Host repair could fail while adopting the published OpenCode Runtime, then
repeat package and payload verification and carry durable metadata snapshots
for recovery. Host preparation now verifies each acquired compound archive
once, adopts signed Agent and Runtime metadata without rereading payload trees,
and retries failed work by cleaning staging and preparing fresh.
The desktop and Agent versions are advanced to 0.11.9 with the approved
bilingual release notes. Remote Projects remain a disabled-by-default technical
preview, Agent packages remain separate Linux x64/arm64 releases, and this
release has no LoongArch preview.
Release note: 修复 Host 更新采用失败，移除重复远端包体校验，并将中断恢复简化为清理暂存后重新准备。
Published Host updates could fail while the desktop reverified Runtime against
its bundled lock and repeatedly traversed remote payloads. Host preparation now
verifies and extracts once, adopts Agent and Runtime on one pinned connection,
and uses registered metadata for normal health, capability, and prompt paths.
Interrupted commits and adoption retain bounded recovery and rollback state.
Desktop and Agent versions are 0.11.8. Remote Projects remain a technical
preview; the Agent targets Linux x64 and arm64, with no LoongArch preview.
Release note: 修复正式环境 Host 更新失败并移除重复远端包体扫描；中断恢复与清理失败不再破坏已健康环境。
Add the approved matching Chinese and English notes for the desktop 0.11.7
release and its separately published Agent 0.11.7 requirement. Remote Projects
remain a technical preview, and no LoongArch preview is included.
An interrupted dispatch could leave the same user input both in conversation
history and in the pending queue, causing it to be sent again after restart.
Persisted user messages now retain their queue identity, startup recovery drops
only matching materialized inputs, and conversation branches discard that
ownership marker.
Explicit GoodBuddy transfer now leases a verified local Agent package when the
catalog is unavailable or the local version is at least as new, while a known
newer online package still wins. Prepare both the desktop and Agent locks for
0.11.7; the experimental LoongArch preview remains excluded.
Release note: 修复对话中断后同一条排队输入可能重复发送的问题；GoodBuddy 传输现在可复用已验证的本地 Agent 包，同时不会阻止已知的线上新版。
Managed SSH project selection repeatedly activated the remote Host and could
leave idle ACP bindings rejected as stale-controller after a controller
generation change. Host environment updates also coupled project state to
component installation evidence and presented a crowded control surface.
Project selection is now local-only, one Host connection serves compatible
project and conversation callers, idle bindings are safely replaced only
after proven controller takeover, and active prompts keep exact resume/replay.
Remote environment setup now uses explicit signed compound package
preparation with bounded transfer, rollback, recovery, and clearer settings.
Managed Hosts must be updated to separately distributed Agent 0.11.6 before
the daemon-side controller recovery fix takes effect. Desktop packages do not
embed the Agent or remote Runtime, and existing project data is preserved.
Release note: 托管 SSH 项目切换不再重复连接，同一 Host 可顺畅承载多个项目和对话；同时修复重连后的 stale-controller，并优化远程环境安装、更新与状态布局。
The Chinese download cards briefly exposed the GitHub fallback before OSS index validation completed. They now stay disabled while loading and only show GitHub if the OSS request or validation fails; English downloads remain unchanged.
Release note: 中文官网下载入口加载 OSS 索引期间不再短暂跳转 GitHub，仅在索引失败时回退。
Add the approved Simplified Chinese and English release notes for sidebar brand customization, independent Anthropic output limits, and restored composer and brand guidance.
The primary sidebar brand was fixed to the built-in name, subtitle, and logo. Appearance settings now let users preview and save a custom brand name, localized Chinese and English subtitles, and a validated local PNG, JPEG, or WebP logo, with default-logo and full-reset actions.
Customization remains device-local and limited to the top-left brand area; installer, update, Agent, and protocol identities remain GoodBuddy. The desktop package version is now 0.11.6.
Release note: 新增“外观 → 品牌定制”，可修改左上角品牌名称、中英文副标题和本地 Logo，并支持实时预览、恢复默认及本机持久化。
The primary sidebar showed only the GoodBuddy name after its supporting brand line was removed. It now displays the localized “智能工作台” / “Intelligent Workspace” subtitle beneath the product name again.
Release note: 恢复左上角 GoodBuddy 标题下方的“智能工作台”副标题，使品牌区域的信息层级更加完整。
The composer placeholder had been reduced to only the message prompt, hiding send, newline, and paste guidance unless users hovered the field. The full localized keyboard guidance now appears directly in the empty text area again for both chat and image generation.
Release note: 恢复聊天输入框中的发送、换行和粘贴快捷键提示，空输入框会再次直接显示完整操作说明。
Wrapped feature rows were centered independently, which shifted the lower-right item away from the column above it. The Chinese homepage now uses a shared two-column grid and collapses to one aligned column on narrow screens.
Release note: 官网首页特性列表现在按列对齐，桌面与移动端布局更整齐。
The homepage hero paragraph and page description now focus on GoodBuddy's desktop assistant and Agent Runtime capabilities. Download options and architecture support remain unchanged.
