OpenClaw — The AI Toolchain

OpenClaw v2026.8.1

Mon, 31 Aug 2026 03:30:51 GMT

OpenClaw v2026.8.1 adds private credential requests, per-operation approval grants, team roles, shared credential store, external supervisor mode, and more. • Adds `OPENCLAW_SUPERVISOR_MODE=external` environment variable to let an external supervisor own Gateway restarts, service lifecycle, and updates without competing native service changes. • Adds `openclaw telemetry show` command to inspect outgoing usage-statistics payloads; opt-in feature statistics default off. • Adds `openclaw update repair` and `openclaw doctor --fix` recovery commands for missing configured provider packages. • Adds `--agent-name` flag during interactive onboarding to name the first agent and migrate legacy main-session history to its clear owner. • Adds `modelPolicy.allow` configuration for explicit per-agent model allowlists and provider wildcards, separate from aliases and per-model settings. • Adds `plugins.load.paths` cleanup on plugin uninstall, removing exact recorded install paths for marketplace, npm, and other managed installs while preserving parent, child, prefix, and unrelated paths. • Adds private credential requests: agents can request credentials through a masked prompt without exposing values in chat or model context, with an opt-in proxy limiting protected-secret substitution to approved destinations. • Adds per-operation automation approval grants: grant a permission for an exact operation once, inspect or revoke it later, and require fresh approval when the job or operation changes. • Adds team operator roles to assign verified users named roles that limit accessible agents, other people's sessions, and operator scopes, with optional sandboxed execution for newly created sessions. • Adds a shared credential store managing team-scoped secrets and environment entries in SQLite through the CLI and Settings, with write-only secret values, protected egress bound to declared hosts, and distinction between readable environment values and secrets. • Adds optional 1Password broker to resolve SecretRefs or read selected 1Password fields with service-account auth, per-secret approval, and value-free audit. • Adds session permission modes to choose an explicit mode and keep restricted filesystem access anchored to its recorded workspace or worktree; newly created worktrees inherit configured policy unless a mode is selected. • Adds widget support in chat: pin widgets to session dashboards, grant specific actions or network origins, and export rendered views as images. • Adds incognito threads keeping Control UI conversation transcripts and compaction state in Gateway memory only until restart, with memory flush off. • Adds recoverable database backups: schedule recorded backups, keep versioned snapshots in an operator-owned Git repository, and restore a verified full archive into a fresh staging directory. • Adds cloud worker bootstrap using the running Gateway's verified runtime artifact for cloud nodes, aligning source builds and worker packages. • Adds ClickClack integration with one-use expiring setup codes, immediate account verification, and native command menus published at Gateway startup when the token has `commands:write`. • Adds personal conversation recall: with Active Memory enabled, retrieves bounded same-agent private conversation context by default on personal installs; explicit controls can disable recall. • Adds grounded dreaming (model-backed background memory consolidation) enabled by default, with a Dream Diary and an explicit disable control. • Adds automatic self-learning to capture reusable lessons and apply scanner-approved new or Workshop-owned skills by default, while leaving user-authored skill changes pending. • Adds conversation search to find past conversations by exact words or phrases and reopen surrounding messages from a matching result. • Adds structured agent question answering through web and native cards, messaging buttons, or plain text, with free-text alternatives and an explicit Skip path. • Adds richer audio and video support with native playback controls, media persistence across uploads and reloads, and video uploads on Apple and Android clients. • Adds named agent setup during onboarding, migrating legacy main-session history and reusing `main` as an ordinary agent ID after required doctor repairs. • Adds plugin install provenance warnings requiring `--force` for arbitrary executable plugin sources in CLI/chat installs; trusted ClawHub, bundled, official-catalog, and tracked-update sources skip the warning. • Adds official provider packages for BytePlus, ComfyUI, Mistral, NovitaAI, OpenCode, Synthetic, Volcengine, Vydra, and Xiaomi installable through onboarding. • Adds official plugins for Cohere and Meta providers, DuckDuckGo search, Voyage embeddings, and iMessage messaging installable separately. • Adds CPU-scaled foreground concurrency sizing default top-level agent concurrency from available CPU parallelism, bounded between 8 and 16 simultaneous runs. • Adds conversation-bound automations and `/loop` command (owner-only) supporting fixed-interval or self-paced checks, defaulting new agent-turn automations to their originating conversation. • Adds remembered model selection with explicit scopes to choose whether a model change affects the current session, its agent, or the shared default. • Adds shared Gateway profiles with display names, avatars, online presence, and session-creator attribution with person filters. • Adds cloud session support for paired devices and cloud workers, moving session workspaces with the session and reusing warm machines and project seeds. • Adds durable session progress cards that persist through reloads and follow subagent activity and accumulating edits across web and native chat. • Adds memory import from detected Claude Code, Codex, and Hermes memory during CLI, macOS, and Linux onboarding. • Adds PWA approval notifications and preferences (commit `20a6147`). • Adds session permissions picker label indicating the configured default in the Control UI (commit `c9b3fa5`). Breaking changes: • The bundled OpenProse plugin and `/prose` command are removed; run `openclaw doctor --fix` to clean stale configuration and follow the upstream Agent Skill migration, keeping existing `.prose` source files. • All shipped `codex/*` and `openai-codex/*` model refs, provider config, stored sessions, and automation routes must be migrated to `openai/*`; run `openclaw doctor --fix` to perform the migration and flag conflicts for operator repair.

OpenClaw v2026.6.33

Sat, 08 Aug 2026 07:16:21 GMT

OpenClaw v2026.6.33 hardens approval authority, scopes MCP session grants, and adds extended-stable channel support. • Adds `extended-stable` channel support so package installations can select, update from, and receive availability notices for the `extended-stable` release line without silently falling back to another channel. • Scopes external MCP loopback clients to short-lived session-bound attach grants instead of inheriting mutable child-process authority, limiting lateral movement from compromised MCP sessions. • Restricts narrow tool allowlists to the factory that constructs them, preventing privilege escalation through allowlist inheritance. • Ensures Gateway message actions retain trusted requester provenance and reject untrusted callers, closing an authorization bypass in action bridges. • Improves long-running agent reliability by distinguishing genuine stalls from active long model calls and wedged backends in run-release, liveness-check, and watchdog logic. • Preserves SecretRef-backed Telegram credentials across service restarts, preventing credential loss on restart.

OpenClaw v2026.6.33

Sat, 08 Aug 2026 07:16:21 GMT

OpenClaw v2026.6.33 hardens agent authority, MCP session scoping, channel delivery, and extended-stable package channel support. • External MCP loopback clients now use short-lived session-bound attach grants instead of inheriting mutable child-process authority, limiting lateral movement from compromised plugins. • Gateway message actions retain trusted requester provenance and reject untrusted callers, closing an escalation path through the action bridge. • Narrow tool allowlists remain owned by the factory that constructs them, preventing downstream components from widening their own privilege set. • Package installations can now select, update from, and receive availability notices for the `extended-stable` channel without silently falling back to another release line. • Liveness checks and watchdog semantics now distinguish genuine agent stalls from active long model calls and wedged backends, reducing false-positive run terminations. • Discord reconnects no longer silently drop queued messages or repeat ambiguous non-idempotent sends. • Telegram bot-to-bot and reply-fence handling now preserves intended thread context and authorization results on delivery.

OpenClaw v2026.7.1

Mon, 13 Jul 2026 22:33:14 GMT

OpenClaw v2026.7.1 adds new AI providers, native macOS/mobile chat, Telegram Codex pairing, ClawRouter, and expanded CLI workflows. • Adds Featherless, Claude Sonnet 5, Mythos 5, Meta Muse Spark 1.1, GPT-5.6, and ClawRouter as new model providers and routing options. • Adds `openclaw attach` CLI subcommand plus node context-path support, soft-resume on prompt metadata changes, and actionable device-approval recovery guidance. • Adds ClawRouter bundled provider plugin with credential-scoped dynamic model discovery, OpenAI-compatible and native Anthropic/Gemini transports, and managed budget reporting. • Adds Meta `muse-spark-1.1` Responses API support with streaming, tool calls, encrypted reasoning replay, and standalone npm distribution as `@openclaw/meta-provider`. • Adds exit-triggered cron schedules and detached session-targeted cron runs. • Adds native macOS session browser with model and thinking pickers, slash commands, transcript export, and context usage display. • Adds conversational Crestodian onboarding agent loop across CLI, web install, and macOS app with AI-guided provider setup, masked credential prompts, and exact operation approval binding. • Adds iOS/Android offline pre-painted session and transcript caches, with Apple Watch full voice turns and iOS Gateway TTS reply playback with on-device fallback. • Adds Gateway-backed session groups, unread state, rename, fork, archive, and delete controls across web, iOS, and Android. • Adds Telegram Codex pairing via private `/login`, active-run steering with `/steer` and `/tell`, and multi-lane Telegram progress summaries. • Adds native iMessage polls and Signal target aliases. • Adds Android in-chat agent selector to switch active agents from the live chat screen. • Adds Gateway host status panel in Control UI Settings showing host, network address, OS, runtime, uptime, CPU, memory, and disk details. • Adds Logbook work-journal bundled plugin that turns paired-node screen snapshots into a private timeline, daily standups, and timeline-grounded Q&A in a Control UI tab. • Adds operator-scoped `tts.speak` RPC returning configured-provider speech as inline whole-clip audio for remote clients. • Adds auto-discovery of Ollama inference nodes. • Adds Cursor Agent as an autoreview engine. • Adds `doctor --fix` policy repair previews showing review-required Gateway bind and denied node-command changes without applying them. • Expands `doctor` diagnostics to surface auth-profile, workspace, device-pairing, channel-plugin, memory-provider, systemd exhaustion, and Windows LAN firewall findings. • Adds Control UI GitHub hover/focus cards showing issue and PR state, title, author, activity, comments, and change statistics. • Adds generated session titles via utility-model routing with configurable per-agent `utilityModel` for lower-cost title generation. • Adds Control UI reasoning-effort slider and compact context ring showing context-window progress, token counts, and active model. • Adds Android syntax highlighting for fenced Kotlin, Swift, TypeScript, JavaScript, Python, Bash, and JSON code blocks. • Slack integration now uses native assistant thread status and rotating loading messages by default; lifecycle reaction updates require `messages.statusReactions.enabled: true`. • Adds Swedish mobile localization. • Makes GPT-5.6 the default model for new setups with `/think ultra` for Sol and Terra and `max` for Luna. Breaking changes: • Slack lifecycle reaction updates now require `messages.statusReactions.enabled: true`; previously they were emitted by default.

OpenClaw v2026.6.11

Tue, 30 Jun 2026 16:06:39 GMT

OpenClaw v2026.6.11 adds per-contact model assignment, Mattermost /oc_queue slash command, and QQBot slash-command scoping controls. • Supports assigning different models to individual direct-message contacts across supported chat channels, while existing group and wildcard model choices continue to work. • Adds `/oc_queue` native slash command for Mattermost operators to tune active-run queuing mode, debounce timing, cap, and drop handling directly in Mattermost. • Enables QQBot group admins to control how broadly slash commands are available, with private-only commands directing users to a private chat instead of being exposed or silently ignored in groups. • Mattermost thread participation now persists across gateway restarts without requiring users to re-mention the bot, surviving up to seven days of thread idle time.

