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/cmd/server/main.go

@@ -56,7 +56,25 @@ func main() {
 
 	h := api.NewHandler(brainDir, logger, pipelineCfg)
 
-	mcpSrv := mcp.NewServer(brainDir, &pipelineCfg, llmClient.Complete)
+	var answerComplete pipeline.CompleteFunc
+	if primaryURL := os.Getenv("BRAIN_LLM_PRIMARY_URL"); primaryURL != "" {
+		primaryModel := envOr("BRAIN_LLM_PRIMARY_MODEL", "gemma4:31b")
+		primaryKey := os.Getenv("BERGET_API_KEY")
+		timeoutMS := envInt("BRAIN_LLM_TIMEOUT_MS", 10000)
+		timeout := time.Duration(timeoutMS) * time.Millisecond
+
+		primary := llm.New(primaryURL, primaryKey, primaryModel, timeout)
+		router := &llm.Router{Primary: primary}
+
+		if fallbackURL := os.Getenv("BRAIN_LLM_FALLBACK_URL"); fallbackURL != "" {
+			fallbackModel := envOr("BRAIN_LLM_FALLBACK_MODEL", "gemma4:31b")
+			router.Fallback = llm.New(fallbackURL, "", fallbackModel, timeout)
+		}
+		answerComplete = router.Complete
+		logger.Info("brain answer LLM configured", "primary", primaryURL, "model", primaryModel)
+	}
+
+	mcpSrv := mcp.NewServer(brainDir, &pipelineCfg, llmClient.Complete, answerComplete)
 
 	mcpToken := os.Getenv("BRAIN_MCP_TOKEN")
 	if mcpToken == "" {