[pull] main from xintaofei:main#157
Merged
Merged
Conversation
Marketplace list thumbnails and action-preview popovers loaded poster and preview images by fetching codex-pets.net directly from the webview, so they stayed blank wherever that host is unreachable while the backend-fetched listing still populated. Add a pet_marketplace_asset command (Tauri command + Axum route) that fetches the image bytes through the marketplace HTTP client and returns them as a base64 asset the renderer turns into a blob URL. A hook caches each fetched asset by URL and mints a per-consumer blob URL revoked on unmount; the list thumbnails and preview grid show a loading spinner and a fallback icon when an image is unavailable.
Inactive conversation tabs stay mounted and hide with visibility:hidden. Tailwind v4's transition-all transitions visibility too, so welcome controls (agent-selector pills, quick-action tabs, composer buttons) kept animating their inherited visibility and stayed painted 150-300ms over the newly-active conversation. Suppress transitions on the hidden tab subtree so visibility snaps immediately, and derive the tab body's active state directly from the active tab id.
- codebuddy 2.126.0 -> 2.127.0 - kimi-code 0.29.0 -> 0.29.1 - pi-acp 0.0.31 -> 0.0.32 - cursor 2026.07.20-8cc9c0b -> 2026.07.23-e383d2b
Update the bundled expert skills from superpowers v6.1.1 to v6.2.0. Replace test-driven-development's testing-anti-patterns reference with a positive, rules-based writing-good-tests catalog, and scope the subagent-driven-development workspace per plan while routing the review-fix loop back to the original implementer through a new re-review-prompt. Make finishing-a-development-branch's PR creation forge-agnostic and limit the discard option to explicit requests, restore the gemini-tools harness reference, fix find-polluter.sh path matching, and compress the per-skill guidance across the remaining SKILL.md files. Skills are vendored verbatim from upstream; experts.toml is unchanged since the skill ids are stable.
- Terminal: fall back to the shell when a direct exec fails with ENAMETOOLONG (over-length command line), so Grok's long file-writing commands run instead of failing with "File name too long". - Plan-mode approval: reply to exit_plan_mode with the outcome shape Grok expects (approved / keep_planning / abandoned), so "Approve & build" is honored instead of being read as "request changes"; deliver request-changes notes as a follow-up prompt so Grok revises and re-presents the plan. - Plan-mode rendering: resolve live EnterPlanMode/ExitPlanMode calls from x.ai/tool.kind so they use the dedicated plan-mode card like history, instead of folding into a generic tool group. - Context compaction: surface auto_compact_completed in the live stream and history as a standalone centered divider between turns showing the token delta, instead of wedging it inside a reply or wrapping it in a tool group.
- feat(codex): **Answer Codex's prompts with codeg's own cards.** Plan-mode questions, MCP forms, and tool-call approvals from Codex now surface as codeg's interactive ask and permission cards — synthesized live and preserved on reload — and its plans render as a proper markdown card. (Codex updated to 1.1.7) - feat(codex): **Pause or clear an active goal.** The goal card gains Pause and Clear buttons; resuming is just re-sending your `/goal`. The controls hide on history reload, for viewers, and in the read-only sub-agent dialog. - feat(codex): **A clearer live sub-agent card.** It now shows the sub-agent's model and reasoning effort as it runs, no longer draws an empty white box when there's nothing to report, and picks up Codex's new retry banner and context-compaction card. - feat(codex): **Plan mode moved to the mode selector.** The redundant `/plan` slash command is gone — toggle plan mode from the collaboration-mode selector instead. - feat(grok): **Grok plan mode, end to end.