Skip to content

openai-agents-python

v0.18.2 Feature

This release adds 2 notable features for engineering teams evaluating rollout.

Published 16d AI Agents & Assistants
✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agents ai harness llm openai python

Summary

AI summary

Updates sandbox, Documentation & Other Changes, and chore across a mixed release.

Changes in this release

Feature Medium

Adds support for GPT-5.6 request controls.

Adds support for GPT-5.6 request controls.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Feature Medium

Adds hosted multi-agent beta support.

Adds hosted multi-agent beta support.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes sandbox to own Daytona PTY worker tasks.

Fixes sandbox to own Daytona PTY worker tasks.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes realtime to enqueue callback errors synchronously.

Fixes realtime to enqueue callback errors synchronously.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes realtime to use monotonic playback timing.

Fixes realtime to use monotonic playback timing.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes sandbox to own Docker deferred cleanup tasks.

Fixes sandbox to own Docker deferred cleanup tasks.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes sandbox to own Unix PTY fd close tasks.

Fixes sandbox to own Unix PTY fd close tasks.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Fixes litellm to surface content-filter refusals instead of empty turn.

Fixes litellm to surface content-filter refusals instead of empty turn.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Bugfix Medium

Serializes model‑backed rollout interruptions as dicts.

Serializes model‑backed rollout interruptions as dicts.

Source: llm_adapter@2026-07-15

Confidence: high

 —
Full changelog

What's Changed

  • feat: support GPT-5.6 request controls by @seratch in https://github.com/openai/openai-agents-python/pull/3794
  • feat: add hosted multi-agent beta support by @seratch in https://github.com/openai/openai-agents-python/pull/3788
  • fix(sandbox): own Daytona PTY worker tasks by @seratch in https://github.com/openai/openai-agents-python/pull/3778
  • fix(realtime): enqueue callback errors synchronously by @seratch in https://github.com/openai/openai-agents-python/pull/3777
  • fix(realtime): use monotonic playback timing by @seratch in https://github.com/openai/openai-agents-python/pull/3776
  • fix(sandbox): own Docker deferred cleanup tasks by @seratch in https://github.com/openai/openai-agents-python/pull/3779
  • fix(sandbox): own Unix PTY fd close tasks by @seratch in https://github.com/openai/openai-agents-python/pull/3780
  • fix(litellm): surface content-filter refusals instead of an empty turn by @seanturner83 in https://github.com/openai/openai-agents-python/pull/3769
  • refactor(sandbox): share core PTY output collection by @seratch in https://github.com/openai/openai-agents-python/pull/3796
  • refactor(sandbox): share extension PTY output collection by @seratch in https://github.com/openai/openai-agents-python/pull/3797
  • refactor(sandbox): share E2B rclone setup by @seratch in https://github.com/openai/openai-agents-python/pull/3798
  • refactor(sandbox): share Runloop rclone setup by @seratch in https://github.com/openai/openai-agents-python/pull/3799
  • refactor: share retry error metadata extraction by @seratch in https://github.com/openai/openai-agents-python/pull/3800
  • refactor: share retry-after parsing by @seratch in https://github.com/openai/openai-agents-python/pull/3801

Documentation & Other Changes

  • fix: serialize model-backed rollout interruptions as dicts by @Otis0408 in https://github.com/openai/openai-agents-python/pull/3790
  • chore: enable G004 logging lint rule by @seratch in https://github.com/openai/openai-agents-python/pull/3802
  • chore: enable RUF012 for runtime source by @seratch in https://github.com/openai/openai-agents-python/pull/3803
  • chore: remove unused noqa directives by @seratch in https://github.com/openai/openai-agents-python/pull/3804
  • chore: exempt OpenAI package from dependency cooldown by @seratch in https://github.com/openai/openai-agents-python/pull/3792
  • Release 0.18.2 by @github-actions[bot] in https://github.com/openai/openai-agents-python/pull/3805

New Contributors

  • @Otis0408 made their first contribution in https://github.com/openai/openai-agents-python/pull/3790
  • @seanturner83 made their first contribution in https://github.com/openai/openai-agents-python/pull/3769

Full Changelog: https://github.com/openai/openai-agents-python/compare/v0.18.1...v0.18.2

View diff on GitHub

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Share on X Share on Bluesky

Track openai-agents-python

Get notified when new releases ship.

Sign up free

About openai-agents-python

A lightweight, powerful framework for multi-agent workflows

All releases →

Related context

Beta — feedback welcome: [email protected]