* Add French language support for EU AI Act Article 5 template
- Create eu_ai_act_article5_fr.yaml with comprehensive French keywords
- Includes identifier words: concevoir, créer, développer, noter, classer, etc.
- Includes block words: crédit social, comportement social, émotion des employés, etc.
- Includes always-block keywords for explicit prohibited practices
- Includes exceptions for research, compliance, and legitimate use cases
- Catches circumvention attempts with phrase variations
* Add comprehensive tests for French EU AI Act guardrail
- Test 3 critical scenarios: blocked query, circumvention attempt, safe query
- Test edge cases: case-insensitive, mixed language, research exceptions
- All 7 tests passing
- Validates both blocking and allowing behavior
* Fix content filter to support conditional matching without inherit_from
- Enable conditional matching when identifier_words + additional_block_words are present
- Previously required inherit_from, but EU AI Act templates are self-contained
- Fixes Greptile feedback: conditional matching now works as documented
* Add pure conditional matching test for French guardrail
- Test identifier + block word combinations not in always_block_keywords
- Verifies conditional matching works independently
- Addresses Greptile feedback about test coverage gap
* Fix exception word bypass risk in French template
- Replace short words (film, jeu, juste) with context-specific phrases
- Prevents substring matching bypasses (e.g., enjeu matching jeu)
- Add tests for bypass prevention and legitimate game context
- Addresses Greptile security feedback
* Make conditional match assertion more robust
- Use getattr to safely access exception detail field
- Check if detail is dict before calling .get()
- Addresses Greptile feedback about brittle string assertion
* Add 6 new EU PII patterns for GDPR compliance
- fr_nir: French Social Security Number (NIR/INSEE) with validation
- eu_iban_enhanced: Enhanced IBAN detection with specific format
- fr_phone: French phone numbers (+33, 0033, 0 formats)
- eu_vat: EU VAT identification numbers (all 27 member states)
- eu_passport_generic: Generic EU passport format
- fr_postal_code: French postal codes with contextual keywords
* Add GDPR Art. 32 EU PII Protection policy template
- Comprehensive GDPR Article 32 compliance policy
- 4 guardrail groups: National IDs, Financial, Contact Info, Business IDs
- Masks French NIR/INSEE, EU IBANs, French phones, EU VAT numbers
- Includes EU passport numbers and email addresses
- Medium complexity template with indigo icon
* Add comprehensive tests for EU PII patterns
- Test French NIR validation (sex digit, month range)
- Test enhanced IBAN detection (French, German)
- Test French phone number formats
- Test EU VAT numbers
- Test generic EU passport format
- Test French postal code pattern
* Add EU pattern loading and category validation tests
- Verify all 6 EU PII patterns are loaded correctly
- Verify patterns are categorized as 'EU PII Patterns'
- Ensure pattern loading consistency
* Add end-to-end tests for GDPR policy template
- 4 tests for PII that should be masked (NIR, IBAN, phone, VAT)
- 4 tests for text that should pass through (invalid patterns, no PII)
- 1 bonus test for multiple PII types in same message
- All tests verify correct masking behavior
* Add region field to policy templates
- Added region field to all 6 templates (EU, AU, Global)
- Updated both main and backup JSON files
- Enables region-based filtering in UI
* Add region filter to policy templates UI
- Added Radio.Group filter for regions (All, AU, EU, Global)
- Efficient filtering with useMemo hooks
- Clean button-based UI matching existing design
- Defaults missing regions to Global
* feat: add EU AI Act Article 5 policy template
Add policy template for detecting EU AI Act Article 5 prohibited practices using conditional keyword matching.
Coverage:
- Article 5.1.c: Social scoring systems
- Article 5.1.f: Emotion recognition in workplace/education
- Article 5.1.h: Biometric categorization of protected characteristics
- Article 5.1.a: Harmful manipulation techniques
- Article 5.1.b: Vulnerability exploitation
Implementation:
- Uses proven conditional matching pattern (identifier + block words)
- 10 always-block keywords for explicit violations
- 8 exceptions for research/compliance/entertainment
- Zero cost (<5ms), no external APIs, 100% private
* feat: add EU AI Act guardrail config example
Example configuration showing how to enable EU AI Act Article 5 guardrail.
* test: add 40 test cases for EU AI Act Article 5
Comprehensive test coverage:
- 10 always-block keywords (explicit violations)
- 15 conditional matches (identifier + block word)
- 8 exceptions (research, compliance, entertainment)
- 7 no-match cases (legitimate uses)
Tests validate correct blocking/allowing behavior for Article 5 prohibited practices.
