Release version 0.15.5

• feat(agent): Hermes Agent joins the workbench. Hermes (from Nous Research) is now a first-class agent alongside Claude Code, Codex, OpenCode, Gemini, OpenClaw and Cline. A guided setup in Settings walks you through choosing a model provider and entering your key — with a linked editor for the key and the Hermes config — and codeg provisions the Python toolchain for you on first launch. Hermes works with more than 30 providers out of the box (OpenRouter, OpenAI-compatible endpoints, Anthropic, Google AI Studio, DeepSeek, xAI Grok, Z.AI / GLM, MiniMax, Kimi / Moonshot, Qwen, GitHub Copilot, Ollama Cloud, Nous Portal, and more), including your own custom OpenAI-compatible endpoint. It also supports MCP servers — so codeg's multi-agent delegation and your own MCP tools are available — and loads your existing Hermes conversation history into the sidebar.
• feat(chat): Questions you've answered now stay in the conversation. Building on the ask-a-question card from 0.15.3, an answered question is kept as a dedicated card in the message stream, mirroring the live card's layout with your chosen options shown as selected. The record stays collapsed by default to keep the transcript tidy, and expands whenever you want to revisit what was asked and what you picked.
• feat(chat): Agent plans now render as an inline card. When an agent shares or updates a plan, it appears as a dedicated card right in the conversation instead of only behind the corner chip. Long plans cap their height and scroll, so a large checklist never takes over the view.
• feat(chat): Live feedback checks read as a tidy capsule. When an agent picks up the notes you've left through Live feedback, the result now shows as a collapsed capsule that summarizes how many notes arrived and previews the first one, expanding to the full list with locale-aware send times. Routine checks that found nothing new — and checks still in flight — are hidden so they don't clutter the transcript.
• chore(registry): Bundled Claude Code updated to 0.43.0.
• style(chat): The composer toolbar controls are more compact.

发布版本 0.15.5

• 功能(代理)：Hermes Agent 加入工作台。Hermes（来自 Nous Research）现已成为与 Claude Code、Codex、OpenCode、Gemini、OpenClaw、Cline 并列的一等代理。设置中的向导会引导你选择模型 provider 并填入密钥——同时提供密钥与 Hermes 配置的联动编辑器——首次启动时由 codeg 自动为你装好 Python 工具链。Hermes 开箱即支持 30 多家 provider（OpenRouter、OpenAI 兼容端点、Anthropic、Google AI Studio、DeepSeek、xAI Grok、Z.AI / GLM、MiniMax、Kimi / Moonshot、Qwen、GitHub Copilot、Ollama Cloud、Nous Portal 等），也包括你自建的 OpenAI 兼容端点。它还支持 MCP 服务器——因此 codeg 的多智能体委托和你自己的 MCP 工具均可使用——并会把你已有的 Hermes 会话历史载入侧边栏。
• 功能(聊天)：你回答过的问题现在会留在会话中。在 0.15.3 的提问卡片基础上，已回答的问题会作为一张专属卡片保留在消息流里，沿用实时卡片的布局，并将你所选的选项标记为已选中。该记录默认折叠以保持记录整洁，需要时展开即可回看当时的提问与你的选择。
• 功能(聊天)：代理的计划现在以内联卡片呈现。当代理给出或更新计划时，它会作为一张专属卡片直接显示在会话中，而不再只藏在右上角的圆形图标后；较长的计划会限制高度并滚动，再大的清单也不会占满视图。
• 功能(聊天)：实时反馈的查询以紧凑胶囊呈现。当代理读取你通过「实时反馈」留下的留言时，结果会显示为一个折叠胶囊，概括收到的留言数量并预览第一条，展开后是带本地化发送时间的完整列表。没有新内容的例行查询，以及仍在进行中的查询都会被隐藏，避免干扰记录。
• 更新(注册表)：内置 Claude Code 升级至 0.43.0。
• 样式(聊天)：输入框工具栏的控件更加紧凑。