experiment: add workload regime taxonomy

tests/test_materialize_workload_regimes.py

@@ -0,0 +1,84 @@
+import importlib.util
+import sys
+from pathlib import Path
+
+
+SCRIPT = (
+    Path(__file__).resolve().parents[1]
+    / "runs/frontier-workload-regime-taxonomy-v0/materialize_workload_regimes.py"
+)
+SPEC = importlib.util.spec_from_file_location("workload_regimes", SCRIPT)
+MODULE = importlib.util.module_from_spec(SPEC)
+assert SPEC.loader is not None
+sys.modules[SPEC.name] = MODULE
+SPEC.loader.exec_module(MODULE)
+
+
+def source_rows():
+    return [
+        {
+            "source_index": index,
+            "source_arrived_at": arrival,
+            "input_length": input_length,
+            "output_length": output_length,
+            "session_id": 100 + index,
+            "runtime_block_ids": list(range(input_length // 16)),
+            "body": {"prompt": f"prompt-{index}", "model": "fixture"},
+        }
+        for index, (arrival, input_length, output_length) in enumerate(
+            [(10.0, 16, 4), (10.5, 32, 8), (14.0, 48, 12)]
+        )
+    ]
+
+
+def test_arrival_contracts_preserve_rate_and_burst_pattern():
+    rows = source_rows()
+    uniform = MODULE.arrivals_for(rows, "uniform", 2.0)
+    traced = MODULE.arrivals_for(rows, "trace", 2.0)
+
+    assert uniform == [0.0, 0.5, 1.0]
+    assert (len(traced) - 1) / (traced[-1] - traced[0]) == 2.0
+    assert traced[1] - traced[0] < traced[2] - traced[1]
+
+
+def test_family_axes_change_only_the_declared_contract():
+    rows = source_rows()
+    token_ids = [10, 11, 12, 13]
+    families = {family.name: family for family in MODULE.FAMILIES}
+
+    w1 = MODULE.build_family_rows(
+        rows,
+        families["w1-mean-fixed-uniform-none"],
+        target_rate=1.0,
+        fixed_token_ids=token_ids,
+    )
+    w3 = MODULE.build_family_rows(
+        rows,
+        families["w3-heterogeneous-uniform-none"],
+        target_rate=1.0,
+        fixed_token_ids=token_ids,
+    )
+    w5 = MODULE.build_family_rows(
+        rows,
+        families["w5-heterogeneous-uniform-prefix"],
+        target_rate=1.0,
+        fixed_token_ids=token_ids,
+    )
+
+    assert {(row["input_length"], row["output_length"]) for row in w1} == {(32, 8)}
+    assert [(row["input_length"], row["output_length"]) for row in w3] == [
+        (16, 4),
+        (32, 8),
+        (48, 12),
+    ]
+    assert all(row["runtime_block_ids"] == [] for row in w1 + w3)
+    assert [row["runtime_block_ids"] for row in w5] == [
+        [0],
+        [0, 1],
+        [0, 1, 2],
+    ]
+    assert [row["body"]["prompt"] for row in w3] == [
+        "prompt-0",
+        "prompt-1",
+        "prompt-2",
+    ]