regression_tests.yml

name: Connector Ops CI - Run Regression Tests

concurrency:
  # This is the name of the concurrency group. It is used to prevent concurrent runs of the same workflow.
  #
  # - github.head_ref is only defined on PR runs, it makes sure that the concurrency group is unique for pull requests
  #  ensuring that only one run per pull request is active at a time.
  #
  # - github.run_id is defined on all runs, it makes sure that the concurrency group is unique for workflow dispatches.
  # This allows us to run multiple workflow dispatches in parallel.
  group: ${{ github.workflow }}-${{ github.head_ref || github.run_id }}
  cancel-in-progress: true

on:
  workflow_dispatch:
    inputs:
      connector_name:
        description: Connector name (e.g. source-faker)
        required: true
      connection_id:
        description: ID of the connection to test; use "auto" to let the connection retriever choose a connection
        required: true
      pr_url:
        description: URL of the PR containing the code change
        required: true
      streams:
        description: Streams to include in regression tests
      should_read_with_state:
        description: Whether to run tests against the read command with state
        default: "true"
        type: boolean
      use_local_cdk:
        description: Use the local CDK when building the target connector
        default: "false"
        type: boolean
      connection_subset:
        description: The subset of connections to select from.
        required: true
        type: choice
        options:
          - sandboxes
          - all

jobs:
  regression_tests:
    name: Regression Tests
    runs-on: connector-test-large
    timeout-minutes: 360 # 6 hours
    steps:
      - name: Checkout Airbyte
        uses: actions/checkout@v4
      - name: Check PAT rate limits
        run: |
          ./tools/bin/find_non_rate_limited_PAT \
            ${{ secrets.GH_PAT_BUILD_RUNNER_OSS }} \
            ${{ secrets.GH_PAT_BUILD_RUNNER_BACKUP }}
      - name: Extract branch name [WORKFLOW DISPATCH]
        shell: bash
        if: github.event_name == 'workflow_dispatch'
        run: echo "branch=${GITHUB_REF#refs/heads/}" >> $GITHUB_OUTPUT
        id: extract_branch

      - name: Install Poetry
        id: install_poetry
        uses: snok/install-poetry@v1

      - name: Make poetry venv in project
        id: poetry_venv
        run: poetry config virtualenvs.in-project true

      - name: Install Python packages
        id: install_python_packages
        working-directory: airbyte-ci/connectors/pipelines
        run: poetry install

      - name: Fetch last commit id from remote branch [WORKFLOW DISPATCH]
        if: github.event_name == 'workflow_dispatch'
        id: fetch_last_commit_id_wd
        run: echo "commit_id=$(git rev-parse origin/${{ steps.extract_branch.outputs.branch }})" >> $GITHUB_OUTPUT

      - name: Setup Stream Parameters
        if: github.event_name == 'workflow_dispatch'
        run: |
          if [ -z "${{ github.event.inputs.streams }}" ]; then
            echo "STREAM_PARAMS=" >> $GITHUB_ENV
          else
            STREAMS=$(echo "${{ github.event.inputs.streams }}" | sed 's/,/ --connector_live_tests.selected-streams=/g')
            echo "STREAM_PARAMS=--connector_live_tests.selected-streams=$STREAMS" >> $GITHUB_ENV
          fi

      - name: Setup Local CDK Flag
        if: github.event_name == 'workflow_dispatch'
        run: |
          if ${{ github.event.inputs.use_local_cdk }}; then
            echo "USE_LOCAL_CDK_FLAG=--use-local-cdk" >> $GITHUB_ENV
          else
            echo "USE_LOCAL_CDK_FLAG=" >> $GITHUB_ENV
          fi

      - name: Setup State Flag
        if: github.event_name == 'workflow_dispatch'
        run: |
          if ${{ github.event.inputs.should_read_with_state }}; then
            echo "READ_WITH_STATE_FLAG=--connector_live_tests.should-read-with-state" >> $GITHUB_ENV
          else
            echo "READ_WITH_STATE_FLAG=" >> $GITHUB_ENV
          fi

      - name: Setup Connection Subset Option
        if: github.event_name == 'workflow_dispatch'
        run: |
          echo "CONNECTION_SUBSET=--connector_live_tests.connection-subset=${{ github.event.inputs.connection_subset }}" >> $GITHUB_ENV

      - name: Run Regression Tests [WORKFLOW DISPATCH]
        if: github.event_name == 'workflow_dispatch' # TODO: consider using the matrix strategy (https://docs.github.com/en/actions/using-jobs/using-a-matrix-for-your-jobs). See https://github.com/airbytehq/airbyte/pull/37659#discussion_r1583380234 for details.
        uses: ./.github/actions/run-airbyte-ci
        with:
          context: "manual"
          dagger_cloud_token: ${{ secrets.DAGGER_CLOUD_TOKEN_CACHE_4 }}
          docker_hub_password: ${{ secrets.DOCKER_HUB_PASSWORD }}
          docker_hub_username: ${{ secrets.DOCKER_HUB_USERNAME }}
          gcp_gsm_credentials: ${{ secrets.GCP_GSM_CREDENTIALS }}
          gcp_integration_tester_credentials: ${{ secrets.GCLOUD_INTEGRATION_TESTER }}
          sentry_dsn: ${{ secrets.SENTRY_AIRBYTE_CI_DSN }}
          git_branch: ${{ steps.extract_branch.outputs.branch }}
          git_revision: ${{ steps.fetch_last_commit_id_pr.outputs.commit_id }}
          github_token: ${{ secrets.GH_PAT_MAINTENANCE_OSS }}
          s3_build_cache_access_key_id: ${{ secrets.SELF_RUNNER_AWS_ACCESS_KEY_ID }}
          s3_build_cache_secret_key: ${{ secrets.SELF_RUNNER_AWS_SECRET_ACCESS_KEY }}
          subcommand: connectors ${{ env.USE_LOCAL_CDK_FLAG }} --name ${{ github.event.inputs.connector_name }} test --only-step connector_live_tests --connector_live_tests.test-suite=regression --connector_live_tests.connection-id=${{ github.event.inputs.connection_id }} --connector_live_tests.pr-url=${{ github.event.inputs.pr_url }} ${{ env.READ_WITH_STATE_FLAG }} ${{ env.STREAM_PARAMS }} ${{ env.CONNECTION_SUBSET }} --global-status-check-context="Regression Tests" --global-status-check-description='Running regression tests'