Merge pull request 'Serve PuppetDB meta and metrics endpoints, sum node and resource counts' (#11) from benvin/meta-metrics-and-counts into main

Reviewed-on: #11

README.md

@@ -24,14 +24,20 @@ not PQL) is forwarded verbatim.
 
 | Path | Behaviour |
 |---|---|
-| `GET /pdb/query/v4/nodes` | Fan out to all backends, dedupe by `certname`, keep the record with the newer `report_timestamp`. |
+| `GET /pdb/query/v4/nodes` | Fan out to all backends, dedupe by `certname`, keep the record with the newer `report_timestamp`. An `extract`/`count` query is **summed** instead. |
 | `GET /pdb/query/v4/facts` | Fan out to all, and per `certname` keep **all** facts from the backend that owns that node (see merge semantics). |
+| `GET /pdb/query/v4/resources` | An `extract`/`count` query is fanned out and **summed**; any other query is an unmerged pass-through. |
 | `GET /pdb/query/v4/reports` | Fan out to all and serve the **union**, deduped by report `hash`, re-ordered and re-paged across backends. |
 | `GET /pdb/query/v4/events` | Fan out to all and serve the **union**, deduped by record identity, re-ordered and re-paged. |
 | `GET /pdb/query/v4/event-counts` | Fan out to all and **sum** each subject's counts into one row per subject. |
 | `GET /pdb/query/v4/aggregate-event-counts` | Fan out to all and **sum** the summary object's counts. |
 | `GET /pdb/query/v4/reports/<hash>/{events,logs,metrics}` | Ask every backend; serve the answer from whichever backend actually holds that report. `404` when none does. |
 | `GET /pdb/query/v4/*` (any other) | No merge rule, so backends are tried in configured order and the first success is streamed back verbatim; if all reject it, the first upstream error response is replayed. |
+| `GET /pdb/meta/v1/version` | Fan out to all and report the **lowest** version any backend runs. |
+| `GET /pdb/meta/v1/server-time` | Fan out to all and serve the first reachable backend's clock. |
+| `GET /metrics/v2/read/<mbean>` | Fan out to all and merge the Jolokia response; numeric attributes are **summed** by default (see merge semantics). |
+| `GET /metrics/v2/list` | Fan out to all and serve the **union** of the backends' MBean trees. |
+| `GET /metrics/v1/mbeans[/<mbean>]` | Same merge, applied to the legacy envelope-less body. |
 | `GET /healthz` | Per-backend reachability. `200 {"status":"ok"}` if all reachable, `200 degraded` if some fail, `503 down` if all fail. |
 
 Fan-out is concurrent. If one backend errors or times out, `pdbmux` serves the
@@ -62,12 +68,20 @@ unknown fields survive untouched.
   reporting to more than one backend stores identical records in each).
 - **Aggregates** — `extract`/`group_by` rows are counts, not records, so each
   backend returns a partial answer that has to be **added**, not deduped. This
-  covers `/event-counts`, `/aggregate-event-counts`, and a `/reports` query whose
-  `extract` carries a `["function", ...]` column.
-  - The grouping key is the row's non-aggregate fields: for `/reports` they come
-    from the query — the plain `extract` fields plus any `group_by` clause — and
-    for the event-count endpoints from the row itself (`subject_type`/`subject`,
-    or `summarize_by`), whose remaining fields are all counts.
+  covers `/event-counts`, `/aggregate-event-counts`, and any `/reports`,
+  `/nodes` or `/resources` query whose `extract` carries a `["function", ...]`
+  column.
+  - The grouping key is the row's non-aggregate fields: for `/reports`,
+    `/nodes` and `/resources` they come from the query — the plain `extract`
+    fields plus any `group_by` clause — and for the event-count endpoints from
+    the row itself (`subject_type`/`subject`, or `summarize_by`), whose
+    remaining fields are all counts.
+  - On `/nodes` this takes precedence over the `certname` merge: a count row has
+    no `certname`, so deduping would collapse every backend's count into one
+    backend's number. A `/nodes` query with no `function` column — including a
+    plain `extract` projection — still merges by `certname`.
+  - `/resources` has no cross-backend record identity to dedupe on, so only its
+    aggregate queries merge; everything else stays an unmerged pass-through.
   - Rows sharing a key collapse into one with their numeric columns summed. A key
     only one backend reported is passed through byte-for-byte. An aggregate column
     that is absent or non-numeric in a row is skipped, never zeroed, so the
@@ -77,6 +91,39 @@ unknown fields survive untouched.
   - `include_total=true` on a summed endpoint reports the **merged** row count,
     not the sum of the backends' `X-Records`, since shared keys collapse.
 
+### Metadata and metrics
+
+- **`/pdb/meta/v1/version`** — when the backends agree, that version is served.
+  When they differ, `pdbmux` reports the **lowest**: a client reads this as the
+  feature level it may rely on, and the estate can only be relied on for what its
+  oldest PuppetDB implements. Versions compare segment by segment, numerically
+  where both segments are numbers (`7.9.0` < `7.12.0`), lexically otherwise.
+  A backend whose body is unparseable is skipped rather than treated as lowest.
+- **`/pdb/meta/v1/server-time`** — the clock of whichever PuppetDB answered is
+  not estate state and has no meaningful merge, so the first **reachable**
+  backend in configured order supplies it, the same tie-break used elsewhere.
+- **`/metrics/...`** — the Jolokia envelope's `value` is merged and the rest of
+  the envelope comes from the first backend (with the newest `timestamp`).
+  Values merge recursively:
+  - Objects merge over the **union** of their keys, so an MBean attribute only
+    one backend exposes still survives.
+  - Numbers combine by the attribute's own name. The default is a **sum** —
+    almost everything here is a population count (`num-nodes`, `num-resources`,
+    queue depth, command totals) whose estate-wide value is the total, and rates
+    are additive throughput. The exceptions describe a distribution or a bound,
+    where adding two servers' numbers yields a figure that was never true of
+    either: `Min` takes the minimum; `Max`, `Uptime` and `StartTime` take the
+    maximum; `Mean`, `Median`, `StdDev` and `*Percentile` take the unweighted
+    arithmetic mean (`pdbmux` has no per-backend sample counts to weight by).
+    Matching is case-insensitive.
+  - Strings, booleans, arrays, nulls and mixed kinds keep the first backend's
+    value — there is no sound way to add them.
+  - Jolokia signals a bad MBean as a non-2xx `status` **inside** an HTTP 200.
+    Such a backend is skipped; if every backend does so, the first one's error
+    envelope is replayed verbatim so the client sees the real reason.
+  - MBean names arrive percent-encoded over Jolokia's own `!`-escaping; the raw
+    path is forwarded so neither layer is lost.
+
 ### Paging and ordering on the merged endpoints
 
