nntrivi2001
57dc91585d
Internal SmartGift build of a Claude Code monitoring dashboard. Lanes: a durable unit of parallel agent work, one per working directory, tracked across session restarts. Managed lanes are git worktrees the dashboard provisions and can reset or remove behind a three-check destroy guard and a counted preflight; adopted lanes are directories you already own and are never destroyable. Pipelines: a lane moves through pipeline stages. A stage the agent declares with evidence renders green; a stage inferred from the tool-event stream renders dashed amber and never counts as done. Detection is forward-only within a 30-minute window, and never writes the declared stage. Workspace: one page at /run with a lane grid, the selected lane's pipeline, and a full Claude console behind a disclosure.
227 lines
7.8 KiB
YAML
227 lines
7.8 KiB
YAML
# ─────────────────────────────────────────────────────────────────────────────
|
|
# Prometheus configuration for Claude Code Agent Monitor
|
|
# ─────────────────────────────────────────────────────────────────────────────
|
|
global:
|
|
scrape_interval: 15s
|
|
scrape_timeout: 10s
|
|
evaluation_interval: 15s
|
|
|
|
external_labels:
|
|
cluster: "${CLUSTER_NAME:agent-monitor}"
|
|
environment: "${ENVIRONMENT:production}"
|
|
|
|
# ── Rule files ──────────────────────────────────────────────────────────────
|
|
rule_files:
|
|
- /etc/prometheus/rules/*.rules.yaml
|
|
|
|
# ── Alertmanager ────────────────────────────────────────────────────────────
|
|
alerting:
|
|
alertmanagers:
|
|
- static_configs:
|
|
- targets:
|
|
- alertmanager:9093
|
|
scheme: http
|
|
timeout: 10s
|
|
api_version: v2
|
|
|
|
# ── Scrape configs ──────────────────────────────────────────────────────────
|
|
scrape_configs:
|
|
# ── Agent Monitor application ─────────────────────────────────────────────
|
|
- job_name: "agent-monitor"
|
|
metrics_path: /api/health
|
|
scrape_interval: 15s
|
|
scrape_timeout: 5s
|
|
scheme: http
|
|
|
|
# Static target for standalone deployments
|
|
static_configs:
|
|
- targets:
|
|
- "agent-monitor:4820"
|
|
labels:
|
|
app: agent-monitor
|
|
component: server
|
|
|
|
# Relabeling to add standard labels
|
|
relabel_configs:
|
|
- source_labels: [__address__]
|
|
target_label: instance
|
|
- target_label: __metrics_path__
|
|
replacement: /api/health
|
|
|
|
metric_relabel_configs:
|
|
- source_labels: [__name__]
|
|
regex: "go_.*"
|
|
action: drop
|
|
|
|
# ── Agent Monitor MCP sidecar ─────────────────────────────────────────────
|
|
- job_name: "agent-monitor-mcp"
|
|
scrape_interval: 30s
|
|
static_configs:
|
|
- targets:
|
|
- "agent-monitor-mcp:8819"
|
|
labels:
|
|
app: agent-monitor
|
|
component: mcp
|
|
|
|
# ── Kubernetes service discovery (pods) ───────────────────────────────────
|
|
- job_name: "kubernetes-pods"
|
|
scrape_interval: 15s
|
|
|
|
kubernetes_sd_configs:
|
|
- role: pod
|
|
namespaces:
|
|
own_namespace: false
|
|
names:
|
|
- agent-monitor
|
|
- agent-monitor-dev
|
|
- agent-monitor-staging
|
|
- agent-monitor-production
|
|
|
|
relabel_configs:
|
|
# Only scrape pods with annotation prometheus.io/scrape=true
|
|
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scrape]
|
|
action: keep
|
|
regex: true
|
|
|
|
# Use custom metrics path if annotated
|
|
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_path]
|
|
action: replace
|
|
target_label: __metrics_path__
|
|
regex: (.+)
|
|
|
|
# Use custom port if annotated
|
|
- source_labels: [__address__, __meta_kubernetes_pod_annotation_prometheus_io_port]
|
|
action: replace
|
|
regex: ([^:]+)(?::\d+)?;(\d+)