Release note: 官网首页产品介绍现更聚焦桌面助手与 Agent Runtime 能力。
The Linux download card now presents only the preview version, DEB format, size, and checksum. Preview index validation and fail-closed download behavior are unchanged.
Release note: 官网龙芯下载信息现仅展示版本、包格式、大小与校验值。
The Chinese Linux download card now includes a LoongArch processor option and fixes its package type to DEB. It reads a separate strictly validated OSS preview index, while the formal six-target release index and English GitHub downloads remain unchanged.
The page keeps three symmetric platform cards, disables only the LoongArch selection when its index is unavailable, and labels the package as unverified on real LoongArch hardware.
Release note: 官网 Linux 下载新增龙芯 LoongArch 处理器选项，选择后提供独立 DEB 预览包；正式下载与更新索引保持不变。
Direct Anthropic connections reused the configured context window as max_tokens, which could impose an unintended output value or send a provider-invalid request. Anthropic connections now expose an independent per-response maximum output setting, defaulting to 32K for the protocol-required field, while OpenAI direct requests remain without an added output token cap and direct tool rounds remain unmetered.
Release note: Anthropic 直连模型现在可单独配置单次最大输出，不再复用上下文窗口；OpenAI 直连请求和工具调用轮次不增加额外配额。
Generate SHA256SUMS from inside the timestamped artifact directory so it records only the DEB filename and remains verifiable after copying the preview output elsewhere.
Legacy key-only environment deployments retain their historical model endpoint, name, and protocol while generic model variables continue to take precedence. Agent inventory scanning now overlaps the signed catalog check instead of waiting for the network first.
The separate LoongArch preview builder derives node-pty from the candidate lockfile and verifies the installed version before cross-compiling it, preventing stale preview-only pins.
Valid Agent packages could be rejected when packaged trusted-key JSON used CRLF, and Settings could not show whether a newer compatible Agent existed. Registry formatting is now parsed independently of cryptographic trust, and Settings reads only the signed catalog to report local and latest versions.
New installations use a credential-free local Ollama-compatible profile. The v20 migration changes only untouched historical defaults, while explicit profiles and legacy environment aliases remain compatible. Magic Notes count badges no longer shift navigation rows.
Release note: 修复 Agent 下载兼容性并在设置中显示更新状态；新安装默认连接本地模型，保留显式用户配置；魔法笔记待办数字不再改变侧栏菜单高度。
The unpublished 0.11.3 candidate could not validate the DeepSeek Harness node-pty prebuilds on every native target, and catalog signing could misread large compound Agent payloads. Release packaging now verifies the rc.8 native layout and writes deterministic stored .gbagent archives with bounded central-directory, mode, CRC, SHA-256, and signature checks.
The 0.11.4 recovery also pins reviewed dependency lifecycle scripts, packages the omitted ONNX Runtime license, and carries the approved unpublished notes forward without changing the immutable failed tags or adding a LoongArch package.
Release note: 修复跨平台桌面包和大文件 Agent 包的发行校验失败，并将未发布的 0.11.3 内容顺延至 0.11.4。
The desktop runtime still pinned the rc.6 Harness family. It now uses the coherent rc.8 package set, adapts the revised image-attachment limits and error contract, and derives release checks from the lockfile. The managed SSH Agent package remains unchanged.
Release note: 内置 DeepSeek Harness 已升级至 0.1.0-rc.8，并适配新版图片附件限制；托管 SSH Agent 包不受影响。
The total-deadline test relied on a timer firing at an exact millisecond boundary, so a shared runner could legally begin the second extension before observing expiration. Use the existing finite synchronous-work fixture to exceed the total budget deterministically while preserving the same production behavior assertion.
Use one generic GoodBuddy Ed25519 identity for the Agent bundle, bundled Runtime, outer package, and signed catalog while preserving each layer's existing signature domain.
Rename the production Environment contract to GOODBUDDY_SIGNING_*, register the matching production public key, and keep desktop and branch CI workflows isolated from the private key.
Node and libuv remove a bound Unix socket path when the server closes. The removed test required protecting a same-user replacement inside the Agent-owned 0700 directory, which would need disproportionate custom socket publication machinery without crossing a real trust boundary.
Keep the practical live-endpoint and shutdown lifecycle coverage instead.
Ubuntu validation exposed a missing Unix socket test import, a platform-dependent cancellation-message assertion, and a maximum-frame test that could exceed the default timeout under shared-runner load. The tests now exercise the intended behavior consistently without changing product code.
The native Linux CI builder completed both deterministic package assemblies but read an obsolete nested return field while producing its result JSON. It now reports the archive name from the actual assembleAgentPackage result and guards that shape in workflow tests.
Linux .gbagent extraction inherited permissive directory modes, so compound packages failed secure Runtime verification on POSIX runners. Package roots and nested bundle directories now use private modes.
