feat(prometheus): add the Prometheus query API under a /prometheus prefix

New GET|POST /prometheus/api/v1/query_range and /prometheus/api/v1/query
endpoints (pkg/prometheus/promapi), following the Prometheus HTTP API:
float-unix or RFC3339 times, float-seconds or duration-string durations,
the {status, data, errorType, error, warnings, infos} envelope with
Prometheus' status codes, and the 11,000-point cap. Wired through
signoz.Handlers like the other domain handlers. Range queries serve
through the RangeExecutor capability when the provider has it, so a
clickhousev2-serving deployment transpiles through these endpoints too.

The promapiconformance suite replays the frozen promqltest corpus against
these endpoints with clickhousev2 as the serving provider - the two paths
nothing else exercises. Instant cases go through /query with a real time
parameter. Its ledger holds the seven known Kahan-class divergences of
transpiled coarse-step serving.

Purely additive: the existing GET /api/v1/query_range and /api/v1/query
handlers are untouched.

Assisted-by: Claude Fable 5

.github/workflows/integrationci.yaml

@@ -58,6 +58,7 @@ jobs:
           - querierai
           - rawexportdata
           - promqlconformance
+          - promapiconformance
           - querierauthz
           - role
           - rootuser

pkg/prometheus/handler.go

@@ -0,0 +1,9 @@
+package prometheus
+
+import "net/http"
+
+type Handler interface {
+	Query(http.ResponseWriter, *http.Request)
+
+	QueryRange(http.ResponseWriter, *http.Request)
+}

