Skip to content
Tests

feat(app): give first-run its own setup step instead of the settings page #2559

Sign in to view logs

feat(app): give first-run its own setup step instead of the settings page

feat(app): give first-run its own setup step instead of the settings page #2559

Workflow file for this run

.github/workflows/test.yml at faf71c1
name: Tests
# A discover job computes which suites a change touches (via Turbo) and runs
# only those, so unaffected suites are never spun up. Suites map from affected
# packages in packages/browseros-agent/ci/affected-suites.ts; a gate job rolls
# up pass/skip and the summary job posts the sticky per-suite table.
on:
pull_request:
types:
- opened
- synchronize
- reopened
- ready_for_review
paths:
- .github/workflows/test.yml
- .github/workflows/build-browseros.yml
- .github/workflows/nightly*.yml
- .github/workflows/publish-server-ota.yml
- .github/workflows/release-*.yml
- packages/browseros-agent/**
workflow_dispatch:
permissions:
contents: read
env:
BROWSEROS_APPIMAGE_URL: https://files.browseros.com/download/BrowserOS.AppImage
concurrency:
group: tests-${{ github.event.pull_request.number || github.ref }}
cancel-in-progress: true
jobs:
discover:
name: Tests / discover
runs-on: ubuntu-latest
defaults:
run:
working-directory: packages/browseros-agent
outputs:
matrix: ${{ steps.affected.outputs.matrix }}
has_any: ${{ steps.affected.outputs.has_any }}
all_suites: ${{ steps.affected.outputs.all_suites }}
steps:
- name: Checkout code
uses: actions/checkout@v7
with:
# Full history so Turbo's --affected has the merge base; a shallow
# checkout would silently mark every package changed.
fetch-depth: 0
- name: Setup Bun
uses: oven-sh/setup-bun@v2
with:
bun-version-file: packages/browseros-agent/package.json
- name: Install dependencies
run: bun ci
- name: Compute affected suites
id: affected
env:
BROWSEROS_AFFECTED_BASE: ${{ github.event.pull_request.base.sha }}
TURBO_SCM_BASE: ${{ github.event.pull_request.base.sha }}
run: bun run ci/affected-suites.ts
test:
name: Tests / ${{ matrix.suite }}
needs: discover
if: needs.discover.outputs.has_any == 'true'
runs-on: ubuntu-latest
timeout-minutes: ${{ matrix.needs_rust && 45 || 20 }}
defaults:
run:
working-directory: packages/browseros-agent
strategy:
fail-fast: false
matrix: ${{ fromJSON(needs.discover.outputs.matrix) }}
steps:
- name: Checkout code
uses: actions/checkout@v7
- name: Setup Bun
uses: oven-sh/setup-bun@v2
with:
bun-version-file: packages/browseros-agent/package.json
- name: Setup Rust
if: matrix.needs_rust == true
# Pinned so the clippy lint set is deterministic and matches local dev;
# a floating `stable` silently changes which lints fire across runs.
uses: dtolnay/rust-toolchain@1.95.0
with:
components: clippy,rustfmt
- name: Cache Rust build
if: matrix.needs_rust == true
uses: Swatinem/rust-cache@v2
with:
workspaces: packages/browseros-agent
# Without this the key embeds GITHUB_JOB, so the warm cache produced
# on main by a differently named job could never be restored here.
shared-key: browseros-agent
# rust-cache hashes every toolchain `rustup toolchain list` reports,
# not just the pinned one, and the runner image ships its own Rust
# alongside it. That set changes as images roll out, so the key
# fragmented across runners and a warm cache was a coin flip. The
# lockfile hash still keys the cache, so dependency changes bust it;
# cargo fingerprints by rustc version itself, so a toolchain change
# rebuilds rather than reusing the wrong artifacts.
add-rust-environment-hash-key: false
# Intermediate artifacts live outside the checkout so worktrees can
# share them, and rust-cache only saves workspace target dirs plus the
# registry and git caches by default. Name the build dir explicitly or
# every run would recompile the dependency graph from scratch.
cache-directories: ~/.cargo/build/browseros
- name: Install dependencies
run: bun ci
- name: Resolve BrowserOS cache key
if: matrix.needs_browser == true
id: browseros-cache-key
run: |
set -euo pipefail
headers="$(curl -fsSI "$BROWSEROS_APPIMAGE_URL")"
etag="$(printf '%s\n' "$headers" | awk 'BEGIN{IGNORECASE=1} /^etag:/ {sub(/\r$/, "", $2); gsub(/"/, "", $2); print $2; exit}')"
last_modified="$(printf '%s\n' "$headers" | awk 'BEGIN{IGNORECASE=1} /^last-modified:/ {$1=""; sub(/^ /, ""); sub(/\r$/, ""); print; exit}')"
