headroom/.github/workflows/eval.yml

name: Evaluation Suite

on:
  schedule:
    - cron: '0 6 * * 1'  # Weekly on Monday 6am UTC
  workflow_dispatch:       # Manual trigger
  pull_request:
    paths:
      - 'headroom/transforms/**'
      - 'headroom/evals/**'
      - 'headroom/compress.py'

jobs:
  # Fast smoke test on PRs touching compression code (~$0.05, ~2 min)
  smoke-test:
    if: github.event_name == 'pull_request'
    runs-on: ubuntu-latest
    timeout-minutes: 30
    steps:
      - uses: actions/checkout@v7
      - uses: actions/setup-python@v7
        with:
          python-version: "3.11"

      - name: Cache pip
        uses: actions/cache@v6
        with:
          path: ~/.cache/pip
          key: ${{ runner.os }}-pip-eval-${{ hashFiles('pyproject.toml') }}
          restore-keys: ${{ runner.os }}-pip-eval-

      # `pip install -e .` invokes maturin (declared in pyproject.toml's
      # build-system) which calls cargo to compile the Rust extension.
      - name: Install Rust toolchain
        uses: dtolnay/rust-toolchain@1.96.0

      - name: Cache cargo registry + build
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: ". -> target"

      - name: Install dependencies (builds Rust extension via maturin)
        run: |
          pip install -e ".[all]"
          python -c "from headroom._core import SmartCrusher; print('headroom._core OK:', SmartCrusher)"

      - name: Run CCR round-trip (zero cost)
        run: |
          python -c "
          from headroom.evals.runners.compression_only import CompressionOnlyRunner
          runner = CompressionOnlyRunner()
          cases = runner.generate_ccr_test_cases(n=50)
          result = runner.evaluate_ccr_lossless(cases)
          print(f'CCR Round-trip: {result.passed_cases}/{result.total_cases} passed')
          assert result.passed, f'CCR failures: {result.errors}'
          "

      - name: Run tool schema compaction integrity eval (zero cost)
        run: |
          python -c "
          from headroom.evals.runners.compression_only import CompressionOnlyRunner
          runner = CompressionOnlyRunner()
          result = runner.evaluate_tool_schema_compaction()
          print(f'Tool schema compaction: {result.passed_cases}/{result.total_cases} passed, {result.total_tokens_saved} annotation tokens stripped')
          assert result.passed, f'Schema compaction failures: {result.errors}'
          "

      # OPENAI_API_KEY is intentionally not set in the public OSS repo
      # (the secret list is empty). The CCR round-trip step above is the
      # mandatory gate; this step only runs when an operator has wired
      # OPENAI_API_KEY as a repo secret (e.g. on a downstream fork). When
      # missing, emit a loud GitHub `::warning::` annotation so the skip
      # is visible in the run summary — never a silent pass.
      - name: Run built-in tool output eval (skipped when OPENAI_API_KEY unset)
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
        run: |
          if [ -z "${OPENAI_API_KEY}" ]; then
            echo "::warning title=Smoke eval skipped::OPENAI_API_KEY is not configured for this repo; only the CCR round-trip gate ran. Wire the secret to enable the live OpenAI eval."
            exit 0
          fi
          python -m headroom.evals quick -n 8 --provider openai --model gpt-4o-mini

  # Full Tier 1 suite, weekly or manual (~$3-5, ~30-45 min)
  weekly-suite:
    if: github.event_name == 'schedule' || github.event_name == 'workflow_dispatch'
    runs-on: ubuntu-latest
    timeout-minutes: 90
    steps:
      - uses: actions/checkout@v7
      - uses: actions/setup-python@v7
        with:
          python-version: "3.11"

      - name: Cache pip
        uses: actions/cache@v6
        with:
          path: ~/.cache/pip
          key: ${{ runner.os }}-pip-eval-${{ hashFiles('pyproject.toml') }}
          restore-keys: ${{ runner.os }}-pip-eval-

