P2.2+P2.3: NATS offload node-worker + router offload integration

Node Worker (services/node-worker/):
- NATS subscriber for node.{NODE_ID}.llm.request / vision.request
- Canonical JobRequest/JobResponse envelope (Pydantic)
- Idempotency cache (TTL 10min) with inflight dedup
- Deadline enforcement (DEADLINE_EXCEEDED on expired jobs)
- Concurrency limiter (semaphore, returns busy)
- Ollama + Swapper vision providers

Router offload (services/router/offload_client.py):
- NATS req/reply with configurable retries
- Circuit breaker per node+type (3 fails/60s → open 120s)
- Concurrency semaphore for remote requests

Model selection (services/router/model_select.py):
- exclude_nodes parameter for circuit-broken nodes
- force_local flag for fallback re-selection
- Integrated circuit breaker state awareness

Router /infer pipeline:
- Remote offload path when NCS selects remote node
- Automatic fallback: exclude failed node → force_local re-select
- Deadline propagation from router to node-worker

Tests: 17 unit tests (idempotency, deadline, circuit breaker)
Docs: ops/offload_routing.md (subjects, envelope, verification)
Made-with: Cursor

services/node-worker/config.py

@@ -0,0 +1,12 @@
+"""Node-worker configuration from environment."""
+import os
+
+NODE_ID = os.getenv("NODE_ID", "noda2")
+NATS_URL = os.getenv("NATS_URL", "nats://dagi-nats:4222")
+OLLAMA_BASE_URL = os.getenv("OLLAMA_BASE_URL", "http://host.docker.internal:11434")
+SWAPPER_URL = os.getenv("SWAPPER_URL", "http://swapper-service:8890")
+DEFAULT_LLM = os.getenv("NODE_DEFAULT_LLM", "qwen3:14b")
+DEFAULT_VISION = os.getenv("NODE_DEFAULT_VISION", "llava:13b")
+MAX_CONCURRENCY = int(os.getenv("NODE_WORKER_MAX_CONCURRENCY", "2"))
+MAX_PAYLOAD_BYTES = int(os.getenv("NODE_WORKER_MAX_PAYLOAD_BYTES", str(1024 * 1024)))
+PORT = int(os.getenv("PORT", "8109"))