mirror of
https://github.com/ErlichLiu/DeepClaude.git
synced 2026-04-25 05:05:57 +03:00
[GH-ISSUE #95] [Bug]: 非原生推理格式推理模型无法正常回复 #64
Labels
No labels
bug
documentation
duplicate
enhancement
good first issue
help wanted
invalid
pull-request
question
wontfix
No milestone
No project
No assignees
1 participant
Notifications
Due date
No due date set.
Dependencies
No dependencies set.
Reference
starred/DeepClaude#64
Loading…
Add table
Add a link
Reference in a new issue
No description provided.
Delete branch "%!s()"
Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?
Originally created by @yzlltyyh on GitHub (Mar 13, 2025).
Original GitHub issue: https://github.com/ErlichLiu/DeepClaude/issues/95
提交前确认
发生了什么?
使用不支持原生推理格式的deepseek模型时,会输出几个字,然后就停下,推测是由于max_token参数导致的问题
复现步骤
使用最新版deepclaude,使用不支持原生推理格式的deepseek作为推理模型。
@GowayLee commented on GitHub (Mar 14, 2025):
但是deepclaude并在发送请求时并没有设置max_tokens参数. 会不会是魔塔的api问题, 尝试使用一下其他供应商的看看
@yzlltyyh commented on GitHub (Mar 15, 2025):
使用的是提供商nebius的r1,测试了kluster的也不行🥲测试回退到上一个版本可以正常使用。
@yzlltyyh commented on GitHub (Mar 15, 2025):
看了看,应该是有设置max_token的耶
@GowayLee commented on GitHub (Mar 16, 2025):
确实......我们会再检查一下代码
@GowayLee commented on GitHub (Mar 16, 2025):
#64
@igeekbb commented on GitHub (Mar 16, 2025):
一样
@zzzh3ng commented on GitHub (Mar 16, 2025):
把/DeepClaude/app/clients/deepseek_client.py里面的max_tokens去掉,可以正常工作了。
@minghuayao81 commented on GitHub (Mar 17, 2025):
是的。
我测试的环境是dp+gemini。