 Each backend applies `order_by`/`limit`/`offset` to its own slice only, so

meta.go

@@ -0,0 +1,195 @@
+package main
+
+import (
+	"context"
+	"encoding/json"
+	"io"
+	"net/http"
+	"strconv"
+	"strings"
+	"sync"
+)
+
+const (
+	metaVersionPath    = "/pdb/meta/v1/version"
+	metaServerTimePath = "/pdb/meta/v1/server-time"
+)
+
+// rawResult is one backend's verbatim response, for endpoints whose payload is
+// not a PuppetDB record array.
+type rawResult struct {
+	name        string
+	status      int
+	contentType string
+	body        []byte
+	err         error
+}
+
+// ok reports whether the backend answered 2xx.
+func (r rawResult) ok() bool {
+	return r.err == nil && r.status >= 200 && r.status < 300
+}
+
+// fanOutRaw asks every backend for path concurrently and returns one result per
+// backend, in configured order, without interpreting the bodies.
+func (s *Server) fanOutRaw(ctx context.Context, path, rawQuery string) []rawResult {
+	results := make([]rawResult, len(s.cfg.Backends))
+	var wg sync.WaitGroup
+	for i, b := range s.cfg.Backends {
+		wg.Add(1)
+		go func(i int, b Backend) {
+			defer wg.Done()
+			results[i] = s.rawBackend(ctx, b, path, rawQuery)
+		}(i, b)
+	}
+	wg.Wait()
+	return results
+}
+
+func (s *Server) rawBackend(ctx context.Context, b Backend, path, rawQuery string) rawResult {
+	target := strings.TrimRight(b.URL, "/") + path
+	if rawQuery != "" {
+		target += "?" + rawQuery
+	}
+	req, err := http.NewRequestWithContext(ctx, http.MethodGet, target, nil)
+	if err != nil {
+		return rawResult{name: b.Name, err: err}
+	}
+	resp, err := s.client.Do(req)
+	if err != nil {
+		return rawResult{name: b.Name, err: err}
+	}
+	defer func() { _ = resp.Body.Close() }()
+	body, err := io.ReadAll(resp.Body)
+	if err != nil {
+		return rawResult{name: b.Name, err: err}
+	}
+	return rawResult{
+		name:        b.Name,
+		status:      resp.StatusCode,
+		contentType: resp.Header.Get("Content-Type"),
+		body:        body,
+	}
+}
+
+// aliveRaw drops backends that errored or answered non-2xx, writing a 502 and
+// returning ok=false only when none is left.
+func (s *Server) aliveRaw(w http.ResponseWriter, results []rawResult, path string) ([]rawResult, bool) {
+	var alive []rawResult
+	for _, res := range results {
+		if !res.ok() {
+			s.log.Printf("warning: backend %q failed for %s: %s", res.name, path, res.reason())
+			continue
+		}
+		alive = append(alive, res)
+	}
+	if len(alive) == 0 {
+		http.Error(w, "all backends failed", http.StatusBadGateway)
+		return nil, false
+	}
+	return alive, true
+}
+
+func (r rawResult) reason() string {
+	if r.err != nil {
+		return r.err.Error()
+	}
+	return "HTTP " + strconv.Itoa(r.status) + ": " + strings.TrimSpace(string(r.body))
+}
+
+// handleMetaVersion serves /pdb/meta/v1/version. Clients (pypuppetdb, and so
+// Puppetboard's startup check) treat the answer as the feature level they may
+// rely on, so the merged answer is the *lowest* version any backend reports:
+// the estate can only be counted on for what its oldest member implements.
+func (s *Server) handleMetaVersion(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		http.Error(w, "only GET is supported", http.StatusMethodNotAllowed)
+		return
+	}
+	alive, ok := s.aliveRaw(w, s.fanOutRaw(r.Context(), metaVersionPath, r.URL.RawQuery), metaVersionPath)
+	if !ok {
+		return
+	}
+
+	lowest := alive[0]
+	lowestVer, hasVer := metaField(lowest.body, "version")
+	for _, res := range alive[1:] {
+		v, ok := metaField(res.body, "version")
+		if !ok {
+			continue
+		}
+		if !hasVer || compareVersions(v, lowestVer) < 0 {
+			lowest, lowestVer, hasVer = res, v, true
+		}
+	}
+	writeRaw(w, lowest)
+}
+
+// handleMetaServerTime serves /pdb/meta/v1/server-time. The clock of whichever
+// PuppetDB answered is not estate state and does not merge, so the first
+// reachable backend in configured order supplies it — the same tie-break rule
+// used everywhere else.
+func (s *Server) handleMetaServerTime(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		http.Error(w, "only GET is supported", http.StatusMethodNotAllowed)
+		return
+	}
+	alive, ok := s.aliveRaw(w, s.fanOutRaw(r.Context(), metaServerTimePath, r.URL.RawQuery), metaServerTimePath)
+	if !ok {
+		return
+	}
+	writeRaw(w, alive[0])
+}
+
+// metaField pulls a string field out of a `{"version": "..."}`-shaped body.
+func metaField(body []byte, field string) (string, bool) {
+	var obj map[string]json.RawMessage
+	if json.Unmarshal(body, &obj) != nil {
+		return "", false
+	}
+	var s string
+	if json.Unmarshal(obj[field], &s) != nil || s == "" {
+		return "", false
+	}
+	return s, true
+}
+
+// compareVersions orders dotted version strings segment by segment, comparing
+// numerically where both segments are numbers and lexically otherwise, so
+// "7.12.1" sorts below "8.4.0" and below "7.12.2". A prefix is lower than a
+// longer string sharing it ("7.12" < "7.12.1"), and a pre-release suffix is
+// compared as text within its segment ("8.0.0" < "8.0.0-SNAPSHOT").
+func compareVersions(a, b string) int {
+	as, bs := strings.Split(a, "."), strings.Split(b, ".")
+	for i := 0; i < len(as) && i < len(bs); i++ {
+		an, aok := strconv.Atoi(as[i])
+		bn, bok := strconv.Atoi(bs[i])
+		if aok == nil && bok == nil {
+			if an != bn {
+				return sign(an - bn)
+			}
+			continue
+		}
+		if c := strings.Compare(as[i], bs[i]); c != 0 {
+			return c
+		}
+	}
+	return sign(len(as) - len(bs))
+}
+
+func sign(n int) int {
+	switch {
+	case n < 0:
+		return -1
+	case n > 0:
+		return 1
+	default:
+		return 0
+	}
+}
+
+func writeRaw(w http.ResponseWriter, res rawResult) {
+	setContentType(w, res.contentType)
+	w.WriteHeader(res.status)
+	_, _ = w.Write(res.body)
+}

