OpenClaw v2026.6.1-beta.2

## 2026.6.1 ### 亮点 - 智能体和基于命令行的运行时在处理中断的工具调用、过期的会话绑定、压缩交接和媒体投递重试时恢复更干净。 (#88129, #88136, #88141, #88162, #88182) - 频道和移动投递在 Telegram、WhatsApp、iMessage、Slack、Discord、Microsoft Teams、Google Chat、Google Meet 和 iOS 实时通话中更加稳定。 (#88096, #88105, #88183, #88231) - 提供者和插件请求现在绑定了更多定时器、重试次数、OAuth/设备码生命周期、媒体下载、本地服务探测和生成内容轮询路径，以防止它们挂起运行。 - 技能、会话元数据、网关运行时状态、插件元数据、内存监视器和存储写入在热路径上减少了重复工作，同时保持配置、分发和 Linux 文件监视行为稳定。 (#89185, #89188, #85351) 感谢 @RomneyDa 和 @NianJiuZst。 - 技能和插件加载现在更清晰地处理过期的禁用快照和加载器失败，从而使频道轮次避免禁用 SecretRef，操作员获得更好的恢复指导。 (#79072, #79173) 感谢 @zeus1959。 - Workboard、SecretRef 插件清单、托管 iOS 推送中继以及外部 Copilot/Tokenjuice 打包增加了更广泛的编排、集成和插件交付面。 (#82326, #87469, #87796, #88107, #88117) - Skill Workshop 现在拥有更完整的控制 UI 流程，包括提案列表、今日操作、修订交接、可搜索的文件预览、审查状态、区域覆盖和可复用的会话路由。 - 聊天和控制 UI 启动路径在历史加载期间保持发送存活，增量流式传输增量，流式传输时跳过 markdown 工作，输入时保持草稿本地化，发送后清除编辑器，追踪首次输出延迟，优先首次连接，并提供更平静的编辑器控件。 (#88772, #88825, #88998, #89030, #89106) 感谢 @vincentkoc 和 @sallyom。 - 提供者覆盖和模型元数据现在包括 MiniMax M3、账户 OAuth 端点、Google/Vertex 目录修复、OpenRouter SQLite 模型缓存、Copilot Claude 1M 能力、Foundry 推理对齐以及 OpenAI 响应回放保护。 (#88480, #88512, #88851, #88860) - iMessage 监视器状态、入站队列和插件安装账本已迁移到基于 SQLite 的状态，以便重启和本地监视器能够以更少的重复文件系统扫描进行恢复。 (#88794, #88797) - 发布、CI、Docker、E2E、插件安装和诊断通道现在限制更多日志、响应体、就绪探测、工件检查、状态轮询、子工作流等待、Docker 包清理、静默测试卡顿和回滚快照，从而使失败报告有限证据而非停滞。 (#88966) 感谢 @RomneyDa。 ### 变更 - 文档：添加专门的 Skill Workshop 指南，涵盖受管技能创建、可审查提案、CLI、网关、智能体工具行为、审批策略、支持文件和恢复，并刷新 ClawHub 展示卡片。 (#88734) 感谢 @shakkernerd 和 @vyctorbrzezowski。 - 技能：让 `skill_workshop` 智能体工具通过受保护的审查流程应用、拒绝和隔离明确提案。感谢 @shakkernerd。 - 技能：让提案在标准技能文件夹下携带已批准的支持文件，并具有扫描器、哈希和回滚保护。感谢 @shakkernerd。 - 技能：让待处理提案在批准前以带版本和日期的提案前置元数据进行原地修订。感谢 @shakkernerd。 - 技能：添加 Skill Workshop，包括待处理提案、CLI/网关审查操作、回滚元数据和 `skill_workshop` 智能体工具。感谢 @shakkernerd。 - Skill Workshop：添加控制 UI 导航、样式化仪表板、提案今日视图、修订对话框、文件预览模态框、可搜索的预览文件、可复用的会话交接和本地化字符串。 - 插件：将 Tokenjuice 外部化为官方 `@openclaw/tokenjuice` 插件，附带 npm 和 ClawHub 发布元数据。 - 插件：将 GitHub Copilot 智能体运行时外部化为官方 `@openclaw/copilot` 插件，附带 npm 和 ClawHub 发布元数据。 - iOS：添加托管推送中继默认值、实时通话回放和受保护的 WebSocket ping 路径，以实现更可靠的移动会话。 (#88096, #88105, #88231) - iOS：支持原生 iPad 显示布局。 - Workboard：添加用于多智能体规划和运行跟踪的编排原语和智能体协调工具。 (#87469) - Workboard：连接基于任务的板运行，并在编辑模态框中显示任务评论。 - 代码模式：为限定的智能体/全局会话和精确命名空间工具调度添加内部命名空间。 (#88043) - 代码模式：为代码模式集成添加 MCP API 文件和文档。 - 控制 UI：添加 Dreaming 标签页的智能体选择器，并将所选智能体传播到 Dreaming 状态、日记和日记操作中。 (#78748) 感谢 @stevenepalmer。 - 控制 UI：添加更平静的聊天编辑器控件、本地草稿输入状态以及活动聊天条目的首次输出延迟检测。 (#88772, #88998) 感谢 @vincentkoc。 - 插件：添加 SecretRef 提供者集成清单契约，并提取共享 LLM 核心包以供提供者/插件复用。 (#82326, #88117) - 插件：将插件安装索引持久化到 SQLite，以便已安装的包查找在重载后减少文件系统扫描。 (#88794) - 提供者：添加 MiniMax M3 模型支持。 (#88860) - Doctor：添加磁盘空间健康检查，并稳定升级后的 JSON 探测。 - 频道：将入站队列存储在 SQLite 中，并将 iMessage 监视器状态迁移到基于 SQLite 的跟踪。 (#88797) - 技能：添加核心技能索引，并集中处理技能运行时加载、状态、过滤和提示格式。 ### 修复 - 智能体/TUI：当插件禁用时，阻止本地自定义提供者运行加载插件运行时和认证别名元数据。 - 智能体/TUI：恢复进行中的 TUI 运行切换回行为，保持无策略原生钩子回退可用，处理消失的工作区，并保持轻量隔离子智能体的轻量性。 - 智能体/媒体：保持异步图像、音乐和视频生成启动不会结束 Codex 轮次，以便混合请求可以在后台渲染媒体时继续处理摘要或其他工作。 - 智能体/Codex：防止公共 OpenAI API 密钥配置文件被当作原生 Codex 应用服务器认证，同时保留持久化的 Codex OAuth 会话。 - 智能体/Codex：流式传输 Codex 应用服务器最终答案部分到实时回复预览，在 SQLite 中保留 ACP 元数据，优先使用真实工具结果而非合成修复输出，防止中止的应用服务器轮次句柄残留，迁移旧版 OpenAI Codex `lastGood` 认证状态，并在 ACP 运行时重构期间保留工作区/会话元数据。 (#88405, #88724, #88730) 感谢 @vincentkoc。 - 控制 UI：保持折叠的工具卡片使用工具名称和操作进行标记，而不是通用输出文本。感谢 @shakkernerd。 - 智能体/Codex：当 `skill_workshop` 可用时，在 Codex 应用服务器提示中展示 Skill Workshop 指导。感谢 @shakkernerd。 - 智能体/认证：原子写入认证配置文件，按类型分发认证失败，添加强制重新登录恢复，在仅状态卸载期间保留工作区，并在过大轮次之前进行压缩，以便恢复路径避免部分状态。 (#89181) 感谢 @RomneyDa。 - 技能：从过期的持久快照中跳过禁用的技能环境覆盖，以便禁用的技能 `apiKey` SecretRef 不会中止嵌入式或频道轮次。 (#79072, #79173) 感谢 @zeus1959。 - Skill Workshop：从过滤后的导航状态渲染控制 UI 标签页，并保持过滤后的回退路由稳定。 - CLI：在 `openclaw agents add` 期间避免实时目录验证，因此添加辅助智能体不再依赖提供者目录可用性。 (#76284, #88314) 感谢 @zhangguiping-xydt。 - CLI：将 `plugins list --json` 保持在仅快照路径上，以便插件扫描避免加载完整运行时状态图。 - CLI/桌面：通过 shell 桥接 WSL 剪贴板操作，识别手动更新的 launchd 任务，并在进度设置期间保持机器可读的启动输出可解析。 (#88764, #88689) 感谢 @alexzhu0。 - 插件：使 PixVerse 外部插件 ClawHub 元数据明确，并将其排除在捆绑分发构建之外。 - 插件：澄清插件加载器失败指导，以便缺失或不兼容的插件包引导操作员走向正确的修复路径。 - 插件：在受阻安装后保留 npm 插件根目录，在回滚快照期间跳过插件本地 `openclaw` 对等符号链接，在恢复后重新链接这些对等项，隔离缓存工具运行时同级，并隔离 Web 提供者工厂失败，以便一个坏插件不会污染同级运行时路径。 (#77237, #88807) - Cron：保持 SQLite cron 迁移与旧版运行日志表、归档作业存储、诊断 cron 名称以及旧版一次性删除后运行行为兼容。 (#88285) - Cron：将更新交付验证范围限定，强化重启状态，并在隔离 cron 清理中停用 MCP 运行时。 - 内存：按存储序列化 QMD 更新/嵌入写入，减少 Linux 监视器扇出，重试临时 FileProvider 支持的读取，在读取错误时保留阶段信号，强化信封元数据清理，在目录重新创建时重新附加 Linux 原生监视器，并在滚动时重写生成的字幕路径，以便内存/搜索状态在并发的网关和 CLI 活动中幸存。 (#66339, #85931, #89185, #89188, #85351) 感谢 @openperf, @amittell, @RomneyDa 和 @NianJiuZst。 - 提供者：限制来自 OpenAI、Runway、xAI、MiniMax、BytePlus、DashScope 兼容、FAL、OpenRouter、Google、Vydra 和 Comfy 提供者的生成媒体下载。 - 提供者：将 Google 默认值解析为 `google-generative-ai`，注册 Vertex 静态目录行，对齐 Foundry 推理元数据，在 Foundry 回退时跳过 DeepSeek V4 思考参数，使用 MiniMax 账户 OAuth 端点，保留 Copilot Claude 1M 能力，抑制禁用的 Ollama 推理输出，保留 OpenAI 停止完成的工具调用，并在 Responses 存储禁用时避免重放 ID。 (#88480, #88512) - 提供者：在创建中止信号之前限制 GitHub Copilot OAuth 请求超时。 - Cron：在等待下一个预定槽位之前，在临时模型速率限制后重试定期作业。 - 智能体/Codex：在清理期间保持实时会话锁，恢复中断的 CLI 工具记录，保留 Codex 认证和压缩会话身份，清除孤立的工具状态，限制应用服务器空闲定时器，并保持媒体完成投递可重试。 (#88129, #88136, #88141, #88162, #88182) - 聊天/UI：将网关聊天失败显示为控制 UI 中的可见助手消息，而不是仅设置不可见错误状态。 - 频道：限制 Telegram、Discord、WhatsApp、Signal、Feishu、Google Chat、Microsoft Teams、QQBot、Nostr、Zalo、Zalouser 和 Nextcloud 风格的请求/重试定时器；保留 SMS 审批回复路由；并重试 WhatsApp QR 登录 408 超时。 (#88183) - 安全/配置解析：拒绝不安全的 OAuth/令牌生命周期、重试后延迟、入站时间戳、响应体大小、命令超时配置、沙箱观察者令牌 TTL 以及关闭后的网关 WebSocket 调用。 - 提供者/媒体：在托管和本地提供者中限制本地服务、模型、用量、队列、生成媒体、TTS、音乐、工作流轮询和提供者 OAuth 请求定时器。 - 发布/CI/E2E：限制发布候选读取、beta 烟雾 REST 调用、插件 npm 验证命令、变更日志恢复、跨 OS 进程组、厨房水槽和捆绑插件就绪探测、密钥提供者探测、Telegram 凭据超时、控制 UI i18n 和 CLI 启动元数据生成、Vitest 路由、依赖守卫管理员审批、子工作流失败检测、静默 Node 测试分片卡顿、Docker 包清理和主线测试不稳定。 (#88127, #88137, #88155, #88160, #88966) 感谢 @RomneyDa。 - 发布/CI/E2E：保持 Kitchen Sink 实时插件 MCP 探测解析源代码检出工作区包，并使实时考验与当前 Kitchen Sink 诊断对齐。 - 发布/CI/E2E：通过仓库 pnpm 运行器运行密钥提供者集成验证，以便原生 macOS 和 Windows 验证使用水合包管理器 shim。 - 发布/CI/E2E：通过仓库 pnpm 运行器运行 Telegram 桌面验证网关，以便原生 macOS 验证使用水合包管理器 shim。 - 文档/CI：通过仓库 pnpm 运行器运行 Mintlify 锚点检查，以便文档链接验证在 pnpm 仅通过水合包管理器 shim 可用时正常工作。 - 智能体：保持配置的回退模型元数据具有类型，以便提供者参数、上下文令牌上限和媒体输入限制不会破坏更改的门类型检查。 - 智能体：在验证之前接受隐藏的 `sessions_send` 体别名，同时保持面向模型的 `message` 模式为规范。 (#88229) 感谢 @zhangguiping-xydt。 - 聊天/UI：在历史加载期间保留启动聊天发送，解除初始控制 UI 聊天发送阻塞，增量流式传输聊天增量，流式传输时跳过 markdown 解析，输入时保持草稿本地化，保护编辑器重新渲染，尊重 Chromium 可执行文件覆盖，并为 E2E 检测系统 Chromium。 (#88998) 感谢 @vincentkoc。 - 频道：保留长 Feishu 流式回复，在接受的 Feishu 轮次未生成最终回复时发送可见回退，容忍 iMessage 自拍时间戳偏差，在提及解析中保留冒号前缀的斜杠命令，正确解码 Nostr `npub` 允许列表，并在频道投递期间抑制原始提供者错误。 (#87896) - 配置/状态/doctor：在状态目录 dotenv 文件中跳过未解析的 shell 引用，在深度状态审计中解析网关认证密钥，尊重明确的 PI 运行时策略，报告运行时工具模式错误，并保持升级后 JSON 稳定。 (#88288) - 网关/会话状态：从网关插件注册表中列出命令，强化 MCP 回环工具模式，隐藏幽灵智能体存储行免于 `sessions.list`，使任务持久化失败明确，并在交互式分发事件上携带会话 UUID。 - 网关/插件：将插件查找记忆化限制为稳定的插件/运行时输入，避免重复查找工作而不混合禁用或过滤的插件状态。 - OpenAI/TTS：处理 OpenAI TTS 语音的速度指令。 (#74089) - CI/Crabbox：在 Azure 信用支持的按需 D4 通道上保持默认运行器容量，使用 Azure SSH 端口和独立于 Git 的完整检查作业，以便广泛验证避免低优先级 spot 配额卡顿、水合端口不匹配、非 Git 水合工作区和过时的 AWS 区域提示。 - CI/Crabbox：将 Crabbox 包装器和 Testbox 工作流编辑路由到其回归测试，以便更改的测试门不会静默运行零规范。 - CI/工作流：将工作流健全性助手编辑路由到其守卫测试，并覆盖复合操作输入插值检查。 - CI/工具：将 CI 范围、依赖、变更日志和文档助手编辑路由到其所有者测试，而不是静默跳过更改的测试覆盖。 - CI/工具：将包、发布和安装助手编辑路由到其所有者测试，以便更改的测试门覆盖发布和安装程序脚本更改。 - CI/工具：将共享脚本库编辑通过其所有者测试，以便锁定、进程、安全和扫描助手不会跳过更改的测试覆盖。 - CI/工具：一旦更改的差异已经需要广泛回退，则跳过昂贵的导入图扫描，保持本地更改的测试规划快速，同时仍收集显式所有者测试。 - CI/工具：当匹配 `test/scripts` 或 `src/scripts` 覆盖已存在时，将脚本编辑通过常规所有者测试路由。 - CI/工具：在内存 FD 重现脚本中尊重选项终止符，以便后续参数不会被重新解析。 - 发布/CI/E2E：断言插件生命周期运行时检查输出，而不仅仅是捕获它。 - 发布/CI/E2E：使网关网络验证宣称的健康 RPC，并重试早期 WebSocket 关闭而不耗尽完整打开超时。 - 发布/CI/E2E：在发布、Parallels 烟雾、插件考验和扩展内存脚本中尊重选项终止符。 - 发布/CI/E2E：当请求的套件摘要缺失或无效时，使插件网关考验 QA 块失败。 - 性能：使用生成的插件资产但不含 CLI 启动元数据预构建 QA 运行时探测。 - 性能：跳过仅运行时 CLI 启动和网关监视构建配置的声明捆绑。 - 性能：复用准备好的提供者句柄、严格的工具模式、网关运行时元数据、会话维护配置、插件元数据、捆绑技能允许列表、包本地插件工件、单条目存储写入以及验证/序列化的会话提示 blob。

## 2026.6.1 ### Highlights - Agents and CLI-backed runtimes recover more cleanly from interrupted tool calls, stale session bindings, compaction handoffs, and media delivery retries. (#88129, #88136, #88141, #88162, #88182) - Channels and mobile delivery are steadier across Telegram, WhatsApp, iMessage, Slack, Discord, Microsoft Teams, Google Chat, Google Meet, and iOS realtime Talk. (#88096, #88105, #88183, #88231) - Provider and plugin requests now bound more timers, retries, OAuth/device-code lifetimes, media downloads, local service probes, and generated-content polling paths before they can hang a run. - Skills, session metadata, gateway runtime state, plugin metadata, memory watchers, and store writes do less repeated work on hot paths while keeping config, dispatch, and Linux file-watch behavior stable. (#89185, #89188, #85351) Thanks @RomneyDa and @NianJiuZst. - Skills and plugin loading now handle stale disabled snapshots and loader failures more clearly, so channel turns avoid disabled SecretRefs and operators get better recovery guidance. (#79072, #79173) Thanks @zeus1959. - Workboard, SecretRef plugin manifests, hosted iOS push relay, and external Copilot/Tokenjuice packaging add broader orchestration, integration, and plugin delivery surfaces. (#82326, #87469, #87796, #88107, #88117) - Skill Workshop now has a fuller Control UI flow with proposal lists, today