Benchmarks (weekly) #9

	name: Benchmarks (weekly)

	on:
	schedule:
	- cron: '17 6 * * 1' # Mondays 06:17 UTC
	workflow_dispatch:

	permissions:
	contents: read

	jobs:
	full-bench:
	name: Full 4-benchmark sweep
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	- uses: actions/setup-node@v4
	with:
	node-version: '20'
	cache: 'npm'
	- name: Install dependencies
	run: npm ci
	- name: Build TypeScript
	run: npm run build
	- name: Run all benchmarks (if datasets available)
	run: \|
	if [ -f /tmp/longmemeval-data/longmemeval_s_cleaned.json ] && [ -f /tmp/locomo/data/locomo10.json ] && [ -d /tmp/membench-data/MemData/FirstAgent ] && [ -d /tmp/beam/chats/100K ]; then
	npm run bench
	else
	echo "Dataset(s) missing — skipping full run." >&2
	exit 0
	fi
	- name: Upload results artifact
	uses: actions/upload-artifact@v4
	if: always()
	with:
	name: benchmark-results
	path: benchmarks/results/

Navigation Menu