Fix extraction grounding bugs: page fallback, idempotency, label-set scoping #4434

Workflow file for this run

.github/workflows/backend.yml at b6f8e0f

	name: Backend CI

	# Enable Buildkit and let compose use it to speed up image building
	env:
	DOCKER_BUILDKIT: 1
	COMPOSE_DOCKER_CLI_BUILD: 1
	SKLEARN_ALLOW_DEPRECATED_SKLEARN_PACKAGE_INSTALL: True

	defaults:
	run:
	working-directory: ./

	on:
	pull_request:
	branches: [ "master", "main", "v*" ]
	paths-ignore: [ "docs/**" ]

	push:
	branches: [ "master", "main", "v*" ]
	paths-ignore: [ "docs/**" ]

	concurrency:
	group: ${{ github.head_ref \|\| github.run_id }}
	cancel-in-progress: true

	jobs:
	changes:
	# Path filtering only gates pull_request events; pushes to protected
	# branches always run downstream regardless of which files changed.
	# dorny/paths-filter@v4 additionally needs a checked-out repo on push
	# events (it shells out to `git branch --show-current`), so scoping
	# this job to pull_request avoids the "fatal: not a git repository"
	# red X that would otherwise appear on every push to main.
	if: github.event_name == 'pull_request'
	runs-on: ubuntu-latest
	# Fail open: if this job errors (e.g., transient GitHub API failure),
	# downstream jobs should still run rather than being silently skipped.
	continue-on-error: true
	permissions:
	contents: read
	pull-requests: read
	outputs:
	backend: ${{ steps.filter.outputs.backend }}
	steps:
	# No checkout needed: dorny/paths-filter@v4 reads diffs from the
	# pull_request event payload.
	- uses: dorny/paths-filter@v4
	id: filter
	with:
	filters: \|
	backend:
	- 'opencontractserver/**'
	- 'config/**'
	- '*.py'
	- 'requirements/**'
	- 'test.yml'
	- 'compose/**'
	- 'Dockerfile*'
	- '.pre-commit-config.yaml'
	- 'setup.cfg'
	- 'mypy.ini'
	- 'pyproject.toml'
	- '.github/workflows/backend.yml'

	linter:
	needs: changes
	# Run on every push, and on PRs unless the filter explicitly reports
	# no backend changes ('false'). `always()` is required because the
	# `changes` job is skipped on push events (see its `if:` above), and
	# a skipped `needs` target would otherwise cascade-skip this job.
	# The `!= 'false'` form also preserves the fail-open behaviour on
	# PRs where `changes` errors transiently (outputs.backend is '').
	if: always() && (github.event_name == 'push' \|\| needs.changes.outputs.backend != 'false')
	runs-on: ubuntu-latest
	permissions:
	contents: read
	steps:
	- name: Checkout Code Repository
	uses: actions/checkout@v6

	- name: Set up Python
	uses: actions/setup-python@v6
	with:
	python-version: "3.12"
	cache: pip
	cache-dependency-path: \|
	requirements/base.txt
	requirements/local.txt

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

	- name: Run pre-commit
	run: pre-commit run --all-files

	- name: Run mypy
	# Runs from requirements/local.txt (not via pre-commit) so CI is
	# authoritative even when contributors skip the hook. Keep the
	# mypy pin in requirements/local.txt in sync with the `rev:` of
	# the mirrors-mypy hook in .pre-commit-config.yaml — a drift
	# means the hook and CI can disagree silently. See
	# docs/typing/README.md.
	run: python -m mypy --config-file mypy.ini opencontractserver config

	pytest:
	needs: [changes, linter]
	# Same fail-open semantics as the linter gate above.
	if: always() && needs.linter.result == 'success' && (github.event_name == 'push' \|\| needs.changes.outputs.backend != 'false')
	runs-on: yuge
	timeout-minutes: 180
	permissions:
	contents: read
	actions: read

	steps:
	- name: Checkout Code Repository
	uses: actions/checkout@v6

	- name: Store Codecov Env Flags
	continue-on-error: true
	run: \|
	ci_env=`bash <(curl -s https://codecov.io/env)`
	echo "$ci_env"

	- name: Build the Stack
	run: docker compose -f test.yml build

	- name: Run DB Migrations
	run: docker compose -f test.yml run --rm django python manage.py migrate

	- name: Collect Static Files
	run: docker compose -f test.yml run --rm django python manage.py collectstatic

	- name: Verify Docker Containers
	run: \|
	docker compose -f test.yml ps

	- name: Capture Docker Compose Logs
	if: failure()
	run: \|
	docker compose -f test.yml logs --no-color > docker-compose-logs.txt

	- name: Upload Docker Compose Logs
	if: failure()
	uses: actions/upload-artifact@v7
	with:
	name: docker-compose-logs
	path: docker-compose-logs.txt

	- name: Check Container Health
	run: \|
	echo "=== Docker containers status ==="
	docker compose -f test.yml ps
	echo "=== Container logs (last 20 lines each) ==="
	for container in $(docker compose -f test.yml ps -q); do
	name=$(docker inspect -f '{{.Name}}' $container \| sed 's/^\///')
	echo "--- Logs for $name ---"
	docker logs --tail 20 $container 2>&1 \|\| true
	done
	echo "=== Memory usage ==="
	docker stats --no-stream
	free -h

	- name: Build Pytest Coverage File
	timeout-minutes: 100
	run: \|
	# Run the full test suite with coverage using parallel workers
	# pytest-cov with pytest-xdist handles coverage merging automatically
	docker compose -f test.yml run django pytest --cov --cov-report=xml -n auto --dist loadscope -v

	- name: Verify Coverage File Exists
	run: \|
	# Verify coverage.xml exists in the working directory
	ls -la coverage.xml

	- name: Upload Coverage Reports to Codecov
	uses: codecov/codecov-action@v6
	with:
	token: ${{ secrets.CODECOV_TOKEN }}
	files: ./coverage.xml
	flags: backend
	name: backend-coverage
	fail_ci_if_error: false

	- name: Tear down the Stack
	run: docker compose -f test.yml down

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Uh oh!

Fix extraction grounding bugs: page fallback, idempotency, label-set scoping #4434

Workflow file

Fix extraction grounding bugs: page fallback, idempotency, label-set scoping #4434

Uh oh!

Workflow file for this run