Reorganize core into subpackages, add local KB, ruff/pyright tooling

- Split backend/app/core into weather/, discord/, memory_kb/, search/
  subpackages by responsibility, keeping config.py and llm.py as the
  shared foundation; updated all import sites accordingly.
- Add local Markdown knowledge base support (local_knowledge.py,
  knowledge_base/fgo.md, LOCAL_KB_* settings) that embeds and injects
  relevant docs into the system prompt by topic similarity.
- Add ruff and pyright as backend dev dependencies with basic config
  in pyproject.toml for linting and type checking.
- Document local machine quirks in CLAUDE.md (Postgres on port 8080,
  SSLKEYLOGFILE breaking litellm/pyright via OPENSSL_Uplink crashes).
- Add backend/run_dev.ps1 dev launcher and docs/discord-bot.md.

backend/app/core/config.py

@@ -17,6 +17,12 @@ TAVILY_API_KEY: str | None = os.getenv("TAVILY_API_KEY")
 # 蓄積した知識をシステムプロンプトに注入する際の最大件数
 KNOWLEDGE_CONTEXT_LIMIT: int = int(os.getenv("KNOWLEDGE_CONTEXT_LIMIT", "15"))
 
+# ローカルMarkdownナレッジベース（話題に応じて関連ファイルをシステムプロンプトに注入）
+LOCAL_KB_DIR: str = os.getenv("LOCAL_KB_DIR", "knowledge_base")
+LOCAL_KB_EMBEDDING_MODEL: str = os.getenv("LOCAL_KB_EMBEDDING_MODEL", "text-embedding-3-small")
+LOCAL_KB_TOP_K: int = int(os.getenv("LOCAL_KB_TOP_K", "3"))
+LOCAL_KB_MIN_SCORE: float = float(os.getenv("LOCAL_KB_MIN_SCORE", "0.75"))
+
 # Amazon Bedrock
 # 以下はすべて LiteLLM(boto3) が os.environ から直接読み取るため、.env に書くだけで自動的に有効になる。
 # IAM経由（推奨）: AWS_ACCESS_KEY_ID / AWS_SECRET_ACCESS_KEY を設定する。