fix: guard widgets against undefined in handleRowCollapse

* fix(querier): return proper HTTP status for PromQL timeout errors

PromQL queries hitting the context deadline were incorrectly returning
400 Bad Request with "invalid_input" because enhancePromQLError
unconditionally wrapped all errors as TypeInvalidInput. Extract
tryEnhancePromQLExecError to properly classify timeout, cancellation,
and storage errors before falling through to parse error handling.

Also make the PromQL engine timeout configurable via prometheus.timeout
config (default 2m) instead of hardcoding it.

* chore: refactor files

* fix(prometheus): validate timeout config and fix test setups

Add validation in prometheus.Config to reject zero timeout. Update all
test files to explicitly set Timeout: 2 * time.Minute in prometheus.Config
literals to avoid immediate query timeouts.

conf/example.yaml

@@ -144,6 +144,8 @@ telemetrystore:
 
 ##################### Prometheus #####################
 prometheus:
+  # The maximum time a PromQL query is allowed to run before being aborted.
+  timeout: 2m
   active_query_tracker:
     # Whether to enable the active query tracker.
     enabled: true

ee/query-service/rules/manager_test.go

@@ -257,7 +257,7 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
 						WillReturnRows(samplesRows)
 
 					// Create Prometheus provider for this test
-					promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, store)
+					promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, store)
 				},
 				ManagerOptionsHook: func(opts *rules.ManagerOptions) {
 					// Set Prometheus provider for PromQL queries

frontend/src/container/GridCardLayout/GridCardLayout.tsx

@@ -337,9 +337,9 @@ function GraphLayout(props: GraphLayoutProps): JSX.Element {
 			for (let j = idxCurrentRow + 1; j < dashboardLayout.length; j++) {
 				updatedDashboardLayout[j].y += maxY;
 				if (updatedPanelMap[updatedDashboardLayout[j].i]) {
-					updatedPanelMap[updatedDashboardLayout[j].i].widgets = updatedPanelMap[
-						updatedDashboardLayout[j].i
-					].widgets.map((w) => ({
+					updatedPanelMap[updatedDashboardLayout[j].i].widgets = (
+						updatedPanelMap[updatedDashboardLayout[j].i].widgets ?? []
+					).map((w) => ({
 						...w,
 						y: w.y + maxY,
 					}));
@@ -376,9 +376,9 @@ function GraphLayout(props: GraphLayoutProps): JSX.Element {
 			for (let j = currentIdx + 1; j < updatedDashboardLayout.length; j++) {
 				updatedDashboardLayout[j].y += maxY;
 				if (updatedPanelMap[updatedDashboardLayout[j].i]) {
-					updatedPanelMap[updatedDashboardLayout[j].i].widgets = updatedPanelMap[
-						updatedDashboardLayout[j].i
-					].widgets.map((w) => ({
+					updatedPanelMap[updatedDashboardLayout[j].i].widgets = (
+						updatedPanelMap[updatedDashboardLayout[j].i].widgets ?? []
+					).map((w) => ({
 						...w,
 						y: w.y + maxY,
 					}));

pkg/prometheus/config.go

@@ -3,6 +3,7 @@ package prometheus
 import (
 	"time"
 
+	"github.com/SigNoz/signoz/pkg/errors"
 	"github.com/SigNoz/signoz/pkg/factory"
 )
 
@@ -20,6 +21,9 @@ type Config struct {
 	//
 	// If not set, the prometheus default is used (currently 5m).
 	LookbackDelta time.Duration `mapstructure:"lookback_delta"`
+
+	// Timeout is the maximum time a query is allowed to run before being aborted.
+	Timeout time.Duration `mapstructure:"timeout"`
 }
 
 func NewConfigFactory() factory.ConfigFactory {
@@ -33,10 +37,14 @@ func newConfig() factory.Config {
 			Path:          "",
 			MaxConcurrent: 20,
 		},
+		Timeout: 2 * time.Minute,
 	}
 }
 
 func (c Config) Validate() error {
+	if c.Timeout <= 0 {
+		return errors.Newf(errors.TypeInvalidInput, errors.CodeInvalidInput, "prometheus::timeout must be greater than 0")
+	}
 	return nil
 }
 

pkg/prometheus/constants.go

@@ -1,3 +0,0 @@
-package prometheus
-
-const FingerprintAsPromLabelName = "fingerprint"

pkg/prometheus/engine.go

@@ -2,7 +2,6 @@ package prometheus
 
 import (
 	"log/slog"
-	"time"
 
