cherry-studio

AIAGPL-3.0

cherry-studio release notes.

Latest v2.0.14 · by cherry-studioWritten in TypeScriptWebsiteCherryHQ/cherry-studioRSS

Release activity

Release activity — 31 releases across 28 days since Apr 30, 2026. Each cell is one day; darker means more releases that day. Nothing is recorded before Apr 30, 2026. Older weeks are hidden at this screen width.
JunJulAugSep
Sunday1 release on May 31, 20261 release on Jun 7, 2026No releases on Jun 14, 2026No releases on Jun 21, 2026No releases on Jun 28, 20261 release on Jul 5, 2026No releases on Jul 12, 2026No releases on Jul 19, 2026No releases on Jul 26, 20261 release on Aug 2, 2026No releases on Aug 9, 2026No releases on Aug 16, 2026No releases on Aug 23, 2026No releases on Aug 30, 2026No releases on Sep 6, 2026No releases on Sep 13, 2026
MondayNo releases on Jun 1, 2026No releases on Jun 8, 2026No releases on Jun 15, 2026No releases on Jun 22, 2026No releases on Jun 29, 2026No releases on Jul 6, 2026No releases on Jul 13, 2026No releases on Jul 20, 20261 release on Jul 27, 20261 release on Aug 3, 20261 release on Aug 10, 20261 release on Aug 17, 20261 release on Aug 24, 2026No releases on Aug 31, 2026No releases on Sep 7, 2026No releases on Sep 14, 2026
Tuesday1 release on Jun 2, 2026No releases on Jun 9, 2026No releases on Jun 16, 2026No releases on Jun 23, 2026No releases on Jun 30, 2026No releases on Jul 7, 2026No releases on Jul 14, 2026No releases on Jul 21, 20262 releases on Jul 28, 20261 release on Aug 4, 2026No releases on Aug 11, 2026No releases on Aug 18, 2026No releases on Aug 25, 2026No releases on Sep 1, 20261 release on Sep 8, 2026No releases on Sep 15, 2026
WednesdayNo releases on Jun 3, 2026No releases on Jun 10, 2026No releases on Jun 17, 2026No releases on Jun 24, 2026No releases on Jul 1, 2026No releases on Jul 8, 2026No releases on Jul 15, 2026No releases on Jul 22, 20261 release on Jul 29, 20261 release on Aug 5, 2026No releases on Aug 12, 20261 release on Aug 19, 2026No releases on Aug 26, 2026No releases on Sep 2, 20261 release on Sep 9, 2026
ThursdayNo releases on Jun 4, 2026No releases on Jun 11, 2026No releases on Jun 18, 2026No releases on Jun 25, 2026No releases on Jul 2, 2026No releases on Jul 9, 2026No releases on Jul 16, 2026No releases on Jul 23, 2026No releases on Jul 30, 2026No releases on Aug 6, 20262 releases on Aug 13, 2026No releases on Aug 20, 2026No releases on Aug 27, 20261 release on Sep 3, 2026No releases on Sep 10, 2026
FridayNo releases on Jun 5, 2026No releases on Jun 12, 2026No releases on Jun 19, 2026No releases on Jun 26, 2026No releases on Jul 3, 2026No releases on Jul 10, 2026No releases on Jul 17, 20261 release on Jul 24, 20261 release on Jul 31, 20262 releases on Aug 7, 2026No releases on Aug 14, 2026No releases on Aug 21, 20261 release on Aug 28, 20261 release on Sep 4, 2026No releases on Sep 11, 2026
SaturdayNo releases on Jun 6, 2026No releases on Jun 13, 2026No releases on Jun 20, 2026No releases on Jun 27, 2026No releases on Jul 4, 2026No releases on Jul 11, 2026No releases on Jul 18, 2026No releases on Jul 25, 2026No releases on Aug 1, 2026No releases on Aug 8, 2026No releases on Aug 15, 2026No releases on Aug 22, 2026No releases on Aug 29, 2026No releases on Sep 5, 2026No releases on Sep 12, 2026

31 releases since Apr 30, 2026, busiest day 2

Changelog

What changed from 1 to 2

v2.0.14

Latest
Added 3
  • Agent sessions now label self-started replies with "Goal round N" for DSH goal continuations or "Continued after background work"
  • DeepSeek V4.1 Flash Expires-On-0910 vision model is now available in the catalog
  • Cloud sessions are now bound to the current computer, preserving free-grant history across credential resets
Changed 1
  • Knowledge page management dialogs and item detail panels are now loaded on demand instead of with the page
Fixed 14
  • Fixed Cherry Studio failing to start after an upgrade when the built-in Support Agent still needs to be created
  • Windows cleanup now tolerates transient DLL release failures after an inference utility process exits
  • Fixed tables from PDFs imported through Mistral OCR being dropped; table contents are now indexed as Markdown tables
  • Fix OpenCode Go/Zen requests failing with MissingSessionID by preserving the agent session header
  • Notion export now waits for the page body to be written and reports failed writes as errors instead of success
  • Fix invalid front matter when the note title contains ": " or starts with "#", and export tags as a proper YAML list

From cherry-studio

Downloads / 下载 (v2.0.14)
PlatformArchitectureGlobalChina Edition
Windowsx64Installer · PortableInstaller · Portable
Windowsarm64Installer · PortableInstaller · Portable
macOSApple M SeriesDMG · ZIPDMG · ZIP
macOSIntelDMG · ZIPDMG · ZIP
Linuxx64AppImage · DEB · RPMAppImage · DEB · RPM
Linuxarm64AppImage · DEB · RPMAppImage · DEB · RPM
Release Notes / 发布说明

Cherry Studio 2.0.14 - New Features, Fixes, and Performance

✨ New Features

  • [Agent] Agent sessions now label self-started replies — “Goal round N” for DSH goal continuations, or “Continued after background work” — so users understand why a new message appears.
  • [Models] DeepSeek V4.1 Flash Expires-On-0910 vision model is now available in the catalog.
  • [Cherry Cloud] Cloud sessions are now bound to the current computer, preserving free-grant history across credential resets.

🐛 Bug Fixes

  • [Startup] Fixed Cherry Studio failing to start after an upgrade when the built-in Support Agent still needs to be created.
  • [Local Models] Windows cleanup now tolerates transient DLL release failures after an inference utility process exits.
  • [Knowledge Base] Fixed tables from PDFs imported through Mistral OCR being dropped; table contents are now indexed as Markdown tables.
  • [Pi] Fix OpenCode Go/Zen requests failing with MissingSessionID by preserving the agent session header.
  • [Export] Notion export now waits for the page body to be written and reports failed writes as errors instead of success.
  • [Obsidian] Fix invalid front matter when the note title contains “: “ or starts with “#”, and export tags as a proper YAML list.
  • [Prompt Polish] Add cancellation and a 60-second timeout so stalled requests return to a retryable state.
  • [Chat] Show safe, actionable provider details instead of generic errors such as “400 null”.
  • [Debug] Fixed truncated Outputs and UI freezes when inspecting long streaming responses in the message debug panel (Call Chain).
  • [Provider] OpenCode Go/Zen requests from model health checks, topic naming, and context compaction now carry the required session header.
  • [Chat] Deleting a response selected for context now preserves other replies and transfers context and follow-up messages to an adjacent reply.
  • [Cherry Cloud] Unsupported client versions now show an update-required message instead of asking users to retry login.
  • [Chat] Fixed text-only continuation turns incorrectly processing stale image attachments and failing before the response starts.
  • [Cherry Cloud] Login now requires a configured client signing key for custom builds.

⚡ Performance

  • [Knowledge] Knowledge page management dialogs and item detail panels are now loaded on demand instead of with the page.

