vmalert: skip a redundant pending state when an alert can be restored to firing

See https://github.com/golang/go/issues?q=milestone%3AGo1.26.6%20label%3ACherryPickApproved

.github/workflows/build.yml

@@ -73,11 +73,19 @@ jobs:
         id: go
         uses: actions/setup-go@4a3601121dd01d1626a1e23e37211e3254c1c06c  # v6.4.0
         with:
-          cache-dependency-path: |
-            go.sum
-            Makefile
-            app/**/Makefile
+          cache: false
           go-version-file: 'go.mod'
+
+      - name: Cache Go build artifacts
+        uses: actions/cache@27d5ce7f107fe9357f9df03efb73ab90386fccae  # v5.0.5
+        with:
+          path: |
+            ~/.cache/go-build
+            ~/go/pkg/mod
+          key: go-build-${{ matrix.os }}-${{ matrix.arch }}-${{ hashFiles('go.sum', 'Makefile') }}
+          restore-keys: |
+            go-build-${{ matrix.os }}-${{ matrix.arch }}-
+
       - run: go version
 
       - name: Build victoria-metrics for ${{ matrix.os }}-${{ matrix.arch }}

README.md

@@ -2,7 +2,6 @@
 
 [![Latest Release](https://img.shields.io/github/v/release/VictoriaMetrics/VictoriaMetrics?sort=semver&label=&filter=!*-victorialogs&logo=github&labelColor=gray&color=gray&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Freleases%2Flatest)](https://github.com/VictoriaMetrics/VictoriaMetrics/releases)
 [![Docker Pulls](https://img.shields.io/docker/pulls/victoriametrics/victoria-metrics?label=&logo=docker&logoColor=white&labelColor=2496ED&color=2496ED&link=https%3A%2F%2Fhub.docker.com%2Fr%2Fvictoriametrics%2Fvictoria-metrics)](https://hub.docker.com/u/victoriametrics)
-[![Go Report](https://goreportcard.com/badge/github.com/VictoriaMetrics/VictoriaMetrics?link=https%3A%2F%2Fgoreportcard.com%2Freport%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics)](https://goreportcard.com/report/github.com/VictoriaMetrics/VictoriaMetrics)
 [![Build Status](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml/badge.svg?branch=master&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Factions)](https://github.com/VictoriaMetrics/VictoriaMetrics/actions/workflows/build.yml)
 [![License](https://img.shields.io/github/license/VictoriaMetrics/VictoriaMetrics?labelColor=green&label=&link=https%3A%2F%2Fgithub.com%2FVictoriaMetrics%2FVictoriaMetrics%2Fblob%2Fmaster%2FLICENSE)](https://github.com/VictoriaMetrics/VictoriaMetrics/blob/master/LICENSE)
 [![Join Slack](https://img.shields.io/badge/Join%20Slack-4A154B?logo=slack)](https://slack.victoriametrics.com)

app/victoria-metrics/main.go

@@ -63,6 +63,7 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 
@@ -170,3 +171,9 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/
 `
 	flagutil.Usage(s)
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	pushmetrics.InitSecretFlags()
+	vmselect.InitSecretFlags()
+}

app/vmagent/main.go

@@ -84,7 +84,7 @@ var (
 	maxLabelNameLen        = flag.Int("maxLabelNameLen", 0, "The maximum length of label names in the accepted time series. Series with longer label name are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_name\"} metric at /metrics page is incremented")
 	maxLabelValueLen       = flag.Int("maxLabelValueLen", 0, "The maximum length of label values in the accepted time series. Series with longer label value are ignored. In this case the vm_rows_ignored_total{reason=\"too_long_label_value\"} metric at /metrics page is incremented")
 
-	enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", false, "Enables multitenancy via HTTP headers. "+
+	enableMultitenancyViaHeaders = flag.Bool("enableMultitenancyViaHeaders", true, "Enables multitenancy via HTTP headers. "+
 		"See https://docs.victoriametrics.com/victoriametrics/vmagent/#multitenancy")
 )
 
@@ -115,7 +115,7 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
-	remotewrite.InitSecretFlags()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 	opentelemetry.Init()
@@ -843,3 +843,9 @@ See the docs at https://docs.victoriametrics.com/victoriametrics/vmagent/ .
 `
 	flagutil.Usage(s)
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	remotewrite.InitSecretFlags()
+	pushmetrics.InitSecretFlags()
+}

app/vmagent/prometheusimport/request_handler_test.go

@@ -52,6 +52,7 @@ func setUp() {
 
 func tearDown() {
 	protoparserutil.StopUnmarshalWorkers()
+	remotewrite.Stop()
 	srv.Close()
 	logger.ResetOutputForTest()
 	tmpDataDir := flag.Lookup("remoteWrite.tmpDataPath").Value.String()

app/vmagent/remotewrite/remotewrite.go

@@ -156,7 +156,8 @@ var maxQueues = cgroup.AvailableCPUs() * 16
 
 const persistentQueueDirname = "persistent-queue"
 
-// InitSecretFlags must be called after flag.Parse and before any logging.
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
 func InitSecretFlags() {
 	if !*showRemoteWriteURL {
 		// remoteWrite.url can contain authentication codes, so hide it at `/metrics` output.
@@ -245,6 +246,8 @@ func Init() {
 	dropDanglingQueues()
 
 	// Start config reloader.
+	configReloaderStopCh = make(chan struct{})
+	configReloaderWG = sync.WaitGroup{}
 	configReloaderWG.Go(func() {
 		for {
 			select {
@@ -331,7 +334,7 @@ func initRemoteWriteCtxs(urls []string) {
 }
 
 var (
-	configReloaderStopCh = make(chan struct{})
+	configReloaderStopCh chan struct{}
 	configReloaderWG     sync.WaitGroup
 )
 

app/vmalert/datasource/client.go

@@ -11,6 +11,7 @@ import (
 	"strings"
 	"time"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/netutil"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promauth"
@@ -267,7 +268,11 @@ func (c *Client) do(req *http.Request) (*http.Response, error) {
 	if resp.StatusCode != http.StatusOK {
 		body, _ := io.ReadAll(resp.Body)
 		_ = resp.Body.Close()
-		return nil, fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body)
+		err = &httpserver.ErrorWithStatusCode{
+			StatusCode: resp.StatusCode,
+			Err:        fmt.Errorf("unexpected response code %d for %s. Response body %s", resp.StatusCode, ru, body),
+		}
+		return nil, err
 	}
 	return resp, nil
 }

app/vmalert/datasource/init.go

@@ -60,7 +60,8 @@ var (
 		`Only valid for VictoriaMetrics as the datasource.`)
 )
 
-// InitSecretFlags must be called after flag.Parse and before any logging
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
 func InitSecretFlags() {
 	if !*showDatasourceURL {
 		flagutil.RegisterSecretFlag("datasource.url")

app/vmalert/main.go

@@ -88,10 +88,7 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
-	remoteread.InitSecretFlags()
-	remotewrite.InitSecretFlags()
-	datasource.InitSecretFlags()
-	notifier.InitSecretFlags()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 
@@ -438,3 +435,12 @@ func getLastConfigError() error {
 	defer lastConfigErrMu.RUnlock()
 	return lastConfigErr
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	remoteread.InitSecretFlags()
+	remotewrite.InitSecretFlags()
+	datasource.InitSecretFlags()
+	notifier.InitSecretFlags()
+	pushmetrics.InitSecretFlags()
+}

app/vmalert/notifier/alert.go

@@ -31,6 +31,8 @@ type Alert struct {
 	State AlertState
 	// Expr contains expression that was executed to generate the Alert
 	Expr string
+	// Interval contains the evaluation interval of the Alert's group
+	Interval time.Duration
 	// ActiveAt defines the moment of time when Alert has become active
 	ActiveAt time.Time
 	// Start defines the moment of time when Alert has become firing
@@ -84,6 +86,7 @@ type AlertTplData struct {
 	Labels    map[string]string
 	Value     float64
 	Expr      string
+	Interval  time.Duration
 	AlertID   uint64
 	GroupID   uint64
 	ActiveAt  time.Time
@@ -96,6 +99,7 @@ var tplHeaders = []string{
 	"{{ $type := .Type }}",
 	"{{ $labels := .Labels }}",
 	"{{ $expr := .Expr }}",
+	"{{ $interval := .Interval }}",
 	"{{ $externalLabels := .ExternalLabels }}",
 	"{{ $externalURL := .ExternalURL }}",
 	"{{ $alertID := .AlertID }}",
@@ -115,6 +119,7 @@ func (a *Alert) ExecTemplate(q templates.QueryFn, labels, annotations map[string
 		Type:     a.Type,
 		Labels:   labels,
 		Expr:     a.Expr,
+		Interval: a.Interval,
 		AlertID:  a.ID,
 		GroupID:  a.GroupID,
 		ActiveAt: a.ActiveAt,

app/vmalert/notifier/alert_test.go

@@ -129,6 +129,17 @@ func TestAlertExecTemplate(t *testing.T) {
 		"exprEscapedHTML":   "vm_rows{"label"="bar"}<0",
 	})
 
+	// interval-template
+	f(&Alert{
+		Interval: 10 * time.Second,
+	}, map[string]string{
+		"interval":         "{{ .Interval }}",
+		"intervalVariable": "{{ $interval }}",
+	}, map[string]string{
+		"interval":         "10s",
+		"intervalVariable": "10s",
+	})
+
 	// query
 	f(&Alert{
 		Expr: `vm_rows{"label"="bar"}>0`,

app/vmalert/notifier/init.go

@@ -189,7 +189,8 @@ func Init(extLabels map[string]string, extURL string) error {
 	return nil
 }
 
-// InitSecretFlags must be called after flag.Parse and before any logging
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
 func InitSecretFlags() {
 	if !*showNotifierURL {
 		flagutil.RegisterSecretFlag("notifier.url")

app/vmalert/remoteread/init.go

@@ -56,7 +56,8 @@ var (
 	oauth2Scopes   = flag.String("remoteRead.oauth2.scopes", "", "Optional OAuth2 scopes to use for -remoteRead.url. Scopes must be delimited by ';'.")
 )
 
-// InitSecretFlags must be called after flag.Parse and before any logging
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
 func InitSecretFlags() {
 	if !*showRemoteReadURL {
 		flagutil.RegisterSecretFlag("remoteRead.url")

app/vmalert/remotewrite/init.go

@@ -57,7 +57,8 @@ var (
 	oauth2Scopes   = flag.String("remoteWrite.oauth2.scopes", "", "Optional OAuth2 scopes to use for -notifier.url. Scopes must be delimited by ';'.")
 )
 
-// InitSecretFlags must be called after flag.Parse and before any logging
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
 func InitSecretFlags() {
 	if !*showRemoteWriteURL {
 		flagutil.RegisterSecretFlag("remoteWrite.url")

app/vmalert/replay.go

@@ -25,11 +25,13 @@ var (
 	replayMaxDatapoints = flag.Int("replay.maxDatapointsPerQuery", 1e3,
 		"Max number of data points expected in one request. It affects the max time range for every '/query_range' request during the replay. The higher the value, the less requests will be made during replay.")
 	replayRuleRetryAttempts = flag.Int("replay.ruleRetryAttempts", 5,
-		"Defines how many retries to make before giving up on rule if request for it returns an error.")
+		"Defines how many retries to make before giving up on rule if request for it returns a retriable error.")
 	disableProgressBar = flag.Bool("replay.disableProgressBar", false, "Whether to disable rendering progress bars during the replay. "+
 		"Progress bar rendering might be verbose or break the logs parsing, so it is recommended to be disabled when not used in interactive mode.")
 	ruleEvaluationConcurrency = flag.Int("replay.ruleEvaluationConcurrency", 1, "The maximum number of concurrent '/query_range' requests when replay recording rule or alerting rule with for=0. "+
 		"Increasing this value when replaying for a long time, since each request is limited by -replay.maxDatapointsPerQuery.")
+	continueWithExecutionErr = flag.Bool("replay.continueWithExecutionErr", false, "Whether to continue replaying other rules if a rule execution fails with a 400 or 422 response code, "+
+		"which can happen due to an expression syntax error or a resource limit being hit.")
 )
 
 func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewrite.RWClient) (totalRows, droppedRows int, err error) {
@@ -73,7 +75,7 @@ func replay(groupsCfg []config.Group, qb datasource.QuerierBuilder, rw remotewri
 
 	for _, cfg := range groupsCfg {
 		ng := rule.NewGroup(cfg, qb, *evaluationInterval, labels)
-		totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency)
+		totalRows += ng.Replay(tFrom, tTo, rw, *replayMaxDatapoints, *replayRuleRetryAttempts, *replayRulesDelay, *disableProgressBar, *ruleEvaluationConcurrency, *continueWithExecutionErr)
 	}
 	logger.Infof("replay evaluation finished, generated %d samples", totalRows)
 	if err := rw.Close(); err != nil {

app/vmalert/replay_test.go

@@ -8,8 +8,10 @@ import (
 
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/config"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/promutil"
+	"github.com/VictoriaMetrics/metricsql"
 )
 
 type fakeReplayQuerier struct {
@@ -32,6 +34,14 @@ func (fc *fakeRWClient) Close() error {
 }
 
 func (fr *fakeReplayQuerier) QueryRange(_ context.Context, q string, from, to time.Time) (res datasource.Result, err error) {
+	_, err = metricsql.Parse(q)
+	if err != nil {
+		return res, &httpserver.ErrorWithStatusCode{
+			StatusCode: 422,
+			Err:        err,
+		}
+	}
+
 	key := fmt.Sprintf("%s+%s", from.Format("15:04:05"), to.Format("15:04:05"))
 	dps, ok := fr.registry[q]
 	if !ok {
@@ -275,4 +285,28 @@ func TestReplay(t *testing.T) {
 			},
 		},
 	}, 10)
+
+	// rule with wrong expression won't break the other rule with continueWithExecutionErr
+	continueWithExecutionErrOld := *continueWithExecutionErr
+	defer func() {
+		*continueWithExecutionErr = continueWithExecutionErrOld
+	}()
+	*continueWithExecutionErr = true
+	f("2021-01-01T12:00:00.000Z", "2021-01-01T12:02:30.000Z", 1, 1, time.Millisecond, []config.Group{
+		{Rules: []config.Rule{{Record: "foo", Expr: "sum(up)"}}},
+		{Rules: []config.Rule{{Record: "bar", Expr: "up ++"}}},
+	}, &fakeReplayQuerier{
+		registry: map[string]map[string][]datasource.Metric{
+			"sum(up)": {
+				"12:00:00+12:01:00": {
+					{
+						Timestamps: []int64{1, 2},
+						Values:     []float64{1, 2},
+					},
+				},
+				"12:01:00+12:02:00": {},
+				"12:02:00+12:02:30": {},
+			},
+		},
+	}, 2)
 }

app/vmalert/rule/alerting.go

@@ -437,7 +437,7 @@ const resolvedRetention = 15 * time.Minute
 
 // exec executes AlertingRule expression via the given Querier.
 // Based on the Querier results AlertingRule maintains notifier.Alerts
-func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]prompb.TimeSeries, error) {
+func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int, getRemoteReadQuerier func(enableDebug bool) datasource.Querier) ([]prompb.TimeSeries, error) {
 	start := time.Now()
 	res, req, err := ar.q.Query(ctx, ar.Expr, ts)
 	curState := StateEntry{
@@ -462,7 +462,11 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 	}
 
 	isPartial := isPartialResponse(res)
-	ar.logDebugf(ts, nil, "query returned %d series (elapsed: %s, isPartial: %t)", curState.Samples, curState.Duration, isPartial)
+	seriesFetched := 0
+	if res.SeriesFetched != nil {
+		seriesFetched = *res.SeriesFetched
+	}
+	ar.logDebugf(ts, nil, "query returned %d series (series_fetched: %d, elapsed: %s, isPartial: %t)", curState.Samples, seriesFetched, curState.Duration, isPartial)
 	qFn := func(query string) ([]datasource.Metric, error) {
 		res, _, err := ar.q.Query(ctx, query, ts)
 		return res.Data, err
@@ -530,6 +534,7 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 				ar.logDebugf(ts, a, "INACTIVE => PENDING")
 			}
 			a.Value = m.Values[0]
+			a.Interval = ar.EvalInterval
 			a.Annotations = annotations
 			a.KeepFiringSince = time.Time{}
 			continue
@@ -541,6 +546,15 @@ func (ar *AlertingRule) exec(ctx context.Context, ts time.Time, limit int) ([]pr
 		ar.alerts[alertID] = a
 		ar.logDebugf(ts, a, "created in state PENDING")
 	}
+	// try to restore alerts state from remoteRead if necessary
+	if getRemoteReadQuerier != nil {
+		rr := getRemoteReadQuerier(ar.Debug)
+		err := ar.restore(ctx, rr, ts)
+		// do not break the current evaluation if restore request fails
+		if err != nil {
+			logger.Errorf("error while restoring ruleState for group %q(file %q) rule %q: %s", ar.GroupName, ar.File, ar.Name, err)
+		}
+	}
 	var numActivePending int
 	var tss []prompb.TimeSeries
 	for h, a := range ar.alerts {
@@ -612,6 +626,7 @@ func (ar *AlertingRule) expandAnnotationTemplates(m datasource.Metric, qFn templ
 		Type:      ar.Type.String(),
 		Labels:    ls.origin,
 		Expr:      ar.Expr,
+		Interval:  ar.EvalInterval,
 		AlertID:   hash(ls.processed),
 		GroupID:   ar.GroupID,
 		ActiveAt:  activeAt,
@@ -673,6 +688,7 @@ func (ar *AlertingRule) newAlert(m datasource.Metric, start time.Time, labels, a
 		Name:        ar.Name,
 		Type:        ar.Type.String(),
 		Expr:        ar.Expr,
+		Interval:    ar.EvalInterval,
 		For:         ar.For,
 		ActiveAt:    start,
 		Value:       m.Values[0],
@@ -792,7 +808,7 @@ func firingAlertStaleTimeSeries(ls map[string]string, timestamp int64) []prompb.
 // restore restores the value of ActiveAt field for active alerts,
 // based on previously written time series `alertForStateMetricName`.
 // Only rules with For > 0 can be restored.
-func (ar *AlertingRule) restore(ctx context.Context, q datasource.Querier, ts time.Time, lookback time.Duration) error {
+func (ar *AlertingRule) restore(ctx context.Context, q datasource.Querier, ts time.Time) error {
 	if ar.For < 1 {
 		return nil
 	}
@@ -818,11 +834,9 @@ func (ar *AlertingRule) restore(ctx context.Context, q datasource.Querier, ts ti
 	}
 	// use `default_rollup()` instead of `last_over_time()` here to accounts for possible staleness markers
 	expr := fmt.Sprintf("default_rollup(%s{%s%s}[%ds])",
-		alertForStateMetricName, nameStr, labelsFilter, int(lookback.Seconds()))
+		alertForStateMetricName, nameStr, labelsFilter, int(remoteReadLookBack.Seconds()))
 
-	// query ALERTS_FOR_STATE at `ts-1s` instead `ts` to avoid retrieving data written in the current run,
-	// see https://github.com/VictoriaMetrics/VictoriaMetrics/issues/10335
-	res, _, err := q.Query(ctx, expr, ts.Add(-1*time.Second))
+	res, _, err := q.Query(ctx, expr, ts)
 	if err != nil {
 		return fmt.Errorf("failed to execute restore query %q: %w ", expr, err)
 	}
@@ -832,9 +846,6 @@ func (ar *AlertingRule) restore(ctx context.Context, q datasource.Querier, ts ti
 		return nil
 	}
 
-	ar.alertsMu.Lock()
-	defer ar.alertsMu.Unlock()
-
 	for _, series := range res.Data {
 		series.DelLabel("__name__")
 		labelSet := make(map[string]string, len(series.Labels))

app/vmalert/rule/alerting_synctest_test.go

@@ -44,7 +44,7 @@ func TestAlertingRule_ActiveAtPreservedInAnnotations(t *testing.T) {
 
 		// First execution - creates new alert
 		ts1 := time.Now()
-		_, err := ar.exec(context.TODO(), ts1, 0)
+		_, err := ar.exec(context.TODO(), ts1, 0, nil)
 		if err != nil {
 			t.Fatalf("unexpected error on first exec: %s", err)
 		}
@@ -71,7 +71,7 @@ func TestAlertingRule_ActiveAtPreservedInAnnotations(t *testing.T) {
 		// sleep is non-blocking thanks to synctest
 		time.Sleep(2 * time.Second)
 		ts2 := time.Now()
-		_, err = ar.exec(context.TODO(), ts2, 0)
+		_, err = ar.exec(context.TODO(), ts2, 0, nil)
 		if err != nil {
 			t.Fatalf("unexpected error on second exec: %s", err)
 		}

app/vmalert/rule/alerting_test.go

@@ -229,7 +229,7 @@ func TestAlertingRule_Exec(t *testing.T) {
 		for i, step := range steps {
 			fq.Reset()
 			fq.Add(step...)
-			tss, err := rule.exec(context.TODO(), ts, 0)
+			tss, err := rule.exec(context.TODO(), ts, 0, nil)
 			if err != nil {
 				t.Fatalf("unexpected error: %s", err)
 			}
@@ -662,6 +662,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
 			GroupID:     fakeGroup.GetID(),
 			Name:        "for-pending",
 			Type:        config.NewPrometheusType().String(),
+			Interval:    time.Second,
 			Labels:      map[string]string{"alertname": "for-pending"},
 			Annotations: map[string]string{},
 			State:       notifier.StatePending,
@@ -682,6 +683,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
 			GroupID:     fakeGroup.GetID(),
 			Name:        "for-firing",
 			Type:        config.NewPrometheusType().String(),
+			Interval:    3 * time.Second,
 			Labels:      map[string]string{"alertname": "for-firing"},
 			Annotations: map[string]string{},
 			State:       notifier.StateFiring,
@@ -703,6 +705,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
 			GroupID:     fakeGroup.GetID(),
 			Name:        "for-hold-pending",
 			Type:        config.NewPrometheusType().String(),
+			Interval:    time.Second,
 			Labels:      map[string]string{"alertname": "for-hold-pending"},
 			Annotations: map[string]string{},
 			State:       notifier.StatePending,
@@ -759,6 +762,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
 			GroupID:     fakeGroup.GetID(),
 			Name:        "multi-series",
 			Type:        config.NewPrometheusType().String(),
+			Interval:    3 * time.Second,
 			Labels:      map[string]string{"alertname": "multi-series"},
 			Annotations: map[string]string{},
 			State:       notifier.StateFiring,
@@ -771,6 +775,7 @@ func TestAlertingRuleExecRange(t *testing.T) {
 			GroupID:     fakeGroup.GetID(),
 			Name:        "multi-series",
 			Type:        config.NewPrometheusType().String(),
+			Interval:    3 * time.Second,
 			Labels:      map[string]string{"alertname": "multi-series", "foo": "bar"},
 			Annotations: map[string]string{},
 			State:       notifier.StatePending,
@@ -819,10 +824,11 @@ func TestAlertingRuleExecRange(t *testing.T) {
 func TestGroup_Restore(t *testing.T) {
 	defaultTS := time.Now()
 	fqr := &datasource.FakeQuerierWithRegistry{}
-	fn := func(rules []config.Rule, expAlerts map[uint64]*notifier.Alert) {
+	f := func(rules []config.Rule, expAlerts map[uint64]*notifier.Alert, expNotificationNum int) {
 		t.Helper()
 		defer fqr.Reset()
-
+		fn, cleanup := notifier.InitFakeNotifier()
+		defer cleanup()
 		fg := NewGroup(config.Group{Name: "TestRestore", Rules: rules}, fqr, time.Second, nil)
 		fg.Init()
 		wg := sync.WaitGroup{}
@@ -852,8 +858,8 @@ func TestGroup_Restore(t *testing.T) {
 			if !ok {
 				t.Fatalf("expected to have key %d", key)
 			}
-			if got.State != notifier.StatePending {
-				t.Fatalf("expected state %d; got %d", notifier.StatePending, got.State)
+			if got.State != exp.State {
+				t.Fatalf("expected state %d; got %d", exp.State, got.State)
 			}
 			if got.ActiveAt != exp.ActiveAt {
 				t.Fatalf("expected ActiveAt %v; got %v", exp.ActiveAt, got.ActiveAt)
@@ -862,6 +868,9 @@ func TestGroup_Restore(t *testing.T) {
 				t.Fatalf("expected alertname %q; got %q", exp.Name, got.Name)
 			}
 		}
+		if fn.GetCounter() != expNotificationNum {
+			t.Fatalf("expected %d notifications; got %d", expNotificationNum, fn.GetCounter())
+		}
 	}
 
 	stateMetric := func(name string, value time.Time, labels ...string) datasource.Metric {
@@ -873,28 +882,30 @@ func TestGroup_Restore(t *testing.T) {
 
 	// one active alert, no previous state
 	fqr.Set("foo", metricWithValueAndLabels(t, 0, "__name__", "foo"))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "foo",
 				ActiveAt: defaultTS,
+				State:    notifier.StatePending,
 			},
-		})
+		}, 0)
 
 	// one active alert with state restore
 	ts := time.Now().Truncate(time.Hour)
 	fqr.Set("foo", metricWithValueAndLabels(t, 0, "__name__", "foo"))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
 		stateMetric("foo", ts))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "foo",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
-		})
+		}, 1)
 
 	// one rule, two active alerts, one with state restored
 	ts = time.Now().Truncate(time.Hour)
@@ -904,7 +915,7 @@ func TestGroup_Restore(t *testing.T) {
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo"}[3600s])`,
 		// only env=prod has state metric, so only it will have state restore
 		stateMetric("foo", ts, "env", "prod"))
-	fn(
+	f(
 		[]config.Rule{
 			{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)},
 		},
@@ -912,12 +923,14 @@ func TestGroup_Restore(t *testing.T) {
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
 				Name:     "foo",
 				ActiveAt: defaultTS,
+				State:    notifier.StatePending,
 			},
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "prod"}): {
 				Name:     "foo",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
-		})
+		}, 1)
 
 	// two rules, two active alerts, one with state restored
 	ts = time.Now().Truncate(time.Hour)
@@ -925,7 +938,7 @@ func TestGroup_Restore(t *testing.T) {
 	fqr.Set("bar", metricWithValueAndLabels(t, 0, "__name__", "bar"))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
 		stateMetric("bar", ts))
-	fn(
+	f(
 		[]config.Rule{
 			{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)},
 			{Alert: "bar", Expr: "bar", For: promutil.NewDuration(time.Second)},
@@ -934,12 +947,14 @@ func TestGroup_Restore(t *testing.T) {
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "foo",
 				ActiveAt: defaultTS,
+				State:    notifier.StatePending,
 			},
 			hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "bar",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
-		})
+		}, 1)
 
 	// two rules, two active alerts, two with state restored
 	ts = time.Now().Truncate(time.Hour)
@@ -949,63 +964,68 @@ func TestGroup_Restore(t *testing.T) {
 		stateMetric("foo", ts))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="bar"}[3600s])`,
 		stateMetric("bar", ts))
-	fn(
+	f(
 		[]config.Rule{
 			{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)},
-			{Alert: "bar", Expr: "bar", For: promutil.NewDuration(time.Second)},
+			{Alert: "bar", Expr: "bar", For: promutil.NewDuration(time.Hour)},
 		},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "foo",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
 			hash(map[string]string{alertNameLabel: "bar", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "bar",
 				ActiveAt: ts,
+				State:    notifier.StatePending,
 			},
-		})
+		}, 1)
 
 	// one active alert but wrong state restore
 	ts = time.Now().Truncate(time.Hour)
 	fqr.Set("foo", metricWithValueAndLabels(t, 0, "__name__", "foo"))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertname="bar",alertgroup="TestRestore"}[3600s])`,
 		stateMetric("wrong alert", ts))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore"}): {
 				Name:     "foo",
 				ActiveAt: defaultTS,
+				State:    notifier.StatePending,
 			},
-		})
+		}, 0)
 
 	// one active alert with labels
 	ts = time.Now().Truncate(time.Hour)
 	fqr.Set("foo", metricWithValueAndLabels(t, 0, "__name__", "foo"))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
 		stateMetric("foo", ts, "env", "dev"))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
 				Name:     "foo",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
-		})
+		}, 1)
 
 	// one active alert with restore labels mismatch
 	ts = time.Now().Truncate(time.Hour)
 	fqr.Set("foo", metricWithValueAndLabels(t, 0, "__name__", "foo"))
 	fqr.Set(`default_rollup(ALERTS_FOR_STATE{alertgroup="TestRestore",alertname="foo",env="dev"}[3600s])`,
 		stateMetric("foo", ts, "env", "dev", "team", "foo"))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "dev"}, For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
 				Name:     "foo",
 				ActiveAt: defaultTS,
+				State:    notifier.StatePending,
 			},
-		})
+		}, 0)
 