meta_test.go

@@ -0,0 +1,170 @@
+package main
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"testing"
+)
+
+func metaGet(t *testing.T, h http.Handler, path string) *httptest.ResponseRecorder {
+	t.Helper()
+	rec := httptest.NewRecorder()
+	h.ServeHTTP(rec, httptest.NewRequest(http.MethodGet, path, nil))
+	return rec
+}
+
+func metaString(t *testing.T, body []byte, field string) string {
+	t.Helper()
+	var obj map[string]string
+	if err := json.Unmarshal(body, &obj); err != nil {
+		t.Fatalf("unmarshal %s: %v", body, err)
+	}
+	return obj[field]
+}
+
+func TestMetaVersion_BackendsAgree(t *testing.T) {
+	// Puppetboard's check_db_version() calls this at import and exits 2 on any
+	// non-200, so a 404 here is the difference between a running dashboard and
+	// CrashLoopBackOff.
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[metaVersionPath] = `{"version":"7.12.1"}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaVersionPath] = `{"version":"7.12.1"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), metaVersionPath)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d: %s", rec.Code, rec.Body.String())
+	}
+	if got := metaString(t, rec.Body.Bytes(), "version"); got != "7.12.1" {
+		t.Errorf("version = %q, want 7.12.1", got)
+	}
+}
+
+func TestMetaVersion_DisagreementReportsLowest(t *testing.T) {
+	// The estate can only be relied on for what its oldest PuppetDB implements.
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[metaVersionPath] = `{"version":"8.4.0"}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaVersionPath] = `{"version":"7.12.1"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if got := metaString(t, metaGet(t, srv.Handler(), metaVersionPath).Body.Bytes(), "version"); got != "7.12.1" {
+		t.Errorf("version = %q, want the lower 7.12.1", got)
+	}
+}
+
+func TestMetaVersion_LowestIsIndependentOfBackendOrder(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[metaVersionPath] = `{"version":"7.12.1"}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaVersionPath] = `{"version":"8.4.0"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if got := metaString(t, metaGet(t, srv.Handler(), metaVersionPath).Body.Bytes(), "version"); got != "7.12.1" {
+		t.Errorf("version = %q, want the lower 7.12.1", got)
+	}
+}
+
+func TestMetaVersion_OneBackendDown(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.fail = true
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaVersionPath] = `{"version":"8.4.0"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), metaVersionPath)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("expected 200 serving the survivor, got %d", rec.Code)
+	}
+	if got := metaString(t, rec.Body.Bytes(), "version"); got != "8.4.0" {
+		t.Errorf("version = %q, want 8.4.0", got)
+	}
+}
+
+func TestMetaVersion_AllBackendsDown(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.fail = true
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.fail = true
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if rec := metaGet(t, srv.Handler(), metaVersionPath); rec.Code != http.StatusBadGateway {
+		t.Errorf("status %d, want 502", rec.Code)
+	}
+}
+
+func TestMetaServerTime_FirstReachableBackend(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[metaServerTimePath] = `{"server_time":"2026-08-29T01:00:00.000Z"}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaServerTimePath] = `{"server_time":"2026-08-29T02:00:00.000Z"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	got := metaString(t, metaGet(t, srv.Handler(), metaServerTimePath).Body.Bytes(), "server_time")
+	if got != "2026-08-29T01:00:00.000Z" {
+		t.Errorf("server_time = %q, want the first backend's", got)
+	}
+}
+
+func TestMetaServerTime_SkipsDeadBackend(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.fail = true
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaServerTimePath] = `{"server_time":"2026-08-29T02:00:00.000Z"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), metaServerTimePath)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("expected 200 serving the survivor, got %d", rec.Code)
+	}
+	if got := metaString(t, rec.Body.Bytes(), "server_time"); got != "2026-08-29T02:00:00.000Z" {
+		t.Errorf("server_time = %q, want the survivor's", got)
+	}
+}
+
+func TestMetaVersion_RejectsNonGET(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	b := newFakeBackend(t, `[]`, `[]`)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(rec, httptest.NewRequest(http.MethodPost, metaVersionPath, nil))
+	if rec.Code != http.StatusMethodNotAllowed {
+		t.Errorf("status %d, want 405", rec.Code)
+	}
+}
+
+func TestCompareVersions(t *testing.T) {
+	cases := []struct {
+		a, b string
+		want int
+	}{
+		{"7.12.1", "7.12.1", 0},
+		{"7.12.1", "8.4.0", -1},
+		{"8.4.0", "7.12.1", 1},
+		{"7.9.0", "7.12.0", -1}, // numeric, not lexical: 9 < 12
+		{"7.12", "7.12.1", -1},
+		{"8.0.0", "8.0.0-SNAPSHOT", -1},
+		{"8.0.0-SNAPSHOT", "8.0.0", 1},
+	}
+	for _, c := range cases {
+		if got := compareVersions(c.a, c.b); got != c.want {
+			t.Errorf("compareVersions(%q, %q) = %d, want %d", c.a, c.b, got, c.want)
+		}
+	}
+}
+
+func TestMetaField_MalformedBodyIgnored(t *testing.T) {
+	// A backend serving junk must not become the "lowest" version.
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[metaVersionPath] = `not json`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[metaVersionPath] = `{"version":"8.4.0"}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if got := metaString(t, metaGet(t, srv.Handler(), metaVersionPath).Body.Bytes(), "version"); got != "8.4.0" {
+		t.Errorf("version = %q, want 8.4.0 from the only parseable backend", got)
+	}
+}

