From cd018814feba3fca3ac3d5f6beadb555fc272739 Mon Sep 17 00:00:00 2001
From: lanceyq <1982376970@qq.com>
Date: Fri, 10 Apr 2026 00:42:11 +0800
Subject: [PATCH] fix(memory): improve metadata language detection and
 clean_metadata logic

- Make MetadataExtractor language param optional (default None) to
  support auto-detection fallback when no language is explicitly set
- Refactor clean_metadata from walrus-operator dict comprehension to
  explicit loop for correctness and readability
---
 .../knowledge_extraction/metadata_extractor.py   | 10 +++++++---
 api/app/tasks.py                                 | 16 +++++++++++-----
 2 files changed, 18 insertions(+), 8 deletions(-)

diff --git a/api/app/core/memory/storage_services/extraction_engine/knowledge_extraction/metadata_extractor.py b/api/app/core/memory/storage_services/extraction_engine/knowledge_extraction/metadata_extractor.py
index 8b749c40..19f1e533 100644
--- a/api/app/core/memory/storage_services/extraction_engine/knowledge_extraction/metadata_extractor.py
+++ b/api/app/core/memory/storage_services/extraction_engine/knowledge_extraction/metadata_extractor.py
@@ -31,7 +31,7 @@ def _is_user_entity(ent: ExtractedEntityNode) -> bool:
 class MetadataExtractor:
     """Extracts user metadata from post-dedup graph data via independent LLM call."""
 
-    def __init__(self, llm_client, language: str = "zh"):
+    def __init__(self, llm_client, language: Optional[str] = None):
         self.llm_client = llm_client
         self.language = language
 
@@ -134,8 +134,12 @@ class MetadataExtractor:
         try:
             from app.core.memory.utils.prompt.prompt_utils import prompt_env
 
-            detected_language = self.detect_language(statements)
-            logger.info(f"元数据提取语言检测结果: {detected_language}")
+            if self.language:
+                detected_language = self.language
+                logger.info(f"元数据提取使用显式指定语言: {detected_language}")
+            else:
+                detected_language = self.detect_language(statements)
+                logger.info(f"元数据提取语言自动检测结果: {detected_language}")
 
             template = prompt_env.get_template("extract_user_metadata.jinja2")
             prompt = template.render(
diff --git a/api/app/tasks.py b/api/app/tasks.py
index 6fd5f8d6..9afb6225 100644
--- a/api/app/tasks.py
+++ b/api/app/tasks.py
@@ -3030,11 +3030,17 @@ def extract_user_metadata_task(
         # 4. 清洗元数据、覆盖写入元数据和别名
         def clean_metadata(raw: dict) -> dict:
             """递归移除空字符串、空列表、空字典。"""
-            return {
-                k: (cleaned if isinstance(v, dict) and (cleaned := clean_metadata(v)) else v)
-                for k, v in raw.items()
-                if not (v == "" or v == [] or (isinstance(v, dict) and not clean_metadata(v)))
-            }
+            result = {}
+            for k, v in raw.items():
+                if v == "" or v == []:
+                    continue
+                if isinstance(v, dict):
+                    cleaned = clean_metadata(v)
+                    if cleaned:
+                        result[k] = cleaned
+                else:
+                    result[k] = v
+            return result
 
         raw_dict = user_metadata.model_dump(exclude_none=True) if user_metadata else {}
         logger.info(f"[CELERY METADATA] LLM 输出完整元数据: {json.dumps(raw_dict, ensure_ascii=False)}")