raw_key="${etag:-$last_modified}"
if [ -z "$raw_key" ]; then
raw_key="$BROWSEROS_APPIMAGE_URL"
fi
cache_key="$(printf '%s' "$raw_key" | shasum -a 256 | awk '{print $1}')"
echo "key=browseros-appimage-${{ runner.os }}-$cache_key" >> "$GITHUB_OUTPUT"
- name: Restore BrowserOS cache
if: matrix.needs_browser == true
id: browseros-cache
uses: actions/cache@v6.1.0
with:
path: packages/browseros-agent/.ci/bin/BrowserOS.AppImage
key: ${{ steps.browseros-cache-key.outputs.key }}
- name: Download BrowserOS
if: matrix.needs_browser == true && steps.browseros-cache.outputs.cache-hit != 'true'
run: |
mkdir -p .ci/bin
curl -fsSL "$BROWSEROS_APPIMAGE_URL" -o .ci/bin/BrowserOS.AppImage
chmod +x .ci/bin/BrowserOS.AppImage
- name: Prepare BrowserOS wrapper
if: matrix.needs_browser == true
run: |
mkdir -p .ci/bin
cat > .ci/bin/browseros <<'EOF'
#!/usr/bin/env bash
set -euo pipefail
export APPIMAGE_EXTRACT_AND_RUN=1
# Chromium's hidden-window APIs require a real X11 platform.
if [ "${BROWSEROS_TEST_HEADLESS:-true}" = "false" ]; then
export XDG_SESSION_TYPE=x11
exec xvfb-run --auto-servernum "$(dirname "$0")/BrowserOS.AppImage" "$@"
fi
exec "$(dirname "$0")/BrowserOS.AppImage" "$@"
EOF
chmod +x .ci/bin/browseros
- name: Create dev env file
working-directory: packages/browseros-agent
run: cp .env.development.example .env.development
- name: Run ${{ matrix.suite }} tests
id: test
env:
BROWSEROS_BINARY: ${{ github.workspace }}/packages/browseros-agent/.ci/bin/browseros
BROWSEROS_TEST_HEADLESS: ${{ matrix.suite == 'claw-mcp' && 'false' || 'true' }}
BROWSEROS_TEST_EXTRA_ARGS: --no-sandbox --disable-dev-shm-usage
BROWSEROS_JUNIT_PATH: ${{ github.workspace }}/packages/browseros-agent/${{ matrix.junit_path }}
run: |
set +e
mkdir -p test-results
# Bun's TS-file parser has occasional races on Linux when many test
# workers parse the same source concurrently, surfacing as
# `SyntaxError: Export named 'X' not found in module ...` on files
# whose source clearly exports X. It is not reproducible locally
# and clears on rerun. Retry once on failure so a single flake does
# not block PRs; a second consecutive failure still fails the job.
attempt=0
max_attempts=2
exit_code=1
while [ "$attempt" -lt "$max_attempts" ]; do
attempt=$((attempt + 1))
if [ "$attempt" -gt 1 ]; then
echo "::warning::${{ matrix.suite }} attempt $attempt (previous exit $exit_code)"
# Fresh junit slot per attempt so stale output does not mask the retry.
rm -f "${{ matrix.junit_path }}"
fi
${{ matrix.command }}
exit_code=$?
if [ "$exit_code" = "0" ]; then break; fi
done
if [ ! -f "${{ matrix.junit_path }}" ]; then
if [ "$exit_code" = "0" ]; then
cat > "${{ matrix.junit_path }}" <<EOF
<?xml version="1.0" encoding="UTF-8"?>
<testsuites tests="0" failures="0">
<testsuite name="${{ matrix.suite }}" tests="0" failures="0">
</testsuite>
</testsuites>
EOF
else
cat > "${{ matrix.junit_path }}" <<EOF
<?xml version="1.0" encoding="UTF-8"?>
<testsuites tests="1" failures="1">
<testsuite name="${{ matrix.suite }}" tests="1" failures="1">
<testcase classname="workflow" name="${{ matrix.suite }} setup">
<failure message="Test run failed before JUnit output was written">See workflow logs for details.</failure>
</testcase>
</testsuite>
</testsuites>
EOF
fi
fi
echo "exit_code=$exit_code" >> "$GITHUB_OUTPUT"
- name: Upload JUnit XML
if: always()
uses: actions/upload-artifact@v7
with:
name: junit-${{ matrix.suite }}
path: packages/browseros-agent/${{ matrix.junit_path }}
- name: Summarize suite result
if: always()
run: |
if [ "${{ steps.test.outputs.exit_code }}" = "0" ]; then
echo "### :white_check_mark: ${{ matrix.suite }} suite passed" >> "$GITHUB_STEP_SUMMARY"
else
{
echo "### :x: ${{ matrix.suite }} suite failed (exit code ${{ steps.test.outputs.exit_code }})"
echo ""
echo "See the uploaded \`junit-${{ matrix.suite }}\` artifact for details."
} >> "$GITHUB_STEP_SUMMARY"
exit 1
fi
gate:
name: Tests / gate
needs: [discover, test]
if: always()
runs-on: ubuntu-latest
steps:
- name: Require every suite to pass or be skipped
run: |
echo 'needs = ${{ toJSON(needs) }}'
jq -e 'to_entries | all(.value.result == "success" or .value.result == "skipped")' <<< '${{ toJSON(needs) }}'
comment:
name: Tests / summary
needs: [discover, test]
if: >-
always()
&& github.event_name == 'pull_request'
