[Release] openclaw/openclaw v2026.4.11: openclaw 2026.4.11

OpenClaw v2026.4.11 introduces major enhancements to memory/dreaming features with ChatGPT import ingestion, improved media rendering in chat UIs, expanded video generation capabilities, and better integration with platforms like Feishu and Microsoft Teams. The release includes plugin manifest improvements for declarative setup flows, performance optimizations for model discovery caching, and numerous bug fixes across OAuth, transcription, timeouts, and platform-specific issues to improve stability and user experience.

Key Points

• •Memory/Dreaming now supports ChatGPT import ingestion with new 'Imported Insights' and 'Memory Palace' diary subtabs for direct UI inspection of imported chats and wiki pages
• •Control UI renders assistant media/reply/voice directives as structured chat bubbles with new `[embed ...]` rich output tag and configurable external embed URL gating
• •Video generation expanded with URL-only asset delivery, typed providerOptions, reference audio inputs, adaptive aspect-ratio support, and higher image-input caps
• •Plugin manifests can now declare activation and setup descriptors to describe auth, pairing, and configuration steps without hardcoded core special cases
• •Ollama model discovery performance improved by caching `/api/show` context-window and capability metadata to prevent repeated refetches
• •OpenAI-compatible endpoint classification now surfaced in debug logs for easier diagnosis of local and proxy routing issues
• •Fixed OpenAI Codex OAuth scope rewriting that caused `invalid_scope` errors on new sign-ins
• •Audio transcription pinned DNS disabled selectively for OpenAI-compatible multipart requests while maintaining hostname validation
• •macOS Talk Mode now continues after microphone permission grant instead of requiring second toggle
• •Agents/failover now scopes fallback classification to current attempt instead of inheriting stale session history from previous providers

Workflow Diagram

Concepts