fix: strip markdown code fences from LLM responses before json.loads

- glm-5.2 returns JSON wrapped in ```json ... ``` code fences
- Added fence stripping in services.py, query_understanding.py, jobs.py

app/plugins/builtins/unified_search/query_understanding.py

@@ -104,6 +104,12 @@ async def llm_analyze_query(
 
         response = await litellm.acompletion(**litellm_kwargs)
         content = response.choices[0].message.content
+        # Strip markdown code fences if present
+        content = content.strip()
+        if content.startswith("```"):
+            content = content.split("\n", 1)[-1] if "\n" in content else content[3:]
+        if content.endswith("```"):
+            content = content[:-3].strip()
         return json.loads(content)
     except Exception:
         logger.warning("LLM query analysis failed, using fallback", exc_info=True)
@@ -150,6 +156,12 @@ async def llm_aggregate_results(
 
         response = await litellm.acompletion(**litellm_kwargs)
         content = response.choices[0].message.content
+        # Strip markdown code fences if present
+        content = content.strip()
+        if content.startswith("```"):
+            content = content.split("\n", 1)[-1] if "\n" in content else content[3:]
+        if content.endswith("```"):
+            content = content[:-3].strip()
         return json.loads(content)
     except Exception:
         logger.warning("LLM result aggregation failed, using fallback", exc_info=True)