feat(brain): add brain_answer and brain_classify MCP tools

Adds two new LLM-backed MCP tools to the ingestion service:

- brain_answer(query): BM25 retrieval + LLM synthesis → answer + sources
- brain_classify(text): classifies doc into type/title/tags via LLM

Adds llm.Router for primary→fallback routing (berget.ai → iguana).
Wired via BRAIN_LLM_PRIMARY_URL/BRAIN_LLM_FALLBACK_URL env vars;
no-op when unset so existing deployments are unaffected.

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

ingestion/internal/mcp/integration_test.go

@@ -14,7 +14,7 @@ import (
 )
 
 func TestMCPMountedHandler(t *testing.T) {
-	srv := mcp.NewServer(t.TempDir(), nil, nil)
+	srv := mcp.NewServer(t.TempDir(), nil, nil, nil)
 	mux := http.NewServeMux()
 	mux.Handle("POST /mcp", srv)