이전 버전입니다. 현재 최신 버전은 0.4.5입니다. TextLens 0.4.5 · 출시일:
설치 파일 0.4.2
| 아키텍처 | 형식 | 설치 범위 | 파일 크기 | 다운로드 | SHA256 |
|---|---|---|---|---|---|
| 64비트 | EXE (NSIS) | 현재 사용자 | — | github.com | VirusTotal |
링크와 SHA256은 Windows 패키지 관리자 커뮤니티 매니페스트에서 가져왔습니다. 실행하기 전에 다운로드한 파일의 해시를 비교해 보십시오.
릴리스 노트
- Improved selection capture and stability across macOS and Windows, including app-specific handling, ordered event processing, and more reliable recovery when the toolbar or settings renderer encounters an error.
- Prevented stale selections from reopening the toolbar. After an action, TextLens clears the highlight in the app that owns the selection; if the clipboard cannot be fully restored, temporary copying is skipped to protect images and other clipboard content.
- Rebuilt Settings into seven sections, added field-level error feedback and filter-tag editing, and made saving run in the background with backups. Testing a connection or fetching models now prompts you to save pending changes first.
- Added OpenAI Responses, Anthropic Messages, and Google Gemini protocols alongside OpenAI Chat Completions, with support for streaming and model discovery.
- Expanded translation to seven languages: Chinese, English, Japanese, Korean, Russian, German, and French. Added configurable default and target languages, automatic direction switching, and a control to swap translation direction.
- Added per-model thinking controls, including selectable thinking levels and an option to disable thinking when the model supports it. Models that require thinking use their minimum budget when thinking is turned off.
- Added five appearance themes and improved keyboard navigation and focus indicators across menus and controls. Ask AI results now copy the complete conversation transcript.
- Improved streaming responsiveness and input-limit handling. Diagnostic logs show selection length and a hash by default; text previews require explicit opt-in.
发布版本 0.4.2
- 提升 macOS 与 Windows 的划词捕获稳定性，优化应用适配与事件处理顺序，并改进工具栏或设置界面异常后的恢复。
- 改进旧选区判定，避免工具栏重复弹出；执行动作后清除选区所属应用中的高亮。剪贴板无法完整恢复时跳过临时复制，保护截图等内容。
- 设置页重构为七个分区，加入字段级错误提示和过滤标签编辑；设置保存改为后台处理并保留备份。测试连接或获取模型前，会提示先保存未提交的更改。
- 在 OpenAI Chat Completions 之外，新增 OpenAI Responses、Anthropic Messages 和 Google Gemini 协议支持，并支持流式输出与模型列表获取。
- 翻译扩展至中文、英语、日语、韩语、俄语、德语和法语；支持设置默认语言与目标语言、自动切换翻译方向，以及手动交换方向。
- 新增按模型配置思考强度，可选择思考档位；模型支持时可关闭思考。无法完全关闭思考的模型会使用最低预算。
- 新增五套外观主题，改进菜单与控件的键盘导航和焦点提示；复制问 AI 结果时会包含完整对话记录。
- 提升流式输出响应并完善输入限制。诊断日志默认只记录选区长度和哈希；文本预览需显式开启。
