releaseintermediate
[Release] openclaw/openclaw v2026.4.15-beta.2: openclaw 2026.4.15-beta.2
By steipetegithub
View original on githubOpenClaw v2026.4.15-beta.2 introduces Anthropic model updates with Claude Opus 4.7 as the default and new Gemini text-to-speech support in the Google plugin. The release includes improvements to gateway tool handling with enhanced security for local media tool-result passthrough and stricter validation of client tool definitions. Key enhancements focus on model defaults, TTS capabilities, and tool registration robustness.
Key Points
- •Anthropic models now default to Claude Opus 4.7 with opus aliases and CLI defaults configured
- •Claude Opus 4.7 includes bundled image understanding capabilities
- •Google plugin extended with Gemini text-to-speech (TTS) support
- •TTS provider registration and voice selection implemented for Google plugin
- •WAV reply output and PCM telephony output formats supported for TTS
- •Gateway tools security improved: trusted local MEDIA tool-result passthrough anchored to exact registered tool names
- •Client tool definitions now validated against normalized names to prevent injection attacks
- •Setup and documentation guidance provided for new TTS features
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