Cherry Studio 2.0.14 - 新功能、修复与性能优化

✨ 新功能

  • [智能体] 智能体会话现在为自动发起的回复添加标签——DSH 目标推进显示”目标推进 · 第 N 轮”，后台工作后继续显示”后台工作后继续”——让用户了解为什么出现了新消息。
  • [模型] DeepSeek V4.1 Flash Expires-On-0910 视觉模型现已上架模型目录。
  • [樱桃云] 云会话现已绑定当前设备，在凭证重置后保留免费额度历史。

🐛 问题修复

  • [启动] 修复升级后需要首次创建内置产品反馈 Agent 时 Cherry Studio 无法启动的问题。
  • [本地模型] 修复 Windows 下 inference utility process 退出后 DLL 短暂占用导致模型清理偶发失败的问题。
  • [知识库] 修复通过 Mistral OCR 导入的 PDF 表格丢失问题；表格内容现在以 Markdown 表格形式索引。请重新索引已有条目以获取表格内容。
  • [Pi] 修复 OpenCode Go/Zen 请求因 MissingSessionID 失败的问题，现已保留智能体会话头部。
  • [导出] Notion 导出现在等待页面正文写入完成，写入失败时正确报错而非显示成功。
  • [Obsidian] 修复笔记标题包含”: “或以”#”开头时导出无效前置数据的问题，并将标签导出为正确的 YAML 列表。
  • [提示词润色] 支持取消和 60 秒超时，卡住的请求可立即恢复为可重试状态。
  • [对话] 显示安全可操作的错误详情，而非”400 null”等通用错误。
  • [调试] 修复消息调试面板(Call Chain)中长输出被截断和 UI 卡死的问题。
  • [服务商] OpenCode Go/Zen 的模型健康检查、话题命名和上下文压缩请求现在携带必需的会话头部。
  • [对话] 删除用于上下文的回复时，现在保留其他回复，并将上下文和后续消息转移到相邻回复。
  • [樱桃云] 不支持的客户端版本现在显示更新提示，而非让用户重试登录。
  • [对话] 修复纯文本续写轮次错误处理残留图片附件并在响应开始前失败的问题。
  • [樱桃云] 自定义构建现在需要配置客户端签名密钥才能登录。

⚡ 性能优化

  • [知识库] 知识库页面管理对话框和条目详情面板现在按需加载，而非随页面加载。
What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.13...v2.0.14

View originalPermalink
How v2.0.14 went

v2.0.13

Added 7
  • Add GPT-6 Astra support with context limits, reasoning controls, Fast mode, native web search, tiered pricing, and the official model icon
  • Add TokenDance as a built-in model provider with browser-based API key authorization
  • Daily, weekdays, and weekly presets now support multiple times per day
  • Show topic and session titles, switch branches from the header, and export individual branches as Markdown
  • Add installed-skill source filters and a single/double-column layout switch in Skills settings
  • Management actions now stay in an accessible footer across prompts, skills, MCP, Notes, Knowledge Base, and toolbar customization
  • Add a configurable Ctrl+I / Cmd+I shortcut to focus the input in Composer
Changed 2
  • Message image export now uses Chromium's compositor for pixel-perfect output matching what you see on screen
  • Render streamed output with rich Markdown formatting in Translate
Fixed 10
  • Fix custom model providers that reject Cherry Studio's automatic attribution headers
  • Fix Moonshot Kimi K2.5+ requests failing when custom sampling settings are enabled
  • Fix Kimi K3 requests failing when an unsupported reasoning effort was selected
  • Profiles migrated from v1 now retain access to all providers and models regardless of the installed edition
  • Fix a topic permanently failing with a 400 error after a tool call when the provider returns a non-standard item id
  • Fix switching between multi-model answers while a response is streaming
Removed 1
  • Retire the Yi (01.AI) provider following its service shutdown

From cherry-studio

Downloads / 下载 (v2.0.13)
PlatformArchitectureGlobalChina Edition
Windowsx64Installer · PortableInstaller · Portable
Windowsarm64Installer · PortableInstaller · Portable
macOSIntelDMG · ZIPDMG · ZIP
macOSApple M SeriesDMG · ZIPDMG · ZIP
Linuxx64AppImage · DEB · RPMAppImage · DEB · RPM
Linuxarm64AppImage · DEB · RPMAppImage · DEB · RPM
Release Notes / 发布说明

Cherry Studio 2.0.13 - New Features, Fixes, and Improvements

✨ New Features

  • [Models] Add GPT-6 Astra support with context limits, reasoning controls, Fast mode, native web search, tiered pricing, and the official model icon.
  • [Models] Add TokenDance as a built-in model provider with browser-based API key authorization.
  • [Scheduled Tasks] Daily, weekdays, and weekly presets now support multiple times per day (e.g. 09:00 and 18:00).
  • [Chat] Show topic and session titles, switch branches from the header, and export individual branches as Markdown.
  • [Skills] Add installed-skill source filters and a single/double-column layout switch in Skills settings.
  • [Quick Panel] Management actions now stay in an accessible footer across prompts, skills, MCP, Notes, Knowledge Base, and toolbar customization.
  • [Composer] Add a configurable Ctrl+I / Cmd+I shortcut to focus the input.
  • [Image Export] Message image export now uses Chromium's compositor for pixel-perfect output matching what you see on screen.
  • [Translate] Render streamed output with rich Markdown formatting.

🐛 Bug Fixes

  • [Models] Fix custom model providers that reject Cherry Studio's automatic attribution headers.
  • [Models] Fix Moonshot Kimi K2.5+ requests failing when custom sampling settings are enabled.
  • [Models] Fix Kimi K3 requests failing when an unsupported reasoning effort was selected.
  • [Models] Retired the Yi (01.AI) provider following its service shutdown.
  • [Models] Profiles migrated from v1 now retain access to all providers and models regardless of the installed edition.
  • [Chat] Fix a topic permanently failing with a 400 error after a tool call when the provider returns a non-standard item id.
  • [Chat] Fix switching between multi-model answers while a response is streaming.
  • [Chat] Fix normal chat authentication errors failing to link to provider settings after automatic retries.
  • [Chat] Native web search citations returned by providers are now displayed in chat responses.
  • [Chat] Completed Agent sessions now show unavailable token usage instead of a misleading zero.
  • [Chat] Agent client-certificate authentication failures now show proxy and SSL recovery guidance.
  • [Chat] Claude Code Agent sign-in failures now link to the provider settings needed for recovery.
  • [Chat] Add a provider settings recovery action to generic HTTP 400 errors.
  • [Chat] Fix message quotes routing to the wrong window.
  • [Scheduled Tasks] Fixed the task run log losing its “view session” link when a scheduled agent run failed, timed out, or was cancelled.
  • [Agent] Fix taskless agents disappearing from the agent list when sessions are displayed on the right.
  • [Agent] Fix Bash tool failures labeled as errors instead of command output.
  • [Agent] Fix tool calls so repaired and replayed arguments keep their expected JSON shape.
  • [Agent] Restore Claude Code's repeat-command loop guard when RTK rewrites Bash commands.
  • [Agent] Prevent agents from modifying Cherry Studio user-data SQLite files through native tools.
  • [Agent] Claude Code process failures now show an actionable cause and diagnostic reference.
  • [Agent] The context-usage indicator now advances live during a task instead of only at completion.
  • [DeepSeek] DeepSeek Harness Web sessions now start correctly when the runtime requires its token-authenticated URL.
  • [Pi] Resume Pi tasks after context-clamped length responses with a bounded compact-and-retry attempt.
  • [OpenCode] OpenCode Go automatic conversation titles now preserve session identity.
  • [Context] Fixed the context compression model selector so users can switch back to “Follow current model”.
  • [Settings] Fix the provider model list freezing the app when a provider has many models.
  • [Settings] Fix Assistant settings breaking auto-save with unsafe Max tokens values.
  • [Settings] China-edition onboarding now uses CherryIN login by default again.
  • [Settings] AMD GPU Cloud no longer shows promotional “Free” or daily-credit messaging.
  • [Quick Assistant] Fix built-in selection quick actions to call MCP tools when a quickAssistant with MCP is configured.
  • [Translate] Fixed the copy button showing its feedback on the wrong pane.
  • [Translate] Fixed translation history stars opening details instead of toggling when activated with Enter or Space.
  • [Web Search] Keep valid Querit results when individual items omit optional metadata.
  • [Word Export] Word export now renders four-space-indented code blocks, numbered lists, image alt text, strikethrough, and fixes empty blockquote errors.
  • [Markdown] Horizontal scrollbars are now visible on overflowing content inside markdown.
  • [Browser MCP] Prevent hidden or inactive built-in browser pages from playing audible media.
  • [Backup] Fix misleading “Backup file format error” when restoring a backup created by a newer version.
  • [Backup] Fixed Qiniu Cloud S3 backup, restore, management, and retention cleanup when using regional endpoints.
  • [Region] Region-dependent routing now falls back to global endpoints when IP region detection fails instead of treating failure as mainland China.
  • [Region] Fix region detection reusing an in-flight request from a different proxy.
  • [Mini Apps] Fixed Mini Apps search failing to find apps by their translated display names.
  • [Mini Apps] Remove raw permission key tooltips that showed untranslated strings.
  • [Notes] Fixed note and folder rename fields closing before users could enter a new name.
  • [PDF Preview] Fixed PDF page input retaining an out-of-range number when submitting.
  • [Cherry Cloud] Bring Cherry Studio to the foreground after sign-in completes.
  • [Portable] Fix Windows portable deep links opening a second app instance that can lose packaged resources.
  • [Windows] Fix garbled localized default application names in the Open with menu.
  • [macOS] Repair macOS keychain signing.