 	// two active alerts with dynamic labels and restore
 	ts = time.Now().Truncate(time.Hour)
@@ -1015,18 +1035,20 @@ func TestGroup_Restore(t *testing.T) {
 	fqr.Set("foo",
 		metricWithValueAndLabels(t, 0, "__name__", "foo", "env", "dev"),
 		metricWithValueAndLabels(t, 0, "__name__", "foo", "env", "prod"))
-	fn(
+	f(
 		[]config.Rule{{Alert: "foo", Expr: "foo", Labels: map[string]string{"env": "{{$labels.env}}"}, For: promutil.NewDuration(time.Second)}},
 		map[uint64]*notifier.Alert{
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "dev"}): {
 				Name:     "foo",
 				ActiveAt: ts,
+				State:    notifier.StateFiring,
 			},
 			hash(map[string]string{alertNameLabel: "foo", alertGroupNameLabel: "TestRestore", "env": "prod"}): {
 				Name:     "foo",
 				ActiveAt: ts.Add(time.Second),
+				State:    notifier.StateFiring,
 			},
-		})
+		}, 2)
 }
 
 func TestAlertingRule_Exec_Negative(t *testing.T) {
@@ -1039,14 +1061,14 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 	// label `job` will be overridden by rule extra label, the original value will be reserved by "exported_job"
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "baz"))
-	_, err := ar.exec(context.TODO(), time.Now(), 0)
+	_, err := ar.exec(context.TODO(), time.Now(), 0, nil)
 	if err != nil {
 		t.Fatal(err)
 	}
 
 	// label `__name__` will be omitted and get duplicated results here
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo_1", "job", "bar"))
-	_, err = ar.exec(context.TODO(), time.Now(), 0)
+	_, err = ar.exec(context.TODO(), time.Now(), 0, nil)
 	if !errors.Is(err, errDuplicate) {
 		t.Fatalf("expected to have %s error; got %s", errDuplicate, err)
 	}
@@ -1055,7 +1077,7 @@ func TestAlertingRule_Exec_Negative(t *testing.T) {
 
 	expErr := "connection reset by peer"
 	fq.SetErr(errors.New(expErr))
-	_, err = ar.exec(context.TODO(), time.Now(), 0)
+	_, err = ar.exec(context.TODO(), time.Now(), 0, nil)
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}
@@ -1078,7 +1100,7 @@ func TestAlertingRuleLimit_Failure(t *testing.T) {
 		fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "bar", "job"))
 
 		timestamp := time.Now()
-		_, err := ar.exec(context.TODO(), timestamp, limit)
+		_, err := ar.exec(context.TODO(), timestamp, limit, nil)
 		if err == nil {
 			t.Fatalf("expecting non-nil error")
 		}
@@ -1106,7 +1128,7 @@ func TestAlertingRuleLimit_Success(t *testing.T) {
 		fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "bar", "job"))
 
 		timestamp := time.Now()
-		_, err := ar.exec(context.TODO(), timestamp, limit)
+		_, err := ar.exec(context.TODO(), timestamp, limit, nil)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
@@ -1134,7 +1156,8 @@ func TestAlertingRule_Template(t *testing.T) {
 		fq.Add(metrics...)
 		fq.SetPartialResponse(isResponsePartial)
 
-		if _, err := rule.exec(context.TODO(), time.Now(), 0); err != nil {
+		ts := time.Unix(3600, 0)
+		if _, err := rule.exec(context.TODO(), ts, 0, nil); err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
 		for hash, expAlert := range alertsExpected {
@@ -1152,12 +1175,14 @@ func TestAlertingRule_Template(t *testing.T) {
 	}
 
 	f(&AlertingRule{
-		Name: "common",
+		Name:         "common",
+		EvalInterval: time.Hour,
 		Labels: map[string]string{
 			"region": "east",
 		},
 		Annotations: map[string]string{
-			"summary": `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
+			"summary":   `{{ $labels.alertname }}: Too high connection number for "{{ $labels.instance }}"`,
+			"dashboard": `&from={{ ($activeAt.Add (parseDurationTime (printf "-%s" .Interval))).UnixMilli }}&to={{ $activeAt.UnixMilli }}`,
 		},
 		alerts: make(map[uint64]*notifier.Alert),
 	}, []datasource.Metric{
@@ -1166,7 +1191,8 @@ func TestAlertingRule_Template(t *testing.T) {
 	}, false, map[uint64]*notifier.Alert{
 		hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "foo"}): {
 			Annotations: map[string]string{
-				"summary": `common: Too high connection number for "foo"`,
+				"summary":   `common: Too high connection number for "foo"`,
+				"dashboard": "&from=0&to=3600000",
 			},
 			Labels: map[string]string{
 				alertNameLabel: "common",
@@ -1176,7 +1202,8 @@ func TestAlertingRule_Template(t *testing.T) {
 		},
 		hash(map[string]string{alertNameLabel: "common", "region": "east", "instance": "bar"}): {
 			Annotations: map[string]string{
-				"summary": `common: Too high connection number for "bar"`,
+				"summary":   `common: Too high connection number for "bar"`,
+				"dashboard": "&from=0&to=3600000",
 			},
 			Labels: map[string]string{
 				alertNameLabel: "common",
@@ -1388,7 +1415,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
 		"alertname":     "ConfigurationReloadFailure",
 		"alertgroup":    "vmalert",
 		"pod":           "vmalert-0",
-		"invalid_label": `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
+		"invalid_label": `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
 	}
 
 	expectedProcessedLabels := map[string]string{
@@ -1398,7 +1425,7 @@ func TestAlertingRule_ToLabels(t *testing.T) {
 		"exported_alertname": "ConfigurationReloadFailure",
 		"group":              "vmalert",
 		"alertgroup":         "vmalert",
-		"invalid_label":      `error evaluating template: template: :1:298: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
+		"invalid_label":      `error evaluating template: template: :1:326: executing "" at <.Values.mustRuntimeFail>: can't evaluate field Values in type notifier.tplData`,
 	}
 
 	ls, err := ar.toLabels(metric, nil)
@@ -1429,7 +1456,7 @@ func TestAlertingRuleExec_Partial(t *testing.T) {
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "bar"))
 
 	ts := time.Now()
-	_, err := ar.exec(context.TODO(), ts, 0)
+	_, err := ar.exec(context.TODO(), ts, 0, nil)
 	if err != nil {
 		t.Fatalf("unexpected error: %s", err)
 	}
@@ -1461,7 +1488,7 @@ func TestAlertingRule_QueryTemplateInLabels(t *testing.T) {
 	fq.Add(metricWithValueAndLabels(t, 1, "device", "sda1"))
 
 	ts := time.Now()
-	_, err := ar.exec(context.TODO(), ts, 0)
+	_, err := ar.exec(context.TODO(), ts, 0, nil)
 	if err != nil {
 		t.Fatalf("unexpected error with query template in labels: %s", err)
 	}

app/vmalert/rule/group.go

@@ -222,29 +222,6 @@ func (g *Group) CreateID() uint64 {
 	return hash.Sum64()
 }
 
-// restore restores alerts state for group rules
-func (g *Group) restore(ctx context.Context, qb datasource.QuerierBuilder, ts time.Time, lookback time.Duration) error {
-	for _, rule := range g.Rules {
-		ar, ok := rule.(*AlertingRule)
-		if !ok {
-			continue
-		}
-		if ar.For < 1 {
-			continue
-		}
-		q := qb.BuildWithParams(datasource.QuerierParams{
-			EvaluationInterval: g.Interval,
-			QueryParams:        g.Params,
-			Headers:            g.Headers,
-			Debug:              ar.Debug,
-		})
-		if err := ar.restore(ctx, q, ts, lookback); err != nil {
-			return fmt.Errorf("error while restoring rule %q: %w", rule, err)
-		}
-	}
-	return nil
-}
-
 // updateWith updates existing group with
 // passed group object. This function ignores group
 // evaluation interval change. It supposed to be updated
@@ -290,6 +267,8 @@ func (g *Group) updateWith(newGroup *Group) error {
 	g.Headers = newGroup.Headers
 	g.NotifierHeaders = newGroup.NotifierHeaders
 	g.Labels = newGroup.Labels
+	g.EvalDelay = newGroup.EvalDelay
+	g.evalAlignment = newGroup.evalAlignment
 	g.Limit = newGroup.Limit
 	g.checksum = newGroup.checksum
 	g.Rules = newRules
@@ -337,7 +316,7 @@ func (g *Group) Init() {
 		i := g.Interval.Seconds()
 		return i
 	})
-	g.metrics.iterationLimit = g.metrics.set.NewGauge(fmt.Sprintf(`vmalert_rule_group_results_limit{%s}`, labels), func() float64 {
+	g.metrics.iterationLimit = g.metrics.set.NewGauge(fmt.Sprintf(`vmalert_group_rule_results_limit{%s}`, labels), func() float64 {
 		g.mu.RLock()
 		limit := g.Limit
 		g.mu.RUnlock()
@@ -373,7 +352,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 				g.mu.Lock()
 				err := g.updateWith(ng)
 				if err != nil {
-					logger.Errorf("group %q: failed to update: %s", g.Name, err)
+					logger.Errorf("group %q (file=%q): failed to update: %s", g.Name, g.File, err)
 					g.mu.Unlock()
 					continue
 				}
@@ -393,7 +372,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 
 	g.infof("started")
 
-	eval := func(ctx context.Context, ts time.Time) time.Time {
+	eval := func(ctx context.Context, ts time.Time, getRemoteReadQuerier func(enableDebug bool) datasource.Querier) {
 		g.metrics.iterationTotal.Inc()
 
 		start := time.Now()
@@ -403,23 +382,22 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 			g.mu.Lock()
 			g.LastEvaluation = start
 			g.mu.Unlock()
-			return ts
+			return
 		}
 
 		resolveDuration := getResolveDuration(g.Interval, *resendDelay, *maxResolveDuration)
 		// adjust request timestamp using evalDelay and evalAlignment if necessary
 		ts = g.adjustReqTimestamp(ts)
-		errs := e.execConcurrently(ctx, g.Rules, ts, g.Concurrency, resolveDuration, g.Limit)
+		errs := e.execConcurrently(ctx, g.Rules, ts, g.Concurrency, resolveDuration, g.Limit, getRemoteReadQuerier)
 		for err := range errs {
 			if err != nil {
-				logger.Errorf("group %q: %s", g.Name, err)
+				logger.Errorf("group %q (file=%q): %s", g.Name, g.File, err)
 			}
 		}
 		g.metrics.iterationDuration.UpdateDuration(start)
 		g.mu.Lock()
 		g.LastEvaluation = start
 		g.mu.Unlock()
-		return ts
 	}
 
 	evalCtx, cancel := context.WithCancel(ctx)
@@ -434,24 +412,27 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 	t := time.NewTicker(g.Interval)
 	defer t.Stop()
 
-	realEvalTS := eval(evalCtx, evalTS)
-
-	// restore the rules state after the first evaluation
-	// so only active alerts can be restored.
+	var getRemoteReadQuerier func(enableDebug bool) datasource.Querier
 	if rr != nil {
-		err := g.restore(ctx, rr, realEvalTS, *remoteReadLookBack)
-		if err != nil {
-			logger.Errorf("error while restoring ruleState for group %q: %s", g.Name, err)
+		getRemoteReadQuerier = func(enableDebug bool) datasource.Querier {
+			return rr.BuildWithParams(datasource.QuerierParams{
+				EvaluationInterval: g.Interval,
+				QueryParams:        g.Params,
+				Headers:            g.Headers,
+				Debug:              enableDebug,
+			})
 		}
 	}
+	// pass getRemoteReadQuerier to the first evaluation, so it can be used for restoring alert states
+	eval(evalCtx, evalTS, getRemoteReadQuerier)
 
 	for {
 		select {
 		case <-ctx.Done():
-			logger.Infof("group %q: context cancelled", g.Name)
+			logger.Infof("group %q (file=%q): context cancelled", g.Name, g.File)
 			return
 		case <-g.doneCh:
-			logger.Infof("group %q: received stop signal", g.Name)
+			logger.Infof("group %q (file=%q): received stop signal", g.Name, g.File)
 			return
 		case ng := <-g.updateCh:
 			g.mu.Lock()
@@ -465,7 +446,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 
 			err := g.updateWith(ng)
 			if err != nil {
-				logger.Errorf("group %q: failed to update: %s", g.Name, err)
+				logger.Errorf("group %q (file=%q): failed to update: %s", g.Name, g.File, err)
 				g.mu.Unlock()
 				continue
 			}
@@ -494,7 +475,7 @@ func (g *Group) Start(ctx context.Context, rw remotewrite.RWClient, rr datasourc
 				g.metrics.iterationMissed.Inc()
 			}
 
-			eval(evalCtx, evalTS)
+			eval(evalCtx, evalTS, nil)
 		}
 	}
 }
@@ -543,12 +524,12 @@ func (g *Group) delayBeforeStart(ts time.Time, maxDelay time.Duration) time.Dura
 
 func (g *Group) infof(format string, args ...any) {
 	msg := fmt.Sprintf(format, args...)
-	logger.Infof("group %q %s; interval=%v; eval_offset=%v; concurrency=%d",
-		g.Name, msg, g.Interval, g.EvalOffset, g.Concurrency)
+	logger.Infof("group %q (file=%q; interval=%v; eval_offset=%v; concurrency=%d) %s",
+		g.Name, g.File, g.Interval, g.EvalOffset, g.Concurrency, msg)
 }
 
 // Replay performs group replay
-func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int) int {
+func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoint, replayRuleRetryAttempts int, replayDelay time.Duration, disableProgressBar bool, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
 	var total int
 	step := g.Interval * time.Duration(maxDataPoint)
 	ri := rangeIterator{start: start, end: end, step: step}
@@ -576,7 +557,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
 			if !disableProgressBar {
 				bar = pb.StartNew(iterations)
 			}
-			total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
+			total += replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
 			if bar != nil {
 				bar.Finish()
 			}
@@ -598,7 +579,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
 		rule := g.Rules[i]
 		sem <- struct{}{}
 		wg.Go(func() {
-			res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency)
+			res <- replayRuleRange(rule, ri, bar, rw, replayRuleRetryAttempts, ruleEvaluationConcurrency, continueWithExecutionErr)
 			<-sem
 		})
 	}
@@ -618,7 +599,7 @@ func (g *Group) Replay(start, end time.Time, rw remotewrite.RWClient, maxDataPoi
 	return total
 }
 
-func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int) int {
+func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewrite.RWClient, replayRuleRetryAttempts, ruleEvaluationConcurrency int, continueWithExecutionErr bool) int {
 	fmt.Printf("> Rule %q (ID: %d)\n", r, r.ID())
 	// alerting rule with for>0 can't be replayed concurrently, since the status change might depend on the previous evaluation
 	// see https://github.com/VictoriaMetrics/VictoriaMetrics/commit/abcb21aa5ee918ba9a4e9cde495dba06e1e9564c
@@ -633,7 +614,7 @@ func replayRuleRange(r Rule, ri rangeIterator, bar *pb.ProgressBar, rw remotewri
 		start := ri.s
 		end := ri.e
 		wg.Go(func() {
-			n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts)
+			n, err := replayRule(r, start, end, rw, replayRuleRetryAttempts, continueWithExecutionErr)
 			if err != nil {
 				logger.Fatalf("rule %q: %s", r, err)
 			}
@@ -665,7 +646,7 @@ func (g *Group) ExecOnce(ctx context.Context, rw remotewrite.RWClient, evalTS ti
 		return nil
 	}
 	resolveDuration := getResolveDuration(g.Interval, *resendDelay, *maxResolveDuration)
-	return e.execConcurrently(ctx, g.Rules, evalTS, g.Concurrency, resolveDuration, g.Limit)
+	return e.execConcurrently(ctx, g.Rules, evalTS, g.Concurrency, resolveDuration, g.Limit, nil)
 }
 
 type rangeIterator struct {
@@ -739,12 +720,12 @@ type executor struct {
 }
 
 // execConcurrently executes rules concurrently if concurrency>1
-func (e *executor) execConcurrently(ctx context.Context, rules []Rule, ts time.Time, concurrency int, resolveDuration time.Duration, limit int) chan error {
+func (e *executor) execConcurrently(ctx context.Context, rules []Rule, ts time.Time, concurrency int, resolveDuration time.Duration, limit int, getRemoteReadQuerier func(enableDebug bool) datasource.Querier) chan error {
 	res := make(chan error, len(rules))
 	if concurrency == 1 {
 		// fast path
 		for _, rule := range rules {
-			res <- e.exec(ctx, rule, ts, resolveDuration, limit)
+			res <- e.exec(ctx, rule, ts, resolveDuration, limit, getRemoteReadQuerier)
 		}
 		close(res)
 		return res
@@ -757,7 +738,7 @@ func (e *executor) execConcurrently(ctx context.Context, rules []Rule, ts time.T
 			rule := rules[i]
 			sem <- struct{}{}
 			wg.Go(func() {
-				res <- e.exec(ctx, rule, ts, resolveDuration, limit)
+				res <- e.exec(ctx, rule, ts, resolveDuration, limit, getRemoteReadQuerier)
 				<-sem
 			})
 		}
@@ -774,10 +755,10 @@ var (
 	execErrors = metrics.NewCounter(`vmalert_execution_errors_total`)
 )
 
-func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDuration time.Duration, limit int) error {
+func (e *executor) exec(ctx context.Context, r Rule, ts time.Time, resolveDuration time.Duration, limit int, getRemoteReadQuerier func(enableDebug bool) datasource.Querier) error {
 	execTotal.Inc()
 
-	tss, err := r.exec(ctx, ts, limit)
+	tss, err := r.exec(ctx, ts, limit, getRemoteReadQuerier)
 	if err != nil {
 		if errors.Is(err, context.Canceled) {
 			// the context can be cancelled on graceful shutdown

app/vmalert/rule/group_test.go

@@ -78,6 +78,12 @@ func TestUpdateWith(t *testing.T) {
 		if g.Debug != expect.Debug {
 			t.Fatalf("expected to have debug %v; got %v", expect.Debug, g.Debug)
 		}
+		if !durationPtrEqual(g.EvalDelay, expect.EvalDelay) {
+			t.Fatalf("expected to have eval_delay %v; got %v", expect.EvalDelay, g.EvalDelay)
+		}
+		if !boolPtrEqual(g.evalAlignment, expect.evalAlignment) {
+			t.Fatalf("expected to have eval_alignment %v; got %v", expect.evalAlignment, g.evalAlignment)
+		}
 	}
 
 	// new rule
@@ -237,6 +243,37 @@ func TestUpdateWith(t *testing.T) {
 			{Alert: "foo1", Debug: &debug},
 		},
 	})
+
+	// update group evaluation settings
+	evalDelay := promutil.NewDuration(time.Minute)
+	evalAlignment := false
+	f(config.Group{
+		Rules: []config.Rule{{
+			Record: "foo",
+			Expr:   "max(up)",
+		}},
+	}, config.Group{
+		EvalDelay:     evalDelay,
+		EvalAlignment: &evalAlignment,
+		Rules: []config.Rule{{
+			Record: "foo",
+			Expr:   "min(up)",
+		}},
+	})
+}
+
+func durationPtrEqual(a, b *time.Duration) bool {
+	if a == nil || b == nil {
+		return a == b
+	}
+	return *a == *b
+}
+
+func boolPtrEqual(a, b *bool) bool {
+	if a == nil || b == nil {
+		return a == b
+	}
+	return *a == *b
 }
 
 func TestUpdateDuringRandSleep(t *testing.T) {
@@ -484,7 +521,7 @@ func TestFaultyNotifier(t *testing.T) {
 	defer cancel()
 
 	go func() {
-		_ = e.exec(ctx, r, time.Now(), 0, 10)
+		_ = e.exec(ctx, r, time.Now(), 0, 10, nil)
 	}()
 
 	tn := time.Now()
@@ -516,7 +553,7 @@ func TestFaultyRW(t *testing.T) {
 		Rw: &remotewrite.Client{},
 	}
 
-	err := e.exec(context.Background(), r, time.Now(), 0, 10)
+	err := e.exec(context.Background(), r, time.Now(), 0, 10, nil)
 	if err == nil {
 		t.Fatalf("expected to get an error from faulty RW client, got nil instead")
 	}

app/vmalert/rule/recording.go

@@ -184,7 +184,7 @@ func (rr *RecordingRule) execRange(ctx context.Context, start, end time.Time) ([
 }
 
 // exec executes RecordingRule expression via the given Querier.
-func (rr *RecordingRule) exec(ctx context.Context, ts time.Time, limit int) ([]prompb.TimeSeries, error) {
+func (rr *RecordingRule) exec(ctx context.Context, ts time.Time, limit int, _ func(enableDebug bool) datasource.Querier) ([]prompb.TimeSeries, error) {
 	start := time.Now()
 	res, req, err := rr.q.Query(ctx, rr.Expr, ts)
 	curState := StateEntry{
@@ -208,7 +208,11 @@ func (rr *RecordingRule) exec(ctx context.Context, ts time.Time, limit int) ([]p
 		return nil, curState.Err
 	}
 
-	rr.logDebugf(ts, "query returned %d samples (elapsed: %s, isPartial: %t)", curState.Samples, curState.Duration, isPartialResponse(res))
+	seriesFetched := 0
+	if res.SeriesFetched != nil {
+		seriesFetched = *res.SeriesFetched
+	}
+	rr.logDebugf(ts, "query returned %d samples (series_fetched: %d, elapsed: %s, isPartial: %t)", curState.Samples, seriesFetched, curState.Duration, isPartialResponse(res))
 
 	qMetrics := res.Data
 	numSeries := len(qMetrics)

app/vmalert/rule/recording_test.go

@@ -52,7 +52,7 @@ func TestRecordingRule_Exec(t *testing.T) {
 			rule.state = &ruleState{
 				entries: make([]StateEntry, 10),
 			}
-			tss, err := rule.exec(context.TODO(), ts, 0)
+			tss, err := rule.exec(context.TODO(), ts, 0, nil)
 			if err != nil {
 				t.Fatalf("fail to test rule %s: unexpected error: %s", rule.Name, err)
 			}
@@ -358,7 +358,7 @@ func TestRecordingRuleLimit_Failure(t *testing.T) {
 		}
 		rule.q = fq
 
-		_, err := rule.exec(context.TODO(), time.Now(), limit)
+		_, err := rule.exec(context.TODO(), time.Now(), limit, nil)
 		if err == nil {
 			t.Fatalf("expecting non-nil error")
 		}
@@ -394,7 +394,7 @@ func TestRecordingRuleLimit_Success(t *testing.T) {
 		}
 		rule.q = fq
 
-		_, err := rule.exec(context.TODO(), time.Now(), limit)
+		_, err := rule.exec(context.TODO(), time.Now(), limit, nil)
 		if err != nil {
 			t.Fatalf("unexpected error: %s", err)
 		}
@@ -422,7 +422,7 @@ func TestRecordingRuleExec_Negative(t *testing.T) {
 	expErr := "connection reset by peer"
 	fq.SetErr(errors.New(expErr))
 	rr.q = fq
-	_, err := rr.exec(context.TODO(), time.Now(), 0)
+	_, err := rr.exec(context.TODO(), time.Now(), 0, nil)
 	if err == nil {
 		t.Fatalf("expected to get err; got nil")
 	}
@@ -437,7 +437,7 @@ func TestRecordingRuleExec_Negative(t *testing.T) {
 	fq.Add(metricWithValueAndLabels(t, 1, "__name__", "foo", "job", "foo"))
 	fq.Add(metricWithValueAndLabels(t, 2, "__name__", "foo", "job", "bar"))
 
-	_, err = rr.exec(context.TODO(), time.Now(), 0)
+	_, err = rr.exec(context.TODO(), time.Now(), 0, nil)
 	if err != nil {
 		t.Fatalf("cannot execute recording rule: %s", err)
 	}
@@ -479,7 +479,7 @@ func TestRecordingRuleExec_Partial(t *testing.T) {
 	}
 	rule.Debug = true
 	rule.q = fq
-	got, err := rule.exec(context.TODO(), ts, 0)
+	got, err := rule.exec(context.TODO(), ts, 0, nil)
 	want := []prompb.TimeSeries{
 		newTimeSeries([]float64{10}, []int64{ts.UnixNano()}, []prompb.Label{
 			{

app/vmalert/rule/rule.go

@@ -4,12 +4,15 @@ import (
 	"context"
 	"errors"
 	"fmt"
+	"net/http"
 	"sync"
 	"time"
 
 	"github.com/VictoriaMetrics/metrics"
 
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/datasource"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmalert/remotewrite"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/prompb"
 )
@@ -25,7 +28,7 @@ type Rule interface {
 	ToAPI() ApiRule
 	// exec executes the rule with given context at the given timestamp and limit.
 	// returns an err if number of resulting time series exceeds the limit.
-	exec(ctx context.Context, ts time.Time, limit int) ([]prompb.TimeSeries, error)
+	exec(ctx context.Context, ts time.Time, limit int, getRemoteReadQuerier func(enableDebug bool) datasource.Querier) ([]prompb.TimeSeries, error)
 	// execRange executes the rule on the given time range.
 	execRange(ctx context.Context, start, end time.Time) ([]prompb.TimeSeries, error)
 	// updateWith performs modification of current Rule
@@ -118,7 +121,7 @@ func (s *ruleState) add(e StateEntry) {
 	s.entries[s.cur] = e
 }
 
-func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int) (int, error) {
+func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRuleRetryAttempts int, continueWithExecutionErr bool) (int, error) {
 	var err error
 	var tss []prompb.TimeSeries
 	for i := range replayRuleRetryAttempts {
@@ -126,6 +129,22 @@ func replayRule(r Rule, start, end time.Time, rw remotewrite.RWClient, replayRul
 		if err == nil {
 			break
 		}
+		// retry request if possible to tolerate temporary network or datasource unavailability issues
+		var esc *httpserver.ErrorWithStatusCode
+		if errors.As(err, &esc) {
+			statusCode := esc.StatusCode
+			// if the status code is 400 or 422, the query failed due to reasons such as an expression syntax error or a resource limit being hit,
+			// rather than datasource unavailability.
+			// Continue replaying but skip the problematic execution if continueWithExecutionErr is true, otherwise, return the error without retry.
+			if statusCode == http.StatusUnprocessableEntity || statusCode == http.StatusBadRequest {
+				if continueWithExecutionErr {
+					logger.Errorf("rule %q: %s", r, err)
+					return 0, nil
+				} else {
+					return 0, err
+				}
+			}
+		}
 		logger.Errorf("attempt %d to execute rule %q failed: %s", i+1, r, err)
 		time.Sleep(time.Second)
 	}

app/vmauth/main.go

@@ -96,6 +96,7 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 
@@ -911,3 +912,8 @@ func slowdownUnauthorizedResponse(r *http.Request) {
 	}
 	timerpool.Put(t)
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	pushmetrics.InitSecretFlags()
+}

app/vmbackup/main.go

@@ -47,9 +47,8 @@ func main() {
 	// Write flags and help message to stdout, since it is easier to grep or pipe.
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
-	flagutil.RegisterSecretFlag("snapshot.createURL")
-	flagutil.RegisterSecretFlag("snapshot.deleteURL")
 	envflag.Parse()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 
@@ -273,3 +272,10 @@ func newRemoteOriginFS(ctx context.Context) (common.RemoteFS, error) {
 	}
 	return fs, nil
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	flagutil.RegisterSecretFlag("snapshot.createURL")
+	flagutil.RegisterSecretFlag("snapshot.deleteURL")
+	pushmetrics.InitSecretFlags()
+}

app/vmctl/main.go

@@ -47,6 +47,7 @@ func main() {
 	start := time.Now()
 	beforeFn := func(c *cli.Context) error {
 		flag.Parse()
+		initSecretFlags()
 		logger.Init()
 		isSilent = c.Bool(globalSilent)
 		if c.Bool(globalDisableProgressBar) {
@@ -619,3 +620,8 @@ func initConfigVM(c *cli.Context) (vm.Config, error) {
 		Backoff:            bf,
 	}, nil
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	pushmetrics.InitSecretFlags()
+}

app/vmctl/remoteread/remoteread.go

@@ -8,12 +8,14 @@ import (
 	"io"
 	"net/http"
 	"net/url"
+	"strconv"
 	"strings"
 	"time"
 
 	"github.com/gogo/protobuf/proto"
 	"github.com/golang/snappy"
 	"github.com/prometheus/prometheus/config"
+	"github.com/prometheus/prometheus/model/histogram"
 	"github.com/prometheus/prometheus/prompb"
 	"github.com/prometheus/prometheus/storage/remote"
 	"github.com/prometheus/prometheus/tsdb/chunkenc"
@@ -234,9 +236,29 @@ func processResponse(body io.ReadCloser, callback StreamCallback) error {
 	// shouldn't be accounted as an error.
 	for _, res := range readResp.Results {
 		for _, ts := range res.Timeseries {
-			vmTs := convertSamples(ts.Samples, ts.Labels)
-			if err := callback(vmTs); err != nil {
-				return err
+			// A series contains either float samples or native histogram samples.
+			// Both fields are processed independently, since a series may switch
+			// from float to native histogram representation at some point in time,
+			// so the requested time range may contain samples of both types.
+			if len(ts.Samples) > 0 {
+				vmTs := convertSamples(ts.Samples, ts.Labels)
+				if err := callback(vmTs); err != nil {
+					return err
+				}
+			}
+			if len(ts.Histograms) > 0 {
+				hSamples := make([]histogramSample, 0, len(ts.Histograms))
+				for _, h := range ts.Histograms {
+					hSamples = append(hSamples, histogramSample{
+						timestamp: h.Timestamp,
+						fh:        h.ToFloatHistogram(),
+					})
+				}
+				for _, vmTs := range convertHistograms(hSamples, ts.Labels) {
+					if err := callback(vmTs); err != nil {
+						return err
+					}
+				}
 			}
 		}
 	}
@@ -263,17 +285,45 @@ func processStreamResponse(body io.ReadCloser, callback StreamCallback) error {
 
 		for _, series := range res.ChunkedSeries {
 			samples := make([]prompb.Sample, 0)
+			var hSamples []histogramSample
 			for _, chunk := range series.Chunks {
-				s, err := parseSamples(chunk.Data)
-				if err != nil {
-					return err
+				switch chunk.Type {
+				case prompb.Chunk_XOR, prompb.Chunk_UNKNOWN:
+					// In proto3 the `type` field may be left unset (UNKNOWN) for XOR chunks.
+					// Prometheus remote.proto: "REQUIREMENT: when using proto3, this field
+					// MUST be set when using anything else than XOR". Senders before native
+					// histograms support (Prometheus < 2.40) do not set this field at all,
+					// so UNKNOWN chunks must be parsed as XOR ones.
+					s, err := parseSamples(chunk.Data)
+					if err != nil {
+						return err
+					}
+					samples = append(samples, s...)
+				case prompb.Chunk_HISTOGRAM, prompb.Chunk_FLOAT_HISTOGRAM:
+					hs, err := parseHistograms(chunk.Type, chunk.Data)
+					if err != nil {
+						return err
+					}
+					hSamples = append(hSamples, hs...)
+				default:
+					return fmt.Errorf("unsupported chunk encoding %q", chunk.Type)
 				}
-				samples = append(samples, s...)
 			}
 
