Add advisory harness attribution and descriptor planner MVP

tests/test_mechanism_planner.py

@@ -0,0 +1,68 @@
+from __future__ import annotations
+
+import unittest
+
+from aituner.engine_adapters.vllm import default_vllm_descriptors
+from aituner.knob_descriptor import KnobConstraints, KnobDescriptor
+from aituner.mechanism_planner import coordinate_line_search_candidates
+
+
+class MechanismPlannerTests(unittest.TestCase):
+    def test_coordinate_search_uses_mechanism_not_knob_name(self) -> None:
+        vllm_descriptor = default_vllm_descriptors(tunable_flags=("max-num-seqs",))[0]
+        sglang_descriptor = KnobDescriptor(
+            name="max-running-requests",
+            location="flag",
+            value_type="int",
+            mechanisms=("admission_capacity", "kv_memory_pressure"),
+            search_geometry="positive_capacity",
+            operators=("coordinate_line_search",),
+            constraints=KnobConstraints(min_value=1, integer=True, multiple_of=8),
+            directional_effects={
+                "increase": ("admission_capacity",),
+                "decrease": ("kv_memory_pressure",),
+            },
+        )
+
+        vllm_candidates = coordinate_line_search_candidates(
+            current_config={"max-num-seqs": 8},
+            descriptors=(vllm_descriptor,),
+            evidence_weights={"admission_capacity": 0.9},
+        )
+        sglang_candidates = coordinate_line_search_candidates(
+            current_config={"max-running-requests": 8},
+            descriptors=(sglang_descriptor,),
+            evidence_weights={"admission_capacity": 0.9},
+        )
+
+        self.assertEqual(vllm_candidates[0].patch, {"max-num-seqs": 16})
+        self.assertEqual(sglang_candidates[0].patch, {"max-running-requests": 16})
+        self.assertEqual(vllm_candidates[0].mechanism, "admission_capacity")
+        self.assertEqual(sglang_candidates[0].mechanism, "admission_capacity")
+
+    def test_positive_capacity_can_decrease_for_memory_pressure(self) -> None:
+        descriptor = default_vllm_descriptors(tunable_flags=("max-num-seqs",))[0]
+
+        candidates = coordinate_line_search_candidates(
+            current_config={"max-num-seqs": 64},
+            descriptors=(descriptor,),
+            evidence_weights={"kv_memory_pressure": 0.8},
+        )
+
+        self.assertEqual(candidates[0].direction, "decrease")
+        self.assertEqual(candidates[0].patch, {"max-num-seqs": 32})
+
+    def test_bounded_fraction_respects_constraints(self) -> None:
+        descriptor = default_vllm_descriptors(tunable_flags=("gpu-memory-utilization",))[0]
+
+        candidates = coordinate_line_search_candidates(
+            current_config={"gpu-memory-utilization": 0.98},
+            descriptors=(descriptor,),
+            evidence_weights={"kv_memory_capacity": 0.8},
+        )
+
+        self.assertEqual(candidates[0].patch, {"gpu-memory-utilization": 1.0})
+
+
+if __name__ == "__main__":
+    unittest.main()