OpenClaw v2026.3.13-beta.1 预发布

Pre-release for npm beta tag `v2026.3.13-beta.1`. macOS assets are built with stable app version `2026.3.13` so they can be reused for the later non-beta release. `appcast.xml` is intentionally unchanged in this pre-release. ### Changes - Android/chat settings: redesign the chat settings sheet with grouped device and media sections, refresh the Connect and Voice tabs, and tighten the chat composer/session header for a denser mobile layout. (#44894) Thanks @obviyus. - iOS/onboarding: add a first-run welcome pager before gateway setup, stop auto-opening the QR scanner, and show `/pair qr` instructions on the connect step. (#45054) Thanks @ngutman. - Browser/existing-session: add an official Chrome DevTools MCP attach mode for signed-in live Chrome sessions, with docs for `chrome://inspect/#remote-debugging` enablement and direct backlinks to Chrome’s own setup guides. - Browser/agents: add built-in `profile="user"` for the logged-in host browser and `profile="chrome-relay"` for the extension relay, so agent browser calls can prefer the real signed-in browser without the extra `browserSession` selector. - Browser/act automation: add batched actions, selector targeting, and delayed clicks for browser act requests with normalized batch dispatch. Thanks @vincentkoc. - Docker/timezone override: add `OPENCLAW_TZ` so `docker-setup.sh` can pin gateway and CLI containers to a chosen IANA timezone instead of inheriting the daemon default. (#34119) Thanks @Lanfei. - Dependencies/pi: bump `@mariozechner/pi-agent-core`, `@mariozechner/pi-ai`, `@mariozechner/pi-coding-agent`, and `@mariozechner/pi-tui` to `0.58.0`. ### Fixes - Dashboard/chat UI: stop reloading full chat history on every live tool result in dashboard v2 so tool-heavy runs no longer trigger UI freeze/re-render storms while the final event still refreshes persisted history. (#45541) Thanks @BunsDev. - Ollama/reasoning visibility: stop promoting native `thinking` and `reasoning` fields into final assistant text so local reasoning models no longer leak internal thoughts in normal replies. (#45330) Thanks @xi7ang. - Android/onboarding QR scan: switch setup QR scanning to Google Code Scanner so onboarding uses a more reliable scanner instead of the legacy embedded ZXing flow. (#45021) Thanks @obviyus. - Browser/existing-session: harden driver validation and session lifecycle so transport errors trigger reconnects while tool-level errors preserve the session, and extract shared ARIA role sets to deduplicate Playwright and Chrome MCP snapshot paths. (#45682) Thanks @odysseus0. - Browser/existing-session: accept text-only `list_pages` and `new_page` responses from Chrome DevTools MCP so live-session tab discovery and new-tab open flows keep working when the server omits structured page metadata. - Control UI/insecure auth: preserve explicit shared token and password auth on plain-HTTP Control UI connects so LAN and reverse-proxy sessions no longer drop shared auth before the first WebSocket handshake. (#45088) Thanks @velvet-shark. - Gateway/session reset: preserve `lastAccountId` and `lastThreadId` across gateway session resets so replies keep routing back to the same account and thread after `/reset`. (#44773) Thanks @Lanfei. - macOS/onboarding: avoid self-restarting freshly bootstrapped launchd gateways and give new daemon installs longer to become healthy, so `openclaw onboard --install-daemon` no longer false-fails on slower Macs and fresh VM snapshots. - Gateway/status: add `openclaw gateway status --require-rpc` and clearer Linux non-interactive daemon-install failure reporting so automation can fail hard on probe misses instead of treating a printed RPC error as green. - macOS/exec approvals: respect per-agent exec approval settings in the gateway prompter, including allowlist fallback when the native prompt cannot be shown, so gateway-triggered `system.run` requests follow configured policy instead of always prompting or denying unexpectedly. (#13707) Thanks @sliekens. - Telegram/media downloads: thread the same direct or proxy transport policy into SSRF-guarded file fetches so inbound attachments keep working when Telegram falls back between env-proxy and direct networking. (#44639) Thanks @obviyus. - Telegram/inbound media IPv4 fallback: retry SSRF-guarded Telegram file downloads once with the same IPv4 fallback policy as Bot API calls so fresh installs on IPv6-broken hosts no longer fail to download inbound images. - Windows/gateway install: bound `schtasks` calls and fall back to the Startup-folder login item when task creation hangs, so native `openclaw gateway install` fails fast instead of wedging forever on broken Scheduled Task setups. - Windows/gateway stop: resolve Startup-folder fallback listeners from the installed `gateway.cmd` port, so `openclaw gateway stop` now actually kills fallback-launched gateway processes before restart. - Windows/gateway status: reuse the installed service command environment when reading runtime status, so startup-fallback gateways keep reporting the configured port and running state in `gateway status --json` instead of falling back to `gateway port unknown`. - Windows/gateway auth: stop attaching device identity on local loopback shared-token and password gateway calls, so native Windows agent replies no longer log stale `device signature expired` fallback noise before succeeding. - Discord/gateway startup: treat plain-text and transient `/gateway/bot` metadata fetch failures as transient startup errors so Discord gateway boot no longer crashes on unhandled rejections. (#44397) Thanks @jalehman. - Slack/probe: keep `auth.test()` bot and team metadata mapping stable while simplifying the probe result path. (#44775) Thanks @Cafexss. - Dashboard/chat UI: render oversized plain-text replies as normal paragraphs instead of capped gray code blocks, so long desktop chat responses stay readable without tab-switching refreshes. - Dashboard/chat UI: restore the `chat-new-messages` class on the New messages scroll pill so the button uses its existing compact styling instead of rendering as a full-screen SVG overlay. (#44856) Thanks @Astro-Han. - Gateway/Control UI: restore the operator-only device-auth bypass and classify browser connect failures so origin and