molecule-core/.github/workflows/e2e-api.yml

name: E2E API Smoke Test
# Extracted from ci.yml so workflow-level concurrency can protect this job
# from run-level cancellation (issue #458).
#
# Trigger model (revised 2026-04-29):
#
# Always FIRES on push/pull_request to staging+main. Real work is gated
# per-step on `needs.detect-changes.outputs.api` — when paths under
# `workspace-server/`, `tests/e2e/`, or this workflow file haven't
# changed, the no-op step alone runs and emits SUCCESS for the
# `E2E API Smoke Test` check, satisfying branch protection without
# spending CI cycles. See the in-job comment on the `e2e-api` job for
# why this is one job (not two-jobs-sharing-name) and the 2026-04-29
# PR #2264 incident that drove the consolidation.

on:
  push:
    branches: [main, staging]
  pull_request:
    branches: [main, staging]
  workflow_dispatch:

concurrency:
  # Per-SHA grouping (changed 2026-04-28 from per-ref). Per-ref had the
  # same auto-promote-staging brittleness as e2e-staging-canvas — back-
  # to-back staging pushes share refs/heads/staging, so the older push's
  # queued run gets cancelled when a newer push lands. Auto-promote-
  # staging then sees `completed/cancelled` for the older SHA and stays
  # put; the newer SHA's gates may eventually save the day, but if the
  # newer push gets cancelled too, we deadlock.
  #
  # See e2e-staging-canvas.yml's identical concurrency block for the full
  # rationale and the 2026-04-28 incident reference.
  group: e2e-api-${{ github.event.pull_request.head.sha || github.sha }}
  cancel-in-progress: false

jobs:
  detect-changes:
    runs-on: ubuntu-latest
    outputs:
      api: ${{ steps.decide.outputs.api }}
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
      - uses: dorny/paths-filter@fbd0ab8f3e69293af611ebaee6363fc25e6d187d # v4.0.1
        id: filter
        with:
          filters: |
            api:
              - 'workspace-server/**'
              - 'tests/e2e/**'
              - '.github/workflows/e2e-api.yml'            
      - id: decide
        # Always run real work for manual dispatch — no diff context to
        # filter against and ops dispatching this expects the suite to
        # actually exercise the platform.
        run: |
          if [ "${{ github.event_name }}" = "workflow_dispatch" ]; then
            echo "api=true" >> "$GITHUB_OUTPUT"
          else
            echo "api=${{ steps.filter.outputs.api }}" >> "$GITHUB_OUTPUT"
          fi          

  # ONE job (no job-level `if:`) that always runs and reports under the
  # required-check name `E2E API Smoke Test`. Real work is gated per-step
  # on `needs.detect-changes.outputs.api`. Reason: GitHub registers a
  # check run for every job that matches `name:`, and a job-level
  # `if: false` produces a SKIPPED check run. Branch protection treats
  # all check runs with a matching context name on the latest commit as a
  # SET — any SKIPPED in the set fails the required-check eval, even with
  # SUCCESS siblings. Verified 2026-04-29 on PR #2264 (staging→main):
  # 4 check runs (2 SKIPPED + 2 SUCCESS) at the head SHA blocked
  # promotion despite all real work succeeding. Collapsing to a single
  # always-running job with conditional steps emits exactly one SUCCESS
  # check run regardless of paths filter — branch-protection-clean.
  e2e-api:
    needs: detect-changes
    name: E2E API Smoke Test
    runs-on: ubuntu-latest
    timeout-minutes: 15
    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:
      - name: No-op pass (paths filter excluded this commit)
        if: needs.detect-changes.outputs.api != 'true'
        run: |
          echo "No workspace-server / tests/e2e / workflow changes — E2E API gate satisfied without running tests."
          echo "::notice::E2E API Smoke Test no-op pass (paths filter excluded this commit)."          
      - if: needs.detect-changes.outputs.api == 'true'
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5 # v4
      - if: needs.detect-changes.outputs.api == 'true'
        uses: actions/setup-go@40f1582b2485089dde7abd97c1529aa768e1baff # v5
        with:
          go-version: 'stable'
          cache: true
          cache-dependency-path: workspace-server/go.sum
      - name: Start Postgres (docker)
        if: needs.detect-changes.outputs.api == 'true'
        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)
        if: needs.detect-changes.outputs.api == 'true'
        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 ${i}s"
              exit 0
            fi
            sleep 1
          done
          echo "::error::Redis did not become ready in 15s"
          docker logs "$REDIS_CONTAINER" || true
          exit 1          
      - name: Build platform
        if: needs.detect-changes.outputs.api == 'true'
        working-directory: workspace-server
        run: go build -o platform-server ./cmd/server
      - name: Start platform (background)
        if: needs.detect-changes.outputs.api == 'true'
        working-directory: workspace-server
        run: |
          ./platform-server > platform.log 2>&1 &
          echo $! > platform.pid          
      - name: Wait for /health
        if: needs.detect-changes.outputs.api == 'true'
        run: |
          for i in $(seq 1 30); do
            if curl -sf http://localhost:8080/health > /dev/null; then
              echo "Platform up after ${i}s"
              exit 0
            fi
            sleep 1
          done
          echo "::error::Platform did not become healthy in 30s"
          cat workspace-server/platform.log || true
          exit 1          
      - name: Assert migrations applied
        if: needs.detect-changes.outputs.api == 'true'
        run: |
          tables=$(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"
            cat workspace-server/platform.log || true
            exit 1
          fi
          echo "Migrations OK"          
      - name: Run E2E API tests
        if: needs.detect-changes.outputs.api == 'true'
        run: bash tests/e2e/test_api.sh
      - name: Run notify-with-attachments E2E
        if: needs.detect-changes.outputs.api == 'true'
        run: bash tests/e2e/test_notify_attachments_e2e.sh
      - name: Run priority-runtimes E2E (claude-code + hermes — skips when keys absent)
        if: needs.detect-changes.outputs.api == 'true'
        run: bash tests/e2e/test_priority_runtimes_e2e.sh
      - name: Dump platform log on failure
        if: failure() && needs.detect-changes.outputs.api == 'true'
        run: cat workspace-server/platform.log || true
      - name: Stop platform
        if: always() && needs.detect-changes.outputs.api == 'true'
        run: |
          if [ -f workspace-server/platform.pid ]; then
            kill "$(cat workspace-server/platform.pid)" 2>/dev/null || true
          fi          
      - name: Stop service containers
        if: always() && needs.detect-changes.outputs.api == 'true'
        run: |
          docker rm -f "$PG_CONTAINER" 2>/dev/null || true
          docker rm -f "$REDIS_CONTAINER" 2>/dev/null || true