codeg v0.21.4

Release version 0.21.4

• feat(workspace): A reorganized desktop layout. The folder selector now lives in the conversation header — sized to the title and aware of your folder aliases — while the git branch selector and command launcher move into the bottom status bar as paired controls. A one-click pull-code button sits beside the branch name, cloud pull/push actions live in the branch menu, and the redundant pickers below the composer are gone.
• feat(workspace): Mobile now mirrors the desktop. The mobile workspace adopts the same conversation header, file breadcrumb, and bottom status bar under a slimmed top bar. The sidebar and file drawer close on their own after you pick a conversation, start a new one, or open a file.
• feat(import-sessions): Import local sessions in bulk from a dedicated window. A new window scans every local agent store, groups the sessions it finds by project folder, and imports your whole selection in one pass — with live per-agent scan progress, title/path search, an agent filter, and folder- and session-level selection. Open it from a folder's menu or the Folders header.
• feat(chat): Long messages you sent now collapse. A long message you sent clips to a comfortable height with a fading edge and a "Show more" / "Show less" toggle; assistant replies are left untouched.
• fix(chat): Windows file links open instead of reading "[blocked]". Local Windows paths (C:\…, file:///C:/…) — including Chinese, spaced, and URL-encoded ones — now open through the workspace file opener instead of being dropped.
• fix(git): The branch label holds steady after a pull or switch. The bottom status bar no longer flashes "no branch" for a moment after a pull, fetch, commit, or checkout.
• fix(workspace): Cleaner chrome over a background image. The status bar, sidebar, tab-strip line, and active-tab arch keep a legible tinted hairline over a background image, and the new-conversation button's hover and the hovered-tab corners render cleanly.
• fix(logging): Quieter, bounded logs. A debug target that could grow the log file without bound is capped at warnings, and repeated broadcast-lag warnings collapse to one line per window.
• chore(acp): Upgraded the bundled agent versions in the registry. Claude Code 0.60.0, OpenCode 1.18.4, Gemini 0.51.0, Cline 3.0.46, Hermes 0.19.0, CodeBuddy 2.125.0, and Kimi Code 0.28.1.

---

发布版本 0.21.4

• 功能(工作台)：重新组织的桌面布局。 文件夹选择器现在位于会话标题栏中——按标题大小排布、并识别你的文件夹别名；git 分支选择器与命令启动器则下移到底部状态栏，成为一对并列控件。分支名旁新增一键拉取代码按钮，云端拉取/推送操作收进分支菜单，输入框下方冗余的选择器也已移除。
• 功能(工作台)：移动端现在与桌面端一致。 移动端工作台采用相同的会话标题栏、文件面包屑与底部状态栏，顶栏也随之精简。选择会话、新建会话或打开文件后，侧边栏与文件抽屉会自动收起。
• 功能(会话导入)：在独立窗口中批量导入本地会话。 新窗口会扫描每个本地智能体的存储、按项目文件夹归类发现的会话，并一次性导入你的全部选择——支持各智能体的实时扫描进度、标题/路径搜索、智能体筛选，以及文件夹与会话两级选择。可从文件夹菜单或「文件夹」区头部打开。
• 功能(聊天)：你发送的长消息现在可折叠。 过长的已发送消息会收拢到合适的高度并带有渐隐边缘，配以「展开」/「收起」开关；助手回复保持原样。
• 修复(聊天)：Windows 文件链接可以打开，而不再显示「[blocked]」。 本地 Windows 路径（C:\…、file:///C:/…）——包括中文、含空格与 URL 编码的路径——现在会通过工作区文件打开器打开，而不再被丢弃。
• 修复(Git)：拉取或切换分支后分支名保持稳定。 底部状态栏在拉取、抓取、提交或检出后不再短暂闪现「无分支」。
• 修复(工作台)：背景图之上更干净的框架。 状态栏、侧边栏、标签条底线与激活标签拱形在背景图之上保持清晰的淡色发丝线，新建会话按钮的悬停与悬停标签的圆角也渲染得干净利落。
• 修复(日志)：更安静、有上限的日志。 一个可能让日志文件无限增长的 debug 目标被限制为 warning 级别，重复的广播滞后警告也在每个时间窗内合并为一行。
• 维护(智能体)：升级注册表中的内置智能体版本。 Claude Code 0.60.0、OpenCode 1.18.4、Gemini 0.51.0、Cline 3.0.46、Hermes 0.19.0、CodeBuddy 2.125.0、Kimi Code 0.28.1。

codeg v0.21.3

Release version 0.21.3

• feat(chat): Frosted message surfaces over your background image. With a workspace background image on, the surfaces inside chat messages — bubbles, capsules, cards, code headers, tables, and inline code — turn to one family of translucent frosted panels so the image shows through. Inline code also reads as a pill and tables as rounded, bordered cards.
• fix(tabs): The new-conversation button sits neatly beside the tabs. It shares the tab row and stays right next to the last tab, and over a background image its hover frost and the strip's bottom border render cleanly.

