feat: embed k3s to run soul-demo as self-healing k8s pods #13

Merged
will.anderson merged 2 commits from feat/k3s-embedded-soul into dev 2026-05-09 17:40:46 +00:00
7 changed files with 183 additions and 17 deletions
+3
View File
@@ -211,6 +211,7 @@ jobs:
--image "$IMAGE" \
--region us-central1 \
--project neuron-785695 \
--execution-environment gen2 \
--service-account neuron-marketing-sa@neuron-785695.iam.gserviceaccount.com \
--update-env-vars "NODE_ENV=production,STRIPE_PUBLISHABLE_KEY=pk_test_51TPoHnJg9Fv1D3AUp1FEMcy4MGlKRZqs4scW66kjQFQjWofmNc2rottzXzDaXekHvuw1OQpyp2WCIsc7O5fXIG0G00HQQrkdGX,GCS_SHARE_BUCKET=neuron-shares-prod,SUPABASE_ANON_KEY=eyJhbGciOiJIUzI1NiIsInR5cCI6IkpXVCJ9.eyJpc3MiOiJzdXBhYmFzZSIsInJlZiI6Im9jb2pzZ2hhb25sdHVuaWRrenB3Iiwicm9sZSI6ImFub24iLCJpYXQiOjE3Nzc2NDIxNjgsImV4cCI6MjA5MzIxODE2OH0.e0FVFw1aahnrBVvnkR5R8a-RxCx095U8o_gsk7Quq3E,NEURON_LLM_0_FORMAT=anthropic,NEURON_LLM_0_MODEL=claude-sonnet-4-5,NEURON_LLM_0_URL=https://api.anthropic.com/v1/messages" \
--update-secrets "SUPABASE_SERVICE_KEY=supabase-service-key:latest,NEURON_LLM_0_KEY=anthropic-api-key:latest,ANTHROPIC_API_KEY=anthropic-api-key:latest,STRIPE_SECRET_KEY=stripe-secret-key-stage:latest,STRIPE_WEBHOOK_SECRET=stripe-webhook-secret-stage:latest,STRIPE_PRICE_PROFESSIONAL=stripe-price-professional-stage:latest,STRIPE_PRICE_FOUNDING=stripe-price-founding-stage:latest,STRIPE_PRICE_FAMILY_CHILD=stripe-price-family-child:latest,RESEND_API_KEY=resend-api-key:latest,DOCUSEAL_WEBHOOK_TOKEN=docuseal-webhook-token:latest" \
@@ -228,6 +229,7 @@ jobs:
gcloud run services update marketing-stage \
--region us-central1 --project neuron-785695 \
--execution-environment gen2 \
--update-env-vars "NEURON_ORIGIN=${STAGE_URL}" \
--quiet
@@ -265,6 +267,7 @@ jobs:
--image "$IMAGE" \
--region "$region" \
--project neuron-785695 \
--execution-environment gen2 \
--quiet
}
deploy us-central1 marketing-prod-us &
+7
View File
@@ -31,3 +31,10 @@ src/assets/js/
!dist/elhtml_impl.c
!dist/entrypoint.sh
!dist/engram-snapshot.json
!dist/Dockerfile.soul-demo
!dist/k3s-soul-demo.yaml
# Build artifacts produced by the soul-demo packaging step in build-stage.sh
dist/soul-demo
dist/soul-demo-snapshot.json
dist/soul-demo-image.tar
+23 -2
View File
@@ -17,6 +17,7 @@ FROM debian:bookworm-slim AS builder
RUN apt-get update \
&& apt-get install -y --no-install-recommends \
build-essential \
curl \
libcurl4-openssl-dev \
libssl-dev \
ca-certificates \
@@ -41,6 +42,10 @@ RUN cc -O2 -rdynamic \
soul-demo.c vessel_stubs.c el_runtime.o \
-lcurl -lpthread -ldl -lm -lssl -lcrypto
# ── Download k3s binary ───────────────────────────────────────────────────────
RUN curl -fL https://github.com/k3s-io/k3s/releases/download/v1.32.4%2Bk3s1/k3s -o /usr/local/bin/k3s \
