fix(multimodal): 冻结推理环境并隔离迟到导入错误

backend/tests/test_local_models.py

@@ -47,7 +47,7 @@ def test_local_model_missing_is_explicit():
 def test_cancel_reaps_active_model_process(monkeypatch):
     import app.local_models.runtime as module
     monkeypatch.setattr(module,'read_state',lambda key:{'status':'installed'})
-    monkeypatch.setattr(module,'interpreter',lambda:Path(sys.executable))
+    monkeypatch.setattr(module,'interpreter',lambda *_:Path(sys.executable))
     class Input:
         def write(self, value):
             request = json.loads(value)
@@ -92,7 +92,7 @@ def test_subprocess_fallback_runs_and_reaps_real_worker(monkeypatch, tmp_path, c
     import app.local_models.process as process_module
 
     monkeypatch.setattr(module, 'read_state', lambda key: {'status': 'installed'})
-    monkeypatch.setattr(module, 'interpreter', lambda: Path(sys.executable))
+    monkeypatch.setattr(module, 'interpreter', lambda *_: Path(sys.executable))
     worker = tmp_path / 'worker.py'
     worker.write_text(
         'import json,sys,time\n'

backend/tests/test_multimodal_finalization.py

@@ -21,7 +21,7 @@ def test_cuda_retries_only_device_failures_in_reaped_process(monkeypatch, code,
     from app.services.usage_service import connection
     monkeypatch.setattr(module, 'configuration', lambda: module.RuntimeConfig(device='cuda'))
     monkeypatch.setattr(module, 'read_state', lambda key: {'status': 'installed'})
-    monkeypatch.setattr(module, 'interpreter', lambda: Path(sys.executable))
+    monkeypatch.setattr(module, 'interpreter', lambda *_: Path(sys.executable))
     events = []
 
     class Process:

backend/tests/test_runtime_components.py

@@ -79,7 +79,8 @@ def test_interpreter_keeps_cpu_default_and_respects_explicit_override(monkeypatc
     (components.ROOT / 'ready.json').write_text('{}')
     monkeypatch.setattr(runtime, 'configuration', lambda: runtime.RuntimeConfig(device='cpu'))
     assert runtime.interpreter() != python
-    monkeypatch.setattr(runtime, 'configuration', lambda: runtime.RuntimeConfig(device='cuda'))
-    assert runtime.interpreter() == python
+    # A queued attempt keeps its frozen device even after the saved setting changes.
+    assert runtime.interpreter(runtime.RuntimeConfig(device='cuda')) == python
+    assert runtime.interpreter(runtime.RuntimeConfig(device='cpu')) != python
     monkeypatch.setenv('APP_MODEL_PYTHON', 'explicit-python.exe')
     assert str(runtime.interpreter()) == 'explicit-python.exe'