Changelog

行为变化：听写设置不再提供「使用对话模型直接转写音频」的选项（该方式需要支持音频输入的模型，普通文本模型会转写失败）——已配置该方式的会话会自动切回「禁用」，请改用本地模型或云端转写服务。另外，输入框工具区已重新布局：添加文件 / 图片的入口移至左下角「+」菜单，麦克风按钮移至发送按钮旁。

新增

• 会话模式一键切换：在输入框中即可在 自主 / 手动 / 智能 / 仅聊天 四种模式间切换，仅对当前会话生效；新会话的默认模式仍在设置中选择。
• 全局右键菜单：在对话区右键即可复制所选文字、复制整条消息、朗读，或把选中内容作为引用加入输入框；空白处右键不再弹出浏览器默认菜单。
• 听写转写语言设置：本地听写新增转写语言选择（此前固定按英文识别），支持中文、英语、日语、韩语等 15 种语言。
• 「+」添加菜单：输入框左下角新增添加入口，上传图片（自动压缩、可预览）与上传文件一步完成。
• 历史消息窗口：超长会话默认只加载最近 100 条消息，打开速度显著提升；更早的历史可一键展开（每次 100 条），Ctrl+F 全历史搜索功能保留不变，且不再出现加载动画闪烁。
• 消息操作行统一：所有回复都提供复制入口（此前工具调用类回复没有），并新增「复制为 Markdown」（仅纯文本，贴入 GitHub / 编辑器更干净）。
• 发送即刻响应：新对话发送消息后立即进入对话页（会话在后台创建），失败时保留草稿可一键重试。
• 等待状态可操作：「正在等待你的确认」提示条现在会显示等待数量与类型，点击即可定位到对应的审批卡片。

变更

• 输入框工具区重新布局：添加文件 / 图片的入口移至左下角「+」菜单；麦克风按钮移至发送按钮旁；工具排与输入框边缘的间距整体收紧。
• 听写转写失败提示更友好：使用了不支持音频的模型时，会给出更换听写方式的指引，而不是显示技术错误详情。
• 浏览器面板工具条合并为单行：导航与页面动作排在同一行，且在浏览器未打开时隐藏不可用的导航按钮（此前为一排置灰按钮）。

移除

• 本次发布没有移除既有功能；听写「使用对话模型直接转写」选项的调整见顶部行为变化。

修复

• 更新安装不再弹出向导：点击「安装并重启」后，更新在后台完成并自动重启——期间仅显示一个会自动关闭的进度条，不再弹出需要逐步点击的安装向导窗口。
• 上下文压缩更干净：修复压缩超长对话时，内部的压缩进度信息可能进入模型上下文并影响回答质量的问题。
• 上传文件无响应：修复了部分环境下选择文件后没有任何反馈的问题（此前会连续弹出两个文件选择器）。

安全

• 本次发布未包含已知安全公告；随常规更新一并加固。

Behavior change: dictation settings no longer offer the option to "transcribe audio directly with the conversation model" (it requires a model that supports audio input — plain-text models fail to transcribe). Sessions previously configured this way automatically revert to "Disabled"; please switch to a local model or a cloud transcription service instead. The input box toolbar is also relaid out: the image and file upload entries now live in the "+" menu at the bottom-left, and the microphone button sits next to the send button.

Added

• One-click session mode switch: switch between Autonomous / Manual / Smart / Chat-only right from the input box, applying to the current session only; the default for new sessions is still chosen in Settings.
• Global context menu: right-click in the conversation to copy selected text, copy the whole message, read it aloud, or quote it into the input box; right-clicking empty space no longer shows the browser's default menu.
• Dictation transcription language: local dictation gains a transcription-language setting (previously fixed to English recognition), covering Chinese, English, Japanese, Korean and 11 more languages.
• "+" Add menu: a new add menu at the bottom-left of the input box — upload images (auto-compressed with preview) or files in one step.
• History window for long sessions: very long sessions now load only the latest 100 messages by default (dramatically faster to open); older history expands 100 at a time, Ctrl+F full-history search is preserved, and the flickering loading animation is gone.
• Unified message actions: every reply now has a copy entry (tool-call replies previously had none), plus a new Copy as Markdown (plain text only — cleaner when pasting into GitHub or editors).
• Instant send on new chats: sending from a new chat enters the conversation immediately (the session is created in the background); on failure your draft is kept for one-click retry.
• Actionable waiting state: the "waiting for your confirmation" bar now shows how many items are waiting and of which type, and clicking it scrolls to the corresponding approval card.

