transformers/.circleci/config.yml

version: 2.1
setup: true
orbs:
    continuation: circleci/continuation@0.1.0

parameters:
    nightly:
        type: boolean
        default: false

jobs:
    # Ensure running with CircleCI/huggingface
    check_circleci_user:
        docker:
            - image: python:3.10-slim
        resource_class: small
        parallelism: 1
        steps:
            - run: echo $CIRCLE_PROJECT_USERNAME
            - run: |
                if [ "$CIRCLE_PROJECT_USERNAME" = "huggingface" ]; then
                    exit 0
                else
                    echo "The CI is running under $CIRCLE_PROJECT_USERNAME personal account. Please follow https://support.circleci.com/hc/en-us/articles/360008097173-Troubleshooting-why-pull-requests-are-not-triggering-jobs-on-my-organization- to fix it."; exit -1
                fi                
    # Fetch the tests to run
    fetch_tests:
        working_directory: ~/transformers
        docker:
            - image: huggingface/transformers-quality
        parallelism: 1
        steps:
            - checkout
            - run: if [[ "$CIRCLE_PULL_REQUEST" == "" && "$CIRCLE_BRANCH" != "main" && "$CIRCLE_BRANCH" != *-release ]]; then echo "Not a PR, not the main branch and not a release branch, skip test!"; circleci-agent step halt; fi
            - run: 'curl -L -H "Accept: application/vnd.github+json" -H "X-GitHub-Api-Version: 2022-11-28" https://api.github.com/repos/$CIRCLE_PROJECT_USERNAME/$CIRCLE_PROJECT_REPONAME/pulls/${CIRCLE_PULL_REQUEST##*/} >> github.txt'
            - run: cat github.txt
            - run: (python3 -c 'import json; from datetime import datetime; fp = open("github.txt"); data = json.load(fp); fp.close(); f = "%Y-%m-%dT%H:%M:%SZ"; created = datetime.strptime(data["created_at"], f); updated = datetime.strptime(data["updated_at"], f); s = (updated - created).total_seconds(); print(int(s))' || true) > elapsed.txt
            - run: if [ "$(cat elapsed.txt)" == "" ]; then echo 60 > elapsed.txt; fi
            - run: cat elapsed.txt
            - run: if [ "$(cat elapsed.txt)" -lt "30" ]; then echo "PR is just opened, wait some actions from GitHub"; sleep 30; fi
            - run: 'if grep -q "\"draft\": true," github.txt; then echo "draft mode, skip test!"; circleci-agent step halt; fi'
            - run: uv pip install -U -e .
            - run: echo 'export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)"' >> "$BASH_ENV" && source "$BASH_ENV"
            - run: mkdir -p test_preparation
            - run: python utils/tests_fetcher.py | tee tests_fetched_summary.txt
            - run: python utils/tests_fetcher.py --filter_tests
            - run: export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)" && echo $GIT_COMMIT_MESSAGE && python .circleci/create_circleci_config.py --fetcher_folder test_preparation
            - run: |
                if [ ! -s test_preparation/generated_config.yml ]; then
                    echo "No tests to run, exiting early!"
                    circleci-agent step halt
                fi                

            - store_artifacts:
                path: test_preparation

            - run:
                name: "Retrieve Artifact Paths"
                # [reference] https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts
                # `CIRCLE_TOKEN` is defined as an environment variables set within a context, see `https://circleci.com/docs/contexts/`
                command: |
                    project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
                    job_number=${CIRCLE_BUILD_NUM}
                    url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
                    curl -o test_preparation/artifacts.json ${url} --header "Circle-Token: $CIRCLE_TOKEN"                    
            - run:
                name: "Prepare pipeline parameters"
                command: |
                    python utils/process_test_artifacts.py                    

            # To avoid too long generated_config.yaml on the continuation orb, we pass the links to the artifacts as parameters.
            # Otherwise the list of tests was just too big. Explicit is good but for that it was a limitation.
            # We used:

            # https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts : to get the job artifacts
            # We could not pass a nested dict, which is why we create the test_file_... parameters for every single job

            - store_artifacts:
                path: test_preparation/transformed_artifacts.json
            - store_artifacts:
                path: test_preparation/artifacts.json
            - continuation/continue:
                parameters:  test_preparation/transformed_artifacts.json
                configuration_path: test_preparation/generated_config.yml

