refactor(agent): inject deps via context_schema, LLM-driven photo/confirm nodes

- graph.py: LangGraph-native DI - StateGraph(context_schema=GraphDeps),
  nodes take (state, runtime: Runtime[GraphDeps]); build_graph() decoupled
  from LLM; deleted scaffold _event_reply/_fake_llm_propose/stub nodes
- photo.py: model proposes stage+body via per-mode prompts (direct/addon);
  validator enforces clientMode exits; deterministic event forcing removed
- confirm.py: single runtime for single/dual confirm, extraction call
  isolated per person_index
- llm.py: workflow_fake_llm() (offline workflow-faithful responder,
  history-aware) for smoke/tests
- backend: LangGraphBackend(graph, llm) passes context per call
- tests: invoke helpers inject GraphDeps; illegal-proposal test asserts
  error + state untouched via second well-behaved fake

Verified: 143 passed; smoke turns 1/2/1 with original welcome text

src/backends/langgraph.py

@@ -14,18 +14,21 @@
 
 from collections.abc import AsyncIterator
 
-from ..agent.graph import build_graph
+from ..agent.graph import GraphDeps, build_graph, workflow_fake_llm
 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):
+    def __init__(self, graph=None, llm=None):
         """参数:
-        graph: 编译后的图；缺省调用 ``build_graph()``（内存 checkpoint）。
+        graph: 编译后的图；缺省调用 ``build_graph()``。
+        llm: LLM 服务（运行时依赖）；缺省为离线 workflow fake。
+            生产环境由 lifespan 注入 ``build_llm_service()`` 的实例。
         """
         self._graph = graph if graph is not None else build_graph()
+        self._llm = llm if llm is not None else workflow_fake_llm()
 
     async def complete(self, chat_input: ChatInput) -> ChatResult:
         """非流式：执行一轮图并翻译结果。
@@ -40,8 +43,13 @@ class LangGraphBackend(ChatBackend):
           （作业 6 起实现）。
         """
         result = await self._graph.ainvoke(
-            {"session_id": chat_input.session_id, "input_text": chat_input.text},
+            {
+                "session_id": chat_input.session_id,
+                "input_text": chat_input.text,
+                "client_mode": chat_input.client_mode,
+            },
             config={"configurable": {"thread_id": chat_input.session_id}},
+            context=GraphDeps(llm=self._llm),
         )
         return ChatResult(
           content = result["response_text"],