Skip to content

Conversation

@eurogig
Copy link

@eurogig eurogig commented Dec 17, 2025

Relevant issues

[Feature]: Add monitor mode support to Lakera guardrails #18015

Pre-Submission checklist

Please complete all items before asking a LiteLLM maintainer to review your PR

  • I have Added testing in the tests/litellm/ directory, Adding at least 1 test is a hard requirement - see details
  • My PR passes all unit tests on make test-unit
  • [x ] My PR's scope is as isolated as possible, it only solves 1 specific problem

CI (LiteLLM team)

CI status guideline:

  • 50-55 passing tests: main is stable with minor issues.
  • 45-49 passing tests: acceptable but needs attention
  • <= 40 passing tests: unstable; be careful with your merges and assess the risk.
  • Branch creation CI run
    Link:

  • CI run for the last commit
    Link:

  • Merge / cherry-pick CI run
    Links:

Type

🆕 New Feature

Changes

  • Add on_flagged parameter to LakeraV2GuardrailConfigModel (default: 'block')
  • Support 'monitor' mode that logs violations without blocking requests
  • Support 'block' mode (default) that raises HTTPException on violations
  • Update async_pre_call_hook and async_moderation_hook to check on_flagged
  • Update guardrail initializer to pass on_flagged from config
  • Add documentation with monitor mode examples

This allows users to tune Lakera security policies by monitoring violations without blocking legitimate requests.

- Add on_flagged parameter to LakeraV2GuardrailConfigModel (default: 'block')
- Support 'monitor' mode that logs violations without blocking requests
- Support 'block' mode (default) that raises HTTPException on violations
- Update async_pre_call_hook and async_moderation_hook to check on_flagged
- Update guardrail initializer to pass on_flagged from config
- Add documentation with monitor mode examples

This allows users to tune Lakera security policies by monitoring violations
without blocking legitimate requests, similar to Pillar's on_flagged_action.
- Test monitor mode allows flagged content through (pre_call hook)
- Test block mode raises HTTPException for violations (pre_call hook)
- Test monitor mode works with during_call (moderation_hook)

These tests verify the on_flagged parameter functionality for both
monitor and block modes across different guardrail hooks.
@vercel
Copy link

vercel bot commented Dec 17, 2025

The latest updates on your projects. Learn more about Vercel for GitHub.

Project Deployment Review Updated (UTC)
litellm Ready Ready Preview, Comment Dec 17, 2025 0:34am

@CLAassistant
Copy link

CLA assistant check
Thank you for your submission! We really appreciate it. Like many open source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution.
You have signed the CLA already but the status is still pending? Let us recheck it.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

3 participants