|
|
replacement: $1:$2
|
|
target_label: __address__
|
|
|
|
# Use custom scheme if annotated
|
|
- source_labels: [__meta_kubernetes_pod_annotation_prometheus_io_scheme]
|
|
action: replace
|
|
target_label: __scheme__
|
|
regex: (.+)
|
|
|
|
# Map pod labels to Prometheus labels
|
|
- action: labelmap
|
|
regex: __meta_kubernetes_pod_label_(.+)
|
|
|
|
# Add namespace label
|
|
- source_labels: [__meta_kubernetes_namespace]
|
|
action: replace
|
|
target_label: namespace
|
|
|
|
# Add pod name label
|
|
- source_labels: [__meta_kubernetes_pod_name]
|
|
action: replace
|
|
target_label: pod
|
|
|
|
# Add node name label
|
|
- source_labels: [__meta_kubernetes_pod_node_name]
|
|
action: replace
|
|
target_label: node
|
|
|
|
# ── Kubernetes service discovery (services) ──────────────────────────────
|
|
- job_name: "kubernetes-services"
|
|
scrape_interval: 15s
|
|
|
|
kubernetes_sd_configs:
|
|
- role: service
|
|
namespaces:
|
|
names:
|
|
- agent-monitor
|
|
- agent-monitor-dev
|
|
- agent-monitor-staging
|
|
- agent-monitor-production
|
|
|
|
relabel_configs:
|
|
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_scrape]
|
|
action: keep
|
|
regex: true
|
|
|
|
- source_labels: [__meta_kubernetes_service_annotation_prometheus_io_path]
|
|
action: replace
|
|
target_label: __metrics_path__
|
|
regex: (.+)
|
|
|
|
- source_labels: [__address__, __meta_kubernetes_service_annotation_prometheus_io_port]
|
|
action: replace
|
|
regex: ([^:]+)(?::\d+)?;(\d+)
|
|
replacement: $1:$2
|
|
target_label: __address__
|
|
|
|
- action: labelmap
|
|
regex: __meta_kubernetes_service_label_(.+)
|
|
|
|
- source_labels: [__meta_kubernetes_namespace]
|
|
action: replace
|
|
target_label: namespace
|
|
|
|
- source_labels: [__meta_kubernetes_service_name]
|
|
action: replace
|
|
target_label: service
|
|
|
|
# ── Kubernetes nodes ──────────────────────────────────────────────────────
|
|
- job_name: "kubernetes-nodes"
|
|
scrape_interval: 30s
|
|
scheme: https
|
|
|
|
kubernetes_sd_configs:
|
|
- role: node
|
|
|
|
tls_config:
|
|
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecure_skip_verify: false
|
|
|
|
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
|
|
relabel_configs:
|
|
- action: labelmap
|
|
regex: __meta_kubernetes_node_label_(.+)
|
|
|
|
- target_label: __address__
|
|
replacement: kubernetes.default.svc:443
|
|
|
|
- source_labels: [__meta_kubernetes_node_name]
|
|
regex: (.+)
|
|
target_label: __metrics_path__
|
|
replacement: /api/v1/nodes/$1/proxy/metrics
|
|
|
|
# ── Kubernetes cadvisor (container metrics) ───────────────────────────────
|
|
- job_name: "kubernetes-cadvisor"
|
|
scrape_interval: 15s
|
|
scheme: https
|
|
|
|
kubernetes_sd_configs:
|
|
- role: node
|
|
|
|
tls_config:
|
|
ca_file: /var/run/secrets/kubernetes.io/serviceaccount/ca.crt
|
|
insecure_skip_verify: false
|
|
|
|
bearer_token_file: /var/run/secrets/kubernetes.io/serviceaccount/token
|
|
|
|
relabel_configs:
|
|
- action: labelmap
|
|
regex: __meta_kubernetes_node_label_(.+)
|
|
|
|
- target_label: __address__
|
|
replacement: kubernetes.default.svc:443
|
|
|
|
- source_labels: [__meta_kubernetes_node_name]
|
|
regex: (.+)
|
|
target_label: __metrics_path__
|
|
replacement: /api/v1/nodes/$1/proxy/metrics/cadvisor
|
|
|
|
metric_relabel_configs:
|
|
# Keep only container metrics for agent-monitor pods
|
|
- source_labels: [container]
|
|
regex: "agent-monitor.*"
|
|
action: keep
|
|
|
|
# ── Prometheus self-monitoring ────────────────────────────────────────────
|
|
- job_name: "prometheus"
|
|
static_configs:
|
|
- targets:
|
|
- "localhost:9090"
|