Repository navigation
feat(agents): let callers choose the report tool - #1550
Merged
Merged
Conversation
ian-at-strix
marked this pull request as ready for review
October 20, 2026 23:46
Contributor
[Medium impact] The changes since the previous review introduce no new blocking issue. SummaryLets callers choose the reporting tool for root and child agents.
Reviews (2) · Last reviewed commit: "refactor(agents): name the report tool v..." · Reviewed by Greptile |
…tring replacement
Contributor
Author
0xallam
approved these changes
Oct 21, 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
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
run_strix_scanandbuild_strix_agentnow takereport_tool(defaultcreate_vulnerability_report). Every agent, root and children, gets that tool in place ofcreate_vulnerability_report, and the rendered system prompt names it.strix-pro passes
create_pr_vulnerability_reportfor PR reviews. Until now subagents there had both tools, and their prompt told them to use the generic one. They filed confirmed bugs with it in 217 calls across 123 eval runs, and the review never counted them: about 3.7 points of catch rate. Same pattern as #1496 (root_finish_tool).