onyx/.github/workflows/pr-python-connector-tests.yml

name: Connector Tests
concurrency:
  group: Connector-Tests-${{ github.workflow }}-${{ github.head_ref || github.event.workflow_run.head_branch || github.run_id }}
  cancel-in-progress: true

on:
  merge_group:
  pull_request:
    branches: [main]
  schedule:
    # This cron expression runs the job daily at 16:00 UTC (9am PT)
    - cron: "0 16 * * *"

env:
  # AWS
  AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
  AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS: ${{ secrets.AWS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS }}

  # Cloudflare R2
  R2_ACCOUNT_ID_DAILY_CONNECTOR_TESTS: ${{ vars.R2_ACCOUNT_ID_DAILY_CONNECTOR_TESTS }}
  R2_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.R2_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
  R2_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS: ${{ secrets.R2_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS }}

  # Google Cloud Storage
  GCS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS: ${{ secrets.GCS_ACCESS_KEY_ID_DAILY_CONNECTOR_TESTS }}
  GCS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS: ${{ secrets.GCS_SECRET_ACCESS_KEY_DAILY_CONNECTOR_TESTS }}

  # Confluence
  CONFLUENCE_TEST_SPACE_URL: ${{ vars.CONFLUENCE_TEST_SPACE_URL }}
  CONFLUENCE_TEST_SPACE: ${{ vars.CONFLUENCE_TEST_SPACE }}
  CONFLUENCE_TEST_PAGE_ID: ${{ secrets.CONFLUENCE_TEST_PAGE_ID }}
  CONFLUENCE_USER_NAME: ${{ vars.CONFLUENCE_USER_NAME }}
  CONFLUENCE_ACCESS_TOKEN: ${{ secrets.CONFLUENCE_ACCESS_TOKEN }}
  CONFLUENCE_ACCESS_TOKEN_SCOPED: ${{ secrets.CONFLUENCE_ACCESS_TOKEN_SCOPED }}

  # Jira
  JIRA_BASE_URL: ${{ secrets.JIRA_BASE_URL }}
  JIRA_USER_EMAIL: ${{ secrets.JIRA_USER_EMAIL }}
  JIRA_API_TOKEN: ${{ secrets.JIRA_API_TOKEN }}
  JIRA_API_TOKEN_SCOPED: ${{ secrets.JIRA_API_TOKEN_SCOPED }}

  # Gong
  GONG_ACCESS_KEY: ${{ secrets.GONG_ACCESS_KEY }}
  GONG_ACCESS_KEY_SECRET: ${{ secrets.GONG_ACCESS_KEY_SECRET }}

  # Google
  GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_DRIVE_SERVICE_ACCOUNT_JSON_STR }}
  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR_TEST_USER_1 }}
  GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_DRIVE_OAUTH_CREDENTIALS_JSON_STR }}
  GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR: ${{ secrets.GOOGLE_GMAIL_SERVICE_ACCOUNT_JSON_STR }}
  GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR: ${{ secrets.GOOGLE_GMAIL_OAUTH_CREDENTIALS_JSON_STR }}

  # Slab
  SLAB_BOT_TOKEN: ${{ secrets.SLAB_BOT_TOKEN }}

  # Zendesk
  ZENDESK_SUBDOMAIN: ${{ secrets.ZENDESK_SUBDOMAIN }}
  ZENDESK_EMAIL: ${{ secrets.ZENDESK_EMAIL }}
  ZENDESK_TOKEN: ${{ secrets.ZENDESK_TOKEN }}

  # Salesforce
  SF_USERNAME: ${{ secrets.SF_USERNAME }}
  SF_PASSWORD: ${{ secrets.SF_PASSWORD }}
  SF_SECURITY_TOKEN: ${{ secrets.SF_SECURITY_TOKEN }}

  # Hubspot
  HUBSPOT_ACCESS_TOKEN: ${{ secrets.HUBSPOT_ACCESS_TOKEN }}

  # IMAP
  IMAP_HOST: ${{ vars.IMAP_HOST }}
  IMAP_USERNAME: ${{ vars.IMAP_USERNAME }}
  IMAP_PASSWORD: ${{ secrets.IMAP_PASSWORD }}
  IMAP_MAILBOXES: ${{ vars.IMAP_MAILBOXES }}

  # Airtable
  AIRTABLE_TEST_BASE_ID: ${{ vars.AIRTABLE_TEST_BASE_ID }}
  AIRTABLE_TEST_TABLE_ID: ${{ vars.AIRTABLE_TEST_TABLE_ID }}
  AIRTABLE_TEST_TABLE_NAME: ${{ vars.AIRTABLE_TEST_TABLE_NAME }}
  AIRTABLE_ACCESS_TOKEN: ${{ secrets.AIRTABLE_ACCESS_TOKEN }}

  # Sharepoint
  SHAREPOINT_CLIENT_ID: ${{ vars.SHAREPOINT_CLIENT_ID }}
  SHAREPOINT_CLIENT_SECRET: ${{ secrets.SHAREPOINT_CLIENT_SECRET }}
  SHAREPOINT_CLIENT_DIRECTORY_ID: ${{ vars.SHAREPOINT_CLIENT_DIRECTORY_ID }}
  SHAREPOINT_SITE: ${{ vars.SHAREPOINT_SITE }}

