Skip to content

Conversation

@vria
Copy link

@vria vria commented Jul 16, 2025

Description

Using LiteLLM, I have access to a variety of models. When I run agent.structured_output, some models like gemini-2.5-flash, gpt-4o return a perfectly formatted output that satisfies output_model but with a finish_reason different from tool_calls.

In my opinion, checking the finish_reason isn’t useful when we're only interested in the content itself.

Type of Change

Bug fix

Testing

How have you tested the change? Verify that the changes do not break functionality or introduce warnings in consuming repositories: agents-docs, agents-tools, agents-cli

  • I ran hatch run prepare

Checklist

  • I have read the CONTRIBUTING document
  • I have added any necessary tests that prove my fix is effective or my feature works
  • I have updated the documentation accordingly
  • I have added an appropriate example to the documentation to outline the feature, or no new docs are needed
  • My changes generate no new warnings
  • Any dependent changes have been merged and published

By submitting this pull request, I confirm that you can use, modify, copy, and redistribute this contribution, under the terms of your choice.

@dbschmigelski
Copy link
Member

Hi closing this out as #1021 should address it. But we also released a new mechanism for structured_output which we believe will be much more robust https://strandsagents.com/latest/documentation/docs/user-guide/concepts/agents/structured-output/#basic-usage

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants