Track HiveGrid Cloud planning reference

This commit is contained in:
david committed 2026-06-26 20:48:01 +02:00
1 parent b3d5ea6764
commit e341c5938a
5784 files changed
+1104929 -3

No files matched your search

@@ -0,0 +1,53 @@
{
"uid": "boilerplate-ai-cost",
"title": "Boilerplate — AI Cost per Tenant",
"tags": ["boilerplate", "ai"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "1m",
"time": { "from": "now-24h", "to": "now" },
"panels": [
{
"id": 1,
"type": "barchart",
"title": "Top tenants — tokens consumed (last 24h)",
"gridPos": { "h": 10, "w": 12, "x": 0, "y": 0 },
"targets": [
{
"refId": "A",
"expr": "topk(20, sum by (tenant_bucket) (increase(ai_tokens_consumed_total[24h])))",
"legendFormat": "{{tenant_bucket}}",
"datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" }
}
]
},
{
"id": 2,
"type": "piechart",
"title": "Tokens by provider (24h)",
"gridPos": { "h": 10, "w": 12, "x": 12, "y": 0 },
"targets": [
{ "refId": "A", "expr": "sum by (provider) (increase(ai_tokens_consumed_total[24h]))", "legendFormat": "{{provider}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 3,
"type": "timeseries",
"title": "Daily token-consumption trend (per model)",
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 10 },
"targets": [
{ "refId": "A", "expr": "sum by (model) (rate(ai_tokens_consumed_total[1h]))", "legendFormat": "{{model}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 4,
"type": "stat",
"title": "Cardinality of tenant_bucket (should stay ≤ 101)",
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 20 },
"targets": [
{ "refId": "A", "expr": "count(count by (tenant_bucket) (ai_tokens_consumed_total))", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
],
"fieldConfig": { "defaults": { "thresholds": { "mode": "absolute", "steps": [{ "color": "green", "value": null }, { "color": "yellow", "value": 80 }, { "color": "red", "value": 101 }] } } }
}
]
}
@@ -0,0 +1,41 @@
{
"uid": "boilerplate-api-latency",
"title": "Boilerplate — API Latency",
"tags": ["boilerplate", "api"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "30s",
"time": { "from": "now-1h", "to": "now" },
"panels": [
{
"id": 1,
"type": "timeseries",
"title": "p50 / p95 / p99 (s) per route",
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 0 },
"targets": [
{ "refId": "A", "expr": "histogram_quantile(0.50, sum by (le, route) (rate(http_request_duration_seconds_bucket{service=\"api\"}[5m])))", "legendFormat": "p50 {{route}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } },
{ "refId": "B", "expr": "histogram_quantile(0.95, sum by (le, route) (rate(http_request_duration_seconds_bucket{service=\"api\"}[5m])))", "legendFormat": "p95 {{route}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } },
{ "refId": "C", "expr": "histogram_quantile(0.99, sum by (le, route) (rate(http_request_duration_seconds_bucket{service=\"api\"}[5m])))", "legendFormat": "p99 {{route}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
],
"fieldConfig": { "defaults": { "unit": "s" } }
},
{
"id": 2,
"type": "timeseries",
"title": "Request rate per route",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 10 },
"targets": [
{ "refId": "A", "expr": "sum by (route) (rate(http_requests_total{service=\"api\"}[1m]))", "legendFormat": "{{route}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 3,
"type": "timeseries",
"title": "Status-code distribution",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 10 },
"targets": [
{ "refId": "A", "expr": "sum by (status) (rate(http_requests_total{service=\"api\"}[1m]))", "legendFormat": "{{status}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
}
]
}
@@ -0,0 +1,65 @@
{
"uid": "boilerplate-business-kpi",
