Commit graph

5 commits

Author SHA1 Message Date
Steve G
9806e21871
Add Lakera v2 post-call hook and tests (fixed PII masking) (#21783)
* Add post-call hook for Lakera guardrail and mask PII in responses

* Add post-call hook for Lakera and mask PII in responses

* Fix post-call hook: pass event_type to call_v2_guard

* Address Greptile review: return ModelResponse, fix mutation, add header, test location, mask order

- PII masking path: return ModelResponse instead of dict so deployment hook accepts it
- Avoid mutating request data: deep copy original_messages and messages in _mask_pii_in_messages
- Add guardrail header in PII-only return path
- Add test in tests/test_litellm/ (test_lakera_ai_v2.py) per PR checklist
- Sort PII payload spans by (start,end) descending so multiple spans in one message mask correctly

Co-authored-by: Cursor <cursoragent@cursor.com>

* Updated ponteital for index mismatch when choices have null content and inconsistent on_flagged access pattern

* Update litellm/proxy/guardrails/guardrail_hooks/lakera_ai_v2.py

Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>

* Update to explicitly state supported endpoints - chat completions

* Fix minor lint error on masked_entity_count

---------

Co-authored-by: Steve <steve.giguere@lakera.ai>
Co-authored-by: Cursor <cursoragent@cursor.com>
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
2026-02-25 17:20:38 -08:00
Alexsander Hamir
69bd4426e8
[Release Day] - Fixed CI/CD issues & changed processes (#19902) 2026-01-28 17:57:24 -08:00
Steve G
c94f61b1da
Feature/lakera monitor mode (#18084)
* Add monitor mode support to Lakera guardrail

- 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.

* Add tests for Lakera guardrail monitor mode

- 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.

---------

Co-authored-by: Steve <steve.giguere@lakera.ai>
2025-12-18 19:57:43 +05:30
Ishaan Jaff
c69bac991b
[Fix] LakeraAI v2 Guardrail - Ensure exception is raised correctly (#14867)
* fix exception lakera

* test lakera ai v2

* ruff fix
2025-09-24 10:55:56 -07:00
Ishaan Jaff
bd1e0634bf
[Feat] Add Lakera v2 Guardrail Support (#10880)
* feat: add types for lakera v2

* feat: add call v2 guard for lakera

* feat: add call v2 guard for lakera

* feat: add LAKERA_V2

* feat: add LAKERA_V2 params

* feat: add initialize_lakera_v2

* fix: lakera pii masking

* test: lakera pii masking

* fix: lakera pii masking with tracing

* fix: lakera pii masking with tracing

* fix: fix linting errors

* fix: lakera ai docs
2025-05-16 17:08:21 -07:00