Release version 0.44.0

This release makes task delivery easier, improves long conversations and desktop memory cleanup, fixes GitLab image previews, and updates agents and built-in skills.

New

• Include uncommitted task changes when creating or updating a PR/MR, with a file list and editable commit message before committing and pushing to the task branch.

Improved

• Streaming replies and long execution histories are more responsive, with steps loading as you scroll and fewer blank areas, missing steps or unexpected scroll jumps in chat and sub-agent panels.
• Built-in expert skills are updated to Superpowers 7.0.2, improving plan execution when skills are installed individually.
• Built-in research skills are updated to scientific-agent-skills 2.72.0, expanding paper lookup to 18 scholarly sources and improving data analysis, scientific figures and research reviews.
• Updated CodeBuddy to 2.184.0, Kimi Code to 2.6.1, Qoder to 1.1.88 and Antigravity to 1.5.0.

Fixed

• Reduced memory retained after closing desktop conversation tabs or sub-agent panels while they are still loading, and fixed cases where reopening a conversation could remain stuck waiting. (#1148 by @kogekiplay)
• GitLab issue and comment images display correctly across desktop, Web and remote workspaces, including private uploads and images hosted in object storage.
• CodeBuddy file previews no longer include extra reading hints as file content, keeping the displayed content and line numbers accurate.

Thanks to @kogekiplay for contributing to this release.

发布版本 0.44.0

这一版让任务交付更方便，提升长对话的响应与滚动体验，减少桌面端关闭会话后的内存残留，修复 GitLab 图片预览，并更新多个智能体及内置技能。

新增

• 创建或更新任务 PR/MR 时，可以一并提交任务工作区中尚未提交的改动，交付前可查看文件清单并编辑提交信息。

改进

• 长回复和大量工具调用时，内容更新与滚动更加流畅，执行步骤随滚动加载，并减少聊天与子智能体面板中的空白、步骤漏显和位置跳动。
• 内置专家技能更新至 Superpowers 7.0.2，改善单独安装技能时的计划执行体验。
• 内置科研技能更新至 scientific-agent-skills 2.72.0，论文检索扩展至 18 个学术来源，并改进数据分析、科研绘图与学术评审流程。
• CodeBuddy 更新至 2.184.0，Kimi Code 更新至 2.6.1，Qoder 更新至 1.1.88，Antigravity 更新至 1.5.0。

修复

• 减少桌面端关闭仍在加载的会话标签页或子智能体面板后的内存残留，并修复关闭后重新打开会话可能一直等待的问题。（#1148 by @kogekiplay）
• GitLab Issue 和评论中的图片可在桌面端、Web 端及远程工作区正常显示，兼容私有上传和对象存储中的图片。
• CodeBuddy 文件预览不再将额外的读取提示混入文件内容，确保内容与行号正确显示。

感谢 @kogekiplay 为本次发布做出的贡献。

Release version 0.43.0

This release adds conversation moves between folders, clearer tracking of background work, and more convenient repository collaboration, while improving file search, memory usage and agent compatibility.

New

• Move idle conversations that are not tied to a task between open folders, individually or in bulk, with menu selection and folder search while keeping their history.
• Control the desktop Web Service from the status bar, with its current status, start/stop controls and a new option to allow connections only from this computer.
• PR/MR lists show CI status, passing/total counts and approval reminders, with direct access to check details and approval of GitHub workflows awaiting maintainer authorization.
• Agents can attach files and images when creating to-do tasks, keeping reference material alongside the task instructions.

Improved

• Track background tasks and sub-agents from the running count above the chat input, including work that continues after a reply ends and delegated agents awaiting your response.
• Redesigned Session Details and message navigation make it easier to find the running message, inspect sub-agents and review file changes.
• Codex sub-agent activities now appear as expandable timeline steps, with task details, replies, errors and a shortcut to open the child conversation.
• Task completion comments can include an agent-drafted reply that you review and edit before publishing, with an optional Codeg footer.
• File search uses less frontend memory and avoids repeatedly scanning the same workspace, while keeping results current as files change in open projects. (#1116 by @kogekiplay)
• Updated Cursor to 2026.11.11-b912975, Kimi Code to 2.6.0, Qoder to 1.1.87, CodeBuddy to 2.183.0 and the ZCode bridge to 0.84.2.

Fixed

• Further reduced memory retained by very long tool output and closed HTML previews. (#1132, #1137 by @kogekiplay)
• Codex MCP screenshots and image results display correctly in desktop and Web chat, including after reopening a conversation. (#1134 by @PengXiaoyi)
• Kimi MCP authorization correctly shows the browser authorization link and reconnection status while waiting. (#1133 by @Cuinnchen)
• Kimi Code 2.6.0 plan reviews no longer incorrectly appear as tool failures when you approve, dismiss or request changes, both during the conversation and in its history.
• The ZCode bridge supports encrypted credentials used by ZCode 3.18+, fixing related execution failures and improving handling of duplicate history messages and replies.
• Interactive question cards for agents such as DeepSeek Harness correctly display the question text and option descriptions, fixing cases where only a short label appeared. (#1140 by @mvanhorn)
• Antigravity instances configured as custom agents correctly display interactive questions and preserve your selections in conversation history. (#1127 by @ana52070)
• Questions that only accept preset choices, including applicable Antigravity and Pi questions, no longer offer an unsupported “Other” input, preventing typed answers from being treated as cancellations. (#1131 by @ana52070)
• Custom Antigravity instances on Windows now include their startup temporary files in automatic cleanup, reducing disk space buildup after repeated launches. (#1139 by @ana52070)
• Long content in dialogs such as the model picker no longer causes horizontal overflow or clips buttons.
• Fixed an occasional cleanup error when an agent connection ends.

Thanks to @kogekiplay, @ana52070, @PengXiaoyi, @Cuinnchen and @mvanhorn for contributing to this release.

