fix: extract text from tool_result content blocks in search#1
Merged
fix: extract text from tool_result content blocks in search#1
Conversation
ExtractTextFromContent only checked block["text"], but tool_result blocks store their payload in block["content"]. This made tool outputs, AskUserQuestion answers, and sub-agent responses completely unsearchable. Replace the flat extraction with a recursive design that follows both "text" and "content" fields on any block, bounded by a max recursion depth. Non-text types (thinking, image, tool_use, redacted_thinking, document) are skipped via an explicit set. Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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
ExtractTextFromContentonly checkedblock["text"], buttool_resultblocks store their payload inblock["content"]— making tool outputs, AskUserQuestion answers, and sub-agent responses completely unsearchabletextandcontentfields on any block, with an explicit skip set for non-text types (thinking,redacted_thinking,image,document,tool_use)Test plan
TestExtractTextFromContentcases still pass (string, nil, text blocks, thinking/tool_use skip)tool_resultwith string content, array content, base64 skip,redacted_thinking/documentskip, mixed content, recursion depth guardTestSearchFiles_ToolResultverifies search finds text insidetool_resultblocks and still skipstool_usecct search 'ASUS ZenBook'now finds the previously invisible nix-config session🤖 Generated with Claude Code