By devasher · Edited by Nominiclaw
This beta release focuses on stabilizing agent and Codex runtimes, enhancing channel security for Microsoft Teams and WhatsApp, and introducing support for Claude Opus 4.8 and Fal Krea image models.
OpenClaw v2026.5.28-beta.3 introduces a comprehensive set of stability and security enhancements designed to make agent runtimes more resilient and channel integrations more robust. The core of this release focuses on "steadying" the recovery of Agent and Codex runtimes, ensuring that sub-agents maintain strict workspace separation and that session locks are released reliably even during timeout aborts.
Beyond runtime stability, this version significantly expands the ecosystem of supported models and tools. From the addition of Claude Opus 4.8 and Fal Krea image schemas to the integration of the GitHub Copilot agent runtime, OpenClaw continues to broaden its capabilities for complex, delegated workflows.
Significant work has been done to prevent gateway hangs and session deadlocks. A critical fix addresses a "self-wait" bug in the Pi embedded runner where tool-call processing could deadlock on its own session event queue, potentially making the gateway unresponsive to health probes and channel replies (#86123, #87409).
Additionally, the Codex runtime has been hardened to ensure that shared app-server state is preserved even when spawned helper runs fail logically (e.g., due to authentication errors), preventing a single failed sub-task from tearing down the entire shared runtime state (#87375, #87399).
Security boundaries have been tightened across several major integrations:
@microsoft/teams.apps SDK, replacing legacy Bot Framework patterns. This migration fixes several critical bugs, including streaming cards that never closed and Adaptive Card buttons that failed silently. Furthermore, outbound requests are now guarded by a serviceUrl allowlist to prevent SSRF and credential leakage (#76262, #87160, #87334).403 Forbidden errors on delivery (#87366).OpenClaw continues to grow its provider coverage:
reasoning_content was stripped from tier-suffixed models (e.g., -free), which previously caused 400 errors on follow-up API calls (#87593).openclaw skills verify, with the Control UI displaying trust verdicts and lazy-loading skill cards directly from ClawHub (#86699).MEMORY.md) through tools rather than pasting it raw into the prompt, saving significant token budget for tool-enabled turns (#87383)..env files. Operators who relied on project-local .env files for provider keys must move these to the shell environment or the trusted global OpenClaw runtime .env (#83655).voice, voiceName, and voiceId configuration keys are migrated to speakerVoice and speakerVoiceId (#87794).openclaw.compat.pluginApi metadata. Plugins requiring a newer API version than the current host will be rejected at install time with a clear error message (#87477).