发布版本 0.43.0

这一版支持跨文件夹移动会话，让后台任务进度更清晰、仓库协作更方便，并改进文件搜索、内存占用和智能体兼容性。

新增

• 支持将未绑定任务的空闲会话单独或批量移到其他已打开的文件夹，可通过菜单选择或搜索目标文件夹，并保留历史记录。
• 桌面端状态栏新增 Web 服务入口，可查看运行状态、快速启停，并支持将访问范围设为仅限本机。
• PR/MR 列表直接显示检查状态、通过数与总数，并提示等待批准的工作流，可点击查看检查详情或批准 GitHub 工作流运行。
• 智能体创建待办任务时可以附带文件和图片，方便将参考资料与任务说明一起交给后续执行者。

改进

• 输入框上方集中显示后台任务和子智能体的运行数量与详情，回复结束后仍可跟踪未完成的工作，并提示等待你回应的委派任务。
• 重新设计会话详情与消息导航，更方便定位正在执行的消息、查看子智能体和审阅文件改动。
• Codex 子智能体活动统一展示为可展开的时间线步骤，可查看任务、回复和错误，并直接打开子会话。
• 任务完成后回写到 Issue 或 PR 的评论支持由智能体起草、经你审阅修改后发布，并可选择是否附带 Codeg 落款。
• 文件搜索减少前端内存占用和重复扫描，并随已打开项目中的文件变化更新搜索结果。（#1116 by @kogekiplay）
• Cursor 更新至 2026.11.11-b912975，Kimi Code 更新至 2.6.0，Qoder 更新至 1.1.87，CodeBuddy 更新至 2.183.0，ZCode 桥接更新至 0.84.2。

修复

• 进一步减少超长工具输出和已关闭 HTML 预览的内存占用。（#1132、#1137 by @kogekiplay）
• Codex 的 MCP 截图和图片结果可在桌面端与 Web 端正常预览，重新打开会话后也能正确显示。（#1134 by @PengXiaoyi）
• Kimi 等待 MCP 授权时会正确显示浏览器授权链接和重连状态。（#1133 by @Cuinnchen）
• Kimi Code 2.6.0 中批准计划、关闭审批或要求修改后，不再误显示为工具执行失败，实时对话和历史记录均能正确展示。
• ZCode 桥接兼容 3.18 及更新版本的加密凭据，修复相关执行失败，并改善历史消息和回复重复显示的问题。
• DeepSeek Harness 等智能体的提问卡片能正确显示问题正文和选项说明，修复只显示简短标题、缺少问题内容或选项解释的情况。（#1140 by @mvanhorn）
• 以自定义智能体接入的 Antigravity 能正常显示交互式提问，并在历史记录中保留你的选择。（#1127 by @ana52070）
• Antigravity、Pi 中仅支持预设选项的提问不再显示「其他」输入框，避免手动输入的回答被误当作取消。（#1131 by @ana52070）
• Windows 上的自定义 Antigravity 实例会将启动临时文件纳入自动清理，减少反复启动后的磁盘空间占用。（#1139 by @ana52070）
• 模型选择等弹窗遇到较长内容时不再横向溢出或遮挡按钮。
• 修复智能体连接结束时偶发的清理异常。

感谢 @kogekiplay、@ana52070、@PengXiaoyi、@Cuinnchen 和 @mvanhorn 为本次发布做出的贡献。

Release version 0.42.3

This release reduces memory growth during extended use, fixes missing collaboration tools in forked Codex conversations, restores skill selection for custom agents, and updates several agents.

Improved

• Claude Code is updated to 2.1.322 with adapter 0.106.0.
• Updated OpenCode to 2.2.7, Kimi Code to 2.5.3, Hermes Agent to 0.23.1 and the ZCode bridge to 0.83.3.

Fixed

• Reduced memory buildup during repeated scrolling, view changes and streaming code generation, improving memory usage during extended sessions. (#1114, #1115, #1117 by @kogekiplay)
• Custom agents with a configured skill directory or shared skill store now list their skills in the / menu, in both chat and automation editors. (#1121 by @ana52070)
• Forked Codex conversations retain their enabled MCP tools, allowing you to continue delegating work to sub-agents and retrieving their results. (#1105)
• Reopening a conversation no longer adds duplicate context compaction cards after the existing history.
• OpenCode commands that time out or are terminated no longer incorrectly appear as successful.
• OpenCode file previews correctly display reads beyond the end of a file, while reads counted from the end no longer show a misleading line range.
• Reopening older ZCode conversations correctly restores their saved titles.

Thanks to @kogekiplay (#1114, #1115, #1117) and @ana52070 (#1121) for their contributions, and to @lxpsxx (#1105) for the report.

发布版本 0.42.3

这一版改善长时间使用时的内存占用，修复 Codex 分叉会话后协作工具丢失、自定义智能体无法选择技能等问题，并更新多个智能体。

改进

• Claude Code 更新至 2.1.322，适配器更新至 0.106.0。
• OpenCode 更新至 2.2.7，Kimi Code 更新至 2.5.3，Hermes Agent 更新至 0.23.1，ZCode 桥接更新至 0.83.3。

修复

• 减少反复滚动、切换视图和持续生成代码时的内存累积，改善长时间使用时的内存占用。（#1114、#1115、#1117 by @kogekiplay）
• 配置了技能目录或共享技能库的自定义智能体，可以在 / 菜单中选择技能，聊天输入框和自动化编辑器均可使用。（#1121 by @ana52070）
• Codex 分叉会话后会保留已启用的 MCP 工具，可以继续委派子智能体并获取执行结果。（#1105）
• 重新打开会话时，已有的上下文压缩卡片不会再重复出现在历史记录末尾。
• OpenCode 中超时或被终止的命令，不再被误标为执行成功。
• OpenCode 读取位置超出文件末尾时，返回内容仍能正确预览，从文件末尾倒数读取时也不会再显示错误的行号范围。
• 重新打开较早的 ZCode 会话时，能正确恢复已保存的会话标题。

感谢 @kogekiplay（#1114、#1115、#1117）和 @ana52070（#1121）的贡献，以及 @lxpsxx（#1105）的反馈。

Release version 0.42.2

This release adds support for Claude Fable 5.2, updates Codex and several other agents, and fixes Qoder failing to start on Windows and MiniMax questions not showing as cards.

