my_voice_assistant_v2/app/store.py

585 lines
23 KiB
Python
Raw Permalink Normal View History

"""Persistenzschicht: Nutzer und Sessions.
Ein abstraktes Store-Interface mit SQLite-Default (stdlib). Spaetere Backends
(Postgres/Redis) koennen dasselbe Interface implementieren, ohne die App zu aendern.
"""
from __future__ import annotations
import json
import hashlib
import secrets
import sqlite3
import uuid
from abc import ABC, abstractmethod
from dataclasses import dataclass, field
from datetime import datetime, timezone
from pathlib import Path
ANONYMOUS_USER_ID = "anonymous"
def hash_token(raw_token: str) -> str:
return hashlib.sha256(raw_token.encode("utf-8")).hexdigest()
def _now() -> str:
return datetime.now(timezone.utc).isoformat()
@dataclass
class User:
id: str
display_name: str
prefs: dict = field(default_factory=dict)
created_at: str = ""
external_id: str | None = None # SSO-/Proxy-Identitaet (Forward-Auth)
is_admin: bool = False # transient, aus ADMIN_USERS abgeleitet
@dataclass
class Session:
id: str
user_id: str
data: dict = field(default_factory=dict)
@dataclass
class Memory:
id: int
content: str
created_at: str = ""
class SessionOwnershipError(Exception):
"""Eine Session gehoert einem anderen Nutzer (-> HTTP 403)."""
class Store(ABC):
@abstractmethod
def create_user(self, display_name: str) -> tuple[User, str]:
"""Legt einen Nutzer an und liefert (User, Klartext-Token). Token nur hier sichtbar."""
@abstractmethod
def get_user_by_token(self, raw_token: str) -> User | None: ...
@abstractmethod
def get_user(self, user_id: str) -> User | None: ...
@abstractmethod
def set_user_prefs(self, user_id: str, prefs: dict) -> User: ...
@abstractmethod
def ensure_anonymous_user(self) -> User: ...
@abstractmethod
def list_users(self) -> list[User]: ...
@abstractmethod
def get_user_by_external_id(self, external_id: str) -> User | None: ...
@abstractmethod
def get_or_create_user_by_external_id(
self, external_id: str, display_name: str | None = None
) -> User: ...
@abstractmethod
def get_session(self, session_id: str) -> Session | None: ...
@abstractmethod
def update_session(self, session_id: str, user_id: str, values: dict) -> Session:
"""Erstellt/aktualisiert eine Session des Nutzers. Fremde Session -> SessionOwnershipError."""
@abstractmethod
def append_message(self, session_id: str, user_id: str, role: str, content: str) -> None:
"""Haengt eine Nachricht an die Session an. Fremde Session -> SessionOwnershipError."""
@abstractmethod
def get_recent_messages(self, session_id: str, limit: int) -> list[dict]:
"""Liefert die letzten `limit` Nachrichten chronologisch ([{'role','content'}, ...])."""
@abstractmethod
def add_memory(self, user_id: str, content: str) -> Memory:
"""Speichert eine dauerhafte Erinnerung (Fakt/Vorliebe) zum Nutzer."""
@abstractmethod
def get_memories(self, user_id: str) -> list[Memory]:
"""Liefert alle Erinnerungen des Nutzers (chronologisch)."""
@abstractmethod
def delete_memory(self, user_id: str, memory_id: int) -> bool:
"""Loescht eine Erinnerung des Nutzers. True, wenn etwas geloescht wurde."""
@abstractmethod
def get_request_count(self, user_id: str, day: str | None = None) -> int:
"""Anzahl der Anfragen des Nutzers am angegebenen Tag (Default: heute, UTC)."""
@abstractmethod
def add_usage(self, user_id: str, units: int = 0, day: str | None = None) -> int:
"""Zaehlt eine Anfrage (+units) und liefert die neue Tages-Anfragezahl."""
@abstractmethod
def delete_user(self, user_id: str) -> bool:
"""Loescht einen Nutzer und alle seine Daten (Sessions, Nachrichten, Erinnerungen,
Nutzungsdaten). Anonymer Nutzer kann nicht geloescht werden.
Liefert True, wenn der Nutzer existierte und geloescht wurde."""
@abstractmethod
def reset_token(self, user_id: str) -> tuple[User, str] | None:
"""Generiert einen neuen Token fuer den Nutzer; der alte wird sofort ungueltig.
