Fix deploy job dependencies and add production deployment (#63)

2026-01-15 15:16:07 -06:00
parent 0ad106a141
commit 823dfcb400
3 changed files with 281 additions and 9 deletions
--- a/.gitlab-ci.yml
+++ b/.gitlab-ci.yml
@@ -124,8 +124,8 @@ python_tests:
      - .pip-cache/
    policy: pull-push
  before_script:
-    - pip install -r backend/requirements.txt
-    - pip install pytest pytest-asyncio pytest-cov httpx
+    - pip install --index-url "$PIP_INDEX_URL" -r backend/requirements.txt
+    - pip install --index-url "$PIP_INDEX_URL" pytest pytest-asyncio pytest-cov httpx
  script:
    - cd backend
    # Only run unit tests - integration tests require Docker Compose services
@@ -175,7 +175,7 @@ frontend_tests:
 # Shared deploy configuration
 .deploy_template: &deploy_template
  stage: deploy
-  needs: [build_image, kics, hadolint, python_tests, frontend_tests, secrets]
+  needs: [build_image, test_image, kics, hadolint, python_tests, frontend_tests, secrets, app_deps_scan, cve_scan, cve_sbom_analysis, app_sbom_analysis]
  image: deps.global.bsf.tools/registry-1.docker.io/alpine/k8s:1.29.12

 .helm_setup: &helm_setup
@@ -246,8 +246,8 @@ deploy_stage:
        --set image.tag=git.linux-amd64-$CI_COMMIT_SHA \
        --wait \
        --atomic \
-        --timeout 5m
-    - kubectl rollout status deployment/orchard-stage-server -n $NAMESPACE --timeout=5m
+        --timeout 10m
+    - kubectl rollout status deployment/orchard-stage-server -n $NAMESPACE --timeout=10m
    - *verify_deployment
  environment:
    name: stage
@@ -256,7 +256,7 @@ deploy_stage:
      agent: esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-stage
  rules:
    - if: '$CI_COMMIT_BRANCH == "main"'
-      when: always
+      when: on_success

 # Deploy feature branch to dev namespace
 deploy_feature:
@@ -282,8 +282,8 @@ deploy_feature:
        --set minioIngress.tls.secretName=minio-$CI_COMMIT_REF_SLUG-tls \
        --wait \
        --atomic \
-        --timeout 5m
-    - kubectl rollout status deployment/orchard-$CI_COMMIT_REF_SLUG-server -n $NAMESPACE --timeout=5m
+        --timeout 10m
+    - kubectl rollout status deployment/orchard-$CI_COMMIT_REF_SLUG-server -n $NAMESPACE --timeout=10m
    - export BASE_URL="https://orchard-$CI_COMMIT_REF_SLUG.common.global.bsf.tools"
    - *verify_deployment
  environment:
@@ -295,7 +295,7 @@ deploy_feature:
      agent: esv/bsf/bsf-integration/orchard/orchard-mvp:orchard
  rules:
    - if: '$CI_COMMIT_BRANCH && $CI_COMMIT_BRANCH != "main"'
-      when: always
+      when: on_success

 # Cleanup feature branch deployment
 cleanup_feature:
@@ -318,3 +318,51 @@ cleanup_feature:
    - if: '$CI_COMMIT_BRANCH && $CI_COMMIT_BRANCH != "main"'
      when: manual
  allow_failure: true
+
+# Deploy to production (version tags only, manual approval required)
+deploy_prod:
+  stage: deploy
+  # For tag pipelines, most jobs don't run (trusting main was tested)
+  # We only need build_image to have the image available
+  needs: [build_image]
+  image: deps.global.bsf.tools/registry-1.docker.io/alpine/k8s:1.29.12
+  variables:
+    NAMESPACE: orch-prod-namespace
+    VALUES_FILE: helm/orchard/values-prod.yaml
+    BASE_URL: https://orchard.common.global.bsf.tools
+  before_script:
+    - kubectl config use-context esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-prod
+    - *helm_setup
+  script:
+    - echo "Deploying to PRODUCTION - version $CI_COMMIT_TAG"
+    - cd $CI_PROJECT_DIR
+    - |
+      helm upgrade --install orchard-prod ./helm/orchard \
+        --namespace $NAMESPACE \
+        -f $VALUES_FILE \
+        --set image.tag=git.linux-amd64-$CI_COMMIT_SHA \
+        --wait \
+        --atomic \
+        --timeout 10m
+    - kubectl rollout status deployment/orchard-prod-server -n $NAMESPACE --timeout=10m
+    - *verify_deployment
+  environment:
+    name: production
+    url: https://orchard.common.global.bsf.tools
+    kubernetes:
+      agent: esv/bsf/bsf-integration/orchard/orchard-mvp:orchard-prod
+  rules:
+    # Only run on semantic version tags (v1.0.0, v1.2.3, etc.)
+    - if: '$CI_COMMIT_TAG =~ /^v\d+\.\d+\.\d+$/'
+      when: manual  # Require manual approval for prod
+  allow_failure: false
+
+# Integration tests for production deployment
+integration_test_prod:
+  <<: *integration_test_template
+  needs: [deploy_prod]
+  variables:
+    BASE_URL: https://orchard.common.global.bsf.tools
+  rules:
+    - if: '$CI_COMMIT_TAG =~ /^v\d+\.\d+\.\d+$/'
+      when: on_success
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -7,6 +7,9 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0

