P3.1: GPU/Queue-aware routing — NCS metrics + scoring-based model selection

NCS (services/node-capabilities/metrics.py):
- NodeLoad: inflight_jobs, queue_depth, concurrency_limit, estimated_wait_ms,
  cpu_load_1m, mem_pressure (macOS + Linux), rtt_ms_to_hub
- RuntimeLoad: per-runtime healthy, p50_ms, p95_ms from rolling 50-sample window
- POST /capabilities/report_latency for node-worker → NCS reporting
- NCS fetches worker metrics via NODE_WORKER_URL

Node Worker:
- GET /metrics endpoint (inflight, concurrency, latency buffers)
- Latency tracking per job type (llm/vision) with rolling buffer
- Fire-and-forget latency reporting to NCS after each successful job

Router (model_select v3):
- score_candidate(): wait + model_latency + cross_node_penalty + prefer_bonus
- LOCAL_THRESHOLD_MS=250: prefer local if within threshold of remote
- ModelSelection.score field for observability
- Structured [score] logs with chosen node, model, and score breakdown

Tests: 19 new (12 scoring + 7 NCS metrics), 36 total pass
Docs: ops/runbook_p3_1.md, ops/CHANGELOG_FABRIC.md

No breaking changes to JobRequest/JobResponse or capabilities schema.

Made-with: Cursor

services/node-worker/main.py

@@ -26,6 +26,11 @@ async def healthz():
     }
 
 
+@app.get("/metrics")
+async def metrics():
+    return worker.get_metrics()
+
+
 @app.on_event("startup")
 async def startup():
     global _nats_client