feat(knowledge): multi-query retrieval with LLM query rewrite

Add a shared structured query builder (knowledge_query.go) and switch
all generation paths to it, so retrieval queries carry task intent
(type, brand, region, keywords, key points) instead of a raw prompt.

ResolveContext now rewrites the query into multiple sub-questions via
the URL-markdown model, embeds and searches each, and merges/dedupes
candidates before rerank; falls back to parsed fallback questions when
rewrite is unavailable or returns too few. Resolve logs gain query
list, count, and rewrite stage/model for observability.

- knowledge_query.go/_test.go: BuildKnowledgeQuery + intent normalization
- knowledge_service.go: per-query embed/search loop, query rewrite, logs
- template_prompt/template_service/prompt_generate/article_imitation/
  kol_generation_worker: adopt the shared query builder
- generation_observability: richer task error logging

server/internal/tenant/app/prompt_generate_service.go

@@ -718,7 +718,7 @@ func (s *PromptRuleGenerationService) failGeneration(ctx context.Context, job pr
 	now := time.Now()
 	logCtx := promptRuleGenerationJobLogContext(job, stage, "", "failed", GenerationTaskResultFailure)
 	RecordGenerationTaskEvent(GenerationTaskEventFailure, logCtx)
-	LogGenerationTaskWarn(s.logger, "prompt rule generation failed", logCtx, zap.Error(genErr))
+	LogGenerationTaskWarn(s.logger, "prompt rule generation failed", logCtx, GenerationTaskErrorFields(genErr)...)
 	failureTitle := strings.TrimSpace(extractString(job.InputParams, "task_name"))
 	if failureTitle == "" {
 		failureTitle = title
@@ -857,41 +857,28 @@ func buildPromptRuleGenerationPrompt(rule *promptRuleGenerationRecord, params ma
 }
 
 func buildPromptRuleKnowledgeQuery(rule *promptRuleGenerationRecord, params map[string]interface{}) string {
-	parts := make([]string, 0, 6)
+	intent := knowledgeQueryIntent{
+		TaskType:       "自定义生成",
+		Title:          firstNonEmptyPromptString(params, "task_name", "title", "topic", "subject"),
+		Topic:          firstNonEmptyPromptString(params, "topic", "subject", "title"),
+		BrandName:      extractString(params, "brand_name"),
+		PrimaryKeyword: extractString(params, "primary_keyword"),
+		Keywords:       mergeKnowledgeQueryKeywords(params["keywords"], params["primary_keyword"]),
+		KeyPoints:      extractString(params, "key_points"),
+		Extra:          extractString(params, "extra_requirements"),
+	}
 	if rule != nil {
-		if text := strings.TrimSpace(rule.Name); text != "" {
-			parts = append(parts, text)
+		if name := strings.TrimSpace(rule.Name); name != "" {
+			intent.TemplateName = name
+			if intent.Title == "" {
+				intent.Title = name
+			}
 		}
 		if rule.Scene != nil && strings.TrimSpace(*rule.Scene) != "" {
-			parts = append(parts, strings.TrimSpace(*rule.Scene))
+			intent.TaskType = strings.TrimSpace(*rule.Scene)
 		}
 	}
-	if taskName := strings.TrimSpace(extractString(params, "task_name")); taskName != "" {
-		parts = append(parts, taskName)
-	}
-	for _, key := range []string{
-		"title",
-		"topic",
-		"subject",
-		"brand_name",
-		"product_name",
-		"primary_keyword",
-		"key_points",
-		"extra_requirements",
-	} {
-		if text := strings.TrimSpace(extractString(params, key)); text != "" {
-			parts = append(parts, text)
-		}
-	}
-	if keywords := extractStringList(params["keywords"], 16); len(keywords) > 0 {
-		parts = append(parts, strings.Join(keywords, "\n"))
-	}
-	if rule != nil {
-		if text := strings.TrimSpace(rule.PromptContent); text != "" {
-			parts = append(parts, text)
-		}
-	}
-	return strings.Join(parts, "\n")
+	return buildKnowledgeQueryInputText(intent)
 }
 
 func extractGenerateCount(extra map[string]interface{}) int {