💄 Improvements

  • [Image Generation] Disable automatic retries to avoid duplicate billable requests.
  • [Image Generation] Probe edit-only image models via edit mode.
  • [Agent Channels] Begin processing incoming messages after a one-second batching delay.

⚡ Performance

  • [Code Editor] CodeMirror theme catalog is now loaded only when a code editor is opened.
  • [HTML Artifacts] HTML artifact previews skip full-element layout sweeps for scrollable content.

Cherry Studio 2.0.13 - 新功能、修复与改进

✨ 新功能

  • [模型] 新增 GPT-6 Astra 支持，包括上下文限制、推理控制、快速模式、原生联网搜索、分层定价和官方模型图标。
  • [模型] 新增 TokenDance 内置模型服务商，支持浏览器 API 密钥授权。
  • [定时任务] 每天、工作日和每周预设现在支持每天多个时间点（如 09:00 和 18:00）。
  • [对话] 显示话题和会话标题，从标题栏切换分支，并将单个分支导出为 Markdown。
  • [技能] 技能设置中新增已安装技能来源过滤和单/双列布局切换。
  • [快捷面板] 管理操作现在固定在可访问的页脚，涵盖提示词、技能、MCP、笔记、知识库和工具栏自定义。
  • [输入框] 新增可配置的 Ctrl+I / Cmd+I 快捷键聚焦输入框。
  • [图片导出] 对话消息图片导出现在使用 Chromium 合成器，输出像素完美匹配屏幕显示。
  • [翻译] 翻译输出使用富 Markdown 格式渲染。

🐛 问题修复

  • [模型] 修复拒绝 Cherry Studio 自动归属头部的自定义模型服务商请求。
  • [模型] 修复启用自定义采样设置时 Moonshot Kimi K2.5+ 请求失败的问题。
  • [模型] 修复选择不支持的推理强度时 Kimi K3 请求失败的问题。
  • [模型] 因服务关闭，已停用零一万物 (Yi) 服务商。
  • [模型] 从 v1 迁移的配置文件现在无论安装版本如何都能访问所有服务商和模型。
  • [对话] 修复服务商返回非标准项目 ID 时工具调用导致话题永久 400 错误的问题。
  • [对话] 修复响应流式传输时切换多模型答案的问题。
  • [对话] 修复自动重试后普通对话认证错误无法链接到服务商设置的问题。
  • [对话] 服务商返回的原生联网搜索引用现在显示在对话响应中。
  • [对话] 完成的智能体会话现在正确显示不可用的令牌用量，而非误导性的零值。
  • [对话] 智能体客户端证书认证失败现在显示代理和 SSL 恢复指导。
  • [对话] Claude Code 智能体登录失败现在链接到恢复所需的服务商设置。
  • [对话] 为通用 HTTP 400 错误添加服务商设置恢复操作。
  • [对话] 修复消息引用路由到错误窗口的问题。
  • [定时任务] 修复定时智能体运行失败、超时或取消后任务运行日志丢失”查看会话”链接的问题。
  • [智能体] 修复会话显示在右侧时无任务智能体从列表消失的问题。
  • [智能体] Bash 工具失败现在正确标记为错误而非命令输出。
  • [智能体] 修复工具调用中修复和重放的参数保持预期的 JSON 格式。
  • [智能体] 恢复 RTK 重写 Bash 命令时的重复命令循环保护。
  • [智能体] 防止智能体通过原生工具修改 Cherry Studio 用户数据 SQLite 文件。
  • [智能体] Claude Code 进程失败现在显示可操作的成因和诊断参考。
  • [智能体] 上下文用量指示器现在在任务期间实时推进，而非仅在完成时更新。
  • [DeepSeek] 当运行时需要令牌认证 URL 时，DeepSeek Harness Web 会话现在正确启动。
  • [Pi] 上下文截断长度响应后通过有界压缩重试恢复 Pi 任务。
  • [OpenCode] OpenCode Go 自动对话标题现在保留会话身份。
  • [上下文] 修复上下文压缩模型选择器，用户可以切换回”跟随当前模型”。
  • [设置] 修复服务商模型数量较多时模型列表卡死界面的问题。
  • [设置] 修复不安全的 Max tokens 值导致助手自动保存失败的问题。
  • [设置] 中国版引导现在默认再次使用 CherryIN 登录。
  • [设置] AMD GPU Cloud 不再显示”免费”或每日积分促销信息。
  • [快捷助手] 修复配置 MCP 的快捷助手调用内置选择快捷操作时正确使用 MCP 工具。
  • [翻译] 修复复制按钮反馈显示在错误面板的问题。
  • [翻译] 修复使用 Enter 或 Space 激活翻译历史星标时打开详情而非切换的问题。
  • [联网搜索] Querit 单条结果缺少可选元数据时仍保留其他有效搜索结果。
  • [Word 导出] Word 导出现在正确渲染四空格缩进代码块、有序列表、图片替代文本、删除线，并修复空引用块错误。
  • [Markdown] Markdown 中溢出内容现在显示水平滚动条。
  • [浏览器 MCP] 防止隐藏或非活动的内置浏览器页面播放音频。
  • [备份] 修复从更新版本恢复备份时显示误导性的”备份文件格式错误”。
  • [备份] 修复使用区域或存储桶前缀端点时的七牛云 S3 备份、恢复、管理和保留清理。
  • [区域] IP 区域检测失败时，依赖区域的路由现在回退到全球默认端点，而非将失败视为中国大陆。
  • [区域] 修复区域检测复用来自不同代理的进行中请求。
  • [小程序] 修复小程序搜索无法按翻译后的显示名称查找应用的问题。
  • [小程序] 移除显示未翻译字符串的原始权限键工具提示。
  • [笔记] 修复笔记和文件夹重命名字段在输入前关闭的问题。
  • [PDF 预览] 修复 PDF 页码输入在最后一页提交时保留越界数字的问题。
  • [樱桃云] 登录完成后将 Cherry Studio 带到前台。
  • [便携版] 修复 Windows 便携版深度链接打开第二个应用实例导致丢失打包资源的问题。
  • [Windows] 修复”打开方式”菜单中本地化的默认应用程序名称显示乱码。
  • [macOS] 修复 macOS 钥匙串签名。

💄 改进

  • [图片生成] 禁用自动重试以避免重复计费请求。
  • [图片生成] 通过编辑模式探测仅编辑的图片模型。
  • [智能体通道] 现在在一秒批量延迟后开始处理传入消息。

⚡ 性能优化

  • [代码编辑器] CodeMirror 主题目录现在仅在打开代码编辑器时加载。
  • [HTML 产物] HTML 产物预览跳过可滚动内容的全元素布局扫描。
What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.12...v2.0.13

View originalPermalink
How v2.0.13 went

v2.0.12

Added 2
  • Settings now has a sidebar search to find any setting row across all sections with keyboard navigation
  • Translate model now has its own temperature, top-p and reasoning effort settings editable from the translation settings panel and translate page toolbar
Changed 4
  • Markdown previews outside chat now use the same rich renderer as chat messages
  • Workspace links in agent session messages and rendered artifact Markdown previews open files in the artifact pane and directories in the system file manager
  • Cherry Cloud models now honor server-declared capabilities and support configured OpenAI Chat Completions routes
  • Message token details now show time to first token without requiring the expanded runtime breakdown
Fixed 9
  • Preserve partial chat responses and show a clear retryable error when a provider stream ends without a finish reason
  • Fix middle-click autoscroll scrolling in the chat message list so it no longer vibrates or jumps
  • Sent image attachments now appear as compact filename chips with real image thumbnails including after reopening a conversation
  • Model health check results no longer linger after leaving the provider page
  • Allow grep searches in Filesystem MCP to use regular expression syntax supported by ripgrep
  • Empty knowledge bases now appear in the knowledge list

From cherry-studio

Downloads / 下载 (v2.0.12)
PlatformArchitectureGlobalChina Edition
Windowsx64Installer · PortableInstaller · Portable
Windowsarm64Installer · PortableInstaller · Portable
macOSIntelDMG · ZIPDMG · ZIP
macOSApple M SeriesDMG · ZIPDMG · ZIP
Linuxx64AppImage · DEB · RPMAppImage · DEB · RPM
Linuxarm64AppImage · DEB · RPMAppImage · DEB · RPM
Release Notes / 发布说明

Cherry Studio 2.0.12 - Features, Fixes, and Improvements

✨ New Features

  • [Settings] Settings gains a sidebar search: find any setting row across all sections (title/description/aliases, Chinese pinyin included), jump to it with scroll + highlight, full keyboard navigation.
  • [Settings] Settings search now covers all sections with static settings rows, including MCP tabs.
  • [Translation] The translate model now has its own temperature, top-p and reasoning effort settings, editable from the translation settings panel and the translate page toolbar.
  • [Markdown] Markdown previews outside chat now use the same rich renderer as chat messages. In agent session messages and rendered artifact Markdown previews, workspace links open files in the artifact pane and directories in the system file manager; relative links resolve from the agent workspace root.

