federated_runtime.yml

#---------------------------------------------------------------------------
# Workflow to run 301_MNIST_Watermarking notebook
# Authors - Noopur, Payal Chaurasiya
#---------------------------------------------------------------------------
name: Federated Runtime 301 MNIST Watermarking

on:
  pull_request:
    types: [opened, synchronize, reopened, ready_for_review]

  workflow_dispatch:

permissions:
  contents: read

jobs:
  run_notebook:
    if: github.event.pull_request.draft == false
    runs-on: ubuntu-22.04
    timeout-minutes: 20
    steps:
    - name: Checkout OpenFL repository
      uses: actions/checkout@v4.1.1
      with:
        fetch-depth: 2 # needed for detecting changes
        submodules: "true"
        token: ${{ secrets.GITHUB_TOKEN }}

    - name: Set up Python
      uses: actions/setup-python@v3
      with:
        python-version: "3.10"

    - name: Install dependencies # Without this step, fx command will not work
      id: install_dependencies
      run: |
        python -m pip install --upgrade pip
        pip install .

    - name: Install Jupyter Lab Package
      run: pip install jupyterlab

    - name: Create results folder for logs
      run: | # Present working director - /home/runner/work/openfl/openfl
        mkdir -p /home/runner/results
        cd /home/runner/results
        touch director.log bangalore.log chandler.log && chmod 755 director.log bangalore.log chandler.log

    - name: Activate and run the director in background
      run: |
        cd openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking
        fx experimental activate
        cd director
        nohup ./start_director.sh &> ~/results/director.log &
        echo "Director started with 30s sleep time. This will be removed once the retry logic at envoy side is implemented."
        sleep 30 # DO NOT remove - envoys will simply exit if director is not ready

    - name: Run the envoy Bangalore in background
      run: |
        cd openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking/Bangalore
        nohup ./start_envoy.sh Bangalore Bangalore_config.yaml &> ~/results/bangalore.log &
        echo "Bangalore envoy started"

    - name: Run the envoy Chandler in background
      run: |
        cd openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking/Chandler
        nohup ./start_envoy.sh Chandler Chandler_config.yaml &> ~/results/chandler.log &
        echo "Chandler envoy started"

    - name: Check if envoys are connected to the director
      run: |
        python_path="tests/end_to_end/utils/github_helper.py"
        python3 $python_path --func_name "verify_envoys_director_conn_federated_runtime" \
          --notebook_path "openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking/workspace/MNIST_Watermarking.ipynb" \
          --expected_envoys "['Bangalore', 'Chandler']"

    - name: Run Notebook
      run: |
        cd openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking/workspace
        jupyter nbconvert --execute --to markdown ./MNIST_Watermarking.ipynb --no-input --stdout
        echo "Notebook run completed"

    - name: Check if the experiment was successful using logs
      run: |
        cd openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking

        if ! grep "End of Federation reached." ~/results/bangalore.log; then
          echo "Federation didn't reach end for Bangalore envoy"
        fi
        if ! grep "End of Federation reached." ~/results/chandler.log; then
          echo "Federation didn't reach end for Chandler envoy"
        fi
        if ! grep "Experiment FederatedFlow_MNIST_Watermarking was finished successfully" ~/results/director.log; then
          echo "Experiment didn't finish successfully"
          exit 1
        fi

        echo "Notebook run was successful"
        echo "| Aggregated model validation score |" >> $GITHUB_STEP_SUMMARY
        echo "| -------------- |" >> $GITHUB_STEP_SUMMARY
        echo $(grep -oP 'Aggregated model validation score = \K[\d.]+' ~/results/director.log | tail -1) >> $GITHUB_STEP_SUMMARY

    - name: Tar files
      if: ${{ always() }}   # collect artifacts regardless of failures
      run: |
        tar -cvf notebook.tar \
          ./openfl-tutorials/experimental/workflow/FederatedRuntime/301_MNIST_Watermarking/workspace \
          ~/results \
          --ignore-failed-read
        echo "TAR file created"

    - name: Upload Artifacts
      uses: actions/upload-artifact@v4
      if: ${{ always() }}   # collect artifacts regardless of failures
      with:
        name: federated_runtime_301_watermarking_${{ github.run_id }}
        path: notebook.tar