Overview

Qhaway includes a pre-built Grafana dashboard JSON that visualizes your agent telemetry. It uses Prometheus as the data source, consuming metrics served by Qhaway’s metrics endpoint.

Setup

1. Deploy the Metrics Server

import { serveMetrics, MemoryStorage } from '@carloscortezcloud/qhaway';

const { server } = serveMetrics({
  port: 9090,
  storage: new MemoryStorage(),
});

2. Configure Prometheus

# prometheus.yml
scrape_configs:
  - job_name: 'qhaway'
    static_configs:
      - targets: ['localhost:9090']

3. Import the Dashboard

The dashboard JSON is at @carloscortezcloud/qhaway/src/dashboard/qhaway-dashboard.json.

In Grafana:

1. Click + → Import
2. Paste the JSON or upload the file
3. Select your Prometheus data source
4. Click Import

Dashboard Panels

Panel	Metric	Description
Cost by Model	qhaway_cost_total	Stacked bar chart of cost per model
Latency P99	qhaway_latency_seconds	Histogram of response times
Token Usage	qhaway_tokens_input_total + qhaway_tokens_output_total	Token counts over time
Call Volume	qhaway_calls_total	Request rate by model and success
Cost by User	qhaway_cost_total{user=~".*"}	Per-user spend breakdown

Grafana Cloud / Local

# docker-compose.yml
services:
  prometheus:
    image: prom/prometheus
    volumes:
      - ./prometheus.yml:/etc/prometheus/prometheus.yml
    ports:
      - 9090:9090

  grafana:
    image: grafana/grafana
    ports:
      - 3000:3000
    environment:
      - GF_AUTH_ANONYMOUS_ENABLED=true

Available Metrics

Metric	Type	Labels
qhaway_cost_total	Counter	model, provider, user
qhaway_latency_seconds	Histogram	model (buckets: 0.1, 0.5, 1, 2, 5, 10)
qhaway_tokens_input_total	Counter	model
qhaway_tokens_output_total	Counter	model
qhaway_calls_total	Counter	model, success