OpenClaw v2026.6.10

Wed, 24 Jun 2026 03:06:38 GMT

OpenClaw v2026.6.10 adds automatic fast mode, a session-transcript SDK, expanded GLM-5.2 reasoning tiers, and new OpenCode Go catalog models. • Adds `/fast auto` command so short conversational calls start in fast mode and longer or fallback work automatically returns to normal mode with effective state still visible in status. • Displays the effective automatic fast-mode state in status (instead of a simple on/off) so operators can see what a session is actually using, including in connected-agent sessions. • Adds a durable session-transcript SDK contract so plugins can read, append, publish, and lock the intended transcript without relying on legacy file paths as identity. • Expands `zai/glm-5.2` thinking choices beyond binary on/off, enabling high or max reasoning effort requests to Z.AI. • Adds GLM-5.2 and Kimi K2.7 Code to the OpenCode Go model catalog so users can select them directly from OpenClaw. • Enables ClawHub discovery for the StepFun provider plugin so operators can install it through either ClawHub or npm. • Keeps `openclaw doctor` core diagnostics in their normal order before extension checks, making diagnostic output easier to follow.

OpenClaw v2026.6.9

Sun, 21 Jun 2026 01:44:28 GMT

OpenClaw v2026.6.9 adds Codex Hosted Search, auto plugin approvals, standalone provider npm packages, OpenTelemetry log export, and new UI/mobile controls. • Adds Codex Hosted Search as a new search provider option. • Adds automatic plugin approvals for Codex, reducing manual intervention in agentic workflows. • Adds remote-node `exec` exposed as a dynamic tool in Codex when a remote node is connected. • Adds OpenTelemetry log export for observability pipeline integration. • Publishes official provider plugins as standalone, independently installable npm packages. • Enables Gateway to discover and load externally installed channel plugins at startup. • Makes StepFun provider available via npm and ClawHub. • Adds a session workspace rail to the Control UI. • Adds plugin health status display to the Control UI. • Adds iOS Watch controls for session management. • Adds Android chat context display. • Adds SecretRefs support in Codex for safer credential handling. • Preserves ClawHub skill install source provenance for verified installs. • Key-free search providers remain deliberate opt-ins, preventing accidental exposure. • QA scenarios now authored in YAML with broader profile evidence and channel/plugin matrix coverage.

OpenClaw v2026.6.8

Tue, 16 Jun 2026 16:32:26 GMT

OpenClaw v2026.6.8 adds GLM-5.2 and Claude Haiku 4.5 support, Telegram rich-message delivery, WhatsApp ACP bindings, /btw CLI command, and built-in usage footer rendering. • Adds GLM-5.2 and Claude Haiku 4.5 catalog entries with normalized provider-qualified model IDs across OpenRouter and Google Vertex paths. • Adds Telegram rich-message delivery: tables, lists, expandable blockquotes, preserved intentional line breaks, and CLI-backed replies. • Adds WhatsApp ACP binding support so configured ACP bindings are honored on delivery. • Adds `/btw` command support in CLI-backed sessions. • Adds built-in full footer renderer for `/usage` and reply payload hooks, including a default footer template, per-turn usage state, credential-aware limits, and fixed-decimal formatting for usage-bar templates. • Keeps key-free web search providers (Parallel Free, DuckDuckGo, Ollama, Codex Hosted Search) as explicit opt-ins rather than automatic fallbacks when no API-backed provider is configured.

OpenClaw v2026.6.6

Fri, 12 Jun 2026 11:04:42 GMT

OpenClaw v2026.6.6 adds OpenRouter OAuth, Claude Fable 5, QQBot group mentions, trusted diagnostics tool I/O capture, and ClawHub reusable package publishing. • Adds OpenRouter OAuth support as a new provider authentication path. • Adds Claude Fable 5 model support. • Adds QQBot group mention toggle for channel integrations. • Emits Claude CLI commentary progress events and bridges inter-tool commentary into channel progress. • Enables trusted diagnostics channels to capture tool input/output content for observability. • Adds first-assistant-event tracing and slow-initial-reply warnings to the Control UI. • Supports reusable ClawHub package publishing with dry-run skip-approval option. • Moves the local llama.cpp runtime into its own provider plugin and batches embeddings across files. • Persists the agent model catalog cache to speed up startup. • Exposes the active connection host in the TUI footer. • Improves iPad and iPhone control surfaces. • Prewarms TUI runtime plugins for faster startup. • Supports declared installed trusted hooks for plugins. • Reports managed plugin version drift via the doctor command.

OpenClaw v2026.6.5

Tue, 09 Jun 2026 18:13:20 GMT

OpenClaw v2026.6.5 adds Parallel web search, GitHub-backed ClawHub skills, native Google Chat approval cards, QMD rerank, and a QQBot @mention toggle. • Adds Parallel bundled web-search plugin with API-key discovery, guarded `api.parallel.ai/v1/search` endpoint support, cache-safe session IDs, and onboarding integration. • Adds GitHub-backed ClawHub skill installation: downloads pinned GitHub commits, applies install-policy checks, and reports install telemetry on success. • Adds native Google Chat approval card actions and click handling so approvals use platform-native cards instead of generic message flow. • Adds `/bot-group-allways on|off` slash command in QQBot (with named-account and default-account support) to toggle whether group messages require an `@mention` before the bot replies. • Adds QMD memory search rerank toggle for more precise memory retrieval. • Adds Matrix voice-message preflight and thread-aware read/reply behavior. • Adds clearer expiring, unavailable, unresolved, and attention states to Android provider/model screens.

OpenClaw v2026.6.1

Wed, 03 Jun 2026 19:35:12 GMT

OpenClaw v2026.6.1 adds Skill Workshop, Workboard multi-agent coordination, MiniMax M3, Tailscale routing, and Android inspection commands. • Adds Skill Workshop with pending proposals, CLI/Gateway review actions, rollback metadata, and the `skill_workshop` agent tool for governed skill lifecycle management. • Adds Control UI Skill Workshop dashboard with proposal today view, revision dialog, file preview modal, searchable preview files, and localized strings. • Adds Workboard orchestration primitives and agent coordination tools for multi-agent planning and run tracking. • Adds task-backed board runs and task comment display in the Workboard edit modal. • Adds Android installed-app inspection commands, notification picker helpers, and updated-system-app classification. • Adds MiniMax M3 model support. • Supports Tailscale Serve service names for local service routing in the Gateway. • Adds a Dreaming-tab agent selector in Control UI, propagating the selected agent through Dreaming status, diary, and diary actions. • Adds disk space health checks to the Doctor command. • Externalizes Tokenjuice as the official `@openclaw/tokenjuice` plugin with npm and ClawHub publish metadata. • Externalizes the GitHub Copilot agent runtime as the official `@openclaw/copilot` plugin with npm and ClawHub publish metadata. • Adds typed presentation command actions and the bounded `resolve_exec_env` hook to the Plugin SDK for plugin-provided exec environment contributions. • Adds a SecretRef provider integration manifest contract for plugins. • Persists the plugin install index in SQLite so installed package lookup survives reloads without full filesystem scanning. • Stores inbound channel queues in SQLite and migrates iMessage monitor state to SQLite-backed tracking. • Adds hosted push relay defaults, realtime Talk playback, and a guarded WebSocket ping path for more reliable iOS mobile sessions. • Supports native iPad display layouts. • Adds internal namespaces for scoped agent/global sessions and exact namespace tool dispatch in Code mode. • Allows validated host-local text document media sends while keeping unsafe plain-text media sends blocked. • Adds calmer chat composer controls, local draft typing state, and first-output latency instrumentation in Control UI.

OpenClaw v2026.5.28

Sat, 30 May 2026 20:06:10 GMT

OpenClaw v2026.5.28 adds Claude Opus 4.8, encrypted PDF extraction, GitHub Copilot agent runtime, policy conformance checks, and Workboard agent coordination tools. • Adds Claude Opus 4.8 as a supported provider model. • Adds GitHub Copilot agent runtime and Codex Supervisor plugin package for delegated Codex workflows. • Supports encrypted PDF extraction via ClawPDF integration. • Surfaces MCP structured content in agent tool results. • Adds Fal Krea image model schemas and NVIDIA featured model catalogs. • Adds MiniMax streaming music response support. • Adds provider-backed voice model catalogs. • Adds Workboard agent coordination tools for tracking and handing off active agent work. • Adds policy comparison, ingress-channel conformance, and sandbox-posture conformance checks. • Shows active subagent details in status output. • Adds Plugin SDK reply payload sending hook for plugins that deliver channel-owned replies. • Adds ClawHub plugin display names plus skill verification and trust surfaces. • Externalizes GitHub Copilot and Tokenjuice as official install-on-demand plugins with npm and ClawHub publish metadata. • Shows commentary in progress drafts for live Discord runs. • Adds iOS Pro app refresh including Pro Command, Chat, Agents, Settings, hosted push relay defaults, and realtime Talk playback. • Expands default Diffs language coverage with a split language pack.

OpenClaw v2026.5.27

Thu, 28 May 2026 11:41:42 GMT

OpenClaw v2026.5.27 adds native OpenAI-compatible embeddings, Pixverse video generation, full DeepInfra catalog, and plugin approval metadata. • Adds a core OpenAI-compatible embedding provider supporting local and hosted OpenAI-style endpoints, with config, doctor, and docs integration. • Adds the Pixverse video generation provider with API region selection, docs, and external plugin packaging support. • Loads the full credential-aware DeepInfra model catalog when users browse models during onboarding, preserving configured API-key catalogs. • Exposes plugin approval action metadata via the Plugin SDK. • Adds plugin display metadata to ClawHub so catalog and package listings use cleaner names. • Wires configured VLLM thinking params to provider requests. • Loads Claude CLI OAuth overlays for PI auth profiles. • Supports bare direct Anthropic model IDs without requiring a cached catalog. Breaking changes: • Memory-specific embedding provider registration in the Plugin SDK is marked deprecated; non-bundled usage is now surfaced in plugin compatibility diagnostics. • Old channel turn runtime aliases are removed from the Channel SDK. • Vitest test helpers are no longer exported from the public Plugin SDK surface.

OpenClaw v2026.5.26

Wed, 27 May 2026 11:27:24 GMT

OpenClaw v2026.5.26 adds transcript capture, named auth profiles, reaction approvals, QA coverage matching, and a live Activity tab. • Adds core transcript capture and source-provider support for transcript-backed meeting summaries, with a new CLI surface and cleaned user-turn persistence. • Adds named model login profiles with credential migration for Hermes, OpenCode, and Codex auth profiles, including explicit opt-out and non-interactive controls. • Adds `qa coverage --match ` subcommand for focused proof selection against existing scenario metadata before running live or remote lanes. • Adds Signal, iMessage, and WhatsApp thumb/reaction approval support so mobile approval flows work without textual `/approve` commands. • Adds Android pair-new-gateway action and iOS direct realtime Talk mode with compact toolbar status and responsive voice waveform feedback. • Adds an alpha-bucket model picker for Discord when provider or model lists exceed 25 items, grouping entries by first-letter ranges instead of prev/next pagination. • Adds an ephemeral Activity tab in Control UI for sanitized live tool activity summaries without persisting raw telemetry. • Adds OpenTelemetry LLM content spans and alertable telemetry signals for blocked tools, failover, stale sessions, liveness, oversized payloads, and webhook ingress. • Adds gateway secret-preparation tracing, skill/tool usage classification, and model stream progress surfacing for improved observability. • Forwards OpenAI sampling parameters through the Gateway and exposes estimated context-budget status for active agent runs. • Queues prompts submitted while an agent is busy and shows explicit fast-mode state plus richer systemd Gateway hygiene in status output. • Defaults `cron.maxConcurrentRuns` to 8 so scheduled automations run in parallel without explicit configuration. • Replaces the Sharp image backend with Rastermill for metadata, resizing, EXIF orientation, and PNG alpha-preserving optimization, removing the Sharp and WhatsApp Jimp dependencies. • Exposes shared realtime voice SDK surface for turn-context tracking, output activity tracking, consult question matching, and activation-name matching, reused across Discord, browser voice, and meeting surfaces. • Adds Plugin SDK reaction approval helpers and makes diagnostic event root exports discoverable across function-name and alias-bound module graphs. Breaking changes: • The Sharp image backend and the WhatsApp Jimp fallback are removed; image processing now uses Rastermill, so any environment relying on Sharp being installed by OpenClaw will no longer have it.

