[错误]: LlamaCpp 和 LmStudio 登录时无法获取模型

QQ 错误描述

当与“LlamaCpp”或“LmStudio”供应商登录时,“forge”连接到后端,但由于一个明显的计划错误而未能分析返回的模型清单。

• 重现步骤

1. 运行 " /模式 "
2. 选择 " LlamaCpp " 或 " LmStudio " 作为提供者;或首次设置,或尝试选择已经设置的模型
3. `forge'试图以OpenAI兼容方式与供应商连接,但失败

• 预期行为

模型列表被正确解析( 因为我可以在服务器日志中看到数据被返回) 。

实际行为

我出错的有:

* [22:02:09] 错误:从OpenAI兼容供应商取出模型失败

原因是:
0: 模式响应去序列化失败
1: 获取 http://127. 0.0.1:8080/v1/models
2: 第1行第668行所缺的字段 " 模式 "

我使用LMStudio 0.4.16 (Build 2)和"LLaMA-server"版本:9601 (2c00efc).

< 细节> < summary > 一个实际的 LlamaCpp 模型端点响应 </ summary >

贾森 { "数据":[ { "id":"GLM-4.7-Flash-GGUF","G". "别名": [], "tags":[],,, "对象":"模",". "自有":"行马克普". "被创造":1781360984, (中文(简体) ). "状态":{ "值":"未载",". "ar":[ “/usr/bin/LLaMA-服务器”, " - - -host" " - -host", "127.0.0.1","12","0.0". "-端口", "0" "0" "0" (英语). "-i-mcp-代号", " - -别名" "GLM-4.7-Flash-GGUF","GLM-4.7-Flash-GGUF","GLM-4.7-Flash-GGUF","GLM-GUF","GLM-GUF","GLM-GLM-GUF","GLM-GUF","GLM-GUF","GLM-GUF","GLM-GUF","GLM-GUF","GLM-","GLM-GUF-",""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""""" "-ctx-尺寸", "一万三千" "一万三千" " - -型号", “/home/greg/.lmstudio/models/lmstudio-community/GLM-4.7-Flash-GGUF/GLM-4.7-Flash-Q4 K M.gguf”, "-平行", 1号 [ "预设":"[GLM-4.7-Flash-GGUF]\nui-mcp-prox=1\nctx-大小=135000\nmodel=/home/greg/.lmstudio/models/lmstudio-community/GLM-4.7-Flash-GGUF/GLM-4.7-Flash-Q4 K M.gguf\non-n-on-n" {\fn华文楷体\fs16\1cHE0E0E0} "建筑":{ "输入 模式":[ "文字" (中文(简体) ). [ "输出 模式":[ "文字" (中文(简体) ). [ . ] {\fn华文楷体\fs16\1cHE0E0E0} "需要下载":虚假 {\fn华文楷体\fs16\1cHE0E0E0} { "id":"Qune3.6-35B-A3B-GGUF","Q". "别名": [], "tags":[],,, "对象":"模",". "自有":"行马克普". "被创造":1781360984, (中文(简体) ). "状态":{ "价值":"载",". "ar":[ "(/usr/bin/LLaMA-server),". " - - -host" " - -host", "127.0.0.1","12","0.0". "-端口", "49759" (英语). "-i-mcp-代号", " - -别名" "Quen3.6-35B-A3B-GGUF","Q". "-ctx-尺寸", "一万三千" "一万三千" " - -型号", "/home/greg/.lmstudio/models/lmstudio-community/Qune3.6-35B-A3B-GGUF/Qune3.6-35B-A3B-Q8 0.gguf",. "--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------- "/home/greg/.lmstudio/models/lmstudio-community/Qwen3.6-35B-A3B-GGUF/mmproj-Qwen3.6-35B-A3B-BF16.gguf",. "-平行", 1号 [ "预设":"[出文3.6-35B-A3B-GGUF]\nui-mcp-proxy= 1\nctx-size=135000\nmodel= . . . . . . .