** Leaving plan mode now shows an approval card (approve / request changes / abandon) in both the main conversation and the sub-agent dialog, and survives a mid-turn reconnect. "Approve & build" is honored correctly, request-changes notes go back as a follow-up so Grok revises, and plan calls render in the dedicated plan-mode card. - fix(grok): **Long file writes no longer fail.** When a command line is too long to run directly, Grok now falls back to the shell instead of erroring with "File name too long." - feat(grok): **Context compaction shown inline.** Auto-compaction now appears as a centered divider between turns with the token delta, in both the live stream and history. - feat(sidebar): **A more focused sidebar.** Finished conversations are now hidden by default — flip on "Show completed" to see them. Imported local sessions arrive as pending review so they stay visible. - feat(settings): **New Claude Code privacy toggles.** Two switches now control Claude Code's attribution/billing header (off by default) and non-essential network traffic (disabled by default), written straight to your native config. - fix(settings): **A cleaner skill import picker.** Built-in expert, office, and science skills no longer clutter the agent skill-import list. - fix(pet): **Pet marketplace images load everywhere.** Thumbnails and previews are now fetched through the backend, so they show up even where the marketplace host is unreachable from the webview. - fix(chat): **Snappier session switching.** The outgoing tab hides immediately, and the new-session welcome controls no longer linger and animate over the conversation you just opened. - fix(messages): **Right-sized message bubbles.** Your messages and ask-question results now hug their content instead of stretching to full width. - feat(layout): **Smarter branch search.** The branch selector now ranks matches by relevance, with exact matches first. - chore(experts): **Updated expert skills to superpowers 6.2.0.** Brings a rules-based "writing good tests" guide, a plan-scoped subagent workspace whose review-fix loop routes back to the original implementer, and forge-agnostic PR creation, among other refinements. - chore(acp): **Refreshed the bundled agents.** CodeBuddy 2.127.0, Kimi Code 0.29.1, Pi 0.0.32, Cursor 2026.07.23, and Codex 1.1.7. ----------------------------- # 发布版本 0.21.7 - 功能(Codex)：**用 codeg 自己的卡片回应 Codex 的提问。** Codex 的计划模式提问、MCP 表单与工具调用授权，现在都以 codeg 的交互式提问卡与授权卡呈现——实时合成、重载后仍保留——其计划也渲染为规范的 markdown 卡片。（Codex 升级至 1.1.7） - 功能(Codex)：**暂停或清除进行中的目标。** 目标卡片新增「暂停」与「清除」按钮；重新发送 `/goal` 即可恢复。这些按钮在历史重载、旁观者视角以及只读子智能体对话中会自动隐藏。 - 功能(Codex)：**更清晰的实时子智能体卡片。** 运行时即显示子智能体的模型与推理强度；无内容可展示时不再画出空白「白框」；并接入 Codex 新的重试提示与上下文压缩卡片。 - 功能(Codex)：**计划模式移至模式选择器。** 移除多余的 `/plan` 斜杠命令，改从协作模式选择器切换计划模式。 - 功能(Grok)：**Grok 计划模式，端到端可用。** 离开计划模式时，主对话与子智能体对话中都会弹出审批卡（批准 / 请求修改 / 放弃），并可在回合中途重连后恢复。「批准并构建」被正确执行，「请求修改」的意见会作为后续提示回传让 Grok 修订，计划调用也渲染进专属的计划模式卡片。 - 修复(Grok)：**长文件写入不再失败。** 当命令行过长无法直接执行时，Grok 现在会回退到 shell 运行，而不再报「文件名过长」。 - 功能(Grok)：**上下文压缩内联显示。** 自动压缩现在以居中分隔线的形式显示在两回合之间，并标注 token 变化，实时流与历史均可见。 - 功能(侧边栏)：**更专注的侧边栏。** 已完成的会话现在默认隐藏，需要时打开「显示已完成」即可查看。导入的本地会话以「待评审」状态进入，保持可见。 - 功能(设置)：**新增 Claude Code 隐私开关。** 两个开关分别控制 Claude Code 的归属/计费标头（默认关闭）与非必要网络请求（默认禁用），直接写入原生配置。 - 修复(设置)：**更清爽的技能导入选择器。** 内置的专家、办公与科研技能不再出现在智能体的技能导入列表中。 - 修复(宠物)：**宠物市场图片处处可加载。** 缩略图与预览现在改由后端代理拉取，即便 webview 直连市场主机不通也能正常显示。 - 修复(聊天)：**切换会话更利落。** 切出的标签立即隐藏，新会话的欢迎控件不再滞留、也不再在你刚打开的会话上继续动画。 - 修复(消息)：**大小合适的消息气泡。** 你的消息与提问结果现在按内容自适应宽度，不再撑满整行。 - 功能(布局)：**更聪明的分支搜索。** 分支选择器现在按相关度排序，精确匹配优先。 - 维护(专家)：**专家技能升级至 superpowers 6.2.0。** 带来基于规则的「编写优质测试」指南、按计划隔离且将「评审—修复」环路回交给原实现者的子智能体工作区，以及不依赖特定托管平台的 PR 创建等改进。 - 维护(智能体)：**刷新内置智能体版本。** CodeBuddy 2.127.0、Kimi Code 0.29.1、Pi 0.0.32、Cursor 2026.07.23、Codex 1.1.7。
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to subscribe to this conversation on GitHub.
Already have an account?
Sign in.
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
See Commits and Changes for more details.
Created by
pull[bot] (v2.0.0-alpha.4)
Can you help keep this open source service alive? 💖 Please sponsor : )