Skip to content

Fix broken dashboard panels (Active Sessions, Tool Success Rate, API Error Rate) + add usage panels #11

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Open
404pilo wants to merge 1 commit into
base: main
Choose a base branch
from
Open

Fix broken dashboard panels (Active Sessions, Tool Success Rate, API Error Rate) + add usage panels #11

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
263 changes: 258 additions & 5 deletions claude-code-dashboard.json
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -86,9 +86,9 @@
"type": "prometheus",
"uid": "prometheus"
},
"expr": "sum(increase(claude_code_session_count_total{job=\"otel-collector\"}[1h]))",
"expr": "count(count by (session_id) (increase(claude_code_active_time_seconds_total{job=\"otel-collector\"}[1h]) > 0))",
"interval": "",
"legendFormat": "Sessions (1h)",
"legendFormat": "Active Sessions",
"refId": "A"
}
],
Expand Down Expand Up @@ -1087,7 +1087,7 @@
"type": "loki",
"uid": "loki"
},
"expr": "100 * (sum by (tool_name) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.tool_result\" | json | success=\"true\" [15m]))) / (sum by (tool_name) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.tool_result\" [15m])))",
"expr": "100 * (sum by (tool_name) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.tool_result\" | success=\"true\" [15m]))) / (sum by (tool_name) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.tool_result\" [15m])))",
"interval": "",
"legendFormat": "{{tool_name}}",
"refId": "A"
Expand Down Expand Up @@ -1202,7 +1202,7 @@
"mode": "palette-classic"
},
"custom": {
"axisLabel": "Errors/min",
"axisLabel": "Errors",
"axisPlacement": "auto",
"barAlignment": 0,
"drawStyle": "bars",
Expand Down Expand Up @@ -1271,7 +1271,7 @@
"type": "loki",
"uid": "loki"
},
"expr": "sum by (status_code) (rate({service_name=\"claude-code\"} |= \"claude_code.api_error\" | json | __error__ = \"\" [$__interval]))",
"expr": "sum by (status_code) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.api_error\" [$__interval]))",
"interval": "",
"legendFormat": "HTTP {{status_code}}",
"refId": "A"
Expand Down Expand Up @@ -1549,6 +1549,259 @@
],
"title": "API Error Events",
"type": "logs"
},
{
"title": "📈 Efficiency, Sessions & Breakdown",
"type": "row",
"gridPos": {"h": 1, "w": 24, "x": 0, "y": 66},
"collapsed": false
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "thresholds"},
"mappings": [],
"max": 100,
"min": 0,
"thresholds": {
"mode": "absolute",
"steps": [
{"color": "red", "value": null},
{"color": "yellow", "value": 50},
{"color": "green", "value": 90}
]
},
"unit": "percent"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 6, "x": 0, "y": 67},
"id": 18,
"options": {
"colorMode": "background",
"graphMode": "area",
"justifyMode": "center",
"orientation": "auto",
"reduceOptions": {"values": false, "calcs": ["lastNotNull"], "fields": ""},
"textMode": "auto"
},
"targets": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"expr": "100 * sum(increase(claude_code_token_usage_tokens_total{job=\"otel-collector\", type=\"cacheRead\"}[$__range])) / sum(increase(claude_code_token_usage_tokens_total{job=\"otel-collector\", type=~\"cacheRead|input\"}[$__range]))",
"interval": "",
"legendFormat": "Cache Hit %",
"refId": "A"
}
],
"title": "Cache Hit Ratio",
"type": "stat"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "USD",
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 20,
"lineInterpolation": "linear",
"lineWidth": 2,
"showPoints": "never",
"spanNulls": false,
"stacking": {"group": "A", "mode": "normal"}
},
"mappings": [],
"unit": "currencyUSD"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 18, "x": 6, "y": 67},
"id": 19,
"options": {
"legend": {"calcs": ["max", "mean"], "displayMode": "table", "placement": "bottom"},
"tooltip": {"mode": "multi", "sort": "desc"}
},
"targets": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"expr": "sum by (query_source) (increase(claude_code_cost_usage_USD_total{job=\"otel-collector\"}[1h]))",
"interval": "",
"legendFormat": "{{query_source}}",
"refId": "A"
}
],
"title": "Cost by Source (main vs subagent vs auxiliary)",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "Tokens",
