Files
Jesse JaggarsandDrew Newberry 02b664bb0d refactor(config): normalize and enforce gateway schema v2 (#2814)
* refactor(config): normalize compute driver field names

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* refactor(config): introduce canonical gateway fields

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* refactor(config): enforce gateway schema version 2

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve compute driver runtime guarantees

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): address schema v2 review regressions

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): complete schema v2 migration safeguards

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(config): expand schema v2 regression coverage

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(config): add schema v2 parity manifest

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): correct parity manifest inventory

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): record schema v2 intentional changes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): disposition schema v2 parity gaps

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add dual schema parity harness

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): establish compute lifecycle parity baseline

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve gateway option compatibility

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record gateway option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* docs(config): close gateway-wide parity gaps

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(podman): apply configured pids limit

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): validate Podman option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add Kubernetes option parity harness

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record Kubernetes option parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): disposition VM parity lanes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): add external driver parity lane

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): preserve external driver pull policy

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): attest parity artifacts and launches

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): require clean parity build sources

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): bind parity runtime artifacts

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): use isolated supervisor tags

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): qualify parity image tags

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): serve parity supervisor locally

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): isolate parity podman services

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): harden parity evidence provenance

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): pin parity sandbox artifacts

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): attest parity runtime inputs

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): bind parity runtime evidence

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): record compute boundary parity

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(e2e): disposition cross-cutting parity lanes

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(packaging): preflight gateway config upgrades

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): preserve rebase integration guarantees

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(ci): isolate temporary git signing config

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): update remaining schema v2 consumers

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(ci): provide e2fs tools to VM tests

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): align preflight with gateway startup

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(vm): preserve rootfs tar configuration

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* chore(config): adopt duration unit constructors

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(packaging): preflight RPM gateway config

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(config): address driver review findings

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(e2e): require fresh semantic parity evidence

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* fix(docker): update tests for renamed sandbox label

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>

* test(gateway): preserve selective driver coverage after rebase

Signed-off-by: Drew Newberry <anewberry@nvidia.com>

---------

Signed-off-by: Jesse Jaggars <jjaggars@redhat.com>
Signed-off-by: Drew Newberry <anewberry@nvidia.com>
Co-authored-by: Drew Newberry <anewberry@nvidia.com>
2026-09-11 05:00:24 +00:00

