VS Code Continue

Configure Continue, the open-source AI code assistant for VS Code, to use agentgateway deployed in Kubernetes.

Before you begin

1. Set up an agentgateway proxy.
2. Set up access to the OpenAI LLM provider.

Get the gateway URL

export INGRESS_GW_ADDRESS=$(kubectl get svc -n agentgateway-system agentgateway-proxy \
  -o jsonpath='{.status.loadBalancer.ingress[0].ip}')

echo "Gateway address: $INGRESS_GW_ADDRESS"

export INGRESS_GW_ADDRESS=$(kubectl get svc -n agentgateway-system agentgateway-proxy \
  -o jsonpath='{.status.loadBalancer.ingress[0].hostname}')

echo "Gateway address: $INGRESS_GW_ADDRESS"

kubectl port-forward -n agentgateway-system svc/agentgateway-proxy 8080:80

Configure Continue

1. Edit the ~/.continue/config.json file to add your agentgateway endpoint.
2. Replace <INGRESS_GW_ADDRESS> and <route-path> with your gateway address and the path from your HTTPRoute configuration.

{
  "models": [
    {
      "title": "agentgateway (Kubernetes)",
      "provider": "openai",
      "model": "gpt-4o-mini",
      "apiBase": "http://<INGRESS_GW_ADDRESS>/<route-path>",
      "apiKey": "anything"
    }
  ]
}

Review the following table to understand this configuration.

Verify the connection

1. Open the Continue sidebar in VS Code (Cmd + M on macOS, Ctrl + M on Windows/Linux).
2. Select agentgateway (Kubernetes) from the model dropdown.
3. Send a test message to confirm the connection.