[Release] openai/openai-agents-python v0.9.2: v0.9.2

OpenAI Agents Python v0.9.2 introduces a new `reasoning_item_id_policy: 'omit'` option for RunConfig to prevent 400 errors when using reasoning models with inconsistent item sets. The release includes fixes for reasoning item filtering in nested handoffs and voice trace handling, plus documentation updates.

Key Points

• •Introduce `reasoning_item_id_policy: 'omit'` option in RunConfig to prevent 400 errors when using reasoning models with inconsistent item sets
• •The new reasoning_item_id_policy is opt-in; default behavior remains unchanged to maintain backward compatibility
• •Reasoning item ID policy now persists across agent resumes and streamed follow-up turns for consistent behavior
• •Filter reasoning items from nested handoff input to prevent conflicts during agent-to-agent transfers
• •Keep voice trace active until pipeline processing completes to ensure proper logging and debugging of voice interactions
• •Use RunConfig with reasoning_item_id_policy when calling Runner.run() for agents that use reasoning models
• •Update configuration documentation to reflect new reasoning_item_id_policy option and usage patterns

Workflow Diagram

Concepts

Artifacts (1)

run_config = RunConfig(reasoning_item_id_policy="omit")
result = await Runner.run(
    agent,
    "Tell me about recursion in programming.",
    run_config=run_config,
)