&& chmod +x /usr/local/bin/k3s
# ── Stage 2: runtime image ────────────────────────────────────────────────────
FROM debian:bookworm-slim
@@ -53,7 +58,9 @@ RUN apt-get update \
&& groupadd -r landing && useradd -r -g landing landing \
&& mkdir -p /srv/landing/assets /srv/landing/js /srv/landing/shares \
&& mkdir -p /srv/soul/engram-demo \
&& chown -R landing:landing /srv/landing /srv/soul
&& chown -R landing:landing /srv/landing /srv/soul \
&& mkdir -p /var/lib/rancher/k3s /tmp/k3s \
&& chown -R landing:landing /var/lib/rancher /tmp/k3s
# neuron-web binary — produced by `elb build` in CI (linux/amd64)
COPY dist/neuron-landing /usr/local/bin/neuron-web
@@ -61,6 +68,17 @@ RUN chmod +x /usr/local/bin/neuron-web
COPY --from=builder /build/soul-demo /usr/local/bin/soul-demo
# k3s binary
COPY --from=builder /usr/local/bin/k3s /usr/local/bin/k3s
# soul-demo OCI image tar — k3s imports this at startup (no registry needed)
RUN mkdir -p /var/lib/rancher/k3s/agent/images
COPY dist/soul-demo-image.tar /var/lib/rancher/k3s/agent/images/soul-demo.tar
# k3s manifests — auto-applied when k3s starts
RUN mkdir -p /var/lib/rancher/k3s/server/manifests
COPY dist/k3s-soul-demo.yaml /var/lib/rancher/k3s/server/manifests/soul-demo.yaml
# Engram snapshot — baked in so soul has memory from cold start
COPY dist/engram-snapshot.json /srv/soul/engram-demo/snapshot.json
@@ -83,8 +101,11 @@ ENV LANDING_ROOT=/srv/landing
ENV PORT=8080
ENV NEURON_HOME=/srv/soul/engram-demo
ENV NEURON_PORT=7772
ENV K3S_DATA_DIR=/var/lib/rancher/k3s
ENV KUBECONFIG=/var/lib/rancher/k3s/server/cred/admin.kubeconfig
USER landing
# k3s requires root to create network namespaces and mount cgroups.
# Cloud Run gen2 sandbox is the security boundary here.
EXPOSE 8080
CMD ["/usr/local/bin/entrypoint.sh"]
+18
View File
@@ -43,4 +43,22 @@ docker build \
-t "marketing:${TAG}" \
.
# Extract soul-demo binary and engram snapshot from built image
echo "==> Packaging soul-demo:local image for k3s..."
CONTAINER_ID=$(docker create "marketing:${TAG}")
docker cp "${CONTAINER_ID}:/usr/local/bin/soul-demo" dist/soul-demo
docker cp "${CONTAINER_ID}:/srv/soul/engram-demo/snapshot.json" dist/soul-demo-snapshot.json 2>/dev/null || true
docker rm "${CONTAINER_ID}"
# Build minimal soul-demo container image
cp dist/soul-demo-snapshot.json dist/engram-snapshot.json 2>/dev/null || true
docker build \
-f dist/Dockerfile.soul-demo \
-t soul-demo:local \
dist/
# Save as OCI tar for k3s to import at startup
docker save soul-demo:local -o dist/soul-demo-image.tar
echo "==> soul-demo:local image saved ($(du -sh dist/soul-demo-image.tar | cut -f1))"
echo "==> Done. marketing:${TAG} built."