---

发布版本 0.21.3

• 功能(聊天)：背景图之上的磨砂消息表面。 启用工作区背景图后，消息内的各类表面——气泡、胶囊、卡片、代码标题栏、表格与内联代码——统一为一族半透明磨砂面板，背景图得以透出。内联代码也呈现为胶囊，表格呈现为带边框的圆角卡片。
• 修复(标签栏)：新建会话按钮妥帖地落在标签旁边。 按钮与标签同处一行、紧贴最后一个标签，在背景图之上其悬停磨砂与标签条底边框也渲染得干净利落。

codeg v0.21.2

Release version 0.21.2

• feat(git-log): The Commit history tab is now a continuous timeline. History renders as one virtualized timeline that loads older commits on demand as you scroll, so the whole log stays reachable — not just the first page.
• feat(file-tree): Drive the file tree from the keyboard. Arrow keys move, expand, and collapse the selection, Enter or Space opens a file or toggles a folder, and Home/End jump to the ends — with the selected row kept in view.
• feat(grok): Choose how Grok authenticates. Pick an official subscription (grok login), an XAI_API_KEY, or a custom endpoint; the panel shows only the credential that method needs and recognizes your current one from the saved config.
• feat(workspace): Frosted surfaces over a background image. With a background image enabled, inline code, message bubbles, delegation cards, and Monaco's sticky-scroll header turn to frosted glass instead of opaque blocks.
• feat(workspace): A tidier titlebar at any zoom. The browser-style tabs draw at equal width under a continuous arch, and the window controls no longer overflow when the app is zoomed in.
• feat(workspace): Remote windows show the workspace name. A remote-desktop window's status bar now shows the connected workspace's name — with its address on hover — beside the session count.
• fix(search): The file search dialog finds deeply-nested files. A gitignore-aware backend walk reaches files at any depth without descending into node_modules or target, and fuzzy ranking surfaces deep matches. The composer's @-mention picker benefits too.
• fix(workspace): Cursor and Grok delegation cards show their icon again. They no longer render a blank icon for those sub-agent types.

---

发布版本 0.21.2

• 功能(提交历史)：「提交」标签现在是一条连续的时间线。 历史以单条虚拟化的时间线呈现，滚动时按需加载更早的提交，整段历史都可触达，而不再只有第一页。
• 功能(文件树)：用键盘操作文件树。 方向键移动、展开、收起选中项，Enter 或 Space 打开文件或折叠目录，Home/End 跳到首尾，选中行始终保持在可视范围内。
• 功能(Grok)：自选 Grok 的鉴权方式。 可在官方订阅（grok login）、XAI_API_KEY、自定义端点之间选择；面板只显示所选方式需要的凭据，并从已保存的配置识别你当前的方式。
• 功能(工作台)：背景图之上的磨砂表面。 启用背景图后，内联代码、消息气泡、委派卡片与 Monaco 吸顶滚动头会变为磨砂玻璃，而非不透明色块。
• 功能(工作台)：任意缩放下更整洁的标题栏。 浏览器式标签以等宽绘制、底部连成一道拱形，放大应用时窗口控件也不再溢出。
• 功能(工作台)：远程窗口显示工作区名称。 远程桌面窗口的状态栏现在会在会话计数旁显示所连工作区的名称——悬停可见其地址。
• 修复(搜索)：文件搜索对话框能找到深层嵌套的文件。 后端按 gitignore 规则遍历，不进入 node_modules 或 target 即可触达任意深度的文件，模糊排序让深层匹配浮现。输入框的 @ 提及选择器也同样受益。
• 修复(工作台)：Cursor 与 Grok 的委派卡片重新显示图标。 这两类子智能体不再显示空白图标。

