openai/openai-agents-python v0.22.1

v0.22.1

Repository: openai/openai-agents-python

Tag: v0.22.1

Published: 2026-09-08T09:18:00Z

Prerelease: no

Release notes:

What's Changed

• feat(core): support image results in web search tools by @seratch in https://github.com/openai/openai-agents-python/pull/4898
• feat(core): customize output guardrail blocked messages by @seratch in https://github.com/openai/openai-agents-python/pull/4594
• feat(mcp): add server-wide guardrails to MCP tools by @seratch in https://github.com/openai/openai-agents-python/pull/4632
• feat(sandbox): add configurable Unix-local environment isolation by @seratch in https://github.com/openai/openai-agents-python/pull/4640
• feat(sandbox): allow labels on Docker sandbox containers by @seanxuu in https://github.com/openai/openai-agents-python/pull/4564
• feat(voice): expose streamed transcription options by @seratch in https://github.com/openai/openai-agents-python/pull/4645
• fix(core): detach aggregated request usage entries by @green3sf in https://github.com/openai/openai-agents-python/pull/4519
• fix(core): fail closed on empty tool arguments by @hsusul in https://github.com/openai/openai-agents-python/pull/4545
• fix(core): strip created_by when replaying RunItems as input by @hsusul in https://github.com/openai/openai-agents-python/pull/4568
• fix(core): strict_schema error message, REPL whitespace input, debug docstrings by @simpleqt in https://github.com/openai/openai-agents-python/pull/4600
• fix(core): max_turns no longer clobbers a tripped input guardrail exception in streaming by @shoemoney in https://github.com/openai/openai-agents-python/pull/4606
• fix(core): preserve serialized approval resume ownership by @seratch in https://github.com/openai/openai-agents-python/pull/4613
• fix(core): read tool args without Pydantic property shadowing by @hsusul in https://github.com/openai/openai-agents-python/pull/4627
• fix(core): accept JSON Schema type arrays of object for tool outputs by @hsusul in https://github.com/openai/openai-agents-python/pull/4647
• fix(core): honor End of File hunks when the file ends in a newline by @lllakshit in https://github.com/openai/openai-agents-python/pull/4661
• fix(core): preserve tuple annotations for variadic tool arguments by @Excelius-Wang in https://github.com/openai/openai-agents-python/pull/4655
• fix(core): fix streamed response span losing response/input when consumer stops at completed event by @XuQuanxin04 in https://github.com/openai/openai-agents-python/pull/4692
• fix(core): apply **kwargs value annotation to each keyword value by @abhay-codes07 in https://github.com/openai/openai-agents-python/pull/4714
• fix(core): reject **kwargs keys that collide with named tool parameters by @rajarshidattapy in https://github.com/openai/openai-agents-python/pull/4674
• fix(core): reject fixed-length tuple annotations for variadic tool arguments by @subhashpolisetti in https://github.com/openai/openai-agents-python/pull/4735
• fix(core): preserve Field constraints on variadic tool parameters by @rioyu123 in https://github.com/openai/openai-agents-python/pull/4739
• fix(core): close model providers created by Runner by @Excelius-Wang in https://github.com/openai/openai-agents-python/pull/4785
• fix(core/voice): honor OpenAI provider options over default clients by @green3sf in https://github.com/openai/openai-agents-python/pull/4530
• fix(chat-completions): merge a streamed turn's message into its pending tool-call message by @mmjerge in https://github.com/openai/openai-agents-python/pull/4728
• fix(chat-completions): raise ModelBehaviorError on truncated empty completions by @weike-zhang in https://github.com/openai/openai-agents-python/pull/4513
• fix(chat-completions) reject unpaired function outputs in Chat Completions by @apcha-oai in https://github.com/openai/openai-agents-python/pull/4699
• fix(extensions): skip AdvancedSQLiteSession usage store when the branch has no turn by @rioyu123 in https://github.com/openai/openai-agents-python/pull/4822
• fix(extensions): nest extra_body on the any-llm chat path by @hsusul in https://github.com/openai/openai-agents-python/pull/4544
• fix(mcp): deep-copy cached tools before returning them by @hsusul in https://github.com/openai/openai-agents-python/pull/4525
• fix(mcp): clear active MCP servers after cleanup by @sylvesterkaczmarek in https://github.com/openai/openai-agents-python/pull/4586
• fix(mcp): deduplicate managed servers by @hsusul in https://github.com/openai/openai-agents-python/pull/4591
• fix(realtime): advance crossed guardrail thresholds by @hsusul in https://github.com/openai/openai-agents-python/pull/4590
• fix(realtime): preserve item status on retrieved conversation items by @shoutoutuoadi325 in https://github.com/openai/openai-agents-python/pull/4598
• fix(sandbox): finish dependency cleanup on cancellation by @hsusul in https://github.com/openai/openai-agents-python/pull/4607
• fix(sandbox): keep unbounded UnixLocal workspace I/O off the event loop by @ayaangazali in https://github.com/openai/openai-agents-python/pull/4700
• fix(sandbox): preserve UTF-8 boundaries in Cloudflare SSE by @Hughhhhcoder in https://github.com/openai/openai-agents-python/pull/4707
• fix(sandbox): clean up PTY startup cancellation by @Hughhhhcoder in https://github.com/openai/openai-agents-python/pull/4750
• fix(sandbox): settle PTY output before cleanup by @seratch in https://github.com/openai/openai-agents-python/pull/4738
• fix(sandbox): preserve workdir for shell command lists by @hsusul in https://github.com/openai/openai-agents-python/pull/4915
• fix(sessions): recover failed resumed Session writes before model calls by @seratch in https://github.com/openai/openai-agents-python/pull/4630
• fix(sessions): recover failed resumed Session writes on a renewed interruption by @ayaangazali in https://github.com/openai/openai-agents-python/pull/4650
• fix(sessions): persist resumed tool guardrail results by @FU-max-boop in https://github.com/openai/openai-agents-python/pull/4654
• fix(sessions): recover resumed handoffs after session append failures by @seratch in https://github.com/openai/openai-agents-python/pull/4725
• fix(sessions): settle conversation deletion before propagating cancellation by @Excelius-Wang in https://github.com/openai/openai-agents-python/pull/4790
• fix(sessions): preserve concurrent writes during compaction by @seratch in https://github.com/openai/openai-agents-python/pull/4736
• fix(sessions): reject resuming a run whose...