mirror of
https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git
synced 2026-11-03 01:13:24 +00:00
feat(repo)!: restructure around the dsh-harness image and one example per implementation
- the root Dockerfile is the primary artifact; versions.env is the single source of truth
- merge gateway-api/dsh-demo into examples/dsh-agents-as-a-service (manifests/, exposure variants)
- move the single-tenant template into examples/minimal-single-tenant
- publish the gateway as a nested package under the repository image
- mirror the DSH ref for release identities (first release dsh-v0.2.1-rc.2-r2)
- CI: lint/python/manifests/gateway-image, reusable multi-arch build, tag-driven release, weekly e2e
- docs: README, docs/{main-image,examples,gitflow,versioning}, example READMEs, AGENTS.md, governance
- SSO is opt-in again; gateway pull policy and cookie defaults match the documented demo
BREAKING CHANGE: example manifest paths, the gateway image name, and the removal
of deploy/ and gateway-api/ affect existing deployments; see the migration table
in README.md.
This commit is contained in:
SREDevOpsAgents
@@ -0,0 +1,128 @@
|
||||
# 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 key
|
||||
# is 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 gateway does not manage NetworkPolicy, so it is left
|
||||
# unmanaged here. A production platform would use
|
||||
# networkPolicyManagement: Managed and restrict ingress to its gateway on
|
||||
# :3080 — with the shared provider key, that NetworkPolicy is the per-user
|
||||
# isolation boundary.
|
||||
networkPolicyManagement: Unmanaged
|
||||
|
||||
podTemplate:
|
||||
spec:
|
||||
# DSH Web is multi-arch (amd64 + arm64); no arch nodeSelector needed.
|
||||
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.2-r2
|
||||
imagePullPolicy: IfNotPresent
|
||||
ports:
|
||||
- name: web
|
||||
containerPort: 3080
|
||||
envFrom:
|
||||
- secretRef:
|
||||
name: dsh-provider-keys
|
||||
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)
|
||||
Reference in New Issue
Block a user