Ensure MCP loops output the right response format#89
Merged
Conversation
In a tool loop, you can't set response_format because the model needs to be able to think in plain English. But you still need the final response to be in the desired format, so we add response_format only on the last iteration.
Contributor
There was a problem hiding this comment.
Pull Request Overview
This PR ensures that MCP loops output responses in the correct format by applying response_format only on the final iteration. The change prevents conflicts between tool calls and structured output formatting.
- Moves
response_formatapplication from first iteration to final iteration only - Adds logic to trigger an additional loop iteration when no tool calls are made but response formatting is required
- Ensures tools are excluded when response formatting is applied to avoid API conflicts
Reviewed Changes
Copilot reviewed 2 out of 4 changed files in this pull request and generated 2 comments.
| File | Description |
|---|---|
| src/inference.ts | Implements conditional response format application and final message loop logic |
| tests/inference.test.ts | Adds comprehensive test coverage for response format behavior in MCP loops |
Yuzuki-S
approved these changes
Aug 6, 2025
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
In a tool loop, you can't set response_format because the model needs to be able to think in plain English. But you still need the final response to be in the desired format, so we add response_format only on the last iteration.