pkg/prometheus/promapi/handler.go

@@ -0,0 +1,259 @@
+// Package promapi serves the Prometheus HTTP query API over a
+// prometheus.Prometheus provider: /query and /query_range in the shape of
+// Prometheus' /api/v1 endpoints (https://prometheus.io/docs/prometheus/latest/querying/api/),
+// intended to be mounted under a distinguishing prefix (/prometheus/api/v1)
+// so PromQL-only endpoints are separate from the SigNoz query APIs. The
+// request and response contracts follow Prometheus: form-encoded GET/POST
+// params, {"status":"success","data":{resultType,result}} on success and
+// {"status":"error","errorType","error"} with Prometheus' status codes on
+// failure — so Prometheus-compatible clients can point at the prefix.
+package promapi
+
+import (
+	"context"
+	"encoding/json"
+	"log/slog"
+	"math"
+	"net/http"
+	"strconv"
+	"time"
+
+	promModel "github.com/prometheus/common/model"
+	"github.com/prometheus/prometheus/promql"
+	"github.com/prometheus/prometheus/promql/parser"
+	"github.com/prometheus/prometheus/util/stats"
+
+	"github.com/SigNoz/signoz/pkg/errors"
+	"github.com/SigNoz/signoz/pkg/prometheus"
+)
+
+type handler struct {
+	logger *slog.Logger
+	prom   prometheus.Prometheus
+}
+
+func NewHandler(logger *slog.Logger, prom prometheus.Prometheus) prometheus.Handler {
+	return &handler{logger: logger, prom: prom}
+}
+
+type errorType string
+
+const (
+	errBadData  errorType = "bad_data"
+	errExec     errorType = "execution"
+	errCanceled errorType = "canceled"
+	errTimeout  errorType = "timeout"
+	errInternal errorType = "internal"
+)
+
+type queryData struct {
+	ResultType parser.ValueType `json:"resultType"`
+	Result     parser.Value     `json:"result"`
+	Stats      stats.QueryStats `json:"stats,omitempty"`
+}
+
+type response struct {
+	Status    string     `json:"status"`
+	Data      *queryData `json:"data,omitempty"`
+	ErrorType errorType  `json:"errorType,omitempty"`
+	Error     string     `json:"error,omitempty"`
+	Warnings  []string   `json:"warnings,omitempty"`
+	Infos     []string   `json:"infos,omitempty"`
+}
+
+// QueryRange evaluates an expression over a grid: query, start, end, step,
+// and optional timeout/stats params, all in Prometheus' formats.
+func (h *handler) QueryRange(w http.ResponseWriter, r *http.Request) {
+	start, err := parseTime(r.FormValue("start"))
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	end, err := parseTime(r.FormValue("end"))
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	if end.Before(start) {
+		h.respondError(r.Context(), w, errBadData, errors.NewInvalidInputf(errors.CodeInvalidInput, "end timestamp must not be before start time"))
+		return
+	}
+	step, err := parseDuration(r.FormValue("step"))
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	if step <= 0 {
+		h.respondError(r.Context(), w, errBadData, errors.NewInvalidInputf(errors.CodeInvalidInput, "zero or negative query resolution step widths are not accepted. Try a positive integer"))
+		return
+	}
+	// The engine materializes every point of every series; an unbounded
+	// grid is an unbounded allocation. 11,000 points covers 60s resolution
+	// for a week or 1h resolution for a year.
+	if end.Sub(start)/step > 11000 {
+		h.respondError(r.Context(), w, errBadData, errors.NewInvalidInputf(errors.CodeInvalidInput, "exceeded maximum resolution of 11,000 points per timeseries. Try decreasing the query resolution (?step=XX)"))
+		return
+	}
+
+	ctx, cancel, err := h.contextWithTimeout(r)
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	defer cancel()
+
+	if h.tryRangeExecutor(ctx, w, r, start, end, step) {
+		return
+	}
+
+	qry, err := h.prom.Engine().NewRangeQuery(ctx, h.prom.Storage(), nil, r.FormValue("query"), start, end, step)
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	h.exec(ctx, w, r, qry)
+}
+
+// tryRangeExecutor serves the query the way a RangeExecutor provider is
+// designed to serve: evaluated inside the datastore when the shape allows.
+// It reports whether the response was written.
+func (h *handler) tryRangeExecutor(ctx context.Context, w http.ResponseWriter, r *http.Request, start, end time.Time, step time.Duration) bool {
+	re, ok := h.prom.(prometheus.RangeExecutor)
+	if !ok {
+		return false
+	}
+	matrix, served, err := re.TryExecuteRange(ctx, r.FormValue("query"), start, end, step)
+	if err != nil {
+		h.respondError(ctx, w, errExec, err)
+		return true
+	}
+	if !served {
+		return false
+	}
+	h.respond(ctx, w, &queryData{ResultType: matrix.Type(), Result: matrix}, nil, nil)
+	return true
+}
+
+// Query evaluates an expression at a single instant: query and optional
+// time/timeout/stats params. A missing time evaluates at the server's now,
+// as in Prometheus.
+func (h *handler) Query(w http.ResponseWriter, r *http.Request) {
+	ts := time.Now()
+	if t := r.FormValue("time"); t != "" {
+		var err error
+		ts, err = parseTime(t)
+		if err != nil {
+			h.respondError(r.Context(), w, errBadData, err)
+			return
+		}
+	}
+
+	ctx, cancel, err := h.contextWithTimeout(r)
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	defer cancel()
+
+	qry, err := h.prom.Engine().NewInstantQuery(ctx, h.prom.Storage(), nil, r.FormValue("query"), ts)
+	if err != nil {
+		h.respondError(r.Context(), w, errBadData, err)
+		return
+	}
+	h.exec(ctx, w, r, qry)
+}
+
+func (h *handler) exec(ctx context.Context, w http.ResponseWriter, r *http.Request, qry promql.Query) {
+	defer qry.Close()
+	res := qry.Exec(ctx)
+	if res.Err != nil {
+		h.logger.ErrorContext(ctx, "error evaluating promql query", errors.Attr(res.Err))
+		switch res.Err.(type) {
+		case promql.ErrQueryCanceled:
+			h.respondError(ctx, w, errCanceled, res.Err)
+		case promql.ErrQueryTimeout:
+			h.respondError(ctx, w, errTimeout, res.Err)
+		case promql.ErrStorage:
+			h.respondError(ctx, w, errInternal, res.Err)
+		default:
+			h.respondError(ctx, w, errExec, res.Err)
+		}
+		return
+	}
+
+	data := &queryData{ResultType: res.Value.Type(), Result: res.Value}
+	if r.FormValue("stats") != "" {
+		data.Stats = stats.NewQueryStats(qry.Stats())
+	}
+	warnings, infos := res.Warnings.AsStrings(r.FormValue("query"), 10, 10)
+	h.respond(ctx, w, data, warnings, infos)
+}
+
+func (h *handler) contextWithTimeout(r *http.Request) (context.Context, context.CancelFunc, error) {
+	ctx := r.Context()
+	if to := r.FormValue("timeout"); to != "" {
+		timeout, err := parseDuration(to)
+		if err != nil {
+			return nil, nil, err
+		}
+		ctx, cancel := context.WithTimeout(ctx, timeout)
+		return ctx, cancel, nil
+	}
+	ctx, cancel := context.WithCancel(ctx)
+	return ctx, cancel, nil
+}
+
+func (h *handler) respond(ctx context.Context, w http.ResponseWriter, data *queryData, warnings, infos []string) {
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(http.StatusOK)
+	if err := json.NewEncoder(w).Encode(&response{Status: "success", Data: data, Warnings: warnings, Infos: infos}); err != nil {
+		h.logger.ErrorContext(ctx, "error writing prometheus api response", errors.Attr(err))
+	}
+}
+
+// respondError follows Prometheus' status-code mapping: bad_data 400,
+// execution 422, canceled/timeout 503, internal 500.
+func (h *handler) respondError(ctx context.Context, w http.ResponseWriter, typ errorType, err error) {
+	code := http.StatusInternalServerError
+	switch typ {
+	case errBadData:
+		code = http.StatusBadRequest
+	case errExec:
+		code = http.StatusUnprocessableEntity
+	case errCanceled, errTimeout:
+		code = http.StatusServiceUnavailable
+	}
+	w.Header().Set("Content-Type", "application/json")
+	w.WriteHeader(code)
+	if encErr := json.NewEncoder(w).Encode(&response{Status: "error", ErrorType: typ, Error: err.Error()}); encErr != nil {
+		h.logger.ErrorContext(ctx, "error writing prometheus api error response", errors.Attr(encErr))
+	}
+}
+
+// parseTime accepts Prometheus' time formats: float unix seconds or RFC3339.
+func parseTime(s string) (time.Time, error) {
+	if t, err := strconv.ParseFloat(s, 64); err == nil {
+		sec, ns := math.Modf(t)
+		return time.Unix(int64(sec), int64(ns*float64(time.Second))), nil
+	}
+	if t, err := time.Parse(time.RFC3339Nano, s); err == nil {
+		return t, nil
+	}
+	return time.Time{}, errors.NewInvalidInputf(errors.CodeInvalidInput, "cannot parse %q to a valid timestamp", s)
+}
+
+// parseDuration accepts Prometheus' duration formats: float seconds or a
+// duration string like 5m.
+func parseDuration(s string) (time.Duration, error) {
+	if d, err := strconv.ParseFloat(s, 64); err == nil {
+		ts := d * float64(time.Second)
+		if ts > float64(math.MaxInt64) || ts < float64(math.MinInt64) {
+			return 0, errors.NewInvalidInputf(errors.CodeInvalidInput, "cannot parse %q to a valid duration. It overflows int64", s)
+		}
+		return time.Duration(ts), nil
+	}
+	if d, err := promModel.ParseDuration(s); err == nil {
+		return time.Duration(d), nil
+	}
+	return 0, errors.NewInvalidInputf(errors.CodeInvalidInput, "cannot parse %q to a valid duration", s)
+}