+13
View File
@@ -0,0 +1,13 @@
FROM debian:bookworm-slim
RUN apt-get update \
&& apt-get install -y --no-install-recommends libcurl4 libssl3 ca-certificates \
&& rm -rf /var/lib/apt/lists/* \
&& groupadd -r landing && useradd -r -g landing landing \
&& mkdir -p /srv/soul/engram-demo \
&& chown -R landing:landing /srv/soul
COPY soul-demo /usr/local/bin/soul-demo
COPY engram-snapshot.json /srv/soul/engram-demo/snapshot.json
ENV NEURON_HOME=/srv/soul/engram-demo
ENV NEURON_PORT=7772
USER landing
CMD ["/usr/local/bin/soul-demo"]
+29 -15
View File
@@ -1,21 +1,35 @@
#!/usr/bin/env bash
# entrypoint.sh — Start soul-demo then neuron-web in the same container.
#
# soul-demo runs in the background on :7772 (localhost only, not exposed).
# neuron-web runs in the foreground on :8080 (Cloud Run health checks this).
# If neuron-web exits, the container exits. Soul crashing is non-fatal —
# chat will return "demo soul not responding" but the page stays up.
#!/bin/sh
set -e
set -euo pipefail
echo "[entrypoint] Starting k3s server (embedded soul-demo orchestrator)..."
echo "[entrypoint] starting soul-demo on :7772"
/usr/local/bin/soul-demo &
SOUL_PID=$!
# k3s server — single-node mode, disable unused components
# --disable traefik,servicelb: we don't need an ingress or LB
# --disable metrics-server: saves ~50MB RAM
# --write-kubeconfig-mode=644: allow non-root reads
# --data-dir: use the pre-chowned dir
k3s server \
--disable traefik \
--disable servicelb \
--disable metrics-server \
--write-kubeconfig-mode=644 \
--data-dir /var/lib/rancher/k3s \
--node-name soul-node &
# Give the soul a few seconds to load its engram and seed safety nodes
sleep 4
K3S_PID=$!
echo "[entrypoint] soul-demo started (pid=$SOUL_PID)"
echo "[entrypoint] starting neuron-web on :${PORT:-8080}"
echo "[entrypoint] Waiting for k3s to become ready..."
until k3s kubectl get nodes --no-headers 2>/dev/null | grep -q "Ready"; do
sleep 2
done
echo "[entrypoint] k3s ready. soul-demo Deployment will be applied automatically from manifests."
# Wait for soul-demo pod to be Running before starting neuron-web
echo "[entrypoint] Waiting for soul-demo pod..."
until k3s kubectl get pods -l app=soul-demo --no-headers 2>/dev/null | grep -q "Running"; do
sleep 3
done
echo "[entrypoint] soul-demo is running."
echo "[entrypoint] Starting neuron-web on port ${PORT:-8080}..."
exec /usr/local/bin/neuron-web
+90
View File
@@ -0,0 +1,90 @@
---
apiVersion: apps/v1
kind: Deployment
metadata:
name: soul-demo
namespace: default
labels:
app: soul-demo
spec:
replicas: 1
selector:
matchLabels:
app: soul-demo
template:
metadata:
labels:
app: soul-demo
spec:
containers:
- name: soul-demo
image: soul-demo:local
imagePullPolicy: Never
ports:
- containerPort: 7772
env:
- name: NEURON_HOME
value: /srv/soul/engram-demo
- name: NEURON_PORT
value: "7772"
resources:
requests:
cpu: 250m
memory: 256Mi
limits:
cpu: 1000m
memory: 512Mi
livenessProbe:
httpGet:
path: /healthz
port: 7772
initialDelaySeconds: 10
periodSeconds: 15
failureThreshold: 3
readinessProbe:
httpGet:
path: /healthz
port: 7772
initialDelaySeconds: 5
periodSeconds: 10
volumeMounts:
- name: engram-data
mountPath: /srv/soul/engram-demo
volumes:
- name: engram-data
emptyDir: {}
---
apiVersion: v1
kind: Service
metadata:
name: soul-demo
namespace: default
spec:
type: NodePort
selector:
app: soul-demo
ports:
- port: 7772
targetPort: 7772
nodePort: 7772
protocol: TCP
---
apiVersion: autoscaling/v2
kind: HorizontalPodAutoscaler
metadata:
name: soul-demo
namespace: default
spec:
scaleTargetRef:
apiVersion: apps/v1
kind: Deployment
name: soul-demo
minReplicas: 1
maxReplicas: 8
metrics:
- type: Resource
resource:
name: cpu
target:
type: Utilization
averageUtilization: 80