feat: expand AI moderation with structured analysis, review workflow, and guardrails

- Add structured AI moderation fields (categories, severity, confidence,
  recommended_action, policy_version, evidence) to messages table
- Add moderation_reviews, moderation_actions, and retention_policies tables
- Upgrade LLM response parsing to support structured metadata with backwards
  compatibility for legacy responses
- Implement public AI evaluation review UI with decision controls
  (approve, false positive + reanalyze, escalate)
- Add auto-delete guardrails requiring high confidence, severity, and
  allowed categories; log all attempts to moderation_actions
- Add retention manager scaffolding for messages/attachments/voice
- Add action executor for moderation actions (mute, warn, kick, ban)
- Add review routes: GET/POST/PATCH /api/reviews, GET/POST/PATCH /api/actions
- Preserve auth separation: voice/media/recordings gated, review public

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

frontend/src/api/client.ts

@@ -1,4 +1,12 @@
 export type AIStatus = "pending" | "clean" | "warn" | "flagged" | "error";
+export type AISeverity = "none" | "low" | "medium" | "high" | "critical";
+export type AIRecommendedAction =
+  | "none"
+  | "monitor"
+  | "warn"
+  | "review"
+  | "delete"
+  | "escalate";
 
 export interface MessageRecord {
   id: string;
@@ -20,6 +28,12 @@ export interface MessageRecord {
   ai_moderation_score?: number | null;
   ai_moderation_raw?: string | null;
   ai_analysis?: string | null;
+  ai_categories?: string | null;
+  ai_severity?: AISeverity | null;
+  ai_confidence?: number | null;
+  ai_recommended_action?: AIRecommendedAction | null;
+  ai_policy_version?: string | null;
+  ai_evidence?: string | null;
   ai_analyzed_at?: number | null;
   ai_error?: string | null;
 }