OpenClaw Releases v2026.4.11, Adds ChatGPT Import and Video Generation Capability Expansion

According to Golden Finance, on April 12, OpenClaw released its latest version, v2026.4.11, focusing on feature extensions and stability fixes. In terms of core new features, the Dreaming module now supports importing ChatGPT conversation history. Two new diary sub-tabs, 'Import Insights' and 'Memory Palace,' have been added to the UI, allowing users to directly browse imported raw conversations, compiled Wiki pages, and complete source pages within the interface, further enhancing the long-term memory management experience. For video generation capabilities, this update introduces a URL-only asset delivery method, typed providerOptions, reference audio input, adaptive aspect ratio support, and a higher image input limit. Video providers can now expose richer generation modes while avoiding large files lingering in memory. Regarding channels and platforms, Feishu document comment conversations now support richer context parsing, comment reactions, and input feedback. Microsoft Teams has added reaction actions, reaction lists, Graph pagination, and delegated OAuth sending support. Additionally, the plugin manifest can now declare activation and configuration descriptors, simplifying the plugin integration process. On the fixes side, this update resolves several stability issues, including new user login failures caused by Codex OAuth scope overwrites, interruptions in OpenAI/Groq/Mistral voice transcription due to DNS configuration anomalies, the need to toggle the microphone permission twice in macOS Talk Mode after granting access, as well as issues like WhatsApp default account registration confusion, Telegram topic conversation file path misalignment, and sub-agent internal progress information leaking into parent sessions.