-			ts := convertSamples(samples, series.Labels)
-			if err := callback(ts); err != nil {
-				return err
+			// A series contains either XOR chunks or native histogram chunks.
+			// Both are processed independently, since a series may switch
+			// from float to native histogram representation at some point in time,
+			// so the requested time range may contain chunks of both types.
+			if len(samples) > 0 {
+				ts := convertSamples(samples, series.Labels)
+				if err := callback(ts); err != nil {
+					return err
+				}
+			}
+			for _, ts := range convertHistograms(hSamples, series.Labels) {
+				if err := callback(ts); err != nil {
+					return err
+				}
 			}
 		}
 	}
@@ -312,6 +362,151 @@ func parseSamples(chunk []byte) ([]prompb.Sample, error) {
 	return samples, it.Err()
 }
 
+// histogramSample represents a single native histogram sample.
+type histogramSample struct {
+	timestamp int64
+	fh        *histogram.FloatHistogram
+}
+
+func parseHistograms(encoding prompb.Chunk_Encoding, chunk []byte) ([]histogramSample, error) {
+	var enc chunkenc.Encoding
+	switch encoding {
+	case prompb.Chunk_HISTOGRAM:
+		enc = chunkenc.EncHistogram
+	case prompb.Chunk_FLOAT_HISTOGRAM:
+		enc = chunkenc.EncFloatHistogram
+	default:
+		return nil, fmt.Errorf("unsupported histogram chunk encoding %q", encoding)
+	}
+	c, err := chunkenc.FromData(enc, chunk)
+	if err != nil {
+		return nil, fmt.Errorf("error read chunk: %w", err)
+	}
+
+	var hSamples []histogramSample
+	it := c.Iterator(nil)
+	for {
+		typ := it.Next()
+		if typ == chunkenc.ValNone {
+			break
+		}
+		switch typ {
+		case chunkenc.ValHistogram:
+			ts, h := it.AtHistogram(nil)
+			hSamples = append(hSamples, histogramSample{
+				timestamp: ts,
+				fh:        h.ToFloat(nil),
+			})
+		case chunkenc.ValFloatHistogram:
+			ts, fh := it.AtFloatHistogram(nil)
+			hSamples = append(hSamples, histogramSample{
+				timestamp: ts,
+				fh:        fh,
+			})
+		default:
+			// Skip unsupported values
+			continue
+		}
+	}
+	if err := it.Err(); err != nil {
+		return nil, fmt.Errorf("error iterate over chunks: %w", err)
+	}
+
+	return hSamples, nil
+}
+
+// convertHistograms converts native histogram samples into VictoriaMetrics histogram
+// time series in the same way as VictoriaMetrics converts native histograms
+// received via Prometheus remote write protocol: every native histogram sample
+// is converted into `<name>_count` and `<name>_sum` series plus a set of
+// `<name>_bucket` series with `vmrange` labels containing non-cumulative bucket counts.
+// The only difference is that for native histograms with custom buckets (NHCB)
+// bucket bounds are taken from the custom values, while the remote write protocol
+// parser ignores custom values and estimates the bounds with the exponential formula.
+// See https://prometheus.io/docs/specs/native_histograms/#data-model
+func convertHistograms(hSamples []histogramSample, labels []prompb.Label) []*vm.TimeSeries {
+	if len(hSamples) == 0 {
+		return nil
+	}
+
+	labelPairs := make([]vm.LabelPair, 0, len(labels))
+	nameValue := ""
+	for _, label := range labels {
+		if label.Name == "__name__" {
+			nameValue = label.Value
+			continue
+		}
+		labelPairs = append(labelPairs, vm.LabelPair{Name: label.Name, Value: label.Value})
+	}
+	// the metric has no name, skip it in the same way as VictoriaMetrics does
+	// when it receives a native histogram without the metric name via remote write protocol.
+	if nameValue == "" {
+		return nil
+	}
+
+	countSeries := &vm.TimeSeries{
+		Name:       nameValue + "_count",
+		LabelPairs: labelPairs,
+	}
+	sumSeries := &vm.TimeSeries{
+		Name:       nameValue + "_sum",
+		LabelPairs: labelPairs,
+	}
+	bucketSeries := make(map[string]*vm.TimeSeries)
+	// vmranges preserves the order of bucketSeries creation
+	// in order to get deterministic results.
+	var vmranges []string
+
+	for _, hs := range hSamples {
+		fh := hs.fh
+		countSeries.Timestamps = append(countSeries.Timestamps, hs.timestamp)
+		countSeries.Values = append(countSeries.Values, fh.Count)
+		sumSeries.Timestamps = append(sumSeries.Timestamps, hs.timestamp)
+		sumSeries.Values = append(sumSeries.Values, fh.Sum)
+
+		it := fh.AllBucketIterator()
+		for it.Next() {
+			b := it.At()
+			if b.Count <= 0 {
+				continue
+			}
+			vmrange := formatVmrange(b.Lower, b.Upper)
+			s := bucketSeries[vmrange]
+			if s == nil {
+				bucketLabelPairs := make([]vm.LabelPair, len(labelPairs), len(labelPairs)+1)
+				copy(bucketLabelPairs, labelPairs)
+				bucketLabelPairs = append(bucketLabelPairs, vm.LabelPair{Name: "vmrange", Value: vmrange})
+				s = &vm.TimeSeries{
+					Name:       nameValue + "_bucket",
+					LabelPairs: bucketLabelPairs,
+				}
+				bucketSeries[vmrange] = s
+				vmranges = append(vmranges, vmrange)
+			}
+			s.Timestamps = append(s.Timestamps, hs.timestamp)
+			s.Values = append(s.Values, b.Count)
+		}
+	}
+
+	tss := make([]*vm.TimeSeries, 0, 2+len(vmranges))
+	tss = append(tss, countSeries, sumSeries)
+	for _, vmrange := range vmranges {
+		tss = append(tss, bucketSeries[vmrange])
+	}
+	return tss
+}
+
+// formatVmrange formats the given bucket bounds into `vmrange` label value
+// in the same way as VictoriaMetrics does for native histograms
+// received via Prometheus remote write protocol.
+func formatVmrange(lower, upper float64) string {
+	b := make([]byte, 0, 24)
+	b = strconv.AppendFloat(b, lower, 'e', 3, 64)
+	b = append(b, "..."...)
+	b = strconv.AppendFloat(b, upper, 'e', 3, 64)
+	return string(b)
+}
+
 type keyValue struct {
 	key   string
 	value string

app/vmctl/remoteread/remoteread_test.go

@@ -0,0 +1,334 @@
+package remoteread
+
+import (
+	"bytes"
+	"io"
+	"reflect"
+	"testing"
+
+	"github.com/gogo/protobuf/proto"
+	"github.com/golang/snappy"
+	"github.com/prometheus/prometheus/model/histogram"
+	"github.com/prometheus/prometheus/prompb"
+	"github.com/prometheus/prometheus/storage/remote"
+	"github.com/prometheus/prometheus/tsdb/chunkenc"
+
+	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmctl/vm"
+)
+
+func testHistogram(mul int64) *histogram.Histogram {
+	return &histogram.Histogram{
+		Schema:          0,
+		Count:           uint64(10 * mul),
+		Sum:             25.5 * float64(mul),
+		ZeroThreshold:   0.001,
+		ZeroCount:       uint64(2 * mul),
+		PositiveSpans:   []histogram.Span{{Offset: 0, Length: 2}},
+		PositiveBuckets: []int64{1 * mul, 2 * mul},
+		NegativeSpans:   []histogram.Span{{Offset: 0, Length: 1}},
+		NegativeBuckets: []int64{4 * mul},
+	}
+}
+
+func TestConvertHistograms(t *testing.T) {
+	f := func(hSamples []histogramSample, labels []prompb.Label, expected []*vm.TimeSeries) {
+		t.Helper()
+
+		tss := convertHistograms(hSamples, labels)
+		if !reflect.DeepEqual(tss, expected) {
+			t.Fatalf("unexpected result\ngot:\n%v\nwant:\n%v", tss, expected)
+		}
+	}
+
+	// series without samples
+	f(nil, []prompb.Label{{Name: "__name__", Value: "foo"}}, nil)
+
+	// series without the metric name must be skipped
+	f([]histogramSample{
+		{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
+	}, []prompb.Label{{Name: "job", Value: "bar"}}, nil)
+
+	// native histogram must be converted to _count, _sum and _bucket series
+	// in the same way as VictoriaMetrics does for Prometheus remote write protocol
+	labels := []prompb.Label{
+		{Name: "__name__", Value: "request_duration_seconds"},
+		{Name: "job", Value: "bar"},
+	}
+	jobLabel := []vm.LabelPair{{Name: "job", Value: "bar"}}
+	bucketLabels := func(vmrange string) []vm.LabelPair {
+		return []vm.LabelPair{
+			{Name: "job", Value: "bar"},
+			{Name: "vmrange", Value: vmrange},
+		}
+	}
+	f([]histogramSample{
+		{timestamp: 1000, fh: testHistogram(1).ToFloat(nil)},
+		{timestamp: 2000, fh: testHistogram(2).ToFloat(nil)},
+	}, labels, []*vm.TimeSeries{
+		{
+			Name:       "request_duration_seconds_count",
+			LabelPairs: jobLabel,
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{10, 20},
+		},
+		{
+			Name:       "request_duration_seconds_sum",
+			LabelPairs: jobLabel,
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{25.5, 51},
+		},
+		{
+			Name:       "request_duration_seconds_bucket",
+			LabelPairs: bucketLabels("-1.000e+00...-5.000e-01"),
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{4, 8},
+		},
+		{
+			Name:       "request_duration_seconds_bucket",
+			LabelPairs: bucketLabels("-1.000e-03...1.000e-03"),
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{2, 4},
+		},
+		{
+			Name:       "request_duration_seconds_bucket",
+			LabelPairs: bucketLabels("5.000e-01...1.000e+00"),
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{1, 2},
+		},
+		{
+			Name:       "request_duration_seconds_bucket",
+			LabelPairs: bucketLabels("1.000e+00...2.000e+00"),
+			Timestamps: []int64{1000, 2000},
+			Values:     []float64{3, 6},
+		},
+	})
+}
+
+func TestParseHistograms(t *testing.T) {
+	c := chunkenc.NewHistogramChunk()
+	app, err := c.Appender()
+	if err != nil {
+		t.Fatalf("cannot create chunk appender: %s", err)
+	}
+	if _, _, _, err := app.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
+		t.Fatalf("cannot append histogram: %s", err)
+	}
+	if _, _, _, err := app.AppendHistogram(nil, 0, 2000, testHistogram(2), true); err != nil {
+		t.Fatalf("cannot append histogram: %s", err)
+	}
+
+	hSamples, err := parseHistograms(prompb.Chunk_HISTOGRAM, c.Bytes())
+	if err != nil {
+		t.Fatalf("cannot parse histogram chunk: %s", err)
+	}
+	if len(hSamples) != 2 {
+		t.Fatalf("unexpected number of histogram samples; got %d; want 2", len(hSamples))
+	}
+	for i, expected := range []struct {
+		timestamp int64
+		count     float64
+		sum       float64
+	}{
+		{timestamp: 1000, count: 10, sum: 25.5},
+		{timestamp: 2000, count: 20, sum: 51},
+	} {
+		if hSamples[i].timestamp != expected.timestamp {
+			t.Fatalf("unexpected timestamp; got %d; want %d", hSamples[i].timestamp, expected.timestamp)
+		}
+		if hSamples[i].fh.Count != expected.count {
+			t.Fatalf("unexpected count; got %f; want %f", hSamples[i].fh.Count, expected.count)
+		}
+		if hSamples[i].fh.Sum != expected.sum {
+			t.Fatalf("unexpected sum; got %f; want %f", hSamples[i].fh.Sum, expected.sum)
+		}
+	}
+
+	// unsupported chunk encoding must return error
+	if _, err := parseHistograms(prompb.Chunk_XOR, c.Bytes()); err == nil {
+		t.Fatalf("expecting non-nil error for unsupported chunk encoding")
+	}
+}
+
+func TestProcessResponse(t *testing.T) {
+	readResp := &prompb.ReadResponse{
+		Results: []*prompb.QueryResult{
+			{
+				Timeseries: []*prompb.TimeSeries{
+					{
+						Labels: []prompb.Label{
+							{Name: "__name__", Value: "cpu_usage"},
+							{Name: "job", Value: "bar"},
+						},
+						Samples: []prompb.Sample{
+							{Timestamp: 1000, Value: 1.5},
+						},
+					},
+					{
+						Labels: []prompb.Label{
+							{Name: "__name__", Value: "request_duration_seconds"},
+							{Name: "job", Value: "bar"},
+						},
+						Histograms: []prompb.Histogram{
+							prompb.FromIntHistogram(1000, testHistogram(1)),
+						},
+					},
+				},
+			},
+		},
+	}
+	data, err := proto.Marshal(readResp)
+	if err != nil {
+		t.Fatalf("cannot marshal ReadResponse: %s", err)
+	}
+	compressed := snappy.Encode(nil, data)
+
+	var tss []*vm.TimeSeries
+	err = processResponse(io.NopCloser(bytes.NewReader(compressed)), func(ts *vm.TimeSeries) error {
+		tss = append(tss, ts)
+		return nil
+	})
+	if err != nil {
+		t.Fatalf("cannot process response: %s", err)
+	}
+
+	// 1 float series + _count + _sum + 4 buckets
+	if len(tss) != 7 {
+		t.Fatalf("unexpected number of time series; got %d; want 7", len(tss))
+	}
+	if tss[0].Name != "cpu_usage" || !reflect.DeepEqual(tss[0].Values, []float64{1.5}) {
+		t.Fatalf("unexpected float series: %v", tss[0])
+	}
+	if tss[1].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[1].Values, []float64{10}) {
+		t.Fatalf("unexpected _count series: %v", tss[1])
+	}
+	if tss[2].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[2].Values, []float64{25.5}) {
+		t.Fatalf("unexpected _sum series: %v", tss[2])
+	}
+	for _, ts := range tss[3:] {
+		if ts.Name != "request_duration_seconds_bucket" {
+			t.Fatalf("unexpected bucket series name %q", ts.Name)
+		}
+	}
+}
+
+type nopFlusher struct{}
+
+func (nopFlusher) Flush() {}
+
+func TestProcessStreamResponse(t *testing.T) {
+	// build a histogram chunk
+	hc := chunkenc.NewHistogramChunk()
+	hApp, err := hc.Appender()
+	if err != nil {
+		t.Fatalf("cannot create histogram chunk appender: %s", err)
+	}
+	if _, _, _, err := hApp.AppendHistogram(nil, 0, 1000, testHistogram(1), true); err != nil {
+		t.Fatalf("cannot append histogram: %s", err)
+	}
+
+	// build a float chunk
+	xc := chunkenc.NewXORChunk()
+	xApp, err := xc.Appender()
+	if err != nil {
+		t.Fatalf("cannot create xor chunk appender: %s", err)
+	}
+	xApp.Append(0, 1000, 1.5)
+
+	res := &prompb.ChunkedReadResponse{
+		ChunkedSeries: []*prompb.ChunkedSeries{
+			{
+				Labels: []prompb.Label{
+					{Name: "__name__", Value: "request_duration_seconds"},
+					{Name: "job", Value: "bar"},
+				},
+				Chunks: []prompb.Chunk{
+					{Type: prompb.Chunk_HISTOGRAM, Data: hc.Bytes()},
+				},
+			},
+			{
+				Labels: []prompb.Label{
+					{Name: "__name__", Value: "cpu_usage"},
+				},
+				Chunks: []prompb.Chunk{
+					{Type: prompb.Chunk_XOR, Data: xc.Bytes()},
+				},
+			},
+			{
+				Labels: []prompb.Label{
+					{Name: "__name__", Value: "memory_usage"},
+				},
+				Chunks: []prompb.Chunk{
+					// the `type` field may be unset for XOR chunks,
+					// such chunks must be parsed as XOR ones
+					{Type: prompb.Chunk_UNKNOWN, Data: xc.Bytes()},
+				},
+			},
+		},
+	}
+	data, err := proto.Marshal(res)
+	if err != nil {
+		t.Fatalf("cannot marshal ChunkedReadResponse: %s", err)
+	}
+	var buf bytes.Buffer
+	cw := remote.NewChunkedWriter(&buf, nopFlusher{})
+	if _, err := cw.Write(data); err != nil {
+		t.Fatalf("cannot write chunked response: %s", err)
+	}
+
+	var tss []*vm.TimeSeries
+	err = processStreamResponse(io.NopCloser(&buf), func(ts *vm.TimeSeries) error {
+		tss = append(tss, ts)
+		return nil
+	})
+	if err != nil {
+		t.Fatalf("cannot process stream response: %s", err)
+	}
+
+	// _count + _sum + 4 buckets + 1 float series + 1 float series from UNKNOWN chunk
+	if len(tss) != 8 {
+		t.Fatalf("unexpected number of time series; got %d; want 8", len(tss))
+	}
+	if tss[0].Name != "request_duration_seconds_count" || !reflect.DeepEqual(tss[0].Values, []float64{10}) {
+		t.Fatalf("unexpected _count series: %v", tss[0])
+	}
+	if tss[1].Name != "request_duration_seconds_sum" || !reflect.DeepEqual(tss[1].Values, []float64{25.5}) {
+		t.Fatalf("unexpected _sum series: %v", tss[1])
+	}
+	for _, ts := range tss[2:6] {
+		if ts.Name != "request_duration_seconds_bucket" {
+			t.Fatalf("unexpected bucket series name %q", ts.Name)
+		}
+	}
+	if tss[6].Name != "cpu_usage" || !reflect.DeepEqual(tss[6].Values, []float64{1.5}) {
+		t.Fatalf("unexpected float series: %v", tss[6])
+	}
+	if tss[7].Name != "memory_usage" || !reflect.DeepEqual(tss[7].Values, []float64{1.5}) {
+		t.Fatalf("unexpected float series from UNKNOWN chunk: %v", tss[7])
+	}
+}
+
+func TestParseFloatHistograms(t *testing.T) {
+	c := chunkenc.NewFloatHistogramChunk()
+	app, err := c.Appender()
+	if err != nil {
+		t.Fatalf("cannot create chunk appender: %s", err)
+	}
+	fh := testHistogram(1).ToFloat(nil)
+	if _, _, _, err := app.AppendFloatHistogram(nil, 0, 1000, fh, true); err != nil {
+		t.Fatalf("cannot append float histogram: %s", err)
+	}
+
+	hSamples, err := parseHistograms(prompb.Chunk_FLOAT_HISTOGRAM, c.Bytes())
+	if err != nil {
+		t.Fatalf("cannot parse float histogram chunk: %s", err)
+	}
+	if len(hSamples) != 1 {
+		t.Fatalf("unexpected number of histogram samples; got %d; want 1", len(hSamples))
+	}
+	if hSamples[0].timestamp != 1000 {
+		t.Fatalf("unexpected timestamp; got %d; want 1000", hSamples[0].timestamp)
+	}
+	if hSamples[0].fh.Count != 10 {
+		t.Fatalf("unexpected count; got %f; want 10", hSamples[0].fh.Count)
+	}
+}

app/vmrestore/main.go

@@ -38,6 +38,7 @@ func main() {
 	flag.CommandLine.SetOutput(os.Stdout)
 	flag.Usage = usage
 	envflag.Parse()
+	initSecretFlags()
 	buildinfo.Init()
 	logger.Init()
 
@@ -112,3 +113,8 @@ func newSrcFS(ctx context.Context) (common.RemoteFS, error) {
 	}
 	return fs, nil
 }
+
+// initSecretFlags manages the secret flags for this app and must be called after flag parsing and before logger init.
+func initSecretFlags() {
+	pushmetrics.InitSecretFlags()
+}

app/vmselect/main.go

@@ -59,6 +59,12 @@ func Init(vmselectMaxConcurrentRequests int, vmselectMaxQueueDuration time.Durat
 	initVMUIConfig()
 
 	vmalertproxy.Init(*vmalertProxyURL)
+
+}
+
+// InitSecretFlags manages the secret flags for this pkg and must be called by app-level initSecretFlags.
+// It should run before logger initialization and package Init() (if exists).
+func InitSecretFlags() {
 	flagutil.RegisterSecretFlag("vmalert.proxyURL")
 }
 

app/vmselect/prometheus/prometheus.go

@@ -516,7 +516,7 @@ func DeleteHandler(startTime time.Time, r *http.Request) error {
 	cp.deadline = searchutil.GetDeadlineForDelete(r, startTime)
 
 	if !cp.IsDefaultTimeRange() {
-		return fmt.Errorf("start=%d and end=%d args aren't supported. Remove these args from the query in order to delete all the matching metrics", cp.start, cp.end)
+		return fmt.Errorf("delete API does not support specific time ranges using start and end args, the series can only be deleted completely")
 	}
 	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxDeleteSeries)
 	deletedCount, err := netstorage.DeleteSeries(nil, sq, cp.deadline)
@@ -540,11 +540,11 @@ func LabelValuesHandler(qt *querytracer.Tracer, startTime time.Time, labelName s
 
 	cp, err := getCommonParamsForLabelsAPI(r, startTime, false)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	limit, err := httputil.GetInt(r, "limit")
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxLabelsAPISeries)
 
@@ -584,7 +584,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
 
 	cp, err := getCommonParams(r, startTime, false)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	cp.deadline = searchutil.GetDeadlineForStatusRequest(r, startTime)
 
@@ -596,7 +596,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
 		} else {
 			t, err := time.Parse("2006-01-02", dateStr)
 			if err != nil {
-				return fmt.Errorf("cannot parse `date` arg %q: %w", dateStr, err)
+				return httpserver.InvalidParamError(fmt.Errorf("cannot parse `date` arg %q: %w", dateStr, err))
 			}
 			date = uint64(t.Unix()) / secsPerDay
 		}
@@ -607,7 +607,7 @@ func TSDBStatusHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
 	if len(topNStr) > 0 {
 		n, err := strconv.Atoi(topNStr)
 		if err != nil {
-			return fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err)
+			return httpserver.InvalidParamError(fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err))
 		}
 		if n <= 0 {
 			n = 1
@@ -645,11 +645,11 @@ func LabelsHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
 
 	cp, err := getCommonParamsForLabelsAPI(r, startTime, false)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	limit, err := httputil.GetInt(r, "limit")
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxLabelsAPISeries)
 	labels, err := netstorage.LabelNames(qt, sq, limit, cp.deadline)
@@ -671,10 +671,9 @@ func LabelsHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
 //
 // See https://prometheus.io/docs/prometheus/latest/querying/api/#querying-metric-metadata
 func MetadataHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWriter, r *http.Request) error {
-
 	limit, err := httputil.GetInt(r, "limit")
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	if limit < 0 {
 		limit = 0
@@ -734,11 +733,11 @@ func SeriesHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseW
 	// See https://github.com/VictoriaMetrics/VictoriaMetrics/issues/91
 	cp, err := getCommonParamsForLabelsAPI(r, startTime, true)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	limit, err := httputil.GetInt(r, "limit")
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 
 	sq := storage.NewSearchQuery(cp.start, cp.end, cp.filterss, *maxSeriesLimit)
@@ -772,19 +771,19 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
 	mayCache := !httputil.GetBool(r, "nocache")
 	query := r.FormValue("query")
 	if len(query) == 0 {
-		return fmt.Errorf("missing `query` arg")
+		return httpserver.InvalidParamError(fmt.Errorf("missing `query` arg"))
 	}
 	start, err := httputil.GetTime(r, "time", ct)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	lookbackDelta, err := getMaxLookback(r)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	step, err := httputil.GetDuration(r, "step", lookbackDelta)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	if step <= 0 {
 		step = defaultStep
@@ -792,16 +791,16 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
 
 	maxLen := searchutil.GetMaxQueryLen()
 	if len(query) > maxLen {
-		return fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen)
+		return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen))
 	}
 	etfs, err := searchutil.GetExtraTagFilters(r)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	if childQuery, windowExpr, offsetExpr := promql.IsMetricSelectorWithRollup(query); childQuery != "" {
 		window, err := windowExpr.NonNegativeDuration(step)
 		if err != nil {
-			return fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err)
+			return httpserver.InvalidParamError(fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err))
 		}
 		offset := offsetExpr.Duration(step)
 		start -= offset
@@ -815,7 +814,7 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
 
 		tagFilterss, err := getTagFilterssFromMatches([]string{childQuery})
 		if err != nil {
-			return err
+			return httpserver.InvalidParamError(err)
 		}
 		filterss := searchutil.JoinTagFilterss(tagFilterss, etfs)
 
