Compare commits

...

3 Commits

Author SHA1 Message Date
will.anderson fd6df322f6 ci: merge deploy into ci.yaml to fix orphaned-job race
Neuron Soul CI / build (push) Successful in 7m30s
Neuron Soul CI / deploy (push) Failing after 6m54s
Neuron Soul CI / build (pull_request) Failing after 10m27s
Neuron Soul CI / deploy (pull_request) Failing after 14m36s
Both ci.yaml and deploy-gke.yaml triggered on push/main and shared the
neuron-runner concurrency group. Gitea's cancel-in-progress:false protects
running jobs but not queued ones — a new push arriving while a build was
in progress cancelled the queued deploy job from the previous push, leaving
the soul permanently at 0/0 replicas on GKE.

Fix: add deploy as a needs:build job in ci.yaml so build+deploy are a single
workflow instance. One push queues one instance — no more orphaned deploys.
deploy-gke.yaml is demoted to workflow_dispatch-only for manual slot overrides.
2026-06-28 15:05:07 -05:00
will.anderson 20d279598a ci: also remove unnecessary foundation/el checkout (elb not called)
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Has been cancelled
2026-06-28 14:54:47 -05:00
will.anderson 9dade105b6 ci: skip elb on Linux — compile dist/soul.c directly to prevent OOM
Neuron Soul CI / build (push) Has been cancelled
Deploy Soul to GKE / deploy (push) Has been cancelled
elb runs elc which consumes 24GB+ virtual memory on the 16GB GCE runner,
OOM-killing the runner process and crashing the VM. We already restore the
repo's pre-built soul.c immediately after elb runs, so elb's output is
discarded anyway. Skip elb entirely: download only the El runtime headers
and compile dist/soul.c directly.

Root cause: runner VM was unresponsive for 7+ weeks due to repeated elc
OOM kills. VM was manually reset 2026-06-28 to restore CI.
2026-06-28 14:53:09 -05:00
2 changed files with 242 additions and 62 deletions
+235 -51
View File
@@ -9,8 +9,10 @@ on:
- main - main
workflow_dispatch: workflow_dispatch:
# Same group as deploy-gke so builds and deploys queue behind each other. # Serialize all activity on the single GCE runner.
# Prevents concurrent Docker daemon exhaustion on the single GCE runner. # With build+deploy in the same workflow, a new push queues a single
# workflow instance — not two competing ones — so the deploy job is
# never orphaned by a cancellation race.
concurrency: concurrency:
group: neuron-runner group: neuron-runner
cancel-in-progress: false cancel-in-progress: false
@@ -29,12 +31,6 @@ jobs:
- name: Checkout - name: Checkout
uses: actions/checkout@v4 uses: actions/checkout@v4
- name: Checkout foundation/el (ELP source for soul.el imports)
run: |
git clone https://git.neuralplatform.ai/neuron-technologies/el.git \
--depth=1 --branch=main \
../foundation/el
- name: Install build dependencies - name: Install build dependencies
run: | run: |
apt-get update -qq apt-get update -qq
@@ -43,7 +39,7 @@ jobs:
> /etc/apt/sources.list.d/google-cloud-sdk.list > /etc/apt/sources.list.d/google-cloud-sdk.list
apt-get update -qq && apt-get install -y google-cloud-cli apt-get update -qq && apt-get install -y google-cloud-cli
- name: Download El SDK from Artifact Registry - name: Download El runtime from Artifact Registry
env: env:
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }} GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
run: | run: |
@@ -51,10 +47,12 @@ jobs:
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
gcloud config set project neuron-785695 gcloud config set project neuron-785695
rm -rf /opt/el/dist /opt/el/runtime rm -rf /opt/el/runtime
mkdir -p /opt/el/dist/platform /opt/el/dist/bin /opt/el/runtime mkdir -p /opt/el/runtime
