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/compliance/service.go

@@ -1120,6 +1120,7 @@ func (s *Service) ProcessReviewJob(ctx context.Context, msg ReviewJobMessage) er
 		return s.markReviewJobDone(ctx, job.ID)
 	}
 	result, err := s.llm.Generate(ctx, sharedllm.GenerateRequest{
+		Model:           strings.TrimSpace(cfg.LLMJudgeModel),
 		Prompt:          prompt,
 		Timeout:         cfg.ReviewWorkerTimeout,
 		MaxOutputTokens: 900,