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

examples/langgraph_smoke.py

@@ -1,28 +1,31 @@
-"""LangGraph 脚手架冒烟脚本（作业 1）。
+"""LangGraph 脚手架冒烟脚本。
 
 同一 thread 输入两次、另一个 thread 输入一次，打印轮数和文本。
-预期输出轮数依次为 1、2、1。
+预期轮数依次为 1、2、1；首轮为 welcome（1001 固定问候，不调模型），
+第二轮起由注入的 workflow fake LLM 按提示词语义回复。
 
 本脚本不导入 FastGPT、不读取其密钥；离线即可运行：
 
-    python examples/langgraph_smoke.py
+    python -m examples.langgraph_smoke
 """
 
 import asyncio
 
-from src.agent.graph import build_graph
+from src.agent.graph import GraphDeps, build_graph, workflow_fake_llm
 
 
 async def main() -> None:
     graph = build_graph()
+    deps = GraphDeps(llm=workflow_fake_llm())
 
     async def ask(thread_id: str, text: str) -> None:
-        # 只传本轮变化的字段；会话字段（turn_count 等）由 checkpoint 保管。
-        # 注意：对已有 checkpoint 的 thread 传入完整初始状态，
-        # 其中的 turn_count=0 会覆盖已累计的值。
+        # 只传本轮变化的字段；会话字段（turn_count/stage_code 等）
+        # 由 checkpoint 保管。注意：对已有 checkpoint 的 thread 传
+        # 完整初始状态会覆盖已累计的值。
         result = await graph.ainvoke(
             {"session_id": thread_id, "input_text": text},
             config={"configurable": {"thread_id": thread_id}},
+            context=deps,
         )
         print(
             f"thread={thread_id} turn_count={result['turn_count']} "