clear old assets, new ci/cd flow

This commit is contained in:
2026-05-26 11:54:41 -04:00
parent 82815009c9
commit 72609755f8
87 changed files with 4132 additions and 7158 deletions

View File

@@ -1,246 +0,0 @@
name: CI
on:
push:
branches: [main, develop]
pull_request:
branches: [main]
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
NODE_VERSION: "20"
PNPM_VERSION: "9"
jobs:
lint:
name: Lint
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Setup Node.js ${{ env.NODE_VERSION }}
uses: actions/setup-node@v4
with:
node-version: ${{ env.NODE_VERSION }}
cache: "pnpm"
- uses: pnpm/action-setup@v4
with:
version: ${{ env.PNPM_VERSION }}
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Run linter
run: pnpm lint
typecheck:
name: Type Check
runs-on: ubuntu-latest
steps:
- uses: actions/checkout@v4
- name: Setup Node.js ${{ env.NODE_VERSION }}
uses: actions/setup-node@v4
with:
node-version: ${{ env.NODE_VERSION }}
cache: "pnpm"
- uses: pnpm/action-setup@v4
with:
version: ${{ env.PNPM_VERSION }}
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Build all packages
run: pnpm build
test:
name: Test Suite
runs-on: ubuntu-latest
services:
postgres:
image: postgres:16-alpine
env:
POSTGRES_DB: kordant
POSTGRES_USER: kordant
POSTGRES_PASSWORD: kordant_dev
ports:
- 5432:5432
options: >-
--health-cmd "pg_isready -U kordant"
--health-interval 5s
--health-timeout 5s
--health-retries 5
redis:
image: redis:7-alpine
ports:
- 6379:6379
options: >-
--health-cmd "redis-cli ping"
--health-interval 5s
--health-timeout 5s
--health-retries 5
steps:
- uses: actions/checkout@v4
- name: Setup Node.js ${{ env.NODE_VERSION }}
uses: actions/setup-node@v4
with:
node-version: ${{ env.NODE_VERSION }}
cache: "pnpm"
- uses: pnpm/action-setup@v4
with:
version: ${{ env.PNPM_VERSION }}
- name: Install dependencies
run: pnpm install --frozen-lockfile
- name: Run tests
run: pnpm test
env:
DATABASE_URL: "postgresql://kordant:kordant_dev@localhost:5432/kordant"
REDIS_URL: "redis://localhost:6379"
- name: Upload coverage to Codecov
uses: codecov/codecov-action@v4
with:
file: ./coverage/lcov.info
flags: unittests
name: kordant-coverage
fail_on_empty: false
docker-build:
name: Docker Build
runs-on: ubuntu-latest
needs: [lint, typecheck, test]
steps:
- uses: actions/checkout@v4
- name: Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Build Docker image
uses: docker/build-push-action@v5
with:
context: .
push: false
tags: kordant:${{ github.sha }}
cache-from: type=gha
cache-to: type=gha,mode=max
security-scan:
name: Security Scan
runs-on: ubuntu-latest
needs: [lint]
steps:
- uses: actions/checkout@v4
- name: Run pnpm audit
run: pnpm audit --prod
- name: Trivy filesystem scan
uses: aquasecurity/trivy-action@master
with:
scan-type: fs
scan-ref: "."