The production workflow now uses one GoodBuddy Agent signing identity for the Agent, bundled Runtime, outer package, and catalog. The unpublished 0.11.2 candidate is carried forward as desktop and Agent 0.11.3 without a LoongArch preview.
Release note: 修复 Linux 上 Agent 包解压后无法通过权限验证的问题，并将复合包各层统一为一组 GoodBuddy Agent 发布密钥。
Synchronize the desktop package and lockfile versions and package the approved
Simplified Chinese and English release notes for GoodBuddy 0.11.2.
The managed SSH package lock uses the formal Agent 0.11.2 release. Its
independent Agent tag and publication remain separate from the desktop tag,
and this release does not build the experimental LoongArch preview.
Clicking the built-in embedding model download could appear to do nothing while
Main waited for the full transfer to finish. The vector model UI now follows
the speech model workflow with an immediate preparing state, verified source
and package metadata, live progress, cancellation, unavailable-source guidance,
and success notifications.
Use a bounded progress-only IPC instead of overlapping full snapshot polling,
and share model package size and progress presentation across embedding,
speech, and OCR model settings. Promote the GoodBuddy Agent lock from the e2e
prerelease identifier to the formal 0.11.2 version for production publication.
Release note: 修复点击内置向量模型下载后界面无响应的问题；现在会立即显示下载来源、进度与取消操作，并将 GoodBuddy Agent 版本标识转为正式的 0.11.2。
GoodBuddy can now be cross-packaged as an isolated Debian loong64 preview with verified Electron, node-pty, and Koffi binaries. The preview remains separate from the standard release matrix and excludes Agent, Remote Runtime, OpenCode, and native Canvas until those dependencies support LoongArch.
The Chinese website identifies GoodBuddy as the first open-source desktop AI assistant with LoongArch support while clearly labeling the independently built package as a preview.
Release note: 新增龙芯 LoongArch 独立编译预览版，并提供完整构建文档；当前预览版不包含 Agent、Remote Runtime、OpenCode 和原生 Canvas。
Managed SSH previously tied remote Agent and Runtime artifacts to desktop
packaging and Host activation. Settings now manages verified Linux x64 and
arm64 .gbagent packages explicitly, with source-aligned download and update
plus offline import and export. Each package contains the signed Agent, pinned
Node, and compatible OpenCode Runtime, and project activation never downloads
one automatically.
Dedicated native CI and a protected release workflow publish deterministic,
signed cumulative catalogs to GitHub and Beijing OSS without replacing the
desktop Latest release. Desktop packaging is metadata-only, remains independent
of Agent artifacts and signing credentials, and Linux desktop releases add RPM
installers.
The managed SSH path also keeps model credentials in Main, enforces Ask as
read-only, verifies signed Agent and Runtime inputs, preserves ACP recovery, and
reports Host update cancellation and failures accurately.
Release note: 远程项目现可在“设置”中手动下载、更新或离线导入签名 Agent 包，桌面安装包与远程组件发布相互独立；Linux 桌面版同时新增 RPM 安装包。
Long document imports could send oversized graph prompts, surface empty model
responses without useful diagnostics, and fail the entire new document even
when its full-text index was usable. Graph extraction now uses bounded token
batches with retry and timeout handling, preserves successful partial results,
and reports graph failures independently from new-document indexing.
Chinese graph retrieval now recognizes bounded CJK query terms, while graph
search keeps one-hop relationship context visible around matched entities.
Release note: 修复长文档知识图谱抽取易因空响应或超时导致整篇文档导入失败的问题；现在图谱按 Token 分批重试，失败时仍保留新文档全文检索，并改进中文图谱问答和关系上下文展示。
GoodBuddy previously had no direct way to send feedback from the desktop app. The About & Updates page now opens a bilingual, accessible feedback dialog for problems, feature requests, experience notes, and other feedback, with an optional email address and one screenshot.
Submissions use the narrow preload and trusted IPC boundary, a fixed production endpoint with strict TLS, bounded screenshot processing, an isolated resettable installation ID, preserved drafts, and idempotent manual retries. GoodBuddy does not automatically attach conversations, logs, files, settings, or credentials.
Release note: 现在可在“关于与更新”中直接提交问题、建议与体验反馈；邮箱和截图均可选，提交失败时会保留草稿供重试。
Remote Host and managed SSH project entry points were always exposed while the signed artifact workflow remains preview-stage. Remote Projects now defaults off behind its own Platform Features tab, preserves saved Hosts, projects, and credentials, and returns active remote work to a local project when disabled.
Main IPC enforces the same setting while still allowing in-flight cancellation. Application settings migrate to version 9 with the preview disabled.
Release note: 新增“远程项目（技术预览）”独立页签和开关，默认关闭；启用后显示 SSH Host 与远程项目功能，关闭不会删除已有配置。
Add managed SSH Hosts and projects with signed side-by-side GoodBuddy Agent and OpenCode Runtime installation, Ask and Execute workspace access, a Main-owned model bridge, detached Agent lifecycle, durable ACP output recovery, and project activation UI.