 	"github.com/prometheus/prometheus/promql"
 )
@@ -21,7 +20,7 @@ func NewEngine(logger *slog.Logger, cfg Config) *Engine {
 		Logger:             logger,
 		Reg:                nil,
 		MaxSamples:         5_0000_000,
-		Timeout:            2 * time.Minute,
+		Timeout:            cfg.Timeout,
 		ActiveQueryTracker: activeQueryTracker,
 		LookbackDelta:      cfg.LookbackDelta,
 	})

pkg/prometheus/label.go

@@ -6,6 +6,8 @@ import (
 	"github.com/prometheus/prometheus/promql"
 )
 
+const FingerprintAsPromLabelName string = "fingerprint"
+
 func RemoveExtraLabels(res *promql.Result, labelsToRemove ...string) error {
 	if len(labelsToRemove) == 0 || res == nil {
 		return nil

pkg/querier/promql_query.go

@@ -36,6 +36,28 @@ var unquotedDottedNamePattern = regexp.MustCompile(`(?:^|[{,(\s])([a-zA-Z_][a-zA
 // This is a common mistake when migrating to UTF-8 syntax.
 var quotedMetricOutsideBracesPattern = regexp.MustCompile(`"([^"]+)"\s*\{`)
 
+// tryEnhancePromQLExecError attempts to convert a PromQL execution error into
+// a properly typed error. Returns nil if the error is not a recognized execution error.
+func tryEnhancePromQLExecError(execErr error) error {
+	var eqc promql.ErrQueryCanceled
+	var eqt promql.ErrQueryTimeout
+	var es promql.ErrStorage
+	switch {
+	case errors.As(execErr, &eqc):
+		return errors.Newf(errors.TypeCanceled, errors.CodeCanceled, "query canceled").WithAdditional(eqc.Error())
+	case errors.As(execErr, &eqt):
+		return errors.Newf(errors.TypeTimeout, errors.CodeTimeout, "query timed out").WithAdditional(eqt.Error())
+	case errors.Is(execErr, context.DeadlineExceeded):
+		return errors.Newf(errors.TypeTimeout, errors.CodeTimeout, "query timed out")
+	case errors.Is(execErr, context.Canceled):
+		return errors.Newf(errors.TypeCanceled, errors.CodeCanceled, "query canceled")
+	case errors.As(execErr, &es):
+		return errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", execErr)
+	default:
+		return nil
+	}
+}
+
 // enhancePromQLError adds helpful context to PromQL parse errors,
 // particularly for UTF-8 syntax migration issues where metric and label
 // names containing dots need to be quoted.
@@ -213,27 +235,20 @@ func (q *promqlQuery) Execute(ctx context.Context) (*qbv5.Result, error) {
 		time.Unix(0, end),
 		q.query.Step.Duration,
 	)
-
 	if err != nil {
+		// NewRangeQuery can fail with execution errors (e.g. context deadline exceeded)
+		// during the query queue/scheduling stage, not just parse errors.
+		if err := tryEnhancePromQLExecError(err); err != nil {
+			return nil, err
+		}
+
 		return nil, enhancePromQLError(query, err)
 	}
 
 	res := qry.Exec(ctx)
 	if res.Err != nil {
-		var eqc promql.ErrQueryCanceled
-		var eqt promql.ErrQueryTimeout
-		var es promql.ErrStorage
-		switch {
-		case errors.As(res.Err, &eqc):
-			return nil, errors.Newf(errors.TypeCanceled, errors.CodeCanceled, "query canceled")
-		case errors.As(res.Err, &eqt):
-			return nil, errors.Newf(errors.TypeTimeout, errors.CodeTimeout, "query timeout")
-		case errors.As(res.Err, &es):
-			return nil, errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", res.Err)
-		}
-
-		if errors.Is(res.Err, context.Canceled) {
-			return nil, errors.Newf(errors.TypeCanceled, errors.CodeCanceled, "query canceled")
+		if err := tryEnhancePromQLExecError(res.Err); err != nil {
+			return nil, err
 		}
 
