feat(memory,conversation): 记忆富化/证据包、时间线幂等字段与对话分段全链路

数据库
- 新增迁移 0003：timeline_events.memory_source_id 外键 → memory_sources，便于按 ingest 源做时间线幂等

后端 - 记忆
- 新增 ingest 后 LLM 富化（摘要/事实/时间线），可配置开关与最大字符数
- 新增证据包组装：合并 chunk、摘要、事实、时间线、故事等检索结果；支持空 query 时是否仍带 rolling 等开关
- repo/retriever/service/router/schemas/summarizer/timeline/extractor 等扩展；文档 memory-retrieval.md 更新

后端 - 对话 WS
- 增加 PING/PONG；分段 ASR 日志与空音频处理；转写失败与「无助手回复」错误提示更明确
- 助手多段回复持久化使用统一分隔符，与分段逻辑一致

后端 - Agent
- reply_limits：按 [SPLIT] 与段落拆段，并保证非空 fallback，供 WS 与 TTS 多段下发

后端 - 回忆录任务
- transcript ingest 记录 source_id；任务成功结?

app-expo/tests/features/voice/recorder.test.ts

@@ -0,0 +1,51 @@
+/* eslint-disable import/first */
+
+import { Platform } from 'react-native';
+
+jest.mock('expo-audio', () => ({
+  AudioModule: { AudioRecorder: jest.fn() },
+  AudioQuality: {
+    HIGH: 'high',
+  },
+  IOSOutputFormat: {
+    MPEG4AAC: 'aac',
+  },
+}));
+
+import {
+  buildVoiceRecordingOptions,
+  VOICE_RECORDING_OPTIONS,
+} from '@/features/voice/recorder';
+
+describe('buildVoiceRecordingOptions', () => {
+  test('uses 16 kHz mono m4a recording options for Tencent-compatible speech capture', () => {
+    const passedOptions = buildVoiceRecordingOptions();
+
+    expect(passedOptions).toEqual(
+      expect.objectContaining({
+        extension: '.m4a',
+        sampleRate: 16_000,
+        numberOfChannels: 1,
+        bitRate: 32_000,
+      }),
+    );
+
+    if (Platform.OS === 'ios') {
+      expect(passedOptions).toEqual(
+        expect.objectContaining({
+          outputFormat: VOICE_RECORDING_OPTIONS.ios.outputFormat,
+          audioQuality: VOICE_RECORDING_OPTIONS.ios.audioQuality,
+        }),
+      );
+    }
+
+    if (Platform.OS === 'android') {
+      expect(passedOptions).toEqual(
+        expect.objectContaining({
+          outputFormat: VOICE_RECORDING_OPTIONS.android.outputFormat,
+          audioEncoder: VOICE_RECORDING_OPTIONS.android.audioEncoder,
+        }),
+      );
+    }
+  });
+});