codeg v0.32.0

Release version 0.32.0

Claude Code and Codex move up together this time, and codeg takes up the two things both of them just learned to say: a notice now pops up as a toast instead of being written into the reply, and a context compaction shows how it really ended — and what it kept.
Underneath, codeg now talks to every agent through the official Agent Client Protocol 2.2 runtime. Server deployments can reach dev servers by hostname instead of a port range guessed in advance, and the web version gets the browser settings that still apply to it.

New

• A context compaction can show the summary it kept — when a live Claude Code or Codex session compacts, the divider gains a "Summary" toggle that opens what the model retained of the dropped history, streaming in as it is written. (#809, #814, @xintaofei)
• Server deployments can reach dev servers by hostname instead of by port — set CODEG_BRIDGE_HOST_PATTERN to auto or a template like {port}.preview.example.com, and 3000.codeg.example.com reaches port 3000 through the port codeg already listens on, with no port range to publish in advance. (#788 reported by @kekxv, #801, @xintaofei)

Improved

• Updated bundled agents: Claude Code ACP 0.81.0 (Claude Code 2.1.280), Codex ACP 1.13.0 (Codex CLI 0.155.1, which retires gpt-5.2 and gpt-5.4-mini). (#806, @xintaofei)
• Claude Code and Codex notices pop up as a toast instead of a bold line in the reply — a model fallback, a hook that blocked your prompt, a config or deprecation warning; warnings and errors also stay on the session banner. (#809, @xintaofei)
• Codex commands stream their output into the card as they run, instead of sitting on a [Terminal: …] placeholder and filling in all at once when the command ends. (#806, @xintaofei)
• Settings → Browser in the web version now holds the settings that still apply there — Local servers, Site rules and the Terminal link menu — so the notice for a server started in a terminal can finally be turned off or made to open a tab. (#788 reported by @kekxv, #798, @xintaofei)
• Writing to an agent's JSON config no longer re-sorts it — saving an MCP server, for one, leaves the rest of the file in the order you wrote it, and tool parameters likewise read in the order the agent sent them. (#814, @xintaofei)
• codeg now talks to every agent through the official Agent Client Protocol 2.2 runtime, where one message codeg fails to handle no longer drops the whole connection. (#814, @xintaofei)

Fixed

• A compaction divider says how the compaction really ended — a failed one gives its reason, an interrupted or cancelled one stops spinning, and two Codex compactions in one turn each get a divider of their own. (#806, #809, @xintaofei)
• Claude Code sub-agent cards in your history open on the sub-agent's report, not on the provenance boilerplate Claude Code 2.1.277 and later put in front of it. (#806, @xintaofei)
• The first turn after resuming a Claude Code session no longer counts the whole earlier session's tokens, so the Token Usage dashboard's per-model rows stop jumping after a resume. (#806, @xintaofei)
• Codex sub-agents no longer outlive a failed or interrupted turn — Codex 1.13.0 now closes every sub-agent the turn started, so their cards stop hanging on "running". (#806, @xintaofei)

Thanks to @kekxv for the feedback.

---

发布版本 0.32.0

这一版 Claude Code 和 Codex 一起升级，codeg 也接住了它俩刚学会表达的两件事：提示信息改为 toast 弹出，不再写进回复正文；上下文压缩会如实显示它是怎么结束的，以及保留下了什么。
底层方面，codeg 现在通过官方的 Agent Client Protocol 2.2 运行时与所有智能体通信。服务器部署可以按主机名访问开发服务，不必再预先猜一段端口范围；网页版也补上了仍然生效的浏览器设置。

新增

• 上下文压缩可以展开查看保留下来的摘要——Claude Code 或 Codex 会话进行中发生压缩时，分隔线上会多出一个「摘要」开关，点开就能看到模型从被压掉的历史里留下了什么，生成过程中实时显示。（#809、#814，@xintaofei）
• 服务器部署可以按主机名而不是端口访问开发服务——把 CODEG_BRIDGE_HOST_PATTERN 设为 auto 或 {port}.preview.example.com 这类模板后，3000.codeg.example.com 会经由 codeg 已在监听的端口直达 3000 端口，不必再预先开放一段端口范围。（#788 由 @kekxv 反馈，#801，@xintaofei）

改进

• 内置智能体版本更新： Claude Code ACP 0.81.0（Claude Code 2.1.280）、Codex ACP 1.13.0（Codex CLI 0.155.1，gpt-5.2 与 gpt-5.4-mini 随之下线）。（#806，@xintaofei）
• Claude Code 与 Codex 的提示信息改为 toast 弹出，不再以粗体行写进回复——模型回退、hook 拦截了你的提示、配置或弃用警告都在此列，其中警告和错误还会留在会话横幅上。（#809，@xintaofei）
• Codex 执行命令时，输出会实时流进卡片，不再整段时间停在 [Terminal: …] 占位符上、等命令结束才一次性填满。（#806，@xintaofei）
• 网页版的「设置 → 浏览器」补上了仍然生效的设置——本机服务、站点规则和终端链接菜单，终端里启动服务时弹出的提示终于可以关掉，或改成直接打开标签页。（#788 由 @kekxv 反馈，#798，@xintaofei）
• 写入智能体的 JSON 配置时不再打乱键的顺序——比如保存 MCP 服务器时，文件其余部分保持你原来写的顺序，不会被整体按字母重排；工具参数也按智能体发来的顺序显示。（#814，@xintaofei）
• codeg 现在通过官方的 Agent Client Protocol 2.2 运行时与所有智能体通信，某条消息处理出错不会再拖垮整条连接。（#814，@xintaofei）

修复

• 压缩分隔线如实显示压缩的结局——失败会给出原因，被中断或取消的不再一直转圈，Codex 同一回合里的两次压缩也各有一条分隔线。（#806、#809，@xintaofei）
• 历史记录里的 Claude Code 子智能体卡片直接从汇报内容开始，不再先显示 Claude Code 2.1.277 及以上版本垫在前面的一段来源说明。（#806，@xintaofei）
• 恢复 Claude Code 会话后，第一轮不再把之前整段会话的 Token 都算进来，Token 用量看板里的分模型数据不会在恢复后虚高。（#806，@xintaofei）
• Codex 的子智能体不会再比失败或被中断的回合活得更久——Codex 1.13.0 会关掉该回合启动的所有子智能体，卡片不再一直挂在「运行中」。（#806，@xintaofei）

感谢 @kekxv 的反馈。