name: E2E API Smoke Test
# Extracted from ci.yml so workflow-level concurrency can protect this job
# from run-level cancellation (issue #458).
#
# Problem: the job-level `concurrency.cancel-in-progress: false` in ci.yml
# prevented *sibling* E2E jobs from killing each other, but GitHub still
# cancelled the parent *workflow run* when a new push arrived. Since the job
# lived inside that run, it got cancelled too.
#
# Fix: a dedicated workflow gets its own concurrency group at the workflow
# level. New pushes to the same branch queue here instead of cancelling.
# Fast jobs (platform-build, canvas-build, etc.) stay in ci.yml and continue
# to benefit from run-level cancellation for quick feedback.

on:
  push:
    branches: [main]
    paths:
      - 'workspace-server/**'
      - 'tests/e2e/**'
      - '.github/workflows/e2e-api.yml'
  pull_request:
    branches: [main]
    paths:
      - 'workspace-server/**'
      - 'tests/e2e/**'
      - '.github/workflows/e2e-api.yml'

# Workflow-level concurrency: new runs queue rather than cancel.
# `cancel-in-progress: false` is load-bearing — without it GitHub would still
# cancel this run when the next push arrives, defeating the whole fix.
# The group key includes github.ref so PRs don't compete with main.
concurrency:
  group: e2e-api-${{ github.ref }}
  cancel-in-progress: false

jobs:
  e2e-api:
    name: E2E API Smoke Test
    runs-on: [self-hosted, macos, arm64]
    timeout-minutes: 15
    # `services:` is Linux-only on self-hosted runners — we start postgres
    # and redis via `docker run` instead. Ports 15432/16379 avoid collision
    # with anything the host may already have on the standard ports.
    env:
      DATABASE_URL: postgres://dev:dev@localhost:15432/molecule?sslmode=disable
      REDIS_URL: redis://localhost:16379
      PORT: "8080"
      PG_CONTAINER: molecule-ci-postgres
      REDIS_CONTAINER: molecule-ci-redis
    steps:
      - uses: actions/checkout@v4
      - uses: actions/setup-go@v5
        with:
          go-version: 'stable'
          cache: true
          cache-dependency-path: workspace-server/go.sum
      - name: Start Postgres (docker)
        run: |
          docker rm -f "$PG_CONTAINER" 2>/dev/null || true
          docker run -d --name "$PG_CONTAINER" \
            -e POSTGRES_USER=dev \
            -e POSTGRES_PASSWORD=dev \
            -e POSTGRES_DB=molecule \
            -p 15432:5432 \
            postgres:16
          for i in $(seq 1 30); do
            if docker exec "$PG_CONTAINER" pg_isready -U dev >/dev/null 2>&1; then
              echo "Postgres ready after ${i}s"
              exit 0
            fi
            sleep 1
          done
          echo "::error::Postgres did not become ready in 30s"
          docker logs "$PG_CONTAINER" || true
          exit 1
      - name: Start Redis (docker)
        run: |
          docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true
          docker run -d --name "$REDIS_CONTAINER" -p 16379:6379 redis:7
          for i in $(seq 1 15); do
            if docker exec "$REDIS_CONTAINER" redis-cli ping 2>/dev/null | grep -q PONG; then
              echo "Redis ready after ${i}s"
              exit 0
            fi
            sleep 1
          done
          echo "::error::Redis did not become ready in 15s"
          exit 1
      - name: Build platform
        working-directory: workspace-server
        run: go build -o platform-server ./cmd/server
      - name: Start platform (background)
        working-directory: workspace-server
        run: |
          ./platform-server > platform.log 2>&1 &
          echo $! > platform.pid
      - name: Wait for /health
        run: |
          for i in $(seq 1 30); do
            if curl -sf http://localhost:8080/health > /dev/null; then
              echo "Platform up after ${i}s"
              exit 0
            fi
            sleep 1
          done
          echo "::error::Platform did not become healthy in 30s"
          cat workspace-server/platform.log || true
          exit 1
      - name: Assert migrations applied
        # Migrations auto-run at platform boot. Fail fast if they silently
        # didn't — catches future migration-author mistakes before the E2E run.
        run: |
          tables=$(docker exec "$PG_CONTAINER" psql -U dev -d molecule -tAc "SELECT count(*) FROM information_schema.tables WHERE table_schema='public' AND table_name='workspaces'")
          if [ "$tables" != "1" ]; then
            echo "::error::Migrations did not apply — 'workspaces' table missing"
            cat workspace-server/platform.log || true
            exit 1
          fi
          echo "Migrations OK (workspaces table present)"
      - name: Run E2E API tests
        run: bash tests/e2e/test_api.sh
      - name: Dump platform log on failure
        if: failure()
        run: cat workspace-server/platform.log || true
      - name: Stop platform
        if: always()
        run: |
          if [ -f workspace-server/platform.pid ]; then
            kill "$(cat workspace-server/platform.pid)" 2>/dev/null || true
          fi
      - name: Stop service containers
        if: always()
        run: |
          docker rm -f "$PG_CONTAINER" 2>/dev/null || true
          docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true