feat: Phase 3 - LLM mesh health integration, recommendations, and health commands

New files:
- mesh_reporter.py: MeshReporter class for prompt injection
  - build_tier1_summary(): ~500-800 token mesh health summary
  - build_region_detail(): Detailed region breakdown
  - build_node_detail(): Single node info with recommendations
  - build_recommendations(): Optimization suggestions
  - build_lora_compact(): Short format for LoRa messages
  - list_regions_compact(): Region list with scores

- commands/health.py: !health and !region commands
  - !health: Quick mesh summary (no LLM)
  - !region [name]: Region info or list all regions

Modified files:
- router.py: Mesh question detection and prompt injection
  - _is_mesh_question(): Keyword/phrase matching
  - _detect_mesh_scope(): Node/region/mesh scope detection
  - Inject Tier 1/2 data for mesh questions
  - Add mesh awareness instructions to LLM

- main.py: Create MeshReporter, pass to dispatcher/router

- commands/dispatcher.py: Register health/region commands

- mesh_health.py: Fix role type (int -> str)

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

meshai/mesh_health.py

@@ -279,7 +279,7 @@ class MeshHealthEngine:
             role = node.get("role") or node.get("hwModel") or ""
 
             # Determine if infrastructure
-            is_infra = role.upper() in INFRASTRUCTURE_ROLES
+            is_infra = str(role).upper() in INFRASTRUCTURE_ROLES
 
             # Get position (handle different API formats)
             lat = node.get("latitude") or node.get("lat")