Liefert (User, Klartext-Token) oder None, wenn der Nutzer nicht existiert."""
@abstractmethod
def update_display_name(self, user_id: str, display_name: str) -> User | None:
"""Aktualisiert den Anzeigenamen. None wenn nicht gefunden."""
@abstractmethod
def log_emergency(self, user_id: str, category: str, snippet: str) -> None:
"""Protokolliert ein erkanntes Notfall-Signal (sensibel!)."""
@abstractmethod
def list_sessions_for_user(self, user_id: str) -> list[dict]: ...
@abstractmethod
def get_messages_for_session(self, session_id: str, limit: int = 200) -> list[dict]: ...
@abstractmethod
def list_emergency_events(self, limit: int = 50) -> list[dict]: ...
@abstractmethod
def get_usage_for_user(self, user_id: str) -> list[dict]: ...
@abstractmethod
def get_all_usage(self) -> list[dict]: ...
@abstractmethod
def get_config_overrides(self) -> dict[str, str]: ...
@abstractmethod
def set_config_override(self, key: str, value: str) -> None: ...
@abstractmethod
def delete_config_override(self, key: str) -> bool: ...
class SQLiteStore(Store):
def __init__(self, db_path: str):
self.db_path = db_path
Path(db_path).parent.mkdir(parents=True, exist_ok=True)
self._init_schema()
def _connect(self) -> sqlite3.Connection:
conn = sqlite3.connect(self.db_path)
conn.row_factory = sqlite3.Row
conn.execute("PRAGMA journal_mode=WAL")
conn.execute("PRAGMA foreign_keys=ON")
return conn
def _init_schema(self) -> None:
with self._connect() as conn:
conn.executescript(
"""
CREATE TABLE IF NOT EXISTS users (
id TEXT PRIMARY KEY,
display_name TEXT NOT NULL,
token_hash TEXT NOT NULL UNIQUE,
prefs_json TEXT NOT NULL DEFAULT '{}',
created_at TEXT NOT NULL,
external_id TEXT
);
CREATE TABLE IF NOT EXISTS sessions (
id TEXT PRIMARY KEY,
user_id TEXT NOT NULL,
data_json TEXT NOT NULL DEFAULT '{}',
created_at TEXT NOT NULL,
updated_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS messages (
id INTEGER PRIMARY KEY AUTOINCREMENT,
session_id TEXT NOT NULL,
role TEXT NOT NULL,
content TEXT NOT NULL,
created_at TEXT NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_messages_session
ON messages(session_id, id);
CREATE TABLE IF NOT EXISTS memories (
id INTEGER PRIMARY KEY AUTOINCREMENT,
user_id TEXT NOT NULL,
content TEXT NOT NULL,
created_at TEXT NOT NULL
);
CREATE INDEX IF NOT EXISTS idx_memories_user
ON memories(user_id, id);
CREATE TABLE IF NOT EXISTS usage (
user_id TEXT NOT NULL,
day TEXT NOT NULL,
requests INTEGER NOT NULL DEFAULT 0,
units INTEGER NOT NULL DEFAULT 0,
PRIMARY KEY (user_id, day)
);
CREATE TABLE IF NOT EXISTS emergency_events (
id INTEGER PRIMARY KEY AUTOINCREMENT,
user_id TEXT NOT NULL,
category TEXT NOT NULL,
snippet TEXT NOT NULL,
created_at TEXT NOT NULL
);
CREATE TABLE IF NOT EXISTS config_overrides (
key TEXT PRIMARY KEY,
value TEXT NOT NULL,
updated_at TEXT NOT NULL
);
"""
)
# Migration fuer bestehende DBs: external_id ergaenzen (falls noch nicht da).
cols = {row["name"] for row in conn.execute("PRAGMA table_info(users)")}
if "external_id" not in cols:
conn.execute("ALTER TABLE users ADD COLUMN external_id TEXT")
