codeg

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。