Docs: Removes Agentgateway Docs (#1771)

Signed-off-by: Daneyon Hansen <[email protected]>

Author: danehans

config/manifests/gateway/agentgateway/gateway.yaml

@@ -3,7 +3,7 @@ kind: Gateway
 metadata:
   name: inference-gateway
 spec:
-  gatewayClassName: kgateway
+  gatewayClassName: agentgateway
   listeners:
   - name: http
     port: 80

config/manifests/gateway/agentgateway/httproute.yaml

@@ -7,11 +7,11 @@ This guide provides the steps for running Gateway conformance tests against [kga
 
 | Extension Version Tested | Profile Tested | Implementation Version | Mode    | Report                                                                     |
 |--------------------------|----------------|------------------------|---------|----------------------------------------------------------------------------|
-| v1.0.0                   | Gateway        | v2.1.0-main            | default | [v2.1.0-main report](./inference-v2.1.0-main-report.yaml)   |
+| v1.0.2                   | Gateway        | v2.1.1                 | default | [v2.1.1 report](./inference-v2.1.1-report.yaml)                            |
 
 ## Reproduce
 
-This is a mirror of the kgateway [conformance test] with the default (Envoy) data plane [conformance test](../README.md).
+This is a mirror of the kgateway [inference conformance GHA workflow](https://github.com/kgateway-dev/kgateway/blob/v2.0.x/.github/actions/kube-inference-extension-conformance-tests/action.yaml).
 
 ### Prerequisites
 
@@ -26,7 +26,7 @@ In order to run the conformance tests, the following prerequisites must be met:
 
    ```sh
    # The kgateway version
-   export VERSION=v2.1.0-main
+   export VERSION=v2.1.1
    # Skip building and loading the kgateway images
    export SKIP_DOCKER=true
    # Install Gateway API and Inference Extension CRDs
@@ -42,7 +42,7 @@ In order to run the conformance tests, the following prerequisites must be met:
 3. Create a KinD cluster:
 
    ```sh
-   make kind-setup
+   make setup-base
    ```
 
 4. Install the kgateway CRDs:
@@ -57,7 +57,7 @@ In order to run the conformance tests, the following prerequisites must be met:
    ```sh
    helm upgrade -i --namespace kgateway-system --version $VERSION \
    kgateway oci://cr.kgateway.dev/kgateway-dev/charts/kgateway \
-   --set inferenceExtension.enabled=true --set agentGateway.enabled=true
+   --set inferenceExtension.enabled=true --set agentgateway.enabled=true
    ```
 
 6. Wait for the kgateway rollout to complete:

config/manifests/gateway/kgateway/gateway.yaml

@@ -1,15 +1,15 @@
-GatewayAPIInferenceExtensionVersion: v1.0.0
+GatewayAPIInferenceExtensionVersion: v1.0.2
 apiVersion: gateway.networking.k8s.io/v1
-date: "2025-09-14T10:03:01-07:01"
+date: "2025-10-27T13:11:40-07:00"
 gatewayAPIChannel: experimental
-gatewayAPIVersion: v1.3.0
+gatewayAPIVersion: v1.4.0
 implementation:
   contact:
   - github.com/kgateway-dev/kgateway/issues/new/choose
   organization: kgateway-dev
   project: kgateway
   url: github.com/kgateway-dev/kgateway
-  version: v2.1.0-main
+  version: v2.1.1
 kind: ConformanceReport
 mode: default
 profiles:

conformance/reports/v1.0.0/gateway/kgateway/README.md

@@ -30,14 +30,3 @@
       --version $IGW_CHART_VERSION \
       oci://us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/charts/inferencepool
       ```
-
-=== "Agentgateway"
-
-      ```bash
-      export GATEWAY_PROVIDER=none
-      helm install vllm-llama3-8b-instruct \
-      --set inferencePool.modelServers.matchLabels.app=vllm-llama3-8b-instruct \
-      --set provider.name=$GATEWAY_PROVIDER \
-      --version $IGW_CHART_VERSION \
-      oci://us-central1-docker.pkg.dev/k8s-staging-images/gateway-api-inference-extension/charts/inferencepool
-      ```

conformance/reports/v1.0.0/gateway/kgateway/inference-v2.1.0-main-report.yaml

@@ -30,14 +30,3 @@
       --version $IGW_CHART_VERSION \
       oci://registry.k8s.io/gateway-api-inference-extension/charts/inferencepool
       ```
-
-=== "Agentgateway"
-
-      ```bash
-      export GATEWAY_PROVIDER=none
-      helm install vllm-llama3-8b-instruct \
-      --set inferencePool.modelServers.matchLabels.app=vllm-llama3-8b-instruct \
-      --set provider.name=$GATEWAY_PROVIDER \
-      --version $IGW_CHART_VERSION \
-      oci://registry.k8s.io/gateway-api-inference-extension/charts/inferencepool
-      ```

conformance/reports/v1.0.0/gateway/kgateway/agentgateway/README.md renamed to conformance/reports/v1.0.2/gateway/kgateway/README.md

