OpenClaw released v2026.4.11, featuring ChatGPT import and enhanced video generation capabilities

BlockBeats News, April 12, OpenClaw released the latest version v2026.4.11, focusing on feature extension and stability fixes in this update.

As for core new features, the Dreaming module has added a ChatGPT conversation history import function, and added two diary sub-tabs, "Insight Import" and "Memory Palace," in the UI. Users can directly browse the imported original dialogue, the compiled Wiki page, and the full source page in the interface, further enhancing the long-term memory management experience.

In terms of video generation capabilities, this update adds asset delivery via URL only, typed providerOptions, reference audio input, adaptive aspect ratio support, and a higher image input limit. Video providers can expose richer generation modes through this, while avoiding large file memory residency.

Regarding channels and platforms, Feishu document comment conversations support richer context parsing, comment reactions, and input feedback; Microsoft Teams adds reaction actions, reaction lists, Graph pagination, and delegated OAuth sending support. In addition, the plugin manifest can now declare activation and configuration descriptors, simplifying the plugin integration process.

On the fix side, this update addresses several channel stability issues, including Codex OAuth login failure for new users due to scope rewriting, interruption of OpenAI/Groq/Mistral speech-to-text transcription due to DNS configuration issues, macOS Talk Mode requiring a second switch after microphone permission is granted, default account registration confusion in WhatsApp, Telegram topic conversation file path misalignment, and internal progress information leakage from child agents to parent sessions.