OpenClaw v2026.3.24-beta.1

## 2026.3.24-beta.1 ### 重大变更 ### 功能更新 - **网关/OpenAI 兼容性**：新增 `/v1/models` 和 `/v1/embeddings` 端点，并通过 `/v1/chat/completions` 和 `/v1/responses` 转发显式模型覆盖设置，以提升更广泛客户端和 RAG 系统的兼容性。感谢 @vincentkoc。 - **代理/工具**：使 `/tools` 端点仅显示当前代理实际可用的工具，新增紧凑型默认视图（可选详细模式），并在控制界面中添加实时“当前可用”板块，以便在提问前更清晰地了解可执行操作。感谢 @BunsDev。 - **Microsoft Teams**：迁移至官方 Teams SDK，并引入 AI 代理用户体验最佳实践，包括流式一对一回复、带提示启动器的欢迎卡片、反馈/反思功能、信息性状态更新、输入指示器以及原生 AI 标签。 (#51808) - **Microsoft Teams**：为已发送消息添加编辑和删除支持，包括在未提供明确目标时提供线程内回退机制。 (#49925) - **技能/安装元数据**：为捆绑技能（coding-agent、gh-issues、openai-whisper-api、session-logs、tmux、trello、weather）添加一键安装配方，使 CLI 和控制界面能在依赖缺失时提供安装指引。 (#53411) 感谢 @BunsDev。 - **控制界面/技能**：新增带计数的状态筛选标签页（全部/就绪/需配置/已禁用），用点击查看详情的对话框替换内联技能卡片，展示需求、切换开关、安装操作、API 密钥输入、源元数据和主页链接。 (#53411) 感谢 @BunsDev。 - **Slack/交互式回复**：恢复直接投递的富回复一致性，自动将尾随简单 `Options:` 行渲染为按钮/选择器，改进 Slack 交互式设置默认值，并将回复控件与插件交互处理器隔离。 (#53389) 感谢 @vincentkoc。 - **CLI/容器**：新增 `--container` 和 `OPENCLAW_CONTAINER` 参数，支持在运行的 Docker 或 Podman OpenClaw 容器内执行 `openclaw` 命令。 (#52651) 感谢 @sallyom。 - **Discord/自动线程**：新增可选 `autoThreadName: "generated"` 命名配置，使新自动创建的线程能通过 LLM 生成的简洁标题异步重命名，同时保留现有基于消息的命名作为默认行为。 (#43366) 感谢 @davidguttman。 - **插件/钩子**：新增 `before_dispatch` 钩子（携带规范化的入站元数据），并将已处理回复路由至常规最终投递路径，保留 TTS 和路由投递语义。 (#50444) 感谢 @gfzhx。 - **控制界面/代理**：将代理工作区文件行转换为可展开的 `<details>` 元素（支持延迟加载内联 Markdown 预览），并为标题、列表、代码块、表格、引用以及 details/summary 元素添加全面的 `.sidebar-markdown` 样式。 (#53411) 感谢 @BunsDev。 - **控制界面/Markdown 预览**：重新设计代理工作区文件预览对话框（采用毛玻璃背景、自适应面板和样式化页头），并集成 `@create-markdown/preview` v2 系统主题以实现富 Markdown 渲染（标题、表格、代码块、标注、引用），自动适配应用的明/暗设计令牌。 (#53411) 感谢 @BunsDev。 - **macOS 应用/配置**：用可折叠树形侧边栏（带展开箭头和缩进子区块行）替换水平胶囊式子区块导航。 (#53411) 感谢 @BunsDev。 - **CLI/技能**：将“缺失”需求标签柔化为“需配置”，并在 `openclaw skills info` 输出中展示 API 密钥设置指引（密钥获取位置、CLI 保存命令、存储路径）。 (#53411) 感谢 @BunsDev。 - **macOS 应用/技能**：在 API 密钥编辑器对话框中添加“获取密钥”主页链接和存储路径提示，并在保存确认消息中显示配置路径。 (#53411) 感谢 @BunsDev。 - **控制界面/代理**：在默认代理模型选择下拉框中添加“未设置”占位符。 (#53411) 感谢 @BunsDev。 ### 问题修复 - **安全/沙箱媒体投递**：关闭 `mediaUrl`/`fileUrl` 别名绕过漏洞，防止出站工具和消息操作突破媒体根目录限制。 (#54034) - **网关/重启信标**：重启后通过心跳唤醒中断的代理会话（而非仅发送尽力而为的重启通知），在瞬时故障时重试出站投递一次，并保留显式线程/话题路由信息以确保回复准确落入 Telegram 话题或 Slack 线程。 (#53940) 感谢 @VACInc。 - **Docker/安装**：通过 `openclaw-gateway` 路由安装时的 onboard/config 写入操作，避免预启动 `openclaw-cli` 共享网络命名空间循环，使全新 Docker 安装在网关启动前不再失败。 (#53385) 感谢 @amsminn。 - **网关/频道**：保持频道启动顺序执行，同时隔离各频道启动失败情况，使单个频道故障不再阻塞后续频道启动。 (#54215) 感谢 @JonathanJing。 - **嵌入式运行/密钥**：通过回退到已解析的运行时快照，阻止未解析的 `SecretRef` 配置导致嵌入式代理运行崩溃。修复 #45838。 - **WhatsApp/群组**：跟踪最近网关发送的消息 ID，仅抑制匹配的群组回声，保留所有者 `/status`、`/new` 和 `/activation` 命令免受关联账户 `fromMe` 流量干扰。 (#53624) 感谢 @w-sss。 - **WhatsApp/回复机器人检测**：通过解包 `botInvokeMessage` 载荷并从 `creds.json` 读取 `selfLid`，恢复隐式群组回复检测，使关联账户群聊中的基于回复的提及能重新触达机器人。 - **Telegram/论坛话题**：当 Telegram 省略论坛元数据时恢复 `#General` 话题 `1` 路由，涵盖原生命令、交互式回调、入站消息上下文和回退错误回复。 (#53699) 感谢 @huntharo。 - **Discord/网关监管**：将网关错误处理集中到生命周期拥有的监管者中，确保早期、活跃和后期拆卸阶段的 Carbon 网关错误保持一致的分类，并防止其作为进程终止性拆卸崩溃暴露。 (#53823) 感谢 @Kimbo7870。 - **Discord/超时**：当入站 Discord 工作线程在最终回复开始前超时时，发送可见超时回复（包括已创建的自动线程目标和排队运行顺序）。 (#53823) 感谢 @Kimbo7870。 - **ACP/直接聊天**：即使最终 TTS 未生成音频，也始终交付终端 ACP 结果（即使先前已流式传输块文本），并跳过冗余的空文本最终合成。 (#53692) 感谢 @w-sss。 - **Telegram/出站错误**：保留可操作的 403 成员资格/屏蔽/踢出详情，并将 `bot not a member` 视为永久投递失败，使 Telegram 停止重试 doomed 聊天。 (#53635) 感谢 @w-sss。 - **Telegram/照片**：预检 Telegram 照片尺寸和宽高比规则，当图像元数据无效或不可用时回退至文档发送，防止照片上传因 `PHOTO_INVALID_DIMENSIONS` 失败。 (#52545) 感谢 @hnshah。 - **Slack/运行时默认值**：精简 Slack DM 回复开销，恢复 Codex 自动传输，并收紧 Slack/网络搜索运行时默认设置（DM 预览线程化、缓存范围、警告去重、显式网络搜索选择加入）。 (#53957) 感谢 @vincentkoc。 - **Doctor/图像生成**：为迁移的遗留 Nano Banana Google 提供商配置植入 `/v1beta` API 根和空模型列表，使 `openclaw doctor --fix` 能完成迁移，且迁移后的原生 Google 图像路径继续命中正确端点。 (#53757) 感谢 @mahopan。 - **模型/Google**：规范裸 Google Generative AI API 根的自定义提供商名称，并在仅在各模型上声明 `api` 时保持内置 Google 模型 ID 重写生效，使自定义 Google 通道和旧配置不再缺失 `/v1beta` 或预览 ID 规范化。 (#44969) 感谢 @Kathie-yu。 - **飞书/启动**：在账户解析期间将未解析的 `SecretRef` 应用凭据视为未配置，防止 CLI 启动和只读飞书配置在运行时支持的密钥解析前崩溃。 (#53675) 感谢 @hpt。 - **飞书/群组**：当 `groupPolicy` 为 `open` 时，停止隐式要求未设置 `requireMention` 的 @提及，使图像、文件、音频等非文本群消息能送达机器人（除非操作员明确保持提及限制）。 (#54058) 感谢 @byungsker。 - **飞书/启动**：在机器人身份启动探测失败时保持 `requireMention` 强制严格，将启动机器人信息超时提升至 30 秒，并添加可取消的后台身份恢复，使提及限制群组能在无干扰回退情况下恢复。 (#43788) 感谢 @lefarcen。 - **飞书/MSTeams 消息工具**：在合并的工具架构中保持提供商原生 `card` 载荷可选，防止仅媒体发送在通道运行时投递前验证失败。 (#53715) 感谢 @lndyzwdxhs。 - **飞书/docx 块排序**：插入块时保留 `docx.document.convert` 的文档树顺序，修复新写入飞书文档中标题/段落/列表错序问题。 (#40524) 感谢 @TaoXieSZ。 - **Telegram/原生命令**：对已解析运行时快照执行原生斜杠命令，确保当新鲜配置读取暴露未解析 SecretRefs 时 DM 命令仍能回复。 (#53179) 感谢 @nimbleenigma。 - **网关/端口**：正确解析 Docker Compose 风格的 `OPENCLAW_GATEWAY_PORT` 主机发布值，不再复活遗留的 `CLAWDBOT_GATEWAY_PORT` 覆盖。 (#44083) 感谢 @bebule。 - **插件/memory-lancedb**：在 OpenAI 嵌入请求前引导环境配置的 HTTP/HTTPS 代理调度器，使内存捕获和召回在需要代理的环境中恢复工作。 (#54119) 感谢 @neeravmakwana。 - **运行时/构建**：稳定长期惰性 `dist` 运行时入口路径，并强化捆绑插件 npm 暂存，防止本地重建因缺失哈希块或损坏的 shell `npm` 填充而失败。 (#53855) 感谢 @vincentkoc。 - **安全/技能**：针对各包管理器对技能安装程序元数据执行严格正则允许列表验证，净化技能元数据终端输出，在 Markdown 预览和技能主页链接中实施 URL 协议允许列表，警告非捆绑技能安装源，并移除不安全的 `file://` 工作区链接。 (#53471) 感谢 @BunsDev。 - **内存/内置 sqlite**：通过每个源快照文件状态一次、重用同步语句以及合并状态聚合读取，削减冗余同步和状态查询波动，降低内置内存在同步/状态/doctor 类路径上的开销。感谢 @vincentkoc。 - **TUI/聊天**：当缓慢的本地运行发出空最终事件时保留待定用户消息，但仍在新活动运行完成后延迟刷新所需历史记录，避免静默/仅工具运行保持不完整状态。 (#53130) 感谢 @joelnishanth。 - **DeepSeek/定价**：用当前 DeepSeek V3.2 定价替换零成本 DeepSeek 目录费率，使 DeepSeek 会话使用总额不再显示 `$0.00`。 (#54143) 感谢 @arkyu2077。 - **CLI/日志**：使美观日志时间戳在默认 UTC 和 `--local-time` 模式下始终包含显式时区偏移，防止事件排查混合使用模糊时钟显示。 (#38904) 感谢 @sahilsatralkar。 - **浏览器/默认检测**：识别 macOS LaunchServices Edge 捆绑 ID，使默认 Chromium 检测在 Edge 为系统默认时不再回退到 Chrome。 (#48561) 感谢 @zoherghadyali。 - **CLI/Telegram 话题**：通过 Telegram `topic-create` 路由 `message thread create`（需提供话题 `name` 字段），使 Telegram 论坛话题创建功能在 CLI 中恢复工作。 (#54336) 感谢 @andyliu。 - **Telegram/配对**：将配对码和批准命令渲染为 Telegram 专用代码块，同时保持共享配对回复为其他频道的纯文本。 (#52784) 感谢 @sumukhj1219。 - **代理/cron**：即使目标非 cron 会话密钥，也抑制 cron 触发嵌入式运行的默认心跳系统提示，防止 cron 任务读取 `HEARTBEAT.md` 并污染无关线程。 (#53152) 感谢 @Protocol-zero-0。 - **代理/cron**：当任何载荷失败时将尽力而为的公告运行标记为未投递，并记录部分投递失败而非静默报告成功。 (#42535) 感谢 @MoerAI。 - **插件**：对工具/消息守卫强制执行终端钩子决策语义。 (#54241) 感谢 @joshavant。 - **市场/代理**：修正代理文档中的 ClawHub 技能 URL，并将市场归档下载流式传输至磁盘，避免安装过程内存使用过量并在空响应时干净失败。 (#54160) 感谢 @QuinnH496。 - **Discord/配置类型**：向 `DiscordGuildChannelConfig` 添加缺失的 `autoArchiveDuration`，使 TypeScript 配置定义与现有架构和运行时支持匹配。 (#43427) 感谢 @davidguttman。 - **文档/IRC**：修复 IRC 频道示例中五个 `json55` 代码围栏拼写错误，使 Mintlify 正确应用 JSON5 语法高亮。 (#50842) 感谢 @Hollychou924。

## 2026.3.24-beta.1 ### Breaking ### Changes - Gateway/OpenAI compatibility: add `/v1/models` and `/v1/embeddings`, and forward explicit model overrides through `/v1/chat/completions` and `/v1/responses` for broader client and RAG compatibility. Thanks @vincentkoc. - Agents/tools: make `/tools` show the tools the current agent can actually use right now, add a compact default view with an optional detailed mode, and add a live “Available Right Now” section in the Control UI so it is easier to see what will work before you ask. - Microsoft Teams: migrate to the official Teams SDK and add AI-agent UX best practices including streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, informative status updates, typing indicators, and native AI labeling. (#51808) - Microsoft Teams: add message edit and delete support for sent messages, including in-thread fallbacks when no explicit target is provided. (#49925) - Skills/install metadata: add one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) so the CLI and Control UI can offer dependency installation when requirements are missing. (#53411) Thanks @BunsDev. - Control UI/skills: add status-filter tabs (All / Ready / Needs Setup / Disabled) with counts, replace inline skill cards with a click-to-detail dialog showing requirements, toggle switch, install action, API key entry, source metadata, and homepage link. (#53411) Thanks @BunsDev. - Slack/interactive replies: restore rich reply parity for direct deliveries, auto-render simple trailing `Options:` lines as buttons/selects, improve Slack interactive setup defaults, and isolate reply controls from plugin interactive handlers. (#53389) Thanks @vincentkoc. - CLI/containers: add `--container` and `OPENCLAW_CONTAINER` to run `openclaw` commands inside a running Docker or Podman OpenClaw container. (#52651) Thanks @sallyom. - Discord/auto threads: add optional `autoThreadName: "generated"` naming so new auto-created threads can be renamed asynchronously with concise LLM-generated titles while keeping the existing message-based naming as the default. (#43366) Thanks @davidguttman. - Plugins/hooks: add `before_dispatch` with canonical inbound metadata and route handled replies through the normal final-delivery path, preserving TTS and routed delivery semantics. (#50444) Thanks @gfzhx. - Control UI/agents: convert agent workspace file rows to expandable `<details>` with lazy-loaded inline markdown preview, and add comprehensive `.sidebar-markdown` styles for headings, lists, code blocks, tables, blockquotes, and details/summary elements. (#53411) Thanks @BunsDev. - Control UI/markdown preview: restyle the agent workspace file preview dialog with a frosted backdrop, sized panel, and styled header, and integrate `@create-markdown/preview` v2 system theme for rich markdown rendering (headings, tables, code blocks, callouts, blockquotes) that auto-adapts to the app's light/dark design tokens. (#53411) Thanks @BunsDev. - macOS app/config: replace horizontal pill-based subsection navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows. (#53411) Thanks @BunsDev. - CLI/skills: soften missing-requirements label from "missing" to "needs setup" and surface API key setup guidance (where to get a key, CLI save command, storage path) in `openclaw skills info` output. (#53411) Thanks @BunsDev. - macOS app/skills: add "Get your key" homepage link and storage-path hint to the API key editor dialog, and show the config path in save confirmation messages. (#53411) Thanks @BunsDev. - Control UI/agents: add a "Not set" placeholder to the default agent model selector dropdown. (#53411) Thanks @BunsDev. ### Fixes - Security/sandbox media dispatch: close the `mediaUrl`/`fileUrl` alias bypass so outbound tool and message actions cannot escape media-root restrictions. (#54034) - Gateway/restart sentinel: wake the interrupted agent session via heartbeat after restart instead of only sending a best-effort restart note, retry outbound delivery once on transient failure, and preserve explicit thread/topic routing through the wake path so replies land in the correct Telegram topic or Slack thread. (#53940) Thanks @VACInc. - Docker/setup: avoid the pre-start `openclaw-cli` shared-network namespace loop by routing setup-time onboard/config writes through `openclaw-gateway`, so fresh Docker installs stop failing before the gateway comes up. (#53385) Thanks @amsminn. - Gateway/channels: keep channel startup sequential while isolating per-channel boot failures, so one broken channel no longer blocks later channels from starting. (#54215) Thanks @JonathanJing. - Embedded runs/secrets: stop unresolved `SecretRef` config from crashing embedded agent runs by falling back to the resolved runtime snapshot when needed. Fixes #45838. - WhatsApp/groups: track recent gateway-sent message IDs and suppress only matching group echoes, preserving owner `/status`, `/new`, and `/activation` commands from linked-account `fromMe` traffic. (#53624) Thanks @w-sss. - WhatsApp/reply-to-bot detection: restore implicit group reply detection by unwrapping `botInvokeMessage` payloads and reading `selfLid` from `creds.json`, so reply-based mentions reach the bot again in linked-account group chats. - Telegram/forum topics: recover `#General` topic `1` routing when Telegram omits forum metadata, including native commands, interactive callbacks, inbound message context, and fallback error replies. (#53699) thanks @huntharo - Discord/gateway supervision: centralize gateway error handling behind a lifetime-owned supervisor so early, active, and late-teardown Carbon gateway errors stay classified consistently and stop surfacing as process-killing teardown crashes. - Discord/timeouts: send a visible timeout reply when the inbound Discord worker times out before a final reply starts, including created auto-thread targets and queued-run ordering. (#53823) Thanks @Kimbo7870. - ACP/direct chats: always deliver a terminal ACP result when final TTS does not yield audio, even if block text already streamed earlier, and skip redundant empty-text final synthesis. (#53692) Thanks @w-sss. - Telegram/outbound errors: preserve actionable 403 membership/block/kick details and