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>

src/http/app.ts

@@ -16,6 +16,7 @@ import { createAnalyticsRoutes } from "../routes/analyticsRoutes.js";
 import { createMediaRoutes } from "../routes/mediaRoutes.js";
 import { createMessageRoutes } from "../routes/messageRoutes.js";
 import { createRecordingsRoutes } from "../routes/recordingsRoutes.js";
+import { createReviewRoutes } from "../routes/reviewRoutes.js";
 import { createSyncRoutes } from "../routes/syncRoutes.js";
 import { createUIStateRoutes } from "../routes/uiStateRoutes.js";
 import { createVoiceRoutes } from "../routes/voiceRoutes.js";
@@ -114,6 +115,7 @@ export function createHttpApp(options: CreateHttpAppOptions) {
   );
   app.use("/api", createMessageRoutes());
   app.use("/api", createAnalysisRoutes());
+  app.use("/api", createReviewRoutes());
   app.use("/api", createAnalyticsRoutes());
   app.use("/api", createSyncRoutes(options.client));
   app.use("/api", createRecordingsRoutes());