OpenClaw v2026.5.22

Sun, 24 May 2026 01:12:56 GMT

OpenClaw v2026.5.22 adds meeting-notes capture, 4,100× faster model listing, poll sender SDK, embedding provider API, and chat session search. • Adds `openclaw meeting-notes` CLI with auto-start capture, manual transcript imports, and Discord voice as the first live source via a new external meeting-notes plugin. • Pre-warms provider auth-state at gateway startup, dropping `/models` and model-listing call cost from ~20 s to ~5 ms (~4,100× speedup). • Adds search and Load More pagination to the Control UI chat session picker so older conversations remain reachable. • Enables configurable `agentComponents.ttlMs` callback registry lifetime for Discord long-running component workflows, with per-account overrides and a 24-hour cap. • Adds a generic channel-message poll sender to the Plugin SDK so channel plugins can deliver polls without depending on channel-specific SDK facades. • Adds a general `embeddingProviders` capability contract and registration API so embeddings become a reusable provider surface outside memory-specific adapters. • Adds row-level session workflow helpers to the Plugin SDK and deprecates `loadSessionStore` so plugins can read and patch sessions without the legacy whole-store shape. • Extends the OpenTelemetry smoke harness to prove trace, metric, and log export, and adds first-class Prometheus and observability smoke aliases. • Adds curated mock JSONL replay fixtures and first-drift reporting to QA-Lab for runtime-parity audits. • Reuses xAI OAuth auth profiles for Grok `web_search`, threads active-agent auth through web search, and adds Grok model aliases. • Starts classic onboarding when bare `openclaw` runs before an authored config exists, keeping configured installs on Crestodian. • Lazy-loads startup-idle plugin work and the embedded ACPX runtime so Gateway health and ready signals no longer wait on unused handler trees. • Ships the root npm package and OpenClaw-owned plugins with generated shrinkwrap and bundled plugin runtime dependencies, requiring review for lockfile changes. • Limits default sub-agent bootstrap context to `AGENTS.md` and `TOOLS.md`, excluding persona, identity, user, memory, heartbeat, and setup files from delegated workers by default. • Adds `openclaw-landable-bug-sweep` maintainer skill for producing small, reviewed, CI-green bugfix PRs from issue/PR sweeps. Breaking changes: • Default sub-agent bootstrap context is now limited to `AGENTS.md` and `TOOLS.md`; persona, identity, user, memory, heartbeat, and setup files are no longer passed to delegated workers by default. • Gemini CLI is no longer auto-probed for media understanding; Antigravity CLI is used only as a lower-priority image/video fallback after configured provider APIs. • The old sender-owner tool gating path is removed; configured tools are now always visible for trusted sessions while command and channel-action auth still carry real sender identity.

OpenClaw v2026.5.20

Thu, 21 May 2026 20:44:50 GMT

OpenClaw v2026.5.20 adds Discord voice follow, bundled Policy plugin, xAI device-code OAuth, and per-agent lean local-model mode. • Adds Discord voice-follow: voice sessions now track configured users into channels with allowed-channel checks, multi-user handoff, bounded reconciliation, and DAVE recovery preservation. • Adds automatic injection of bounded `IDENTITY.md`, `USER.md`, and `SOUL.md` profile context into realtime voice session instructions by default, configurable via `voice.realtime.bootstrapContextFiles`. • Adds bundled Policy plugin for policy-backed channel conformance checks, doctor lint findings, and opt-in workspace repair. • Adds `agents.list[].experimental.localModelLean` config option to enable lean local-model mode per agent instead of globally. • Adds device-code OAuth login for xAI provider, enabling authorization from remote and headless environments without a localhost browser callback. • Adds provider-level `params.provider` routing policy support for OpenRouter requests, with model and agent params able to override defaults. Breaking changes: • The old `cat SKILL.md && printf ... && ` allowlist compatibility path for exec approvals is removed; skill files must now be loaded with the read tool and only the real skill executable is auto-allowed.

OpenClaw v2026.5.19

Wed, 20 May 2026 20:20:53 GMT

OpenClaw v2026.5.19 adds typed plugin scaffolding, Android realtime voice, global skill installs, browser dialog handling, and sweeping QA-Lab expansions. • Adds `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` for scaffolding typed simple tool plugins with generated manifest metadata, optional tool declarations, and context factories. • Adds `--global` flag to `openclaw skills install` and `openclaw skills update` so shared managed skills can be targeted without per-user installs. • Adds `openclaw browser evaluate --timeout-ms` to extend both the evaluate action and request timeout budgets for long-running in-page functions. • Surfaces pending and recently handled browser modal dialogs in snapshots, returns `blockedByDialog` when an action opens a modal, and adds `browser dialog --dialog-id` to answer pending dialogs. • Switches Android Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. • Adds `openclaw qa suite --runtime-parity-tier` to wire standard Codex-vs-Pi tier checks into release gates separately from optional/live-only/soak lanes. • Exposes runtime tool fixture coverage through `openclaw qa coverage --tools` with optional suite-summary evaluation for parity gate artifacts. • Adds `/codex plugins list`, `enable`, and `disable` for managing configured native Codex plugins from chat without editing config by hand. • Adds `OPENCLAW_IMAGE_APT_PACKAGES` as the runtime-neutral image build arg for extra apt packages (with `OPENCLAW_DOCKER_APT_PACKAGES` kept as a legacy fallback). • Adds `OPENCLAW_IMAGE_PIP_PACKAGES` for opt-in Python package installation in local Docker/Podman image builds. • Supports HTTPS managed forward-proxy endpoints and scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. • Exposes config lookup reload metadata so tools can distinguish restart-required, hot-reloadable, and no-op fields before applying config edits. • Adds Telegram allowlisted native DM draft previews for transient tool progress while keeping final answers on the normal persistent delivery path. • Adds admin HTTP RPC support for trusted clients to start and wait for web QR login flows. • Adds a meme-maker skill covering curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links. • Adds a Python debugging skill for pdb, breakpoint(), post-mortem inspection, and debugpy remote attach. • Adds node inspector debugging, fused diagram generation, and throwaway spike workflow skills. • Adds QA-Lab personal-agent benchmark scenarios for approval-denial, local task followthrough, share-safe diagnostics, no-fake-progress verification, and report-only dreaming shadow-trial. • Adds `pnpm test:restart:gateway` benchmark tooling for measuring repeated restart readiness, downtime, trace, and resource-slope evidence. • Adds QA-Lab live-only harness self-health scenarios for plugin hook crashes, manifest contract errors, and WebChat direct-reply self-message routing. • Adds a live-frontier Codex-vs-Pi runtime token-efficiency artifact lane in the all-lanes QA workflow. • Redesigns Mac app Settings pages with consistent card layouts, cached navigation, and cleaner permissions/voice/skills/cron/exec/debug panes. • Adds presentation capability limits for channel renderers and adapts rich message controls before native rendering.

OpenClaw v2026.5.18

Mon, 18 May 2026 18:54:22 GMT

OpenClaw v2026.5.18 adds a meme-maker skill, Python/node debugger skills, typed plugin SDK, HTTPS proxy support, and Android realtime voice. • Adds `defineToolPlugin` plus `openclaw plugins build`, `validate`, and `init` commands for authoring typed simple tool plugins with generated manifest metadata and context factories. • Adds a meme-maker skill supporting curated template search, local SVG/PNG rendering, Imgflip hosted rendering, and Know Your Meme provenance links. • Adds a Python debugging skill covering pdb, breakpoint(), post-mortem inspection, and debugpy remote attach. • Adds node inspector debugging, fused diagram generation, and throwaway spike workflow skills. • Switches Android Talk Mode to realtime Gateway relay voice sessions with streaming mic input, realtime audio playback, tool-result bridging, and on-screen transcripts. • Supports HTTPS managed forward-proxy endpoints with scoped `proxy.tls.caFile` CA trust for proxy endpoint TLS. • Adds `OPENCLAW_IMAGE_APT_PACKAGES` as a runtime-neutral image build arg for extra apt packages (Docker/Podman), keeping `OPENCLAW_DOCKER_APT_PACKAGES` as a legacy fallback. • Surfaces pending and recently handled modal dialogs in browser snapshots, returns `blockedByDialog` when an action opens a modal, and adds `browser dialog --dialog-id` to answer pending dialogs. • Adds `openclaw qa suite --runtime-parity-tier` to wire the standard Codex-vs-Pi tier into release checks separately from optional/live-only/soak lanes. • Exposes runtime tool fixture coverage through `openclaw qa coverage --tools` with optional suite-summary evaluation for parity gate artifacts. • Allows trusted admin HTTP RPC clients to start and wait for web QR login flows. • Redesigns Mac app Settings pages with consistent card layouts, cached navigation, and cleaner permissions/voice/skills/cron/exec/debug panes. • Adds `pnpm test:restart:gateway` benchmark tooling for repeated restart readiness, downtime, trace, and resource-slope evidence. • Overlaps startup logging and plugin-service startup with channel sidecars to reduce restart ready latency while preserving `/readyz` sidecar gating. • Adds presentation capability limits for channel renderers and adapts rich message controls before native rendering. • Updates the Obsidian skill to target the official `obsidian` CLI and require its registered binary instead of the third-party `obsidian-cli`. • Renames the repo-local Codex closeout review skill and helper to `autoreview` while preserving the Codex-first fallback behavior. Breaking changes: • The Obsidian skill now requires the official `obsidian` binary to be registered instead of the third-party `obsidian-cli`; setups using `obsidian-cli` will break. • The repo-local Codex closeout review skill is renamed to `autoreview`; any config or scripts referencing the old skill name must be updated. • The minimum supported Node.js 22 line is raised to 22.19; environments running an earlier 22.x patch will no longer be supported.

OpenClaw v2026.5.12

Thu, 14 May 2026 18:28:04 GMT

OpenClaw v2026.5.12 adds ACP fallback backends, persisted scroll mode, leaner installs, and hardened Gateway pairing approval. • Adds `acp.fallbacks` config so ACP turns can try configured backup runtime backends when the primary backend is unavailable before any output is emitted. • Adds a persisted auto-scroll mode selector in Control UI/WebChat: always follow streaming output, stay near-bottom, or disable auto-scroll and use the New Messages button manually. • Externalizes Amazon Bedrock, Bedrock Mantle, Slack, OpenShell sandbox, and Anthropic Vertex provider/plugin packages so core installs only pull AWS/Slack/Vertex SDK dependencies when those providers are explicitly installed. • Requires approval before exposing pending Node pairing commands, capabilities, and permissions in Gateway, and refreshes the live approved surface when pairings change. • Requires v4 Gateway clients and streams explicit chat `deltaText`/`replace` frames so SDK clients can consume assistant updates without local diffing. • Requires system TLS trust before pinning a first-use direct `wss://` gateway certificate on macOS, and honors `gateway.remote.tlsFingerprint` as an explicit pin for remote node-mode sessions. • Discovers provider plugins from `setup.providers[].envVars` credentials during provider discovery. • Serializes and retries semantic config mutations centrally so concurrent commands can rebase safe changes instead of clobbering each other. • Enforces inbound media size caps on download streams for Feishu, WhatsApp, and Line plugins. • Limits install-time code safety scans to plugin-owned runtime entrypoints while keeping dependency manifest denylist checks. • Classifies ACP spawn-child sessions as `kind: "spawn-child"` in `openclaw sessions` and status output. • Reports `agentRuntime.id: "acpx"` with `source: "session-key"` for ACP control-plane session rows in `openclaw sessions --json`, `openclaw status`, and Gateway session RPC responses. • Honors `--no-git-update` for existing git checkouts before resolving release refs, preventing pinned source installs from moving during reinstall. Breaking changes: • Provider `apiKey` values are now resolved only through structured env SecretRefs (`secrets.providers[id]` / `secrets.defaults`); broad environment variable strings matching `^[A-Z_][A-Z0-9_]*$` are no longer inferred as provider credentials, which will break setups that relied on that implicit inference. • Gateway now requires v4 clients and streams explicit `deltaText`/`replace` frames; older SDK clients that relied on local diffing of assistant updates will break.