@@ -831,22 +830,25 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
 		return nil
 	}
 	if childQuery, windowExpr, stepExpr, offsetExpr := promql.IsRollup(query); childQuery != "" {
+		if len(childQuery) > maxLen {
+			return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(childQuery), maxLen))
+		}
 		newStep, err := stepExpr.NonNegativeDuration(step)
 		if err != nil {
-			return fmt.Errorf("cannot parse step in square brackets at %s: %w", query, err)
+			return httpserver.InvalidParamError(fmt.Errorf("cannot parse step in square brackets at %s: %w", query, err))
 		}
 		if newStep > 0 {
 			step = newStep
 		}
 		window, err := windowExpr.NonNegativeDuration(step)
 		if err != nil {
-			return fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err)
+			return httpserver.InvalidParamError(fmt.Errorf("cannot parse lookbehind window in square brackets at %s: %w", query, err))
 		}
 		offset := offsetExpr.Duration(step)
 		start -= offset
 		end := start
 		start = end - window
-		if err := queryRangeHandler(qt, startTime, w, childQuery, start, end, step, r, ct, etfs); err != nil {
+		if err := queryRangeHandler(qt, startTime, w, childQuery, start, end, step, lookbackDelta, r, ct, etfs); err != nil {
 			return fmt.Errorf("error when executing query=%q on the time range (start=%d, end=%d, step=%d): %w", childQuery, start, end, step, err)
 		}
 		return nil
@@ -854,7 +856,7 @@ func QueryHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWr
 
 	queryOffset, err := getLatencyOffsetMilliseconds(r)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	if !httputil.GetBool(r, "nocache") && ct-start < queryOffset && start-ct < queryOffset {
 		// Adjust start time only if `nocache` arg isn't set.
@@ -928,45 +930,43 @@ func QueryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
 	ct := startTime.UnixNano() / 1e6
 	query := r.FormValue("query")
 	if len(query) == 0 {
-		return fmt.Errorf("missing `query` arg")
+		return httpserver.InvalidParamError(fmt.Errorf("missing `query` arg"))
+	}
+	maxLen := searchutil.GetMaxQueryLen()
+	if len(query) > maxLen {
+		return httpserver.InvalidParamError(fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen))
 	}
 	start, err := httputil.GetTime(r, "start", ct-defaultStep)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	end, err := httputil.GetTime(r, "end", ct)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	step, err := httputil.GetDuration(r, "step", defaultStep)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
 	etfs, err := searchutil.GetExtraTagFilters(r)
 	if err != nil {
-		return err
+		return httpserver.InvalidParamError(err)
 	}
-	if err := queryRangeHandler(qt, startTime, w, query, start, end, step, r, ct, etfs); err != nil {
+	lookbackDelta, err := getMaxLookback(r)
+	if err != nil {
+		return httpserver.InvalidParamError(err)
+	}
+	if err := queryRangeHandler(qt, startTime, w, query, start, end, step, lookbackDelta, r, ct, etfs); err != nil {
 		return fmt.Errorf("error when executing query=%q on the time range (start=%d, end=%d, step=%d): %w", query, start, end, step, err)
 	}
 	return nil
 }
 
 func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.ResponseWriter, query string,
-	start, end, step int64, r *http.Request, ct int64, etfs [][]storage.TagFilter) error {
+	start, end, step, lookbackDelta int64, r *http.Request, ct int64, etfs [][]storage.TagFilter) error {
 	deadline := searchutil.GetDeadlineForQuery(r, startTime)
 	mayCache := !httputil.GetBool(r, "nocache")
 	optimizeRepeatedBinaryOpSubexprs := httputil.GetBool(r, "optimize_repeated_binary_op_subexprs")
-	lookbackDelta, err := getMaxLookback(r)
-	if err != nil {
-		return err
-	}
-
-	// Validate input args.
-	maxLen := searchutil.GetMaxQueryLen()
-	if len(query) > maxLen {
-		return fmt.Errorf("too long query; got %d bytes; mustn't exceed `-search.maxQueryLen=%d` bytes", len(query), maxLen)
-	}
 	if start > end {
 		end = start + defaultStep
 	}
@@ -1005,7 +1005,7 @@ func queryRangeHandler(qt *querytracer.Tracer, startTime time.Time, w http.Respo
 	if step < maxStepForPointsAdjustment.Milliseconds() {
 		queryOffset, err := getLatencyOffsetMilliseconds(r)
 		if err != nil {
-			return err
+			return httpserver.InvalidParamError(err)
 		}
 		if ct-queryOffset < end {
 			result = adjustLastPoints(result, ct-queryOffset, ct+step)
@@ -1156,13 +1156,13 @@ func QueryStatsHandler(w http.ResponseWriter, r *http.Request) error {
 	if len(topNStr) > 0 {
 		n, err := strconv.Atoi(topNStr)
 		if err != nil {
-			return fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err)
+			return httpserver.InvalidParamError(fmt.Errorf("cannot parse `topN` arg %q: %w", topNStr, err))
 		}
 		topN = n
 	}
 	maxLifetimeMsecs, err := httputil.GetDuration(r, "maxLifetime", 10*60*1000)
 	if err != nil {
-		return fmt.Errorf("cannot parse `maxLifetime` arg: %w", err)
+		return httpserver.InvalidParamError(fmt.Errorf("cannot parse `maxLifetime` arg: %w", err))
 	}
 	maxLifetime := time.Duration(maxLifetimeMsecs) * time.Millisecond
 	w.Header().Set("Content-Type", "application/json")

app/vmselect/promql/exec.go

@@ -11,6 +11,7 @@ import (
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/netstorage"
 	"github.com/VictoriaMetrics/VictoriaMetrics/app/vmselect/querystats"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/decimal"
+	"github.com/VictoriaMetrics/VictoriaMetrics/lib/httpserver"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/logger"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/querytracer"
 	"github.com/VictoriaMetrics/VictoriaMetrics/lib/storage"
@@ -46,15 +47,15 @@ func Exec(qt *querytracer.Tracer, ec *EvalConfig, q string, isFirstPointOnly boo
 
 	e, err := parsePromQLWithCache(q)
 	if err != nil {
-		return nil, err
+		return nil, httpserver.InvalidParamError(err)
 	}
 
 	if *disableImplicitConversion || *logImplicitConversion {
 		isInvalid := metricsql.IsLikelyInvalid(e)
 		if isInvalid && *disableImplicitConversion {
 			// we don't add query=%q to err message as it will be added by the caller
-			return nil, fmt.Errorf("query requires implicit conversion and is rejected according to -search.disableImplicitConversion command-line flag. " +
-				"See https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details")
+			return nil, httpserver.InvalidParamError(fmt.Errorf("query requires implicit conversion and is rejected according to -search.disableImplicitConversion command-line flag. " +
+				"See https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details"))
 		}
 		if isInvalid && *logImplicitConversion {
 			logger.Warnf("query=%q requires implicit conversion, see https://docs.victoriametrics.com/victoriametrics/metricsql/#implicit-query-conversions for details", e.AppendString(nil))

app/vmselect/vmui/index.html

@@ -37,7 +37,7 @@
   <meta property="og:title" content="UI for VictoriaMetrics">
   <meta property="og:url" content="https://victoriametrics.com/">
   <meta property="og:description" content="Explore and troubleshoot your VictoriaMetrics data">
-  <script type="module" crossorigin src="./assets/index-D5egN2id.js"></script>
+  <script type="module" crossorigin src="./assets/index-B1dXK3k7.js"></script>
   <link rel="modulepreload" crossorigin href="./assets/rolldown-runtime-CNC7AqOf.js">
   <link rel="modulepreload" crossorigin href="./assets/vendor-DwJYpOdw.js">
   <link rel="stylesheet" crossorigin href="./assets/vendor-CnsZ1jie.css">

app/vmui/Dockerfile-web

@@ -1,4 +1,4 @@
-FROM golang:1.26.5 AS build-web-stage
+FROM golang:1.26.6 AS build-web-stage
 COPY build /build
 
 WORKDIR /build

app/vmui/packages/vmui/assets/favicon.svg

@@ -0,0 +1,5 @@
+<svg width="48" height="48" fill="#020202" xmlns="http://www.w3.org/2000/svg">
+    <path d="M24.5475 0C10.3246.0265251 1.11379 3.06365 4.40623 6.10077c0 0 12.32997 11.23333 16.58217 14.84083.8131.6896 2.1728 1.1936 3.5191 1.2201h.1199c1.3463-.0265 2.706-.5305 3.5191-1.2201 4.2522-3.5942 16.5422-14.84083 16.5422-14.84083C48.0478 3.06365 38.8636.0265251 24.6674 0"/>
+    <path d="M28.1579 27.0159c-.8131.6896-2.1728 1.1936-3.5191 1.2201h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2201-2.9725-2.5067-13.35639-11.87-17.26201-15.3979v5.4112c0 .5968.22661 1.3793.6265 1.7506C7.00358 21.1936 17.2675 30.5437 20.9731 33.6737c.8132.6896 2.1728 1.1936 3.5191 1.2201h.12c1.3463-.0265 2.7059-.5305 3.519-1.2201 3.679-3.13 13.9429-12.4536 16.6089-14.8939.4132-.3713.6265-1.1538.6265-1.7506V11.618c-3.9323 3.5411-14.3162 12.931-17.2354 15.3979h.0267Z"/>
+    <path d="M28.1579 39.748c-.8131.6897-2.1728 1.1937-3.5191 1.2202h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2202-2.9725-2.4933-13.35639-11.8567-17.26201-15.3978v5.4111c0 .5969.22661 1.3793.6265 1.7507C7.00358 33.9258 17.2675 43.2759 20.9731 46.4058c.8132.6897 2.1728 1.1937 3.5191 1.2202h.12c1.3463-.0265 2.7059-.5305 3.519-1.2202 3.679-3.1299 13.9429-12.4535 16.6089-14.8938.4132-.3714.6265-1.1538.6265-1.7507v-5.4111c-3.9323 3.5411-14.3162 12.931-17.2354 15.3978h.0267Z"/>
+</svg>

app/vmui/packages/vmui/index.html

@@ -2,9 +2,9 @@
 <html lang="en">
 <head>
   <meta charset="utf-8"/>
-  <link rel="icon" href="/favicon.svg"/>
-  <link rel="apple-touch-icon" href="/favicon.svg"/>
-  <link rel="mask-icon" href="/favicon.svg" color="#000000">
+  <link id="favicon" rel="icon" href="/assets/favicon.svg" />
+  <link rel="apple-touch-icon" href="/assets/favicon.svg" />
+  <link id="mask-icon" rel="mask-icon" href="/assets/favicon.svg?no-inline" color="#000000">
 
   <meta name="robots" content="noindex">
   <meta name="viewport" content="width=device-width, initial-scale=1, maximum-scale=5"/>

app/vmui/packages/vmui/public/favicon.svg

@@ -1 +0,0 @@
-<svg width="48" height="48" fill="none" xmlns="http://www.w3.org/2000/svg"><path d="M24.5475 0C10.3246.0265251 1.11379 3.06365 4.40623 6.10077c0 0 12.32997 11.23333 16.58217 14.84083.8131.6896 2.1728 1.1936 3.5191 1.2201h.1199c1.3463-.0265 2.706-.5305 3.5191-1.2201 4.2522-3.5942 16.5422-14.84083 16.5422-14.84083C48.0478 3.06365 38.8636.0265251 24.6674 0" fill="#020202"/><path d="M28.1579 27.0159c-.8131.6896-2.1728 1.1936-3.5191 1.2201h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2201-2.9725-2.5067-13.35639-11.87-17.26201-15.3979v5.4112c0 .5968.22661 1.3793.6265 1.7506C7.00358 21.1936 17.2675 30.5437 20.9731 33.6737c.8132.6896 2.1728 1.1936 3.5191 1.2201h.12c1.3463-.0265 2.7059-.5305 3.519-1.2201 3.679-3.13 13.9429-12.4536 16.6089-14.8939.4132-.3713.6265-1.1538.6265-1.7506V11.618c-3.9323 3.5411-14.3162 12.931-17.2354 15.3979h.0267Z" fill="#020202"/><path d="M28.1579 39.748c-.8131.6897-2.1728 1.1937-3.5191 1.2202h-.12c-1.3463-.0265-2.7059-.5305-3.519-1.2202-2.9725-2.4933-13.35639-11.8567-17.26201-15.3978v5.4111c0 .5969.22661 1.3793.6265 1.7507C7.00358 33.9258 17.2675 43.2759 20.9731 46.4058c.8132.6897 2.1728 1.1937 3.5191 1.2202h.12c1.3463-.0265 2.7059-.5305 3.519-1.2202 3.679-3.1299 13.9429-12.4535 16.6089-14.8938.4132-.3714.6265-1.1538.6265-1.7507v-5.4111c-3.9323 3.5411-14.3162 12.931-17.2354 15.3978h.0267Z" fill="#020202"/></svg>

app/vmui/packages/vmui/public/manifest.json

@@ -3,7 +3,7 @@
   "name": "vmui",
   "icons": [
     {
-      "src": "favicon.svg",
+      "src": "./assets/favicon.svg",
       "sizes": "any",
       "type": "image/svg+xml"
     }

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/BrowserTabController/BrowserTabController.tsx

@@ -0,0 +1,61 @@
+import { FC, useMemo } from "preact/compat";
+import "./style.scss";
+import { createFaviconUrl } from "../../../../utils/favicon";
+import classNames from "classnames";
+import { useBrowserTabSync } from "./hooks/useBrowserTabSync";
+import { CloseIcon } from "../../../Main/Icons";
+import { faviconColors } from "../../../../constants/faviconColors";
+
+const BrowserTabController: FC = () => {
+  const { faviconColor, changeFaviconColor } = useBrowserTabSync();
+
+  const faviconUrl = useMemo(() => {
+    return createFaviconUrl(faviconColor);
+  }, [faviconColor]);
+
+  const createHandlerClick = (color?: string) => () => {
+    changeFaviconColor(color);
+  };
+
+  return (
+    <div className="vm-browser-tab-controller">
+      <p className="vm-server-configurator__title">Favicon color</p>
+
+      <div className="vm-browser-tab-controller-palette">
+        <div className="vm-browser-tab-controller-palette-list">
+          <button
+            className="vm-browser-tab-controller-palette-list__item vm-browser-tab-controller-palette-list__item_reset"
+            type="button"
+            onClick={createHandlerClick()}
+            aria-label="Reset favicon color"
+          >
+            <CloseIcon />
+          </button>
+
+          {faviconColors.map(color => (
+            <button
+              className={classNames({
+                "vm-browser-tab-controller-palette-list__item": true,
+                "vm-browser-tab-controller-palette-list__item_selected": faviconColor === color
+              })}
+              key={color}
+              type="button"
+              style={{ color }}
+              onClick={createHandlerClick(color)}
+              aria-label={`Set favicon color to ${color}`}
+              aria-pressed={faviconColor === color}
+            />
+          ))}
+        </div>
+
+        <img
+          className="vm-browser-tab-controller-palette__preview"
+          src={faviconUrl}
+          alt="Favicon preview"
+        />
+      </div>
+    </div>
+  );
+};
+
+export default BrowserTabController;

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/BrowserTabController/hooks/useBrowserTabSync.ts

@@ -0,0 +1,41 @@
+import useEventListener from "../../../../../hooks/useEventListener";
+import { useEffect, useState } from "preact/compat";
+import { getFromStorage, removeFromStorage, saveToStorage } from "../../../../../utils/storage";
+import { getFaviconStorageKey, updateFaviconColor } from "../../../../../utils/favicon";
+
+const storageKey = `FAVICON_COLOR:${getFaviconStorageKey()}` as const;
+
+const getColorFromStorage = () => {
+  return getFromStorage(storageKey) as string | undefined;
+};
+
+export const useBrowserTabSync = () => {
+  const [faviconColor, setFaviconColor] = useState(getColorFromStorage);
+
+  const handleUpdateColor = () => {
+    setFaviconColor(getColorFromStorage());
+  };
+
+  const changeFaviconColor = (color?: string) => {
+    if (color) {
+      saveToStorage(storageKey, color);
+    } else {
+      removeFromStorage([storageKey]);
+    }
+  };
+
+  useEffect(() => {
+    handleUpdateColor();
+  }, []);
+
+  useEffect(() => {
+    updateFaviconColor(faviconColor);
+  }, [faviconColor]);
+
+  useEventListener("storage", handleUpdateColor);
+
+  return {
+    faviconColor,
+    changeFaviconColor,
+  };
+};

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/BrowserTabController/style.scss

@@ -0,0 +1,71 @@
+@use "src/styles/variables" as *;
+
+$color-item-size: 28px;
+$outline-width: 2px;
+$outline-offset: 2px;
+$outline-space: $outline-width + $outline-offset;
+
+.vm-browser-tab-controller {
+  .vm-server-configurator__title {
+    padding-bottom: 2px;
+  }
+
+  &-palette {
+    display: flex;
+    align-items: flex-start;
+    justify-content: space-between;
+    gap: calc($padding-large * 2);
+
+    &-list {
+      display: flex;
+      align-items: center;
+      justify-content: flex-start;
+      flex-wrap: wrap;
+      gap: $padding-small;
+
+      &__item {
+        width: $color-item-size;
+        height: $color-item-size;
+        aspect-ratio: 1;
+        border-radius: 50%;
+        background-color: currentColor;
+        cursor: pointer;
+        transition-property: transform;
+        transition-duration: 0.15s;
+        transition-timing-function: linear;
+
+        &:hover {
+          transform: scale(1.1);
+        }
+
+        &:focus-visible {
+          transform: scale(1.1);
+        }
+
+        &_reset {
+          display: flex;
+          align-items: center;
+          justify-content: center;
+          background: transparent;
+          border: $border-divider;
+          color: $color-text-disabled;
+          padding: calc($padding-small / 2);
+        }
+
+        &_selected {
+          width: $color-item-size - 2 * $outline-space;
+          height: $color-item-size - 2 * $outline-space;
+          margin: $outline-space;
+          outline: $outline-width solid currentColor;
+          outline-offset: $outline-offset;
+          pointer-events: none;
+        }
+      }
+    }
+
+    &__preview {
+      width: $color-item-size;
+      height: auto;
+    }
+  }
+}

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/GlobalSettings.tsx

@@ -8,10 +8,12 @@ import Tooltip from "../../Main/Tooltip/Tooltip";
 import LimitsConfigurator from "./LimitsConfigurator/LimitsConfigurator";
 import { getAppModeEnable } from "../../../utils/app-mode";
 import classNames from "classnames";
-import Timezones from "./Timezones/Timezones";
+import TimezonesPicker from "./Timezones/TimezonesPicker";
 import ThemeControl from "../ThemeControl/ThemeControl";
 import useDeviceDetect from "../../../hooks/useDeviceDetect";
 import useBoolean from "../../../hooks/useBoolean";
+import BrowserTabController from "./BrowserTabController/BrowserTabController";
+import LegendCollapseController from "./LegendCollapseController/LegendCollapseController";
 
 const title = "Settings";
 
@@ -26,7 +28,6 @@ const GlobalSettings: FC = () => {
 
   const serverSettingRef = useRef<ChildComponentHandle>(null);
   const limitsSettingRef = useRef<ChildComponentHandle>(null);
-  const timezoneSettingRef = useRef<ChildComponentHandle>(null);
 
   const {
     value: open,
@@ -37,7 +38,6 @@ const GlobalSettings: FC = () => {
   const handleApply = () => {
     serverSettingRef.current && serverSettingRef.current.handleApply();
     limitsSettingRef.current && limitsSettingRef.current.handleApply();
-    timezoneSettingRef.current && timezoneSettingRef.current.handleApply();
     handleClose();
   };
 
@@ -49,6 +49,10 @@ const GlobalSettings: FC = () => {
         onClose={handleClose}
       />
     },
+    {
+      show: true,
+      component: <TimezonesPicker/>
+    },
     {
       show: true,
       component: <LimitsConfigurator
@@ -58,12 +62,16 @@ const GlobalSettings: FC = () => {
     },
     {
       show: true,
-      component: <Timezones ref={timezoneSettingRef}/>
+      component: <LegendCollapseController/>
     },
     {
       show: !appModeEnable,
       component: <ThemeControl/>
-    }
+    },
+    {
+      show: true,
+      component: <BrowserTabController/>
+    },
   ].filter(control => control.show);
 
   return <>

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/LegendCollapseController/LegendCollapseController.tsx

@@ -0,0 +1,30 @@
+import { FC, useEffect, useState } from "preact/compat";
+import { getFromStorage, saveToStorage } from "../../../../utils/storage";
+import Switch from "../../../Main/Switch/Switch";
+import { LEGEND_COLLAPSE_SERIES_LIMIT } from "../../../../constants/graph";
+import "./style.scss";
+
+const LegendCollapseController: FC = () => {
+  const storageCollapse = getFromStorage("LEGEND_AUTO_COLLAPSE");
+  const [legendCollapse, setLegendCollapse] = useState(storageCollapse ? storageCollapse === "true" : true);
+
+  useEffect(() => {
+    saveToStorage("LEGEND_AUTO_COLLAPSE", `${legendCollapse}`);
+  }, [legendCollapse]);
+
+  return (
+    <div className="vm-legend-collapse-controller">
+      <Switch
+        fullWidth
+        color="neutral"
+        value={legendCollapse}
+        onChange={setLegendCollapse}
+        label={<span className="vm-server-configurator__title">Auto-collapse legend</span>}
+      />
+      <span className="vm-legend-collapse-controller__description">
+        Collapses the legend when series count exceeds {LEGEND_COLLAPSE_SERIES_LIMIT} to reduce UI load.
+      </span>
+    </div>);
+};
+
+export default LegendCollapseController;

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/LegendCollapseController/style.scss

@@ -0,0 +1,19 @@
+@use "src/styles/variables" as *;
+
+.vm-legend-collapse-controller {
+  background-color: $color-hover-black;
+  border-radius: $border-radius-medium;
+  padding: $padding-large;
+  border: $border-divider;
+
+  .vm-graph-settings-row__label {
+    margin: 0;
+  }
+
+  &__description {
+    padding-top: $padding-global;
+    font-size: $font-size-small;
+    line-height: 1.3;
+    text-wrap: pretty;
+  }
+}

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/LimitsConfigurator/LimitsConfigurator.tsx

@@ -1,23 +1,21 @@
-import { forwardRef, useCallback, useEffect, useImperativeHandle, useState } from "preact/compat";
+import { forwardRef, useCallback, useImperativeHandle, useState } from "preact/compat";
 import { DisplayType, ErrorTypes } from "../../../../types";
 import TextField from "../../../Main/TextField/TextField";
 import Tooltip from "../../../Main/Tooltip/Tooltip";
 import { InfoIcon, RestartIcon } from "../../../Main/Icons";
 import Button from "../../../Main/Button/Button";
-import { DEFAULT_MAX_SERIES, LEGEND_COLLAPSE_SERIES_LIMIT } from "../../../../constants/graph";
+import { DEFAULT_MAX_SERIES } from "../../../../constants/graph";
 import "./style.scss";
 import classNames from "classnames";
 import useDeviceDetect from "../../../../hooks/useDeviceDetect";
 import { ChildComponentHandle } from "../GlobalSettings";
 import { useCustomPanelDispatch, useCustomPanelState } from "../../../../state/customPanel/CustomPanelStateContext";
-import Switch from "../../../Main/Switch/Switch";
-import { getFromStorage, saveToStorage } from "../../../../utils/storage";
 
 interface ServerConfiguratorProps {
-  onClose: () => void
+  onClose: () => void;
 }
 
-const fields: {label: string, type: DisplayType}[] = [
+const fields: { label: string, type: DisplayType }[] = [
   { label: "Graph", type: DisplayType.chart },
   { label: "JSON", type: DisplayType.code },
   { label: "Table", type: DisplayType.table }
@@ -29,8 +27,7 @@ const LimitsConfigurator = forwardRef<ChildComponentHandle, ServerConfiguratorPr
   const { seriesLimits } = useCustomPanelState();
   const customPanelDispatch = useCustomPanelDispatch();
 
-  const storageCollapse = getFromStorage("LEGEND_AUTO_COLLAPSE");
-  const [legendCollapse, setLegendCollapse] = useState(storageCollapse ? storageCollapse === "true" : true);
+
 
   const [limits, setLimits] = useState(seriesLimits);
   const [error, setError] = useState({
@@ -43,7 +40,7 @@ const LimitsConfigurator = forwardRef<ChildComponentHandle, ServerConfiguratorPr
     setLimits(DEFAULT_MAX_SERIES);
   };
 
-  const createChangeHandler = (type: DisplayType) =>  (val: string) => {
+  const createChangeHandler = (type: DisplayType) => (val: string) => {
     const value = val || "";
     setError(prev => ({ ...prev, [type]: +value < 0 ? ErrorTypes.positiveNumber : "" }));
     setLimits({
@@ -57,10 +54,6 @@ const LimitsConfigurator = forwardRef<ChildComponentHandle, ServerConfiguratorPr
     onClose();
   }, [limits]);
 
-  useEffect(() => {
-    saveToStorage("LEGEND_AUTO_COLLAPSE", `${legendCollapse}`);
-  }, [legendCollapse]);
-
   useImperativeHandle(ref, () => ({ handleApply }), [handleApply]);
 
   return (
@@ -106,19 +99,6 @@ const LimitsConfigurator = forwardRef<ChildComponentHandle, ServerConfiguratorPr
           </div>
         ))}
       </div>
-
-      <div className="vm-graph-settings-row">
-        <span className="vm-graph-settings-row__label">Auto-collapse legend</span>
-        <Switch
-          value={legendCollapse}
-          onChange={setLegendCollapse}
-          label={legendCollapse ? "Enabled" : "Disabled"}
-          fullWidth={isMobile}
-        />
-        <span className="vm-legend-configs-item__info">
-          Collapses the legend when series count exceeds {LEGEND_COLLAPSE_SERIES_LIMIT} to reduce UI load.
-        </span>
-      </div>
     </div>
   );
 });

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/Timezones/Timezones.tsx

@@ -1,183 +0,0 @@
-import { FC, forwardRef, useEffect, useImperativeHandle, useMemo, useRef, useState } from "preact/compat";
-import { getBrowserTimezone, getTimezoneList, getUTCByTimezone } from "../../../../utils/time";
-import { ArrowDropDownIcon } from "../../../Main/Icons";
-import classNames from "classnames";
-import Popper from "../../../Main/Popper/Popper";
-import Accordion from "../../../Main/Accordion/Accordion";
-import TextField from "../../../Main/TextField/TextField";
-import { Timezone } from "../../../../types";
-import "./style.scss";
-import useDeviceDetect from "../../../../hooks/useDeviceDetect";
-import useBoolean from "../../../../hooks/useBoolean";
-import WarningTimezone from "./WarningTimezone";
-import { useTimeDispatch, useTimeState } from "../../../../state/time/TimeStateContext";
-
-interface PinnedTimezone extends Timezone {
-  title: string;
-  isInvalid?: boolean;
-}
-
-const browserTimezone = getBrowserTimezone();
-
-const Timezones: FC = forwardRef((props, ref) => {
-  const { isMobile } = useDeviceDetect();
-  const timezones = getTimezoneList();
-
-  const { timezone: stateTimezone, defaultTimezone } = useTimeState();
-  const timeDispatch = useTimeDispatch();
-
-  const [timezone, setTimezone] = useState(stateTimezone);
-  const [search, setSearch] = useState("");
-  const targetRef = useRef<HTMLDivElement>(null);
-
-  const {
-    value: openList,
-    toggle: toggleOpenList,
-    setFalse: handleCloseList,
-  } = useBoolean(false);
-
-  const pinnedTimezones = useMemo(() => [
-    {
-      title: `Default time (${defaultTimezone})`,
-      region: defaultTimezone,
-      utc: defaultTimezone ? getUTCByTimezone(defaultTimezone) : "UTC"
-    },
-    {
-      title: browserTimezone.title,
-      region: browserTimezone.region,
-      utc: getUTCByTimezone(browserTimezone.region),
-      isInvalid: !browserTimezone.isValid
-    },
-    {
-      title: "UTC (Coordinated Universal Time)",
-      region: "UTC",
-      utc: "UTC"
-    },
-  ].filter(t => t.region) as PinnedTimezone[], [defaultTimezone]);
-
-  const searchTimezones = useMemo(() => {
-    if (!search) return timezones;
-    try {
-      return getTimezoneList(search);
-    } catch (e) {
-      return {};
-    }
-  }, [search, timezones]);
-
-  const timezonesGroups = useMemo(() => Object.keys(searchTimezones), [searchTimezones]);
-
-  const activeTimezone = useMemo(() => ({
-    region: timezone,
-    utc: getUTCByTimezone(timezone)
-  }), [timezone]);
-
-  const handleChangeSearch = (val: string) => {
-    setSearch(val);
-  };
-
-  const handleSetTimezone = (val: Timezone) => {
-    setTimezone(val.region);
-    setSearch("");
-    handleCloseList();
-  };
-
-  const createHandlerSetTimezone = (val: Timezone) => () => {
-    handleSetTimezone(val);
-  };
-
-  useEffect(() => {
-    setTimezone(stateTimezone);
-  }, [stateTimezone]);
-
-  useImperativeHandle(ref, () => ({
-    handleApply: () => {
-      timeDispatch({ type: "SET_TIMEZONE", payload: timezone });
-    }
-  }), [timezone]);
-
-  return (
-    <div className="vm-timezones">
-      <div className="vm-server-configurator__title">
-        Time zone
-      </div>
-      <div
-        className="vm-timezones-item vm-timezones-item_selected"
-        onClick={toggleOpenList}
-        ref={targetRef}
-      >
-        <div className="vm-timezones-item__title">{activeTimezone.region}</div>
-        <div className="vm-timezones-item__utc">{activeTimezone.utc}</div>
-        <div
-          className={classNames({
-            "vm-timezones-item__icon": true,
-            "vm-timezones-item__icon_open": openList
-          })}
-        >
-          <ArrowDropDownIcon/>
-        </div>
-      </div>
-      <Popper
-        open={openList}
-        buttonRef={targetRef}
-        placement="bottom-left"
-        onClose={handleCloseList}
-        fullWidth
-        title={isMobile ? "Time zone" : undefined}
-      >
-        <div
-          className={classNames({
-            "vm-timezones-list": true,
-            "vm-timezones-list_mobile": isMobile,
-          })}
-        >
-          <div className="vm-timezones-list-header">
-            <div className="vm-timezones-list-header__search">
-              <TextField
-                autofocus
-                label="Search"
-                value={search}
-                onChange={handleChangeSearch}
-              />
-            </div>
-            {pinnedTimezones.map((t, i) => t && (
-              <div
-                key={`${i}_${t.region}`}
-                className="vm-timezones-item vm-timezones-list-group-options__item"
-                onClick={createHandlerSetTimezone(t)}
-              >
-                <div className="vm-timezones-item__title">{t.title}{t.isInvalid && <WarningTimezone/>}</div>
-                <div className="vm-timezones-item__utc">{t.utc}</div>
-              </div>
-            ))}
-          </div>
-          {timezonesGroups.map(t => (
-            <div
-              className="vm-timezones-list-group"
-              key={t}
-            >
-              <Accordion
-                defaultExpanded={true}
-                title={<div className="vm-timezones-list-group__title">{t}</div>}
-              >
-                <div className="vm-timezones-list-group-options">
-                  {searchTimezones[t] && searchTimezones[t].map(item => (
-                    <div
-                      className="vm-timezones-item vm-timezones-list-group-options__item"
-                      onClick={createHandlerSetTimezone(item)}
-                      key={item.search}
-                    >
-                      <div className="vm-timezones-item__title">{item.region}</div>
-                      <div className="vm-timezones-item__utc">{item.utc}</div>
-                    </div>
-                  ))}
-                </div>
-              </Accordion>
-            </div>
-          ))}
-        </div>
-      </Popper>
-    </div>
-  );
-});
-
-export default Timezones;

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/Timezones/TimezonesList.tsx