 		return nil, errors.Newf(errors.TypeInternal, errors.CodeInternal, "query execution error: %v", res.Err)

pkg/query-service/app/querier/querier_test.go

@@ -1407,7 +1407,7 @@ func Test_querier_Traces_runWindowBasedListQueryDesc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -1633,7 +1633,7 @@ func Test_querier_Traces_runWindowBasedListQueryAsc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -1934,7 +1934,7 @@ func Test_querier_Logs_runWindowBasedListQueryDesc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -2162,7 +2162,7 @@ func Test_querier_Logs_runWindowBasedListQueryAsc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,

pkg/query-service/app/querier/v2/querier_test.go

@@ -1459,7 +1459,7 @@ func Test_querier_Traces_runWindowBasedListQueryDesc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -1685,7 +1685,7 @@ func Test_querier_Traces_runWindowBasedListQueryAsc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -1985,7 +1985,7 @@ func Test_querier_Logs_runWindowBasedListQueryDesc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,
@@ -2213,7 +2213,7 @@ func Test_querier_Logs_runWindowBasedListQueryAsc(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Duration(time.Second),
 				nil,

pkg/query-service/rules/base_rule_test.go

@@ -698,7 +698,7 @@ func TestBaseRule_FilterNewSeries(t *testing.T) {
 				slog.Default(),
 				nil,
 				telemetryStore,
-				prometheustest.New(context.Background(), settings, prometheus.Config{}, telemetryStore),
+				prometheustest.New(context.Background(), settings, prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore),
 				"",
 				time.Second,
 				nil,

pkg/query-service/rules/manager_test.go

@@ -253,7 +253,7 @@ func TestManager_TestNotification_SendUnmatched_PromRule(t *testing.T) {
 						WillReturnRows(samplesRows)
 
 					// Create Prometheus provider for this test
-					promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, store)
+					promProvider = prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, store)
 				},
 				ManagerOptionsHook: func(opts *ManagerOptions) {
 					// Set Prometheus provider for PromQL queries

pkg/query-service/rules/managertestfactory.go

@@ -99,7 +99,7 @@ func NewTestManager(t *testing.T, testOpts *TestManagerOptions) *Manager {
 
 	options := clickhouseReader.NewOptions("", "", "archiveNamespace")
 	providerSettings := instrumentationtest.New().ToProviderSettings()
-	prometheus := prometheustest.New(context.Background(), providerSettings, prometheus.Config{}, telemetryStore)
+	prometheus := prometheustest.New(context.Background(), providerSettings, prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
 	reader := clickhouseReader.NewReader(
 		instrumentationtest.New().Logger(),
 		nil,

pkg/query-service/rules/prom_rule_test.go

@@ -940,7 +940,7 @@ func TestPromRuleUnitCombinations(t *testing.T) {
 			).
 			WillReturnRows(samplesRows)
 
-		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore)
+		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
 
 		postableRule.RuleCondition.CompareOp = ruletypes.CompareOp(c.compareOp)
 		postableRule.RuleCondition.MatchType = ruletypes.MatchType(c.matchType)
@@ -1061,7 +1061,7 @@ func _Enable_this_after_9146_issue_fix_is_merged_TestPromRuleNoData(t *testing.T
 			WithArgs("test_metric", "__name__", "test_metric").
 			WillReturnRows(fingerprintRows)
 
-		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore)
+		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
 
 		var target float64 = 0
 		postableRule.RuleCondition.Thresholds = &ruletypes.RuleThresholdData{
@@ -1281,7 +1281,7 @@ func TestMultipleThresholdPromRule(t *testing.T) {
 			).
 			WillReturnRows(samplesRows)
 