Improved

• Claude Code is updated to 2.1.321 with adapter 0.102.0, so the Fable model is now Fable 5.2, and a saved Fable 5.1 selection through an API gateway switches to Fable 5.2 automatically instead of falling back to the default model.
• Codex is updated to adapter 2.6.0 (Codex 0.166.0), and its async questions now display as answer cards that stay in sync during the conversation and in history.
• Grok background sub-agents show live progress after the turn that launched them ends. (#1109)
• Updated OpenCode to 2.2.6, CodeBuddy to 2.182.0, Qoder to 1.1.86, the ZCode bridge to 0.82.3 and Command Code to 1.88.5.

Fixed

• Qoder starts normally again on Windows, and its diagnostics show the actual program being launched or the reason it could not be found. (#1101 by @leehom0123)
• MiniMax questions to the user appear as interactive question cards instead of raw JSON, including each option's description. (#1111 by @xy3xy3)
• When a Codex conversation's model provider no longer matches, codeg shows a clear notice instead of silently starting an empty session that loses the history.
• Reopened Claude Code context compaction summaries no longer include internal prompt text meant for the model.
• OpenCode 2.2.6 conversation history displays its complete content.

Thanks to @leehom0123 (#1101) and @xy3xy3 (#1111) for their contributions, and to @momomomo820 (#1109) for the report.

发布版本 0.42.2

这一版支持 Claude Fable 5.2，更新 Codex 及多个智能体，并修复 Qoder 在 Windows 上无法启动、MiniMax 提问不弹出卡片等问题。

改进

• Claude Code 更新至 2.1.321，适配器更新至 0.102.0，Fable 模型升级为 Fable 5.2，通过 API 网关使用时，已保存的 Fable 5.1 选择会自动切换到 Fable 5.2，不再回落到默认模型。
• Codex 适配器更新至 2.6.0（Codex 0.166.0），异步提问会显示为答题卡片，会话中和历史记录里都能正确展示。
• Grok 后台子智能体在启动它的回合结束后，仍会实时显示运行进度。（#1109）
• OpenCode 更新至 2.2.6，CodeBuddy 更新至 2.182.0，Qoder 更新至 1.1.86，ZCode 桥接更新至 0.82.3，Command Code 更新至 1.88.5。

修复

• Qoder 在 Windows 上恢复正常启动，诊断信息也会显示实际启动的程序或无法找到的原因。（#1101 by @leehom0123）
• MiniMax 向用户提问时会弹出可交互的提问卡片，不再只显示 JSON 参数，并展示每个选项的说明。（#1111 by @xy3xy3）
• Codex 会话的模型供应商不再匹配时，会显示明确提示，不再悄悄新开一个空会话导致历史丢失。
• 重新打开 Claude Code 的上下文压缩摘要时，不再显示写给模型的内部提示文本。
• OpenCode 2.2.6 的历史会话能完整显示内容。

感谢 @leehom0123（#1101）和 @xy3xy3（#1111）的贡献，以及 @momomomo820（#1109）的反馈。

Release version 0.42.1

This release lets you handle related issues in one task, keeps background work running when you leave a conversation, improves Office previews, and updates multiple agents.

New

• Related issues can be selected across pages and handled in one task, with a single PR or merge request and a choice of which issues it closes when merged.

Improved

• Claude Code is updated to 2.1.318 with adapter 0.101.0, and new sessions default to Auto unless you have selected another permission mode.
• Claude Code’s idle context compaction appears directly in the conversation, including its summary, without needing to reopen the session.
• Updated Hermes Agent to 0.23.0, CodeBuddy to 2.181.0, Grok to 1.0.77, Kimi Code to 2.5.2, Cursor to 2026.11.05-86047df, Qoder to 1.1.84, the ZCode bridge to 0.82.1 and Command Code to 1.88.4.

Fixed

• Closing or switching conversation panes, or refreshing the web page, no longer unexpectedly stops background commands, Remote Control or running sub-agents.
• Office auto-preview reliably opens documents created or modified in the current turn, fixing unrelated templates opening, closed previews reappearing and occasional missed previews on Linux and Windows.
• Updating Grok through codeg now runs the updated version, and uninstalling it correctly removes its installed status.
• Kimi Code retains MCP execution environment and deferred tool-loading settings when codeg saves or syncs its configuration.
• Kimi Code tool cards restore their correct titles when calls finish, instead of continuing to show reconnection or sign-in messages.
• Qoder 1.1.84 keeps MCP tool cards and history displaying correctly, while codeg’s built-in tools such as questions continue without unnecessary permission requests.
• Cursor conversation history includes the new access-management and code-execution tool steps.
• The built-in browser no longer covers fullscreen tables or Mermaid diagrams opened from chat.
• Agent error messages retain the file paths needed to locate and fix configuration problems.

Note

• Claude Code’s Auto mode may refuse commands when an API gateway cannot support its permission checks, in which case you can switch to Manual.
• In Hermes 0.23.0, MCP servers configured in Hermes itself cannot connect when used alongside MCP servers injected by codeg.
• On Linux, Windows and some macOS setups, disconnecting the session that started Hermes’ shared background service may interrupt tasks running in other Hermes conversations.

Thanks to @Time-w (#1090), @HOMEFTW (#1091) and @monkeyDragonLiu (#1096) for the reports.

