diff --git a/kong/observability.yaml b/kong/observability.yaml
index b213c10..46a3ac2 100644
--- a/kong/observability.yaml
+++ b/kong/observability.yaml
@@ -6,6 +6,12 @@
 # defines its own AI-specific versions of. Applying it here would duplicate
 # them, so the three observability plugins are declared locally instead,
 # with the same configuration as the shared template.
+#
+# That parity is manual and has already broken once: the propagation block
+# below was added to the shared template and not here, so this gateway kept
+# starting a fresh trace per request while the five domains propagated
+# correctly. Any change to the shared template's observability plugins has to
+# be mirrored here by hand.
 apiVersion: configuration.konghq.com/v1
 kind: KongPlugin
 metadata:
@@ -30,6 +36,23 @@ config:
     service.name: ${NAME}
   sampling_rate: 1
   http_response_header_for_traceid: X-Trace-Id
+  # Without this block every hop starts its own trace: a single end-to-end
+  # transaction shows up in Tempo as a dozen unrelated traces, one per service.
+  # `extract` is what makes the gateway continue the caller's trace instead of
+  # opening a new one, and `inject` is what carries it to the upstream so the
+  # backend can continue it in turn.
+  #
+  # This gateway is where LibreChat enters, so without it the chain breaks at
+  # the very first hop and nothing downstream can be correlated.
+  propagation:
+    extract:
+      - w3c
+      - b3
+      - jaeger
+    inject:
+      - w3c
+    default_format: w3c
+    clear: []
 ---
 apiVersion: configuration.konghq.com/v1
 kind: KongPlugin