Add AI chat with skills management and model provider settings

- Model providers for OpenAI and Anthropic message formats (e.g. via
  Sub2API), with API keys encrypted at rest and never returned
- Skills tree with markdown editing, priorities, drafts, publishing and
  rollback; only published skills enter the chat prompt
- Chat page with tool calls over collected news and Binance USD-M
  klines, a persisted CONTEXT.md, reset, and stop-generation support
- Chat may only create skill drafts and update CONTEXT.md; publishing,
  deleting, moving and priority changes stay with the user

backend/src/alphapulse/core/config.py

@@ -13,6 +13,8 @@ class Settings(BaseSettings):
     admin_username: str
     admin_password_hash: str = ""
     jwt_expire_days: int = 7
+    # Fernet 密钥，加密存库的第三方 API key
+    secret_encryption_key: str
 
 
 @lru_cache

backend/src/alphapulse/core/crypto.py

@@ -0,0 +1,20 @@
+"""存库凭证的加解密；密钥只在 .env 中"""
+
+from functools import lru_cache
+
+from cryptography.fernet import Fernet
+
+from alphapulse.core.config import get_settings
+
+
+@lru_cache
+def _fernet() -> Fernet:
+    return Fernet(get_settings().secret_encryption_key)
+
+
+def encrypt(plain: str) -> bytes:
+    return _fernet().encrypt(plain.encode())
+
+
+def decrypt(token: bytes) -> str:
+    return _fernet().decrypt(token).decode()