# A category-threshold filter, the shape every hosted moderation product ships.
#
# The classifier reports a score per category; the rule owns the bar and the
# exemption. Both of those are the parts an operator argues about, so both are
# here in the document rather than in the classifier's configuration.
oar: "1.0"
id: HATE_HIGH
namespace: example.moderation
kind: detector
anchor: model.output
requires:
  profiles: [moderation]
detector:
  ref: detector://fixture
when: 'moderation_score("hate") >= 0.7'
effect: block
status: stable
references:
  owasp_llm: [LLM01]
copy:
  title: Hateful content
  what: The response scored above the bar for the hate category.
---
# The same category at a lower bar, reported rather than refused. Two rules
# rather than one field with three values, because "warn here, block there" is
# a policy and policies are documents.
oar: "1.0"
id: HATE_ELEVATED
namespace: example.moderation
kind: detector
anchor: model.output
requires:
  profiles: [moderation]
detector:
  ref: detector://fixture
when: 'moderation_score("hate") >= 0.4 && moderation_score("hate") < 0.7'
effect: warn
status: stable
copy:
  what: The response scored in the elevated band for the hate category.
---
# An exemption that a hosted product usually cannot express at all: the same
# bar, relaxed for an internal posture. The condition says so in one line where
# a reviewer can read it.
oar: "1.0"
id: VIOLENCE_HIGH
namespace: example.moderation
kind: detector
anchor: model.output
requires:
  profiles: [moderation, session]
detector:
  ref: detector://fixture
when: 'moderation_score("violence") >= 0.7 && session_posture != "internal"'
effect: block
status: stable
copy:
  what: The response scored above the bar for the violence category.
  fix: Internal sessions are exempt; this one is not.