format: table
exit-code: 1
ignore-unfixed: true
severity: CRITICAL,HIGH
terraform-plan:
name: Terraform Plan
runs-on: ubuntu-latest
needs: [lint]
if: github.event_name == 'pull_request'
steps:
- uses: actions/checkout@v4
- name: Configure AWS Credentials
uses: aws-actions/configure-aws-credentials@v4
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: us-east-1
- name: Terraform Format
working-directory: infra
run: terraform fmt -check -diff
- name: Terraform Init
working-directory: infra
run: terraform init
- name: Terraform Validate
working-directory: infra
run: terraform validate
- name: Terraform Plan
working-directory: infra
run: terraform plan -var-file=environments/staging/terraform.tfvars.example -no-color
env:
TF_VAR_hibp_api_key: ${{ secrets.HIBP_API_KEY }}
TF_VAR_resend_api_key: ${{ secrets.RESEND_API_KEY }}
load-test:
name: Load Test
runs-on: ubuntu-latest
needs: [lint, typecheck, test, docker-build]
if: github.event_name == 'push' && github.ref == 'refs/heads/main'
environment: staging
steps:
- uses: actions/checkout@v4
- name: Install k6
run: |
K6_VERSION="v0.50.0"
K6_URL="https://github.com/grafana/k6/releases/download/${K6_VERSION}/k6-linux-amd64.tar.gz"
K6_SHA256="d950a2408d0be2dc81aef397a7c984a1d84271d7ae94ff7a47d08371904f0800"
curl -sSL "${K6_URL}" -o k6.tar.gz
echo "${K6_SHA256} k6.tar.gz" | sha256sum --check --strict -
tar xzf k6.tar.gz
sudo mv k6 /usr/local/bin/
k6 version
- name: Validate required secrets
run: |
if [ -z "$API_TOKEN" ]; then
echo "❌ LOAD_TEST_API_TOKEN secret is not set"
exit 1
fi
- name: Run combined load tests
run: |
chmod +x scripts/load-test/run-all.sh
./scripts/load-test/run-all.sh
env:
LOAD_TEST_BASE_URL: ${{ secrets.LOAD_TEST_BASE_URL || 'http://localhost:3000' }}
API_TOKEN: ${{ secrets.LOAD_TEST_API_TOKEN }}
TARGET_RPS: ${{ vars.LOAD_TEST_TARGET_RPS || '500' }}
DURATION: ${{ vars.LOAD_TEST_DURATION || '300s' }}
K6_CLOUD_TOKEN: ${{ secrets.K6_CLOUD_TOKEN || '' }}
K6_CLOUD_PROJECT_ID: ${{ vars.K6_CLOUD_PROJECT_ID || '' }}
- name: Upload load test report
if: always()
uses: actions/upload-artifact@v4
with:
name: load-test-report-${{ github.sha }}
path: scripts/load-test/reports/
retention-days: 30
- name: Check P99 thresholds
if: always()
run: |
if [ -f scripts/load-test/reports/threshold-results.json ]; then
FAILURES=$(jq -r '[.services | to_entries[] | select(.value.exitCode != 0) | .key] | join(", ")' scripts/load-test/reports/threshold-results.json 2>/dev/null || echo "")
if [ -n "$FAILURES" ] && [ "$FAILURES" != "" ]; then
echo "❌ Load test failures: $FAILURES"
exit 1
else
echo "✅ All load tests passed"
fi
else
echo "⚠️ No threshold results file found"
exit 1
fi
- name: Validate auto-scaling
if: always()
run: |
SUMMARY_FILE=$(ls scripts/load-test/reports/*-summary-*.json 2>/dev/null | head -1)
if [ -n "$SUMMARY_FILE" ]; then
MAX_VUS=$(jq -r '.metrics.vus.max // 0' "$SUMMARY_FILE")
TARGET_VUS=20
if [ "$(echo "$MAX_VUS >= $TARGET_VUS" | bc -l)" -eq 1 ]; then
echo "✅ Auto-scaling validated: max VUs ($MAX_VUS) >= target ($TARGET_VUS)"
else
echo "⚠️ Auto-scaling below target: max VUs ($MAX_VUS) < target ($TARGET_VUS)"
fi
else