Use protocol v2 with bounded FIFO frames over SSH instead of custom credit, priority, batching, or model-message chunking. Mismatched Host Agents now upgrade automatically, an exactly verified Node runtime is reused on-host, and local Portable builds can embed strictly verified Agent artifacts.
Release note: 新增托管 SSH 远程项目，可自动安装或升级签名 Agent/OpenCode Runtime，并在 SSH 断线后继续 Agent 工作和同步未确认输出。
Define the About-page feedback workflow, public API boundary, strict Main-process TLS path, screenshot handling, privacy rules, idempotency, and validation plan. The external feedback platform remains separately maintained and the client implementation remains gated on its final production HTTPS origin.
The Platform Features tab strip could shrink to zero height inside the scrollable Settings layout, leaving the Magic Notes tab present in the DOM but invisible and unusable. Prevent the strip from shrinking and add a CSS regression guard.
Release note: 修复设置中心“平台功能”中的“魔法笔记”页签不可见、无法点击的问题。
Settings navigation and several workspace surfaces had lost context that helps users scan, understand, and operate them. Restore concise bilingual descriptions, workflow cues, and visual hierarchy for the welcome message, composer, activity history, knowledge workflows, Magic Notes, assistant workbar, Runtime settings, and channel projects while keeping decorative or duplicate copy removed.
Release note: 恢复设置菜单副标题、新对话引导及知识库、运行记录、魔法笔记和助手工作栏中的必要说明，提升功能可发现性与页面信息层级。
GoodBuddy previously required an external OpenAI-compatible endpoint for vector retrieval. It can now install, verify, import, remove, and run the built-in Granite multilingual embedding model in an isolated local inference process, while retaining custom embedding connections and migrating existing settings.
The model connection UI now manages built-in and custom vector connections consistently, reports the actual retrieval path, preserves credentials across failed saves, and renders the vector tab synchronously. Related settings copy, switch styling, metadata typography, and renderer bundle guardrails are aligned with the resulting workflow.
Release note: 新增可管理的内置 Granite 多语言向量模型，支持本地下载、离线导入、连接切换与诊断；同时优化向量设置及相关界面的文案、开关和状态显示。
The assistant workbar duplicated attachment and knowledge-library controls already available in the composer, while its memory section exposed an unimplemented placeholder. The workbar now keeps Task Center, Files, Browser, and Results, with future task context and memory details assigned to Task Center.
Release note: 移除助手工作栏中重复且暂未完整实现的上下文页签；附件与知识库继续在会话输入区管理，工作栏保留任务中心、工作区、浏览器和成果。
Conversation rows always reserved space for the more-actions button, and the active row kept it visible. The button now replaces the right-side timestamp only on hover, keyboard focus, or while its menu is open, leaving more room for conversation titles and timestamps by default.
Release note: 会话列表仅在悬停或键盘聚焦时显示更多操作按钮，更新时间默认更靠右，为会话标题留出更多空间。
Magic Notes can now show a default-on incomplete todo badge in the primary
navigation. The badge hides at zero, caps its visual label at 99+ while
retaining the exact accessible count, and refreshes after user or Agent/MCP
note changes.
Platform Features > Magic Notes includes a persistent switch that hides only
the count without changing notes or the Magic Notes entry. Existing settings
migrate with the count enabled.
Release note: 左侧“魔法笔记”入口现在可显示未完成待办数量；可在“平台功能 → 魔法笔记”中关闭，超过 99 项显示“99+”。
Completing a Magic Notes todo updated the stored checklist but left the cached
source note stale until the workspace was remounted. Todo updates now return
the refreshed source note and update the active note cache immediately for
both completion and reopening.
Release note: 修复在待办视图勾选或取消待办后，源笔记必须切换页面才显示最新状态的问题；现在会即时同步。
The full-width titlebar pushed the brand, project switcher, navigation, and account controls down from the window edge. The primary sidebar now spans the full window height while the titlebar belongs only to the right content frame, preserving the docked assistant workbar alignment.
Release notes now use the same full-window backdrop as other application modals, including over the titlebar.
Release note: 恢复左侧主导航的全高布局，并让版本更新说明的遮罩完整覆盖顶栏。
Existing titlebar controls could be pushed into a second row, while task controls left uneven or redundant surfaces. The window titlebar is restored, the shared workbar toggle stays directly below the close control, empty conversation task rows disappear, and Task index owns creation plus full-width filters.
Release note: 修复助手工作栏顶部错位与任务入口重复问题；空会话不再显示任务栏，任务索引统一提供新建入口和全宽状态筛选。
The right assistant workbar could switch to an overlay, duplicate its close control, and let resizing crowd or clip the chat composer. It now uses one directional toggle below the window controls, remains a docked sibling, and preserves equal 300px minimums for the chat and workbar with symmetric composer gutters.
Release note: 修复右侧助手工作栏遮挡聊天区及拖动边界不一致的问题；工作栏现在使用单一方向按钮，并在左右区域达到相同最小宽度后停止拖动。
Selecting ModelScope could leave supported speech models unavailable because their fixed targets were incomplete and the official LFS redirect host was not allowed. Speech models now resolve complete per-source artifact fingerprints while preserving integrity checks, ZIP compatibility, and source isolation.
Release note: 修复选择 ModelScope 后部分语音模型仍无法下载的问题；六个语音模型现均可从已验证的固定 ModelScope 来源下载。
Local conversations can now continue in a new branch after stable content is persisted. Each branch uses new conversation and message IDs, keeps its source visible, and remains independent without copying Tasks, queue items, runs, memories, or artifact ownership.
Conversation Task rows are also denser, align status markers at the right edge, and use an accessible checked success marker without redundant completion text.
Release note: 本地会话现在可从“在新会话中继续”创建独立分支并显示来源；Task 子项布局更紧凑，状态统一显示在右侧。
The Magic Notes editor inherited Quill's dark placeholder color, making the hint difficult to read in dark mode. It now uses the shared muted text token in both themes, with regression coverage for the editor style.
Release note: 修复暗色模式下魔法笔记输入提示文字过暗的问题，现在提示内容清晰可读。
Prepare the approved bilingual 0.11.0 release metadata and synchronize package versions. macOS packaging now signs and notarizes when all Apple credentials are available, emits unsigned packages when none are configured, and rejects partial credential sets so the six-platform release can proceed without silently misrepresenting signing status.
Save and test could accept a successful endpoint response without proving that the selected model generated output, while changing a connection URL or temporarily disabling authentication could require the API Key again.
Model tests now issue bounded real text or image generation requests and validate their output. API Keys remain encrypted with their connection across URL and authentication changes until explicitly cleared or the connection is deleted, and the form places the key directly below authentication. Real tests may incur a small amount of provider usage.
Release note: 修复模型“保存并测试”仅验证连通性的问题；现在会执行真实文本或图片生成测试，并在修改地址或临时关闭认证时继续保留该连接的加密 API Key。
Address reliability and consistency gaps across Agent Runtimes, persistence, settings, Knowledge, Magic Notes, Smart Heartbeat, and the download site. Runtime processes now have bounded lifecycle cleanup and atomic configuration rollback, while model packages and persisted mutations recover safely.
Add a configurable global shortcut, protect unsaved work, improve modal and keyboard behavior, localize the built-in project without rewriting stored data, and lazy-load heavy renderer routes under enforced bundle budgets. Align project forms and disabled controls with shared typography and interaction states, and strengthen website release metadata validation and navigation accessibility.
Release note: 修复 Runtime、设置、知识库、魔法笔记与智能心跳中的可靠性和交互一致性问题；新增可配置全局快捷键，改进无障碍与加载性能，并强化官网下载校验。
The project selector previously used a native list that showed only project names and inherited platform-specific styling. It now presents an accessible rich menu grouped into local projects and remote channels, with folder or channel context for each option.
Release note: 项目选择器现在按本地项目和远程通道分组，并显示目录或通道来源，切换项目时更容易辨认目标。
Messages and Scheduled Task occurrences previously could not share one ordered path while a Conversation was active. They now enter a durable FIFO queue with frozen execution settings and bounded attachments, recover safely after restart, and never write concurrently to the same timeline.
The compact queue above Composer supports removal and explicit interrupt-and-promote actions. SQLite schema v23 preserves pending schedule work, while Conversation Task children reuse the shared status-dot semantics for running, completed, failed, approval, paused, and cancelled states.
Release note: 回复生成期间仍可继续发送普通消息；消息与 Scheduled Task 会按 Conversation 顺序排队，并支持删除待发送项或立即中断后优先执行。
Scheduled tasks previously created separate visible work for each run and lacked one conversation-backed product identity. Custom tasks now create or reuse one stable Task and Conversation, reuse that identity across triggers, and write text results back with Task provenance.
Tasks default to Execute while preserving the configured Runtime, tool authorization, and high-risk approval boundaries. Schema v22 backfills existing schedules to stable Task and Conversation links without deleting historical runs.
The conversation list, conversation Task strip, and Task Center now expose the same Task, with localized status metadata, overflow-aware titles, and shared schedule controls.
Release note: 现在可以创建关联当前或新会话的定制计划任务；重复执行会复用同一 Task 并将文本结果回写会话，左侧会话列表和 Task Center 可直接查看和管理。
Managed speech and OCR downloads previously used catalog-specific source URLs without a global selection. Platform Features now lets users choose ModelScope by default or Hugging Face, while Main validates and freezes that source for each download.
Verified coverage remains explicit: downloads never mix artifacts or silently switch sources, and installed models plus ZIP imports stay source-independent.
Release note: 可在“设置 → 平台功能 → 通用设置”中选择 ModelScope 或 Hugging Face 作为后续语音输入与 OCR 模型下载源；缺少完整已验证文件或下载失败时不会静默换源。
Replace the flat features directory with document-type and functional-domain navigation, update repository-wide links, and add a top-level documentation index.
