0ddb504a98
The operator asked for this when the dashboard was first reviewed and it was deferred, not declined: the container metric family carried no hive label, so selecting a hive emptied every container panel while the "All" default hid the problem completely -- a `.*` matcher matches series where the label is absent. That family now carries hive and swarm, verified against the live store rather than inferred from the fix having merged: a hive selection returns the same 7 agents as the All default, at every window out to 168h, with a nonexistent hive returning zero. The agent list chains off the hive selection, so picking a hive narrows the agent dropdown rather than leaving entries in it that resolve to nothing.
678 lines
18 KiB
JSON
678 lines
18 KiB
JSON
{
|
|
"uid": "hyperhive-agents",
|
|
"title": "hyperhive · agents",
|
|
"description": "Per-agent view: resource usage from hive-c0re's container sampler, activity from Claude Code's own export. Renamed from 'overview' — every producer we have today is per-agent, so a genuine swarm overview has nothing cross-cutting to summarise yet and should be built last, not first. Metric names are the OTLP DOTTED form, so every query uses the {__name__=\"...\"} selector — the underscore spelling matches nothing in this store. Cost/token totals use increase(), which is correct here: the claude_code.* counters are cumulative (forced in nix/agent-modules/otel.nix) but reset once per turn, since each turn is a new claude process.",
|
|
"tags": [
|
|
"hyperhive",
|
|
"agents"
|
|
],
|
|
"timezone": "utc",
|
|
"schemaVersion": 39,
|
|
"version": 1,
|
|
"editable": true,
|
|
"refresh": "1m",
|
|
"time": {
|
|
"from": "now-6h",
|
|
"to": "now"
|
|
},
|
|
"templating": {
|
|
"list": [
|
|
{
|
|
"name": "hive",
|
|
"label": "Hive",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"query": "label_values({__name__=\"hyperhive.container.cpu.percent\"}, hive)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"multi": true,
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
},
|
|
{
|
|
"name": "agent",
|
|
"label": "Agent",
|
|
"type": "query",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"query": "label_values({__name__=\"hyperhive.container.cpu.percent\", hive=~\"$hive\"}, agent)",
|
|
"refresh": 2,
|
|
"includeAll": true,
|
|
"allValue": ".*",
|
|
"multi": true,
|
|
"current": {
|
|
"text": "All",
|
|
"value": "$__all"
|
|
},
|
|
"sort": 1
|
|
}
|
|
]
|
|
},
|
|
"panels": [
|
|
{
|
|
"id": 1,
|
|
"type": "stat",
|
|
"title": "Agents reporting",
|
|
"description": "Distinct agents whose container metrics reached the store in the selected range. This counts what hive-c0re observes, not what the topology declares — a gap between the two is the interesting case.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 0,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "count(count by (agent) ({__name__=\"hyperhive.container.cpu.percent\", hive=~\"$hive\", agent=~\"$agent\"}))",
|
|
"instant": true,
|
|
"legendFormat": "agents"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "text"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"justifyMode": "auto",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 2,
|
|
"type": "stat",
|
|
"title": "Cost",
|
|
"description": "sum(increase(claude_code.cost.usage)). Agent-reported, so it covers claude's own token spend only — nothing else in the swarm reports cost.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 6,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(increase({__name__=\"claude_code.cost.usage\", hive=~\"$hive\", agent=~\"$agent\"}[$__range]))",
|
|
"instant": true,
|
|
"legendFormat": "cost"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "currencyUSD",
|
|
"decimals": 2,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "text"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 3,
|
|
"type": "stat",
|
|
"title": "Tokens (excl. cache reads)",
|
|
"description": "Excludes type=cacheRead, which would otherwise BE this number: measured over 6h on this store, cacheRead was 273.5M of 275.8M total — 99.2%. Counting it makes the tile a cache-hit-rate readout wearing a token label, and it drowns the input/output volume that actually tracks work done. Remaining types: input, output, cacheCreation.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 12,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(increase({__name__=\"claude_code.token.usage\", hive=~\"$hive\", agent=~\"$agent\", type!=\"cacheRead\"}[$__range]))",
|
|
"instant": true,
|
|
"legendFormat": "tokens"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 1,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "text"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 4,
|
|
"type": "stat",
|
|
"title": "CLI sessions started",
|
|
"description": "claude_code.session.count counts CLI STARTS, and the harness starts one claude process per turn — so this reads as turns, not as long-lived sessions. Named for what it measures rather than what the metric is called.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 4,
|
|
"w": 6,
|
|
"x": 18,
|
|
"y": 0
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum(increase({__name__=\"claude_code.session.count\", hive=~\"$hive\", agent=~\"$agent\"}[$__range]))",
|
|
"instant": true,
|
|
"legendFormat": "sessions"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "text"
|
|
},
|
|
"mappings": []
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"graphMode": "none",
|
|
"colorMode": "value",
|
|
"textMode": "value",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 10,
|
|
"type": "timeseries",
|
|
"title": "Cost rate by agent",
|
|
"description": "USD per hour, from rate() over the cumulative counter — reset-safe. A flat line at zero is an idle agent, not a broken exporter; check the CPU panel to tell them apart.\n\nThe 10m minimum step is load-bearing, not a style choice: agents export every 60s, and measured against this store a rate window of 1m or 2m resolves ONE agent instead of five. Any shorter and the panel quietly under-reports.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"interval": "10m",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 4
