[Release] google/adk-python v1.32.0: v1.32.0

Google ADK Python v1.32.0 introduces significant enhancements to agent development capabilities, including native OpenTelemetry metrics, Anthropic thinking blocks support, improved authentication mechanisms (2LO/3LO via GcpAuthProvider), and express mode deployment. The release addresses critical security vulnerabilities (RCE via YAML, SSRF), fixes parallel tool execution issues, and improves analytics with BigQuery LLM cache metadata logging and credential isolation to prevent race conditions.

Key Points

• •Add native OpenTelemetry agentic metrics and tracing for event compaction to improve observability
• •Support Anthropic's thinking blocks and graceful MCP tool execution error handling
• •Implement express mode onboarding for adk deploy CLI to streamline agent deployment
• •Add GcpAuthProvider sample agent demonstrating 2LO, 3LO, and API Key authentication methods
• •Block RCE vulnerability via nested YAML configurations and SSRF in load_web_page function
• •Isolate resolved credentials in context to prevent race conditions and data leakage in auth flows
• •Add BigQuery analytics support for LLM cache metadata logging and credentials parameter
• •Fix parallel tool call state_delta merging to properly accumulate list values
• •Support credential_key definition for McpToolset and refusal messages in ApigeeLlm
• •Add circular reference detection to schema resolution to prevent RecursionError

Workflow Diagram

Concepts