# NULLs gelten in SQLite als verschieden -> Alt-Nutzer ohne external_id ok.
conn.execute(
"CREATE UNIQUE INDEX IF NOT EXISTS idx_users_external"
" ON users(external_id)"
)
# ----- Nutzer -----------------------------------------------------------
def _row_to_user(self, row: sqlite3.Row) -> User:
keys = row.keys()
return User(
id=row["id"],
display_name=row["display_name"],
prefs=json.loads(row["prefs_json"] or "{}"),
created_at=row["created_at"],
external_id=row["external_id"] if "external_id" in keys else None,
)
def create_user(self, display_name: str) -> tuple[User, str]:
raw_token = secrets.token_urlsafe(32)
user = User(id=uuid.uuid4().hex, display_name=display_name, prefs={}, created_at=_now())
with self._connect() as conn:
conn.execute(
"INSERT INTO users (id, display_name, token_hash, prefs_json, created_at)"
" VALUES (?, ?, ?, ?, ?)",
(user.id, user.display_name, hash_token(raw_token), "{}", user.created_at),
)
return user, raw_token
def get_user_by_token(self, raw_token: str) -> User | None:
with self._connect() as conn:
row = conn.execute(
"SELECT * FROM users WHERE token_hash = ?", (hash_token(raw_token),)
).fetchone()
return self._row_to_user(row) if row else None
def get_user(self, user_id: str) -> User | None:
with self._connect() as conn:
row = conn.execute("SELECT * FROM users WHERE id = ?", (user_id,)).fetchone()
return self._row_to_user(row) if row else None
def set_user_prefs(self, user_id: str, prefs: dict) -> User:
with self._connect() as conn:
conn.execute(
"UPDATE users SET prefs_json = ? WHERE id = ?",
(json.dumps(prefs), user_id),
)
row = conn.execute("SELECT * FROM users WHERE id = ?", (user_id,)).fetchone()
if row is None:
raise KeyError(f"Unbekannter Nutzer: {user_id}")
return self._row_to_user(row)
def ensure_anonymous_user(self) -> User:
existing = self.get_user(ANONYMOUS_USER_ID)
if existing:
return existing
with self._connect() as conn:
conn.execute(
"INSERT OR IGNORE INTO users (id, display_name, token_hash, prefs_json, created_at)"
" VALUES (?, ?, ?, ?, ?)",
(ANONYMOUS_USER_ID, "Anonymous", f"anon-{ANONYMOUS_USER_ID}", "{}", _now()),
)
return self.get_user(ANONYMOUS_USER_ID)
def list_users(self) -> list[User]:
with self._connect() as conn:
rows = conn.execute(
"SELECT * FROM users WHERE id != ? ORDER BY created_at",
(ANONYMOUS_USER_ID,),
).fetchall()
return [self._row_to_user(row) for row in rows]
def get_user_by_external_id(self, external_id: str) -> User | None:
with self._connect() as conn:
row = conn.execute(
"SELECT * FROM users WHERE external_id = ?", (external_id,)
).fetchone()
return self._row_to_user(row) if row else None
def get_or_create_user_by_external_id(
self, external_id: str, display_name: str | None = None
) -> User:
"""Findet den Nutzer zur SSO-/Proxy-Identitaet oder legt ihn an (Forward-Auth)."""
existing = self.get_user_by_external_id(external_id)
if existing:
return existing
user = User(
id=uuid.uuid4().hex,
display_name=display_name or external_id,
prefs={},
created_at=_now(),
external_id=external_id,
)
with self._connect() as conn:
conn.execute(
"INSERT INTO users (id, display_name, token_hash, prefs_json, created_at,"
