fix(issue-6): fail-closed registry timeout and TUI turn handshake

- Introduce finalize_unfinished in multi-agent-mux-delegate-job for fail-closed atomic transitions
- Enforce CAS dispatch_token and attempt_id pinning across engine, CLI, and lifecycle scripts
- Integrate Herdr wait_for_agent_idle turn handshake to prevent prompt loss and race conditions
- Resolve bash 3.2 set -u empty array expansion compatibility in lib.sh
- Preserve Issue #5 R2 contract in CAS transition engine (engine.py, publish_event.py, service.py)
- Add comprehensive regression suites (test_issue6_fail_closed.py, test_issue6_turn_handshake.py)
- Bump lockstep framework and skills to v4.4.1 across lib.sh, eager.py, VERSIONS.md, 8 SKILL.md
- Synchronize documentation (IMPROVEMENTS.md, MESSAGING.md, state-transitions.md, task.md, phase5-e2e.md)
- Unanimous PASS achieved across 4 reviewer team leaders (Claude, Codex, OpenCode, Grok)

Closes #6

.agents/skills/lib_py/loop/watcher.py

@@ -59,10 +59,14 @@ class WaitOutcome(object):
 
 
 def build_argv(target: str, until: Sequence[str] = DEFAULT_UNTIL,
-               timeout_ms: Optional[int] = None) -> list:
+               timeout_ms: Optional[int] = None,
+               session: Optional[str] = None) -> list:
     if not target:
         raise ValueError("wait target is required")
-    argv = ["herdr", "agent", "wait", target]
+    if session and session != "default":
+        argv = ["herdr", "--session", session, "agent", "wait", target]
+    else:
+        argv = ["herdr", "agent", "wait", target]
     for state in until:
         if state not in VALID_STATES:
             raise ValueError("unsupported --until state: {!r}".format(state))
@@ -83,9 +87,10 @@ def _parse(stream: str) -> Optional[Dict[str, Any]]:
 
 
 def wait_once(target: str, until: Sequence[str] = DEFAULT_UNTIL,
-              timeout_ms: Optional[int] = None, run=subprocess.run) -> WaitOutcome:
+              timeout_ms: Optional[int] = None, session: Optional[str] = None,
+              run=subprocess.run) -> WaitOutcome:
     """One barrier call. `run` is injectable so tests never touch a real herdr."""
-    argv = build_argv(target, until, timeout_ms)
+    argv = build_argv(target, until, timeout_ms, session=session)
     try:
         proc = run(argv, capture_output=True, text=True)
     except Exception as exc:
@@ -164,3 +169,42 @@ class ReconnectBackoff(object):
             return [self.record_failure() for _ in range(n)]
         finally:
             self.current, self.consecutive_failures, self.cached_snapshot = saved
+
+
+def main(argv: Optional[Sequence[str]] = None) -> int:
+    import argparse
+    import os
+    import sys
+
+    parser = argparse.ArgumentParser(description="watcher CLI for herdr agent wait")
+    sub = parser.add_subparsers(dest="command", required=True)
+    p_wait = sub.add_parser("wait", help="wait for agent state")
+    p_wait.add_argument("target", help="target agent name")
+    p_wait.add_argument("--session", default=None, help="herdr session name")
+    p_wait.add_argument("--until", action="append", default=[], help="until state(s)")
+    p_wait.add_argument("--timeout-ms", type=int, default=None, help="timeout in ms")
+
+    args = parser.parse_args(argv)
+    session = args.session or os.environ.get("HERDR_SESSION_NAME") or None
+    until = args.until or DEFAULT_UNTIL
+    outcome = wait_once(args.target, until=until, timeout_ms=args.timeout_ms, session=session)
+    agent_st = None
+    if outcome.agent:
+        agent_st = outcome.agent.get("agent_status")
+    print(json.dumps({
+        "kind": outcome.kind,
+        "agent_status": agent_st,
+        "error_code": outcome.error_code,
+    }))
+    rc_map = {
+        MATCHED: 0,
+        TIMEOUT: 2,
+        AGENT_NOT_FOUND: 3,
+        TRANSPORT_ERROR: 4,
+    }
+    return rc_map.get(outcome.kind, 4)
+
+
+if __name__ == "__main__":
+    import sys
+    sys.exit(main())