recallnest 2.2.1 → 2.3.0

package/CLAUDE.md

@@ -42,5 +42,5 @@
 ## 6. 测试基线
 
 - 改完代码必须跑 `bun test`，全量通过才能 commit
-- 当前基线：1428 tests / 0 fail
+- 当前基线：1486 tests / 0 fail
 - 新增功能必须配套测试，基线只能涨不能降

package/README.md

@@ -10,10 +10,10 @@ A local-first memory system backed by LanceDB that turns scattered conversation
 
 [![GitHub](https://img.shields.io/github/stars/AliceLJY/recallnest?style=social)](https://github.com/AliceLJY/recallnest)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-[![Bun](https://img.shields.io/badge/Runtime-Bun-f9f1e1?logo=bun)](https://bun.sh)
+[![Runtime](https://img.shields.io/badge/Runtime-Bun_|_Node.js_18+-f9f1e1?logo=bun)](https://bun.sh)
 [![LanceDB](https://img.shields.io/badge/LanceDB-Vector+FTS-orange)](https://lancedb.com)
 [![MCP](https://img.shields.io/badge/MCP-41_tools-blue)](https://modelcontextprotocol.io)
-[![Tests](https://img.shields.io/badge/Tests-1428_pass-brightgreen)](https://github.com/AliceLJY/recallnest)
+[![Tests](https://img.shields.io/badge/Tests-1486_pass-brightgreen)](https://github.com/AliceLJY/recallnest)
 [![CC Plugin](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://github.com/AliceLJY/recallnest)
 
 **English** | [简体中文](README_CN.md) | [Roadmap](ROADMAP.md)
@@ -54,9 +54,20 @@ Wins or ties in **all 6 categories**, with no regression. The hybrid retrieval p
 
 RecallNest starts automatically with Claude Code. No manual MCP config needed.
 
-> **Requires:** [Bun](https://bun.sh) runtime. Dependencies install on first start.
+> **Requires:** [Bun](https://bun.sh) (recommended) or Node.js 18+. Dependencies install on first start.
 
-### Option B: Manual setup
+### Option B: npm install
+
+```bash
+npx recallnest --help          # run directly
+# or
+npm install -g recallnest      # install globally
+recallnest doctor
+```
+
+Works with Node.js 18+ (via tsx) or Bun. No git clone needed.
+
+### Option C: Manual setup
 
 ```bash
 git clone https://github.com/AliceLJY/recallnest.git
@@ -186,9 +197,11 @@ bun run src/ui-server.ts
 | **Dashboard** | Web UI with stats, category distribution, growth trends, and health |
 | **Workflow Observation** | Dedicated append-only workflow health records, outside regular memory |
 | **Structured Assets** | Pins, briefs, and distilled summaries — not just raw logs |
-| **Data Checkup** | Data quality health checks on the memory store |
+| **Data Checkup** | Data quality health checks on the memory store (including source health) |
+| **Source Heartbeats** | Automatic ingest health tracking per data source with staleness alerts |
 | **Export Graph** | Export interactive HTML knowledge graph visualization |
 | **Batch Operations** | Store up to 20 memories in a single call with dedup |
+| **Connector Framework** | Standard connector-v1 format for external data sources with example adapters |
 
 ---
 
@@ -222,6 +235,18 @@ v2.1 added philosophy-informed behavior; v2.2 closes the last three engine-layer
 
 ---
 
+## New in v2.3: Connector Ecosystem + Source Health
+
+v2.2 hardened retrieval quality; v2.3 opens RecallNest to external data sources with a standard connector framework and operational health monitoring.
+
+- **Connector-v1 Standard** *(GB-2)* — A JSON format (`ConnectorOutputV1`) that any external script can produce. Obsidian vaults, emails, RSS feeds, log files — normalize once, ingest through the full dedup/embed/extract pipeline. See [`docs/connector-spec.md`](docs/connector-spec.md) for the specification and [`connectors/examples/`](connectors/examples/) for adapter skeletons (email, logs, RSS).
+
+- **Obsidian Vault Ingestion** *(GB-1)* — First-party Obsidian connector: scans `.md` files, extracts frontmatter + wikilinks, maps folder structure to tags. One command: `lm ingest --obsidian /path/to/vault`.
+
+- **Source Health Monitoring** *(GB-3)* — Every connector ingest writes a heartbeat to `data/source-heartbeat.json`. `data_checkup` flags stale sources (>7d warning, >30d error). `doctor --ci` shows a per-source heartbeat summary with human-readable age.
+
+---
+
 ## Architecture
 
