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 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。
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。
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.
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。
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。
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。
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。
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。
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。
mesalogo