From 45a992f5a8be266c7c0ccfbe728fac9867af2297 Mon Sep 17 00:00:00 2001
From: Marcel <marcel@familienarchiv>
Date: Sat, 16 May 2026 15:18:13 +0200
Subject: [PATCH] fix(obs): fix OTLP transport port and add application metrics
 tag

- Change OTEL default endpoint from port 4317 (gRPC) to 4318 (HTTP) to
  match Spring Boot's HttpExporter; sending HTTP/1.1 to a gRPC listener
  caused "Connection reset" errors
- Add otel.logs.exporter=none: Promtail captures Docker logs via the
  logging driver; sending logs to Tempo's OTLP endpoint (which only
  handles traces) produced 404 errors
- Add management.metrics.tags.application to every metric so Grafana's
  Spring Boot Observability dashboard (ID 17175) can filter by the
  application label_values() template variable
- Add MANAGEMENT_METRICS_TAGS_APPLICATION and OTEL_LOGS_EXPORTER env
  vars to docker-compose.prod.yml; production Tempo endpoint already
  uses 4318
- Add MANAGEMENT_TRACING_SAMPLING_PROBABILITY to prod compose with
  0.1 default to avoid 100% trace sampling in production

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
---
 backend/src/main/resources/application.yaml | 12 ++++++++++--
 docker-compose.prod.yml                     |  5 ++++-
 2 files changed, 14 insertions(+), 3 deletions(-)

diff --git a/backend/src/main/resources/application.yaml b/backend/src/main/resources/application.yaml
index 5f4fb207..1d502776 100644
--- a/backend/src/main/resources/application.yaml
+++ b/backend/src/main/resources/application.yaml
@@ -64,6 +64,11 @@ management:
     metrics:
       export:
         enabled: true
+  metrics:
+    tags:
+      # Common tag applied to every metric so Grafana's Spring Boot dashboard can filter by application name.
+      # Override via MANAGEMENT_METRICS_TAGS_APPLICATION env var.
+      application: ${spring.application.name}
   health:
     mail:
       enabled: false
@@ -72,13 +77,16 @@ management:
       probability: 1.0   # 100% in dev; override via MANAGEMENT_TRACING_SAMPLING_PROBABILITY in prod compose
 
 # OpenTelemetry trace export — failures are non-fatal (app starts cleanly without Tempo running)
-# The default http://localhost:4317 ensures CI compatibility when no observability stack is present.
+# Port 4318 = OTLP HTTP (the default transport for Spring Boot's HttpExporter).
+# Port 4317 is gRPC-only; sending HTTP/1.1 to it produces "Connection reset".
 otel:
   service:
     name: familienarchiv-backend
   exporter:
     otlp:
-      endpoint: ${OTEL_EXPORTER_OTLP_ENDPOINT:http://localhost:4317}
+      endpoint: ${OTEL_EXPORTER_OTLP_ENDPOINT:http://localhost:4318}
+  logs:
+    exporter: none   # Promtail captures Docker logs; disable OTLP log export to Tempo (which doesn't accept logs)
 
 springdoc:
   api-docs:
diff --git a/docker-compose.prod.yml b/docker-compose.prod.yml
index 28730f7e..ff8db357 100644
--- a/docker-compose.prod.yml
+++ b/docker-compose.prod.yml
@@ -213,7 +213,10 @@ services:
       APP_MAIL_FROM: ${APP_MAIL_FROM:-noreply@raddatz.cloud}
       SPRING_MAIL_PROPERTIES_MAIL_SMTP_AUTH: ${MAIL_SMTP_AUTH:-true}
       SPRING_MAIL_PROPERTIES_MAIL_SMTP_STARTTLS_ENABLE: ${MAIL_STARTTLS_ENABLE:-true}
-      OTEL_EXPORTER_OTLP_ENDPOINT: http://tempo:4317
+      OTEL_EXPORTER_OTLP_ENDPOINT: http://tempo:4318
+      OTEL_LOGS_EXPORTER: none
+      MANAGEMENT_METRICS_TAGS_APPLICATION: Familienarchiv
+      MANAGEMENT_TRACING_SAMPLING_PROBABILITY: ${MANAGEMENT_TRACING_SAMPLING_PROBABILITY:-0.1}
     networks:
       - archiv-net
     healthcheck: