feat: add queue-aware adaptive scheduling

tests/test_gpu_strategy.py

@@ -49,6 +49,15 @@ class HistoryClient:
         return list(self.tasks)
 
 
+class WeightedMarket:
+    def gpu_weight(self, gpu: str, *, category: str) -> float:
+        del category
+        return {"gpu-a": 3.0, "gpu-b": 0.1, "gpu-c": 0.1, "gpu-d": 0.1}[gpu]
+
+    def gpu_metadata(self, gpu: str) -> dict:
+        return {"marketWeight": self.gpu_weight(gpu, category=ALL_SUPPORTED)}
+
+
 class GPUStrategyTests(unittest.TestCase):
     def test_long_term_ranking_rejects_tiny_high_rate_sample(self) -> None:
         start = datetime(2026, 1, 1, tzinfo=timezone.utc)
@@ -117,6 +126,28 @@ class GPUStrategyTests(unittest.TestCase):
             self.assertEqual(200, manager.state["acceptedTotal"])
             self.assertEqual(0, manager.state["acceptedSinceRefresh"])
 
+    def test_market_weights_change_gpu_mix_without_changing_50_30_20_split(self) -> None:
+        supported = ["gpu-a", "gpu-b", "gpu-c", "gpu-d"]
+        manager = GPUStrategyManager("unused.json", market_intelligence=WeightedMarket())
+        manager.state = build_strategy_snapshot([], supported_gpus=supported)
+        candidates = [
+            {"repoId": f"owner/model-{model}", "targetGpu": gpu}
+            for model in range(300)
+            for gpu in supported
+        ]
+
+        ordered = manager.order_candidates(candidates)[:200]
+        category_counts = Counter(candidate["strategyCategory"] for candidate in ordered)
+        exploration_counts = Counter(
+            candidate["targetGpu"]
+            for candidate in ordered
+            if candidate["strategyCategory"] == ALL_SUPPORTED
+        )
+
+        self.assertEqual({LONG_TERM: 100, ALL_SUPPORTED: 60, RECENT: 40}, category_counts)
+        self.assertGreater(exploration_counts["gpu-a"], exploration_counts["gpu-b"])
+        self.assertTrue(all(exploration_counts[gpu] > 0 for gpu in supported))
+
 
 if __name__ == "__main__":
     unittest.main()