feat: Add Deduplication Agent with embedding and LLM methods

Implement a new Deduplication Agent that identifies and groups similar
transformation descriptions. Supports two deduplication methods:
- Embedding: Fast vector similarity comparison using cosine similarity
- LLM: Accurate pairwise semantic comparison (slower but more precise)

Backend changes:
- Add deduplication router with /deduplicate endpoint
- Add embedding_service for vector-based similarity
- Add llm_deduplication_service for LLM-based comparison
- Improve expert_transformation error handling and progress reporting

Frontend changes:
- Add DeduplicationPanel with interactive group visualization
- Add useDeduplication hook for state management
- Integrate deduplication tab in main App
- Add threshold slider and method selector in sidebar

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

backend/app/prompts/expert_transformation_prompt.py

@@ -90,16 +90,15 @@ def get_single_description_prompt(
 ) -> str:
     """Step 2: 為單一關鍵字生成描述"""
     # 如果 domain 是通用的，就只用職業名稱
-    domain_text = f"（{expert_domain}）" if expert_domain and expert_domain != "Professional Field" else ""
+    domain_text = f"（{expert_domain}領域）" if expert_domain and expert_domain != "Professional Field" else ""
 
     return f"""/no_think
-物件：「{query}」
-專家：{expert_name}{domain_text}
+你是一位{expert_name}{domain_text}。
+
+任務：為「{query}」生成一段創新應用描述。
 關鍵字：{keyword}
 
-你是一位{expert_name}。從你的專業視角，生成一段創新應用描述（15-30字），說明如何將「{keyword}」的概念應用到「{query}」上。
+從你的專業視角，說明如何將「{keyword}」的概念應用到「{query}」上。描述要具體、有創意，15-30字。
 
-描述要體現{expert_name}的專業思維和獨特觀點。
-
-回傳 JSON：
-{{"description": "應用描述"}}"""
+只回傳 JSON，不要其他文字：
+{{"description": "你的創新應用描述"}}"""