fix(agents-core): prevent premature agent termination with text and function calls #57
Conversation
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
…ool calls - Continue agent loop when function results or computer results are present - Ensures agent continues processing when models return both text and tool calls - Add comment explaining the logic for future maintainers
🦋 Changeset detectedLatest commit: 2c248b9 The changes in this PR will be included in the next version bump. This PR includes changesets to release 5 packages
Not sure what this means? Click here to learn what changesets are. Click here if you're a maintainer who wants to add another changeset to this PR |
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Outdated suggestions cannot be applied.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.
Description
Agent Loop Continuation: Prevents premature agent termination when models return both text output and tool calls
Problem
Some models (Claude Sonnet 4) return both text and tool calls in their responses. Previously, if there was any potential final output (text), the agent would terminate even if there were pending function results or computer results to process. This caused the agent to stop prematurely before completing all requested tool operations.
Solution
executeToolsAndSideEffectsto continue the agent loop when there are function results or computer results present, regardless of text outputTesting
pnpm build(had to futz with some types to getbuildworking after initial fork, not sure if it was a setup issue on my side)CI=1 pnpm testpnpm lintType of Change