Define Task, Conversation, Job, Subjob, Run, Scheduled Task, Goal Task, and Task Center in one canonical document set. Keep Smart Heartbeat ownership separate and leave future partitioned memory explicitly undesigned.
Smart Heartbeat plans were implicitly bound to one active project and duplicated across multiple configuration surfaces. Plans can now target Global or selected projects from one authoritative editor, aggregate bounded input across that scope, validate project-specific outputs, and preserve existing data through the schema migration.
Reports remain unscoped with frozen scope metadata, while duplicate Heartbeat forms are removed from Settings and Task Center.
Release note: 智能心跳计划现在可从统一入口选择 Global 或一个、多个 Project；旧配置和历史会自动保留，项目级记忆与后续任务会严格写入所选范围。
Parallel expert runs previously exposed only child status, while the synthesized answer appeared above the expert cards. Each expert now retains and exposes its complete output, the cards can be expanded, and the final synthesis is rendered beneath them and persisted with the conversation.
Release note: 多专家并行分析现在可展开查看每位专家的完整输出，并在其下方显示总 Agent 的综合结果。
ChannelService previously truncated every reply at 4,000 characters and discarded the remainder before the platform adapter could handle it. Complete executor output now reaches each channel driver, while error redaction and channel-specific platform limits remain intact.
Release note: 消息通道回复不再由公共服务统一截断；完整结果现在交由微信、企业微信或钉钉按各自平台能力处理。
Completed local and channel replies were duplicated into Results as Markdown artifacts, making the panel a second conversation history. Replies now stay in their conversations, legacy duplicates are filtered without deleting data, and standalone images, scheduled jobs, headless delegations, heartbeats, and imports remain visible.
Release note: 普通本地与消息通道回复不再重复出现在成果栏；已有重复内容仅从列表隐藏，不会删除历史数据。
The resizable assistant sidebar stopped at 640px even on wide windows, leaving result and workspace previews unnecessarily cramped. It now expands up to the viewport-derived limit while preserving at least 520px for the main workspace.
Release note: 助手工作栏现在可在宽屏上拉伸到更大宽度，同时为主工作区保留至少 520 像素。
Managed browser profile controls suggested that login state and cookies would be reused, but named profiles do not yet affect browser execution. The settings UI now hides profile management while preserving the built-in browser switch, diagnostics, stored profile metadata, and compatibility APIs.
Release note: 暂时隐藏尚未实际生效的托管浏览器配置，避免误以为登录状态和 Cookie 会被复用；已有底层数据不会删除。
Browser control was grouped with client PC control even though it operates GoodBuddy's isolated browser. It now appears as Built-in Browser under direct-model tools with its existing master switch, profiles, and diagnostics, while Computer Control only lists capabilities that act on the client PC.
The existing capability ID and saved state are preserved. Enabling the browser lets direct models use it in Execute mode without per-action prompts.
Release note: 将内置浏览器移至直连模型工具，并明确它不会控制客户端已安装的浏览器；原有开关状态保持不变。
Record the end-to-end tagged release process, OSS OIDC publication contract, immutable-tag recovery rules, and public post-release checks verified by v0.10.4.
Align the build guide with the 12 installer and 20 GitHub asset contract, latest-index ordering, rerun behavior, and annotated release tags.
The v0.10.3 release index was generated, but the pinned upload client rejected object uploads because V4 signing did not receive a region. The application and website also addressed the Beijing bucket through the previous Hangzhou endpoint.
Derive and pass the endpoint region to every upload, pin workflow configuration to the trusted production bucket, and align application and website URL validation with its actual endpoint. Advance recovery metadata to 0.10.4 and remove the unpublished 0.10.3 note.
Release note: 0.10.4 carries forward the approved mirror-node and conversation timestamp improvements from the unpublished candidates.
The v0.10.2 native packages completed, but the publication job rejected the valid --base-url option before any GitHub Release or mirror assets were published. Normalize CLI option names and cover the exact workflow arguments with a regression test.
Advance recovery metadata to 0.10.3 and move the approved user-facing notes forward, removing the unpublished 0.10.2 note to avoid a duplicate first-open display.
Release note: 0.10.3 carries forward the approved mirror-node and conversation timestamp improvements from the unpublished 0.10.2 candidate.
The support overview previously listed its counts as 3, 2, 4, 1. It now presents Runtime, systems, architectures, and the entry point in a clear 4, 3, 2, 1 sequence.
Set package metadata to 0.10.2 and package the approved bilingual release notes for the mirror-node update source and clearer recent-conversation timestamps.
Version checks and downloads previously depended on GitHub Release. About & Updates now offers GitHub or a validated mirror source, keeps the selector beneath the startup-check switch, and disables it when startup checks are off.
The website resolves platform downloads from a bounded OSS release index with a GitHub fallback. Tagged releases publish and verify immutable OSS assets through OIDC before switching the latest-version index; deployment requires the configured Alibaba Cloud environment variables and role.
