Files
gstack/bin/gstack-session-update
T
Garry TanandClaude Fable 5 b7d44c45b4 fix: pre-landing review round — 8 auto-fixes + 8 accepted findings hardened
The ship review army (4 specialists + red-team + checklist, 29 findings)
produced 8 mechanical auto-fixes and 11 decisions; the accepted set:

- win32 slug parity completed: lib/bin-context.ts gains the remote-first
  outermost walk + degraded-cache self-heal the bash side got this wave —
  the two implementations now agree on the stray-marker live-bug shape,
  pinned by shared fixtures (multi-specialist 9/10 finding).
- probe honors the plan's bounded-read decision: 256KB prefix, extraction
  semantics mirrored from parseTranscriptJsonl so probe/prepare can never
  diverge on the same file (>1MB transcript test).
- policy normalize parity: bash normalize() now matches canonicalizeRemote
  on .git/-trailing and uppercase-.GIT shapes (7-shape corpus pinned two
  ways) — a deny for those shapes could previously slip the transcript gate.
- session-update reclaim is TOCTOU-safe (atomic mv-aside on both branches).
- settings-hook: unparseable settings.json errors instead of being replaced
  with {}; ensure-event keys on (event, source) so matcher changes update
  in place — never zero or two registrations.
- dot-only slug guard at both parse sites (hostile 'url = ..' can't escape
  projects/); enqueue tmp-file janitor (1h TTL, inside the drain lock);
  brain-sync .migrating never clobbered; drop-queue/status count .migrating;
  snapshot -o warning correct + surfaced in diff mode; version-bump test
  order-dependence removed; uninstall clears the advance stamp.

Deferred with record: slug heal-probe cost sentinel (P3 TODO), FF_OK
conflation (noted, misdiagnosis-only).

270 pass / 0 fail across the 10 touched suites.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-08-17 13:20:20 -07:00