    # To run all tests for the nightly build
    fetch_all_tests:
        working_directory: ~/transformers
        docker:
            - image: huggingface/transformers-quality
        parallelism: 1
        steps:
            - checkout
            - run: uv pip install -U -e .
            - run: echo 'export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)"' >> "$BASH_ENV" && source "$BASH_ENV"
            - run: mkdir -p test_preparation
            - run: python utils/tests_fetcher.py --fetch_all | tee tests_fetched_summary.txt
            - run: python utils/tests_fetcher.py --filter_tests
            - run: export "GIT_COMMIT_MESSAGE=$(git show -s --format=%s)" && echo $GIT_COMMIT_MESSAGE && python .circleci/create_circleci_config.py --fetcher_folder test_preparation
            - run: |
                if [ ! -s test_preparation/generated_config.yml ]; then
                    echo "No tests to run, exiting early!"
                    circleci-agent step halt
                fi                

            - store_artifacts:
                path: test_preparation

            - run:
                name: "Retrieve Artifact Paths"
                env:
                    CIRCLE_TOKEN: ${{ secrets.CI_ARTIFACT_TOKEN }}
                command: |
                    project_slug="gh/${CIRCLE_PROJECT_USERNAME}/${CIRCLE_PROJECT_REPONAME}"
                    job_number=${CIRCLE_BUILD_NUM}
                    url="https://circleci.com/api/v2/project/${project_slug}/${job_number}/artifacts"
                    curl -o  test_preparation/artifacts.json ${url}                    
            - run:
                name: "Prepare pipeline parameters"
                command: |
                    python utils/process_test_artifacts.py                    

            # To avoid too long generated_config.yaml on the continuation orb, we pass the links to the artifacts as parameters.
            # Otherwise the list of tests was just too big. Explicit is good but for that it was a limitation.
            # We used:

            # https://circleci.com/docs/api/v2/index.html#operation/getJobArtifacts : to get the job artifacts
            # We could not pass a nested dict, which is why we create the test_file_... parameters for every single job

            - store_artifacts:
                path: test_preparation/transformed_artifacts.json
            - store_artifacts:
                path: test_preparation/artifacts.json
            - continuation/continue:
                parameters:  test_preparation/transformed_artifacts.json
                configuration_path: test_preparation/generated_config.yml

    check_code_quality:
        working_directory: ~/transformers
        docker:
            - image: huggingface/transformers-quality
        resource_class: large
        environment:
            TRANSFORMERS_IS_CI: yes
            PYTEST_TIMEOUT: 120
        parallelism: 1
        steps:
            - checkout
            - run: uv pip install -e ".[quality]"
            - run:
                name: Show installed libraries and their versions
                command: pip freeze | tee installed.txt
            - store_artifacts:
                  path: ~/transformers/installed.txt
            - run: python -c "from transformers import *" || (echo '🚨 import failed, this means you introduced unprotected imports! 🚨'; exit 1)
            - run: ruff check examples tests src utils
            - run: ruff format tests src utils --check
            - run: python utils/custom_init_isort.py --check_only
            - run: python utils/sort_auto_mappings.py --check_only
            - run: python utils/check_doc_toc.py
            - run: python utils/check_docstrings.py --check_all

    check_repository_consistency:
        working_directory: ~/transformers
        docker:
            - image: huggingface/transformers-consistency
        resource_class: large
        environment:
            TRANSFORMERS_IS_CI: yes
            PYTEST_TIMEOUT: 120
        parallelism: 1
        steps:
            - checkout
            - run: uv pip install -e ".[quality]"
            - run:
                name: Show installed libraries and their versions
                command: pip freeze | tee installed.txt
            - store_artifacts:
                  path: ~/transformers/installed.txt
            - run: python utils/check_copies.py
            - run: python utils/check_modular_conversion.py
            - run: python utils/check_dummies.py
            - run: python utils/check_repo.py
            - run: python utils/check_inits.py
            - run: python utils/check_config_docstrings.py
            - run: python utils/check_config_attributes.py
            - run: python utils/check_doctest_list.py
            - run: make deps_table_check_updated
            - run: python utils/update_metadata.py --check-only
            - run: python utils/check_docstrings.py

workflows:
    version: 2
    setup_and_quality:
        when:
            and:
                - equal: [<<pipeline.project.git_url>>, https://github.com/huggingface/transformers]
                - not: <<pipeline.parameters.nightly>>
        jobs:
            - check_circleci_user
            - check_code_quality
            - check_repository_consistency
            - fetch_tests

    setup_and_quality_2:
        when:
            not:
                 equal: [<<pipeline.project.git_url>>, https://github.com/huggingface/transformers]
        jobs:
            - check_circleci_user
            - check_code_quality
            - check_repository_consistency
            - fetch_tests:
                # [reference] https://circleci.com/docs/contexts/
                context:
                    - TRANSFORMERS_CONTEXT

    nightly:
        when: <<pipeline.parameters.nightly>>
        jobs:
            - check_circleci_user
            - check_code_quality
            - check_repository_consistency
            - fetch_all_tests