🐛 Bug Fixes

  • [Cherry Cloud] Cherry Cloud models now honor server-declared capabilities, support configured OpenAI Chat Completions routes, and remain compatible with older model-list responses. Message token details now also show time to first token without requiring the expanded runtime breakdown.
  • [Chat] Preserve partial chat responses and show a clear, retryable error when a provider stream ends without a finish reason.
  • [Chat] Fix middle-click (autoscroll) scrolling in the chat message list so it no longer vibrates or jumps.
  • [Chat] Sent image attachments now appear as compact filename chips with real image thumbnails, including after reopening a conversation.
  • [Model Health] Model health check results no longer linger after leaving the provider page.
  • [Filesystem MCP] Allow grep searches to use regular expression syntax supported by ripgrep.
  • [Knowledge Base] Empty knowledge bases now appear in the knowledge list.
  • [Chat Export] Prevent fraction denominators from being clipped when exporting conversations as images.
  • [OpenClaw] Prevent the OpenClaw gateway from failing to start when Cherry Studio uses a socks5 proxy.
  • [Web Search] Web fetch no longer sends localhost, LAN, or locally-unresolvable URLs to Jina Reader when the built-in fetch fails, regardless of the “Allow fetching local network addresses” setting.
  • [Topics] Pinned topics and agent sessions now keep their text aligned with unpinned items in owner-grouped lists.
  • [Agent] The task progress capsule now always tracks the main agent's task plan; todo lists written by spawned subagents no longer replace it.
  • [Agent] Fixed the permission-mode popup showing two highlighted rows at once, and tooltips no longer pop up on their own when the panel opens.
  • [PDF Preview] Preserve colors in colored PDF documents.
  • [Models] Fix reasoning mode not being available for Xunfei MaaS (讯飞星辰) custom models — their model IDs are now recognized and expose the reasoning toggle/effort controls.
  • [UI] Improved Skills detail scrolling and Sidebar avatar and title-bar alignment.

💄 Improvements

  • [Input Fields] Number fields across settings, model options, MCP servers, assistants and painting parameters no longer show the browser's native spinner buttons, and no longer change value when the mouse wheel scrolls over a focused field. They step with the arrow keys, announce their allowed range to screen readers, and the API gateway port now tells you when a value is out of range instead of quietly applying a different one.

⚡ Performance

  • [Paintings] Improved painting history refresh performance by reusing unchanged hydrated records.

Cherry Studio 2.0.12 - 新功能、修复与改进

✨ 新功能

  • [设置] 设置侧边栏新增搜索功能：可搜索所有设置项（标题/描述/别名，支持中文拼音），点击跳转并高亮显示，支持完整的键盘导航。
  • [设置] 设置搜索现覆盖所有包含静态设置行的部分，包括 MCP 标签页。
  • [翻译] 翻译模型现在可以单独设置温度、Top-P 和推理强度，在翻译设置面板和翻译页工具栏均可调整。
  • [Markdown] 聊天外的 Markdown 预览现在使用与聊天消息相同的富渲染器。在智能体会话和渲染的产物 Markdown 预览中，工作区链接在产物面板中打开文件，目录在系统文件管理器中打开；相对链接从智能体工作区根目录解析。

🐛 问题修复

  • [樱桃云] 樱桃云模型现在遵循服务器声明的功能，支持配置的 OpenAI Chat Completions 路由，并与旧版模型列表响应保持兼容。消息令牌详情现在也显示首个令牌时间，无需展开运行时明细。
  • [对话] 当服务商流在没有结束原因的情况下终止时，保留部分对话响应并显示清晰的可重试错误。
  • [对话] 修复聊天消息列表中的中键自动滚动不再抖动或跳跃。
  • [对话] 发送的图片附件现在显示为紧凑的文件名芯片，带有真实的图片缩略图，包括重新打开对话后。
  • [模型健康] 离开服务商页面后，模型健康检查结果不再残留。
  • [文件系统 MCP] 允许 grep 搜索使用 ripgrep 支持的正则表达式语法。
  • [知识库] 空知识库现在显示在知识库列表中。
  • [对话导出] 防止导出对话图片时分数分母被裁剪。
  • [OpenClaw] 防止 Cherry Studio 使用 socks5 代理时 OpenClaw 网关启动失败。
  • [联网搜索] 当内置获取失败时，Web 获取不再将 localhost、局域网或本地无法解析的 URL 发送到 Jina Reader，无论”允许获取本地网络地址”设置如何。
  • [话题] 固定的话题和智能体会话现在在按所有者分组的列表中与未固定项目保持文本对齐。
  • [智能体] 任务进度胶囊现在始终跟踪主智能体的任务计划；子智能体编写的待办列表不再替换它。
  • [智能体] 修复权限模式弹出窗口同时显示两个高亮行的问题，工具提示不再在面板打开时自动弹出。
  • [PDF 预览] 在彩色 PDF 文档中保留颜色。
  • [模型] 修复讯飞星辰自定义模型无法使用推理模式的问题 —— 其模型 ID 现在被识别并显示推理开关/强度控制。
  • [界面] 改进技能详情滚动和侧边栏头像及标题栏对齐。

💄 改进

  • [输入字段] 设置、模型选项、MCP 服务器、助手和绘画参数中的数字字段不再显示浏览器的原生微调按钮，鼠标滚轮滚动聚焦字段时不再改变值。它们使用方向键步进，向屏幕阅读器宣布允许的范围，API 网关端口现在会告诉您值何时超出范围，而不是悄悄应用不同的值。

⚡ 性能优化

  • [绘画] 通过重用未更改的水合记录改进绘画历史刷新性能。
What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.11...v2.0.12

View originalPermalink
How v2.0.12 went

v2.0.11

Added 11
  • Sign in to Cherry Cloud for entitlement-aware Agent models, automatic local Gateway startup, quota-aware model selection, and durable Product Session handling
  • Configure the compression trigger threshold per assistant or globally in Settings
  • Improved installation and navigation for Mini Apps with drag-and-drop packages, stable tabs and icons, and transparent Translate and Painting views
  • Press Ctrl+A (Cmd+A on macOS) in the file list to select all files in the current view
  • Added an inline delete button to remove a message's translation in one click
  • Hide the chat assistant from the sidebar via Appearance Settings, and launch directly to the first visible sidebar app
Changed 5
  • Single-direction text translation now requires only a target language and starts without source-language detection
  • Confirm screenshot capture on double-click inside the selection rectangle
  • WebDAV backups now verify the server's TLS certificate by default with option to enable Allow Self-Signed Certificates
  • Web search now prefers model-native search by default, with automatic fallback to configured services
  • Improved PDF previews with selectable text, direct page jumps, and document outlines
Fixed 4
  • Pinned agent sessions now remain in their agent group and appear before unpinned sessions
  • Knowledge base and web search citations referenced again in a later turn now render as numbered citations and export correctly
  • Fixed markdown export with images: oversized embeds are skipped, folder-mode images are copied directly, and broken links are removed
  • Fixed the app freezing for seconds when removing all models of a provider on a large chat history

From cherry-studio

Downloads / 下载 (v2.0.11)
PlatformArchitectureGlobalChina Edition
Windowsx64Installer · PortableInstaller · Portable
Windowsarm64Installer · PortableInstaller · Portable
macOSx64DMG · ZIPDMG · ZIP
macOSarm64DMG · ZIPDMG · ZIP
Linuxx64AppImage · DEB · RPMAppImage · DEB · RPM
Linuxarm64AppImage · DEB · RPMAppImage · DEB · RPM
Release Notes / 发布说明

Cherry Studio 2.0.11 - Features, Fixes, and Improvements

✨ New Features

  • [Cherry Cloud] Sign in to Cherry Cloud for entitlement-aware Agent models, automatic local Gateway startup, quota-aware model selection, and durable Product Session handling.
  • [Context Management] Configure the compression trigger threshold per assistant or globally in Settings.
  • [Mini Apps] Improved installation and navigation with drag-and-drop packages, stable tabs and icons, and transparent Translate and Painting views.
  • [Translate] Single-direction text translation now requires only a target language and starts without source-language detection.
  • [Files] Press Ctrl+A (Cmd+A on macOS) in the file list to select all files in the current view.
  • [Translate] Added an inline delete button to remove a message's translation in one click.
  • [Sidebar] Hide the chat assistant from the sidebar via Appearance Settings, and launch directly to the first visible sidebar app.
  • [Agent] Added a global search action to the Agent conversation toolbar.
  • [Models] Add Hy4 Preview, Ling 3.0 Flash, and Qwen3.8 Flash support.
  • [Anthropic Cache] Anthropic-compatible providers can now keep prompt caches for 1 hour from API Settings.
  • [i18n] Added initial Turkish localization support across Cherry Studio.
  • [Screenshot] Confirm the capture on double-click inside the selection rectangle.

