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>
160 lines
7.3 KiB
YAML
160 lines
7.3 KiB
YAML
# The reusable DSH Web blueprint. Warm pools stamp pod env BEFORE any user
|
|
# exists, so per-user secrets cannot live in pod env; the shared provider keys
|
|
# are injected via envFrom, and claims that would bypass the warm pool are
|
|
# rejected outright (see 40-claim-rejected.yaml).
|
|
#
|
|
# A stripped-down single-tenant variant of this template (no warm pool, no
|
|
# policy enforcement) lives in examples/minimal-single-tenant/.
|
|
apiVersion: extensions.agents.x-k8s.io/v1beta1
|
|
kind: SandboxTemplate
|
|
metadata:
|
|
name: dsh-web
|
|
namespace: dsh-demo
|
|
spec:
|
|
# Claims must not inject env or volumeClaimTemplates: with Disallowed, such
|
|
# claims are REJECTED instead of silently taking the cold (non-warm-pool)
|
|
# provisioning path. Demonstrated in step 6.
|
|
envVarsInjectionPolicy: Disallowed
|
|
volumeClaimTemplatesPolicy: Disallowed
|
|
|
|
# Per-sandbox headless Service -> stable DNS (sandbox.status.serviceFQDN).
|
|
# The gateway routes each user to their DSH Web instance by this name.
|
|
service: true
|
|
|
|
# The example leaves NetworkPolicy to an optional, opt-in manifest
|
|
# (manifests/optional/network-policy/): the base walkthrough should not
|
|
# require a policy-capable CNI, and the controller's Managed secure default
|
|
# only allows the sandbox-router, which this example does not deploy. If you
|
|
# switch to Managed, define spec.networkPolicy explicitly or the gateway will
|
|
# be blocked. See docs/optional-hardening.md.
|
|
networkPolicyManagement: Unmanaged
|
|
|
|
# OPTIONAL: replace a Failed sandbox Pod instead of parking the sandbox.
|
|
# The default, Retain, leaves the Failed Pod in place and surfaces
|
|
# Finished=True on the Sandbox until a human intervenes. Recreate deletes the
|
|
# Failed Pod and starts a replacement with the same Sandbox identity and
|
|
# Sandbox-owned PVCs, backing off (5s doubling to 5m) on repeated failures.
|
|
# Requires agent-sandbox v1.0.8+; existing Sandboxes keep their own stamped
|
|
# policy, so patch them separately. See docs/optional-hardening.md.
|
|
# failedPodPolicy: Recreate
|
|
|
|
podTemplate:
|
|
spec:
|
|
# DSH Web is multi-arch (amd64 + arm64); no arch nodeSelector is needed.
|
|
#
|
|
# OPTIONAL: run the sandbox under gVisor. Requires a RuntimeClass named
|
|
# "gvisor" and nodes that can run it; gVisor breaks `kubectl port-forward`
|
|
# into the sandbox (use the gateway). Existing Sandboxes snapshot their
|
|
# pod template, so enabling it later requires patching/recreating them.
|
|
# See docs/optional-hardening.md.
|
|
# runtimeClassName: gvisor
|
|
#
|
|
# OPTIONAL: pin sandboxes to a dedicated node pool (for example a gVisor
|
|
# pool). Replace this placeholder with a label your nodes actually carry;
|
|
# add a matching toleration if the pool is tainted. Active
|
|
# cluster-specific scheduling belongs in a local patch, not here.
|
|
# nodeSelector:
|
|
# dsh.example.com/node-pool: dsh
|
|
restartPolicy: "OnFailure"
|
|
securityContext:
|
|
runAsUser: 1000 # the 'node' user in the DSH image
|
|
runAsGroup: 1000
|
|
fsGroup: 1000
|
|
runAsNonRoot: true
|
|
# 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") recursively ORs 0660 into
|
|
# every file each time the pod starts, so a resumed sandbox comes back
|
|
# with 0660 and crash-loops before the gateway can proxy to it.
|
|
# OnRootMismatch skips that walk once the volume root already carries
|
|
# the fsGroup ownership/mode applied on the first mount.
|
|
# Keep in sync with the minimal variant:
|
|
# examples/minimal-single-tenant/manifests/sandbox-template.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
|
|
# Optional extra provider keys (OpenRouter, Gemini, NVIDIA, ...).
|
|
# The Secret may be absent; every key in it becomes an env var.
|
|
# Create it before the warm pool, because pod env is stamped at
|
|
# pod creation. See docs/optional-hardening.md.
|
|
- secretRef:
|
|
name: dsh-provider-keys-extra
|
|
optional: true
|
|
env:
|
|
# Empty => DSH derives links from the request Host, which the
|
|
# gateway forwards (plus X-Forwarded-*). Point this at the
|
|
# gateway base URL if you want hard-coded absolute links instead.
|
|
- name: DSH_PUBLIC_URL
|
|
value: ""
|
|
# DSH Host/Origin-fences /api. The gateway forwards the browser's
|
|
# Host, so DSH must trust the public gateway host. Empty is right
|
|
# for port-forward/localhost; for either exposure variant set this
|
|
# to the public host (e.g. dsh.example.com for
|
|
# manifests/exposure/ingress/60-ingress.yaml, or
|
|
# dsh-demo.example.com for the gateway-api-sso/ HTTPRoute).
|
|
- name: DSH_TRUSTED_HOSTS
|
|
value: ""
|
|
# Probes target /favicon.svg: DSH gates / behind its launch-token
|
|
# cookie and answers 401 to an unauthenticated GET, which would
|
|
# otherwise fail readiness and then get the pod killed by liveness.
|
|
# /favicon.svg is served without auth and is the cheapest liveness
|
|
# signal that proves the HTTP server is actually serving requests.
|
|
#
|
|
# Gate liveness/readiness behind a startup probe: a cold start on a
|
|
# small node takes tens of seconds to load plugins and start serving
|
|
# (a resumed sandbox starts cold too). Without it the kubelet can kill
|
|
# DSH mid-startup, and a SIGTERM'd DSH exits 0, which the sandbox
|
|
# controller records as finished. 24 x 5s = 120s, matching the
|
|
# gateway's WAKE_TIMEOUT.
|
|
startupProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
periodSeconds: 5
|
|
failureThreshold: 24
|
|
readinessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 5
|
|
periodSeconds: 5
|
|
failureThreshold: 30
|
|
livenessProbe:
|
|
httpGet:
|
|
path: /favicon.svg
|
|
port: 3080
|
|
initialDelaySeconds: 15
|
|
periodSeconds: 15
|
|
failureThreshold: 3
|
|
# The container only needs to serve HTTP; drop every capability and
|
|
# disallow privilege escalation. DSH writes only to DSH_HOME (PVC).
|
|
securityContext:
|
|
allowPrivilegeEscalation: false
|
|
capabilities:
|
|
drop: ["ALL"]
|
|
seccompProfile:
|
|
type: RuntimeDefault
|
|
resources:
|
|
requests: {cpu: 250m, memory: 512Mi}
|
|
limits: {cpu: "1", memory: 1Gi}
|
|
volumeMounts:
|
|
- name: dsh-home
|
|
mountPath: /home/node/.dsh # DSH_HOME: sessions, config, state
|
|
volumeClaimTemplates:
|
|
- metadata:
|
|
name: dsh-home
|
|
spec:
|
|
accessModes: ["ReadWriteOnce"]
|
|
resources:
|
|
requests:
|
|
storage: 5Gi
|
|
# storageClassName omitted => cluster default (kind & GKE both work)
|