Changelog

Track every improvement to OpenClaw. New features, fixes, and platform updates.

Gateway startup performance, meeting notes and locked release packages

  • Gateway startup and model-listing hot paths reuse cached channel catalogs, plugin metadata and provider auth state so /models can drop from about 20 s to about 5 ms after warmup
  • Added a source-only external meeting-notes plugin with SDK source-provider contract, auto-start capture config, manual transcript imports and read-only openclaw meeting-notes CLI access
  • Root and OpenClaw-owned npm packages now ship generated shrinkwraps and run package integrity checks before package acceptance lanes
  • Control UI chat session picker added search and Load More pagination so older conversations remain reachable without unbounded initial loads
  • Windows install, update and service paths gained safer command shims, rollback and LaunchAgent handoff fixes

Policy plugin, Discord voice follow mode and xAI device login

  • Exec approvals removed the old skill-wrapper allowlist compatibility path so skill files must be loaded through the read tool
  • Discord voice sessions can follow configured Discord users into allowed voice channels with bounded reconciliation and DAVE recovery preservation
  • Realtime voice bootstrap now includes bounded IDENTITY.md, USER.md and SOUL.md profile context by default, with voice.realtime.bootstrapContextFiles available to disable it
  • Added the bundled Policy plugin for channel conformance checks, doctor lint findings and opt-in workspace repair
  • xAI device-code OAuth login supports remote and headless authorization without a localhost browser callback

Startup trace attribution, image package args and runtime dependency bumps

  • Docker and Podman image builds added OPENCLAW_IMAGE_APT_PACKAGES while keeping OPENCLAW_DOCKER_APT_PACKAGES as a legacy fallback
  • Gateway/ACPX restart traces now attribute startup probe, config, runtime and resource-count costs
  • Gateway startup overlaps logging and plugin-service startup with channel sidecars while preserving /readyz sidecar gating
  • Updated @openclaw/proxyline to 0.3.3 and Pi packages to 0.75.1
  • Raised the minimum supported Node.js 22 line to 22.19

Typed plugin SDK, runtime parity QA and realtime Android voice

  • Added defineToolPlugin plus openclaw plugins build, validate and init for typed simple tool plugins with generated manifest metadata
  • QA-Lab gained runtime parity suites, tool fixture coverage and release-check gates for Codex-vs-Pi drift
  • Android Talk Mode switched to realtime Gateway relay voice sessions with streaming mic input, audio playback and transcripts
  • Gateway restart traces now attribute startup probe, config, runtime and resource-count costs without changing readiness behavior
  • Proxy endpoints can use HTTPS managed forward-proxy routing with scoped proxy.tls.caFile CA trust
  • Docker/Podman added OPENCLAW_IMAGE_APT_PACKAGES while keeping OPENCLAW_DOCKER_APT_PACKAGES as a legacy fallback

Telegram polling resilience and externalized provider plugins

  • Telegram ingress moved to an isolated worker with a durable local spool so polling survives main-loop stalls
  • Externalized Amazon Bedrock, Slack, OpenShell sandbox and Anthropic Vertex so installs only pull what you use
  • Sandbox blocks Windows USERPROFILE home roots so credential-bearing binds (.codex, .openclaw, .ssh) are denied
  • Added acp.fallbacks so ACP turns try backup runtime backends before any output is emitted
  • Control UI/WebChat persisted auto-scroll mode selector (follow streaming, near-bottom, or off)
  • Stale long-poll offsets discarded after Telegram bot token rotation so bots no longer silently skip messages

Delivery, cron and channel reliability fixes

  • Cron list/show JSON now includes computed job status for external tooling
  • Agent delivery reports failure when an outbound send returns no adapter result
  • Telegram, Discord and WhatsApp routing and authorization fixes
  • Native commands and Active Memory toggles now require the correct admin scope
  • Plugin install/rollback uses a consistent npm lifecycle shell to avoid broken cleanup

Codex OAuth routing hotfix

  • Reverted the 2026.5.5 doctor --fix repair that rewrote valid -codex/* OAuth routes
  • Plugin runtime fetch drops third-party header metadata that broke guarded/proxy requests
  • Web fetch bounds dispatcher cleanup so timed-out fetches return tool errors instead of hanging
  • Debug proxy normalizes captured fetch headers before replaying requests

