Artifact triage ergonomics: head+tail previews, batched contextual search - #52
Merged
Conversation
…arch Truncated active tool results now preview the head AND the tail — build/test logs put the verdict at the end, and a head-only preview sent models on long artifact_search fishing expeditions (observed: ~40 blind greps per xcodebuild failure). artifact_search now accepts a batched `queries` array (single `query` still works), searches via the artifact content directly, and returns each match with ±2 context lines and a per-query no-match report — one round trip instead of one call per keyword. Co-Authored-By: Claude Opus 4.8 (1M context) <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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Fixes the grep-storm behavior observed in Naseem runs: after a failed
xcodebuild(exit 65), the model issued ~40 blindartifact_searchcalls per build because the truncated preview showed only the head of the output (boilerplate) while the verdict lives at the tail.Changes
queriesarray (legacyquerystring still works; at least one required), returns matches with ±2 context lines, marks the matched line with>, and reports per-query misses — all in one round trip.Tests
4 new tests; full suite 262/262 green.
🤖 Generated with Claude Code