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.
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。
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。
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。
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。
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。
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。
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