chore(routing): flip LITELLM_BASE_URL default to https://llm-api.d-ma.be

Follow-up to infra#70. LiteLLM moved off piguard into k3s and the
public llm-api.d-ma.be hostname now upstreams to koala:30401. The
piguard:4000 default in the source bit-rots — works today because
piguard:4000 is still alive during the 7-day soak, breaks the moment
the compose comes down.

Pointing the default at the public hostname survives the cutover
without needing a follow-up. Production deploys via k3s already
override via env (in-cluster Service DNS) so this only affects local
dev shells without LITELLM_BASE_URL set.

- internal/config/routing.go: comment + envOr fallback
- internal/config/routing_test.go: expected value in defaults test
- scripts/smoke-routing.sh: shell default

task check: clean (tests + vet + govulncheck).

internal/config/routing.go

@@ -11,7 +11,7 @@ import (
 type RoutingConfig struct {
 	Port               string  // ROUTING_PORT, default 3210
 	MCPAuthToken       string  // ROUTING_MCP_TOKEN, optional bearer token
-	LiteLLMBaseURL     string  // LITELLM_BASE_URL, default http://piguard:4000
+	LiteLLMBaseURL     string  // LITELLM_BASE_URL, default https://llm-api.d-ma.be
 	LiteLLMAPIKey      string  // LITELLM_API_KEY
 	BrainURL           string  // BRAIN_URL, default http://ingestion.supervisor:3300
 	FastModel          string  // HYPERGUILD_FAST_MODEL, default koala/qwen35-9b-fast
@@ -41,7 +41,7 @@ func LoadRouting() (RoutingConfig, error) {
 	cfg := RoutingConfig{
 		Port:           envOr("ROUTING_PORT", "3210"),
 		MCPAuthToken:   os.Getenv("ROUTING_MCP_TOKEN"),
-		LiteLLMBaseURL: envOr("LITELLM_BASE_URL", "http://piguard:4000"),
+		LiteLLMBaseURL: envOr("LITELLM_BASE_URL", "https://llm-api.d-ma.be"),
 		LiteLLMAPIKey:  os.Getenv("LITELLM_API_KEY"),
 		BrainURL:       envOr("BRAIN_URL", "http://ingestion.supervisor:3300"),
 		FastModel:      envOr("HYPERGUILD_FAST_MODEL", "koala/qwen35-9b-fast"),