 ```

package/README_CN.md

@@ -10,10 +10,10 @@
 
 [![GitHub](https://img.shields.io/github/stars/AliceLJY/recallnest?style=social)](https://github.com/AliceLJY/recallnest)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green.svg)](LICENSE)
-[![Bun](https://img.shields.io/badge/Runtime-Bun-f9f1e1?logo=bun)](https://bun.sh)
+[![Runtime](https://img.shields.io/badge/Runtime-Bun_|_Node.js_18+-f9f1e1?logo=bun)](https://bun.sh)
 [![LanceDB](https://img.shields.io/badge/LanceDB-Vector+FTS-orange)](https://lancedb.com)
 [![MCP](https://img.shields.io/badge/MCP-41_tools-blue)](https://modelcontextprotocol.io)
-[![Tests](https://img.shields.io/badge/Tests-1428_pass-brightgreen)](https://github.com/AliceLJY/recallnest)
+[![Tests](https://img.shields.io/badge/Tests-1486_pass-brightgreen)](https://github.com/AliceLJY/recallnest)
 [![CC Plugin](https://img.shields.io/badge/Claude_Code-Plugin-blueviolet)](https://github.com/AliceLJY/recallnest)
 
 [English](README.md) | **简体中文** | [Roadmap](ROADMAP.md)
@@ -54,9 +54,20 @@ RecallNest 的解法：**一个 LanceDB 驱动的记忆层，三个终端共读
 
 RecallNest 随 Claude Code 自动启动，无需手动配置 MCP。
 
-> **前置要求：** 安装 [Bun](https://bun.sh) 运行时。首次启动自动安装依赖。
+> **前置要求：** [Bun](https://bun.sh)（推荐）或 Node.js 18+。首次启动自动安装依赖。
 
-### 方式 B：手动安装
+### 方式 B：npm 安装
+
+```bash
+npx recallnest --help          # 直接运行
+# 或
+npm install -g recallnest      # 全局安装
+recallnest doctor
+```
+
+支持 Node.js 18+（通过 tsx）或 Bun，无需 clone 仓库。
+
+### 方式 C：手动安装
 
 ```bash
 git clone https://github.com/AliceLJY/recallnest.git
@@ -186,9 +197,11 @@ bun run src/ui-server.ts
 | **Dashboard** | Web UI 首页：统计卡片、类别分布、增长趋势、健康概览 |
 | **Workflow Observation** | 专门的 append-only 工作流观测层，不混入普通 memory |
 | **结构化资产** | Pin、Brief、Distill —— 不只是原始日志 |
-| **Data Checkup** | 记忆存储数据质量健康检查 |
+| **Data Checkup** | 记忆存储数据质量健康检查（含数据源健康） |
+| **数据源心跳** | 按数据源自动追踪 ingest 健康状态，过期告警 |
 | **导出图谱** | 导出交互式 HTML 知识图谱可视化 |
 | **批量操作** | 单次调用存储最多 20 条记忆，自带去重 |
+| **Connector 框架** | 标准 connector-v1 格式接入外部数据源，附带适配器示例 |
 
 ---
 
@@ -222,6 +235,18 @@ v2.1 加入了哲学记忆行为；v2.2 补齐前沿扫描（ACC、PI-LLM、TSM
 
 ---
 
+## v2.3 新增：Connector 生态 + 数据源健康
+
+v2.2 强化了检索质量；v2.3 通过标准 Connector 框架和运维健康监控，把 RecallNest 开放给外部数据源。
+
+- **Connector-v1 标准** *（GB-2）* —— 一套 JSON 格式（`ConnectorOutputV1`），任何外部脚本都可以输出。Obsidian 笔记、邮件、RSS、日志文件——标准化一次，走完整的 dedup/embed/extract 管线入库。规范见 [`docs/connector-spec.md`](docs/connector-spec.md)，适配器骨架见 [`connectors/examples/`](connectors/examples/)（email、logs、RSS）。
+
+- **Obsidian Vault 接入** *（GB-1）* —— 官方 Obsidian 连接器：扫描 `.md` 文件，提取 frontmatter + wikilink，文件夹结构映射为 tag。一条命令：`lm ingest --obsidian /path/to/vault`。
+
+- **数据源健康监控** *（GB-3）* —— 每次 connector ingest 写心跳到 `data/source-heartbeat.json`。`data_checkup` 标记过期数据源（>7 天 warning，>30 天 error）。`doctor --ci` 按数据源展示心跳摘要（如"obsidian: 2h ago"）。
+
+---
+
 ## 架构
 