Sessions, runtime visibility and provider fixes

  • Sessions, status and Control UI surfaces now show each session agent runtime
  • doctor --fix repairs heartbeat-poisoned default sessions and stale TUI restore pointers
  • xAI Grok Responses models no longer receive unsupported reasoning-effort controls
  • OpenAI-compatible streaming flushes the first chunk so cold setups do not hang clients
  • Control UI chat keeps assistant progress text visible across history reloads

Realtime Gemini voice bridge for Google Meet calls

  • Twilio Meet dial-in joins speak through the realtime Gemini voice bridge with paced audio
  • Windows loopback listener binds to 127.0.0.1 to avoid dual-stack localhost stalls
  • Codex audio transcription advertised in runtime/manifest metadata
  • Workspace-scoped plugin metadata reuse trims cold plugin scans on hot paths
  • Refreshed runtime/provider deps including Pi 0.73.0, , Anthropic, Slack and TypeScript

Bundled file-transfer plugin and plugin install hardening

  • New file-transfer plugin: file_fetch, dir_list, dir_fetch and file_write with default-deny path policy
  • Hardened official plugin install, uninstall, update and ClawHub fallback paths
  • Added /steer for queue-independent steering of an idle active session
  • Unified streaming.mode "progress" drafts across Discord, Telegram, Matrix, Slack and Teams
  • doctor --fix now commits safe legacy migrations even when unrelated validation fails

npm-first plugin cutover and startup leanness

  • External plugin install, update, doctor repair and beta-channel fallback moved to npm-first
  • Leaner and agent hot paths: startup, session listing, prompt prep and tool planning
  • Control UI and WebChat resilience across Sessions, Cron and long-running WebSockets
  • WhatsApp Channel/Newsletter outbound targets and Telegram/Discord/Slack/Signal fixes
  • Added Grok 4.3 to the bundled xAI catalog as the default xAI chat model

Active-run steering by default and a people-aware memory wiki

  • Active-run steering on by default with visible-reply enforcement and opt-in follow-up commitments
  • Memory grows into a people wiki: provenance views, per-conversation Active Memory filters, partial recall on timeout
  • Added the NVIDIA provider with API-key onboarding and static catalogs
  • Restricted tool profiles no longer implicitly widen when tools.exec/tools.fs are configured
  • Security and ops: OpenGrep scanning, sharper GHSA triage, safer exec/pairing/owner-scope handling

Codex Computer Use and the DeepInfra provider

  • Codex Computer Use setup with status/install commands and fail-closed MCP checks
  • DeepInfra joins the bundled provider set with model discovery, media, TTS and embeddings
  • Tencent Yuanbao docs/catalog and QQBot group chat, streaming and media upload
  • Opt-in operator-managed outbound proxy routing with strict forward-proxy validation
  • Manifest-first model catalogs make provider rows, aliases and suppressions easier to audit

Cerebras provider and a bundled Claude importer

  • Added Cerebras as a bundled provider with onboarding and a static model catalog
  • migrate adds a bundled Claude Code / Claude Desktop importer with dry-run and backups
  • Control UI raw-config pending-changes diff panel with redaction until reveal
  • Asymmetric embedding endpoint config for memory search (inputType / query / document)
  • matrix encryption setup enables Matrix E2EE, recovery bootstrap and verification in one flow

Voice reply upgrade and new TTS providers

  • /tts latest, chat-scoped auto-TTS controls, personas and per-agent/per-account voice overrides
  • New TTS provider coverage: Azure Speech, Xiaomi, Local CLI, Inworld, Volcengine and ElevenLabs v3
  • Plugin startup moves to the cold persisted registry, cutting broad manifest scans
  • Expanded OpenTelemetry coverage across model calls, tool loops, exec and memory pressure
  • Control UI adds PWA install support and Web Push notifications

Google Meet bundled participant plugin and DeepSeek V4

  • Google Meet joins as a bundled participant plugin with personal Google auth and Chrome/Twilio realtime sessions
  • DeepSeek V4 Flash and V4 Pro added to the bundled catalog; V4 Flash is the onboarding default
  • Realtime voice loops in Talk, Voice Call and Google Meet can consult the full agent
  • Browser automation gains coordinate clicks, longer action budgets and per-profile headless overrides
  • Breaking: removed the Pi-only api.registerEmbeddedExtensionFactory compatibility path

Want the full technical details? Check out the GitHub releases.

View all releases on GitHub →