Merge pull request #64 from dumbovita/master

Cap local model thread count by available CPU threads

dikte/settings_ui.py

@@ -1211,13 +1211,13 @@ class SettingsWindow(QDialog):
               "spends that once instead of on the first dictation, at the cost of "
               "the memory it sits in."))
         self.local_threads = QSpinBox()
-        self.local_threads.setRange(0, 64)
+        max_threads = max(1, os.cpu_count() or 1)
+        self.local_threads.setRange(0, max_threads)
         self.local_threads.setSpecialValueText(t("Automatic"))
-        # A spin box asks for room for its numbers, and 64 is two characters:
+        # A spin box asks for room for its numbers, and the word standing in for
-        # the word standing in for zero is what actually has to fit, and on
+        # zero is what actually has to fit, and on macOS, where the stepper sits
-        # macOS, where the stepper sits inside the frame, it does not. Widened
+        # inside the frame, it does not. Widened to the word rather than to a
-        # to the word rather than to a number picked by eye, so that it still
+        # number picked by eye, so that it still fits once the word is "Otomatik".
-        # fits once the word is "Otomatik".
         self.local_threads.setMinimumWidth(
             self.local_threads.fontMetrics()
             .horizontalAdvance(t("Automatic")) + 56)

tests/test_ui.py

@@ -77,7 +77,7 @@ CHANGED = {
     "local_model": "ggml-small.bin",
     "local_gpu": False,
     "local_preload": False,
-    "local_threads": 6,
+    "local_threads": 1,
     "local_llm_model": "gemma-3-4b-it-Q4_K_M.gguf",
     "local_llm_repo": "ggml-org/gemma-4-E2B-it-GGUF",
     "local_llm_gpu": False,
@@ -1831,3 +1831,15 @@ class LocalModels(DikteTest):
                     # isHidden rather than isVisible: the window itself is never
                     # shown in a test, so nothing in it is ever visible.
                     self.assertEqual(other.isHidden(), name != chosen)
+
+    def test_local_threads_range_is_bounded_by_cpu_count(self):
+        with mock.patch("os.cpu_count", return_value=8):
+            window = self.window(cfg.Config())
+            self.assertEqual(window.local_threads.minimum(), 0)
+            self.assertEqual(window.local_threads.maximum(), 8)
+
+    def test_local_threads_range_has_safe_minimum_when_cpu_count_is_none(self):
+        with mock.patch("os.cpu_count", return_value=None):
+            window = self.window(cfg.Config())
+            self.assertEqual(window.local_threads.minimum(), 0)
+            self.assertEqual(window.local_threads.maximum(), 1)