发布版本 0.42.1

这一版支持将多个相关 Issue 合并为一个任务处理，修复会话页面关闭导致后台任务中断、Office 文档误弹出等问题，并更新多个智能体。

新增

• 支持跨页多选相关 Issue 并合并为一个任务处理，统一交付为 PR 或合并请求，并选择合并后关闭哪些 Issue。

改进

• Claude Code 更新至 2.1.318，适配器更新至 0.101.0，未指定其他权限模式时，新会话默认使用 Auto 模式。
• Claude Code 空闲时自动压缩上下文的结果会直接显示在会话中，无需重新打开即可查看压缩摘要。
• Hermes Agent 更新至 0.23.0，CodeBuddy 更新至 2.181.0，Grok 更新至 1.0.77，Kimi Code 更新至 2.5.2，Cursor 更新至 2026.11.05-86047df，Qoder 更新至 1.1.84，ZCode 桥接更新至 0.82.1，Command Code 更新至 1.88.4。

修复

• 关闭或切换会话面板、刷新网页时，后台命令、远程控制和正在运行的子智能体不再被意外中断。
• Office 自动预览准确识别智能体本轮创建或修改的文档，修复无关模板误打开、关闭后反复弹出及 Linux、Windows 下偶尔漏开预览的问题。
• 通过 codeg 更新 Grok 后会实际运行新版本，卸载后也会正确显示为未安装。
• 保存或同步 Kimi Code 的 MCP 配置时，会保留运行环境和工具延迟加载设置。
• Kimi Code 工具调用结束后会恢复正确的卡片标题，不再残留「重连中」或登录授权提示。
• Qoder 升级至 1.1.84 后，MCP 工具卡片和历史记录仍能正确显示，codeg 内置提问等工具也不会出现多余的授权请求。
• Cursor 历史会话能正确显示新增的权限管理和代码执行工具步骤。
• 打开聊天中的全屏表格或 Mermaid 图表时，内置浏览器页面不再遮挡内容。
• 智能体错误提示会保留相关文件路径，方便定位和修复配置问题。

注意

• Claude Code 的 Auto 模式在 API 网关无法支持其权限检查时可能拒绝执行命令，遇到这种情况可切换至 Manual 模式。
• Hermes 0.23.0 自身配置的 MCP 服务，在与 codeg 注入的 MCP 服务同时使用时暂时无法连接。
• 在 Linux、Windows 及部分 macOS 环境中，断开启动 Hermes 共享后台服务的会话，可能中断其他 Hermes 会话正在执行的任务。

感谢 @Time-w（#1090）、@HOMEFTW（#1091）和 @monkeyDragonLiu（#1096）的问题反馈。

Release version 0.42.0

This release adds CNB repository support and global system instruction editing, makes tasks awaiting your response easier to continue, and improves notifications and conversation history.

New

• CNB (cnb.cool) joins the supported code hosting platforms, with issue and merge request management, automatic issue processing, and task delivery through merge requests. (#1066, @abigmiu)
• Global system instructions can be viewed and edited directly in agent settings for supported agents such as Claude Code, Codex and OpenCode, making it easier to set preferences and working rules. (#1060, @ana52070)
• Channel and webhook notifications can be limited to top-level session completions and errors, reducing sub-agent notifications while keeping permission requests and questions visible.

Improved

• Tasks awaiting permission, an answer or plan approval now prioritize “Respond”, opening the conversation so you can handle the request and let the task continue.
• Webhook notifications include conversation, agent and parent-session details, making their source and delegation relationships easier to identify.
• Expandable steps in the execution timeline highlight on hover and keyboard focus, making it easier to see which step you are about to open.
• Self-updated Hermes 0.22.6 installations retain provider-grouped model selection and mode switching, with reasoning effort available alongside them.
• Updated Claude Code to claude-agent-acp 0.100.0 and CodeBuddy to 2.179.3.

Fixed

• OpenCode’s / menu once again lists the skills it loads, making them available in chat, automation and task editors.
• OpenCode’s default model lists in Settings correctly hide disabled models and providers. (#1079, @xyalter)
• DeepSeek Harness 0.2.x history correctly displays tool output, failures and cache-write usage, including conversations migrated from earlier versions. (#1086, @Cuinnchen)
• PowerShell in the built-in terminal and “Run on this computer” loads your profile, allowing fnm, conda, aliases and other environment customizations to work.
• Reopening a Pi conversation correctly restores its message history, fixing cases where the conversation appeared empty.
• Claude Code preserves the original conversation and explains why it cannot be restored, avoiding an unexpected switch to an empty session when it is held by a background task or its worktree cannot be reopened.
• Claude Code replies triggered by MCP prompt commands no longer appear twice in the conversation.

Thanks to @abigmiu, @ana52070, @xyalter and @Cuinnchen for contributing to this release, and to @grykom, @branll, @DaYePython and @ZhangSanMo for the reports and suggestions.

发布版本 0.42.0

这一版新增 CNB 仓库支持和全局系统提示词编辑，让等待你回应的任务更容易继续，并改进消息通知与历史会话展示。

新增

• 新增腾讯 CNB（cnb.cool）支持，可管理 Issue 和合并请求、自动处理 Issue，并将任务成果交付为合并请求。（#1066，@abigmiu）
• 支持在智能体设置中直接查看和编辑全局系统提示词，适用于 Claude Code、Codex、OpenCode 等智能体，方便配置角色、回复偏好和工作规范。（#1060，@ana52070）
• 消息渠道和 Webhook 可仅推送主会话的完成与错误通知，减少子智能体的通知干扰，同时保留授权请求和提问提醒。

改进

• 等待授权、回答问题或审批计划的任务会优先显示「去回应」，点击即可打开会话处理请求，回应后任务会自动继续。
• Webhook 通知会附带会话、智能体及父会话信息，方便识别消息来源和委派关系。
• 执行过程中可展开的步骤会在鼠标悬停或键盘聚焦时高亮，更容易看清即将打开的步骤。
• 兼容自行升级的 Hermes 0.22.6，保留按供应商分组的模型选择和模式切换，并支持调整推理强度。
• Claude Code 适配器更新至 claude-agent-acp 0.100.0，CodeBuddy 更新至 2.179.3。

