llama.cpp b11057 新增 Ling 3.0 专用解析器
原标题：b11057
AI 摘要
llama.cpp 发布 b11057 版本，新增针对 Ling 3.0（Bailing V3）的专用聊天解析器。由于 Ling 3.0 Flash 模板在生成提示中预先打开 think 块，模型不会输出起始 <think> 标签，且工具调用可能出现在 </think> 之前，导致原有自动解析器将工具调用误判为 reasoning_content，客户端收到空 content 且无 tool_calls，使 agent 循环中断。新解析器在 think 结束标签或 <tool_call> 起始处终止推理，并新增 Ling 3.0 Flash 聊天模板及多项测试。
正文节选
<details open> chat : add dedicated Ling 3.0 (Bailing V3) parser (#28682) * chat: add dedicated Ling 3.0 (Bailing V3) parser Ling 3.0 Flash templates pre-open the think block in the generation prompt, so the model never emits an opening <think>, and a tool call can arrive before any </think>. The generated autoparser terminated reasoning only at the close tag, which classified such tool calls entirely as reasoning_content: clients received content="" with no tool_calls and agent loops died as