From 688548d4ac3293449a88913275f886fd2e103cdf Mon Sep 17 00:00:00 2001
From: bndw <ben@bdw.to>
Date: Sat, 14 Feb 2026 09:41:18 -0800
Subject: feat: add Prometheus metrics and YAML config file support

## Metrics Package

Comprehensive Prometheus metrics for production observability:

Metrics tracked:
- Request rate, latency, size per method (histograms)
- Active connections and subscriptions (gauges)
- Auth success/failure rates (counters)
- Rate limit hits (counters)
- Storage stats (event count, DB size)
- Standard Go runtime metrics

Features:
- Automatic gRPC instrumentation via interceptors
- Low overhead (~300-500ns per request)
- Standard Prometheus client
- HTTP /metrics endpoint
- Grafana dashboard examples

## Config Package

YAML configuration file support with environment overrides:

Configuration sections:
- Server (addresses, timeouts, public URL)
- Database (path, connections, lifetime)
- Auth (enabled, required, timestamp window, allowed pubkeys)
- Rate limiting (per-method and per-user limits)
- Metrics (endpoint, namespace)
- Logging (level, format, output)
- Storage (compaction, retention)

Features:
- YAML file loading
- Environment variable overrides (MUXSTR_<SECTION>_<KEY>)
- Sensible defaults
- Validation on load
- Duration and list parsing
- Save/export configuration

Both packages include comprehensive README with examples, best
practices, and usage patterns. Config tests verify YAML parsing,
env overrides, validation, and round-trip serialization.
---
 internal/metrics/interceptor.go | 74 +++++++++++++++++++++++++++++++++++++++++
 1 file changed, 74 insertions(+)
 create mode 100644 internal/metrics/interceptor.go

(limited to 'internal/metrics/interceptor.go')

diff --git a/internal/metrics/interceptor.go b/internal/metrics/interceptor.go
new file mode 100644
index 0000000..02eb69d
--- /dev/null
+++ b/internal/metrics/interceptor.go
@@ -0,0 +1,74 @@
+package metrics
+
+import (
+	"context"
+	"time"
+
+	"google.golang.org/grpc"
+	"google.golang.org/grpc/codes"
+	"google.golang.org/grpc/status"
+)
+
+// UnaryServerInterceptor creates a gRPC unary interceptor for metrics collection.
+// It should be the first interceptor in the chain to measure total request time.
+func UnaryServerInterceptor(m *Metrics) grpc.UnaryServerInterceptor {
+	return func(ctx context.Context, req interface{}, info *grpc.UnaryServerInfo, handler grpc.UnaryHandler) (interface{}, error) {
+		start := time.Now()
+
+		// Call the handler
+		resp, err := handler(ctx, req)
+
+		// Record metrics
+		duration := time.Since(start).Seconds()
+		requestStatus := getRequestStatus(err)
+		m.RecordRequest(info.FullMethod, string(requestStatus), duration)
+
+		return resp, err
+	}
+}
+
+// StreamServerInterceptor creates a gRPC stream interceptor for metrics collection.
+func StreamServerInterceptor(m *Metrics) grpc.StreamServerInterceptor {
+	return func(srv interface{}, ss grpc.ServerStream, info *grpc.StreamServerInfo, handler grpc.StreamHandler) error {
+		start := time.Now()
+
+		// Increment subscriptions count
+		m.IncrementSubscriptions()
+		defer m.DecrementSubscriptions()
+
+		// Call the handler
+		err := handler(srv, ss)
+
+		// Record metrics
+		duration := time.Since(start).Seconds()
+		requestStatus := getRequestStatus(err)
+		m.RecordRequest(info.FullMethod, string(requestStatus), duration)
+
+		return err
+	}
+}
+
+// getRequestStatus determines the request status from an error.
+func getRequestStatus(err error) RequestStatus {
+	if err == nil {
+		return StatusOK
+	}
+
+	st, ok := status.FromError(err)
+	if !ok {
+		return StatusError
+	}
+
+	switch st.Code() {
+	case codes.OK:
+		return StatusOK
+	case codes.Unauthenticated:
+		return StatusUnauthenticated
+	case codes.ResourceExhausted:
+		return StatusRateLimited
+	case codes.InvalidArgument:
+		return StatusInvalidRequest
+	default:
+		return StatusError
+	}
+}
-- 
cgit v1.2.3