修复

• OpenCode 的 / 菜单恢复显示已加载的技能，可在聊天、自动化和任务编辑器中直接选用。
• OpenCode 设置中的默认模型列表会正确隐藏已禁用的模型和供应商。（#1079，@xyalter）
• DeepSeek Harness 0.2.x 的历史会话能正确显示工具输出、失败状态和缓存写入用量，从旧版迁移的会话也能正常查看。（#1086，@Cuinnchen）
• 内置终端和「在本机运行」会正确加载 PowerShell 个人配置，让 fnm、conda、命令别名等自定义环境正常生效。
• 重新打开 Pi 会话时可以正确恢复历史消息，修复部分会话记录显示为空的问题。
• Claude Code 无法恢复会话时会保留原会话并说明原因，避免因后台任务占用或工作树无法重新打开而误切到空白会话。
• Claude Code 使用 MCP 提示词命令时，同一轮对话不再重复显示。

感谢 @abigmiu、@ana52070、@xyalter 和 @Cuinnchen 为本次发布做出的贡献，也感谢 @grykom、@branll、@DaYePython 和 @ZhangSanMo 的问题反馈和功能建议。

Release version 0.41.4

This release renders inline math more reliably, fixes duplicated terminal output in remote workspaces, makes the execution timeline easier to read, and updates five agents.

New

• ZCode supports /rename to rename the current session, and the conversation title in codeg updates to match unless you have already renamed the conversation yourself.
• OpenCode's reserved space before automatic compaction can be set as a share of the context window, such as 20%, as well as a token count.

Improved

• Resumed delegations appear as delegation rows in the execution timeline, marked as resumed and showing the reason for resuming.
• Read and search steps inside explore groups use the same layout as command rows, and the secondary text of non-text steps has higher contrast.
• Updated OpenCode to 2.2.5, CodeBuddy to 2.179.2, Kimi Code to 2.4.1, Antigravity to 1.4.5 and the ZCode bridge to 0.82.0.
• Kimi Code can read text files up to 16 MiB, so files larger than 2 MiB no longer fail to load.

Fixed

• Single-dollar inline formulas such as $T$ now render as math, while amounts, shell variables and code stay exactly as written. (#1081, @xy3xy3)
• Opening another window in a remote workspace no longer duplicates terminal output, including the window for importing local conversations. (#1085, @xyalter)
• Background command and image generation cards in OpenCode history now show their final results and no longer stay stuck as running.

Note

• OpenCode's /goal, /init and /review commands currently show no progress after you send them, and the session can stop responding if a step needs your approval.
• OpenCode's background command and image generation results appear after you reopen the conversation, not while they are still running.

发布版本 0.41.4

这一版改进了行内公式的渲染，修复了远程工作区终端输出重复的问题，让执行过程时间线更易阅读，并更新了五个智能体。

新增

• ZCode 支持用 /rename 重命名当前会话，codeg 中的会话标题会同步更新，你自己改过的标题不会被覆盖。
• OpenCode 自动压缩前预留的空间可以按上下文窗口占比填写，例如 20%，也可以继续填写 token 数。

改进

• 恢复后的委派在执行过程时间线中显示为委派行，并带有已恢复标记和恢复原因。
• 探索分组里的读取和搜索步骤改用与命令行一致的布局，非文字步骤的次要文字也更加清晰。
• OpenCode 更新至 2.2.5，CodeBuddy 更新至 2.179.2，Kimi Code 更新至 2.4.1，Antigravity 更新至 1.4.5，ZCode 桥接更新至 0.82.0。
• Kimi Code 支持读取最大 16 MiB 的文本文件，查看超过 2 MiB 的文件时不再失败。

修复

• $T$ 这类单美元符号行内公式现在可以正常渲染，金额、Shell 变量和代码内容仍按原样显示。(#1081, @xy3xy3)
• 在远程工作区打开其他窗口时，终端输出不再重复显示，打开导入本地会话的窗口也是如此。(#1085, @xyalter)
• OpenCode 历史会话中的后台命令和图片生成卡片会显示最终结果，不再一直停留在运行中。

注意

• OpenCode 的 /goal、/init、/review 命令发出后暂时看不到执行进度，如果中途需要授权，会话可能停止响应。
• OpenCode 后台命令和图片生成的结果需要重新打开会话才会显示，运行期间暂时无法实时看到。

Release version 0.41.3

This release improves file pasting and reply presentation, adds new Claude Code and Codex capabilities, and brings support for larger workspace backgrounds.

New

• Claude Code offers a thinking-summary switch, letting you show summaries of its reasoning from the agent’s settings.
• Codex offers follow-up prompt suggestions in chat, while automated runs skip generating suggestions to avoid extra model requests.
• GPT-6.1 Terra joins Codex’s built-in model list, with matching context-usage tracking.

Improved

• Pasting files and folders into desktop chat is more reliable, including files copied from your file manager and pasted through the right-click menu.
• Claude Code skills are easier to identify in / menus, with skill icons in chat, automation and task editors, plus source paths on hover when available.
• Instructions sent while Codex is working can guide the current task directly, while messages sent during an approval request stay queued.
• Workspace backgrounds support images up to 64 MiB and 100 million pixels, with more time allowed for large transfers and wallpaper downloads.
• Opening text flows naturally into later execution steps, with smoother transitions from waiting to the first reply content.
• Updated Claude Code to claude-agent-acp 0.99.1 and Codex to codex-acp 2.5.0.
• Antigravity 1.4.4 can read text files up to 16 MiB, avoiding failures when viewing files larger than 2 MiB.
• ZCode 0.79.1 improves request retries and failure messages, allowing you to resend in the same conversation when retries are exhausted.

