AI网关新增xAI格式TTS端点与过滤弃用模型开关

- POST /ai/v1/tts:xAI 官方 TTS 格式转换层(text/voice_id→input/voice),复用 Speech 编排,model 缺省 xai.grok-tts;实测 output_format/speed 透传生效
- 「过滤弃用模型」开关(GET/PUT /api/v1/ai-settings,settings 表持久化):开启后已宣布弃用(未退役)模型从列表与路由排除;同步入库与退役提醒不受影响
- AI 网关文档更名 docs/AI网关.md,补 tts 矩阵段与开关说明;README 引用同步
- CHANGELOG 0.5.0(0.4.0 已发版冻结);DASH_VERSION v0.5.0

internal/service/aigateway_test.go

@@ -136,7 +136,7 @@ func (f *gatewayStubClient) GenAiProbeChat(ctx context.Context, cred oci.Credent
 func newTestGateway(t *testing.T, client oci.Client) (*AiGatewayService, *OciConfigService) {
 	t.Helper()
 	svc := newTestService(t, client)
-	if err := svc.db.AutoMigrate(&model.AiKey{}, &model.AiChannel{}, &model.AiModelCache{}, &model.AiModelBlacklist{}, &model.AiCallLog{}); err != nil {
+	if err := svc.db.AutoMigrate(&model.Setting{}, &model.AiKey{}, &model.AiChannel{}, &model.AiModelCache{}, &model.AiModelBlacklist{}, &model.AiCallLog{}); err != nil {
 		t.Fatalf("auto migrate ai tables: %v", err)
 	}
 	return NewAiGatewayService(svc.db, svc, client), svc
@@ -228,6 +228,46 @@ func seedChannel(t *testing.T, gw *AiGatewayService, cfgID uint, region string,
 	return ch
 }
 
+// TestFilterDeprecatedModels 断言「过滤弃用模型」开关对列表 / 路由的过滤与持久化。
+func TestFilterDeprecatedModels(t *testing.T) {
+	gw, svc := newTestGateway(t, &gatewayStubClient{fakeClient: &fakeClient{tenancy: oci.TenancyInfo{Name: "t"}}})
+	cfg := importAliveConfig(t, svc)
+	ch := seedChannel(t, gw, cfg.ID, "eu-frankfurt-1", 1, 1)
+	dep := time.Now().Add(-24 * time.Hour)
+	old := &model.AiModelCache{ChannelID: ch.ID, ModelOcid: "ocid1..dep", Name: "meta.llama-old",
+		Vendor: "meta", SyncedAt: time.Now(), DeprecatedAt: &dep}
+	if err := gw.db.Create(old).Error; err != nil {
+		t.Fatalf("seed deprecated cache: %v", err)
+	}
+	ctx := context.Background()
+
+	list, _ := gw.GatewayModels(ctx, "")
+	if len(list.Data) != 2 {
+		t.Fatalf("开关关:应含弃用模型,got %d", len(list.Data))
+	}
+	if err := gw.SetFilterDeprecated(ctx, true); err != nil {
+		t.Fatalf("SetFilterDeprecated: %v", err)
+	}
+	list, _ = gw.GatewayModels(ctx, "")
+	if len(list.Data) != 1 || list.Data[0].ID != "meta.llama-3.3-70b-instruct" {
+		t.Fatalf("开关开:弃用模型应被过滤,got %+v", list.Data)
+	}
+	if _, err := gw.pick(ctx, "meta.llama-old", "", "CHAT", map[uint]bool{}); !errors.Is(err, ErrAiUnknownModel) {
+		t.Errorf("开关开:弃用模型路由应不可达,err = %v", err)
+	}
+	// 持久化:重建 service 后开关仍生效
+	gw2 := NewAiGatewayService(gw.db, svc, &gatewayStubClient{})
+	if !gw2.FilterDeprecated() {
+		t.Error("重建后开关状态应保持开启")
+	}
+	if err := gw.SetFilterDeprecated(ctx, false); err != nil {
+		t.Fatalf("关闭开关: %v", err)
+	}
+	if list, _ = gw.GatewayModels(ctx, ""); len(list.Data) != 2 {
+		t.Errorf("开关关:弃用模型应恢复,got %d", len(list.Data))
+	}
+}
+
 func TestPickPriorityAndBreaker(t *testing.T) {
 	gw, svc := newTestGateway(t, &gatewayStubClient{fakeClient: &fakeClient{tenancy: oci.TenancyInfo{Name: "t"}}})
 	cfg := importAliveConfig(t, svc)