🔵 界面更新
- • Plugin SDK/tool-result transforms: remove the Pi-only `api.registerEmbeddedExtensionFactory(...)` compatibility path. Bundled tool-result rewrites must use `api.registerAgentToolResultMiddleware(...)` with `contracts.agentToolResultMiddleware` declaring the targeted harnesses, so transforms run consistently across Pi and Codex app-server dynamic tools. Thanks @vincentkoc.
- • Control UI/Talk: 新增 browser WebRTC realtime voice sessions backed by OpenAI Realtime, with Gateway-minted ephemeral client secrets and `openclaw_agent_consult` handoff to the full OpenClaw agent.
- • Control UI: refine the agent Tool Access panel with compact live-tool chips, collapsible tool groups, direct per-tool toggles, and clearer runtime/source provenance. (#71405) Thanks @BunsDev.
- • Control UI/chat: 新增 a Steer action on queued messages so a browser follow-up can be injected into the active run without retyping it.
- • Matrix: require full cross-signing identity trust for self-device verification and 新增 `openclaw matrix verify self` so operators can establish that trust from the CLI. (#70401).
- • Dependencies/memory: stop installing `node-llama-cpp` by default; local embeddings now load it only when operators install the optional runtime package. Thanks @vincentkoc.
- • WebChat/sessions: keep runtime-only prompt context out of visible transcript history and scrub legacy wrappers from session history surfaces. Thanks @91wan.
- • Plugins/setup: honor explicit `setup.requiresRuntime: false` as a descriptor-only setup contract while keeping omitted values on the legacy setup-api fallback path. Thanks @vincentkoc.
🔴 底层架构更新
- • Google Meet joins OpenClaw as a bundled participant plugin, with personal Google 认证, Chrome/Twilio realtime sessions, paired-node Chrome support, artifact/attendance exports, and recovery tooling for already-open Meet tabs.
- • Talk, Voice Call, and Google Meet can use realtime voice loops that consult the full OpenClaw agent for deeper tool-backed answers.
- • Plugin and model infrastructure is lighter at startup: static model catalogs, manifest-backed model rows, lazy provider dependencies, and external runtime-dependency repair for packaged installs.
- • Plugins/Google Meet: add a bundled participant plugin with personal Google 认证, explicit meeting URL joins, Chrome and Twilio realtime transports, paired-node `chrome-node` support for Parallels-style Chrome/BlackHole/SoX hosts, and full-agent consults inside live voice sessions. (#70765)
- • Plugins/Google Meet: 新增 artifact and attendance workflows for conference records, recordings, transcripts, smart notes, and participant sessions, including markdown/file output, latest-record lookup, and `--all-conference-records` history scans.
- • Plugins/Google Meet: add OAuth and browser-state doctor/recovery flows, including `googlemeet doctor --oauth` and `recover_current_tab`/`recover-tab` so agents can inspect already-open Meet tabs without opening duplicates.
- • Plugins/Voice Call: expose the shared `openclaw_agent_consult` realtime tool so live phone calls can ask the full OpenClaw agent for deeper/tool-backed answers.
- • Plugins/Voice Call: 新增 `voicecall setup` and a dry-run-by-default `voicecall smoke` command so Twilio/provider readiness can be checked before placing a live test call.
🟢 安全更新
- • Browser/sandbox: pass the resolved `browser.ssrfPolicy` into sandbox browser bridges and refresh cached bridges when the effective policy changes, so sandboxed browser navigation honors private-network opt-ins. Fixes #45153 and #57055. Thanks @jzakirov, @zuoanCo, and @kybrcore.
- • Slack/messages: keep Slack bot tokens out of internal message-ordering and DM cache keys.
🟡 其他更新
- • DeepSeek V4 Flash and V4 Pro are in the bundled catalog, V4 Flash is the onboarding default, and DeepSeek thinking/replay behavior is fixed for follow-up tool-call turns.
- • Browser automation gets coordinate clicks, longer default action budgets, per-profile headless overrides, and steadier tab reuse/recovery.
- • Browser: 新增 `browser.actionTimeoutMs` and use a 60s default action budget so healthy long browser waits do not fail at the client transport boundary. (#62589).
- • Browser/config: support per-profile `browser.profiles.
.headless` overrides for locally launched browser profiles, so one profile can run headless without forcing all browser profiles headless. Thanks @nakamotoliu. - • Dependencies/Pi: 更新 bundled Pi packages to `0.70.2`, use Pi's upstream `gpt-5.5` and DeepSeek V4 catalog metadata, and keep only local `gpt-5.5-pro` forward-compat handling..
- • Diagnostics/OTEL: 新增 a lightweight diagnostic trace-context carrier for future span correlation without adding OTEL SDK state to core..
- • Diagnostics/OTEL: attach diagnostic trace context to exported OTEL logs so log records can correlate with future spans without adding retained process state. Thanks @vincentkoc.
- • Diagnostics/OTEL: make exporter startup restart-safe so config reloads do not retain stale SDKs, log transports, or diagnostic event listeners. Thanks @vincentkoc.
📝 完整更新日志： 查看 GitHub 官方 Release