🐛 Bug Fixes

  • [Agent Sessions] Pinned agent sessions now remain in their agent group and appear before unpinned sessions.
  • [Citations] Knowledge base and web search citations referenced again in a later turn now render as numbered citations and export correctly.
  • [WebDAV] WebDAV backups now verify the server's TLS certificate by default. Enable “Allow Self-Signed Certificates” if your server uses a self-signed certificate.
  • [Web Search] Web search now prefers model-native search by default, with automatic fallback to configured services.
  • [Export] Fixed markdown export with images: oversized embeds are skipped, folder-mode images are copied directly, and broken links are removed.
  • [Backup] Shows the available disk space when a backup or restore fails because the disk is full.
  • [Chat] Fixed the app freezing for seconds when removing all models of a provider on a large chat history.
  • [PDF] Improved PDF previews with selectable text, direct page jumps, and document outlines.
  • [Thinking] Fixed thinking time restarting from 0 when switching tabs during streaming.
  • [Migration] Fixed v1-to-v2 migration so multi-model conversations preserve the response selected as context.
  • [Topics] Fixed a race where deleting the active conversation could leave the UI stuck on the deleted conversation.
  • [Topics] Keep pinned conversations inside their assistant group when conversations are grouped by assistant.
  • [Composer] Fixed the agent input box sometimes showing a raw knowledge-base prompt sentence after switching sessions.
  • [Composer] Long pasted text is pasted as plain text by default again; the “paste long text as file” toggle is back in Input Settings.
  • [Provider] Fixed custom request headers not being deletable in the provider request-configuration drawer.
  • [Provider] Fixed image generation icon not displaying for OpenRouter models with versioned GPT image IDs.
  • [Provider] Restored the Off reasoning option for optional OpenRouter reasoning models.
  • [Provider] Corrected reasoning-effort options for Qwen3.8 Flash and Max on DashScope Responses endpoint.
  • [Provider] Point the TokenHub “Get API key” link to the API Key management page.
  • [Models] Preserve Fireworks Kimi Fast and Turbo variants.
  • [Models] Fixed Kimi K2.5 and newer requests failing when assistant sampling settings were enabled.
  • [Chat] Fixed the inconsistent edit action on assistant messages so all assistant replies with text are uniformly editable.
  • [Chat] Fixed a race where switching the model from the conversation header could leave the next message routed to the previously selected model.
  • [Chat] Improved automatic conversation titles by requesting them in the selected language using an explicit language name.
  • [Chat] Citation markers that cannot be matched to a source are no longer shown as raw [cite:...] text in answers.
  • [Chat] Fixed scheduled task cards showing “Running” forever for runs that were cancelled before the app quit.
  • [Chat] Fixed the agent heartbeat toggle being ignored for agents migrated from v1.
  • [Chat] Fixed the right-side list opening at the same width as the left list and remembering its own width.
  • [Chat] Improved focus responsiveness in large Assistant and Agent resource selectors.
  • [Chat] Keep thinking elapsed stable across tab switches.
  • [Markdown] Fixed rendering of standalone LaTeX environments such as equation and aligned.
  • [Markdown] Fixed table columns keeping a stale fixed width after inserting or resizing columns in the notes editor.
  • [Mini Apps] Passing null options to chat or file export no longer rejects with an unexpected error.
  • [Mini Apps] Use a fixed 25px size for Mini App tab icons.
  • [Mini Apps] Managed DeepSeek Harness sessions no longer open the system browser when they start or restart.
  • [Mini Apps] Links inside unauthorized HTML artifact previews can no longer navigate the preview frame.
  • [MCP Browser] Restored MCP browser window controls and tab-bar actions on Windows.
  • [Knowledge] Reindex now re-acquires files from the real source.
  • [Files] Pasting multiple files into the composer no longer drops the remaining files when one fails to read.
  • [Painting] Fixed painting migrator leaving dangling model references that disabled the send button.
  • [Sidebar] New installs now open Agent first and place it before Chat; existing users keep their saved order.

⚡ Performance

  • [Export] Exporting or analyzing a long topic with many web/knowledge searches no longer slows down quadratically.
  • [File Preview] Improved file preview startup time by loading supported preview modules while file metadata is checked.

Cherry Studio 2.0.11 - 新功能、修复与改进

✨ 新功能

  • [樱桃云] 登录樱桃云获取权益感知的智能体模型、自动本地网关启动、配额感知的模型选择和持久的产品会话处理。
  • [上下文管理] 在设置中为每个助手或全局配置压缩触发阈值。
  • [小程序] 改进安装和导航，支持拖放包、稳定的标签和图标，以及透明的翻译和绘画视图。
  • [翻译] 单向文本翻译现在只需要目标语言，无需源语言检测即可开始。
  • [文件] 在文件列表中按 Ctrl+A（macOS 上为 Cmd+A）全选当前视图中的所有文件。
  • [翻译] 添加内联删除按钮，一键删除消息的翻译。
  • [侧边栏] 通过外观设置隐藏聊天助手，启动时直接打开第一个可见的侧边栏应用。
  • [智能体] 在智能体会话工具栏添加全局搜索操作。
  • [模型] 新增 Hy4 Preview、Ling 3.0 Flash 和 Qwen3.8 Flash 支持。
  • [Anthropic 缓存] Anthropic 兼容服务商现在可以从 API 设置中将提示缓存保持 1 小时。
  • [国际化] 在 Cherry Studio 中添加初始土耳其语本地化支持。
  • [截图] 在选择区域内双击确认截图。