metrics.go

@@ -0,0 +1,272 @@
+package main
+
+import (
+	"bytes"
+	"encoding/json"
+	"net/http"
+	"strconv"
+	"strings"
+)
+
+// metricsPrefix covers PuppetDB's Jolokia surface, which sits at the server root
+// rather than under /pdb: pypuppetdb's metric() reads /metrics/v2/read/<mbean>,
+// lists via /metrics/v2/list, and falls back to /metrics/v1/mbeans/<mbean>.
+const metricsPrefix = "/metrics/"
+
+type mergeRule int
+
+const (
+	ruleSum mergeRule = iota
+	ruleMin
+	ruleMax
+	ruleMean
+)
+
+// mergeRuleFor picks how one numeric MBean attribute combines across backends.
+// The default is a sum: the metrics Puppetboard renders are population counts
+// (num-nodes, num-resources, queue depth, command totals) whose estate-wide
+// value is the total. The exceptions are attributes describing a distribution or
+// a bound rather than a quantity, where adding two servers' numbers yields a
+// figure that was never true of either.
+func mergeRuleFor(attr string) mergeRule {
+	a := strings.ToLower(attr)
+	switch a {
+	case "min":
+		return ruleMin
+	case "max", "uptime", "starttime":
+		return ruleMax
+	case "mean", "median", "stddev":
+		return ruleMean
+	}
+	if strings.HasSuffix(a, "percentile") {
+		return ruleMean
+	}
+	return ruleSum
+}
+
+func (s *Server) handleMetrics(w http.ResponseWriter, r *http.Request) {
+	if r.Method != http.MethodGet {
+		http.Error(w, "only GET is supported", http.StatusMethodNotAllowed)
+		return
+	}
+	// MBean names carry Jolokia's !-escapes under percent-encoding; the raw path
+	// is forwarded so neither layer is lost.
+	path := r.URL.EscapedPath()
+	alive, ok := s.aliveRaw(w, s.fanOutRaw(r.Context(), path, r.URL.RawQuery), path)
+	if !ok {
+		return
+	}
+
+	body, ok := mergeMetrics(alive, metricAttribute(r.URL.Path))
+	if !ok {
+		// Every backend answered 2xx but none carried a mergeable payload — a
+		// Jolokia error envelope, or a body that is not a JSON object. Replaying
+		// the first keeps the upstream error text the client expects.
+		writeRaw(w, alive[0])
+		return
+	}
+	w.Header().Set("Content-Type", "application/json")
+	_, _ = w.Write(body)
+}
+
+// metricAttribute names the single attribute a read asked for, when the URL
+// carries one (/metrics/v2/read/<mbean>/<attribute>), so a scalar response body
+// still gets the right numeric rule. Empty means the response is an object whose
+// own keys name its attributes.
+func metricAttribute(path string) string {
+	rest, ok := strings.CutPrefix(path, metricsPrefix)
+	if !ok {
+		return ""
+	}
+	parts := strings.Split(rest, "/") // v2/read/<mbean>[/<attribute>]
+	if len(parts) < 4 {
+		return ""
+	}
+	return parts[len(parts)-1]
+}
+
+// mergeMetrics folds the backends' Jolokia responses into one. A response is
+// either a Jolokia envelope ({"request":…,"value":…,"status":200}), where only
+// "value" merges and the rest comes from the first backend, or a bare attribute
+// object (metrics/v1), which merges whole. ok=false means nothing was mergeable.
+func mergeMetrics(alive []rawResult, attr string) ([]byte, bool) {
+	var objs []map[string]json.RawMessage
+	for _, res := range alive {
+		var obj map[string]json.RawMessage
+		if decodeJSON(res.body, &obj) != nil || obj == nil {
+			continue
+		}
+		// Jolokia reports a per-request failure inside an HTTP 200.
+		if n, ok := numberOf(obj["status"]); ok && (n < 200 || n >= 300) {
+			continue
+		}
+		objs = append(objs, obj)
+	}
+	if len(objs) == 0 {
+		return nil, false
+	}
+
+	_, hasValue := objs[0]["value"]
+	_, hasStatus := objs[0]["status"]
+	if !hasValue || !hasStatus {
+		vals := make([]any, 0, len(objs))
+		for _, obj := range objs {
+			vals = append(vals, decodedObject(obj))
+		}
+		return marshal(mergeMetricValue(vals, attr))
+	}
+
+	vals := make([]any, 0, len(objs))
+	for _, obj := range objs {
+		var v any
+		if decodeJSON(obj["value"], &v) == nil {
+			vals = append(vals, v)
+		}
+	}
+	if len(vals) == 0 {
+		return nil, false
+	}
+	merged, ok := marshal(mergeMetricValue(vals, attr))
+	if !ok {
+		return nil, false
+	}
+
+	out := make(map[string]json.RawMessage, len(objs[0]))
+	for k, v := range objs[0] {
+		out[k] = v
+	}
+	out["value"] = merged
+	// The envelope timestamp says when the answer was produced; the newest one
+	// describes the merged answer.
+	if ts, ok := maxField(objs, "timestamp"); ok {
+		out["timestamp"] = ts
+	}
+	return marshal(out)
+}
+
+// maxField returns the largest numeric value of a field across the responses.
+func maxField(objs []map[string]json.RawMessage, field string) (json.RawMessage, bool) {
+	var best json.RawMessage
+	var bestN float64
+	for _, obj := range objs {
+		n, ok := numberOf(obj[field])
+		if !ok {
+			continue
+		}
+		if best == nil || n > bestN {
+			best, bestN = obj[field], n
+		}
+	}
+	return best, best != nil
+}
+
+// mergeMetricValue folds one attribute's value from every backend into one.
+// Objects merge key by key over the union of keys, so a backend missing an
+// attribute still contributes the rest. Numbers combine by the attribute's rule.
+// Anything else — strings, booleans, arrays, nulls, or a mix of kinds — keeps
+// the first backend's value, there being no sound way to add them.
+func mergeMetricValue(vals []any, attr string) any {
+	if len(vals) == 0 {
+		return nil
+	}
+	if len(vals) == 1 {
+		return vals[0]
+	}
+
+	objs := make([]map[string]any, 0, len(vals))
+	for _, v := range vals {
+		if m, ok := v.(map[string]any); ok {
+			objs = append(objs, m)
+		}
+	}
+	if len(objs) == len(vals) {
+		out := map[string]any{}
+		for _, m := range objs {
+			for k := range m {
+				if _, done := out[k]; done {
+					continue
+				}
+				sub := make([]any, 0, len(objs))
+				for _, o := range objs {
+					if v, ok := o[k]; ok {
+						sub = append(sub, v)
+					}
+				}
+				out[k] = mergeMetricValue(sub, k)
+			}
+		}
+		return out
+	}
+
+	nums := make([]float64, 0, len(vals))
+	for _, v := range vals {
+		n, ok := v.(json.Number)
+		if !ok {
+			break
+		}
+		f, err := n.Float64()
+		if err != nil {
+			break
+		}
+		nums = append(nums, f)
+	}
+	if len(nums) != len(vals) {
+		return vals[0]
+	}
+	return combineNumbers(nums, attr)
+}
+
+func combineNumbers(nums []float64, attr string) json.RawMessage {
+	acc := nums[0]
+	switch mergeRuleFor(attr) {
+	case ruleMin:
+		for _, n := range nums[1:] {
+			if n < acc {
+				acc = n
+			}
+		}
+	case ruleMax:
+		for _, n := range nums[1:] {
+			if n > acc {
+				acc = n
+			}
+		}
+	case ruleMean:
+		for _, n := range nums[1:] {
+			acc += n
+		}
+		acc /= float64(len(nums))
+	default:
+		for _, n := range nums[1:] {
+			acc += n
+		}
+	}
+	return json.RawMessage(strconv.FormatFloat(acc, 'f', -1, 64))
+}
+
+// decodedObject re-reads an object's fields as generic values so the whole thing
+// can go through mergeMetricValue.
+func decodedObject(obj map[string]json.RawMessage) any {
+	out := make(map[string]any, len(obj))
+	for k, raw := range obj {
+		var v any
+		if decodeJSON(raw, &v) == nil {
+			out[k] = v
+		}
+	}
+	return out
+}
+
+// decodeJSON keeps integers exact by decoding numbers as json.Number.
+func decodeJSON(data []byte, v any) error {
+	dec := json.NewDecoder(bytes.NewReader(data))
+	dec.UseNumber()
+	return dec.Decode(v)
+}
+
+// marshal reports ok=false rather than an error: an unmarshalable merge result
+// has only one recovery, replaying a backend's body verbatim.
+func marshal(v any) ([]byte, bool) {
+	b, err := json.Marshal(v)
+	return b, err == nil
+}

