1
0
mirror of https://github.com/sredevopsorg/deepseek-kubernetes-sandbox.git synced 2026-11-03 01:13:24 +00:00
Files
deepseek-kubernetes-sandbox/examples/dsh-agents-as-a-service/10-sandboxtemplate.yaml
SREDevOps.org Agent 6301c21bea Make DSH agents-as-a-service browser-usable; fix probe crash-loop (#3)
* Rewrite DSH gateway for browser sessions, HTTP and WebSocket

- Replace the Flask proxy with a Starlette ASGI app (uvicorn factory),
  keeping the control plane (claims, wake/suspend, idle sweeper).
- Add HttpOnly gateway sessions and a server-side DSH launch-token
  handshake: read the token from pod logs, exchange it for a dsh-auth
  cookie, cache per (user, pod UID, Host), refresh once on 401.
- Proxy HTTP/SSE and WebSocket (/api/remote.mux) under /u/<user>/, with
  header stripping/injection, Location rewriting and wake-on-connect.
- Add a landing/signup/login page, health endpoint, pinned dependencies,
  a read-only-rootfs gateway image, 87 cluster-free tests and docs.

* Fix DSH probe crash-loop and harden gateway manifests

- Probe /favicon.svg instead of /: DSH gates / behind its launch-token
  cookie and returns 401, which made warm-pool pods crash-loop.
- Pass DSH_TRUSTED_HOSTS through the entrypoint as --trusted-host args
  for public/ingress hosts; keep localhost trusted.
- Deploy the published :gateway image, add pods/pods-log RBAC, /healthz
  probes, read-only rootfs with a /tmp emptyDir and non-root security.
- Add optional Traefik Ingress and document the prerequisites.

* Update CI, smoke tests, build tooling and docs

- Run gateway pytest/ruff and build/smoke-test the image in CI.
- Parameterize the DSH build version and pnpm version inputs.
- Exercise cookie signup, HTML proxy, WebSocket auth, suspend/wake and
  delete in run-test-kind.sh.
- Add Makefile/build.sh targets and document the architecture, handshake,
  probes, trusted hosts, troubleshooting and limitations.

---------

Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
2026-10-21 12:10:03 -03:00

101 lines
4.0 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 key
# is injected via envFrom, and claims that would bypass the warm pool are
# rejected outright (see 40-claim-rejected.yaml).
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
# No gateway pod scopes ingress in this standalone demo, so the
# NetworkPolicy is left unmanaged. 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
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
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 the optional Ingress set this to
# the same host as 60-ingress.yaml (e.g. dsh.example.com).
- 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.
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)