🐛 问题修复

  • [智能体会话] 固定的智能体会话现在保留在其智能体组中，并显示在未固定会话之前。
  • [引用] 在后续对话中再次引用的知识库和网络搜索引用现在渲染为编号引用并正确导出。
  • [WebDAV] WebDAV 备份现在默认验证服务器的 TLS 证书。如果您的服务器使用自签名证书，请启用”允许自签名证书”。
  • [联网搜索] 联网搜索现在默认优先使用模型原生搜索，并自动回退到配置的服务。
  • [导出] 修复带图片的 Markdown 导出：跳过超大嵌入、直接复制文件夹模式图片、移除损坏的链接。
  • [备份] 当备份或恢复因磁盘已满而失败时显示可用磁盘空间。
  • [对话] 修复在大型对话历史中删除服务商的所有模型时应用卡顿数秒的问题。
  • [PDF] 改进 PDF 预览，支持可选文本、直接页面跳转和文档大纲。
  • [思考] 修复流式传输期间切换标签时思考时间从 0 重新开始的问题。
  • [迁移] 修复 v1 到 v2 迁移，使多模型对话保留上下文中选择的响应。
  • [话题] 修复删除活动对话可能导致界面卡在已删除对话上的竞争条件。
  • [话题] 按助手分组时，固定对话保留在其助手组中。
  • [输入框] 修复切回已挂载知识库的智能体会话时，输入框偶尔显示知识库提示词原文的问题。
  • [输入框] 长粘贴文本默认再次作为纯文本粘贴；”将长文本粘贴为文件”开关已恢复到输入设置中。
  • [服务商] 修复服务商请求配置抽屉中的自定义请求头无法删除的问题。
  • [服务商] 修复带有版本化 GPT 图像 ID 的 OpenRouter 模型不显示图像生成图标的问题。
  • [服务商] 恢复可选 OpenRouter 推理模型的 Off 推理选项。
  • [服务商] 修正百炼 Responses 接口上 Qwen3.8 Flash 和 Max 的推理强度选项。
  • [服务商] 将 TokenHub”获取 API 密钥”链接指向 API 密钥管理页面。
  • [模型] 保留 Fireworks Kimi Fast 和 Turbo 变体。
  • [模型] 修复开启助手采样设置时 Kimi K2.5 及更新模型请求失败的问题。
  • [对话] 修复助手消息编辑操作不一致的问题，使所有带文本的助手回复可通过”更多操作 → 编辑”统一编辑。
  • [对话] 修复从对话标题切换模型可能导致下一条消息路由到之前选择的模型的竞争条件。
  • [对话] 改进自动对话标题，使用显式语言名称按所选语言请求。
  • [对话] 无法匹配来源的引用标记不再显示为原始 [cite:...] 文本。
  • [对话] 修复定时任务卡片在应用退出前被取消的运行永远显示”运行中”的问题。
  • [对话] 修复从 v1 迁移的智能体的心跳开关被忽略的问题。
  • [对话] 右侧列表现在以与左侧列表相同的宽度打开，并记住自己的宽度。
  • [对话] 改进大型助手和智能体资源选择器中的焦点响应速度。
  • [对话] 保持思考时间在标签切换时稳定。
  • [Markdown] 修复独立 LaTeX 环境（如 equation 和 aligned）的渲染。
  • [Markdown] 修复在笔记编辑器中插入或调整列后表格列保持过时固定宽度的问题。
  • [小程序] 向聊天或文件导出传递 null 选项不再报意外错误。
  • [小程序] 使用固定的 25px 大小显示小程序标签图标。
  • [小程序] 托管的 DeepSeek Harness 会话在启动或重启时不再打开系统浏览器。
  • [小程序] 未授权的 HTML 产物预览中的链接不再能导航预览框架。
  • [MCP 浏览器] 恢复 Windows 上的 MCP 浏览器窗口控件和标签栏操作。
  • [知识库] 重建索引现在从真实来源重新获取文件。
  • [文件] 向输入框粘贴多个文件时，如果一个文件读取失败，不再丢弃其余文件。
  • [绘画] 修复绘画迁移器留下悬空模型引用导致发送按钮禁用的问题。
  • [侧边栏] 全新安装现在首先打开智能体并将其放在聊天之前；现有用户保持其保存的顺序。

⚡ 性能优化

  • [导出] 导出或分析包含多次网络/知识搜索的长话题不再二次方减慢。
  • [文件预览] 改进文件预览启动时间，在检查文件元数据的同时加载支持的预览模块。
What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.10...v2.0.11

View originalPermalink
How v2.0.11 went

v2.0.10

Added 1
  • Show run status on task cards for scheduled tasks
Changed 4
  • Parallelize independent config pipelines for improved performance
  • Parallelize device metadata reads for backup performance
  • Stabilize system prompt prefix in agent
  • Pace markdown renders and move one-shot highlights to the worker
Fixed 15
  • Repair literal autolinks that swallow emphasis markers in chat markdown
  • Resolve spell check real-time highlighting and multi-language issues
  • Polish subagent flow and running status
  • Register the portable Windows launcher at login
  • Refine skill icon styling
  • Anchor relative dates to runtime in web search

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.9...v2.0.10

View originalPermalink
How v2.0.10 went

v2.0.9

Added 5
  • Enable remote catalog hot-update without an app release in provider registry
  • Publish August 2026 privacy policy update
  • Restore Ctrl+L clear messages shortcut
  • Add model settings navigation in assistant settings
  • Pin assistants and agents to the sidebar
Changed 2
  • Unify declarative tool approval policy in agent runtime
  • Lazy-load disabled message outline in chat for performance
Fixed 13
  • Support valid GitHub SKILL.md links in skills
  • Send enable_thinking for Qwen on openai-compatible providers
  • Prevent pinning transient mini-apps in tabs
  • Resolve citations for third-party MCP tool outputs in pi-agent
  • Skip Anthropic tools without an input_schema in api-gateway
  • Only block skills on provable dependency gaps and split SkillService

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.8...v2.0.9

View originalPermalink
How v2.0.9 went

v2.0.8

Added 9
  • add skill global enablement controls
  • add floating task progress capsule to agents
  • add interactive screen capture with annotation and OCR
  • add TypeScript-guided code mode tools to pi-runtime
  • add layout-preserving PDF translation via BabelDOC
  • record translations in history and file manager for pdf-translation
Fixed 23
  • bind send_message anchors by their target subagent id in dsh-runtime
  • honor Cherry proxy environment in pi-runtime
  • terminate parse worker on terminal states in xlsx-preview
  • add horizontal padding and enable wrapping for text previews
  • keep macOS title-bar left inset when detached window is fullscreen
  • skip think:true for Ollama when SDK default triggers auto reasoning
Security 1
  • close four bypass gaps in existing guards including scheme checks, staging residue, and trace perms

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.7...v2.0.8

View originalPermalink
How v2.0.8 went

v2.0.7

Added 3
  • Add sidebar help and diagnostic upload to help-feedback
  • Add auto permission mode for pi agents and flatten the runtime picker
  • Integrate DeepSeek Harness in code-mate
Fixed 16
  • Prevent cross-size model matches in provider registry
  • Keep code fences when saving a conversation to a knowledge base
  • Skip in-flight items in bulk reindex for knowledge data source
  • Recreate session when deleting an agent's only non-active session
  • Remember the usage page's view selections
  • Restore 0.01 similarity-threshold precision in knowledge RAG
Removed 1
  • Retire the per-agent max_turns cap in agent configuration

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.5...v2.0.7

View originalPermalink
How v2.0.7 went

v2.0.5

Added 3
  • Add built-in support agent
  • Add app update notification preference
  • Install a skill from a GitHub SKILL.md URL
Changed 3
  • Reduce cold idle memory with lazy loading
  • Isolate log tab updates in MCP settings
  • Consolidate first-paint lazy loading in renderer
Fixed 18
  • Resolve prefixed size-colliding model ids to their own override
  • Synchronize pin changes across windows
  • Make cross-assistant topic moves atomic
  • Bound background memory usage from tab retention
  • Delete conversations past SQLite's cascade depth limit
  • Bound inactive conversation history cache

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.4...v2.0.5

View originalPermalink
How v2.0.5 went

v2.0.4

Added 6
  • Add back-to-top button and line-break mode to notes
  • Add delete impact preview to agent workspace
  • Add tab navigation shortcuts
  • Restore MCP-over-HTTP endpoints (/v1/mcps) in API gateway
  • Add opt-in MCP sessions with server-to-client push and progress in API gateway
  • Handle GROUP_MESSAGE_CREATE event with per-channel mention-only toggle for QQ channel
Changed 3
  • Serve the trace viewer incrementally and bound its retention
  • Virtualize large span trees in trace viewer
  • Route only PDFs through document processors in knowledge readers
Fixed 10
  • Sync tray-dependent preferences in settings
  • Propagate stream abort signal into in-flight MCP tool calls
  • Normalize legacy v1 MCP tool names before model replay
  • Block unreadable images for text-only models in chat attachments
  • Find deeply nested workspace file mentions in agent
  • Keep window shortcuts local in shortcut service

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.3...v2.0.4

View originalPermalink
How v2.0.4 went

v2.0.3

Added 8
  • Add smooth wheel control for reasoning effort in composer
  • Show assistant context usage in chat composer
  • Add Firecrawl as a URL fetch provider for web search
  • Write a new note straight into the knowledge base
  • Support scoped AGENTS.md instructions in agent runtime
  • Add Pi coding agent to Code Tools
  • Save edited user messages without resending in chat composer
  • Add Windows Terminal (wt.exe) support for external apps
Changed 1
  • Eliminate tab-switch IPC and re-render churn under Activity keep-alive in chat tabs
Fixed 12
  • Add sidebar management menu entry
  • Strip citation markers from IM replies in agent channels
  • Limit automatic naming to initial turn in agent session
  • Make the configured system prompt authoritative in agent
  • Preserve managed files for session history in agent attachments
  • Respect Linux default terminal in code CLI