 ```

package/connectors/examples/email-adapter.ts

@@ -0,0 +1,73 @@
+#!/usr/bin/env bun
+/**
+ * Email Connector Adapter (skeleton)
+ *
+ * Demonstrates how to produce a ConnectorOutputV1 JSON file from an email
+ * source (IMAP, Gmail API, local mbox, etc.) for RecallNest ingestion.
+ *
+ * Usage:
+ *   bun run connectors/examples/email-adapter.ts > email-output.json
+ *   lm ingest --connector email-output.json
+ *
+ * Customize:
+ *   1. Replace the fetchEmails() stub with your IMAP/API client
+ *   2. Adjust scope to match your project naming
+ *   3. Set categoryHint based on email type (meeting invite → "events", etc.)
+ */
+
+import type { ConnectorOutputV1 } from "../../src/connector-types.js";
+import { createHash } from "node:crypto";
+
+// ---------------------------------------------------------------------------
+// TODO: Replace with real email fetching logic
+// ---------------------------------------------------------------------------
+
+interface RawEmail {
+  messageId: string;
+  subject: string;
+  body: string;
+  from: string;
+  date: string; // ISO 8601
+}
+
+async function fetchEmails(_since: Date): Promise<RawEmail[]> {
+  // Example: use imapflow, googleapis, or read from .mbox
+  // const client = new ImapFlow({ host: 'imap.example.com', ... });
+  // await client.connect();
+  // const messages = await client.fetch(...);
+  return []; // Replace with real implementation
+}
+
+// ---------------------------------------------------------------------------
+// Transform → ConnectorOutputV1
+// ---------------------------------------------------------------------------
+
+async function main() {
+  const since = new Date(Date.now() - 7 * 86_400_000); // last 7 days
+  const emails = await fetchEmails(since);
+
+  const output: ConnectorOutputV1 = {
+    version: "connector-v1",
+    source: "email",
+    scope: "inbox:personal",           // Customize: "inbox:work", "project:xyz"
+    producedAt: new Date().toISOString(),
+    records: emails.map((email) => ({
+      id: `email:${email.messageId}`,
+      text: email.body,
+      title: email.subject,
+      categoryHint: "events",          // Customize per email type
+      importanceHint: 0.6,             // Customize: 0.9 for flagged/starred
+      tags: ["email", `from:${email.from}`],
+      timestamp: email.date,
+      contentHash: createHash("sha256").update(email.body).digest("hex"),
+      sourceMetadata: {
+        from: email.from,
+        messageId: email.messageId,
+      },
+    })),
+  };
+
+  console.log(JSON.stringify(output, null, 2));
+}
+
+main().catch(console.error);

