feat: 重构知识库系统，移除Hermes集成，增强RAG和同步功能

主要变更:
- 移除Hermes智能体及相关回调服务
- 新增知识库RAG、同步、调度、规范化和索引任务服务
- 重构orchestrator服务，增强运行时聊天功能
- 更新前端聊天、政策制度、设置等页面样式和逻辑
- 更新expense_claims和document_intelligence服务
- 删除llm_wiki相关服务和测试文件
- 更新docker-compose配置和启动脚本

server/src/app/api/v1/endpoints/hermes.py

@@ -1,44 +0,0 @@
-from __future__ import annotations
-
-from typing import Annotated
-
-from fastapi import APIRouter, Depends, HTTPException, status
-from sqlalchemy.orm import Session
-
-from app.api.deps import get_db
-from app.api.v1.endpoints.settings import require_hermes_agent_token
-from app.schemas.common import ErrorResponse
-from app.schemas.hermes import HermesCallbackRead, HermesCallbackWrite
-from app.services.hermes_callbacks import HermesCallbackService
-
-router = APIRouter(prefix="/hermes")
-DbSession = Annotated[Session, Depends(get_db)]
-
-
-@router.post(
-    "/callback",
-    response_model=HermesCallbackRead,
-    dependencies=[Depends(require_hermes_agent_token)],
-    summary="接收 Hermes 通用回调",
-    description="所有 Hermes 任务统一通过该入口回传进度或完成结果，服务端依据 type 分发到对应业务处理器。",
-    responses={
-        status.HTTP_400_BAD_REQUEST: {
-            "model": ErrorResponse,
-            "description": "Hermes 回调载荷不合法或任务类型暂不支持。",
-        },
-        status.HTTP_404_NOT_FOUND: {
-            "model": ErrorResponse,
-            "description": "回调引用的 AgentRun 不存在。",
-        },
-    },
-)
-def handle_hermes_callback(
-    payload: HermesCallbackWrite,
-    db: DbSession,
-) -> HermesCallbackRead:
-    try:
-        return HermesCallbackService(db).handle_callback(payload)
-    except LookupError as exc:
-        raise HTTPException(status_code=status.HTTP_404_NOT_FOUND, detail=str(exc)) from exc
-    except ValueError as exc:
-        raise HTTPException(status_code=status.HTTP_400_BAD_REQUEST, detail=str(exc)) from exc

server/src/app/api/v1/endpoints/settings.py

@@ -98,7 +98,7 @@ def test_model_connectivity(
     response_model=RuntimeModelConfigRead,
     dependencies=[Depends(require_hermes_agent_token)],
     summary="读取 Hermes 运行时模型配置",
-    description="供 Hermes 进程读取主模型、备用模型、VLM 或 Embedding 模型的运行时配置。",
+    description="供 Hermes 进程读取主模型、备用模型、Embedding 或 Reranker 模型的运行时配置。",
     responses={
         status.HTTP_401_UNAUTHORIZED: {
             "model": ErrorResponse,