releaseintermediate
[Release] google/adk-python v1.31.0: v1.31.0
By wukathgithub
View original on githubGoogle ADK Python v1.31.0 introduces significant enhancements including Vertex AI Agent Engine Sandbox integration for computer use, Firestore support, and improved memory management with VertexAiMemoryBankService. The release adds user agent tracking to Parameter and Secret Manager clients, includes live session tracking in LlmResponse, and resolves multiple bugs related to event callbacks, BigQuery plugin issues, and authentication headers. Several refactoring improvements modernize the live session API and update MCP Toolbox documentation.
Key Points
- •Add 'google-adk' user agent to Parameter Manager and Secret Manager clients for better tracking and identification
- •Implement Vertex AI Agent Engine Sandbox integration enabling computer use capabilities for agents
- •Add Firestore support to expand database integration options for agent data persistence
- •Support memories.ingest_events in VertexAiMemoryBankService for enhanced memory management
- •Add live_session_id to LlmResponse for improved session tracking in live interactions
- •Execute on_event_callback before append_event to ensure plugin modifications persist correctly
- •Bump minimum MCP version from 1.23.0 to 1.24.0 for compatibility improvements
- •Fix console URL path generation after 'adk deploy agent_engine' command execution
- •Refactor live session API to use send_client_content and send_tool_response methods
- •Resolve BigQuery plugin issues affecting A2A transfers, spans, and metadata handling
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