New Schemas: Environment variable models (ConvAIEnvironmentVariable, ConvAIEnvVarLocator, EnvironmentAuthConnectionLocator), guardrail trigger actions (EndCallTriggerAction, RetryTriggerAction), conditional expressions (ConditionalOperator), auth connection management schemas, and speech-to-text evaluation schemas.
Modified Schemas: MCPServerConfig now supports environment variable references, CustomGuardrailConfig added trigger_action field, Contributor added optional bio and profile_id fields, ASTLLMNode added value_schema (with prompt deprecated), and TelephonyDirection refactored as a shared enum.
ElevenAgents: Users page now generally available with unified conversation history view. Custom SIP X-headers automatically exposed as dynamic variables (e.g., {{sip_contact_id}}). Conversation filtering by tool outcome via tool_names_successful and tool_names_errored query parameters. User listing now supports sort_by (by contact time or conversation count) and branch_id filters. Force delete tools with automatic removal from dependent agents. Conversation embedding retention control via conversation_embedding_retention_days field. New ContentThresholdGuardrail schema.
Workspaces: New endpoint to get all workspace groups with member and permission details. Bulk invite endpoint now supports optional seat_type field. Fixed mobile SSO regressions with stuck authentication and workspace switching.
Music: Generate music detailed endpoint now supports respect_sections_durations to control adherence to per-section durations.
ElevenCreative Studio: Chapters now include has_visual_content boolean field. Text styling now supports text_shadow and text_outline via new schemas. Clip task type enum expanded with media_generation value.
SDK Releases: Python v2.39.0/2.39.1 with WebSocket multimodal event support and schema updates. JavaScript v2.39.0 with schema updates. iOS v3.1.0 with improved error handling, event-based state management, software muting, Swift Concurrency, crash fixes, and rebranding. Client packages updated with audio resampling support.
Fetched April 9, 2026