elizaos--eliza/.github/workflows/docker-ci-smoke.yml

name: Docker CI Smoke

on:
  # Reusable entry for the scheduled exhaustive develop lane (#12342).
  workflow_call:
  push:
    branches: [develop]
  schedule:
    # Nightly heavy lane (#14051): 07:00 UTC.
    - cron: "0 7 * * *"
  workflow_dispatch:

# CI fan-out fix: the PR-scoped concurrency from #14069 fell back to
# github.run_id on push, so every develop push got a unique group and
# nothing ever superseded. A 37-merge wave queued thousands of push runs
# and starved the self-hosted fleet. Fall back to github.ref (all develop
# pushes share a group) and cancel superseded runs on push too. PR behavior
# is unchanged (pull_request.number still wins the key); merge_group and
# schedule events are not in the cancel set, so the merge queue and nightly
# runs always complete.
concurrency:
  group: docker-ci-smoke-${{ github.event.pull_request.number || github.ref }}
  cancel-in-progress: ${{ github.event_name == 'pull_request' || github.event_name == 'push' }}

permissions:
  contents: read

jobs:
  changes:
    name: Classify changed paths
    if: github.event_name != 'pull_request' || contains(github.event.pull_request.labels.*.name, 'ci:full')
    # Path classifier is a git-diff + node script: no self-hosted resources.
    # Keep it on GitHub-hosted so a drained hetzner fleet cannot leave it
    # queued indefinitely and pile up runs (#13617/#8501).
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 10
    outputs:
      docker: ${{ steps.filter.outputs.docker }}
    steps:
      - uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          fetch-depth: 0
          submodules: false

      - name: Setup Node.js for path gate
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24"

      - name: Determine affected Docker smoke surface
        id: filter
        shell: bash
        env:
          PR_LABELS: ${{ github.event_name == 'pull_request' && join(github.event.pull_request.labels.*.name, ',') || '' }}
        run: |
          set -euo pipefail
          node packages/scripts/ci-path-gate.mjs \
            --config docker \
            --event "${{ github.event_name }}" \
            --base "${{ github.event.pull_request.base.sha }}" \
            --head "${{ github.event.pull_request.head.sha }}" \
            --labels "$PR_LABELS" \
            --output "$GITHUB_OUTPUT" \
            --summary "$GITHUB_STEP_SUMMARY"

  docker-ci-smoke:
    name: Build production Docker image (+ smoke boot)
    needs: changes
    if: github.event_name != 'pull_request' || needs.changes.outputs.docker == 'true'
    runs-on: ${{ fromJSON(vars.HETZNER_FLEET_ONLINE == 'false' && '["ubuntu-24.04"]' || '["self-hosted","hetzner-robot"]') }}
    timeout-minutes: 90
    env:
      BUN_VERSION: "canary"
      DOCKER_IMAGE: elizaos/agent:docker-smoke
      SMOKE_TIMEOUT_SEC: "420"
      SMOKE_PORT: "32138"
    steps:
      - name: Checkout
        uses: actions/checkout@34e114876b0b11c390a56381ad16ebd13914f8d5
        with:
          submodules: false
          show-progress: false

      - name: Setup Node.js
        uses: actions/setup-node@48b55a011bda9f5d6aeb4c2d9c7362e8dae4041e
        with:
          node-version: "24"

      - name: Setup Bun
        uses: oven-sh/setup-bun@0c5077e51419868618aeaa5fe8019c62421857d6
        with:
          bun-version: ${{ env.BUN_VERSION }}

      - name: Cache Bun install
        uses: actions/cache@55cc8345863c7cc4c66a329aec7e433d2d1c52a9
        with:
          path: ~/.bun/install/cache
          key: bun-${{ runner.os }}-${{ hashFiles('bun.lock') }}
          restore-keys: |
            bun-${{ runner.os }}-

      - name: Free disk space for Docker smoke
        run: |
          df -h
          # github-hosted-only disk cleanup; self-hosted runners (#8501) have no
          # passwordless sudo and don't need it, so never fail the job on it.
          sudo rm -rf /usr/local/lib/android /usr/share/dotnet /opt/ghc /opt/hostedtoolcache/CodeQL || true
          docker system prune -af --volumes || true
          df -h