Changed

• Input toolbar relayout: the image and file upload entries move into the new "+" menu at the bottom-left; the microphone button now sits next to the send button; overall spacing around the toolbar row is tighter.
• Friendlier dictation errors: transcribing with a model that does not support audio now shows guidance on switching dictation providers instead of raw technical details.
• Browser panel toolbar merged into a single row: navigation and page actions share one row, and unavailable navigation buttons are hidden while no browser window is open (previously a row of greyed-out buttons).

Removed

• No existing features were removed in this release; see the behavior change at the top regarding the dictation option adjustment.

Fixed

• No more setup wizard during updates: clicking "Install & Restart" now finishes the update in the background and restarts the app automatically — only a self-closing progress bar is shown, instead of the full setup wizard.
• Cleaner context compaction: fixed an issue where internal compaction progress details could leak into the model's context during long-conversation compaction and affect response quality.
• File upload not responding: fixed an issue where selecting a file gave no feedback in some environments (two pickers were shown back to back).

Security

• No known security advisories are included in this release; routine updates and hardening apply as usual.

---

ChengYoung 1.20.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.20.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

行为变化（Breaking）：本次同步上游后，执行引擎全面切换至状态机（State Machine）——旧执行循环（agent loop）已移除，状态机成为唯一执行路径；扩展改为首次使用时才启动（新对话不再等待全部扩展就绪，启动显著提速）。绝大多数对话行为不变；如遇边缘行为差异请反馈。

新增

• 会话导出为交互式 HTML：将会话导出为单文件 HTML 交互式查看器，便于离线归档与分享。
• 消息引用：在对话中选中文字，即可一键「加入消息」作为引用块继续提问。
• 上下文压缩可视化编辑：上下文压缩阈值（默认 80%，自动压缩上限 225k token）现在可以在压缩提示条内直接查看与编辑，无需手改配置。
• 新声明式模型提供商：新增 AIgateway 与 Z.ai Coding Plan 等声明式提供商定义。
• 首次配置询问运行模式：首次运行引导配置时会询问会话的运行模式。
• 分布式追踪上下文传播（面向集成开发者）：ACP 提示的 W3C 追踪上下文现在会传播到 MCP 工具调用。

变更

• 状态机成为唯一执行引擎：旧执行循环已移除，所有会话统一由状态机驱动（含空响应重试、工具调用余量核算、子代理前台化等新能力）。
• 扩展按需启动：扩展管理器重构为按会话租约（lease）管理，扩展在其首次被会话使用时才启动进程——新会话创建不再等待全部扩展就绪。
• 提供商会话路由统一：会话的提供商路由现在统一由单一 ProviderManager 承载。
• 调度能力模块化：调度（Scheduler）、平台应用、聊天召回、ACP HTTP 等能力改为按 feature 装配。
• 工具链升级：Rust 1.99.0。

移除

• Nostr 会话分享：随上游一并移除（本产品从未在界面开放该入口）。
• MCP sampling：模型侧采样（create_message）随上游重构移除。
• 后台子代理与编排器：后台子代理、orchestrator 与旧执行循环一并移除（Doctor 收敛为会话内能力）。

修复

• 侧栏会话列表新增加载状态：会话列表加载中会显示「正在加载…」而非空白（并修复快速切换时的竞态）。
• 压缩计费口径修复：长上下文价格分档正确应用于成本估算；Bedrock 不再对非上下文类校验错误重试；缓存写入 token 从 Responses API 用量读取。
• 提供商令牌刷新：GitHub Copilot 令牌被撤销后列出模型时会自动刷新（且只刷新一次）。
• 自适应思考：Claude Sonnet 与 Claude Haiku 5.5 的自适应思考正确生效。
• 协议版本声明：initialize 时上报已实现的协议版本。
• GOOSE_MODE 校验：跨 ACP 提供商拒绝非法的运行模式值。
• 调度器工具先完成在途调用：达到最大轮次上限前会先等待在途工具完成。

安全

• 本次同步未包含已知安全公告；上游依赖与子进程处理随常规更新一并加固。

Added

• Interactive HTML session export: export a session as a single-file interactive HTML viewer for offline archiving and sharing.
• Message quoting: select text in the conversation and add it to your next message as a blockquote with one click.
• Visual context-compaction editing: the auto-compaction threshold (default 80%, capped at 225k tokens) can now be viewed and edited directly on the compaction alert bar — no manual config edits.
• New declarative model providers: AIgateway, Z.ai Coding Plan and more declarative provider definitions.
• First-run mode prompt: the first-run configure flow now asks for the session mode.
• Distributed trace context propagation (for integrators): W3C trace context from ACP prompts now propagates to MCP tool calls.