Fixed

• Claude Code receives pasted PDFs correctly and preserves their attachment display in history, without duplicating messages sent with only an attachment.
• Claude Code can fork conversations across working directories and offers a sign-in action when your login expires.
• Codex history preserves clickable file references and gives clearer explanations for ChatGPT workspace connection failures.
• Codex handles Google Cloud Vertex AI configuration correctly, avoiding incompatible settings when binding a provider or changing WebSocket options.
• Command Code 1.88.2 fixes a startup failure affecting fresh installations.
• Qoder 1.1.81 stops pending tool calls correctly when you cancel during approval, and history retains the model name when later records leave it blank.

Note

• Qoder’s follow-up reply after a background sub-agent finishes currently appears after reopening the conversation, rather than arriving live.

发布版本 0.41.3

这一版改进了文件粘贴与回复展示，扩展 Claude Code 和 Codex 的使用体验，并支持更大、更高清的工作区背景图。

新增

• Claude Code 新增「显示 Claude 的思考摘要」开关，可在智能体设置中开启，查看推理过程的摘要说明。
• Codex 支持在聊天输入框显示后续问题建议，自动化等无人输入场景则跳过生成建议，减少额外模型请求。
• Codex 内置模型列表新增 GPT-6.1 Terra，并适配对应的上下文用量显示。

改进

• 桌面端粘贴文件和文件夹更加可靠，从文件管理器复制后即可添加为智能体可访问的附件，右键「粘贴」同样适用。
• Claude Code 技能在 / 菜单中更容易辨认，聊天、自动化和任务编辑器均显示技能图标，有来源路径时还可悬停查看。
• Codex 运行中收到的补充要求可以直接引导当前任务，等待授权期间发送的消息则排队保留。
• 工作区背景图上限提升至 64 MiB、1 亿像素，同时延长大图传输和壁纸下载的等待时间。
• 回复开头的文字与后续执行步骤衔接更加自然，从等待状态切换到首段回复时也更平滑。
• Claude Code 适配器更新至 claude-agent-acp 0.99.1，Codex 适配器更新至 codex-acp 2.5.0。
• Antigravity 更新至 1.4.4，支持读取最大 16 MiB 的文本文件，避免查看超过 2 MiB 的文件时失败。
• ZCode 适配器更新至 0.79.1，改进请求重试与失败提示，重试未成功时仍可在原会话中重新发送。

修复

• Claude Code 可以正确接收粘贴的 PDF，并在历史中保留附件展示，仅发送附件时也不会重复显示消息。
• 修复 Claude Code 跨工作目录分叉会话失败的问题，并在登录过期时提供重新登录入口。
• Codex 历史会话保留可点击的文件引用，并为 ChatGPT 工作区连接失败提供更清晰的说明。
• 修正 Codex 对 Google Cloud Vertex AI 的配置处理，避免绑定供应商或切换 WebSocket 设置时写入不兼容的配置。
• Command Code 更新至 1.88.2，修复全新安装后可能无法启动的问题。
• Qoder 更新至 1.1.81，等待授权时点击停止会正确结束对应工具调用，历史记录中的空模型字段也不会再覆盖原有模型名称。

注意

• Qoder 后台子智能体完成后的后续回复，目前需要重新打开会话才能查看，暂时无法实时显示。

Release version 0.41.2

This release makes replies smoother to follow, keeps background tasks compact, and improves reliability for Kimi Code and CodeBuddy.

Improved

• Replies flow more smoothly as they arrive, with gradual text appearance and natural transitions between messages, steps, command output and completed results, respecting chat animation and reduced-motion settings.
• Background tasks can collapse to a single line with a task count, while longer lists scroll within a limited height to leave more room for the conversation.
• The activity header follows your chat theme and workspace background, with clearer hover feedback and readable text.
• Updated CodeBuddy to 2.177.1, Kimi Code to 2.4.0, Command Code to 1.88.1 and the ZCode bridge to 0.78.0.
• ZCode supports GLM Coding Plan API keys, using keys saved in the desktop app or configured separately through terminal setup.
• Command Code handles image-heavy conversations more reliably, automatically reducing image payloads or compacting context before retrying oversized requests.

Fixed

• Streaming replies keep consistent paragraph, list and code-block layouts, reducing flicker and sudden shifts as content arrives or the reply finishes.
• Command groups stop appearing as the current step once the reply moves on, while commands running in the background retain their actual status.
• Quickly expanding and collapsing the activity header works reliably, without accidentally selecting its text or opening the copy popup.
• Kimi Code’s plan mode no longer ends unexpectedly at the first tool call, allowing the agent to continue gathering information and preparing its plan.
• Stopping CodeBuddy no longer loses the next queued message or incorrectly marks a completed follow-up reply as cancelled.

发布版本 0.41.2

这一版让回复生成和执行过程的展示更加流畅，减少后台任务对聊天空间的占用，并修复 Kimi Code 和 CodeBuddy 的会话问题。

改进

• 回复生成过程更加顺畅，文字逐步呈现，消息、执行步骤、命令输出和最终结果自然衔接，并遵循聊天动画与系统减少动态效果设置。
• 后台任务支持收起为显示任务数量的一行，任务较多时可在固定高度内滚动查看，为对话留出更多空间。
• 「执行过程」标题更好地融入聊天主题和工作区背景图，鼠标悬停时的反馈和文字也更清晰。
• 同步更新 CodeBuddy 至 2.177.1、Kimi Code 至 2.4.0、Command Code 至 1.88.1，以及 ZCode 适配器至 0.78.0。
• ZCode 支持使用 GLM Coding Plan API 密钥连接，可沿用桌面端保存的密钥，也可在终端单独配置。
• Command Code 处理多图会话更加可靠，请求过大时会自动缩减图片内容或压缩上下文后重试。

修复

• 流式回复中的段落、列表和代码块保持一致的排版，减少生成过程中及回复完成时的闪烁和位置跳动。
• 回复进入后续步骤后，旧命令组不会再误显示为当前执行步骤，后台命令仍会保留实际运行状态。
• 快速展开和收起「执行过程」时能正确响应点击，不会再意外选中文字并弹出复制提示。
• 修复 Kimi Code 计划模式在首次调用工具时意外结束的问题，智能体可以正常继续收集信息并制定计划。
• 修复 CodeBuddy 停止后丢失下一条排队消息，以及后续已完成回复被误标为取消的问题。

Release version 0.41.1

This release brings folder-specific tabs and split layouts, HTML previews in replies, native MiniMax Code support and OpenCode 2 integration, alongside easier model selection, more flexible task delivery and improved usage reporting.

