name: CI

on:
  push:
    branches: [main, develop]
  pull_request:
    branches: [main]

env:
  FORCE_JAVASCRIPT_ACTIONS_TO_NODE24: true

jobs:
  lint:
    name: Lint (ruff)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install ruff
        run: pip install ruff

      - name: Run ruff
        run: ruff check src/ tests/

  typecheck:
    name: Type check (mypy)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements/base.txt mypy types-PyYAML types-beautifulsoup4 types-requests

      - name: Run mypy
        run: mypy src/ --ignore-missing-imports

  test:
    name: Unit tests (pytest)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements/base.txt pytest pytest-cov

      - name: Run tests
        run: pytest tests/unit/ -v --cov=src --cov-report=term-missing

  integration:
    name: Integration tests (pytest)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements/base.txt pytest

      - name: Run integration tests
        run: pytest tests/integration/ -v

  evals-smoke:
    name: Eval smoke test (mock pipeline)
    runs-on: ubuntu-latest
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements/base.txt

      - name: Run smoke evals (mock, no LLM required)
        run: |
          PYTHONPATH=. python -m evals.run_evals \
            --dataset evals/datasets/smoke.jsonl \
            --mock \
            --no-nli \
            --output evals/reports/ \
            --correctness-threshold 0.0 \
            --faithfulness-threshold 0.0

      - name: Upload eval report
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: eval-report
          path: evals/reports/

  evals-golden:
    name: Golden evals (Anthropic Haiku)
    if: ${{ secrets.ANTHROPIC_API_KEY != '' }}
    runs-on: ubuntu-latest
    env:
      ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}
    steps:
      - uses: actions/checkout@v4

      - uses: actions/setup-python@v5
        with:
          python-version: "3.13"
          cache: pip

      - name: Install dependencies
        run: pip install -r requirements/base.txt

      - name: Run golden evals (live pipeline, Anthropic Haiku)
        run: |
          PYTHONPATH=. python -m evals.run_evals \
            --dataset evals/datasets/golden_ci.jsonl \
            --judge-provider anthropic \
            --judge-model claude-haiku-4-5 \
            --output evals/reports/ \
            --faithfulness-threshold 0.7 \
            --correctness-threshold 0.2

      - name: Upload golden eval report
        if: always()
        uses: actions/upload-artifact@v4
        with:
          name: eval-report-golden
          path: evals/reports/