codeg v0.21.1

Release version 0.21.1

• feat(acp): Cursor joins as the 12th coding agent. Sign in with your subscription or an API key, pick a model, and use it like any other agent — with full session history, MCP, and delegation.
• fix(chat): Images now work with Grok and other embedded-context agents. Pasted images show as thumbnails and appear in your sent bubbles, and they survive reopening a session.
• perf(chat): Streaming conversations render more smoothly. Several rendering optimizations cut the work repeated on every streamed update.
• fix(files): Editors no longer leak memory. Monaco models are released when file tabs close and when diff editors unmount.
• fix(chat): The new-session composer tracks your agent and focuses on open. It stays in sync with the agent you pick and takes focus the moment a conversation opens, rather than waiting for the ACP connection.
• fix(commands): A command's run state survives reopening the sidebar. Closing and reopening the sidebar keeps the command's run state and your selection instead of resetting them.
• fix(workspace): Background-image refinements. The image now shows through the right sidebar header, and the opacity sliders reach further — the mask up to 99% and panels down to a fully transparent 0%.

---

发布版本 0.21.1

• 功能(智能体)：Cursor 作为第 12 个编码智能体接入。 用订阅账号或 API Key 登录、选择模型，即可像其它智能体一样使用，支持完整会话历史、MCP 与委托。
• 修复(聊天)：Grok 等嵌入式上下文智能体现在能正常处理图片。 粘贴的图片会显示为缩略图并出现在你发送的气泡中，重开会话也不会丢失。
• 性能(聊天)：流式会话渲染更顺滑。 多项渲染优化减少了每次流式更新时的重复计算。
• 修复(文件)：编辑器不再泄漏内存。 关闭文件标签或卸载 diff 编辑器时，Monaco model 会被正确释放。
• 修复(聊天)：新会话输入框跟随所选智能体并在打开时聚焦。 输入框会与你选择的智能体保持同步，并在会话一打开就获得焦点，而不再等到 ACP 连接建立之后。
• 修复(命令)：命令的运行状态在侧边栏重开后得以保留。 关闭再打开侧边栏时，命令会保留其运行状态与你的选择，而不会被重置。
• 修复(工作台)：背景图打磨。 背景图现在会透过右侧栏头显示，不透明度滑块范围也更大——遮罩最高可达 99%，面板最低可至完全透明的 0%。

codeg v0.21.0

Release version 0.21.0

• feat(workspace): A redesigned four-column desktop workspace. Sidebar, conversation, file, and aux panel each get a full-height column with its own top bar; tabs move into the title bar, and new conversation and file detail headers carry quick actions.
• feat(aux-panel): A new Session Details tab. The right panel now shows the active conversation's metadata and live token usage, and hosts the Git branch and command selectors moved out of the title bar.
• feat(appearance): Custom workspace background image with frosted surfaces. Set an image in Appearance settings and tune its blur and opacity; chrome surfaces turn to frosted glass while editors and overlays go transparent.
• feat(appearance): Accent themes now color the whole interface. Muted panels, the sidebar, borders, the light canvas, and the editor background all carry the theme's hue instead of staying gray.
• feat(file-tree): Drag tree entries to move them, or into the composer to reference them. Drop a file or folder onto another folder to move it, or into the chat box to insert a reference.
• feat(workspace): Custom folder aliases. Set an alias from a folder's context menu; the sidebar and header show "alias [ name ]".
• feat(grok): Grok's built-in ask_user_question is now interactive. Its questions render as codeg's question card and your answer goes back to Grok, instead of a dead, unanswerable card.
• fix(sync): A reply that finishes on another device now appears for everyone watching. It syncs into your open conversation instead of showing up only after a reload.
• fix(chat): A clearer composer border and selected quick-action tab. The resting border stays visible in every theme and over a background image, and the active tab now stands out.
• chore(agents): Bundled agents refreshed. Cline 3.0.44, CodeBuddy Code 2.124.0, Kimi Code 0.27.0, and Grok 0.2.103.

