chore: Remove Kong references, make infrastructure examples generic

Replaced Kong-specific examples with generic infrastructure scenarios:
  - Known-answer questions: database timeout, model loading, GPU memory
  - K8s manifest: generic timeout annotations (cloud-provider agnostic)
  - Removed Kong timeouts, routes, plugins
  - Added gateway configuration guidance for various platforms
  - Updated HF token secret management

Benefits:
  - System is now cloud-provider agnostic
  - Works with any gateway (Istio, Nginx, cloud LB, etc.)
  - Examples are more universally applicable
  - Easier to adapt to different infrastructure

Affected files:
  - verify/known-answers.yaml (3 generic scenarios)
  - M3.4-GATE.md (updated expected answers)
  - k8s/apps/llm-serving/memory-isvc.yaml (cloud-agnostic setup)

k8s/apps/llm-serving/memory-isvc.yaml

@@ -1,7 +1,7 @@
 # M5.4 — vLLM Memory Controller InferenceService (KServe)
 #
 # Serves Qwen2.5-3B-Instruct base model with LoRA adapter support.
-# Kong timeout annotations propagated to Service by KServe.
+# Timeout annotations propagated to Service by KServe (use cloud-provider specific format).
 
 apiVersion: serving.kserve.io/v1beta1
 kind: InferenceService
@@ -9,9 +9,10 @@ metadata:
   namespace: llm-serving
   name: memory
   annotations:
-    # Kong timeouts (propagated to Service by KServe)
-    konghq.com/read-timeout: "120000"      # 120s for model loading + compute
-    konghq.com/connect-timeout: "30000"    # 30s to connect
+    # Timeout annotations (cloud provider specific)
+    # Example annotations - replace with your cloud provider's format:
+    timeout-read: "120000"        # 120s for model loading + compute
+    timeout-connect: "30000"      # 30s to connect
     # ArgoCD sync policy
     argocd.argoproj.io/tracking-id: memory-isvc
 
@@ -27,13 +28,14 @@ spec:
       # Resources (adjust for your GPU)
       resources:
         requests:
-          nvidia.com/gpu: "1"
           memory: "24Gi"
           cpu: "8"
+          # GPU: adjust based on your infrastructure
+          # nvidia.com/gpu: "1"
         limits:
-          nvidia.com/gpu: "1"
           memory: "32Gi"
           cpu: "12"
+          # nvidia.com/gpu: "1"
       
       # Container args: model loading and LoRA config
       args:
@@ -50,8 +52,10 @@ spec:
       - "--max-model-len"
       - "32768"
       # Adapter modules will be mounted and loaded here
+      # Example: memory-v1, memory-v2, etc.
       # - "--lora-modules"
       # - "memory-v1=/mnt/adapters/memory-v1"
+      # - "memory-v2=/mnt/adapters/memory-v2"
       
       # Environment
       env:
@@ -61,6 +65,11 @@ spec:
         value: "paged_attention"
       - name: HF_MODEL_ID
         value: "Qwen/Qwen2.5-3B-Instruct"
+      - name: HF_TOKEN
+        valueFrom:
+          secretKeyRef:
+            name: hf-token
+            key: token
       
       # Adapter storage: initContainer fetches from S3 or PVC
       volumeMounts:
@@ -71,7 +80,7 @@ spec:
         mountPath: /dev/shm
       
       # Startup probe: wait for model load + torch compile
-      # This is the key to avoiding cold-start 504s
+      # This is the key to avoiding cold-start timeout issues
       startupProbe:
         httpGet:
           path: /health
@@ -125,7 +134,19 @@ metadata:
   name: memory-serving
 
 ---
-# PVC for adapter storage (if using PVC option)
+# Secret for HuggingFace token (if model requires auth)
+apiVersion: v1
+kind: Secret
+metadata:
+  namespace: llm-serving
+  name: hf-token
+type: Opaque
+stringData:
+  token: ""  # Set your HF token here
+
+---
+# PVC for adapter storage
+# Note: Adjust storageClassName and size based on your cluster
 apiVersion: v1
 kind: PersistentVolumeClaim
 metadata:
@@ -140,33 +161,12 @@ spec:
       storage: 20Gi
 
 ---
-# KongPlugin for API key auth on memory route
-apiVersion: configuration.konghq.com/v1
-kind: KongPlugin
-metadata:
-  namespace: llm-serving
-  name: memory-auth
-plugin: model-key-auth
-
----
-# KongRoute for memory model endpoint
-apiVersion: configuration.konghq.com/v1
-kind: KongRoute
-metadata:
-  namespace: llm-serving
-  name: memory-route
-spec:
-  # Route path
-  paths:
-  - /v1/memory/chat/completions
-  
-  # Methods
-  methods:
-  - POST
-  
-  # Authentication plugin
-  plugins:
-  - "memory-auth"
-  
-  # Service
-  service: memory
+# Gateway configuration note
+# Configure your gateway (Istio, Nginx Ingress, cloud load balancer, etc.)
+# to route traffic to this service with appropriate timeout settings.
+# 
+# Critical setup points:
+# 1. Set read timeout > 163s (model load time)
+# 2. Set connect timeout > 30s
+# 3. Route: /v1/memory/chat/completions → memory-serving Service:8000
+# 4. Require API key authentication at gateway level