Changed

• State Machine is now the only execution engine: the legacy agent loop has been removed; every session is driven by the state machine (with empty-response retries, remaining-tool-call accounting, foregrounded subagents).
• Extensions start on first use: the extension manager was rebuilt around per-session leases — an extension process starts the first time a session requests it, so new sessions no longer wait for every extension to come up.
• Unified provider routing: all session provider routing now goes through a single ProviderManager.
• Modular scheduling: scheduler, platform-apps, chat-recall and ACP HTTP capabilities are now assembled via features.
• Toolchain: Rust 1.99.0.

Removed

• Nostr session sharing: removed along with upstream (never exposed in this product's UI).
• MCP sampling (create_message): removed with the upstream refactor.
• Background subagents & orchestrator: background subagents, the orchestrator and the legacy agent loop are gone (Doctor is now session-only).

Fixed

• Sidebar session list loading state: the list now shows a loading indicator instead of blank space (and a race on rapid refreshes is fixed).
• Cost accounting fixes: long-context price tiers apply to estimates; Bedrock no longer retries non-context validation errors; cache write tokens are read from Responses API usage.
• Provider token refresh: revoked GitHub Copilot tokens refresh when listing models (refreshing only once).
• Adaptive thinking: works correctly for Claude Sonnet and Claude Haiku 5.5.
• Protocol version stamping: the implemented protocol version is reported in initialize.
• GOOSE_MODE validation: malformed mode values are rejected across ACP providers.
• Pending tools finish before max turns: in-flight tool calls complete before the turn limit is enforced.

Security

• No known security advisories in this sync; dependency and subprocess hardening landed with the regular update.

---

ChengYoung 1.19.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.19.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 会话回放：会话历史列表与顶栏会话名菜单新增「查看回放」——全屏只读时间线按发生顺序还原一场对话：你的消息、AI 回复、工具调用与结果（子代理调用带专属徽标）、思考过程与系统事件；支持关键词过滤（检索范围含工具结果正文）与分页加载（每次 200 条）。
• 双阶段求助诊断：从错误通知的「问问 ChengYoung」发起的求助会话先进入只读诊断——模型不执行任何命令，只收集信息并给出分析建议（输入区顶部显示诊断徽标）；你确认后点「开始修复」，会话切换为修复模式并自动发出开始指令，模型给出工具操作供你逐条确认执行；切换失败会明确提示且徽标保留。
• 错误求助自带完整上下文：「问问 ChengYoung」现在会把错误标题、描述、堆栈与恢复建议整理为结构化求助草稿（路径、密钥类敏感信息自动脱敏），填入输入框供你补充场景后发送；不再仅发送一个英文模板句子。
• 网关指标新增引擎维度（实验性功能，默认关闭）：本机网关开启后，/metrics 端点新增 engine_ 前缀指标（引擎启动次数、自动重启次数、最近一次启动耗时）。

修复

• 中文与繁中界面补全「本地目录安装插件」的来源占位文案（此前为英文原文）。
• 会话卡片布局优化：悬停操作按钮合并进信息底行，卡片更紧凑、不再预留空行。

Added

• Session replay: new "View replay" actions in the session history list and the top-bar session menu open a full-screen, read-only timeline that reconstructs a conversation in order — your messages, AI replies, tool calls with results (sub-agent calls with a badge), thinking blocks and system events — with keyword filtering (search covers tool result text) and paginated loading (200 events per page).
• Two-phase diagnostic help: help sessions started from the "Ask ChengYoung" action on error notifications now begin in a read-only diagnosis phase — the model runs no commands and only gathers information and suggestions (a diagnostic badge shows above the input). Once you confirm, "Start fixing" switches the session to fix mode and automatically sends the kickoff instruction; the model then proposes tool actions for your per-item approval. A failed switch shows a clear notice and keeps the badge.
• Error help now carries full context: "Ask ChengYoung" builds a structured help draft — error title, description, sanitized stack trace and recovery hints (paths and secret-like values are redacted automatically) — into the input box for you to review and send; no more just a single English template sentence.
• Engine metrics on the gateway (experimental, off by default): once the local gateway is enabled, /metrics gains engine_-prefixed gauges (engine starts, automatic restarts, last start duration).

Fixed

• The "install from local directory" source placeholder in the plugin dialog is now properly translated in Simplified and Traditional Chinese (previously shown in English).
• Session card layout: hover actions merged into the info row — cards are more compact with no reserved empty row.

---

ChengYoung 1.18.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.18.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 内置帮助中心（用户指南）：对话页右上角的 ChengYoung Logo 现在打开全屏「用户指南」——16 篇离线文档随包分发（快速开始、安装与更新、本地模型、工作流、扩展、技能、调度、会话管理、上下文控制、插件、代码库分析、权限与安全、隐私、常见问题、使用技巧、限流与配额），目录树导航；可收起为悬浮图标随时回到对话，再次点击恢复到原阅读位置；非中英文界面自动切换至中文或英文文档并给出提示
• 凭据保护升级：应用保存的凭据（如云端模型 API Key）迁移到独立的系统密钥链命名空间，与同机安装的官方原版应用互不共享；升级时旧凭据自动迁移、无需任何操作；系统密钥链不可用时不再静默降级为明文文件，而是明确报错（安全行为收紧）

修复

• 扩展（MCP）配置校验更严格：添加扩展时，若 stdio 类型的命令字段中填入了网址，或 Streamable HTTP 类型的端点不是合法的 http(s) 地址，系统会立即在表单内提示并阻止保存（此前会先保存成功，连接时才暴露失败）

Added

• Built-in help center (user guide): the ChengYoung logo at the top-right of the chat page now opens a full-screen "User Guide" — 16 offline docs bundled with the app (quick start, install & update, local models, workflows, extensions, skills, scheduler, session management, context control, plugins, codebase analysis, permissions & safety, privacy, FAQ, tips, rate limits & quotas) with a table-of-contents tree; minimize it to a floating badge to jump back to the conversation and restore your reading position later; non-Chinese/English locales automatically fall back to the Chinese or English docs with a hint
• Stronger credential protection: credentials saved by the app (such as cloud model API keys) now live in a dedicated system keychain namespace, never shared with the official upstream app installed on the same machine; legacy credentials migrate automatically on upgrade with zero action needed; when the system keychain is unavailable the app now fails with a clear error instead of silently falling back to a plaintext file (security hardening)

Fixed

• Stricter extension (MCP) config validation: when adding an extension, if a URL is entered in the command field of a stdio extension, or the endpoint of a Streamable HTTP extension is not a valid http(s) URL, the app flags it inline and blocks saving (previously it saved first and only failed when connecting)

---

ChengYoung 1.17.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.17.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 从本地目录安装插件：除 git 仓库外，现在可以直接选择电脑上的插件文件夹进行安装（适合企业内网与离线分发场景）。本地目录安装同样走「下载 → 启用前审阅」两步确认；「自动更新」仍仅对 git 来源开放（本地目录没有可拉取的远端）

修复

• 插件披露更完整：插件提供的命令（commands）现在也会列在安装确认对话框与插件详情中（此前只列技能、MCP 服务器与钩子）；卸载提示同步更新

Added

• Install plugins from a local directory: alongside git repositories, you can now point the installer at a folder on your computer (useful for offline and intranet distribution). Local installs go through the same two-step "download → review before enabling" flow; per-plugin auto-update remains git-only, since a local directory has nothing to pull from

Fixed

• More complete plugin disclosure: a plugin's commands are now listed in the install review dialog and the plugin details (previously only skills, MCP servers, and hooks were shown); the uninstall prompt is updated accordingly

