From ea4f7fd0d43494c150b282a37a7ff62ad1b77964 Mon Sep 17 00:00:00 2001
From: Pratik Mankawde <3397372+pratikmankawde@users.noreply.github.com>
Date: Wed, 9 Sep 2026 15:11:25 +0100
Subject: [PATCH] fix(telemetry): restore health_check and batch the metrics
 pipeline

The health_check extension was present on the previous branch and dropped
here with no replacement, while this branch's own TESTING.md still polls
http://localhost:13133/ to decide the collector is ready. That check has had
no listener since, so the documented readiness step cannot pass.

Also add batch to the metrics pipeline. Without it the OTLP metric path
exports one request per instrument; the added delay is bounded by the batch
timeout, well under the Prometheus scrape interval.

Both belong here rather than downstream: this branch owns the metrics
pipeline and is the one that regressed the extension.
---
 docker/telemetry/otel-collector-config.yaml | 10 +++++++++-
 1 file changed, 9 insertions(+), 1 deletion(-)

diff --git a/docker/telemetry/otel-collector-config.yaml b/docker/telemetry/otel-collector-config.yaml
index 5f23e3c932..e3429c676a 100644
--- a/docker/telemetry/otel-collector-config.yaml
+++ b/docker/telemetry/otel-collector-config.yaml
@@ -121,7 +121,12 @@ exporters:
     resource_to_telemetry_conversion:
       enabled: true
 
+extensions:
+  health_check:
+    endpoint: 0.0.0.0:13133
+
 service:
+  extensions: [health_check]
   pipelines:
     traces:
       receivers: [otlp]
@@ -129,5 +134,8 @@ service:
       exporters: [debug, otlp/tempo, spanmetrics]
     metrics:
       receivers: [otlp, spanmetrics]
-      processors: [resource/tier, resource/stripsdk]
+      # batch keeps the OTLP metric path from exporting one request per
+      # instrument. It delays a sample by at most the batch timeout, which
+      # is well under the Prometheus scrape interval.
+      processors: [resource/tier, resource/stripsdk, batch]
       exporters: [prometheus]