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 10,
"lineInterpolation": "linear",
"lineWidth": 2,
"showPoints": "never",
"spanNulls": false,
"stacking": {"group": "A", "mode": "none"}
},
"mappings": [],
"unit": "short"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 75},
"id": 20,
"options": {
"legend": {"calcs": ["max", "mean"], "displayMode": "table", "placement": "bottom"},
"tooltip": {"mode": "multi", "sort": "desc"}
},
"targets": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"expr": "sum by (model) (increase(claude_code_token_usage_tokens_total{job=\"otel-collector\"}[1h]))",
"interval": "",
"legendFormat": "{{model}}",
"refId": "A"
}
],
"title": "Token Spend by Model (Hourly)",
"type": "timeseries"
},
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "Seconds",
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 20,
"lineInterpolation": "linear",
"lineWidth": 2,
"showPoints": "never",
"spanNulls": false,
"stacking": {"group": "A", "mode": "normal"}
},
"mappings": [],
"unit": "s"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 75},
"id": 21,
"options": {
"legend": {"calcs": ["sum"], "displayMode": "table", "placement": "bottom"},
"tooltip": {"mode": "multi", "sort": "desc"}
},
"targets": [
{
"datasource": {"type": "prometheus", "uid": "prometheus"},
"expr": "sum by (type) (increase(claude_code_active_time_seconds_total{job=\"otel-collector\"}[1h]))",
"interval": "",
"legendFormat": "{{type}}",
"refId": "A"
}
],
"title": "Active Time: User vs CLI (Hourly)",
"type": "timeseries"
},
{
"datasource": {"type": "loki", "uid": "loki"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "Decisions",
"axisPlacement": "auto",
"drawStyle": "bars",
"fillOpacity": 70,
"lineInterpolation": "linear",
"lineWidth": 1,
"showPoints": "never",
"spanNulls": false,
"stacking": {"group": "A", "mode": "normal"}
},
"mappings": [],
"min": 0,
"unit": "short"
},
"overrides": [
{
"matcher": {"id": "byName", "options": "accept"},
"properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "green"}}]
},
{
"matcher": {"id": "byName", "options": "reject"},
"properties": [{"id": "color", "value": {"mode": "fixed", "fixedColor": "red"}}]
}
]
},
"gridPos": {"h": 8, "w": 12, "x": 0, "y": 83},
"id": 22,
"options": {
"legend": {"calcs": ["sum"], "displayMode": "table", "placement": "bottom"},
"tooltip": {"mode": "multi", "sort": "desc"}
},
"targets": [
{
"datasource": {"type": "loki", "uid": "loki"},
"expr": "sum by (decision) (count_over_time({service_name=\"claude-code\"} |= \"claude_code.tool_decision\" [$__interval]))",
"interval": "",
"legendFormat": "{{decision}}",
"refId": "A"
}
],
"title": "Tool Decisions: Accept vs Reject",
"type": "timeseries"
},
{
"datasource": {"type": "loki", "uid": "loki"},
"fieldConfig": {
"defaults": {
"color": {"mode": "palette-classic"},
"custom": {
"axisLabel": "p95 latency (ms)",
"axisPlacement": "auto",
"drawStyle": "line",
"fillOpacity": 10,
"lineInterpolation": "linear",
"lineWidth": 2,
"showPoints": "never",
"spanNulls": false,
"stacking": {"group": "A", "mode": "none"}
},
"mappings": [],
"unit": "ms"
},
"overrides": []
},
"gridPos": {"h": 8, "w": 12, "x": 12, "y": 83},
"id": 23,
"options": {
"legend": {"calcs": ["mean", "max"], "displayMode": "table", "placement": "bottom"},
"tooltip": {"mode": "multi", "sort": "desc"}
},
"targets": [
{
"datasource": {"type": "loki", "uid": "loki"},
"expr": "quantile_over_time(0.95, {service_name=\"claude-code\"} |= \"claude_code.api_request\" | unwrap duration_ms [$__interval]) by (model)",
"interval": "",
"legendFormat": "{{model}} p95",
"refId": "A"
}
],
"title": "API Latency P95 by Model",
"type": "timeseries"
}
],
"refresh": "30s",
Expand Down
4 changes: 4 additions & 0 deletions collector-config.yaml
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -17,6 +17,10 @@ processors:
exporters:
prometheus:
endpoint: "0.0.0.0:8889"
# One-shot counters (session.count, lines_of_code, commit/PR, code_edit_decision)
# increment once and never update; the default ~5m expiration drops them from
# /metrics, breaking "Active Sessions" and similar panels. Hold series for 2h.
metric_expiration: 2h

debug:
verbosity: normal
Expand Down