chore(backend): Ruff lint pass — deprecated APIs, exception leaks, dead patterns

Mechanical sweep of items called out in the PR review:

- qwen_llm_backend: AutoModelForCausalLM.from_pretrained(torch_dtype=…) is deprecated in transformers ≥4.41 in favor of dtype=. Renamed.
- routes/llm: try/except around backend.generate() raised HTTPException(500, detail=str(e)) which leaks stack traces / paths to clients and trips Ruff B904. Now logs the original exception server-side and hands the client a generic message; chained via `from e` to preserve traceback context.
- mcp_bindings + mcp_server/context: datetime.utcnow() is deprecated since 3.12. Switched the two assignment sites to datetime.now(timezone.utc). The schema-level `default=datetime.utcnow` defaults in database/models.py are left for a later schema-aware pass.
- routes/generations: `logger = …` sat between two import blocks (Ruff E402). Moved below imports.
- mcp_server/server + tests/test_refinement_samples: typing.Callable / typing.Iterable have been preferred-via collections.abc since 3.9 (Ruff UP035).
- routes/events: `except asyncio.TimeoutError` aliases plain `TimeoutError` since 3.11 (UP041).
- services/captures: hoisted WHISPER_NATIVE_FORMATS to module scope (was a function-local UPPER_SNAKE that tripped N806) and replaced the raw_path.unlink try/except OSError-pass with contextlib.suppress (SIM105). Semantic equivalence preserved — written_files.remove(raw_path) still only runs when unlink succeeds because it sits inside the suppressed block after the unlink call.
- database/migrations: hoisted the duplicate `import sqlite3` from inside two helper bodies to a single module-level import.

backend/backends/qwen_llm_backend.py

@@ -108,7 +108,7 @@ class PyTorchQwenLLMBackend:
                 dtype = torch.float16 if self.device in ("cuda", "mps") else torch.float32
                 self.model = AutoModelForCausalLM.from_pretrained(
                     repo,
-                    torch_dtype=dtype,
+                    dtype=dtype,
                 )
                 self.model.to(self.device)
                 self.model.eval()

backend/database/migrations.py

@@ -18,6 +18,7 @@ Adding a new migration:
 """
 
 import logging
+import sqlite3
 
 from sqlalchemy import inspect, text
 
@@ -266,8 +267,6 @@ def _migrate_mcp_bindings(engine, inspector, tables: set[str]) -> None:
             # Leaving the unused column in place is harmless — the ORM
             # only maps declared columns, so a stray one does no work
             # and gets no reads or writes.
-            import sqlite3
-
             logger.warning(
                 "SQLite %s too old to DROP COLUMN (need 3.35+); leaving unused default_intent column on mcp_client_bindings in place.",
                 sqlite3.sqlite_version,
@@ -280,8 +279,6 @@ def _supports_drop_column(engine) -> bool:
     decades; SQLite only gained the feature in 3.35."""
     if engine.dialect.name != "sqlite":
         return True
-    import sqlite3
-
     return tuple(int(p) for p in sqlite3.sqlite_version.split(".")[:3]) >= (3, 35, 0)
 
 

backend/mcp_server/context.py

@@ -11,7 +11,7 @@ import asyncio
 import ipaddress
 import logging
 from contextvars import ContextVar
-from datetime import datetime
+from datetime import datetime, timezone
 
 from starlette.middleware.base import BaseHTTPMiddleware
 from starlette.requests import Request
@@ -141,7 +141,7 @@ def _stamp_last_seen(client_id: str) -> None:
         if row is None:
             row = MCPClientBinding(client_id=client_id)
             db.add(row)
-        row.last_seen_at = datetime.utcnow()
+        row.last_seen_at = datetime.now(timezone.utc)
         db.commit()
     except Exception:
         logger.debug(

backend/mcp_server/server.py

@@ -10,7 +10,7 @@ from __future__ import annotations
 
 import logging
 from contextlib import AsyncExitStack, asynccontextmanager
-from typing import Callable
+from collections.abc import Callable
 
 from fastapi import FastAPI
 from fastmcp import FastMCP

backend/routes/events.py

@@ -34,7 +34,7 @@ async def speak_events(request: Request):
                     return
                 try:
                     event = await asyncio.wait_for(queue.get(), timeout=15.0)
-                except asyncio.TimeoutError:
+                except TimeoutError:
                     # Heartbeat so proxies don't reap idle streams.
                     yield {"event": "ping", "data": "{}"}
                     continue

backend/routes/generations.py

@@ -8,8 +8,6 @@ from fastapi import APIRouter, Depends, HTTPException
 from fastapi.responses import StreamingResponse
 from sqlalchemy.orm import Session
 