 ## [Unreleased]
 ### Added
+- Added production deployment job triggered by semantic version tags (v1.0.0) with manual approval gate (#63)
+- Added production Helm values file with persistence enabled (20Gi PostgreSQL, 100Gi MinIO) (#63)
+- Added integration tests for production deployment (#63)
 - Added GitLab CI pipeline for feature branch deployments to dev namespace (#51)
 - Added `deploy_feature` job with dynamic hostnames and unique release names (#51)
 - Added `cleanup_feature` job with `on_stop` for automatic cleanup on merge (#51)
@@ -16,6 +19,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Added internal proxy configuration for npm, pip, helm, and apt (#51)

 ### Changed
+- Deploy jobs now require all security scans to pass before deployment (added test_image, app_deps_scan, cve_scan, cve_sbom_analysis, app_sbom_analysis to dependencies) (#63)
+- Increased deploy job timeout from 5m to 10m (#63)
 - Added `--atomic` flag to Helm deployments for automatic rollback on failure
 - Adjusted dark mode color palette to use lighter background tones for better readability and reduced eye strain (#52)
 - Replaced project card grid with sortable data table on Home page for better handling of large project lists
@@ -26,6 +31,8 @@ and this project adheres to [Semantic Versioning](https://semver.org/spec/v2.0.0
 - Improved pod naming: Orchard pods now named `orchard-{env}-server-*` for clarity (#51)

