feat: tiered LLM providers (fast/heavy) with multi-provider config

Adds tier-based LLM routing so fast local models (vLLM, Ollama) handle
structured tasks while cloud models (Gemini, Anthropic) are reserved for
heavy reasoning. Single-provider configs continue to work via fallback.

- Tier type + ProviderRegistry with assignTier/getProvider/fallback chain
- Multi-provider config format: { providers: [{ name, type, tier, ... }] }
- NamedProvider wrapper for multiple instances of same provider type
- Setup wizard: Simple (legacy) / Advanced (fast+heavy tiers) modes
- Status display: tiered view with /llm/providers endpoint
- Call sites use getProvider('fast') instead of getActive()
- Full backward compatibility with existing single-provider configs

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

src/mcplocal/tests/llm-config.test.ts

@@ -116,9 +116,9 @@ describe('createProviderFromConfig', () => {
       { provider: 'vllm', model: 'my-model', url: 'http://gpu-server:8000' },
       store,
     );
-    // vLLM reuses OpenAI provider under the hood
+    // vLLM reuses OpenAI provider under the hood, wrapped with NamedProvider
     expect(registry.getActive()).not.toBeNull();
-    expect(registry.getActive()!.name).toBe('openai');
+    expect(registry.getActive()!.name).toBe('vllm');
   });
 
   it('returns empty registry when vllm URL is missing', async () => {