actions, revision handoff, searchable file previews, review states, locale coverage, and reusable session routing. - Chat and Control UI startup paths keep sends alive through history loading, stream deltas incrementally, skip markdown work while streaming, keep drafts local while typing, clear the composer after sends, trace first-output latency, prioritize first connect, and expose calmer composer controls. (#88772, #88825, #88998, #89030, #89106) Thanks @vincentkoc and @sallyom. - Provider coverage and model metadata now include MiniMax M3, account OAuth endpoints, Google/Vertex catalog fixes, OpenRouter SQLite model caching, Copilot Claude 1M capabilities, Foundry reasoning alignment, and OpenAI response replay guards. (#88480, #88512, #88851, #88860) - iMessage monitor state, inbound queues, and plugin install ledgers moved toward SQLite-backed state so restarts and local monitors recover with less duplicate filesystem scanning. (#88794, #88797) - Release, CI, Docker, E2E, plugin install, and diagnostics lanes now cap more logs, response bodies, readiness probes, artifact checks, status polling, child workflow waits, docker package cleanup, quiet test stalls, and rollback snapshots so failures report bounded proof instead of stalling. (#88966) Thanks @RomneyDa. ### Changes - Docs: add a dedicated Skill Workshop guide covering governed skill creation, reviewable proposals, CLI, Gateway, agent tool behavior, approval policy, support files, and recovery, and refresh the ClawHub showcase cards. (#88734) Thanks @shakkernerd and @vyctorbrzezowski. - Skills: let the `skill_workshop` agent tool apply, reject, and quarantine explicit proposals through the guarded review flow. Thanks @shakkernerd. - Skills: let proposals carry approved support files under standard skill folders, with scanner, hash, and rollback safeguards. Thanks @shakkernerd. - Skills: let pending proposals be revised in place with versioned, dated proposal frontmatter before approval. Thanks @shakkernerd. - Skills: add Skill Workshop with pending proposals, CLI/Gateway review actions, rollback metadata, and the `skill_workshop` agent tool. Thanks @shakkernerd. - Skill Workshop: add the Control UI navigation, styled dashboard, proposal today view, revision dialog, file preview modal, searchable preview files, reusable session handoff, and localized strings. - Plugins: externalize Tokenjuice as the official `@openclaw/tokenjuice` plugin with npm and ClawHub publish metadata. - Plugins: externalize the GitHub Copilot agent runtime as the official `@openclaw/copilot` plugin with npm and ClawHub publish metadata. - iOS: add hosted push relay defaults, realtime Talk playback, and a guarded WebSocket ping path for more reliable mobile sessions. (#88096, #88105, #88231) - iOS: support native iPad display layouts. - Workboard: add orchestration primitives and agent coordination tools for multi-agent planning and run tracking. (#87469) - Workboard: wire task-backed board runs and show task comments in the edit modal. - Code mode: add internal namespaces for scoped agent/global sessions and exact namespace tool dispatch. (#88043) - Code mode: add MCP API files and docs for code-mode integrations. - Control UI: add a Dreaming-tab agent selector and propagate the selected agent through Dreaming status, diary, and diary actions. (#78748) Thanks @stevenepalmer. - Control UI: add calmer chat composer controls, local draft typing state, and first-output latency instrumentation for active chat entry. (#88772, #88998) Thanks @vincentkoc. - Plugins: add a SecretRef provider integration manifest contract and extract shared LLM core packages for provider/plugin reuse. (#82326, #88117) - Plugins: persist the plugin install index in SQLite so installed package lookup survives reloads with less filesystem scanning. (#88794) - Providers: add MiniMax M3 model support. (#88860) - Doctor: add disk space health checks and stabilize post-upgrade JSON probes. - Channels: store inbound queues in SQLite and migrate iMessage monitor state to SQLite-backed tracking. (#88797) - Skills: add the core skills index and centralize skills runtime loading, status, filtering, and prompt formatting. ### Fixes - Agents/TUI: keep local custom provider runs from loading plugin runtime and auth alias metadata when plugins are disabled. - Agents/TUI: restore in-flight TUI run switch-back behavior, keep no-policy native hook fallback available, guard vanished workspaces, and keep lightweight isolated subagents lightweight. - Agents/media: keep async image, music, and video generation starts from ending the Codex turn, so mixed requests can continue with summaries or other work while media renders in the background. - Agents/Codex: keep public OpenAI API-key profiles from being treated as native Codex app-server auth while preserving persisted Codex OAuth sessions. - Agents/Codex: stream Codex app-server final-answer partials to live reply previews, preserve ACP metadata in SQLite, prefer real tool results over synthetic repair output, prevent aborted app-server turn handles from lingering, migrate legacy OpenAI Codex `lastGood` auth state, and preserve workspace/session metadata through ACP runtime refactors. (#88405, #88724, #88730) Thanks @vincentkoc. - Control UI: keep collapsed tool cards labeled with the tool name and action instead of generic output text. Thanks @shakkernerd. - Agents/Codex: surface Skill Workshop guidance in Codex app-server prompts when `skill_workshop` is available. Thanks @shakkernerd. - Agents/auth: write auth profiles atomically, dispatch auth failures by type, add force re-login recovery, preserve workspaces during state-only uninstall, and compact before oversized turns so recovery paths avoid partial state. (#89181) Thanks @RomneyDa. - Skills: skip disabled skill env overrides from stale persisted snapshots so disabled skill `apiKey` SecretRefs cannot abort embedded or channel turns. (#79072, #79173) Thanks @zeus1959. - Skill Workshop: render the Control UI tab from filtered navigation state and keep filtered