" external_id) VALUES (?, ?, ?, ?, ?, ?)",
# token_hash ist NOT NULL UNIQUE -> synthetischer, kollisionsfreier Platzhalter
# (SSO-Nutzer authentifizieren sich nicht ueber ein Token).
(user.id, user.display_name, f"ext:{external_id}", "{}",
user.created_at, external_id),
)
return user
# ----- Sessions ---------------------------------------------------------
def get_session(self, session_id: str) -> Session | None:
with self._connect() as conn:
row = conn.execute(
"SELECT * FROM sessions WHERE id = ?", (session_id,)
).fetchone()
if row is None:
return None
return Session(id=row["id"], user_id=row["user_id"], data=json.loads(row["data_json"] or "{}"))
def update_session(self, session_id: str, user_id: str, values: dict) -> Session:
existing = self.get_session(session_id)
if existing and existing.user_id != user_id:
raise SessionOwnershipError(
f"Session {session_id!r} gehoert einem anderen Nutzer"
)
data = dict(existing.data) if existing else {}
data.update({k: v for k, v in values.items() if v is not None})
payload = json.dumps(data)
now = _now()
with self._connect() as conn:
if existing:
conn.execute(
"UPDATE sessions SET data_json = ?, updated_at = ? WHERE id = ?",
(payload, now, session_id),
)
else:
conn.execute(
"INSERT INTO sessions (id, user_id, data_json, created_at, updated_at)"
" VALUES (?, ?, ?, ?, ?)",
(session_id, user_id, payload, now, now),
)
return Session(id=session_id, user_id=user_id, data=data)
# ----- Nachrichten / Gespraechsverlauf ----------------------------------
def append_message(self, session_id: str, user_id: str, role: str, content: str) -> None:
existing = self.get_session(session_id)
if existing and existing.user_id != user_id:
raise SessionOwnershipError(
f"Session {session_id!r} gehoert einem anderen Nutzer"
)
now = _now()
with self._connect() as conn:
if not existing:
conn.execute(
"INSERT INTO sessions (id, user_id, data_json, created_at, updated_at)"
" VALUES (?, ?, ?, ?, ?)",
(session_id, user_id, "{}", now, now),
)
conn.execute(
"INSERT INTO messages (session_id, role, content, created_at)"
" VALUES (?, ?, ?, ?)",
(session_id, role, content, now),
)
def get_recent_messages(self, session_id: str, limit: int) -> list[dict]:
if limit <= 0:
return []
with self._connect() as conn:
rows = conn.execute(
"SELECT role, content FROM messages WHERE session_id = ?"
" ORDER BY id DESC LIMIT ?",
(session_id, limit),
).fetchall()
return [{"role": row["role"], "content": row["content"]} for row in reversed(rows)]
# ----- Langzeit-Erinnerungen --------------------------------------------
def add_memory(self, user_id: str, content: str) -> Memory:
now = _now()
with self._connect() as conn:
cur = conn.execute(
"INSERT INTO memories (user_id, content, created_at) VALUES (?, ?, ?)",
(user_id, content, now),
)
memory_id = cur.lastrowid
return Memory(id=memory_id, content=content, created_at=now)
def get_memories(self, user_id: str) -> list[Memory]:
with self._connect() as conn:
rows = conn.execute(
"SELECT id, content, created_at FROM memories WHERE user_id = ? ORDER BY id",
(user_id,),
).fetchall()
return [
Memory(id=row["id"], content=row["content"], created_at=row["created_at"])
for row in rows
]
def delete_memory(self, user_id: str, memory_id: int) -> bool:
with self._connect() as conn:
cur = conn.execute(
"DELETE FROM memories WHERE id = ? AND user_id = ?",
(memory_id, user_id),
)
return cur.rowcount > 0
# ----- Nutzung / Quota --------------------------------------------------
@staticmethod
def _today() -> str:
return datetime.now(timezone.utc).date().isoformat()
def get_request_count(self, user_id: str, day: str | None = None) -> int:
day = day or self._today()
with self._connect() as conn:
row = conn.execute(
"SELECT requests FROM usage WHERE user_id = ? AND day = ?",
(user_id, day),
).fetchone()
return int(row["requests"]) if row else 0
def add_usage(self, user_id: str, units: int = 0, day: str | None = None) -> int:
day = day or self._today()
with self._connect() as conn:
conn.execute(
"INSERT INTO usage (user_id, day, requests, units) VALUES (?, ?, 1, ?)"
" ON CONFLICT(user_id, day) DO UPDATE SET"
" requests = requests + 1, units = units + excluded.units",
(user_id, day, units),
)
row = conn.execute(
"SELECT requests FROM usage WHERE user_id = ? AND day = ?",
(user_id, day),
).fetchone()
return int(row["requests"])
def delete_user(self, user_id: str) -> bool:
if user_id == ANONYMOUS_USER_ID:
raise ValueError("Der anonyme Nutzer kann nicht geloescht werden.")
