releaseadvanced
[Release] openclaw/openclaw v2026.5.10-beta.5: openclaw 2026.5.10-beta.5
By github-actions[bot]github
View original on githubOpenClaw v2026.5.10-beta.5 introduces significant improvements across CI/CD, runtime detection, provider integrations, and agent capabilities. Key updates include Fly Machines container detection, enhanced Fal provider image editing, stricter build tooling (oxlint, Vitest, TypeScript), pnpm 11 upgrade, and expanded agent-to-agent communication limits. The release also adds Slack thread management improvements, Discord voice diagnostics, plugin SDK deprecations, and QA automation enhancements for Telegram and Mantis.
Key Points
- •CI enhancement: Non-blocking plugin-inspector-advisory artifact added to Plugin Prerelease for compatibility triage without blocking release gates
- •Runtime detection: Fly Machines now automatically detected as container environments via runtime env vars, aligning gateway bind and Bonjour defaults
- •Fal provider: GPT Image 2 and Nano Banana 2 edit requests routed to `/edit` with `image_urls` array; edit caps increased to 10 and 14 respectively; aspect-ratio hints supported
- •Build tooling: Stricter oxlint rules (promise, TypeScript, runtime), Vitest lint rules, and TypeScript compiler checks enabled; oxfmt defaults pinned for stable formatting
- •Agent communication: `session.agentToAgent.maxPingPongTurns` increased to 20 (default 5); per-agent `tools.message.crossContext` and `tools.message.actions.allow` overrides added
- •Slack improvements: `unfurlLinks`/`unfurlMedia` config added with per-account overrides; explicit `replyBroadcast` support for thread replies; mention metadata preserved in inbound context
- •Slack DM handling: Outbound delivery-mirror routes canonicalized for native DM channel IDs to prevent thread splitting
- •Plugin SDK: Deprecated public subpaths with no production imports; removed owner-specific `provider-auth-login` and provider-specific model/stream helpers; exposed active model metadata to native plugin tools
- •Discord voice: Realtime diagnostics added for speaker turns, playback resets, barge-in detection; pure-JS `opusscript` decoder default; opt-in native `@discordjs/opus` for performance lanes; `voice.allowedChannels` config added
- •Gateway skills: Opt-in private skill archive upload path gated by `skills.install.allowUploadedArchives` for trusted clients
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