进阶功能扩展

// examples/ch14-extensions/src/ai-compressor.ts（节选）
import Anthropic from '@anthropic-ai/sdk';
 
const client = new Anthropic(); // 从 ANTHROPIC_API_KEY 等环境变量读取凭据
const MODEL = process.env.ANTHROPIC_MODEL || 'claude-opus-5-5';
 
const message = await client.messages.create({
  model: MODEL,
  max_tokens: 4096,
  output_config: { effort: 'low' },   // 摘要是简单任务，用低 effort 控制思考开销
  messages: [{ role: 'user', content: `你是一个记忆压缩助手……\n\nObservations:\n${observationText}` }],
});
 
if (message.stop_reason === 'refusal') throw new Error('请求被拒绝');
const summary = message.content
  .filter((block): block is Anthropic.TextBlock => block.type === 'text')
  .map((block) => block.text)
  .join('');

// 设计示意：单条工具调用的语义压缩，接入 mini-mem 的完整实现留作练习
const TYPES = ['bugfix', 'feature', 'refactor', 'change', 'discovery', 'decision'] as const;
 
export async function compressObservation(toolName: string, toolInput: unknown, outcome: unknown) {
  const response = await client.messages.create({
    model: MODEL,
    max_tokens: 4096,
    output_config: { effort: 'low' },
    messages: [{
      role: 'user',
      content: `分析下面这次工具调用，判断是否值得记住。
值得记住时，只输出一个 JSON 对象：
{"type": ${TYPES.map(t => `"${t}"`).join(' | ')}, "title": "一句话标题", "narrative": "50 字以内", "facts": ["事实"]}
只是例行操作（空的状态检查、无输出的列表、没有结果的搜索）时，只输出 {"skip": true}。
 
<what_happened>${toolName}</what_happened>
<parameters>${truncate(JSON.stringify(toolInput))}</parameters>
<outcome>${truncate(JSON.stringify(outcome))}</outcome>`,
    }],
  });
  // 解析失败时不要重试到无限：记一条日志，这一次就不记了
}
 
// 保留开头 60% 和结尾 30%，中间标注省略了多少字符（claude-mem 的 truncateObservationField 同款）
function truncate(text: string, max = 4000): string {
  if (text.length <= max) return text;
  const head = text.slice(0, Math.floor(max * 0.6));
  const tail = text.slice(-Math.floor(max * 0.3));
  return `${head}\n... <elided chars="${text.length - head.length - tail.length}" /> ...\n${tail}`;
}

// 设计示意：在 ch13-mini-mem 的 src/db/store.ts 中添加
getTimeline(anchorId: number, before = 3, after = 3) {
  const anchor = this.db.prepare('SELECT created_at, project FROM observations WHERE id = ?').get(anchorId) as
    { created_at: number; project: string } | undefined;
  if (!anchor) return { before: [], anchorId: null, after: [] };
 
  // 时间相同的记录用 id 打破平局，否则同一秒写入的几条会被漏掉或重复（claude-mem #4104 修过同类问题）
  const beforeRows = this.db.prepare(`
    SELECT id, type, title, created_at FROM observations
    WHERE project = ? AND (created_at, id) < (?, ?)
    ORDER BY created_at DESC, id DESC LIMIT ?
  `).all(anchor.project, anchor.created_at, anchorId, before);
 
  const afterRows = this.db.prepare(`
    SELECT id, type, title, created_at FROM observations
    WHERE project = ? AND (created_at, id) > (?, ?)
    ORDER BY created_at ASC, id ASC LIMIT ?
  `).all(anchor.project, anchor.created_at, anchorId, after);
 
  return { before: beforeRows.reverse(), anchorId, after: afterRows };
}

{
  name: 'timeline',
  description: 'Show observations before and after one ID from search.',
  inputSchema: {
    type: 'object',
    properties: {
      anchor: { type: 'integer', description: 'Observation ID from search' },
      before: { type: 'integer', minimum: 0, maximum: 5 },
      after: { type: 'integer', minimum: 0, maximum: 5 },
    },
    required: ['anchor'],
    additionalProperties: false,
  },
  annotations: { readOnlyHint: true },
}

// examples/ch14-extensions/src/vector-search.ts（节选）
import { ChromaClient } from 'chromadb';
import { DefaultEmbeddingFunction } from '@chroma-core/default-embed';
 
const embeddingFunction = new DefaultEmbeddingFunction();
const url = new URL(process.env.CHROMA_URL || 'http://localhost:8000');
const chroma = new ChromaClient({ host: url.hostname, port: Number(url.port), ssl: url.protocol === 'https:' });
 
const collection = await chroma.getOrCreateCollection({ name: 'observations', embeddingFunction });
await collection.add({
  ids: observations.map((obs) => obs.id),
  documents: observations.map((obs) => obs.content),
  metadatas: observations.map((obs) => ({ category: obs.category, timestamp: obs.timestamp })),
});
 
const results = await collection.query({ queryTexts: ['用户的技术栈是什么'], nResults: 3 });
const filtered = await collection.query({
  queryTexts: ['部署方式'], nResults: 3,
  where: { category: { $eq: 'preference' } },
});

# 用 uv（claude-mem 也是这样启动 chroma-mcp 的）
uvx --from chromadb chroma run --path ./chroma-data --port 8000
# 或者用 Docker
docker run -p 8000:8000 chromadb/chroma

[1] (距离: 0.3860) 用户正在写一本关于 LLM 基础设施的技术书籍
[2] (距离: 0.5830) 用户对 Agent 架构很感兴趣，正在研究多 Agent 协作模式
[3] (距离: 0.6536) 用户的包管理器是 npm，不用 yarn 或 pnpm

// examples/ch14-extensions/src/viewer-server.ts（节选）
import express from 'express';
import type { Request, Response } from 'express';
 
const app = express();
app.use(express.json());
 
const observations: Observation[] = [];
const sseClients: Set<Response> = new Set();
 
// SSE 端点：连接时先推全量数据，之后接收增量广播
app.get('/api/stream', (req: Request, res: Response) => {
  res.setHeader('Content-Type', 'text/event-stream');
  res.setHeader('Cache-Control', 'no-cache');
  res.setHeader('Connection', 'keep-alive');
  res.write(`data: ${JSON.stringify({ type: 'init', observations })}\n\n`);
  sseClients.add(res);
  req.on('close', () => sseClients.delete(res));
});
 
function broadcast(observation: Observation) {
  const payload = `data: ${JSON.stringify({ type: 'new', observation })}\n\n`;
  for (const client of sseClients) client.write(payload);
}

// 设计示意：升级 ch13-mini-mem 的 src/utils/project.ts
import { execFileSync } from 'node:child_process';
import path from 'node:path';
 
export function projectNameOf(cwd: string): string {
  try {
    // git 仓库根目录；在子目录里启动也能得到同一个项目
    const top = execFileSync('git', ['rev-parse', '--show-toplevel'], { cwd, stdio: ['ignore', 'pipe', 'ignore'] })
      .toString().trim();
    return path.basename(top).toLowerCase();
  } catch {
    return path.basename(path.resolve(cwd)).toLowerCase();
  }
}