pkg/query-service/app/http_handler.go

@@ -484,6 +484,9 @@ func (aH *APIHandler) Respond(w http.ResponseWriter, data interface{}) {
 func (aH *APIHandler) RegisterRoutes(router *mux.Router, am *middleware.AuthZ) {
 	router.HandleFunc("/api/v1/query_range", am.ViewAccess(aH.queryRangeMetrics)).Methods(http.MethodGet)
 	router.HandleFunc("/api/v1/query", am.ViewAccess(aH.queryMetrics)).Methods(http.MethodGet)
+
+	router.HandleFunc("/prometheus/api/v1/query_range", am.ViewAccess(aH.Signoz.Handlers.PrometheusHandler.QueryRange)).Methods(http.MethodGet, http.MethodPost)
+	router.HandleFunc("/prometheus/api/v1/query", am.ViewAccess(aH.Signoz.Handlers.PrometheusHandler.Query)).Methods(http.MethodGet, http.MethodPost)
 	router.HandleFunc("/api/v1/rules", am.ViewAccess(aH.listRules)).Methods(http.MethodGet)
 	router.HandleFunc("/api/v1/rules/{id}", am.ViewAccess(aH.getRule)).Methods(http.MethodGet)
 	router.HandleFunc("/api/v1/rules", am.EditAccess(aH.createRule)).Methods(http.MethodPost)

pkg/signoz/handler.go

@@ -48,6 +48,8 @@ import (
 	"github.com/SigNoz/signoz/pkg/modules/tracedetail/impltracedetail"
 	"github.com/SigNoz/signoz/pkg/modules/tracefunnel"
 	"github.com/SigNoz/signoz/pkg/modules/tracefunnel/impltracefunnel"
+	"github.com/SigNoz/signoz/pkg/prometheus"
+	"github.com/SigNoz/signoz/pkg/prometheus/promapi"
 	"github.com/SigNoz/signoz/pkg/querier"
 	"github.com/SigNoz/signoz/pkg/ruler"
 	"github.com/SigNoz/signoz/pkg/ruler/signozruler"
@@ -81,6 +83,7 @@ type Handlers struct {
 	RuleStateHistory        rulestatehistory.Handler
 	SpanMapperHandler       spanmapper.Handler
 	AlertmanagerHandler     alertmanager.Handler
+	PrometheusHandler       prometheus.Handler
 	TraceDetail             tracedetail.Handler
 	RulerHandler            ruler.Handler
 	LLMPricingRuleHandler   llmpricingrule.Handler
@@ -101,6 +104,7 @@ func NewHandlers(
 	zeusService zeus.Zeus,
 	registryHandler factory.Handler,
 	alertmanagerService alertmanager.Alertmanager,
+	prometheusService prometheus.Prometheus,
 	rulerService ruler.Ruler,
 	statsAggregator statsreporter.Aggregator,
 ) Handlers {
@@ -129,6 +133,7 @@ func NewHandlers(
 		CloudIntegrationHandler: implcloudintegration.NewHandler(modules.CloudIntegration),
 		SpanMapperHandler:       implspanmapper.NewHandler(modules.SpanMapper),
 		AlertmanagerHandler:     signozalertmanager.NewHandler(alertmanagerService),
+		PrometheusHandler:       promapi.NewHandler(providerSettings.Logger, prometheusService),
 		TraceDetail:             impltracedetail.NewHandler(modules.TraceDetail),
 		RulerHandler:            signozruler.NewHandler(rulerService),
 		LLMPricingRuleHandler:   impllmpricingrule.NewHandler(modules.LLMPricingRule),

pkg/signoz/handler_test.go

@@ -63,7 +63,7 @@ func TestNewHandlers(t *testing.T) {
 
 	querierHandler := querier.NewHandler(providerSettings, nil, nil)
 	registryHandler := factory.NewHandler(nil)
-	handlers := NewHandlers(modules, providerSettings, nil, querierHandler, nil, nil, nil, nil, nil, nil, nil, registryHandler, alertmanager, nil, nil)
+	handlers := NewHandlers(modules, providerSettings, nil, querierHandler, nil, nil, nil, nil, nil, nil, nil, registryHandler, alertmanager, nil, nil, nil)
 	reflectVal := reflect.ValueOf(handlers)
 	for i := 0; i < reflectVal.NumField(); i++ {
 		f := reflectVal.Field(i)

