Fix code review issues: security, race conditions, resource leaks

- Fix race condition: pass return_timestamps as parameter instead of mutating shared state
- Remove /local/transcriptions endpoint (path traversal vulnerability)
- Add timeout=30 and URL scheme validation to prevent SSRF
- Add temp file cleanup via try/finally in all route handlers
- AsyncTaskManager: add threading.Lock and TTL cleanup for completed tasks
- Change audio_rate to 16000 (matches Whisper's expected sample rate)
- Extract filename from URL via Content-Disposition/path
- Detect base64 audio format via python-magic
- Fix response_size_bytes to use json.dumps instead of str()
- Move scipy import to module level
- Clamp temperature to [0.0, 1.0]
- Deduplicate _load_model() code
- Fix docstrings, README structure, typo, log level

Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
This commit is contained in:
Serge Zaigraeff
2026-03-30 00:54:50 +03:00
co-authored by Claude Opus 4.6
parent ff4bd2ba3d
commit 2138651474
12 changed files with 153 additions and 189 deletions
+45 -31
View File
@@ -1,11 +1,11 @@
"""
Модуль manager.py содержит функции для асинхронной обработки задач.
Модуль async_tasks.py содержит функции для асинхронной обработки задач.
"""
import uuid
import time
from typing import Dict, Any, Callable, Optional
from threading import Thread
from threading import Thread, Lock
import logging
logger = logging.getLogger('app.async_tasks')
@@ -19,10 +19,13 @@ class AsyncTaskManager:
tasks (Dict): Словарь для хранения информации о задачах.
"""
TASK_TTL = 3600 # 1 час
def __init__(self):
"""
Инициализация менеджера асинхронных задач.
"""
self._lock = Lock()
self.tasks: Dict[str, Dict[str, Any]] = {}
def run_task(self, func: Callable, *args, **kwargs) -> str:
@@ -38,23 +41,33 @@ class AsyncTaskManager:
ID задачи.
"""
task_id = str(uuid.uuid4())
# Создание информации о задаче
self.tasks[task_id] = {
"status": "pending",
"result": None,
"error": None,
"created_at": time.time(),
"started_at": None,
"completed_at": None
}
# Создание и запуск потока
with self._lock:
self._cleanup_old_tasks()
self.tasks[task_id] = {
"status": "pending",
"result": None,
"error": None,
"created_at": time.time(),
"started_at": None,
"completed_at": None
}
thread = Thread(target=self._run_task_thread, args=(task_id, func, args, kwargs))
thread.daemon = True
thread.start()
return task_id
def _cleanup_old_tasks(self) -> None:
"""Удаляет завершённые задачи старше TASK_TTL. Вызывать под self._lock."""
now = time.time()
expired = [
tid for tid, info in self.tasks.items()
if info["completed_at"] and now - info["completed_at"] > self.TASK_TTL
]
for tid in expired:
del self.tasks[tid]
def _run_task_thread(self, task_id: str, func: Callable, args: tuple, kwargs: dict) -> None:
"""
@@ -66,26 +79,25 @@ class AsyncTaskManager:
args: Позиционные аргументы для функции.
kwargs: Именованные аргументы для функции.
"""
try:
# Обновление статуса задачи
with self._lock:
self.tasks[task_id]["status"] = "running"
self.tasks[task_id]["started_at"] = time.time()
# Выполнение функции
try:
result = func(*args, **kwargs)
# Сохранение результата
self.tasks[task_id]["status"] = "completed"
self.tasks[task_id]["result"] = result
self.tasks[task_id]["completed_at"] = time.time()
with self._lock:
self.tasks[task_id]["status"] = "completed"
self.tasks[task_id]["result"] = result
self.tasks[task_id]["completed_at"] = time.time()
logger.info(f"Задача {task_id} завершена успешно")
except Exception as e:
# Обработка ошибки
self.tasks[task_id]["status"] = "failed"
self.tasks[task_id]["error"] = str(e)
self.tasks[task_id]["completed_at"] = time.time()
with self._lock:
self.tasks[task_id]["status"] = "failed"
self.tasks[task_id]["error"] = str(e)
self.tasks[task_id]["completed_at"] = time.time()
logger.error(f"Задача {task_id} завершилась с ошибкой: {e}")
def get_task_status(self, task_id: str) -> Optional[Dict[str, Any]]:
@@ -98,7 +110,9 @@ class AsyncTaskManager:
Returns:
Информация о задаче или None, если задача не найдена.
"""
return self.tasks.get(task_id)
with self._lock:
task = self.tasks.get(task_id)
return dict(task) if task else None
# Глобальный экземпляр менеджера асинхронных задач