asepharyana
1ae19074ee
- Persist structured verdict (flags/severity/confidence/evidence) on moderation_actions so the public web can show WHY a message was moderated. - Add a persistent Qdrant archive collection (gmw_message_archive); embed every captured message at capture time (fire-and-forget, best-effort). - Public semantic search over the archive (backend oRPC + FE toggle on the messages view). Both features are read-only/public and fully automatic. Migration: 0015_add_moderation_explainability.sql
49 lines
1.7 KiB
TypeScript
49 lines
1.7 KiB
TypeScript
import type { MessageRecord } from "../message-capture/types.js";
|
|
|
|
/**
|
|
* Map a captured message's persisted AI verdict (the `ai_*` columns on
|
|
* MessageRecord) into the explainability columns of a moderation action.
|
|
*
|
|
* This is READ-ONLY structured data — it never changes any enforcement
|
|
* decision. It exists so the public web view can show *why* a message was
|
|
* moderated, making GMW's automod transparent instead of a black box.
|
|
*
|
|
* All fields are null-safe: manual actions (e.g. command-handler bans) carry
|
|
* no AI verdict, so they simply store nulls and the UI falls back to the
|
|
* free-text `reason`.
|
|
*/
|
|
export function verdictToActionFields(message?: MessageRecord | null): {
|
|
flags: string | null;
|
|
categories: string | null;
|
|
severity: string | null;
|
|
confidence: number | null;
|
|
score: number | null;
|
|
evidence: string | null;
|
|
policy_version: string | null;
|
|
} {
|
|
if (!message) {
|
|
return {
|
|
flags: null,
|
|
categories: null,
|
|
severity: null,
|
|
confidence: null,
|
|
score: null,
|
|
evidence: null,
|
|
policy_version: null,
|
|
};
|
|
}
|
|
|
|
// ai_moderation_flags / ai_categories are stored as JSON-stringified TEXT
|
|
// (see messagesAnalysis.buildAIAnalysisSet → stringifyAIList). Pass them
|
|
// through verbatim so the backend can JSON.parse them back into arrays.
|
|
return {
|
|
flags: message.ai_moderation_flags ?? null,
|
|
categories: message.ai_categories ?? null,
|
|
severity: message.ai_severity ?? null,
|
|
confidence: message.ai_confidence ?? null,
|
|
score: message.ai_moderation_score ?? null,
|
|
evidence: null, // not persisted on MessageRecord; reserved for future use
|
|
policy_version: null, // set by caller if a policy version is available
|
|
};
|
|
}
|