name: notification-platform

# Verification tiers for the Notification Delivery Platform.
#
# The PR tier is deliberately free of any external provider. A gate that depends on a third-party
# sandbox fails for reasons that have nothing to do with the change under review, and a gate people
# learn to re-run is not a gate. Real provider smoke tests live in the secret-protected tier, where
# a failure is an environment signal rather than a merge blocker.
#
# Every job that invokes Gradle validates the wrapper first with the repository's pinned action;
# the wrapper JAR is executable code fetched at build time, so validating it is what keeps a
# compromised wrapper from turning any workflow run into arbitrary code execution.

on:
  pull_request:
    paths:
      # The filter used to stop at the four notification source trees, so a change to the
      # composition root, the settings binding, the schema migrations, or the evidence manifest
      # ran none of this — and those are exactly the surfaces that decide whether the platform
      # assembles, binds and migrates at all.
      - 'src/application-core/src/**/notification/**'
      - 'src/adapter/outbound/notification/**'
      - 'src/adapter/outbound/persistence-jpa/src/**/notification/**'
      - 'src/adapter/outbound/persistence-jpa/src/main/resources/db/migration/jpa/notification-platform/**'
      - 'src/adapter/inbound/web/src/**/notification/**'
      - 'src/app-bootstrap/src/**/notification/**'
      - 'src/app-bootstrap/src/main/resources/application*.yml'
      - 'src/gradle/notification-*.gradle'
      - 'src/config/architecture/modules.json'
      - 'src/.env'
      - 'docs/notification/**'
      - 'infra/notification/**'
      - '.github/workflows/notification-platform.yml'
  push:
    branches: [ main ]
  schedule:
    # Nightly: the chaos tier, which is slower and inherently less deterministic than the PR tier.
    - cron: '0 17 * * *'
  workflow_dispatch:

permissions:
  contents: read

concurrency:
  group: notification-platform-${{ github.ref }}
  cancel-in-progress: true

jobs:
  pr:
    name: contract (Java 21, no external provider)
    runs-on: ubuntu-latest
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # actions/checkout@v4.2.2
      - name: Validate Gradle wrapper
        id: gradle-wrapper-validation
        uses: gradle/actions/wrapper-validation@3f131e8634966bd73d06cc69884922b02e6faf92 # gradle/actions@v6
      - uses: actions/setup-java@c5195efecf7bdfc987ee8bae7a71cb8b11521c00 # actions/setup-java@v4.7.1
        with:
          distribution: temurin
          java-version: "21.0.11+10"
          cache: gradle
          cache-dependency-path: |
            src/**/*.gradle
            src/**/gradle-wrapper.properties
            src/**/gradle.lockfile
      - name: Compile and format check
        working-directory: src
        run: ./gradlew :application-core:compileJava :adapter:outbound:notification:compileJava --console=plain
      - name: Application contracts
        working-directory: src
        run: ./gradlew :application-core:test --console=plain
      - name: Provider contract suite
        working-directory: src
        run: ./gradlew :adapter:outbound:notification:test --console=plain
      - name: Persistence and web
        working-directory: src
        run: ./gradlew :adapter:outbound:persistence-jpa:test :adapter:inbound:web:test --console=plain
      # The PR tier never touched a database, so every claim about migrations, claim atomicity and
      # lease fencing rested on a fake. Docker is available on this runner; the lane fails closed
      # when the container cannot start, because a skipped contract reports success for a database
      # nobody tested.
      - name: Notification schema and claim contracts (real PostgreSQL)
        working-directory: src
        run: ./gradlew :adapter:outbound:persistence-jpa:jpaPlatformContractTest --console=plain
      - name: Notification migration upgrade (real PostgreSQL)
        working-directory: src
        run: ./gradlew :adapter:outbound:persistence-jpa:jpaPlatformMigrationTest --console=plain
      - name: Architecture gates
        working-directory: src
        run: |
          ./gradlew verifyCleanArchitectureDependencies --console=plain
          ./gradlew :app-bootstrap:test --tests '*CleanArchitectureTest' --tests '*NotificationArchitectureTest' --console=plain
      - name: Configuration surface
        working-directory: src
        run: |
          ./gradlew verifyEnvKeys verifyPublicPathSnapshot --console=plain
          ./gradlew verifyNotificationApiSurface verifyNotificationConfiguration --console=plain
      # A support grade is a promise about production behaviour. This refuses one the pipeline
      # cannot back — the check that would have caught five channels reading "Stable" while no
      # request had ever left the process.
      - name: Evidence manifest
        working-directory: src
        run: ./gradlew verifyNotificationEvidence --console=plain
      - name: Static analysis
        working-directory: src
        run: ./gradlew :adapter:outbound:notification:check -x test --console=plain