fallback routing stable. - CLI: avoid live catalog validation during `openclaw agents add`, so adding a secondary agent no longer depends on provider catalog availability. (#76284, #88314) Thanks @zhangguiping-xydt. - CLI: keep `plugins list --json` on the snapshot-only path so plugin sweeps avoid loading the full runtime status graph. - CLI/desktop: bridge WSL clipboard operations through the shell, recognize manual-update launchd jobs, and keep machine-readable startup output parseable during progress setup. (#88764, #88689) Thanks @alexzhu0. - Plugins: make PixVerse external-plugin ClawHub metadata explicit and keep it out of bundled dist builds. - Plugins: clarify plugin loader failure guidance so missing or incompatible plugin packages point operators at the right repair path. - Plugins: preserve npm plugin roots after blocked installs, skip plugin-local `openclaw` peer symlinks during rollback snapshots, relink those peers after restore, isolate cached tool runtime siblings, and isolate web-provider factory failures so one bad plugin does not poison sibling runtime paths. (#77237, #88807) - Cron: keep SQLite cron migrations compatible with legacy run-log tables, archived job stores, diagnostic cron names, and legacy one-shot delete-after-run behavior. (#88285) - Cron: keep update delivery validation scoped, harden restart state, and retire MCP runtimes on isolated cron cleanup. - Memory: serialize QMD update/embed writes per store, reduce Linux watcher fan-out, retry transient FileProvider-backed reads, preserve phase signals on read errors, harden envelope metadata sanitization, reattach Linux native watchers when directories are recreated, and rewrite generated transcript paths on rollover so memory/search state survives concurrent gateway and CLI activity. (#66339, #85931, #89185, #89188, #85351) Thanks @openperf, @amittell, @RomneyDa, and @NianJiuZst. - Providers: bound generated media downloads from OpenAI, Runway, xAI, MiniMax, BytePlus, DashScope-compatible, FAL, OpenRouter, Google, Vydra, and Comfy providers. - Providers: resolve Google defaults to `google-generative-ai`, register Vertex static catalog rows, align Foundry reasoning metadata, skip DeepSeek V4 thinking params on Foundry fallback, use MiniMax account OAuth endpoints, preserve Copilot Claude 1M capabilities, suppress disabled Ollama reasoning output, keep OpenAI stop-finished tool calls, and avoid replay ids when the Responses store is disabled. (#88480, #88512) - Providers: cap GitHub Copilot OAuth request timeouts before creating abort signals. - Cron: retry recurring jobs after transient model rate limits before waiting for the next scheduled slot. - Agents/Codex: keep live session locks during cleanup, recover interrupted CLI tool transcripts, preserve Codex auth and compaction session identity, clear orphan tool state, cap app-server idle timers, and keep media completion delivery retryable. (#88129, #88136, #88141, #88162, #88182) - Chat/UI: show Gateway chat failures as visible assistant messages