---

ChengYoung 1.16.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.16.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 插件系统（首批）：新增「设置 → 插件」，可以从 git 仓库安装插件，为 ChengYoung 扩展技能、命令与生命周期钩子。安装分两步：先下载，启用前先审阅——清单会列出插件提供的组件，钩子明确标注「会在本机执行命令」；安装后默认停用、由你逐个启用；「自动更新」默认关闭、需逐插件手动开启；卸载会同时清理配置与文件、不留残留。隐私说明同步更新：插件只在你安装或更新时从其来源下载，此外无任何联网行为
• 本地模型自动调用显卡：启动本地模型时按显存大小自动决定放入显卡的层数——放得下就整体进显卡（更快），放不下就自动把多出的层留在内存，避免「显存不够还硬塞」导致的加载失败
• 双显卡笔记本的本地推理更稳：核显 + 独显并存的机器上，此前本地模型可能因显存被分配到核显而启动失败；现在启动时固定使用独立显卡
• 更新失败可见：应用内检查或下载更新失败时，失败原因会常驻显示在设置里（此前只弹一次提示，错过就无处可看）；托盘菜单新增「检查更新」入口

修复

• 移除已失效的「分享到 Nostr」入口：该能力已退役，旧入口点了也不会成功；从 Nostr 链接导入会话不受影响

Added

• Plugin system (first batch): a new Settings → Plugins page lets you install plugins from git repositories to extend ChengYoung with skills, commands, and lifecycle hooks. Installation is two-step: download first, then review before enabling — the dialog lists the plugin's components and clearly marks hooks that run commands on this machine. Plugins are disabled by default and enabled individually; per-plugin auto-update is off by default and must be turned on manually; uninstalling removes both config entries and files with nothing left behind. The privacy notice is updated accordingly: plugins are downloaded from their source only when you install or update them, with no other network activity
• Local models use your GPU automatically: when starting a local model, the number of layers offloaded to the GPU is now chosen from your VRAM size — the model goes entirely to the GPU when it fits (faster), otherwise extra layers stay in memory, avoiding failures from over-offloading
• More reliable local inference on dual-GPU laptops: on machines with both an integrated and a discrete GPU, local models could previously fail to start when memory was allocated to the integrated GPU; startup now pins the discrete GPU
• Update failures are visible: when an in-app update check or download fails, the reason now stays visible in Settings (it previously flashed once and was gone); the tray menu gains a "Check for updates" entry

Fixed

• Removed the defunct "Share to Nostr" entry: the capability was retired and the old entry never succeeded; importing sessions from Nostr links is unaffected

---

ChengYoung 1.15.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.15.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 本地 OpenAI 兼容网关：本机上的 IDE、脚本与第三方工具可以直接连接你已下载的本地模型（也可以把请求用你自己的 API Key 转发到你配置的云端提供商）。默认不监听——在「设置 → 网关」里配置别名并开启后才会启动；仅监听本机 127.0.0.1，所有请求都需要令牌（令牌明文只保存在系统凭据库），并且面板里常显数据去向说明
• 点击通知直接回到对话窗口：点击「任务完成」这类系统通知，即可把 ChengYoung 窗口带回前台
• 标题栏新增置顶图钉：一键把窗口置顶；同时开多个窗口时，每个窗口各记各的状态

修复

• 全新安装也会把数据放在 ChengYoung 自己的目录下：此前只有从旧版本升级过的用户会迁移数据，全新安装的用户数据仍写在旧版目录里（与旧版应用并装会互相影响）；现在两种情况一致，都在 %APPDATA%\ChengYoung\ 下
• 应用内「项目提示」帮助页的配置目录改成真实路径：此前仍写着品牌化之前的旧目录
• 首次启动的数据说明改写为「你的数据，始终在你手里」：四条改为「存储位置 / 无遥测 / 审计日志 / API Key」的分组写法，写明数据保存在本机 %APPDATA%\ChengYoung 目录且不经过我们的服务器、不会向任何外部地址上传遥测或行为数据、审计日志默认加密存储且仅你可读写（可随时关闭或彻底删除）、API Key 只存放在操作系统密钥链中且不以明文写盘
• 右栏文件树在每轮对话结束后自动刷新：此前要手动刷新才能看到新文件
• 中文回复更一致：强化了输出语言指令，减少回复里中英混排
• 网关在异常退出后能正常启动：断电或进程被杀会留下半条审计记录，此前会让网关无法启动；现在只丢弃这条损坏的尾部记录并记入日志，其余记录完整保留（本机加密审计文件位于数据目录的 gateway\ 下）
• 提示文件改用 ChengYoung 自己的名字 .cyhints：此前设置 → 聊天的标题、配置弹窗与「使用 .goosehints」帮助页里都写着上游的 .goosehints，现在界面与帮助文档统一为 .cyhints。旧项目里的 .goosehints 照旧会被读取（不必改名、内容零丢失），应用新建或保存时写入 .cyhints
• 右栏浏览器工具条改为图标按钮：打开 / 关闭 / 用系统浏览器打开 / 后退 / 前进 / 刷新只留图标，含义改为鼠标悬停提示显示（键盘聚焦同样显示）—— 这些文案在其它语言里可能长出一倍，此前会把按钮行折成两三行、把网页区域挤小
• 回答「怎么做」类问题时先说明、不抢跑：本地小模型面对「怎么创建工作流」这类提问，会先用文字把方法讲清楚，再主动提议代为执行，而不是上来就运行命令演示
• 工作流目录指引统一为 .agents/recipes/：模型介绍工作流的存放位置时，统一指向项目内的 .agents/recipes/ 目录（各工具通用的约定）；老项目里 .goose/recipes/ 下的工作流照旧会被读取，无需迁移

