feat(messaging): implement Track 0 fault tolerance (B-14, B-15) and add 10 regression guards (G-1 to G-10)

.agents/skills/multi-agent-mux-delegate-job/scripts/publish_event.py

@@ -192,15 +192,19 @@ def main(argv=None) -> int:
         attempts=args.attempts,
         exceptions=(OSError, TimeoutError, ConnectionError, ValueError),
     )
+    publish_ok = True
+    publish_error: Optional[str] = None
     try:
         publish(config, topic, body, retain)
     except Exception as exc:
+        publish_ok = False
+        publish_error = str(exc)
         logger.error("publish failed after %d attempts: %s", args.attempts, exc)
-        return 2
 
-    # Persistent audit log: record the exact payload we put on the wire so the
-    # publish is reproducible from the log alone. Best-effort (isolated inside
-    # append_event) — never fails the publish.
+    # Persistent audit log: record the exact payload we put on the wire (or intended to).
+    # Best-effort (isolated inside append_event) — never fails the publish.
+    # Policy Note: Seq consumption on failure is intentionally maintained for monotonic replay
+    # defense (> highest accepted seq), with failure documented explicitly in the audit record.
     mqtt_common.append_event(job_id, {
         "event": "published",
         "source_event": args.event,
@@ -210,6 +214,8 @@ def main(argv=None) -> int:
         "timestamp": payload["timestamp"],
         "detail": args.detail,
         "payload": payload,
+        "published": publish_ok,
+        "publish_error": publish_error,
     })
 
     # Best-effort side effects: registry status sync + (debug) event log. Never
@@ -222,6 +228,9 @@ def main(argv=None) -> int:
         except Exception as exc:  # pragma: no cover - best effort
             logger.warning("status sync failed: %s", exc)
 
+    if not publish_ok:
+        return 2
+
     logger.info("published %s seq=%d job=%s retain=%s", args.event, seq, job_id, retain)
     return 0