mirror of
https://github.com/garrytan/gstack.git
synced 2026-09-12 07:59:02 +02:00
fix(setup): Chromium bootstrap is best-effort and bounded — skills always register (#1900, #1901, #1902, #913, #2233)
setup runs under `set -e`, and the Chromium bootstrap in section 2 sat ahead of skill registration in section 4 with a bare `bunx playwright install chromium`, an unbounded download, and an explicit `exit 1` after the post-install launch probe. On an offline, proxied, or AppArmor-restricted box the user ended with ZERO skills registered and a re-run that died at the same line; a wedged download hung setup indefinitely. Every browser failure now records a reason code in _PW_FAIL_REASON and setup continues: skipped (GSTACK_SKIP_PLAYWRIGHT=1, #913), chromium-install, chromium-install-timeout (the download is bounded by the existing _wait_with_deadline helper, default 600s, env GSTACK_PLAYWRIGHT_INSTALL_TIMEOUT, process tree killed via _kill_tree), chromium-install-locked (another setup holds the lock: this one registers skills and re-probes next time instead of exiting), windows-no-node, windows-node-modules, post-install-launch (with the GSTACK_CHROMIUM_NO_SANDBOX=1 hint for Ubuntu 24.04's userns policy, #2157). The daemon font refresh is skipped when Chromium is unavailable. The final summary names the skills that need the browser (/qa, /qa-only, /design-review, /browse, make-pdf, /pair-agent) and the fix for the recorded reason, and logs the reason code (never a path) through gstack-telemetry-log when telemetry is on. Tests: static invariants over the anchor-sliced block (no exit, every reason code, deadline helper, trap chaining, guarded refresh, summary contents) plus an integration harness that executes the real block with a stubbed probe and installer: install failure, hang killed at the deadline with the tree kill recorded, non-numeric knob fallback, live lock (continues, installer not run, lock preserved), stale lock reclaimed, post-install probe failure, and the skip flag. Credit @DavidMiserak (PR #1900) for the best-effort shape; re-implemented on the current block. Co-Authored-By: Claude Fable 5.1 <noreply@anthropic.com>
This commit is contained in:
Garry Tan
co-authored by
Claude Fable 5.1
Claude Fable 5.1
parent
584c2a44fb
commit
550352c1b7
@@ -776,7 +776,33 @@ if [ -f /etc/os-release ]; then
|
||||
fi
|
||||
fi
|
||||
|
||||
if ! ensure_playwright_browser; then
|
||||
# Chromium is BEST-EFFORT (#1900, #1901, #1902, #913, #2233). Every later step
|
||||
# — skill registration (# 4), Codex/Kiro installs, migrations, hooks — is
|
||||
# independent of the browser, so a failed or wedged download must never abort
|
||||
# setup under `set -e`. Each failure records a reason code in _PW_FAIL_REASON;
|
||||
# the skills that need Chromium (/qa, /qa-only, /design-review, /browse,
|
||||
# make-pdf, /pair-agent) are named in the final summary instead of the user
|
||||
# discovering a half-installed gstack. Lock contention is a reason too: another
|
||||
# setup is installing Chromium right now, so this run registers skills and
|
||||
# re-probes next time. The download is bounded (default 600s, env
|
||||
# GSTACK_PLAYWRIGHT_INSTALL_TIMEOUT) because Playwright's own retries cover a
|
||||
# flaky socket but not a wedged bunx; the killed tree is the whole process
|
||||
# group via _kill_tree. Reason codes: skipped, chromium-install,
|
||||
# chromium-install-timeout, chromium-install-locked, windows-no-node,
|
||||
# windows-node-modules, post-install-launch.
|
||||
# test/setup-playwright-best-effort.test.ts pins this block.
|
||||
_PW_FAIL_REASON=""
|
||||
_pw_fail() {
|
||||
local code="$1"; shift
|
||||
_PW_FAIL_REASON="${_PW_FAIL_REASON:+$_PW_FAIL_REASON,}$code"
|
||||
echo " Chromium bootstrap: $code — $*" >&2
|
||||
}
|
||||
_PW_INSTALL_TIMEOUT="${GSTACK_PLAYWRIGHT_INSTALL_TIMEOUT:-600}"
|
||||
case "$_PW_INSTALL_TIMEOUT" in ''|*[!0-9]*) _PW_INSTALL_TIMEOUT=600 ;; esac
|
||||
|
||||
if [ "${GSTACK_SKIP_PLAYWRIGHT:-0}" = "1" ]; then
|
||||
_pw_fail skipped "GSTACK_SKIP_PLAYWRIGHT=1 — Chromium install skipped by request (#913)"
|
||||
elif ! ensure_playwright_browser; then
|
||||
echo "Installing Playwright Chromium..."
