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>

backend/app/models/schemas.py

@@ -206,6 +206,13 @@ class ExpertTransformationDAGResult(BaseModel):
     results: List[ExpertTransformationCategoryResult]
 
 
+class ExpertSource(str, Enum):
+    """專家來源類型"""
+    LLM = "llm"
+    WIKIDATA = "wikidata"
+    CONCEPTNET = "conceptnet"
+
+
 class ExpertTransformationRequest(BaseModel):
     """Expert Transformation Agent 請求"""
     query: str
@@ -217,6 +224,10 @@ class ExpertTransformationRequest(BaseModel):
     keywords_per_expert: int = 1                 # 每個專家為每個屬性生成幾個關鍵字 (1-3)
     custom_experts: Optional[List[str]] = None   # 用戶指定專家 ["藥師", "工程師"]
 
+    # Expert source parameters
+    expert_source: ExpertSource = ExpertSource.LLM  # 專家來源
+    expert_language: str = "zh"                     # 外部來源的語言
+
     # LLM parameters
     model: Optional[str] = None
     temperature: Optional[float] = 0.7