treat `bot not a member` as a permanent delivery failure so Telegram sends stop retrying doomed chats. (#53635) Thanks @w-sss. - Telegram/photos: preflight Telegram photo dimension and aspect-ratio rules, and fall back to document sends when image metadata is invalid or unavailable so photo uploads stop failing with `PHOTO_INVALID_DIMENSIONS`. (#52545) Thanks @hnshah. - Slack/runtime defaults: trim Slack DM reply overhead, restore Codex auto transport, and tighten Slack/web-search runtime defaults around DM preview threading, cache scoping, warning dedupe, and explicit web-search opt-in. (#53957) Thanks @vincentkoc. - Doctor/image generation: seed migrated legacy Nano Banana Google provider config with the `/v1beta` API root and an empty model list so `openclaw doctor --fix` completes and the migrated native Google image path keeps hitting the correct endpoint. (#53757) Thanks @mahopan. - Models/google: normalize bare Google Generative AI API roots for custom provider names, and keep built-in Google model-id rewrites working when `api` is declared only on individual models, so custom Google lanes and older configs stop missing `/v1beta` or preview-id normalization. (#44969) Thanks @Kathie-yu. - Feishu/startup: treat unresolved `SecretRef` app credentials as not configured during account resolution so CLI startup and read-only Feishu config surfaces stop crashing before runtime-backed secret resolution is available. (#53675) Thanks @hpt. - Feishu/groups: when `groupPolicy` is `open`, stop implicitly requiring @mentions for unset `requireMention`, so image, file, audio, and other non-text group messages reach the bot unless operators explicitly keep mention gating on. (#54058) Thanks @byungsker. - Feishu/startup: keep `requireMention` enforcement strict when bot identity startup probes fail, raise the startup bot-info timeout to 30s, and add cancellable background identity recovery so mention-gated groups recover without noisy fallback. (#43788) Thanks @lefarcen. - Feishu/MSTeams message tool: keep provider-native `card` payloads optional in merged tool schemas so media-only sends stop failing validation before channel runtime dispatch. (#53715) Thanks @lndyzwdxhs. - Feishu/docx block ordering: preserve the document tree order from `docx.document.convert` when inserting blocks, fixing heading/paragraph/list misordering in newly written Feishu documents. (#40524) Thanks @TaoXieSZ. - Telegram/native commands: run native slash-command execution against the resolved runtime snapshot so DM commands still reply when fresh config reads surface unresolved SecretRefs. (#53179) Thanks @nimbleenigma. - Gateway/ports: parse Docker Compose-style `OPENCLAW_GATEWAY_PORT` host publish values correctly without reviving the legacy `CLAWDBOT_GATEWAY_PORT` override. (#44083) Thanks @bebule. - Plugins/memory-lancedb: bootstrap the env-configured HTTP/HTTPS proxy dispatcher before OpenAI embeddings requests so memory capture and recall work in proxy-required environments again. (#54119) Thanks @neeravmakwana. - Runtime/build: stabilize long-lived lazy `dist` runtime entry paths and harden bundled plugin npm staging