Class: DatadogAPIClient::V2::AIGuardEvaluateAttributesResponse

Inherits:
Object
  • Object
show all
Includes:
BaseGenericModel
Defined in:
lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb

Overview

The evaluation result with the recommended action and detected threat information.

Instance Attribute Summary collapse

Method Summary

Methods included from BaseGenericModel

included

Instance Attribute Details

#action ⇒ Object

The recommended action for the evaluated conversation.



25
26
27
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 25

def action
  @action
end

#additional_properties ⇒ Object

Returns the value of attribute additional_properties.



65
66
67
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 65

def additional_properties
  @additional_properties
end

#global_prob ⇒ Object

The global threat probability, between 0 and 1. Included only when computed.



28
29
30
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 28

def global_prob
  @global_prob
end

#is_blocking_enabled ⇒ Object

Whether blocking is enabled for the organization.



31
32
33
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 31

def is_blocking_enabled
  @is_blocking_enabled
end

#reason ⇒ Object

The explanation for the recommended action, for logging rather than user-facing display.



34
35
36
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 34

def reason
  @reason
end

#redaction_replacements ⇒ Object

The redacted replacements computed for the request. Included only when redaction applies.



37
38
39
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 37

def redaction_replacements
  @redaction_replacements
end

#scfw_findings ⇒ Object

The Supply Chain Firewall verdict for the version-pinned install packages found in the request. Evaluation requires Supply Chain Firewall to be enabled for the organization and the caller to have the appsec_vm_read permission. Without that permission, Supply Chain Firewall evaluation is skipped; the AI Guard evaluation request itself is not rejected. Findings are omitted when Supply Chain Firewall does not produce a result. The recommended action combines the package outcomes. Confirmation support is inferred from the evaluator profile, not from a separate confirmation-capability flag. By default, a non-empty meta.coding_agent selects the coding-agent profile, which assumes the caller can ask for confirmation and retains WARN in recommended_action. Omitting meta.coding_agent or setting it to an empty string selects the default profile, which assumes the caller cannot ask for confirmation and returns ALLOW instead of WARN in recommended_action. Package outcomes still retain WARN, and BLOCK is never changed to ALLOW by this rule.



54
55
56
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 54

def scfw_findings
  @scfw_findings
end

#sds_findings ⇒ Object

The sensitive data findings from the Sensitive Data Scanner. Included only when findings exist.



57
58
59
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 57

def sds_findings
  @sds_findings
end

#tag_probs ⇒ Object

The detection confidence for each threat tag, between 0 and 1. May be null when the evaluation does not produce per-category scores.



60
61
62
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 60

def tag_probs
  @tag_probs
end

#tags ⇒ Object

The threat tags detected in the conversation.



63
64
65
 
# File 'lib/datadog_api_client/v2/models/ai_guard_evaluate_attributes_response.rb', line 63

def tags
  @tags
end