responses 直通超时可配,流式去总超时,代理补阶段超时

internal/service/aigateway_test.go

@@ -83,7 +83,7 @@ func (f *gatewayStubClient) GenAiApplyGuardrails(ctx context.Context, cred oci.C
 	return f.guardOutcome, f.guardErr
 }
 
-func (f *gatewayStubClient) GenAiCompatResponses(ctx context.Context, cred oci.Credentials, region string, body []byte) ([]byte, error) {
+func (f *gatewayStubClient) GenAiCompatResponses(ctx context.Context, cred oci.Credentials, region string, body []byte, wait time.Duration) ([]byte, error) {
 	f.passCalls++
 	f.passRegions = append(f.passRegions, region)
 	if len(f.passErrs) > 0 {
@@ -96,7 +96,7 @@ func (f *gatewayStubClient) GenAiCompatResponses(ctx context.Context, cred oci.C
 	return f.passPayload, nil
 }
 
-func (f *gatewayStubClient) GenAiCompatResponsesStream(ctx context.Context, cred oci.Credentials, region string, body []byte) (io.ReadCloser, error) {
+func (f *gatewayStubClient) GenAiCompatResponsesStream(ctx context.Context, cred oci.Credentials, region string, body []byte, wait time.Duration) (io.ReadCloser, error) {
 	f.passCalls++
 	f.passRegions = append(f.passRegions, region)
 	if len(f.passErrs) > 0 {
@@ -1124,3 +1124,38 @@ func TestAggregatedModelsFilterDeprecated(t *testing.T) {
 		t.Fatalf("开关开:弃用模型应被过滤, got %+v", items)
 	}
 }
+
+func TestUpstreamWaitSetting(t *testing.T) {
+	gw, _ := newTestGateway(t, &gatewayStubClient{fakeClient: &fakeClient{}})
+	ctx := context.Background()
+
+	if got := gw.UpstreamWait(); got != 300*time.Second {
+		t.Fatalf("缺省上游无响应预算 = %v, 期望 300s", got)
+	}
+	tests := []struct {
+		name    string
+		sec     int
+		wantErr bool
+	}{
+		{name: "下界 30 有效", sec: 30},
+		{name: "上界 900 有效", sec: 900},
+		{name: "低于下界拒绝", sec: 29, wantErr: true},
+		{name: "高于上界拒绝", sec: 901, wantErr: true},
+	}
+	for _, tt := range tests {
+		t.Run(tt.name, func(t *testing.T) {
+			err := gw.SetUpstreamWait(ctx, tt.sec)
+			if (err != nil) != tt.wantErr {
+				t.Fatalf("SetUpstreamWait(%d) = %v, wantErr=%v", tt.sec, err, tt.wantErr)
+			}
+			if !tt.wantErr && gw.UpstreamWait() != time.Duration(tt.sec)*time.Second {
+				t.Fatalf("UpstreamWait = %v, 期望 %ds", gw.UpstreamWait(), tt.sec)
+			}
+		})
+	}
+	// 持久化后新实例应加载已存值(最后一次成功设置为 900)
+	gw2 := NewAiGatewayService(gw.db, nil, nil)
+	if got := gw2.UpstreamWait(); got != 900*time.Second {
+		t.Fatalf("重建服务加载预算 = %v, 期望 900s", got)
+	}
+}