OpenClaw v2026.5.4

Tue, 05 May 2026 08:24:01 GMT

OpenClaw v2026.5.4 adds Gemini voice bridge for Google Meet, new auth/model/status CLI commands, OpenRouter caching, WhatsApp Newsletter targets, and tree-sitter shell explainer. • Adds Gemini realtime voice bridge for Google Meet/Twilio dial-in with paced audio streaming, backpressure-aware buffering, and barge-in queue clearing for snappier voice agents. • Adds `openclaw models auth list [--provider ] [--json]` to inspect saved per-agent auth profiles without exposing secrets. • Adds `openclaw qa mantis slack-desktop-smoke` to run Slack live QA inside a Crabbox VNC desktop with screenshot capture. • Adds degraded Discord transport and gateway event-loop starvation signals to `openclaw channels status` and `openclaw status --deep`. • Adds opt-in OpenRouter response caching via `X-OpenRouter-Cache`, `X-OpenRouter-Cache-TTL`, and cache-clear headers on verified OpenRouter routes. • Supports explicit WhatsApp Channel/Newsletter `@newsletter` outbound message targets with channel session metadata. • Adds a tree-sitter-backed shell command explainer for approval and command-review surfaces. • Adds `before_agent_finalize` bounded retry instructions in the Plugin SDK so workflow plugins can request one additional model pass. • Adds `registerIfAbsent` to the plugin runtime-state API for atomic keyed-store dedupe claims. • Adds plugin-owned `SessionEntry` slot projection and scoped trusted-policy session extension reads to the Plugin SDK. • Adds `streaming.progress.render: "rich"` for Block Kit progress drafts backed by structured progress line data in Slack. • Adds `agents.defaults.toolProgressDetail: "raw"` and per-agent overrides to control compact vs. raw tool summaries in `/verbose` and progress drafts. • Adds startup phase spans, active work labels, stale terminal bridge markers, and default sync-I/O tracing in `pnpm gateway:watch` for Gateway diagnostics. • Annotates ClawHub 429 errors with the reset window from `RateLimit-Reset`/`Retry-After` and appends a sign-in hint for unauthenticated requests. • Supports drive-absolute Docker bind sources on Windows sandbox while keeping blocked-path and allowed-root policy comparisons case-insensitive. • Advertises Codex audio transcription in runtime and manifest metadata, routing active Codex chat models to the OpenAI transcription default. • Preserves `realtime.introMessage: ""` so realtime Chrome joins can stay silent instead of restoring the default spoken intro. • Adds an agent-first filter to the Control UI chat session picker with responsive layout across phone/tablet/desktop widths. • Collapses consecutive duplicate text messages in the Control UI chat into one bubble with a count. • Makes the New Job sidebar in the Control UI cron view collapsible to reclaim space for the jobs list. • Shows the active agent name in Control UI dashboard breadcrumbs. • Records browser long animation frame or long task entries in the debug event log for slow dashboard render attribution. • Expands OpenRouter app-attribution categories to include coding, programming, writing, chat, and personal-agent usage on verified routes.

OpenClaw v2026.5.3

Mon, 04 May 2026 07:01:29 GMT

OpenClaw v2026.5.3 adds a bundled file-transfer plugin, /steer command, WhatsApp Newsletter targets, and unified streaming progress drafts. • Adds bundled file-transfer plugin with `file_fetch`, `dir_list`, `dir_fetch`, and `file_write` agent tools for binary file operations on paired nodes, with default-deny per-node path policy, symlink traversal off by default (opt-in `followSymlinks`), and a 16 MB per-round-trip ceiling. • Adds `/steer ` command for queue-independent steering of the active current-session run without starting a new turn when the session is idle. • Adds `/side` as a text and native slash-command alias for `/btw` side questions. • Adds unified `streaming.mode: "progress"` drafts with auto single-word status labels and shared progress configuration across Discord, Telegram, Matrix, Slack, and Microsoft Teams. • Supports explicit WhatsApp Channel/Newsletter `@newsletter` outbound message targets with channel session metadata instead of DM routing. • Adds `trackToolCalls: true` option on explicit Discord reaction tool calls to opt into tracking subsequent tool progress on the reacted message. • Adds tree-sitter-backed shell command explainer for approval and command-review surfaces. • Includes package dependency install state in `openclaw plugins list --json` output. • Annotates ClawHub 429 errors with reset windows and unauthenticated higher-rate-limit hints so operators can tell when downloads recover and when signing in helps. • Stores sandbox container and browser registry entries as per-runtime shard files, reducing unrelated session lock contention. • Adds `pnpm openclaw qa mantis discord-smoke` runner and manual GitHub workflow to verify Mantis Discord bot connectivity, smoke posting, reactions, and artifact upload. • Adds a Slack live transport QA runner with canary and mention-gating coverage. • Exposes the external Codex plugin as a selectable provider setup choice in Manual setup onboarding. • Tries plugin `@beta` updates first on the beta OpenClaw channel, falling back to default/latest when no plugin beta release exists. Breaking changes: • Gateway startup and hot reload no longer auto-restore invalid config; invalid config now fails closed and requires `openclaw doctor --fix` to repair.

OpenClaw v2026.5.2

Sat, 02 May 2026 23:37:55 GMT

OpenClaw v2026.5.2 adds git-based plugin installs, ClawHub search, proxy validation, Google Meet captions, and a structured heartbeat tool. • Adds `openclaw gateway restart --force` and `--wait ` flags, with active task run ID logging before restart deferral and explicit forced-restart reporting. • Adds first-class `git:` plugin installs with ref checkout, commit metadata, scanner/staging, and `plugins update` support for recorded git sources. • Adds ClawHub plugin search plus Crestodian plugin list/search/install/uninstall operations with approval and audit coverage. • Adds `openclaw proxy validate` so operators can verify effective proxy configuration, reachability, and allow/deny behavior before deploying proxy-routed commands. • Includes package dependency install state in `openclaw plugins list --json` so scripts can detect missing plugin dependencies without runtime-loading plugins. • On the beta update channel, plugin updates now try `@beta` first and fall back to default/latest when no plugin beta release exists. • Adds Grok 4.3 to the bundled xAI catalog and makes it the default xAI chat model. • Adds `googlemeet end-active-conference` command for closing managed Google Meet spaces after a call. • Adds `googlemeet test-listen` command and matching `google_meet` `test_listen` action so transcribe-mode joins wait for real caption or transcript movement before reporting listen-first health. • Adds live caption health monitoring for Chrome transcribe mode in Google Meet, including caption observer state, transcript counters, last caption text, and recent transcript lines in status and doctor output. • Adds SDK-facing `tools.invoke` RPC with shared HTTP policy, typed approval/refusal results, and SDK helper support. • Adds `extraBody`/`extra_body` passthrough for OpenAI-compatible TTS endpoints, enabling custom fields such as `lang` in `/audio/speech` requests. • Adds structured `heartbeat_respond` tool for tool-capable heartbeat runs so agents can record quiet outcomes or explicit notification text. • Adds `agents.defaults.skipOptionalBootstrapFiles` config key for skipping selected optional workspace files during bootstrap without disabling required workspace setup. • Adds UTC quarter-hour token buckets for the Usage Mosaic in Control UI with reuse for hour filtering. • Adds opt-in `channels.bluebubbles.replyContextApiFallback` for fetching original messages from the BlueBubbles HTTP API on reply-context cache misses, with SSRF protection and concurrent-request coalescing. • Adds `accessGroup:` reusable message-channel access groups for Discord channel-audience DM authorization so allowlists can reference named groups across channel auth paths. • Supports explicit WhatsApp Channel/Newsletter `@newsletter` outbound message targets with channel session metadata. • Allows `$include` directives in Gateway config to read files from operator-approved `OPENCLAW_INCLUDE_ROOTS` directories. • Adds a platform-level tool descriptor planner and caches plugin tool descriptors from api.registerTool(...) so repeated prompt-time planning skips plugin runtime loading. • Adds a fast path for canonical absolute POSIX containment checks in hot filesystem walkers, avoiding repeated `path.resolve` and `path.relative` work. • Externalizes ACPX behind `@openclaw/acpx` and diagnostics OpenTelemetry behind `@openclaw/diagnostics-otel`, keeping heavier runtime stacks out of core until installed. • Keeps active Discord buttons, selects, and forms working across Gateway restarts until they expire, preserving multi-step interactions during upgrades. • Publishes a safe default Slack App Home tab view on `app_home_opened` and tracks bot-participated threads across restarts so threaded conversations continue auto-replying after Gateway restarts. • Moves macOS menu bar companion recent session context rows into a Context submenu while keeping usage and cost details root-level for compactness. • Loads bundled plugins from the `extensions/*` pnpm workspace tree in source checkouts so plugin-local dependencies and edits are used directly. Breaking changes: • The split subagent/ACP thread-spawn toggles are replaced by `threadBindings.spawnSessions`; thread-bound spawns now default on. Run `openclaw doctor --fix` to migrate the legacy keys.

OpenClaw v2026.4.29

Thu, 30 Apr 2026 21:01:08 GMT

OpenClaw v2026.4.29 adds NVIDIA provider, people-aware memory wiki, opt-in follow-up commitments, OpenGrep scanning, and SQLite plugin state store. • Adds NVIDIA provider with API-key onboarding, static catalog metadata, and literal model-ref picker so NVIDIA hosted models can be selected with their provider prefix intact. • Adds agent-facing people wiki with canonical aliases, person cards, relationship graphs, privacy/provenance reports, evidence-kind drilldown, and search modes for person lookup, question routing, source evidence, and raw claims. • Adds opt-in inferred follow-up commitments with hidden batched extraction, per-agent/per-channel scoping, heartbeat delivery, CLI management, and `commitments.enabled`/`commitments.maxPerDay` config. • Introduces `steer` as the default active-run queue mode, draining all pending steering messages at the next model boundary, with a 500ms followup fallback debounce; legacy one-at-a-time steering remains available as `queue`. • Adds global `messages.visibleReplies` so operators can require visible output to go through message(action=send) for any source chat, with `messages.groupChat.visibleReplies` as the group/channel override. • Surfaces `spawnedBy` on subagent chat and agent broadcast payloads so clients can route child session events without an extra session lookup. • Adds optional per-conversation `allowedChatIds` and `deniedChatIds` filters to Active Memory so recall can be scoped to selected conversations. • Returns bounded partial recall summaries when the hidden memory sub-agent times out, including the default temporary-transcript path, so recovered context is not discarded. • Adds read-only `doctor.memory.remHarness` RPC so operator clients can preview bounded REM dreaming output without running mutation paths. • Adds SQLite-backed plugin state store (`api.runtime.state.openKeyedStore`) for restart-safe keyed registries with TTL, eviction, and automatic plugin isolation. • Adds `OPENCLAW_SKIP_ONBOARDING` environment variable so automated Docker installs can skip interactive onboarding while still applying gateway defaults. • Adds OpenGrep rulepack, source-rule compiler, provenance metadata check, and PR/full scan workflows that upload SARIF to GitHub Code Scanning. • Adds opt-in startup diagnostics timeline that records gateway lifecycle and plugin-load phases behind a config flag for slow-start diagnosis. • Extends Control UI locale registry with Persian (fa), Dutch (nl), Vietnamese (vi), Italian (it), Arabic (ar), and Thai (th) entries. • Adds Tencent Yuanbao channel to the channel listing and sidebar navigation. • Runs `pnpm gateway:watch` through a named tmux session by default, with `gateway:watch:raw` and `OPENCLAW_GATEWAY_WATCH_TMUX=0` for foreground mode. Breaking changes: • Configured tool sections (`tools.exec`, `tools.fs`) no longer implicitly widen restrictive profiles (`messaging`, `minimal`); users who need those tools under a restricted profile must add explicit `alsoAllow` entries — a startup warning identifies affected configs.