metrics_test.go

@@ -0,0 +1,285 @@
+package main
+
+import (
+	"encoding/json"
+	"net/http"
+	"net/http/httptest"
+	"reflect"
+	"strconv"
+	"testing"
+)
+
+const (
+	numNodesMBean = "puppetlabs.puppetdb.population:name=num-nodes"
+	numNodesPath  = metricsPrefix + "v2/read/" + numNodesMBean
+	// What pypuppetdb actually sends: quote() percent-encodes ':' and '='.
+	numNodesEscaped = metricsPrefix + "v2/read/puppetlabs.puppetdb.population%3Aname%3Dnum-nodes"
+)
+
+// jolokiaRead wraps an MBean value in the envelope PuppetDB's Jolokia returns.
+func jolokiaRead(mbean, value string, timestamp int) string {
+	return `{"request":{"mbean":"` + mbean + `","type":"read"},` +
+		`"value":` + value + `,"timestamp":` + strconv.Itoa(timestamp) + `,"status":200}`
+}
+
+func metricValue(t *testing.T, body []byte) map[string]any {
+	t.Helper()
+	var env map[string]json.RawMessage
+	if err := json.Unmarshal(body, &env); err != nil {
+		t.Fatalf("unmarshal envelope %s: %v", body, err)
+	}
+	var val map[string]any
+	if err := json.Unmarshal(env["value"], &val); err != nil {
+		t.Fatalf("unmarshal value %s: %v", env["value"], err)
+	}
+	return val
+}
+
+func TestMetrics_ReadSumsPopulationCounts(t *testing.T) {
+	// Puppetboard's landing page and radiator read num-nodes when
+	// DEFAULT_ENVIRONMENT is '*'; each backend only knows its own nodes.
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":90}`, 1000)
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":53}`, 2000)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), numNodesEscaped)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d: %s", rec.Code, rec.Body.String())
+	}
+	if got := metricValue(t, rec.Body.Bytes())["Value"]; got != float64(143) {
+		t.Errorf("Value = %v, want 143", got)
+	}
+}
+
+func TestMetrics_EscapedMBeanNameSurvives(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":1}`, 1)
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":1}`, 1)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	metaGet(t, srv.Handler(), numNodesEscaped)
+	if !a.sawRawPath(numNodesEscaped) {
+		t.Errorf("backend saw %v, want the percent-encoded path %q", a.rawPaths, numNodesEscaped)
+	}
+}
+
+func TestMetrics_EnvelopeKeepsNewestTimestamp(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":1}`, 1000)
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":1}`, 2000)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	var env map[string]any
+	if err := json.Unmarshal(metaGet(t, srv.Handler(), numNodesEscaped).Body.Bytes(), &env); err != nil {
+		t.Fatal(err)
+	}
+	if env["timestamp"] != float64(2000) {
+		t.Errorf("timestamp = %v, want 2000", env["timestamp"])
+	}
+	if env["status"] != float64(200) {
+		t.Errorf("status = %v, want 200", env["status"])
+	}
+}
+
+func TestMetrics_PerAttributeRules(t *testing.T) {
+	const mbean = "puppetlabs.puppetdb.mq:name=global.processing-time"
+	path := metricsPrefix + "v2/read/" + mbean
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[path] = jolokiaRead(mbean,
+		`{"Count":10,"Min":2,"Max":9,"Mean":4,"StdDev":1,"50thPercentile":3,"MeanRate":1.5}`, 1)
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[path] = jolokiaRead(mbean,
+		`{"Count":6,"Min":1,"Max":20,"Mean":6,"StdDev":3,"50thPercentile":5,"MeanRate":0.5}`, 1)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	got := metricValue(t, metaGet(t, srv.Handler(), path).Body.Bytes())
+	want := map[string]any{
+		"Count":          float64(16), // counts add
+		"Min":            float64(1),  // a bound stays a bound
+		"Max":            float64(20),
+		"Mean":           float64(5), // distribution stats average
+		"StdDev":         float64(2),
+		"50thPercentile": float64(4),
+		"MeanRate":       float64(2), // throughput adds
+	}
+	if !reflect.DeepEqual(got, want) {
+		t.Errorf("merged value = %v, want %v", got, want)
+	}
+}
+
+func TestMetrics_ScalarReadUsesURLAttributeName(t *testing.T) {
+	// /metrics/v2/read/<mbean>/<attribute> answers with a bare number, so the
+	// rule has to come from the URL rather than an object key.
+	const mbean = "puppetlabs.puppetdb.population:name=num-resources"
+	sumPath := metricsPrefix + "v2/read/" + mbean + "/Value"
+	maxPath := metricsPrefix + "v2/read/" + mbean + "/Max"
+
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[sumPath] = jolokiaRead(mbean, `1000`, 1)
+	a.bodies[maxPath] = jolokiaRead(mbean, `1000`, 1)
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[sumPath] = jolokiaRead(mbean, `234`, 1)
+	b.bodies[maxPath] = jolokiaRead(mbean, `234`, 1)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	for _, c := range []struct {
+		path string
+		want float64
+	}{{sumPath, 1234}, {maxPath, 1000}} {
+		var env map[string]any
+		if err := json.Unmarshal(metaGet(t, srv.Handler(), c.path).Body.Bytes(), &env); err != nil {
+			t.Fatal(err)
+		}
+		if env["value"] != c.want {
+			t.Errorf("%s value = %v, want %v", c.path, env["value"], c.want)
+		}
+	}
+}
+
+func TestMetrics_ListUnionsDomains(t *testing.T) {
+	// Puppetboard's /metrics page calls metric() with no name, which is a
+	// Jolokia list; a backend-local MBean must not vanish from the browse tree.
