After a managed SSH disconnect the renderer kept showing the remote
Agent as processing even though the recovered task had already been
persisted as completed. Local streaming copies shadowed the persisted
terminal state in mergePersistedConversations, and recovery completion
never asked the renderer to re-read conversations.
- Prefer the persisted terminal state over a local streaming message
- Settle active runs whose messages already reached a persisted terminal
state and release the conversation queue once
- Refresh conversations on window focus and visibility changes
- Publish a conversation change before recovery reports completed/failed
OpenCode status checks could cold-start throwaway servers, unrelated
conversations could block each other, and model, Continue, or remote paths
could replay or duplicate work under failure and backlog conditions. Settings
could also lose edits or overwrite unrelated model fields.
This update makes status checks passive, keeps per-conversation ordering while
allowing concurrency, preserves native long-running work with bounded display
capture and backpressure, narrows retries to known pre-dispatch failures, and
aligns remote Ask permissions without reducing Execute. It also keeps
Embedding updates narrow, improves settings and browser guidance, removes the
unused legacy Main gateway state, and records the validated Desktop 0.12.3 and
Agent 0.11.17 release metadata.
Release note: 改善 OpenCode 切换、多会话长任务、模型重试、远程 Ask/Execute 与设置保存可靠性，并完成 Desktop 0.12.3 / Agent 0.11.17 发布准备。
Model connections can now save bounded JSON request headers and top-level body fields. Direct requests and Continue support both; local OpenCode and DeepSeek Harness use only native header support, while the managed remote OpenCode gateway applies both.
Runtime, protocol, and authentication fields keep precedence. Custom values are ordinary connection settings, not credential storage. This migrates Runtime settings from v20 to v21 and updates the DeepSeek control and managed Runtime ACP capabilities.
Release note: 模型连接详情新增自定义请求头和请求体；直连与 Continue 支持两者，本地 OpenCode 和 DeepSeek Harness 仅应用原生支持的请求头，受管远程 OpenCode 支持两者，界面会明确提示生效范围。
The built-in browser was limited to direct-model tools, and its Agent switch also blocked manual Browser workbar actions. It is now a request-scoped GoodBuddy capability assignable to direct models, managed OpenCode, and Continue, while manual browser controls remain available when Agent access is off.
Existing browser enablement migrates to capability settings version 6. DeepSeek Harness remains unsupported.
Release note: 内置浏览器现在可分配给直连模型、OpenCode 和 Continue；关闭 Agent 浏览器能力不会影响用户在浏览器工作栏中的手动操作。
Local embedded OpenCode serialized otherwise independent conversations, and GoodBuddy could stop long Runtime tasks after fixed tool, activity, model-call, or accumulated display-output limits.
Different conversations can now run concurrently while requests in the same conversation stay ordered. Dynamic MCP tools remain isolated to the current request. OpenCode, Continue, managed ACP, and the Agent model gateway no longer stop native execution at GoodBuddy-defined call counts or prompt-wide output totals; display copies truncate and transport queues apply backpressure instead. Prompt-wide quota fields are removed from the current contracts.
Per-call model settings, provider request timeouts, cancellation, and same-conversation ordering remain unchanged.
Release note: 修复本机 OpenCode 不同会话互相等待的问题，并移除 GoodBuddy 对单次 Runtime 工具、活动和模型调用次数的人为上限；长输出现在只截断展示或施加传输背压，不再取消原生任务。
Terminal paste previously relied on the Renderer browser Clipboard API, which could be denied by Electron and leave the toolbar action unusable. Text clipboard access now goes through the trusted Main/Preload bridge, and the workbar tabs plus terminal toolbar use straight corners for a continuous docked appearance.
Release note: 修复终端工具栏粘贴可能因剪贴板权限被拒绝而失败的问题，并将工作栏页签与终端工具栏调整为直角样式。
Direct model conversations previously stopped after the first transient network error or request timeout, including TLS setup ECONNRESET failures. Text requests now retry up to three times with cancellable backoff before visible output, while partial streamed responses are never replayed.
