Files
foxhunt/infra/k8s/argo/ci-pipeline-template.yaml
jgrusewski 87a37ac020 fix: detect config/training + config/gpu changes as ml-changed
TOML training profiles are include_str!() into the ml binary at compile
time. Changes to config/training/ or config/gpu/ must trigger GPU test
rebuild, otherwise the binary runs with stale embedded defaults.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
2026-03-22 10:56:44 +01:00

663 lines
23 KiB
YAML

apiVersion: argoproj.io/v1alpha1
kind: WorkflowTemplate
metadata:
name: ci-pipeline
namespace: foxhunt
labels:
app.kubernetes.io/name: ci-pipeline
app.kubernetes.io/part-of: foxhunt
spec:
activeDeadlineSeconds: 7200
serviceAccountName: argo-workflow
entrypoint: pipeline
onExit: notify-result
podMetadata:
labels:
app.kubernetes.io/component: ci-pipeline
app.kubernetes.io/part-of: foxhunt
podGC:
strategy: OnPodCompletion
ttlStrategy:
secondsAfterCompletion: 3600
volumes:
- name: git-ssh-key
secret:
secretName: argo-git-ssh-key
defaultMode: 256
- name: registry-auth
secret:
secretName: gitlab-registry
optional: true
items:
- key: .dockerconfigjson
path: config.json
- name: cargo-target-cpu
persistentVolumeClaim:
claimName: cargo-target-cpu
arguments:
parameters:
- name: commit-sha
value: HEAD
- name: commits-json
value: "[]"
templates:
# ── DAG: orchestrate pipeline ──
# Compile + deploy moved to compile-and-deploy-template.yaml (manual trigger).
# This pipeline handles infra, docker images, dashboard, and argo templates only.
- name: pipeline
dag:
tasks:
- name: detect-changes
template: detect-changes
- name: build-web-dashboard
depends: "detect-changes"
template: build-web-dashboard
when: "{{tasks.detect-changes.outputs.parameters.needs-dashboard}} == true"
- name: rebuild-ci-builder
depends: "detect-changes"
templateRef:
name: build-ci-image
template: build
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
- name: dockerfile
value: Dockerfile.ci-builder
- name: image-name
value: ci-builder
when: "{{tasks.detect-changes.outputs.parameters.docker-images}} == true"
- name: rebuild-ci-builder-cpu
depends: "detect-changes"
templateRef:
name: build-ci-image
template: build
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
- name: dockerfile
value: Dockerfile.ci-builder-cpu
- name: image-name
value: ci-builder-cpu
when: "{{tasks.detect-changes.outputs.parameters.docker-images}} == true"
- name: rebuild-runtime
depends: "detect-changes"
templateRef:
name: build-ci-image
template: build
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
- name: dockerfile
value: Dockerfile.foxhunt-runtime
- name: image-name
value: foxhunt-runtime
when: "{{tasks.detect-changes.outputs.parameters.docker-images}} == true"
- name: rebuild-training-runtime
depends: "detect-changes"
templateRef:
name: build-ci-image
template: build
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
- name: dockerfile
value: Dockerfile.foxhunt-training-runtime
- name: image-name
value: foxhunt-training-runtime
when: "{{tasks.detect-changes.outputs.parameters.docker-images}} == true"
- name: test-gate
depends: "detect-changes && (rebuild-ci-builder-cpu.Succeeded || rebuild-ci-builder-cpu.Skipped)"
template: test-gate
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
when: "{{tasks.detect-changes.outputs.parameters.needs-code}} == true"
- name: apply-argo-templates
depends: "detect-changes.Succeeded && (rebuild-ci-builder-cpu.Succeeded || rebuild-ci-builder-cpu.Skipped)"
template: apply-argo-templates
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
when: "{{tasks.detect-changes.outputs.parameters.needs-argo-templates}} == true"
- name: terragrunt-apply
depends: "detect-changes.Succeeded && (rebuild-ci-builder-cpu.Succeeded || rebuild-ci-builder-cpu.Skipped)"
template: terragrunt-apply
arguments:
parameters:
- name: commit-sha
value: "{{workflow.parameters.commit-sha}}"
when: "{{tasks.detect-changes.outputs.parameters.needs-infra}} == true"
- name: gpu-test
depends: "detect-changes"
template: submit-gpu-test
when: "{{tasks.detect-changes.outputs.parameters.ml-changed}} == true"
# ── detect-changes: classify changed files to gate downstream steps ──
- name: detect-changes
nodeSelector:
k8s.scaleway.com/pool-name: platform
container:
image: gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/foxhunt-runtime:latest
command: ["/bin/sh", "-c"]
env:
- name: COMMITS_JSON
value: "{{workflow.parameters.commits-json}}"
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 500m
memory: 256Mi
args:
