mirror of
https://wget.la/https://github.com/Wxw-Gu/WechatExplorer
synced 2026-08-21 21:47:00 +08:00
fix(ai): 让严格执行max_tokens的API恢复工作,如DeepSeek (#19)
* fix(ai): 让严格执行`max_tokens`的API恢复工作,如DeepSeek - AI 请求优先使用当前模型配置的`Max Tokens`,并依次回退到供应商高级设置的`Max Tokens`和默认值 4096 - 透传`OpenAI-compatible`与`Anthropic`的结束原因,补充`preload`类型声明 - 群日报生成和修复遇到模型异常结束生成时终止处理,并针对token上限给出配置提示 - 优化 AI 未返回有效内容时的错误信息 - 统一行尾配置 Signed-off-by: longhuan1999 <2114467924@qq.com> * Update .gitignore --------- Signed-off-by: longhuan1999 <2114467924@qq.com> Co-authored-by: qingmao <84499436+Wxw-Gu@users.noreply.github.com>
This commit is contained in:
Vendored
+2
-1
@@ -7,5 +7,6 @@
|
||||
},
|
||||
"[json]": {
|
||||
"editor.defaultFormatter": "vscode.json-language-features"
|
||||
}
|
||||
},
|
||||
"files.eol": "\n"
|
||||
}
|
||||
Reference in New Issue
Block a user