OpenClaw v2026.4.27

Wed, 29 Apr 2026 22:12:19 GMT

OpenClaw v2026.4.27 adds Codex Computer Use, DeepInfra provider, QQBot group chat, outbound proxy routing, and GPU passthrough for sandboxed agents. • Adds `/codex computer-use status/install` commands plus marketplace discovery, optional auto-install, and fail-closed MCP server checks before Codex-mode desktop-control turns start. • Adds bundled DeepInfra provider with `DEEPINFRA_API_KEY` onboarding, dynamic OpenAI-compatible model discovery, image generation/editing, image/audio media understanding, TTS, text-to-video, and memory embeddings. • Adds Tencent Yuanbao channel plugin (`openclaw-plugin-yuanbao`) with WebSocket bot DMs, group chats, and a new `docs/channels/yuanbao.md` quick-start guide. • Adds full QQBot group chat support: history tracking, @-mention gating, activation modes, per-group config, FIFO message queue with deliver debounce, C2C streaming via `StreamingController`, and chunked `sendMedia` for large files. • Adds opt-in operator-managed outbound proxy routing via `proxy.enabled` + `proxy.proxyUrl` / `OPENCLAW_PROXY_URL` with strict `http://` forward-proxy validation and loopback-only Gateway bypass. • Adds opt-in `sandbox.docker.gpus` passthrough so local GPU workloads can run inside Docker sandbox containers when the host runtime supports `--gpus`. • Adds `node.presence.alive` authenticated protocol event and `node.list` last-seen fields so background iOS and Android wakes mark paired nodes recently alive without treating them as connected. • Accepts non-image attachments through `chat.send` by staging them as agent-readable media paths instead of silently dropping files. • Adds `streaming.preview.toolProgress: false` config flag to hide interim tool lines in live Matrix preview edits while keeping answer previews. • Adds generic host hooks in Plugin SDK for session state, next-turn context, trusted tool policy, UI descriptors, events, scheduler cleanup, and run-scoped plugin context. • Exposes shared channel route normalization, parser-driven target resolution, raw-target compact keys, parsed-target types, and route comparison helpers through `openclaw/plugin-sdk/channel-route`. • Wires manifest `modelCatalog.aliases` and `modelCatalog.suppressions` into model-catalog planning and built-in model suppression, enabling provider rows/aliases/suppressions to be declared in plugin manifests. • Adds plugin compatibility warnings for deprecated implicit startup loading so plugin authors can migrate to explicit `activation.onStartup` metadata. • Attaches versioned structured approval metadata to pending Matrix approval messages so capable clients can render richer approval UI.

OpenClaw v2026.4.26

Tue, 28 Apr 2026 01:11:02 GMT

OpenClaw v2026.4.26 adds Matrix E2EE setup, a new migrate command, Cerebras provider, and asymmetric embedding config. • Adds `openclaw matrix encryption setup` to enable Matrix E2EE, bootstrap recovery, and print verification status in a single flow. • Adds `openclaw migrate` with plan, dry-run, JSON output, pre-migration backup, onboarding detection, and a bundled Hermes importer for config, memory, plugins, model providers, MCP servers, skills, and credentials. • Adds a bundled Claude importer to preview and apply Claude Code and Claude Desktop instructions, MCP servers, skills, command prompts, and archived state. • Adds Cerebras as a bundled provider plugin with onboarding, static model catalog, docs, and manifest-owned endpoint metadata. • Adds optional `memorySearch.inputType`, `queryInputType`, and `documentInputType` config for asymmetric embedding endpoints on OpenAI-compatible memory backends. • Adds model-specific retrieval query prefixes for `nomic-embed-text`, `qwen3-embedding`, and `mxbai-embed-large` in Ollama memory-search queries. • Adds a raw config pending-changes diff panel in Control UI that parses JSON5 and redacts sensitive values until revealed. • Adds opt-in `agents.defaults.compaction.maxActiveTranscriptBytes` preflight trigger to run local compaction when active JSONL grows too large. • Adds `openclaw nodes remove --node ` and `node.pair.remove` to clean stale gateway-owned node pairing records. • Adds a generic browser realtime transport contract, Google Live browser Talk sessions with constrained ephemeral tokens, and a Gateway relay for backend-only realtime voice plugins. • Moves model-id normalization, provider endpoint host metadata, and OpenAI-compatible request-family hints into plugin manifests, removing bundled-provider routing tables from core. • Allows `OPENCLAW_PLUGIN_STAGE_DIR` to contain layered runtime-dependency roots, resolving read-only preinstalled deps before installing missing deps into the writable root. Breaking changes: • Direct plugin config load/write helpers are deprecated in favor of passed runtime snapshots and transactional mutation helpers with explicit restart follow-up policy; existing callers must migrate to the new snapshot-based API.

OpenClaw v2026.4.25

Mon, 27 Apr 2026 12:45:30 GMT

OpenClaw v2026.4.25 adds TTS overhaul with 6 new providers, expanded OpenTelemetry coverage, browser automation upgrades, PWA/Web Push, and new plugin registry CLI commands. • Adds `/tts latest` read-aloud command and `/tts chat on|off|default` session-scoped auto-TTS controls for WhatsApp and chat channels. • Adds Azure Speech as a bundled TTS provider with Speech-resource auth, SSML escaping, native Ogg/Opus voice-note output, and telephony output. • Enables per-agent TTS voice overrides via `agents.list[].tts` and per-account deep-merge of `channels..accounts..tts` for Feishu and QQBot. • Adds `channels.discord.voice.model` config key to override the LLM used for Discord voice channel responses. • Adds Google Meet calendar-backed attendance export workflows, export manifests, and dry-run previews. • Adds PWA install support and Web Push notifications for Gateway chat in the Control UI. • Adds `openclaw browser start --headless` for one-shot local managed browser launch without modifying persisted browser config. • Adds `openclaw browser doctor --deep` for live CDP role-snapshot probing on slow hosts, with iframe-aware refs and cursor-clickable detection. • Exposes `--background` flag on `openclaw infer image generate` and `openclaw infer image edit` (with `--openai-background` as an OpenAI-specific alias), plus `--output-format png|jpeg` for fal image generation. • Adds `openclaw plugins registry` command for explicit persisted-registry inspection and `--refresh` repair. • Adds before-agent-finalize plugin hooks, cron `jobId` hook context, bounded native permission fingerprints, and Codex MCP hook relay support. • Adds metadata-only `model_call_started` and `model_call_ended` plugin hooks for provider/model call telemetry. • Adds a bundled `diagnostics-prometheus` plugin with a protected gateway scrape route for low-cardinality diagnostics metrics. • Emits OpenTelemetry `openclaw.harness.run` spans and `openclaw.harness.duration_ms` metrics for agent harness lifecycle telemetry. • Exports `openclaw.tool.loop` counters and spans, `openclaw.context.assembled` spans, and bounded memory histograms/pressure spans via OTEL. • Adds GenAI `gen_ai.client.token.usage` histogram and `gen_ai.client.operation.duration` histogram for model usage and latency tracking. • Supports signal-specific OTLP endpoint overrides for traces, metrics, and logs via config or standard OTEL environment variables. • Propagates W3C `traceparent` headers from trusted model-call trace context to provider transports. • Adds bounded `openclaw.agent` label to OpenClaw token metrics for per-agent Grafana dashboard grouping. • Adds first-run TUI setup helper, local planner fallback, full-TUI interactive Crestodian, startup progress indicators, and context mode selector. Breaking changes: • Managed plugin install metadata consolidates into `plugins/installs.json`, replacing `plugins/installed-index.json`; `plugins.installs` is no longer an authored config surface. • `OPENCLAW_DISABLE_PERSISTED_PLUGIN_REGISTRY` is now a deprecated break-glass switch; operators should use registry repair instead.

OpenClaw v2026.4.24

Sat, 25 Apr 2026 18:15:17 GMT

OpenClaw v2026.4.24 adds Google Meet, DeepSeek V4, realtime voice loops, coordinate-click browser automation, and OTEL diagnostics. • Adds a bundled Google Meet participant plugin with personal Google auth, Chrome/Twilio realtime transports, paired-node `chrome-node` support, artifact/attendance exports, and `googlemeet doctor --oauth` / `recover-tab` recovery tooling. • Adds DeepSeek V4 Flash and V4 Pro to the bundled model catalog; V4 Flash becomes the new onboarding default. • Enables realtime voice loops backed by the full OpenClaw agent (`openclaw_agent_consult`) in Talk, Voice Call, and Google Meet sessions. • Adds a Gemini Live realtime voice provider for Voice Call and Google Meet audio bridges, with bidirectional audio and function-call support. • Adds a Gateway realtime brain WebSocket endpoint backed by Gemini Live, with owner-auth gating and async OpenClaw tool handoff. • Adds viewport coordinate-click support for browser automation, accessible via `openclaw browser click-coords` for CLI use. • Adds `browser.actionTimeoutMs` config with a 60-second default action budget to prevent healthy long browser waits from timing out. • Supports per-profile `browser.profiles..headless` overrides so individual browser profiles can run headless independently. • Adds `voicecall setup` and a dry-run-by-default `voicecall smoke` command to verify Twilio/provider readiness before a live call. • Adds `openclaw matrix verify self` to establish full cross-signing identity trust for self-device verification from the CLI. • Adds a bundled Gradium text-to-speech provider with voice-note and telephony output support. • Exposes raw `vectorScore` and `textScore` alongside the combined `score` on hybrid memory search results for retrieval contribution inspection. • Adds `agents.defaults.contextInjection: "never"` config option to disable workspace bootstrap file injection for agents that fully own their prompt lifecycle. • Adds disabled-by-default `gateway.nodes.pairing.autoApproveCidrs` for automated first-time node pairing from explicit trusted CIDRs. • Exports run, model-call, and tool-execution lifecycle events as OTEL spans, with opt-in `diagnostics.otel.captureContent` controls for content attributes. • Refines the agent Tool Access panel with compact live-tool chips, collapsible tool groups, direct per-tool toggles, and runtime/source provenance display. • Adds a Steer action on queued chat messages so a browser follow-up can be injected into the active run without retyping it. • Adds a `modelCatalog` plugin manifest contract for provider-owned model rows, aliases, and suppression rules without loading plugin runtime. • Moves local PDF extraction into a bundled `document-extract` plugin, decoupling `pdfjs-dist` from core. • Moves Bonjour LAN Gateway discovery advertising into a default-enabled bundled plugin so users can disable it without affecting wide-area discovery. • Adds a central plugin compatibility registry with dated migration metadata for SDK/config/setup/runtime deprecation records. • Speeds up `openclaw models list` with static catalogs for bundled providers and narrower registry enumeration. • Lets Gemini TTS prepend configured `audioProfile` and `speakerName` prompt text for reusable speech-style control. • Exposes activation plan reasons and a richer plan API so callers can inspect why a plugin was selected. Breaking changes: • The Pi-only api.registerEmbeddedExtensionFactory(...) compatibility path is removed; bundled tool-result rewrites must now use api.registerAgentToolResultMiddleware(...) with `contracts.agentToolResultMiddleware` declaring the targeted harnesses.