-logger = logging.getLogger(__name__)
-
 from .. import models
 from ..services import history, personality, profiles, tts
 from ..database import Generation as DBGeneration, VoiceProfile as DBVoiceProfile, get_db
@@ -17,6 +15,8 @@ from ..services.generation import run_generation
 from ..services.task_queue import cancel_generation as cancel_generation_job, enqueue_generation
 from ..utils.tasks import get_task_manager
 
+logger = logging.getLogger(__name__)
+
 router = APIRouter()
 
 

backend/routes/llm.py

@@ -1,5 +1,7 @@
 """LLM inference endpoints."""
 
+import logging
+
 from fastapi import APIRouter, HTTPException
 from fastapi.responses import JSONResponse
 
@@ -9,6 +11,8 @@ from ..services import llm
 from ..services.task_queue import create_background_task
 from ..utils.tasks import get_task_manager
 
+logger = logging.getLogger(__name__)
+
 router = APIRouter()
 
 
@@ -70,4 +74,7 @@ async def llm_generate(request: models.LLMGenerateRequest):
         )
         return models.LLMGenerateResponse(text=text, model_size=model_size)
     except Exception as e:
-        raise HTTPException(status_code=500, detail=str(e))
+        # The backend exception text can include filesystem paths and stack
+        # frames — log it server-side and hand the client a generic message.
+        logger.exception("LLM generate failed")
+        raise HTTPException(status_code=500, detail="LLM generation failed") from e

backend/routes/mcp_bindings.py

@@ -6,7 +6,7 @@ column is the same value the MCP client sends in ``X-Voicebox-Client-Id``
 (or the stdio shim pulls from ``VOICEBOX_CLIENT_ID``).
 """
 
-from datetime import datetime
+from datetime import datetime, timezone
 
 from fastapi import APIRouter, Depends, HTTPException
 from sqlalchemy.orm import Session
@@ -56,7 +56,7 @@ async def upsert_mcp_binding(
     row.profile_id = data.profile_id
     row.default_engine = data.default_engine
     row.default_personality = data.default_personality
-    row.updated_at = datetime.utcnow()
+    row.updated_at = datetime.now(timezone.utc)
     db.commit()
     db.refresh(row)
     return models.MCPClientBindingResponse.model_validate(row)

backend/services/captures.py

@@ -7,6 +7,7 @@ uploaded file). Storage mirrors the generations flow: audio lives under
 ``data/captures/<id>.wav`` and rows live in the ``captures`` table.
 """
 
+import contextlib
 import json
 import logging
 import uuid
@@ -27,6 +28,10 @@ logger = logging.getLogger(__name__)
 
 
 VALID_SOURCES = {"dictation", "recording", "file"}
+# Suffixes whisper's miniaudio loader can read directly. Anything outside
+# this set has to go through librosa for decode + a soundfile transcode
+# before whisper sees it.
+WHISPER_NATIVE_FORMATS = (".wav", ".mp3", ".flac", ".ogg")
 
 
 def _to_response(row: DBCapture) -> CaptureResponse:
@@ -91,13 +96,11 @@ async def create_capture(
             audio, sr = None, None
             duration_ms = None
 
-        _WHISPER_NATIVE_FORMATS = (".wav", ".mp3", ".flac", ".ogg")
-
         if audio is None or sr is None:
             # Decode failed. Only pass the file straight to whisper if the
             # source is a format its miniaudio loader can still read — webm,
             # m4a, etc. would just 500 later. Surface a clean error instead.
-            if suffix not in _WHISPER_NATIVE_FORMATS:
+            if suffix not in WHISPER_NATIVE_FORMATS:
                 raise ValueError(
                     f"Could not decode {suffix} audio — the recording may be empty or corrupt"
                 )
@@ -110,11 +113,8 @@ async def create_capture(
             audio_path = config.get_captures_dir() / f"{capture_id}.wav"
             sf.write(str(audio_path), audio, sr, format="WAV")
             written_files.append(audio_path)
-            try:
+            with contextlib.suppress(OSError):
                 raw_path.unlink()
-            except OSError:
-                pass
-            else:
                 written_files.remove(raw_path)
 
         whisper = get_whisper_model()

backend/tests/test_refinement_samples.py

@@ -34,7 +34,8 @@ import sys
 import time
 from dataclasses import asdict, dataclass, field
 from pathlib import Path
-from typing import Iterable, Optional
+from collections.abc import Iterable
+from typing import Optional
 
 import httpx