Skip to content

perf: avoid full-width post-clean narrative profiling #35

perf: avoid full-width post-clean narrative profiling

perf: avoid full-width post-clean narrative profiling #35

Workflow file for this run

# Validation Gauntlet: gold-labelled disposition benchmark for the validation,
# domain and text-cleaning surfaces. Runs the lightweight fixtures on every PR
# and gates on the absolute thresholds plus no-regression vs the stored
# baseline (benchmarks/gauntlet/baseline.json). Heavier sizes stay manual.
name: Validation Gauntlet
on:
pull_request:
paths-ignore:
- "docs/**"
- "*.md"
workflow_dispatch:
inputs:
rows:
description: "rows per fixture"
default: "300"
update_baseline:
description: "re-pin baseline.json from this run (commit it manually)"
type: boolean
default: false
permissions:
contents: read
jobs:
gauntlet:
runs-on: ubuntu-latest
timeout-minutes: 20
steps:
- uses: actions/checkout@v4
- uses: actions/setup-python@v5
with:
python-version: "3.12"
cache: pip
- name: Install
run: |
python -m pip install --upgrade pip
pip install -e ".[dev]"
- name: Run gauntlet with gates
run: |
ROWS="${{ github.event.inputs.rows || '300' }}"
EXTRA=""
if [ "${{ github.event.inputs.update_baseline }}" = "true" ]; then
EXTRA="--update-baseline"
fi
python -m benchmarks.gauntlet run --rows "$ROWS" --check $EXTRA
- name: Job summary
if: always()
run: |
if [ -f benchmarks/gauntlet/results/gauntlet.md ]; then
cat benchmarks/gauntlet/results/gauntlet.md >> "$GITHUB_STEP_SUMMARY"
fi
- name: Upload results
if: always()
uses: actions/upload-artifact@v4
with:
name: gauntlet-results
path: benchmarks/gauntlet/results/
if-no-files-found: warn