"title": "Boilerplate — Business KPIs",
"tags": ["boilerplate", "business"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "1m",
"time": { "from": "now-24h", "to": "now" },
"panels": [
{
"id": 1,
"type": "stat",
"title": "Active tenants",
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
"targets": [
{ "refId": "A", "expr": "active_tenants", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 2,
"type": "stat",
"title": "Active users (24h)",
"gridPos": { "h": 4, "w": 6, "x": 6, "y": 0 },
"targets": [
{ "refId": "A", "expr": "active_users_24h", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 3,
"type": "timeseries",
"title": "Stripe webhook events / min by type",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 4 },
"targets": [
{ "refId": "A", "expr": "sum by (event_type) (rate(stripe_webhook_events_total[5m]))", "legendFormat": "{{event_type}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 4,
"type": "timeseries",
"title": "Mail delivery rate by status",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 4 },
"targets": [
{ "refId": "A", "expr": "sum by (status) (rate(mail_sent_total[5m]))", "legendFormat": "{{status}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 5,
"type": "timeseries",
"title": "Outbound webhook attempts by status",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 12 },
"targets": [
{ "refId": "A", "expr": "sum by (status) (rate(webhook_delivery_attempts_total[5m]))", "legendFormat": "{{status}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 6,
"type": "timeseries",
"title": "Active subscriptions by plan",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 12 },
"targets": [
{ "refId": "A", "expr": "subscription_active", "legendFormat": "{{plan_id}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
}
]
}
@@ -0,0 +1,60 @@
{
"uid": "boilerplate-overview",
"title": "Boilerplate — Overview",
"tags": ["boilerplate", "overview"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "30s",
"time": { "from": "now-3h", "to": "now" },
"panels": [
{
"id": 1,
"type": "stat",
"title": "Services up",
"gridPos": { "h": 4, "w": 6, "x": 0, "y": 0 },
"targets": [
{ "refId": "A", "expr": "count(up{job=~\"boilerplate-.*\"} == 1)", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
],
"fieldConfig": { "defaults": { "mappings": [], "thresholds": { "mode": "absolute", "steps": [{ "color": "red", "value": null }, { "color": "green", "value": 3 }] } } }
},
{
"id": 2,
"type": "timeseries",
"title": "HTTP request rate (per service)",
"gridPos": { "h": 8, "w": 12, "x": 6, "y": 0 },
"targets": [
{ "refId": "A", "expr": "sum by (service) (rate(http_requests_total[1m]))", "legendFormat": "{{service}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 3,
"type": "timeseries",
"title": "HTTP error ratio (5xx / total)",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
"targets": [
{
"refId": "A",
"expr": "sum by (service) (rate(http_requests_total{status=~\"5..\"}[5m])) / clamp_min(sum by (service) (rate(http_requests_total[5m])), 0.001)",
"legendFormat": "{{service}}",
"datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" }
}
],
"fieldConfig": { "defaults": { "unit": "percentunit", "max": 0.5 } }
},
{
"id": 4,
"type": "timeseries",
"title": "HTTP latency p95",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
"targets": [
{
"refId": "A",
"expr": "histogram_quantile(0.95, sum by (le, service) (rate(http_request_duration_seconds_bucket[5m])))",
"legendFormat": "{{service}}",
"datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" }
}
],
"fieldConfig": { "defaults": { "unit": "s" } }
}
]
}
@@ -0,0 +1,56 @@
{
"uid": "boilerplate-queue-health",
"title": "Boilerplate — Queue Health",
"tags": ["boilerplate", "queue"],
