docs: fix garbled text, sync architecture with code, add tool limits API

docs/en/api.md

@@ -27,6 +27,8 @@ class PacketType(Enum):
     GET_STATUS = "get_status"            # Get status
     GET_CONFIG = "get_config"            # Get config
     SET_CONFIG = "set_config"            # Set config
+    GET_TOOL_LIMITS = "get_tool_limits"   # Get tool limits
+    SET_TOOL_LIMITS = "set_tool_limits"   # Set tool limits
     GET_HISTORY = "get_history"           # Get history
     SAVE_HISTORY = "save_history"         # Save history
     SHUTDOWN = "shutdown"                 # Shutdown service
@@ -199,7 +201,71 @@ body = {
 
 ---
 
-### 6. GET_HISTORY - Get Message History
+### 6. GET_TOOL_LIMITS - Get Tool Limits
+
+Get current AI reasoning tool call limits.
+
+**Request Parameters:**
+```python
+body = {}  # No parameters
+```
+
+**Response Data:**
+```python
+{
+    "persona_query_max": int,   # Persona graph query limit
+    "persona_update_max": int,  # Persona graph update limit
+    "task_query_max": int,       # Working memory query limit
+    "task_update_max": int,     # Working memory update limit
+    "memory_query_max": int,      # General memory query limit
+    "memory_update_max": int    # General memory update limit
+}
+```
+
+**Example:**
+```python
+result = client.get_tool_limits()
+print(result["data"]["persona_query_max"])  # 1
+```
+
+---
+
+### 7. SET_TOOL_LIMITS - Set Tool Limits
+
+Set AI reasoning tool call limits.
+
+**Request Parameters:**
+```python
+body = {
+    "persona_query_max": int,   # Persona query limit (≥1)
+    "persona_update_max": int,  # Persona update limit (≥1)
+    "task_query_max": int,       # Working memory query limit (≥1)
+    "task_update_max": int,      # Working memory update limit (≥1)
+    "memory_query_max": int,     # General memory query limit (≥1)
+    "memory_update_max": int     # General memory update limit (≥1)
+}
+```
+
+**Response Data:**
+```python
+{
+    "status": "tool_limits_updated",
+    "limits": {...}  # Updated limits
+}
+```
+
+**Example:**
+```python
+result = client.update_tool_limits(
+    persona_query_max=2,
+    task_query_max=5,
+    memory_query_max=30
+)
+```
+
+---
+
+### 8. GET_HISTORY - Get Message History
 
 Get saved message history.
 

docs/en/architecture.md

@@ -22,16 +22,15 @@ TrulyMEM-TrueHumanMEM/
 │   ├── tool_executor.py # Tool executor
 │   ├── tool_limiter.py # Tool call limiter
 │   ├── tools/          # Tool definitions
-│   │   ├── __init__.py
 │   │   └── memory_tools.py
 │   └── prompts/        # Prompt management
 ├── ui/                 # TUI display layer (display only, no AI logic)
-│   ├── __init__.py     # Export GraphMemoryApp, AppConfig
+│   ├── __init__.py     # Export GraphMemoryApp
 │   ├── app.py          # GraphMemoryApp (communicates via BackendClient)
 │   ├── widgets/        # TUI components
-│   ├── handlers/       # Event handlers
 │   ├── models/         # Data models
 │   ├── services/       # Service layer (config only)
+│   ├── handlers/      # Event handlers
 │   └── styles/         # Style files
 └── tests/              # Tests (42 tests)
 ```

docs/zh/api.md

@@ -27,6 +27,8 @@ class PacketType(Enum):
     GET_STATUS = "get_status"            # 获取状态
     GET_CONFIG = "get_config"            # 获取配置
     SET_CONFIG = "set_config"            # 设置配置
+    GET_TOOL_LIMITS = "get_tool_limits"   # 获取工具限制
+    SET_TOOL_LIMITS = "set_tool_limits"   # 设置工具限制
     GET_HISTORY = "get_history"           # 获取历史
     SAVE_HISTORY = "save_history"         # 保存历史
     SHUTDOWN = "shutdown"                 # 关闭服务
@@ -214,7 +216,71 @@ result = client.update_config(
 
 ---
 
-### 6. GET_HISTORY - 获取消息历史
+### 6. GET_TOOL_LIMITS - 获取工具限制
+
+获取当前 AI 推理时的工具调用限制配置。
+
+**请求参数：**
+```python
+body = {}  # 无参数
+```
+
+**响应数据：**
+```python
+{
+    "persona_query_max": int,   # 人设图查询上限
+    "persona_update_max": int,  # 人设图修改上限
+    "task_query_max": int,       # 工作记忆查询上限
+    "task_update_max": int,      # 工作记忆修改上限
+    "memory_query_max": int,     # 一般记忆查询上限
+    "memory_update_max": int    # 一般记忆修改上限
+}
+```
+
+**示例：**
+```python
+result = client.get_tool_limits()
+print(result["data"]["persona_query_max"])  # 1
+```
+
+---
+
+### 7. SET_TOOL_LIMITS - 设置工具限制
+
+设置 AI 推理时的工具调用限制。
+
+**请求参数：**
+```python
+body = {
+    "persona_query_max": int,   # 人设图查询上限 (≥1)
+    "persona_update_max": int,  # 人设图修改上限 (≥1)
+    "task_query_max": int,       # 工作记忆查询上限 (≥1)
+    "task_update_max": int,     # 工作记忆修改上限 (≥1)
+    "memory_query_max": int,    # 一般记忆查询上限 (≥1)
+    "memory_update_max": int     # 一般记忆修改上限 (≥1)
+}
+```
+
+**响应数据：**
+```python
+{
+    "status": "tool_limits_updated",
+    "limits": {...}  # 更新后的限制
+}
+```
+
+**示例：**
+```python
+result = client.update_tool_limits(
+    persona_query_max=2,
+    task_query_max=5,
+    memory_query_max=30
+)
+```
+
+---
+
+### 8. GET_HISTORY - 获取消息历史
 
 获取保存的消息历史。
 

docs/zh/architecture.md

@@ -22,16 +22,15 @@ TrulyMEM-TrueHumanMEM/
 │   ├── tool_executor.py # 工具执行器
 │   ├── tool_limiter.py # 工具调用限制器
 │   ├── tools/          # 工具定义
-│   │   ├── __init__.py
 │   │   └── memory_tools.py
 │   └── prompts/        # 提示词管理
 ├── ui/                 # TUI 显示层（仅显示，无 AI 逻辑）
-│   ├── __init__.py     # 导出 GraphMemoryApp, AppConfig
+│   ├── __init__.py     # 导出 GraphMemoryApp
 │   ├── app.py          # GraphMemoryApp (通过 BackendClient 通信)
 │   ├── widgets/        # TUI 组件
-│   ├── handlers/       # 事件处理
 │   ├── models/         # 数据模型
 │   ├── services/       # 服务层（仅配置管理）
+│   ├── handlers/      # 事件处理
 │   └── styles/         # 样式文件
 └── tests/              # 测试 (42 tests)
 ```

docs/zh/memory.md

@@ -133,7 +133,7 @@ task_create(
 
 ---
 
-## 必须查<EFBFBD><EFBFBD><EFBFBD>工作记忆链的场景
+## 必须查询工作记忆链的场景
 
 ### 强制查询场景