Add GitHub Actions health check workflow

Introduces a new GitHub Actions workflow to periodically check service health and version information for specified endpoints. The workflow includes:
- Scheduled runs every 5 minutes
- Checks version information
- Monitors service status
- Raises an error if any services are down

TMP: test

Test it

Author: KevinMind

.github/workflows/health_check.yml

@@ -0,0 +1,67 @@
+name: Health Check
+
+on:
+  # Run the workflow test on push events
+  push:
+  # Run the main workflow on workflow_dispatch or schedule
+  workflow_dispatch:
+  schedule:
+    # Every 5 minutes
+    - cron: '*/5 * * * *'
+
+jobs:
+  health_check:
+    runs-on: ubuntu-latest
+    strategy:
+      fail-fast: false
+      matrix:
+        environment: ${{fromJson(github.event_name == 'push' && '["test"]' || '["dev","stage","prod"]')}}
+
+    steps:
+      - uses: actions/checkout@v4
+
+      - name: Set up Python
+        uses: actions/setup-python@v5
+        with:
+          python-version: '3.11'
+          cache: 'pip'
+
+      - name: Install dependencies
+        run: |
+          python -m pip install --upgrade pip
+          pip install requests
+
+      - name: Run Health Checks
+        shell: bash
+        run: |
+          set -ue
+
+          environment="${{ matrix.environment }}"
+          output_file="out.json"
+          ./scripts/health_check.py --env $environment --verbose --output $output_file
+
+          version=$(cat $output_file | jq -r '.version')
+          monitors=$(cat $output_file | jq -r '.monitors')
+
+          echo "Version: $version"
+          echo "Monitors: $monitors"
+
+          if [ "$version" = "null" ] || [ "$monitors" = "null" ]; then
+            echo "Environment $environment is not reachable"
+            exit 1
+          fi
+
+          message=""
+
+          data=$(echo $monitors | jq -r 'to_entries[] | select(.value.state == false) | .key')
+          for monitor in $data; do
+            message="$message\n- $monitor: $(echo $monitors | jq -r ".[\"$monitor\"].status")"
+          done
+
+          echo "Environment: $environment"
+          echo "Message:"
+          echo $message
+
+
+
+

scripts/health_check.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+
+import argparse
+import json
+from enum import Enum
+
+import requests
+
+
+ENV_ENUM = Enum(
+    'ENV',
+    [
+        ('dev', 'https://addons-dev.allizom.org'),
+        ('stage', 'https://addons.allizom.org'),
+        ('prod', 'https://addons.mozilla.org'),
+        # TODO: maybe we could use the local environmnet here
+        ('test', ''),
+    ],
+)
+
+
+class Fetcher:
+    def __init__(self, env: ENV_ENUM, verbose: bool = False):
+        self.environment = ENV_ENUM[env]
+        self.verbose = verbose
+
+    def _fetch(self, path: str) -> dict[str, str] | None:
+        url = f'{self.environment.value}/{path}'
+        if self.verbose:
+            print(f'Requesting {url} for {self.environment.name}')
+
+        try:
+            response = requests.get(url)
+            response.raise_for_status()
+            try:
+                data = response.json()
+            except json.JSONDecodeError as e:
+                if self.verbose:
+                    print(f'Error decoding JSON for {url}: {e}')
+
+        except requests.exceptions.HTTPError as e:
+            if self.verbose:
+                print(f'Error fetching {url}: {e}')
+
+        if self.verbose and data is not None:
+            print(json.dumps(data, indent=2))
+
+        return data
+
+    def version(self):
+        if self.environment.name == 'test':
+            return {}
+        return self._fetch('__version__')
+
+    def monitors(self):
+        if self.environment.name == 'test':
+            return {
+                'up': {'state': True},
+                'down': {'state': False, 'status': 'something is wrong'},
+            }
+        return self._fetch('services/monitor.json')
+
+
+def main(env: ENV_ENUM, verbose: bool = False, output: str | None = None):
+    fetcher = Fetcher(env, verbose)
+
+    version_data = fetcher.version()
+    monitors_data = fetcher.monitors()
+
+    if output:
+        with open(output, 'w') as f:
+            json.dump({'version': version_data, 'monitors': monitors_data}, f, indent=2)
+    elif monitors_data is not None:
+        if any(monitor['state'] is False for monitor in monitors_data.values()):
+            raise ValueError(f'Some monitors are failing {monitors_data}')
+
+
+if __name__ == '__main__':
+    args = argparse.ArgumentParser()
+    args.add_argument(
+        '--env', type=str, choices=list(ENV_ENUM.__members__.keys()), required=True
+    )
+    args.add_argument('--verbose', action='store_true')
+    args.add_argument('--output', type=str, required=False)
+    args = args.parse_args()
+
+    main(args.env, args.verbose, args.output)