chore(warden): Reduce review cost and use Luna auxiliary calls - #209
Merged
Conversation
Cut org-wide Warden spend by dropping default effort from max to high and ignoring docs, tests, fixtures, and snapshot paths that security review still paid to analyze. Co-Authored-By: David Cramer <david@sentry.io>
Use OpenAI gpt-5.6-luna via OpenRouter for auxiliary structured calls instead of kimi-k2.6. Co-Authored-By: David Cramer <david@sentry.io>
sentry-junior
Bot
changed the title
dcramer
marked this pull request as ready for review
August 12, 2026 22:01
dcramer
approved these changes
Aug 12, 2026
Use the supported agent effort block and set Luna auxiliary calls to high reasoning once auxiliary effort support lands in Warden. Co-Authored-By: David Cramer <david@sentry.io>
sentry-junior
Bot
changed the title
![cursor[bot]](https://avatars.githubusercontent.com/in/1210556?s=60&v=4){kind=small}
There was a problem hiding this comment.
Cursor Bugbot has reviewed your changes and found 1 potential issue.
❌ Bugbot Autofix is OFF. To automatically fix reported issues with cloud agents, enable autofix in the Cursor dashboard.
Reviewed by Cursor Bugbot for commit ee2e1ad. Configure here.
| [defaults.auxiliary] | ||
| model = "openrouter/moonshotai/kimi-k2.6" | ||
| model = "openrouter/openai/gpt-5.6-luna" | ||
| effort = "high" |
There was a problem hiding this comment.
Unsupported auxiliary effort setting
Medium Severity
effort under [defaults.auxiliary] is not a supported field for that lane. Warden documents effort only on [defaults.agent]; auxiliary accepts model and maxRetries. This key will not control Luna’s reasoning effort as intended, and may fail strict config validation on the org-wide base config.
Reviewed by Cursor Bugbot for commit ee2e1ad. Configure here.
Member
|
blocked on getsentry/warden#469 |
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.
Cut org-wide Warden spend after we burned through the daily budget.
Changes
highunder[defaults.agent]ignorePathsfor docs, tests, fixtures, snapshots, and similar low-signal filesopenrouter/openai/gpt-5.6-lunahighTelemetry showed
security-reviewspending heavily on low-signal paths. The skill prompt treats many of these files as out of scope, but Warden still pays to analyze them without path filters.[defaults.auxiliary].effortdepends on getsentry/warden#469 and must land in a Warden release before this PR can merge.Requested by David Cramer.
--
View Junior Session [Sentry]