Add GUI settings panel for API keys, model presets, and embedding model

- Add a password-protected /api/settings endpoint (HTTP Basic auth,
  backend/app/core/auth.py) backed by a DB-stored allowlist of
  connection settings (OPENAI_API_KEY, ANTHROPIC_API_KEY, AWS creds,
  OLLAMA_API_BASE, TAVILY_API_KEY, LOCAL_KB_EMBEDDING_MODEL). Saved
  values override .env and apply immediately via os.environ, so
  Lightsail deployments no longer need SSH + `.env` edits to rotate
  keys. Values are always returned masked to the frontend.
- Replace ModelSelector.vue's hardcoded model list with a DB-backed
  /api/models CRUD API (read is public, writes reuse the settings
  password) so the chat model dropdown can be edited from the GUI;
  seed it once with the previous hardcoded presets on first boot.
- Fix local_knowledge.py reading LOCAL_KB_EMBEDDING_MODEL once at
  import time instead of per-call, which would have silently ignored
  GUI/DB overrides for the embedding model.
- Add SettingsPanel.vue (API keys + model management UI) and document
  the new SETTINGS_PASSWORD env var in .env.example and the Lightsail
  deploy guide.

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

backend/app/core/memory_kb/local_knowledge.py

@@ -7,12 +7,13 @@ import hashlib
 import json
 import logging
 import math
+import os
 from pathlib import Path
 
 from sqlalchemy.orm import Session as DBSession
 
 from app.core import llm
-from app.core.config import LOCAL_KB_DIR, LOCAL_KB_EMBEDDING_MODEL, LOCAL_KB_MIN_SCORE, LOCAL_KB_TOP_K
+from app.core.config import LOCAL_KB_DIR, LOCAL_KB_MIN_SCORE, LOCAL_KB_TOP_K
 from app.db.models import KnowledgeEntry, LocalKnowledgeDoc
 
 logger = logging.getLogger(__name__)
@@ -22,6 +23,11 @@ def _kb_dir() -> Path:
     return Path(LOCAL_KB_DIR)
 
 
+def _embedding_model() -> str:
+    """GUIの設定画面から実行時に変更できるよう、起動時定数ではなく都度 os.environ を見に行く。"""
+    return os.environ.get("LOCAL_KB_EMBEDDING_MODEL", "text-embedding-3-small")
+
+
 def _hash(content: str) -> str:
     return hashlib.sha256(content.encode("utf-8")).hexdigest()
 
@@ -104,7 +110,7 @@ async def sync_local_kb(db: DBSession) -> None:
             continue
 
         try:
-            [embedding] = await llm.embed([content], model=LOCAL_KB_EMBEDDING_MODEL)
+            [embedding] = await llm.embed([content], model=_embedding_model())
         except Exception:
             logger.exception("Failed to embed local knowledge file: %s", rel_path)
             continue
@@ -142,7 +148,7 @@ async def get_local_kb_context(db: DBSession, query_text: str) -> str | None:
         return None
 
     try:
-        [query_embedding] = await llm.embed([query_text], model=LOCAL_KB_EMBEDDING_MODEL)
+        [query_embedding] = await llm.embed([query_text], model=_embedding_model())
     except Exception:
         logger.exception("Failed to embed query for local knowledge search")
         return None