From 86381d705974f8145711d81e46e11f8041d9ca38 Mon Sep 17 00:00:00 2001
From: Niek Otten <not@respellion.nl>
Date: Mon, 28 Sep 2026 14:31:48 +0200
Subject: [PATCH] feat(k8s): make the OTLP trace endpoint a chart value (refs
 #186)

otelEndpoint defaults to the chart's own tempo; deploy overrides it from the
OTEL_ENDPOINT repo variable, so the labs cluster can ship traces to the
monitoring stack's Tempo instead of failing every export.

Co-Authored-By: Claude Opus 5.5 (1M context) <noreply@anthropic.com>
---
 .gitea/workflows/deploy.yaml         |  5 ++++-
 infra/helm/big-reference/values.yaml | 13 ++++++++++---
 2 files changed, 14 insertions(+), 4 deletions(-)

diff --git a/.gitea/workflows/deploy.yaml b/.gitea/workflows/deploy.yaml
index 5c53711..6db3231 100644
--- a/.gitea/workflows/deploy.yaml
+++ b/.gitea/workflows/deploy.yaml
@@ -34,6 +34,9 @@ jobs:
       # `true` fills in the medewerker OTP step for the public demo (chart value
       # demo.otpAutofill). The fixture secret is committed: demo only.
       OTP_AUTOFILL: ${{ vars.OTP_AUTOFILL }}
+      # Tempo for the services' traces, e.g. http://tempo.monitoring.svc:4317 (the
+      # cluster monitoring stack, Infra repo). Empty = the chart default.
+      OTEL_ENDPOINT: ${{ vars.OTEL_ENDPOINT }}
     steps:
       - uses: https://github.com/actions/checkout@v4
 
@@ -100,7 +103,7 @@ jobs:
           make k8s-reseed \
             TALOS_HOST=${TALOS_HOST:-localhost} \
             K8S_REGISTRY=${TALOS_VM_IP:-192.168.122.173}:30500 \
-            K8S_SET="${KEYCLOAK_URL:+--set keycloakUrl=$KEYCLOAK_URL} --set demo.otpAutofill=${OTP_AUTOFILL:-false}"
+            K8S_SET="${KEYCLOAK_URL:+--set keycloakUrl=$KEYCLOAK_URL} --set demo.otpAutofill=${OTP_AUTOFILL:-false}${OTEL_ENDPOINT:+ --set otelEndpoint=$OTEL_ENDPOINT}"
 
       # `dev` is a mutable tag and helm sees an unchanged pod template, so the
       # new images only land on a restart (pullPolicy is already Always).
diff --git a/infra/helm/big-reference/values.yaml b/infra/helm/big-reference/values.yaml
index 2ef6cda..a3b057b 100644
--- a/infra/helm/big-reference/values.yaml
+++ b/infra/helm/big-reference/values.yaml
@@ -30,6 +30,12 @@ host: 192.168.122.100
 # portals' authority (runbook, "Publishing through the labs Caddy").
 keycloakUrl: ""
 
+# Where the .NET services send traces (OTLP gRPC). The default is the chart's own
+# `tempo` workload (off by default, like compose). Point it at a Tempo outside the
+# release, e.g. the cluster monitoring stack's http://tempo.monitoring.svc:4317 —
+# with no Tempo at all, every export fails and is counted as a .NET exception.
+otelEndpoint: http://tempo:4317
+
 demo:
   # Fill in and submit the medewerker OTP step from the fixture secret, so a public
   # demo shows MFA enforced without an authenticator: makes the big-demo theme
@@ -160,10 +166,11 @@ envGroups:
     NOTIFICATIONS_DISABLED: "false"
     RUN_SETUP_CONFIG: "true"
 
-  # Traces for the .NET services. Always set, like compose: the exporter fails
-  # harmlessly when Tempo is absent (services/*/Program.cs).
+  # Traces for the .NET services. Always set, like compose. With no Tempo behind
+  # `otelEndpoint` the exporter fails quietly but throws on every batch, which
+  # shows up as HttpRequestException/SocketException in dotnet_exceptions_total.
   otel:
-    OTEL_EXPORTER_OTLP_ENDPOINT: http://tempo:4317
+    OTEL_EXPORTER_OTLP_ENDPOINT: '{{ .Values.otelEndpoint }}'
     OTEL_EXPORTER_OTLP_PROTOCOL: grpc
 
 # ── Workloads ──────────────────────────────────────────────────────────────────
-- 
2.54.0