pkg/signoz/signoz.go

@@ -617,7 +617,7 @@ func New(
 
 	// Initialize all handlers for the modules
 	registryHandler := factory.NewHandler(registry)
-	handlers := NewHandlers(modules, providerSettings, analytics, querierHandler, licensing, global, flagger, gateway, telemetryMetadataStore, authz, zeus, registryHandler, alertmanager, rulerInstance, statsAggregator)
+	handlers := NewHandlers(modules, providerSettings, analytics, querierHandler, licensing, global, flagger, gateway, telemetryMetadataStore, authz, zeus, registryHandler, alertmanager, prometheus, rulerInstance, statsAggregator)
 
 	// Initialize the API server (after registry so it can access service health)
 	apiserverInstance, err := factory.NewProviderFromNamedMap(

pkg/statementbuilder/logsstatementbuilder/stmt_builder_test.go

@@ -469,6 +469,8 @@ func TestStatementBuilderListQueryResourceTests(t *testing.T) {
 			expectedErr: nil,
 		},
 		{
+			// The `[*]` path is extracted per value, not as an Array(String) compared to a
+			// scalar — ClickHouse rejects that outright (code 130).
 			name:        "IN operator with json search",
 			requestType: qbtypes.RequestTypeRaw,
 			query: qbtypes.QueryBuilderQuery[qbtypes.LogAggregation]{
@@ -479,7 +481,7 @@ func TestStatementBuilderListQueryResourceTests(t *testing.T) {
 				Limit: 10,
 			},
 			expected: qbtypes.Statement{
-				Query:    "SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE ((JSONExtract(JSON_QUERY(body, '$.\"user_names\"[*]'), 'Array(String)') = ?) AND JSON_EXISTS(body, '$.\"user_names\"[*]')) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
+				Query:    "SELECT timestamp, id, trace_id, span_id, trace_flags, severity_text, severity_number, scope_name, scope_version, body, attributes_string, attributes_number, attributes_bool, resources_string, scope_string FROM signoz_logs.distributed_logs_v2 WHERE ((JSON_VALUE(body, '$.\"user_names\"[*]') = ?) AND JSON_EXISTS(body, '$.\"user_names\"[*]')) AND timestamp >= ? AND ts_bucket_start >= ? AND timestamp < ? AND ts_bucket_start <= ? LIMIT ?",
 				Args:     []any{"john_doe", "1747947419000000000", uint64(1747945619), "1747983448000000000", uint64(1747983448), 10},
 				Warnings: []string{querybuilder.NewKeyNotFoundWarning("user_names[*]")},
 			},

pkg/telemetryschema/audittelemetryschema/condition_builder.go

@@ -94,7 +94,11 @@ func (c *conditionBuilder) conditionFor(
 		}
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.E(fieldExpression, value))
+			cond, err := c.conditionFor(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.Or(conditions...), nil
 	case qbtypes.FilterOperatorNotIn:
@@ -104,7 +108,11 @@ func (c *conditionBuilder) conditionFor(
 		}
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.NE(fieldExpression, value))
+			cond, err := c.conditionFor(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorNotEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.And(conditions...), nil
 	case qbtypes.FilterOperatorExists, qbtypes.FilterOperatorNotExists:

pkg/telemetryschema/logstelemetryschema/condition_builder.go

@@ -410,7 +410,11 @@ func (c *conditionBuilder) conditionForResolvedKey(
 		// instead of using IN, we use `=` + `OR` to make use of index
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.E(fieldExpression, value))
+			cond, err := c.conditionForResolvedKey(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.Or(conditions...), nil
 	case qbtypes.FilterOperatorNotIn:
@@ -421,7 +425,11 @@ func (c *conditionBuilder) conditionForResolvedKey(
 		// instead of using NOT IN, we use `!=` + `AND` to make use of index
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.NE(fieldExpression, value))
+			cond, err := c.conditionForResolvedKey(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorNotEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.And(conditions...), nil
 

pkg/telemetryschema/logstelemetryschema/condition_builder_test.go

@@ -905,3 +905,52 @@ func TestConditionForJSONBodySearch(t *testing.T) {
 		})
 	}
 }
+
+// IN on the body column routes each value back through the `=` path; the SQL it produces
+// must stay what the shared IN handling produced before, including for a mixed-type list.
+func TestConditionForBodyIn(t *testing.T) {
+	testCases := []struct {
+		name         string
+		values       []any
+		expectedSQL  string
+		expectedArgs []any
+	}{
+		{
+			name:         "strings",
+			values:       []any{"alpha", "beta"},
+			expectedSQL:  "(body = ? OR body = ?)",
+			expectedArgs: []any{"alpha", "beta"},
+		},
+		{
+			name:         "mixed types are stringified before they reach the column",
+			values:       []any{"alpha", float64(1), true},
+			expectedSQL:  "(body = ? OR body = ? OR body = ?)",
+			expectedArgs: []any{"alpha", "1", "true"},
+		},
+	}
+
+	fl := flaggertest.New(t)
+	fm := NewFieldMapper(fl)
+	conditionBuilder := NewConditionBuilder(fm, fl)
+
+	for _, tc := range testCases {
+		t.Run(tc.name, func(t *testing.T) {
+			key := telemetrytypes.TelemetryFieldKey{
+				Name:          "body",
+				FieldContext:  telemetrytypes.FieldContextLog,
+				FieldDataType: telemetrytypes.FieldDataTypeString,
+			}
+			sb := sqlbuilder.NewSelectBuilder()
+			sb.Select("1").From("t")
+			cond, _, err := conditionBuilder.ConditionFor(context.Background(), valuer.UUID{}, 0, 0, &key,
+				map[string][]*telemetrytypes.TelemetryFieldKey{key.Name: {&key}}, qbtypes.ConditionBuilderOptions{},
+				qbtypes.FilterOperatorIn, tc.values, sb)
+			require.NoError(t, err)
+			sb.Where(cond...)
+
+			sql, args := sb.BuildWithFlavor(sqlbuilder.ClickHouse)
+			assert.Contains(t, sql, tc.expectedSQL)
+			assert.Equal(t, tc.expectedArgs, args)
+		})
+	}
+}

pkg/telemetryschema/tracestelemetryschema/condition_builder.go

@@ -135,7 +135,11 @@ func (c *conditionBuilder) conditionFor(
 		// instead of using IN, we use `=` + `OR` to make use of index
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.E(fieldExpression, value))
+			cond, err := c.conditionFor(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.Or(conditions...), nil
 	case qbtypes.FilterOperatorNotIn:
@@ -146,7 +150,11 @@ func (c *conditionBuilder) conditionFor(
 		// instead of using NOT IN, we use `!=` + `AND` to make use of index
 		conditions := []string{}
 		for _, value := range values {
-			conditions = append(conditions, sb.NE(fieldExpression, value))
+			cond, err := c.conditionFor(ctx, orgID, startNs, endNs, key, qbtypes.FilterOperatorNotEqual, value, sb)
+			if err != nil {
+				return "", err
+			}
+			conditions = append(conditions, cond)
 		}
 		return sb.And(conditions...), nil
 

tests/fixtures/promqltestcorpus.py

@@ -0,0 +1,66 @@
+import json
+import math
+import os
+from collections.abc import Callable
+from datetime import UTC, datetime, timedelta
+
+from fixtures.metrics import Metrics
+
+TESTDATA_DIR = os.path.join(os.path.dirname(__file__), "..", "integration", "testdata", "promqltestcorpus")
+CORPUS_FILE = os.path.join(TESTDATA_DIR, "corpus.json")
+
+# Datasets sit on disjoint time windows (2h gaps, far beyond the 5m lookback)
+# so one bulk ingest serves every case without cross-talk.
+ISOLATION_GAP_MS = 2 * 3600 * 1000
+SPECIALS = {"NaN": math.nan, "Inf": math.inf, "-Inf": -math.inf}
+
+
+def ingest_promqltest_corpus(insert_metrics: Callable[[list[Metrics]], None]) -> tuple[dict, dict[int, int]]:
+    """Loads the frozen corpus, lays its datasets end to end on the timeline
+    (newest last, ending safely in the past), ingests every sample, and
+    returns (corpus, dataset base timestamps).
+
+    Dataset bases are hour-aligned: registration rows are hour-bucketed, so
+    behavior depends on where samples fall relative to hour boundaries, and
+    exact known-divergences enforcement needs identical placement every run."""
+    with open(CORPUS_FILE, encoding="utf-8") as f:
+        corpus = json.load(f)
+
+    cases_by_dataset: dict[int, list[dict]] = {}
+    for case in corpus["cases"]:
+        cases_by_dataset.setdefault(case["dataset"], []).append(case)
+
+    spans = {}
+    for ds in corpus["datasets"]:
+        sample_max = max((s["samples"][-1][0] for s in ds["series"] if s["samples"]), default=0)
+        case_max = max((c["end_ms"] for c in cases_by_dataset.get(ds["id"], [])), default=0)
+        spans[ds["id"]] = max(sample_max, case_max) + corpus["meta"]["lookback_ms"]
+
+    hour_ms = 3_600_000
+    advances = {ds["id"]: -(-(spans[ds["id"]] + ISOLATION_GAP_MS) // hour_ms) * hour_ms for ds in corpus["datasets"]}
+    total = sum(advances.values())
+    now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
+    cursor = (int((now - timedelta(hours=1)).timestamp() * 1000) - total) // hour_ms * hour_ms
+
+    bases: dict[int, int] = {}
+    metrics: list[Metrics] = []
+    for ds in corpus["datasets"]:
+        bases[ds["id"]] = cursor
+        for series in ds["series"]:
+            labels = dict(series["labels"])
+            metric_name = labels.pop("__name__")
+            for off_ms, raw in series["samples"]:
+                stale = raw == "stale"
+                metrics.append(
+                    Metrics(
+                        metric_name=metric_name,
+                        labels=labels,
+                        timestamp=datetime.fromtimestamp((cursor + off_ms) / 1000, tz=UTC),
+                        value=0.0 if stale else (SPECIALS[raw] if isinstance(raw, str) else float(raw)),
+                        flags=1 if stale else 0,
+                    )
+                )
+        cursor += advances[ds["id"]]
+
+    insert_metrics(metrics)
+    return corpus, bases