---

发布版本 0.21.0

• 功能(工作台)：全新四列式桌面工作台。 侧边栏、会话、文件、辅助面板各占一条全高列并拥有独立顶栏；标签移入标题栏，新增的会话与文件详情头附带快捷操作。
• 功能(辅助面板)：新增「会话详情」标签。 右侧面板现在展示当前会话的元数据与实时 token 用量，并接管了从标题栏移出的 Git 分支与命令选择器。
• 功能(外观)：自定义工作台背景图，配以磨砂表面。 在外观设置中选择背景图并调节模糊与不透明度；界面表面变为磨砂玻璃，而编辑器与浮层则透明。
• 功能(外观)：强调色主题现在贯穿整个界面。 柔和面板、侧边栏、边框、浅色画布与编辑器背景都带上主题色相，不再是灰色。
• 功能(文件树)：拖动文件树条目即可移动，或拖入输入框即可引用。 将文件或文件夹拖到另一个文件夹即可移动，或拖入聊天框即可插入引用。
• 功能(工作台)：自定义文件夹别名。 在文件夹右键菜单中设置别名后，侧边栏与详情头会显示「别名 [ 原名 ]」。
• 功能(Grok)：Grok 内置的 ask_user_question 现在可交互作答。 它的提问会渲染为 codeg 的问题卡片，你的回答会回传给 Grok，不再是无法作答的死卡片。
• 修复(同步)：在其它设备上完成的回复，现在会呈现给所有正在查看的人。 它会同步进你打开的会话，而不必等到重新加载后才出现。
• 修复(聊天)：更清晰的输入框边框与选中的快捷操作标签。 静息边框在任何主题下及背景图之上都清晰可见，当前标签也更突出。
• 更新(智能体)：内置智能体已刷新。 Cline 3.0.44、CodeBuddy Code 2.124.0、Kimi Code 0.27.0、Grok 0.2.103。

codeg v0.20.4

Release version 0.20.4

• fix(pet): Desktop pets with extra animations now install and display correctly. The marketplace's new "v2" pets add animation rows that codeg used to reject or render squished. It now adapts to each spritesheet's real size, keeping every pet sharp.
• fix(chat): Cleaner command and skill badges in sent messages. Badges now show just their name, dropping the leading / or $ to match the composer. What's sent to the agent is unchanged.
• chore(agents): Bundled agents refreshed. OpenCode (1.18.3), Cline (3.0.42), CodeBuddy Code (2.123.1), and Kimi Code (0.26.0) updated; Claude Code's ACP adapter pinned to 0.58.1.

---

发布版本 0.20.4

• 修复(宠物)：带更多动作的桌面宠物现在能正确安装与显示。 市场新增的「v2」宠物带有额外动画行，过去会被拒绝安装或显示压扁。现在按每张精灵图的真实尺寸自适应，宠物随处都清晰。
• 修复(聊天)：已发送消息里的命令与技能徽章更清爽。 徽章只显示名称，去掉开头的 / 或 $，与编辑时一致。发送给智能体的内容保持不变。
• 更新(智能体)：内置智能体已刷新。 OpenCode（1.18.3）、Cline（3.0.42）、CodeBuddy Code（2.123.1）、Kimi Code（0.26.0）已更新；Claude Code 的 ACP 适配器固定到 0.58.1。

codeg v0.20.3

Release version 0.20.3

• feat(chat-channel): Telegram Topic mode. Run multiple sessions inside one Telegram forum supergroup, each bound to its own topic. /task <description> opens a new topic and session, /resume <id> binds an existing one, and plain text follows up in the current topic. Requires a forum supergroup with the bot as a topic-managing admin. Thanks @AnotiaWang (#322).
• feat(codex): Custom Codex models without hand-editing JSON. A structured editor in Codex settings lets you define custom models and curate the list — clone an official model, override only what differs, pick enum fields from dropdowns. Official models are read live from the launched Codex, so new ones appear automatically.
• feat(grok): Real Grok permission modes and reasoning effort. Permission mode now uses Grok's own --permission-mode values (old settings migrate automatically), and the reasoning-effort selector follows the chosen model — showing only the efforts it supports, or hiding entirely when it has none.
• feat(skills): Author your own skills. A new Custom tab in Skill Packs lets you create, edit, duplicate, and delete skills in the shared store and enable them for any agent — write once, reuse everywhere. Import from a local folder or from an agent's existing global skills.
• fix(chat): Async sub-agent results settle cleanly into their turn. Held-turn content no longer double-renders, the launch card updates in place to its finished result, and the "syncing results" strip stops lingering.
• fix(chat): Correct first-reply stats after resuming a conversation. The first reply after reopening a conversation no longer absorbs every earlier turn's duration and tokens — each reply reports only its own.
• fix(acp): A session's last error survives a reconnect. Reconnecting after missing the live error event still shows what went wrong, and a stale error is never resurrected onto a session that moved on. Thanks @ijry (#314).
• fix(chat-channel): Telegram tokens no longer leak; @username channels bind correctly. Bot tokens are scrubbed from error messages, and an @username is resolved to its numeric chat id so a follow-up no longer spawns a duplicate agent.
• fix(session): Completed sessions show their true runtime, computed from start and end timestamps. Thanks @cnYui (#311).
• fix(editor): Windows IME composition is preserved when typing Chinese, Japanese, or Korean in the built-in editor. Thanks @youxikexue (#332).
• fix(docker): Docker builds include the pnpm workspace config, so container and self-hosted deployments build cleanly. Thanks @AnotiaWang (#322).
• chore(agents): Bundled agents refreshed — Claude Code (0.59.0), OpenCode (1.17.20), OpenClaw (2026.7.1), Cline (3.0.40), CodeBuddy (2.121.2), Kimi Code (0.24.1), Grok (0.2.101).