Release note: 直连模型遇到临时网络故障或请求超时时，会在尚未输出内容的情况下自动重试最多 3 次，并支持随时取消。
Managed Python installation rejected valid case-distinct terminfo symlinks in the pinned Astral archives on Linux x64 and arm64. Archive uniqueness now follows the target filesystem: Linux preserves case-distinct paths, while every target still rejects exact duplicates and unsafe entries.
Move the unpublished 0.12.0 bilingual release notes to the immutable-tag recovery version 0.12.1 and record the failed tag evidence.
Release note: 修复 Linux x64/ARM64 上托管 Python 因官方归档包含大小写不同路径而无法安装的问题。
The complete-snapshot boundary test performs 501 synchronous SQLite source and document writes. It passed functionally but could exceed its 10-second case timeout on the serial Linux CI runner, so give this I/O-heavy case a bounded 30-second allowance without changing product behavior or global test limits.
The Linux routing test still referenced the obsolete bin/opencode name. With intentional path-only Runtime selection, that stale fixture was no longer masked by automatic discovery; use the locked opencode-ai 1.18.9 bin/opencode.exe entrypoint on every platform.
Keep the approved 0.12.0 notes and bilingual feature matrices explicit that local OpenCode paths are not prevalidated and fail only at actual launch.
OpenCode startup on Linux ARM could run a --version probe before launching the configured Runtime and recheck registered remote binary metadata. Execution now trusts the selected path and registered manifest identity after setup-time verification, so switching and cold launch avoid duplicate binary work.
Release note: 优化 Linux ARM 上切换 OpenCode 的启动速度；已安装或已登记的 Runtime 在执行时不再重复启动或检查二进制。
Update the desktop version, approved bilingual release notes, and synchronized English and Chinese feature matrices for the 0.12.0 candidate.
Release preparation now runs local tests, type checks, and lint without a local production build, then requires the main-branch CI build before tagging. The package matrix uses a native Windows arm64 runner and validates managed Python on every target without adding extra license files to the desktop package.
DeepSeek Harness previously required a separate Runtime model selection when no administrator-provided connection was available, even if the user had already selected a compatible GoodBuddy model. It now prefers the administrator connection, then follows the compatible default model or first compatible connection across conversations, projects, and messaging channels.
Release note: 修复 DeepSeek Harness 未自动使用已选兼容模型的问题；没有管理员预置连接时，现在会跟随当前默认或首个兼容模型，无需再到 Harness 页面重复指定。
Completed AI responses now expose a bottom copy action that copies their Markdown source without reasoning, tool logs, or citation metadata. Clipboard writes use a validated Preload/Main bridge so sandboxed Electron sessions no longer fail with a renderer clipboard permission error; full-conversation copy uses the same path.
Release note: AI 回复底部现在可以直接复制 Markdown 原文，并修复了沙箱环境下回复和完整会话可能无法写入剪贴板的问题。
The custom Node.js and Python choices could appear unavailable until a candidate was already discovered, and selecting the source implicitly adopted the first candidate. The chooser now stays operable, waits for an explicit validated path, keeps cancellation quiet, and shows validation errors beside the affected runtime.
Candidate discovery now prioritizes active virtual environments and Conda before bounded user/system PATH and common Node/Python locations, while preserving canonical validation and deduplication.
Release note: 修复自定义 Node.js/Python 环境入口不可用的问题，并增加对 PATH、venv、Conda 和常见安装位置的解释器检测。
GoodBuddy can now provide managed Node.js and on-demand Python to local Skills and stdio MCP servers, or validate an explicitly selected custom interpreter. The Capabilities and tools settings page exposes source selection, diagnostics, installation progress, cancellation, and removal while new processes receive immutable PATH snapshots.
Application settings migrate to v10. Local terminal and remote Host environments remain unchanged. Windows x64 native-source Node and Python paths are validated; OSS mirror publication, redistributed license resources, and the remaining native platform probes are recorded as release blockers.
