mirror of
https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git
synced 2026-11-03 01:13:24 +00:00
14c3fb840e
agent-sandbox v1.0.8 adds spec.failedPodPolicy to Sandbox and SandboxTemplate. The default, Retain, leaves a Failed Pod in place and surfaces Finished=True; Recreate deletes it and starts a replacement with the same Sandbox identity and PVCs. Ship it as an opt-in toggle next to the other commented fields, with a new section 5 in the optional-hardening doc: what it changes, how to enable it for new, warm-pool and already-claimed Sandboxes (the policy is stamped at creation), a failure drill, caveats and rollback. The base walkthrough stays on Retain because a deterministic failure would otherwise recreate forever, and because the templates use restartPolicy OnFailure, so the policy only matters for terminal cases such as node eviction. Cross-references updated in the example README, the optional-manifests index, the architecture failure-mode table and the platform skill's troubleshooting table. Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
124 lines
5.3 KiB
YAML
124 lines
5.3 KiB
YAML
# Minimal single-tenant SandboxTemplate for DeepSeek Harness Web.
|
|
#
|
|
# This is the "just one DSH Web" quick-start template. For the full
|
|
# multi-tenant platform (warm pool, per-user claims, gateway, idle-suspend),
|
|
# see examples/dsh-agents-as-a-service/.
|
|
#
|
|
# Claims reference this template directly (spec.sandboxTemplateRef): there is
|
|
# no warm pool and no per-user platform here. See the README for the full
|
|
# quickstart; in short the prerequisites are:
|
|
# - Namespace dsh-demo.
|
|
# - Secret dsh-provider-keys in dsh-demo with key DEEPSEEK_API_KEY
|
|
# (injected via envFrom; the pod starts without it, only model calls fail).
|
|
# - Optional: Secret dsh-provider-keys-extra with additional provider keys
|
|
# (OPENROUTER_API_KEY, GEMINI_API_KEY, NVIDIA_API_KEY, ...). It is
|
|
# referenced with `optional: true`, so it may be absent.
|
|
# The agent-sandbox controller (v1.0.8, API v1beta1) must be installed.
|
|
apiVersion: extensions.agents.x-k8s.io/v1beta1
|
|
kind: SandboxTemplate
|
|
metadata:
|
|
name: dsh-web-template
|
|
namespace: dsh-demo
|
|
spec:
|
|
service: true # headless Service per Sandbox -> stable DNS (status.serviceFQDN)
|
|
# networkPolicyManagement is omitted, so the controller uses its Managed
|
|
# secure default (ingress only from the sandbox-router, public egress). This
|
|
# quickstart reaches the sandbox through `kubectl port-forward`, which is
|
|
# local to the pod. The multi-tenant example documents opt-in policies in
|
|
# examples/dsh-agents-as-a-service/docs/optional-hardening.md.
|
|
#
|
|
# OPTIONAL: recreate a Failed sandbox Pod instead of retaining it
|
|
# (agent-sandbox v1.0.8+). Documented with the multi-tenant example.
|
|
# failedPodPolicy: Recreate
|
|
podTemplate:
|
|
spec:
|
|
# OPTIONAL: run under gVisor. gVisor breaks `kubectl port-forward`, so
|
|
# this quickstart's only access path will not work; use the multi-tenant
|
|
# gateway example or a Service/NodePort instead.
|
|
# runtimeClassName: gvisor
|
|
#
|
|
# OPTIONAL: pin to a dedicated node pool. Replace the placeholder with a
|
|
# node label; add a matching toleration if the pool is tainted.
|
|
# nodeSelector:
|
|
# dsh.example.com/node-pool: dsh
|
|
securityContext:
|
|
runAsNonRoot: true
|
|
runAsUser: 1000 # Matches the UID of the 'node' user
|
|
runAsGroup: 1000
|
|
fsGroup: 1000
|
|
# DSH's credentials plugin refuses to start when .credentials.yaml has
|
|
# any group/other permission bit (it creates the file 0600). The
|
|
# default kubelet fsGroup policy ("Always") rewrites it to 0660 on every
|
|
# pod start, so a recreated or resumed sandbox crash-loops; OnRootMismatch
|
|
# avoids that walk once the volume root already carries the ownership.
|
|
# Rationale in full at
|
|
# examples/dsh-agents-as-a-service/manifests/10-sandboxtemplate.yaml.
|
|
fsGroupChangePolicy: OnRootMismatch
|
|
containers:
|
|
- name: dsh-web
|
|
image: ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:dsh-v0.2.1-rc.3-r4
|
|
imagePullPolicy: IfNotPresent
|
|
ports:
|
|
- name: web
|
|
containerPort: 3080
|
|
envFrom:
|
|
- secretRef:
|
|
name: dsh-provider-keys # Secret with key DEEPSEEK_API_KEY
|
|
# Optional extra provider keys; an absent Secret is safe.
|
|
- secretRef:
|
|
name: dsh-provider-keys-extra
|
|
optional: true
|
|
env:
|
|
# Empty => DSH derives links from the request Host. Keep it empty
|
|
# when fronting the sandbox with a proxy/gateway.
|
|
- name: DSH_PUBLIC_URL
|
|
value: ""
|
|
# DSH Host/Origin-fences /api. Empty trusts only localhost, which
|
|
# is right for `kubectl port-forward`. Set this to the public host
|
|
# (e.g. dsh.example.com) if you front DSH with a proxy or Ingress,
|
|
# so requests forwarded with the browser's Host are accepted. The
|
|
# full example documents both exposure variants in
|
|
# examples/dsh-agents-as-a-service/manifests/exposure/README.md.
|
|
- name: DSH_TRUSTED_HOSTS
|
|
value: ""
|
|
volumeMounts:
|
|
- name: dsh-home
|
|
mountPath: /home/node/.dsh # DSH_HOME
|
|
# / is behind DSH's launch-token cookie (401 without it); use an
|
|
# unauthenticated path for probes. The startup probe gives a cold
|
|
# start (plugin activation on a small node, or the first resume of a
|
|
# suspended sandbox) up to 120s before liveness can restart it.
|
|
startupProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
periodSeconds: 5
|
|
failureThreshold: 24
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 15
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
volumeClaimTemplates:
|
|
- metadata:
|
|
name: dsh-home
|
|
spec:
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 5Gi
|
|
# storageClassName omitted => cluster default
|