signal-bot/.pre-commit-config.yaml

# Pre-commit hooks for signal-bot.
#
# Install with:  pre-commit install
# Run manually:  pre-commit run --all-files
#
# Every hook is `language: system` because the tools already live in .venv;
# pre-commit must not build isolated environments for them. fail_fast so a
# later check cannot run after an earlier one has already rejected the commit.
fail_fast: true

repos:
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v4.6.0
    hooks:
      - id: trailing-whitespace
        args: [--markdown-linebreak-ext=md]
      - id: end-of-file-fixer
      - id: check-yaml
      - id: check-json
      - id: check-toml
      - id: check-merge-conflict
      - id: check-case-conflict
      - id: check-executables-have-shebangs
      - id: check-shebang-scripts-are-executable
      - id: detect-private-key
      - id: debug-statements
      - id: check-ast
      - id: mixed-line-ending
        args: [--fix=lf]

  - repo: local
    hooks:
      # Suppressions are blocked mechanically, not by discipline. This repo
      # has zero of them and the only way it stays that way is a gate: the
      # rule is "fix the finding, or ask first", and a habit is not a gate.
      - id: no-noqa
        name: block noqa / type:ignore comments
        entry: '(?i)#\s*(noqa|type:\s*ignore)'
        language: pygrep
        types: [python]

      - id: no-ruff-noqa
        name: block file-level ruff noqa
        entry: '(?i)#\s*ruff:\s*noqa'
        language: pygrep
        types: [python]

      # This repository is public and holds a private message database. The
      # database is gitignored, but three binary SQLite files reached the
      # history anyway before this gate existed, so .gitignore is evidently
      # not the whole defence. Exceptions go in .binary-allowlist.
      # This repository is public and leaked once: real names, two phone
      # numbers and a member's Signal uuid reached GitHub and only came off
      # it by deleting the repository. The checker learns what to refuse from
      # OUTSIDE the repo -- the photo pack, the message database, .env -- so
      # the list of real names is never in the thing being checked.
      - id: personal-data
        name: no personal data
        entry: scripts/check_personal_data.sh
        language: system
        types: [text]

      # The same check on the commit message, because that is where two of
      # the leaks actually lived.
      - id: personal-data-message
        name: no personal data in the commit message
        entry: scripts/check_personal_data.sh --message
        language: system
        stages: [commit-msg]
        always_run: true
        pass_filenames: true

      - id: no-binaries
        name: no binary or image files
        entry: scripts/check_no_binaries.sh
        language: script
        pass_filenames: true

      # The shared 250-line cap. Checks only the files in the commit, so an
      # unrelated commit never breaks. No baseline, no allowlist -- those are
      # suppressions. The exemption list lives with the checker in ~/utils so
      # this repo's idea of the rule cannot drift from every other repo's.
      - id: file-length
        name: file length <= 250 lines
        entry: scripts/check_file_length.sh
        language: system

      # Four markdown namespaces (README / CLAUDE* / DOCS* / TODO*), plus the
      # rule that a TODO carries "REMOVE ME AFTER FINISH" and nothing else may.
      - id: md-naming
        name: markdown naming convention
        entry: scripts/check_md_naming.sh
        language: system
        files: \.md$

      # Exact pins at newest stable. Runs repo-wide: a pin goes stale because
      # upstream released, not because this commit touched the manifest.
      - id: dependency-freshness
        name: dependencies are newest stable
        entry: scripts/check_dependency_freshness.sh --all
        language: system
        pass_filenames: false
        always_run: true

      - id: ruff-format
        name: ruff format
        entry: .venv/bin/ruff format --check
        language: system
        types_or: [python, pyi]

      - id: ruff
        name: ruff (ALL rules)
        entry: .venv/bin/ruff check --force-exclude
        language: system
        types_or: [python, pyi]

      - id: mypy
        name: mypy --strict
        entry: .venv/bin/mypy
        language: system
        pass_filenames: false
        args: [signal_bot, fake_signal, tool]

      - id: shellcheck
        name: shellcheck
        # Same severity floor as CI: a stricter runner version must not be
        # the thing that discovers a finding this hook let through.
        entry: shellcheck -x --severity=style
        language: system
        types: [shell]

      # The watchdog is bash, so pytest cannot reach it. Its own suite stubs
      # curl, docker, notify-send and logger, and drives every branch --
      # including the give-up cap and how many popups a whole window produces.
      - id: watchdog-tests
        name: watchdog behaviour (bash)
        entry: scripts/test_watchdog.sh
        language: system
        pass_filenames: false
        files: ^scripts/(signal_api_watchdog|test_watchdog|test_watchdog_harness)\.sh$

      # 100% branch coverage, no omits. Runs on every commit: coverage is the
      # whole point of the suite, and a partial run cannot prove it.
      - id: pytest
        name: pytest (100% branch coverage)
        entry: .venv/bin/python -m pytest -q
        language: system
        pass_filenames: false
        always_run: true