feat: paired review system overhaul — unified service, configurable agents, silent output removal

- Remove UNIFIED_MODE legacy: single service manages all 3 Discord bots
- Add OWNER_AGENT_TYPE / REVIEWER_AGENT_TYPE env vars for configurable agent selection
- Fix Discord channel routing: reviewer output goes through correct bot (discord/discord-review)
- Fix channel name assignment: explicit names prevent agentTypeFilter collision
- Remove silent output suppression system: harness-level protections replace prompt workarounds
- Add reviewer approval detection: DONE marker on first line stops ping-pong
- Include user's original message in reviewer prompt for context
- Fix round_trip_count auto-reset on new user message
- Fix session ID conflict: reviewer doesn't reuse owner's session
- Fix pending progress text flush in runner on close sentinel
- Promote buffered intermediate text to final result when result event has no text
- Remove legacy files: .env.codex.example, .env.codex-review.example, migrate-unify.cjs
- Update CLAUDE.md: server-side build deployment, unified architecture docs

src/db.ts

@@ -1053,6 +1053,18 @@ export function getLastHumanMessageTimestamp(chatJid: string): string | null {
   return row?.timestamp ?? null;
 }
 
+export function getLastHumanMessageContent(chatJid: string): string | null {
+  const row = db
+    .prepare(
+      `SELECT content FROM messages
+       WHERE chat_jid = ? AND is_bot_message = 0 AND is_from_me = 0
+         AND content != '' AND content IS NOT NULL
+       ORDER BY timestamp DESC, seq DESC LIMIT 1`,
+    )
+    .get(chatJid) as { content: string } | undefined;
+  return row?.content ?? null;
+}
+
 export function hasRecentRestartAnnouncement(
   chatJid: string,
   sinceTimestamp: string,