Files
steve 68276810ec e2e: dump error-context.md to log on failure + bump upload-artifact
The Playwright run produces error-context.md per failed test
with a full DOM snapshot — useful for triaging UI test failures
without round-tripping through downloaded artifacts. Cat it
into the workflow log on failure.

Also bump actions/upload-artifact v3 → v4. v3 uploads still
return success on this Gitea runner but the artifacts don't
surface through the API or UI; v4 is the correct version per
the workflow header note.
2026-05-08 21:41:38 +01:00

134 lines
4.9 KiB
YAML

# P5-06 — End-to-end test suite.
#
# Spec : docs/superpowers/specs/2026-05-07-p5-oss-readiness-design.md
# Stack: e2e/compose.e2e.yml (server + agent + rest-server + playwright)
# Tests: e2e/playwright/tests/*.spec.ts
#
# Triggered on every PR into main and on workflow_dispatch. Runs
# longer than the unit-test workflow (~3-4 minutes for a clean run);
# kept separate so a slow e2e doesn't block the fast lint/test loop.
#
# Networking note: every interaction with the server (health probe,
# Playwright) happens from a container on the compose `rmnet`
# network, addressing the server as `http://server:8080`. We can't
# rely on `127.0.0.1:8080` because Gitea's runner executes steps
# inside its own container, where compose's host port-publish is
# not visible.
name: e2e
on:
pull_request:
branches: [main]
workflow_dispatch:
# Force bash as the default shell — see ci.yml header.
defaults:
run:
shell: bash
jobs:
e2e:
name: Playwright vs docker-compose
runs-on: ubuntu-latest
container: gitea.dcglab.co.uk/steve/ci-runner-go:2026-05-08
timeout-minutes: 15
steps:
- uses: actions/checkout@v4
- name: Build the e2e stack
# --profile test pulls in the playwright service which is
# otherwise gated. --pull refreshes base images so a bump
# to the Dockerfile's FROM tag (e.g. mcr.microsoft.com/
# playwright:vX.Y.Z-jammy) isn't masked by a stale runner
# cache that still has the old tag's layers.
run: docker compose --profile test -f e2e/compose.e2e.yml build --pull
- name: Bring up the stack
run: docker compose -f e2e/compose.e2e.yml up -d server rest-server source-fixture
- name: Wait for server health
run: |
set -eu
for i in $(seq 1 30); do
if docker run --rm --network e2e_rmnet curlimages/curl:8.10.1 \
-fsS http://server:8080/api/version >/dev/null 2>&1; then
echo "server up"; exit 0
fi
sleep 2
done
echo "server didn't come up"; docker compose -f e2e/compose.e2e.yml logs server; exit 1
- name: Capture bootstrap token from server logs
id: bootstrap
run: |
set -eu
for i in $(seq 1 15); do
line=$(docker compose -f e2e/compose.e2e.yml logs server 2>&1 | grep -E 'bootstrap token' -A2 | grep -Eo '[a-zA-Z0-9_-]{40,}' | head -1 || true)
if [ -n "$line" ]; then
echo "RM_BOOTSTRAP_TOKEN=$line" >> "$GITHUB_ENV"
echo "got bootstrap token (${#line} chars)"
exit 0
fi
sleep 1
done
echo "bootstrap token not found in logs"
docker compose -f e2e/compose.e2e.yml logs server
exit 1
- name: Start the agent
run: docker compose -f e2e/compose.e2e.yml up -d agent
- name: Run Playwright tests
id: playwright
env:
RM_BOOTSTRAP_TOKEN: ${{ env.RM_BOOTSTRAP_TOKEN }}
# --name pins a stable container ID so the next step can
# docker cp out of it before tear-down. We deliberately
# drop --rm so the container survives the test exit; the
# tear-down step removes it.
run: docker compose -f e2e/compose.e2e.yml run --name e2e-pw playwright
- name: Extract Playwright report
if: always() && steps.playwright.outcome != 'skipped'
run: |
mkdir -p e2e/playwright/playwright-report e2e/playwright/test-results
docker cp e2e-pw:/work/playwright-report/. e2e/playwright/playwright-report/ || true
docker cp e2e-pw:/work/test-results/. e2e/playwright/test-results/ || true
- name: Show Playwright failure context (on failure)
if: failure()
run: |
set +e
shopt -s nullglob globstar
for f in e2e/playwright/test-results/**/error-context.md; do
echo "::group::$f"
cat "$f"
echo "::endgroup::"
done
echo "Failure attachments (download via the playwright-report artifact):"
find e2e/playwright/test-results \( -name '*.png' -o -name '*.webm' -o -name 'trace.zip' \) -printf ' %p\n' | sort
- name: Compose logs (on failure)
if: failure()
run: |
docker compose -f e2e/compose.e2e.yml logs --tail=200 server
docker compose -f e2e/compose.e2e.yml logs --tail=200 agent
docker compose -f e2e/compose.e2e.yml logs --tail=200 rest-server
- name: Upload Playwright report (on failure)
if: failure()
uses: actions/upload-artifact@v4
with:
name: playwright-report
path: |
e2e/playwright/playwright-report
e2e/playwright/test-results
retention-days: 7
- name: Tear down
if: always()
run: |
docker rm -f e2e-pw 2>/dev/null || true
docker compose -f e2e/compose.e2e.yml down -v