feat: add multi-model delegation (Phase 0) and context compaction (Phase 1)

Phase 0 — Multi-Model Delegation:
- AgentOrchestrator wraps NativeAgent with delegate() for stateless
  single-turn calls to any model tier (fast/default/complex/local)
- DelegationConfig maps task types (compaction, classification, etc.)
  to model tiers
- Delegation prompts for compaction, memory extraction, classification,
  and tool summarisation
- Per-tier usage tracking for cost visibility
- Config schema: agents.delegation and agents.primary_tier

Phase 1 — Context Compaction:
- Token estimation (char/4 heuristic) with context window lookup
- shouldCompact() threshold check against context window percentage
- compactHistory() splits old/recent messages, delegates summary to
  fast tier, returns CompactionResult
- Automatic compaction in AgentOrchestrator.process() when configured
- Force-compact via orchestrator.compact() with session persistence
- Session.replaceHistory() with atomic SQLite transaction
- /compact TUI command with feedback on compacted token counts
- Config schema: compaction.enabled, threshold_pct, keep_turns,
  summary_max_tokens

Tests: 385 passing across 50 files (22 new tests in 2 new test files)

src/frontends/tui/commands.test.ts

@@ -26,6 +26,10 @@ describe('parseCommand', () => {
     expect(parseCommand('/fs')).toEqual({ type: 'fullscreen' });
   });
 
+  it('parses /compact command', () => {
+    expect(parseCommand('/compact')).toEqual({ type: 'compact' });
+  });
+
   it('parses /model command without argument', () => {
     expect(parseCommand('/model')).toEqual({ type: 'model' });
   });
@@ -64,6 +68,7 @@ describe('getHelpText', () => {
     expect(help).toContain('/help');
     expect(help).toContain('/model');
     expect(help).toContain('/reset');
+    expect(help).toContain('/compact');
     expect(help).toContain('/quit');
   });
 });