mirror of
https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git
synced 2026-11-03 01:13:24 +00:00
c193ed21a4
DSH takes tens of seconds to load plugins and start serving on a small node, and every resume starts cold. The liveness budget (initialDelay 15s, period 15s, failureThreshold 3) is shorter than that, so the kubelet killed the container mid-startup. DSH exits 0 on SIGTERM, which the sandbox controller records as PodSucceeded/Finished - the pod is then never recreated and the sandbox stays unusable until a manual suspend/resume cycle. Gate liveness and readiness behind a startupProbe on /favicon.svg with a 120s budget (24 x 5s, matching the gateway's WAKE_TIMEOUT). Liveness still catches a genuinely hung server once startup succeeds. Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
97 lines
3.8 KiB
YAML
97 lines
3.8 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/.
|
|
#
|
|
# Prerequisites (create these first, or apply 00-prereqs.yaml from the
|
|
# examples directory):
|
|
# - 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).
|
|
# The agent-sandbox controller (v1.0.7, 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)
|
|
podTemplate:
|
|
spec:
|
|
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") recursively ORs 0660 into
|
|
# every file each time the pod starts, so a recreated/resumed sandbox
|
|
# comes back with 0660 and crash-loops. OnRootMismatch skips that walk
|
|
# once the volume root already has the fsGroup ownership/mode from the
|
|
# first mount. Keep in sync with
|
|
# examples/dsh-agents-as-a-service/10-sandboxtemplate.yaml.
|
|
fsGroupChangePolicy: OnRootMismatch
|
|
containers:
|
|
- name: dsh-web
|
|
image: ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:dsh-v0.2.1-rc.2
|
|
imagePullPolicy: IfNotPresent
|
|
ports:
|
|
- name: web
|
|
containerPort: 3080
|
|
envFrom:
|
|
- secretRef:
|
|
name: dsh-provider-keys # Secret with key DEEPSEEK_API_KEY
|
|
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 expose DSH behind an Ingress, so
|
|
# requests forwarded with the browser's Host are accepted.
|
|
- 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
|