+	const path = metricsPrefix + "v2/list"
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[path] = `{"value":{"java.lang":{"type=Memory":{"attr":{"HeapMemoryUsage":{"rw":false}}}}},"status":200,"timestamp":1}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[path] = `{"value":{"puppetlabs.puppetdb.population":{"name=num-nodes":{"attr":{"Value":{"rw":false}}}}},"status":200,"timestamp":1}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	got := metricValue(t, metaGet(t, srv.Handler(), path).Body.Bytes())
+	if _, ok := got["java.lang"]; !ok {
+		t.Errorf("java.lang missing from merged list: %v", got)
+	}
+	if _, ok := got["puppetlabs.puppetdb.population"]; !ok {
+		t.Errorf("puppetlabs.puppetdb.population missing from merged list: %v", got)
+	}
+}
+
+func TestMetrics_V1BareObjectMerged(t *testing.T) {
+	// metrics/v1/mbeans has no Jolokia envelope; the whole body is the value.
+	const path = metricsPrefix + "v1/mbeans/" + numNodesMBean
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[path] = `{"Value":90}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[path] = `{"Value":53}`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	var got map[string]any
+	if err := json.Unmarshal(metaGet(t, srv.Handler(), path).Body.Bytes(), &got); err != nil {
+		t.Fatal(err)
+	}
+	if got["Value"] != float64(143) {
+		t.Errorf("Value = %v, want 143", got["Value"])
+	}
+}
+
+func TestMetrics_MissingMBeanKeepsUpstreamError(t *testing.T) {
+	// Jolokia reports a bad MBean as a 200 with an error envelope, which
+	// pypuppetdb turns into DoesNotComputeError; the client must still see it.
+	const path = metricsPrefix + "v2/read/nope:name=nothing"
+	errEnv := `{"request":{"mbean":"nope:name=nothing"},"error_type":"javax.management.InstanceNotFoundException","error":"nope:name=nothing is not registered","status":404}`
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[path] = errEnv
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[path] = errEnv
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), path)
+	var env map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &env); err != nil {
+		t.Fatal(err)
+	}
+	if env["error"] == nil {
+		t.Errorf("expected the upstream Jolokia error to be replayed, got %s", rec.Body.String())
+	}
+}
+
+func TestMetrics_ErroringBackendIgnoredWhenAnotherAnswers(t *testing.T) {
+	const path = metricsPrefix + "v2/read/" + numNodesMBean
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[path] = `{"request":{},"error":"boom","status":500}`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[path] = jolokiaRead(numNodesMBean, `{"Value":53}`, 1)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if got := metricValue(t, metaGet(t, srv.Handler(), path).Body.Bytes())["Value"]; got != float64(53) {
+		t.Errorf("Value = %v, want 53 from the backend that answered", got)
+	}
+}
+
+func TestMetrics_OneBackendDown(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.fail = true
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[numNodesPath] = jolokiaRead(numNodesMBean, `{"Value":53}`, 1)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := metaGet(t, srv.Handler(), numNodesEscaped)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("expected 200 serving the survivor, got %d", rec.Code)
+	}
+	if got := metricValue(t, rec.Body.Bytes())["Value"]; got != float64(53) {
+		t.Errorf("Value = %v, want 53", got)
+	}
+}
+
+func TestMetrics_AllBackendsDown(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.fail = true
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.fail = true
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	if rec := metaGet(t, srv.Handler(), numNodesEscaped); rec.Code != http.StatusBadGateway {
+		t.Errorf("status %d, want 502", rec.Code)
+	}
+}
+
+func TestMetrics_RejectsNonGET(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	b := newFakeBackend(t, `[]`, `[]`)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := httptest.NewRecorder()
+	srv.Handler().ServeHTTP(rec, httptest.NewRequest(http.MethodPost, numNodesEscaped, nil))
+	if rec.Code != http.StatusMethodNotAllowed {
+		t.Errorf("status %d, want 405", rec.Code)
+	}
+}
+
+func TestMergeMetricValue_NonNumericKeepsFirst(t *testing.T) {
+	a := map[string]any{"Name": "pdb-a", "Enabled": true}
+	b := map[string]any{"Name": "pdb-b", "Enabled": false}
+	got, ok := mergeMetricValue([]any{a, b}, "").(map[string]any)
+	if !ok {
+		t.Fatalf("expected an object, got %T", got)
+	}
+	if got["Name"] != "pdb-a" || got["Enabled"] != true {
+		t.Errorf("merged = %v, want the first backend's strings and booleans", got)
+	}
+}
+
+func TestMergeRuleFor(t *testing.T) {
+	cases := map[string]mergeRule{
+		"Count":          ruleSum,
+		"Value":          ruleSum,
+		"MeanRate":       ruleSum,
+		"queue-depth":    ruleSum,
+		"min":            ruleMin,
+		"Max":            ruleMax,
+		"Uptime":         ruleMax,
+		"StartTime":      ruleMax,
+		"Mean":           ruleMean,
+		"StdDev":         ruleMean,
+		"99thPercentile": ruleMean,
+	}
+	for attr, want := range cases {
+		if got := mergeRuleFor(attr); got != want {
+			t.Errorf("mergeRuleFor(%q) = %v, want %v", attr, got, want)
+		}
+	}
+}