315 lines
12 KiB
Smarty

{{/*
Expand the name of the chart.
*/}}
{{- define "openshell.name" -}}
{{- default .Chart.Name .Values.nameOverride | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Create a default fully qualified app name.
*/}}
{{- define "openshell.fullname" -}}
{{- if .Values.fullnameOverride }}
{{- .Values.fullnameOverride | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- $name := default .Chart.Name .Values.nameOverride }}
{{- if contains $name .Release.Name }}
{{- .Release.Name | trunc 63 | trimSuffix "-" }}
{{- else }}
{{- printf "%s-%s" .Release.Name $name | trunc 63 | trimSuffix "-" }}
{{- end }}
{{- end }}
{{- end }}
{{/*
Create chart name and version as used by the chart label.
*/}}
{{- define "openshell.chart" -}}
{{- printf "%s-%s" .Chart.Name .Chart.Version | replace "+" "_" | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Common labels
*/}}
{{- define "openshell.labels" -}}
helm.sh/chart: {{ include "openshell.chart" . }}
{{ include "openshell.selectorLabels" . }}
{{- if .Chart.AppVersion }}
app.kubernetes.io/version: {{ .Chart.AppVersion | quote }}
{{- end }}
app.kubernetes.io/managed-by: {{ .Release.Service }}
{{- end }}
{{/*
Selector labels
*/}}
{{- define "openshell.selectorLabels" -}}
app.kubernetes.io/name: {{ include "openshell.name" . }}
app.kubernetes.io/instance: {{ .Release.Name }}
{{- end }}
{{/*
Create the name of the service account to use
*/}}
{{- define "openshell.serviceAccountName" -}}
{{- if .Values.serviceAccount.create }}
{{- default (include "openshell.fullname" .) .Values.serviceAccount.name }}
{{- else }}
{{- default "default" .Values.serviceAccount.name }}
{{- end }}
{{- end }}
{{/*
Create the name of the service account assigned to sandbox pods
*/}}
{{- define "openshell.sandboxServiceAccountName" -}}
{{- if .Values.sandboxServiceAccount.create }}
{{- default (printf "%s-sandbox" (include "openshell.fullname" .) | trunc 63 | trimSuffix "-") .Values.sandboxServiceAccount.name }}
{{- else }}
{{- default "default" .Values.sandboxServiceAccount.name }}
{{- end }}
{{- end }}
{{/*
Whether this chart owns workspace-scoped resources. Missing legacy values
default to enabled so upgrades with --reuse-values preserve the old topology.
*/}}
{{- define "openshell.workspaceResourcesEnabled" -}}
{{- $workspaceResources := .Values.workspaceResources | default dict -}}
{{- $enabled := true -}}
{{- if hasKey $workspaceResources "enabled" -}}
{{- $enabled = get $workspaceResources "enabled" -}}
{{- end -}}
{{- if $enabled -}}true{{- end -}}
{{- end }}
{{/*
Gateway image reference. Uses image.tag when set; falls back to .Chart.AppVersion
so a released chart automatically pulls the matching image without extra overrides.
*/}}
{{- define "openshell.image" -}}
{{- printf "%s:%s" .Values.image.repository (.Values.image.tag | default .Chart.AppVersion) }}
{{- end }}
{{/* Official supervisor repository used by the gateway's built-in default. */}}
{{- define "openshell.defaultSupervisorRepository" -}}
ghcr.io/nvidia/openshell/supervisor
{{- end }}
{{/*
Whether the gateway listener should verify client certificates (mTLS).
An explicit empty server.tls.clientCaSecretName disables client-CA wiring in
both gateway.toml and the workload, overriding built-in PKI and cert-manager
defaults.
*/}}
{{- define "openshell.gatewayClientCaEnabled" -}}
{{- if .Values.server.disableTls -}}
{{- else if eq .Values.server.tls.clientCaSecretName "" -}}
{{- else if or .Values.server.tls.clientCaSecretName (and .Values.pkiInitJob.enabled (not .Values.certManager.enabled)) (and .Values.certManager.enabled .Values.certManager.clientCaFromServerTlsSecret) -}}
true
{{- end -}}
{{- end -}}
{{/*
Whether Helm must propagate a supervisor image override into gateway.toml.
The chart's documented repository and empty tag are the gateway-owned default.
*/}}
{{- define "openshell.supervisorImageOverrideEnabled" -}}
{{- $defaultRepository := include "openshell.defaultSupervisorRepository" . -}}
{{- $repository := .Values.supervisor.image.repository | default $defaultRepository -}}