package/connectors/examples/logs-adapter.ts

@@ -0,0 +1,103 @@
+#!/usr/bin/env bun
+/**
+ * Log File Connector Adapter (skeleton)
+ *
+ * Demonstrates how to produce a ConnectorOutputV1 JSON file from application
+ * log files for RecallNest ingestion. Useful for tracking deploy events,
+ * error patterns, and operational decisions.
+ *
+ * Usage:
+ *   bun run connectors/examples/logs-adapter.ts /var/log/myapp/*.log > logs-output.json
+ *   lm ingest --connector logs-output.json
+ *
+ * Customize:
+ *   1. Replace parseLogLine() with your log format parser
+ *   2. Adjust the importance/category logic for your use case
+ *   3. Set scope to match your project
+ */
+
+import type { ConnectorOutputV1 } from "../../src/connector-types.js";
+import { readFileSync } from "node:fs";
+import { createHash } from "node:crypto";
+
+// ---------------------------------------------------------------------------
+// TODO: Replace with your log format parser
+// ---------------------------------------------------------------------------
+
+interface ParsedLogEntry {
+  timestamp: string;  // ISO 8601
+  level: "info" | "warn" | "error" | "debug";
+  message: string;
+  source?: string;    // e.g. module name, service
+}
+
+function parseLogLine(line: string): ParsedLogEntry | null {
+  // Example: "2026-04-14T10:00:00Z [ERROR] auth: login failed for user@example.com"
+  const match = line.match(
+    /^(\d{4}-\d{2}-\d{2}T[\d:.]+Z?)\s+\[(\w+)]\s+(?:(\w+):\s+)?(.+)$/,
+  );
+  if (!match) return null;
+  return {
+    timestamp: match[1],
+    level: match[2].toLowerCase() as ParsedLogEntry["level"],
+    source: match[3],
+    message: match[4],
+  };
+}
+
+function levelToImportance(level: string): number {
+  switch (level) {
+    case "error": return 0.9;
+    case "warn":  return 0.7;
+    case "info":  return 0.5;
+    default:      return 0.3;
+  }
+}
+
+// ---------------------------------------------------------------------------
+// Transform → ConnectorOutputV1
+// ---------------------------------------------------------------------------
+
+function main() {
+  const files = process.argv.slice(2);
+  if (files.length === 0) {
+    console.error("Usage: logs-adapter.ts <logfile> [logfile...]");
+    process.exit(1);
+  }
+
+  const records: ConnectorOutputV1["records"] = [];
+
+  for (const file of files) {
+    const lines = readFileSync(file, "utf-8").split("\n").filter(Boolean);
+    for (const line of lines) {
+      const entry = parseLogLine(line);
+      if (!entry) continue;
+
+      // Skip debug-level by default — too noisy for memory storage
+      if (entry.level === "debug") continue;
+
+      records.push({
+        id: `log:${createHash("md5").update(line).digest("hex")}`,
+        text: entry.message,
+        title: entry.source ? `[${entry.level.toUpperCase()}] ${entry.source}` : undefined,
+        categoryHint: entry.level === "error" ? "cases" : "events",
+        importanceHint: levelToImportance(entry.level),
+        tags: ["log", entry.level, ...(entry.source ? [`module:${entry.source}`] : [])],
+        timestamp: entry.timestamp,
+        contentHash: createHash("sha256").update(line).digest("hex"),
+      });
+    }
+  }
+
+  const output: ConnectorOutputV1 = {
+    version: "connector-v1",
+    source: "logs",
+    scope: "ops:myapp",               // Customize: "project:xyz", "ops:production"
+    producedAt: new Date().toISOString(),
+    records,
+  };
+
+  console.log(JSON.stringify(output, null, 2));
+}
+
+main();

package/connectors/examples/rss-adapter.ts

@@ -0,0 +1,95 @@
+#!/usr/bin/env bun
+/**
+ * RSS Feed Connector Adapter (skeleton)
+ *
+ * Demonstrates how to produce a ConnectorOutputV1 JSON file from RSS/Atom
+ * feeds for RecallNest ingestion. Useful for tracking industry news,
+ * blog posts, and research updates.
+ *
+ * Usage:
+ *   bun run connectors/examples/rss-adapter.ts > rss-output.json
+ *   lm ingest --connector rss-output.json
+ *
+ * Customize:
+ *   1. Replace fetchFeed() with your RSS parsing library (e.g. rss-parser)
+ *   2. Adjust feed URLs and scope
+ *   3. Set categoryHint / importanceHint based on feed type
+ */
+
+import type { ConnectorOutputV1 } from "../../src/connector-types.js";
+import { createHash } from "node:crypto";
+
+// ---------------------------------------------------------------------------
+// TODO: Replace with real RSS/Atom parsing
+// ---------------------------------------------------------------------------
+
+interface FeedItem {
+  guid: string;
+  title: string;
+  content: string;        // HTML stripped to plain text
+  link: string;
+  pubDate: string;         // ISO 8601
+  categories?: string[];
+}
+
+interface FeedConfig {
+  url: string;
+  scope: string;           // e.g. "feeds:ai-news"
+  categoryHint?: string;
+  importanceHint?: number;
+}
+
+const FEEDS: FeedConfig[] = [
+  // Add your feeds here:
+  // { url: "https://example.com/feed.xml", scope: "feeds:example" },
+];
+
+async function fetchFeed(_url: string): Promise<FeedItem[]> {
+  // Example with rss-parser:
+  // import Parser from "rss-parser";
+  // const parser = new Parser();
+  // const feed = await parser.parseURL(url);
+  // return feed.items.map(item => ({ ... }));
+  return []; // Replace with real implementation
+}
+
+// ---------------------------------------------------------------------------
+// Transform → ConnectorOutputV1
+// ---------------------------------------------------------------------------
+
+async function main() {
+  for (const feed of FEEDS) {
+    const items = await fetchFeed(feed.url);
+
+    const output: ConnectorOutputV1 = {
+      version: "connector-v1",
+      source: "rss",
+      scope: feed.scope,
+      producedAt: new Date().toISOString(),
+      records: items.map((item) => ({
+        id: `rss:${createHash("md5").update(item.guid || item.link).digest("hex")}`,
+        text: item.content,
+        title: item.title,
+        categoryHint: feed.categoryHint ?? "knowledge",
+        importanceHint: feed.importanceHint ?? 0.6,
+        tags: [
+          "rss",
+          ...(item.categories ?? []),
+          `link:${item.link}`,
+        ],
+        timestamp: item.pubDate,
+        contentHash: createHash("sha256").update(item.content).digest("hex"),
+        sourceMetadata: {
+          feedUrl: feed.url,
+          link: item.link,
+          guid: item.guid,
+        },
+      })),
+    };
+
+    // Each feed outputs one JSON — pipe to separate files if needed
+    console.log(JSON.stringify(output, null, 2));
+  }
+}
+
+main().catch(console.error);