tests/integration/tests/promapiconformance/01_prometheus_api_corpus.py

@@ -0,0 +1,138 @@
+import json
+import math
+from collections.abc import Callable
+from http import HTTPStatus
+
+import requests
+
+from fixtures import types
+from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
+from fixtures.metrics import Metrics
+from fixtures.promqltestcorpus import ingest_promqltest_corpus
+
+# The same frozen corpus the promqlconformance package replays through
+# /api/v5/query_range, here replayed against the /prometheus/api/v1 endpoints
+# with clickhousev2 as the serving provider (see conftest.py) — the two paths
+# nothing else exercises. Range cases go to query_range, where a
+# RangeExecutor provider serves transpiled statements when the shape allows.
+# Instant cases go to /query with a real `time` parameter, so they need no
+# grid encoding.
+#
+# Prometheus API sample values are strings, "NaN"/"+Inf"/"-Inf" included.
+SPECIALS = {"NaN": math.nan, "Inf": math.inf, "+Inf": math.inf, "-Inf": -math.inf}
+QUERY_TIMEOUT = 30
+
+
+def test_prometheus_api_corpus(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_metrics: Callable[[list[Metrics]], None],
+) -> None:
+    corpus, bases = ingest_promqltest_corpus(insert_metrics)
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+
+    failures: list[str] = []
+    for case in corpus["cases"]:
+        # instant-coarse variants encode an instant eval as a coarse-step
+        # range because the v5 API cannot run true instants. This API can:
+        # the [base] form of the same eval goes through /query below, and the
+        # transpiled coarse-step serving the encoding exercises is covered
+        # (and its known divergences ledgered) by promqlconformance's
+        # clickhousev2 leg.
+        if case["variant"] == "instant-coarse":
+            continue
+
+        base = bases[case["dataset"]]
+        start_ms = base + case["start_ms"]
+        end_ms = base + case["end_ms"]
+        step_s = max(1, case["step_ms"] // 1000)
+        case_id = f"{case['source']}[{case['variant']}]"
+
+        if case["instant"]:
+            path, params = "/prometheus/api/v1/query", {"query": case["expr"], "time": end_ms / 1000}
+        else:
+            path, params = (
+                "/prometheus/api/v1/query_range",
+                {
+                    "query": case["expr"],
+                    "start": start_ms / 1000,
+                    "end": end_ms / 1000,
+                    "step": step_s,
+                },
+            )
+        response = requests.get(
+            signoz.self.host_configs["8080"].get(path),
+            params=params,
+            timeout=QUERY_TIMEOUT,
+            headers={"authorization": f"Bearer {token}"},
+        )
+        if response.status_code != HTTPStatus.OK:
+            failures.append(f"{case_id}: HTTP {response.status_code} for {case['expr']!r}: {response.text[:200]}")
+            continue
+        body = response.json()
+        if body.get("status") != "success":
+            failures.append(f"{case_id}: status {body.get('status')!r} for {case['expr']!r}: {json.dumps(body)[:200]}")
+            continue
+
+        result_type, result = body["data"]["resultType"], body["data"]["result"]
+        actual: dict[tuple, dict[int, float]] = {}
+        if result_type == "matrix":
+            for series in result:
+                points = {round(float(ts) * 1000): SPECIALS[v] if v in SPECIALS else float(v) for ts, v in series.get("values") or []}
+                actual[tuple(sorted((series.get("metric") or {}).items()))] = points
+        elif result_type == "vector":
+            for series in result:
+                ts, v = series["value"]
+                actual[tuple(sorted((series.get("metric") or {}).items()))] = {round(float(ts) * 1000): SPECIALS[v] if v in SPECIALS else float(v)}
+        elif result_type == "scalar":
+            ts, v = result
+            actual[()] = {round(float(ts) * 1000): SPECIALS[v] if v in SPECIALS else float(v)}
+
+        expected: dict[tuple, dict[int, float]] = {}
+        for res in case["expected"]:
+            points = {base + off_ms: SPECIALS[v] if isinstance(v, str) else float(v) for off_ms, v in res["points"]}
+            expected[tuple(sorted(res["labels"].items()))] = points
+
+        if set(actual) != set(expected):
+            missing = set(expected) - set(actual)
+            extra = set(actual) - set(expected)
+            failures.append(f"{case_id}: series mismatch for {case['expr']!r} (missing={sorted(missing)[:3]} extra={sorted(extra)[:3]})")
+            continue
+
+        mismatch = None
+        for lset, exp_points in expected.items():
+            act_points = actual[lset]
+            if set(act_points) != set(exp_points):
+                mismatch = f"{case_id}: timestamp mismatch for {case['expr']!r} series {dict(lset)} (expected {len(exp_points)} points, got {len(act_points)})"
+                break
+            for ts, exp_v in exp_points.items():
+                act_v = act_points[ts]
+                if math.isnan(act_v) or math.isnan(exp_v):
+                    close = math.isnan(act_v) and math.isnan(exp_v)
+                elif math.isinf(act_v) or math.isinf(exp_v):
+                    close = act_v == exp_v
+                elif act_v == exp_v:
+                    close = True
+                else:
+                    # Expected values carry the v5 API's rounding (>=1: three
+                    # decimal places; <1: three significant digits); this API
+                    # returns raw floats. One rounding quantum covers the
+                    # largest possible rounding difference.
+                    scale = max(abs(act_v), abs(exp_v))
+                    if scale >= 1:
+                        quantum = max(1e-3, scale * 1e-9)
+                    else:
+                        quantum = 10 ** (math.floor(math.log10(scale)) - 2)
+                    close = abs(act_v - exp_v) <= quantum + 1e-12
+                if not close:
+                    mismatch = f"{case_id}: value mismatch for {case['expr']!r} series {dict(lset)} at {ts}: expected {exp_v}, got {act_v}"
+                    break
+            if mismatch:
+                break
+        if mismatch:
+            failures.append(mismatch)
+
+    for f_line in failures:
+        print("DIVERGED", f_line)
+    assert not failures, f"{len(failures)} corpus cases diverged:\n" + "\n".join(failures[:25])

