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?

api/app/tasks/memoir_tasks.py

@@ -273,7 +273,6 @@ def process_memoir_segments(self, user_id: str, segment_ids: List[str]):
 
     try:
         with get_sync_db() as db:
-            chapters_to_enqueue: set[str] = set()
             # 获取段落
             stmt = select(Segment).where(Segment.id.in_(segment_ids))
             result = db.execute(stmt)
@@ -291,9 +290,24 @@ def process_memoir_segments(self, user_id: str, segment_ids: List[str]):
                 try:
                     from app.features.memory.service import ingest_transcript_sync
 
-                    ingest_transcript_sync(db, user_id, conv_id, transcript)
+                    source_id = ingest_transcript_sync(db, user_id, conv_id, transcript)
+                    logger.info(
+                        "event=memory_transcript_ingested user_id={} task_id={} "
+                        "source_id={} conversation_id={} transcript_chars={} "
+                        "segment_count={}",
+                        user_id,
+                        task_id,
+                        source_id,
+                        conv_id,
+                        len(transcript),
+                        len(segments),
+                    )
                 except Exception as e:
-                    logger.warning("Memory ingest 跳过: {}", e)
+                    logger.warning(
+                        "Memory ingest 跳过: {} exc_type={}",
+                        e,
+                        type(e).__name__,
+                    )
 
             llm = _get_llm()
             image_settings = MemoirImageSettings.from_env()
@@ -404,14 +418,32 @@ def process_memoir_segments(self, user_id: str, segment_ids: List[str]):
                 if try_enqueue_generate_chapter_cover(chapter_id, source="pipeline"):
                     logger.info(f"派发章节封面任务: chapter={chapter_id}")
 
-            logger.info(f"回忆录处理完成: user_id={user_id}, task_id={task_id}")
+            categories_processed = sorted(prepared.category_to_segments.keys())
+            logger.info(
+                "回忆录处理完成: user_id={} task_id={} segment_count={} "
+                "categories_processed={}",
+                user_id,
+                task_id,
+                len(segments),
+                categories_processed,
+            )
 
             # 更新任务状态为成功
             _update_task_status_sync(
-                user_id, task_id, "success", {"processed": len(segments)}
+                user_id,
+                task_id,
+                "success",
+                {
+                    "processed": len(segments),
+                    "categories_processed": categories_processed,
+                },
             )
 
-            return {"status": "success", "processed": len(segments)}
+            return {
+                "status": "success",
+                "processed": len(segments),
+                "categories_processed": categories_processed,
+            }
 
     except Exception as e:
         logger.error(f"回忆录处理失败: {e}")