feat(agent): LLM-powered collection node with welcome stage and session-scoped delete (assignment 4)

- prompts/collection.md: versioned collection system prompt extracted
  from workflow node yQaBxfrWjbRr with source/version/porting notes
- llm.py: LLMService protocol; FakeLLMService (scripted, records
  calls); OpenAILLMService (async, wait_for timeout with cancellation,
  retry only on timeout/429/connection, errors normalized)
- collect.py: run_collect reference impl - one LLM call produces
  state prefix + body, controlled repair (max 1 retry) for missing
  prefix or illegal stage proposal, whitelist guard, CollectReplyError
  without raw model content; dialogue history + confirmed fields
  injected into prompt so the model skips known info (作业4-5)
- fields.py / clock.py: three-state field candidates (unknown/
  candidate/confirmed), per-type validation (count not inferred from
  description, future time rejected), injectable Clock
- graph.py: welcome node - first message returns fixed 1001 greeting
  without LLM (mirrors workflow is_first_message -> Assigned Reply#3),
  route empty stage to welcome
- endpoints/delete_session: backend switch - langgraph clears graph
  checkpoint, fastgpt path unchanged
- config: AGENT_LLM_PROVIDER fake|openai with validation
- untrack .env (secrets), move template to root .env.example

Verified:
- pytest 103 passed; smoke turns 1/2/1
- Real LLM e2e: POST /chat multi-turn context works
- Golden eval collection_skip_known_info: 12/12 cases pass
- Golden eval no_false: 8/10 cases pass; 4 confirm/photo cases fail
  at final step - model routes on short reply '对' (prompt-adherence
  gap, photo/confirm stages are assignment 5 scope); recorded in
  evals/results/20261020-144856

Known limits: field extraction from model reply not wired (stub);
photo/confirm nodes still scaffold; clarify counting is approximate.

test/agent/test_scaffold.py

@@ -46,11 +46,24 @@ async def test_different_threads_are_isolated() -> None:
 
 
 @pytest.mark.asyncio
-async def test_reply_uses_fixed_template_with_stage_prefix() -> None:
+async def test_first_turn_is_welcome_stage() -> None:
+    # 新会话首条消息：welcome 节点固定问候，返回 1001（对照工作流
+    # work_start is_first_message → Assigned Reply#3），不调用模型
     graph = build_graph()
-
     result = await ask(graph, "thread-a", "你好")
 
-    assert result["stage_code"] == "1002"
-    assert result["response_text"].startswith("<state>1002</state>")
-    assert "你好" in result["response_text"]
+    assert result["stage_code"] == "1001"
+    assert result["response_text"].startswith("<state>1001</state>")
+    assert result["turn_count"] == 1
+
+
+@pytest.mark.asyncio
+async def test_second_turn_keeps_stage_without_event() -> None:
+    # 问候后的普通输入：脚手架版无事件则保持 1001，
+    # 【继续办理】等事件经白名单进入 1002（见 test_transitions.py）
+    graph = build_graph()
+    await ask(graph, "thread-a", "你好")
+    result = await ask(graph, "thread-a", "我出车祸了")
+
+    assert result["stage_code"] == "1001"
+    assert "我出车祸了" in result["response_text"]