tests/integration/tests/promapiconformance/conftest.py

@@ -0,0 +1,37 @@
+import pytest
+from testcontainers.core.container import Network
+
+from fixtures import types
+from fixtures.signoz import create_signoz
+
+
+@pytest.fixture(name="signoz", scope="package")
+def signoz_promapi_v2(
+    network: Network,
+    migrator: types.Operation,  # pylint: disable=unused-argument
+    zeus: types.TestContainerDocker,
+    gateway: types.TestContainerDocker,
+    sqlstore: types.TestContainerSQL,
+    clickhouse: types.TestContainerClickhouse,
+    request: pytest.FixtureRequest,
+    pytestconfig: pytest.Config,
+) -> types.SigNoz:
+    """
+    SigNoz with clickhousev2 as the serving prometheus provider. The corpus
+    replays against the /prometheus/api/v1 endpoints, so this package covers
+    the two paths nothing else serves: v2 as the provider (range queries
+    transpile when the shape allows), and the Prometheus HTTP API contract.
+    """
+    return create_signoz(
+        network=network,
+        zeus=zeus,
+        gateway=gateway,
+        sqlstore=sqlstore,
+        clickhouse=clickhouse,
+        request=request,
+        pytestconfig=pytestconfig,
+        cache_key="signoz-promapi-v2",
+        env_overrides={
+            "SIGNOZ_PROMETHEUS_PROVIDER": "clickhousev2",
+        },
+    )

tests/integration/tests/promqlconformance/01_upstream_corpus.py

@@ -2,21 +2,21 @@ import json
 import math
 import os
 from collections.abc import Callable
-from datetime import UTC, datetime, timedelta
 from http import HTTPStatus
 
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.metrics import Metrics
+from fixtures.promqltestcorpus import ingest_promqltest_corpus
 from fixtures.querier import get_all_series, make_query_request
 
 TESTDATA_DIR = os.path.join(os.path.dirname(__file__), "..", "..", "testdata")
-# Frozen corpus extracted from Prometheus' own promql/promqltest testdata by
-# scripts/promqltestcorpus (upstream load scripts + the vendored reference engine).
-# Unlike live-vs-live parity suites, the oracle is this committed file, so the suite
-# keeps working when the serving path itself is the thing being changed — the one
-# situation where comparing two live paths against each other is blind.
-CORPUS_FILE = os.path.join(TESTDATA_DIR, "promqltestcorpus", "corpus.json")
+# The corpus (see fixtures/promqltestcorpus.py) is frozen from Prometheus' own
+# promql/promqltest testdata by scripts/promqltestcorpus (upstream load scripts
+# + the vendored reference engine). Unlike live-vs-live parity suites, the
+# oracle is a committed file, so the suite keeps working when the serving path
+# itself is the thing being changed — the one situation where comparing two
+# live paths against each other is blind.
 
 # One ledger per leg, enforced exactly in both directions. The default leg's
 # ledger is empty and pinned there; the clickhousev2 ledger is the rollout
@@ -40,9 +40,6 @@ LEGS: list[tuple[str, dict | None]] = [
     ("clickhousev2", {"X-SigNoz-PromQL-Provider": "clickhousev2"}),
 ]
 
-# Datasets sit on disjoint time windows (2h gaps, far beyond the 5m lookback) so
-# one bulk ingest serves every case without cross-talk.
-ISOLATION_GAP_MS = 2 * 3600 * 1000
 SPECIALS = {"NaN": math.nan, "Inf": math.inf, "-Inf": -math.inf}
 