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.2...v2.0.3

View originalPermalink
How v2.0.3 went

v2.0.2

Added 6
  • Persist empty branch nodes in chat branch
  • Built-in web search for DeepSeek, OpenRouter, and Dashscope with distinguishable resolved model names
  • Add selective cache and legacy data cleanup
  • Add Claude (Anthropic) conversation import support
  • Support detailed models through unified gateway in CLI config
  • Allow rerunning v1 migration in data migration
Changed 2
  • Skip redundant re-show work in message tools, artifact pane, and trace page
  • Make ProxyService own worker routing policy
Fixed 11
  • Reap SDK CLI subprocesses on shutdown in claude-code
  • Raise the default tool-call round cap
  • Close the snapshot-to-stream delivery gap in directory-tree
  • Allow direct upgrades to v2.0.x in v2 migration
  • Open image tokens in shared preview in composer
  • Start WeChat QR login in agent channels

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.1...v2.0.2

View originalPermalink
How v2.0.2 went

v2.0.1

Added 7
  • Enable drag reorder for assistant groups
  • Add 'embedding' endpoint type for NEWAPI model configuration
  • Keep the create row visible while searching in conversation picker
  • Support built-in web search for DeepSeek
  • Show settings as a focused tab in tab bar
  • Draw a Chrome-style divider between adjacent tabs in tab bar
  • Read binary office documents through anydoc in knowledge readers
Changed 1
  • Reduce renderer loading work in agent session
Fixed 34
  • Localize workspace tree errors in agent files
  • Use preset append mode for agent prompts in claude-code
  • Serve DeepSeek V4 models over the Anthropic endpoint
  • Recover stale dashboards across windows in openclaw
  • Prevent reference context leaks in collapsed previews
  • Normalize no-prefill agent requests in API gateway
Security 1
  • Address high and critical security advisories

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0...v2.0.1

View originalPermalink
How v2.0.1 went

v2.0.0

Added 6
  • Support for both OpenAI and Anthropic endpoints
  • Built-in core Agent runtime, reducing dependency installation and environment setup
  • Agents can read and maintain knowledge bases
  • Multi-window and split-view layouts for multitasking
  • One-click previews of agent results
  • One-click model service configuration for Claude Code, Codex, and more in Code Mate
Changed 4
  • Upgraded interactions and visual design for chats, roles, projects, and tasks
  • Code tools upgraded to Code Mate
  • Image generation now dynamically shows available parameters for each model
  • Data foundation upgraded for responsiveness with extensive history
Fixed 2
  • Improved scrolling performance in very long conversations
  • Large-folder imports no longer block the interface

From cherry-studio

Cherry Studio 2.0.0 - A New AI Workspace, from Chat to Getting Work Done

✨ New Interface, New Experience

  • Upgraded interactions and visual design make chats, roles, projects, and tasks clearer and easier to organize
  • Built for multitasking, with multi-window and split-view layouts for switching between work and reviewing progress and deliverables

🤖 More Powerful Agents

  • Supports both OpenAI and Anthropic endpoints, reuses Claude and Codex subscriptions, and works with more models
  • The core Agent runtime is built in, greatly reducing dependency installation and environment setup
  • Complete research, documents, presentations, data analysis, and coding faster, with one-click previews of results

🛠️ More Tool Upgrades

  • Agents can read and maintain knowledge bases, helping your knowledge grow continuously like a Wiki
  • Code tools are upgraded to Code Mate, with one-click model service configuration for Claude Code, Codex, and more
  • Image generation dynamically shows the parameters available for each model, making results easier to control

⚡ Performance

  • A fully upgraded data foundation stays responsive even with extensive history
  • Smoother scrolling in very long conversations, while large-folder imports no longer block the interface
View originalPermalink
How v2.0.0 went

v2.0.0-rc.5

Pre-release
Added 4
  • Refine anchor navigation into a minimal tick rail
  • Add save-as actions to image preview
  • Download local embedding model in background for knowledge
  • Add built-in Cherry tool guide for agent skills
Fixed 16
  • Enable Gemma 4 thinking in Ollama
  • Preserve streamed code block identity
  • Avoid false failure toast after successful agent pin
  • Preserve snake_case custom parameters in AI provider
  • Settle interrupted block animations in message rendering
  • Restore GitHub alert styling in markdown

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-rc.4...v2.0.0-rc.5

View originalPermalink
How v2.0.0-rc.5 went

v1.9.13

Added 3
  • Support LongCat 2.0 thinking for models
  • Add support for doubao-seed-2-1 and doubao-seed-evolving models
  • Support PowerShell fallback on Windows for agents
Changed 1
  • Use managed release service for updater
Fixed 8
  • Correct misclassifications in AI diagnosis and surface provider error JSON
  • Prevent renderer OOM during long streaming responses
  • Use v1beta for NewAPI Gemini endpoints
  • Update CherryIN website and OAuth domains
  • Send rewritten search prompt as user content
  • Load history when message lists are underfilled
  • Wire Ctrl+F in-chat search in AgentChat
  • Preserve authorization headers in copilot

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.12...v1.9.13

View originalPermalink
How v1.9.13 went

v2.0.0-rc.4

Pre-release
Added 10
  • Add bounded chunk reads for file IPC
  • Allow changing the default endpoint in provider settings
  • Add Radeon Cloud integration
  • Show folder import copy progress in knowledge
  • Restore inline web search and knowledge base citations in chat
  • Support DeepSeek V4 Flash Responses API in provider registry
Fixed 10
  • Unify file and artifact preview routing
  • Stop defaulting new agents to auto in permission mode
  • Distinguish mini app launchpad icon from window pin
  • Reset stale filesystem targets in agent migration
  • Sync multi-model context selection in chat
  • Keep the mode warning out of single-line rows in agent permission mode

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-rc.3...v2.0.0-rc.4

View originalPermalink
How v2.0.0-rc.4 went

v2.0.0-rc.3

Pre-release
Added 7
  • Add aria-labels and tooltips to page-zoom buttons
  • Add shared group creation dialog
  • Restore isolated inline HTML previews
  • Persist reasoning effort
  • Improve migration failure recovery
  • Add provider-aware speed controls
  • Add interactive link tokens
Changed 1
  • Reduce Agent session startup latency
Fixed 14
  • Hide injected knowledge prompts
  • Use readable names for saved messages
  • Keep dialog open and report failure on empty title in obsidian-export
  • Render absolute OpenAPI server URL for curl examples
  • View a note's original content on primary click
  • Drop the uri format that strict providers reject

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-rc.2...v2.0.0-rc.3

View originalPermalink
How v2.0.0-rc.3 went

v2.0.0-rc.2

Pre-release
Added 3
  • Restore clear-context boundaries in chat context
  • Serve Claude Opus 5, Sonnet 5, and 1M-context variants on Claude Code in provider registry
  • Add select all to note import in knowledge
Fixed 15
  • Preserve model endpoint routing during data migration
  • Preserve workspace and Claude session continuity during agent migration
  • Name per-item history star buttons after the favourite action in translate
  • Only autofocus the editor for empty notes
  • Clear empty MCP environment fields in settings
  • Stop table-recreate migrations from silently deleting child rows in database migrations

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-rc.1...v2.0.0-rc.2

View originalPermalink
How v2.0.0-rc.2 went

v2.0.0-rc.1

Pre-release
Added 4
  • Select knowledge bases from the input in agent composer
  • Sync skill catalog from disk so authored skills appear in agent skills
  • Warn before contextual model switches in agent chat
  • Add cost analytics and durable usage records in AI usage
Fixed 16
  • Allow selecting Markdown files from import hint in notes
  • Filter non-chat model choices in onboarding
  • Include sqlite-vec in portable Windows builds
  • Stabilize topic and session image export in message capture
  • Install both CPU architectures so x64 macOS builds ship sharp
  • Preserve migrated custom apps and icon sizing in mini-app

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-beta.3...v2.0.0-rc.1

View originalPermalink
How v2.0.0-rc.1 went

v2.0.0-beta.3

Pre-release
Added 4
  • Add managed CLI discovery and installation for agent-cli
  • Show client ID in developer mode in system-settings
  • Mask API key and Authorization Header with a reveal toggle in api-gateway
  • Offer a v1 download when a retried migration fails again
Changed 3
  • Disable model thinking for translation when supported
  • Pass model contextWindow as num_ctx in Ollama API requests
  • Rename Code Switch across locales
Fixed 13
  • Validate renderer URL origins in window navigation
  • Keep AskUserQuestion interactive in claude-code
  • Create channels inactive so credential-gated types can be added
  • Keep empty skills identity stable while the query loads
  • Refine global-search reveal and composer toolbar behavior
  • Stabilize streamed process history in message-renderer

From cherry-studio

[!WARNING] This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.