196 lines
8.8 KiB
Bash
Executable File

#!/usr/bin/env bash
# gstack-session-update — auto-update gstack on session start (team mode)
#
# Called by Claude Code SessionStart hook. Must be fast, silent, non-fatal.
# The entire update runs in background (forked). The hook itself exits
# immediately so session startup is never delayed.
#
# Exit 0 always — errors must never block a Claude Code session.
set +e
GSTACK_DIR="${GSTACK_DIR:-$HOME/.claude/skills/gstack}"
STATE_DIR="${GSTACK_STATE_DIR:-$HOME/.gstack}"
# Egress receipt helpers (_receipted_git): fail-open — an update pull must
# never block a session over a receipt hiccup.
. "$(cd "$(dirname "$0")" && pwd)/gstack-egress-lib.sh"
THROTTLE_FILE="$STATE_DIR/.last-session-update"
LOCK_DIR="$STATE_DIR/.setup-lock"
LOG_FILE="$STATE_DIR/analytics/session-update.log"
THROTTLE_SECONDS=3600 # 1 hour
log_entry() {
mkdir -p "$(dirname "$LOG_FILE")"
echo "$(date -u +%Y-%m-%dT%H:%M:%SZ) $1" >> "$LOG_FILE" 2>/dev/null || true
}
# ── Guard: gstack must be a git repo ──
if [ ! -d "$GSTACK_DIR/.git" ]; then
exit 0
fi
# ── Guard: team mode must be enabled ──
AUTO=$("$GSTACK_DIR/bin/gstack-config" get auto_upgrade 2>/dev/null || true)
if [ "$AUTO" != "true" ]; then
exit 0
fi
# ── Throttle: skip if checked recently ──
if [ -f "$THROTTLE_FILE" ]; then
LAST=$(cat "$THROTTLE_FILE" 2>/dev/null || echo 0)
NOW=$(date +%s)
ELAPSED=$(( NOW - LAST ))
if [ "$ELAPSED" -lt "$THROTTLE_SECONDS" ]; then
exit 0
fi
fi
# ── Fork to background: zero latency on session start ──
(
# Prevent git from prompting for credentials (would hang the background process)
export GIT_TERMINAL_PROMPT=0
mkdir -p "$STATE_DIR"
# ── Acquire lockfile (skip if another session is running setup) ──
#
# Staleness has two independent detectors (#2613):
# 1. PID liveness — the pidfile records the HOLDER subshell's PID and a
# dead PID means reclaim. ($BASHPID, never $$: $$ expands to the PARENT
# hook's PID even inside this backgrounded subshell, and the parent
# exits immediately — so every later session judged the lock stale and
# rm -rf'd a LIVE holder's lock, letting concurrent updaters in.)
# 2. Hard TTL on the heartbeat mtime — reclaim regardless of kill -0, so a
# recycled PID or a hung holder can't wedge the lock forever. The
# holder touches the pidfile at step boundaries (after the pull, after
# setup), so a legitimately-slow run keeps itself alive. The TTL also
# bounds the missing/empty-pidfile states: inside the window they mean
# "just acquired, between mkdir and echo" and are respected.
LOCK_TTL_MINUTES=30
lock_is_expired() {
_hb="$LOCK_DIR/pid"
[ -f "$_hb" ] || _hb="$LOCK_DIR"
[ -n "$(find "$_hb" -maxdepth 0 -mmin +$LOCK_TTL_MINUTES 2>/dev/null)" ]
}
# Reclaim is TOCTOU-safe via atomic mv-aside: `rm -rf` then `mkdir` lets TWO
# contenders both judge the lock stale, both remove it, and both win the
# mkdir (one rm can land between the other's rm and mkdir). `mv` of the lock
# dir is atomic — exactly one contender's mv succeeds; the loser's mv fails
# (ENOENT) and it backs off. The winner reaps the moved-aside dir at leisure.
if ! mkdir "$LOCK_DIR" 2>/dev/null; then
if lock_is_expired; then
mv "$LOCK_DIR" "$LOCK_DIR.reap.$$" 2>/dev/null || { log_entry "SKIP lock_contested"; exit 0; }
rm -rf "$LOCK_DIR.reap.$$" 2>/dev/null
mkdir "$LOCK_DIR" 2>/dev/null || { log_entry "SKIP lock_contested"; exit 0; }
log_entry "RECLAIMED lock_ttl_expired"
elif [ -f "$LOCK_DIR/pid" ]; then
LOCK_PID=$(cat "$LOCK_DIR/pid" 2>/dev/null || echo 0)
if [ "$LOCK_PID" -gt 0 ] 2>/dev/null && ! kill -0 "$LOCK_PID" 2>/dev/null; then
# Stale lock — mv aside atomically (see reclaim note above), re-acquire
mv "$LOCK_DIR" "$LOCK_DIR.reap.$$" 2>/dev/null || { log_entry "SKIP lock_contested"; exit 0; }
rm -rf "$LOCK_DIR.reap.$$" 2>/dev/null
mkdir "$LOCK_DIR" 2>/dev/null || { log_entry "SKIP lock_contested"; exit 0; }
else
# Live holder — or an empty/non-numeric pidfile inside the TTL
# window (the -gt test fails on garbage, landing here by design).
log_entry "SKIP locked_by=$LOCK_PID"
exit 0
fi
else
# Missing pidfile inside the TTL window: just-acquired (mkdir→echo race).
log_entry "SKIP locked_no_pid"
exit 0
fi
fi