Release note: “关于与更新”新增 GitHub 与镜像节点选择，启动检查、手动检查和下载页使用同一可信来源；官网下载也可按系统、架构和安装包类型直接选择。
The recent-conversation list previously showed only a time, making older entries ambiguous. It now shows local time for conversations updated today, a local date for older entries, and includes the year when needed; the full timestamp remains available on hover.
Release note: 会话列表现在当天显示时间、较早会话显示日期，跨年记录同时显示年份，更容易快速判断最近更新时间。
The cumulative recovery notes carried the failed 0.10.0 content forward but did not yet mention the user-visible Magic Notes loading-state correction. Include that behavior in both languages without adding another item or retaining a duplicate 0.10.0 entry.
The AI comments pane reused its final empty-state title while the selected note detail was still loading. Slow CI runners could therefore satisfy the title wait before the final hint existed, causing the immutable v0.10.0 release validation to fail repeatedly.
The pane now presents a distinct loading state until note data is ready, and regression coverage controls the delayed detail response before asserting the final empty state. Recovery metadata moves the unpublished 0.10.0 notes forward to 0.10.1 so upgrading users see the cumulative release once.
Release note: 魔法笔记的 AI 评论区在笔记详情加载期间会明确显示加载状态，不再短暂显示空评论提示。
The GitHub Pages deployment commit existed only on github/main while the local branch had independently retained the same workflow and continued evolving the website. Record both histories in one merge without changing the already reviewed 0.10.0 candidate tree.
The Magic Notes editor had ambiguous font-size labels, cramped pane spacing, and a fixed short writing area. The toolbar now groups controls and uses numeric sizes, the pane and empty states are balanced, and the editor can be resized vertically from a taller default.
Release note: 优化魔法笔记编辑体验：字号改为数字、工具栏与分栏布局更清晰，输入区域支持纵向拖拽并默认显示更多内容。
The website used redrawn brand marks, generated icons retained opaque white edges, and adjacent download and Runtime sections accumulated excessive vertical space. It now uses synchronized official theme icons with transparent antialiased edges and a consistent responsive section rhythm.
Release note: 官网与应用图标现统一使用官方 GoodBuddy 标识，并优化下载区与 Agent Runtime 区之间的页面间距。
The website previously buried platform downloads and presented the desktop assistant, Agent Runtime, and broader work capabilities with competing priorities. It now leads with the desktop assistant and AI programming workbench positioning, surfaces cross-platform and domestic Linux compatibility, and uses a responsive interactive product preview with synchronized tilt and soft lighting.
Release note: GoodBuddy 官网现在更清晰地展示桌面助手、Agent Runtime、跨平台与国产化支持，并提供更直观的动态产品预览。
Settings Center used different header and content gutters, omitted the standard title divider, and mirrored scrollbar space on the left of its category navigation. The title and two-column content now share responsive page gutters, restore the standard PageHeader boundary, and balance selected rows against the visible scrollport.
Release note: 统一设置中心与其他一级页面的标题分隔线和响应式边距，并修复左侧分类选中高亮在滚动时的视觉偏移。
The settings category list reserved scrollbar space only on its right edge, so selected rows appeared visibly offset. The navigation now reserves symmetric space and uses wider desktop and medium-width columns while preserving the horizontal narrow-window layout.
Release note: 修复设置中心左侧分类选中高亮左右不平衡的问题，并适当加宽分类导航以改善标题和说明的可读性。
Built-in MCP servers were always granted to supported runtimes without per-server controls. They now have persistent enablement and runtime assignments for direct models, managed OpenCode, and Continue, while DeepSeek Harness remains visibly unsupported and cannot be assigned.
MCP settings are reorganized into Built-in MCP, Direct model, Custom MCP, and Computer control tabs. Direct-model web search now uses the same accessible collapsible inventory pattern as other tool groups.
Release note: 内置 MCP 现在可分别启停并分配给直连模型、OpenCode 和 Continue；MCP 设置分类与直连模型工具列表也更清晰，DeepSeek Harness 会明确显示为暂不支持。
DeepSeek Harness previously treated every selected model as text-only. It now carries the model profile's image capability through Main, the Utility Host, ACP, and Pi-AI, rejects unsupported images before model invocation, and validates supported JPEG/PNG data in a bounded process-local attachment store.
The Composer keeps universal controls on its first row, places OpenCode and Continue controls on a dedicated responsive row, and anchors context compaction without shifting the footer. Runtime supervision ownership for future Subagents and Jobs is documented for the right sidebar.
Release note: DeepSeek Harness 现可按所选模型连接的能力安全接收 JPEG/PNG 图片；Composer 同时将 Runtime 专属选择器移到独立一行，并固定上下文压缩入口。
Direct-model conversation history began carrying GoodBuddy UUIDs after durable context compression was added. OpenAI Responses rejected follow-up messages because provider message IDs must start with msg_, and the same metadata could also reach other protocol payloads.
