default_language_version:
  python: python3

# The vendored upstream module stays byte-diffable against its source; keep
# formatters and linters away so upstream-tracking diffs remain minimal.
exclude: '^miles/utils/chat_template_utils/templates/encoding_dsv32\.py$'

ci:
  autofix_prs: true
  autoupdate_commit_msg: '[pre-commit.ci] pre-commit suggestions'
  autoupdate_schedule: quarterly

repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v4.5.0
    hooks:
      - id: check-yaml
        args: ['--allow-multiple-documents']
        exclude: '^charts/.*/templates/'
      - id: check-case-conflict
      - id: detect-private-key
      - id: check-added-large-files
        args: ['--maxkb=1000']
      - id: requirements-txt-fixer

  - repo: https://github.com/astral-sh/ruff-pre-commit
    rev: v0.14.7
    hooks:
      - id: ruff-check
        args: [ --fix ]

  - repo: https://github.com/PyCQA/autoflake
    rev: v2.0.2
    hooks:
      - id: autoflake
        args: [--remove-all-unused-imports, --in-place]

  - repo: https://github.com/pycqa/isort
    rev: 5.13.2          # 选一个稳定版本
    hooks:
      - id: isort
        args:
          - "--profile=black"        # 常见：与 Black 对齐风格
          - "--filter-files"         # 忽略已在 .gitignore 的文件
        additional_dependencies: []  # 需要插件时在这里加

  - repo: https://github.com/psf/black
    rev: 24.3.0
    hooks:
      - id: black
        name: Format code
        additional_dependencies: ['click==8.0.2']

  - repo: local
    hooks:
      - id: sync-example-docs
        name: Mirror examples/ READMEs into the docs site
        language: system
        entry: python3 scripts/tools/sync_example_docs.py
        files: '^(examples/.*README\.md|docs/examples/.*|docs/docs\.json|scripts/tools/sync_example_docs\.py)$'
        pass_filenames: false

      - id: ban-docs-nav-group-root
        name: Ban group `root` in docs navigation (put the landing page first in `pages` with `sidebarTitle Overview` instead; see docs/README.md)
        language: pygrep
        entry: '"root":'
        files: ^docs/docs\.json$

      - id: helm-lint
        name: helm lint every chart
        language: system
        entry: python3 tools/kubernetes/lint_charts.py
        pass_filenames: false
        files: '^charts/'

      - id: ban-mpu-get
        name: Ban direct mpu.get_* calls (use ParallelState)
        language: pygrep
        entry: 'mpu\.get_'
        types: [python]
        exclude: '(backends/megatron_utils/parallel\.py|tools/convert_to_hf\.py|miles_plugins/|examples/)'

      - id: ban-bare-auto-loaders
        name: Ban bare Auto{Config,Tokenizer}.from_pretrained (use load_hf_config / load_tokenizer)
        language: pygrep
        entry: '(AutoConfig|AutoTokenizer)\.from_pretrained'
        types: [python]
        exclude: '(miles/utils/hf_utils/config\.py|miles/utils/processing_utils\.py|tests/|test_utils/|miles_plugins/|examples/)'

      - id: ban-huggingface-cli
        name: Ban deprecated huggingface-cli (use hf)
        language: pygrep
        entry: 'huggingface-cli'
        types: [python]