Release note: 新增工具执行环境，可为本机 Skills 和 stdio MCP 使用 GoodBuddy 托管的 Node.js、按需安装的 Python，或经过验证的自定义解释器。
Direct model conversations can now execute bounded platform-native processes and delegate one level of programming work without duplicating tools in Agent Runtimes. Process and Subagent activity follows existing workspace, mode, approval, cancellation, and lifecycle boundaries, with chat attribution and complete feature documentation.
Remove the static Renderer bundle baseline gate and its build-only manifests; production builds continue to compile all processes and verify the control-plane installer. Also include the pending documentation link normalization.
Release note: 直连模型现在可在 Execute 模式运行本机命令，并可委派编程 Subagent 完成修改、测试和复核；构建流程不再因静态 Renderer 包体基线阻塞。
The Skills catalog exposed nine product-marketing recipes as independent
capabilities and enabled every marketing package for every Runtime by default.
It now keeps five top-level Skills, loads the nine recipes on demand through
the product-marketing package, and leaves the three marketing Skills disabled
until users enable them. Existing saved Skill settings remain authoritative.
Release note: 内置 Skills 已从 14 个顶层入口精简为 5 个；去 AI 味和长文工具默认启用，产品营销类默认停用，已保存的用户设置保持不变。
The Browser workbar previously showed the Agent-controlled page but did not let users navigate it directly. It now provides Back, Refresh or Stop Loading, an address field, and Go alongside the existing interaction and close actions.
User and Agent operations share the same per-conversation browser session and serialization path. Loading, committed URL, and history state keep the toolbar accurate, while Stop Loading interrupts page navigation without closing the session or releasing Runtime context.
Direct navigation continues to use the existing built-in-browser capability and URL policy. Closing the browser remains a distinct lifecycle action.
Release note: 浏览器工作栏新增返回、刷新/停止加载、地址栏和前往操作；用户与 Agent 共用同一浏览器会话，停止加载不会关闭会话。
The assistant workbar now uses persistent application tabs with a permanent catalog entry point and supports multiple local or managed SSH terminals bound to the current project. Terminal sessions flow through the Main, preload, and renderer boundaries with bounded output, resize, lifecycle, and cleanup behavior.
The main sidebar and Magic Notes list now support pointer and keyboard resizing. Magic Notes can also hide and restore its list, remembers the chosen layout, and stacks its panes when the available width is narrow.
Closing a terminal tab ends its Shell session. Restored terminal tabs do not restart prior Shell processes and require an explicit reconnect.
Release note: 助手工作栏现可通过“+”打开多个本机或当前远程项目终端；主侧栏和魔法笔记列表支持拖拽调宽，魔法笔记列表可隐藏并记住布局。
Ask and Execute guidance, Runtime state, live announcements, loading states,
retry paths, settings focus, and update failures now provide consistent and
accessible feedback across the desktop experience.
Add bounded redacted Desktop and Agent diagnostic logs, a read-only Agent
diagnostics command, and an explicit opt-in for attaching a small Desktop
diagnostic summary to in-app feedback. Diagnostics stay local by default and
the existing feedback v1 service contract remains compatible.
Release note: 新增可选桌面诊断反馈与 Agent 诊断导出，并统一 Ask/Execute 状态、错误恢复和无障碍反馈；诊断默认保留在本地，仅在用户明确勾选时附加桌面摘要。
OpenCode health polling restored a ten-second startup limit, causing Linux ARM systems and QEMU environments that became healthy just after that boundary to be reported unavailable. Managed local OpenCode now retains health-based readiness detection while allowing up to thirty seconds for startup.
Release note: 修复部分 Linux ARM 设备切换 OpenCode 时因启动超过 10 秒而误报超时的问题；健康检查现在最多等待 30 秒。
Managed SSH prompts previously depended on Desktop-owned provider and transcript state, so accepted work could stop or become uncertain when the Desktop, network, or power disappeared. The Agent now owns accepted OpenCode prompt execution, model and tool rounds, cancellation, and the durable semantic transcript, while Desktop remains authoritative for permanent projects, conversations, tasks, and messages.
