
// Empty values remain valid because read-time fallback returns the default.
|
|
func ValidateGeminiSafetySettings(value string) error {
|
|
var settings map[string]string
|
|
if err := common.UnmarshalJsonStr(value, &settings); err != nil {
|
|
return fmt.Errorf("Gemini safety settings must be a JSON string map: %w", err)
|
|
}
|
|
if settings == nil {
|
|
return fmt.Errorf("Gemini safety settings must be a JSON string map")
|
|
}
|
|
for category, threshold := range settings {
|
|
if threshold == "" {
|
|
continue
|
|
}
|
|
if _, ok := validGeminiSafetySettings[threshold]; !ok {
|
|
return fmt.Errorf("invalid Gemini safety threshold %q for %q", threshold, category)
|
|
}
|
|
}
|
|
return nil
|
|
}
|
|
|
|
// GetGeminiVersionSetting 获取版本设置
|
|
func GetGeminiVersionSetting(key string) string {
|
|
if value, ok := geminiSettings.VersionSettings[key]; ok {
|
|
return value
|
|
}
|
|
return geminiSettings.VersionSettings["default"]
|
|
}
|
|
|
|
func IsGeminiModelSupportImagine(model string) bool {
|
|
for _, v := range geminiSettings.SupportedImagineModels {
|
|
if v == model {
|
|
return true
|
|
}
|
|
}
|
|
return false
|
|
}
|