responses 直通超时可配,流式去总超时,代理补阶段超时

internal/service/aigateway.go

@@ -68,6 +68,9 @@ type AiGatewayService struct {
 	// 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
+	// upstreamWaitSec 是 responses 直通的上游无响应预算(秒):非流式为单次尝试
+	// 总超时,流式为等待响应头预算;multi-agent/搜索类模型远超 SDK 默认 60s
+	upstreamWaitSec atomic.Int64
 }
 
 // NewAiGatewayService 组装依赖;调用 StartCleanup 后开始调用日志周期清理。
@@ -78,6 +81,7 @@ func NewAiGatewayService(db *gorm.DB, configs *OciConfigService, client oci.Clie
 	s.streamGuardKB.Store(int64(loadIntSetting(db, settingAiStreamGuardKB, defaultStreamGuardKB)))
 	s.grokWebSearch.Store(loadBoolSetting(db, settingAiGrokWebSearch, true))
 	s.grokXSearch.Store(loadBoolSetting(db, settingAiGrokXSearch, true))
+	s.upstreamWaitSec.Store(int64(loadIntSetting(db, settingAiUpstreamWaitSec, defaultUpstreamWaitSec)))
 	return s
 }
 
@@ -93,11 +97,17 @@ const (
 	// 开关,缺省开。
 	settingAiGrokWebSearch = "ai_grok_web_search"
 	settingAiGrokXSearch   = "ai_grok_x_search"
+	// settingAiUpstreamWaitSec 是 responses 直通的上游无响应预算(秒)。
+	settingAiUpstreamWaitSec = "ai_upstream_wait_seconds"
 )
 
 // defaultStreamGuardKB 是保险丝阈值缺省值,低于实测断流边界留余量。
 const defaultStreamGuardKB = 60
 
+// defaultUpstreamWaitSec 是上游无响应预算缺省值(秒):multi-agent 非流式
+// 实测 100~180s 才回响应头,给足余量;上下限见 SetUpstreamWait。
+const defaultUpstreamWaitSec = 300
+
 // 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
@@ -165,6 +175,25 @@ func (s *AiGatewayService) SetStreamGuard(ctx context.Context, on bool, kb int)
 	return nil
 }
 
+// UpstreamWait 返回 responses 直通的上游无响应预算。
+func (s *AiGatewayService) UpstreamWait() time.Duration {
+	return time.Duration(s.upstreamWaitSec.Load()) * time.Second
+}
+
+// SetUpstreamWait 持久化并即时生效上游无响应预算;sec 限定 30..900。
+func (s *AiGatewayService) SetUpstreamWait(ctx context.Context, sec int) error {
+	if sec < 30 || sec > 900 {
+		return fmt.Errorf("上游无响应预算须在 30..900 秒, 收到 %d", sec)
+	}
+	err := s.db.WithContext(ctx).
+		Save(&model.Setting{Key: settingAiUpstreamWaitSec, Value: strconv.Itoa(sec)}).Error
+	if err != nil {
+		return fmt.Errorf("保存上游无响应预算: %w", err)
+	}
+	s.upstreamWaitSec.Store(int64(sec))
+	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()

internal/service/aigateway_chat.go

@@ -64,7 +64,7 @@ func (s *AiGatewayService) passthroughOnce(ctx context.Context, cand *aiCandidat
 	if err != nil {
 		return nil, err
 	}
-	return s.client.GenAiCompatResponses(ctx, cred, cand.ch.Region, raw)
+	return s.client.GenAiCompatResponses(ctx, cred, cand.ch.Region, raw, s.UpstreamWait())
 }
 
 // RespPassthroughStream 编排流式直通:流建立成功即绑定渠道,建立失败按 switchable
@@ -83,7 +83,7 @@ func (s *AiGatewayService) RespPassthroughStream(ctx context.Context, raw []byte
 		if err != nil {
 			return nil, meta, err
 		}
-		stream, err := s.client.GenAiCompatResponsesStream(ctx, cred, cand.ch.Region, raw)
+		stream, err := s.client.GenAiCompatResponsesStream(ctx, cred, cand.ch.Region, raw, s.UpstreamWait())
 		if err == nil {
 			s.markSuccess(ctx, cand.ch.ID)
 			return stream, meta, nil

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)
+	}
+}