* Fix: support standalone conditional matching without inherit_from
- Updated loading logic to activate conditional matching when either:
1. identifier_words + inherit_from (existing pattern)
2. identifier_words + additional_block_words (new standalone pattern)
- Modified _load_conditional_category to handle standalone templates
- EU AI Act template now works properly without inherit_from
- All 45 tests passing
Fixes Greptile feedback: conditional matching now activates for templates
that define additional_block_words without requiring inherit_from
* fix: address Greptile code review feedback (2/5 score)
- patterns.json: add keyword_pattern to eu_vat and eu_passport_generic
- patterns.json: fix fr_phone pattern with leading word boundary
- patterns.json: fix eu_iban_enhanced regex efficiency
- policy_templates.json: remove country-specific passport patterns from GDPR template
- policy_templates_backup.json: sync with main templates file
- test_gdpr_policy_e2e.py: update test setup and fix VAT test text
All tests now pass. Keyword guards prevent false positives.
* Fix: address Greptile pattern feedback
- Fix fr_phone: use negative lookbehind (?<!\d) to prevent false matches in digit strings
- Add keyword_pattern to eu_passport_generic to reduce false positives
- Add keyword_pattern to eu_vat for contextual matching
All pattern tests passing
* Update litellm/proxy/guardrails/guardrail_hooks/litellm_content_filter/patterns.json
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
---------
Co-authored-by: greptile-apps[bot] <165735046+greptile-apps[bot]@users.noreply.github.com>
* support policy mapping on team key level
* update document
* update document
* address comments
* update document
* add unit test for new feature
* add more test case
* 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>
Fixed two issues:
1. Presidio guardrail test TypeError:
- Issue: test_presidio_apply_guardrail() was calling apply_guardrail() with
incorrect arguments (text=, language=) instead of the correct signature
(inputs=, request_data=, input_type=)
- Fix: Updated test to use correct method signature:
- Changed from: apply_guardrail(text=..., language=...)
- Changed to: apply_guardrail(inputs={'texts': [...]}, request_data={}, input_type='request')
- Also updated assertions to extract text from response['texts'][0]
2. License verification base64 decoding error:
- Issue: verify_license_without_api_request() was failing with
'Invalid base64-encoded string: number of data characters (185) cannot be
1 more than a multiple of 4' when license keys lacked proper base64 padding
- Root cause: Base64 strings must be a multiple of 4 characters. Some license
keys were missing padding characters (=) needed for proper decoding
- Fix: Added automatic padding before base64 decoding:
- Calculate padding needed: len(license_key) % 4
- Add '=' characters to make length a multiple of 4
- This makes license verification robust to keys with or without padding
Both fixes ensure the code handles edge cases properly and tests use correct APIs.
* fix(unified_guardrail.py): correctly map a v1/messages call to the anthropic unified guardrail
* fix: add more rigorous call type checks
* fix(anthropic_endpoints/endpoints.py): initialize logging object at the beginning of endpoint
ensures call id + trace id are emitted to guardrail api
* feat(anthropic/chat/guardrail_translation): support streaming guardrails
sample on every 5 chunks
* fix(openai/chat/guardrail_translation): support openai streaming guardrails
* fix: initial commit fixing output guardrails for responses api
* feat(openai/responses/guardrail_translation): handler.py - fix output checks on responses api
* fix(openai/responses/guardrail_translation/handler.py): ensure responses api guardrails work on streaming
* test: update tests
* test: update tests
* test: update tests
* fix(bedrock_guardrails.py): fix post call streaming iterator logic
* fix: fix return
* fix(bedrock_guardrails.py): fix
* fix: use fastuuid helper across the codebase
First batch of changes, simple drop in replacement.
* second batch of changes
* fixed: script mistake on helper file
* feat: Add Pillar Security guardrail integration
Implements comprehensive LLM security guardrails using Pillar Security API with support for prompt injection detection, PII/secret detection, content moderation, and multi-mode execution (pre_call, during_call, post_call). Includes complete documentation, testing, and configurable actions on flagged content.
* fix: Resolve MyPy type error in Pillar guardrail config
Restructure PillarGuardrailConfigModel to properly inherit from GuardrailConfigModel[T]
and resolve return type compatibility issue in get_config_model method.
* fix: Resolve MyPy type error in Pillar guardrail config
Restructure PillarGuardrailConfigModel to properly inherit from GuardrailConfigModel[T]
and resolve return type compatibility issue in get_config_model method.
