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>

eslint.config.mjs

@@ -24,6 +24,12 @@ export default defineConfig(
       'react-refresh': eslintPluginReactRefresh
     },
     rules: {
+      'prettier/prettier': [
+        'error',
+        {
+          endOfLine: 'auto'
+        }
+      ],
       ...eslintPluginReactHooks.configs.recommended.rules,
       ...eslintPluginReactRefresh.configs.vite.rules
     }