fix: normalize paths in editor cache to prevent stale content#491
Open
xlyoung wants to merge 1 commit into
Open
fix: normalize paths in editor cache to prevent stale content#491xlyoung wants to merge 1 commit into
xlyoung wants to merge 1 commit into
Conversation
The editor tool's content cache used raw path parameters as keys. When the same file was accessed via different path formats (relative vs absolute), separate cache entries were created, causing stale content to be returned after modifications. Fix: normalize paths with os.path.abspath() after expanduser() to ensure consistent cache keys regardless of how the path is specified. This prevents agents from retrying edits unnecessarily due to seeing stale content after modifications, saving LLM tokens. Fixes strands-agents#345
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Problem
The editor tool's content cache used raw path parameters as cache keys. When the same file was accessed via different path formats (relative vs absolute), separate cache entries were created:
This caused agents to retry edits unnecessarily, wasting LLM tokens.
Fix
Normalize paths with
os.path.abspath()afterexpanduser()to ensure consistent cache keys:Testing
All 32 editor tests pass.
Fixes #345