Releasesby GlyphOpenAI Agents SDK 0.21.1
- feat(core): add model call timeouts feat(sandbox): add run-scoped sandbox working directories feat(sandbox): allow Docker sandboxes to disable networking feat(sandbox): add Modal sandbox resource options fix(core): honor exact call approval decisions fix(core): count Responses requests without usage fix(core): close all MultiProvider children after...
Also shipped Aug 16, 2026OpenAI in August 2026 →
Feature policy rules (General availability)
With this release, we are pleased to announce the general availability of feature policy rules. A feature policy can carry a YAML body that conditionally blocks object creation based on attributes of the request. For example, you can permit tables in general but block temporary tables, or permit tasks but block serverless (no-warehouse) tasks.
Govern Replit at scale
Replit has released a new Admin API, Audit Logs, and Workspace Settings to support enterprise AI adoption. The update includes comprehensive audit logs covering over 50 events with native streaming to SIEM systems.
2026.02
We're excited to announce major updates to the Gradium API and Gradium Studio, delivering enhanced text-to-speech (TTS) and speech-to-text (STT) capabilities for developers and enterprises.
More from OpenAI Agents SDKEvery OpenAI Agents SDK release →
OpenAI Agents SDK 0.21.0
Key Changes This minor release does not introduce a known breaking SDK behavior change. The minor version bump is for the new provider-neutral testing APIs and the OpenAI Python v3 compatibility update.
OpenAI Agents SDK 0.22.0
Key Changes Version 0.22.0 is a minor release because it adds substantial runtime hardening and tightens an existing provider configuration contract. Applications that combine an explicit openai_client with organization or project must move those values to the AsyncOpenAI client.
OpenAI Agents SDK 0.20.0
Key Changes Version 0.20.0 is a minor release because it changes the implicit default model and includes a potentially breaking MCP dependency migration for applications with customized local HTTP transports. MCP v1 remains supported, and affected applications can migrate to httpx2 or pin mcp<2 .
OpenAI Agents SDK 0.19.4
- fix: preserve completed tool guardrail results fix: redact invalid tool argument errors fix: defer non-stream session saves until output guardrails fix: honor resolved status before policy checks fix: cancel sibling work after concurrent failures fix: surface non-streaming content-filter refusals fix(mcp): derive streamable HTTP retry backoff from...
OpenAI Agents SDK 0.19.3
- fix: resolve agent tool name collisions consistently fix: reconcile resumed tool name collisions fix: persist the max-turns handler output to the session fix: report output guardrail results when a tripwire aborts the run fix: replace closed default loop in run_sync fix: honor falsey custom output extractors for agents as tools fix: report tool guardrail...
OpenAI Agents SDK 0.19.2
- feat: expose original callable through wrapped fix: report input guardrail results when a tripwire aborts the run fix: consolidate same-exception re-raises into bare raise across all modules fix(sandbox): preserve tagged EnvValue subclasses fix(modal): reject ephemeral paths during tar hydration fix(mcp): redact MCP prompt and resource transport errors...
OpenAI Agents SDK 0.22.1
- feat(core): support image results in web search tools feat(core): customize output guardrail blocked messages feat(mcp): add server-wide guardrails to MCP tools feat(sandbox): add configurable Unix-local environment isolation feat(sandbox): allow labels on Docker sandbox containers feat(voice): expose streamed transcription options fix(core): detach...
OpenAI Agents SDK 0.22.2
- feat: support current image generation tool options fix(sandbox): prevent UnixLocal file API symlink races fix(sessions): reset compaction response chain after pop Documentation & Other Changes docs: document v0.22.1 behavior updates release: 0.22.2 v0.22.1...v0.22.2