package/logs/daily-recall.log

@@ -28,3 +28,33 @@ Deleted  : 0
 Errors   : 0
 === 2026-04-12 08:00:13 daily-recall 结束 ===
 === 2026-04-12 08:00:13 daily-recall 结束 ===
+=== 2026-04-13 08:00:01 daily-recall 开始 ===
+=== 2026-04-13 08:00:01 daily-recall 开始 ===
+  今日主题 (#1): 成长 经历 改变了什么
+  今日主题 (#1): 成长 经历 改变了什么
+  检查 distill gate...
+  检查 distill gate...
+  distill gate: 
+  distill gate: 
+  执行 distill...
+  执行 distill...
+  distill 完成，31 行
+  distill 完成，31 行
+  [完成] 回顾已写入: /Users/anxianjingya/recallnest/daily-reflections/2026-04-13.md
+  [完成] 回顾已写入: /Users/anxianjingya/recallnest/daily-reflections/2026-04-13.md
+  执行 checkpoint-gc...
+  执行 checkpoint-gc...
+  checkpoint-gc: === Checkpoint GC ===
+
+Kept     : 218
+Archived : 0
+Deleted  : 0
+Errors   : 0
+  checkpoint-gc: === Checkpoint GC ===
+
+Kept     : 218
+Archived : 0
+Deleted  : 0
+Errors   : 0
+=== 2026-04-13 08:00:22 daily-recall 结束 ===
+=== 2026-04-13 08:00:22 daily-recall 结束 ===

