refactor(security,concurrency): resolve structural issues, enforce Claude permission skip, update docs

This commit is contained in:
2026-06-23 08:03:43 +09:00
parent 12dceb14b2
commit 99ac8b3ce4
7 changed files with 209 additions and 45 deletions
@@ -164,12 +164,10 @@ run_agent() {
# The user attaches with `tmux attach -t <session>` and types follow-up
# prompts themselves. We pre-load the first prompt via stdin and `read`
# keeps the pane open after the agent exits so the user can review.
case "$AGENT" in
claude-code) bin="claude";;
codex) bin="codex";;
human) echo "[human agent] complete the task, then run publish_event.py --event completed"; return;;
*) bin="$AGENT";;
esac
if [ "$AGENT" = "human" ]; then
echo "[human agent] complete the task, then run publish_event.py --event completed"
return
fi
if [[ "$DRY_RUN" == "1" ]]; then
echo "[dry-run] would launch agent '$AGENT' in a fresh tmux session with instructions:"
@@ -182,21 +180,17 @@ run_agent() {
echo " Install with: brew install tmux (or your package manager)" >&2
return 1
fi
if ! command -v "$bin" >/dev/null 2>&1; then
echo "ERROR: agent binary '$bin' not found in PATH." >&2
return 1
local _tmux="tmux"
if [ -n "${TMUX_SERVER_NAME:-}" ]; then
_tmux="tmux -L $TMUX_SERVER_NAME"
fi
local sess="${AGENT_SESSION#tmux:}"
# Detect a stale session with the same name (e.g. the user is still attached
# from an earlier run, or a previous wrapper died without cleanup). tmux
# new-session on an existing name fails silently; check first and fail loud.
if tmux has-session -t "$sess" 2>/dev/null; then
local attached
attached=$(tmux list-clients -t "$sess" 2>/dev/null | wc -l | tr -d ' ')
echo "ERROR: tmux session '$sess' already exists (clients attached: $attached)." >&2
echo " Pick a unique --agent-session (e.g. tmux:demo, tmux:claude-a) or" >&2
echo " kill the stale one first: tmux kill-session -t $sess" >&2
if ! $_tmux has-session -t "$sess" 2>/dev/null; then
echo "ERROR: 에이전트 세션 '$sess'이 존재하지 않습니다. 작업을 위임하기 전에 먼저 에이전트 세션을 기동해 주세요." >&2
echo " 팁: 'multi-agent-mux-resume' 또는 'multi-agent-mux-create'를 통해 에이전트를 먼저 생성할 수 있습니다." >&2
return 1
fi
@@ -206,9 +200,13 @@ run_agent() {
trap 'rc=$?; if [ $rc -ne 0 ]; then "$PY" "$pub_script" --job "$job_id" --event error --detail "agent bootstrap failed (exit $rc)"; fi' EXIT
fi
tmux new-session -d -s "$sess" -c "$WORKDIR" \
"printf '%s' \"$instructions\" | $bin --dangerously-skip-permissions; echo; echo '--- agent exited (job $job_id); press enter to close ---'; read"
echo "agent launched in tmux session: $sess (attach with: tmux attach -t $sess)"
echo "살아있는 에이전트 세션 '$sess'에 작업을 위임합니다..."
$_tmux set-buffer -b "job_buf_$job_id" "$instructions"
$_tmux paste-buffer -b "job_buf_$job_id" -t "$sess"
$_tmux send-keys -t "$sess" C-m
$_tmux delete-buffer -b "job_buf_$job_id"
echo "작업이 세션 '$sess'에 전송되었습니다. (연결하려면: $_tmux attach -t $sess)"
trap - EXIT
}
@@ -328,24 +328,24 @@ def update_job_status(job_id: str, registry_dir: str = DEFAULT_REGISTRY_DIR, **f
This is the single chokepoint for status writes (both ``registry.update_status``
and ``publish_event.py``'s status sync route through here), so it also mirrors
any ``status`` change into the persistent audit log — best-effort, after the
registry lock is released so a slow/failed log write never blocks the record."""
any ``status`` change into the persistent audit log. We perform the log mirror
under the lock to guarantee sequential consistency in audit history."""
with registry_lock(registry_dir):
record = load_job(job_id, registry_dir)
old_status = record.get("status")
record.update(fields)
record["updated_at"] = _utcnow()
_atomic_write_record(job_id, registry_dir, record)
if "status" in fields:
new_status = record.get("status")
update_logged_status(job_id, new_status, updated_at=record["updated_at"])
if old_status != new_status:
append_event(job_id, {
"event": "status_changed",
"from": old_status,
"to": new_status,
"timestamp": record["updated_at"],
})
if "status" in fields:
new_status = record.get("status")
update_logged_status(job_id, new_status, updated_at=record["updated_at"])
if old_status != new_status:
append_event(job_id, {
"event": "status_changed",
"from": old_status,
"to": new_status,
"timestamp": record["updated_at"],
})
return record
@@ -410,6 +410,21 @@ def _file_lock(fh):
fcntl.flock(fh.fileno(), fcntl.LOCK_UN)
def _redact_dict(d: Any) -> Any:
"""Recursively mask sensitive values (passwords, secrets, tokens) inside logs."""
if isinstance(d, dict):
redacted = {}
for k, v in d.items():
if any(s in k.lower() for s in ("password", "token", "secret", "auth_token", "key")):
redacted[k] = "[REDACTED]"
else:
redacted[k] = _redact_dict(v)
return redacted
elif isinstance(d, list):
return [_redact_dict(item) for item in d]
return d
def append_event(job_id: str, event_dict: Dict[str, Any], logs_dir: Optional[str] = None) -> None:
"""Append one event as a JSON line to ``<logs>/<job_id>/events.ndjson``.
@@ -418,7 +433,7 @@ def append_event(job_id: str, event_dict: Dict[str, Any], logs_dir: Optional[str
try:
path = job_log_path(job_id, EVENTS_FILENAME, logs_dir)
path.parent.mkdir(parents=True, exist_ok=True)
record = dict(event_dict)
record = _redact_dict(dict(event_dict))
record.setdefault("logged_at", _utcnow_precise())
line = json.dumps(record, ensure_ascii=False) + "\n"
with open(path, "a", encoding="utf-8") as fh:
@@ -453,8 +468,9 @@ def init_job_log(job_id: str, meta: Dict[str, Any], logs_dir: Optional[str] = No
try:
d = job_log_dir(job_id, logs_dir)
d.mkdir(parents=True, exist_ok=True)
meta_redacted = _redact_dict(meta)
with open(d / META_FILENAME, "w", encoding="utf-8") as fh:
json.dump(meta, fh, ensure_ascii=False, indent=2)
json.dump(meta_redacted, fh, ensure_ascii=False, indent=2)
fh.write("\n")
status = meta.get("status", "pending")
update_logged_status(