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 29eefd6ae5 Fix idle sweeper suspending claims the gateway does not own (#4)
The sweeper listed every SandboxClaim in NAMESPACE and treated each
dsh-<user> name as one of its own users. A claim applied by hand from
the resource-layer manifests (e.g. 30-claim-alice.yaml) therefore looked
exactly like a gateway user: the idle clock started on first sighting
and the pod was suspended after IDLE_TIMEOUT. That deletes the pod the
README's step 3 logs/port-forward targets, so the walkthrough broke as
soon as the gateway was deployed next to it.

Mark claims created by create_claim() with
aaas.example.com/managed-by=dsh-gateway and skip everything else in
sweep_once() before any idle bookkeeping happens. Document the
ownership boundary in the example docs, the manifest and ADR-5, add
unit coverage for the marker and the skipped sweep, and assert in
run-test-kind.sh that alice's hand-applied claim stays Running while
bob is correctly idle-suspended.

Co-authored-by: SREDevOpsAgents <agents@sredevops.org>
2026-10-21 13:27:19 -03:00

164 lines
5.4 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. Only claims this
# gateway created are swept: a claim applied by hand from the
# resource-layer manifests carries no aaas.example.com/managed-by
# annotation and is never suspended.
- 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