|
||||
# XProtect self-heal (#2554): the probe failure may be the OS killing the
|
||||
# cached Chromium, not a missing install. Clear quarantine on the Playwright
|
||||
@@ -806,48 +832,50 @@ if ! ensure_playwright_browser; then
|
||||
else
|
||||
bunx playwright install chromium
|
||||
fi
|
||||
)
|
||||
) &
|
||||
_PW_RC=0
|
||||
_wait_with_deadline $! "$_PW_INSTALL_TIMEOUT" || _PW_RC=$?
|
||||
if [ "$_PW_RC" -eq 124 ]; then
|
||||
_pw_fail chromium-install-timeout "bunx playwright install chromium exceeded ${_PW_INSTALL_TIMEOUT}s and was killed (raise with GSTACK_PLAYWRIGHT_INSTALL_TIMEOUT=<seconds>)"
|
||||
elif [ "$_PW_RC" -ne 0 ]; then
|
||||
_pw_fail chromium-install "bunx playwright install chromium exited $_PW_RC (offline, proxy, or blocked download?)"
|
||||
fi
|
||||
rm -rf "$_PW_LOCK" 2>/dev/null || true
|
||||
# Restore the original handler (never `trap - EXIT`, which would clear
|
||||
# cleanup_copied_bun for the rest of the script).
|
||||
trap cleanup_copied_bun EXIT
|
||||
else
|
||||
echo " another gstack setup is already installing Chromium (lock: $_PW_LOCK)." >&2
|
||||
echo " Wait for it to finish, then re-run ./setup. If no other setup is running," >&2
|
||||
echo " remove the stale lock: rm -rf \"$_PW_LOCK\"" >&2
|
||||
exit 1
|
||||
_pw_fail chromium-install-locked "another gstack setup is installing Chromium (lock: $_PW_LOCK) — re-run ./setup after it finishes, or remove a stale lock: rm -rf \"$_PW_LOCK\""
|
||||
fi
|
||||
|
||||
if [ "$IS_WINDOWS" -eq 1 ]; then
|
||||
if [ -z "$_PW_FAIL_REASON" ] && [ "$IS_WINDOWS" -eq 1 ]; then
|
||||
# On Windows, Node.js launches Chromium (not Bun — see oven-sh/bun#4253).
|
||||
# Ensure playwright is importable by Node from the gstack directory.
|
||||
if ! command -v node >/dev/null 2>&1; then
|
||||
echo "gstack setup failed: Node.js is required on Windows (Bun cannot launch Chromium due to a pipe bug)" >&2
|
||||
echo " Install Node.js: https://nodejs.org/" >&2
|
||||
exit 1
|
||||
_pw_fail windows-no-node "Node.js is required on Windows to launch Chromium (Bun cannot: oven-sh/bun#4253) — install from https://nodejs.org/ and re-run ./setup"
|
||||
else
|
||||
echo "Windows detected — verifying Node.js can load Playwright..."
|
||||
if ! (
|
||||
cd "$SOURCE_GSTACK_DIR"
|
||||
# Bun's node_modules already has playwright; verify Node can require it
|
||||
node -e "require('playwright')" 2>/dev/null || npm install --no-save playwright
|
||||
# @ngrok/ngrok is externalized in server-node.mjs and resolved at runtime.
|
||||
# Verify the platform-specific native binary is installed so /pair-agent
|
||||
# tunnels don't fail later with a cryptic module-not-found error.
|
||||
node -e "require('@ngrok/ngrok')" 2>/dev/null || npm install --no-save @ngrok/ngrok
|
||||
); then
|
||||
_pw_fail windows-node-modules "npm could not install playwright / @ngrok/ngrok for Node.js"
|
||||
fi
|
||||
fi
|
||||
echo "Windows detected — verifying Node.js can load Playwright..."
