nemoguardrails.library.crowdstrike_aidr.actions
nemoguardrails.library.crowdstrike_aidr.actions
Module Contents
Classes
Functions
Data
API
Bases: BaseModel
Bases: BaseModel
Whether or not the prompt triggered a block detection.
Updated structured prompt, if applicable.
Whether or not the original input was transformed.
Bases: typing.TypedDict
Bases: BaseModel
Convert a CrowdStrike result into a rail decision.
Blocking takes precedence over transformation. A transformed input rewrites the user message, while a transformed output rewrites the bot message.
Evaluate conversation content with CrowdStrike AI Guard.
The action evaluates the user message for input rails and includes the bot message for output rails. A successful provider response can allow, block, or transform the active message.
Expected provider failures fail open: unsuccessful HTTP status responses, transport failures, malformed JSON, and response-schema validation errors are logged and return an allow outcome containing the original messages. Unexpected programming errors are not swallowed.
Parameters:
Whether the action is evaluating an input or output rail.
RailsConfig — Active rails configuration.
Conversation context used when explicit messages are omitted.
Optional user message override.
Optional bot message override.
Optional[ HTTPClient ] — Optional caller-owned HTTP client. The action does not
close an injected client.
Returns: RailOutcome
The provider-derived rail outcome, or an allow outcome for an expected
Raises:
ValueError: If the API token or required conversation content is missing.