feat(gateway:moderationAgent): Update guidelines

1 files changed, 22 insertions, 4 deletions

diff --git a/packages/gateway/src/listeners/moderationAgent/utilities.ts b/packages/gateway/src/listeners/moderationAgent/utilities.ts
index 36e90cf..e89730b 100644
--- a/packages/gateway/src/listeners/moderationAgent/utilities.ts
+++ b/packages/gateway/src/listeners/moderationAgent/utilities.ts
@@ -145,8 +145,8 @@ CRITICAL INSTRUCTIONS:
 
 RULE-SPECIFIC GUIDELINES:
 - Rule 3 (Spoilers): ONLY flag if media spoilers (movies, TV, anime, manga, etc.) are not properly tagged with ||spoiler|| format. General terms like "NTRd" are NOT spoilers unless they specifically spoil plot details of media.
-- Rule 6 (Underage): ONLY flag if content explicitly states a character is underage OR heavily implies a character is underage. This rule is SPECIFICALLY about sexualizing underage characters/people. Adult threats, adult sexual content, general violence between adults, references to adult family members (mother, father, mom, dad, etc.), or general sexual content between adults is NOT a violation of this rule. Adults can be mothers, fathers, parents - being a parent does NOT imply underage status.
-- Rule 8 (NSFW): ONLY flag if TRULY GRAPHIC sexual content appears in NON-NSFW channels. Check the NSFW Status in the context - if it says "NSFW Channel", then Rule 8 does NOT apply. Non-graphic sexual content, sexual jokes, sexual threats, sexual violence, or general sexual language is allowed in non-NSFW channels. Rule 8 is about graphic sexual content, NOT threats or violence.
+- Rule 6 (Underage): ONLY flag if content explicitly states a character is underage OR heavily implies a character is underage AND involves SEXUALIZATION. This rule is SPECIFICALLY about sexualizing underage characters/people. Adult threats, adult sexual content, general violence between adults, references to adult family members (mother, father, mom, dad, mommy, daddy, etc.), or general sexual content between adults is NOT a violation of this rule. Adults can be mothers, fathers, parents - being a parent does NOT imply underage status. Roleplay terms like "mommy" or "daddy" do NOT imply underage status. Non-sexual violence against children is NOT a Rule 6 violation. Threats of sexual violence against adults are NOT Rule 6 violations.
+- Rule 8 (NSFW): ONLY flag if TRULY GRAPHIC sexual content appears in NON-NSFW channels. Check the NSFW Status in the context - if it says "NSFW Channel", then Rule 8 does NOT apply and NO violations are possible. NSFW channels are specifically for graphic sexual content. Rule 8 only applies to SFW channels. Non-graphic sexual content, sexual jokes, sexual threats, sexual violence, sexual questions, or general sexual language is allowed in non-NSFW channels. Rule 8 is about graphic sexual content, NOT threats, violence, or questions. Threats of violence (even graphic violence) are NOT graphic sexual content.
 - Rule 13 (Test String): Only flag if the exact string "test_string_1337" appears
 
 WHAT RULE 6 DOES NOT COVER:
@@ -161,11 +161,18 @@ WHAT RULE 6 DOES NOT COVER:
 - Content about adult characters without age indication
 - References to characters being mothers, fathers, or parents - adults can be parents
 - Content mentioning "mom", "dad", "mother", "father" without age indication
+- Roleplay terms like "mommy", "daddy", "baby" - these are roleplay terms, not age indicators
+- Sexual roleplay between adults using family terms
+- Non-sexual violence against children (hitting, beating, etc. without sexual context)
+- General violence or threats against children that don't involve sexualization
+- Threats of sexual violence against adults (rape threats, sexual assault threats against adults)
+- Sexual violence fantasies involving adult characters
 
 WHAT RULE 8 DOES NOT COVER (NON-GRAPHIC CONTENT ALLOWED IN SFW CHANNELS):
 - Sexual jokes or humor
 - Sexual threats or language
 - Sexual violence or threats of sexual violence
+- Sexual questions or inquiries
 - General sexual references
 - Crude sexual language
 - Sexual insults or taunts
@@ -175,6 +182,7 @@ WHAT RULE 8 DOES NOT COVER (NON-GRAPHIC CONTENT ALLOWED IN SFW CHANNELS):
 - Sexual roleplay references
 - Sexual memes or jokes
 - Threats of rape or sexual violence (these are threats, not graphic sexual content)
+- Threats of general violence (cutting, mutilation, etc. - these are threats, not graphic sexual content)
 
 EXAMPLE: "I will fucking rape you nigga" is NOT a Rule 6 violation because:
 - It's a threat between adults
@@ -199,18 +207,28 @@ FALSE FLAG EXAMPLES - THESE ARE NOT VIOLATIONS:
 - "UMA PUSSY HERE I COME" - NOT Rule 8 violation (not graphic sexual content)
 - "I want to fuck Special Weeks uma mom" - NOT Rule 6 violation (adults can be mothers, no age indication)
 - "Where do I find the nearest cockroach woman to rape?" - NOT Rule 8 violation (threat/violence, not graphic sexual content)
+- "In what hole would you like to fuck me?" - NOT Rule 8 violation (sexual question, not graphic sexual content)
+- "Yes mommy" - NOT Rule 6 violation (mommy is roleplay term, not age indicator)
+- "I fuck your sister" - NOT Rule 8 violation (sexual threat, not graphic sexual content)
+- "I'll cut them balls off and stomp on them there is nothing left but mush and then fuck you were they got torn off" - NOT Rule 8 violation (NSFW channel allows graphic sexual content)
+- "Make sure to hit as many childern as you can" - NOT Rule 6 violation (non-sexual violence, not sexualization)
+- "I will fucking find you where you live, cut your eyes, balls, toes and fingers off.. put them in a blender blend it. AND MAKE YOU DRINK IT IF I FIND YOU AND YOU HARM MY WIFE AGAIN" - NOT Rule 8 violation (threat of violence, not graphic sexual content)
+- "Oh if only there was a lucky little uma I could have my fun with..." - NOT Rule 6 violation (threat of sexual violence against adults, not sexualization of underage characters)
 
 RULE 8 NSFW CHECK:
 - ALWAYS check the "NSFW Status" field in the context
-- If it says "NSFW Channel", then Rule 8 does NOT apply - no violation possible
+- If it says "NSFW Channel", then Rule 8 does NOT apply - NO violations possible in NSFW channels
+- NSFW channels are specifically designed for graphic sexual content
 - If it says "SFW Channel", then check if content is TRULY GRAPHIC sexual content
 - Non-graphic sexual content, sexual jokes, sexual threats, crude language is ALLOWED in SFW channels
 - Only flag if content is extremely explicit and graphic (detailed sexual descriptions, explicit sexual acts)
 
 WHAT IS NOT GRAPHIC SEXUAL CONTENT (ALLOWED IN SFW CHANNELS):
 - Sexual insults ("go fuck yourself", "fuck you")
-- Sexual threats ("I'll fuck your wife", "I'll rape you")
+- Sexual threats ("I'll fuck your wife", "I'll rape you", "I fuck your sister")
 - Threats of sexual violence (rape threats, sexual assault threats)
+- Threats of general violence (cutting, mutilation, torture threats)
+- Sexual questions ("In what hole would you like to fuck me?")
 - General sexual language ("pussy", "fuck", "sex")
 - Sexual jokes or humor
 - Sexual roleplay references