{{- if or (ne $repository $defaultRepository) .Values.supervisor.image.tag -}}true{{- end -}}
{{- end }}
{{/*
Supervisor image override. A tag-only override uses the official repository;
a repository-only override uses the effective gateway image tag.
*/}}
{{- define "openshell.supervisorImage" -}}
{{- $repository := .Values.supervisor.image.repository | default (include "openshell.defaultSupervisorRepository" .) -}}
{{- $tag := .Values.supervisor.image.tag | default .Values.image.tag | default .Chart.AppVersion -}}
{{- printf "%s:%s" $repository $tag }}
{{- end }}
{{/*
Namespaced Issuer (selfSigned) for cert-manager CA bootstrap.
*/}}
{{- define "openshell.issuerSelfSigned" -}}
{{- printf "%s-selfsigned" (include "openshell.fullname" .) | trunc 63 | trimSuffix "-" }}
{{- end }}
{{/*
Namespace where sandbox pods are created. An explicit
.Values.server.sandboxNamespace is used verbatim. Otherwise it defaults to
.Release.Namespace so `helm install -n my-ns` works without extra overrides.
*/}}
{{- define "openshell.sandboxNamespace" -}}
{{- .Values.server.sandboxNamespace | default .Release.Namespace -}}
{{- end }}
{{/*
Namespace where Kubernetes Secret-backed provider credentials live.
*/}}
{{- define "openshell.credentialKubernetesSecretsNamespace" -}}
{{- .Values.server.credentialDrivers.kubernetesSecrets.namespace | default .Release.Namespace -}}
{{- end }}
{{/*
Name of the Secret holding the default credential storage key-encryption key.
When server.credentialStorage.existingSecret is set, returns that name instead
of the chart-generated name (for GitOps / helm-template workflows).
*/}}
{{- define "openshell.credentialStorageKeyEncryptionKeySecretName" -}}
{{- if .Values.server.credentialStorage.existingSecret -}}
{{- .Values.server.credentialStorage.existingSecret -}}
{{- else -}}
{{- printf "%s-credential-storage-key-encryption-key" (include "openshell.fullname" .) | trunc 63 | trimSuffix "-" -}}
{{- end -}}
{{- end }}
{{/*
Key inside the default credential storage key-encryption key Secret.
*/}}
{{- define "openshell.credentialStorageKeyEncryptionKeySecretKey" -}}
key-encryption-key
{{- end }}
{{/*
Gateway environment variable used to pass the default credential storage key-encryption key.
*/}}
{{- define "openshell.credentialStorageKeyEncryptionKeyEnvName" -}}
OPENSHELL_GATEWAY_CREDENTIAL_KEY_ENCRYPTION_KEY
{{- end }}
{{/*
Name of the Secret holding gateway-minted sandbox JWT signing material.
*/}}
{{- define "openshell.sandboxJwtSecretName" -}}
{{- .Values.server.sandboxJwt.signingSecretName | default (printf "%s-jwt-keys" (include "openshell.fullname" .)) -}}
{{- end }}
{{/*
gRPC endpoint sandbox pods use to call back into the gateway. An explicit
.Values.server.grpcEndpoint is used verbatim. Otherwise it is derived from
the in-cluster Service DNS, release namespace, service port, and disableTls
flag — so the default value works for any release name or namespace without
override.
*/}}
{{/*
Supervisor sideload method. When supervisor.sideloadMethod is set, use it
verbatim. Otherwise auto-detect from the cluster version: the ImageVolume
feature gate is enabled by default starting in K8s v1.35 (GA in v1.36).
Clusters on v1.33-v1.34 can opt in by setting sideloadMethod explicitly
after enabling the feature gate.
*/}}
{{- define "openshell.supervisorSideloadMethod" -}}
{{- if .Values.supervisor.sideloadMethod -}}
{{- .Values.supervisor.sideloadMethod -}}
{{- else -}}
{{- if semverCompare ">=1.35-0" .Capabilities.KubeVersion.Version -}}
image-volume
{{- else -}}
init-container
{{- end -}}
{{- end -}}
{{- end }}
{{- define "openshell.grpcEndpoint" -}}
{{- if .Values.server.grpcEndpoint -}}
{{- .Values.server.grpcEndpoint -}}
{{- else -}}
{{- $scheme := ternary "http" "https" (default false .Values.server.disableTls) -}}
{{- printf "%s://%s.%s.svc.cluster.local:%d" $scheme (include "openshell.fullname" .) .Release.Namespace (int .Values.service.port) -}}
{{- end -}}
{{- end }}
{{/*
Default server certificate DNS SANs derived from the release name and namespace.
Returns a YAML list. Append extra SANs from values with range loops.
*/}}
