manifest modifications to enable duplex streaming

Author: kfswain

config/manifests/gateway/enable_patch_policy.yaml

@@ -19,9 +19,9 @@ data:
     extensionApis:
       enableEnvoyPatchPolicy: true      
       enableBackend: true
-#    admin:
-#      enablePprof: true
-#      address:
-#        host: 127.0.0.1
-#        port: 19000
-#      enabledDumpConfig: true
+    admin:
+      enablePprof: true
+      address:
+        host: 127.0.0.1
+        port: 19000
+      enabledDumpConfig: true

config/manifests/gateway/extension_policy.yaml

@@ -11,6 +11,7 @@ spec:
         name: inference-gateway-ext-proc
         port: 9002
       processingMode:
+        allowModeOverride: true
         request:
           body: Buffered
         response:

config/manifests/gateway/patch_policy.yaml

@@ -48,10 +48,22 @@ spec:
           typed_config:
             "@type": "type.googleapis.com/envoy.extensions.transport_sockets.tls.v3.UpstreamTlsContext"
             common_tls_context: {}
-
     - type: "type.googleapis.com/envoy.config.route.v3.RouteConfiguration"
       name: default/inference-gateway/llm-gw
       operation:
         op: replace
         path: "/virtual_hosts/0/routes/0/route/cluster"
         value: original_destination_cluster
+    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+    #   name: "default/inference-gateway/llm-gw"
+    #   operation:
+    #     op: add
+    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_body_mode"
+    #     #value: FULL_DUPLEX_STREAMED
+    #     value: BUFFERED
+    # - type: "type.googleapis.com/envoy.config.listener.v3.Listener"
+    #   name: "default/inference-gateway/llm-gw"
+    #   operation:
+    #     op: add
+    #     path: "/default_filter_chain/filters/0/typed_config/http_filters/0/typed_config/processing_mode/request_trailer_mode"
+    #     value: SEND