Adriano
9c53995f23
- Tier S → google/gemini-3-flash-preview ($0.50/$3.00) - Tier A/B → deepseek/deepseek-v4-flash ($0.14/$0.28) - Tier C → qwen/qwen3-235b-a22b-2507 ($0.071/$0.10) — Phase 2 target - Tier D → openai/gpt-oss-20b ($0.03/$0.14) Aggiornato cost_tracker con prezzi reali per tier. Defaults config.py ora rispecchiano .env corrente per evitare divergenze dead-code. Tier S/A/B/D restano cablati ma non ancora invocati nel loop Phase 2 (solo Hypothesis tier C attivo). Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
64 lines
2.2 KiB
Python
64 lines
2.2 KiB
Python
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 == 0.071 + 0.10
|
|
|
|
|
|
def test_estimate_cost_tier_b():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.B)
|
|
assert cost == 0.14 + 0.28
|
|
|
|
|
|
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"]
|
|
|
|
|
|
def test_estimate_cost_tier_s():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.S)
|
|
assert cost == 0.50 + 3.00
|
|
|
|
|
|
def test_estimate_cost_tier_a():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.A)
|
|
assert cost == 0.14 + 0.28
|
|
|
|
|
|
def test_estimate_cost_tier_d():
|
|
cost = estimate_cost(input_tokens=1_000_000, output_tokens=1_000_000, tier=ModelTier.D)
|
|
assert cost == 0.03 + 0.14
|
|
|
|
|
|
def test_tracker_summary_contains_all_five_tiers():
|
|
t = CostTracker()
|
|
for tier in (ModelTier.S, ModelTier.A, ModelTier.B, ModelTier.C, ModelTier.D):
|
|
t.record(
|
|
input_tokens=1_000,
|
|
output_tokens=1_000,
|
|
tier=tier,
|
|
run_id="r",
|
|
agent_id=f"a-{tier.value}",
|
|
)
|
|
summary = t.summary()
|
|
for tier_letter in ("S", "A", "B", "C", "D"):
|
|
assert tier_letter in summary["by_tier"]
|
|
assert summary["by_tier"][tier_letter]["calls"] == 1
|