Enforce modern typing (#258)

* Allow UP

* Upgrade typing

* test smolagents

* Change to contextlib

---------

Co-authored-by: Marcus Valtonen Örnhag <marcus.valtonen.ornhag@ericsson.com>

backend/fastrtc/pause_detection/silero.py

@@ -2,7 +2,6 @@ import logging
 import warnings
 from dataclasses import dataclass
 from functools import lru_cache
-from typing import List
 
 import click
 import numpy as np
@@ -102,7 +101,7 @@ class SileroVADModel:
         return h, c
 
     @staticmethod
-    def collect_chunks(audio: np.ndarray, chunks: List[AudioChunk]) -> np.ndarray:
+    def collect_chunks(audio: np.ndarray, chunks: list[AudioChunk]) -> np.ndarray:
         """Collects and concatenates audio chunks."""
         if not chunks:
             return np.array([], dtype=np.float32)
@@ -116,7 +115,7 @@ class SileroVADModel:
         audio: np.ndarray,
         vad_options: SileroVadOptions,
         **kwargs,
-    ) -> List[AudioChunk]:
+    ) -> list[AudioChunk]:
         """This method is used for splitting long audios into speech chunks using silero VAD.
 
         Args:

backend/fastrtc/reply_on_pause.py

@@ -1,9 +1,10 @@
 import asyncio
 import inspect
+from collections.abc import AsyncGenerator, Callable, Generator
 from dataclasses import dataclass, field
 from logging import getLogger
 from threading import Event
-from typing import Any, AsyncGenerator, Callable, Generator, Literal, cast
+from typing import Any, Literal, cast
 
 import numpy as np
 from numpy.typing import NDArray

backend/fastrtc/reply_on_stopwords.py

@@ -1,7 +1,8 @@
 import asyncio
 import logging
 import re
-from typing import Callable, Literal
+from collections.abc import Callable
+from typing import Literal
 
 import numpy as np
 

backend/fastrtc/stream.py

@@ -1,11 +1,10 @@
 import logging
+from collections.abc import Callable
+from contextlib import AbstractAsyncContextManager
 from pathlib import Path
 from typing import (
     Any,
-    AsyncContextManager,
-    Callable,
     Literal,
-    Optional,
     TypedDict,
     cast,
 )
@@ -29,8 +28,8 @@ curr_dir = Path(__file__).parent
 
 
 class Body(BaseModel):
-    sdp: Optional[str] = None
-    candidate: Optional[dict[str, Any]] = None
+    sdp: str | None = None
+    candidate: dict[str, Any] | None = None
     type: str
     webrtc_id: str
 
@@ -253,7 +252,7 @@ class Stream(WebRTCConnectionMixin):
         return wrapper
 
     def _inject_startup_message(
-        self, lifespan: Callable[[FastAPI], AsyncContextManager] | None = None
+        self, lifespan: Callable[[FastAPI], AbstractAsyncContextManager] | None = None
     ):
         """
         Create a FastAPI lifespan context manager to print startup messages and check environment.

backend/fastrtc/text_to_speech/tts.py

@@ -1,8 +1,9 @@
 import asyncio
 import re
+from collections.abc import AsyncGenerator, Generator
 from dataclasses import dataclass
 from functools import lru_cache
-from typing import AsyncGenerator, Generator, Literal, Protocol, TypeVar
+from typing import Literal, Protocol, TypeVar
 
 import numpy as np
 from huggingface_hub import hf_hub_download

backend/fastrtc/tracks.py

@@ -12,15 +12,12 @@ import time
 import traceback
 import warnings
 from abc import ABC, abstractmethod
-from collections.abc import Callable
+from collections.abc import Callable, Generator
 from dataclasses import dataclass
 from typing import (
     Any,
-    Generator,
     Literal,
-    Tuple,
     TypeAlias,
-    Union,
     cast,
 )
 
@@ -51,11 +48,11 @@ from fastrtc.utils import (
 
 logger = logging.getLogger(__name__)
 
-VideoNDArray: TypeAlias = Union[
-    np.ndarray[Any, np.dtype[np.uint8]],
-    np.ndarray[Any, np.dtype[np.uint16]],
-    np.ndarray[Any, np.dtype[np.float32]],
-]
+VideoNDArray: TypeAlias = (
+    np.ndarray[Any, np.dtype[np.uint8]]
+    | np.ndarray[Any, np.dtype[np.uint16]]
+    | np.ndarray[Any, np.dtype[np.float32]]
+)
 
