feat(ai-moderation): reset offensive nickname instead of deleting message

When the ONLY violation is offensive_username (message content clean):
- Message is NOT deleted (nickname-only violation bypasses auto-delete)
- Member's server nickname is reset to default username via
  setNickname(null) (Discord shows the global username again)
- Action 'reset_nickname' logged to moderation_actions; cooldown
  10min per guild:user (LRU) so repeated messages by same member
  don't hammer the Discord PATCH
- Config: AUTO_NICKNAME_RESET_ENABLED / AUTO_NICKNAME_RESET_COOLDOWN_MS
This commit is contained in:
asepharyana
2026-08-10 11:48:27 +07:00
parent ecbb538c9f
commit 185d81f0e0
6 changed files with 260 additions and 2 deletions
@@ -47,6 +47,40 @@ export function deriveRecommendedAction(msg: MessageRecord): string {
return "none";
}
/** Parse the flag list from a structured result or the stored column. */
export function parseModerationFlags(
message: MessageRecord,
analysisResult?: AnalysisResult,
): string[] {
const flags = analysisResult?.flags ?? null;
if (flags && flags.length > 0) return flags;
const stored = message.ai_moderation_flags;
if (!stored) return [];
try {
const parsed = JSON.parse(stored) as unknown;
return Array.isArray(parsed)
? parsed.filter((f): f is string => typeof f === "string")
: [];
} catch {
return [];
}
}
/**
* True when the ONLY violation is the member's server nickname — the message
* content itself is clean. Such messages must NOT be auto-deleted; the
* correct enforcement is resetting the nickname to the default username.
* Any other flag (sara, harassment, vulgar_language, ...) keeps the normal
* delete path.
*/
export function isNicknameOnlyViolation(
message: MessageRecord,
analysisResult?: AnalysisResult,
): boolean {
const flags = parseModerationFlags(message, analysisResult);
return flags.length > 0 && flags.every((f) => f === "offensive_username");
}
/**
* Check whether a message qualifies for auto-deletion.
* Uses the structured `analysisResult` fields when provided, falling back