Summary
The release carries budget and progress guidance into continuation prompts, journals failed agents, adds browser-task notifications and separates planning from execution permissions. It also adds token-based remote starts with QR pairing, same-origin shell access and improved content filtering.
Why it matters
It moves a coding CLI towards recoverable, inspectable agent orchestration while tightening operational safeguards.
Related coverage
- OpenAI Agents Python 0.22.2 adds image-tool support and closes a sandbox race
- Gemini CLI preview strengthens MCP OAuth, sandboxing and path boundaries
- LiteLLM adds streaming guardrail pipelines and stronger agent gateway controls