This release adds 2 notable features for engineering teams evaluating rollout.
✓ No known CVEs patched in this version
Topics
Summary
AI summaryUpdates Documentation & Other Changes, fix, and realtime across a mixed release.
Changes in this release
| Type | Severity | Summary | CVE |
|---|---|---|---|
| Feature | Medium |
Adds GPT-5.6 model defaults and migrates examples. Adds GPT-5.6 model defaults and migrates examples. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Performance | Medium |
Accumulates streamed logprobs in place to avoid O(n^2) copies. Accumulates streamed logprobs in place to avoid O(n^2) copies. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Fixes cache-write usage across OpenAI Python versions. Fixes cache-write usage across OpenAI Python versions. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Makes session cleanup deterministic in realtime mode. Makes session cleanup deterministic in realtime mode. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Preserves nested tool state during restoration. Preserves nested tool state during restoration. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Closes Chat Completions streams on early exit. Closes Chat Completions streams on early exit. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Handles list content in AdvancedSQLiteSession browsing helpers. Handles list content in AdvancedSQLiteSession browsing helpers. Source: llm_adapter@2026-07-16 Confidence: high |
— |
| Bugfix | Medium |
Sends logprobs=True when top_logprobs is set on Chat Completions. Sends logprobs=True when top_logprobs is set on Chat Completions. Source: llm_adapter@2026-07-16 Confidence: high |
— |
Full changelog
What's Changed
- feat: add GPT-5.6 model defaults and migrate examples by @seratch in https://github.com/openai/openai-agents-python/pull/3774
- fix: support cache-write usage across OpenAI Python versions by @seratch in https://github.com/openai/openai-agents-python/pull/3773
- fix(realtime): make session cleanup deterministic by @seratch in https://github.com/openai/openai-agents-python/pull/3767
- fix: preserve nested tool state during restoration by @seratch in https://github.com/openai/openai-agents-python/pull/3753
- fix: close Chat Completions streams on early exit by @fallintoplace in https://github.com/openai/openai-agents-python/pull/3689
- fix(sessions): handle list content in AdvancedSQLiteSession browsing helpers by @anxkhn in https://github.com/openai/openai-agents-python/pull/3761
- fix(models): accumulate streamed logprobs in place to avoid O(n^2) copies by @anxkhn in https://github.com/openai/openai-agents-python/pull/3762
- fix: send logprobs=True when top_logprobs is set on Chat Completions by @winklemad in https://github.com/openai/openai-agents-python/pull/3763
Documentation & Other Changes
- docs: updates for v0.18.0 by @seratch in https://github.com/openai/openai-agents-python/pull/3741
- docs(realtime): fix RealtimeRunner context docstring by @anxkhn in https://github.com/openai/openai-agents-python/pull/3748
- docs: clarify agent tool state options by @william-xue in https://github.com/openai/openai-agents-python/pull/3754
- test(items): document refusal None invariant by @seratch in https://github.com/openai/openai-agents-python/pull/3751
- Release 0.18.1 by @github-actions[bot] in https://github.com/openai/openai-agents-python/pull/3775
New Contributors
- @william-xue made their first contribution in https://github.com/openai/openai-agents-python/pull/3754
- @winklemad made their first contribution in https://github.com/openai/openai-agents-python/pull/3763
Full Changelog: https://github.com/openai/openai-agents-python/compare/v0.18.0...v0.18.1
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
About openai-agents-python
A lightweight, powerful framework for multi-agent workflows
Related context
Related tools
Beta — feedback welcome: [email protected]