Sync data from eval-pipeline #3

	name: Sync data from eval-pipeline

	on:
	pull_request:

	# TODO XXX replace with
	# push:
	# branches: [main]

	jobs:
	sync-data:
	runs-on: ubuntu-latest
	steps:
	- uses: actions/checkout@v4
	with:
	ref: ${{ github.head_ref \|\| github.ref }}
	token: ${{ secrets.GITHUB_TOKEN }}

	- name: Install Poetry
	run: pipx install poetry==1.8.3

	- name: Install python
	uses: actions/setup-python@v5
	with:
	python-version: "3.11"
	cache: poetry

	- name: poetry install
	run: \|-
	poetry install
	echo "$(poetry env info --path)/bin" >> $GITHUB_PATH

	- name: Configure SSH
	run: \|-
	eval `ssh-agent -s`
	ssh-add - <<< "${{ secrets.EVAL_PIPELINE_DEPLOY_KEY }}"
	mkdir -p ~/.ssh
	ssh-keyscan github.com >> ~/.ssh/known_hosts
	echo "SSH_AUTH_SOCK=${SSH_AUTH_SOCK}" >> $GITHUB_ENV
	echo "SSH_AGENT_PID=${SSH_AGENT_PID}" >> $GITHUB_ENV

	- name: Fetch data and commit back to repo
	run: \|-

	git status

	dvc get --force [email protected]:METR/eval-pipeline public/data/external/all_runs.jsonl -o data/external/all_runs.jsonl --remote-config access_key_id=${{ secrets.AWS_ACCESS_KEY_ID }} secret_access_key=${{ secrets.AWS_SECRET_ACCESS_KEY }}

	if git diff --name-only --exit-code
	then
	echo "No changes"
	exit 0
	fi

	git config --local user.email "[email protected]"
	git config --local user.name "GitHub Action"
	git commit -am "Update data from eval-pipeline"
	echo "Pushing..."
	git push origin HEAD:${{ github.head_ref }}

Provide feedback