  # Github
  ACCESS_TOKEN_GITHUB: ${{ secrets.ACCESS_TOKEN_GITHUB }}

  # Gitlab
  GITLAB_ACCESS_TOKEN: ${{ secrets.GITLAB_ACCESS_TOKEN }}

  # Gitbook
  GITBOOK_SPACE_ID: ${{ secrets.GITBOOK_SPACE_ID }}
  GITBOOK_API_KEY: ${{ secrets.GITBOOK_API_KEY }}

  # Notion
  NOTION_INTEGRATION_TOKEN: ${{ secrets.NOTION_INTEGRATION_TOKEN }}

  # Highspot
  HIGHSPOT_KEY: ${{ secrets.HIGHSPOT_KEY }}
  HIGHSPOT_SECRET: ${{ secrets.HIGHSPOT_SECRET }}

  # Slack
  SLACK_BOT_TOKEN: ${{ secrets.SLACK_BOT_TOKEN }}

  # Teams
  TEAMS_APPLICATION_ID: ${{ secrets.TEAMS_APPLICATION_ID }}
  TEAMS_DIRECTORY_ID: ${{ secrets.TEAMS_DIRECTORY_ID }}
  TEAMS_SECRET: ${{ secrets.TEAMS_SECRET }}

  # Bitbucket
  BITBUCKET_WORKSPACE: ${{ secrets.BITBUCKET_WORKSPACE }}
  BITBUCKET_REPOSITORIES: ${{ secrets.BITBUCKET_REPOSITORIES }}
  BITBUCKET_PROJECTS: ${{ secrets.BITBUCKET_PROJECTS }}
  BITBUCKET_EMAIL: ${{ vars.BITBUCKET_EMAIL }}
  BITBUCKET_API_TOKEN: ${{ secrets.BITBUCKET_API_TOKEN }}

  # Fireflies
  FIREFLIES_API_KEY: ${{ secrets.FIREFLIES_API_KEY }}

jobs:
  connectors-check:
    # See https://runs-on.com/runners/linux/
    runs-on: [runs-on, runner=8cpu-linux-x64, "run-id=${{ github.run_id }}-connectors-check", "extras=s3-cache"]

    env:
      PYTHONPATH: ./backend

    steps:
      - uses: runs-on/action@cd2b598b0515d39d78c38a02d529db87d2196d1e # ratchet:runs-on/action@v2

      - name: Checkout code
        uses: actions/checkout@08eba0b27e820071cde6df949e0beb9ba4906955 # ratchet:actions/checkout@v4
        with:
          persist-credentials: false

      - name: Setup Python and Install Dependencies
        uses: ./.github/actions/setup-python-and-install-dependencies

      - name: Setup Playwright
        uses: ./.github/actions/setup-playwright

      - name: Detect Connector changes
        id: changes
        uses: dorny/paths-filter@de90cc6fb38fc0963ad72b210f1f284cd68cea36 # ratchet:dorny/paths-filter@v3
        with:
          filters: |
            hubspot:
              - 'backend/onyx/connectors/hubspot/**'
              - 'backend/tests/daily/connectors/hubspot/**'
            salesforce:
              - 'backend/onyx/connectors/salesforce/**'
              - 'backend/tests/daily/connectors/salesforce/**'
            github:
              - 'backend/onyx/connectors/github/**'
              - 'backend/tests/daily/connectors/github/**'
            file_processing:
              - 'backend/onyx/file_processing/**'

      - name: Run Tests (excluding HubSpot, Salesforce, and GitHub)
        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
        run: |
          py.test \
            -n 8 \
            --dist loadfile \
            --durations=8 \
            -o junit_family=xunit2 \
            -xv \
            --ff \
            backend/tests/daily/connectors \
            --ignore backend/tests/daily/connectors/hubspot \
            --ignore backend/tests/daily/connectors/salesforce \
            --ignore backend/tests/daily/connectors/github

      - name: Run HubSpot Connector Tests
        if: ${{ github.event_name == 'schedule' || steps.changes.outputs.hubspot == 'true' || steps.changes.outputs.file_processing == 'true' }}
        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
        run: |
          py.test \
            -n 8 \
            --dist loadfile \
            --durations=8 \
            -o junit_family=xunit2 \
            -xv \
            --ff \
            backend/tests/daily/connectors/hubspot

      - name: Run Salesforce Connector Tests
        if: ${{ github.event_name == 'schedule' || steps.changes.outputs.salesforce == 'true' || steps.changes.outputs.file_processing == 'true' }}
        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
        run: |
          py.test \
            -n 8 \
            --dist loadfile \
            --durations=8 \
            -o junit_family=xunit2 \
            -xv \
            --ff \
            backend/tests/daily/connectors/salesforce

      - name: Run GitHub Connector Tests
        if: ${{ github.event_name == 'schedule' || steps.changes.outputs.github == 'true' || steps.changes.outputs.file_processing == 'true' }}
        shell: script -q -e -c "bash --noprofile --norc -eo pipefail {0}"
        run: |
          py.test \
            -n 8 \
            --dist loadfile \
            --durations=8 \
            -o junit_family=xunit2 \
            -xv \
            --ff \
            backend/tests/daily/connectors/github

      - name: Alert on Failure
        if: failure() && github.event_name == 'schedule'
        env:
          SLACK_WEBHOOK: ${{ secrets.SLACK_WEBHOOK }}
        run: |
          curl -X POST \
            -H 'Content-type: application/json' \
            --data '{"text":"Scheduled Connector Tests failed! Check the run at: https://github.com/${{ github.repository }}/actions/runs/${{ github.run_id }}"}' \
            $SLACK_WEBHOOK