in the Control UI instead of only setting an invisible error state. - Channels: cap Telegram, Discord, WhatsApp, Signal, Feishu, Google Chat, Microsoft Teams, QQBot, Nostr, Zalo, Zalouser, and Nextcloud-style request/retry timers; preserve SMS approval reply routes; and retry WhatsApp QR login 408 timeouts. (#88183) - Security/config parsing: reject unsafe OAuth/token lifetimes, retry-after delays, inbound timestamps, response body sizes, command timeout config, sandbox observer token TTLs, and gateway WebSocket calls after close. - Providers/media: cap local service, model, usage, queue, generated media, TTS, music, workflow polling, and provider OAuth request timers across hosted and local providers. - Release/CI/E2E: bound release candidate reads, beta smoke REST calls, plugin npm verification commands, changelog restore, cross-OS process groups, kitchen-sink and bundled plugin readiness probes, secret-provider probes, Telegram credential timeouts, Control UI i18n and CLI startup metadata generation, Vitest routing, dependency guard admin approvals, child workflow failure detection, quiet Node test shard stalls, docker package cleanup, and mainline test flakes. (#88127, #88137, #88155, #88160, #88966) Thanks @RomneyDa. - Release/CI/E2E: keep Kitchen Sink live plugin MCP probes resolving source-checkout workspace packages and align the live gauntlet with current Kitchen Sink diagnostics. - Release/CI/E2E: run the secret-provider integration proof through the repo pnpm runner so native macOS and Windows validation use the hydrated package-manager shim. - Release/CI/E2E: run the Telegram desktop proof gateway through the repo pnpm runner so native macOS proof uses the hydrated package-manager shim. - Docs/CI: run Mintlify anchor checks through the repo pnpm runner so docs link validation works when pnpm is only available through the hydrated package-manager shim. - Agents: keep configured fallback model metadata typed so provider params, context-token caps, and media input limits do not break changed-gate typechecks. - Agents: accept hidden `sessions_send` body aliases before validation while keeping the model-facing `message` schema canonical. (#88229) Thanks @zhangguiping-xydt. - Chat/UI: preserve startup chat sends during history loading, unblock the initial Control UI chat send, stream chat deltas incrementally, skip markdown parsing while streaming, keep drafts local while typing, guard composer rerenders, honor Chromium executable overrides, and detect system Chromium for E2E. (#88998) Thanks @vincentkoc. - Channels: preserve long Feishu streaming replies, send visible fallbacks when accepted Feishu turns produce no final reply, tolerate iMessage self-chat timestamp skew, preserve colon-prefixed slash commands in mention parsing, decode Nostr `npub` allowlists correctly, and suppress raw provider errors during channel delivery. (#87896) - Config/status/doctor: skip unresolved shell references in state-dir dotenv files, resolve gateway auth secrets during deep status audits, respect