Have you ever described anything for observability — metrics, alerts?

For observability in Go projects, I described metrics using the Prometheus client_golang library. I usually created counters for counting events, histograms for measuring execution time, and gauges for current values.

Example of creating and registering a metric:

var httpRequestsTotal = prometheus.NewCounterVec(
    prometheus.CounterOpts{
        Name: "http_requests_total",
        Help: "Number of HTTP requests",
    },
    []string{"method", "endpoint"},
)

func init() {
    prometheus.MustRegister(httpRequestsTotal)
}

func handler(w http.ResponseWriter, r *http.Request) {
    httpRequestsTotal.WithLabelValues(r.Method, r.URL.Path).Inc()
    // handle request
}

For alerts, I usually set up rules in Prometheus Alertmanager, for example, if the number of errors exceeds a threshold over a certain period. This allows for prompt response to service issues.