"timezone": "browser",
"schemaVersion": 39,
"refresh": "30s",
"time": { "from": "now-3h", "to": "now" },
"panels": [
{
"id": 1,
"type": "timeseries",
"title": "Active jobs (gauge) per queue",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 0 },
"targets": [
{ "refId": "A", "expr": "queue_jobs_active", "legendFormat": "{{queue}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 2,
"type": "timeseries",
"title": "Waiting jobs (gauge) per queue",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 0 },
"targets": [
{ "refId": "A", "expr": "queue_jobs_waiting", "legendFormat": "{{queue}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 3,
"type": "timeseries",
"title": "Completed rate per queue",
"gridPos": { "h": 8, "w": 12, "x": 0, "y": 8 },
"targets": [
{ "refId": "A", "expr": "sum by (queue) (rate(queue_jobs_completed_total[5m]))", "legendFormat": "{{queue}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 4,
"type": "timeseries",
"title": "Failed rate per queue (by error_type)",
"gridPos": { "h": 8, "w": 12, "x": 12, "y": 8 },
"targets": [
{ "refId": "A", "expr": "sum by (queue, error_type) (rate(queue_jobs_failed_total[5m]))", "legendFormat": "{{queue}} / {{error_type}}", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
},
{
"id": 5,
"type": "heatmap",
"title": "Job duration heatmap",
"gridPos": { "h": 10, "w": 24, "x": 0, "y": 16 },
"targets": [
{ "refId": "A", "expr": "sum by (le) (rate(queue_job_duration_seconds_bucket[5m]))", "format": "heatmap", "datasource": { "uid": "boilerplate-prometheus", "type": "prometheus" } }
]
}
]
}
@@ -0,0 +1,50 @@
# Grafana stack for the boilerplate.
#
# Deploys alongside Prometheus on the Hetzner observability box. Joins the
# same docker network so Grafana can reach Prometheus via DNS
# `prometheus:9090`.
services:
grafana:
image: grafana/grafana-oss:11.4.0
container_name: boilerplate-grafana
restart: unless-stopped
user: "472:472"
environment:
# All sensitive values come from the operator's Coolify secrets.
GF_SECURITY_ADMIN_USER: ${GRAFANA_ADMIN_USER:-admin}
GF_SECURITY_ADMIN_PASSWORD: ${GRAFANA_ADMIN_PASSWORD:?GRAFANA_ADMIN_PASSWORD must be set}
# Disable anonymous access — Business / per-tenant data lives in here.
GF_AUTH_ANONYMOUS_ENABLED: "false"
GF_AUTH_DISABLE_LOGIN_FORM: "false"
GF_SERVER_ROOT_URL: ${GRAFANA_ROOT_URL:-https://grafana.boiler.saas-ctrl.com}
# Prometheus token used by the provisioned datasource. The yaml
# references it via env interpolation.
GRAFANA_PROMETHEUS_TOKEN: ${GRAFANA_PROMETHEUS_TOKEN:?GRAFANA_PROMETHEUS_TOKEN must be set}
volumes:
- ./provisioning:/etc/grafana/provisioning:ro
- ./dashboards:/var/lib/grafana/dashboards:ro
- grafana-data:/var/lib/grafana
ports:
- "3000:3000"
networks:
- observability
depends_on:
- waitfornet
# Lightweight no-op service that fails compose-up early if the shared
# network is missing. Cheaper than letting grafana retry indefinitely.
waitfornet:
image: alpine:3
command: ["true"]
networks:
- observability
networks:
observability:
name: boilerplate-observability
external: true
volumes:
grafana-data:
name: boilerplate-grafana-data
@@ -0,0 +1,13 @@
apiVersion: 1
providers:
- name: boilerplate
orgId: 1
folder: Boilerplate
type: file
disableDeletion: true
updateIntervalSeconds: 30
allowUiUpdates: false
options:
path: /var/lib/grafana/dashboards
foldersFromFilesStructure: false
@@ -0,0 +1,16 @@
apiVersion: 1
datasources:
- name: Prometheus
type: prometheus
uid: boilerplate-prometheus
access: proxy
url: http://prometheus:9090
isDefault: true
editable: false
jsonData:
httpHeaderName1: "Authorization"
timeInterval: "15s"
manageAlerts: false
secureJsonData:
httpHeaderValue1: "Bearer ${GRAFANA_PROMETHEUS_TOKEN}"