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/50-gateway.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

161 lines
5.2 KiB
YAML

# The gateway: control+data plane that turns the resources into a usable
# browser-facing service. It is a Starlette ASGI app (see gateway/) listening
# on :8080 and exposing:
# GET /healthz unauthenticated health probe
# GET / landing page (signup / token login)
# POST /users, POST /login, ... session cookie auth
# /u/<user>/... HTTP + WebSocket proxy to the user's DSH
#
# Image: ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:gateway
# For local kind development you can build and load a local tag instead, then
# change `image` below to it:
# docker build -t dsh-aaas-gateway:demo gateway/
# kind load docker-image dsh-aaas-gateway:demo
apiVersion: v1
kind: ServiceAccount
metadata:
name: dsh-gateway
namespace: dsh-demo
---
# Least privilege:
# - claims are created/deleted per user (signup/delete);
# - sandboxes are read, and patched only to flip operatingMode (suspend/resume);
# - pods are read, and pods/log is read to capture DSH's launch token from
# the startup log line (`dsh web: ...?token=...`).
# configmaps are not needed: all state is in memory / claim annotations.
apiVersion: rbac.authorization.k8s.io/v1
kind: Role
metadata:
name: dsh-gateway
namespace: dsh-demo
rules:
- apiGroups: ["extensions.agents.x-k8s.io"]
resources: ["sandboxclaims"]
verbs: ["get", "list", "create", "delete"]
- apiGroups: ["agents.x-k8s.io"]
resources: ["sandboxes"]
verbs: ["get", "list", "patch"]
- apiGroups: [""]
resources: ["pods"]
verbs: ["get", "list"]
- apiGroups: [""]
resources: ["pods/log"]
verbs: ["get"]
---
apiVersion: rbac.authorization.k8s.io/v1
kind: RoleBinding
metadata:
name: dsh-gateway
namespace: dsh-demo
roleRef:
apiGroup: rbac.authorization.k8s.io
kind: Role
name: dsh-gateway
subjects:
- kind: ServiceAccount
name: dsh-gateway
namespace: dsh-demo
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: dsh-gateway
namespace: dsh-demo
spec:
# Single replica BY DESIGN: the idle clock, in-flight counters and the
# per-(user, pod, Host) DSH cookie cache are in-process memory. Running two
# replicas would fragment that state (double suspend/resume races, repeated
# log-token handshakes). Scale only after moving state to a shared store.
replicas: 1
selector:
matchLabels:
app: dsh-gateway
template:
metadata:
labels:
app: dsh-gateway
spec:
serviceAccountName: dsh-gateway
securityContext:
runAsNonRoot: true
runAsUser: 10000 # matches USER in gateway/Dockerfile
runAsGroup: 10000
seccompProfile:
type: RuntimeDefault
containers:
- name: gateway
image: ghcr.io/sredevopsorg/deepseek-kubernetes-sandbox:gateway
imagePullPolicy: IfNotPresent
securityContext:
allowPrivilegeEscalation: false
readOnlyRootFilesystem: true
capabilities:
drop: ["ALL"]
ports:
- name: http
containerPort: 8080
env:
- name: NAMESPACE
value: dsh-demo
- name: POOL
value: dsh-pool
# Seconds a sandbox may sit idle before the sweeper suspends it
# (pod deleted, PVC kept), and the max time a proxy request waits
# for a suspended sandbox to become Ready again.
- name: IDLE_TIMEOUT
value: "60"
- name: WAKE_TIMEOUT
value: "120"
# Container name inside the per-user sandbox pods whose logs carry
# the DSH launch token.
- name: DSH_CONTAINER
value: dsh-web
# Cookie dsh_gw_session is HttpOnly + SameSite=Lax. Set to "true"
# when this Service is reached over HTTPS (e.g. the optional
# 60-ingress.yaml with TLS); "false" keeps the plain-HTTP demo
# usable via port-forward.
- name: COOKIE_SECURE
value: "false"
# Reject proxied request bodies larger than this (413).
- name: MAX_BODY_MB
value: "32"
# /healthz is unauthenticated and returns 200 without touching the
# cluster, so it is safe for both readiness and liveness.
readinessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 5
periodSeconds: 5
failureThreshold: 3
livenessProbe:
httpGet:
path: /healthz
port: 8080
initialDelaySeconds: 10
periodSeconds: 10
failureThreshold: 3
resources:
requests: {cpu: 50m, memory: 128Mi}
limits: {cpu: 500m, memory: 256Mi}
volumeMounts:
# readOnlyRootFilesystem leaves no writable HOME/tmp; the image sets
# HOME=/tmp, so back it with scratch space. No state lives here.
- name: tmp
mountPath: /tmp
volumes:
- name: tmp
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: dsh-gateway
namespace: dsh-demo
spec:
selector:
app: dsh-gateway
ports:
- port: 8080
targetPort: 8080