server.go

@@ -17,6 +17,7 @@ import (
 const (
 	factsPath                = "/pdb/query/v4/facts"
 	nodesPath                = "/pdb/query/v4/nodes"
+	resourcesPath            = "/pdb/query/v4/resources"
 	reportsPath              = "/pdb/query/v4/reports"
 	eventsPath               = "/pdb/query/v4/events"
 	eventCountsPath          = "/pdb/query/v4/event-counts"
@@ -57,6 +58,9 @@ func (s *Server) Handler() http.Handler {
 	mux := http.NewServeMux()
 	mux.HandleFunc("/healthz", s.handleHealth)
 	mux.HandleFunc("/pdb/query/v4/", s.handleQuery)
+	mux.HandleFunc(metaVersionPath, s.handleMetaVersion)
+	mux.HandleFunc(metaServerTimePath, s.handleMetaServerTime)
+	mux.HandleFunc(metricsPrefix, s.handleMetrics)
 	return mux
 }
 
@@ -67,7 +71,9 @@ func (s *Server) handleQuery(w http.ResponseWriter, r *http.Request) {
 	}
 	switch r.URL.Path {
 	case nodesPath:
-		s.serveMerged(w, r, nodesPath, s.mergeNodesResponse)
+		s.serveNodes(w, r)
+	case resourcesPath:
+		s.serveResources(w, r)
 	case factsPath:
 		s.serveMerged(w, r, factsPath, s.mergeFactsResponse)
 	case reportsPath:
@@ -134,6 +140,24 @@ func (s *Server) serveUnion(w http.ResponseWriter, r *http.Request, path string,
 	writeJSON(w, page.apply(merged))
 }
 
+// A count row carries no certname, so the certname-keyed merge would collapse every backend's count into one backend's; aggregates take the summing path instead.
+func (s *Server) serveNodes(w http.ResponseWriter, r *http.Request) {
+	if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {
+		s.serveSummed(w, r, nodesPath, spec.columns)
+		return
+	}
+	s.serveMerged(w, r, nodesPath, s.mergeNodesResponse)
+}
+
+// Only aggregates merge: a resource record has no cross-backend identity to dedupe on, so a plain query stays on the pass-through path.
+func (s *Server) serveResources(w http.ResponseWriter, r *http.Request) {
+	if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {
+		s.serveSummed(w, r, resourcesPath, spec.columns)
+		return
+	}
+	s.proxyUnmerged(w, r)
+}
+
 // An `extract` query with a `function` column returns synthetic aggregate rows that carry no identity, so they are summed rather than unioned.
 func (s *Server) serveReports(w http.ResponseWriter, r *http.Request) {
 	if spec := parseAggregate(r.URL.Query().Get("query")); spec != nil {

server_test.go

@@ -34,6 +34,9 @@ type fakeBackend struct {
 
 	mu        sync.Mutex
 	gotParams map[string]url.Values
+	// rawPaths records the still-escaped request paths, so tests can assert an
+	// MBean name's percent-encoding survived the proxy.
+	rawPaths []string
 }
 
 func newFakeBackend(t *testing.T, nodesBody, factsBody string) *fakeBackend {
@@ -51,6 +54,7 @@ func newFakeBackend(t *testing.T, nodesBody, factsBody string) *fakeBackend {
 		}
 		fb.mu.Lock()
 		fb.gotParams[r.URL.Path] = r.URL.Query()
+		fb.rawPaths = append(fb.rawPaths, r.URL.EscapedPath())
 		fb.mu.Unlock()
 		if fb.fail {
 			http.Error(w, "boom", http.StatusInternalServerError)
@@ -91,6 +95,14 @@ func (fb *fakeBackend) params(path string) (url.Values, bool) {
 	return v, ok
 }
 