@@ -0,0 +1,129 @@
+import { FC, useMemo, useState } from "preact/compat";
+import { getBrowserTimezone, getTimezoneList, getUTCByTimezone } from "../../../../utils/time";
+import classNames from "classnames";
+import Accordion from "../../../Main/Accordion/Accordion";
+import TextField from "../../../Main/TextField/TextField";
+import { Timezone } from "../../../../types";
+import "./style.scss";
+import useDeviceDetect from "../../../../hooks/useDeviceDetect";
+import WarningTimezone from "./WarningTimezone";
+import { useTimeState } from "../../../../state/time/TimeStateContext";
+
+interface PinnedTimezone extends Timezone {
+  title: string;
+  isInvalid?: boolean;
+}
+
+type Props = {
+  onChange: (tz: Timezone) => void;
+}
+
+const browserTimezone = getBrowserTimezone();
+
+const TimezonesList: FC<Props> = ({ onChange }) => {
+  const { isMobile } = useDeviceDetect();
+  const { defaultTimezone } = useTimeState();
+
+  const timezones = useMemo(() => getTimezoneList(), []);
+
+  const [search, setSearch] = useState("");
+
+  const pinnedTimezones = useMemo(() => [
+    {
+      title: `Default time (${defaultTimezone})`,
+      region: defaultTimezone,
+      utc: defaultTimezone ? getUTCByTimezone(defaultTimezone) : "UTC"
+    },
+    {
+      title: browserTimezone.title,
+      region: browserTimezone.region,
+      utc: getUTCByTimezone(browserTimezone.region),
+      isInvalid: !browserTimezone.isValid
+    },
+    {
+      title: "UTC (Coordinated Universal Time)",
+      region: "UTC",
+      utc: "UTC"
+    },
+  ].filter(t => t.region) as PinnedTimezone[], [defaultTimezone]);
+
+  const searchTimezones = useMemo(() => {
+    if (!search) return timezones;
+    try {
+      return getTimezoneList(search);
+    } catch (e) {
+      return {};
+    }
+  }, [search, timezones]);
+
+  const timezonesGroups = useMemo(() => Object.keys(searchTimezones), [searchTimezones]);
+
+  const handleChangeSearch = (val: string) => {
+    setSearch(val);
+  };
+
+  const handleSetTimezone = (tz: Timezone) => {
+    onChange(tz);
+    setSearch("");
+  };
+
+  const createHandlerSetTimezone = (val: Timezone) => () => {
+    handleSetTimezone(val);
+  };
+
+  return (
+    <div
+      className={classNames({
+        "vm-list": true,
+        "vm-timezones-list": true,
+        "vm-timezones-list_mobile": isMobile,
+      })}
+    >
+      <div className="vm-timezones-list-header">
+        <div className="vm-timezones-list-header__search">
+          <TextField
+            label="Search"
+            value={search}
+            onChange={handleChangeSearch}
+          />
+        </div>
+      </div>
+      {pinnedTimezones.map((t, i) => t && (
+        <div
+          key={`${i}_${t.region}`}
+          className="vm-list-item vm-timezones-item vm-timezones-list-group-options__item"
+          onClick={createHandlerSetTimezone(t)}
+        >
+          <div className="vm-timezones-item__title">{t.title}{t.isInvalid && <WarningTimezone/>}</div>
+          <div className="vm-timezones-item__utc">{t.utc}</div>
+        </div>
+      ))}
+      {timezonesGroups.map(t => (
+        <div
+          className="vm-timezones-list-group"
+          key={t}
+        >
+          <Accordion
+            defaultExpanded={true}
+            title={<div className="vm-timezones-list-group__title">{t}</div>}
+          >
+            <div className="vm-timezones-list-group-options">
+              {searchTimezones[t] && searchTimezones[t].map(item => (
+                <div
+                  className="vm-list-item vm-timezones-item vm-timezones-list-group-options__item"
+                  onClick={createHandlerSetTimezone(item)}
+                  key={item.search}
+                >
+                  <div className="vm-timezones-item__title">{item.region}</div>
+                  <div className="vm-timezones-item__utc">{item.utc}</div>
+                </div>
+              ))}
+            </div>
+          </Accordion>
+        </div>
+      ))}
+    </div>
+  );
+};
+
+export default TimezonesList;

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/Timezones/TimezonesPicker.tsx

@@ -0,0 +1,71 @@
+import { FC, useMemo, useRef } from "preact/compat";
+import { getUTCByTimezone } from "../../../../utils/time";
+import { ArrowDropDownIcon } from "../../../Main/Icons";
+import classNames from "classnames";
+import { Timezone } from "../../../../types";
+import "./style.scss";
+import useBoolean from "../../../../hooks/useBoolean";
+import { useTimeDispatch, useTimeState } from "../../../../state/time/TimeStateContext";
+import TimezonesList from "./TimezonesList";
+import Popper from "../../../Main/Popper/Popper";
+import useDeviceDetect from "../../../../hooks/useDeviceDetect";
+
+const TimezonesPicker: FC = () => {
+  const { isMobile } = useDeviceDetect();
+  const { timezone: stateTimezone } = useTimeState();
+  const timeDispatch = useTimeDispatch();
+
+  const triggerRef = useRef<HTMLDivElement>(null);
+
+  const {
+    value: isOpenList,
+    toggle: toggleOpenList,
+    setFalse: handleCloseList,
+  } = useBoolean(false);
+
+  const activeTimezone = useMemo(() => ({
+    region: stateTimezone,
+    utc: getUTCByTimezone(stateTimezone)
+  }), [stateTimezone]);
+
+  const handleSetTimezone = (tz: Timezone) => {
+    timeDispatch({ type: "SET_TIMEZONE", payload: tz.region });
+    handleCloseList();
+  };
+
+  return (
+    <div className="vm-timezones">
+      <div className="vm-server-configurator__title">
+        Time zone
+      </div>
+      <div
+        className="vm-timezones-item vm-timezones-item_selected"
+        onClick={toggleOpenList}
+        ref={triggerRef}
+      >
+        <div className="vm-timezones-item__title">{activeTimezone.region}</div>
+        <div className="vm-timezones-item__utc">{activeTimezone.utc}</div>
+        <div
+          className={classNames({
+            "vm-timezones-item__icon": true,
+            "vm-timezones-item__icon_open": isOpenList
+          })}
+        >
+          <ArrowDropDownIcon/>
+        </div>
+      </div>
+      <Popper
+        open={isOpenList}
+        buttonRef={triggerRef}
+        placement="bottom-left"
+        onClose={handleCloseList}
+        fullWidth
+        title={isMobile ? "Time zone" : undefined}
+      >
+        <TimezonesList onChange={handleSetTimezone}/>
+      </Popper>
+    </div>
+  );
+};
+
+export default TimezonesPicker;

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/Timezones/style.scss

@@ -16,6 +16,7 @@
     }
 
     &__title {
+      flex-grow: 1;
       display: flex;
       align-items: center;
       gap: $padding-small;
@@ -34,6 +35,7 @@
       background-color: $color-hover-black;
       padding: calc($padding-small/2);
       border-radius: $border-radius-small;
+      font-size: $font-size-small;
     }
 
     &__icon {
@@ -54,9 +56,11 @@
   }
 
   &-list {
+    padding-top: 0;
     max-height: 300px;
     background-color: $color-background-block;
     border-radius: $border-radius-medium;
+    font-size: $font-size-small;
     overflow: auto;
 
     &_mobile {
@@ -72,10 +76,9 @@
       top: 0;
       background-color: $color-background-block;
       z-index: 2;
-      border-bottom: $border-divider;
 
       &__search {
-        padding: $padding-small;
+        padding: $padding-small $padding-small calc($padding-small / 2);
       }
     }
 
@@ -91,6 +94,7 @@
         font-weight: bold;
         color: $color-text-secondary;
         padding: $padding-small $padding-global;
+        font-size: $font-size-small;
       }
 
       &-options {
@@ -98,7 +102,7 @@
         align-items: flex-start;
 
         &__item {
-          padding: $padding-small $padding-global;
+          padding: calc($padding-small / 2) $padding-global;
           transition: background-color 200ms ease;
 
           &:hover {

app/vmui/packages/vmui/src/components/Configurators/GlobalSettings/style.scss

@@ -4,9 +4,9 @@
   display: flex;
   flex-direction: column;
   align-items: center;
-  gap: $padding-large;
+  gap: calc($padding-global * 2);
   width: 600px;
-  padding-bottom: $padding-medium;
+  padding-inline: $padding-large;
 
   &_mobile {
     grid-auto-rows: min-content;
@@ -62,6 +62,7 @@
     justify-content: flex-end;
     gap: $padding-small;
     width: 100%;
+    padding-block: $padding-global;
   }
 
   &_mobile &-footer {

app/vmui/packages/vmui/src/components/Configurators/StepConfigurator/StepConfigurator.tsx

@@ -22,12 +22,10 @@ const StepConfigurator: FC = () => {
   const { isMobile } = useDeviceDetect();
 
   const { customStep: value, isHistogram } = useGraphState();
-  const { period: { step, end, start } } = useTimeState();
+  const { period: { end, start } } = useTimeState();
   const graphDispatch = useGraphDispatch();
   const { displayType } = useCustomPanelState();
 
-  const prevDuration = usePrevious(end - start);
-
   const defaultStep = useMemo(() => {
     return getStepFromDuration(end - start, isHistogram, displayType);
   }, [end, start, isHistogram, displayType]);
@@ -106,16 +104,14 @@ const StepConfigurator: FC = () => {
   }, [defaultStep]);
 
   useEffect(() => {
-    const dur = end - start;
-    if (dur === prevDuration || !prevDuration || value !== prevDefaultStep) return;
-    if (defaultStep) {
-      handleApply(defaultStep);
-    }
-  }, [prevDuration, defaultStep]);
+    if (!prevDefaultStep) return;
+    if (value !== prevDefaultStep) return;
+    if (value === defaultStep) return;
 
-  useEffect(() => {
-    if (step === value || step === defaultStep) handleApply(defaultStep);
-  }, [isHistogram, displayType]);
+    graphDispatch({ type: "SET_CUSTOM_STEP", payload: defaultStep });
+    setCustomStep(defaultStep);
+    setError("");
+  }, [defaultStep, prevDefaultStep, value, graphDispatch]);
 
   return (
     <div

app/vmui/packages/vmui/src/components/Configurators/ThemeControl/ThemeControl.tsx

@@ -5,8 +5,20 @@ import useDeviceDetect from "../../../hooks/useDeviceDetect";
 import classNames from "classnames";
 import { FC } from "preact/compat";
 import { useAppDispatch, useAppState } from "../../../state/common/StateContext";
+import { DarkIcon, LightIcon, SystemIcon } from "../../Main/Icons";
+
+const themeIcons = {
+  [Theme.system]: <SystemIcon/>,
+  [Theme.light]: <LightIcon/>,
+  [Theme.dark]: <DarkIcon/>,
+};
+
+const options = Object.values(Theme).map(value => ({
+  title: value,
+  value,
+  icon: themeIcons[value],
+}));
 
-const options = Object.values(Theme).map(value => ({ title: value, value }));
 const ThemeControl: FC = () => {
   const { isMobile } = useDeviceDetect();
   const dispatch = useAppDispatch();
@@ -25,13 +37,14 @@ const ThemeControl: FC = () => {
       })}
     >
       <div className="vm-server-configurator__title">
-        Theme preferences
+        Theme
       </div>
       <div
         className="vm-theme-control__toggle"
         key={`${isMobile}`}
       >
         <Toggle
+          size="large"
           options={options}
           value={theme}
           onChange={handleClickItem}

app/vmui/packages/vmui/src/components/Configurators/ThemeControl/style.scss

@@ -4,7 +4,7 @@
 
   &__toggle {
     display: inline-flex;
-    min-width: 300px;
+    width: 100%;
     text-transform: capitalize;
   }
 

app/vmui/packages/vmui/src/components/Main/Icons/index.tsx

@@ -633,3 +633,60 @@ export const DebugIcon = () => (
     />
   </svg>
 );
+
+export const SystemIcon = () => (
+  <svg
+    viewBox="0 0 24 24"
+    fill="currentColor"
+  >
+    <path
+      d="M18 4C18.7957 4 19.5595 4.3163 20.1221 4.87891C20.6845 5.44148 21 6.20452 21 7V15.5264L21.0069 15.6426C21.0203 15.7579 21.0542 15.8702 21.1065 15.9746L22.1729 18.0996C22.3271 18.4056 22.4009 18.7466 22.3858 19.0889C22.3705 19.431 22.2675 19.7637 22.0869 20.0547C21.9063 20.3457 21.6534 20.5855 21.3535 20.751C21.0555 20.9154 20.7202 21.0003 20.3799 20.999L3.62013 21C3.28002 21.0012 2.94535 20.9153 2.64748 20.751C2.34748 20.5855 2.09477 20.3458 1.91408 20.0547C1.73343 19.7636 1.63047 19.4311 1.61525 19.0889C1.60006 18.7466 1.67297 18.4056 1.82716 18.0996L2.89455 15.9746L2.94045 15.8682C2.9801 15.7589 3.00007 15.6432 3.00002 15.5264V7C3.00002 6.20442 3.3164 5.4415 3.87892 4.87891C4.44146 4.31636 5.20447 4.00007 6.00002 4H18ZM4.62404 16.9873L3.61427 18.999L3.6133 19H20.3877L20.3867 18.999L19.376 16.9873H4.62404ZM6.00002 6C5.7349 6.00007 5.48045 6.1055 5.29298 6.29297C5.10554 6.48049 5.00002 6.73485 5.00002 7V14.9873H19V7C19 6.73478 18.8946 6.48051 18.707 6.29297C18.5195 6.10552 18.2652 6 18 6H6.00002Z"
+    />
+  </svg>
+);
+
+export const LightIcon = () => (
+  <svg
+    viewBox="0 0 24 24"
+    fill="currentColor"
+  >
+    <path
+      d="M12 19C12.5523 19 13 19.4477 13 20V22C13 22.5523 12.5523 23 12 23C11.4477 23 11 22.5523 11 22V20C11 19.4477 11.4477 19 12 19Z"
+    />
+    <path
+      d="M5.63281 16.9531C6.02334 16.5627 6.65638 16.5626 7.04688 16.9531C7.43717 17.3436 7.43725 17.9767 7.04688 18.3672L5.63672 19.7773C5.24625 20.1676 4.61313 20.1676 4.22266 19.7773C3.8322 19.3869 3.83233 18.7538 4.22266 18.3633L5.63281 16.9531Z"
+    />
+    <path
+      d="M16.9531 16.9531C17.3436 16.5626 17.9767 16.5626 18.3672 16.9531L19.7773 18.3633C20.1676 18.7538 20.1678 19.3869 19.7773 19.7773C19.3869 20.1677 18.7538 20.1675 18.3633 19.7773L16.9531 18.3672C16.5626 17.9767 16.5627 17.3437 16.9531 16.9531Z"
+    />
+    <path
+      d="M12 7C14.7614 7 17 9.23858 17 12C17 14.7614 14.7614 17 12 17C9.23858 17 7 14.7614 7 12C7 9.23858 9.23858 7 12 7ZM12 9C10.3431 9 9 10.3431 9 12C9 13.6569 10.3431 15 12 15C13.6569 15 15 13.6569 15 12C15 10.3431 13.6569 9 12 9Z"
+    />
+    <path
+      d="M4 11C4.55228 11 5 11.4477 5 12C5 12.5523 4.55228 13 4 13H2C1.44772 13 1 12.5523 1 12C1 11.4477 1.44772 11 2 11H4Z"
+    />
+    <path
+      d="M22 11C22.5523 11 23 11.4477 23 12C23 12.5523 22.5523 13 22 13H20C19.4477 13 19 12.5523 19 12C19 11.4477 19.4477 11 20 11H22Z"
+    />
+    <path
+      d="M4.22266 4.22266C4.61315 3.83229 5.24623 3.83229 5.63672 4.22266L7.04688 5.63281C7.4372 6.02331 7.43723 6.65639 7.04688 7.04688C6.6564 7.43735 6.02335 7.43724 5.63281 7.04688L4.22266 5.63672C3.83225 5.24618 3.83217 4.61314 4.22266 4.22266Z"
+    />
+    <path
+      d="M18.3633 4.22266C18.7538 3.83237 19.3869 3.83232 19.7773 4.22266C20.1677 4.61312 20.1676 5.2462 19.7773 5.63672L18.3672 7.04688C17.9767 7.4373 17.3436 7.4373 16.9531 7.04688C16.5627 6.65637 16.5627 6.0233 16.9531 5.63281L18.3633 4.22266Z"
+    />
+    <path
+      d="M12 1C12.5523 1 13 1.44772 13 2V4C13 4.55228 12.5523 5 12 5C11.4477 5 11 4.55228 11 4V2C11 1.44772 11.4477 1 12 1Z"
+    />
+  </svg>
+);
+
+export const DarkIcon = () => (
+  <svg
+    viewBox="0 0 24 24"
+    fill="currentColor"
+  >
+    <path
+      d="M11.5809 2.01318C12.1851 2.02907 12.6373 2.40742 12.8475 2.84717C13.0627 3.29758 13.0619 3.86893 12.7615 4.34814L12.7606 4.34717C12.1616 5.30581 11.9061 6.43987 12.034 7.56299C12.162 8.68628 12.6672 9.73328 13.4666 10.5327C14.2661 11.332 15.3131 11.8364 16.4363 11.9644C17.5596 12.0922 18.6934 11.836 19.6522 11.2368L19.8348 11.1382C20.2701 10.9405 20.7563 10.9617 21.1512 11.1499C21.6217 11.3742 22.0194 11.8752 21.9832 12.5405C21.8789 14.4693 21.2181 16.3268 20.0809 17.8882C18.9435 19.4496 17.378 20.6484 15.574 21.3394C13.7701 22.0302 11.8042 22.184 9.91485 21.7817C8.02549 21.3794 6.29356 20.4376 4.92754 19.0718C3.56149 17.7059 2.62012 15.9739 2.21758 14.0845C1.81507 12.195 1.96826 10.2294 2.65899 8.42529C3.34975 6.62115 4.5487 5.05596 6.11016 3.91846C7.6716 2.781 9.52882 2.11947 11.4578 2.01514L11.5809 2.01318ZM10.6209 4.12061C9.42038 4.33038 8.27873 4.81214 7.28692 5.53467C6.03798 6.44459 5.07973 7.69705 4.52715 9.14014C3.97456 10.5834 3.85165 12.156 4.17364 13.6675C4.49565 15.179 5.24872 16.5649 6.34161 17.6577C7.43448 18.7505 8.82026 19.5038 10.3318 19.8257C11.8434 20.1475 13.416 20.0239 14.8592 19.4712C16.3024 18.9184 17.5548 17.9597 18.4647 16.7104C19.1869 15.7188 19.6671 14.5776 19.8768 13.3774C18.7333 13.8927 17.4674 14.0949 16.2098 13.9517C14.637 13.7725 13.1709 13.0661 12.0516 11.9468C10.9324 10.8275 10.2258 9.36126 10.0467 7.78857C9.90352 6.53075 10.1054 5.26417 10.6209 4.12061Z"
+    />
+  </svg>
+);

app/vmui/packages/vmui/src/components/Main/Switch/Switch.tsx

@@ -1,11 +1,10 @@
-import { ReactNode } from "react";
+import { FC, ReactNode } from "preact/compat";
 import classNames from "classnames";
 import "./style.scss";
-import { FC } from "preact/compat";
 
 interface SwitchProps {
   value: boolean
-  color?: "primary" | "secondary" | "error"
+  color?: "primary" | "secondary" | "error" | "neutral"
   disabled?: boolean
   label?: string | ReactNode
   fullWidth?: boolean

app/vmui/packages/vmui/src/components/Main/Switch/style.scss

@@ -29,6 +29,10 @@ $switch-border-radius: $switch-handle-size + ($switch-padding * 2);
     background-color: $color-secondary;
   }
 
+  &_neutral_active &-track {
+    background-color: $color-text;
+  }
+
   &_primary_active &-track {
     background-color: $color-primary;
   }

app/vmui/packages/vmui/src/components/Main/Toggle/Toggle.tsx

@@ -1,22 +1,21 @@
-import { FC, useEffect, useRef, useState } from "preact/compat";
+import { FC, useEffect, useRef, useState, ReactNode } from "preact/compat";
 import classNames from "classnames";
-import { ReactNode } from "react";
 import "./style.scss";
 
 interface ToggleProps {
-  options: {value: string, title?: string, icon?: ReactNode}[]
-  value: string
-  onChange: (val: string) => void
-  label?: string
+  options: { value: string, title?: string, icon?: ReactNode }[];
+  value: string;
+  onChange: (val: string) => void;
+  label?: string;
+  size?: "medium" | "large";
 }
 
-const Toggle: FC<ToggleProps> = ({ options, value, label, onChange }) => {
+const Toggle: FC<ToggleProps> = ({ options, value, label, size = "medium", onChange }) => {
 
   const activeRef = useRef<HTMLDivElement>(null);
   const [position, setPosition] = useState({
     width: "0px",
     left: "0px",
-    borderRadius: "0px"
   });
 
   const createHandlerChange = (value: string) => () => {
@@ -28,35 +27,25 @@ const Toggle: FC<ToggleProps> = ({ options, value, label, onChange }) => {
       setPosition({
         width: "0px",
         left: "0px",
-        borderRadius: "0px"
       });
       return;
     }
     const index = options.findIndex(o => o.value === value);
     const { width: widthRect } = activeRef.current.getBoundingClientRect();
 
-    let width = widthRect;
-    let left = index * width;
-    let borderRadius = "0";
-    if (index === 0) borderRadius = "16px 0 0 16px";
+    const width = widthRect;
+    const left = index * width;
 
-    if (index === options.length - 1) {
-      borderRadius = "10px";
-      left -= 1;
-      borderRadius = "0 16px 16px 0";
-    }
-
-    if (index !== 0 && (index !== options.length - 1)) {
-      width += 1;
-      left -= 1;
-    }
-
-
-    setPosition({ width: `${width}px`, left: `${left}px`, borderRadius });
+    setPosition({ width: `${width}px`, left: `${left}px` });
   }, [activeRef, value, options]);
 
   return (
-    <div className="vm-toggles">
+    <div
+      className={classNames({
+        "vm-toggles": true,
+        [`vm-toggles_${size}`]: size,
+      })}
+    >
       {label && (
         <label className="vm-toggles__label">
           {label}
@@ -66,15 +55,14 @@ const Toggle: FC<ToggleProps> = ({ options, value, label, onChange }) => {
         className="vm-toggles-group"
         style={{ gridTemplateColumns: `repeat(${options.length}, 1fr)` }}
       >
-        {position.borderRadius && <div
+        <div
           className="vm-toggles-group__highlight"
           style={position}
-        />}
-        {options.map((option, i) => (
+        />
+        {options.map((option) => (
           <div
             className={classNames({
               "vm-toggles-group-item": true,
-              "vm-toggles-group-item_first": i === 0,
               "vm-toggles-group-item_active": option.value === value,
               "vm-toggles-group-item_icon": option.icon && option.title
             })}

app/vmui/packages/vmui/src/components/Main/Toggle/style.scss

@@ -20,6 +20,8 @@
     align-items: center;
     justify-content: center;
     overflow: hidden;
+    border-radius: $border-radius-small;
+    background: $color-hover-black;
 
     &-item {
       position: relative;
@@ -27,55 +29,68 @@
       align-items: center;
       justify-content: center;
       padding: $padding-small;
-      border-right: $border-divider;
-      border-top: $border-divider;
-      border-bottom: $border-divider;
       font-size: $font-size-small;
       color: $color-text-secondary;
-      font-weight: bold;
+      font-weight: 500;
       cursor: pointer;
       text-align: center;
-      transition: color 150ms ease-in;
+      transition: opacity 150ms ease-in, color 150ms ease-in;
       z-index: 2;
       user-select: none;
 
-      &_first {
-        border-radius: 16px 0 0 16px;
-        border-left: $border-divider
-      }
-
-      &:last-child {
-        border-radius: 0 16px 16px 0;
-        border-left: none;
-      }
-
       &_icon {
         grid-template-columns: 14px auto;
-        gap: 4px;
+        gap: calc($padding-small / 2);
       }
 
-      &:hover {
-        color: $color-primary;
+      &:hover:not(&_active) {
+        opacity: 0.8;
       }
 
       &_active {
-        color: $color-primary;
-        border-color: transparent;
-
-        &:hover {
-          background-color: transparent;
-        }
+        color: $color-text;
+        font-weight: 600;
       }
     }
 
     &__highlight {
       position: absolute;
       top: 0;
+      display: flex;
+      align-items: center;
+      justify-content: center;
+      padding: 3px;
       height: 100%;
       background-color: rgba($color-primary, 0.08);
-      border: 1px solid $color-primary;
       transition: left 200ms cubic-bezier(0.280, 0.840, 0.420, 1), border-radius 200ms linear;
       z-index: 1;
+
+      &:after {
+        content: '';
+        height: 100%;
+        width: 100%;
+        background-color: $color-background-block;
+        border-radius: $border-radius-small;
+        box-shadow: $box-shadow;
+      }
+    }
+  }
+
+  &_large &-group {
+    border-radius: $border-radius-medium;
+
+    &-item {
+      padding: $padding-global $padding-small;
+
+      &_icon {
+        grid-template-columns: 16px auto;
+        gap: $padding-small;
+      }
+    }
+
+    &__highlight {
+      padding: 4px;
+      border-radius: $border-radius-medium;
     }
   }
 }

app/vmui/packages/vmui/src/constants/faviconColors.ts

@@ -0,0 +1,14 @@
+export const faviconColors = [
+  "#A1A1AA",
+  "#71717A",
+  "#020202",
+  "#E94600",
+  "#FF7A00",
+  "#F2B705",
+  "#84CC16",
+  "#16B86A",
+  "#00AFAF",
+  "#2979FF",
+  "#8B5CF6",
+  "#E83E9A",
+] as const;

app/vmui/packages/vmui/src/layouts/MainLayout/MainLayout.tsx

@@ -14,6 +14,9 @@ import useFetchDefaultTimezone from "../../hooks/useFetchDefaultTimezone";
 import useFetchAppConfig from "../../hooks/useFetchAppConfig";
 import WebStorageCheck from "../../components/WebStorageCheck/WebStorageCheck";
 import { migrateStorageToPrefixedKeys } from "../../utils/storage";
+import {
+  useBrowserTabSync
+} from "../../components/Configurators/GlobalSettings/BrowserTabController/hooks/useBrowserTabSync";
 
 const MainLayout: FC = () => {
   const appModeEnable = getAppModeEnable();
@@ -21,6 +24,7 @@ const MainLayout: FC = () => {
   const { pathname } = useLocation();
   const [searchParams, setSearchParams] = useSearchParams();
 
+  useBrowserTabSync();
   useFetchDashboards();
   useFetchDefaultTimezone();
   useFetchAppConfig();

app/vmui/packages/vmui/src/utils/favicon.tsx

@@ -0,0 +1,29 @@
+import faviconRaw from "../../assets/favicon.svg?raw";
+
+export const createFaviconUrl = (color = "#020202"): string => {
+  const svgDocument = new DOMParser().parseFromString(faviconRaw, "image/svg+xml");
+  const svg = svgDocument.documentElement;
+
+  if (svg.localName !== "svg") {
+    throw new Error("Invalid favicon SVG");
+  }
+
+  svg.setAttribute("fill", color);
+
+  const serializedSvg = new XMLSerializer().serializeToString(svg);
+  return `data:image/svg+xml;charset=utf-8,${encodeURIComponent(serializedSvg)}`;
+};
+
+export const updateFaviconColor = (color = "#020202"): void => {
+  const favicon = document.querySelector<HTMLLinkElement>("#favicon");
+  if (favicon) {
+    favicon.href = createFaviconUrl(color);
+  }
+
+  const maskIcon = document.querySelector<HTMLLinkElement>("#mask-icon");
+  if (maskIcon) {
+    maskIcon.setAttribute("color", color);
+  }
+};
+
+export const getFaviconStorageKey = () => window.location.pathname.replace(/\/+$/, "") || "/";

app/vmui/packages/vmui/src/utils/storage.ts

@@ -17,7 +17,11 @@ export const ALL_STORAGE_KEYS = [
   "POINTS_SHOW_ALL",
 ] as const;
 
-export type StorageKeys = (typeof ALL_STORAGE_KEYS)[number];
+export type FaviconStorageKey = `FAVICON_COLOR:${string}`;
+
+export type StorageKeys =
+  | (typeof ALL_STORAGE_KEYS)[number]
+  | FaviconStorageKey;
 
 type PrefixedStorageKeys = `${typeof STORAGE_PREFIX}${StorageKeys}`;
 
@@ -58,7 +62,10 @@ export const getFromStorage = (key: StorageKeys, withPrefix = true): undefined |
 
 export const removeFromStorage = (keys: StorageKeys[], withPrefix = true): void => {
   const storageKeys = withPrefix ? keys.map(toPrefixedKey) : keys;
-  storageKeys.forEach(k => window.localStorage.removeItem(k));
+  storageKeys.forEach(k => {
+    window.localStorage.removeItem(k);
+    window.dispatchEvent(new StorageEvent("storage", { key: k }));
+  });
 };
 
 /**

app/vmui/packages/vmui/src/utils/time.ts

@@ -205,19 +205,21 @@ export const getUTCByTimezone = (timezone: string) => {
 };
 
 export const getTimezoneList = (search = "") => {
-  const regexp = new RegExp(search, "i");
+  const normalizedSearch = search.toLowerCase();
 
-  return supportedTimezones.reduce((acc: {[key: string]: Timezone[]}, region) => {
+  return supportedTimezones.reduce((acc: { [key: string]: Timezone[] }, region) => {
     const zone = (region.match(/^(.*?)\//) || [])[1] || "unknown";
     const utc = getUTCByTimezone(region);
-    const utcForSearch = utc.replace(/UTC|0/, "");
+    const utcForSearch = utc.replace(/^UTC/, "");
     const regionForSearch = region.replace(/[/_]/g, " ");
+
     const item = {
       region,
       utc,
       search: `${region} ${utc} ${regionForSearch} ${utcForSearch}`
     };
-    const includeZone = !search || (search && regexp.test(item.search));
+
+    const includeZone = !normalizedSearch || item.search.toLowerCase().includes(normalizedSearch);
 
     if (includeZone && acc[zone]) {
       acc[zone].push(item);

app/vmui/packages/vmui/vite.config.ts

@@ -50,6 +50,13 @@ export default defineConfig(() => {
               return "vendor";
             }
           },
+          assetFileNames: (assetInfo) => {
+            if (assetInfo.names.includes("favicon.svg")) {
+              return "assets/favicon.svg";
+            }
+
+            return "assets/[name]-[hash][extname]";
+          },
         },
       },
     },

apptest/client.go

@@ -135,7 +135,7 @@ func tenantViaURL(addr, prefix, tenant, suffix string) string {
 }
 