# Write the HOLDER's PID for stale lock detection (see #2613 note above;
# macOS ships bash 3.2 with no BASHPID — the sh child's $PPID IS this
# subshell, so the fallback is exact there).
echo "${BASHPID:-$(sh -c 'echo $PPID')}" > "$LOCK_DIR/pid" 2>/dev/null
# Clean up lock on exit
trap 'rm -rf "$LOCK_DIR" 2>/dev/null' EXIT
# ── Pull latest ──
OLD_HEAD=$(git -C "$GSTACK_DIR" rev-parse HEAD 2>/dev/null)
UPDATE_URL=$(git -C "$GSTACK_DIR" remote get-url origin 2>/dev/null || echo "")
UPDATE_HOST="${UPDATE_URL#*://}"; UPDATE_HOST="${UPDATE_HOST#*@}"; UPDATE_HOST="${UPDATE_HOST%%[/:]*}"
# --autostash: locally-patched TRACKED files are the NORM on installs, not
# the exception — skill-prefix mode rewrites frontmatter names and
# `gstack-config gbrain-refresh` renders brain blocks into SKILL.md. A bare
# --ff-only refuses over those edits, so auto-upgrade wedged permanently
# (observed: 308 consecutive PULL_FAILED with the reason discarded, #2566).
# Capture stderr: the log must carry WHY a pull failed, never just the code.
PULL_ERR_FILE=$(mktemp "${TMPDIR:-/tmp}/gstack-session-pull-XXXXXX" 2>/dev/null || echo "")
GSTACK_HOME="$STATE_DIR" _receipted_git open session-update "${UPDATE_HOST:-unknown}" gstack-self-update-pull "auto_upgrade=true" \
bash -c 'git -C "$1" pull --ff-only --autostash -q 2>"${2:-/dev/null}"' _ "$GSTACK_DIR" "$PULL_ERR_FILE"
PULL_EXIT=$?
NEW_HEAD=$(git -C "$GSTACK_DIR" rev-parse HEAD 2>/dev/null)
# Heartbeat: pull done — keep the TTL clock fresh for the setup step.
touch "$LOCK_DIR/pid" 2>/dev/null
# Record check time regardless of outcome
date +%s > "$THROTTLE_FILE" 2>/dev/null
if [ "$PULL_EXIT" -ne 0 ]; then
PULL_REASON=$(head -c 300 "$PULL_ERR_FILE" 2>/dev/null | tr '\n' ' ' | tr -s ' ')
log_entry "PULL_FAILED exit=$PULL_EXIT reason=${PULL_REASON:-unknown}"
# Autostash pop conflict leaves the stash behind and the tree half-merged.
# The local patches are REGENERABLE (prefix renames, gbrain blocks), so
# recover to a clean upstream tree and re-render them below rather than
# leaving conflict markers in a live install.
if grep -qi "autostash" "$PULL_ERR_FILE" 2>/dev/null; then
git -C "$GSTACK_DIR" checkout -q -- . 2>/dev/null
git -C "$GSTACK_DIR" stash drop -q 2>/dev/null
log_entry "AUTOSTASH_CONFLICT_RECOVERED tree_reset=1"
_PREFIX_CFG=$("$GSTACK_DIR/bin/gstack-config" get skill_prefix 2>/dev/null || echo false)
"$GSTACK_DIR/bin/gstack-patch-names" "$GSTACK_DIR" "$_PREFIX_CFG" >/dev/null 2>&1 || true
"$GSTACK_DIR/bin/gstack-config" gbrain-refresh >/dev/null 2>&1 || true
fi
rm -f "$PULL_ERR_FILE" 2>/dev/null
exit 0
fi
rm -f "$PULL_ERR_FILE" 2>/dev/null
# Re-render local patches over the fresh tree (both tools are idempotent
# no-ops when the feature is unconfigured); the autostash pop usually
# preserves them, but a clean re-render costs nothing and self-heals.
_PREFIX_CFG=$("$GSTACK_DIR/bin/gstack-config" get skill_prefix 2>/dev/null || echo false)
"$GSTACK_DIR/bin/gstack-patch-names" "$GSTACK_DIR" "$_PREFIX_CFG" >/dev/null 2>&1 || true
"$GSTACK_DIR/bin/gstack-config" gbrain-refresh >/dev/null 2>&1 || true
# ── If HEAD moved, run setup -q ──
if [ "$OLD_HEAD" != "$NEW_HEAD" ]; then
log_entry "UPDATING old=$OLD_HEAD new=$NEW_HEAD"
# bun must be available for setup
if command -v bun >/dev/null 2>&1; then
( cd "$GSTACK_DIR" && ./setup -q ) >/dev/null 2>&1 || {
log_entry "SETUP_FAILED"
}
# Heartbeat: setup done (either way) — refresh the TTL clock.
touch "$LOCK_DIR/pid" 2>/dev/null
else
log_entry "SETUP_SKIPPED bun_missing"
fi
# Write marker so next skill preamble shows "just upgraded"
OLD_VER=$(git -C "$GSTACK_DIR" show "$OLD_HEAD:VERSION" 2>/dev/null || echo "unknown")
echo "$OLD_VER" > "$STATE_DIR/just-upgraded-from" 2>/dev/null
rm -f "$STATE_DIR/last-update-check" 2>/dev/null
rm -f "$STATE_DIR/update-snoozed" 2>/dev/null
log_entry "UPDATED from=$OLD_VER to=$(cat "$GSTACK_DIR/VERSION" 2>/dev/null || echo unknown)"
else
log_entry "UP_TO_DATE head=$OLD_HEAD"
fi
# The detached subshell must own its stdio: it inherits the session hook's
# pipes, and once the hook exits and the caller closes them, any child that
# writes (git pull's autostash notice, setup output) dies of SIGPIPE —
# observed as PULL_FAILED exit=141 with an empty stderr capture. All
# observability goes through LOG_FILE.
) >/dev/null 2>&1 &
exit 0