releaseintermediate
[Release] openai/openai-agents-python v0.9.1: v0.9.1
By seratchgithub
View original on githubOpenAI Agents Python v0.9.1 release includes critical bug fixes for input history materialization, tracing function spans, import-time fork hazards, and nested agent-tool state persistence. The release also bumps the RunState schema to 1.1 with explicit backward-read policy and includes comprehensive documentation updates.
Key Points
- •Fixed materialization of iterable input history in ItemHelpers to prevent lazy evaluation issues
- •Added tracing function spans for shell, apply_patch, and computer runtime tools for better observability
- •Resolved import-time fork hazards by implementing lazy initialization of tracing globals
- •Fixed persistence of nested agent-tool HITL (Human-In-The-Loop) state across RunState JSON serialization/deserialization
- •Isolated nested agent-tool resume cache by RunState scope to prevent cross-contamination
- •Bumped RunState schema to version 1.1 with explicit backward-read policy for compatibility
- •Updated documentation for 0.9.0 release and synchronized tool documentation with coverage for internal helper branches
- •Maintained multi-language documentation through automated translation updates
Found this useful? Add it to a playbook for a step-by-step implementation guide.