 ### Fixed
+- Fixed deploy jobs running even when tests or security scans fail (changed rules from `when: always` to `when: on_success`) (#63)
+- Fixed python_tests job not using internal PyPI proxy (#63)
 - Fixed `cleanup_feature` job failing when branch is deleted (`GIT_STRATEGY: none`) (#51)
 - Fixed gitleaks false positives with fingerprints for historical commits (#51)
 - Fixed integration tests running when deploy fails (`when: on_success`) (#51)
--- a/helm/orchard/values-prod.yaml
+++ b/helm/orchard/values-prod.yaml
@@ -0,0 +1,217 @@
+# Production values for orchard
+# TODO: Replace subcharts with managed services (RDS, S3) when ready
+replicaCount: 1
+
+image:
+  repository: registry.global.bsf.tools/esv/bsf/bsf-integration/orchard/orchard-mvp
+  pullPolicy: IfNotPresent  # Don't always pull in prod
+  tag: "latest"  # Overridden by CI
+
+imagePullSecrets:
+  - name: orchard-pull-secret
+
+initContainer:
+  image:
+    repository: containers.global.bsf.tools/busybox
+    tag: "1.36"
+    pullPolicy: IfNotPresent
+
+serviceAccount:
+  create: true
+  automount: true
+  annotations: {}
+  name: "orchard"
+
+podAnnotations: {}
+podLabels: {}
+
+podSecurityContext: {}
+
+securityContext:
+  readOnlyRootFilesystem: false
+  runAsNonRoot: true
+  runAsUser: 1000
+
+service:
+  type: ClusterIP
+  port: 8080
+
+ingress:
+  enabled: true
+  className: "nginx"
+  annotations:
+    cert-manager.io/cluster-issuer: "letsencrypt"
+  hosts:
+    - host: orchard.common.global.bsf.tools
+      paths:
+        - path: /
+          pathType: Prefix
+  tls:
+    - secretName: orchard-prod-tls
+      hosts:
+        - orchard.common.global.bsf.tools
+
+# Production resources - same as stage for MVP, increase as needed
+resources:
+  limits:
+    cpu: 500m
+    memory: 512Mi
+  requests:
+    cpu: 500m
+    memory: 512Mi
+
+livenessProbe:
+  httpGet:
+    path: /health
+    port: http
+  initialDelaySeconds: 10
+  periodSeconds: 10
+
+readinessProbe:
+  httpGet:
+    path: /health
+    port: http
+  initialDelaySeconds: 5
+  periodSeconds: 5
+
+autoscaling:
+  enabled: false
+  minReplicas: 1
+  maxReplicas: 10
+  targetCPUUtilizationPercentage: 80
+  targetMemoryUtilizationPercentage: 80
+
+nodeSelector: {}
+tolerations: []
+affinity: {}
+
+orchard:
+  server:
+    host: "0.0.0.0"
+    port: 8080
+
+  # Database configuration (used when postgresql.enabled is false)
+  # TODO: Configure for managed PostgreSQL when ready
+  database:
+    host: ""
+    port: 5432
+    user: orchard
+    password: ""
+    dbname: orchard
+    sslmode: disable
+    existingSecret: ""
+    existingSecretPasswordKey: "password"
+
+  # S3 configuration (used when minio.enabled is false)
+  # TODO: Configure for real S3 when ready
+  s3:
+    endpoint: ""
+    region: us-east-1
+    bucket: orchard-artifacts
+    accessKeyId: ""
+    secretAccessKey: ""
+    usePathStyle: true
+    existingSecret: ""
+    existingSecretAccessKeyKey: "access-key-id"
+    existingSecretSecretKeyKey: "secret-access-key"
+
+  download:
+    mode: "presigned"
+    presignedUrlExpiry: 3600
+
+# PostgreSQL subchart - MVP uses subchart, switch to managed later
+postgresql:
+  enabled: true
+  image:
+    registry: containers.global.bsf.tools
+    repository: bitnami/postgresql
+    tag: "15"
+    pullPolicy: IfNotPresent
+  auth:
+    username: orchard
+    password: orchard-prod-password  # TODO: Use existingSecret
+    database: orchard
+  primary:
+    persistence:
+      enabled: true  # Enable persistence for prod
+      size: 20Gi
+    resourcesPreset: "none"
+    resources:
+      limits:
+        cpu: 500m
+        memory: 512Mi
+      requests:
+        cpu: 250m
+        memory: 512Mi
+  volumePermissions:
+    resourcesPreset: "none"
+    resources:
+      limits:
+        cpu: 100m
+        memory: 128Mi
+      requests:
+        cpu: 50m
+        memory: 128Mi
+
+# MinIO subchart - MVP uses subchart, switch to real S3 later
+minio:
+  enabled: true
+  image:
+    registry: containers.global.bsf.tools
+    repository: bitnami/minio
+    tag: "latest"
+    pullPolicy: IfNotPresent
+  auth:
+    rootUser: minioadmin
+    rootPassword: minioadmin-prod  # TODO: Use existingSecret
+  defaultBuckets: "orchard-artifacts"
+  persistence:
+    enabled: true  # Enable persistence for prod
+    size: 100Gi
+  resourcesPreset: "none"
+  resources:
+    limits:
+      cpu: 500m
+      memory: 512Mi
+    requests:
+      cpu: 250m
+      memory: 512Mi
+  defaultInitContainers:
+    volumePermissions:
+      resourcesPreset: "none"
+      resources:
+        limits:
+          cpu: 100m
+          memory: 128Mi
+        requests:
+          cpu: 50m
+          memory: 128Mi
+  provisioning:
+    resources:
+      limits:
+        cpu: 200m
+        memory: 256Mi
+      requests:
+        cpu: 100m
+        memory: 256Mi
+
+# MinIO external ingress for presigned URL access
+minioIngress:
+  enabled: true
+  className: "nginx"
+  annotations:
+    cert-manager.io/cluster-issuer: "letsencrypt"
+    nginx.ingress.kubernetes.io/proxy-body-size: "0"
+  host: "minio-orchard.common.global.bsf.tools"
+  tls:
+    enabled: true
+    secretName: minio-prod-tls
+
+redis:
+  enabled: false
+
+waitForDatabase: true
+
+global:
+  security:
+    allowInsecureImages: true