diff --git a/frontend/src/content/en/application/agents-and-threads.mdx b/frontend/src/content/en/application/agents-and-threads.mdx
index a6be84331..21f71f0c4 100644
--- a/frontend/src/content/en/application/agents-and-threads.mdx
+++ b/frontend/src/content/en/application/agents-and-threads.mdx
@@ -106,10 +106,10 @@ checkpointer:
 ```
 
 <Callout type="info">
-  The LangGraph Server manages its own state separately. The
-  <code>checkpointer</code> setting in <code>config.yaml</code> applies to the
-  embedded <code>DeerFlowClient</code> (used in direct Python integrations), not
-  to the LangGraph Server deployment used by DeerFlow App.
+  DeerFlow App uses the <code>checkpointer</code> setting in <code>config.yaml</code> to
+  persist thread state through the Gateway runtime (via <code>make_checkpointer()</code> in
+  <code>deerflow.agents.checkpointer.async_provider</code>). Configure this section if you
+  want threads to survive process restarts.
 </Callout>
 
 ### Thread data storage
diff --git a/frontend/src/content/en/reference/api-gateway-reference.mdx b/frontend/src/content/en/reference/api-gateway-reference.mdx
index 39e068700..32fb1fdd9 100644
--- a/frontend/src/content/en/reference/api-gateway-reference.mdx
+++ b/frontend/src/content/en/reference/api-gateway-reference.mdx
@@ -44,9 +44,17 @@ http://localhost:2026/api
 |---|---|---|
 | `GET` | `/api/threads` | List threads |
 | `DELETE` | `/api/threads/{thread_id}` | Delete a thread |
-| `GET` | `/api/memory` | Get global memory |
-| `GET` | `/api/memory/{agent_name}` | Get agent-specific memory |
-| `DELETE` | `/api/memory` | Clear global memory |
+| `GET` | `/api/memory` | Get global memory data (context + facts) |
+| `DELETE` | `/api/memory` | Clear all memory data |
+| `POST` | `/api/memory/reload` | Reload memory from storage file |
+| `GET` | `/api/memory/facts` | (included in `/api/memory` response `facts` array) |
+| `POST` | `/api/memory/facts` | Create a memory fact |
+| `PATCH` | `/api/memory/facts/{fact_id}` | Update a memory fact |
+| `DELETE` | `/api/memory/facts/{fact_id}` | Delete a memory fact |
+| `GET` | `/api/memory/export` | Export memory data as JSON |
+| `POST` | `/api/memory/import` | Import and overwrite memory data |
+| `GET` | `/api/memory/config` | Get memory configuration |
+| `GET` | `/api/memory/status` | Get memory config + data in one request |
 
 ### Extensions
 
diff --git a/frontend/src/content/en/reference/configuration-reference.mdx b/frontend/src/content/en/reference/configuration-reference.mdx
index 3d67e063d..f6e6b1d26 100644
--- a/frontend/src/content/en/reference/configuration-reference.mdx
+++ b/frontend/src/content/en/reference/configuration-reference.mdx
@@ -44,8 +44,11 @@ models:
     base_url: null                   # Optional: custom endpoint URL
     request_timeout: 600.0          # Request timeout in seconds
     max_retries: 2                   # Number of retries on failure
-    supports_vision: true            # Whether to enable vision capabilities
-    thinking_enabled: false          # Whether to enable extended thinking
+    supports_vision: true            # Whether the model accepts image inputs
+    supports_thinking: false         # Whether the model supports extended thinking
+    # thinking: {}                   # Optional thinking config (passed when thinking is active)
