- 更新日志(简体中文)
- Changelog(English)
What's Changed
重点更新
- 修复钉钉 Stream 任务异常退出后无法持续重连的问题，提升钉钉适配器长连接稳定性。(#8610)
- Dashboard 登录新增 TOTP 双因素认证。(#8189)
- Dashboard 侧边栏新增插件 WebUI 入口，并支持 MDI 图标；插件页面现在会同步 Dashboard 主题。(#8569, #8390)
- 优化未来任务 UI，提高 “创建任务” 的产品化程度。(#8559)
- 新增
/name命令用于命名 umo 且在 UI 中展示。 (#8575) - MiniMax Token Plan 支持动态获取模型列表，默认模型升级为 M3。(#8475, #8505)
- 优化上下文压缩，提高压缩质量和 KV-cache 命中率。(#8530, #8226)
修复
- 修复 Provider 统计遇到 SQLite lock 时未重试的问题。(commit)
- 修复空 modalities 被当作已配置能力，导致核心图片请求错误路由到视觉 fallback 的问题。(#8451)
- 修复 Reply 组件
toDict额外字段导致私聊消息发送失败的问题。(#8477) - 修复带 Reply 组件唤醒机器人且用户提示为空时的处理问题。(#8461)
- 修复 aiocqhttp 适配器无法解析语音的问题，并增加音频文件存在性检查。(#8523, #8529)
- 修复 OpenAI Embedding 在 SiliconFlow 非 Qwen embedding 模型上的无效参数问题。(#8508)
- 修复 Gemini Embedding 批量文本在
gemini-embedding-2上被折叠的问题。(#8537) - 修复 WeCom AI 消息链提取纯文本时的空白处理问题。(#8563)
- 修复 Dashboard 在 launcher 下运行时 frame 安全头过于严格的问题。(#8554)
- 修复控制台 pip 安装错误展示，改为使用 toast 提示。(#8462)
- 优化模板配置相关问题。(#8228)
优化与工程
- 增强 Reply 消息链对 Record 组件的处理。(#8527)
- Whisper STT 调用 OpenAI 转写接口后会关闭音频文件句柄。(#8528)
- 防止唤醒命令被记录为群聊上下文。(#8536)
- 修正中文文本中的 token 术语。(#8465)
- 更新 GitHub Actions 依赖。(#8533)
What's Changed (EN)
Highlights
- Fixed DingTalk Stream task recovery so the adapter keeps reconnecting after unexpected SDK task exits. (#8610)
- Added TOTP two-factor authentication for Dashboard login. (#8189)
- Added plugin WebUI entries to the Dashboard sidebar with MDI icon support, and synchronized Dashboard theme styling into plugin pages. (#8569, #8390)
- Added the future task UI and introduced
/namefor naming umo entries shown in the UI. (#8559, #8575) - MiniMax Token Plan can now fetch model lists dynamically, with the default model upgraded to M3. (#8475, #8505)
- Improved long-term memory and context compression quality, including better KV-cache hit rates. (#8530, #8226)
Bug Fixes
- Retried provider stats reads when SQLite is locked. (commit)
- Treated empty modalities as unconfigured so image requests do not incorrectly route to vision fallback. (#8451)
- Fixed private message sending failures caused by extra fields in Reply component
toDictoutput. (#8477) - Fixed waking the bot with a Reply component and an empty user prompt. (#8461)
- Fixed voice parsing in the aiocqhttp adapter and added an audio file existence check. (#8523, #8529)
- Fixed invalid OpenAI Embedding parameters for SiliconFlow non-Qwen embedding models. (#8508)
- Wrapped Gemini batch embedding texts in Content to avoid collapse on
gemini-embedding-2. (#8537) - Fixed whitespace handling when extracting plain text from WeCom AI message chains. (#8563)
- Relaxed Dashboard frame security headers when running under the launcher. (#8554)
- Displayed console pip-install errors with toast messages. (#8462)
- Optimized template config handling. (#8228)
Improvements and Maintenance
- Enhanced Reply chain handling for Record components. (#8527)
- Closed audio file handles after OpenAI transcription calls in Whisper STT. (#8528)
- Prevented wake commands from being recorded as group chat context. (#8536)
- Fixed Chinese token terminology. (#8465)
- Updated GitHub Actions dependencies. (#8533)
What's Changed
- Fix&Feat: Template config optimization by @Railgun19457 in #8228
- chore: fix token terminology in zh by @Rain-0x01-39 in #8465
- feat: dynamically fetch model list for MiniMax Token Plan via /v1/models API by @Blueteemo in #8475
- fix: waking bot with a reply component and empty user prompt by @lingyun14beta in #8461
- feat: add TOTP two-factor authentication for dashboard login by @Raven95676 in #8189
- fix(message): 修复 Reply 组件 toDict 方法输出多余字段导致私聊消息发送失败的问题 by @NayukiChiba in #8477
- fix(core): 将空 list modalities 视为未配置，修复图片无法传递到模型的问题 by @Sisyphbaous-DT-Project in #8451
- feat: upgrade MiniMax Token Plan default model to M3 by @octo-patch in #8505
- fix(console): use toast for pip-install error display by @xxynet in #8462
- fix(ltm): prevent wake commands from being recorded as group chat context by @RC-CHN in #8536
- fix: cannot resolve voice when using aiocqhttp adapter by @tjc6666666666666 in #8523
- chore(deps): bump docker/setup-qemu-action from 4.0.0 to 4.1.0 in the github-actions group by @dependabot[bot] in #8533
- Add check for audio file existence by @tjc6666666666666 in #8529
- perf(stt-whisper): close the audio file handle after calling the OpenAI transcription API by @tjc6666666666666 in #8528
- fix(openai-embedding): temporarily fix invalid paramater for SiliconFlow provider's non-Qwen embedding models by @Allenyou1126 in #8508
- fix(gemini-embedding): wrap batch embedding texts in Content to avoid collapse on gemini-embedding-2 by @Rat0323 in #8537
- fix(compress): improve context compression, improve kv-cache rate of context compression, handle compression model modalities by @Foolllll-J in #8530
- fix(dashboard): relax frame security headers when running under launcher by @lxfight in #8554
- feat: future task UI by @Soulter in #8559
- fix(wecomai_event): 修复消息链提取纯文本时的空白处理 by @NayukiChiba in #8563
- Enhance Reply chain handling for Record components by @tjc6666666666666 in #8527
- fix: retry provider stats on sqlite lock by @zouyonghe in #8574
- feat: introduce a command /name to name a umo, and display in ui by @Soulter in #8575
- feat: sync dashboard theme to plugin pages by @lxfight in #8390
- feat(dashboard): add plugin WebUI entries to sidebar with MDI icon support by @lxfight in #8569
- fix: keep DingTalk stream reconnecting by @Soulter in #8610
New Contributors
- @octo-patch made their first contribution in #8505
- @xxynet made their first contribution in #8462
- @Allenyou1126 made their first contribution in #8508
- @Rat0323 made their first contribution in #8537
Full Changelog: v4.25.2...v4.25.3