feat: Complete LLM agent framework with fog-of-war, meeting flow, and prompt assembly

- Core engine: simulator, game mechanics, triggers (138 tests)
- Fog-of-war per-player state tracking
- Meeting flow: interrupt, discussion, voting, consolidation
- Prompt assembler with strategy injection tiers
- LLM client with fallbacks for models without JSON/system support
- Prompt templates: action, discussion, voting, reflection
- Full integration in main.py orchestrator
- Verified working with free OpenRouter models (Gemma)

.gitignore

@@ -34,3 +34,16 @@ env/
 
 # Secrets
 .gitea_token
+
+# Project specific
+available_models.json
+fetch_models.py
+from_user/
+venv/
+
+# Generated Data & Scripts
+available_models.json
+fetch_models.py
+from_user/
+venv/
+