Recovered work attaches to the original conversation without replay. The project switcher also groups managed SSH projects by saved Host and shows live Agent connectivity beside each group without opening a connection merely to read status. Remote project subtitles now show only the path, and the Agent lock advances to 0.11.14 with Runtime ACP v4.
Release note: 托管 SSH 任务在桌面端、网络或电源中断后可继续在主机上运行，并能回到原会话精确恢复；项目菜单现按主机分组并显示实时连接状态。
Chat startup and Runtime switching previously cached status-only Runtime instances, leaving managed OpenCode servers running without active conversations. Status checks now resolve the selected or configured default Runtime through a disposable probe and release it immediately.
Project execution Runtimes remain cached by model selection and execution space, preserving parallel work across different projects.
Release note: 修复启动或切换 Runtime 后空闲 OpenCode 服务持续驻留的问题；状态检查完成后会立即回收，多个项目仍可并行执行。
OpenCode Task calls now appear as first-class subagents in local and managed SSH conversations, with stable status, persistence, terminal handling, and true event ordering instead of duplicate generic tool entries.
GoodBuddy no longer applies a fixed outer wall-clock total to OpenCode, Continue, DeepSeek Harness, or managed SSH Prompts. Runtime-owned limits, user cancellation, bounded control operations, output limits, and released Agent protocol compatibility remain intact. Desktop and Agent release metadata are synchronized at 0.11.13 with approved bilingual notes.
Release note: OpenCode 原生 Task 现在以独立子 Agent 展示；长任务不再被 GoodBuddy 固定总时限中止，并修复 OpenCode 启动识别、可配置 HTTP 服务地址与发布说明读取问题。
DeepSeek Harness and Weixin binding configuration rejected non-loopback HTTP endpoints even when users explicitly selected those internal services. Configurable endpoints now accept valid HTTP and HTTPS URLs without host-location restrictions, while retaining the required protocol and API-key checks.
Release note: 模型连接、DeepSeek Harness 与微信绑定现在可直接使用局域网或公网 HTTP/HTTPS 服务地址，不再强制公网 HTTPS 或本机回环地址。
GoodBuddy previously treated one exact OpenCode stdout line as the startup signal, so harmless log formatting differences could report a timeout even when the server was already listening. It now polls the authenticated health endpoint on the loopback port that GoodBuddy selected, with bounded attempts and the original ten-second startup limit.
Release note: 修复 OpenCode 已启动但因监听日志格式未被识别而误报超时的问题；启动检测现在直接使用本机健康接口。
The bundled OpenCode server could be reported unavailable when slower Linux ARM systems needed more than ten seconds to initialize. GoodBuddy now allows thirty seconds for startup before terminating the server and reports the updated timeout.
Release note: 修复部分 Linux ARM 设备上 OpenCode 冷启动较慢时被误报为启动超时的问题。
An interrupted managed SSH prompt could leave its ACP binding as the permanent owner of the conversation, so every later user message failed with the same uncertain-recovery error. A later explicit prompt now retires that binding and starts a fresh ACP session without replaying the uncertain operation.
Ask-mode Runtime startup also waited on the wrong bubblewrap executable identity. The Agent now supervises the bounded transition to the signed Runtime or model-bridge executable, and the Agent version advances to 0.11.10.
Release note: 修复远程 ACP 请求中断后同一会话无法继续输入，以及 Ask 模式可能在模型调用前启动失败的问题。
Managed SSH Runtime events could complete successfully and then fail local conversation persistence when tool details exceeded a second, smaller renderer-to-Main schema limit. Conversation persistence now stores the complete tool details already accepted from the Runtime, so long remote results no longer leave the final assistant message stuck in a streaming state.
Release note: 修复远程项目工具结果较长时会话持久化失败的问题；Runtime 已返回的工具详情现在会完整保存到本地会话。
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。
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 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。
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。
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 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.
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.
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。
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。
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。
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。
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+”。
mesalogo