+    # when_thinking_enabled: {}      # Optional overrides applied when thinking is enabled
+    # when_thinking_disabled: {}     # Optional overrides applied when thinking is disabled
     # Any additional fields are passed through to the model constructor
 ```
 
diff --git a/frontend/src/content/en/reference/runtime-flags-and-modes.mdx b/frontend/src/content/en/reference/runtime-flags-and-modes.mdx
index b189bc96d..19fdb96db 100644
--- a/frontend/src/content/en/reference/runtime-flags-and-modes.mdx
+++ b/frontend/src/content/en/reference/runtime-flags-and-modes.mdx
@@ -33,4 +33,4 @@ Set in the model configuration in `config.yaml`:
 | Flag | Type | Description |
 |---|---|---|
 | `supports_vision` | `bool` | Model accepts image inputs |
-| `thinking_enabled` | `bool` | Model supports extended thinking mode |
+| `supports_thinking` | `bool` | Model supports extended thinking mode |
diff --git a/frontend/src/content/en/reference/source-map.mdx b/frontend/src/content/en/reference/source-map.mdx
index 9db8942d8..fa53d299a 100644
--- a/frontend/src/content/en/reference/source-map.mdx
+++ b/frontend/src/content/en/reference/source-map.mdx
@@ -14,7 +14,7 @@ backend/
 │       │   ├── memory.py     # Memory read/clear
 │       │   ├── threads.py    # Thread management
 │       │   └── uploads.py    # File uploads
-│       └── main.py           # FastAPI app entry point
+│       └── app.py            # FastAPI app entry point (create_app())
 │
 └── packages/harness/deerflow/
     ├── agents/
@@ -85,4 +85,4 @@ frontend/src/
 | Skill loading (hot reload) | `skills/loader.py` |
 | MCP tool cache | `mcp/cache.py` |
 | File upload handling | `uploads/manager.py` |
-| Gateway main router | `app/gateway/main.py` |
+| Gateway app factory | `app/gateway/app.py` |
diff --git a/frontend/src/content/zh/application/configuration.mdx b/frontend/src/content/zh/application/configuration.mdx
index 011171f3a..f9ba38fe7 100644
--- a/frontend/src/content/zh/application/configuration.mdx
+++ b/frontend/src/content/zh/application/configuration.mdx
@@ -23,19 +23,13 @@ models:
     request_timeout: 600.0
     max_retries: 2
     supports_vision: true
-    thinking_enabled: false
-```
-  </Tabs.Tab>
-  <Tabs.Tab>
-```yaml
-models:
-  - name: claude-sonnet
+    supports_thinking: false
     use: langchain_anthropic:ChatAnthropic
     model: claude-sonnet-4-5
     api_key: $ANTHROPIC_API_KEY
     max_tokens: 16000
     supports_vision: true
-    thinking_enabled: false
+    supports_thinking: false
 ```
 
 启用扩展思考：
@@ -46,11 +40,10 @@ models:
     model: claude-sonnet-4-5
     api_key: $ANTHROPIC_API_KEY
     max_tokens: 16000
-    thinking_enabled: true
-    extra_body:
-      thinking:
-        type: enabled
-        budget_tokens: 10000
+    supports_thinking: true
+    thinking:
+      type: enabled
+      budget_tokens: 10000
 ```
   </Tabs.Tab>
   <Tabs.Tab>
@@ -63,7 +56,7 @@ models:
     request_timeout: 600.0
     max_retries: 2
     supports_vision: true
-    thinking_enabled: false
+    supports_thinking: false
 ```
   </Tabs.Tab>
   <Tabs.Tab>
@@ -77,7 +70,7 @@ models:
     request_timeout: 600.0
     max_retries: 2
     supports_vision: false
-    thinking_enabled: true
+    supports_thinking: true
 ```
   </Tabs.Tab>
   <Tabs.Tab>
@@ -90,7 +83,7 @@ models:
     request_timeout: 600.0
