fix(offline): patch transformers mistral-regex check to survive HF failures (#530)

* fix(offline): patch transformers mistral-regex check to survive HF failures

transformers 4.57.x's `PreTrainedTokenizerBase._patch_mistral_regex` calls
`huggingface_hub.model_info(repo_id)` unconditionally during any non-local
tokenizer load to probe for Mistral-family models. The call raises on
`HF_HUB_OFFLINE=1`, on network outages, and on slow/blocked HF endpoints,
and transformers doesn't catch any of it — the exception bubbles out of
`from_pretrained` and kills the load for unrelated engines (Qwen TTS,
Qwen CustomVoice, TADA, etc.).

0.4.2's load-time `force_offline_if_cached` guard walked straight into
this trap: on cached online users it flipped `HF_HUB_OFFLINE=1` and
converted a healthy load into a hard crash. 0.4.3's inference-path guard
masked it; #524 removed the inference guard in 0.4.4, and users updating
to 0.4.4 started hitting the same error on the load path instead
(#526).

Fix:
- Wrap `_patch_mistral_regex` so any exception from the inner HF
  metadata check is swallowed and the tokenizer is returned unchanged.
  Voicebox never loads Mistral models, so the regex rewrite this check
  gates is a no-op for us; matches the success-path behavior for
  non-Mistral repos (tokenization_utils_base.py:2503).
- Drop the `force_offline_if_cached` wraps from every load path
  (pytorch_backend Qwen + Whisper, qwen_custom_voice_backend,
  mlx_backend Qwen + Whisper). With the mistral patch in place they
  provide zero value and only risk re-introducing the same class of
  bug. Helper and its unit tests stay — still correct for targeted
  future use.
- Add `backend/tests/test_offline_patch.py` covering
  OfflineModeIsEnabled / ConnectionError suppression, success
  pass-through, idempotence, and the missing-method no-op path.

Fixes #526.

* fix(offline): install mistral-regex patch for non-MLX backends

The previous commit left the patch wired only through ``mlx_backend.py``'s
existing import of ``hf_offline_patch``. On Windows/Linux/CUDA users who
never load the MLX backend (everyone who hit #526), the patch module was
never imported, so ``patch_transformers_mistral_regex`` never ran and the
crash persisted.

Hoist the import into ``backends/__init__.py``. Every backend imports from
this package, so the module-level patch install runs before any
``from_pretrained`` call regardless of which engine the user picks.

Caught by CodeRabbit and Cursor Bugbot on #530.

backend/backends/__init__.py

@@ -5,6 +5,13 @@ Provides a unified interface for MLX and PyTorch backends,
 and a model config registry that eliminates per-engine dispatch maps.
 """
 
+# Install HF compatibility patches before any backend imports transformers /
+# huggingface_hub. The module runs ``patch_transformers_mistral_regex`` at
+# import time, which wraps transformers' tokenizer load against the
+# unconditional HuggingFace metadata call that otherwise raises on
+# HF_HUB_OFFLINE=1 and on network failures.
+from ..utils import hf_offline_patch  # noqa: F401
+
 import threading
 from dataclasses import dataclass, field
 from typing import Protocol, Optional, Tuple, List

backend/backends/mlx_backend.py

@@ -20,7 +20,6 @@ ensure_original_qwen_config_cached()
 from . import TTSBackend, STTBackend, LANGUAGE_CODE_TO_NAME, WHISPER_HF_REPOS
 from .base import is_model_cached, combine_voice_prompts as _combine_voice_prompts, model_load_progress
 from ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_prompt
-from ..utils.hf_offline_patch import force_offline_if_cached
 
 
 class MLXTTSBackend:
@@ -99,8 +98,7 @@ class MLXTTSBackend:
 
             logger.info("Loading MLX TTS model %s...", model_size)
 
-            with force_offline_if_cached(is_cached, model_name):
-                self.model = load(model_path)
+            self.model = load(model_path)
 
         self._current_model_size = model_size
         self.model_size = model_size
@@ -311,8 +309,7 @@ class MLXSTTBackend:
             model_name = WHISPER_HF_REPOS.get(model_size, f"openai/whisper-{model_size}")
             logger.info("Loading MLX Whisper model %s...", model_size)
 
