feat(§03): 实现 MCP Server 核心 - Storage/Service/Tool/MCP Protocol Layers

**Storage Layer:**
- Database 类(aiosqlite + WAL + 并发保护)
- WikiPage 数据模型
- fix_dirty_states 恢复机制
- FTS5 全文搜索支持
- 完整的 SQLite 表结构

**Service Layer:**
- CacheService(LRU 缓存 + TTL + 大小限制)
- QueryService(查询服务)
- ParserService(Markdown 解析)
- IndexerService(索引服务)
- GraphService(链接图服务)

**Tool Layer (8 个 MCP Tools):**
- wiki_query - FTS5 全文搜索 + 标签过滤
- memory_bridge - 按工具来源浏览
- wiki_status - 索引状态
- wiki_lint - 健康审计
- cross_linker - 缺失链接发现
- tag_taxonomy - 标签一致性
- wiki_synthesize - 跨概念综合分析
- daily_update - 日常维护 + hot.md 生成

**MCP Protocol Layer:**
- MCP 协议解析和封装
- 工具注册和路由
- 错误处理和日志
- stdio 模式支持

**配置和部署:**
- requirements.txt
- config.example.yaml
- ecosystem.config.cjs (PM2)

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>
This commit is contained in:
2026-06-26 11:32:43 +08:00
parent 67a53d82de
commit dfd8421dc6
22 changed files with 2561 additions and 0 deletions
+105
View File
@@ -0,0 +1,105 @@
"""
Tool Layer - daily_update 工具
日常维护(检查源新鲜度、更新 index、重新生成 hot.md)。
参考设计文档:第 2.2 节
"""
import logging
from typing import Dict, Any
from datetime import datetime
from pathlib import Path
from ..services import QueryService, IndexerService
logger = logging.getLogger(__name__)
class DailyUpdateTool:
"""daily_update 工具实现"""
def __init__(self, query_service: QueryService, indexer_service: IndexerService):
self.query_service = query_service
self.indexer_service = indexer_service
async def handle(self) -> Dict[str, Any]:
"""
日常维护
Returns:
{
"updated": 5,
"new": 2,
"hot_md_generated": true,
"index_status": {...}
}
"""
# 1. 增量更新索引
index_status = await self.indexer_service.incremental_update()
# 2. 获取最近更新的页面
recent_pages = await self.query_service.db.get_recent_pages(days=7, limit=20)
# 3. 获取新增标签
new_tags = await self.query_service.db.get_new_tags(days=7)
# 4. 查找孤立页面
from ..services import GraphService
graph_service = GraphService(self.query_service.db)
orphans = await graph_service.find_orphans()
# 5. 生成 hot.md
hot_md_generated = await self._generate_hot_md(recent_pages, new_tags, orphans)
return {
"updated": len(recent_pages),
"new": len(new_tags),
"hot_md_generated": hot_md_generated,
"index_status": index_status
}
async def _generate_hot_md(self, recent_pages, new_tags, orphans) -> bool:
"""生成热点文件"""
try:
# 确定 hot.md 保存路径
vault_path = Path(self.query_service.db.path).parent.parent / "wiki-vault"
hot_path = vault_path / "hot.md"
# 格式化内容
content = f"""# Wiki Hot - {datetime.now().strftime('%Y-%m-%d')}
## 最近更新(7 天内)
"""
for page in recent_pages[:10]:
content += f"- [[{page.path}|{page.title}]] - {page.updated_at}\n"
content += "\n## 新增标签(7 天内)\n\n"
for tag, updated_at in new_tags[:10]:
content += f"- `{tag}` - {updated_at}\n"
content += "\n## 待链接页面(孤立页面)\n\n"
for orphan in sorted(list(orphans))[:10]:
content += f"- [[{orphan}]]\n"
# 写入文件
with open(hot_path, 'w', encoding='utf-8') as f:
f.write(content)
logger.info(f"Generated hot.md: {hot_path}")
return True
except Exception as e:
logger.error(f"Failed to generate hot.md: {e}")
return False
def get_schema(self) -> dict:
"""返回 MCP Tool schema"""
return {
"name": "daily_update",
"description": "日常维护(检查源新鲜度、更新 index、重新生成 hot.md",
"inputSchema": {
"type": "object",
"properties": {}
}
}