---

发布版本 0.20.3

• 功能(聊天渠道)：Telegram 话题模式。 在一个 Telegram 论坛超级群里同时跑多个会话，每个会话绑定各自的话题。/task <描述> 开新话题并启动新会话，/resume <id> 绑定已有会话，纯文本即为当前话题的跟进。需要论坛超级群、并把机器人设为有话题管理权限的管理员。感谢 @AnotiaWang（#322）。
• 功能(Codex)：无需手写 JSON 的 Codex 自定义模型。 Codex 设置里的结构化编辑器让你定义自定义模型、精选列表——克隆官方模型、只覆盖差异字段、枚举字段从下拉选取。官方模型从启动的 Codex 实时读取，新模型会自动出现。
• 功能(Grok)：真实的 Grok 权限模式与推理强度。 权限模式改用 Grok 自己的 --permission-mode 取值（旧设置自动迁移），推理强度选择器跟随所选模型——只显示它支持的强度，无强度调节时则完全隐藏。
• 功能(技能)：创作你自己的技能。 技能包新增「自定义」标签，可在共享库里创建、编辑、复制、删除技能，并为任意智能体启用——一次编写、处处复用。支持从本地文件夹或某个智能体已有的全局技能导入。
• 修复(聊天)：异步子智能体的结果干净地归入所属回合。 回合内容不再重复渲染，启动卡片就地更新为完成结果，「同步结果中」提示条不再残留。
• 修复(聊天)：恢复会话后的首条回复统计正确了。 重开对话后的第一条回复不再吸收之前所有回合的时长与 token，每条回复只报告自己的数据。
• 修复(会话)：会话最近一次错误在重连后保留。 错过实时错误事件、之后重连仍能看到出错原因，且旧错误不会被复活到已经继续下去的会话上。感谢 @ijry（#314）。
• 修复(聊天渠道)：Telegram token 不再泄漏，@username 渠道正确绑定。 机器人 token 会从错误信息中抹除，@username 会解析为数字 chat id，跟进消息不再重复启动智能体。
• 修复(会话)：已完成会话显示真实运行时长， 依据开始与结束时间戳计算。感谢 @cnYui（#311）。
• 修复(编辑器)：保留 Windows 输入法组词， 在内置编辑器中输入中日韩文时不再丢字或错乱。感谢 @youxikexue（#332）。
• 修复(Docker)：Docker 构建包含 pnpm workspace 配置， 容器与自托管部署可正常构建。感谢 @AnotiaWang（#322）。
• 更新(智能体)：内置智能体已刷新 —— Claude Code（0.59.0）、OpenCode（1.17.20）、OpenClaw（2026.7.1）、Cline（3.0.40）、CodeBuddy（2.121.2）、Kimi Code（0.24.1）、Grok（0.2.101）。

