feat(llm): cost tracker with per-tier pricing and breakdown

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>

tests/unit/test_cost_tracker.py

@@ -0,0 +1,32 @@
+from multi_swarm.genome.hypothesis import ModelTier
+from multi_swarm.llm.cost_tracker import CostTracker, estimate_cost
+
+
+def test_estimate_cost_tier_c():
+    cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.C)
+    assert cost == 0.40 + 0.40
+
+
+def test_estimate_cost_tier_b():
+    cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.B)
+    assert cost == 3.00 + 15.00
+
+
+def test_tracker_accumulates():
+    t = CostTracker()
+    t.record(input_tokens=10_000, output_tokens=20_000, tier=ModelTier.C, run_id="r", agent_id="a")
+    t.record(input_tokens=5_000, output_tokens=15_000, tier=ModelTier.C, run_id="r", agent_id="b")
+    summary = t.summary()
+    assert summary["calls"] == 2
+    assert summary["input_tokens"] == 15_000
+    assert summary["output_tokens"] == 35_000
+    assert summary["cost_usd"] > 0
+
+
+def test_tracker_per_tier_breakdown():
+    t = CostTracker()
+    t.record(input_tokens=10_000, output_tokens=10_000, tier=ModelTier.C, run_id="r", agent_id="a")
+    t.record(input_tokens=10_000, output_tokens=10_000, tier=ModelTier.B, run_id="r", agent_id="b")
+    summary = t.summary()
+    assert "C" in summary["by_tier"]
+    assert "B" in summary["by_tier"]