Implement phases 3-4 + all modules: decision engine, automapper, character creator, quest system, progression optimizer, and hybrid LLM integration

- Phase 4 (Decision Engine): ActionQueue with 7 priority tiers,
  4 behavior states (Idle/Explore/Combat/Loot), CombatAI with skill
  rotation and flee logic, GoalManager with survival override,
  DecisionEngine state machine integrated into the main game loop

- Phase 3 (Automapper): Complete hybrid SQLite/Memvid architecture
  with WorldMapper orchestrator, room fingerprinting (SHA-256),
  bidirectional exit linking, exploration queue, A* pathfinding,
  HistoricalStorage with JSON fallback, SemanticSearch with keyword
  fallback, SyncManager with configurable triggers

- Character Creator: State machine for automated character creation
  with stat rolling/optimization per class weights, race/class/gender
  selection, reroll logic with configurable thresholds

- Quest System: Quest lifecycle tracking (discover->accept->complete),
  NLP-based objective extraction (kill/fetch/talk/explore), EXP/time
  prioritization, pending kill target tracking

- Progression Optimizer: Grinding spot finder (EXP/hour), equipment
  comparison by weighted stats, skill rotation optimizer (DPS vs
  mana efficiency), session summary statistics

- LLM Integration (hybrid): Async Ollama client with retry/backoff,
  LLMBrain coordinator for quest parsing, social AI, decision advice,
  and ambiguous text parsing fallback. SocialAI for detecting and
  responding to player messages (say/tell/shout/group/trade).
  Graceful degradation when Ollama is unavailable.

All 214 tests passing.

src/config/settings.py

@@ -24,12 +24,29 @@ class CharacterConfig(BaseModel):
     play_style: str = "balanced"
 
 
-class AIConfig(BaseModel):
-    """AI engine configuration"""
-    engine: str = "rule_based"
-    llm_model: str = "llama3.2"
-    decision_delay_ms: List[int] = Field(default=[200, 2000])
-    exploration_strategy: str = "depth_first"
+class LLMProviderConfig(BaseModel):
+    """LLM provider configuration (Ollama / OpenAI-compatible)"""
+    enabled: bool = True
+    base_url: str = "http://localhost:11434"
+    model: str = "llama3.2"
+    temperature: float = 0.3
+    max_tokens: int = 512
+    timeout_seconds: float = 30.0
+    max_retries: int = 2
+    system_prompt: str = (
+        "You are an AI playing a text-based MUD game. "
+        "You must respond ONLY with the requested format. "
+        "Be concise and precise. No explanations unless asked."
+    )
+
+
+class AIConfig(BaseModel):
+    """AI engine configuration"""
+    engine: str = "hybrid"
+    llm_model: str = "llama3.2"
+    decision_delay_ms: List[int] = Field(default=[200, 2000])
+    exploration_strategy: str = "depth_first"
+    llm: LLMProviderConfig = Field(default_factory=LLMProviderConfig)
 
 
 class MapperConfig(BaseModel):