* fix docs
* fix docs
* improved docs
* fix examples, READY
* refactor(aim.py): refactor to support adding aim guardrails on UI
* fix(base.py): add ui_friendly_name to config model
* feat(ui/): support loading new guardrails from backend api call
removes need to onboard each guardrail to ui
* fix: don't show optional params if not set and don't show ui_friendly_name (internal param0
* fix(ui/add_guardrail_form.tsx): ensure dynamic provider value is used
* fix(ui/): just one-time update the provider map dictionary
* fix(ui/): show masked api base / api key on guardrail update
* refactor(aporia_ai/): refactor to show on UI
* feat(aporia_ai/): add aporia ai guardrail to UI
* refactor(guardrails_ai/): refactor to add via UI
* refactor(lasso.py): refactor to enable adding lasso guardrails via UI
* feat(pangea.py): add pangea guardrail on UI
* feat(panw): add panw prisma airs through UI
* test: update tests
* fix: fix ruff linting error
* test: update tests
* fix: add missing docs
* fix: fix guardrail init
* fix: suppress linting errors
* fix(proxy_server.py): fix linting error
* build(model_prices_and_context_window.json): remove 'supports_tool_choice' for specific mistral models
Closes https://github.com/BerriAI/litellm/issues/11750
* feat: initial commit adding cleaner ui for azure text moderation guardrails
* feat(guardrail_endpoints.py): add discoverable guardrail configs and improve converting base model to dict with types
* fix(guardrail_provider_fields.tsx): render from api endpoint correctly
* fix(guardrail_provider_fields.tsx): cleanup
* refactor(guardrail_endpoints.py): refactor to handle dictionaries with literal - allows multiselect
* feat(ui/): render dictionary with known keys correctly
* feat(ui/): render optional params on separate page
* style(ui/): style improvements to rendering optional params on the UI
* feat(azure/prompt_shield.py): add azure prompt shield back on UI
* fix(add_guardrail_form.tsx): fix form to handle updated api
* fix(guardrail_optional_params.tsx): ensure values are nested correctly for writing to api
* fix: fix linting error
* feat(text_moderation.py): handle str to int conversion
* fix(guardrail_info.tsx): only render pii settings if guardrail is presidio
* fix(guardrail_info.tsx): add guardrail specific fields to update settings
allows updating guardrail fields (e.g. severity threshold) post-create
* fix(guardrail_endpoints.py): set guardrail_id in guardrail object
ensures duplicate objects not created on guardrail update
* fix(guardrail_endpoints.py): allow provider specific fields to be updated on patch update
* refactor(guardrail_endpoints.py): remove duplicate info endpoint
* fix(guardrail_endpoints.py): mask sensitive keys on returning via guardrail `/info`
Prevent leaking keys
* fix(guardrail_optional_params.tsx): return numerical input when numerical component used
fixes issue where output was a str
* fix(guardrail_optional_params.tsx): render dict keys correctly
* fix(text_moderation.py): fix severity by category check
* fix(proxy/utils.py): check if guardrail should run for post call streaming hook
Prevents invalid guardrails from running if not requested
* test: fix import
* fix: fix linting error
* test: update test
* fix: fix tests
* fix: fix code qa errors
* fix(guardrail_endpoints.py): set max depth for function
* test: update recursive_detector.py
* test: update list
* build: merge main
* fix: fix ruff check errors
* fixes for using bedrock guard
* fixes for output_content_bedrock guard
* test_convert_to_bedrock_format_input_source
* test_convert_to_bedrock_format_post_call_streaming_hook
* test bedrock guard
* Move PANW Prisma AIRS test per feedback on PR #12116
- Move test to tests/test_litellm/proxy/guardrails/guardrail_hooks/
* Remove test file from old location
* Feature/lasso guardrail (#9002)
* first version of lasso guardrail in litellm
* update to the new Lasso API
* change prod api_base and kill the request when lasso detect issue.
* change test for now api, local test pass
* add async tests
* all tests pass
* add docs for the new lasso guardrail
* Remove support for modes other than pre_call in Lasso guardrail
* code structure and naming
* only pre_call docs
* fix lint errors
* move test to the new location follows the same directory structure as litellm/.
* add lasso guard
* docs lasso docs
* add lasso guardrail
* fix lasso guardrail
---------
Co-authored-by: oroxenberg <oro@lasso.security>
* feat: Add presidio_language parameter for PII analysis configuration via yaml config files
- Introduced presidio_language parameter in guardrail_initializers and guardrail_hooks to allow language specification for Presidio PII analysis via yaml config files
- Updated PresidioPresidioConfigModelUserInterface to include presidio_language with a default value of "en".
- Added tests to verify language configuration functionality, ensuring correct language usage in analyze requests.
* docs: Enhance PII masking documentation with language support details
- Added information on configuring the default language for PII analysis using the `presidio_language` parameter in both the UI and YAML configuration.
- Included supported language codes (English, Spanish, German) and their precedence in language settings.
- Provided examples for default language configuration and per-request language overrides to clarify usage.
