feat: add Mixture of Agents (MoA) for arbiter verdicts

When MOA_ENABLED=true, arbiter queries multiple LLM models in parallel
via OpenAI-compatible API, then an aggregator model synthesizes the
final verdict from all opinions. Falls back to single-agent arbiter
when MoA is disabled.

Config: MOA_BASE_URL, MOA_API_KEY, MOA_REFERENCE_MODELS, MOA_AGGREGATOR_MODEL

src/message-runtime.test.ts

@@ -23,6 +23,8 @@ vi.mock('./config.js', () => ({
   isClaudeService: vi.fn(() => true),
   isReviewService: vi.fn(() => false),
   isSessionCommandSenderAllowed: vi.fn(() => false),
+  getMoaConfig: vi.fn(() => ({ enabled: false, referenceModels: [], aggregator: {} })),
+  TIMEZONE: 'Asia/Seoul',
 }));
 
 vi.mock('./paired-execution-context.js', () => ({