fix: format AskUserQuestion tool_result content as natural-language s…#55
Merged
Merged
Conversation
…tring
Match Claude Code CLI's actual tool_result format. The content fed back
to the model should be a human-readable string ("User has answered your
questions: ...") rather than JSON. Structured questions/answers belong in
the transcript's toolUseResult metadata, not the message content.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
hilr
approved these changes
Jun 17, 2026
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
The
AskUserQuestionresume path was sendingtool_result.contentas a JSON string ({"questions": [...], "answers": {...}}). Comparing against a real Claude Code CLI transcript shows the content fed back to the model should be a human-readable string instead:The structured questions/answers live in the transcript's top-level
toolUseResultmetadata (written by the CLI), not in the message content.Changes
_format_answers_for_tool_result()to render answers in the CLI's natural-language format (multiSelect arrays joined with,).run()resume path to use it; fallback now wraps the raw user reply in the same sentence format instead of emitting JSON.Test Plan
uv run pytest tests/test_agents.py(63 passed)