adr/0023-config-hot-reloading.md

@@ -1,6 +1,6 @@
 # Config Hot Reloading Strategy
 
-**Status:** Phase 1+2 Implemented (2026-05-05 — `logging.level` and `auth.jwt.ttl` hot-reloadable via `Config.WatchAndApply` in `pkg/config/config.go`, wired in `pkg/server/server.go Run`. Phase 2 also fixed a pre-existing bug where the hardcoded 24h TTL ignored `auth.jwt.ttl` from config entirely.) Phase 3 sub-phase 3.1 Implemented (2026-05-05 — `ReconfigureTracerProvider` in `pkg/telemetry/telemetry.go` added). Phase 3 sub-phase 3.2 In Flight (2026-05-05 — `telemetry.sampler.type` + `telemetry.sampler.ratio` hot-reload via `SetSamplerReconfigureCallback` in `pkg/config/config.go`. Remaining field: `api.v2_enabled`.)
+**Status:** Phase 1+2+3 Implemented (2026-05-05). Hot-reloadable fields: `logging.level`, `auth.jwt.ttl`, `telemetry.sampler.type`, `telemetry.sampler.ratio`. Plumbing: `Config.WatchAndApply` in `pkg/config/config.go`, `ReconfigureTracerProvider` in `pkg/telemetry/telemetry.go`, sampler reconfigure callback wired in `pkg/server/server.go Run`. Phase 2 also fixed a pre-existing bug where the hardcoded 24h TTL ignored `auth.jwt.ttl` from config. Remaining field `api.v2_enabled` is **deferred**: hot-reloading routing requires either an always-register-with-middleware-gate refactor of the chi router or an atomic router swap — different complexity class, separate ADR if reopened.
 **Authors:** Gabriel Radureau, AI Agent
 **Date:** 2026-04-05
 **Last Updated:** 2026-05-05

pkg/server/server.go

@@ -679,10 +679,11 @@ func (s *Server) Router() http.Handler {
 func (s *Server) Run() error {
 	// Initialize OpenTelemetry if enabled
 	var err error
+	var telemetrySetup *telemetry.Setup
 	if s.withOTEL {
 		log.Trace().Msg("Initializing OpenTelemetry tracing")
 
-		telemetrySetup := &telemetry.Setup{
+		telemetrySetup = &telemetry.Setup{
 			ServiceName:  s.config.GetServiceName(),
 			OTLPEndpoint: s.config.GetOTLPEndpoint(),
 			Insecure:     s.config.GetTelemetryInsecure(),
@@ -694,6 +695,7 @@ func (s *Server) Run() error {
 		if s.tracerProvider, err = telemetrySetup.InitializeTracing(context.Background()); err != nil {
 			log.Error().Err(err).Msg("Failed to initialize OpenTelemetry, continuing without tracing")
 			s.withOTEL = false
+			telemetrySetup = nil
 		} else {
 			log.Trace().Msg("OpenTelemetry tracing initialized successfully")
 		}
@@ -714,7 +716,27 @@ func (s *Server) Run() error {
 		s.userService.StartJWTSecretCleanupLoop(rootCtx, s.config.GetJWTSecretCleanupInterval())
 	}
 
-	// Start config hot-reload watcher (ADR-0023 Phase 1: logging.level only).
+	// Wire the sampler hot-reload callback (ADR-0023 Phase 3, sub-phase 3.3).
+	// telemetrySetup is non-nil only when telemetry was successfully initialized
+	// at startup — hot-reloading telemetry-on is out of scope (see ADR-0023).
+	// The callback updates the SamplerType/Ratio on the captured Setup, then
+	// rebuilds the global tracer provider via ReconfigureTracerProvider.
+	if telemetrySetup != nil {
+		s.config.SetSamplerReconfigureCallback(func(ctx context.Context, samplerType string, samplerRatio float64) error {
+			telemetrySetup.SamplerType = samplerType
+			telemetrySetup.SamplerRatio = samplerRatio
+			newTP, rerr := telemetrySetup.ReconfigureTracerProvider(ctx, s.tracerProvider)
+			if rerr != nil {
+				return rerr
+			}
+			if newTP != nil {
+				s.tracerProvider = newTP
+			}
+			return nil
+		})
+	}
+
+	// Start config hot-reload watcher (ADR-0023 Phase 1+2+3).
 	// Stops automatically on rootCtx cancellation.
 	s.config.WatchAndApply(rootCtx)