-            with force_offline_if_cached(is_cached, progress_model_name):
-                self.model = load(model_name)
+            self.model = load(model_name)
 
         self.model_size = model_size
         logger.info("MLX Whisper model %s loaded successfully", model_size)

backend/backends/pytorch_backend.py

@@ -21,7 +21,6 @@ from .base import (
 )
 from ..utils.cache import get_cache_key, get_cached_voice_prompt, cache_voice_prompt
 from ..utils.audio import load_audio
-from ..utils.hf_offline_patch import force_offline_if_cached
 
 
 class PyTorchTTSBackend:
@@ -106,21 +105,20 @@ class PyTorchTTSBackend:
             from huggingface_hub import constants as hf_constants
             tts_cache_dir = hf_constants.HF_HUB_CACHE
 
-            with force_offline_if_cached(is_cached, model_name):
-                if self.device == "cpu":
-                    self.model = Qwen3TTSModel.from_pretrained(
-                        model_path,
-                        cache_dir=tts_cache_dir,
-                        torch_dtype=torch.float32,
-                        low_cpu_mem_usage=False,
-                    )
-                else:
-                    self.model = Qwen3TTSModel.from_pretrained(
-                        model_path,
-                        cache_dir=tts_cache_dir,
-                        device_map=self.device,
-                        torch_dtype=torch.bfloat16,
-                    )
+            if self.device == "cpu":
+                self.model = Qwen3TTSModel.from_pretrained(
+                    model_path,
+                    cache_dir=tts_cache_dir,
+                    torch_dtype=torch.float32,
+                    low_cpu_mem_usage=False,
+                )
+            else:
+                self.model = Qwen3TTSModel.from_pretrained(
+                    model_path,
+                    cache_dir=tts_cache_dir,
+                    device_map=self.device,
+                    torch_dtype=torch.bfloat16,
+                )
 
         self._current_model_size = model_size
         self.model_size = model_size
@@ -297,9 +295,8 @@ class PyTorchSTTBackend:
             model_name = WHISPER_HF_REPOS.get(model_size, f"openai/whisper-{model_size}")
             logger.info("Loading Whisper model %s on %s...", model_size, self.device)
 
-            with force_offline_if_cached(is_cached, progress_model_name):
-                self.processor = WhisperProcessor.from_pretrained(model_name)
-                self.model = WhisperForConditionalGeneration.from_pretrained(model_name)
+            self.processor = WhisperProcessor.from_pretrained(model_name)
+            self.model = WhisperForConditionalGeneration.from_pretrained(model_name)
 
         self.model.to(self.device)
         self.model_size = model_size

backend/backends/qwen_custom_voice_backend.py

@@ -28,7 +28,6 @@ from .base import (
     combine_voice_prompts as _combine_voice_prompts,
     model_load_progress,
 )
-from ..utils.hf_offline_patch import force_offline_if_cached
 
 logger = logging.getLogger(__name__)
 
@@ -105,19 +104,18 @@ class QwenCustomVoiceBackend:
             model_path = self._get_model_path(model_size)
             logger.info("Loading Qwen CustomVoice %s on %s...", model_size, self.device)
 
-            with force_offline_if_cached(is_cached, model_name):
-                if self.device == "cpu":
-                    self.model = Qwen3TTSModel.from_pretrained(
-                        model_path,
-                        torch_dtype=torch.float32,
-                        low_cpu_mem_usage=False,
-                    )
-                else:
-                    self.model = Qwen3TTSModel.from_pretrained(
-                        model_path,
-                        device_map=self.device,
-                        torch_dtype=torch.bfloat16,
-                    )
+            if self.device == "cpu":
+                self.model = Qwen3TTSModel.from_pretrained(
+                    model_path,
+                    torch_dtype=torch.float32,
+                    low_cpu_mem_usage=False,
+                )
+            else:
+                self.model = Qwen3TTSModel.from_pretrained(
+                    model_path,
+                    device_map=self.device,
+                    torch_dtype=torch.bfloat16,
+                )
 
         self._current_model_size = model_size
         self.model_size = model_size