Merge pull request #2172 from rcourtman/maintainer/20260922T223953Z

Fix TrueNAS CORE CPU and memory telemetry over legacy REST

docs/release-control/v6/internal/subsystems/monitoring.md

@@ -117,16 +117,28 @@ FreeBSD `active` pages are not a total-used-memory alias. Without an explicit
 used series, history derives usage from the known capacity and reported free
 memory, subtracting separately reported ARC as the live projection does.
 
+The legacy REST graph request also matches the request shape the native TrueNAS
+13 GUI itself sends (#2077): a graph that is not scoped to a device omits the
+`identifier` key instead of sending an explicit null. The reporter's CORE
+13.0-U6.1 WebSocket capture shows `reporting.get_data` graphs as
+`{"name":"cpu"}` (also memory, arcsize, load, swap, cputemp), with an
+`identifier` present only for parameterized graphs such as
+`{"name":"arcresult","identifier":"demand_data"}`. Sending `identifier: null`
+is not the native contract and is a plausible whole-batch rejection that would
+discard otherwise usable CPU and memory telemetry.
+
 `TestRESTReportingGraphFailurePreservesSnapshotTelemetry`,
 `TestRESTReportingGraphFailureBoundaries`,
-`TestRESTReportingPartialAndMalformedResponses` and
-`TestReportingActiveMemoryIsNotTotalUsed` in
+`TestRESTReportingPartialAndMalformedResponses`,
+`TestReportingActiveMemoryIsNotTotalUsed` and
+`TestRESTReportingRequestMatchesNativeGraphShape` in
 `internal/truenas/client_test.go` exercise request-validating synthetic REST
 responses, repeated full snapshots, CPU/free/ARC projections, matching history,
-partial data, bounded errors and cancellation. They do not establish the native
-CORE request schema, row timestamps/units, appliance acceptance or the reporter's
-exact failure. Native response evidence remains required before claiming that
-this repair resolves the reported telemetry journey.
+partial data, bounded errors, cancellation and the native identifier-less graph
+request shape. They do not establish the native CORE response schema, row
+timestamps/units, appliance acceptance or the reporter's exact failure. Native
+response evidence remains required before claiming that this repair resolves the
+reported telemetry journey.
 
 
 **Availability backfill preserves concurrent discovery changes (7 September 2026)**

internal/truenas/client.go

@@ -348,15 +348,31 @@ func latestTimeSeriesValue(series []TimeSeriesPoint) (float64, bool) {
 	return latest.Value, true
 }
 
+// reportingGraph builds a reporting.get_data graph entry in the shape the
+// TrueNAS 13 middleware itself accepts: a graph that is not scoped to a device
+// omits the identifier key entirely rather than sending an explicit null. The
+// native GUI requests CPU, memory and ARC as `{"name":"cpu"}` and only supplies
+// an identifier for parameterized graphs such as `arcresult` (#2077).
+func reportingGraph(name, identifier string) map[string]any {
+	graph := map[string]any{"name": name}
+	if trimmed := strings.TrimSpace(identifier); trimmed != "" {
+		graph["identifier"] = trimmed
+	}
+	return graph
+}
+
 // legacyRESTReportingGraphs is the reporting.get_data graph set used to
-// reconstruct live telemetry and history over the legacy REST transport.
+// reconstruct live telemetry and history over the legacy REST transport. The
+// identifier is omitted for device-independent graphs so the request matches
+// the native contract instead of sending a null identifier that the legacy
+// REST schema can reject for the whole batch (#2077).
 func legacyRESTReportingGraphs() []map[string]any {
 	return []map[string]any{
-		{"name": "cpu", "identifier": nil},
-		{"name": "memory", "identifier": nil},
-		{"name": "arcsize", "identifier": nil},
-		{"name": "interface", "identifier": nil},
-		{"name": "disk", "identifier": nil},
+		reportingGraph("cpu", ""),
+		reportingGraph("memory", ""),
+		reportingGraph("arcsize", ""),
+		reportingGraph("interface", ""),
+		reportingGraph("disk", ""),
 	}
 }
 

internal/truenas/client_test.go

@@ -2281,3 +2281,66 @@ func TestRESTReportingPartialAndMalformedResponses(t *testing.T) {
 		}
 	}
 }
+
+// nativeShapeReportingTransport models the request shape the TrueNAS 13
+// middleware accepts: a graph that carries an explicit identifier key (even a
+// null one) is rejected for the whole request, while a device-independent graph
+// that omits the key succeeds. This is a schema-faithful synthetic transport,
+// not an appliance capture; it encodes the native request shape the reporter
+// supplied in #2077.
+type nativeShapeReportingTransport struct {
+	routes alertArgsTransport
+	graphs []map[string]any
+}
+
+func (s *nativeShapeReportingTransport) RoundTrip(r *http.Request) (*http.Response, error) {
+	if r.URL.Path != "/api/v2.0/reporting/get_data" {
+		return s.routes.RoundTrip(r)
+	}
+	var request struct {
+		Graphs []map[string]any `json:"graphs"`
+		Query  map[string]any   `json:"query"`
+	}
+	if err := json.NewDecoder(r.Body).Decode(&request); err != nil {
+		return nil, err
+	}
+	s.graphs = append(s.graphs, request.Graphs...)
+	for _, graph := range request.Graphs {
+		if _, present := graph["identifier"]; present {
+			return (alertArgsTransport{r.URL.Path: apiResponse{
+				status: http.StatusUnprocessableEntity,
+				body:   `{"error":"identifier: Not a string"}`,
+			}}).RoundTrip(r)
+		}
+	}
+	body := `[
+		{"name":"cpu","legend":["user","idle"],"data":[[1789000060,12,88]]},
+		{"name":"memory","legend":["used","free","total"],"data":[[1789000060,6000000000,2000000000,16000000000]]},
+		{"name":"arcsize","legend":["size"],"data":[[1789000060,8000000000]]}
+	]`
+	return (alertArgsTransport{r.URL.Path: apiResponse{status: http.StatusOK, body: body}}).RoundTrip(r)
+}
+
+func TestRESTReportingRequestMatchesNativeGraphShape(t *testing.T) {
+	routes := alertArgsTransport(defaultAPIResponses())
+	routes["/api/v2.0/system/info"] = apiResponse{body: `{"hostname":"core","version":"TrueNAS-13.0-U6.1","physmem":16000000000}`}
+	transport := &nativeShapeReportingTransport{routes: routes}
+	client := newLegacyRESTReportingClient(t, routes)
+	client.httpClient.Transport = transport
+
+	telemetry, err := client.GetSystemTelemetry(context.Background())
+	if err != nil {
+		t.Fatalf("GetSystemTelemetry() error = %v", err)
+	}
+	if telemetry.CPUPercent != 12 || telemetry.MemoryAvailableBytes != 2000000000 || telemetry.ARCSizeBytes != 8000000000 {
+		t.Fatalf("native-shape telemetry lost: %+v", telemetry)
+	}
+	if len(transport.graphs) == 0 {
+		t.Fatal("no reporting graphs requested")
+	}
+	for _, graph := range transport.graphs {
+		if _, present := graph["identifier"]; present {
+			t.Fatalf("legacy REST graph %v sends an identifier key the native client omits", graph)
+		}
+	}
+}