Skip to content
Closed
Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
38 commits
Select commit Hold shift + click to select a range
e4374de
EAI-5821: Add Envoy AI Gateway v0.6.0 sources and enable in all profiles
johnl-amd May 11, 2026
f36a845
EAI-5821: Fix ai-gateway Helm ClusterRole template
johnl-amd May 12, 2026
67e9c45
EAI-5821: Add aim-gateway chart and v0.6.0 bug fix patches
johnl-amd May 12, 2026
5c8b1a7
EAI-5821: Add POC notes and GitOps TODOs for Envoy AI Gateway
johnl-amd May 12, 2026
5933e0c
EAI-5821: Wire aim-gateway as ArgoCD app, make backends configurable
johnl-amd May 13, 2026
506056a
EAI-5821: Remove TLSRoute for k8s API passthrough
johnl-amd May 13, 2026
9c468bb
Add inference token metrics: Envoy access log fields + OTel collector
johnl-amd May 13, 2026
8814f05
Configure Envoy Gateway extensionManager for AI Gateway
johnl-amd May 13, 2026
853c45b
fix: use correct dynamic metadata namespace for AI Gateway token fields
johnl-amd May 13, 2026
9bd2cf1
feat: wire AI Gateway ext_proc for access log token fields
johnl-amd May 13, 2026
3ee0246
feat: scrape AI Gateway metrics from port 1064 via existing collector
johnl-amd May 14, 2026
060972c
fix: use named port aigw-admin for AI Gateway extproc scrape
johnl-amd May 15, 2026
2d80997
feat(aim-gateway): add SecurityPolicy API key auth for inference routes
johnl-amd May 15, 2026
143b1d9
feat(aim-gateway): add api_key_id + aim_service_id metric labels and …
johnl-amd May 15, 2026
008e547
aim-gateway: gate global quota bucket and add secret bootstrap docs
johnl-amd May 15, 2026
3496fbe
EAI-164: expose gateway API key Secret env vars in AIWB chart
johnl-amd May 15, 2026
92ec9bc
EAI-5821: Remove dead comment file and debug annotation from aim-gate…
johnl-amd May 15, 2026
c16f7d4
EAI-5821: Remove temp migration jobs, unused patch, and vendored upst…
johnl-amd May 15, 2026
00e0aa2
EAI-6233: Enable InferencePool backendResources in EG extensionManager
johnl-amd May 20, 2026
06ba4f8
EAI-6038: Fix gateway API keys secret namespace to match SecurityPoli…
johnl-amd May 21, 2026
42e7342
EAI-6038: Allow workbench namespace SecurityPolicies to reference clu…
johnl-amd May 21, 2026
15e0eed
EAI-6038: Add PodMonitor for AI Gateway extproc metrics
johnl-amd May 21, 2026
715605b
EAI-6038: Remove aim-gateway chart and stale PodMonitor
johnl-amd May 27, 2026
14d6a2c
EAI-6038: Remove dead gatewayApiKeys config from aiwb chart
johnl-amd May 27, 2026
e6aa059
EAI-6038: Remove stale POC notes doc
johnl-amd May 27, 2026
587014e
Merge branch 'EAI_5821_evaluate_envoy_gateway_merge_main' into EAI-58…
brownzebra May 28, 2026
18681b2
Remove k8s-passthrough TLS listener and TLSRoute; fix admission webho…
johnl-amd May 28, 2026
640a718
Fix code review issues: remove stale kgateway files, surface MCP seed
johnl-amd May 29, 2026
1b1b9e1
Merge remote-tracking branch 'origin/main' into EAI-5821-add-envoy-ai…
johnl-amd May 29, 2026
ec49c31
EAI-5821: Add envoy-ai-gateway and envoy-ai-gateway-crds to component…
johnl-amd May 29, 2026
0bc126e
EAI-5821: Add SBOM metadata for envoy-ai-gateway and envoy-ai-gateway…
johnl-amd May 29, 2026
9ef8025
EAI-5821: Restore k8s-passthrough TLS listener and TLSRoute
johnl-amd May 29, 2026
4d2d2fd
EAI-5821: Remove global extAuth SecurityPolicy to restore envoy-gatew…
johnl-amd May 29, 2026
5393874
EAI-5821: Restore extAuth SecurityPolicy; remove aigateway GatewayCon…
johnl-amd May 29, 2026
99c945d
EAI-5821: Remove InferencePool backendResources from extensionManager
johnl-amd Jun 1, 2026
fc50125
EAI-5821: Remove global extAuth SecurityPolicy and ReferenceGrant
johnl-amd Jun 1, 2026
0139007
EAI-5821: Complete POC state — InferencePool CRDs, extAuth, backendRe…
johnl-amd Jun 1, 2026
8dc1abb
EAI-5821: Enable inference-extension-crds in all cluster size profiles
johnl-amd Jun 1, 2026
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
54 changes: 54 additions & 0 deletions root/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -293,6 +293,9 @@ apps:
path: cluster-auth/0.5.9
syncWave: -25
valuesFile: values.yaml
valuesObject:
additionalSecurityPolicyNamespaces:
- workbench
cluster-auth-config:
ignoreDifferences:
- group: external-secrets.io
Expand Down Expand Up @@ -576,12 +579,49 @@ apps:
requests:
cpu: "250m"
memory: "512Mi"
inference-extension-crds:
namespace: default
path: inference-extension-crds/v1.5.0
syncWave: -35
envoy-gateway:
namespace: envoy-gateway-system
path: envoy-gateway/v1.7.1
syncWave: -30
valuesObject:
kubernetesClusterDomain: cluster.local
config:
envoyGateway:
extensionApis:
# Required for AI Gateway Backend CRD references to be accepted.
enableBackend: true
# Registers the AI Gateway controller as an xDS extension server.
# Without this, Envoy Gateway does not inject the ext_proc HTTP filter
# into the listener, so token metadata fields stay null in access logs.
extensionManager:
resources:
- group: aigateway.envoyproxy.io
version: v1beta1
kind: AIGatewayRoute
- group: aigateway.envoyproxy.io
version: v1beta1
kind: AIServiceBackend
backendResources:
- group: inference.networking.k8s.io
version: v1
kind: InferencePool
hooks:
xdsTranslator:
post:
- Cluster
- Translation
service:
host: ai-gateway-controller.envoy-ai-gateway-system.svc.cluster.local
port: 1063
tls:
certificateRef:
kind: Secret
name: self-signed-cert-for-mutating-webhook
namespace: envoy-ai-gateway-system
envoy-gateway-config:
helmParameters:
- name: domain
Expand All @@ -590,6 +630,20 @@ apps:
path: envoy-gateway-config
syncWave: -15
valuesFile: values.yaml
envoy-ai-gateway-crds:
namespace: envoy-ai-gateway-system
path: envoy-ai-gateway-crds/v0.6.0
syncWave: -10
envoy-ai-gateway:
namespace: envoy-ai-gateway-system
path: envoy-ai-gateway/v0.6.0
syncWave: -5
valuesObject:
controller:
mcp:
sessionEncryption:
# Must be overridden per deployment with a secure random string.
seed: "cluster-forge-default-seed-override-in-production"
kserve:
namespace: kserve-system
path: kserve/v0.16.0
Expand Down
3 changes: 3 additions & 0 deletions root/values_large.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,11 @@ enabledApps:
- cnpg-operator
- external-secrets
- external-secrets-config
- inference-extension-crds
- envoy-gateway
- envoy-gateway-config
- envoy-ai-gateway-crds
- envoy-ai-gateway
- gitea
- gitea-config
- kaiwo
Expand Down
3 changes: 3 additions & 0 deletions root/values_medium.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -22,8 +22,11 @@ enabledApps:
- cnpg-operator
- external-secrets
- external-secrets-config
- inference-extension-crds
- envoy-gateway
- envoy-gateway-config
- envoy-ai-gateway-crds
- envoy-ai-gateway
- gitea
- gitea-config
- kaiwo
Expand Down
3 changes: 3 additions & 0 deletions root/values_small.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -20,8 +20,11 @@ enabledApps:
- cnpg-operator
- external-secrets
- external-secrets-config
- inference-extension-crds
- envoy-gateway
- envoy-gateway-config
- envoy-ai-gateway-crds
- envoy-ai-gateway
- gitea
- gitea-config
- kaiwo
Expand Down
20 changes: 19 additions & 1 deletion sbom/components.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -59,7 +59,7 @@ components:
licenseUrl: https://github.com/silogen/cluster-forge/blob/main/LICENSE
aiwb:
path: null
repoVersion: 1.1.9
repoVersion: 2.0.0-rc.1
valuesFile: values.yaml
sourceUrl: oci://registry-1.docker.io/amdenterpriseai/aiwb-chart
projectUrl: https://github.com/silogen/aiwb
Expand Down Expand Up @@ -119,6 +119,24 @@ components:
projectUrl: https://github.com/cloudnative-pg/cloudnative-pg
license: Apache License 2.0
licenseUrl: https://github.com/cloudnative-pg/cloudnative-pg/blob/main/LICENSE
envoy-ai-gateway:
path: envoy-ai-gateway/v0.6.0
sourceUrl: https://github.com/envoyproxy/ai-gateway
projectUrl: https://github.com/envoyproxy/ai-gateway
license: Apache License 2.0
licenseUrl: https://github.com/envoyproxy/ai-gateway/blob/main/LICENSE
inference-extension-crds:
path: inference-extension-crds/v1.5.0
sourceUrl: https://github.com/kubernetes-sigs/gateway-api-inference-extension
projectUrl: https://github.com/kubernetes-sigs/gateway-api-inference-extension
license: Apache License 2.0
licenseUrl: https://github.com/kubernetes-sigs/gateway-api-inference-extension/blob/main/LICENSE
envoy-ai-gateway-crds:
path: envoy-ai-gateway-crds/v0.6.0
sourceUrl: https://github.com/envoyproxy/ai-gateway
projectUrl: https://github.com/envoyproxy/ai-gateway
license: Apache License 2.0
licenseUrl: https://github.com/envoyproxy/ai-gateway/blob/main/LICENSE
envoy-gateway:
path: envoy-gateway/v1.7.1
sourceUrl: oci://docker.io/envoyproxy/gateway-helm
Expand Down
28 changes: 28 additions & 0 deletions sources/aiwb/1.0.3/templates/rbac.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -92,6 +92,34 @@ rules:
resources: ["inferenceservices"]
verbs: ["get", "list"]

