fix: replace mutable default arguments with None in LLM chat models (#13513)

## Summary
- Replace `gen_conf={}` with `gen_conf=None` + guard in
`rag/llm/chat_model.py` (12 instances across Base, BaiChuanChat,
LocalLLM, MistralChat, ReplicateChat, BaiduYiyanChat, GoogleChat
classes)
- Replace `doc_ids=[]` with `doc_ids=None` + guard in
`api/db/services/document_service.py` (1 instance)
- Mutable default arguments are shared across all calls, causing
potential cross-request state contamination
- See Python docs:
https://docs.python.org/3/faq/programming.html#why-are-default-values-shared-between-objects

## Test plan
- [x] Verify LLM calls work with and without explicit gen_conf
- [x] No behavior change for existing callers — `None` is replaced with
`{}` at function entry

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-authored-by: Claude Opus 4.6 <noreply@anthropic.com>
Co-authored-by: Jin Hai <haijin.chn@gmail.com>
Co-authored-by: Yingfeng <yingfeng.zhang@gmail.com>
Co-authored-by: Kevin Hu <kevinhu.sh@gmail.com>

api/db/services/document_service.py

@@ -1007,11 +1007,13 @@ class DocumentService(CommonService):
             queue_tasks(doc, bucket, name, 0)
 
 
-def queue_raptor_o_graphrag_tasks(sample_doc, ty, priority, fake_doc_id="", doc_ids=[]):
+def queue_raptor_o_graphrag_tasks(sample_doc, ty, priority, fake_doc_id="", doc_ids=None):
     """
     You can provide a fake_doc_id to bypass the restriction of tasks at the knowledgebase level.
     Optionally, specify a list of doc_ids to determine which documents participate in the task.
     """
+    if doc_ids is None:
+        doc_ids = []
     assert ty in ["graphrag", "raptor", "mindmap"], "type should be graphrag, raptor or mindmap"
 
     chunking_config = DocumentService.get_chunking_config(sample_doc["id"])