> ## Documentation Index
> Fetch the complete documentation index at: https://docs.lingxilearn.cn/llms.txt
> Use this file to discover all available pages before exploring further.

# 创建第一个图

> 定义状态、节点、边并观察流式更新

本教程创建一个两节点支持流程：先规范化请求，再生成结果。它只使用嵌入式核心，不需要数据库或模型 API key。

<Steps>
  <Step title="创建文件">
    新建 `support_graph.py`：

    ```python theme={null}
    from typing import TypedDict

    from lingxigraph import END, START, Runtime, StateGraph


    class SupportState(TypedDict):
        request: str
        normalized: str
        result: str


    class AppContext(TypedDict):
        tenant: str


    def normalize(state: SupportState):
        return {"normalized": state["request"].strip().lower()}


    def resolve(state: SupportState, runtime: Runtime[AppContext]):
        runtime.stream_writer({"stage": "resolved"})
        return {
            "result": f"{runtime.context['tenant']}: {state['normalized']}"
        }


    builder = StateGraph(
        SupportState,
        context_schema=AppContext,
        name="support",
        version="1.0.0",
    )
    builder.add_node("normalize", normalize)
    builder.add_node("resolve", resolve, timeout=30)
    builder.add_edge(START, "normalize")
    builder.add_edge("normalize", "resolve")
    builder.add_edge("resolve", END)
    graph = builder.compile()
    ```
  </Step>

  <Step title="同步调用">
    在文件末尾加入：

    ```python theme={null}
    initial = {"request": "  RESET ACCESS  ", "normalized": "", "result": ""}
    print(graph.invoke(initial, context={"tenant": "acme"}))
    ```

    ```bash theme={null}
    python support_graph.py
    ```
  </Step>

  <Step title="观察状态更新">
    将调用替换为：

    ```python theme={null}
    for update in graph.stream(
        initial,
        context={"tenant": "acme"},
        stream_mode="updates",
    ):
        print(update)
    ```

    `updates` 模式按超步产生增量；`values` 产生完整状态；`events` 产生生命周期事件；`custom` 接收 `stream_writer` 写入的值。
  </Step>
</Steps>

## 编译时发生了什么

`compile()` 会校验可达性、边、状态 schema 和 reducer，并冻结不可变执行计划。默认字段使用 `LastValue`；并行节点写同一字段时，应使用 `Annotated[T, reducer]` 声明确定性归并策略。

## 加入 checkpoint

```python theme={null}
from lingxigraph import InMemorySaver

graph = builder.compile(checkpointer=InMemorySaver())
config = {"configurable": {"thread_id": "ticket-123"}}
result = graph.invoke(initial, config=config, context={"tenant": "acme"})
snapshot = graph.get_state(config)
print(snapshot.values)
```

`InMemorySaver` 适合测试；本地持久化使用 `SqliteSaver`，生产环境使用 `PostgresSaver`。继续阅读[耐久执行](../concepts/durable-execution)。