+// sawRawPath reports whether the backend was asked for a path with exactly that
+// escaping.
+func (fb *fakeBackend) sawRawPath(p string) bool {
+	fb.mu.Lock()
+	defer fb.mu.Unlock()
+	return slices.Contains(fb.rawPaths, p)
+}
+
 // gotQuery returns the PuppetDB query param the backend saw for a path.
 func (fb *fakeBackend) gotQuery(path string) string {
 	v, _ := fb.params(path)
@@ -858,3 +870,120 @@ func TestHandler_EventCountsBadPagingParam(t *testing.T) {
 		t.Errorf("expected 400 for a malformed limit, got %d", rec.Code)
 	}
 }
+
+// What Puppetboard's landing page sends when DEFAULT_ENVIRONMENT names a real
+// environment: an extract/count with no group_by, so every backend returns one
+// anonymous row.
+const nodeCountQuery = `["extract",[["function","count"]],["and",["=","catalog_environment","production"]]]`
+
+func TestHandler_NodesAggregateSummed(t *testing.T) {
+	// A count row has no certname, so the certname-keyed merge would have
+	// collapsed both backends' counts into one backend's number.
+	a := newFakeBackend(t, `[{"count":90}]`, `[]`)
+	b := newFakeBackend(t, `[{"count":53}]`, `[]`)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := doGet(t, srv.Handler(), nodesPath, nodeCountQuery)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d: %s", rec.Code, rec.Body.String())
+	}
+	if got := counts(t, rec.Body.Bytes(), "count"); !slices.Equal(got, []float64{143}) {
+		t.Errorf("count = %v, want [143]", got)
+	}
+}
+
+func TestHandler_NodesAggregateGroupedSummed(t *testing.T) {
+	a := newFakeBackend(t, `[{"count":4,"catalog_environment":"production"},{"count":1,"catalog_environment":"dev"}]`, `[]`)
+	b := newFakeBackend(t, `[{"count":3,"catalog_environment":"production"}]`, `[]`)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := doGet(t, srv.Handler(), nodesPath,
+		`["extract",[["function","count"],"catalog_environment"],["~","certname",".*"],["group_by","catalog_environment"]]`)
+	var got []map[string]any
+	if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
+		t.Fatal(err)
+	}
+	byEnv := map[string]float64{}
+	for _, row := range got {
+		e, _ := row["catalog_environment"].(string)
+		n, _ := row["count"].(float64)
+		byEnv[e] = n
+	}
+	want := map[string]float64{"production": 7, "dev": 1}
+	if !reflect.DeepEqual(byEnv, want) {
+		t.Errorf("counts = %v, want %v", byEnv, want)
+	}
+}
+
+func TestHandler_NodesNonAggregateStillMergedByCertname(t *testing.T) {
+	// Regression: routing aggregates to the summing path must not divert plain
+	// queries, including an extract projection that carries no function column.
+	a := newFakeBackend(t,
+		`[`+node("h1", "2026-07-01T00:00:00Z")+`,`+node("h2", "2026-07-10T00:00:00Z")+`]`, `[]`)
+	b := newFakeBackend(t, `[`+node("h1", "2026-07-20T00:00:00Z")+`]`, `[]`)
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	for _, q := range []string{
+		`["=","certname","h1"]`,
+		`["extract",["certname","report_timestamp"],["~","certname",".*"]]`,
+	} {
+		rec := doGet(t, srv.Handler(), nodesPath, q)
+		var got []recordMeta
+		if err := json.Unmarshal(rec.Body.Bytes(), &got); err != nil {
+			t.Fatalf("query %s: %v", q, err)
+		}
+		if len(got) != 2 {
+			t.Fatalf("query %s: expected 2 deduped nodes, got %d: %s", q, len(got), rec.Body.String())
+		}
+		for _, m := range got {
+			if m.Certname == "h1" && m.ReportTimestamp != "2026-07-20T00:00:00Z" {
+				t.Errorf("query %s: h1 should be the newer record, got %s", q, m.ReportTimestamp)
+			}
+		}
+	}
+}
+
+func TestHandler_ResourcesAggregateSummed(t *testing.T) {
+	// /resources is otherwise an unmerged pass-through, so before this the
+	// landing page's resource total was whichever backend answered first.
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[resourcesPath] = `[{"count":1000}]`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[resourcesPath] = `[{"count":234}]`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := doGet(t, srv.Handler(), resourcesPath,
+		`["extract",[["function","count"]],["=","environment","production"]]`)
+	if rec.Code != http.StatusOK {
+		t.Fatalf("status %d: %s", rec.Code, rec.Body.String())
+	}
+	if got := counts(t, rec.Body.Bytes(), "count"); !slices.Equal(got, []float64{1234}) {
+		t.Errorf("count = %v, want [1234]", got)
+	}
+}
+
+func TestHandler_ResourcesNonAggregateStillPassesThrough(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[resourcesPath] = `[{"certname":"h1","type":"File"}]`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[resourcesPath] = `[{"certname":"h2","type":"File"}]`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	rec := doGet(t, srv.Handler(), resourcesPath, `["=","type","File"]`)
+	if got := rec.Body.String(); !strings.Contains(got, `"h1"`) || strings.Contains(got, `"h2"`) {
+		t.Errorf("body = %s, want the first backend's response verbatim", got)
+	}
+}
+
+func TestHandler_ResourcesAggregateAsksEveryBackend(t *testing.T) {
+	a := newFakeBackend(t, `[]`, `[]`)
+	a.bodies[resourcesPath] = `[{"count":1}]`
+	b := newFakeBackend(t, `[]`, `[]`)
+	b.bodies[resourcesPath] = `[{"count":1}]`
+	srv := newTestServer(testConfig(a.srv.URL, b.srv.URL, mergeStatic))
+
+	doGet(t, srv.Handler(), resourcesPath, `["extract",[["function","count"]],["=","environment","production"]]`)
+	if _, ok := b.params(resourcesPath); !ok {
+		t.Error("second backend was never asked for the resource count")
+	}
+}