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/main.py

@@ -4,13 +4,31 @@ from contextlib import asynccontextmanager
 from fastapi import FastAPI
 from fastapi.middleware.cors import CORSMiddleware
 
+from app.api import chat, logs, memory, system
+from app.api import models as models_api
+from app.api import settings as settings_api
+from app.core import settings_store
 from app.core.config import CORS_ORIGINS
 from app.core.discord.discord_bot import start_discord_bot
 from app.core.discord.scheduler import start_scheduler
 from app.core.memory_kb.word_memory import seed_from_history
 from app.db.database import SessionLocal, init_db
-from app.db.models import Message
-from app.api import chat, memory, logs, system
+from app.db.models import Message, ModelPreset
+
+# ModelSelector.vue に元々ハードコードされていたプリセット。初回起動時のみDBへシードする。
+_DEFAULT_MODEL_PRESETS = [
+    ("GPT-5.5", "gpt-5.5"),
+    ("GPT-5.4", "gpt-5.4"),
+    ("GPT-5.4 mini", "gpt-5.4-mini"),
+    ("Claude Sonnet 4.6", "claude-sonnet-4-6"),
+    ("Claude Haiku 4.5", "claude-haiku-4-5-20251001"),
+    ("Ollama llama3", "ollama/llama3"),
+    ("Ollama Gemma4", "ollama/gemma4"),
+    ("Gemma 4 12B (llama-server)", "gpt-3.5-turbo"),
+    ("Claude Sonnet 4.6 (Bedrock)", "bedrock/jp.anthropic.claude-sonnet-4-6"),
+    ("Llama 3 70B (Bedrock)", "bedrock/meta.llama3-70b-instruct-v1:0"),
+    ("Nova 2 Lite (Bedrock)", "bedrock/jp.amazon.nova-2-lite-v1:0"),
+]
 
 
 def _seed_word_memory_from_db() -> None:
@@ -28,9 +46,31 @@ def _seed_word_memory_from_db() -> None:
         db.close()
 
 
+def _load_settings_into_env() -> None:
+    db = SessionLocal()
+    try:
+        settings_store.load_into_env(db)
+    finally:
+        db.close()
+
+
+def _seed_default_models() -> None:
+    db = SessionLocal()
+    try:
+        if db.query(ModelPreset).first() is not None:
+            return
+        for label, value in _DEFAULT_MODEL_PRESETS:
+            db.add(ModelPreset(label=label, value=value))
+        db.commit()
+    finally:
+        db.close()
+
+
 @asynccontextmanager
 async def lifespan(app: FastAPI):
     init_db()
+    _load_settings_into_env()
+    _seed_default_models()
     _seed_word_memory_from_db()
     start_scheduler()
     asyncio.create_task(start_discord_bot())
@@ -52,6 +92,8 @@ app.include_router(chat.router)
 app.include_router(memory.router)
 app.include_router(logs.router)
 app.include_router(system.router)
+app.include_router(settings_api.router)
+app.include_router(models_api.router)
 
 
 @app.get("/health")