     max_retries: 2
     supports_vision: false
-    thinking_enabled: false
+    supports_thinking: false
 ```
 
 确保 Ollama 已运行并已拉取所需模型：
diff --git a/frontend/src/content/zh/reference/api-gateway-reference.mdx b/frontend/src/content/zh/reference/api-gateway-reference.mdx
index 8d819b1d8..0739cab35 100644
--- a/frontend/src/content/zh/reference/api-gateway-reference.mdx
+++ b/frontend/src/content/zh/reference/api-gateway-reference.mdx
@@ -44,9 +44,16 @@ http://localhost:2026/api
 |---|---|---|
 | `GET` | `/api/threads` | 列出线程 |
 | `DELETE` | `/api/threads/{thread_id}` | 删除线程 |
-| `GET` | `/api/memory` | 获取全局记忆 |
-| `GET` | `/api/memory/{agent_name}` | 获取 Agent 特定记忆 |
-| `DELETE` | `/api/memory` | 清除全局记忆 |
+| `GET` | `/api/memory` | 获取全局记忆数据（上下文 + 事实） |
+| `DELETE` | `/api/memory` | 清除所有记忆数据 |
+| `POST` | `/api/memory/reload` | 从存储文件重新加载记忆 |
+| `POST` | `/api/memory/facts` | 创建一条记忆事实 |
+| `PATCH` | `/api/memory/facts/{fact_id}` | 更新一条记忆事实 |
+| `DELETE` | `/api/memory/facts/{fact_id}` | 删除一条记忆事实 |
+| `GET` | `/api/memory/export` | 导出记忆数据为 JSON |
+| `POST` | `/api/memory/import` | 导入并覆盖记忆数据 |
+| `GET` | `/api/memory/config` | 获取记忆配置 |
+| `GET` | `/api/memory/status` | 一次性获取记忆配置和数据 |
 
 ### 扩展
 
diff --git a/frontend/src/content/zh/reference/configuration-reference.mdx b/frontend/src/content/zh/reference/configuration-reference.mdx
index 0fb2acb23..ef3ff6a5b 100644
--- a/frontend/src/content/zh/reference/configuration-reference.mdx
+++ b/frontend/src/content/zh/reference/configuration-reference.mdx
@@ -44,8 +44,11 @@ models:
     base_url: null                  # 可选：自定义端点
     request_timeout: 600.0         # 请求超时（秒）
     max_retries: 2                  # 重试次数
-    supports_vision: true           # 是否启用视觉功能
-    thinking_enabled: false         # 是否启用扩展思考
+    supports_vision: true           # 模型是否接受图像输入
+    supports_thinking: false        # 模型是否支持扩展思考
+    # thinking: {}                  # 可选思考配置（思考激活时传入）
+    # when_thinking_enabled: {}     # 思考启用时的可选覆盖设置
+    # when_thinking_disabled: {}    # 思考禁用时的可选覆盖设置
     # 任何其他字段都会传递给模型构造函数
 ```
 
diff --git a/frontend/src/content/zh/reference/runtime-flags-and-modes.mdx b/frontend/src/content/zh/reference/runtime-flags-and-modes.mdx
index e6eae11fe..643c82493 100644
--- a/frontend/src/content/zh/reference/runtime-flags-and-modes.mdx
+++ b/frontend/src/content/zh/reference/runtime-flags-and-modes.mdx
@@ -33,4 +33,4 @@
 | 标志 | 类型 | 描述 |
 |---|---|---|
 | `supports_vision` | `bool` | 模型接受图像输入 |
-| `thinking_enabled` | `bool` | 模型支持扩展思考模式 |
+| `supports_thinking` | `bool` | 模型支持扩展思考模式 |
diff --git a/frontend/src/content/zh/reference/source-map.mdx b/frontend/src/content/zh/reference/source-map.mdx
index 0d5711def..a18ccd6f9 100644
--- a/frontend/src/content/zh/reference/source-map.mdx
+++ b/frontend/src/content/zh/reference/source-map.mdx
@@ -14,7 +14,7 @@ backend/
 │       │   ├── memory.py     # 记忆读取/清除
 │       │   ├── threads.py    # 线程管理
 │       │   └── uploads.py    # 文件上传
-│       └── main.py           # FastAPI 应用入口
+│       └── app.py            # FastAPI 应用入口（create_app()）
 │
 └── packages/harness/deerflow/
     ├── agents/
@@ -85,4 +85,4 @@ frontend/src/
 | 技能加载（热重载） | `skills/loader.py` |
 | MCP 工具缓存 | `mcp/cache.py` |
 | 文件上传处理 | `uploads/manager.py` |
-| Gateway 主路由器 | `app/gateway/main.py` |
+| Gateway 应用工厂 | `app/gateway/app.py` |