codeg v0.20.2

Release version 0.20.2

• feat(settings): Experts, Science, and Office Tools are now one "Skill Packs" hub. The three separate settings pages are merged into a single Skill Packs entry with a tabbed switcher for Experts, Scientific Research, and Office — plus a fixed toolbar to open the shared central skills folder or refresh the active tab. Old links to the individual pages redirect here automatically.
• feat(chat): Kick off Scientific Research skills straight from the composer. The composer's "+" menu gains a "Scientific Research" submenu next to Experts and Office Work, listing every bundled science skill; pick one to drop its invocation badge into your message. Skills you haven't enabled for the current agent show a lock and a shortcut to turn them on in Settings.
• feat(layout): Roomier sidebars. The left and right sidebars can now be dragged out to 900px, giving conversation lists and side panels more breathing room on wide displays.
• fix(chat): Quick-skills now use the right prefix for whichever agent you send to. A skill badge inserted before switching agents kept its original trigger, so a skill queued for Codex went out as /skill and Codex rejected it as a slash command. Badges are now re-stamped when you change agents and normalized at send time — $ for Codex, / everywhere else — so the invocation always lands.
• fix(acp): A conversation that can't be resumed now offers a clear way forward. When a historical session can't be restored — the agent process crashed mid-load, or the session has expired or ended — codeg shows a Reload / New conversation banner instead of silently orphaning the context or surfacing a raw protocol error.
• fix(editor): No more phantom errors or orange boxes in the file editor. The built-in editor no longer flags false-positive TypeScript/JSON problems that only exist because it can't see your project's build context ("Cannot find module '@/…'", a missing --jsx flag, unreachable schemas), and Chinese/Japanese full-width punctuation (：；，！？（）) renders as normal text instead of highlighted boxes. Real syntax errors and zero-width/BOM detection are still flagged.
• fix(editor): Markdown list markers show up in file preview. Ordered lists now display their numbers and unordered lists get proper indentation in the editor's Markdown preview.
• fix(chat): The model picker no longer closes when you grab its scrollbar. On the desktop app's WebKit webview, dragging the model list's scrollbar used to dismiss the picker; it now stays open in both the wide picker and the collapsed cog panel.

---

发布版本 0.20.2

• 功能(设置)：专家、科研、办公工具现已合并为统一的「技能包」。 原本三个独立的设置页合并为单一的「技能包」入口，通过标签在专家、科学研究、办公之间切换——右侧还配有固定工具栏，可打开三者共用的中央技能文件夹或刷新当前标签。指向旧页面的链接会自动重定向到这里。
• 功能(聊天)：直接从输入框启动科研技能。 输入框的「+」菜单在「专家」和「办公工作」旁新增「科学研究」子菜单，列出所有内置科研技能；点选其一即可把它的调用徽章插入消息。尚未为当前智能体启用的技能会显示锁标，并提供跳转到设置一键启用的入口。
• 功能(布局)：更宽的侧边栏。 左右侧边栏现在可以拖宽到 900px，在宽屏上为会话列表和侧栏面板留出更充裕的空间。
• 修复(聊天)：快捷技能现在会按你发送的智能体使用正确的前缀。 此前你在切换智能体前插入的技能徽章会保留原始触发符，导致本应发给 Codex 的技能以 /skill 发出、被 Codex 当作 slash 命令拒绝。现在切换智能体时会重新盖章，并在发送时归一化——Codex 用 $，其它一律用 /——调用总能正确生效。
• 修复(会话)：无法恢复的会话现在会给出明确的后续选择。 当历史会话无法恢复时——智能体进程在加载中崩溃、或会话已过期/结束——codeg 会显示「重新加载 / 新建会话」横幅，而不再静默丢弃上下文或抛出原始协议错误。
• 修复(编辑器)：文件编辑器里不再出现莫须有的报错和橙色方框。 内置编辑器不再因看不到你项目的构建上下文而误报 TypeScript/JSON 问题（「找不到模块 '@/…'」、缺少 --jsx 标志、无法加载远程 schema），中日文全角标点（：；，！？（））也会作为普通文本正常显示，不再被标成高亮方框。真正的语法错误以及零宽字符/BOM 检测仍会照常提示。
• 修复(编辑器)：Markdown 预览现在会显示列表标记。 在编辑器的 Markdown 预览中，有序列表会显示编号，无序列表也有了正确的缩进。
• 修复(聊天)：抓取滚动条不再关闭模型选择器。 在桌面版的 WebKit webview 中，拖动模型列表的滚动条以前会关闭选择器；现在无论是宽版选择器还是折叠的齿轮面板，它都会保持打开。

codeg v0.20.1

Release version 0.20.1

• feat(grok): Bring your own Grok endpoint. Grok Build settings gain a "Custom model (BYO endpoint)" section — point it at any Grok-compatible endpoint with your own model id, base URL, API key, backend, context window, and session auto-compact threshold. Leave the URL blank to fall back to xAI's official endpoint.
• feat(grok): Grok no longer updates itself in the background. The Grok CLI launches with its self-updater disabled, so it keeps running the pinned build instead of silently swapping to a newer one — and its interactive approval prompt stays intact unless you've switched to always-approve.
• feat(grok): The context-window meter now works for Grok sessions. Grok conversations show how much of the model's context window you've used, with the window sized per Grok model (from 256K up to 2M) and paired with Grok's running token count — just like every other agent.
• fix(icon): Monochrome agent icons no longer look dimmed. The OpenCode, Hermes, Grok, Cline, and CodeBuddy marks now render at full strength in the agent selector, sidebar, and status bar, instead of appearing faint until you hover over or select them.
• chore(agents): Bundled agents refreshed. CodeBuddy Code (2.118.2) and Kimi Code (0.23.5) were bumped to their latest builds.