      - name: Install Rust toolchain
        uses: dtolnay/rust-toolchain@1.96.0

      - name: Cache cargo registry + build
        uses: Swatinem/rust-cache@v2
        with:
          workspaces: ". -> target"

      - name: Install dependencies (builds Rust extension via maturin)
        run: |
          pip install -e ".[all]"
          python -c "from headroom._core import SmartCrusher; print('headroom._core OK')"
      - name: Run Tier 1 evaluation suite
        run: |
          if [ -z "${OPENAI_API_KEY}" ]; then
            echo "::warning title=Weekly eval skipped::OPENAI_API_KEY is not configured for this repo; skipping the live Tier 1 suite."
            mkdir -p eval_results
            printf '%s\n\n%s\n' \
              '# Weekly Evaluation Skipped' \
              'OPENAI_API_KEY is not configured for this repository, so the live Tier 1 evaluation suite was skipped.' \
              > eval_results/skipped.md
            exit 0
          fi
          python -m headroom.evals suite --tier 1 --ci -o eval_results/
        env:
          OPENAI_API_KEY: ${{ secrets.OPENAI_API_KEY }}
          ANTHROPIC_API_KEY: ${{ secrets.ANTHROPIC_API_KEY }}

      # Recall-based fidelity report on the production routing path. Zero cost
      # (synthetic structured cases -> Rust compressors; no model, no API, no
      # secrets). Non-blocking: surfaces recall trends weekly without gating.
      # The blocking per-PR fidelity gate lives in
      # tests/test_compression_fidelity_regression.py (runs in the [dev] shard).
      - name: Information-retention recall report (zero cost, non-blocking)
        run: |
          python -c "
          from headroom.evals.runners.compression_only import CompressionOnlyRunner
          runner = CompressionOnlyRunner()
          cases = runner.generate_info_retention_cases(n=50)
          result = runner.evaluate_information_retention(cases)
          print(f'Information retention: {result.passed_cases}/{result.total_cases} cases >=0.9 recall, avg compression {result.avg_compression_ratio:.1%}')
          if not result.passed:
              print(f'::warning title=Fidelity recall::{result.failed_cases} case(s) fell below 0.9 recall: {result.errors[:3]}')
          "

      # Real-dataset recall on the prose path (HotpotQA): does the ground-truth
      # answer survive compressing the supporting context? Uses the production
      # routing path, so prose flows through Kompress (ModernBERT) — allowed here
      # because the weekly job installs [all]. Non-blocking and defensive: a
      # dataset download or model failure warns rather than fails the job.
      - name: Dataset recall report — HotpotQA (model-allowed, non-blocking)
        run: |
          python -c "
          try:
              from headroom.transforms.kompress_compressor import warm_kompress_model
              from headroom.evals.datasets import load_hotpotqa
              from headroom.evals.runners.compression_only import CompressionOnlyRunner
              # Block until the Kompress model is loaded; otherwise prose passes
              # through uncompressed and the recall number is meaningless.
              warmed = warm_kompress_model()
              suite = load_hotpotqa(n=50)
              result = CompressionOnlyRunner().evaluate_dataset_recall(suite)
              print(f'HotpotQA answer recall: {result.passed_cases}/{result.total_cases} probeable cases >=0.9, avg compression {result.avg_compression_ratio:.1%} (model_warmed={warmed})')
              if result.avg_compression_ratio < 0.01:
                  print('::warning title=Dataset recall::compression did not engage (~0%); recall is not a meaningful fidelity signal — check Kompress model availability')
              elif result.failed_cases:
                  print(f'::warning title=Dataset recall::{result.failed_cases} HotpotQA case(s) lost the answer under compression')
          except Exception as e:
              print(f'::warning title=Dataset recall::skipped (dataset/model unavailable): {e}')
          " || true

      - name: Upload results
        if: always()
        uses: actions/upload-artifact@v7
        with:
          name: eval-results-${{ github.run_number }}
          path: eval_results/