diff --git a/evals/tasks/observability/labels/series-by-namespace.yaml b/evals/tasks/observability/labels/series-by-namespace.yaml index 23d78b58e..e3201236e 100644 --- a/evals/tasks/observability/labels/series-by-namespace.yaml +++ b/evals/tasks/observability/labels/series-by-namespace.yaml @@ -25,4 +25,5 @@ spec: prompt: inline: | How many time series exist for container_cpu_usage_seconds_total - in the openshift-monitoring namespace? + in the openshift-monitoring namespace? List the label dimensions + (such as pod, container) present in the series. diff --git a/evals/tasks/observability/queries/cpu-usage.yaml b/evals/tasks/observability/queries/cpu-usage.yaml index 3baddf6cf..f3d1ef0ca 100644 --- a/evals/tasks/observability/queries/cpu-usage.yaml +++ b/evals/tasks/observability/queries/cpu-usage.yaml @@ -22,4 +22,5 @@ spec: reason: "Verify the response identifies specific pods" prompt: inline: | - Which pods are using the most CPU? + Which pods are using the most CPU? Show me the top 5. + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/crashlooping-pods.yaml b/evals/tasks/observability/queries/crashlooping-pods.yaml index 4e975964e..9499c6a7c 100644 --- a/evals/tasks/observability/queries/crashlooping-pods.yaml +++ b/evals/tasks/observability/queries/crashlooping-pods.yaml @@ -20,3 +20,4 @@ spec: prompt: inline: | Which pods were crashlooping in the last 5 minutes? + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/diagnose-cluster-health.yaml b/evals/tasks/observability/queries/diagnose-cluster-health.yaml index 7542b61e5..6b7936f4d 100644 --- a/evals/tasks/observability/queries/diagnose-cluster-health.yaml +++ b/evals/tasks/observability/queries/diagnose-cluster-health.yaml @@ -25,4 +25,5 @@ spec: prompt: inline: | Is the cluster healthy? Give me an overview of any issues. - Check alerts, node status, and pod health. + Check alerts, node status, and pod health using Prometheus metrics. + Include the metric names and PromQL queries you used. diff --git a/evals/tasks/observability/queries/memory-usage.yaml b/evals/tasks/observability/queries/memory-usage.yaml index 58da3fce8..784a2ac1d 100644 --- a/evals/tasks/observability/queries/memory-usage.yaml +++ b/evals/tasks/observability/queries/memory-usage.yaml @@ -23,3 +23,4 @@ spec: prompt: inline: | Which pods are using the most memory? Show me the top 5. + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/namespace-pod-count.yaml b/evals/tasks/observability/queries/namespace-pod-count.yaml index b180a917d..e81006820 100644 --- a/evals/tasks/observability/queries/namespace-pod-count.yaml +++ b/evals/tasks/observability/queries/namespace-pod-count.yaml @@ -25,3 +25,4 @@ spec: prompt: inline: | Which namespaces have the most running pods? Show me the top 5. + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/namespace-resource-usage.yaml b/evals/tasks/observability/queries/namespace-resource-usage.yaml index 4434ca52c..d492f9c0d 100644 --- a/evals/tasks/observability/queries/namespace-resource-usage.yaml +++ b/evals/tasks/observability/queries/namespace-resource-usage.yaml @@ -26,3 +26,4 @@ spec: inline: | Which namespace is consuming the most CPU and memory? Show me the top namespace for each. + Use Prometheus metrics and include the metric names and PromQL queries you used. diff --git a/evals/tasks/observability/queries/network-traffic.yaml b/evals/tasks/observability/queries/network-traffic.yaml index 9b1e06fd3..017cf2ff5 100644 --- a/evals/tasks/observability/queries/network-traffic.yaml +++ b/evals/tasks/observability/queries/network-traffic.yaml @@ -23,3 +23,4 @@ spec: prompt: inline: | Which pods are receiving the most network traffic? + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/pending-pods.yaml b/evals/tasks/observability/queries/pending-pods.yaml index f5b47e387..ebc948256 100644 --- a/evals/tasks/observability/queries/pending-pods.yaml +++ b/evals/tasks/observability/queries/pending-pods.yaml @@ -21,3 +21,4 @@ spec: prompt: inline: | Which pods are stuck in pending state? + Use Prometheus metrics and include the metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/pods-created.yaml b/evals/tasks/observability/queries/pods-created.yaml index 097a57e24..65dd773b7 100644 --- a/evals/tasks/observability/queries/pods-created.yaml +++ b/evals/tasks/observability/queries/pods-created.yaml @@ -20,3 +20,4 @@ spec: prompt: inline: | How many pods were created in the last 5 minutes? + Include the Prometheus metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/prometheus-head-series.yaml b/evals/tasks/observability/queries/prometheus-head-series.yaml index 9f62ffdf3..081bacb00 100644 --- a/evals/tasks/observability/queries/prometheus-head-series.yaml +++ b/evals/tasks/observability/queries/prometheus-head-series.yaml @@ -20,3 +20,4 @@ spec: prompt: inline: | How many head series does Prometheus have? + Include the Prometheus metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/prometheus-requests.yaml b/evals/tasks/observability/queries/prometheus-requests.yaml index f436130b4..321638990 100644 --- a/evals/tasks/observability/queries/prometheus-requests.yaml +++ b/evals/tasks/observability/queries/prometheus-requests.yaml @@ -20,3 +20,4 @@ spec: prompt: inline: | How many requests per second are being made to Prometheus? + Include the Prometheus metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/prometheus-wal-size.yaml b/evals/tasks/observability/queries/prometheus-wal-size.yaml index aa19ea451..07eb621e0 100644 --- a/evals/tasks/observability/queries/prometheus-wal-size.yaml +++ b/evals/tasks/observability/queries/prometheus-wal-size.yaml @@ -20,3 +20,4 @@ spec: prompt: inline: | What is the current storage size of the Prometheus WAL? + Include the Prometheus metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/time-range-query.yaml b/evals/tasks/observability/queries/time-range-query.yaml index 80a144be2..a4df7a39b 100644 --- a/evals/tasks/observability/queries/time-range-query.yaml +++ b/evals/tasks/observability/queries/time-range-query.yaml @@ -24,3 +24,4 @@ spec: prompt: inline: | Show me the CPU usage trend for pods in the default namespace over the last 30 minutes. + Include the Prometheus metric name and PromQL query you used. diff --git a/evals/tasks/observability/queries/visualize-cpu-usage.yaml b/evals/tasks/observability/queries/visualize-cpu-usage.yaml index 74d88ac85..29bcd3c03 100644 --- a/evals/tasks/observability/queries/visualize-cpu-usage.yaml +++ b/evals/tasks/observability/queries/visualize-cpu-usage.yaml @@ -21,3 +21,4 @@ spec: prompt: inline: | Visualize the CPU usage for pods in the default namespace over the last 30 minutes. + Include the Prometheus metric name and PromQL query you used.