Fail AI agent step on deterministic Claude Code failures#2027
Merged
Conversation
Per ADR-004, fail the step on any of: a non-zero CLI exit, a non-success terminal status (is_error or subtype != success), or a populated permission_denials list. The processor now captures the final result event and a pure ClaudeAgentOutcomeEvaluator decides the outcome in the runner.
Contributor
|
Looks like I get a failure which is a good sign |
zentron
approved these changes
Jun 18, 2026
It is stateless with a single method, so an instance adds no value. Addresses PR review feedback.
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
2 participants
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Per ADR-004, fail the step on any of: a non-zero CLI exit, a non-success terminal status (is_error or subtype != success), or a populated permission_denials list.
The processor now captures the final result event and a pure ClaudeAgentOutcomeEvaluator decides the outcome in the runner.
As part of testing this I discovered that in built tools appear to be allowed even if not called out in the allowed tools list but tackling that separately.
Resolves MD-2077