# Get latest version of each package # Get latest version of each runtime package (elc/elb not needed — we compile
# dist/soul.c directly; running elb on Linux OOM-kills the runner, and we
# always use the repo's pre-built soul.c anyway).
get_latest() { get_latest() {
gcloud artifacts versions list \ gcloud artifacts versions list \
--repository=foundation-prod \ --repository=foundation-prod \
@@ -66,22 +64,10 @@ jobs:
--format="value(name)" 2>/dev/null | awk -F/ '{print $NF}' --format="value(name)" 2>/dev/null | awk -F/ '{print $NF}'
} }
ELC_VER=$(get_latest el-elc)
ELB_VER=$(get_latest el-elb)
RC_VER=$(get_latest el-runtime-c) RC_VER=$(get_latest el-runtime-c)
RH_VER=$(get_latest el-runtime-h) RH_VER=$(get_latest el-runtime-h)
echo "Downloading elc@${ELC_VER} elb@${ELB_VER} runtime@${RC_VER}" echo "Downloading runtime@${RC_VER}"
gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-elc --version="${ELC_VER}" \
--destination=/opt/el/dist/platform/
gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-elb --version="${ELB_VER}" \
--destination=/opt/el/dist/bin/
gcloud artifacts generic download \ gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \ --repository=foundation-prod --location=us-central1 --project=neuron-785695 \
@@ -93,39 +79,20 @@ jobs:
--package=el-runtime-h --version="${RH_VER}" \ --package=el-runtime-h --version="${RH_VER}" \
--destination=/opt/el/runtime/ --destination=/opt/el/runtime/
# Downloaded files keep original names; rename to canonical paths
mv /opt/el/dist/platform/elc* /opt/el/dist/platform/elc 2>/dev/null || true
mv /opt/el/dist/bin/elb* /opt/el/dist/bin/elb 2>/dev/null || true
mv /opt/el/runtime/el_runtime.c* /opt/el/runtime/el_runtime.c 2>/dev/null || true mv /opt/el/runtime/el_runtime.c* /opt/el/runtime/el_runtime.c 2>/dev/null || true
mv /opt/el/runtime/el_runtime.h* /opt/el/runtime/el_runtime.h 2>/dev/null || true mv /opt/el/runtime/el_runtime.h* /opt/el/runtime/el_runtime.h 2>/dev/null || true
echo "El runtime ready: $(ls /opt/el/runtime/)"
chmod +x /opt/el/dist/platform/elc /opt/el/dist/bin/elb
echo "El SDK ready"
/opt/el/dist/platform/elc --version || true
- name: Build neuron soul binary - name: Build neuron soul binary
run: | run: |
ELB=/opt/el/dist/bin/elb
ELC=/opt/el/dist/platform/elc
RUNTIME=/opt/el/runtime RUNTIME=/opt/el/runtime
# Preserve the pre-compiled dist/soul.c from the repo before running elb. # Compile the self-contained translation unit directly from dist/soul.c.
# elb may overwrite it during compilation; we always want the repo version # dist/soul.c is the authoritative combined unit maintained in the repo
# since it contains the patched self-contained translation unit (all modules # regenerated on macOS by running elb (which succeeds on arm64/macOS ld but
# inlined, workspace scope fix, agentic dedup fix, etc.). # fails on Linux due to duplicate strong symbols). We skip the elb step here
cp dist/soul.c /tmp/soul.c.prebuilt # entirely: elb on Linux would OOM the runner (elc uses 24GB+ virtual memory
# on a 16GB host) and we always restore from the repo's soul.c anyway.
# Compile all El modules to C via elb.
# elb fails at link on Linux (GNU ld rejects duplicate strong symbols that
# macOS ld accepts silently) — that's expected and captured with || true.
$ELB --elc=$ELC --runtime=$RUNTIME/el_runtime.c || true
# Restore the repo's self-contained soul.c — elb may have overwritten it
# with a partial (non-inlined) version that lacks module-level definitions.
cp /tmp/soul.c.prebuilt dist/soul.c
# Compile the self-contained translation unit. No --allow-multiple-definition
# needed since soul.c inlines all modules.
mkdir -p dist mkdir -p dist
cc -O2 -DHAVE_CURL \ cc -O2 -DHAVE_CURL \
-I$RUNTIME \ -I$RUNTIME \
@@ -163,3 +130,220 @@ jobs:
echo "Published neuron-soul@${VERSION}" echo "Published neuron-soul@${VERSION}"
rm -f /tmp/gcp-key.json rm -f /tmp/gcp-key.json
deploy:
runs-on: ubuntu-latest
needs: build
# Only deploy on push to main, not on PRs or manual workflow_dispatch without intent.
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
env:
USE_GKE_GCLOUD_AUTH_PLUGIN: "True"
steps:
- name: Free disk space
run: |
df -h /
docker system prune -af --volumes 2>/dev/null || true
rm -rf /tmp/.act-* /tmp/act-* 2>/dev/null || true
df -h /
- name: Checkout
uses: actions/checkout@v4
- name: Install dependencies
run: |
apt-get update -qq
apt-get install -y --no-install-recommends \
ca-certificates curl apt-transport-https kubectl
echo "deb [trusted=yes] https://packages.cloud.google.com/apt cloud-sdk main" \
> /etc/apt/sources.list.d/google-cloud-sdk.list
apt-get update -qq && apt-get install -y google-cloud-cli google-cloud-cli-gke-gcloud-auth-plugin
- name: Authenticate to GCP
env:
GCP_SA_KEY: ${{ secrets.GCP_SA_KEY }}
run: |
echo "${GCP_SA_KEY}" > /tmp/gcp-key.json
gcloud auth activate-service-account --key-file=/tmp/gcp-key.json
gcloud config set project neuron-785695
gcloud auth configure-docker us-central1-docker.pkg.dev --quiet
- name: Get GKE credentials
run: |
gcloud container clusters get-credentials neuron-platform \
--region=us-central1 \
--project=neuron-785695
- name: Determine image tag and slot
id: vars
run: |
# GITEA_SHA is set by the Gitea runner; fall back to GITHUB_SHA for
# compatibility with older Forgejo/Gitea versions.
RAW_SHA="${GITEA_SHA:-${GITHUB_SHA:-}}"
SHA="${RAW_SHA:0:8}"
if [ -z "$SHA" ]; then
# Last resort: read from git directly
SHA=$(git rev-parse --short=8 HEAD 2>/dev/null || echo "unknown")
fi
IMAGE="us-central1-docker.pkg.dev/neuron-785695/neuron-api/neuron-soul:${SHA}"
echo "sha=${SHA}" >> "$GITEA_OUTPUT"
echo "image=${IMAGE}" >> "$GITEA_OUTPUT"
# Determine which slot is currently idle (0 replicas = idle slot)
# If both are at 0 (fresh deploy), default to blue
BLUE_REPLICAS=$(kubectl get deployment/neuron-mcp-blue \
-n neuron-prod \
-o jsonpath='{.spec.replicas}' 2>/dev/null || echo "0")
GREEN_REPLICAS=$(kubectl get deployment/neuron-mcp-green \
-n neuron-prod \
-o jsonpath='{.spec.replicas}' 2>/dev/null || echo "0")
echo " Blue replicas: ${BLUE_REPLICAS}"
echo " Green replicas: ${GREEN_REPLICAS}"
if [ "${GREEN_REPLICAS}" -eq 0 ] && [ "${BLUE_REPLICAS}" -gt 0 ]; then
SLOT="green"
elif [ "${BLUE_REPLICAS}" -eq 0 ] && [ "${GREEN_REPLICAS}" -gt 0 ]; then
SLOT="blue"
else
# Fresh cluster or both idle — deploy to blue first
SLOT="blue"
fi
echo "slot=${SLOT}" >> "$GITEA_OUTPUT"
echo " Deploying to slot: ${SLOT}"
- name: Prepare build artifacts
run: |
# Pre-download soul binary and El SDK so the Dockerfile can COPY them
# from the build context instead of authenticating inside the build.
mkdir -p build-artifacts
# ── soul binary ────────────────────────────────────────────────────────
# The build job (same workflow run) just published this version.
SOUL_VER=$(gcloud artifacts versions list \
--repository=foundation-prod \
--location=us-central1 \
--project=neuron-785695 \
--package=neuron-soul \
--sort-by="~createTime" \
--limit=1 \
--format="value(name)" 2>/dev/null | awk -F/ '{print $NF}')
echo "Downloading neuron-soul@${SOUL_VER}"
gcloud artifacts generic download \
--repository=foundation-prod \
--location=us-central1 \
--project=neuron-785695 \
--package=neuron-soul \
--version="${SOUL_VER}" \
--destination=build-artifacts/
mv build-artifacts/neuron* build-artifacts/neuron 2>/dev/null || true
chmod +x build-artifacts/neuron
# ── El SDK (for engram source compilation inside the Docker build) ────
ELC_VER=$(gcloud artifacts versions list \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-elc --sort-by="~createTime" --limit=1 \
--format="value(name)" 2>/dev/null | awk -F/ '{print $NF}')
gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-elc --version="${ELC_VER}" --destination=build-artifacts/
mv build-artifacts/elc* build-artifacts/elc 2>/dev/null || true
chmod +x build-artifacts/elc
RC_VER=$(gcloud artifacts versions list \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-runtime-c --sort-by="~createTime" --limit=1 \
--format="value(name)" 2>/dev/null | awk -F/ '{print $NF}')
gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-runtime-c --version="${RC_VER}" --destination=build-artifacts/
mv build-artifacts/el_runtime.c* build-artifacts/el_runtime.c 2>/dev/null || true
RH_VER=$(gcloud artifacts versions list \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-runtime-h --sort-by="~createTime" --limit=1 \
--format="value(name)" 2>/dev/null | awk -F/ '{print $NF}')
gcloud artifacts generic download \
--repository=foundation-prod --location=us-central1 --project=neuron-785695 \
--package=el-runtime-h --version="${RH_VER}" --destination=build-artifacts/
mv build-artifacts/el_runtime.h* build-artifacts/el_runtime.h 2>/dev/null || true
echo "Build artifacts ready:"
ls -lh build-artifacts/
- name: Clone engram source for Docker build context
run: |
# The Dockerfile builds engram from source (no published AR package).
# Clone the engram repo into ./engram/ so it's available in the build context.
git clone http://34.31.145.131/neuron-technologies/engram.git \
--depth=1 --branch=main \
engram
echo "Engram source ready at ./engram/src/server.el"
- name: Build and push Docker image
run: |
IMAGE="${{ steps.vars.outputs.image }}"
echo "Building ${IMAGE}..."
