deploy.yml

name: Deploy

on:
  push:
    branches: [main]
  workflow_dispatch:
    inputs:
      health_timeout:
        description: "Seconds to wait for the container to report healthy. Raise it for a deploy that has to replay a large WAL (i.e. one following a hard kill)."
        required: false
        default: "120"

concurrency:
  group: deploy-main
  cancel-in-progress: false

jobs:
  deploy:
    name: Deploy to self-hosted runner
    runs-on: [self-hosted, flopsstuff, docker]
    env:
      COMPOSE_PROJECT_NAME: cotel
      CLOUDFLARE_TUNNEL_TOKEN: ${{ secrets.CLOUDFLARE_TUNNEL_TOKEN }}
      COTEL_PUBLIC_INGEST_URL: ${{ secrets.COTEL_PUBLIC_INGEST_URL }}
    steps:
      - uses: actions/checkout@v5

      - name: Build image
        run: docker compose build --pull

      - name: Recreate container
        run: docker compose up -d --remove-orphans

      # `up -d` returns once the container has started, not once it works, so
      # without this the job reports success on a container that is still — or
      # forever — `health: starting`. The script dumps container logs on failure.
      - name: Wait for healthy
        env:
          # Via env, not inline `${{ }}`: a dispatch input expanded straight into
          # the run script is a shell-injection sink, and this runner is the
          # production host.
          HEALTH_TIMEOUT: ${{ github.event.inputs.health_timeout || '120' }}
        run: scripts/wait-for-healthy.sh cotel "$HEALTH_TIMEOUT"

      - name: Show status
        run: docker compose ps

      - name: Prune dangling images
        if: always()
        run: docker image prune -f