[Release] openai/openai-agents-python v0.17.5: v0.17.5

OpenAI Agents Python v0.17.5 release includes bug fixes for sandbox error retryability, tool-end hook result typing, and SpeechGroupSpanData slots optimization. The release also bumps the Modal sandbox extra to 1.4.3 and adds comprehensive documentation improvements including a MongoDB session memory example, docstring corrections, and external tracing processor updates. Test coverage enhancements were made for streaming paths and retry helpers.

Key Points

• •Exposed sandbox error retryability to allow proper handling of transient sandbox failures
• •Fixed tool-end hook results to be properly typed as objects for better type safety
• •Optimized SpeechGroupSpanData by using tuple form for __slots__ definition
• •Upgraded Modal sandbox extra dependency to version 1.4.3 for improved stability
• •Added MongoDB session example in examples/memory directory for persistent session management
• •Improved documentation with multiple docstring corrections and grammar fixes across tool.py and agent instructions
• •Added Latitude to the external tracing processors list for expanded observability options
• •Increased test coverage for run_demo_loop streaming, EOF, and empty-input edge cases
• •Enhanced _openai_retry helpers test coverage from 77% to 95% with comprehensive unit tests

Workflow Diagram

Concepts