Skip to content

openai-agents-python

v0.17.3 Bugfix

This release fixes issues for SREs watching stability and regressions.

✓ 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

Affected surfaces

auth rce_ssrf

Summary

AI summary

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

Changes in this release

Bugfix Medium

keep mountpoint credentials out of sandbox commands

keep mountpoint credentials out of sandbox commands

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

unify memory optional dependency import errors

unify memory optional dependency import errors

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

guard None text in text_message_output and add output guardrail count to RunErrorDetails

guard None text in text_message_output and add output guardrail count to RunErrorDetails

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

avoid mutating FunctionTool params_json_schema

avoid mutating FunctionTool params_json_schema

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

avoid mutating codex output schema input

avoid mutating codex output schema input

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

output schema names for Literal types

output schema names for Literal types

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

skip wait_for_status when Vercel sandbox is in a terminal state

skip wait_for_status when Vercel sandbox is in a terminal state

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

filter hosted_tool_call types in remove_all_tools handoff filter

filter hosted_tool_call types in remove_all_tools handoff filter

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

guard None text in ItemHelpers.extract_last_content

guard None text in ItemHelpers.extract_last_content

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

log exception when output guardrail raises instead of silently ignoring

log exception when output guardrail raises instead of silently ignoring

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

reject relative sandbox workspace roots

reject relative sandbox workspace roots

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

normalize leading question marks in exposed port queries

normalize leading question marks in exposed port queries

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

honor short custom voice splitter chunks

honor short custom voice splitter chunks

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: high

Bugfix Medium

runtime handling updates

runtime handling updates

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Bugfix Medium

update runtime handling logic

update runtime handling logic

Source: granite4.1:30b@2026-05-19-audit

Confidence: low

Other Medium

Release 0.17.3

Release 0.17.3

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

add SDK review guidance

add SDK review guidance

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

mark Agent.instructions as optional

mark Agent.instructions as optional

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

translate all pages using new settings

translate all pages using new settings

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

document auto_previous_response_id

document auto_previous_response_id

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

fix LiteLLM API reference redirect

fix LiteLLM API reference redirect

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

fix duplicated word in usaspending glossary example

fix duplicated word in usaspending glossary example

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

clean up CI jobs and update uv pin

clean up CI jobs and update uv pin

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Medium

harden release tag workflow

harden release tag workflow

Source: granite4.1:8b-q6_K@2026-05-19

Confidence: low

Other Low

publish version 0.17.3 release

publish version 0.17.3 release

Source: granite4.1:30b@2026-05-19-audit

Confidence: low

Full changelog

a## What's Changed

  • fix: keep mountpoint credentials out of sandbox commands by @seratch in https://github.com/openai/openai-agents-python/pull/3429
  • fix: unify memory optional dependency import errors by @seratch in https://github.com/openai/openai-agents-python/pull/3389
  • fix: guard None text in text_message_output and add output guardrail count to RunErrorDetails by @zhoufengen in https://github.com/openai/openai-agents-python/pull/3375
  • fix: avoid mutating FunctionTool params_json_schema by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3382
  • fix: avoid mutating codex output schema input by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3385
  • fix: #3357 output schema names for Literal types by @Aphroq in https://github.com/openai/openai-agents-python/pull/3358
  • fix: skip wait_for_status when Vercel sandbox is in a terminal state by @cty-ut in https://github.com/openai/openai-agents-python/pull/3410
  • fix: filter hosted_tool_call types in remove_all_tools handoff filter by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3386
  • fix: guard None text in ItemHelpers.extract_last_content by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3394
  • fix: log exception when output guardrail raises instead of silently ignoring by @cty-ut in https://github.com/openai/openai-agents-python/pull/3411
  • fix: reject relative sandbox workspace roots by @matthewflint in https://github.com/openai/openai-agents-python/pull/3422
  • fix: normalize leading question marks in exposed port queries by @matthewflint in https://github.com/openai/openai-agents-python/pull/3424
  • fix: #3363 honor short custom voice splitter chunks by @Aphroq in https://github.com/openai/openai-agents-python/pull/3364
  • fix: runtime handling updates by @adrianbravo-oai @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3451

Documentation & Other Changes

  • docs: add SDK review guidance by @seratch in https://github.com/openai/openai-agents-python/pull/3376
  • docs: mark Agent.instructions as optional by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3384
  • docs: translate all pages using new settings by @seratch in https://github.com/openai/openai-agents-python/pull/3392
  • docs: document auto_previous_response_id by @ioleksiuk in https://github.com/openai/openai-agents-python/pull/3383
  • docs: fix LiteLLM API reference redirect by @ynachiket in https://github.com/openai/openai-agents-python/pull/3444
  • docs: fix duplicated word in usaspending glossary example by @LeSingh1 in https://github.com/openai/openai-agents-python/pull/3445
  • chore: clean up CI jobs and update uv pin by @seratch in https://github.com/openai/openai-agents-python/pull/3400
  • ci: harden release tag workflow by @hintz-openai in https://github.com/openai/openai-agents-python/pull/3399
  • Release 0.17.3 by @github-actions[bot] in https://github.com/openai/openai-agents-python/pull/3417

New Contributors

  • @zhoufengen made their first contribution in https://github.com/openai/openai-agents-python/pull/3375
  • @hintz-openai made their first contribution in https://github.com/openai/openai-agents-python/pull/3399
  • @cty-ut made their first contribution in https://github.com/openai/openai-agents-python/pull/3410
  • @ynachiket made their first contribution in https://github.com/openai/openai-agents-python/pull/3444
  • @LeSingh1 made their first contribution in https://github.com/openai/openai-agents-python/pull/3445
  • @adrianbravo-oai made their first contribution in https://github.com/openai/openai-agents-python/pull/3451

Full Changelog: https://github.com/openai/openai-agents-python/compare/v0.17.2...v0.17.3

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

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 →

Beta — feedback welcome: [email protected]