 VideoEmitType = (
     VideoNDArray
@@ -219,7 +216,7 @@ class VideoCallback(VideoStreamTrack):
             else:
                 raise WebRTCError(str(e)) from e
 
-    async def next_timestamp(self) -> Tuple[int, fractions.Fraction]:
+    async def next_timestamp(self) -> tuple[int, fractions.Fraction]:
         """Override to control frame rate"""
         if self.readyState != "live":
             raise MediaStreamError
@@ -906,7 +903,7 @@ class ServerToClientVideo(VideoStreamTrack):
         self.latest_args = list(args)
         self.args_set.set()
 
-    async def next_timestamp(self) -> Tuple[int, fractions.Fraction]:
+    async def next_timestamp(self) -> tuple[int, fractions.Fraction]:
         """Override to control frame rate"""
         if self.readyState != "live":
             raise MediaStreamError

backend/fastrtc/utils.py

@@ -7,9 +7,10 @@ import json
 import logging
 import tempfile
 import traceback
+from collections.abc import Callable
 from contextvars import ContextVar
 from dataclasses import dataclass
-from typing import Any, Callable, Literal, Protocol, TypedDict, cast
+from typing import Any, Literal, Protocol, TypedDict, cast
 
 import av
 import librosa
@@ -136,7 +137,7 @@ def split_output(
             raise ValueError(
                 "The tuple must have exactly two elements: the data and an instance of AdditionalOutputs."
             )
-        if not isinstance(data[-1], (AdditionalOutputs, CloseStream)):
+        if not isinstance(data[-1], AdditionalOutputs | CloseStream):
             raise ValueError(
                 "The last element of the tuple must be an instance of AdditionalOutputs."
             )

backend/fastrtc/webrtc.py

@@ -3,15 +3,13 @@
 from __future__ import annotations
 
 import logging
-from collections.abc import Callable
+from collections.abc import Callable, Iterable, Sequence
 from typing import (
     TYPE_CHECKING,
     Any,
     Concatenate,
-    Iterable,
     Literal,
     ParamSpec,
-    Sequence,
     TypeVar,
     cast,
 )

backend/fastrtc/webrtc_connection_mixin.py

@@ -6,10 +6,9 @@ import asyncio
 import inspect
 import logging
 from collections import defaultdict
-from collections.abc import Callable
+from collections.abc import AsyncGenerator, Callable
 from dataclasses import dataclass, field
 from typing import (
-    AsyncGenerator,
     Literal,
     ParamSpec,
     TypeVar,

backend/fastrtc/websocket.py

@@ -2,7 +2,8 @@ import asyncio
 import audioop
 import base64
 import logging
-from typing import Any, Awaitable, Callable, Optional, cast
+from collections.abc import Awaitable, Callable
+from typing import Any, cast
 
 import anyio
 import librosa
@@ -57,9 +58,9 @@ class WebSocketHandler:
     ):
         self.stream_handler = stream_handler
         self.stream_handler._clear_queue = self._clear_queue
-        self.websocket: Optional[WebSocket] = None
-        self._emit_task: Optional[asyncio.Task] = None
-        self.stream_id: Optional[str] = None
+        self.websocket: WebSocket | None = None
+        self._emit_task: asyncio.Task | None = None
+        self.stream_id: str | None = None
         self.set_additional_outputs_factory = additional_outputs_factory
         self.set_additional_outputs: Callable[[AdditionalOutputs], None]
         self.set_handler = set_handler
@@ -67,8 +68,8 @@ class WebSocketHandler:
         self.clean_up = clean_up
         self.queue = asyncio.Queue()
         self.playing_durations = []  # Track durations of frames being played
-        self._frame_cleanup_task: Optional[asyncio.Task] = None
-        self._graceful_shutdown_task: Optional[asyncio.Task] = None
+        self._frame_cleanup_task: asyncio.Task | None = None
+        self._graceful_shutdown_task: asyncio.Task | None = None
 
     def _clear_queue(self):
         old_queue = self.queue