tessl install github:jeremylongshore/claude-code-plugins-plus-skills --skill exa-observabilitygithub.com/jeremylongshore/claude-code-plugins-plus-skills
Set up comprehensive observability for Exa integrations with metrics, traces, and alerts. Use when implementing monitoring for Exa operations, setting up dashboards, or configuring alerting for Exa integration health. Trigger with phrases like "exa monitoring", "exa metrics", "exa observability", "monitor exa", "exa alerts", "exa tracing".
Review Score
88%
Validation Score
12/16
Implementation Score
88%
Activation Score
90%
Set up comprehensive observability for Exa integrations.
| Metric | Type | Description |
|---|---|---|
exa_requests_total | Counter | Total API requests |
exa_request_duration_seconds | Histogram | Request latency |
exa_errors_total | Counter | Error count by type |
exa_rate_limit_remaining | Gauge | Rate limit headroom |
import { Registry, Counter, Histogram, Gauge } from 'prom-client';
const registry = new Registry();
const requestCounter = new Counter({
name: 'exa_requests_total',
help: 'Total Exa API requests',
labelNames: ['method', 'status'],
registers: [registry],
});
const requestDuration = new Histogram({
name: 'exa_request_duration_seconds',
help: 'Exa request duration',
labelNames: ['method'],
buckets: [0.05, 0.1, 0.25, 0.5, 1, 2.5, 5],
registers: [registry],
});
const errorCounter = new Counter({
name: 'exa_errors_total',
help: 'Exa errors by type',
labelNames: ['error_type'],
registers: [registry],
});async function instrumentedRequest<T>(
method: string,
operation: () => Promise<T>
): Promise<T> {
const timer = requestDuration.startTimer({ method });
try {
const result = await operation();
requestCounter.inc({ method, status: 'success' });
return result;
} catch (error: any) {
requestCounter.inc({ method, status: 'error' });
errorCounter.inc({ error_type: error.code || 'unknown' });
throw error;
} finally {
timer();
}
}import { trace, SpanStatusCode } from '@opentelemetry/api';
const tracer = trace.getTracer('exa-client');
async function tracedExaCall<T>(
operationName: string,
operation: () => Promise<T>
): Promise<T> {
return tracer.startActiveSpan(`exa.${operationName}`, async (span) => {
try {
const result = await operation();
span.setStatus({ code: SpanStatusCode.OK });
return result;
} catch (error: any) {
span.setStatus({ code: SpanStatusCode.ERROR, message: error.message });
span.recordException(error);
throw error;
} finally {
span.end();
}
});
}import pino from 'pino';
const logger = pino({
name: 'exa',
level: process.env.LOG_LEVEL || 'info',
});
function logExaOperation(
operation: string,
data: Record<string, any>,
duration: number
) {
logger.info({
service: 'exa',
operation,
duration_ms: duration,
...data,
});
}# exa_alerts.yaml
groups:
- name: exa_alerts
rules:
- alert: ExaHighErrorRate
expr: |
rate(exa_errors_total[5m]) /
rate(exa_requests_total[5m]) > 0.05
for: 5m
labels:
severity: warning
annotations:
summary: "Exa error rate > 5%"
- alert: ExaHighLatency
expr: |
histogram_quantile(0.95,
rate(exa_request_duration_seconds_bucket[5m])
) > 2
for: 5m
labels:
severity: warning
annotations:
summary: "Exa P95 latency > 2s"
- alert: ExaDown
expr: up{job="exa"} == 0
for: 1m
labels:
severity: critical
annotations:
summary: "Exa integration is down"{
"panels": [
{
"title": "Exa Request Rate",
"targets": [{
"expr": "rate(exa_requests_total[5m])"
}]
},
{
"title": "Exa Latency P50/P95/P99",
"targets": [{
"expr": "histogram_quantile(0.5, rate(exa_request_duration_seconds_bucket[5m]))"
}]
}
]
}Implement Prometheus counters, histograms, and gauges for key operations.
Integrate OpenTelemetry for end-to-end request tracing.
Set up JSON logging with consistent field names.
Define Prometheus alerting rules for error rates and latency.
| Issue | Cause | Solution |
|---|---|---|
| Missing metrics | No instrumentation | Wrap client calls |
| Trace gaps | Missing propagation | Check context headers |
| Alert storms | Wrong thresholds | Tune alert rules |
| High cardinality | Too many labels | Reduce label values |
app.get('/metrics', async (req, res) => {
res.set('Content-Type', registry.contentType);
res.send(await registry.metrics());
});For incident response, see exa-incident-runbook.