OpenClaw v2026.4.23

Fri, 24 Apr 2026 15:19:55 GMT

OpenClaw v2026.4.23 adds image generation via OpenAI/OpenRouter, per-call generation timeouts, forked subagent contexts, and tunable local embedding context size. • Adds image generation and reference-image editing for `openai/gpt-image-2` via Codex OAuth, eliminating the need for a separate `OPENAI_API_KEY`. • Adds image generation and reference-image editing for OpenRouter image models via the `image_generate` tool using `OPENROUTER_API_KEY`. • Enables agents to pass provider-supported quality, output format, background, moderation, compression, and user hints through the `image_generate` tool. • Adds optional forked context for native `sessions_spawn` runs so child agents can inherit the requester transcript while keeping isolated sessions as the default. • Adds optional per-call `timeoutMs` support for image, video, music, and TTS generation tools so agents can extend provider request timeouts on a per-generation basis. • Adds configurable `memorySearch.local.contextSize` (default 4096) so local embedding contexts can be tuned for constrained hosts without patching the memory host. • Adds structured debug logging for embedded harness selection decisions in gateway logs, keeping `/status` clean while explaining auto-selection and Pi fallback reasons.

OpenClaw v2026.4.22

Thu, 23 Apr 2026 13:56:23 GMT

OpenClaw v2026.4.22 adds xAI multimodal support, new STT providers, /models add command, WhatsApp reply quoting, and a local embedded TUI mode. • Adds xAI image generation (`grok-imagine-image`, `grok-imagine-image-pro`), reference-image edits, text-to-speech (six voices, MP3/WAV/PCM/G.711), and `grok-stt` audio transcription including realtime Voice Call streaming. • Adds Voice Call streaming transcription for Deepgram, ElevenLabs, and Mistral; ElevenLabs also gains Scribe v2 batch audio transcription for inbound media. • New local embedded TUI mode lets you run terminal chats without a Gateway while keeping plugin approval gates enforced. • Onboarding now auto-installs missing provider and channel plugins so first-run setup completes without manual plugin recovery. • OpenAI Responses models automatically use OpenAI's native `web_search` tool when web search is enabled and no managed search provider is pinned. • New `/models add ` command lets you register a model from chat and use it without restarting the gateway. • Adds configurable native reply quoting via `replyToMode` for WhatsApp conversations. • Adds per-group and per-direct `systemPrompt` config for WhatsApp, injected as `GroupSystemPrompt` context on every turn, with `"*"` wildcard fallback and account-scoped overrides. • Adds mailbox-style `sessions_list` filters for label, agent, and search, plus visibility-scoped derived titles and last-message previews. • Adds a browser-local personal identity (name plus avatar) for the operator in the Control UI. • Enables payload-free stability recording by default and adds a support-ready diagnostics export with sanitized logs, status, health, config, and stability snapshots. • Adds the bundled Tencent Cloud provider plugin with TokenHub onboarding, `hy3-preview` model catalog, and tiered Hy3 pricing metadata. • Adds Claude Opus 4.7 via Amazon Bedrock Mantle's Anthropic Messages route with provider-owned bearer-auth streaming. • Moves GPT-5 prompt overlay into the shared provider runtime; adds `agents.defaults.promptOverlays.gpt5.personality` as a global friendly-style toggle. • Removes the Codex CLI auth import path (`~/.codex`) from onboarding; browser login or device pairing replaces it. • Defaults `claude-cli` runs to warm stdio sessions and resumes from stored Claude session after Gateway restarts or idle exits. • Adds bundled native tokenjuice support as an opt-in plugin that compacts noisy `exec` and `bash` tool results in Pi embedded runs. • Adds `openClawToolsMcpBridge` option that injects a core OpenClaw MCP server for selected built-in tools, starting with `cron`. • Adds an opt-in debug timing helper for local CLI performance investigations with readable stderr output and JSONL capture. • Marks known local backends (vLLM, SGLang, llama.cpp, LM Studio, LocalAI, Jan, TabbyAPI, text-generation-webui) as streaming-usage compatible for accurate token accounting. • Adds an explicit `Runner:` field to `/status` so sessions report whether they run on embedded Pi, a CLI-backed provider, or an ACP harness agent. • Adds Thai translation support for the docs site. • Reduces `doctor --non-interactive` runtime by ~74% via lazy-loading of doctor plugin paths. • Cuts bundled plugin load time by 82–90% via native Jiti loading for built plugin dist modules. • Adds a bundled-plugin embedded extension factory seam so native plugins can extend Pi embedded runs with async `tool_result` hooks. • Routes native Codex app-server turns through `before_prompt_build`, `before_compaction`, `after_compaction`, `llm_input`, `llm_output`, and `agent_end` lifecycle hooks. • Adds a bundled-plugin Codex app-server extension seam for async `tool_result` middleware and fires `after_tool_call` for Codex tool runs. • Records per-scenario reply RTT in the live Telegram QA report and summary. Breaking changes: • The Codex CLI auth import path (`~/.codex`) is removed from onboarding and provider discovery; OpenClaw no longer copies OAuth material from `~/.codex` into agent auth stores — use browser login or device pairing instead.

OpenClaw v2026.4.20

Tue, 21 Apr 2026 19:19:35 GMT

OpenClaw v2026.4.20 adds Mattermost live-draft streaming, QA CLI failure gates, cron state splitting, group-aware BlueBubbles prompts, and Kimi K2.6 defaults. • Adds Mattermost live-draft preview: streams thinking, tool activity, and partial reply text into a single draft post that finalizes in place. • Adds `openclaw qa suite` and `openclaw qa telegram` failure-by-default mode with `--allow-failures` flag for artifact-only CI runs. • Splits cron runtime state into `jobs-state.json` so `jobs.json` remains stable for git-tracked job definitions. • Forwards per-group `systemPrompt` config into `GroupSystemPrompt` context for BlueBubbles, with `"*"` wildcard fallback, so group-specific behavioral instructions are injected on every turn. • Adds opt-in start and completion notices during agent context compaction. • Defaults bundled Moonshot surfaces (setup, web search, media understanding) to `kimi-k2.6`, with `kimi-k2.5` remaining available for compatibility. • Allows `thinking.keep = "all"` on `moonshot/kimi-k2.6`, stripping it for other Moonshot models or when pinned `tool_choice` disables thinking. • Adds tiered model pricing support from cached catalogs and configured models, including bundled Moonshot Kimi K2.6/K2.5 cost estimates for token-usage reports. • Adds detached runtime registration contract so plugin executors can own detached task lifecycle and cancellation independently of core task internals. • Strengthens default system prompt and OpenAI GPT-5 overlay with clearer completion bias, live-state checks, weak-result recovery, and verification-before-final guidance. • Adds configurable `channels.telegram.pollingStallThresholdMs` (also per-account) to tune the polling watchdog threshold. • Adds configurable `channels.bluebubbles.sendTimeoutMs` (also per-account) with a raised default outbound send timeout of 30s. Breaking changes: • Session entry cap and age pruning are now enforced by default; existing deployments with large accumulated session stores will have those stores pruned at load time on upgrade.

OpenClaw v2026.4.15

Thu, 16 Apr 2026 21:50:22 GMT

OpenClaw v2026.4.15 adds Gemini TTS, GitHub Copilot embeddings, LanceDB cloud storage, and a Model Auth status card. • Adds Gemini text-to-speech support to the bundled `google` plugin, with voice selection, WAV reply output, and PCM telephony output. • Adds a Model Auth status card in Control UI/Overview showing OAuth token health and provider rate-limit pressure, with expiry callouts, backed by a new `models.authStatus` gateway method. • Adds GitHub Copilot as an embedding provider for memory search, with a dedicated Copilot embedding host helper for plugin reuse. • Adds cloud storage support to `memory-lancedb` so durable memory indexes can run on remote object storage instead of local disk only. • Adds experimental `agents.defaults.experimental.localModelLean: true` to drop heavyweight default tools (`browser`, `cron`, `message`) and reduce prompt size for weaker local-model setups. • Bundles Claude Opus 4.7 as the new default Anthropic model selection, including `opus` aliases and image understanding. Breaking changes: • The default `dreaming.storage.mode` changes from `inline` to `separate`, so Dreaming phase blocks (`## Light Sleep`, `## REM Sleep`) now land in `memory/dreaming/{phase}/YYYY-MM-DD.md` instead of `memory/YYYY-MM-DD.md`. Operators who want the previous behavior must explicitly set `plugins.entries.memory-core.config.dreaming.storage.mode: "inline"`.

OpenClaw v2026.4.14

Tue, 14 Apr 2026 13:03:29 GMT

OpenClaw v2026.4.14 adds forward-compat support for GPT-5.4-pro and surfaces human Telegram forum topic names in agent context. • Adds forward-compat support for `gpt-5.4-pro` (OpenAI Codex family), including Codex pricing/limits and list/status visibility before the upstream catalog catches up. • Surfaces human Telegram forum topic names in agent context, prompt metadata, and plugin hook metadata by learning names from Telegram forum service messages.

OpenClaw v2026.4.12

Mon, 13 Apr 2026 12:35:53 GMT

OpenClaw v2026.4.12 adds Active Memory sub-agent, LM Studio & Codex providers, MLX speech, exec-policy CLI, and Matrix live markers. • New Active Memory plugin runs a dedicated memory sub-agent before each reply, auto-surfacing relevant preferences and past context with configurable message/recent/full context modes, live `/verbose` inspection, and opt-in transcript persistence. • New bundled LM Studio provider supports onboarding, runtime model discovery, stream preload, and memory-search embeddings for local/self-hosted OpenAI-compatible models. • New bundled Codex provider routes `codex/gpt-*` models through Codex-managed auth, native threads, model discovery, and compaction while keeping `openai/gpt-*` on the standard OpenAI path. • New `openclaw exec-policy` command with `show`, `preset`, and `set` subcommands for synchronizing `tools.exec.*` config with the local exec approvals file. • New `commands.list` RPC on the Gateway lets remote clients discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata. • New per-provider `models.providers.*.request.allowPrivateNetwork` setting enables trusted self-hosted OpenAI-compatible endpoints without broadening global network policy. • New `--runner multipass` lane for `openclaw qa suite` runs repo-backed QA scenarios inside a disposable Linux VM and writes back report, summary, and VM logs. • New `openclaw qa credentials` admin commands and Convex-backed pooled Telegram credential leasing for lab/QA environments. • New `openclaw qa telegram` lane adds live private-group bot-to-bot checks with hardened artifact handling and native Telegram command reply threading. • Experimental local MLX speech provider for Talk Mode on macOS with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. • Matrix integration now adds MSC4357 live markers to draft preview sends and edits so supporting clients can render a typewriter animation that stops when the final edit lands.

