feat: named destinations + permission enforcement + fire-and-forget self-mod

Replaces implicit routing context (NANOCLAW_PLATFORM_ID env vars) with
per-agent named destination maps. Agents reference channels and peer
agents by local names; the host re-validates every outbound route against
a new agent_destinations table that is both the routing map and the ACL.

Model changes:
- New migration 004 adds agent_destinations (agent_group_id, local_name,
  target_type, target_id). Backfills from existing messaging_group_agents.
- Host writes /workspace/.nanoclaw-destinations.json before every container
  wake so admin changes take effect on next start.
- Container loads map at startup, appends system-prompt addendum listing
  available destinations and the <message to="name">…</message> syntax.
- Agent main output is parsed for <message to="..."> blocks; each block
  becomes a messages_out row with routing resolved via the local map.
  Untagged text and <internal>…</internal> are scratchpad (logged only).
- send_message MCP tool now takes `to` (destination name) instead of raw
  routing fields. send_to_agent deleted (redundant — agents are just
  destinations). send_file/edit_message/add_reaction route via map too.
- Inbound formatter adds from="name" attribute via reverse-lookup so the
  agent sees a consistent namespace in both directions.

Permission enforcement:
- Host checks hasDestination() before every channel delivery AND every
  agent-to-agent route. Unauthorized messages dropped and logged.
- routeAgentMessage simplified: ~15 lines, no JSON parse, content copied
  verbatim (target formatter resolves the sender via its own local map).
- create_agent is admin-only, checked at both the container (tool not
  registered for non-admins) and the host (re-check on receive). Inserts
  bidirectional destination rows so parent↔child comms work immediately.
  Includes path-traversal guard on folder name.

Self-modification cleanup:
- add_mcp_server now requires admin approval (previously had none).
- install_packages validates package names on BOTH sides (container tool
  + host receiver) with strict regex. Max 20 packages per request.
- All three self-mod tools are fire-and-forget: write request, return
  immediately with "submitted" message. Admin approval triggers a chat
  notification to the requesting agent — no tool-call polling, no 5-min
  holds. On rebuild/mcp_server approval, the container is killed so the
  next wake picks up new config/image.
- Approval delivery extracted into requestApproval() helper (the one
  place where three call sites were literally identical).

Also folded in the phase-1 dynamic import cleanup (create_agent no longer
does `await import('./db/agent-groups.js')`) and removes NANOCLAW_PLATFORM_ID
/ CHANNEL_TYPE / THREAD_ID env-var routing entirely.

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

src/db/migrations/index.ts

@@ -4,6 +4,7 @@ import { log } from '../../log.js';
 import { migration001 } from './001-initial.js';
 import { migration002 } from './002-chat-sdk-state.js';
 import { migration003 } from './003-pending-approvals.js';
+import { migration004 } from './004-agent-destinations.js';
 
 export interface Migration {
   version: number;
@@ -11,7 +12,7 @@ export interface Migration {
   up: (db: Database.Database) => void;
 }
 
-const migrations: Migration[] = [migration001, migration002, migration003];
+const migrations: Migration[] = [migration001, migration002, migration003, migration004];
 
 export function runMigrations(db: Database.Database): void {
   db.exec(`