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

test/agent/test_scaffold.py

@@ -11,15 +11,16 @@
 
 import pytest
 
-from src.agent.graph import build_graph
+from src.agent.graph import GraphDeps, build_graph, workflow_fake_llm
 
 
-async def ask(graph, thread_id: str, text: str) -> dict:
+async def ask(graph, thread_id: str, text: str, llm=None) -> dict:
     # 只传本轮变化的字段；对已有 checkpoint 的 thread 传完整初始状态，
     # 其中的 turn_count=0 会覆盖已累计的值（LangGraph 输入按通道覆盖）。
     return await graph.ainvoke(
         {"session_id": thread_id, "input_text": text},
         config={"configurable": {"thread_id": thread_id}},
+        context=GraphDeps(llm=llm or workflow_fake_llm()),
     )