{{- define "openshell.defaultServerDnsNames" -}}
{{- $name := include "openshell.fullname" . -}}
{{- $ns := .Release.Namespace -}}
{{- list $name
(printf "%s.%s.svc" $name $ns)
(printf "%s.%s.svc.cluster.local" $name $ns)
"localhost"
(printf "%s.localhost" $name)
(printf "*.%s.localhost" $name)
"host.docker.internal"
"host.containers.internal"
| toYaml }}
{{- end }}
{{/*
Gateway workload kind. StatefulSet is the default because the default SQLite
database requires persistent per-pod storage.
*/}}
{{- define "openshell.workloadKind" -}}
{{- $workload := .Values.workload | default dict -}}
{{- if not (kindIs "map" $workload) -}}
{{- fail "workload must be a map with kind and allowMultiReplicaStatefulSet fields." -}}
{{- end -}}
{{- default "statefulset" (get $workload "kind") | lower -}}
{{- end }}
{{/*
Translate chart image pull policy values to the canonical gateway vocabulary.
The Kubernetes spellings remain accepted so existing values files continue to
work across the schema-v2 chart upgrade.
*/}}
{{- define "openshell.canonicalImagePullPolicy" -}}
{{- $policy := printf "%v" . -}}
{{- if eq $policy "Always" -}}
always
{{- else if eq $policy "IfNotPresent" -}}
if_not_present
{{- else if eq $policy "Never" -}}
never
{{- else if has $policy (list "always" "if_not_present" "never") -}}
{{- $policy -}}
{{- else -}}
{{- fail (printf "image pull policy %q must be one of: always, if_not_present, never, Always, IfNotPresent, Never" $policy) -}}
{{- end -}}
{{- end }}
{{/*
Validate chart values that Helm would otherwise accept silently.
*/}}
{{- define "openshell.validateValues" -}}
{{- $workloadKind := include "openshell.workloadKind" . -}}
{{- $workload := .Values.workload | default dict -}}
{{- $replicaCount := int (default 1 .Values.replicaCount) -}}
{{- if and (hasKey .Values "postgres") (kindIs "map" .Values.postgres) (hasKey .Values.postgres "enabled") -}}
{{- fail "postgres.enabled was removed; the OpenShell chart no longer deploys PostgreSQL. Provision PostgreSQL separately and set server.externalDbSecret to a Secret containing a PostgreSQL URI." -}}
{{- end -}}
{{- if not (or (eq $workloadKind "statefulset") (eq $workloadKind "deployment")) -}}
{{- fail "workload.kind must be one of: statefulset, deployment." -}}
{{- end -}}
{{- if and (eq $workloadKind "deployment") (not .Values.server.externalDbSecret) -}}
{{- fail "workload.kind=deployment requires server.externalDbSecret; use workload.kind=statefulset for the default SQLite database." -}}
{{- end -}}
{{- if and (gt $replicaCount 1) (not .Values.server.externalDbSecret) -}}
{{- fail "replicaCount > 1 requires server.externalDbSecret; multiple gateway replicas cannot share the default per-pod SQLite database." -}}
{{- end -}}
{{- if and (eq $workloadKind "statefulset") (gt $replicaCount 1) (not (get $workload "allowMultiReplicaStatefulSet" | default false)) -}}
{{- fail "replicaCount > 1 with workload.kind=statefulset requires workload.allowMultiReplicaStatefulSet=true; use workload.kind=deployment for external database-backed multi-replica gateways." -}}
{{- end -}}
{{- $workspaceMode := .Values.server.drivers.kubernetes.workspaceMode | default "shared" -}}
{{- if not (has $workspaceMode (list "shared" "managed" "operator")) -}}
{{- fail "server.drivers.kubernetes.workspaceMode must be one of: shared, managed, operator." -}}
{{- end -}}
{{- $credentialDrivers := list -}}
{{- if .Values.server.credentialDrivers.kubernetesSecrets.enabled -}}
{{- $credentialDrivers = append $credentialDrivers "kubernetes-secrets" -}}
{{- end -}}
{{- if .Values.server.credentialDrivers.vault.enabled -}}
{{- $credentialDrivers = append $credentialDrivers "vault" -}}
{{- end -}}
{{- if gt (len $credentialDrivers) 1 -}}
{{- fail "only one external server.credentialDrivers backend can be enabled at a time." -}}
{{- end -}}
{{- if kindIs "invalid" .Values.server.tls.clientCaSecretName -}}
{{- fail "server.tls.clientCaSecretName cannot be null; omit the key to use the chart default (openshell-server-client-ca), or set to \"\" to disable client certificate verification for HTTPS-only mode" -}}
{{- end -}}
{{- end }}