- |
set -e
cat <<'SCRIPT' > /tmp/detect.sh
#!/bin/sh
set -e
# Extract changed file paths from webhook JSON using grep+sed (no jq dependency).
CHANGED_FILES=$(echo "$COMMITS_JSON" \
| grep -oE '"(added|modified|removed)":\[[^]]*\]' \
| sed 's/"added"://;s/"modified"://;s/"removed"://' \
| tr ',' '\n' | tr -d '[]"' | sed '/^$/d' | sort -u \
|| echo "")
if [ -z "$CHANGED_FILES" ]; then
echo "No changed files detected — triggering full rebuild"
CHANGED_FILES="Cargo.toml"
fi
echo "=== Changed files ==="
echo "$CHANGED_FILES"
echo "===================="
# --- Helper: check if any changed file matches a set of path prefixes ---
check_paths() {
local patterns="$1"
for file in $CHANGED_FILES; do
for pattern in $patterns; do
case "$file" in
${pattern}*) echo "true"; return ;;
esac
done
done
echo "false"
}
# --- Boolean gates for downstream DAG tasks ---
NEEDS_CODE=$(check_paths "Cargo.toml Cargo.lock crates/ services/ bin/fxt/")
NEEDS_DASHBOARD=$(check_paths "web-dashboard/")
DOCKER_IMAGES=$(check_paths "infra/docker/")
NEEDS_INFRA=$(check_paths "infra/live/ infra/modules/")
NEEDS_ARGO_TEMPLATES=$(check_paths "infra/k8s/argo/")
ML_CHANGED=$(check_paths "crates/ml crates/ml-dqn crates/ml-core crates/ml-regime crates/ml-features crates/ml-supervised crates/ml-ppo crates/ml-ensemble crates/ml-hyperopt crates/ml-labeling config/training config/gpu")
echo "=== Build decisions ==="
echo "needs-code: $NEEDS_CODE"
echo "needs-dashboard: $NEEDS_DASHBOARD"
echo "docker-images: $DOCKER_IMAGES"
echo "needs-infra: $NEEDS_INFRA"
echo "needs-argo: $NEEDS_ARGO_TEMPLATES"
echo "ml-changed: $ML_CHANGED"
echo "======================"
mkdir -p /tmp/outputs
echo -n "$NEEDS_CODE" > /tmp/outputs/needs-code
echo -n "$NEEDS_DASHBOARD" > /tmp/outputs/needs-dashboard
echo -n "$DOCKER_IMAGES" > /tmp/outputs/docker-images
echo -n "$NEEDS_INFRA" > /tmp/outputs/needs-infra
echo -n "$NEEDS_ARGO_TEMPLATES" > /tmp/outputs/needs-argo-templates
echo -n "$ML_CHANGED" > /tmp/outputs/ml-changed
SCRIPT
chmod +x /tmp/detect.sh
/tmp/detect.sh
outputs:
parameters:
- name: needs-code
valueFrom:
path: /tmp/outputs/needs-code
- name: needs-dashboard
valueFrom:
path: /tmp/outputs/needs-dashboard
- name: docker-images
valueFrom:
path: /tmp/outputs/docker-images
- name: needs-infra
valueFrom:
path: /tmp/outputs/needs-infra
- name: needs-argo-templates
valueFrom:
path: /tmp/outputs/needs-argo-templates
- name: ml-changed
valueFrom:
