feat(backends): wire LangGraph backend behind AGENT_BACKEND switch (assignment 2)

- src/backends/langgraph.py: LangGraphBackend implements ChatBackend;
  complete() runs one graph turn per session (thread_id=sessionId) and
  returns state-prefixed content; stream() emits the full state prefix
  before body fragments (full-answer slicing, not yet real incremental
  output - assignment 8)
- src/core/config.py: AGENT_BACKEND=fastgpt|langgraph, langgraph mode
  no longer requires FastGPT credentials at startup
- src/core/fastgpt_client.py: lifespan builds the backend by switch
- test/backends/test_langgraph_backend.py: adapter acceptance tests

Verified:
- pytest: 48 passed
- AGENT_BACKEND=langgraph uvicorn: POST /chat -> 1002;
  browser_addon -> browser_addon.1002; SSE = stage_code, text_delta,
  single done

Known limit: stream slices a complete answer; no formUpdate deltas yet
(assignment 6).

src/backends/langgraph.py

@@ -0,0 +1,65 @@
+"""LangGraph implementation of the backend-neutral chat contract（作业 2）。
+
+实现 ``ChatBackend`` Protocol，把图执行结果翻译为公共契约：
+- ``complete()`` 返回 ``ChatResult``，``content`` 保留
+  ``<state>XXXX</state>`` 前缀（API 层负责解析）；
+- ``stream()`` 产生 ``TextDelta`` / ``FormUpdate``；初期允许把固定完整答案
+  切成若干片段，真实增量输出在作业 8 接入。
+
+通过 ``build_graph()`` 编译的图构造；会话用
+``configurable.thread_id = chat_input.session_id`` 绑定。
+
+对应测试：test/backends/test_langgraph_backend.py
+"""
+
+from collections.abc import AsyncIterator
+
+from ..agent.graph import build_graph
+from .chat import ChatInput, ChatResult, ChatStreamEvent, ChatBackend, TextDelta
+
+
+class LangGraphBackend(ChatBackend):
+    """Adapt a compiled LangGraph to the neutral chat contract."""
+
+    def __init__(self, graph=None):
+        """参数:
+        graph: 编译后的图；缺省调用 ``build_graph()``（内存 checkpoint）。
+        """
+        self._graph = graph if graph is not None else build_graph()
+
+    async def complete(self, chat_input: ChatInput) -> ChatResult:
+        """非流式：执行一轮图并翻译结果。
+
+        TODO(作业 2): 实现该方法。要求：
+        - 用 ``ainvoke`` 执行图，``thread_id`` 取
+          ``chat_input.session_id``；
+        - 初始 state 至少包含 ``session_id``、``input_text``；
+        - 返回 ``ChatResult(content=<响应文本（含 state 前缀）>,
+          status_code=None, form_update={})``；
+        - 本阶段不处理 ``need_form_update`` 的真实表单差量
+          （作业 6 起实现）。
+        """
+        result = await self._graph.ainvoke(
+            {"session_id": chat_input.session_id, "input_text": chat_input.text},
+            config={"configurable": {"thread_id": chat_input.session_id}},
+        )
+        return ChatResult(
+          content = result["response_text"],
+          status_code = None,
+          form_update = {}
+        )
+
+    async def stream(self, chat_input: ChatInput) -> AsyncIterator[ChatStreamEvent]:
+        """流式：产生中立流事件。
+
+        TODO(作业 2): 实现该方法。最低要求：
+        - 先产出含完整 ``<state>...</state>`` 前缀的 ``TextDelta``，
+          再产出正文片段（保证 API 层的 stage 先于正文约束）；
+        - 本阶段允许“完整答案切片段”，提交说明须标注
+          “尚未接入模型增量输出”（作业 8 改为真实增量）。
+        """
+        result = await self.complete(chat_input)
+        prefix, _, body = result.content.partition("</state>")
+        yield TextDelta(prefix + "</state>")
+        if body:
+            yield TextDelta(body)