# Research Stack pre-commit configuration
# -----------------------------------------------------------------------------
# Math-first guardrails that run on every commit. See docs/math-first-tooling.md
# for the contract and rationale.
#
# Install once per clone:
#   uv tool install pre-commit
#   pre-commit install
#
# Run against the full tree:
#   pre-commit run --all-files
# -----------------------------------------------------------------------------

default_install_hook_types: [pre-commit]
fail_fast: false

repos:
  # --- Generic hygiene -------------------------------------------------------
  - repo: https://github.com/pre-commit/pre-commit-hooks
    rev: v5.0.0
    hooks:
      - id: check-json
        # Schemas, MCP config, package.json, VS Code config, and JSON receipts.
        files: '\.json$'
        # Skip Lean editor metadata and Lake-managed lockfiles.
        exclude: '\.(lean\.pist\.meta|lake)/'
      - id: check-yaml
        # Validate YAML at the syntactic level. The claims registry gets a
        # stronger semantic check below.
        files: '\.(ya?ml)$'
      - id: end-of-file-fixer
        # Force a trailing newline only on text files the math-first scripts
        # actually own. Avoid sweeping the rest of the tree (see AGENTS.md).
        files: '^(scripts/math-first/|shared-data/schemas/|claims\.yaml$|docs/math-first-tooling\.md$|\.mcp\.json$|\.pre-commit-config\.yaml$|\.github/workflows/math-check\.yml$)'
      - id: trailing-whitespace
        files: '^(scripts/math-first/|shared-data/schemas/|claims\.yaml$|docs/math-first-tooling\.md$|\.mcp\.json$|\.pre-commit-config\.yaml$|\.github/workflows/math-check\.yml$)'
      - id: detect-private-key

  # --- Math-first guardrails -------------------------------------------------
  - repo: local
    hooks:
      - id: deepseek-receipt-schema
        name: Validate DeepSeek review receipts
        description: >-
          Validates every tracked *.receipt.json under
          shared-data/artifacts/deepseek_review/ against
          shared-data/schemas/deepseek-review-receipt.schema.json.
        entry: scripts/math-first/validate_deepseek_receipts.py
        language: python
        additional_dependencies:
          - "jsonschema>=4.21"
          - "rfc3339-validator"
        files: '^shared-data/artifacts/deepseek_review/.*\.receipt\.json$'
        # Pass matched files explicitly so partial commits still get a check
        # but stay scoped to the changed receipts.
        require_serial: true
        types_or: [file]

      - id: claims-registry-schema
        name: Validate claims.yaml registry
        description: >-
          Validates claims.yaml against
          shared-data/schemas/claims-registry.schema.json and asserts every
          referenced repo-relative path exists on disk.
        entry: scripts/math-first/validate_claims_registry.py
        language: python
        additional_dependencies:
          - "jsonschema>=4.21"
          - "PyYAML"
        files: '^claims\.yaml$'
        pass_filenames: false
        require_serial: true

      - id: receipt-required-for-math-content
        name: Require a DeepSeek receipt or Lean proof for math-track content
        description: >-
          If a commit touches a file under one of the math-track surfaces
          (Lean Semantics kernels, ArithmeticSpec docs, stack solidification
          receipts), require that at least one file under
          shared-data/artifacts/deepseek_review/ or
          0-Core-Formalism/lean/Semantics/ -- or claims.yaml -- is also part
          of the same commit. This enforces the math-first contract at
          commit time; the same check runs in CI for PR-scope coverage.
        entry: scripts/math-first/require_math_evidence.py --staged
        language: python
        # always_run + pass_filenames: false because pre-commit's per-hook
        # ``files`` filter would otherwise strip evidence files (receipts,
        # claims.yaml) from the staged file list before the script ever
        # sees them. The script reads the full staged set itself via
        # ``git diff --cached --name-only`` and exits 0 early if no
        # math-track files are present, so this is cheap.
        always_run: true
        pass_filenames: false
        require_serial: true