echo "⚠️ No summary file for auto-scaling validation"
fi

View File

@@ -1,242 +0,0 @@
name: Deploy
on:
push:
branches: [main]
release:
types: [published]
concurrency:
group: deploy-${{ github.ref }}
cancel-in-progress: true
env:
NODE_VERSION: "20"
PNPM_VERSION: "9"
jobs:
detect-environment:
name: Detect Environment
runs-on: ubuntu-latest
outputs:
environment: ${{ steps.detect.outputs.environment }}
tag: ${{ steps.tag.outputs.tag }}
steps:
- name: Detect deployment target
id: detect
run: |
if [ "${{ github.event_name }}" = "release" ]; then
echo "environment=production" >> $GITHUB_OUTPUT
else
echo "environment=staging" >> $GITHUB_OUTPUT
fi
- name: Calculate tag
id: tag
run: |
if [ "${{ steps.detect.outputs.environment }}" = "production" ]; then
echo "tag=${{ github.event.release.tag_name }}" >> $GITHUB_OUTPUT
else
echo "tag=${{ github.sha }}" >> $GITHUB_OUTPUT
fi
terraform-apply:
name: Terraform Apply
runs-on: ubuntu-latest
needs: detect-environment
environment: ${{ needs.detect-environment.outputs.environment }}
steps:
- uses: actions/checkout@v4
- name: Setup Terraform
uses: hashicorp/setup-terraform@v3
with:
terraform_version: "~> 1.5"
- name: Terraform Init
working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
run: terraform init -backend-config="bucket=kordant-${{ needs.detect-environment.outputs.environment }}-terraform-state"
- name: Terraform Plan
id: plan
working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
run: |
terraform plan \
-var="hibp_api_key=${{ secrets.HIBP_API_KEY }}" \
-var="resend_api_key=${{ secrets.RESEND_API_KEY }}" \
-var="sentry_dsn=${{ secrets.SENTRY_DSN }}" \
-var="datadog_api_key=${{ secrets.DATADOG_API_KEY }}" \
-no-color | tee /tmp/terraform-plan.out
- name: Terraform Apply
working-directory: infra/environments/${{ needs.detect-environment.outputs.environment }}
run: |
terraform apply -auto-approve \
-var="hibp_api_key=${{ secrets.HIBP_API_KEY }}" \
-var="resend_api_key=${{ secrets.RESEND_API_KEY }}" \
-var="sentry_dsn=${{ secrets.SENTRY_DSN }}" \
-var="datadog_api_key=${{ secrets.DATADOG_API_KEY }}"
env:
AWS_ACCESS_KEY_ID: ${{ secrets.AWS_ACCESS_KEY_ID }}
AWS_SECRET_ACCESS_KEY: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
AWS_DEFAULT_REGION: us-east-1
build-and-push:
name: Build and Push Docker Images
runs-on: ubuntu-latest
needs: [detect-environment]
environment: ${{ needs.detect-environment.outputs.environment }}
strategy:
fail-fast: false
matrix:
include:
- name: api
dockerfile: packages/api/Dockerfile
- name: darkwatch
dockerfile: services/darkwatch/Dockerfile
- name: spamshield
dockerfile: services/spamshield/Dockerfile
- name: voiceprint
dockerfile: services/voiceprint/Dockerfile
steps:
- uses: actions/checkout@v4
- name: Docker Buildx
uses: docker/setup-buildx-action@v3
- name: Login to Container Registry
uses: docker/login-action@v3
with:
registry: ghcr.io
username: ${{ github.actor }}
password: ${{ secrets.GITHUB_TOKEN }}
- name: Calculate image tag
id: tag
run: echo "tag=${{ needs.detect-environment.outputs.tag }}" >> $GITHUB_OUTPUT
- name: Build and push ${{ matrix.name }}
uses: docker/build-push-action@v5
with:
context: .
