Repository navigation
Make Grudges easy to try with native subscriptions - #3
Merged
Merged
Conversation
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Trying Grudges previously required Docker and several backend flags before users could test an agent mistake. This release makes native subscription replay the default:
grudges runruns one starter task once, and--agent claudechooses Claude. Verification runs locally through explicit task commands; API/Harbor remains an advanced alternative.The README now leads with turning agent mistakes into regression tests and explains the capture → reviewed test → replay workflow. Pack docs, authoring defaults, animated demo and security boundaries match that flow. All bundled tasks support native verification and have incremented patch versions; historical receipts remain labeled.
Validation: 81 tests passed on Python 3.11/3.13 (one optional test skipped), including all 28 real native controls. Both live subscription runners passed baseline/rules comparisons with marker files confirming rule delivery. Fresh-wheel, archive, secret-scan and demo checks passed. Linux only; native verification is trusted host execution, not a sandbox.