|
||||
(
|
||||
cd "$SOURCE_GSTACK_DIR"
|
||||
# Bun's node_modules already has playwright; verify Node can require it
|
||||
node -e "require('playwright')" 2>/dev/null || npm install --no-save playwright
|
||||
# @ngrok/ngrok is externalized in server-node.mjs and resolved at runtime.
|
||||
# Verify the platform-specific native binary is installed so /pair-agent
|
||||
# tunnels don't fail later with a cryptic module-not-found error.
|
||||
node -e "require('@ngrok/ngrok')" 2>/dev/null || npm install --no-save @ngrok/ngrok
|
||||
)
|
||||
fi
|
||||
fi
|
||||
|
||||
if ! ensure_playwright_browser; then
|
||||
if [ -z "$_PW_FAIL_REASON" ] && ! ensure_playwright_browser; then
|
||||
if [ "$IS_WINDOWS" -eq 1 ]; then
|
||||
echo "gstack setup failed: Playwright Chromium could not be launched via Node.js" >&2
|
||||
echo " This is a known issue with Bun on Windows (oven-sh/bun#4253)." >&2
|
||||
echo " Ensure Node.js is installed and 'node -e \"require('playwright')\"' works." >&2
|
||||
_pw_fail post-install-launch "Playwright Chromium could not be launched via Node.js (oven-sh/bun#4253) — ensure 'node -e \"require('playwright')\"' works, then re-run ./setup"
|
||||
else
|
||||
echo "gstack setup failed: Playwright Chromium could not be launched" >&2
|
||||
_pw_fail post-install-launch "Playwright Chromium installed but could not be launched — on Ubuntu 24.04+ (AppArmor blocks unprivileged user namespaces) try GSTACK_CHROMIUM_NO_SANDBOX=1 (#2157)"
|
||||
fi
|
||||
exit 1
|
||||
fi
|
||||
|
||||
# 2b. Ensure a color-emoji font is installed so make-pdf emoji render (Linux).
|
||||
@@ -859,7 +887,9 @@ if ! ensure_emoji_font; then
|
||||
echo " Fedora: sudo dnf install google-noto-color-emoji-fonts" >&2
|
||||
echo " Arch: sudo pacman -S noto-fonts-emoji" >&2
|
||||
echo " Alpine: sudo apk add font-noto-emoji" >&2
|
||||
else
|
||||
elif [ -z "$_PW_FAIL_REASON" ]; then
|
||||
# Only when Chromium is actually usable — restarting a daemon that cannot
|
||||
# launch its browser just produces a second failure line.
|
||||
refresh_browse_daemon_for_fonts
|
||||
fi
|
||||
|
||||
@@ -2597,3 +2627,23 @@ if ! grep -q '^redact_prepush_hook:' "$_GSTACK_CFG_FILE" 2>/dev/null; then
|
||||
log " installs the hook automatically in every repo you ship from."
|
||||
fi
|
||||
fi
|
||||
|
||||
# ─── Chromium bootstrap summary (best-effort browser, see # 2) ───────────────
|
||||
# Printed LAST so it is the thing the user sees, after every skill registered.
|
||||
if [ -n "${_PW_FAIL_REASON:-}" ]; then
|
||||
log ""
|
||||
log "Browser unavailable: Chromium bootstrap did not complete ($_PW_FAIL_REASON)."
|
||||
log " Skills that need it: /qa, /qa-only, /design-review, /browse, make-pdf, /pair-agent."
|
||||
log " Everything else is installed and works. Fix the cause and re-run ./setup."
|
||||
case "$_PW_FAIL_REASON" in
|
||||
*chromium-install-timeout*) log " Slow link? Raise the bound: GSTACK_PLAYWRIGHT_INSTALL_TIMEOUT=1800 ./setup" ;;
|
||||
esac
|
||||
case "$_PW_FAIL_REASON" in
|
||||
*post-install-launch*) log " Ubuntu 24.04+ (AppArmor user namespaces): GSTACK_CHROMIUM_NO_SANDBOX=1 ./setup (#2157)" ;;
|
||||
esac
|
||||
# Reason code only — never a path or command line — so a support thread can
|
||||
# be matched to a code. Telemetry-gated inside gstack-telemetry-log.
|
||||
if [ -x "$SOURCE_GSTACK_DIR/bin/gstack-telemetry-log" ]; then
|
||||
"$SOURCE_GSTACK_DIR/bin/gstack-telemetry-log" --event-type onboarding --skill _setup_playwright --outcome "$_PW_FAIL_REASON" >/dev/null 2>&1 || true
|
||||
fi
|
||||
fi
|
||||
|
||||
Reference in New Issue
Block a user