releaseintermediate
[Release] openclaw/openclaw v2026.2.25-beta.1: openclaw 2026.2.25-beta.1
By steipetegithub
View original on githubOpenClaw v2026.2.25-beta.1 release includes improvements to Android chat streaming and startup performance, UI enhancements for mobile compose actions, and a major refactor of heartbeat configuration policy. The release addresses numerous critical fixes across Telegram, Slack, Discord, and LINE channels, including subagent delivery state machine improvements, webhook handling, session threading, media routing, and typing indicator management.
Key Points
- •Improved Android chat UI with better streaming delivery, markdown rendering (GitHub-flavored), and mobile-optimized compose button layout for small screens
- •Enhanced startup performance by deferring foreground-service initialization, moving WebView debugging out of critical path, and adding deterministic cold-start benchmarking tools
- •Replaced heartbeat DM toggle with configurable `agents.defaults.heartbeat.directPolicy` (allow/block) for clearer delivery semantics at global and per-agent levels
- •Clarified security onboarding to emphasize OpenClaw's personal-by-default model; shared/multi-user setups require explicit hardening and lock-down
- •Rebranded all references from `bot.molt` to `ai.openclaw` across iOS app, launchd labels, bundle IDs, logging subsystems, docs, and CLI fixtures
- •Fixed critical subagent delivery issues with explicit queue/direct/fallback state machine and improved channel-plugin resolution in cold/stale registry states
- •Resolved Telegram, Slack, Discord, and LINE webhook/inbound message handling to prevent dropped updates, oversized session inheritance, and stuck typing indicators
- •Corrected multi-account cron routing to honor explicit `delivery.accountId` and fallback to sending agent's bound channel account instead of global default
- •Fixed agent media access by threading `agentId` through gateway RPC and preferring explicit agent ID over session/default resolution
- •Improved model fallback chains to remain reachable with allowlists, handle cooldown/rate-limit errors correctly, and continue traversal on unrecognized errors
Found this useful? Add it to a playbook for a step-by-step implementation guide.
Workflow Diagram
Start Process
Step A
Step B
Step C
Complete