From 3d4ea3b18785f63b7fbd75f4678d979231bc9507 Mon Sep 17 00:00:00 2001 From: Fuwn Date: Fri, 26 Sep 2025 02:36:32 -0700 Subject: feat(gateway:moderationAgent): Update analysis guidelines --- packages/gateway/src/listeners/moderationAgent/utilities.ts | 10 +++++++++- 1 file changed, 9 insertions(+), 1 deletion(-) (limited to 'packages') 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", -- cgit v1.2.3