feat(tenant): make monitoring parse & compliance judge models configurable

Replace the hardcoded doubao-lite model used for monitoring answer
parsing and compliance LLM judging with configurable values, resolved
from config with env overrides and a legacy default fallback.

- Add llm.monitoring_answer_parse_model and compliance.llm_judge_model
  to config struct, env overrides, and all config files
- Thread the resolved model through MonitoringCallbackService via a
  ConfigProvider and into parseMonitoringAnswerWithLLM
- Pass compliance.llm_judge_model into the review-job LLM request

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

server/internal/tenant/transport/desktop_monitoring_handler.go

@@ -18,7 +18,8 @@ type DesktopMonitoringHandler struct {
 
 func NewDesktopMonitoringHandler(a *bootstrap.App) *DesktopMonitoringHandler {
 	return &DesktopMonitoringHandler{
-		svc: app.NewMonitoringCallbackService(a.DB, a.MonitoringDB, a.RabbitMQ, a.LLM, a.Logger),
+		svc: app.NewMonitoringCallbackService(a.DB, a.MonitoringDB, a.RabbitMQ, a.LLM, a.Logger).
+			WithConfigProvider(a.ConfigStore),
 	}
 }