so local rebuilds stop breaking on missing hashed chunks or broken shell `npm` shims. (#53855) Thanks @vincentkoc. - Security/skills: validate skill installer metadata against strict regex allowlists per package manager, sanitize skill metadata for terminal output, add URL protocol allowlisting in markdown preview and skill homepage links, warn on non-bundled skill install sources, and remove unsafe `file://` workspace links. (#53471) Thanks @BunsDev. - Memory/builtin sqlite: cut redundant sync and status query churn by snapshotting file state once per source, reusing sync statements, and consolidating status aggregation reads, which reduces builtin memory overhead on sync/status/doctor-style paths. Thanks @vincentkoc. - TUI/chat: preserve pending user messages when a slow local run emits an empty final event, but still defer and flush the needed history reload after the newer active run finishes so silent/tool-only runs do not stay incomplete. (#53130) Thanks @joelnishanth. - DeepSeek/pricing: replace the zero-cost DeepSeek catalog rates with the current DeepSeek V3.2 pricing so usage totals stop showing `$0.00` for DeepSeek sessions. (#54143) Thanks @arkyu2077. - CLI/logging: make pretty log timestamps always include an explicit timezone offset in default UTC and `--local-time` modes, so incident triage no longer mixes ambiguous clock displays. (#38904) Thanks @sahilsatralkar. - Browser/default detection: recognize macOS LaunchServices Edge bundle ids so default Chromium detection stops falling back to Chrome when Edge is the system default. (#48561) Thanks @zoherghadyali. - CLI/Telegram topics: route `message thread create` through Telegram `topic-create` with the required topic `name` field so Telegram forum topic creation works from the CLI again. (#54336) Thanks @andyliu. - Telegram/pairing: render pairing codes and approval commands as Telegram-only code blocks while keeping shared pairing replies plain text for other channels. (#52784) Thanks @sumukhj1219. - Agents/cron: suppress the default heartbeat system prompt for cron-triggered embedded runs even when they target non-cron session keys, so cron tasks stop reading `HEARTBEAT.md` and polluting unrelated threads. (#53152) Thanks @Protocol-zero-0. - Agents/cron: mark best-effort announce runs as not delivered when any payload fails, and log those partial delivery failures instead of silently reporting success. (#42535) Thanks @MoerAI. - Plugins: enforce terminal hook decision semantics for tool/message guards (#54241) Thanks @joshavant. - Marketplace/agents: correct the ClawHub skill URL in agent docs and stream marketplace archive downloads to disk so installs avoid excess memory use and fail cleanly on empty responses. (#54160) Thanks @QuinnH496. - Discord/config types: add missing `autoArchiveDuration` to `DiscordGuildChannelConfig` so TypeScript config definitions match the existing schema and runtime support. (#43427) Thanks @davidguttman. - Docs/IRC: fix five `json55` code-fence typos in the IRC channel examples so Mintlify applies JSON5 syntax highlighting correctly. (#50842) Thanks @Hollychou924.

OpenClaw v2026.3.24-beta.1 预发布