安全

• 网关仅绑定本机回环地址，校验 Host 头（防 DNS 重绑定），不返回任何 CORS 头；除健康检查外所有端点都要求令牌
• 审计日志只记录元数据（模型、Token 数、延迟），对话正文永不写入，且在本机加密保存；面板提供一键清空

Added

• Local OpenAI-compatible gateway: IDEs, scripts and third-party tools on this computer can connect directly to the local models you already downloaded (or forward requests to the cloud provider you configured, using your own API Key). It does not listen by default — it starts only after you add an alias and turn it on in Settings → Gateway. It binds to 127.0.0.1 only, every request needs a token (the plaintext token is stored in the system keychain), and the panel always shows where data goes
• Clicking a notification brings the chat window back to the front
• New pin button in the title bar: keep the window always on top; with multiple windows open, each window tracks its own state

Fixed

• Fresh installs now keep their data under ChengYoung's own directory too: previously only upgrades migrated it, while a brand-new installation still wrote into the legacy directory (so the two interfered); both paths now use %APPDATA%\ChengYoung\
• The bundled "project hints" help page shows the real config directory: it still named the pre-branding path
• The first-launch data notice now reads "Your data stays in your hands": the four points are grouped as Storage / No telemetry / Audit logs / API keys — stating that data stays in your local %APPDATA%\ChengYoung folder and never passes through our servers, that no telemetry or behavioral data is uploaded to any external address, that audit logs are stored encrypted by default and readable only by you (turn them off or delete them at any time), and that API keys live only in your OS keychain and are never written to disk in plain text
• The file tree in the right panel now refreshes automatically at the end of every turn (it previously needed a manual refresh)
• More consistent Chinese replies: the output-language instruction was strengthened to reduce mixed-language answers
• Gateway recovers after a crash or forced kill: a power loss or killed process could leave a truncated audit record, which previously prevented the gateway from starting; the app now discards only that corrupted trailing record and logs it, while all other records stay intact (the local encrypted audit file is stored in the gateway subfolder of the data directory)
• Project hints now use ChengYoung's own file name .cyhints: the Settings → Chat page title, the configuration dialog, and the bundled help page used to name the upstream .goosehints; the UI and the help documents now say .cyhints. Existing .goosehints files are still read, so nothing needs renaming and no content is lost; the app writes .cyhints when it creates or saves the file
• Browser toolbar uses icons only: Open / Close / Open in system browser / Back / Forward / Refresh now show a hover tooltip (also on keyboard focus) instead of text — those labels can be twice as long in other languages, which used to wrap the button row onto two or three lines and shrink the page area
• How-to questions get an explanation first: when asked things like "how do I create a workflow?", local small models now answer in words first and offer to run it for you, instead of jumping straight into running demo commands
• Workflow directory guidance unified on .agents/recipes/: when describing where workflows live, the model now points to the project's .agents/recipes/ directory (a tool-agnostic convention); workflows under .goose/recipes/ in older projects are still read — nothing needs migrating

Security

• The gateway binds to the loopback address only, validates the Host header (anti DNS-rebinding) and returns no CORS headers; every endpoint except the health check requires the bearer token
• Audit logs keep metadata only (model, token counts, latency) — conversation content is never written — and are stored encrypted on this computer, with a one-click clear button