docker build \
--tag "${IMAGE}" \
--tag "us-central1-docker.pkg.dev/neuron-785695/neuron-api/neuron-soul:latest" \
.
echo "Pushing ${IMAGE}..."
docker push "${IMAGE}"
docker push "us-central1-docker.pkg.dev/neuron-785695/neuron-api/neuron-soul:latest"
- name: Blue-green deploy to GKE
run: |
chmod +x scripts/blue-green-deploy.sh
scripts/blue-green-deploy.sh \
--image "${{ steps.vars.outputs.image }}" \
--slot "${{ steps.vars.outputs.slot }}"
- name: Update infrastructure manifests
if: success()
env:
INFRA_GIT_TOKEN: ${{ secrets.INFRA_GIT_TOKEN }}
run: |
SLOT="${{ steps.vars.outputs.slot }}"
if [ "$SLOT" = "blue" ]; then IDLE="green"; else IDLE="blue"; fi
git clone "http://${INFRA_GIT_TOKEN}@34.31.145.131/neuron-technologies/infrastructure.git" \
--depth=1 --branch=main /tmp/infra-update
cd /tmp/infra-update
DEPLOY_DIR="platform/k8s/neuron-mcp"
sed -i "s/^ replicas: .*/ replicas: 1/" "${DEPLOY_DIR}/deployment-${SLOT}.yaml"
sed -i "s/^ replicas: .*/ replicas: 0/" "${DEPLOY_DIR}/deployment-${IDLE}.yaml"
echo " deployment-${SLOT}.yaml: replicas set to 1"
echo " deployment-${IDLE}.yaml: replicas set to 0"
git config user.email "ci@neurontechnologies.ai"
git config user.name "Neuron CI"
git add "${DEPLOY_DIR}/deployment-blue.yaml" "${DEPLOY_DIR}/deployment-green.yaml"
git diff --staged --quiet && { echo "No manifest changes needed"; exit 0; }
git commit -m "ci: neuron-mcp replica sync after blue-green swap to ${SLOT}"
git push origin main
echo "Infrastructure manifests updated: ${SLOT}=1, ${IDLE}=0"
- name: Verify deployment
run: |
SLOT="${{ steps.vars.outputs.slot }}"
echo "Verifying neuron-mcp-${SLOT} is healthy..."
kubectl rollout status deployment/"neuron-mcp-${SLOT}" \
--namespace=neuron-prod \
--timeout=8m
echo "Active service endpoints:"
kubectl get endpoints neuron-mcp -n neuron-prod
echo "Pod status:"
kubectl get pods -n neuron-prod -l app=neuron-mcp
- name: Cleanup
if: always()
run: rm -f /tmp/gcp-key.json
+7 -11
View File
@@ -1,16 +1,13 @@
name: Deploy Soul to GKE name: Deploy Soul to GKE (manual)
# Triggers on push to main — after the soul binary is built and published # MANUAL OVERRIDE ONLY — push-triggered deploys now run as the 'deploy' job
# by ci.yaml, this workflow builds the Docker image and blue-green deploys # in ci.yaml (needs: build), which eliminates the two-workflow concurrency
# to the neuron-prod namespace on GKE. # race that was cancelling queued deploy runs.
# #
# This workflow runs AFTER ci.yaml has published the neuron-soul generic # Use this workflow only when you need to deploy a specific slot manually
# artifact to Artifact Registry. The Docker build downloads that binary. # (e.g. rollback, force a slot override) without triggering a full CI build.
on: on:
push:
branches:
- main
workflow_dispatch: workflow_dispatch:
inputs: inputs:
slot: slot:
@@ -18,8 +15,7 @@ on:
required: false required: false
default: "green" default: "green"
# Serialize all builds on this runner — concurrent jobs exhaust the Docker daemon. # Manual deploys still share the runner serialization group.
# A queued deploy runs after the in-progress build finishes.
concurrency: concurrency:
group: neuron-runner group: neuron-runner
cancel-in-progress: false cancel-in-progress: false