feat: Add external expert sources (Wikidata SPARQL + ConceptNet API)

- Add expert_cache.py: TTL-based in-memory cache (1 hour default)
- Add expert_source_service.py: WikidataProvider and ConceptNetProvider
  - Wikidata SPARQL queries for occupations with Chinese labels
  - ConceptNet API queries for occupation-related concepts
  - Random selection from cached pool
- Update schemas.py: Add ExpertSource enum (llm/wikidata/conceptnet)
- Update ExpertTransformationRequest with expert_source and expert_language
- Update router: Conditionally use external sources with LLM fallback
  - New SSE events: expert_source, expert_fallback
- Update frontend types with ExpertSource

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>

frontend/src/types/index.ts

@@ -230,6 +230,8 @@ export interface ExpertTransformationDAGResult {
   results: ExpertTransformationCategoryResult[];
 }
 
+export type ExpertSource = 'llm' | 'wikidata' | 'conceptnet';
+
 export interface ExpertTransformationRequest {
   query: string;
   category: string;
@@ -237,6 +239,8 @@ export interface ExpertTransformationRequest {
   expert_count: number;              // 2-8
   keywords_per_expert: number;       // 1-3
   custom_experts?: string[];         // ["藥師", "工程師"]
+  expert_source?: ExpertSource;      // 專家來源 (default: 'llm')
+  expert_language?: string;          // 外部來源語言 (default: 'zh')
   model?: string;
   temperature?: number;
 }