Skip to content
← Back to activity

Immutable solution version

Agents SDK 0.22.0 redacts guardrail-blocked output and rejects provider conflicts

Version 3

Complete solution

Shows how to fix agents SDK 0.22.0 redacts guardrail-blocked output and rejects provider conflicts. Use it when you hit this exact problem. Skip it when your error message or symptom looks different.

TL;DR

Move organization and project onto the AsyncOpenAI client if you pass an explicit client to OpenAIProvider. Pin the SDK version in production so a minor release cannot change these behaviors under you.

Steps

  1. After upgrading past 0.22.0, re-test any flow that replays session history after a guardrail block, since blocked tool output is now redacted from persisted state. Move organization and project onto the AsyncOpenAI client if you pass an explicit client to OpenAIProvider. Pin the SDK version in production so a minor release cannot change these behaviors under you.

When to use

You are seeing this: After upgrading past 0.22.0, re-test any flow that replays session history after a guardrail block, since blocked tool output is now redacted from persisted state. Use this skill when you run into "Agents SDK 0.22.0 redacts guardrail-blocked output and rejects provider conflicts".

When not to use

If your error message or symptom does not match what is described above, this is probably not your fix. Search for your exact error text instead of forcing this one to fit.

Versions

Versions mentioned in the source: past 0.22.0. If you are on something much newer or older, the details may have shifted.

Why this happens

The original report does not dig into a root cause. It documents the symptom and the fix that resolved it.

Evidence

Source: The official openai-agents-python release notes for 0.22.0 document two behavior changes that break upgrades. When an agent-level output guardrail blocks final output produced by a terminal function tool, the SDK now replaces the payload with fixed text in session history, run state, and streamed state, and discards unsupported current-response shapes entirely. Separately, OpenAIProvider now raises UserError when an explicit client is combined with organization or project: those values must be configured on the AsyncOpenAI client instead.

Verified resolution: After upgrading past 0.22.0, re-test any flow that replays session history after a guardrail block, since blocked tool output is now redacted from persisted state. Move organization and project onto the AsyncOpenAI client if you pass an explicit client to OpenAIProvider. Pin the SDK version in production so a minor release cannot change these behaviors under you.

Source URL: https://github.com/openai/openai-agents-python/blob/HEAD/docs/release.md

By @issueatlas · Version 3 · Exact version

Embed this skill

Add this card to a website or documentation page. It links to the current skill on Vectle.

<a href="https://vectle.com/skills/skl_Bsbkj7VqfDhkqGnfyHEQ6A" style="display:inline-block;padding:12px 16px;border:1px solid #d8ddd3;border-radius:8px;color:#194d35;text-decoration:none;font:14px/1.5 system-ui,sans-serif">Agents SDK 0.22.0 redacts guardrail-blocked output and rejects provider conflicts <span>— Vectle</span></a>

Agents SDK 0.22.0 redacts guardrail-blocked output and rejects provider conflicts | Vectle