 // tenantViaHeaders returns path in cluster's URL format where tenant is omitted in URL
-// Only supported if -enableMultitenancyViaHeaders is specified
+// Only supported if -enableMultitenancyViaHeaders is enabled
 func tenantViaHeaders(addr, prefix, suffix string) string {
 	return fmt.Sprintf("http://%s/%s/%s", addr, prefix, suffix)
 }

apptest/tests/multitenancy_via_headers_test.go

@@ -25,12 +25,10 @@ func TestClusterMultiTenantSelectViaHeaders(t *testing.T) {
 	})
 	vminsert := tc.MustStartVminsert("vminsert", []string{
 		"-storageNode=" + vmstorage.VminsertAddr(),
-		"-enableMultitenancyViaHeaders",
 	})
 	vmselect := tc.MustStartVmselect("vmselect", []string{
 		"-storageNode=" + vmstorage.VmselectAddr(),
 		"-search.tenantCacheExpireDuration=0",
-		"-enableMultitenancyViaHeaders",
 	})
 
 	multitenant := make(http.Header)

apptest/tests/per_day_index_test.go

@@ -26,33 +26,20 @@ func TestClusterSearchWithDisabledPerDayIndex(t *testing.T) {
 	defer tc.Stop()
 
 	testSearchWithDisabledPerDayIndex(tc, func(name string, disablePerDayIndex bool) apptest.PrometheusWriteQuerier {
-		// Using static ports for vmstorage because random ports may cause
-		// changes in how data is sharded.
-		vmstorage1 := tc.MustStartVmstorage("vmstorage1-"+name, []string{
-			"-storageDataPath=" + tc.Dir() + "/vmstorage1",
+		vmstorage := tc.MustStartVmstorage("vmstorage-"+name, []string{
+			"-storageDataPath=" + tc.Dir() + "/vmstorage",
 			"-retentionPeriod=100y",
-			"-httpListenAddr=127.0.0.1:61001",
-			"-vminsertAddr=127.0.0.1:61002",
-			"-vmselectAddr=127.0.0.1:61003",
-			fmt.Sprintf("-disablePerDayIndex=%t", disablePerDayIndex),
-		})
-		vmstorage2 := tc.MustStartVmstorage("vmstorage2-"+name, []string{
-			"-storageDataPath=" + tc.Dir() + "/vmstorage2",
-			"-retentionPeriod=100y",
-			"-httpListenAddr=127.0.0.1:62001",
-			"-vminsertAddr=127.0.0.1:62002",
-			"-vmselectAddr=127.0.0.1:62003",
 			fmt.Sprintf("-disablePerDayIndex=%t", disablePerDayIndex),
 		})
 		vminsert := tc.MustStartVminsert("vminsert-"+name, []string{
-			"-storageNode=" + vmstorage1.VminsertAddr() + "," + vmstorage2.VminsertAddr(),
+			"-storageNode=" + vmstorage.VminsertAddr(),
 		})
 		vmselect := tc.MustStartVmselect("vmselect"+name, []string{
-			"-storageNode=" + vmstorage1.VmselectAddr() + "," + vmstorage2.VmselectAddr(),
+			"-storageNode=" + vmstorage.VmselectAddr(),
 			"-search.maxStalenessInterval=1m",
 		})
 		return &apptest.Vmcluster{
-			Vmstorages: []*apptest.Vmstorage{vmstorage1, vmstorage2},
+			Vmstorages: []*apptest.Vmstorage{vmstorage},
 			Vminsert:   vminsert,
 			Vmselect:   vmselect,
 		}

apptest/tests/prometheus_mock_storage.go

@@ -59,7 +59,7 @@ func (ms *PrometheusMockStorage) Read(_ context.Context, query *prompb.Query, so
 		}
 
 		if !notMatch {
-			q.Timeseries = append(q.Timeseries, &prompb.TimeSeries{Labels: s.Labels, Samples: s.Samples})
+			q.Timeseries = append(q.Timeseries, &prompb.TimeSeries{Labels: s.Labels, Samples: s.Samples, Histograms: s.Histograms})
 		}
 	}
 

apptest/tests/remote_read_server.go

@@ -12,6 +12,7 @@ import (
 
 	"github.com/gogo/protobuf/proto"
 	"github.com/golang/snappy"
+	"github.com/prometheus/prometheus/model/histogram"
 	"github.com/prometheus/prometheus/model/labels"
 	"github.com/prometheus/prometheus/prompb"
 	"github.com/prometheus/prometheus/storage/remote"
@@ -86,10 +87,17 @@ func (rrs *RemoteReadServer) getReadHandler(t *testing.T) http.Handler {
 						samples = append(samples, sample)
 					}
 				}
+				var histograms []prompb.Histogram
+				for _, h := range s.Histograms {
+					if h.Timestamp >= startTs && h.Timestamp < endTs {
+						histograms = append(histograms, h)
+					}
+				}
 				var series prompb.TimeSeries
-				if len(samples) > 0 {
+				if len(samples) > 0 || len(histograms) > 0 {
 					series.Labels = s.Labels
 					series.Samples = samples
+					series.Histograms = histograms
 				}
 				ts[i] = &series
 			}
@@ -317,6 +325,37 @@ func generateRemoteReadSamples(idx int, startTime, endTime, numOfSamples int64)
 	return samples
 }
 
+// GenerateRemoteReadHistogramSeries generates a remote read series
+// with native histogram samples within the given time range.
+func GenerateRemoteReadHistogramSeries(start, end, numOfSamples int64) []*prompb.TimeSeries {
+	timeSeries := &prompb.TimeSeries{
+		Labels: []prompb.Label{
+			{Name: labels.MetricName, Value: "vm_histogram_metric"},
+			{Name: "job", Value: "0"},
+		},
+	}
+
+	delta := (end - start) / numOfSamples
+	mul := int64(0)
+	for t := start; t != end; t += delta {
+		mul++
+		h := &histogram.Histogram{
+			Schema:          0,
+			Count:           uint64(10 * mul),
+			Sum:             25.5 * float64(mul),
+			ZeroThreshold:   0.001,
+			ZeroCount:       uint64(2 * mul),
+			PositiveSpans:   []histogram.Span{{Offset: 0, Length: 2}},
+			PositiveBuckets: []int64{mul, 2 * mul},
+			NegativeSpans:   []histogram.Span{{Offset: 0, Length: 1}},
+			NegativeBuckets: []int64{4 * mul},
+		}
+		timeSeries.Histograms = append(timeSeries.Histograms, prompb.FromIntHistogram(t*1000, h))
+	}
+
+	return []*prompb.TimeSeries{timeSeries}
+}
+
 func labelsToLabelsProto(ls labels.Labels) []prompb.Label {
 	result := make([]prompb.Label, 0, ls.Len())
 	ls.Range(func(l labels.Label) {

apptest/tests/vmagent_remotewrite_test.go

@@ -594,7 +594,6 @@ func TestSingleVMAgentMultitenancy(t *testing.T) {
 		fmt.Sprintf(`-remoteWrite.url=%s/api/v1/write`, remoteWriteSrv.URL),
 		"-remoteWrite.tmpDataPath=" + tc.Dir() + "/vmagent-multitenancy",
 		"-enableMultitenantHandlers",
-		"-enableMultitenancyViaHeaders",
 	})
 
 	vmagent.APIV1ImportPrometheus(t, []string{

apptest/tests/vmctl_remote_read_mogration_test.go

@@ -75,6 +75,118 @@ func TestClusterVmctlRemoteReadProtocol(t *testing.T) {
 	testRemoteReadProtocol(tc, clusterDst, newRemoteReadServer, vmctlFlags)
 }
 
+func TestSingleVmctlRemoteReadNativeHistograms(t *testing.T) {
+	fs.MustRemoveDir(t.Name())
+
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+
+	vmsingleDst := tc.MustStartDefaultVmsingle()
+	vmAddr := fmt.Sprintf("http://%s/", vmsingleDst.HTTPAddr())
+	vmctlFlags := []string{
+		`remote-read`,
+		`--remote-read-filter-time-start=2025-06-11T15:31:10Z`,
+		`--remote-read-filter-time-end=2025-06-11T15:31:20Z`,
+		`--remote-read-step-interval=minute`,
+		`--vm-addr=` + vmAddr,
+		`--disable-progress-bar=true`,
+	}
+
+	testRemoteReadNativeHistograms(tc, vmsingleDst, NewRemoteReadServer, vmctlFlags)
+}
+
+func TestSingleVmctlRemoteReadStreamNativeHistograms(t *testing.T) {
+	fs.MustRemoveDir(t.Name())
+
+	tc := apptest.NewTestCase(t)
+	defer tc.Stop()
+
+	vmsingleDst := tc.MustStartDefaultVmsingle()
+	vmAddr := fmt.Sprintf("http://%s/", vmsingleDst.HTTPAddr())
+	vmctlFlags := []string{
+		`remote-read`,
+		`--remote-read-filter-time-start=2025-06-11T15:31:10Z`,
+		`--remote-read-filter-time-end=2025-06-11T15:31:20Z`,
+		`--remote-read-step-interval=minute`,
+		`--vm-addr=` + vmAddr,
+		`--remote-read-use-stream=true`,
+		`--disable-progress-bar=true`,
+	}
+
+	testRemoteReadNativeHistograms(tc, vmsingleDst, NewRemoteReadStreamServer, vmctlFlags)
+}
+
+// testRemoteReadNativeHistograms verifies that native histograms are migrated
+// as _count, _sum and _bucket series with vmrange labels in the same way
+// as VictoriaMetrics converts native histograms received via Prometheus remote write protocol.
+func testRemoteReadNativeHistograms(tc *apptest.TestCase, sut apptest.PrometheusWriteQuerier, newRemoteReadServer func(t *testing.T, series []*prompb.TimeSeries) *RemoteReadServer, vmctlFlags []string) {
+	t := tc.T()
+	t.Helper()
+
+	series := GenerateRemoteReadHistogramSeries(1749655870, 1749655880, 2)
+
+	rrs := newRemoteReadServer(t, series)
+	defer rrs.Close()
+
+	vmctlFlags = append(vmctlFlags, `--remote-read-src-addr=`+rrs.HTTPAddr())
+	tc.MustStartVmctl("vmctl", vmctlFlags)
+
+	sut.ForceFlush(t)
+
+	tc.Assert(&apptest.AssertOptions{
+		Retries: 300,
+		Msg:     `unexpected native histogram metrics stored on vmsingle via the prometheus protocol`,
+		Got: func() any {
+			got := sut.PrometheusAPIV1Export(t, `{__name__=~".*"}`, apptest.QueryOpts{
+				Start: "2025-06-11T15:31:10Z",
+				End:   "2025-06-11T15:32:20Z",
+			})
+			got.Sort()
+			return got.Data.Result
+		},
+		Want: expectedNativeHistogramQueryResult(),
+		CmpOpts: []cmp.Option{
+			cmpopts.IgnoreFields(apptest.PrometheusAPIV1QueryResponse{}, "Status", "Data.ResultType"),
+		},
+	})
+}
+
+// expectedNativeHistogramQueryResult returns the series expected to be stored in VictoriaMetrics
+// after migrating the series generated by GenerateRemoteReadHistogramSeries(1749655870, 1749655880, 2).
+func expectedNativeHistogramQueryResult() []*apptest.QueryResult {
+	metric := func(name, vmrange string) map[string]string {
+		m := map[string]string{
+			"__name__": name,
+			"job":      "0",
+		}
+		if vmrange != "" {
+			m["vmrange"] = vmrange
+		}
+		return m
+	}
+	samples := func(v1, v2 float64) []*apptest.Sample {
+		return []*apptest.Sample{
+			{Timestamp: 1749655870000, Value: v1},
+			{Timestamp: 1749655875000, Value: v2},
+		}
+	}
+	resp := &apptest.PrometheusAPIV1QueryResponse{
+		Data: &apptest.QueryData{
+			Result: []*apptest.QueryResult{
+				{Metric: metric("vm_histogram_metric_count", ""), Samples: samples(10, 20)},
+				{Metric: metric("vm_histogram_metric_sum", ""), Samples: samples(25.5, 51)},
+				{Metric: metric("vm_histogram_metric_bucket", "-1.000e+00...-5.000e-01"), Samples: samples(4, 8)},
+				{Metric: metric("vm_histogram_metric_bucket", "-1.000e-03...1.000e-03"), Samples: samples(2, 4)},
+				{Metric: metric("vm_histogram_metric_bucket", "5.000e-01...1.000e+00"), Samples: samples(1, 2)},
+				{Metric: metric("vm_histogram_metric_bucket", "1.000e+00...2.000e+00"), Samples: samples(3, 6)},
+			},
+		},
+	}
+	// sort in the same way as the exported result
+	resp.Sort()
+	return resp.Data.Result
+}
+
 func testRemoteReadProtocol(tc *apptest.TestCase, sut apptest.PrometheusWriteQuerier, newRemoteReadServer func(t *testing.T) *RemoteReadServer, vmctlFlags []string) {
 	t := tc.T()
 	t.Helper()

deployment/docker/Makefile

@@ -7,7 +7,7 @@ ROOT_IMAGE ?= alpine:3.24.1
 ROOT_IMAGE_SCRATCH ?= scratch
 CERTS_IMAGE := alpine:3.24.1
 
-GO_BUILDER_IMAGE := golang:1.26.5
+GO_BUILDER_IMAGE := golang:1.26.6
 
 BUILDER_IMAGE := local/builder:2.0.0-$(shell echo $(GO_BUILDER_IMAGE) | tr :/ __)-1
 BASE_IMAGE := local/base:1.1.4-$(shell echo $(ROOT_IMAGE) | tr :/ __)-$(shell echo $(CERTS_IMAGE) | tr :/ __)

deployment/docker/compose-vm-cluster.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.148.0
+    image: victoriametrics/vmagent:v1.149.0
     depends_on:
       - "vmauth"
     ports:
@@ -42,14 +42,14 @@ services:
   # vmstorage shards. Each shard receives 1/N of all metrics sent to vminserts,
   # where N is number of vmstorages (2 in this case).
   vmstorage-1:
-    image: victoriametrics/vmstorage:v1.148.0-cluster
+    image: victoriametrics/vmstorage:v1.149.0-cluster
     volumes:
       - strgdata-1:/storage
     command:
       - "--storageDataPath=/storage"
     restart: always
   vmstorage-2:
-    image: victoriametrics/vmstorage:v1.148.0-cluster
+    image: victoriametrics/vmstorage:v1.149.0-cluster
     volumes:
       - strgdata-2:/storage
     command:
@@ -59,7 +59,7 @@ services:
   # vminsert is ingestion frontend. It receives metrics pushed by vmagent,
   # pre-process them and distributes across configured vmstorage shards.
   vminsert-1:
-    image: victoriametrics/vminsert:v1.148.0-cluster
+    image: victoriametrics/vminsert:v1.149.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -68,7 +68,7 @@ services:
       - "--storageNode=vmstorage-2:8400"
     restart: always
   vminsert-2:
-    image: victoriametrics/vminsert:v1.148.0-cluster
+    image: victoriametrics/vminsert:v1.149.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -80,7 +80,7 @@ services:
   # vmselect is a query fronted. It serves read queries in MetricsQL or PromQL.
   # vmselect collects results from configured `--storageNode` shards.
   vmselect-1:
-    image: victoriametrics/vmselect:v1.148.0-cluster
+    image: victoriametrics/vmselect:v1.149.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -90,7 +90,7 @@ services:
       - "--vmalert.proxyURL=http://vmalert:8880"
     restart: always
   vmselect-2:
-    image: victoriametrics/vmselect:v1.148.0-cluster
+    image: victoriametrics/vmselect:v1.149.0-cluster
     depends_on:
       - "vmstorage-1"
       - "vmstorage-2"
@@ -105,7 +105,7 @@ services:
   # read requests from Grafana, vmui, vmalert among vmselects.
   # It can be used as an authentication proxy.
   vmauth:
-    image: victoriametrics/vmauth:v1.148.0
+    image: victoriametrics/vmauth:v1.149.0
     depends_on:
       - "vmselect-1"
       - "vmselect-2"
@@ -119,7 +119,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.148.0
+    image: victoriametrics/vmalert:v1.149.0
     depends_on:
       - "vmauth"
     ports:

deployment/docker/compose-vm-single.yml

@@ -3,7 +3,7 @@ services:
   #  It scrapes targets defined in --promscrape.config
   #  And forward them to --remoteWrite.url
   vmagent:
-    image: victoriametrics/vmagent:v1.148.0
+    image: victoriametrics/vmagent:v1.149.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -18,7 +18,7 @@ services:
   # VictoriaMetrics instance, a single process responsible for
   # storing metrics and serve read requests.
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.148.0
+    image: victoriametrics/victoria-metrics:v1.149.0
     ports:
       - 8428:8428
       - 8089:8089
@@ -59,7 +59,7 @@ services:
 
   # vmalert executes alerting and recording rules
   vmalert:
-    image: victoriametrics/vmalert:v1.148.0
+    image: victoriametrics/vmalert:v1.149.0
     depends_on:
       - "victoriametrics"
       - "alertmanager"

deployment/docker/vmanomaly/vmanomaly-integration/compose.yml

@@ -1,6 +1,6 @@
 services:
   vmagent:
-    image: victoriametrics/vmagent:v1.148.0
+    image: victoriametrics/vmagent:v1.149.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -14,7 +14,7 @@ services:
     restart: always
 
   victoriametrics:
-    image: victoriametrics/victoria-metrics:v1.148.0
+    image: victoriametrics/victoria-metrics:v1.149.0
     ports:
       - 8428:8428
     volumes:
@@ -40,7 +40,7 @@ services:
     restart: always
 
   vmalert:
-    image: victoriametrics/vmalert:v1.148.0
+    image: victoriametrics/vmalert:v1.149.0
     depends_on:
       - "victoriametrics"
     ports:
@@ -59,7 +59,7 @@ services:
       - '--external.alert.source=explore?orgId=1&left=["now-1h","now","VictoriaMetrics",{"expr": },{"mode":"Metrics"},{"ui":[true,true,true,"none"]}]'
     restart: always
   vmanomaly:
-    image: victoriametrics/vmanomaly:v1.30.0
+    image: victoriametrics/vmanomaly:v1.30.2
     depends_on:
       - "victoriametrics"
     ports:

deployment/docker/vmanomaly/vmanomaly-integration/vmanomaly_config.yml

@@ -1,7 +1,7 @@
 schedulers:
   periodic:
     infer_every: "1m"
-    fit_every: "100w" # the online model keeps learning during inference
+    fit_every: "1000d" # bootstrap-only schedule; use a finite cadence if accumulated state must be reset
     fit_window: "2w"
 
 models:

docs/ai-tools/README.md

@@ -1,3 +1,11 @@
+---
+build:
+  list: never
+  publishResources: false
+  render: never
+sitemap:
+  disable: true
+---
 VictoriaMetrics Observability Stack integrates with AI assistants through [MCP servers](https://docs.victoriametrics.com/ai-tools/#mcp-servers)
 and [agent skills](https://docs.victoriametrics.com/ai-tools/#agent-skills).
 The integrations allow AI agents and automation tools to query Metrics, Logs, and Traces, analyze telemetry data, 

docs/anomaly-detection/CHANGELOG.md

@@ -16,6 +16,44 @@ Please find the changelog for VictoriaMetrics Anomaly Detection below.
 
 {{% collapse name="2026" open=true %}}
 
+## v1.30.2
+Released: 2026-08-13
+
+- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.8.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v181) to [v1.8.2](https://docs.victoriametrics.com/anomaly-detection/ui/#v182), fixing tenant discovery and switching for multitenant VictoriaMetrics datasources.
+
+- FEATURE: Added **query**-level [`data_range`, `detection_direction`, `min_dev_from_expected`, and `min_rel_dev_from_expected`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#per-query-parameters). Model-level placement is deprecated but remains a compatible fallback.
+
+- IMPROVEMENT: Added [`reader.workers`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#config-parameters) to cap concurrent datasource requests and disk-streamed query chunks; `0` selects an automatic bound.
+
+- IMPROVEMENT: Added [`settings.native_threads_per_worker`](https://docs.victoriametrics.com/anomaly-detection/components/settings/#parallelization) to reduce [native-thread oversubscription](https://scikit-learn.org/stable/computing/parallelism.html#oversubscription-spawning-too-many-threads), throttling risk, fit latency, and memory. For example, with 16 CPUs/workers, [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) fit time fell 70.6% for 1,000 univariate models and 11.5% for 100 x 10-channel grouped models; inference was unchanged.
+
+- IMPROVEMENT: Removed temporary fit-data generations after all dependent models finish and commit, while safely retaining failed or overlapping generations.
+
+- IMPROVEMENT: Reduced disk-backed grouped multivariate memory and fit latency without model or state migration. For example, 100 x 100-channel four-week fits cut peak PSS/fit time by 63%/56% for [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope).
+
+- BUGFIX: Made [multivariate models](https://docs.victoriametrics.com/anomaly-detection/components/models/#multivariate-models) independent of input channel order when the fitted channel set matches; missing, extra, or duplicate channels remain rejected.
+
+## v1.30.1
+Released: 2026-08-06
+
+- UI: Updated [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) from [v1.8.0](https://docs.victoriametrics.com/anomaly-detection/ui/#v180) to [v1.8.1](https://docs.victoriametrics.com/anomaly-detection/ui/#v181). The update improves UX validation and fixes regressions introduced by new design.
+
+- IMPROVEMENT: Reduced fit and inference latency for the Z-score, MAD, standard deviation, Seasonal Quantile, and Rolling Quantile online models. Representative service-stage gains range from 1.5-2.6x for fit and 1.7-2.3x for inference, depending on model, storage mode, and data size.
+
+- IMPROVEMENT: Removed forwarded datasource credentials from in-memory state for completed, failed, canceled, and shutting-down [analysis and autotune tasks](https://docs.victoriametrics.com/anomaly-detection/components/server/#time-series-analysis-and-autotune-api).
+
+- BUGFIX: Stabilized [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) after fitting across a late level shift. Its level, trend, residual, and supported calendar state now initialize coherently from the recent regime, avoiding stale fitted magnitudes and false seasonal oscillations when periodic inference starts.
+
+- BUGFIX: Corrected `/api/v1/timeseries/characteristics` seasonality detection for time series whose timestamps are offset from whole sampling intervals. Trend interpolation now preserves the original observation grid, allowing daily and weekly patterns to be detected on shifted grids.
+
+- BUGFIX: Restored backward-compatible `inference_only` [backtesting](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#backtesting-scheduler) for configurations that omit `infer_every`. The scheduler derives its inference grid from the query step or reader sampling period and preserves valid single-timestamp range queries.
+
+- BUGFIX: Aligned periodic inference for exact-capable online models with exact backtesting (used in [UI](https://docs.victoriametrics.com/anomaly-detection/ui/) experiments) by applying the configured `infer_every` as the causal update cadence.
+
+- BUGFIX: Corrected [self-monitoring](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#writer-behaviour-metrics) accounting so failed VictoriaMetrics write attempts contribute to `vmanomaly_writer_request_duration_seconds`, including connection retries, and inference counts only unseen *valid* rows in `vmanomaly_model_datapoints_accepted`.
+
+- BUGFIX: Fixed service-level [`settings.anomaly_score_outside_data_range`](https://docs.victoriametrics.com/anomaly-detection/components/settings/#anomaly-score-outside-data-range) propagation so its configured score applies to every model unless the model defines its own override.
+
 ## v1.30.0
 Released: 2026-07-23
 

docs/anomaly-detection/FAQ.md

@@ -24,7 +24,7 @@ The decision to set the changepoint at `1.0` is made to ensure consistency acros
 > `anomaly_score` is a metric itself, which preserves all labels found in input data and (optionally) appends [custom labels, specified in writer](https://docs.victoriametrics.com/anomaly-detection/components/writer/#metrics-formatting) - follow the link for detailed output example.
 
 ## How is anomaly score calculated?
-For most of the [univariate models](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models) that can generate `yhat`, `yhat_lower`, and `yhat_upper` time series in [their output](https://docs.victoriametrics.com/anomaly-detection/components/models/#vmanomaly-output) (such as [Prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) or [Z-score](https://docs.victoriametrics.com/anomaly-detection/components/models/#z-score)), the anomaly score is calculated as follows:
+For most of the [univariate models](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models) that can generate `yhat`, `yhat_lower`, and `yhat_upper` time series in [their output](https://docs.victoriametrics.com/anomaly-detection/components/models/#vmanomaly-output) (such as [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) or [Online Z-score](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-z-score)), the anomaly score is calculated as follows:
 - If `yhat` (expected series behavior) equals `y` (actual value observed), then the anomaly score is 0.
 - If `y` (actual value observed) falls within the `[yhat_lower, yhat_upper]` confidence interval, the anomaly score will gradually approach 1, the closer `y` is to the boundary.
 - If `y` (actual value observed) strictly exceeds the `[yhat_lower, yhat_upper]` interval, the anomaly score will be greater than 1, increasing as the margin between the actual value and the expected range grows.
@@ -33,7 +33,7 @@ Please see example graph illustrating this logic below:
 
 ![anomaly-score-calculation-example](vmanomaly-prophet-example.webp)
 
-> p.s. please note that additional post-processing logic might be applied to produced anomaly scores, if common arguments like [`min_dev_from_expected`](https://docs.victoriametrics.com/anomaly-detection/components/models/#minimal-deviation-from-expected) or [`detection_direction`](https://docs.victoriametrics.com/anomaly-detection/components/models/#detection-direction) are enabled for a particular model. Follow the links above for the explanations.
+> Additional post-processing logic may be applied to produced anomaly scores when query policies such as [`min_dev_from_expected`](https://docs.victoriametrics.com/anomaly-detection/components/models/#minimal-deviation-from-expected) or [`detection_direction`](https://docs.victoriametrics.com/anomaly-detection/components/models/#detection-direction) are configured. Follow the links for details.
 
 
 ## How does vmanomaly work?
@@ -82,7 +82,7 @@ reader:
 
 `vmanomaly` supports timezone-aware anomaly detection {{% available_from "v1.18.0" anomaly %}} through a `tz` argument, available both at the [reader level](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) and at the [query level](https://docs.victoriametrics.com/anomaly-detection/components/reader/#per-query-parameters).
 
-For models that depend on seasonality, such as [`ProphetModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) and [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile), handling timezone shifts is crucial. Changes like Daylight Saving Time (DST) can disrupt seasonality patterns learned by models, resulting in inaccurate anomaly predictions as the periodic patterns shift with time. Proper timezone configuration ensures that seasonal cycles align with expected intervals, even as DST changes occur.
+For models that depend on seasonality, such as [`TemporalEnvelopeModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) and [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile), handling timezone shifts is crucial. Changes like Daylight Saving Time (DST) can disrupt seasonality patterns learned by models, resulting in inaccurate anomaly predictions as the periodic patterns shift with time. Proper timezone configuration ensures that seasonal cycles align with expected intervals, even as DST changes occur.
 