OpenClaw v2026.4.11

Sun, 12 Apr 2026 00:18:03 GMT

OpenClaw v2026.4.11 adds ChatGPT import ingestion, Teams reactions, plugin manifest descriptors, and richer video generation options. • Adds ChatGPT import ingestion to Dreaming/memory-wiki, plus new `Imported Insights` and `Memory Palace` diary subtabs for inspecting imported chats, compiled wiki pages, and full source pages from the UI. • Adds `[embed ...]` rich output tag to Control UI/webchat, renders assistant media/reply/voice directives as structured chat bubbles, and gates external embed URLs behind config. • Extends Tools/video_generate with URL-only asset delivery, typed `providerOptions`, reference audio inputs, per-asset role hints, `adaptive` aspect-ratio support, and a higher image-input cap for richer provider generation modes. • Improves Feishu document comment sessions with richer context parsing, comment reactions, and typing feedback so document-thread conversations behave like chat conversations. • Adds Microsoft Teams reaction support, reaction listing, Graph pagination, and delegated OAuth setup for sending reactions while preserving application-auth read paths. • Allows plugin manifests to declare activation and setup descriptors for required auth, pairing, and configuration steps without hardcoded core special cases. • Caches Ollama `/api/show` context-window and capability metadata during model discovery to eliminate redundant refetches on picker refreshes. • Surfaces how configured OpenAI-compatible endpoints are classified in embedded-agent debug logs for easier diagnosis of local and proxy routing issues. • Adds GPT-5.4 vs Opus 4.6 agentic parity report gate with shared scenario coverage checks, stricter evidence heuristics, and skipped-scenario accounting.

OpenClaw v2026.4.10

Sat, 11 Apr 2026 02:43:25 GMT

OpenClaw v2026.4.10 adds Active Memory sub-agent, local MLX speech, exec-policy CLI, gateway command discovery, and expanded QA lanes. • Adds Active Memory plugin that automatically injects relevant preferences, context, and past details into ongoing chats via a dedicated memory sub-agent before each reply, with configurable context modes and live `/verbose` inspection. • Adds experimental local MLX speech provider for Talk Mode on macOS, with explicit provider selection, local utterance playback, interruption handling, and system-voice fallback. • Adds bundled Codex provider so `codex/gpt-*` models use Codex-managed auth, native threads, model discovery, and compaction while `openai/gpt-*` stays on the standard OpenAI path. • Adds Seedance 2.0 model support to the bundled fal provider, including duration, resolution, audio, and seed metadata fields for video generation. • Adds Microsoft Teams message actions for pin, unpin, read, react, and listing reactions. • Adds `openclaw exec-policy` command with `show`, `preset`, and `set` subcommands for synchronizing `tools.exec.*` config with the local exec approvals file. • Adds `commands.list` RPC to the gateway so remote clients can discover runtime-native, text, skill, and plugin commands with surface-aware naming and serialized argument metadata. • Adds per-provider `models.providers.*.request.allowPrivateNetwork` setting to enable trusted self-hosted OpenAI-compatible endpoints. • Adds `openclaw qa matrix` lane backed by a disposable Matrix homeserver covering threading, reactions, restart, and allowlist transport behavior. • Adds `openclaw qa telegram` lane for private-group bot-to-bot checks with native Telegram command reply threading. • Adds `--runner multipass` option to `openclaw qa suite` for running QA scenarios inside a disposable Linux VM with report and log write-back. • Adds MSC4357 live markers to Matrix draft preview sends and edits, enabling typewriter animation in supporting clients. • Adds opt-in strict-agentic embedded Pi execution contract for GPT-5-family runs so plan-only or filler turns continue acting until a real blocker is reached. • Adds provider-owned OpenAI/Codex tool schema compatibility and surfaces embedded-run replay/liveness state for long-running agent runs. • Adds QQBot per-account streaming mode configuration via `streaming.mode` (`"partial"` | `"off"`) instead of hardcoding it off.

OpenClaw v2026.4.9

Thu, 09 Apr 2026 02:25:28 GMT

OpenClaw v2026.4.9 adds REM backfill for memory/dreaming, diary timeline UI, character-vibes QA reports, and provider auth aliasing. • Adds grounded REM backfill lane via `rem-harness --path` so old daily notes can replay into Dreams and durable memory without a second memory stack. • Adds structured diary view in Control UI with timeline navigation, backfill/reset controls, traceable dreaming summaries, and a grounded Scene lane with promotion hints. • Adds character-vibes evaluation reports in QA/lab with model selection and parallel runs for faster candidate behavior comparison. • Adds `providerAuthAliases` declaration in provider manifests so variants can share env vars, auth profiles, config-backed auth, and API-key onboarding choices. • Adds `pnpm ios:version:pin -- --from-gateway` workflow for iOS release train versioning pinned to explicit CalVer. • Adds `openclaw/plugin-sdk/command-status` subpath to the Plugin SDK, splitting command status builders out of auth-only imports.

OpenClaw v2026.4.7

Wed, 08 Apr 2026 02:12:57 GMT

OpenClaw v2026.4.7 adds a first-class `infer` hub, pluggable compaction, webhook ingress, memory-wiki, Arcee AI, and Gemma 4 support. • Auto-fallback across image, music, and video providers with intent preservation and capability remapping for size/aspect/resolution/duration hints. • New bundled webhook ingress plugin enables external automation to create and drive bound TaskFlows through per-route shared-secret endpoints. • Pluggable compaction provider registry lets plugins replace the built-in summarization pipeline, configured via `agents.defaults.compaction.provider`. • New `agents.defaults.systemPromptOverride` for controlled prompt experiments plus heartbeat prompt-section controls. • Gemma 4 model support added for the Google provider, including reasoning support and explicit thinking-off semantics in compatibility wrappers. • New bundled Arcee AI provider plugin with Trinity catalog entries and OpenRouter support. • Ollama vision capability auto-detected from `/api/show` response, enabling image attachments on supported models. • Dreaming corpus now ingests redacted session transcripts with per-day session-corpus notes, cursor checkpointing, and promotion/doctor support. • Plugin SDK assemble() now receives `availableTools` and `citationsMode`, plus memory-artifact and memory-prompt seams for companion plugins and non-legacy context engines. • Discord `event-create` action accepts a cover image URL or local PNG/JPG/GIF file path. • Prompt-cache runtime context exposed to context engines, with current-turn usage aligned to the active attempt. • String-content compatibility added for stricter OpenAI-compatible chat backends (`inferrs`), with full config example and troubleshooting guidance.

OpenClaw v2026.4.5

Mon, 06 Apr 2026 03:04:54 GMT

OpenClaw v2026.4.5 adds built-in video/music generation tools, ComfyUI integration, 12 new providers, Matrix exec approvals, multilingual Control UI, and experimental memory dreaming. • Adds built-in `video_generate` agent tool so agents can create and return video media directly in replies. • Adds built-in `music_generate` tool with bundled Google Lyria and MiniMax providers plus ComfyUI workflow-backed support, including async task tracking and follow-up audio delivery. • Adds bundled `comfy` workflow media plugin for local ComfyUI and Comfy Cloud, covering `image_generate`, `video_generate`, and `music_generate` with prompt injection, reference-image upload, live tests, and output download. • Adds bundled Qwen, Fireworks AI, StepFun, MiniMax TTS, Ollama Web Search, and MiniMax Search providers for chat, speech, and search workflows. • Adds Amazon Bedrock Mantle support plus inference-profile discovery and automatic request-region injection for Bedrock-hosted Claude, GPT-OSS, Qwen, Kimi, GLM, and similar routes. • Adds Amazon Bedrock embeddings for Titan, Cohere, Nova, and TwelveLabs models with AWS credential-chain auto-detection for memory/search. • Adds localized Control UI for Simplified Chinese, Traditional Chinese, Brazilian Portuguese, German, Spanish, Japanese, Korean, French, Turkish, Indonesian, Polish, and Ukrainian. • Adds `openclaw plugins install --force` to replace existing plugin and hook-pack targets without using the dangerous-code override flag. • Adds ClawHub search, detail, and install flows directly in the Skills panel. • Adds iOS APNs exec approval notifications that open an in-app approval modal and clear stale state on resolution. • Adds Matrix-native exec approval prompts with account-scoped approvers, channel-or-DM delivery, and room-thread aware resolution. • Adds configurable `contextVisibility` per channel (`all`, `allowlist`, `allowlist_quote`) to filter supplemental context by sender allowlists. • Adds shared model and media request transport overrides (headers, auth, proxy, TLS) across OpenAI-, Anthropic-, Google-, and compatible provider paths. • Exposes OpenClaw tools to background Claude CLI runs via a loopback MCP bridge with stdin + `stream-json` streaming for live progress on long replies. • Adds experimental structured plan updates and structured execution-item events for step-by-step agent progress in compatible UIs. • Adds bundled xAI (`grok-imagine-video`), Alibaba Model Studio Wan, and Runway video providers with live-test and default model wiring. • Adds experimental memory dreaming with weighted short-term recall promotion, `/dreaming` command, Dreams UI, multilingual conceptual tagging, and three cooperative phases (light, deep, REM). • Adds configurable dreaming aging controls (`recencyHalfLifeDays`, `maxAgeDays`) and optional verbose logging for recall decay tuning. • Adds REM preview tooling (`openclaw memory rem-harness`, `promote-explain`) and makes deep promotion replay-safe. • Adds Dream Diary surface in Dreams UI with simplified user-facing config (`enabled` plus optional `frequency`). • Adds prompt-cache break diagnostics and explicit cache reuse reporting in `openclaw status --verbose`. • Enriches `openclaw config schema` JSON Schema output with field titles and descriptions for editor and agent consumers. • Embeds ACP runtime directly in the bundled `acpx` plugin with a generic `reply_dispatch` hook, removing the external ACP CLI hop. • Adds plugin-config TUI prompts to guided onboarding/setup flows. Breaking changes: • The legacy config aliases `talk.voiceId`, `talk.apiKey`, `agents.*.sandbox.perSession`, `browser.ssrfPolicy.allowPrivateNetwork`, `hooks.internal.handlers`, and channel/group/room `allow` toggles are removed; use the canonical public paths and `enabled` instead (`openclaw doctor --fix` can migrate existing configs). • Bundled CLI text-provider backends and the `agents.defaults.cliBackends` config surface are removed; ACP harness sessions and Gemini media understanding remain on native bundled providers. • The Claude CLI backend and setup-token are removed from new Anthropic onboarding; existing `anthropic:claude-cli` profiles remain runnable but `openclaw doctor` will repair or remove stale state.

OpenClaw v2026.4.2

Thu, 02 Apr 2026 18:30:45 GMT

OpenClaw v2026.4.2 adds Task Flow orchestration, a `before_agent_reply` plugin hook, Android assistant entrypoints, and new Feishu/Matrix collaboration features. • Adds `openclaw flows` inspection and recovery primitives for durable Task Flow state and revision tracking, with managed-vs-mirrored sync modes for persistent background orchestration. • Adds managed child task spawning with sticky cancel intent, letting external orchestrators stop scheduling immediately and settle parent Task Flows to `cancelled` once active child tasks finish. • Adds `api.runtime.taskFlow` plugin seam so plugins and trusted authoring layers can create and drive managed Task Flows from host-resolved context without passing owner identifiers on each call. • Adds `before_agent_reply` plugin hook so plugins can short-circuit the LLM with synthetic replies after inline actions. • Adds Android assistant-role entrypoints and Google Assistant App Actions metadata so OpenClaw can be launched from the assistant trigger and receive prompts into the chat composer. • Adds provider-owned replay hook surfaces for transcript policy, replay cleanup, and reasoning-mode dispatch. • Adds plugin-owned `viewerBaseUrl` config so diff viewer links can use a stable proxy/public origin without passing `baseUrl` on every tool call. • Adds `agents.defaults.compaction.model` resolution across manual `/compact` and other context-engine compaction paths, ensuring configured override models apply at all runtime entrypoints. • Adds `agents.defaults.compaction.notifyUser` config to make the compaction start notice opt-in rather than always displayed. • Adds a dedicated Feishu Drive comment-event flow with comment-thread context resolution, in-thread replies, and `feishu_drive` comment actions for document collaboration. • Adds spec-compliant `m.mentions` metadata to Matrix text sends, media captions, edits, poll fallback text, and action-driven edits for reliable mention notifications in clients like Element. • Adds `reactionLevel` guidance for WhatsApp agent reactions. • Moves provider-specific session conversation grammar into plugin-owned session-key surfaces, preserving Telegram topic routing and Feishu scoped inheritance across bootstrap, model override, restart, and tool-policy paths. • Auto-enables DM-first native chat approvals when supported channels can infer approvers from existing owner config, while keeping channel fanout explicit. Breaking changes: • The xAI `x_search` settings have moved from `tools.web.x_search.*` to `plugins.entries.xai.config.xSearch.*`; auth is now standardized on `plugins.entries.xai.config.webSearch.apiKey` / `XAI_API_KEY`. Run `openclaw doctor --fix` to migrate. • The Firecrawl `web_fetch` config has moved from `tools.web.fetch.firecrawl.*` to `plugins.entries.firecrawl.config.webFetch.*`, and the `web_fetch` fallback now routes through the new fetch-provider boundary instead of a Firecrawl-only core branch. Run `openclaw doctor --fix` to migrate. • Gateway/node host exec now defaults to YOLO mode (`security=full`, `ask=off`); existing setups that relied on approval prompts from host exec will no longer receive them without explicit reconfiguration.