file: ${{ matrix.dockerfile }}
push: true
tags: |
ghcr.io/${{ github.repository_owner }}/kordant-${{ matrix.name }}:${{ steps.tag.outputs.tag }}
ghcr.io/${{ github.repository_owner }}/kordant-${{ matrix.name }}:latest
cache-from: type=gha
cache-to: type=gha,mode=max
deploy-ecs:
name: Deploy to ECS
runs-on: ubuntu-latest
needs: [detect-environment, terraform-apply, build-and-push]
environment: ${{ needs.detect-environment.outputs.environment }}
strategy:
fail-fast: false
matrix:
service: [api, darkwatch, spamshield, voiceprint]
steps:
- uses: actions/checkout@v4
- name: Configure AWS
uses: aws-actions/configure-aws-credentials@v4
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: us-east-1
- name: Update ECS Service
run: |
IMAGE="ghcr.io/${{ github.repository_owner }}/kordant-${{ matrix.service }}:${{ needs.detect-environment.outputs.tag }}"
CLUSTER="kordant-${{ needs.detect-environment.outputs.environment }}"
SERVICE="${{ matrix.service }}"
TASK_DEF=$(aws ecs describe-task-definition \
--task-definition "${CLUSTER}-${SERVICE}" \
--query 'taskDefinition' --output json)
NEW_TASK_DEF=$(echo "$TASK_DEF" | jq \
--arg image "$IMAGE" \
'.containerDefinitions[0].image = $image')
NEW_TASK_DEF_ARN=$(echo "$NEW_TASK_DEF" | \
aws ecs register-task-definition \
--family "${CLUSTER}-${SERVICE}" \
--cli-input-json - \
--query 'taskDefinition.taskDefinitionArn' --output text)
aws ecs update-service \
--cluster "$CLUSTER" \
--service "${CLUSTER}-${SERVICE}" \
--task-definition "$NEW_TASK_DEF_ARN" \
--force-new-deployment
echo "Deployed $IMAGE to $SERVICE"
health-check:
name: Post-Deploy Health Check
runs-on: ubuntu-latest
needs: [detect-environment, deploy-ecs]
environment: ${{ needs.detect-environment.outputs.environment }}
steps:
- name: Configure AWS
uses: aws-actions/configure-aws-credentials@v4
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: us-east-1
- name: Wait for deployment
run: sleep 30
- name: Health Check
id: health
run: |
ENV="${{ needs.detect-environment.outputs.environment }}"
CLUSTER="kordant-${ENV}"
ALB_DNS=$(aws elbv2 describe-load-balancers \
--query "LoadBalancers[?contains(LoadBalancerName, '${CLUSTER}-alb')].DNSName" \
--output text)
if [ -z "$ALB_DNS" ]; then
echo "Health check failed: ALB DNS not found"
exit 1
fi
echo "ALB DNS: $ALB_DNS"
FAILED=0
for service in api darkwatch spamshield voiceprint; do
HTTP_CODE=$(curl -s -o /dev/null -w "%{http_code}" \
"https://${ALB_DNS}/health" || true)
if [ "$HTTP_CODE" = "200" ]; then
echo "Health check passed: $service"
else
echo "Health check failed: $service (HTTP $HTTP_CODE)"
FAILED=1
fi
done
if [ "$FAILED" -eq 1 ]; then
exit 1
fi
rollback:
name: Rollback on Failure
runs-on: ubuntu-latest
needs: [detect-environment, deploy-ecs, health-check]
environment: ${{ needs.detect-environment.outputs.environment }}
if: failure() && needs.health-check.result == 'failure'
strategy:
fail-fast: false
matrix:
service: [api, darkwatch, spamshield, voiceprint]
steps:
- name: Configure AWS
uses: aws-actions/configure-aws-credentials@v4
with:
aws-access-key-id: ${{ secrets.AWS_ACCESS_KEY_ID }}
aws-secret-access-key: ${{ secrets.AWS_SECRET_ACCESS_KEY }}