path: /tmp/outputs/ml-changed
# ── test-gate: clippy + cargo test quality gate ──
# Uses ci-builder (with CUDA toolkit) because cudarc 0.19 requires nvcc at build time.
- name: test-gate
inputs:
parameters:
- name: commit-sha
nodeSelector:
k8s.scaleway.com/pool-name: ci-compile-cpu
tolerations:
- key: k8s.scaleway.com/pool-name
operator: Equal
value: ci-compile-cpu
effect: NoSchedule
sidecars:
- name: redis
image: redis:7-alpine
command: ["redis-server", "--save", "", "--appendonly", "no"]
ports:
- containerPort: 6379
resources:
requests:
cpu: 100m
memory: 64Mi
limits:
cpu: 500m
memory: 128Mi
readinessProbe:
tcpSocket:
port: 6379
initialDelaySeconds: 1
periodSeconds: 1
container:
image: gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/ci-builder:latest
imagePullPolicy: Always
command: ["/bin/sh", "-c"]
env:
- name: SQLX_OFFLINE
value: "true"
- name: CARGO_TERM_COLOR
value: always
- name: CARGO_TARGET_DIR
value: /cargo-target
- name: CARGO_HOME
value: /cargo-target/cargo-home
- name: REDIS_URL
value: "redis://localhost:6379"
resources:
requests:
cpu: "14"
memory: 16Gi
limits:
cpu: "30"
memory: 32Gi
volumeMounts:
- name: git-ssh-key
mountPath: /etc/git-ssh
readOnly: true
- name: cargo-target-cpu
mountPath: /cargo-target
args:
- |
set -e
SHA="{{inputs.parameters.commit-sha}}"
# SSH setup
mkdir -p ~/.ssh
cp /etc/git-ssh/ssh-privatekey ~/.ssh/id_ed25519
chmod 600 ~/.ssh/id_ed25519
printf 'Host *\n StrictHostKeyChecking no\n UserKnownHostsFile /dev/null\n' > ~/.ssh/config
chmod 600 ~/.ssh/config
REPO="ssh://git@gitlab-gitlab-shell.foxhunt.svc.cluster.local:2222/root/foxhunt.git"
WORKSPACE="/cargo-target/src"
git config --global --add safe.directory "$WORKSPACE"
if [ -d "$WORKSPACE/.git" ]; then
cd "$WORKSPACE"
CURRENT=$(git rev-parse HEAD 2>/dev/null || echo "none")
if [ "$CURRENT" = "$SHA" ]; then
echo "=== Already at $SHA ==="
else
git fetch origin
git checkout --force "$SHA"
git clean -fd
fi
else
git clone --filter=blob:none "$REPO" "$WORKSPACE"
cd "$WORKSPACE"
git checkout "$SHA"
fi
export PATH="${CARGO_HOME}/bin:${PATH}"
echo "=== Waiting for Redis sidecar ==="
for i in 1 2 3 4 5; do
if printf 'PING\r\n' | nc -w1 127.0.0.1 6379 2>/dev/null | grep -q PONG; then
echo "Redis ready"
break
fi
sleep 1
done
echo "=== Running clippy (lib targets) ==="
cargo clippy --workspace --lib -- -D warnings 2>&1 | tee /cargo-target/clippy.log
echo "=== Running tests (lib only, no integration) ==="
set +e
cargo test --workspace --lib 2>&1 | tee /cargo-target/test-output.log
TEST_EXIT=$?
set -e
if [ "$TEST_EXIT" -ne 0 ]; then
echo "=== TEST FAILURES ==="
grep -A5 'FAILED\|panicked\|test result: FAILED\|error\[' /cargo-target/test-output.log || true
exit "$TEST_EXIT"
fi
echo "=== Test gate passed ==="
# ── build-web-dashboard: npm build + upload to MinIO ──
- name: build-web-dashboard
nodeSelector:
k8s.scaleway.com/pool-name: platform
container:
image: node:22-alpine
command: ["/bin/sh", "-c"]
env:
- name: MINIO_ACCESS_KEY
valueFrom:
secretKeyRef:
name: minio-credentials
key: access-key
- name: MINIO_SECRET_KEY
valueFrom:
secretKeyRef:
name: minio-credentials
