+135
-12
@@ -10,6 +10,7 @@ import (
|
||||
"fmt"
|
||||
"log"
|
||||
"sort"
|
||||
"strconv"
|
||||
"strings"
|
||||
"sync"
|
||||
"sync/atomic"
|
||||
@@ -61,20 +62,72 @@ type AiGatewayService struct {
|
||||
onChannelsChanged func(context.Context)
|
||||
// filterDeprecated 是「过滤弃用模型」开关(内存镜像,持久化在 settings 表)
|
||||
filterDeprecated atomic.Bool
|
||||
// streamGuard* 是 Responses 流式保险丝(instructions+tools 合计超阈值改非流式)
|
||||
streamGuardEnabled atomic.Bool
|
||||
streamGuardKB atomic.Int64
|
||||
// grokWebSearch / grokXSearch 是 xai. 模型服务端搜索工具默认注入开关
|
||||
grokWebSearch atomic.Bool
|
||||
grokXSearch atomic.Bool
|
||||
}
|
||||
|
||||
// NewAiGatewayService 组装依赖;调用 StartCleanup 后开始调用日志周期清理。
|
||||
func NewAiGatewayService(db *gorm.DB, configs *OciConfigService, client oci.Client) *AiGatewayService {
|
||||
s := &AiGatewayService{db: db, configs: configs, client: client, lastTouch: map[uint]time.Time{}}
|
||||
var row model.Setting
|
||||
if err := db.Where("key = ?", settingAiFilterDeprecated).First(&row).Error; err == nil {
|
||||
s.filterDeprecated.Store(row.Value == "1")
|
||||
}
|
||||
s.filterDeprecated.Store(loadBoolSetting(db, settingAiFilterDeprecated, false))
|
||||
s.streamGuardEnabled.Store(loadBoolSetting(db, settingAiStreamGuardEnabled, true))
|
||||
s.streamGuardKB.Store(int64(loadIntSetting(db, settingAiStreamGuardKB, defaultStreamGuardKB)))
|
||||
s.grokWebSearch.Store(loadBoolSetting(db, settingAiGrokWebSearch, true))
|
||||
s.grokXSearch.Store(loadBoolSetting(db, settingAiGrokXSearch, true))
|
||||
return s
|
||||
}
|
||||
|
||||
// settingAiFilterDeprecated 是「过滤弃用模型」开关的配置键,值 "1"/"0",缺省关闭。
|
||||
const settingAiFilterDeprecated = "ai_filter_deprecated"
|
||||
// AI 网关运行时设置的配置键;bool 值存 "1"/"0"。
|
||||
const (
|
||||
// settingAiFilterDeprecated 是「过滤弃用模型」开关,缺省关闭。
|
||||
settingAiFilterDeprecated = "ai_filter_deprecated"
|
||||
// settingAiStreamGuardEnabled / settingAiStreamGuardKB 是流式保险丝开关与
|
||||
// 阈值(KB),缺省开、60(上游对 instructions+tools >≈64.5KB 流式静默断流)。
|
||||
settingAiStreamGuardEnabled = "ai_stream_guard_enabled"
|
||||
settingAiStreamGuardKB = "ai_stream_guard_kb"
|
||||
// settingAiGrokWebSearch / settingAiGrokXSearch 是 grok 搜索工具默认注入
|
||||
// 开关,缺省开。
|
||||
settingAiGrokWebSearch = "ai_grok_web_search"
|
||||
settingAiGrokXSearch = "ai_grok_x_search"
|
||||
)
|
||||
|
||||
// defaultStreamGuardKB 是保险丝阈值缺省值,低于实测断流边界留余量。
|
||||
const defaultStreamGuardKB = 60
|
||||
|
||||
// loadBoolSetting 读 settings 表布尔键,无行或值非法时返回缺省。
|
||||
func loadBoolSetting(db *gorm.DB, key string, def bool) bool {
|
||||
var row model.Setting
|
||||
if err := db.Where("key = ?", key).First(&row).Error; err != nil {
|
||||
return def
|
||||
}
|
||||
return row.Value == "1"
|
||||
}
|
||||
|
||||
// loadIntSetting 读 settings 表整数键,无行或解析失败时返回缺省。
|
||||
func loadIntSetting(db *gorm.DB, key string, def int) int {
|
||||
var row model.Setting
|
||||
if err := db.Where("key = ?", key).First(&row).Error; err != nil {
|
||||
return def
|
||||
}
|
||||
n, err := strconv.Atoi(row.Value)
|
||||
if err != nil {
|
||||
return def
|
||||
}
|
||||
return n
|
||||
}
|
||||
|
||||
// saveBoolSetting 持久化布尔键。
|
||||
func (s *AiGatewayService) saveBoolSetting(ctx context.Context, key string, on bool) error {
|
||||
value := "0"
|
||||
if on {
|
||||
value = "1"
|
||||
}
|
||||
return s.db.WithContext(ctx).Save(&model.Setting{Key: key, Value: value}).Error
|
||||
}
|
||||
|
||||
// FilterDeprecated 返回「过滤弃用模型」开关状态。
|
||||
func (s *AiGatewayService) FilterDeprecated() bool { return s.filterDeprecated.Load() }
|
||||
@@ -82,18 +135,54 @@ func (s *AiGatewayService) FilterDeprecated() bool { return s.filterDeprecated.L
|
||||
// SetFilterDeprecated 持久化并即时生效开关:开启后已宣布弃用
|
||||
// (deprecated_at 非空,即使未退役)的模型从列表与路由中排除。
|
||||
func (s *AiGatewayService) SetFilterDeprecated(ctx context.Context, on bool) error {
|
||||
value := "0"
|
||||
if on {
|
||||
value = "1"
|
||||
}
|
||||
err := s.db.WithContext(ctx).Save(&model.Setting{Key: settingAiFilterDeprecated, Value: value}).Error
|
||||
if err != nil {
|
||||
if err := s.saveBoolSetting(ctx, settingAiFilterDeprecated, on); err != nil {
|
||||
return fmt.Errorf("保存过滤弃用模型开关: %w", err)
|
||||
}
|
||||
s.filterDeprecated.Store(on)
|
||||
return nil
|
||||
}
|
||||
|
||||
// StreamGuard 返回流式保险丝开关与阈值(KB)。
|
||||
func (s *AiGatewayService) StreamGuard() (bool, int) {
|
||||
return s.streamGuardEnabled.Load(), int(s.streamGuardKB.Load())
|
||||
}
|
||||
|
||||
// SetStreamGuard 持久化并即时生效流式保险丝;kb 限定 1..1024。
|
||||
func (s *AiGatewayService) SetStreamGuard(ctx context.Context, on bool, kb int) error {
|
||||
if kb < 1 || kb > 1024 {
|
||||
return fmt.Errorf("流式保险丝阈值须在 1..1024 KB, 收到 %d", kb)
|
||||
}
|
||||
if err := s.saveBoolSetting(ctx, settingAiStreamGuardEnabled, on); err != nil {
|
||||
return fmt.Errorf("保存流式保险丝开关: %w", err)
|
||||
}
|
||||
err := s.db.WithContext(ctx).
