feat(production): sync all modified production files to git

Includes updates across gateway, router, node-worker, memory-service,
aurora-service, swapper, sofiia-console UI and node2 infrastructure:

- gateway-bot: Dockerfile, http_api.py, druid/aistalk prompts, doc_service
- services/router: main.py, router-config.yml, fabric_metrics, memory_retrieval,
  offload_client, prompt_builder
- services/node-worker: worker.py, main.py, config.py, fabric_metrics
- services/memory-service: Dockerfile, database.py, main.py, requirements
- services/aurora-service: main.py (+399), kling.py, quality_report.py
- services/swapper-service: main.py, swapper_config_node2.yaml
- services/sofiia-console: static/index.html (console UI update)
- config: agent_registry, crewai_agents/teams, router_agents
- ops/fabric_preflight.sh: updated preflight checks
- router-config.yml, docker-compose.node2.yml: infra updates
- docs: NODA1-AGENT-ARCHITECTURE, fabric_contract updated

Made-with: Cursor

services/router/offload_client.py

@@ -81,7 +81,7 @@ def get_unavailable_nodes(req_type: str) -> Set[str]:
 async def offload_infer(
     nats_client,
     node_id: str,
-    required_type: Literal["llm", "vision", "stt", "tts", "ocr", "image"],
+    required_type: str,  # "llm"|"vision"|"stt"|"tts"|"ocr"|"image"|"voice.tts"|"voice.llm"|"voice.stt"
     job_payload: Dict[str, Any],
     timeout_ms: int = 25000,
 ) -> Optional[Dict[str, Any]]:
@@ -89,6 +89,8 @@ async def offload_infer(
 
     Returns parsed JobResponse dict or None on total failure.
     Retries on transient errors (timeout, busy). Does NOT retry on provider errors.
+
+    Voice HA subjects use dotted notation: "voice.tts" → node.{id}.voice.tts.request
     """
     subject = f"node.{node_id.lower()}.{required_type}.request"
     payload_bytes = json.dumps(job_payload).encode()