OpenClaw v2026.4.1

Wed, 01 Apr 2026 16:58:06 GMT

OpenClaw v2026.4.1 adds a chat-native task board, SearXNG web search, Bedrock Guardrails, Voice Wake, per-job tool allowlists, and more. • Adds `/tasks` as a chat-native background task board for the current session, with recent task details and agent-local fallback counts. • Adds a bundled SearXNG provider plugin for `web_search` with configurable host support. • Adds Amazon Bedrock Guardrails support to the bundled Bedrock provider. • Adds a Voice Wake option on macOS to trigger Talk Mode hands-free. • Adds a dedicated Feishu Drive comment-event flow with comment-thread context resolution, in-thread replies, and `feishu_drive` comment actions. • Makes `chat.history` text truncation configurable via `gateway.webchat.chatHistoryMaxChars` and a per-request `maxChars` field. • Adds `agents.defaults.params` for setting global default provider parameters across all agents. • Adds `auth.cooldowns.rateLimitedProfileRotations` knob and cross-provider model fallback after rate-limit retries are exhausted. • Adds `openclaw cron --tools` flag for per-job tool allowlists. • Adds configurable `errorPolicy` and `errorCooldownMs` controls for Telegram to suppress repeated delivery errors per account, chat, and topic. • Adds `glm-5.1` and `glm-5v-turbo` models to the bundled Z.AI provider catalog. • Adds `reactionLevel` guidance for WhatsApp agent reactions.

OpenClaw v2026.3.31

Tue, 31 Mar 2026 20:54:44 GMT

OpenClaw v2026.3.31 adds QQ Bot channel, Slack exec approvals, Matrix streaming/proxy, MCP remote HTTP/SSE, WhatsApp emoji reactions, and a unified background task control plane. • Adds QQ Bot as a bundled channel plugin with multi-account setup, SecretRef-aware credentials, slash commands, reminders, and media send/receive support. • Adds native Slack approval routing so exec approval prompts can be authorized directly in Slack instead of falling back to the Web UI or terminal. • Adds `openclaw flows list|show|cancel` commands for linear task flow control, surfacing orchestrated work with doctor recovery hints for orphaned flows. • Unifies ACP, subagent, cron, and background CLI execution under one SQLite-backed task ledger with audit, maintenance, and status visibility. • Adds remote HTTP/SSE server support for `mcp.servers` URL configs, including auth headers and safe credential redaction. • Adds draft streaming for Matrix so partial replies update the same message in place rather than sending a new message per chunk. • Adds explicit `channels.matrix.proxy` config for routing Matrix traffic through an HTTP(S) proxy, including account-level overrides. • Adds optional `channels.matrix.historyLimit` for Matrix group triggers, with per-agent watermarks and retry-safe snapshots. • Adds LINE image, video, and audio outbound sends on the LINE-specific delivery path, including preview/tracking handling for videos. • Adds WhatsApp emoji reactions so agents can react to incoming messages instead of sending a text reply. • Adds a Graph-backed member info action for Microsoft Teams to resolve channel member details directly from Microsoft Graph. • Adds per-agent `memorySearch.qmd.extraCollections` so agents can opt into cross-agent session search without collapsing all transcripts into one namespace. • Adds native Codex web search support for embedded Pi runs, including config, docs, and wizard coverage. • Adds Android notification-forwarding controls with package filtering, quiet hours, and rate limiting. • Adds per-agent `threadReplies` overrides for Matrix DMs to keep thread session isolation aligned with the triggering message policy. • Adds bundle MCP tools with provider-safe names (`serverName__toolName`), optional `streamable-http` transport selection, and per-server connection timeouts. • Adds a configurable idle-stream timeout for embedded LLM runner requests so stalled model streams abort cleanly. • Adds structured provider diagnostics and fallback attempt analytics for TTS. • Adds an explicit default-off ACPX plugin-tools MCP bridge config with documented trust boundary. • Adds OpenAI `text.verbosity` forwarding across Responses HTTP and WebSocket transports, surfaced in `/status`. Breaking changes: • The `nodes.run` shell wrapper is removed from the CLI and agent `nodes` tool; node shell execution must now go through `exec host=node`. • Legacy provider compat subpaths, older bundled provider setup, and channel-runtime compatibility shims in the Plugin SDK are deprecated and emit migration warnings; use `openclaw/plugin-sdk/*` entrypoints and local `api.ts`/`runtime-api.ts` barrels going forward. • Built-in dangerous-code `critical` findings and install-time scan failures now fail closed by default; plugin installs and gateway-backed skill dependency installs that previously succeeded may now require `--dangerously-force-unsafe-install` to proceed. • `trusted-proxy` in Gateway/auth now rejects mixed shared-token configs, and local-direct fallback requires the configured token instead of implicitly authenticating same-host callers. • Node commands now stay disabled until node pairing is approved; device pairing alone no longer exposes declared node commands. • Node-originated runs now stay on a reduced trusted surface; notification-driven or node-triggered flows that previously relied on broader host/session tool access may need adjustment.

OpenClaw v2026.3.28

Sun, 29 Mar 2026 01:34:30 GMT

OpenClaw v2026.3.28 adds xAI x_search, MiniMax image gen, async approval hooks, ACP channel binds, and a new config schema command. • Adds first-class `x_search` tool for the xAI/Grok provider via the Responses API, auto-enabled from existing web-search and tool config with no manual plugin toggles required. • Adds optional `x_search` setup (including model picker) during `openclaw onboard` and `openclaw configure --section web` for the bundled Grok web-search plugin. • New MiniMax image generation provider supporting the `image-01` model with generate, image-to-image editing, and aspect ratio control. • Adds async `requireApproval` to `before_tool_call` plugin hooks, enabling plugins to pause tool execution and prompt for approval via the exec overlay, Telegram buttons, Discord interactions, or `/approve`. • Adds ACP current-conversation binds for Discord, BlueBubbles, and iMessage so `/acp spawn codex --bind here` turns the active chat into a Codex-backed workspace without spawning a child thread. • Enables `apply_patch` by default for OpenAI and OpenAI Codex models, aligned with `write` sandbox permissions. • Auto-loads bundled provider and CLI-backend plugins from explicit config refs, removing the need for manual `plugins.allow` entries for Claude CLI, Codex CLI, and Gemini CLI. • New `upload-file` Slack action for routing file uploads through the Slack upload transport with optional filename, title, and comment overrides. • Extends `upload-file` action with explicit Microsoft Teams and Google Chat support, and exposes BlueBubbles file sends through `upload-file` (legacy `sendAttachment` alias preserved). • Matrix TTS auto-replies now sent as native Matrix voice bubbles instead of generic audio attachments. • New `openclaw config schema` command prints the generated JSON schema for `openclaw.json`. • Exposes `runHeartbeatOnce` in the plugin runtime `system` namespace so plugins can trigger a single heartbeat cycle with an explicit delivery target override. • Simplifies Podman rootless container setup and documents the host-CLI `openclaw --container ...` workflow. • Outbound Tavily API requests now tagged with `X-Client-Source: openclaw` for traffic attribution. Breaking changes: • The `qwen-portal-auth` OAuth integration for `portal.qwen.ai` is removed; migrate to Model Studio with `openclaw onboard --auth-choice modelstudio-api-key`. • Automatic config migrations older than two months are dropped; very old legacy keys now fail validation instead of being rewritten on load or by `openclaw doctor`. • MiniMax model catalog is trimmed to M2.7 only; legacy M2, M2.1, M2.5, and VL-01 models are removed. • Regular-mode runtime fallback for old bundled `tts.` API-key shapes is removed (legacy diagnostics remain available via Doctor).

OpenClaw v2026.3.24

Wed, 25 Mar 2026 16:35:52 GMT

OpenClaw v2026.3.24 adds OpenAI-compatible endpoints, Teams streaming, a --container flag, Discord auto-thread naming, and a revamped Skills UI. • Adds `/v1/models` and `/v1/embeddings` Gateway endpoints and forwards explicit model overrides through `/v1/chat/completions` and `/v1/responses` for OpenAI-compatible client and RAG pipeline support. • Adds `--container` flag and `OPENCLAW_CONTAINER` env var to run `openclaw` commands inside a running Docker or Podman OpenClaw container. • Adds `before_dispatch` plugin hook with canonical inbound metadata, routing handled replies through the normal final-delivery path and preserving TTS and routed delivery semantics. • Enhances `/tools` endpoint to show tools the current agent can actually use right now, with a compact default view, optional detailed mode, and a live 'Available Right Now' section in the Control UI. • Migrates Microsoft Teams integration to the official Teams SDK with streaming 1:1 replies, welcome cards with prompt starters, feedback/reflection, typing indicators, status updates, and native AI labeling. • Adds message edit and delete support for sent Teams messages, including in-thread fallbacks when no explicit target is provided. • Adds one-click install recipes to bundled skills (coding-agent, gh-issues, openai-whisper-api, session-logs, tmux, trello, weather) for dependency installation via CLI and Control UI. • Adds Control UI skills status-filter tabs (All / Ready / Needs Setup / Disabled) with counts and a click-to-detail dialog showing requirements, toggle, install action, API key entry, source metadata, and homepage link. • Adds optional `autoThreadName: "generated"` Discord config for asynchronous LLM-generated auto-thread titles. • Adds expandable `

` lazy-loaded inline markdown preview for agent workspace files in Control UI, with comprehensive `.sidebar-markdown` styles. • Integrates `@create-markdown/preview` v2 with frosted-backdrop dialog and auto-adapting light/dark system theme for agent workspace file previews in Control UI. • Replaces macOS app horizontal pill navigation with a collapsible tree sidebar using disclosure chevrons and indented subsection rows. • Surfaces API key setup guidance (where to get a key, CLI save command, storage path) in `openclaw skills info` output. • Adds Node 22.14+ as the supported floor for `openclaw update`, with preflight `engines.node` checks that fail clearly on outdated runtimes instead of attempting unsupported installs.

OpenClaw v2026.3.23

Mon, 23 Mar 2026 23:15:50 GMT

OpenClaw v2026.3.23 adds pay-as-you-go Qwen endpoints, Knot theme overhaul, SHA-256 CSP hashing, and cron timezone-aware scheduling. • Adds standard pay-as-you-go DashScope endpoints for China and global Qwen API keys under the relabeled Qwen (Alibaba Cloud Model Studio) provider group. • New Knot UI theme with black-and-red palette meeting WCAG 2.1 AA contrast, discrete roundness stops, config icons for Diagnostics/CLI/Secrets/ACP/MCP sections, and improved aria-labels. • Adds SHA-256 hash computation for inline `