|
||||
Save(&model.Setting{Key: settingAiStreamGuardKB, Value: strconv.Itoa(kb)}).Error
|
||||
if err != nil {
|
||||
return fmt.Errorf("保存流式保险丝阈值: %w", err)
|
||||
}
|
||||
s.streamGuardEnabled.Store(on)
|
||||
s.streamGuardKB.Store(int64(kb))
|
||||
return nil
|
||||
}
|
||||
|
||||
// GrokSearch 返回 grok 服务端搜索工具默认注入开关(web_search, x_search)。
|
||||
func (s *AiGatewayService) GrokSearch() (bool, bool) {
|
||||
return s.grokWebSearch.Load(), s.grokXSearch.Load()
|
||||
}
|
||||
|
||||
// SetGrokSearch 持久化并即时生效 grok 搜索工具默认注入开关。
|
||||
func (s *AiGatewayService) SetGrokSearch(ctx context.Context, web, x bool) error {
|
||||
if err := s.saveBoolSetting(ctx, settingAiGrokWebSearch, web); err != nil {
|
||||
return fmt.Errorf("保存 grok web_search 开关: %w", err)
|
||||
}
|
||||
if err := s.saveBoolSetting(ctx, settingAiGrokXSearch, x); err != nil {
|
||||
return fmt.Errorf("保存 grok x_search 开关: %w", err)
|
||||
}
|
||||
s.grokWebSearch.Store(web)
|
||||
s.grokXSearch.Store(x)
|
||||
return nil
|
||||
}
|
||||
|
||||
// SetOnChannelsChanged 注册渠道数量变化钩子(渠道创建/删除成功后调用)。
|
||||
func (s *AiGatewayService) SetOnChannelsChanged(fn func(context.Context)) {
|
||||
s.onChannelsChanged = fn
|
||||
@@ -661,6 +750,40 @@ func (s *AiGatewayService) GatewayModels(ctx context.Context, group string) (aiw
|
||||
return list, nil
|
||||
}
|
||||
|
||||
// AggregatedModel 是聚合模型目录条目(设置页黑名单添加弹窗用)。
|
||||
type AggregatedModel struct {
|
||||
Name string `json:"name"`
|
||||
Capability string `json:"capability"`
|
||||
}
|
||||
|
||||
// AggregatedModels 返回启用渠道去重后的模型目录(含能力);空能力归一为 CHAT。
|
||||
// 与模型列表口径一致:「过滤弃用」开启时弃用模型不出现在目录中。
|
||||
func (s *AiGatewayService) AggregatedModels(ctx context.Context) ([]AggregatedModel, error) {
|
||||
q := s.db.WithContext(ctx).
|
||||
Joins("JOIN ai_channels ON ai_channels.id = ai_model_caches.channel_id AND ai_channels.enabled = ?", true)
|
||||
if s.FilterDeprecated() {
|
||||
q = q.Where("ai_model_caches.deprecated_at IS NULL")
|
||||
}
|
||||
var rows []model.AiModelCache
|
||||
if err := q.Order("ai_model_caches.name ASC").Find(&rows).Error; err != nil {
|
||||
return nil, fmt.Errorf("聚合模型目录: %w", err)
|
||||
}
|
||||
seen := map[string]bool{}
|
||||
out := []AggregatedModel{}
|
||||
for _, r := range rows {
|
||||
if seen[r.Name] {
|
||||
continue
|
||||
}
|
||||
seen[r.Name] = true
|
||||
cap := r.Capability
|
||||
if cap == "" {
|
||||
cap = "CHAT"
|
||||
}
|
||||
out = append(out, AggregatedModel{Name: r.Name, Capability: cap})
|
||||
}
|
||||
return out, nil
|
||||
}
|
||||
|
||||
// DeprecatingModels 返回 within 窗口内即将退役或即将弃用的在池模型(按名称去重):
|
||||
// 退役(TimeOnDemandRetired)才导致不可调用,单独标注;已过弃用日但未到退役日的
|
||||
// 模型仍可正常调用,不再反复告警;已过退役日的在同步层剔除,不会出现在池中。
|
||||
|
||||
Reference in New Issue
Block a user