Model request serialization now strips local IDs across Anthropic Messages, Chat Completions, and Responses while retaining provider IDs during Responses tool rounds. Regression coverage includes compression, tools, and a gated real-model follow-up.
Release note: 修复默认直连模型在继续对话或重新编辑发送时可能因消息 ID 格式错误而失败的问题。
Settings Center navigation was hard to read and constrained form content,
while Runtime customization duplicated headings and save actions and could
lose drafts. Settings now uses readable navigation and wider content, saves
base and native Runtime settings together, protects drafts, and presents one
compact capabilities and defaults section.
Conversation context meters could retain display-only thresholds from old
Runtime settings. They now persist only measured usage, derive compression
lines from current Runtime and model settings, and normalize legacy snapshots
when loading them.
The static website now uses the project GitHub Pages canonical URL and includes
a validated Pages deployment workflow.
Release note: 优化设置中心和 Agent Runtime 配置流程，避免重复标题、重复保存和未保存定制丢失；压缩线会随当前设置即时更新，官网也可通过 GitHub Pages 自动部署。
OpenCode and Continue customization was previously planned but unavailable, and Runtime-native capabilities were not represented consistently across providers. GoodBuddy now provides secure Main-owned customization settings, truthful native inventories, OpenCode Agents and Commands, Continue Rules and Prompts, DSH Web Search/Fetch, MCP Prompt and Resource metadata, and manual compaction where supported.
Native capabilities are presented in eleven accessible tabs with Tools separated from Commands, LSP, and Formatters. Tool source and Ask/Execute availability are explicit, external OpenCode remains connection-only, Continue reports unsupported static tool discovery instead of advertising unreachable Skills, and disposable inventory probes avoid retaining background runtimes.
Ask remains read-only at the Runtime boundary, Execute keeps the existing authorization controls, and credentials remain confined to Main.
Release note: 新增 OpenCode、Continue 与 DeepSeek Harness 的 Runtime 原生定制与真实能力清单；工具来源、Ask/Execute 可用性、上下文压缩和 MCP 元数据现在可清晰查看，同时继续保持 Main 进程凭据保护与现有权限边界。
The static product site did not have an automated public deployment. Changes under sites now validate and deploy from main to mesalogo.github.io/goodbuddy, and package metadata points to that address.
GoodBuddy could share Skills across runtimes, but custom MCP remained limited and DeepSeek Harness could not manage third-party extensions. The app now provides a default-off DSH npm marketplace with managed installation, configuration, failure isolation, and packaged npm support, while assigned custom MCP is available to managed OpenCode, Continue Agent, and DeepSeek Harness in Execute.
Third-party DSH install scripts, initialization, and tools run with the current user's permissions. Ask remains read-only at dispatch, and turning off the marketplace hides management without disabling installed plugins.
Release note: 新增默认关闭的 DSH 插件市场，并让自定义 MCP 可分配给 OpenCode、Continue 和 DeepSeek Harness；安装第三方插件前会明确提示当前用户权限边界。
Multiple model invocations in one task could share a call identifier when
a provider omitted or reused its response ID. Database upserts then replaced
earlier tool-round or summary usage, causing cumulative activity totals to
undercount successful calls.
Each completed direct-model invocation now receives a unique local call ID
while retaining the provider ID as diagnostic context. Tool rounds, final
responses, image calls, and repeated compression summaries are therefore
stored independently.
Release note: 修复连续工具调用或上下文摘要可能覆盖前序模型用量的问题；现在每次成功调用都会分别计入运行记录和累计统计。
Long direct-model conversations mixed provider usage with local estimates,
and Agent tool rounds could remain above the configured compression target.
Compression state and status markers also did not reliably survive restarts
or bounded history rollover.
Direct-model calls now prefer provider-reported usage, compact complete
conversation turns and Agent tool rounds within reserved payload budgets,
and persist reusable summaries with scope-specific markers. The chat meter
separates latest-call usage from estimated compressed conversation size,
while failed or cancelled calls retain the last successful measurement.
Release note: 直连模型现可在长对话和多轮工具执行中自动压缩旧上下文，并分别显示本次调用用量与压缩后对话估算；摘要会自动保存并跨重启复用，无需手动操作。
Token usage grouped and displayed provider identifiers, which exposed the internal goodbuddy Harness provider and made it appear comparable to OpenAI. Usage rows now follow the product's Runtime and model identity, including Direct model, OpenCode, Continue, and DeepSeek Harness, while provider data remains available only for cache accounting.
Release note: 修复 Token 用量中显示 goodbuddy 等内部标识的问题；统计现在按 Runtime 与模型名称清晰归类。
Token usage previously showed cache reads and writes without a comparable hit rate. Activity usage now calculates a weighted cache hit rate using OpenAI-compatible input totals and Anthropic's separately reported input, cache-read, and cache-write tokens, then shows it in totals and grouped details.
Release note: Token 用量统计新增缓存命中率，并针对 OpenAI 兼容接口与 Anthropic Messages 的不同上报口径进行归一化计算。
mesalogo