 To enable timezone handling:
 1. **Reader-level**: Set `tz` in the [`reader`](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) section to a specific timezone (e.g., `Europe/Berlin`) to apply this setting to all queries.
@@ -100,9 +100,9 @@ reader:
       tz: 'Europe/London'  # per-query override
 models:
   seasonal_model:
-    class: 'prophet'
+    class: 'temporal_envelope'
     queries: ['your_query']
-    # other model params ...
+    seasonalities: ['hod_smooth', 'dow_smooth']
 ```
 
 ## Output produced by vmanomaly
@@ -124,9 +124,8 @@ Selecting the best model for `vmanomaly` depends on the data's nature and the [t
 
 - Use [Online MAD](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-mad) for simple, mostly stationary data with no-to-slow trend, when robustness to outliers is important.
 - Use [Online Z-score](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-z-score) for simple, light-tailed data where standard-deviation units are meaningful.
-- Use [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) {{% available_from "v1.30.0" anomaly %}} for complex data with trends, calendar patterns, holidays, or persistent shifts. It is the preferred *online* alternative to Prophet (which will be deprecated in the future releases).
+- Use [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) {{% available_from "v1.30.0" anomaly %}} for complex data with trends, calendar patterns, holidays, or persistent shifts. It is the preferred online migration target for existing Prophet configurations.
 - Use multivariate Temporal Envelope when normal relationships between aligned metrics matter. This should replace [Isolation Forest](https://docs.victoriametrics.com/anomaly-detection/components/models/#isolation-forest-multivariate) used in previous versions of `vmanomaly`, which will be deprecated in future releases.
-- Use [Prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) when Prophet-specific decomposition outputs, or offline batch behavior are required. Consider using Temporal Envelope instead, as it is more efficient and provides better results in most cases.
 
 There is also an option to auto-tune the most important parameters of a selected model class {{% available_from "v1.12.0" anomaly %}}. {{% available_from "v1.30.0" anomaly %}} The asynchronous autotune API can first profile a bounded sample through `/api/v1/timeseries/characteristics`, then tune a shared concrete configuration through `/api/v1/autotune/tasks`. See the [autotune workflow](https://docs.victoriametrics.com/anomaly-detection/components/models/#shared-asynchronous-autotune-workflow).
 
@@ -136,7 +135,7 @@ Still not 100% sure what to use? We are [here to help](https://docs.victoriametr
 
 ## Incorporating domain knowledge
 
-Anomaly detection models can significantly improve when incorporating business-specific assumptions about the data and what constitutes an anomaly. `vmanomaly` supports various [business-side configuration parameters](https://docs.victoriametrics.com/anomaly-detection/components/models/#common-args) across all built-in models to **reduce [false positives](https://victoriametrics.com/blog/victoriametrics-anomaly-detection-handbook-chapter-1/#false-positive)** and **align model behavior with business needs**, for example:
+Anomaly detection models can significantly improve when incorporating business-specific assumptions about the data and what constitutes an anomaly. `vmanomaly` supports [business policies](https://docs.victoriametrics.com/anomaly-detection/components/models/#common-args) across built-in models to **reduce [false positives](https://victoriametrics.com/blog/victoriametrics-anomaly-detection-handbook-chapter-1/#false-positive)** and **align model behavior with business needs**, for example:
 
 - **Setting `detection_direction`** - use [`detection_direction`](https://docs.victoriametrics.com/anomaly-detection/components/models/#detection-direction) to specify whether anomalies occur **above or below expectations**:
   - Set to `above_expected` for metrics like error rates, where spikes indicate anomalies.
@@ -164,7 +163,7 @@ Then, the following config may be used to benefit from incorporating domain know
 schedulers:
   periodic_http:
     class: periodic
-    fit_every: 12w
+    fit_every: 1000d
     fit_window: 1w
     infer_every: 1m
   # other schedulers ...
@@ -173,18 +172,19 @@ reader:
   queries:
     percentage_4xx:
       expr: respective_metricsQL_expr
-      data_range: [0, 0.05]  # to automatically trigger anomaly score > 1 for error rates > 5%
+      data_range: [0, 0.05]  # query-level business policy from v1.30.2; error rates >5% trigger anomaly score >1
+      detection_direction: 'above_expected'  # query-level from v1.30.2; only spikes are anomalous
+      min_dev_from_expected: [0, 0.005]  # query-level from v1.30.2; ignore upward deviations below 0.5%
+      min_rel_dev_from_expected: [0, 10]  # query-level from v1.30.2; ignore upward deviations below 10%
       step: 1m
 models:
   # other models ...
   zscore:  # let it be online Z-score, for simplicity
     class: zscore_online  # online model update itself each infer call, resulting in resource-efficient setups
     z_threshold: 3.0
+    decay: 0.99  # give more weight to recent data while using the bootstrap-only fit schedule
     schedulers: ['periodic_http']
     queries: ['percentage_4xx']
-    detection_direction: 'above_expected'  # as interested only in spikes, drops are OK
-    min_dev_from_expected: [0, 0.005]  # <0.5% deviations vs expected values should be neglected, generating anomaly score == 0
-    min_rel_dev_from_expected: [0, 0.1]  # <10% relative deviations vs expected values should be neglected, generating anomaly score == 0
     # to align predictions to be within [0, 5%] interval, defined in reader.queries.percentage_4xx.data_range
     clip_predictions: True
     # specify output series produced by vmanomaly to be written to VictoriaMetrics in `writer`
@@ -230,7 +230,7 @@ models:
     schedulers: ['scheduler_alias']  # if omitted, all the defined schedulers will be attached
     queries: ['query_alias1']  # if omitted, all the defined queries will be attached
     # https://docs.victoriametrics.com/anomaly-detection/components/models/#provide-series
-    provide_series: ['anomaly_score']  
+    provide_series: ['anomaly_score']
   # ... other models
 
 reader:
@@ -254,8 +254,9 @@ Configuration above will produce N intervals of full length (`fit_window`=14d +
 
 ## Forecasting
 
-`vmanomaly` can generate future forecasts using [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) {{% available_from "v1.30.0" anomaly %}} or [ProphetModel](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) {{% available_from "v1.25.3" anomaly %}}. This is helpful for capacity planning, resource allocation, or trend analysis when the underlying data is complex and exceeds what inline MetricsQL queries, including [predict_linear](https://docs.victoriametrics.com/victoriametrics/metricsql/#predict_linear), can handle.
+`vmanomaly` can generate future forecasts with [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) {{% available_from "v1.30.0" anomaly %}}, the preferred online forecasting model. [ProphetModel](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) {{% available_from "v1.25.3" anomaly %}} also supports forecasting for existing offline configurations. Forecasts help with capacity planning, resource allocation, or trend analysis when the underlying data is complex and exceeds what inline MetricsQL queries, including [predict_linear](https://docs.victoriametrics.com/victoriametrics/metricsql/#predict_linear), can handle.
 
+> [!WARNING]
 > However, please note that this mode should be used with care, as the model will produce `yhat_{h}` (and probably `yhat_lower_{h}`, and `yhat_upper_{h}`) time series **for each timeseries returned by input queries and for each forecasting horizon specified in `forecast_at` argument, which can lead to a significant increase in the number of active timeseries in VictoriaMetrics TSDB**.
 
 Here's an example of how to produce forecasts using `vmanomaly` and combine it with the regular model, e.g. to estimate daily outcomes for a disk usage metric:
@@ -265,12 +266,12 @@ Here's an example of how to produce forecasts using `vmanomaly` and combine it w
 schedulers:
   periodic_5m:  # this scheduler will be used to produce anomaly scores each 5 minutes using "regular" simple model
     class: 'periodic'
-    fit_every: '100w'
+    fit_every: '1000d'
     fit_window: '3d'
     infer_every: '5m'
   periodic_forecast:  # this scheduler will be used to produce forecasts each 24h using "daily" model
     class: 'periodic'
-    fit_every: '1000w'
+    fit_every: '1000d'
     fit_window: '730d' # to fit the model on 2 years of data to account for seasonality and holidays
     infer_every: '24h'
 # https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader
@@ -290,6 +291,7 @@ reader:
           1h
         )
       data_range: [0, 1]
+      detection_direction: 'above_expected'  # query-level from v1.30.2
       # step: '1m'  # default will be inherited from sampling_period
     disk_usage_perc_1d:
       expr: |
@@ -301,14 +303,15 @@ reader:
         )
       step: '1d'  # override default step to 1d, as we want to produce daily forecasts
       data_range: [0, 1]
+      detection_direction: 'above_expected'  # query-level from v1.30.2
 # https://docs.victoriametrics.com/anomaly-detection/components/models/
 models:
   quantile_5m:
     class: 'quantile_online'  # online model, which updates itself each infer call
     queries: ['disk_usage_perc_5m']
     schedulers: ['periodic_5m']
+    decay: 0.99  # give more weight to recent data while using the bootstrap-only fit schedule
     clip_predictions: True
-    detection_direction: 'above_expected'  # as we are interested in spikes in capacity planning
     quantiles: [0.25, 0.5, 0.75]  # to produce median and upper quartiles
     iqr_threshold: 2.0
 
@@ -316,8 +319,9 @@ models:
     class: 'temporal_envelope'
     queries: ['disk_usage_perc_1d']
     schedulers: ['periodic_forecast']
+    alpha: 0.005  # capture the changes faster if increased
+    loss_reactivity: 3  # allow new deviations to update the envelope
     clip_predictions: True
-    detection_direction: 'above_expected'  # as we are interested in spikes in capacity planning
     forecast_at: ['3d', '7d']  # this will produce forecasts for 3 and 7 days ahead
     provide_series: ['yhat', 'yhat_upper']  # to write forecasts back to VictoriaMetrics, omitting `yhat_lower` as it is not needed in this example
     seasonalities: [dow_smooth]
@@ -426,13 +430,15 @@ For information on migrating between different versions of `vmanomaly`, please r
 
 > {{% available_from "v1.24.0" anomaly %}} This feature is best used in conjunction with [stateful mode](https://docs.victoriametrics.com/anomaly-detection/components/settings/#state-restoration) to ensure that the model state is preserved across service restarts.
 
+> {{% available_from "v1.30.2" anomaly %}} Scheduler-managed fit data is **temporary**. It is removed after every dependent univariate or multivariate model completes fitting and commits its state, rather than being retained until the next `fit_every` cycle. Model dumps and state metadata remain available for restoration.
+
 Here's an example of how to set it up in docker-compose using volumes:
 ```yaml
 services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.30.0
+    image: victoriametrics/vmanomaly:v1.30.2
     # ...
     restart: always
     volumes:
@@ -503,7 +509,7 @@ settings:
 schedulers:
   periodic:
     class: 'periodic'
-    fit_every: '180d'  # we need only initial fit to start
+    fit_every: '1000d'
     fit_window: '4h'  # reduced window, especially if the data doesn't have strong seasonality
     infer_every: '1m'  # the model will be updated during each infer call
   # other schedulers ...
@@ -511,7 +517,7 @@ models:
   zscore_example:
     class: 'zscore_online'
     min_n_samples_seen: 120  # i.e. minimal relevant seasonality or (initial) fit_window / sampling_period
-    decay: 0.999  # decay factor to control how fast the model adapts to new data, the lower, the faster it adapts
+    decay: 0.99  # decay factor to control how fast the model adapts to new data, the lower, the faster it adapts
     schedulers: ['periodic']
     # other model params ...
 # other config sections ...
@@ -525,11 +531,11 @@ As a result, switching from the offline Z-score model to the Online Z-score mode
 
 **New configuration**: 
 - `fit_window`: 4 hours
-- `fit_every`: 180 days ( >1 week)
+- `fit_every`: 1000 days ( >1 week)
 
 The old configuration would perform 168 (hours in a week) `fit` calls, each using 2 days (48 hours) of data, totaling 168 * 48 = 8064 hours of data for each timeseries returned.
 
-The new configuration performs only 1 `fit` call in 180 days, using 4 hours of data initially, totaling 4 hours of data, which is **magnitudes smaller**.
+The new configuration performs only 1 `fit` call in 1000 days, using 4 hours of data initially, totaling 4 hours of data, which is **magnitudes smaller**.
 
 P.s. `infer` data volume will remain the same for both models, so it does not affect the overall calculations.
 
@@ -554,11 +560,10 @@ reader:
       expr: 'sum(ALERTS{alertstate=~'(pending|firing)'}) by (alertstate)'
       max_points_per_query: 5000  # query-level override
 models:
-    prophet:
+    temporal_envelope:
+      class: temporal_envelope
       # other model args
-      queries: [
-        'sum_alerts',
-      ]
+      queries: ['sum_alerts']
 # other config sections
 ```
 
@@ -575,11 +580,10 @@ reader:
     sum_alerts:
       expr: 'sum(ALERTS{alertstate=~'(pending|firing)'}) by (alertstate)'
 models:
-    prophet:
+    temporal_envelope:
+      class: temporal_envelope
       # other model args
-      queries: [
-        'sum_alerts',
-      ]
+      queries: ['sum_alerts']
 # other config sections
 ```
 
@@ -594,12 +598,10 @@ reader:
     sum_alerts_firing:
       expr: 'sum(ALERTS{alertstate='firing'}) by ()'
 models:
-    prophet:
+    temporal_envelope:
+      class: temporal_envelope
       # other model args
-      queries: [
-        'sum_alerts_pending',
-        'sum_alerts_firing',
-      ]
+      queries: ['sum_alerts_pending', 'sum_alerts_firing']
 # other config sections
 ```
 
@@ -649,10 +651,12 @@ options:
                         Minimum level to log. Default: INFO
 ```
 
+For a side-by-side comparison of all split modes and their resulting sub-configurations, see [splitting strategies](https://docs.victoriametrics.com/anomaly-detection/scaling-vmanomaly/#splitting-strategies).
+
 Here’s an example of using the config splitter to divide configurations based on the `extra_filters` argument from the reader section:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.30.0 && docker image tag victoriametrics/vmanomaly:v1.30.0 vmanomaly
+docker pull victoriametrics/vmanomaly:v1.30.2 && docker image tag victoriametrics/vmanomaly:v1.30.2 vmanomaly
 ```
 
 ```sh
@@ -685,10 +689,11 @@ reader:
   # ...
   queries:
     extra_big_query: metricsql_expression_returning_too_many_timeseries
-    extra_filters:
+    extra_filters: [
       # suppose you have a label `region` with values to deterministically define such subsets
-      - '{env="region_name_1"}'
+      '{env="region_name_1"}',
       # ...
+    ]
 ```
 
 ```yaml
@@ -698,10 +703,11 @@ reader:
   # ...
   queries:
     extra_big_query: metricsql_expression_returning_too_many_timeseries
-    extra_filters:
+    extra_filters: [
       # suppose you have a label `region` with values to deterministically define such subsets
-      - '{region="region_name_2"}'
+      '{region="region_name_2"}',
       # ...
+    ]
 ```
 
 ## Monitoring vmanomaly

docs/anomaly-detection/Migration.md

@@ -45,7 +45,7 @@ There are 2 types of compatibility to consider when migrating in stateful mode:
 
 | Group start | Group end | Compatibility | Notes |
 |---------|--------- |------------|-------|
-| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.30.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1300) | Fully Compatible | v1.30.0 adds new [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) model state without changing the compatibility of existing model and data artifacts. |
+| [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) | [v1.30.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1302) | Fully Compatible | v1.30.0 adds new [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) model state without changing the compatibility of existing model and data artifacts. v1.30.2 remains compatible with v1.30.1 state and its compatible predecessors; no persisted-state migration is required. |
 | [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) | Partially compatible* | Dumped models of class [prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) and [seasonal quantile](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile) have problems with loading to [v1.29.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1290) due to dropped `pytz` library. **Upgrading directly from v1.28.7 to [v1.29.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1291) with a fix is suggested** |
 | [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262) | [v1.28.7](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1287) | Fully Compatible | [v1.28.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1280) introduced [rolling](https://docs.victoriametrics.com/anomaly-detection/components/models/#rolling-models) model class drop in favor of [online](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models) models (`rolling_quantile` and `std` models), however, it does not impact compatibility, as artifacts were not produced by default for rolling models. Also, offline `mad` and `zscore` models are redirecting to their respective online counterparts since [v1.28.4](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1284). |
 | [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) | [v1.26.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270) | Partially Compatible* | [v1.25.3](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1253) introduced `forecast_at` argument for base [univariate](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models) and `Prophet` [models](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet), however, itself remains backward-reversible from newer states like [v1.26.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1262), [v1.27.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1270). (All models except `isolation_forest_multivariate` class will be dropped) |
@@ -71,7 +71,7 @@ In stateless mode, the migration process is almost straightforward as there are
 
 **Breaking Changes**
 
-- [v1.12.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1120) **ARIMA** model is removed from [built-in models](https://docs.victoriametrics.com/anomaly-detection/components/models/#built-in-models); Action:  replace ARIMA by [Prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) or alternative seasonal models in `model(s)` section of your configuration files.
+- [v1.12.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1120) **ARIMA** model is removed from [built-in models](https://docs.victoriametrics.com/anomaly-detection/components/models/#built-in-models). Action: for vmanomaly v1.30.0 and newer, replace ARIMA with [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) {{% available_from "v1.30.0" anomaly %}}; for older releases, use another supported seasonal model in the `models` section of the configuration.
 
 - [v1.9.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v190) The `sampling_period` parameter is now mandatory in `VmReader`. This change aims to clarify and standardize the frequency of input/output in `vmanomaly`, thereby reducing uncertainty and aligning with user expectations; Action: Add the `sampling_period` parameter to your `VmReader` configuration, e.g.:
 

docs/anomaly-detection/QuickStart.md

@@ -126,13 +126,18 @@ groups:
 > docker pull quay.io/victoriametrics/vmanomaly:vX.Y.Z
 > ```
 
+> [!NOTE] ARM64 startup on affected Apple Silicon virtualization
+> On some `linux/arm64` environments running through virtualization on Apple M4/M5 hosts, `vmanomaly` may exit with `SIGILL` (exit code `132`) before startup. This is caused by the virtualized host advertising an SVE2 capability that traps when used by OpenSSL 4.x; it does not affect all ARM64 systems.
+>
+> On affected hosts, add `-e OPENSSL_armcap=0` to `docker run`, or add `- OPENSSL_armcap=0` under the service's Docker Compose `environment`, matching the list syntax used below. This disables ARM cryptographic acceleration, so apply it only as a temporary workaround on affected hosts.
+
 
 Below are the steps to get `vmanomaly` up and running inside a Docker container:
 
 1. Pull Docker image:
 
 ```sh
-docker pull victoriametrics/vmanomaly:v1.30.0
+docker pull victoriametrics/vmanomaly:v1.30.2
 ```
 
 2. Create the license file with your license key.
@@ -152,7 +157,7 @@ docker run -it \
     -v ./license:/license \
     -v ./config.yaml:/config.yaml \
     -p 8490:8490 \
-    victoriametrics/vmanomaly:v1.30.0 \
+    victoriametrics/vmanomaly:v1.30.2 \
     /config.yaml \
     --licenseFile=/license \
     --loggerLevel=INFO \
@@ -169,7 +174,7 @@ docker run -it \
     -e VMANOMALY_DATA_DUMPS_DIR=/tmp/vmanomaly/data \
     -e VMANOMALY_MODEL_DUMPS_DIR=/tmp/vmanomaly/models \
     -p 8490:8490 \
-    victoriametrics/vmanomaly:v1.30.0 \
+    victoriametrics/vmanomaly:v1.30.2 \
     /config.yaml \
     --licenseFile=/license \
     --loggerLevel=INFO \
@@ -182,7 +187,7 @@ services:
   # ...
   vmanomaly:
     container_name: vmanomaly
-    image: victoriametrics/vmanomaly:v1.30.0
+    image: victoriametrics/vmanomaly:v1.30.2
     # ...
     restart: always
     volumes:
@@ -245,12 +250,13 @@ Before deploying, check the correctness of your configuration validate config fi
 
 ### Example
 
-Here is an example of a config file that runs the online [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) model on a CPU metric. The scheduler runs inference every five minutes and performs a full refit only every 100 weeks; between refits the model updates causally from each inference batch. The initial fit uses four weeks of data. The model produces `anomaly_score`, `yhat`, `yhat_lower`, and `yhat_upper` [series](https://docs.victoriametrics.com/anomaly-detection/components/models/#vmanomaly-output) for debugging, and its hour-of-day and day-of-week profiles follow the query timezone and daylight-saving-time changes.
+Here is an example of a config file that runs the online [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) model on a CPU metric. The scheduler runs inference every five minutes and uses the fit only for initial bootstrap; between fits the model updates causally from each inference batch. The initial fit uses four weeks of data. The model produces `anomaly_score`, `yhat`, `yhat_lower`, and `yhat_upper` [series](https://docs.victoriametrics.com/anomaly-detection/components/models/#vmanomaly-output) for debugging, and its hour-of-day and day-of-week profiles follow the query timezone and daylight-saving-time changes.
 
 ```yaml
 settings:
   # https://docs.victoriametrics.com/anomaly-detection/components/settings/
   n_workers: 2  # number of workers to run workload in parallel, set to 0 or negative number to use all available CPU cores
+  native_threads_per_worker: 0  # automatically divide container-aware CPU capacity across workers
   anomaly_score_outside_data_range: 5.0  # default anomaly score for anomalies outside expected data range
   restore_state: true  # restore state from previous run, available since v1.24.0
   # https://docs.victoriametrics.com/anomaly-detection/components/settings/#logger-levels
@@ -263,13 +269,12 @@ settings:
     model.online.temporal_envelope: WARNING
 
 schedulers:
-  100w_5m:
+  online_5m:
     # https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#periodic-scheduler
     class: 'periodic'
     infer_every: '5m'
     scatter_infer_jobs: true
-    # Temporal Envelope learns online between full refits.
-    fit_every: '100w'
+    fit_every: '1000d'
     fit_window: '4w'
 
 models:
@@ -277,7 +282,7 @@ models:
   temporal_envelope_model:
     class: 'temporal_envelope'
     queries: ['cpu_user']
-    schedulers: ['100w_5m']
+    schedulers: ['online_5m']
     provide_series: ['anomaly_score', 'yhat', 'yhat_lower', 'yhat_upper']  # for debugging
     seasonalities: ['hod_smooth', 'dow_smooth']
     alpha: 0.005  # trend reactivity; try 0.0025-0.02
@@ -292,12 +297,15 @@ reader:
   tenant_id: '0:0'
   sampling_period: "5m"
   tz: 'UTC'  # set the IANA timezone that defines local calendar patterns, e.g. 'America/New_York'
+  workers: 0  # automatically choose bounded datasource concurrency
   series_processing_batch_size: 8  # number of time series to process together while preparing data for fit or infer stages
   queries:
     # define your queries with MetricsQL - https://docs.victoriametrics.com/victoriametrics/metricsql/
     cpu_user:
       expr: 'sum(rate(node_cpu_seconds_total{mode=~"user"}[10m])) by (container)'
-      max_datapoints_per_query: 15000  # to deal with longer queries hitting search.MaxPointsPerTimeseries
+      data_range: [0, 'inf']  # query-level business policy from v1.30.2
+      detection_direction: 'above_expected'  # query-level from v1.30.2; only spikes are anomalous
+      max_points_per_query: 15000  # to deal with longer queries hitting search.maxPointsPerTimeseries
     # other queries ...
 
 writer:

docs/anomaly-detection/Scaling-vmanomaly.md

@@ -32,14 +32,15 @@ schedulers:
   periodic_1d:  # alias
     class: 'periodic' # scheduler class
     infer_every: "30s"
-    fit_every: "1h"
+    fit_every: "1000d"
     fit_window: "24h"
 
 # https://docs.victoriametrics.com/anomaly-detection/components/models/
 models:
   zscore:  # we can set up alias for model
-    class: 'zscore'  # model class
+    class: 'zscore_online'  # online model class
     z_threshold: 3.5
+    decay: 0.99  # give more weight to recent data while using the bootstrap-only fit schedule
     queries: ['cpu_seconds_total', 'host_network_receive_errors']
 
 # https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader
@@ -80,6 +81,7 @@ Additionally, a replication factor `R ≥ 1` ensures [high availability](#high-a
 
 {{% content "vmanomaly-sharding-ha-diagram.md" %}}
 
+> [!WARNING]
 > Please [refer to deployment options section](#deployment-options) for the examples (Docker, Docker Compose, Helm). To avoid duplicate metrics being reported from each vmanomaly service used in sharded mode, make sure that [deduplication](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) is configured on vmsingle or vmselect and vmstorage for the VictoriaMetrics instance used in the [writer section of the configuration](https://docs.victoriametrics.com/anomaly-detection/components/writer/).
 
 Sharding configuration can be controlled by using the following environment variables:
@@ -87,7 +89,94 @@ Sharding configuration can be controlled by using the following environment vari
 - **`VMANOMALY_MEMBERS_COUNT`**: Defines the total number of shards (i.e., available nodes to distribute [sub-configurations](#sub-configuration) to). <br>Defaults to `1` for backward compatibility.
 - **`VMANOMALY_MEMBER_NUM`**: Specifies the shard index (`0` to `VMANOMALY_MEMBERS_COUNT - 1`), determining the subset of [sub-configurations](#sub-configuration) to run on a specific node. Defaults to `0`. Supports automatic **pod name discovery** in Kubernetes [StatefulSets](https://kubernetes.io/docs/concepts/workloads/controllers/statefulset/) (e.g., if set to `vmanomaly-node-exporter-7`, shard `7` will be extracted).
 - **`VMANOMALY_REPLICATION_FACTOR`**: If `R > 1`, enables [high availability](#high-availability) by ensuring each [sub-configuration](#sub-configuration) is assigned to exactly `R` shards. Defaults to `1` (no replication).
-- **`VMANOMALY_SPLIT_BY`**: Defines the logical entity used to split the global config into [sub-configurations](#sub-configuration). Defaults to `complete`, which provides the most granular distribution (1 model per [sub-config](#sub-configuration), mapped to 1 query and attached to 1 scheduler) for balanced workloads.
+- **`VMANOMALY_SPLIT_BY`**: Defines the logical entity used to split the global config into [sub-configurations](#sub-configuration). The accepted values are `SCHEDULERS`, `MODELS`, `QUERIES`, `EXTRA_FILTERS`, and `COMPLETE` (case-insensitive). It defaults to `COMPLETE`, which usually provides the most granular and balanced distribution.
+
+The split strategies differ as follows:
+
+| `VMANOMALY_SPLIT_BY` | Unit of work in each sub-configuration | Recommended use |
+| --- | --- | --- |
+| `SCHEDULERS` | One scheduler and the workload attached to it | Separate workloads by fit and inference cadence. The number of sub-configurations is limited by the number of referenced schedulers. |
+| `MODELS` | One configured model alias with its attached schedulers and queries | Isolate computationally different models or distribute several models that process the same queries. |
+| `QUERIES` | One query for [univariate models](https://docs.victoriametrics.com/anomaly-detection/components/models/#univariate-models); the complete attached query set for each [multivariate model](https://docs.victoriametrics.com/anomaly-detection/components/models/#multivariate-models) | Distribute independent query workloads. Queries belonging to one multivariate model remain together because the model needs all channels. This option does not split the series returned by one query. |
+| `EXTRA_FILTERS` | One configured `reader.extra_filters` selector, with the full model/query/scheduler topology retained | Partition the series returned by large queries, for example by region, cluster, another stable label, or by [VictoriaMetrics tenant](https://docs.victoriametrics.com/victoriametrics/cluster-victoriametrics/#multitenancy-via-labels) using `vm_account_id` and `vm_project_id` selectors with the multitenant endpoint. The filters must already be defined in the global configuration. |
+| `COMPLETE` | One valid scheduler/model/query combination; [multivariate](https://docs.victoriametrics.com/anomaly-detection/components/models/#multivariate-models) query sets remain together | Obtain the finest general-purpose split and the default choice for balanced sharding. `reader.extra_filters` are intentionally not expanded by this strategy. |
+
+After the selected strategy creates the sub-configurations, they are assigned to members in deterministic round-robin order and then replicated according to `VMANOMALY_REPLICATION_FACTOR`.
+
+### Splitting strategies
+
+{{% collapse name="Configuration and resulting sub-configurations" %}}
+
+The following abbreviated global configuration contains two schedulers, two models, four queries, and two data partitions:
+
+```yaml
+schedulers:
+  fast:
+    class: periodic
+    infer_every: 1m
+    fit_every: 1000d
+    fit_window: 1d
+  seasonal:
+    class: periodic
+    infer_every: 5m
+    fit_every: 1000d
+    fit_window: 2w
+
+models:
+  cpu_zscore:
+    class: zscore_online
+    schedulers: [fast]
+    queries: [cpu, error_rate]
+    decay: 0.99
+  gpu_envelope:
+    class: temporal_envelope_multivariate
+    schedulers: [seasonal]
+    queries: [temperature, power]
+    seasonalities: [hod_smooth, dow_smooth]
+
+reader:
+  class: vm
+  datasource_url: http://victoriametrics:8428/
+  sampling_period: 1m
+  queries:
+    cpu:
+      expr: avg(rate(node_cpu_seconds_total[5m])) by (instance)
+    error_rate:
+      expr: rate(application_errors_total[5m])
+    temperature:
+      expr: avg(gpu_temperature_celsius) by (gpu)
+    power:
+      expr: avg(gpu_power_watts) by (gpu)
+  extra_filters: ['{region="us-east"}', '{region="eu-west"}']
+
+writer:
+  class: vm
+  datasource_url: http://victoriametrics:8428/
+```
+
+For this configuration, each strategy produces the following logical units before they are assigned to shards:
+
+| Value | Resulting sub-configurations |
+| --- | --- |
+| `SCHEDULERS` | `fast`; `seasonal` |
+| `MODELS` | `cpu_zscore`; `gpu_envelope` |
+| `QUERIES` | `cpu`; `error_rate`; the multivariate set `power,temperature` |
+| `EXTRA_FILTERS` | `{region="us-east"}`; `{region="eu-west"}`; each retains all schedulers, models, and queries, while the query context is restricted by its selector |
+| `COMPLETE` | `fast:cpu_zscore:cpu`; `fast:cpu_zscore:error_rate`; `seasonal:gpu_envelope:power,temperature` |
+
+For example, choose the query split with:
+
+```yaml
+environment:
+  VMANOMALY_MEMBERS_COUNT: 3
+  VMANOMALY_MEMBER_NUM: 0
+  VMANOMALY_REPLICATION_FACTOR: 1
+  VMANOMALY_SPLIT_BY: QUERIES
+```
+
+To partition the timeseries returned by the same large query instead, define non-overlapping selectors in `reader.extra_filters` and use `VMANOMALY_SPLIT_BY: EXTRA_FILTERS`. Each generated sub-configuration keeps one selector, for example `{region="us-east"}` or `{region="eu-west"}`.
+
+{{% /collapse %}}
 
 ---
 
@@ -130,6 +219,7 @@ When `VMANOMALY_REPLICATION_FACTOR` > 1, each [sub-config](#sub-configuration) `
 
 {{% content "vmanomaly-sharding-ha-diagram.md" %}}
 
+> [!WARNING]
 > Please [refer to deployment options section](#deployment-options) for the examples (Docker, Docker Compose, Helm). To avoid duplicate metrics being reported from each vmanomaly service used in sharded mode, make sure that [deduplication](https://docs.victoriametrics.com/victoriametrics/single-server-victoriametrics/#deduplication) is configured on vmsingle or vmselect and vmstorage for the VictoriaMetrics instance used in the [writer section of the configuration](https://docs.victoriametrics.com/anomaly-detection/components/writer/).
 