package/logs/ingest-2026-04-13.log

@@ -0,0 +1,87 @@
+=== 2026-04-13 03:00:04 增量更新开始 ===
+[INFO] LLM client initialized: qwen-turbo @ https://dashscope.aliyuncs.com/compatible-mode/v1
+
+🔑 验证 Embedding API...
+  ✅ jina-embeddings-v5-text-small (1024d)
+  ✅ LLM: qwen-turbo (L0 摘要 + 语义去重)
+  ✅ 两阶段去重: vector + LLM 语义判断
+
+🔄 开始导入记忆 (source: all)...
+
+📝 导入 Claude Code 对话...
+[INFO] noise-filter: short boilerplate filtered: "收到！多路并行处理："
+  CC: 430/1002 files, 87 chunks ingested
+  CC: 680/1002 files, 217 chunks ingested
+  ✅ CC: 23 files, 378 ingested, 655 deduped (hard:67, exact:279, llm-skip:202, llm-merge:107), 0 errors
+🤖 导入 Codex 对话...
+  ✅ Codex: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+💎 导入 Gemini 对话...
+  ✅ Gemini: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+🖥️  导入 Claude Desktop 对话...
+  ✅ Desktop: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+📚 导入记忆文件...
+  ✅ Memory: 7 files, 26 ingested, 216 deduped (hard:1, exact:192, llm-skip:16, llm-merge:7), 0 errors
+
+📊 导入汇总:
+  总计: 404 chunks 已索引, 871 chunks 去重 (hard:68, exact:471, llm-skip:218, llm-merge:114), 0 errors
+
+=== 2026-04-13 03:13:05 增量更新完成 ===
+
+=== 2026-04-13 11:13:05 增量更新开始 ===
+[INFO] LLM client initialized: qwen-turbo @ https://dashscope.aliyuncs.com/compatible-mode/v1
+
+🔑 验证 Embedding API...
+  ✅ jina-embeddings-v5-text-small (1024d)
+  ✅ LLM: qwen-turbo (L0 摘要 + 语义去重)
+  ✅ 两阶段去重: vector + LLM 语义判断
+
+🔄 开始导入记忆 (source: all)...
+
+📝 导入 Claude Code 对话...
+  CC: 480/1006 files, 20 chunks ingested
+[INFO] noise-filter: denial pattern matched: "好，全文读完了。这篇文章标题是「Claude Code 省 Token 指南：慎用 1M 上下文，不开新会话或者总是开新..."
+  ✅ CC: 5 files, 130 ingested, 153 deduped (hard:14, exact:44, llm-skip:46, llm-merge:49), 0 errors
+🤖 导入 Codex 对话...
+[INFO] noise-filter: meta-question filtered: "# AGENTS.md instructions for /Users/anxianjingya
+
+<INSTRUCTI..."
+  Codex: 295/295 files, 2 chunks ingested
+  ✅ Codex: 1 files, 2 ingested, 1 deduped (hard:0, exact:0, llm-skip:0, llm-merge:1), 0 errors
+💎 导入 Gemini 对话...
+  ✅ Gemini: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+🖥️  导入 Claude Desktop 对话...
+  ✅ Desktop: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+📚 导入记忆文件...
+  ✅ Memory: 1 files, 1 ingested, 185 deduped (hard:0, exact:172, llm-skip:13, llm-merge:0), 0 errors
+
+📊 导入汇总:
+  总计: 133 chunks 已索引, 339 chunks 去重 (hard:14, exact:216, llm-skip:59, llm-merge:50), 0 errors
+
+=== 2026-04-13 11:19:05 增量更新完成 ===
+
+=== 2026-04-13 19:19:05 增量更新开始 ===
+[INFO] LLM client initialized: qwen-turbo @ https://dashscope.aliyuncs.com/compatible-mode/v1
+
+🔑 验证 Embedding API...
+  ✅ jina-embeddings-v5-text-small (1024d)
+  ✅ LLM: qwen-turbo (L0 摘要 + 语义去重)
+  ✅ 两阶段去重: vector + LLM 语义判断
+
+🔄 开始导入记忆 (source: all)...
+
+📝 导入 Claude Code 对话...
+  ✅ CC: 12 files, 193 ingested, 225 deduped (hard:19, exact:71, llm-skip:74, llm-merge:61), 0 errors
+🤖 导入 Codex 对话...
+  ✅ Codex: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+💎 导入 Gemini 对话...
+  ✅ Gemini: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+🖥️  导入 Claude Desktop 对话...
+  ✅ Desktop: 0 files, 0 ingested, 0 deduped (hard:0, exact:0, llm-skip:0, llm-merge:0), 0 errors
+📚 导入记忆文件...
+  ✅ Memory: 6 files, 16 ingested, 229 deduped (hard:0, exact:202, llm-skip:16, llm-merge:11), 0 errors
+
+📊 导入汇总:
+  总计: 209 chunks 已索引, 454 chunks 去重 (hard:19, exact:273, llm-skip:90, llm-merge:72), 0 errors
+
+=== 2026-04-13 19:27:06 增量更新完成 ===
+