explicit PI runtime policy, report runtime tool-schema errors, and keep post-upgrade JSON stable. (#88288) - Gateway/session state: list commands from the Gateway plugin registry, harden MCP loopback tool schemas, hide phantom agent-store rows from `sessions.list`, make task persistence failures explicit, and carry session UUIDs on interactive dispatch events. - Gateway/plugins: narrow plugin lookup memoization to the stable plugin/runtime inputs, avoiding repeated lookup work without mixing disabled or filtered plugin state. - OpenAI/TTS: handle speed directives for OpenAI TTS voices. (#74089) - CI/Crabbox: keep default runner capacity on the Azure credit-backed on-demand D4 lane with the Azure SSH port and a Git-independent full check job, so broad validation avoids low-priority spot quota stalls, hydrate port mismatches, non-Git hydrated workspaces, and stale AWS region hints. - CI/Crabbox: route Crabbox wrapper and Testbox workflow edits to their regression tests so changed-test gates do not silently run zero specs. - CI/workflows: route workflow sanity helper edits to their guard tests and cover composite-action input interpolation checks. - CI/tooling: route CI scope, dependency, changelog, and docs helper edits to their owner tests instead of silently skipping changed-test coverage. - CI/tooling: route package, release, and install helper edits to their owner tests so changed-test gates cover publish and installer script changes. - CI/tooling: route shared script library edits through their owner tests so lock, process, safety, and scan helpers do not skip changed-test coverage. - CI/tooling: skip expensive import-graph scans once a changed diff already requires broad fallback, keeping local changed-test planning fast while still collecting explicit owner tests. - CI/tooling: route script edits through conventional owner tests when matching `test/scripts` or `src/scripts` coverage already exists. - CI/tooling: honor option terminators in the memory FD repro script so follow-on arguments are not reparsed. - Release/CI/E2E: assert plugin lifecycle runtime inspect output instead of only capturing it. - Release/CI/E2E: make gateway-network prove the advertised health RPC and retry early WebSocket closes without burning full open timeouts. - Release/CI/E2E: honor option terminators across release, Parallels smoke, plugin gauntlet, and extension-memory scripts. - Release/CI/E2E: fail plugin gateway gauntlet QA chunks when the requested suite summary is missing or invalid. - Performance: prebuild QA runtime probes with generated plugin assets but without CLI startup metadata. - Performance: skip declaration bundling for runtime-only CLI startup and gateway watch build profiles. - Performance: reuse prepared provider handles, strict tool schemas, gateway runtime metadata, session maintenance config, plugin metadata, bundled skill allowlists, package-local plugin artifacts, single-entry store writes, and validated/serialized session prompt blobs.

OpenClaw v2026.6.1-beta.2 预发布