key: secret-key
resources:
requests:
cpu: "1"
memory: 1Gi
limits:
cpu: "2"
memory: 2Gi
volumeMounts:
- name: git-ssh-key
mountPath: /etc/git-ssh
readOnly: true
args:
- |
set -e
SHA="{{workflow.parameters.commit-sha}}"
# Git clone
apk add --no-cache git openssh rclone
mkdir -p ~/.ssh
cp /etc/git-ssh/ssh-privatekey ~/.ssh/id_ed25519
chmod 600 ~/.ssh/id_ed25519
printf 'Host *\n StrictHostKeyChecking no\n UserKnownHostsFile /dev/null\n' > ~/.ssh/config
chmod 600 ~/.ssh/config
REPO="ssh://git@gitlab-gitlab-shell.foxhunt.svc.cluster.local:2222/root/foxhunt.git"
WORKSPACE="/tmp/workspace"
git clone --no-checkout --filter=blob:none "$REPO" "$WORKSPACE"
cd "$WORKSPACE"
git checkout "$SHA"
cd "$WORKSPACE/web-dashboard"
echo "=== Building web dashboard ==="
npm ci
npm run build
echo "=== Uploading to MinIO ==="
rclone copy dist/ :s3:foxhunt-binaries/web-dashboard/ \
--s3-provider=Minio \
--s3-endpoint=http://minio.foxhunt.svc.cluster.local:9000 \
--s3-access-key-id="${MINIO_ACCESS_KEY}" \
--s3-secret-access-key="${MINIO_SECRET_KEY}" \
--s3-no-check-bucket
echo "=== Web dashboard build + upload done ==="
# ── terragrunt-apply: apply infra changes on main push ──
- name: terragrunt-apply
inputs:
parameters:
- name: commit-sha
nodeSelector:
k8s.scaleway.com/pool-name: platform
serviceAccountName: argo-workflow
container:
image: gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/ci-builder-cpu:latest
command: ["/bin/sh", "-c"]
env:
- name: GITLAB_TOKEN
valueFrom:
secretKeyRef:
name: gitlab-pat
key: token
- name: TF_HTTP_USERNAME
value: root
- name: TF_HTTP_PASSWORD
valueFrom:
secretKeyRef:
name: gitlab-pat
key: token
- name: SCW_ACCESS_KEY
valueFrom:
secretKeyRef:
name: scaleway-credentials
key: access-key
- name: SCW_SECRET_KEY
valueFrom:
secretKeyRef:
name: scaleway-credentials
key: secret-key
- name: SCW_DEFAULT_PROJECT_ID
valueFrom:
secretKeyRef:
name: scaleway-credentials
key: project-id
- name: GITLAB_TF_STATE_URL
value: "http://gitlab-webservice-default.foxhunt.svc.cluster.local:8181"
resources:
requests:
cpu: 200m
memory: 256Mi
limits:
cpu: "1"
memory: 512Mi
volumeMounts:
- name: git-ssh-key
mountPath: /etc/git-ssh
readOnly: true
args:
- |
set -e
# Clone repo
mkdir -p /root/.ssh
cp /etc/git-ssh/ssh-privatekey /root/.ssh/id_ed25519
chmod 600 /root/.ssh/id_ed25519
printf 'Host *\n StrictHostKeyChecking no\n UserKnownHostsFile /dev/null\n' > /root/.ssh/config
chmod 600 /root/.ssh/config
SHA="{{inputs.parameters.commit-sha}}"
REPO="ssh://git@gitlab-gitlab-shell.foxhunt.svc.cluster.local:2222/root/foxhunt.git"
git clone --no-checkout --filter=blob:none "$REPO" /workspace/src
cd /workspace/src
git checkout "$SHA"
echo "Checked out $(git rev-parse --short HEAD)"
tofu --version
terragrunt --version
# Apply each terragrunt module
for module in block-storage dns public-gateway kapsule; do
MODULE_DIR="infra/live/production/${module}"
if [ -d "$MODULE_DIR" ]; then
echo "=== Terragrunt plan: ${module} ==="
cd "/workspace/src/${MODULE_DIR}"
terragrunt init --non-interactive -reconfigure
OUTPUT=$(terragrunt plan --non-interactive -detailed-exitcode 2>&1) || EXITCODE=$?