-		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore)
+		promProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
 
 		postableRule.RuleCondition.CompareOp = ruletypes.CompareOp(c.compareOp)
 		postableRule.RuleCondition.MatchType = ruletypes.MatchType(c.matchType)
@@ -1441,7 +1441,7 @@ func TestPromRule_NoData(t *testing.T) {
 			promProvider := prometheustest.New(
 				context.Background(),
 				instrumentationtest.New().ToProviderSettings(),
-				prometheus.Config{},
+				prometheus.Config{Timeout: 2 * time.Minute},
 				telemetryStore,
 			)
 			defer func() {
@@ -1590,7 +1590,7 @@ func TestPromRule_NoData_AbsentFor(t *testing.T) {
 			promProvider := prometheustest.New(
 				context.Background(),
 				instrumentationtest.New().ToProviderSettings(),
-				prometheus.Config{},
+				prometheus.Config{Timeout: 2 * time.Minute},
 				telemetryStore,
 			)
 			defer func() {
@@ -1748,7 +1748,7 @@ func TestPromRuleEval_RequireMinPoints(t *testing.T) {
 			promProvider := prometheustest.New(
 				context.Background(),
 				instrumentationtest.New().ToProviderSettings(),
-				prometheus.Config{LookbackDelta: lookBackDelta},
+				prometheus.Config{Timeout: 2 * time.Minute, LookbackDelta: lookBackDelta},
 				telemetryStore,
 			)
 			defer func() {

pkg/query-service/rules/threshold_rule_test.go

@@ -779,7 +779,7 @@ func TestThresholdRuleUnitCombinations(t *testing.T) {
 			},
 		)
 		require.NoError(t, err)
-		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore), "", time.Duration(time.Second), nil, readerCache, options)
+		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore), "", time.Duration(time.Second), nil, readerCache, options)
 		rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, reader, nil, logger)
 		rule.TemporalityMap = map[string]map[v3.Temporality]bool{
 			"signoz_calls_total": {
@@ -894,7 +894,7 @@ func TestThresholdRuleNoData(t *testing.T) {
 		)
 		assert.NoError(t, err)
 		options := clickhouseReader.NewOptions("", "", "archiveNamespace")
-		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore), "", time.Duration(time.Second), nil, readerCache, options)
+		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore), "", time.Duration(time.Second), nil, readerCache, options)
 
 		rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, reader, nil, logger)
 		rule.TemporalityMap = map[string]map[v3.Temporality]bool{
@@ -1014,7 +1014,7 @@ func TestThresholdRuleTracesLink(t *testing.T) {
 		}
 
 		options := clickhouseReader.NewOptions("", "", "archiveNamespace")
-		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore), "", time.Duration(time.Second), nil, nil, options)
+		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore), "", time.Duration(time.Second), nil, nil, options)
 
 		rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, reader, nil, logger)
 		rule.TemporalityMap = map[string]map[v3.Temporality]bool{
@@ -1151,7 +1151,7 @@ func TestThresholdRuleLogsLink(t *testing.T) {
 		}
 
 		options := clickhouseReader.NewOptions("", "", "archiveNamespace")
-		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore), "", time.Duration(time.Second), nil, nil, options)
+		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore), "", time.Duration(time.Second), nil, nil, options)
 
 		rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, reader, nil, logger)
 		rule.TemporalityMap = map[string]map[v3.Temporality]bool{
@@ -1418,7 +1418,7 @@ func TestMultipleThresholdRule(t *testing.T) {
 			},
 		)
 		require.NoError(t, err)
-		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore), "", time.Second, nil, readerCache, options)
+		reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore), "", time.Second, nil, readerCache, options)
 		rule, err := NewThresholdRule("69", valuer.GenerateUUID(), &postableRule, reader, nil, logger)
 		rule.TemporalityMap = map[string]map[v3.Temporality]bool{
 			"signoz_calls_total": {
@@ -2220,7 +2220,7 @@ func TestThresholdEval_RequireMinPoints(t *testing.T) {
 			)
 			require.NoError(t, err)
 
-			prometheusProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{}, telemetryStore)
+			prometheusProvider := prometheustest.New(context.Background(), instrumentationtest.New().ToProviderSettings(), prometheus.Config{Timeout: 2 * time.Minute}, telemetryStore)
 			reader := clickhouseReader.NewReader(slog.Default(), nil, telemetryStore, prometheusProvider, "", time.Second, nil, readerCache, options)
 
 			rule, err := NewThresholdRule("some-id", valuer.GenerateUUID(), &postableRule, reader, nil, logger)