refactor(server): user_agent/steward/ocr 等服务重构并适配关联任务

- user_agent 拆分 application/locations/knowledge/response/review 四个子模块，接入申请位置语义与关联草稿分支
- steward planner/runtime/slot/plan_builder 决策链路重构，travel_reimbursement_calculator/orchestrator_expense_query 适配
- ocr/document_preview/document_intelligence/receipt_folder 复用预览与资产缓存，expense_claim_draft_flow/application_handoff 适配
- pyproject.toml 新增依赖，paddleocr bootstrap 脚本与 server_start.sh 调整
- 更新差旅/交通/通信等财务规则表，同步 document_intelligence/ocr/receipt_folder/user_agent 等测试

server/src/app/services/expense_claim_draft_flow.py

@@ -827,8 +827,8 @@ class ExpenseClaimDraftFlowMixin(ExpenseClaimApplicationLinkMixin, ExpenseClaimD
             document_count = max(len(context_documents), len(attachment_names), self._resolve_attachment_count(context_json))
             return {
                 "message": (
-                    f"检测到你已有草稿 {association_candidate.claim_no}，"
-                    f"当前新上传了 {document_count} 张票据，请先选择关联到现有草稿，或单独建立新的报销单。"
+                    f"检测到您已有草稿 {association_candidate.claim_no}，"
+                    f"当前新上传了 {document_count} 张票据，请先选择关联到现有草稿，或单独新建一张报销单。"
                 ),
                 "draft_only": False,
                 "status": "pending_association_decision",
@@ -859,7 +859,7 @@ class ExpenseClaimDraftFlowMixin(ExpenseClaimApplicationLinkMixin, ExpenseClaimD
             if existing_draft_count >= MAX_DRAFT_CLAIMS_PER_USER:
                 return {
                     "message": (
-                        f"你当前已保存 {MAX_DRAFT_CLAIMS_PER_USER} 个草稿，请先完成已保存的草稿，"
+                        f"您当前已保存 {MAX_DRAFT_CLAIMS_PER_USER} 个草稿，请先完成已保存的草稿，"
                         "才能再次新建草稿。"
                     ),
                     "draft_limit_reached": True,