summaryrefslogtreecommitdiff
path: root/packages
diff options
context:
space:
mode:
authorFuwn <[email protected]>2025-09-26 02:36:32 -0700
committerFuwn <[email protected]>2025-09-26 02:36:32 -0700
commit3d4ea3b18785f63b7fbd75f4678d979231bc9507 (patch)
tree9ec509cd67d280480d35e44ecf3dc6b94aab9ca7 /packages
parentfeat(gateway:moderationAgent): Switch model to Microsoft: Phi 4 Multimodal In... (diff)
downloadumabotdiscord-3d4ea3b18785f63b7fbd75f4678d979231bc9507.tar.xz
umabotdiscord-3d4ea3b18785f63b7fbd75f4678d979231bc9507.zip
feat(gateway:moderationAgent): Update analysis guidelines
Diffstat (limited to 'packages')
-rw-r--r--packages/gateway/src/listeners/moderationAgent/utilities.ts10
1 files changed, 9 insertions, 1 deletions
diff --git a/packages/gateway/src/listeners/moderationAgent/utilities.ts b/packages/gateway/src/listeners/moderationAgent/utilities.ts
index eb55f1c..52b08ad 100644
--- a/packages/gateway/src/listeners/moderationAgent/utilities.ts
+++ b/packages/gateway/src/listeners/moderationAgent/utilities.ts
@@ -99,7 +99,7 @@ SEXUAL CONTENT GUIDELINES:
- When in doubt, be lenient with sexual content - most sexual references are acceptable
UNDERAGE CONTENT RULES:
-- ONLY flag if words like "underage", "loli", "minor", "child", "teen", "young", or specific ages are explicitly mentioned
+- ONLY flag if words like "underage", "minor", "child", "teen", "young", or specific ages are explicitly mentioned
- FAMILY WORDS DO NOT MEAN UNDERAGE: "daughter", "son", "mom", "dad", "sister", "brother" = ADULT roleplay
- ASSUME EVERYONE IS AN ADULT unless explicitly stated otherwise
- ASSUME NO DIRECT FAMILY RELATIONSHIP unless explicitly stated otherwise
@@ -107,6 +107,14 @@ UNDERAGE CONTENT RULES:
- EXAMPLES: "look down at my daughter" = ADULT roleplay, NOT underage content
- ROLEPLAY CONTENT: All family sexual content is adult roleplay between consenting adults
- When in doubt, assume adult roleplay rather than underage content
+
+TERM CLARIFICATIONS:
+- "LEWDS" = Adult sexual content, NOT underage content
+- "LOLI" MENTIONS = Discussing the term is acceptable, NOT a violation
+- "emergency lewds" = Adult sexual content, NOT underage content
+- MENTIONING TERMS = Talking about "loli" or other terms is acceptable
+- DENYING CONTENT = "This is not loli content" is acceptable discussion
+- When in doubt, assume adult content rather than underage content
`;
const response = await fetch(
"https://openrouter.ai/api/v1/chat/completions",