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/cmd/tenant-api/main.go

@@ -35,7 +35,8 @@ func main() {
 	app.DesktopDispatch.Run(workerCtx)
 
 	monitoringService := app.MonitoringService
-	monitoringCallbackService := tenantapp.NewMonitoringCallbackService(app.DB, app.MonitoringDB, app.RabbitMQ, app.LLM, app.Logger)
+	monitoringCallbackService := tenantapp.NewMonitoringCallbackService(app.DB, app.MonitoringDB, app.RabbitMQ, app.LLM, app.Logger).
+		WithConfigProvider(app.ConfigStore)
 	tenantapp.NewMonitoringCollectOutboxWorker(monitoringService, app.Logger).Start(workerCtx)
 	tenantapp.NewMonitoringResultIngestWorker(monitoringCallbackService, app.RabbitMQ, app.Logger, app.Config().MonitoringWorkers).Start(workerCtx)
 	tenantapp.NewMonitoringProjectionRebuildWorker(monitoringCallbackService, app.RabbitMQ, app.Logger, app.Config().MonitoringWorkers).Start(workerCtx)