  nightly-chaos:
    name: chaos (ambiguity, restart recovery, callback burst)
    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
    runs-on: ubuntu-latest
    timeout-minutes: 60
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # actions/checkout@v4.2.2
      - name: Validate Gradle wrapper
        id: gradle-wrapper-validation
        uses: gradle/actions/wrapper-validation@3f131e8634966bd73d06cc69884922b02e6faf92 # gradle/actions@v6
      - uses: actions/setup-java@c5195efecf7bdfc987ee8bae7a71cb8b11521c00 # actions/setup-java@v4.7.1
        with:
          distribution: temurin
          java-version: "21.0.11+10"
          cache: gradle
          cache-dependency-path: |
            src/**/*.gradle
            src/**/gradle-wrapper.properties
            src/**/gradle.lockfile
      # This job is named for ambiguity, restart recovery and callback burst. It used to run a
      # unit-test filter and then `test` — neither of which restarts anything or bursts anything —
      # so the job name was the only place those three properties existed.
      - name: Ambiguity and fault harness
        working-directory: src
        run: ./gradlew :adapter:outbound:notification:test --tests '*ChaosSecurity*' --tests '*CrossProviderContractSuite*' --console=plain
      - name: Concurrency and rotation races
        working-directory: src
        run: ./gradlew :adapter:outbound:notification:test --tests '*ConcurrencyTest' --tests '*ProviderRuntimeStateTest' --console=plain
      - name: Restart recovery and lease fencing (real PostgreSQL)
        working-directory: src
        run: ./gradlew :adapter:outbound:persistence-jpa:jpaPlatformContractTest :adapter:outbound:persistence-jpa:jpaPlatformFailureTest --console=plain
      - name: Full suite
        working-directory: src
        run: ./gradlew test --console=plain
      # A filter that matches nothing passes. Each --tests filter above names a class that exists
      # today; if one is renamed the job must fail rather than quietly stop covering it.
      - name: Every named suite actually ran
        working-directory: src
        run: |
          set -euo pipefail
          for suite in ChaosSecurity CrossProviderContractSuite ConcurrencyTest ProviderRuntimeStateTest; do
            if ! find . -path '*/build/test-results/*' -name "*${suite}*.xml" | grep -q .; then
              echo "no test results for ${suite}: the filter matched nothing and the job passed vacuously" >&2
              exit 1
            fi
          done

  provider-sandbox:
    name: provider sandbox smoke (secret-protected, non-blocking)
    if: github.event_name == 'workflow_dispatch'
    runs-on: ubuntu-latest
    timeout-minutes: 30
    environment: notification-provider-sandbox
    # Not a required check: an external outage must not block a merge. But not continue-on-error
    # either — a job that cannot fail produces no evidence, and this job's entire previous body was
    # two echo statements, which is what let five channels be graded Stable on nothing.
    steps:
      - uses: actions/checkout@11bd71901bbe5b1630ceea73d27597364c9af683 # actions/checkout@v4.2.2
      - name: Validate Gradle wrapper
        id: gradle-wrapper-validation
        uses: gradle/actions/wrapper-validation@3f131e8634966bd73d06cc69884922b02e6faf92 # gradle/actions@v6
      - uses: actions/setup-java@c5195efecf7bdfc987ee8bae7a71cb8b11521c00 # actions/setup-java@v4.7.1
        with:
          distribution: temurin
          java-version: "21.0.11+10"
          cache: gradle
          cache-dependency-path: |
            src/**/*.gradle
            src/**/gradle-wrapper.properties
            src/**/gradle.lockfile
      - name: Refuse to report a pass with no credentials
        env:
          NOTIFICATION_SANDBOX_CREDENTIALS: ${{ secrets.NOTIFICATION_SANDBOX_CREDENTIALS }}
        run: |
          set -euo pipefail
          if [ -z "${NOTIFICATION_SANDBOX_CREDENTIALS:-}" ]; then
            echo "provider sandbox credentials are not configured for this environment." >&2
            echo "The job stops here rather than reporting a green run that called nothing." >&2
            exit 1
          fi
      - name: Smoke test against real provider sandboxes
        working-directory: src
        env:
          NOTIFICATION_SANDBOX_ENABLED: 'true'
          NOTIFICATION_SANDBOX_CREDENTIALS: ${{ secrets.NOTIFICATION_SANDBOX_CREDENTIALS }}
        run: ./gradlew :adapter:outbound:notification:test --tests '*ProviderSandbox*' --console=plain
      - name: Upload the wire evidence
        if: always()
        uses: actions/upload-artifact@ea165f8d65b6e75b540449e92b4886f43607fa02 # actions/upload-artifact@v4.6.2
        with:
          name: notification-provider-sandbox-evidence
          path: src/adapter/outbound/notification/build/test-results/test/
          if-no-files-found: error
          retention-days: 90