@@ -149,7 +149,8 @@ kubectl apply -k https://github.com/kubernetes-sigs/gateway-api-inference-extens
 
       [Kgateway](https://kgateway.dev/) is a Gateway API and Inference Gateway
       [conformant](https://github.com/kubernetes-sigs/gateway-api-inference-extension/tree/main/conformance/reports/v1.0.0/gateway/kgateway)
-      gateway. Follow these steps to run Kgateway:
+      implementation. Kgateway supports Inference Gateway with the [agentgateway](https://agentgateway.dev/) data plane. Follow these steps
+      to run Kgateway as an Inference Gateway:
 
       1. Requirements
 
@@ -177,9 +178,7 @@ kubectl apply -k https://github.com/kubernetes-sigs/gateway-api-inference-extens
 
          Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
          ```bash
-         $ kubectl get gateway inference-gateway
-         NAME                CLASS               ADDRESS         PROGRAMMED   AGE
-         inference-gateway   kgateway            <MY_ADDRESS>    True         22s
+         kubectl get gateway inference-gateway
          ```
 
       5. Deploy the HTTPRoute
@@ -194,55 +193,6 @@ kubectl apply -k https://github.com/kubernetes-sigs/gateway-api-inference-extens
          kubectl get httproute llm-route -o yaml
          ```
 
-=== "Agentgateway"
-
-      [Agentgateway](https://agentgateway.dev/) is a purpose-built proxy designed for AI workloads, and comes with native support for Inference Gateway.
-      Agentgateway integrates with [Kgateway](https://kgateway.dev/) as it's control plane. Follow these steps to run Kgateway with the agentgateway
-      data plane:
-
-      1. Requirements
-
-         - [Helm](https://helm.sh/docs/intro/install/) installed.
-         - Gateway API [CRDs](https://gateway-api.sigs.k8s.io/guides/#installing-gateway-api) installed.
-
-      2. Set the Kgateway version and install the Kgateway CRDs.
-
-         ```bash
-         KGTW_VERSION=v2.2.0-main
-         helm upgrade -i --create-namespace --namespace kgateway-system --version $KGTW_VERSION kgateway-crds oci://cr.kgateway.dev/kgateway-dev/charts/kgateway-crds
-         ```
-
-      3. Install Kgateway
-
-         ```bash
-         helm upgrade -i --namespace kgateway-system --version $KGTW_VERSION kgateway oci://cr.kgateway.dev/kgateway-dev/charts/kgateway --set inferenceExtension.enabled=true --set agentgateway.enabled=true
-         ```
-
-      4. Deploy the Gateway
-
-         ```bash
-         kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/agentgateway/gateway.yaml
-         ```
-
-         Confirm that the Gateway was assigned an IP address and reports a `Programmed=True` status:
-         ```bash
-         $ kubectl get gateway inference-gateway
-         NAME                CLASS               ADDRESS         PROGRAMMED   AGE
-         inference-gateway   agentgateway        <MY_ADDRESS>    True         22s
-         ```
-
-      5. Deploy the HTTPRoute
-
-         ```bash
-         kubectl apply -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/agentgateway/httproute.yaml
-         ```
-
-      6. Confirm that the HTTPRoute status conditions include `Accepted=True` and `ResolvedRefs=True`:
-
-         ```bash
-         kubectl get httproute llm-route -o yaml
-         ```
-
 ### Deploy InferenceObjective (Optional)
 
 Deploy the sample InferenceObjective which allows you to specify priority of requests.
@@ -335,30 +285,3 @@ Deploy the sample InferenceObjective which allows you to specify priority of req
          ```bash
          kubectl delete ns kgateway-system
          ```
-
-=== "Agentgateway"
-
-      ```bash
-      kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/agentgateway/gateway.yaml --ignore-not-found
-      kubectl delete -f https://github.com/kubernetes-sigs/gateway-api-inference-extension/raw/main/config/manifests/gateway/agentgateway/httproute.yaml --ignore-not-found
-      ```
-
-      The following steps assume you would like to cleanup ALL Kgateway resources that were created in this quickstart guide.
-
-      1. Uninstall Kgateway
-
-         ```bash
-         helm uninstall kgateway -n kgateway-system
-         ```
-
-      2. Uninstall the Kgateway CRDs.
-
-         ```bash
-         helm uninstall kgateway-crds -n kgateway-system
-         ```
-
-      3. Remove the Kgateway namespace.
-
-         ```bash
-         kubectl delete ns kgateway-system
-         ```