此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-beta.2...v2.0.0-beta.3

View originalPermalink
How v2.0.0-beta.3 went

v2.0.0-beta.2

Pre-release
Added 9
  • Unify collection empty states with v1-style illustrations
  • Clearer stream-status indicators and awaiting-approval badge in session list
  • Enable transparent windows by default on macOS
  • Add copy action to span details in trace
  • Warmer runtime copy and rolling reasoning preview in agent message
  • Reference topics and sessions as @ mention context tokens in composer
Changed 1
  • Adopt Chrome-style tab context menu and close behavior
Fixed 10
  • Accept nullable Bocha response fields in web search
  • Make read_file offset/limit schema Gemini-compatible in builtin tools
  • Delay conversation link preview cards in chat
  • Identify models in multi-model replies
  • Localize initial agent name for Chinese systems in cherry assistant
  • Constrain opacity slider height in selection assistant

From cherry-studio

[!WARNING] This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.

此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v2.0.0-beta.1...v2.0.0-beta.2

View originalPermalink
How v2.0.0-beta.2 went

v2.0.0-beta.1

Pre-release
Added 7
  • Upgraded interface with new interactions and visual design for chats, roles, projects, and tasks
  • Multi-window and split-view layouts for multitasking and switching between work and reviewing progress
  • Support for both OpenAI and Anthropic endpoints
  • Built-in Agent runtime core, reducing dependency installation and environment setup
  • Agents can read and maintain knowledge bases
  • Code tools upgraded to Code Mate with one-click model service configuration
  • Image generation dynamically shows parameters available for each model
Changed 1
  • Data foundation upgraded for improved responsiveness with extensive history
Fixed 2
  • Smoother scrolling in very long conversations
  • Large-folder imports no longer block the interface

From cherry-studio

[!WARNING] This Beta is not stable and is intended for testing only. Do not use it as a replacement for Cherry Studio v1. Data created by v2 may be cleared in later Beta releases or the final v2 release.

此 Beta 版本尚不稳定，仅供测试使用，请勿将其作为 Cherry Studio v1 的替代版本。v2 产生的数据可能会在后续 Beta 版本或 v2 正式版发布时被清除。

Cherry Studio 2.0.0-beta.1 - A New AI Workspace, from Chat to Getting Work Done

✨ New Interface, New Experience

  • Upgraded interactions and visual design make chats, roles, projects, and tasks clearer and easier to organize
  • Built for multitasking, with multi-window and split-view layouts for switching between work and reviewing progress and deliverables

🤖 More Powerful Agents

  • Supports both OpenAI and Anthropic endpoints, reuses Claude and Codex subscriptions, and works with more models
  • The core Agent runtime is built in, greatly reducing dependency installation and environment setup
  • Complete research, documents, presentations, data analysis, and coding faster, with one-click previews of results

🛠️ More Tool Upgrades

  • Agents can read and maintain knowledge bases, helping your knowledge grow continuously like a Wiki
  • Code tools are upgraded to Code Mate, with one-click model service configuration for Claude Code, Codex, and more
  • Image generation dynamically shows the parameters available for each model, making results easier to control

⚡ Performance

  • A fully upgraded data foundation stays responsive even with extensive history
  • Smoother scrolling in very long conversations, while large-folder imports no longer block the interface
View originalPermalink
How v2.0.0-beta.1 went

v1.9.12

Added 1
  • Add Kimi K2.7 Code support
Changed 1
  • Redirect provider links to inferera and follow configured base URL in aihubmix
Fixed 16
  • Forward DeepSeek V4+ reasoning_effort for openai-compatible providers
  • Support Claude Fable series and Opus 5 in capability detection
  • Add Anthropic native /v1/models fetcher
  • Prevent AccordionTrigger toggle when clicking approval buttons in collapsed group header
  • Use anthropicApiHost for NewAPI provider's anthropic endpoint
  • Inject Cherry Studio identity headers into agent mode requests

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.11...v1.9.12

View originalPermalink
How v1.9.12 went

v1.9.11

Added 2
  • Add MiniMax M3 thinking process support
  • Support Anthropic Opus 4.8 adaptive thinking
Changed 1
  • Use openPath instead of openExternal for HTML artifacts external browser
Fixed 8
  • Encode gemini model list API key
  • Infer custom provider model groups
  • Clean up agent session messages on delete
  • Fix oversized text in Gemini mini-program due to Electron UA detection
  • Avoid embedding dimensions request parameter
  • Bind CherryIN OAuth flow to sender
  • Upgrade mermaid to 11.15.0 to fix CJK parsing error in flowcharts
  • Fix agent task completed but task list still shows unchecked items
Removed 1
  • Prune legacy MiniMax models, keeping only M2.7 and M3

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.9...v1.9.11

View originalPermalink
How v1.9.11 went

v1.9.9

Added 1
  • Add MiniMax M3 to the system model registry
Fixed 2
  • Guard OV OCR availability CPU detection
  • Respect topic naming setting for agent sessions

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.8...v1.9.9

View originalPermalink
How v1.9.9 went

v1.9.8

Changed 1
  • Update tool components for improved styling and functionality
Fixed 1
  • Add v1 branch to workflow triggers

From cherry-studio

What's Changed

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.7...v1.9.8

View originalPermalink
How v1.9.8 went

v1.9.7

Added 1
  • Support StepFun as Anthropic-compatible provider
Changed 1
  • Change Gemini Safety Settings to BLOCK_NONE
Fixed 17
  • Clarify OpenClaw external install prompt
  • Support Grok 4.3 reasoning effort in xAI responses
  • Keep light theme tokens readable in code view
  • Apply [1m] context suffix for DeepSeek V4 Flash and MiMo V2.5+ in claudecode
  • Pass custom headers to claude code in agents
  • Launch opencode from package-local executable

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.6...v1.9.7

View originalPermalink
How v1.9.7 went

v1.9.6

Fixed 17
  • Preserve HTTP URLs in knowledge base documents
  • Thread idle timeout handle to stream chunk adapter
  • Improve GitCode sync reliability
  • Convert assistant image blocks to base64 for multi-turn editing
  • Invalidate provider cache on settings changes
  • Recognize ctrl by uniKey value

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.5...v1.9.6

View originalPermalink
How v1.9.6 went

v1.9.5

Added 3
  • Add timeout_minutes parameter to cron tool
  • Support Claude Opus 4.7
  • Add gpt-image-2 to AiHubMix provider painting module
Changed 1
  • Update DeepSeek default models to V4
Fixed 15
  • Prevent empty activeTools when web search is the only tool
  • Fix vertex model list fetch and improve service account setup
  • Prevent outer scrolling in horizontal multi-model layout
  • Use enable_thinking param for SiliconFlow DeepSeek/Zhipu models when reasoning_effort is none
  • Bypass @ai-sdk/gateway schema for Vercel model listing
  • Strip trailing /v1 from Anthropic SDK baseURL
Security 1
  • Sanitize subprocess call in run_eval.py

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.4...v1.9.5

View originalPermalink
How v1.9.5 went

v1.9.4

Added 3
  • Add DeepSeek V4+ model support with reasoning effort
  • Add MiMo V2.5 model support
  • Add vision and reasoning_effort support for mistral-small-2603
Changed 2
  • Forward reasoning effort for DeepSeek V4+ via Claude endpoint
  • Disable temperature and top_p for Kimi K2.6
Fixed 10
  • Fix GitHub Copilot model fetch
  • Fix gpt-image-2 and gpt-image-1.5 failures and stuck pending placeholder
  • Pass user apiKey to createGateway when fetching models
  • Support new-api providers and endpoint type routing for OpenCode
  • Default to image/png when file has no extension in images/edits
  • Do not recognize Unix-style paths as clickable links on Windows in CodeBlock
Removed 1
  • Drop @cherry/browser MCP auto-injection

From cherry-studio

What's Changed
New Contributors

Full Changelog: https://github.com/CherryHQ/cherry-studio/compare/v1.9.3...v1.9.4

View originalPermalink
How v1.9.4 went

More in AI

View all
Codex

OpenAI's coding agent, running locally in the terminal.

OpenAI
Ollama

Get up and running with large language models locally.

Ollama
openclaw

Your own personal AI assistant. Any OS. Any Platform. The lobster way. 🦞

openclaw
tensorflow

An Open Source Machine Learning Framework for Everyone

tensorflow
superpowers

An agentic skills framework & software development methodology that works.

obra
skills

Skills for Real Engineers. Straight from my .agents directory.

mattpocock

Discussion

If you publish cherry-studio, you can claim this product by proving you administer its repository.