# Envoy Gateway resources (for per-AIM dynamic routing and API key auth)
- apiGroups: ["gateway.envoyproxy.io"]
resources: ["backends", "securitypolicies"]
verbs: ["get", "list", "create", "update", "patch", "delete"]
- apiGroups: ["aigateway.envoyproxy.io"]
resources: ["aiservicebackends", "aigatewayroutes"]
verbs: ["get", "list", "create", "update", "patch", "delete"]

# InferencePool + InferenceObjective (for EPP-based replica-aware routing)
- apiGroups: ["inference.networking.k8s.io"]
resources: ["inferencepools"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete", "deletecollection"]
- apiGroups: ["inference.networking.x-k8s.io"]
resources: ["inferenceobjectives"]
verbs: ["get", "list", "watch", "create", "update", "patch", "delete", "deletecollection"]
# EPP Role grants watch on x-k8s.io/inferencepools too — AIWB must hold it to be able to grant it
- apiGroups: ["inference.networking.x-k8s.io"]
resources: ["inferencepools"]
verbs: ["get", "list", "watch"]

# ServiceAccount + RBAC (for per-AIM EPP identity and permissions)
- apiGroups: [""]
resources: ["serviceaccounts"]
verbs: ["get", "list", "create", "update", "patch", "delete", "deletecollection"]
- apiGroups: ["rbac.authorization.k8s.io"]
resources: ["roles", "rolebindings"]
verbs: ["get", "list", "create", "update", "patch", "delete", "deletecollection"]

# PVC access (read-only)
- apiGroups: [""]
resources: ["persistentvolumeclaims"]
Expand Down
4 changes: 4 additions & 0 deletions sources/cluster-auth/0.5.0/values.yaml
Original file line number Diff line number Diff line change
Expand Up @@ -13,6 +13,10 @@ namespace:
name: cluster-auth
create: true

# Additional namespaces whose SecurityPolicies are allowed to reference the cluster-auth service.
# Needed when per-AIM SecurityPolicies are created in workload namespaces (e.g., workbench).
additionalSecurityPolicyNamespaces: []

existingSecret: "cluster-auth-secrets"

service:
Expand Down
20 changes: 20 additions & 0 deletions sources/envoy-ai-gateway-crds/v0.6.0/Chart.yaml
Original file line number Diff line number Diff line change
@@ -0,0 +1,20 @@
apiVersion: v2
appVersion: v0.6.0
description: The Helm chart for Envoy AI Gateway CRD
home: https://aigateway.envoyproxy.io/
icon: https://raw.githubusercontent.com/envoyproxy/ai-gateway/refs/heads/main/site/static/img/logo.svg
keywords:
- gateway-api
- envoyproxy
- envoy-gateway
- eg
- ai-gateway
- ai
maintainers:
- name: envoy-ai-gateway-maintainers
url: https://github.com/envoyproxy/ai-gateway/blob/main/CODEOWNERS
name: ai-gateway-crds-helm
sources:
- https://github.com/envoyproxy/ai-gateway
type: application
version: v0.6.0
Loading
Loading