Skip to content

Releases: nextai-translator/bob-plugin-openai-translator

v5.0.1

Choose a tag to compare

@github-actions github-actions released this 12 Aug 15:12

Preserve streamed provider errors and align API field heights

v5.0.0

Choose a tag to compare

@github-actions github-actions released this 24 Jul 02:49

主要变化

  • 配置精简为 API Key、模型和可选的完整 API URL,插件会根据模型和 URL 选择请求格式
  • Gemini 模型更新为 gemini-3.6-flashgemini-3.5-flash-lite
  • 推理设置改为“默认”和“关闭”,插件不再发送 temperature
  • 系统指令用于改变任务,用户指令用于补充术语、语气和格式要求
  • 修复流式响应、取消请求、空结果和 API 错误处理中的问题

升级说明

只填写 API Key 并使用默认模型的用户无需调整。使用旧 Gemini 选项或自定义 API 地址的用户,请重新检查模型与 API URL;完整请求 URL 需以 /responses/chat/completions 结尾。

配置示例见配置手册

v4.3.4

Choose a tag to compare

@github-actions github-actions released this 17 Jul 20:26

Update OpenAI model list and default to GPT-5.6 Luna

v4.3.3

Choose a tag to compare

@github-actions github-actions released this 04 Jun 04:47

Update model list and fix reasoning effort for GPT-5 pro models

v4.3.2

Choose a tag to compare

@github-actions github-actions released this 02 Apr 13:30

Fix reasoning effort being incorrectly sent to non-GPT models

v4.3.1

Choose a tag to compare

@github-actions github-actions released this 21 Mar 08:57

Add support for MiniMax

v4.3.0

Choose a tag to compare

@github-actions github-actions released this 18 Mar 15:16

What's Changed

  • Add GPT-5.4 series models (gpt-5.4, gpt-5.4-mini, gpt-5.4-nano)
  • Update default model from gpt-5-mini to gpt-5.4-mini
  • Fix reasoning.effort: 'minimal' error on GPT-5.4 models
  • Refactor reasoning effort handling with config table for easier maintenance
  • Set explicit reasoning.effort: 'medium' when thinking mode is enabled

v4.2.3

Choose a tag to compare

@github-actions github-actions released this 02 Jan 15:34

Reorder config options for better UX

v4.2.2

Choose a tag to compare

@github-actions github-actions released this 31 Dec 09:50

修复 non-streaming 下模型返回连续空行的问题

v4.2.1

Choose a tag to compare

@github-actions github-actions released this 18 Dec 16:29

Fix API error "Unsupported parameter: 'reasoning.effort' is not supported with this model" when using non-reasoning models