Add Docker/Lightsail deployment, web search summarization, and fix vite peer dep

- Add backend/frontend Dockerfiles, nginx reverse proxy config, and
  docker-compose.yml to run the app on AWS Lightsail; document the setup
  in docs/deploy-lightsail.md. Fix a .gitignore path anchoring bug that
  left backend/knowledge_base/web_search/ untracked instead of ignored.
- Summarize web search results into structured Markdown via LLM before
  saving them to the local knowledge base, and support regenerating
  existing entries from their source URLs (backend/app/core/memory_kb).
- Downgrade vite to ^6 to match @vitejs/plugin-vue's peer dependency
  range, fixing a failing `npm ci` (found while testing the Docker build).

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

backend/app/api/chat.py

@@ -11,6 +11,7 @@ from app.db.models import Session, Message
 from app.core.memory_kb import memory as mem
 from app.core import llm
 from app.core.memory_kb import knowledge
+from app.core.memory_kb import local_knowledge
 from app.core.search.websearch import WEB_SEARCH_TOOL
 from app.core.config import DEFAULT_MODEL
 from app.core.memory_kb.tagging import tag_message_by_id
@@ -77,6 +78,13 @@ def delete_session(session_id: str, db: DBSession = Depends(get_db)):
     db.commit()
 
 
+@router.post("/knowledge/regenerate")
+async def regenerate_knowledge(db: DBSession = Depends(get_db)):
+    """既存のKnowledgeEntryを出典URLから取得し直し、構造化要約に再生成する（一括実行用）。"""
+    count = await knowledge.regenerate_from_sources(db)
+    return {"regenerated": count}
+
+
 @router.post("/stream")
 async def stream_chat(req: ChatRequest, db: DBSession = Depends(get_db)):
     # セッション取得 or 新規作成
@@ -126,9 +134,10 @@ async def stream_chat(req: ChatRequest, db: DBSession = Depends(get_db)):
                 ]
                 yield sse({"type": "sources", "value": sources})
                 for s in searches:
-                    summary = "\n".join(r["content"][:300] for r in s["results"] if r["content"])
+                    summary = await knowledge.summarize_results(s["query"], s["results"])
                     if summary:
                         knowledge.save_knowledge(db, s["query"], summary, s["results"])
+                        local_knowledge.save_search_result(s["query"], summary, s["results"])
 
             search_tools = [WEB_SEARCH_TOOL] if len(resolved_context) > len(context) else None
             async for chunk in llm.stream_chat(