fix(metrics): align metric descriptions with updated docs

crates/api-core/src/logging/service_health_metrics.rs

@@ -33,7 +33,7 @@ pub fn start_export_service_health_metrics(health_context: ServiceHealthContext)
     health_context
         .meter
         .u64_observable_gauge("carbide_api_ready")
-        .with_description("Whether the Forge Site Controller API is running")
+        .with_description("Whether the NICo API is running")
         .with_callback(|observer| {
             observer.observe(1, &[]);
         })

crates/api-core/src/logging/setup.rs

@@ -309,7 +309,7 @@ pub fn create_metric_for_spancount_reader(
 ) {
     meter
         .u64_observable_gauge("carbide_api_tracing_spans_open")
-        .with_description("Whether the Forge Site Controller API is running")
+        .with_description("Number of open logging/tracing spans")
         .with_callback(move |observer| {
             let open_spans = if let Some(spancount_reader) = &spancount_reader {
                 spancount_reader.open_spans()

crates/api-core/src/tests/metrics_fixtures/test_service_health_metrics.txt

@@ -1,4 +1,4 @@
-# HELP carbide_api_ready Whether the Forge Site Controller API is running
+# HELP carbide_api_ready Whether the NICo API is running
 # TYPE carbide_api_ready gauge
 carbide_api_ready 1
 # HELP carbide_api_version Version (git sha, build date, etc) of this service

crates/api-integration-tests/tests/lib.rs

@@ -218,14 +218,14 @@ fn generate_core_metric_docs(metrics_endpoints: &[SocketAddr]) {
         .into_iter()
         .filter(|metric| !metric.name.starts_with("alt_metric"))
         .collect();
-    let mut docs = "# NCX Infra Controller (NICo) core metrics\n\n".to_string();
+    let mut docs = "# NVIDIA Infra Controller (NICo) Core Metrics\n\n".to_string();
     use std::fmt::Write;
 
     use askama_escape::Escaper;
 
     writeln!(
         &mut docs,
-        "This file contains a list of metrics exported by NCX Infra Controller (NICo). \
+        "This file contains a list of metrics exported by NVIDIA Infra Controller (NICo). \
         The list is auto-generated from an integration test (`test_integration`). \
         Metrics for workflows which are not exercised by the test are missing."
     )
@@ -249,7 +249,7 @@ fn generate_core_metric_docs(metrics_endpoints: &[SocketAddr]) {
         write!(&mut docs, "</td>").unwrap();
         writeln!(&mut docs, "</tr>").unwrap();
     }
-    writeln!(&mut docs, "<table>").unwrap();
+    writeln!(&mut docs, "</table>").unwrap();
 
     let path = std::path::Path::new(METRIC_DOC_PATH);
     assert!(

crates/health-metrics/src/lib.rs

@@ -130,6 +130,7 @@ impl<D: HealthMetricDimension> HealthIterationMetrics<D> {
 pub fn register_health_gauges<T, D, F>(
     metric_prefix: &str,
     suppressed_label_key: &'static str,
+    display_name_plural: &str,
     meter: &Meter,
     shared: SharedMetricsHolder<T>,
     project: F,
@@ -147,7 +148,7 @@ pub fn register_health_gauges<T, D, F>(
         meter
             .u64_observable_gauge(format!("{metric_prefix}_health_status_count"))
             .with_description(
-                "The total number of objects in the system that have reported either a healthy or not healthy status - based on the presence of health probe alerts",
+                format!("The total number of {display_name_plural} in the system that have reported either a healthy or not healthy status - based on the presence of health probe alerts"),
             )
             .with_callback(move |observer| {
                 metrics.if_available(|metrics, attrs| {

crates/machine-controller/src/metrics.rs

@@ -124,7 +124,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_gpus_total_count")
-                .with_description("The total number of GPUs available in the Forge site")
+                .with_description("The total number of GPUs available in the NICo deployment")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         observer.observe(metrics.gpus_total as u64, attrs);
@@ -136,7 +136,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_hosts_usable_count")
-                .with_description("The remaining number of hosts in the Forge site which are available for immediate instance creation")
+                .with_description("The remaining number of hosts in the NICo deployment which are available for immediate instance creation")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         observer.observe(
@@ -151,7 +151,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_gpus_usable_count")
-                .with_description("The remaining number of GPUs in the Forge site which are available for immediate instance creation")
+                .with_description("The remaining number of GPUs in the NICo deployment which are available for immediate instance creation")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         observer.observe(
@@ -166,7 +166,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_gpus_in_use_count")
-                .with_description("The total number of GPUs that are actively used by tenants in instances in the Forge site")
+                .with_description("The total number of GPUs that are actively used by tenants in instances in the NICo deployment")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         let total_in_use_gpus = metrics.gpus_in_use_by_tenant.values().copied().reduce(|a,b| a + b).unwrap_or_default();
@@ -182,7 +182,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_hosts_in_use_count")
-                .with_description("The total number of hosts that are actively used by tenants as instances in the Forge site")
+                .with_description("The total number of hosts that are actively used by tenants as instances in the NICo deployment")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         let total_in_use_hosts = metrics.hosts_in_use_by_tenant.values().copied().reduce(|a,b| a + b).unwrap_or_default();
@@ -266,6 +266,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
         register_health_gauges::<_, IsInUseByTenant, _>(
             "carbide_hosts",
             "machine_id",
+            "Managed Hosts",
             meter,
             shared_metrics.clone(),
             |m| &m.health,
@@ -347,9 +348,7 @@ impl MetricsEmitter for MachineMetricsEmitter {
             let metrics = shared_metrics.clone();
             meter
                 .u64_observable_gauge("carbide_dpu_agent_version_count")
-                .with_description(
-                    "The amount of Forge DPU agents which have reported a certain version.",
-                )
+                .with_description("The amount of DPU agents which have reported a certain version.")
                 .with_callback(move |observer| {
                     metrics.if_available(|metrics, attrs| {
                         for (version, count) in &metrics.agent_versions {

crates/power-shelf-controller/src/metrics.rs

@@ -45,6 +45,7 @@ impl MetricsEmitter for PowerShelfMetricsEmitter {
         register_health_gauges::<_, (), _>(
             "carbide_power_shelves",
             "power_shelf_id",
+            "Power Shelves",
             meter,
             shared_metrics,
             |m| &m.health,

crates/rack-controller/src/metrics.rs

@@ -45,6 +45,7 @@ impl MetricsEmitter for RackMetricsEmitter {
         register_health_gauges::<_, (), _>(
             "carbide_racks",
             "rack_id",
+            "Racks",
             meter,
             shared_metrics,
             |m| &m.health,

crates/switch-controller/src/metrics.rs

@@ -45,6 +45,7 @@ impl MetricsEmitter for SwitchMetricsEmitter {
         register_health_gauges::<_, (), _>(
             "carbide_switches",
             "switch_id",
+            "Switches",
             meter,
             shared_metrics,
             |m| &m.health,