with self._connect() as conn:
if not conn.execute("SELECT 1 FROM users WHERE id = ?", (user_id,)).fetchone():
return False
conn.execute(
"DELETE FROM messages WHERE session_id IN"
" (SELECT id FROM sessions WHERE user_id = ?)",
(user_id,),
)
conn.execute("DELETE FROM sessions WHERE user_id = ?", (user_id,))
conn.execute("DELETE FROM memories WHERE user_id = ?", (user_id,))
conn.execute("DELETE FROM usage WHERE user_id = ?", (user_id,))
conn.execute("DELETE FROM users WHERE id = ?", (user_id,))
return True
def reset_token(self, user_id: str) -> tuple[User, str] | None:
with self._connect() as conn:
row = conn.execute("SELECT * FROM users WHERE id = ?", (user_id,)).fetchone()
if not row:
return None
raw_token = secrets.token_urlsafe(32)
conn.execute(
"UPDATE users SET token_hash = ? WHERE id = ?",
(hash_token(raw_token), user_id),
)
user = self._row_to_user(conn.execute("SELECT * FROM users WHERE id = ?", (user_id,)).fetchone())
return user, raw_token
def update_display_name(self, user_id: str, display_name: str) -> User | None:
with self._connect() as conn:
conn.execute(
"UPDATE users SET display_name = ? WHERE id = ?",
(display_name, user_id),
)
row = conn.execute("SELECT * FROM users WHERE id = ?", (user_id,)).fetchone()
return self._row_to_user(row) if row else None
# ----- Notfall-Protokoll ------------------------------------------------
def log_emergency(self, user_id: str, category: str, snippet: str) -> None:
with self._connect() as conn:
conn.execute(
"INSERT INTO emergency_events (user_id, category, snippet, created_at)"
" VALUES (?, ?, ?, ?)",
(user_id, category, snippet, _now()),
)
# ----- Admin-Abfragen ---------------------------------------------------
def list_sessions_for_user(self, user_id: str) -> list[dict]:
with self._connect() as conn:
rows = conn.execute(
"SELECT s.id, s.created_at, s.updated_at,"
" (SELECT COUNT(*) FROM messages m WHERE m.session_id = s.id) AS msg_count"
" FROM sessions s WHERE s.user_id = ?"
" ORDER BY s.updated_at DESC LIMIT 50",
(user_id,),
).fetchall()
return [dict(r) for r in rows]
def get_messages_for_session(self, session_id: str, limit: int = 200) -> list[dict]:
with self._connect() as conn:
rows = conn.execute(
"SELECT role, content, created_at FROM messages"
" WHERE session_id = ? ORDER BY id LIMIT ?",
(session_id, limit),
).fetchall()
return [dict(r) for r in rows]
def list_emergency_events(self, limit: int = 50) -> list[dict]:
with self._connect() as conn:
rows = conn.execute(
"SELECT e.id, e.user_id, e.category, e.snippet, e.created_at,"
" COALESCE(u.display_name, e.user_id) AS display_name"
" FROM emergency_events e LEFT JOIN users u ON u.id = e.user_id"
" ORDER BY e.id DESC LIMIT ?",
(limit,),
).fetchall()
return [dict(r) for r in rows]
def get_usage_for_user(self, user_id: str) -> list[dict]:
with self._connect() as conn:
rows = conn.execute(
"SELECT day, requests, units FROM usage"
" WHERE user_id = ? ORDER BY day DESC LIMIT 30",
(user_id,),
).fetchall()
return [dict(r) for r in rows]
def get_all_usage(self) -> list[dict]:
with self._connect() as conn:
rows = conn.execute(
"SELECT u.user_id, COALESCE(usr.display_name, u.user_id) AS display_name,"
" SUM(u.requests) AS total_requests, SUM(u.units) AS total_units,"
" MAX(u.day) AS last_active"
" FROM usage u LEFT JOIN users usr ON usr.id = u.user_id"
" GROUP BY u.user_id ORDER BY total_requests DESC",
).fetchall()
return [dict(r) for r in rows]
def get_config_overrides(self) -> dict[str, str]:
with self._connect() as conn:
rows = conn.execute("SELECT key, value FROM config_overrides").fetchall()
return {r["key"]: r["value"] for r in rows}
def set_config_override(self, key: str, value: str) -> None:
with self._connect() as conn:
conn.execute(
"INSERT INTO config_overrides(key, value, updated_at) VALUES(?,?,?)"
" ON CONFLICT(key) DO UPDATE SET value=excluded.value, updated_at=excluded.updated_at",
(key, value, _now()),
)
def delete_config_override(self, key: str) -> bool:
with self._connect() as conn:
cur = conn.execute("DELETE FROM config_overrides WHERE key=?", (key,))
return cur.rowcount > 0