New

• Tabs can follow the selected folder: enable “Tabs follow folder” in the sidebar’s View options to switch conversations, files and split layouts together while preserving drafts, unsaved edits and running conversations. (#1039, @fengpanhe)
• HTML/CSS cards and charts can appear directly in replies: enable “Chat HTML rendering” in Settings → Appearance to preview static HTML alongside Markdown, including during streaming, and switch back to the source when needed. (#1041, @ana52070)
• MiniMax Code joins the built-in agents, connecting to your installed mcode with its existing login and provider settings, with support for MCP tools and multi-agent delegation. (#1028, @xy3xy3)
• Model fields can fetch and list your provider’s models directly, with search, refresh and retry controls for Claude Code, Gemini CLI, OpenCode and other supported agents.
• Codex model management is gathered into one section, where you can choose the built-in or provider list, select models and refresh automatically while retaining the last working list if a refresh fails.
• Tasks ready for review can open pull requests on GitHub, GitLab and Gitea/Forgejo, including tasks created without an issue, with the option to keep the task open and push later changes to the same request.
• ZCode supports unified Skills management, including browsing, editing, importing and installing skills through codeg’s settings. (#1021, @jackie-cqz)

Improved

• OpenCode moves to 2.2.0, with updated provider connections, permissions, MCP and plugin management that preserve comments in JSONC configuration files.
• OpenCode conversations show form questions, scripts and background sub-agent progress, and saved conversations include the newer database’s compaction records, command exit codes and media attachments.
• Claude Code moves to claude-agent-acp 0.98.0, with dedicated monitor steps showing the watched command or address, plus progress and trigger details for work started by background tasks or scheduled wakeups.
• Claude Code’s sandbox network permission cards name the destination host, making it easier to decide whether to allow a connection.
• Codex moves to codex-acp 2.3.0, reducing the wait to reopen a fork’s parent conversation to about a minute and improving saved tool output and error messages.
• Cline, CodeBuddy, Kimi Code, Grok, Cursor, Antigravity, ZCode and Command Code are updated, with compatibility adjustments for their current tools and configuration.
• Bundled Superpowers skills move to v7.0.1, adding session diagnostics for repeated work, plan drift and unusual costs, alongside improved planning, execution, review and standalone skill compatibility.
• Hermes conversations offer model selection grouped by provider and a mode selector, restoring your choices when you reopen the conversation.
• Creating a task from a message opens the editor over the current conversation, with the message and project filled in so you can save without leaving what you were reading.
• The activity timeline uses clearer grey backgrounds, text hierarchy and icon spacing, with a collapse action at the bottom of expanded steps that brings their header back into view.
• Command rows explain outcomes such as no matches, false conditions, differing files and timeouts, while command output stays folded by default.
• TRAE CLI usage comes from its native records and includes sub-agent consumption, giving conversations and usage reports more complete token totals. (#1019, @fengpanhe)

Fixed

• Antigravity’s native questions appear as interactive cards, with selected answers preserved after reopening and historical multi-select, written-in and skipped answers displayed correctly. (#1043, @ana52070)
• OpenCode 2 delegations display as sub-agent tasks with the correct conversation links, including after reopening and when several delegations run in parallel. (#1020, @Liang-HZ)
• Files with Chinese or other non-ASCII names, and renamed files, show correct change counts and diff previews in the Changes panel and task details. (#1022, @MaxFreedomPollard)
• Usage and Manage Conversations filters include custom agents and show their current names, making their conversations and consumption easier to find. (#1029, @Adam-Dalloul)
• Conversations using the official Claude adapter retain reported per-prompt usage and costs after reopening, including custom agents, whose linked native sessions are also skipped during new imports to avoid duplicate usage counts. (#1048, @Adam-Dalloul)
• Conversations retain their recorded duration even without token data, and reported turn usage is preserved when a Remote Control message ends the reply.
• A Codex reply that continues after automatic context compaction stays together in history, instead of splitting into separate replies with duplicate activity headers and footers.
• Claude advisor results remain visible after reopening, in both the main conversation and sub-agent conversations.
• A Kimi Code conversation that is busy in another client reports that it is in use, instead of switching the conversation to a new empty session.
• Dragging agents to reorder them in Settings keeps the list in place, while selecting another agent still scrolls it into view. (#1033, @xyalter)
• Agents that depend on installation scripts, including Hermes Agent, install correctly with npm 12.
• Fixed a Windows issue where ending an agent session could leave Git Bash with a missing temporary directory, causing later commands to fail.
• The macOS desktop app avoids the system’s low-swap suspension, which could leave every conversation unresponsive while the agents kept running.
• Multi-agent tool calls stop waiting when codeg remains unresponsive, preventing them from hanging indefinitely.

Note

• OpenCode now requires version 2.0 or later, so upgrade any 1.x installation before opening conversations and use plugins compatible with OpenCode 2.
• OpenCode 2 does not support SSE MCP servers, so use streamable HTTP when the server offers it, or leave OpenCode out of that server’s assignments.
• The macOS standalone server now retains Full Disk Access and other privacy permissions across future updates, but moving from an older build to this release requires granting those permissions once more.