---

发布版本 0.20.1

• 功能(Grok)：接入你自己的 Grok 端点。 Grok Build 设置新增「自定义模型（BYO 端点）」区域——用你自己的模型 id、base URL、API Key、后端、上下文窗口与会话自动压缩阈值，将 Grok 指向任意兼容的自定义端点；URL 留空则回落到 xAI 官方端点。
• 功能(Grok)：Grok 不再在后台自行更新。 Grok CLI 会以禁用自更新的方式启动，因此它始终运行固定的构建，而不会在后台悄悄换成新版本——其交互式审批提示也照常保留，除非你已切换到「始终批准」。
• 功能(Grok)：上下文窗口计量器现已支持 Grok 会话。 Grok 对话会显示你已用去的上下文窗口比例，窗口大小按各 Grok 模型自动推断（从 256K 到 2M），并与 Grok 的累计 token 数配对显示——与其它智能体完全一致。
• 修复(图标)：单色智能体图标不再显得暗淡。 OpenCode、Hermes、Grok、Cline、CodeBuddy 的图标现在在智能体选择器、侧边栏和状态栏中以全强度渲染，不再要等到悬停或选中时才变清晰。
• 更新(智能体)：内置智能体已刷新。 CodeBuddy Code（2.118.2）和 Kimi Code（0.23.5）升级到最新构建。

codeg v0.20.0

Release version 0.20.0

• feat(acp): Meet Grok Build — the 11th built-in agent. xAI's Grok Build joins codeg as a first-class coding agent: sign in with your xAI API key, choose its model and reasoning effort, delegate sub-agents, and manage its MCP servers — with live and replayed sessions rendered exactly like every other agent.
• feat(science): A new Scientific Research skills mode. Thirteen curated, open-source research skills (from K-Dense-AI's scientific-agent-skills) now ship alongside the bundled expert and office skills. Install them to the shared library, enable them per agent in Settings, and start from the new "Scientific Research" tab on the new-conversation screen — localized in all 10 languages.
• feat(chat): The composer and your sent messages are now plain text. What you type, and the messages you've already sent, display as clean plain text with file and session references shown as compact badges — so your input reads exactly as written instead of being reflowed as Markdown. (Assistant replies are unchanged and still render Markdown.)
• fix(chat): Background tasks now settle correctly. A background task that's been collected or stopped is now marked as finished, so its indicator no longer lingers as if it were still running.
• fix(chat): The model picker stays open while you use its scrollbar. Dragging the scrollbar inside the model list no longer dismisses the picker.

---

发布版本 0.20.0

• 功能(智能体)：认识第 11 个内置智能体——Grok Build。 xAI 的 Grok Build 作为一等编码智能体加入 codeg：用 xAI API Key 登录，选择模型与推理强度，委托子智能体，管理它的 MCP 服务器——实时与回放会话的渲染都与其它智能体完全一致。
• 功能(科研)：全新「科学研究」技能模式。 13 个精选的开源科研技能（来自 K-Dense-AI 的 scientific-agent-skills）现已与内置的专家技能、办公技能一同发布。可安装到共享技能库、在设置中按智能体启用，并从新会话页面新增的「科学研究」标签开始——已本地化为全部 10 种语言。
• 功能(聊天)：输入框和你发送的消息现在为纯文本。 你正在输入的内容以及已发送的消息，都以清爽的纯文本显示，文件与会话引用呈现为紧凑徽章——所见即所写，不再被重排为 Markdown。（智能体的回复不受影响，仍以 Markdown 渲染。）
• 修复(聊天)：后台任务现在能正确结算。 被收集或停止的后台任务现在会被标记为已完成，其指示条不再一直停留在「运行中」。
• 修复(聊天)：拖动滚动条时模型选择器保持打开。 在模型列表内拖动滚动条不再关闭选择器。