device-identity problems no longer show up as auth errors in the Control UI and web chat. (#45512) thanks @sallyom. - macOS/voice wake: stop crashing wake-word command extraction when speech segment ranges come from a different transcript instance. - Discord/allowlists: honor raw `guild_id` when hydrated guild objects are missing so allowlisted channels and threads like `#maintainers` no longer get false-dropped before channel allowlist checks. - macOS/runtime locator: require Node >=22.16.0 during macOS runtime discovery so the app no longer accepts Node versions that the main runtime guard rejects later. Thanks @sumleo. - Agents/custom providers: preserve blank API keys for loopback OpenAI-compatible custom providers by clearing the synthetic Authorization header at runtime, while keeping explicit apiKey and oauth/token config from silently downgrading into fake bearer auth. (#45631) Thanks @xinhuagu. - Models/google-vertex Gemini flash-lite normalization: apply existing bare-ID preview normalization to `google-vertex` model refs and provider configs so `google-vertex/gemini-3.1-flash-lite` resolves as `gemini-3.1-flash-lite-preview`. (#42435) thanks @scoootscooob. - iMessage/remote attachments: reject unsafe remote attachment paths before spawning SCP, so sender-controlled filenames can no longer inject shell metacharacters into remote media staging. Thanks @lintsinghua. - Telegram/webhook auth: validate the Telegram webhook secret before reading or parsing request bodies, so unauthenticated requests are rejected immediately instead of consuming up to 1 MB first. Thanks @space08. - Security/device pairing: make bootstrap setup codes single-use so pending device pairing requests cannot be silently replayed and widened to admin before approval. Thanks @tdjackey. - Security/external content: strip zero-width and soft-hyphen marker-splitting characters during boundary sanitization so spoofed `EXTERNAL_UNTRUSTED_CONTENT` markers fall back to the existing hardening path instead of bypassing marker normalization. - Security/exec approvals: unwrap more `pnpm` runtime forms during approval binding, including `pnpm --reporter ... exec` and direct `pnpm node` file runs, with matching regression coverage and docs updates. - Security/exec approvals: fail closed for Perl `-M` and `-I` approval flows so preload and load-path module resolution stays outside approval-backed runtime execution unless the operator uses a broader explicit trust path. - Security/exec approvals: recognize PowerShell `-File` and `-f` wrapper forms during inline-command extraction so approval and command-analysis paths treat file-based PowerShell launches like the existing `-Command` variants. - Security/exec approvals: unwrap `env` dispatch wrappers inside shell-segment allowlist resolution on macOS so `env FOO=bar /path/to/bin` resolves against the effective executable instead of the wrapper token. - Security/exec approvals: treat backslash-newline as shell line continuation during macOS shell-chain parsing so line-continued `$(` substitutions fail closed instead of slipping past command-substitution checks. - Security/exec approvals: bind macOS skill auto-allow trust to both executable name and resolved path so same-basename binaries no longer inherit trust from unrelated skill bins. - Build/plugin-sdk bundling: bundle plugin-sdk subpath entries in one shared build pass so published packages stop duplicating shared chunks and avoid the recent plugin-sdk memory blow-up. (#45426) Thanks @TarasShyn. - Cron/isolated sessions: route nested cron-triggered embedded runner work onto the nested lane so isolated cron jobs no longer deadlock when compaction or other queued inner work runs. Thanks @vincentkoc. - Agents/OpenAI-compatible compat overrides: respect explicit user `models[].compat` opt-ins for non-native `openai-completions` endpoints so usage-in-streaming capability overrides no longer get forced off when the endpoint actually supports them. (#44432) Thanks @cheapestinference. - Agents/Azure OpenAI startup prompts: rephrase the built-in `/new`, `/reset`, and post-compaction startup instruction so Azure OpenAI deployments no longer hit HTTP 400 false positives from the content filter. (#43403) Thanks @xingsy97. - Agents/memory bootstrap: load only one root memory file, preferring `MEMORY.md` and using `memory.md` as a fallback, so case-insensitive Docker mounts no longer inject duplicate memory context. (#26054) Thanks @Lanfei. - Agents/compaction: compare post-compaction token sanity checks against full-session pre-compaction totals and skip the check when token estimation fails, so sessions with large bootstrap context keep real token counts instead of falling back to unknown. (#28347) thanks @efe-arv. - Agents/compaction: preserve safeguard compaction summary language continuity via default and configurable custom instructions so persona drift is reduced after auto-compaction. (#10456) Thanks @keepitmello. - Agents/tool warnings: distinguish gated core tools like `apply_patch` from plugin-only unknown entries in `tools.profile` warnings, so unavailable core tools now report current runtime/provider/model/config gating instead of suggesting a missing plugin. - Config/validation: accept documented `agents.list[].params` per-agent overrides in strict config validation so `openclaw config validate` no longer rejects runtime-supported `cacheRetention`, `temperature`, and `maxTokens` settings. (#41171) Thanks @atian8179. - Config/web fetch: restore runtime validation for documented `tools.web.fetch.readability` and `tools.web.fetch.firecrawl` settings so valid web fetch configs no longer fail with unrecognized-key errors. (#42583) Thanks @stim64045-spec. - Signal/config validation: add `channels.signal.groups` schema support so per-group `requireMention`, `tools`, and `toolsBySender` overrides no longer get rejected during config validation. (#27199) Thanks @unisone. - Config/discovery: accept `discovery.wideArea.domain` in strict config validation so unicast DNS-SD gateway configs no longer fail with an unrecognized-key error. (#35615) Thanks @ingyukoh. - Telegram/media errors: redact Telegram file URLs before building media fetch errors so failed inbound downloads do not leak bot tokens into logs. Thanks @space08.