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "recallnest",
-  "version": "2.2.1",
+  "version": "2.3.0",
   "description": "RecallNest \u2014 MCP-native, local-first memory search and distillation for AI conversations",
   "license": "MIT",
   "type": "module",

package/src/cli.ts

@@ -29,6 +29,8 @@ import {
   ingestCodexSessions,
   ingestGeminiSessions,
   ingestMarkdownFiles,
+  ingestObsidianVault,
+  ingestConnectorFile,
 } from "./ingest.js";
 import { runDoctor, formatDoctorResults } from "./doctor.js";
 import { persistCaseMemory, persistMemory, persistWorkflowPattern } from "./capture-engine.js";
@@ -1306,6 +1308,8 @@ program
   .option("--no-dedup", "跳过向量去重")
   .option("--no-llm", "禁用 LLM 提取（原始对话将跳过不存入，排入待处理队列）")
   .option("--recent [hours]", "快速模式：只处理最近 N 小时修改的文件（默认 2 小时），跳过 ingested-files 检查")
+  .option("--obsidian <vault-path>", "导入 Obsidian vault（自动检测 .obsidian/ 目录）")
+  .option("--connector <file-path>", "导入 connector-v1 格式 JSON 文件")
   .action(async (options) => {
     const config = loadConfig();
     const { store, embedder, llm } = createComponents(config);
@@ -1440,6 +1444,32 @@ program
       }
     }
 
+    // Obsidian vault (--obsidian <path>)
+    if (options.obsidian) {
+      console.log("🗃️  导入 Obsidian vault...");
+      const r = await ingestObsidianVault(store, embedder, options.obsidian, {
+        verbose,
+        noDedup,
+        llm: effectiveLlm,
+      });
+      results.push(r);
+      console.log(`  ✅ Obsidian: ${formatIngestSummary(r)}`);
+    }
+
+    // Connector-v1 file (--connector <path>)
+    if (options.connector) {
+      console.log("🔌 导入 connector-v1 文件...");
+      const { readFileSync: readFs } = await import("node:fs");
+      const connectorContent = readFs(options.connector, "utf-8");
+      const r = await ingestConnectorFile(store, embedder, connectorContent, {
+        verbose,
+        noDedup,
+        llm: effectiveLlm,
+      });
+      results.push(r);
+      console.log(`  ✅ Connector: ${formatIngestSummary(r)}`);
+    }
+
     // Summary
     console.log("\n📊 导入汇总:");
     let totalChunks = 0;

package/src/connector-types.ts

@@ -0,0 +1,57 @@
+/**
+ * Connector Standard Types (connector-v1)
+ *
+ * 定义外部数据源（Obsidian、Email、RSS、自定义脚本）统一产出的 JSON 格式。
+ * ingest.ts 的 ingestConnectorFile 消费这个格式，走已有的 dedup/extract/入库管线。
+ *
+ * 协议版本管理：version 字段用于未来兼容性。当前固定 "connector-v1"。
+ */
+
+export interface ConnectorOutputV1 {
+  /** 格式版本，固定 "connector-v1" */
+  version: "connector-v1";
+  /** 数据源标识，如 "obsidian", "email", "rss", "x-bookmarks" */
+  source: string;
+  /** 目标 scope，如 "vault:my-notes", "project:research" */
+  scope: string;
+  /** 批次 ID（可选，用于幂等重试） */
+  batchId?: string;
+  /** 产出时间 ISO 8601 */
+  producedAt: string;
+  /** 记录列表 */
+  records: ConnectorRecord[];
+}
+
+export interface ConnectorRecord {
+  /** 记录唯一 ID（source 内唯一，用于增量去重） */
+  id: string;
+  /** 正文 */
+  text: string;
+  /** 标题/heading（可选） */
+  title?: string;
+  /** 分类提示：preferences / events / knowledge / facts / decisions */
+  categoryHint?: string;
+  /** 重要性提示 0-1（可选，默认 0.7） */
+  importanceHint?: number;
+  /** 标签 */
+  tags?: string[];
+  /** 原始时间戳 ISO 8601 */
+  timestamp?: string;
+  /** 内容哈希（用于增量同步，调用方计算） */
+  contentHash?: string;
+  /** 来源元数据（自由字段） */
+  sourceMetadata?: Record<string, unknown>;
+}
+
+/** 运行时格式验证：判定一个 parsed JSON 是否是合法 connector-v1 */
+export function isConnectorOutputV1(value: unknown): value is ConnectorOutputV1 {
+  if (!value || typeof value !== "object") return false;
+  const obj = value as Record<string, unknown>;
+  return (
+    obj.version === "connector-v1"
+    && typeof obj.source === "string"
+    && typeof obj.scope === "string"
+    && typeof obj.producedAt === "string"
+    && Array.isArray(obj.records)
+  );
+}