Files
new-api/setting/model_setting/gemini.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

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
}