# Copyright Envoy AI Gateway Authors
# SPDX-License-Identifier: Apache-2.0
# The full text of the Apache license is available in the LICENSE file at
# the root of the repo.

apiVersion: gateway.networking.k8s.io/v1
kind: GatewayClass
metadata:
  name: envoy-ai-gateway-basic
spec:
  controllerName: gateway.envoyproxy.io/gatewayclass-controller
---
apiVersion: gateway.networking.k8s.io/v1
kind: Gateway
metadata:
  name: envoy-ai-gateway-basic
  namespace: default
spec:
  gatewayClassName: envoy-ai-gateway-basic
  listeners:
    - name: http
      protocol: HTTP
      port: 80
  infrastructure:
    parametersRef:
      group: gateway.envoyproxy.io
      kind: EnvoyProxy
      name: envoy-ai-gateway-basic
---
# By default, Envoy Gateway sets the buffer limit to 32kiB which is not sufficient for AI workloads.
# This ClientTrafficPolicy sets the buffer limit to 50MiB as an example.
apiVersion: gateway.envoyproxy.io/v1alpha1
kind: ClientTrafficPolicy
metadata:
  name: client-buffer-limit
  namespace: default
spec:
  targetRefs:
    - group: gateway.networking.k8s.io
      kind: Gateway
      name: envoy-ai-gateway-basic
  connection:
    bufferLimit: 50Mi
---
apiVersion: aigateway.envoyproxy.io/v1alpha1
kind: AIGatewayRoute
metadata:
  name: envoy-ai-gateway-basic
  namespace: default
spec:
  parentRefs:
    - name: envoy-ai-gateway-basic
      kind: Gateway
      group: gateway.networking.k8s.io
  rules:
    - matches:
        - headers:
            - type: Exact
              name: x-ai-eg-model
              value: some-cool-self-hosted-model
      backendRefs:
        - name: envoy-ai-gateway-basic-testupstream
---
apiVersion: aigateway.envoyproxy.io/v1alpha1
kind: AIServiceBackend
metadata:
  name: envoy-ai-gateway-basic-testupstream
  namespace: default
spec:
  schema:
    name: OpenAI
  backendRef:
    name: envoy-ai-gateway-basic-testupstream
    kind: Backend
    group: gateway.envoyproxy.io
---
apiVersion: gateway.envoyproxy.io/v1alpha1
kind: Backend
metadata:
  name: envoy-ai-gateway-basic-testupstream
  namespace: default
spec:
  endpoints:
    - fqdn:
        hostname: envoy-ai-gateway-basic-testupstream.default.svc.cluster.local
        port: 80
---
apiVersion: apps/v1
kind: Deployment
metadata:
  name: envoy-ai-gateway-basic-testupstream
  namespace: default
spec:
  replicas: 1
  selector:
    matchLabels:
      app: envoy-ai-gateway-basic-testupstream
  template:
    metadata:
      labels:
        app: envoy-ai-gateway-basic-testupstream
    spec:
      containers:
        - name: testupstream
          image: docker.io/envoyproxy/ai-gateway-testupstream:latest
          imagePullPolicy: IfNotPresent
          ports:
            - containerPort: 8080
          env:
            - name: TESTUPSTREAM_ID
              value: test
          readinessProbe:
            httpGet:
              path: /health
              port: 8080
            initialDelaySeconds: 5
            periodSeconds: 10
          livenessProbe:
            httpGet:
              path: /health
              port: 8080
            initialDelaySeconds: 10
            periodSeconds: 20
---
apiVersion: v1
kind: Service
metadata:
  name: envoy-ai-gateway-basic-testupstream
  namespace: default
spec:
  selector:
    app: envoy-ai-gateway-basic-testupstream
  ports:
    - protocol: TCP
      port: 80
      targetPort: 8080
  type: ClusterIP
---
apiVersion: gateway.envoyproxy.io/v1alpha1
kind: EnvoyProxy
metadata:
  name: envoy-ai-gateway-basic
  namespace: default
spec:
  provider:
    type: Kubernetes
    kubernetes:
      envoyDeployment:
        container:
          # Note: this is to clear the large default memory/cpu requirements for local tests.
          # In production, you should set these to values that make sense for your environment.
          resources: {}