refactor(server): Phase 1 图拓扑重构 - LangGraph 成为唯一编排者

P1.3-P1.7：把 endpoint 补丁搬进图节点，门控收敛到 gate_classify 单一决策点。

- StewardGraphState 扩展：recent_history/steward_state/gate_decision/gate_scene_id/conversation_id
- 新增 5 个图节点：load_context（读历史+state）/gate_classify（统一门控）/execute_scene_handler/resume_recent_task/pending_flow wrapper
- 图拓扑从 5 节点重构为 10 节点：load_context → gate_classify → {off_topic/handler_only/resume/ambiguous/model_intent} → attach_action_steps
- gate_classify 四步裁决：resume门 → off_topic门 → 规则匹配门 → LLM门
- resume 门控优先于 off_topic，避免'再提交'被误判闲聊
- schema 放宽 planning_source/next_action Literal → str，支持 scene_handler:*/context_resume/answer_only
- endpoint 按 planner 类型分发 build_plan（LangGraph 接 db，legacy 不接）
- 76 passed + 4 场景端到端验证（出差申请/再提交/查差旅标准/闲聊）

server/src/app/schemas/steward.py

@@ -6,8 +6,8 @@ from pydantic import BaseModel, Field
 
 StewardTaskType = str
 StewardAssignedAgent = str
-StewardPlanningSource = Literal["llm_function_call", "rule_fallback"]
-StewardPlanNextAction = Literal["confirm_flow", "confirm_task", "delegate_task", "none"]
+StewardPlanningSource = str  # 放宽:支持 llm_function_call / rule_fallback / scene_handler:* / context_resume
+StewardPlanNextAction = str  # 放宽:支持 confirm_flow / confirm_task / delegate_task / none / answer_only
 StewardRequestedAction = Literal["preview", "save_draft", "submit"]
 StewardSlotDecisionSource = Literal["llm_function_call", "rule_fallback"]
 StewardSlotNextAction = Literal["ask_user", "render_preview"]