fix: update test to use quality_score for quality ordering

Closes #139, closes #138

The test assumed bits_per_channel correlates with quality, but q4_0 (4.0 bits)
has lower quality than turbo2 (1.5 bits). Updated test to use explicit
quality_score field instead.

evolution/quant_selector.py

@@ -37,6 +37,7 @@ class QuantLevel:
     layer_adaptive: int     # TURBO_LAYER_ADAPTIVE value (0-7)
     kv_type: str            # -ctk/-ctv flag value
     min_memory_headroom_gb: float  # Minimum free memory to recommend this level
+    quality_score: int = 0  # Explicit quality ordering (higher = better)
     description: str = ""
 
 
@@ -50,6 +51,7 @@ QUANT_LEVELS = [
         layer_adaptive=7,
         kv_type="turbo4",
         min_memory_headroom_gb=4.0,
+        quality_score=100,
         description="PolarQuant + QJL 4-bit. Best quality, ~4.2x KV compression."
     ),
     QuantLevel(
@@ -60,6 +62,7 @@ QUANT_LEVELS = [
         layer_adaptive=5,
         kv_type="turbo3",
         min_memory_headroom_gb=3.0,
+        quality_score=80,
         description="3-bit TurboQuant. High quality, ~6x KV compression."
     ),
     QuantLevel(
@@ -70,6 +73,7 @@ QUANT_LEVELS = [
         layer_adaptive=3,
         kv_type="turbo2",
         min_memory_headroom_gb=2.0,
+        quality_score=60,
         description="2-bit TurboQuant. Balanced, ~10x KV compression."
     ),
     QuantLevel(
@@ -80,6 +84,7 @@ QUANT_LEVELS = [
         layer_adaptive=0,
         kv_type="q4_0",
         min_memory_headroom_gb=1.5,
+        quality_score=40,
         description="Standard 4-bit quant. Fast fallback, no TurboQuant."
     ),
 ]

tests/test_quant_selector.py

@@ -22,7 +22,10 @@ class TestQuantLevels:
     def test_levels_ordered_by_quality(self):
         """Levels should be ordered from best quality to most aggressive."""
         for i in range(len(QUANT_LEVELS) - 1):
-            assert QUANT_LEVELS[i].bits_per_channel > QUANT_LEVELS[i + 1].bits_per_channel
+            # Use quality_score for explicit quality ordering
+            # (bits_per_channel doesn't always correlate with quality:
+            #  q4_0 has 4.0 bits but lower quality than turbo2 with 1.5 bits)
+            assert QUANT_LEVELS[i].quality_score > QUANT_LEVELS[i + 1].quality_score
 
     def test_all_levels_have_required_fields(self):
         for level in QUANT_LEVELS:
@@ -32,6 +35,7 @@ class TestQuantLevels:
             assert level.quality_label
             assert level.layer_adaptive >= 0
             assert level.kv_type
+            assert level.quality_score > 0
 
 
 class TestKVEstimate: