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/app/monitoring_answer_llm_parse.go

@@ -11,7 +11,7 @@ import (
 )
 
 const (
-	monitoringAnswerParseLLMModel           = "doubao-seed-2-0-lite-260215"
+	defaultMonitoringAnswerParseLLMModel    = "doubao-seed-2-0-lite-260215"
 	monitoringAnswerParseLLMTimeout         = 30 * time.Second
 	monitoringAnswerParseLLMMaxOutputTokens = 600
 )
@@ -63,6 +63,7 @@ func parseMonitoringAnswerWithLLM(
 	client sharedllm.Client,
 	answer string,
 	brandName string,
+	model string,
 ) (monitoringAnswerParseSummary, error) {
 	answer = strings.TrimSpace(answer)
 	brandName = strings.TrimSpace(brandName)
@@ -72,9 +73,13 @@ func parseMonitoringAnswerWithLLM(
 	if brandName == "" {
 		return monitoringAnswerParseSummary{}, fmt.Errorf("brand name is empty")
 	}
+	model = strings.TrimSpace(model)
+	if model == "" {
+		model = defaultMonitoringAnswerParseLLMModel
+	}
 
 	result, err := client.Generate(ctx, sharedllm.GenerateRequest{
-		Model:           monitoringAnswerParseLLMModel,
+		Model:           model,
 		Prompt:          buildMonitoringAnswerParsePrompt(answer, brandName),
 		Timeout:         monitoringAnswerParseLLMTimeout,
 		MaxOutputTokens: monitoringAnswerParseLLMMaxOutputTokens,