发布版本 0.41.1

这一版加入了按文件夹切换标签页和分屏布局、对话内 HTML 预览、MiniMax Code 原生支持和 OpenCode 2 适配，同时改进模型选择、任务交付和用量统计。

新增

• 标签页可以跟随当前文件夹切换——在侧栏「视图选项」中开启「标签页跟随文件夹」，即可一起切换各文件夹的会话、文件和分屏布局，并保留草稿、未保存的修改和正在运行的对话。（#1039，@fengpanhe）
• AI 回复中的 HTML/CSS 卡片和图表可以直接预览——在「设置 → 外观」开启「聊天 HTML 渲染」，即可在流式回复中查看与 Markdown 混排的静态 HTML，并随时切回源码。（#1041，@ana52070）
• 新增内置智能体 MiniMax Code，可连接已安装的 mcode，沿用已有登录和供应商配置，并支持 MCP 工具与多智能体委派。（#1028，@xy3xy3）
• 模型输入框可以直接获取并列出供应商提供的模型，支持搜索、刷新和失败重试，适用于 Claude Code、Gemini CLI、OpenCode 等智能体。
• Codex 的模型集中在同一处管理，可切换内置或供应商列表、勾选模型并自动刷新，刷新失败时保留上次可用的列表。
• 待验收的任务可以直接创建 GitHub、GitLab 和 Gitea/Forgejo 的拉取请求，无需先关联 Issue，也可以在交付后保留任务，继续处理并更新同一个 PR。
• ZCode 接入统一的技能管理，可以在 codeg 设置中查看、编辑、导入和安装技能。（#1021，@jackie-cqz）

改进

• OpenCode 升级到 2.2.0，供应商连接、权限、MCP 和插件管理均适配新版，并保留 JSONC 配置文件中的注释。
• OpenCode 会话支持展示表单提问、脚本执行和后台子智能体进度，历史会话也能读取新版数据库中的压缩记录、命令退出码和媒体附件。
• Claude Code 升级到 claude-agent-acp 0.98.0，监控任务会单独展示正在监听的命令或地址，后台任务和定时唤醒触发的工作也能查看进度与触发原因。
• Claude Code 的沙箱联网授权会明确显示目标主机，方便确认当前请求要连接哪里。
• Codex 升级到 codex-acp 2.3.0，分叉后重新打开父会话的等待时间缩短至约一分钟，历史工具输出和错误提示也更易读。
• 同步更新 Cline、CodeBuddy、Kimi Code、Grok、Cursor、Antigravity、ZCode 和 Command Code，并适配新版工具记录和配置行为。
• 内置 Superpowers 技能更新到 v7.0.1，新增会话诊断来分析重复工作、计划偏离和异常开销，同时改进计划编写、执行、审核及技能单独安装的兼容性。
• Hermes 会话支持按供应商分组选择模型和切换运行模式，重新打开会话后会恢复之前的选择。
• 从消息创建任务时，编辑窗口直接在当前对话上打开，自动带入消息内容和所属项目，保存任务无需离开正在阅读的会话。
• 执行过程采用更清晰的灰色背景、文字层次和图标间距，展开的步骤列表底部可一键收起，并自动回到对应标题。
• 命令结果会直接说明「无匹配」「条件不成立」「有差异」「超时」等含义，命令输出默认保持收起，按需展开查看。
• TRAE CLI 用量统计改为读取原生记录，并计入子智能体消耗，会话和用量报表中的 token 总量更加完整。（#1019，@fengpanhe）

修复

• Antigravity 的原生提问会显示为可直接回答的交互卡片，重新打开后仍能看到已选答案，历史中的多选、自填和跳过记录也能正确展示。（#1043，@ana52070）
• OpenCode 2 的委派会正确显示为子智能体任务并关联对应会话，重新打开或同时委派多个任务时也能正确查看。（#1020，@Liang-HZ）
• 中文等非 ASCII 文件名和重命名文件能正确显示增删行数与差异预览，覆盖「变更」面板和任务详情。（#1022，@MaxFreedomPollard）
• 用量统计和「管理会话」的筛选包含自定义智能体，并显示当前名称，查找对应会话和消耗更方便。（#1029，@Adam-Dalloul）
• 使用官方 Claude 适配器的会话会保留每轮返回的用量与费用，自定义智能体也适用，新导入时还会跳过已关联的原生会话，避免重复统计。（#1048，@Adam-Dalloul）
• 没有 token 数据的会话仍会保留已记录的执行耗时，远程控制消息结束当前回复时，也不会丢失本轮已报告的用量。
• Codex 在自动压缩上下文后继续生成的回复，回看时会保持完整，不会再拆成两条并重复显示执行过程和统计。
• Claude 顾问模型的回答会保留在历史中，重新打开主会话或子智能体会话后都能查看。
• Kimi Code 会话被其他客户端占用时会正确提示，不会再误建空会话并切换过去。
• 在设置中拖动智能体排序时，列表不会再突然跳回当前选中项，切换智能体时仍会自动滚动到对应位置。（#1033，@xyalter）
• 使用 npm 12 也能正确安装 Hermes Agent 等依赖安装脚本的智能体。
• 修复 Windows 上结束智能体会话后，Git Bash 临时目录失效的问题，避免后续命令因找不到临时目录而失败。
• 修复 macOS 因交换空间耗尽而挂起 codeg 的问题，避免智能体仍在运行、所有会话却一起失去响应。
• 多智能体工具调用在 codeg 长时间失去响应时会结束等待，避免一直卡住。

注意

• OpenCode 现在要求 2.0 及以上版本，请先升级已有的 1.x 安装再打开会话，并换用兼容 OpenCode 2 的插件。
• OpenCode 2 不支持 SSE 类型的 MCP 服务器，如果服务器提供 streamable HTTP，请改用该方式，否则不要为该服务器选择 OpenCode。
• macOS 独立服务器版在后续更新中可以保留「完全磁盘访问」等隐私权限，但从旧版首次升级到本版时，需要重新授予一次权限。