&& github.event.pull_request.head.repo.full_name == github.repository
runs-on: ubuntu-latest
permissions:
pull-requests: write
actions: read
steps:
- name: Download JUnit artifacts
uses: actions/download-artifact@v4
continue-on-error: true
with:
path: junit
pattern: junit-*
- name: Build comment body
env:
ALL_SUITES: ${{ needs.discover.outputs.all_suites }}
run: |
python3 <<'PY'
import glob, json, os, xml.etree.ElementTree as ET
run_url = f"{os.environ['GITHUB_SERVER_URL']}/{os.environ['GITHUB_REPOSITORY']}/actions/runs/{os.environ['GITHUB_RUN_ID']}"
marker = "<!-- browseros-agent-tests-summary -->"
all_suites = json.loads(os.environ.get("ALL_SUITES") or "[]")
ran = {}
failed_cases = []
for xml_path in sorted(glob.glob("junit/junit-*/*.xml")):
suite_name = os.path.basename(os.path.dirname(xml_path)).removeprefix("junit-")
try:
root = ET.parse(xml_path).getroot()
except ET.ParseError:
ran[suite_name] = (0, 1, 0, 1)
failed_cases.append((suite_name, "(could not parse junit XML)"))
continue
testsuites = root.findall("testsuite") if root.tag == "testsuites" else [root]
s_tests = s_fail = s_err = s_skip = 0
for ts in testsuites:
s_tests += int(ts.get("tests") or 0)
s_fail += int(ts.get("failures") or 0)
s_err += int(ts.get("errors") or 0)
s_skip += int(ts.get("skipped") or 0)
for tc in ts.iter("testcase"):
if tc.find("failure") is not None or tc.find("error") is not None:
cls = tc.get("classname") or ""
name = tc.get("name") or "(unnamed)"
failed_cases.append((suite_name, f"{cls} > {name}" if cls else name))
s_failed = s_fail + s_err
s_passed = max(s_tests - s_failed - s_skip, 0)
ran[suite_name] = (s_passed, s_failed, s_skip, s_tests)
total_passed = sum(v[0] for v in ran.values())
total_failed = sum(v[1] for v in ran.values())
total_tests = sum(v[3] for v in ran.values())
order = all_suites or sorted(ran)
n_total = len(order)
n_ran = len(ran)
n_skipped = max(n_total - n_ran, 0)
if total_failed:
header = f"## :x: Tests failed: {total_failed}/{total_tests} failed"
elif n_ran == 0:
header = "## :white_check_mark: No suites affected by this change"
else:
header = f"## :white_check_mark: Tests passed: {total_passed}/{total_tests}"
lines = [marker, header, "",
f"Ran {n_ran} of {n_total} suites ({n_skipped} not affected by this change).", ""]
lines.append("| Suite | Passed | Failed | Skipped |")
lines.append("|-------|--------|--------|---------|")
gate_suites = []
for name in order:
if name in ran:
passed, failed, skipped, total = ran[name]
if failed > 0:
icon, passed_cell = ":x:", f"{passed}/{total}"
elif total == 0:
icon, passed_cell = ":white_check_mark:", "passed"
gate_suites.append(name)
else:
icon, passed_cell = ":white_check_mark:", f"{passed}/{total}"
lines.append(f"| {icon} `{name}` | {passed_cell} | {failed} | {skipped} |")
else:
lines.append(f"| :fast_forward: `{name}` | n/a | n/a | not affected |")
if gate_suites:
lines += ["", "> `passed` = ran successfully but emits no JUnit counts (a lint/format gate)."]
if failed_cases:
lines += ["", "<details open>", "<summary><b>Failed tests</b></summary>", ""]
for suite_name, label in failed_cases[:50]:
lines.append(f"- **{suite_name}** `{label}`")
if len(failed_cases) > 50:
lines.append(f"- ...and {len(failed_cases) - 50} more")
lines += ["", "</details>"]
lines += ["", f"[View workflow run]({run_url})"]
with open("comment.md", "w") as fp:
fp.write("\n".join(lines) + "\n")
PY
- name: Upsert sticky PR comment
uses: actions/github-script@v9
with:
script: |
const fs = require('fs');
const body = fs.readFileSync('comment.md', 'utf8');
const marker = '<!-- browseros-agent-tests-summary -->';
const { owner, repo } = context.repo;
const issue_number = context.payload.pull_request.number;
const triggerSha = context.payload.pull_request.head.sha;
const { data: pr } = await github.rest.pulls.get({ owner, repo, pull_number: issue_number });
if (pr.head.sha !== triggerSha) {
core.info(`PR head has moved (${pr.head.sha} vs ${triggerSha}), skipping stale comment.`);
return;
}
const comments = await github.paginate(github.rest.issues.listComments, {
owner, repo, issue_number, per_page: 100,
});
const existing = comments.find(c => c.body && c.body.includes(marker));
if (existing) {
await github.rest.issues.updateComment({ owner, repo, comment_id: existing.id, body });
} else {
await github.rest.issues.createComment({ owner, repo, issue_number, body });
}