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (agent) (rate({__name__=\"claude_code.cost.usage\", hive=~\"$hive\", agent=~\"$agent\"}[$__rate_interval])) * 3600",
|
|
"legendFormat": "{{agent}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "currencyUSD",
|
|
"decimals": 2,
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"axisSoftMin": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"calcs": []
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 11,
|
|
"type": "timeseries",
|
|
"title": "Container CPU by agent",
|
|
"description": "hyperhive.container.cpu.percent, sampled by hive-c0re. Percent of one core.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 12
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (agent) ({__name__=\"hyperhive.container.cpu.percent\", hive=~\"$hive\", agent=~\"$agent\"})",
|
|
"legendFormat": "{{agent}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "percent",
|
|
"decimals": 1,
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"axisSoftMin": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"calcs": []
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 20,
|
|
"type": "timeseries",
|
|
"title": "Container memory by agent",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 0,
|
|
"y": 12
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (agent) ({__name__=\"container.memory.usage\", hive=~\"$hive\", agent=~\"$agent\"})",
|
|
"legendFormat": "{{agent}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"axisSoftMin": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"calcs": []
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 21,
|
|
"type": "timeseries",
|
|
"title": "Tokens by model (excl. cache reads)",
|
|
"description": "Split by model rather than by agent on purpose — 'which model is the spend on' is the question this answers. Excludes type=cacheRead for the same reason as the tile above: at ~99% of volume it flattens every model into one line shaped like its cache. 10m minimum step for the same reason as the cost-rate panel.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"interval": "10m",
|
|
"gridPos": {
|
|
"h": 8,
|
|
"w": 12,
|
|
"x": 12,
|
|
"y": 4
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (model) (rate({__name__=\"claude_code.token.usage\", hive=~\"$hive\", agent=~\"$agent\", type!=\"cacheRead\"}[$__rate_interval])) * 60",
|
|
"legendFormat": "{{model}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"axisSoftMin": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"calcs": []
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 30,
|
|
"type": "bargauge",
|
|
"title": "Container storage by agent",
|
|
"description": "Magnitude comparison, so a bar rather than seven lines. One fixed colour on purpose: the agents are nominal categories, and colouring them by size would encode the bar length twice.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 8,
|
|
"x": 0,
|
|
"y": 20
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (agent) ({__name__=\"hyperhive.container.storage.usage\", hive=~\"$hive\", agent=~\"$agent\"})",
|
|
"instant": true,
|
|
"legendFormat": "{{agent}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "bytes",
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "blue"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "blue",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"displayMode": "basic",
|
|
"orientation": "horizontal",
|
|
"showUnfilled": true,
|
|
"valueMode": "text",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 31,
|
|
"type": "timeseries",
|
|
"title": "Lines of code changed",
|
|
"description": "claude_code.lines_of_code.count carries a `type` label (added / removed). 10m minimum step for the same reason as the cost-rate panel.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"interval": "10m",
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 8,
|
|
"x": 8,
|
|
"y": 20
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (type) (rate({__name__=\"claude_code.lines_of_code.count\", hive=~\"$hive\", agent=~\"$agent\"}[$__rate_interval])) * 60",
|
|
"legendFormat": "{{type}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "short",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "palette-classic"
|
|
},
|
|
"custom": {
|
|
"drawStyle": "line",
|
|
"lineWidth": 1,
|
|
"fillOpacity": 0,
|
|
"showPoints": "never",
|
|
"spanNulls": false,
|
|
"axisSoftMin": 0
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"legend": {
|
|
"displayMode": "list",
|
|
"placement": "bottom",
|
|
"showLegend": true,
|
|
"calcs": []
|
|
},
|
|
"tooltip": {
|
|
"mode": "multi",
|
|
"sort": "desc"
|
|
}
|
|
}
|
|
},
|
|
{
|
|
"id": 32,
|
|
"type": "bargauge",
|
|
"title": "Active time by agent",
|
|
"description": "claude_code.active_time.total — seconds an agent was actually working, not wall-clock uptime.",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"gridPos": {
|
|
"h": 7,
|
|
"w": 8,
|
|
"x": 16,
|
|
"y": 20
|
|
},
|
|
"targets": [
|
|
{
|
|
"refId": "A",
|
|
"datasource": {
|
|
"type": "prometheus",
|
|
"uid": "@datasourceUid@"
|
|
},
|
|
"expr": "sum by (agent) (increase({__name__=\"claude_code.active_time.total\", hive=~\"$hive\", agent=~\"$agent\"}[$__range]))",
|
|
"instant": true,
|
|
"legendFormat": "{{agent}}"
|
|
}
|
|
],
|
|
"fieldConfig": {
|
|
"defaults": {
|
|
"unit": "s",
|
|
"decimals": 0,
|
|
"color": {
|
|
"mode": "fixed",
|
|
"fixedColor": "purple"
|
|
},
|
|
"thresholds": {
|
|
"mode": "absolute",
|
|
"steps": [
|
|
{
|
|
"color": "purple",
|
|
"value": null
|
|
}
|
|
]
|
|
}
|
|
},
|
|
"overrides": []
|
|
},
|
|
"options": {
|
|
"displayMode": "basic",
|
|
"orientation": "horizontal",
|
|
"showUnfilled": true,
|
|
"valueMode": "text",
|
|
"reduceOptions": {
|
|
"calcs": [
|
|
"lastNotNull"
|
|
],
|
|
"fields": "",
|
|
"values": false
|
|
}
|
|
}
|
|
}
|
|
]
|
|
}
|