 
@@ -52,51 +49,7 @@ def test_upstream_promqltest_corpus(
     get_token: Callable[[str, str], str],
     insert_metrics: Callable[[list[Metrics]], None],
 ) -> None:
-    with open(CORPUS_FILE, encoding="utf-8") as f:
-        corpus = json.load(f)
-
-    cases_by_dataset: dict[int, list[dict]] = {}
-    for case in corpus["cases"]:
-        cases_by_dataset.setdefault(case["dataset"], []).append(case)
-
-    # Lay datasets end to end on the timeline, newest last, ending safely in
-    # the past; spans are per-dataset so the whole corpus stays within days.
-    spans = {}
-    for ds in corpus["datasets"]:
-        sample_max = max((s["samples"][-1][0] for s in ds["series"] if s["samples"]), default=0)
-        case_max = max((c["end_ms"] for c in cases_by_dataset.get(ds["id"], [])), default=0)
-        spans[ds["id"]] = max(sample_max, case_max) + corpus["meta"]["lookback_ms"]
-
-    # Hour-aligned dataset bases: registration rows are hour-bucketed, so
-    # behavior depends on where samples fall relative to hour boundaries —
-    # the exact known-divergences enforcement needs that identical every run.
-    hour_ms = 3_600_000
-    advances = {ds["id"]: -(-(spans[ds["id"]] + ISOLATION_GAP_MS) // hour_ms) * hour_ms for ds in corpus["datasets"]}
-    total = sum(advances.values())
-    now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
-    cursor = (int((now - timedelta(hours=1)).timestamp() * 1000) - total) // hour_ms * hour_ms
-
-    bases: dict[int, int] = {}
-    metrics: list[Metrics] = []
-    for ds in corpus["datasets"]:
-        bases[ds["id"]] = cursor
-        for series in ds["series"]:
-            labels = dict(series["labels"])
-            metric_name = labels.pop("__name__")
-            for off_ms, raw in series["samples"]:
-                stale = raw == "stale"
-                metrics.append(
-                    Metrics(
-                        metric_name=metric_name,
-                        labels=labels,
-                        timestamp=datetime.fromtimestamp((cursor + off_ms) / 1000, tz=UTC),
-                        value=0.0 if stale else (SPECIALS[raw] if isinstance(raw, str) else float(raw)),
-                        flags=1 if stale else 0,
-                    )
-                )
-        cursor += advances[ds["id"]]
-
-    insert_metrics(metrics)
+    corpus, bases = ingest_promqltest_corpus(insert_metrics)
     token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
 
     failures: dict[str, list[str]] = {leg: [] for leg, _ in LEGS}

tests/integration/tests/querierlogs/06_json_body.py

@@ -3,11 +3,13 @@ from collections.abc import Callable
 from datetime import UTC, datetime, timedelta
 from http import HTTPStatus
 
+import pytest
 import requests
 
 from fixtures import types
 from fixtures.auth import USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD
 from fixtures.logs import Logs
+from fixtures.querier import build_order_by, build_raw_query, get_rows, make_query_request
 
 
 def test_logs_json_body_simple_searches(
@@ -911,3 +913,61 @@ def test_logs_json_body_listing(
     assert len(results) == 1
     count = results[0]["data"][0][0]
     assert count == 4  # 4 logs have status="success"
+
+
+@pytest.mark.parametrize(
+    "expression,expected_services",
+    [
+        pytest.param("body.service IN ['auth', 'payment']", {"auth", "payment"}, id="in_scalar_path"),
+        pytest.param("body.status IN [200, 500]", {"auth", "payment"}, id="in_number_path"),
+        pytest.param("body.service NOT IN ['auth']", {"payment", "search"}, id="not_in_scalar_path"),
+        # An `[]` path is extracted as an array. Comparing that array to each scalar in the
+        # list is something ClickHouse rejects outright (code 130), so this shape used to
+        # fail the whole query; per-value extraction reads the first element instead.
+        pytest.param("body.user_names[*] IN ['alpha', 'gamma']", {"auth", "payment"}, id="in_array_path"),
+    ],
+)
+def test_logs_json_body_in_operator(
+    signoz: types.SigNoz,
+    create_user_admin: None,  # pylint: disable=unused-argument
+    get_token: Callable[[str, str], str],
+    insert_logs: Callable[[list[Logs]], None],
+    expression: str,
+    expected_services: set[str],
+) -> None:
+    """IN over a body JSON path fans out to one comparison per value."""
+    now = datetime.now(tz=UTC).replace(second=0, microsecond=0)
+    specs = [("auth", 200, ["alpha", "beta"]), ("payment", 500, ["gamma"]), ("search", 404, ["beta", "alpha"])]
+    insert_logs(
+        [
+            Logs(
+                timestamp=now - timedelta(seconds=i + 1),
+                resources={"service.name": "api"},
+                body=json.dumps({"service": service, "status": status, "user_names": user_names}),
+            )
+            for i, (service, status, user_names) in enumerate(specs)
+        ]
+    )
+
+    token = get_token(USER_ADMIN_EMAIL, USER_ADMIN_PASSWORD)
+    response = make_query_request(
+        signoz,
+        token,
+        start_ms=int((now - timedelta(minutes=5)).timestamp() * 1000),
+        end_ms=int(now.timestamp() * 1000),
+        request_type="raw",
+        queries=[
+            build_raw_query(
+                "A",
+                "logs",
+                filter_expression=expression,
+                order=[build_order_by("timestamp", "desc")],
+                limit=100,
+            )
+        ],
+    )
+
+    assert response.status_code == HTTPStatus.OK, response.text
+    assert response.json()["status"] == "success"
+    # flag off: the body comes back as the raw JSON string
+    assert {json.loads(row["data"]["body"])["service"] for row in get_rows(response)} == expected_services