---

ChengYoung 1.14.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.14.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 自动检查与下载更新：应用默认每 4 小时自动检查更新（首次检查在启动 5 分钟后），发现新版本会自动后台下载并在就绪时通知——安装仍需确认；两个开关（自动检查 / 自动下载）均可在设置 → 关于 ChengYoung 中关闭
• README 说明增强：新增修改声明（Apache-2.0 第 4 节）、零遥测自测方法、minisign 公钥指纹、内存分档建议与常见问题（FAQ）

修复

• 修复托盘「停止引擎」后托盘图标无响应的问题：确认对话框此前在主线程上同步等待，导致托盘图标的左键与右键全部失去响应；现改为非阻塞弹窗，停止操作在确认后正常执行，无需重启应用

Added

• Automatic update checks and downloads: the app now checks for updates every 4 hours by default (first check 5 minutes after launch), downloads new versions automatically in the background and notifies you when ready — installation still asks for confirmation. Both switches (automatic check / automatic download) can be turned off in Settings → About ChengYoung
• README improvements: notice of modifications (Apache-2.0 §4), zero-telemetry self-verification guide, minisign public-key fingerprint, tiered memory recommendations, and a FAQ

Fixed

• Fixed the tray icon becoming unresponsive after "Stop engine": the confirmation dialog previously blocked the main thread, freezing all tray interactions; the dialog is now non-blocking and the stop action runs normally after confirmation, with no restart required

---

ChengYoung 1.13.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.13.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

新增

• 引擎生命周期管理：本地推理引擎意外退出后，应用会自动按退避策略重启（立即 / 2 秒 / 8 秒，最多 3 次）；长期稳定运行（超过 60 秒）后的崩溃不会继承历史失败。多次重启仍失败时才显示错误，并提供诊断与日志入口
• 托盘新增引擎控制：托盘菜单显示引擎状态（运行中 / 已停止），并提供「停止引擎」与「启动引擎」入口。停止引擎只释放模型占用的显存——聊天记录保留、应用保持打开（需二次确认）；停止引擎 ≠ 退出应用
• 错误页按引擎状态区分：引擎是从托盘主动停止时，错误页显示「启动引擎」而非「重启」；连续两次重启失败后收起重试按钮，只保留「打开日志文件夹」诊断出口

Added

• Engine lifecycle management: after an unexpected exit of the local inference engine, the app now restarts it automatically with backoff (immediately / 2 s / 8 s, up to 3 attempts); a crash after a long stable run (over 60 s) does not inherit past failures. The error state is shown only after repeated restart attempts fail, with diagnostics and log access
• Engine controls in the tray: the tray menu now shows the engine state (running / stopped) and offers "Stop engine" / "Start engine". Stopping the engine only frees the model's GPU memory — chat history is kept and the app stays open (with a confirmation dialog). Stopping the engine is distinct from quitting the app
• Error page distinguishes engine states: when the engine was stopped from the tray, the page offers "Start engine" instead of "Restart"; after two consecutive failed restarts the retry button is replaced by an "Open logs folder" diagnostics exit

---

ChengYoung 1.12.0

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.12.0_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.

修复

• 错误页的「重试」现在真正可用：此前本地推理引擎被停止或意外退出后，错误页的重试只会反复检查一个已不存在的服务、永远失败；现在重试会让应用自动重启引擎并重新连接（约 3-5 秒）。重启本身失败时提供「打开日志目录」，便于附在反馈里排查
• 系统信息的 OS 一行现在带平台名（Windows 10.0.26300），不再只有裸版本号

Fixed

• The "Retry" button on the error page now actually works: after the local inference engine was stopped or crashed, retrying only re-checked a dead endpoint and always failed; retrying now restarts the engine automatically and reconnects (about 3-5 seconds). If the restart itself fails, an "Open logs folder" action is offered for troubleshooting feedback
• The OS line in system info now includes the platform name (Windows 10.0.26300) instead of a bare version number

---

ChengYoung 1.11.1

Artifacts

• latest.json - Tauri updater manifest (minisign signature enables auto-update)
• SHA256SUMS.txt - SHA-256 checksums for the assets above

Verify the download
certutil -hashfile ChengYoung_1.11.1_x64-setup.exe SHA256 (compare with SHA256SUMS.txt)

Licensing
Apache License 2.0. See LICENSE and NOTICE bundled alongside the app executable inside the installed application.