 ### Example
@@ -198,7 +288,11 @@ services:
     user: "1000:1000"
     restart: always
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://127.0.0.1:8490/health"]
+      test:
+        - "CMD"
+        - "curl"
+        - "-f"
+        - "http://127.0.0.1:8490/health"
       interval: 30s
       timeout: 10s
       retries: 5
@@ -218,7 +312,11 @@ services:
     user: "1000:1000"
     restart: always
     healthcheck:
-      test: ["CMD", "curl", "-f", "http://127.0.0.1:8490/health"]
+      test:
+        - "CMD"
+        - "curl"
+        - "-f"
+        - "http://127.0.0.1:8490/health"
       interval: 30s
       timeout: 10s
       retries: 5

docs/anomaly-detection/UI.md

@@ -137,13 +137,13 @@ users:
     password: '<password>'
     url_map:
       - src_hosts:
-        - "metrics.local.some-domain.net"
+          - "metrics.local.some-domain.net"
         url_prefix: "http://victoriametrics:8428"
       - src_hosts:
-        - "vl.local.some-domain.net"
+          - "vl.local.some-domain.net"
         url_prefix: "http://victorialogs:9428"
       - src_hosts:
-        - "vmanomaly.local.some-domain.net"
+          - "vmanomaly.local.some-domain.net"
         url_prefix: "http://vmanomaly:8490"
         keep_original_host: true
 ```
@@ -193,7 +193,7 @@ The best applications of this mode are:
 
 ### What you can do with Copilot
 
-- **Ask questions** about any model (e.g. [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope), [Prophet](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet), or [Z-score](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-z-score) - parameters, trade-offs, when to use each)
+- **Ask questions** about any model (e.g. [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope), [Online Seasonal Quantile](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile), or [Online Z-score](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-z-score) - parameters, trade-offs, when to use each)
 - **Improve detection quality** - describe what's wrong ("too many false positives", "missing spikes") and Copilot reads the config, searches the docs, and proposes a validated configuration change to fix the issue.
 - **Get config suggestions inline** - suggestions appear as interactive cards with an explanation and a YAML diff; click **Apply** to write the change directly to your current settings, or **Decline** to keep the conversation going.
 - {{% available_from "v1.30.0" anomaly %}} **Profile and tune the real query** - with [mcp-vmanomaly](#mcp-tools-server) connected, Copilot can inspect bounded time-series characteristics, recommend an online model, start an asynchronous autotune task, and apply its validated query and model suggestions.
@@ -316,7 +316,7 @@ docker run -it --rm \
   -e VMANOMALY_MCP_SERVER_URL=http://mcp-vmanomaly:8081/mcp \
   -p 8080:8080 \
   -p 8490:8490 \
-  victoriametrics/vmanomaly:v1.30.0 \
+  victoriametrics/vmanomaly:v1.30.2 \
   vmanomaly_config.yaml
 ```
 
@@ -569,7 +569,7 @@ Set up the time range and resolution (step) for data visualization and anomaly d
 
 ![vmanomaly-ui-sections-explore](vmanomaly-ui-sections-explore.webp)
 
-Pay attention to trends, seasonality, noise, outliers, and other patterns in the data, which can influence the choice of anomaly detection model and its hyperparameters (e.g. use seasonal models for seasonal data - like `Prophet`, robust models for noisy de-seasonalized data - like `MAD`, etc.).
+Pay attention to trends, seasonality, noise, outliers, and other patterns in the data, which can influence the choice of anomaly detection model and its hyperparameters. Use [Temporal Envelope](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) for complex data with trend or calendar patterns, and [Online MAD](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-mad) for simple, mostly stationary data where robustness to outliers matters.
 
 ![vmanomaly-ui-sections-plot-area-query-mode](vmanomaly-ui-sections-plot-area-query-mode.webp)
 
@@ -645,6 +645,26 @@ If the **results** look good and the **model configuration should be deployed in
 
 {{% collapse name="Release history" %}}
 
+### v1.8.2
+Released: 2026-08-13
+
+vmanomaly version: [v1.30.2](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1302)
+
+- BUGFIX: Fixed tenant discovery for VictoriaMetrics datasource URLs containing `/select/multitenant/prometheus`. The UI now loads available numeric tenants from `/admin/tenants` and can switch the datasource URL from `multitenant` to the selected tenant.
+
+### v1.8.1
+Released: 2026-08-06
+
+vmanomaly version: [v1.30.1](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1301)
+
+- IMPROVEMENT: Model settings are validated and normalized when applied. Invalid drafts remain open with actionable feedback, and advanced-setting summaries open the corresponding editor directly.
+
+- BUGFIX: Server-query counts load when the query drawer opens, and numeric model fields preserve valid scalar and range values while reporting parsing errors on blur.
+
+- BUGFIX: The anomaly visualization empty state now follows the active theme instead of using light-theme colors in dark mode.
+
+- BUGFIX: Tenant selection now follows the datasource URL resolved by the server, avoiding an incorrect switch to tenant `0` when it is unavailable.
+
 ### v1.8.0
 Released: 2026-07-23
 

docs/anomaly-detection/components/README.md

@@ -37,6 +37,7 @@ The following minimal configuration demonstrates current many-to-many model, que
 ```yaml
 settings:
   n_workers: 4  # number of workers to run models in parallel
+  native_threads_per_worker: 0  # automatically divide container-aware CPU capacity across workers
   anomaly_score_outside_data_range: 5.0  # default anomaly score for anomalies outside expected data range
   restore_state: True  # restore state from previous run, if available
   retention:  # how long to keep stale models on disk/in memory
@@ -50,15 +51,15 @@ schedulers:
     class: 'periodic' # scheduler class
     infer_every: "30s"  # how often to produce anomaly scores for new data
     scatter_infer_jobs: true  # distribute infer jobs evenly across the infer interval to reduce synchronized bursts
-    fit_every: "365d"  # how often to re-fit the models, for online models used effectively once, then they are updated with new data and won't require re-fit
+    fit_every: "1000d"  # bootstrap-only schedule; use a finite cadence if accumulated state must be reset
     fit_window: "3d"  # how much historical data to use for fit stage
-    start_from: "00:00"  # align the annual fit schedule to midnight in the configured timezone
+    start_from: "00:00"  # align the bootstrap fit to midnight in the configured timezone
     tz: "Europe/Kyiv"  # timezone to use for start_from
-  periodic_offline_1w:
+  periodic_online_weekly:
     class: 'periodic'
     infer_every: "15m"
     scatter_infer_jobs: true
-    fit_every: "24h"
+    fit_every: "1000d"  # bootstrap-only schedule; use a finite cadence if accumulated state must be reset
     fit_window: "14d"
     # if no start_from is specified, jobs will start immediately after service starts
 
@@ -72,21 +73,17 @@ models:
     provide_series: ['anomaly_score', 'y', 'yhat', 'yhat_upper']  # what series to produce as output of the model
     queries: ['host_network_receive_errors']  # what queries to run particular model on
     schedulers: ['periodic_online']  # will be fit once, used for infer every 30s
-    min_dev_from_expected: 0.0  # turned off. if |y - yhat| < min_dev_from_expected, anomaly score will be 0
-    detection_direction: 'above_expected' # detect anomalies only when y > yhat, "peaks"
     clip_predictions: True  # clip predictions to expected data range, i.e. [0, inf] for this query `host_network_receive_errors
-  prophet_weekly: # we can set up alias for model
-    class: 'prophet'
+  envelope_weekly: # we can set up alias for model
+    class: 'temporal_envelope'
+    alpha: 0.005  # adapt the trend while using the bootstrap-only fit schedule
+    loss_reactivity: 3  # allow new deviations to update the envelope
     provide_series: ['anomaly_score', 'y', 'yhat', 'yhat_lower', 'yhat_upper']
     queries: ['cpu_seconds_total']
-    schedulers: ['periodic_offline_1w']  # will be attached to 1-week scheduler, re-fit every 24h and infer every 15m
-    min_dev_from_expected: [0.01, 0.01]  # minimum deviation from expected value to be even considered as anomaly
+    schedulers: ['periodic_online_weekly']  # fit on two weekly cycles, then update online every 15m
     anomaly_score_outside_data_range: 1.5  # override default anomaly score outside expected data range
-    detection_direction: 'above_expected'
     clip_predictions: True  # clip predictions to expected data range, i.e. [0, inf] for this query `cpu_seconds_total`
-    args:  # model-specific arguments
-      interval_width: 0.98
-      yearly_seasonality: False  # disable yearly seasonality, since we have only 7 days of data
+    seasonalities: ['hod_smooth', 'dow_smooth']
 
 # where to read data from
 # https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader
@@ -95,6 +92,7 @@ reader:
   datasource_url: "https://play.victoriametrics.com/"
   tenant_id: "0:0"
   sampling_period: "30s"  # what data resolution to fetch from VictoriaMetrics' /query_range endpoint
+  workers: 0  # automatically choose bounded datasource concurrency
   latency_offset: '1ms'
   query_from_last_seen_timestamp: False
   tz: "UTC"  # timezone to use for queries without explicit timezone
@@ -103,17 +101,21 @@ reader:
     cpu_seconds_total:
       expr: 'avg(rate(node_cpu_seconds_total[5m])) by (mode)' 
       # step: '30s'  # if not set, will be equal to reader-level sampling_period
-      data_range: [0, 'inf']  # expected value range, anomaly_score = anomaly_score_outside_data_range if y (real value) is outside
+      data_range: [0, 'inf']  # query-level business policy from v1.30.2
+      detection_direction: 'above_expected'  # query-level from v1.30.2; detect spikes only
+      min_dev_from_expected: [0.01, 0.01]  # query-level from v1.30.2
     host_network_receive_errors:
       expr: 'rate(node_network_receive_errs_total[3m]) / rate(node_network_receive_packets_total[3m])'
       step: '15m'  # here we override per-query `sampling_period` to request way less data from VM TSDB
-      data_range: [0, 'inf']
+      data_range: [0, 'inf']  # query-level business policy from v1.30.2
+      detection_direction: 'above_expected'  # query-level from v1.30.2; detect spikes only
+      min_dev_from_expected: 0.0  # query-level from v1.30.2; absolute-deviation filtering is disabled
 
 # where to write data to
 # https://docs.victoriametrics.com/anomaly-detection/components/writer/
 writer:
   datasource_url: "http://victoriametrics:8428/"
-  # tenant_id: "0:0"  # for VictoriaMetrics cluster, can support "multitenant"
+  tenant_id: "0:0"  # for VictoriaMetrics cluster, can support "multitenant"
   # https://docs.victoriametrics.com/anomaly-detection/components/writer/#metrics-formatting
   metric_format:
     __name__: $VAR
@@ -148,7 +150,7 @@ server:
 
 {{% available_from "v1.25.0" anomaly %}} The service supports hot reload of configuration files, applying changes without an explicit restart. Enable it with the `--watch` [CLI argument](https://docs.victoriametrics.com/anomaly-detection/quickstart/#command-line-arguments). The `vmanomaly_config_reload_enabled` [self-monitoring metric](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#startup-metrics) is `1` when hot reload is enabled and `0` otherwise.
 
-> [!NOTE]
+> [!WARNING]
 > {{% deprecated_from "v1.29.5" anomaly %}} File system event-based hot reload has been deprecated in favor of content-based polling with configurable `-configCheckInterval` due to reliability issues with Kubernetes ConfigMap symlink rotations and other filesystems where event delivery can be inconsistent. If you were using file system event-based hot reload, please switch to content-based polling by enabling `--watch` flag and configuring `-configCheckInterval` as needed.
 
 ### How it works
@@ -175,7 +177,7 @@ schedulers:
   periodic:
     class: 'periodic'
     infer_every: "30s"
-    fit_every: "365d"
+    fit_every: "1000d"  # bootstrap-only schedule; use a finite cadence if accumulated state must be reset
     fit_window: "24h"
 
 reader:
@@ -204,6 +206,7 @@ models:
 
 writer:
   datasource_url: "http://victoriametrics:8428/"
+  tenant_id: "0:0"
 
 monitoring:
   push:

docs/anomaly-detection/components/monitoring.md

@@ -333,6 +333,14 @@ For detailed guidance on configuring mTLS parameters such as `verify_tls`, `tls_
         <tr>
             <td>
 
+<span style="white-space: nowrap;">`vmanomaly_native_threads_per_worker`</span>
+            </td>
+            <td>Gauge</td>
+            <td>Effective maximum native numerical-library threads per model worker{{% available_from "v1.30.2" anomaly %}} after resolving [`settings.native_threads_per_worker`](https://docs.victoriametrics.com/anomaly-detection/components/settings/#parallelization) against the effective worker count and container-aware CPU capacity.</td>
+        </tr>
+        <tr>
+            <td>
+
 <span style="white-space: nowrap;">`vmanomaly_config_entities`</span>
             </td>
             <td>Gauge</td>
@@ -588,7 +596,7 @@ Label names [description](#labelnames)
 
 `Counter`
             </td>
-            <td>The number of valid datapoints accepted by `model_alias`, excluding NaN and Inf values, during `fit`, `infer`, or combined `fit_infer` execution for the `query_key` query.</td>
+            <td>The number of valid datapoints accepted by `model_alias`, excluding NaN and Inf values, during `fit`, `infer`, or combined `fit_infer` execution for the `query_key` query. During inference, only previously unseen valid rows are counted {{% available_from "v1.30.1" anomaly %}}.</td>
             <td>
 
 `stage`, `query_key`, `model_alias`, `scheduler_alias`, `preset`
@@ -687,7 +695,7 @@ Label names [description](#labelnames)
 
 `Histogram` (was `Summary`{{% deprecated_from "v1.17.0" anomaly %}})
             </td>
-            <td>The total time (in seconds) taken by write requests to VictoriaMetrics `url` for the `query_key` query within the specified scheduler `scheduler_alias`, in the `vmanomaly` service running in `preset` mode.
+            <td>The total time (in seconds) taken by write requests to VictoriaMetrics `url` for the `query_key` query within the specified scheduler `scheduler_alias`, in the `vmanomaly` service running in `preset` mode. Successful and handled failed attempts, including connection retries, are observed {{% available_from "v1.30.1" anomaly %}}.
 </td>
             <td>
 

docs/anomaly-detection/components/reader.md

@@ -59,7 +59,7 @@ reader:
       step: '10s'  # individual step for this query, will be filled with `sampling_period` from the root level
       data_range: ['-inf', 'inf']  # by default, no constraints applied on data range
       tz: 'UTC'  # by default, tz-free data is used throughout the model lifecycle
-      # new query-level arguments will be added in backward-compatible way in future releases
+      # from v1.30.2, explicitly add detection_direction and minimum-deviation policies here when needed
 ```
 {{% /collapse %}}
 
@@ -85,9 +85,19 @@ There is change {{% available_from "v1.13.0" anomaly %}} of [`queries`](https://
 
   > If not set explicitly (or if older config style prior to [v1.13.0](https://docs.victoriametrics.com/anomaly-detection/changelog/#v1130)) is used, then it is set to reader-level `data_range` arg{{% available_from "v1.18.1" anomaly %}}
 
+  > Configuring `data_range` in a model is {{% deprecated_from "v1.30.2" anomaly %}}. Configure it under `reader.queries.<alias>` so the KPI domain remains the same when the query is attached to different models. Existing model-level values remain compatible as model-local fallbacks when the query does not define an explicit value.
+
+- `detection_direction`{{% available_from "v1.30.2" anomaly %}} (`both`, `above_expected`, or `below_expected`): controls whether deviations on both sides, only above the expected value, or only below it can produce anomaly scores. The default is `both`. See [detection direction](https://docs.victoriametrics.com/anomaly-detection/components/models/#detection-direction) for behavior details.
+
+- `min_dev_from_expected`{{% available_from "v1.30.2" anomaly %}} (float or one/two-element list[float]): ignores deviations smaller than the configured absolute threshold. A scalar or one-element list applies to both directions; a two-element list configures lower and upper deviations separately. See [minimal deviation from expected](https://docs.victoriametrics.com/anomaly-detection/components/models/#minimal-deviation-from-expected).
+
+- `min_rel_dev_from_expected`{{% available_from "v1.30.2" anomaly %}} (float or one/two-element list[float]): ignores deviations smaller than the configured percentage of the absolute expected value. A scalar or one-element list applies to both directions; a two-element list configures lower and upper percentages separately. See [minimal relative deviation from expected](https://docs.victoriametrics.com/anomaly-detection/components/models/#minimal-relative-deviation-from-expected).
+
+  > Configuring `detection_direction`, `min_dev_from_expected`, or `min_rel_dev_from_expected` in a model is {{% deprecated_from "v1.30.2" anomaly %}}. Query-level values are authoritative. Existing model-level values remain compatible only as model-local fallbacks for attached queries that do not define the corresponding policy.
+
 - `max_points_per_query`{{% available_from "v1.17.0" anomaly %}} (int): Optional arg, overrides how `search.maxPointsPerTimeseries` flag{{% available_from "v1.14.1" anomaly %}} impacts `vmanomaly` on splitting long `fit_window` [queries](https://docs.victoriametrics.com/anomaly-detection/components/reader/#vm-reader) into smaller sub-intervals. This helps users avoid hitting the `search.maxQueryDuration` limit for individual queries by distributing initial query across multiple subquery requests with minimal overhead. Set less than `search.maxPointsPerTimeseries` if hitting `maxQueryDuration` limits. If set on a query-level, it overrides the global `max_points_per_query` (reader-level).
 
-- `tz`{{% available_from "v1.18.0" anomaly %}} (string): this optional argument enables timezone specification per query, overriding the reader’s default `tz`. This setting helps to account for local timezone shifts, such as [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models that are sensitive to seasonal variations (e.g., [`ProphetModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)).
+- `tz`{{% available_from "v1.18.0" anomaly %}} (string): this optional argument enables timezone specification per query, overriding the reader’s default `tz`. This setting helps to account for local timezone shifts, such as [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models that are sensitive to seasonal variations (e.g., [`TemporalEnvelopeModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)).
 
 - `tenant_id` {{% available_from "v1.19.0" anomaly %}} (string): this optional argument enables tenant-level separation for queries (e.g. `query1` to get the data from tenant "0:0", `query2` - from tenant "1:0"). It works as follows:
   - if *not set, inherits* reader-level `tenant_id`
@@ -115,7 +125,10 @@ reader:
     ingestion_rate_t1:
       expr: 'sum(rate(vm_rows_inserted_total[5m])) by (type) > 0'
       step: '2m'  # overrides global `sampling_period` of 1m
-      data_range: [10, 'inf']  # meaning only positive values > 10 are expected, i.e. a value `y` < 10 will trigger anomaly score > 1
+      data_range: [10, 'inf']  # query-level business policy from v1.30.2; y < 10 triggers anomaly score > 1
+      detection_direction: 'above_expected'  # query-level from v1.30.2; only spikes can be anomalous
+      min_dev_from_expected: [0, 5]  # query-level from v1.30.2; ignore upward deviations smaller than 5
+      min_rel_dev_from_expected: [0, 15]  # query-level from v1.30.2; ignore upward deviations below 15%
       max_points_per_query: 5000 # overrides reader-level value of 10000 for `ingestion_rate` query
       tz: 'America/New_York'  # to override reader-wise `tz`
       tenant_id: '1:0'  # overriding tenant_id to isolate data
@@ -302,6 +315,19 @@ Optional timeout {{% available_from "v1.30.0" anomaly %}} for post-fetch process
         <tr>
             <td>
 
+<span style="white-space: nowrap;">`workers`</span>
+            </td>
+            <td>
+
+`0`
+            </td>
+            <td>
+Maximum concurrent datasource fetch threads {{% available_from "v1.30.2" anomaly %}}. `0` selects a bounded value automatically from the number of queries and available CPUs. A positive value sets an explicit cap for queries and disk-streamed split-query chunks.
+            </td>
+        </tr>
+        <tr>
+            <td>
+
 <span style="white-space: nowrap;">`verify_tls`</span>
             </td>
             <td>
@@ -441,7 +467,7 @@ Optional arg{{% available_from "v1.17.0" anomaly %}} overrides how `search.maxPo
 `UTC`
             </td>
             <td>
-Optional argument {{% available_from "v1.18.0" anomaly %}} specifies the [IANA](https://nodatime.org/TimeZones) timezone to account for local shifts, like [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models sensitive to seasonal patterns (e.g., [`TemporalEnvelopeModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope), [`ProphetModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet), or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)). Defaults to `UTC` if not set and can be overridden on a [per-query basis](#per-query-parameters).
+Optional argument {{% available_from "v1.18.0" anomaly %}} specifies the [IANA](https://nodatime.org/TimeZones) timezone to account for local shifts, like [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models sensitive to seasonal patterns (e.g., [`TemporalEnvelopeModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)). Defaults to `UTC` if not set and can be overridden on a [per-query basis](#per-query-parameters).
             </td>
         </tr>
         <tr>
@@ -510,6 +536,7 @@ reader:
   timeout: '30s'  # backward-compatible default for both phases
   fetch_timeout: '30s'  # timeout for each datasource request, overrides `timeout` if set
   processing_timeout: '1m'  # timeout for preparing fetched series for fit/infer, overrides `timeout` if set
+  workers: 0  # automatic bounded datasource concurrency; set a positive value for an explicit cap
   query_from_last_seen_timestamp: True  # false by default
   latency_offset: '1ms'
   series_processing_batch_size: 8
@@ -825,7 +852,7 @@ Frequency of the points returned. Will be converted to `/select/stats_query_rang
 `America/New_York`
             </td>
             <td>
-(Optional) Specifies the [IANA](https://nodatime.org/TimeZones) timezone to account for local shifts, like [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models sensitive to seasonal patterns (e.g., [`ProphetModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#prophet) or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)). Defaults to `UTC` if not set and can be overridden on a [per-query basis](#per-query-parameters).
+(Optional) Specifies the [IANA](https://nodatime.org/TimeZones) timezone to account for local shifts, like [DST](https://en.wikipedia.org/wiki/Daylight_saving_time), in models sensitive to seasonal patterns (e.g., [`TemporalEnvelopeModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#temporal-envelope) or [`OnlineQuantileModel`](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-seasonal-quantile)). Defaults to `UTC` if not set and can be overridden on a [per-query basis](#per-query-parameters).
             </td>
         </tr>
         <tr>
@@ -896,6 +923,19 @@ Optional timeout {{% available_from "v1.30.0" anomaly %}} for post-fetch process
         <tr>
             <td>
 
+<span style="white-space: nowrap;">`workers`</span>
+            </td>
+            <td>
+
+`0`
+            </td>
+            <td>
+Maximum concurrent datasource fetch threads {{% available_from "v1.30.2" anomaly %}}. `0` selects a bounded value automatically from the number of queries and available CPUs. A positive value sets an explicit cap for queries and disk-streamed split-query chunks.
+            </td>
+        </tr>
+        <tr>
+            <td>
+
 <span style="white-space: nowrap;">`verify_tls`</span>
             </td>
             <td>
@@ -1037,12 +1077,15 @@ reader:
   timeout: '30s'  # backward-compatible default for both phases
   fetch_timeout: '30s'  # timeout for each datasource request, overrides `timeout` if set
   processing_timeout: '1m'  # timeout for preparing fetched series for fit/infer, overrides `timeout` if set
+  workers: 0  # automatic bounded datasource concurrency; set a positive value for an explicit cap
   queries:
     # one query returning 1 result fields (avg_duration), it will have __name__ label (series name) as `duration_30m__avg`
     duration_avg_30m:
       expr: "* | stats avg(duration) as avg"  # initial LogsQL expression
       step: '2m'  # overrides global `sampling_period` of 1m
-      data_range: [0, 'inf']  # meaning only positive values > 0 are expected, i.e. a value `y` < 0 will trigger anomaly score > 1
+      data_range: [0, 'inf']  # query-level business policy from v1.30.2; y < 0 triggers anomaly score > 1
+      detection_direction: 'above_expected'  # query-level from v1.30.2
+      min_rel_dev_from_expected: [0, 20]  # query-level from v1.30.2; ignore upward deviations below 20%
       tz: 'America/New_York'  # to override reader-wise `tz`
       # tenant_id: '1:0'  # overriding tenant_id to isolate data
       # offset: '-15s'  # to override reader-wise `offset` and query data 15 seconds earlier to account for data collection delays

docs/anomaly-detection/components/scheduler.md

@@ -70,10 +70,13 @@ options={`"scheduler.periodic.PeriodicScheduler"`, `"scheduler.oneoff.OneoffSche
 
 ## Periodic scheduler 
 
+> [!WARNING]
 > If `start_from` [parameter](#parameters-1) is used, it's suggested to also set `restore_state: true` in the [Settings section](https://docs.victoriametrics.com/anomaly-detection/components/settings/#state-restoration) of a config, so that the scheduler can restore its state from the previous run **if terminated or restarted in between scheduled runs** and continue producing anomaly scores without interruptions, otherwise the service will be idle until future `start_from` time is reached. E.g. if `start_from` is set to `20:00` and the service is started and then terminated and restarted at `20:30`, it will not produce any anomaly scores until the next day's `20:00` is reached (+23:30 of being idle), which introduces inconvenience for the users.
 
 > {{% available_from "v1.30.0" anomaly %}} If a periodic scheduler worker exits unexpectedly, the service attempts bounded restarts with exponential backoff instead of shutting down unrelated schedulers. Monitor [`vmanomaly_scheduler_alive`](https://docs.victoriametrics.com/anomaly-detection/components/monitoring/#startup-metrics) and `vmanomaly_scheduler_restarts_total` to alert on persistent failures.
 
+> {{% available_from "v1.30.1" anomaly %}} For exact-capable [online models](https://docs.victoriametrics.com/anomaly-detection/components/models/#online-models), `infer_every` is also the causal model-update cadence. If a delayed periodic job fetches several observations at once, they are processed on the same chronological grid used by exact backtesting rather than as one behaviorally different batch.
+
 ### Parameters
 
 For periodic scheduler parameters are defined as differences in times, expressed in difference units, e.g. days, hours, minutes, seconds. Time granularity is defined by the last characters of a string. Examples: `"50s"` (seconds), `"4m"` (minutes), `"3h"` (hours), `"2d"` (days), `"1w"` (weeks).
@@ -194,6 +197,7 @@ This configuration specifies that `vmanomaly` will calculate a 14-day time windo
 
 ## Oneoff scheduler
 
+> [!WARNING]
 > As of latest version, the Oneoff scheduler can't be explicitly used with a combination of [stateful service](https://docs.victoriametrics.com/anomaly-detection/components/settings/#state-restoration). It is designed to run once and exit, so it does not maintain state across runs. A warning will be raised in logs and internal state for such scheduler will not be saved and restored upon restart. If you need to run the scheduler periodically and/or maintain state, consider using the [Periodic scheduler](#periodic-scheduler) instead.
 
 ### Parameters
@@ -365,6 +369,7 @@ schedulers:
 
 > {{% available_from "v1.26.0" anomaly %}} `BacktestingScheduler` in [inference-only](https://docs.victoriametrics.com/anomaly-detection/components/scheduler/#inference-only-mode) mode is used in UI for backtesting configurations on historical data to verify that it works as expected before it goes live. See [vmanomaly UI](https://docs.victoriametrics.com/anomaly-detection/ui/) on how to access and use the UI.
 
+> [!WARNING]
 > As of latest version, the Backtesting scheduler can't be explicitly used with a combination of [state restoration](https://docs.victoriametrics.com/anomaly-detection/components/settings/#state-restoration). It is designed to run once and exit, so it does not maintain state across runs. A warning will be raised in logs and internal state for such scheduler will not be saved and restored upon restart. If you need to run the scheduler periodically and/or maintain state, consider using the [Periodic scheduler](#periodic-scheduler) instead.
 
 > A new, more intuitive backtesting mode is available {{% available_from "v1.22.1" anomaly %}}. In **Inference only** mode, the window you specify via `[from, to]` (or `[from_iso, to_iso]`) is used *solely for inference*, and the corresponding training (“fit”) windows are determined automatically. To enable this behavior, set:
@@ -440,7 +445,7 @@ In **Inference only** mode {{% available_from "v1.22.1" anomaly %}}, the schedul
 - `fit_window`: Duration of historical data used for each training run (e.g. `P7D`, `PT1H`).
 - `fit_every`: Interval between consecutive training/inference cycles.
 - {{% available_from "v1.28.0" anomaly %}} `exact`: If set to `true`, BacktestingScheduler will execute inference for online models in small chronological batches equal to `infer_every` to mimic the production scheduler. (default: `false`)
-- {{% available_from "v1.28.0" anomaly %}} `infer_every`: Optional inference cadence for exact mode, defining how often the scheduler should call infer between two fits, otherwise defaults to `fit_every` when unset.
+- {{% available_from "v1.28.0" anomaly %}} `infer_every`: Optional inference grid and, in exact mode, model-call cadence between two fits. {{% available_from "v1.30.1" anomaly %}} In `inference_only` mode, an omitted value is derived from the effective query step or reader sampling period and capped by `fit_every`; it falls back to `fit_every` only when neither reader value is available.
 - `n_jobs`: Number of parallel jobs for backtesting (default: `1`).
 
 #### Example