feat: Implement enhanced action economy for LLM agent orchestration (#156)

- Add action economy system with free (LOOK, SPEAK) vs turn-ending (GO, WAIT, TAKE) actions
- Implement LOOK action with detailed descriptions for doors, objects, entities, directions
- Add SPEAK/ANNOUNCE speech system with room-wide and proximity-based message delivery
- Create multi-tile pathing with FOV interrupt detection (path cancels when new entity visible)
- Implement TAKE action with adjacency requirement and clear error messages
- Add conversation history and error feedback loop so agents learn from failed actions
- Create structured simulation logging for offline viewer replay
- Document offline viewer requirements in OFFLINE_VIEWER_SPEC.md
- Fix import path in 1_multi_agent_demo.py for standalone execution

🤖 Generated with [Claude Code](https://claude.com/claude-code)

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

tests/vllm_demo/1_multi_agent_demo.py

@@ -14,12 +14,15 @@ Three agents:
 Each agent gets their own screenshot and VLLM query.
 """
 
+import sys
+import os
+# Add the vllm_demo directory to path for imports
+sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
+
 import mcrfpy
 from mcrfpy import automation
-import sys
 import requests
 import base64
-import os
 import random
 
 from action_parser import parse_action