feat(guardrail_model): support guardrail policy configuration for agents #698
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Outdated suggestions cannot be applied.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.
Add Guardrails Models
Summary
Implements a comprehensive guardrails system for UiPath agents with configurable validation rules and actions.
Changes
Guardrails Models (
src/uipath/models/guardrails.py
)Core Components
AllFieldsSelector
,SpecificFieldsSelector
with discriminated unionsWordRule
- Text validation with operators (contains, equals, startsWith, etc.)NumberRule
- Numeric validation with comparison operatorsBooleanRule
- Boolean field validationUniversalRule
- Always-apply rules for input/output/bothBlockAction
- Stop execution with reasonFilterAction
- Remove specific fieldsLogAction
- Log events with severity levelsEscalateAction
- Human-in-the-loop workflowsCustomGuardrail
- User-defined rules and logicBuiltInValidatorGuardrail
- Pre-built validators with parametersAgent Integration (
src/uipath/agent/models/agent.py
)guardrails: Optional[List[Guardrail]]
toBaseAgentDefinition
Testing and Example Usage (
tests/agent/models/test_agent.py
)test_agent_config_loads_guardrails