Files
classic-models-agent-catalogue/k8s/deployment.yaml
T
Stéphane Tailland fd2df93683 fix(deploy): the ghcr package is private, so declare the pull secret
Same arrangement classic-models already uses: a hand-created ghcr-pull-secret
rather than one committed or held in Vault, since the credential is a GitHub
token that belongs to no estate in particular. Without it the pod would sit in
ImagePullBackOff with no hint as to why.

Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
2026-08-29 07:16:40 +02:00

78 lines
2.5 KiB
YAML

apiVersion: apps/v1
kind: Deployment
metadata:
name: catalogue-agent
namespace: agents
spec:
# One replica, and that is a constraint rather than a default. Conversation
# history — which the confirm-before-writing flow depends on — lives in the
# process, keyed by A2A contextId. A second replica would route the user's
# "yes" to a pod that never saw the question. Scaling out needs sticky routing
# on contextId or a shared store first.
replicas: 1
selector:
matchLabels:
app: catalogue-agent
template:
metadata:
labels:
app: catalogue-agent
spec:
# The ghcr package is private, like classic-models-api's. The secret is
# created by hand once (see the README) rather than committed or pulled
# from Vault — same arrangement classic-models already uses, and the
# credential is a GitHub token that belongs to no estate in particular.
imagePullSecrets:
- name: ghcr-pull-secret
securityContext:
runAsNonRoot: true
runAsUser: 10001
seccompProfile:
type: RuntimeDefault
containers:
- name: agent
image: ghcr.io/staillanibm/classic-models-agent-catalogue:v0.1.0
ports:
- name: http
containerPort: 8080
envFrom:
- configMapRef:
name: catalogue-agent-config
- secretRef:
name: catalogue-agent-secrets
volumeMounts:
- name: sttlab-ca
mountPath: /etc/sttlab-ca
readOnly: true
# The Agent Card needs no auth and is served by the same app, so a 200
# means the A2A routes are genuinely mounted — not merely that the
# process is alive.
readinessProbe:
httpGet:
path: /.well-known/agent-card.json
port: http
initialDelaySeconds: 5
periodSeconds: 10
livenessProbe:
httpGet:
path: /.well-known/agent-card.json
port: http
initialDelaySeconds: 15
periodSeconds: 20
resources:
requests:
cpu: 50m
memory: 192Mi
limits:
cpu: "1"
memory: 512Mi
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: ["ALL"]
volumes:
- name: sttlab-ca
configMap:
name: sttlab-ca