PR for #451 - fix: delay final output until tools complete

[seratch]

This pull request aligns with openai/openai-agents-python#1689.

Additional changes

• ensure final outputs emitted in the same turn are delivered once synchronous tool execution finishes so structured agents do not loop forever.

---

https://chatgpt.com/codex/tasks/task_i_68bfd32ff4648320a47edf1493101691

[changeset-bot]

⚠️ No Changeset found

Latest commit: 0bb13c1

Merging this PR will not cause a version bump for any packages. If these changes should not result in a new version, you're good to go. If these changes should result in a version bump, you need to add a changeset.

This PR includes no changesets

When changesets are added to this PR, you'll see the packages that this PR includes changesets for and the associated semver types

Click here to learn what changesets are, and how to add one.

Click here if you're a maintainer who wants to add a changeset to this PR

[seratch]

@codex Check the test failures and resolve it

[chatgpt-codex-connector]

Summary

• No code changes were committed because I could not stabilize the test environment.

View task →

[seratch]

@codex Check the test failures and resolve it

[chatgpt-codex-connector]

Summary

• Updated the executeToolsAndSideEffects text-agent coverage so synchronous tool runs that also emit a final message now assert next_step_final_output and verify the returned text. packages/agents-core/test/runImplementation.test.tsL872-L907
• Adjusted the structured-agent test to expect a final output once tool execution completes in the same turn, including checks for the JSON payload that is returned. packages/agents-core/test/runImplementation.test.tsL910-L957

Testing

• ✅ pnpm build
• ✅ CI=1 pnpm test

View task →