      - name: Run Docker CI smoke path
        timeout-minutes: 45
        # Run the smoke script in its own process group so a wedged docker
        # child cannot outlive the wrapper timeout and keep the step active.
        run: |
          set -euo pipefail

          stop_smoke() {
            if [[ -n "${smoke_pid:-}" ]] && kill -0 "$smoke_pid" 2>/dev/null; then
              kill -TERM "-$smoke_pid" 2>/dev/null || kill -TERM "$smoke_pid" 2>/dev/null || true
              sleep 10
              kill -KILL "-$smoke_pid" 2>/dev/null || kill -KILL "$smoke_pid" 2>/dev/null || true
            fi
          }

          trap 'stop_smoke; exit 130' INT
          trap 'stop_smoke; exit 143' TERM

          mkdir -p .tmp/qa
          smoke_log=".tmp/qa/docker-ci-smoke-step.log"
          setsid bash packages/app-core/scripts/docker-ci-smoke.sh --tag gha-${{ github.run_id }} > >(tee "$smoke_log") 2> >(tee -a "$smoke_log" >&2) &
          smoke_pid=$!
          smoke_started_at=$SECONDS
          last_heartbeat=$SECONDS
          deadline=$((SECONDS + 40 * 60))

          while kill -0 "$smoke_pid" 2>/dev/null; do
            if (( SECONDS >= deadline )); then
              echo "::error::Docker CI smoke path exceeded 40 minutes"
              kill -TERM "-$smoke_pid" 2>/dev/null || kill -TERM "$smoke_pid" 2>/dev/null || true
              sleep 15
              kill -KILL "-$smoke_pid" 2>/dev/null || kill -KILL "$smoke_pid" 2>/dev/null || true
              wait "$smoke_pid" || true
              exit 124
            fi
            if (( SECONDS - last_heartbeat >= 60 )); then
              last_heartbeat=$SECONDS
              echo "[docker-ci-smoke] still running after $((SECONDS - smoke_started_at))s; log: $smoke_log"
            fi
            sleep 10
          done

          set +e
          wait "$smoke_pid"
          smoke_status=$?
          set -e
          if (( smoke_status != 0 )); then
            echo "::group::Docker CI smoke step tail"
            tail -n 240 "$smoke_log" || true
            echo "::endgroup::"
            echo "::error::Docker CI smoke failed with exit code ${smoke_status}; see the step tail and uploaded .tmp/qa artifacts."
            exit "$smoke_status"
          fi

      # Inline log capture runs on failure (not cancelled).
      - name: Dump container log + inspect (inline)
        if: failure()
        timeout-minutes: 2
        run: |
          echo "::group::Docker containers"
          timeout 15 docker ps -a || echo "(docker ps timed out)"
          echo "::endgroup::"
          timeout 15 docker ps -a --format '{{.Names}}' > /tmp/eliza-docker-containers.txt || true
          for C in $(grep '^eliza-docker-smoke-' /tmp/eliza-docker-containers.txt || true); do
            echo "::group::docker logs $C"
            timeout 30 docker logs "$C" 2>&1 || echo "(docker logs timed out)"
            echo "::endgroup::"
            echo "::group::docker inspect $C (state)"
            timeout 15 docker inspect "$C" --format '{{json .State}}' 2>&1 | python3 -m json.tool || true
            echo "::endgroup::"
          done

      - name: Upload container logs + inspect
        if: failure()
        uses: actions/upload-artifact@043fb46d1a93c77aae656e7c1c64a875d1fc6a0a
        with:
          name: docker-ci-smoke-artifacts-${{ github.run_id }}
          path: |
            .tmp/qa/docker-ci-smoke-*
            /tmp/eliza-docker-*.txt
          if-no-files-found: warn
          retention-days: 7

      - name: Summarize Docker smoke result
        if: always()
        run: |
          echo "## Docker CI Smoke" >> "$GITHUB_STEP_SUMMARY"
          echo "" >> "$GITHUB_STEP_SUMMARY"
          echo "- Production Dockerfile: \`packages/app-core/deploy/Dockerfile.ci\`" >> "$GITHUB_STEP_SUMMARY"
          echo "- Script: \`packages/app-core/scripts/docker-ci-smoke.sh\`" >> "$GITHUB_STEP_SUMMARY"
          echo "- Trigger: \`${{ github.event_name }}\`" >> "$GITHUB_STEP_SUMMARY"
          echo "- Ref: \`${{ github.ref }}\`" >> "$GITHUB_STEP_SUMMARY"
          echo "- Smoke endpoints: \`/api/health\` then fallback \`/api/status\`" >> "$GITHUB_STEP_SUMMARY"