aws-region: us-east-1
- name: Rollback ECS Service
run: |
CLUSTER="kordant-${{ needs.detect-environment.outputs.environment }}"
SERVICE="${{ matrix.service }}"
aws ecs update-service \
--cluster "$CLUSTER" \
--service "${CLUSTER}-${SERVICE}" \
--rollback \
--no-cli-auto-prompt
echo "Rolled back $SERVICE"

View File

@@ -1,105 +0,0 @@
name: Load Test
on:
push:
branches: [main]
workflow_dispatch:
inputs:
target_rps:
description: 'Target requests per second'
required: false
default: '500'
duration:
description: 'Test duration'
required: false
default: '300s'
service:
description: 'Service to test (all, api, darkwatch, spamshield, voiceprint)'
required: false
default: 'all'
concurrency:
group: ${{ github.workflow }}-${{ github.ref }}
cancel-in-progress: true
env:
NODE_VERSION: "20"
jobs:
load-test:
name: Load Test (${{ github.event.inputs.service || 'all' }})
runs-on: ubuntu-latest
timeout-minutes: 30
environment: staging
steps:
- uses: actions/checkout@v4
- name: Install k6
run: |
K6_VERSION="v0.50.0"
K6_URL="https://github.com/grafana/k6/releases/download/${K6_VERSION}/k6-linux-amd64.tar.gz"
K6_SHA256="d950a2408d0be2dc81aef397a7c984a1d84271d7ae94ff7a47d08371904f0800"
curl -sSL "${K6_URL}" -o k6.tar.gz
echo "${K6_SHA256} k6.tar.gz" | sha256sum --check --strict -
tar xzf k6.tar.gz
sudo mv k6 /usr/local/bin/
k6 version
- name: Validate required secrets
run: |
if [ -z "$API_TOKEN" ]; then
echo "❌ LOAD_TEST_API_TOKEN secret is not set"
exit 1
fi
- name: Run load tests
run: |
chmod +x scripts/load-test/run-all.sh
./scripts/load-test/run-all.sh ${{ github.event.inputs.service || 'all' }}
env:
LOAD_TEST_BASE_URL: ${{ secrets.LOAD_TEST_BASE_URL || 'http://localhost:3000' }}
API_TOKEN: ${{ secrets.LOAD_TEST_API_TOKEN }}
TARGET_RPS: ${{ github.event.inputs.target_rps || '500' }}
DURATION: ${{ github.event.inputs.duration || '300s' }}
K6_CLOUD_TOKEN: ${{ secrets.K6_CLOUD_TOKEN || '' }}
K6_CLOUD_PROJECT_ID: ${{ vars.K6_CLOUD_PROJECT_ID || '' }}
- name: Upload load test report
if: always()
uses: actions/upload-artifact@v4
with:
name: load-test-report-${{ github.sha }}
path: scripts/load-test/reports/
retention-days: 30
- name: Check P99 thresholds
if: always()
run: |
if [ -f scripts/load-test/reports/threshold-results.json ]; then
FAILURES=$(jq -r '[.services | to_entries[] | select(.value.exitCode != 0) | .key] | join(", ")' scripts/load-test/reports/threshold-results.json 2>/dev/null || echo "")
if [ -n "$FAILURES" ] && [ "$FAILURES" != "" ]; then
echo "❌ Load test failures: $FAILURES"
exit 1
else
echo "✅ All load tests passed"
fi
else
echo "⚠️ No threshold results file found"
exit 1
fi
- name: Validate auto-scaling
if: always()
run: |
SUMMARY_FILE=$(ls scripts/load-test/reports/*-summary-*.json 2>/dev/null | head -1)
if [ -n "$SUMMARY_FILE" ]; then
MAX_VUS=$(jq -r '.metrics.vus.max // 0' "$SUMMARY_FILE")
TARGET_VUS=20
if [ "$(echo "$MAX_VUS >= $TARGET_VUS" | bc -l)" -eq 1 ]; then
echo "✅ Auto-scaling validated: max VUs ($MAX_VUS) >= target ($TARGET_VUS)"
else
echo "⚠️ Auto-scaling below target: max VUs ($MAX_VUS) < target ($TARGET_VUS)"
fi
else
echo "⚠️ No summary file for auto-scaling validation"
fi