EXITCODE=${EXITCODE:-0}
if [ "$EXITCODE" -eq 2 ]; then
echo "=== Terragrunt plan output: ${module} ==="
echo "$OUTPUT"
echo "=== Terragrunt apply: ${module} ==="
terragrunt apply --non-interactive -auto-approve
elif [ "$EXITCODE" -eq 0 ]; then
echo "=== No changes for ${module} ==="
else
echo "=== ERROR planning ${module} ==="
echo "$OUTPUT"
exit 1
fi
cd /workspace/src
fi
done
echo "=== Terragrunt apply complete ==="
# ── apply-argo-templates: self-apply WorkflowTemplates, EventSources, Sensors ──
- name: apply-argo-templates
inputs:
parameters:
- name: commit-sha
nodeSelector:
k8s.scaleway.com/pool-name: platform
serviceAccountName: argo-workflow
container:
image: gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/ci-builder-cpu:latest
command: ["/bin/sh", "-c"]
resources:
requests:
cpu: 100m
memory: 128Mi
limits:
cpu: 500m
memory: 256Mi
volumeMounts:
- name: git-ssh-key
mountPath: /etc/git-ssh
readOnly: true
args:
- |
set -e
# Clone repo at commit
mkdir -p /root/.ssh
cp /etc/git-ssh/ssh-privatekey /root/.ssh/id_ed25519
chmod 600 /root/.ssh/id_ed25519
printf 'Host *\n StrictHostKeyChecking no\n UserKnownHostsFile /dev/null\n' > /root/.ssh/config
chmod 600 /root/.ssh/config
SHA="{{inputs.parameters.commit-sha}}"
REPO="ssh://git@gitlab-gitlab-shell.foxhunt.svc.cluster.local:2222/root/foxhunt.git"
git clone --no-checkout --filter=blob:none "$REPO" /workspace/src
cd /workspace/src
git checkout "$SHA"
echo "Checked out $(git rev-parse --short HEAD)"
# Apply all Argo WorkflowTemplates
for f in infra/k8s/argo/*-template.yaml; do
if [ -f "$f" ]; then
echo "=== Applying $(basename $f) ==="
kubectl -n foxhunt apply -f "$f"
fi
done
# Apply EventSources and Sensors
for f in infra/k8s/argo/events/*.yaml; do
if [ -f "$f" ]; then
echo "=== Applying $(basename $f) ==="
kubectl -n foxhunt apply -f "$f"
fi
done
# Apply RBAC and NetworkPolicies
kubectl -n foxhunt apply -f infra/k8s/argo/ci-deploy-rbac.yaml
kubectl -n foxhunt apply -f infra/k8s/argo/argo-workflow-netpol.yaml
echo "=== Argo templates applied ==="
# ── submit-gpu-test: launch GPU test workflow as a child workflow ──
- name: submit-gpu-test
# Argo executor (main + wait) needs 256Mi to track large child workflow status JSON.
# Default 64Mi causes OOMKilled when child workflow has many parameters.
podSpecPatch: '{"containers":[{"name":"main","resources":{"requests":{"memory":"128Mi"},"limits":{"memory":"256Mi"}}},{"name":"wait","resources":{"requests":{"memory":"128Mi"},"limits":{"memory":"256Mi"}}}]}'
resource:
action: create
setOwnerReference: true
successCondition: status.phase == Succeeded
failureCondition: status.phase in (Failed, Error)
manifest: |
apiVersion: argoproj.io/v1alpha1
kind: Workflow
metadata:
generateName: gpu-test-on-push-
namespace: foxhunt
spec:
workflowTemplateRef:
name: gpu-test-pipeline
arguments:
parameters:
- name: commit-ref
value: "{{workflow.parameters.commit-sha}}"
- name: models
value: "dqn,ppo,tft"
# ── notify-result: post workflow outcome to Mattermost ──
- name: notify-result
nodeSelector:
k8s.scaleway.com/pool-name: platform
container:
image: gitlab-registry.foxhunt.svc.cluster.local:5000/root/foxhunt/foxhunt-runtime:latest
command: ["/bin/sh", "-c"]
env:
- name: WEBHOOK_URL
valueFrom:
secretKeyRef:
name: notification-webhook
key: webhook-url
optional: true
resources:
requests:
cpu: 50m
memory: 32Mi
limits:
cpu: 100m
memory: 64Mi
args:
- |
STATUS="{{workflow.status}}"
NAME="{{workflow.name}}"
if [ -z "$WEBHOOK_URL" ] || echo "$WEBHOOK_URL" | grep -q "PLACEHOLDER"; then
echo "No webhook configured, skipping notification"
exit 0
fi
if [ "$STATUS" = "Succeeded" ]; then
EMOJI=":white_check_mark:"
else
EMOJI=":x:"
fi
PAYLOAD="{\"username\":\"Argo CI\",\"text\":\"${EMOJI} **${NAME}** — ${STATUS} ({{workflow.duration}}s)\"}"
curl -sf -X POST -H 'Content-Type: application/json' \
-d "$PAYLOAD" "$WEBHOOK_URL" || echo "WARN: webhook post failed"