using Envoy to transport traces, not calling OTEL directly

arch/envoy.template.yaml

@@ -469,6 +469,48 @@ static_resources:
                     typed_config:
                       "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
 
+    - name: otel_collector_proxy
+      address:
+        socket_address:
+          address: 0.0.0.0
+          port_value: 9903
+      traffic_direction: OUTBOUND
+      filter_chains:
+        - filters:
+            - name: envoy.filters.network.http_connection_manager
+              typed_config:
+                "@type": type.googleapis.com/envoy.extensions.filters.network.http_connection_manager.v3.HttpConnectionManager
+                stat_prefix: otel_proxy
+                codec_type: AUTO
+                access_log:
+                - name: envoy.access_loggers.file
+                  typed_config:
+                    "@type": type.googleapis.com/envoy.extensions.access_loggers.file.v3.FileAccessLog
+                    path: "/var/log/access_otel.log"
+                    format: |
+                     [%START_TIME%] "%REQ(:METHOD)% %REQ(X-ENVOY-ORIGINAL-PATH?:PATH)% %PROTOCOL%" %RESPONSE_CODE% %RESPONSE_FLAGS% %BYTES_RECEIVED% %BYTES_SENT% %DURATION% %RESP(X-ENVOY-UPSTREAM-SERVICE-TIME)% "%REQ(X-FORWARDED-FOR)%" "%REQ(USER-AGENT)%" "%REQ(X-REQUEST-ID)%" "%REQ(:AUTHORITY)%" "%UPSTREAM_HOST%" "%UPSTREAM_CLUSTER%"
+                route_config:
+                  name: otel_route
+                  virtual_hosts:
+                    - name: otel_backend
+                      domains: ["*"]
+                      routes:
+                        - match:
+                            prefix: "/v1/traces"
+                          route:
+                            cluster: otel_collector_http_proxy
+                            timeout: 5s
+                            retry_policy:
+                              retry_on: "5xx,connect-failure,refused-stream,reset"
+                              num_retries: 3
+                              per_try_timeout: 2s
+                              host_selection_retry_max_attempts: 5
+                              retriable_status_codes: [500, 502, 503, 504]
+                http_filters:
+                  - name: envoy.filters.http.router
+                    typed_config:
+                      "@type": type.googleapis.com/envoy.extensions.filters.http.router.v3.Router
+
     - name: egress_traffic_llm
       address:
         socket_address:
@@ -1033,4 +1075,34 @@ static_resources:
                 socket_address:
                   address: host.docker.internal
                   port_value: 4318
+    # Cluster for OTEL HTTP proxy with retry/circuit breaking
+    - name: otel_collector_http_proxy
+      connect_timeout: 2s
+      type: STRICT_DNS
+      dns_lookup_family: V4_ONLY
+      lb_policy: ROUND_ROBIN
+      load_assignment:
+        cluster_name: otel_collector_http_proxy
+        endpoints:
+          - lb_endpoints:
+              - endpoint:
+                  address:
+                    socket_address:
+                      address: host.docker.internal
+                      port_value: 4318
+      # Circuit breaker configuration to prevent overwhelming OTEL collector
+      circuit_breakers:
+        thresholds:
+          - priority: DEFAULT
+            max_connections: 100
+            max_pending_requests: 100
+            max_requests: 100
+            max_retries: 3
+      # Health checking and outlier detection
+      outlier_detection:
+        consecutive_5xx: 5
+        interval: 10s
+        base_ejection_time: 30s
+        max_ejection_percent: 50
+        enforcing_consecutive_5xx: 100
 {% endif %}