feat(engine): 实现行动点系统

- 扩展 AgentState 添加 action_points, max_action_points, last_action_tick 字段
- 新增 ActionFeedback 模型用于返回行动执行结果
- 创建 action_points.py 模块实现行动点消耗与恢复逻辑
- 行动消耗表: vote=1, trigger_skill=2, influence=2, comment/support/chaos=0
- 每 tick 恢复 1 点行动点（不超过 max）
- 行动点不足时拒绝执行并返回失败反馈
- 新增 7 个测试用例，全部 37 个测试通过

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

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

engine-python/app/state.py

@@ -20,6 +20,9 @@ def get_default_state() -> WorldState:
                 memory=[],
                 stance=Stance(optimism=0.6, fear=0.4),
                 faction="neutral",
+                action_points=3,
+                max_action_points=3,
+                last_action_tick=0,
             ),
             "bob": AgentState(
                 emotion="calm",
@@ -27,6 +30,9 @@ def get_default_state() -> WorldState:
                 memory=[],
                 stance=Stance(optimism=0.4, fear=0.6),
                 faction="neutral",
+                action_points=3,
+                max_action_points=3,
+                last_action_tick=0,
             ),
         },
         events=[],